diff options
1299 files changed, 38886 insertions, 15388 deletions
@@ -108,6 +108,10 @@ Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> <javier@osg.samsung.com> <javier.martinez@collabora.co.uk> +Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com> +Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com> +Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com> +Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com> Jean Tourrilhes <jt@hpl.hp.com> <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com> Jeff Garzik <jgarzik@pretzel.yyz.us> diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats index 2c44b4f1b060..70dcaf2481f4 100644 --- a/Documentation/ABI/testing/procfs-diskstats +++ b/Documentation/ABI/testing/procfs-diskstats @@ -29,4 +29,9 @@ Description: 17 - sectors discarded 18 - time spent discarding + Kernel 5.5+ appends two more fields for flush requests: + + 19 - flush requests completed successfully + 20 - time spent flushing + For more details refer to Documentation/admin-guide/iostats.rst diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index f8c7c7126bb1..ed8c14f161ee 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -15,6 +15,12 @@ Description: 9 - I/Os currently in progress 10 - time spent doing I/Os (ms) 11 - weighted time spent doing I/Os (ms) + 12 - discards completed + 13 - discards merged + 14 - sectors discarded + 15 - time spent discarding (ms) + 16 - flush requests completed + 17 - time spent flushing (ms) For more details refer Documentation/admin-guide/iostats.rst diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 06d0931119cc..fc20cde63d1e 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -486,6 +486,8 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds + /sys/devices/system/cpu/vulnerabilities/tsx_async_abort + /sys/devices/system/cpu/vulnerabilities/itlb_multihit Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst index a30aa91b5fbe..594095b54b29 100644 --- a/Documentation/admin-guide/device-mapper/dm-integrity.rst +++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst @@ -177,6 +177,11 @@ bitmap_flush_interval:number The bitmap flush interval in milliseconds. The metadata buffers are synchronized when this interval expires. +fix_padding + Use a smaller padding of the tag area that is more + 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 diff --git a/Documentation/admin-guide/device-mapper/dm-raid.rst b/Documentation/admin-guide/device-mapper/dm-raid.rst index 2fe255b130fb..f6344675e395 100644 --- a/Documentation/admin-guide/device-mapper/dm-raid.rst +++ b/Documentation/admin-guide/device-mapper/dm-raid.rst @@ -417,3 +417,5 @@ Version History deadlock/potential data corruption. Update superblock when specific devices are requested via rebuild. Fix RAID leg rebuild errors. + 1.15.0 Fix size extensions not being synchronized in case of new MD bitmap + pages allocated; also fix those not occuring after previous reductions diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 49311f3da6f2..0795e3c2643f 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -12,3 +12,5 @@ are configurable at compile, boot or run time. spectre l1tf mds + tsx_async_abort + multihit.rst diff --git a/Documentation/admin-guide/hw-vuln/multihit.rst b/Documentation/admin-guide/hw-vuln/multihit.rst new file mode 100644 index 000000000000..ba9988d8bce5 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/multihit.rst @@ -0,0 +1,163 @@ +iTLB multihit +============= + +iTLB multihit is an erratum where some processors may incur a machine check +error, possibly resulting in an unrecoverable CPU lockup, when an +instruction fetch hits multiple entries in the instruction TLB. This can +occur when the page size is changed along with either the physical address +or cache type. A malicious guest running on a virtualized system can +exploit this erratum to perform a denial of service attack. + + +Affected processors +------------------- + +Variations of this erratum are present on most Intel Core and Xeon processor +models. The erratum is not present on: + + - non-Intel processors + + - Some Atoms (Airmont, Bonnell, Goldmont, GoldmontPlus, Saltwell, Silvermont) + + - Intel processors that have the PSCHANGE_MC_NO bit set in the + IA32_ARCH_CAPABILITIES MSR. + + +Related CVEs +------------ + +The following CVE entry is related to this issue: + + ============== ================================================= + CVE-2018-12207 Machine Check Error Avoidance on Page Size Change + ============== ================================================= + + +Problem +------- + +Privileged software, including OS and virtual machine managers (VMM), are in +charge of memory management. A key component in memory management is the control +of the page tables. Modern processors use virtual memory, a technique that creates +the illusion of a very large memory for processors. This virtual space is split +into pages of a given size. Page tables translate virtual addresses to physical +addresses. + +To reduce latency when performing a virtual to physical address translation, +processors include a structure, called TLB, that caches recent translations. +There are separate TLBs for instruction (iTLB) and data (dTLB). + +Under this errata, instructions are fetched from a linear address translated +using a 4 KB translation cached in the iTLB. Privileged software modifies the +paging structure so that the same linear address using large page size (2 MB, 4 +MB, 1 GB) with a different physical address or memory type. After the page +structure modification but before the software invalidates any iTLB entries for +the linear address, a code fetch that happens on the same linear address may +cause a machine-check error which can result in a system hang or shutdown. + + +Attack scenarios +---------------- + +Attacks against the iTLB multihit erratum can be mounted from malicious +guests in a virtualized system. + + +iTLB multihit system information +-------------------------------- + +The Linux kernel provides a sysfs interface to enumerate the current iTLB +multihit status of the system:whether the system is vulnerable and which +mitigations are active. The relevant sysfs file is: + +/sys/devices/system/cpu/vulnerabilities/itlb_multihit + +The possible values in this file are: + +.. list-table:: + + * - Not affected + - The processor is not vulnerable. + * - KVM: Mitigation: Split huge pages + - Software changes mitigate this issue. + * - KVM: Vulnerable + - The processor is vulnerable, but no mitigation enabled + + +Enumeration of the erratum +-------------------------------- + +A new bit has been allocated in the IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) msr +and will be set on CPU's which are mitigated against this issue. + + ======================================= =========== =============================== + IA32_ARCH_CAPABILITIES MSR Not present Possibly vulnerable,check model + IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '0' Likely vulnerable,check model + IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '1' Not vulnerable + ======================================= =========== =============================== + + +Mitigation mechanism +------------------------- + +This erratum can be mitigated by restricting the use of large page sizes to +non-executable pages. This forces all iTLB entries to be 4K, and removes +the possibility of multiple hits. + +In order to mitigate the vulnerability, KVM initially marks all huge pages +as non-executable. If the guest attempts to execute in one of those pages, +the page is broken down into 4K pages, which are then marked executable. + +If EPT is disabled or not available on the host, KVM is in control of TLB +flushes and the problematic situation cannot happen. However, the shadow +EPT paging mechanism used by nested virtualization is vulnerable, because +the nested guest can trigger multiple iTLB hits by modifying its own +(non-nested) page tables. For simplicity, KVM will make large pages +non-executable in all shadow paging modes. + +Mitigation control on the kernel command line and KVM - module parameter +------------------------------------------------------------------------ + +The KVM hypervisor mitigation mechanism for marking huge pages as +non-executable can be controlled with a module parameter "nx_huge_pages=". +The kernel command line allows to control the iTLB multihit mitigations at +boot time with the option "kvm.nx_huge_pages=". + +The valid arguments for these options are: + + ========== ================================================================ + force Mitigation is enabled. In this case, the mitigation implements + non-executable huge pages in Linux kernel KVM module. All huge + pages in the EPT are marked as non-executable. + If a guest attempts to execute in one of those pages, the page is + broken down into 4K pages, which are then marked executable. + + off Mitigation is disabled. + + auto Enable mitigation only if the platform is affected and the kernel + was not booted with the "mitigations=off" command line parameter. + This is the default option. + ========== ================================================================ + + +Mitigation selection guide +-------------------------- + +1. No virtualization in use +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + The system is protected by the kernel unconditionally and no further + action is required. + +2. Virtualization with trusted guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + If the guest comes from a trusted source, you may assume that the guest will + not attempt to maliciously exploit these errata and no further action is + required. + +3. Virtualization with untrusted guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + If the guest comes from an untrusted source, the guest host kernel will need + to apply iTLB multihit mitigation via the kernel command line or kvm + module parameter. diff --git a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst new file mode 100644 index 000000000000..fddbd7579c53 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst @@ -0,0 +1,276 @@ +.. SPDX-License-Identifier: GPL-2.0 + +TAA - TSX Asynchronous Abort +====================================== + +TAA is a hardware vulnerability that allows unprivileged speculative access to +data which is available in various CPU internal buffers by using asynchronous +aborts within an Intel TSX transactional region. + +Affected processors +------------------- + +This vulnerability only affects Intel processors that support Intel +Transactional Synchronization Extensions (TSX) when the TAA_NO bit (bit 8) +is 0 in the IA32_ARCH_CAPABILITIES MSR. On processors where the MDS_NO bit +(bit 5) is 0 in the IA32_ARCH_CAPABILITIES MSR, the existing MDS mitigations +also mitigate against TAA. + +Whether a processor is affected or not can be read out from the TAA +vulnerability file in sysfs. See :ref:`tsx_async_abort_sys_info`. + +Related CVEs +------------ + +The following CVE entry is related to this TAA issue: + + ============== ===== =================================================== + CVE-2019-11135 TAA TSX Asynchronous Abort (TAA) condition on some + microprocessors utilizing speculative execution may + allow an authenticated user to potentially enable + information disclosure via a side channel with + local access. + ============== ===== =================================================== + +Problem +------- + +When performing store, load or L1 refill operations, processors write +data into temporary microarchitectural structures (buffers). The data in +those buffers can be forwarded to load operations as an optimization. + +Intel TSX is an extension to the x86 instruction set architecture that adds +hardware transactional memory support to improve performance of multi-threaded +software. TSX lets the processor expose and exploit concurrency hidden in an +application due to dynamically avoiding unnecessary synchronization. + +TSX supports atomic memory transactions that are either committed (success) or +aborted. During an abort, operations that happened within the transactional region +are rolled back. An asynchronous abort takes place, among other options, when a +different thread accesses a cache line that is also used within the transactional +region when that access might lead to a data race. + +Immediately after an uncompleted asynchronous abort, certain speculatively +executed loads may read data from those internal buffers and pass it to dependent +operations. This can be then used to infer the value via a cache side channel +attack. + +Because the buffers are potentially shared between Hyper-Threads cross +Hyper-Thread attacks are possible. + +The victim of a malicious actor does not need to make use of TSX. Only the +attacker needs to begin a TSX transaction and raise an asynchronous abort +which in turn potenitally leaks data stored in the buffers. + +More detailed technical information is available in the TAA specific x86 +architecture section: :ref:`Documentation/x86/tsx_async_abort.rst <tsx_async_abort>`. + + +Attack scenarios +---------------- + +Attacks against the TAA vulnerability can be implemented from unprivileged +applications running on hosts or guests. + +As for MDS, the attacker has no control over the memory addresses that can +be leaked. Only the victim is responsible for bringing data to the CPU. As +a result, the malicious actor has to sample as much data as possible and +then postprocess it to try to infer any useful information from it. + +A potential attacker only has read access to the data. Also, there is no direct +privilege escalation by using this technique. + + +.. _tsx_async_abort_sys_info: + +TAA system information +----------------------- + +The Linux kernel provides a sysfs interface to enumerate the current TAA status +of mitigated systems. The relevant sysfs file is: + +/sys/devices/system/cpu/vulnerabilities/tsx_async_abort + +The possible values in this file are: + +.. list-table:: + + * - 'Vulnerable' + - The CPU is affected by this vulnerability and the microcode and kernel mitigation are not applied. + * - 'Vulnerable: Clear CPU buffers attempted, no microcode' + - The system tries to clear the buffers but the microcode might not support the operation. + * - 'Mitigation: Clear CPU buffers' + - The microcode has been updated to clear the buffers. TSX is still enabled. + * - 'Mitigation: TSX disabled' + - TSX is disabled. + * - 'Not affected' + - The CPU is not affected by this issue. + +.. _ucode_needed: + +Best effort mitigation mode +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If the processor is vulnerable, but the availability of the microcode-based +mitigation mechanism is not advertised via CPUID the kernel selects a best +effort mitigation mode. This mode invokes the mitigation instructions +without a guarantee that they clear the CPU buffers. + +This is done to address virtualization scenarios where the host has the +microcode update applied, but the hypervisor is not yet updated to expose the +CPUID to the guest. If the host has updated microcode the protection takes +effect; otherwise a few CPU cycles are wasted pointlessly. + +The state in the tsx_async_abort sysfs file reflects this situation +accordingly. + + +Mitigation mechanism +-------------------- + +The kernel detects the affected CPUs and the presence of the microcode which is +required. If a CPU is affected and the microcode is available, then the kernel +enables the mitigation by default. + + +The mitigation can be controlled at boot time via a kernel command line option. +See :ref:`taa_mitigation_control_command_line`. + +.. _virt_mechanism: + +Virtualization mitigation +^^^^^^^^^^^^^^^^^^^^^^^^^ + +Affected systems where the host has TAA microcode and TAA is mitigated by +having disabled TSX previously, are not vulnerable regardless of the status +of the VMs. + +In all other cases, if the host either does not have the TAA microcode or +the kernel is not mitigated, the system might be vulnerable. + + +.. _taa_mitigation_control_command_line: + +Mitigation control on the kernel command line +--------------------------------------------- + +The kernel command line allows to control the TAA mitigations at boot time with +the option "tsx_async_abort=". The valid arguments for this option are: + + ============ ============================================================= + off This option disables the TAA mitigation on affected platforms. + If the system has TSX enabled (see next parameter) and the CPU + is affected, the system is vulnerable. + + full TAA mitigation is enabled. If TSX is enabled, on an affected + system it will clear CPU buffers on ring transitions. On + systems which are MDS-affected and deploy MDS mitigation, + TAA is also mitigated. Specifying this option on those + systems will have no effect. + + full,nosmt The same as tsx_async_abort=full, with SMT disabled on + vulnerable CPUs that have TSX enabled. This is the complete + mitigation. When TSX is disabled, SMT is not disabled because + CPU is not vulnerable to cross-thread TAA attacks. + ============ ============================================================= + +Not specifying this option is equivalent to "tsx_async_abort=full". + +The kernel command line also allows to control the TSX feature using the +parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used +to control the TSX feature and the enumeration of the TSX feature bits (RTM +and HLE) in CPUID. + +The valid options are: + + ============ ============================================================= + off Disables TSX on the system. + + Note that this option takes effect only on newer CPUs which are + not vulnerable to MDS, i.e., have MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 + and which get the new IA32_TSX_CTRL MSR through a microcode + update. This new MSR allows for the reliable deactivation of + the TSX functionality. + + on Enables TSX. + + Although there are mitigations for all known security + vulnerabilities, TSX has been known to be an accelerator for + several previous speculation-related CVEs, and so there may be + unknown security risks associated with leaving it enabled. + + auto Disables TSX if X86_BUG_TAA is present, otherwise enables TSX + on the system. + ============ ============================================================= + +Not specifying this option is equivalent to "tsx=off". + +The following combinations of the "tsx_async_abort" and "tsx" are possible. For +affected platforms tsx=auto is equivalent to tsx=off and the result will be: + + ========= ========================== ========================================= + tsx=on tsx_async_abort=full The system will use VERW to clear CPU + buffers. Cross-thread attacks are still + possible on SMT machines. + tsx=on tsx_async_abort=full,nosmt As above, cross-thread attacks on SMT + mitigated. + tsx=on tsx_async_abort=off The system is vulnerable. + tsx=off tsx_async_abort=full TSX might be disabled if microcode + provides a TSX control MSR. If so, + system is not vulnerable. + tsx=off tsx_async_abort=full,nosmt Ditto + tsx=off tsx_async_abort=off ditto + ========= ========================== ========================================= + + +For unaffected platforms "tsx=on" and "tsx_async_abort=full" does not clear CPU +buffers. For platforms without TSX control (MSR_IA32_ARCH_CAPABILITIES.MDS_NO=0) +"tsx" command line argument has no effect. + +For the affected platforms below table indicates the mitigation status for the +combinations of CPUID bit MD_CLEAR and IA32_ARCH_CAPABILITIES MSR bits MDS_NO +and TSX_CTRL_MSR. + + ======= ========= ============= ======================================== + MDS_NO MD_CLEAR TSX_CTRL_MSR Status + ======= ========= ============= ======================================== + 0 0 0 Vulnerable (needs microcode) + 0 1 0 MDS and TAA mitigated via VERW + 1 1 0 MDS fixed, TAA vulnerable if TSX enabled + because MD_CLEAR has no meaning and + VERW is not guaranteed to clear buffers + 1 X 1 MDS fixed, TAA can be mitigated by + VERW or TSX_CTRL_MSR + ======= ========= ============= ======================================== + +Mitigation selection guide +-------------------------- + +1. Trusted userspace and guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If all user space applications are from a trusted source and do not execute +untrusted code which is supplied externally, then the mitigation can be +disabled. The same applies to virtualized environments with trusted guests. + + +2. Untrusted userspace and guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If there are untrusted applications or guests on the system, enabling TSX +might allow a malicious actor to leak data from the host or from other +processes running on the same physical core. + +If the microcode is available and the TSX is disabled on the host, attacks +are prevented in a virtualized environment as well, even if the VMs do not +explicitly enable the mitigation. + + +.. _taa_default_mitigations: + +Default mitigations +------------------- + +The kernel's default action for vulnerable processors is: + + - Deploy TSX disable mitigation (tsx_async_abort=full tsx=off). diff --git a/Documentation/admin-guide/iostats.rst b/Documentation/admin-guide/iostats.rst index 5d63b18bd6d1..4f0462af3ca7 100644 --- a/Documentation/admin-guide/iostats.rst +++ b/Documentation/admin-guide/iostats.rst @@ -121,6 +121,15 @@ Field 15 -- # of milliseconds spent discarding This is the total number of milliseconds spent by all discards (as measured from __make_request() to end_that_request_last()). +Field 16 -- # of flush requests completed + This is the total number of flush requests completed successfully. + + Block layer combines flush requests and executes at most one at a time. + This counts flush requests executed by disk. Not tracked for partitions. + +Field 17 -- # of milliseconds spent flushing + This is the total number of milliseconds spent by all flush requests. + To avoid introducing performance bottlenecks, no locks are held while modifying these counters. This implies that minor inaccuracies may be introduced when changes collide, so (for instance) adding up all the diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a84a83f8881e..8dee8f68fe15 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2055,6 +2055,25 @@ KVM MMU at runtime. Default is 0 (off) + kvm.nx_huge_pages= + [KVM] Controls the software workaround for the + X86_BUG_ITLB_MULTIHIT bug. + force : Always deploy workaround. + off : Never deploy workaround. + auto : Deploy workaround based on the presence of + X86_BUG_ITLB_MULTIHIT. + + Default is 'auto'. + + If the software workaround is enabled for the host, + guests do need not to enable it for nested guests. + + kvm.nx_huge_pages_recovery_ratio= + [KVM] Controls how many 4KiB pages are periodically zapped + back to huge pages. 0 disables the recovery, otherwise if + the value is N KVM will zap 1/Nth of the 4KiB pages every + minute. The default is 60. + kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM. Default is 1 (enabled) @@ -2636,6 +2655,13 @@ ssbd=force-off [ARM64] l1tf=off [X86] mds=off [X86] + tsx_async_abort=off [X86] + kvm.nx_huge_pages=off [X86] + + Exceptions: + This does not have any effect on + kvm.nx_huge_pages when + kvm.nx_huge_pages=force. auto (default) Mitigate all CPU vulnerabilities, but leave SMT @@ -2651,6 +2677,7 @@ be fully mitigated, even if it means losing SMT. Equivalent to: l1tf=flush,nosmt [X86] mds=full,nosmt [X86] + tsx_async_abort=full,nosmt [X86] mminit_loglevel= [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this @@ -4848,6 +4875,71 @@ interruptions from clocksource watchdog are not acceptable). + tsx= [X86] Control Transactional Synchronization + Extensions (TSX) feature in Intel processors that + support TSX control. + + This parameter controls the TSX feature. The options are: + + on - Enable TSX on the system. Although there are + mitigations for all known security vulnerabilities, + TSX has been known to be an accelerator for + several previous speculation-related CVEs, and + so there may be unknown security risks associated + with leaving it enabled. + + off - Disable TSX on the system. (Note that this + option takes effect only on newer CPUs which are + not vulnerable to MDS, i.e., have + MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get + the new IA32_TSX_CTRL MSR through a microcode + update. This new MSR allows for the reliable + deactivation of the TSX functionality.) + + auto - Disable TSX if X86_BUG_TAA is present, + otherwise enable TSX on the system. + + Not specifying this option is equivalent to tsx=off. + + See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst + for more details. + + tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async + Abort (TAA) vulnerability. + + Similar to Micro-architectural Data Sampling (MDS) + certain CPUs that support Transactional + Synchronization Extensions (TSX) are vulnerable to an + exploit against CPU internal buffers which can forward + information to a disclosure gadget under certain + conditions. + + In vulnerable processors, the speculatively forwarded + data can be used in a cache side channel attack, to + access data to which the attacker does not have direct + access. + + This parameter controls the TAA mitigation. The + options are: + + full - Enable TAA mitigation on vulnerable CPUs + if TSX is enabled. + + full,nosmt - Enable TAA mitigation and disable SMT on + vulnerable CPUs. If TSX is disabled, SMT + is not disabled because CPU is not + vulnerable to cross-thread TAA attacks. + off - Unconditionally disable TAA mitigation + + Not specifying this option is equivalent to + tsx_async_abort=full. On CPUs which are MDS affected + and deploy MDS mitigation, TAA mitigation is not + required and doesn't provide any additional + mitigation. + + For details see: + Documentation/admin-guide/hw-vuln/tsx_async_abort.rst + turbografx.map[2|3]= [HW,JOY] TurboGraFX parallel port interface Format: diff --git a/Documentation/admin-guide/perf/imx-ddr.rst b/Documentation/admin-guide/perf/imx-ddr.rst index 517a205abad6..90056e4e8859 100644 --- a/Documentation/admin-guide/perf/imx-ddr.rst +++ b/Documentation/admin-guide/perf/imx-ddr.rst @@ -17,7 +17,8 @@ The "format" directory describes format of the config (event ID) and config1 (AXI filtering) fields of the perf_event_attr structure, see /sys/bus/event_source/ devices/imx8_ddr0/format/. The "events" directory describes the events types hardware supported that can be used with perf tool, see /sys/bus/event_source/ -devices/imx8_ddr0/events/. +devices/imx8_ddr0/events/. The "caps" directory describes filter features implemented +in DDR PMU, see /sys/bus/events_source/devices/imx8_ddr0/caps/. e.g.:: perf stat -a -e imx8_ddr0/cycles/ cmd perf stat -a -e imx8_ddr0/read/,imx8_ddr0/write/ cmd @@ -25,9 +26,12 @@ devices/imx8_ddr0/events/. AXI filtering is only used by CSV modes 0x41 (axid-read) and 0x42 (axid-write) to count reading or writing matches filter setting. Filter setting is various from different DRAM controller implementations, which is distinguished by quirks -in the driver. +in the driver. You also can dump info from userspace, filter in "caps" directory +indicates whether PMU supports AXI ID filter or not; enhanced_filter indicates +whether PMU supports enhanced AXI ID filter or not. Value 0 for un-supported, and +value 1 for supported. -* With DDR_CAP_AXI_ID_FILTER quirk. +* With DDR_CAP_AXI_ID_FILTER quirk(filter: 1, enhanced_filter: 0). Filter is defined with two configuration parts: --AXI_ID defines AxID matching value. --AXI_MASKING defines which bits of AxID are meaningful for the matching. @@ -50,3 +54,8 @@ in the driver. axi_id to monitor a specific id, rather than having to specify axi_mask. e.g.:: perf stat -a -e imx8_ddr0/axid-read,axi_id=0x12/ cmd, which will monitor ARID=0x12 + +* With DDR_CAP_AXI_ID_FILTER_ENHANCED quirk(filter: 1, enhanced_filter: 1). + This is an extension to the DDR_CAP_AXI_ID_FILTER quirk which permits + counting the number of bytes (as opposed to the number of bursts) from DDR + read and write transactions concurrently with another set of data counters. diff --git a/Documentation/admin-guide/perf/thunderx2-pmu.rst b/Documentation/admin-guide/perf/thunderx2-pmu.rst index 08e33675853a..01f158238ae1 100644 --- a/Documentation/admin-guide/perf/thunderx2-pmu.rst +++ b/Documentation/admin-guide/perf/thunderx2-pmu.rst @@ -3,24 +3,26 @@ Cavium ThunderX2 SoC Performance Monitoring Unit (PMU UNCORE) ============================================================= The ThunderX2 SoC PMU consists of independent, system-wide, per-socket -PMUs such as the Level 3 Cache (L3C) and DDR4 Memory Controller (DMC). +PMUs such as the Level 3 Cache (L3C), DDR4 Memory Controller (DMC) and +Cavium Coherent Processor Interconnect (CCPI2). The DMC has 8 interleaved channels and the L3C has 16 interleaved tiles. Events are counted for the default channel (i.e. channel 0) and prorated to the total number of channels/tiles. -The DMC and L3C support up to 4 counters. Counters are independently -programmable and can be started and stopped individually. Each counter -can be set to a different event. Counters are 32-bit and do not support -an overflow interrupt; they are read every 2 seconds. +The DMC and L3C support up to 4 counters, while the CCPI2 supports up to 8 +counters. Counters are independently programmable to different events and +can be started and stopped individually. None of the counters support an +overflow interrupt. DMC and L3C counters are 32-bit and read every 2 seconds. +The CCPI2 counters are 64-bit and assumed not to overflow in normal operation. PMU UNCORE (perf) driver: The thunderx2_pmu driver registers per-socket perf PMUs for the DMC and -L3C devices. Each PMU can be used to count up to 4 events -simultaneously. The PMUs provide a description of their available events -and configuration options under sysfs, see -/sys/devices/uncore_<l3c_S/dmc_S/>; S is the socket id. +L3C devices. Each PMU can be used to count up to 4 (DMC/L3C) or up to 8 +(CCPI2) events simultaneously. The PMUs provide a description of their +available events and configuration options under sysfs, see +/sys/devices/uncore_<l3c_S/dmc_S/ccpi2_S/>; S is the socket id. The driver does not support sampling, therefore "perf record" will not work. Per-task perf sessions are also not supported. diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst index d3f3a60fbf25..5d78a6f5b0ae 100644 --- a/Documentation/arm64/booting.rst +++ b/Documentation/arm64/booting.rst @@ -213,6 +213,9 @@ Before jumping into the kernel, the following conditions must be met: - ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1. - ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b1. + - ICC_CTLR_EL3.PMHE (bit 6) must be set to the same value across + all CPUs the kernel is executing on, and must stay constant + for the lifetime of the kernel. - If the kernel is entered at EL1: diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 2955287e9acc..b6e44884e3ad 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -168,8 +168,15 @@ infrastructure: +------------------------------+---------+---------+ - 3) MIDR_EL1 - Main ID Register + 3) ID_AA64PFR1_EL1 - Processor Feature Register 1 + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | SSBS | [7-4] | y | + +------------------------------+---------+---------+ + + 4) MIDR_EL1 - Main ID Register +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ @@ -188,11 +195,15 @@ infrastructure: as available on the CPU where it is fetched and is not a system wide safe value. - 4) ID_AA64ISAR1_EL1 - Instruction set attribute register 1 + 5) ID_AA64ISAR1_EL1 - Instruction set attribute register 1 +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | SB | [39-36] | y | + +------------------------------+---------+---------+ + | FRINTTS | [35-32] | y | + +------------------------------+---------+---------+ | GPI | [31-28] | y | +------------------------------+---------+---------+ | GPA | [27-24] | y | @@ -210,7 +221,7 @@ infrastructure: | DPB | [3-0] | y | +------------------------------+---------+---------+ - 5) ID_AA64MMFR2_EL1 - Memory model feature register 2 + 6) ID_AA64MMFR2_EL1 - Memory model feature register 2 +------------------------------+---------+---------+ | Name | bits | visible | @@ -218,7 +229,7 @@ infrastructure: | AT | [35-32] | y | +------------------------------+---------+---------+ - 6) ID_AA64ZFR0_EL1 - SVE feature ID register 0 + 7) ID_AA64ZFR0_EL1 - SVE feature ID register 0 +------------------------------+---------+---------+ | Name | bits | visible | diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index 91f79529c58c..7fa3d215ae6a 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -119,10 +119,6 @@ HWCAP_LRCPC HWCAP_DCPOP Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001. -HWCAP2_DCPODP - - Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010. - HWCAP_SHA3 Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001. @@ -141,30 +137,6 @@ HWCAP_SHA512 HWCAP_SVE Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001. -HWCAP2_SVE2 - - Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001. - -HWCAP2_SVEAES - - Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001. - -HWCAP2_SVEPMULL - - Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010. - -HWCAP2_SVEBITPERM - - Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001. - -HWCAP2_SVESHA3 - - Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001. - -HWCAP2_SVESM4 - - Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001. - HWCAP_ASIMDFHM Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001. @@ -180,13 +152,12 @@ HWCAP_ILRCPC HWCAP_FLAGM Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0001. -HWCAP2_FLAGM2 - - Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010. - HWCAP_SSBS Functionality implied by ID_AA64PFR1_EL1.SSBS == 0b0010. +HWCAP_SB + Functionality implied by ID_AA64ISAR1_EL1.SB == 0b0001. + HWCAP_PACA Functionality implied by ID_AA64ISAR1_EL1.APA == 0b0001 or ID_AA64ISAR1_EL1.API == 0b0001, as described by @@ -197,6 +168,38 @@ HWCAP_PACG ID_AA64ISAR1_EL1.GPI == 0b0001, as described by Documentation/arm64/pointer-authentication.rst. +HWCAP2_DCPODP + + Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010. + +HWCAP2_SVE2 + + Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001. + +HWCAP2_SVEAES + + Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001. + +HWCAP2_SVEPMULL + + Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010. + +HWCAP2_SVEBITPERM + + Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001. + +HWCAP2_SVESHA3 + + Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001. + +HWCAP2_SVESM4 + + Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001. + +HWCAP2_FLAGM2 + + Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010. + HWCAP2_FRINT Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001. diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 5a09661330fc..99b2545455ff 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -70,8 +70,12 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A57 | #1319537 | ARM64_ERRATUM_1319367 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A72 | #853709 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A72 | #1319367 | ARM64_ERRATUM_1319367 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A55 | #1024718 | ARM64_ERRATUM_1024718 | @@ -88,6 +92,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/block/stat.rst b/Documentation/block/stat.rst index 9c07bc22b0bc..77311335c08b 100644 --- a/Documentation/block/stat.rst +++ b/Documentation/block/stat.rst @@ -41,6 +41,8 @@ discard I/Os requests number of discard I/Os processed discard merges requests number of discard I/Os merged with in-queue I/O discard sectors sectors number of sectors discarded discard ticks milliseconds total wait time for discard requests +flush I/Os requests number of flush I/Os processed +flush ticks milliseconds total wait time for flush requests =============== ============= ================================================= read I/Os, write I/Os, discard I/0s @@ -48,6 +50,14 @@ read I/Os, write I/Os, discard I/0s These values increment when an I/O request completes. +flush I/Os +========== + +These values increment when an flush I/O request completes. + +Block layer combines flush requests and executes at most one at a time. +This counts flush requests executed by disk. Not tracked for partitions. + read merges, write merges, discard merges ========================================= @@ -62,8 +72,8 @@ discarded from this block device. The "sectors" in question are the standard UNIX 512-byte sectors, not any device- or filesystem-specific block size. The counters are incremented when the I/O completes. -read ticks, write ticks, discard ticks -====================================== +read ticks, write ticks, discard ticks, flush ticks +=================================================== These values count the number of milliseconds that I/O requests have waited on this block device. If there are multiple I/O requests waiting, diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst index b0522a4dd107..09dee10d2592 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -24,6 +24,7 @@ whole; patches welcome! gdb-kernel-debugging kgdb kselftest + kunit/index .. only:: subproject and html diff --git a/Documentation/dev-tools/kunit/api/index.rst b/Documentation/dev-tools/kunit/api/index.rst new file mode 100644 index 000000000000..9b9bffe5d41a --- /dev/null +++ b/Documentation/dev-tools/kunit/api/index.rst @@ -0,0 +1,16 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============= +API Reference +============= +.. toctree:: + + test + +This section documents the KUnit kernel testing API. It is divided into the +following sections: + +================================= ============================================== +:doc:`test` documents all of the standard testing API + excluding mocking or mocking related features. +================================= ============================================== diff --git a/Documentation/dev-tools/kunit/api/test.rst b/Documentation/dev-tools/kunit/api/test.rst new file mode 100644 index 000000000000..aaa97f17e5b3 --- /dev/null +++ b/Documentation/dev-tools/kunit/api/test.rst @@ -0,0 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======== +Test API +======== + +This file documents all of the standard testing API excluding mocking or mocking +related features. + +.. kernel-doc:: include/kunit/test.h + :internal: diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst new file mode 100644 index 000000000000..bf2095112d89 --- /dev/null +++ b/Documentation/dev-tools/kunit/faq.rst @@ -0,0 +1,62 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================== +Frequently Asked Questions +========================== + +How is this different from Autotest, kselftest, etc? +==================================================== +KUnit is a unit testing framework. Autotest, kselftest (and some others) are +not. + +A `unit test <https://martinfowler.com/bliki/UnitTest.html>`_ is supposed to +test a single unit of code in isolation, hence the name. A unit test should be +the finest granularity of testing and as such should allow all possible code +paths to be tested in the code under test; this is only possible if the code +under test is very small and does not have any external dependencies outside of +the test's control like hardware. + +There are no testing frameworks currently available for the kernel that do not +require installing the kernel on a test machine or in a VM and all require +tests to be written in userspace and run on the kernel under test; this is true +for Autotest, kselftest, and some others, disqualifying any of them from being +considered unit testing frameworks. + +Does KUnit support running on architectures other than UML? +=========================================================== + +Yes, well, mostly. + +For the most part, the KUnit core framework (what you use to write the tests) +can compile to any architecture; it compiles like just another part of the +kernel and runs when the kernel boots. However, there is some infrastructure, +like the KUnit Wrapper (``tools/testing/kunit/kunit.py``) that does not support +other architectures. + +In short, this means that, yes, you can run KUnit on other architectures, but +it might require more work than using KUnit on UML. + +For more information, see :ref:`kunit-on-non-uml`. + +What is the difference between a unit test and these other kinds of tests? +========================================================================== +Most existing tests for the Linux kernel would be categorized as an integration +test, or an end-to-end test. + +- A unit test is supposed to test a single unit of code in isolation, hence the + name. A unit test should be the finest granularity of testing and as such + should allow all possible code paths to be tested in the code under test; this + is only possible if the code under test is very small and does not have any + external dependencies outside of the test's control like hardware. +- An integration test tests the interaction between a minimal set of components, + usually just two or three. For example, someone might write an integration + test to test the interaction between a driver and a piece of hardware, or to + test the interaction between the userspace libraries the kernel provides and + the kernel itself; however, one of these tests would probably not test the + entire kernel along with hardware interactions and interactions with the + userspace. +- An end-to-end test usually tests the entire system from the perspective of the + code under test. For example, someone might write an end-to-end test for the + kernel by installing a production configuration of the kernel on production + hardware with a production userspace and then trying to exercise some behavior + that depends on interactions between the hardware, the kernel, and userspace. diff --git a/Documentation/dev-tools/kunit/index.rst b/Documentation/dev-tools/kunit/index.rst new file mode 100644 index 000000000000..26ffb46bdf99 --- /dev/null +++ b/Documentation/dev-tools/kunit/index.rst @@ -0,0 +1,79 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================= +KUnit - Unit Testing for the Linux Kernel +========================================= + +.. toctree:: + :maxdepth: 2 + + start + usage + api/index + faq + +What is KUnit? +============== + +KUnit is a lightweight unit testing and mocking framework for the Linux kernel. +These tests are able to be run locally on a developer's workstation without a VM +or special hardware. + +KUnit is heavily inspired by JUnit, Python's unittest.mock, and +Googletest/Googlemock for C++. KUnit provides facilities for defining unit test +cases, grouping related test cases into test suites, providing common +infrastructure for running tests, and much more. + +Get started now: :doc:`start` + +Why KUnit? +========== + +A unit test is supposed to test a single unit of code in isolation, hence the +name. A unit test should be the finest granularity of testing and as such should +allow all possible code paths to be tested in the code under test; this is only +possible if the code under test is very small and does not have any external +dependencies outside of the test's control like hardware. + +Outside of KUnit, there are no testing frameworks currently +available for the kernel that do not require installing the kernel on a test +machine or in a VM and all require tests to be written in userspace running on +the kernel; this is true for Autotest, and kselftest, disqualifying +any of them from being considered unit testing frameworks. + +KUnit addresses the problem of being able to run tests without needing a virtual +machine or actual hardware with User Mode Linux. User Mode Linux is a Linux +architecture, like ARM or x86; however, unlike other architectures it compiles +to a standalone program that can be run like any other program directly inside +of a host operating system; to be clear, it does not require any virtualization +support; it is just a regular program. + +KUnit is fast. Excluding build time, from invocation to completion KUnit can run +several dozen tests in only 10 to 20 seconds; this might not sound like a big +deal to some people, but having such fast and easy to run tests fundamentally +changes the way you go about testing and even writing code in the first place. +Linus himself said in his `git talk at Google +<https://gist.github.com/lorn/1272686/revisions#diff-53c65572127855f1b003db4064a94573R874>`_: + + "... a lot of people seem to think that performance is about doing the + same thing, just doing it faster, and that is not true. That is not what + performance is all about. If you can do something really fast, really + well, people will start using it differently." + +In this context Linus was talking about branching and merging, +but this point also applies to testing. If your tests are slow, unreliable, are +difficult to write, and require a special setup or special hardware to run, +then you wait a lot longer to write tests, and you wait a lot longer to run +tests; this means that tests are likely to break, unlikely to test a lot of +things, and are unlikely to be rerun once they pass. If your tests are really +fast, you run them all the time, every time you make a change, and every time +someone sends you some code. Why trust that someone ran all their tests +correctly on every change when you can just run them yourself in less time than +it takes to read their test log? + +How do I use it? +================ + +* :doc:`start` - for new users of KUnit +* :doc:`usage` - for a more detailed explanation of KUnit features +* :doc:`api/index` - for the list of KUnit APIs used for testing diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst new file mode 100644 index 000000000000..aeeddfafeea2 --- /dev/null +++ b/Documentation/dev-tools/kunit/start.rst @@ -0,0 +1,180 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============== +Getting Started +=============== + +Installing dependencies +======================= +KUnit has the same dependencies as the Linux kernel. As long as you can build +the kernel, you can run KUnit. + +KUnit Wrapper +============= +Included with KUnit is a simple Python wrapper that helps format the output to +easily use and read KUnit output. It handles building and running the kernel, as +well as formatting the output. + +The wrapper can be run with: + +.. code-block:: bash + + ./tools/testing/kunit/kunit.py run + +Creating a kunitconfig +====================== +The Python script is a thin wrapper around Kbuild as such, it needs to be +configured with a ``kunitconfig`` file. This file essentially contains the +regular Kernel config, with the specific test targets as well. + +.. code-block:: bash + + git clone -b master https://kunit.googlesource.com/kunitconfig $PATH_TO_KUNITCONFIG_REPO + cd $PATH_TO_LINUX_REPO + ln -s $PATH_TO_KUNIT_CONFIG_REPO/kunitconfig kunitconfig + +You may want to add kunitconfig to your local gitignore. + +Verifying KUnit Works +--------------------- + +To make sure that everything is set up correctly, simply invoke the Python +wrapper from your kernel repo: + +.. code-block:: bash + + ./tools/testing/kunit/kunit.py run + +.. note:: + You may want to run ``make mrproper`` first. + +If everything worked correctly, you should see the following: + +.. code-block:: bash + + Generating .config ... + Building KUnit Kernel ... + Starting KUnit Kernel ... + +followed by a list of tests that are run. All of them should be passing. + +.. note:: + Because it is building a lot of sources for the first time, the ``Building + kunit kernel`` step may take a while. + +Writing your first test +======================= + +In your kernel repo let's add some code that we can test. Create a file +``drivers/misc/example.h`` with the contents: + +.. code-block:: c + + int misc_example_add(int left, int right); + +create a file ``drivers/misc/example.c``: + +.. code-block:: c + + #include <linux/errno.h> + + #include "example.h" + + int misc_example_add(int left, int right) + { + return left + right; + } + +Now add the following lines to ``drivers/misc/Kconfig``: + +.. code-block:: kconfig + + config MISC_EXAMPLE + bool "My example" + +and the following lines to ``drivers/misc/Makefile``: + +.. code-block:: make + + obj-$(CONFIG_MISC_EXAMPLE) += example.o + +Now we are ready to write the test. The test will be in +``drivers/misc/example-test.c``: + +.. code-block:: c + + #include <kunit/test.h> + #include "example.h" + + /* Define the test cases. */ + + static void misc_example_add_test_basic(struct kunit *test) + { + KUNIT_EXPECT_EQ(test, 1, misc_example_add(1, 0)); + KUNIT_EXPECT_EQ(test, 2, misc_example_add(1, 1)); + KUNIT_EXPECT_EQ(test, 0, misc_example_add(-1, 1)); + KUNIT_EXPECT_EQ(test, INT_MAX, misc_example_add(0, INT_MAX)); + KUNIT_EXPECT_EQ(test, -1, misc_example_add(INT_MAX, INT_MIN)); + } + + static void misc_example_test_failure(struct kunit *test) + { + KUNIT_FAIL(test, "This test never passes."); + } + + static struct kunit_case misc_example_test_cases[] = { + KUNIT_CASE(misc_example_add_test_basic), + KUNIT_CASE(misc_example_test_failure), + {} + }; + + static struct kunit_suite misc_example_test_suite = { + .name = "misc-example", + .test_cases = misc_example_test_cases, + }; + kunit_test_suite(misc_example_test_suite); + +Now add the following to ``drivers/misc/Kconfig``: + +.. code-block:: kconfig + + config MISC_EXAMPLE_TEST + bool "Test for my example" + depends on MISC_EXAMPLE && KUNIT + +and the following to ``drivers/misc/Makefile``: + +.. code-block:: make + + obj-$(CONFIG_MISC_EXAMPLE_TEST) += example-test.o + +Now add it to your ``kunitconfig``: + +.. code-block:: none + + CONFIG_MISC_EXAMPLE=y + CONFIG_MISC_EXAMPLE_TEST=y + +Now you can run the test: + +.. code-block:: bash + + ./tools/testing/kunit/kunit.py + +You should see the following failure: + +.. code-block:: none + + ... + [16:08:57] [PASSED] misc-example:misc_example_add_test_basic + [16:08:57] [FAILED] misc-example:misc_example_test_failure + [16:08:57] EXPECTATION FAILED at drivers/misc/example-test.c:17 + [16:08:57] This test never passes. + ... + +Congrats! You just wrote your first KUnit test! + +Next Steps +========== +* Check out the :doc:`usage` page for a more + in-depth explanation of KUnit. diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst new file mode 100644 index 000000000000..c6e69634e274 --- /dev/null +++ b/Documentation/dev-tools/kunit/usage.rst @@ -0,0 +1,576 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========== +Using KUnit +=========== + +The purpose of this document is to describe what KUnit is, how it works, how it +is intended to be used, and all the concepts and terminology that are needed to +understand it. This guide assumes a working knowledge of the Linux kernel and +some basic knowledge of testing. + +For a high level introduction to KUnit, including setting up KUnit for your +project, see :doc:`start`. + +Organization of this document +============================= + +This document is organized into two main sections: Testing and Isolating +Behavior. The first covers what a unit test is and how to use KUnit to write +them. The second covers how to use KUnit to isolate code and make it possible +to unit test code that was otherwise un-unit-testable. + +Testing +======= + +What is KUnit? +-------------- + +"K" is short for "kernel" so "KUnit" is the "(Linux) Kernel Unit Testing +Framework." KUnit is intended first and foremost for writing unit tests; it is +general enough that it can be used to write integration tests; however, this is +a secondary goal. KUnit has no ambition of being the only testing framework for +the kernel; for example, it does not intend to be an end-to-end testing +framework. + +What is Unit Testing? +--------------------- + +A `unit test <https://martinfowler.com/bliki/UnitTest.html>`_ is a test that +tests code at the smallest possible scope, a *unit* of code. In the C +programming language that's a function. + +Unit tests should be written for all the publicly exposed functions in a +compilation unit; so that is all the functions that are exported in either a +*class* (defined below) or all functions which are **not** static. + +Writing Tests +------------- + +Test Cases +~~~~~~~~~~ + +The fundamental unit in KUnit is the test case. A test case is a function with +the signature ``void (*)(struct kunit *test)``. It calls a function to be tested +and then sets *expectations* for what should happen. For example: + +.. code-block:: c + + void example_test_success(struct kunit *test) + { + } + + void example_test_failure(struct kunit *test) + { + KUNIT_FAIL(test, "This test never passes."); + } + +In the above example ``example_test_success`` always passes because it does +nothing; no expectations are set, so all expectations pass. On the other hand +``example_test_failure`` always fails because it calls ``KUNIT_FAIL``, which is +a special expectation that logs a message and causes the test case to fail. + +Expectations +~~~~~~~~~~~~ +An *expectation* is a way to specify that you expect a piece of code to do +something in a test. An expectation is called like a function. A test is made +by setting expectations about the behavior of a piece of code under test; when +one or more of the expectations fail, the test case fails and information about +the failure is logged. For example: + +.. code-block:: c + + void add_test_basic(struct kunit *test) + { + KUNIT_EXPECT_EQ(test, 1, add(1, 0)); + KUNIT_EXPECT_EQ(test, 2, add(1, 1)); + } + +In the above example ``add_test_basic`` makes a number of assertions about the +behavior of a function called ``add``; the first parameter is always of type +``struct kunit *``, which contains information about the current test context; +the second parameter, in this case, is what the value is expected to be; the +last value is what the value actually is. If ``add`` passes all of these +expectations, the test case, ``add_test_basic`` will pass; if any one of these +expectations fail, the test case will fail. + +It is important to understand that a test case *fails* when any expectation is +violated; however, the test will continue running, potentially trying other +expectations until the test case ends or is otherwise terminated. This is as +opposed to *assertions* which are discussed later. + +To learn about more expectations supported by KUnit, see :doc:`api/test`. + +.. note:: + A single test case should be pretty short, pretty easy to understand, + focused on a single behavior. + +For example, if we wanted to properly test the add function above, we would +create additional tests cases which would each test a different property that an +add function should have like this: + +.. code-block:: c + + void add_test_basic(struct kunit *test) + { + KUNIT_EXPECT_EQ(test, 1, add(1, 0)); + KUNIT_EXPECT_EQ(test, 2, add(1, 1)); + } + + void add_test_negative(struct kunit *test) + { + KUNIT_EXPECT_EQ(test, 0, add(-1, 1)); + } + + void add_test_max(struct kunit *test) + { + KUNIT_EXPECT_EQ(test, INT_MAX, add(0, INT_MAX)); + KUNIT_EXPECT_EQ(test, -1, add(INT_MAX, INT_MIN)); + } + + void add_test_overflow(struct kunit *test) + { + KUNIT_EXPECT_EQ(test, INT_MIN, add(INT_MAX, 1)); + } + +Notice how it is immediately obvious what all the properties that we are testing +for are. + +Assertions +~~~~~~~~~~ + +KUnit also has the concept of an *assertion*. An assertion is just like an +expectation except the assertion immediately terminates the test case if it is +not satisfied. + +For example: + +.. code-block:: c + + static void mock_test_do_expect_default_return(struct kunit *test) + { + struct mock_test_context *ctx = test->priv; + struct mock *mock = ctx->mock; + int param0 = 5, param1 = -5; + const char *two_param_types[] = {"int", "int"}; + const void *two_params[] = {¶m0, ¶m1}; + const void *ret; + + ret = mock->do_expect(mock, + "test_printk", test_printk, + two_param_types, two_params, + ARRAY_SIZE(two_params)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ret); + KUNIT_EXPECT_EQ(test, -4, *((int *) ret)); + } + +In this example, the method under test should return a pointer to a value, so +if the pointer returned by the method is null or an errno, we don't want to +bother continuing the test since the following expectation could crash the test +case. `ASSERT_NOT_ERR_OR_NULL(...)` allows us to bail out of the test case if +the appropriate conditions have not been satisfied to complete the test. + +Test Suites +~~~~~~~~~~~ + +Now obviously one unit test isn't very helpful; the power comes from having +many test cases covering all of your behaviors. Consequently it is common to +have many *similar* tests; in order to reduce duplication in these closely +related tests most unit testing frameworks provide the concept of a *test +suite*, in KUnit we call it a *test suite*; all it is is just a collection of +test cases for a unit of code with a set up function that gets invoked before +every test cases and then a tear down function that gets invoked after every +test case completes. + +Example: + +.. code-block:: c + + static struct kunit_case example_test_cases[] = { + KUNIT_CASE(example_test_foo), + KUNIT_CASE(example_test_bar), + KUNIT_CASE(example_test_baz), + {} + }; + + static struct kunit_suite example_test_suite = { + .name = "example", + .init = example_test_init, + .exit = example_test_exit, + .test_cases = example_test_cases, + }; + kunit_test_suite(example_test_suite); + +In the above example the test suite, ``example_test_suite``, would run the test +cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``, +each would have ``example_test_init`` called immediately before it and would +have ``example_test_exit`` called immediately after it. +``kunit_test_suite(example_test_suite)`` registers the test suite with the +KUnit test framework. + +.. note:: + A test case will only be run if it is associated with a test suite. + +For a more information on these types of things see the :doc:`api/test`. + +Isolating Behavior +================== + +The most important aspect of unit testing that other forms of testing do not +provide is the ability to limit the amount of code under test to a single unit. +In practice, this is only possible by being able to control what code gets run +when the unit under test calls a function and this is usually accomplished +through some sort of indirection where a function is exposed as part of an API +such that the definition of that function can be changed without affecting the +rest of the code base. In the kernel this primarily comes from two constructs, +classes, structs that contain function pointers that are provided by the +implementer, and architecture specific functions which have definitions selected +at compile time. + +Classes +------- + +Classes are not a construct that is built into the C programming language; +however, it is an easily derived concept. Accordingly, pretty much every project +that does not use a standardized object oriented library (like GNOME's GObject) +has their own slightly different way of doing object oriented programming; the +Linux kernel is no exception. + +The central concept in kernel object oriented programming is the class. In the +kernel, a *class* is a struct that contains function pointers. This creates a +contract between *implementers* and *users* since it forces them to use the +same function signature without having to call the function directly. In order +for it to truly be a class, the function pointers must specify that a pointer +to the class, known as a *class handle*, be one of the parameters; this makes +it possible for the member functions (also known as *methods*) to have access +to member variables (more commonly known as *fields*) allowing the same +implementation to have multiple *instances*. + +Typically a class can be *overridden* by *child classes* by embedding the +*parent class* in the child class. Then when a method provided by the child +class is called, the child implementation knows that the pointer passed to it is +of a parent contained within the child; because of this, the child can compute +the pointer to itself because the pointer to the parent is always a fixed offset +from the pointer to the child; this offset is the offset of the parent contained +in the child struct. For example: + +.. code-block:: c + + struct shape { + int (*area)(struct shape *this); + }; + + struct rectangle { + struct shape parent; + int length; + int width; + }; + + int rectangle_area(struct shape *this) + { + struct rectangle *self = container_of(this, struct shape, parent); + + return self->length * self->width; + }; + + void rectangle_new(struct rectangle *self, int length, int width) + { + self->parent.area = rectangle_area; + self->length = length; + self->width = width; + } + +In this example (as in most kernel code) the operation of computing the pointer +to the child from the pointer to the parent is done by ``container_of``. + +Faking Classes +~~~~~~~~~~~~~~ + +In order to unit test a piece of code that calls a method in a class, the +behavior of the method must be controllable, otherwise the test ceases to be a +unit test and becomes an integration test. + +A fake just provides an implementation of a piece of code that is different than +what runs in a production instance, but behaves identically from the standpoint +of the callers; this is usually done to replace a dependency that is hard to +deal with, or is slow. + +A good example for this might be implementing a fake EEPROM that just stores the +"contents" in an internal buffer. For example, let's assume we have a class that +represents an EEPROM: + +.. code-block:: c + + struct eeprom { + ssize_t (*read)(struct eeprom *this, size_t offset, char *buffer, size_t count); + ssize_t (*write)(struct eeprom *this, size_t offset, const char *buffer, size_t count); + }; + +And we want to test some code that buffers writes to the EEPROM: + +.. code-block:: c + + struct eeprom_buffer { + ssize_t (*write)(struct eeprom_buffer *this, const char *buffer, size_t count); + int flush(struct eeprom_buffer *this); + size_t flush_count; /* Flushes when buffer exceeds flush_count. */ + }; + + struct eeprom_buffer *new_eeprom_buffer(struct eeprom *eeprom); + void destroy_eeprom_buffer(struct eeprom *eeprom); + +We can easily test this code by *faking out* the underlying EEPROM: + +.. code-block:: c + + struct fake_eeprom { + struct eeprom parent; + char contents[FAKE_EEPROM_CONTENTS_SIZE]; + }; + + ssize_t fake_eeprom_read(struct eeprom *parent, size_t offset, char *buffer, size_t count) + { + struct fake_eeprom *this = container_of(parent, struct fake_eeprom, parent); + + count = min(count, FAKE_EEPROM_CONTENTS_SIZE - offset); + memcpy(buffer, this->contents + offset, count); + + return count; + } + + ssize_t fake_eeprom_write(struct eeprom *this, size_t offset, const char *buffer, size_t count) + { + struct fake_eeprom *this = container_of(parent, struct fake_eeprom, parent); + + count = min(count, FAKE_EEPROM_CONTENTS_SIZE - offset); + memcpy(this->contents + offset, buffer, count); + + return count; + } + + void fake_eeprom_init(struct fake_eeprom *this) + { + this->parent.read = fake_eeprom_read; + this->parent.write = fake_eeprom_write; + memset(this->contents, 0, FAKE_EEPROM_CONTENTS_SIZE); + } + +We can now use it to test ``struct eeprom_buffer``: + +.. code-block:: c + + struct eeprom_buffer_test { + struct fake_eeprom *fake_eeprom; + struct eeprom_buffer *eeprom_buffer; + }; + + static void eeprom_buffer_test_does_not_write_until_flush(struct kunit *test) + { + struct eeprom_buffer_test *ctx = test->priv; + struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer; + struct fake_eeprom *fake_eeprom = ctx->fake_eeprom; + char buffer[] = {0xff}; + + eeprom_buffer->flush_count = SIZE_MAX; + + eeprom_buffer->write(eeprom_buffer, buffer, 1); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0); + + eeprom_buffer->write(eeprom_buffer, buffer, 1); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0); + + eeprom_buffer->flush(eeprom_buffer); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff); + } + + static void eeprom_buffer_test_flushes_after_flush_count_met(struct kunit *test) + { + struct eeprom_buffer_test *ctx = test->priv; + struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer; + struct fake_eeprom *fake_eeprom = ctx->fake_eeprom; + char buffer[] = {0xff}; + + eeprom_buffer->flush_count = 2; + + eeprom_buffer->write(eeprom_buffer, buffer, 1); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0); + + eeprom_buffer->write(eeprom_buffer, buffer, 1); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff); + } + + static void eeprom_buffer_test_flushes_increments_of_flush_count(struct kunit *test) + { + struct eeprom_buffer_test *ctx = test->priv; + struct eeprom_buffer *eeprom_buffer = ctx->eeprom_buffer; + struct fake_eeprom *fake_eeprom = ctx->fake_eeprom; + char buffer[] = {0xff, 0xff}; + + eeprom_buffer->flush_count = 2; + + eeprom_buffer->write(eeprom_buffer, buffer, 1); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0); + + eeprom_buffer->write(eeprom_buffer, buffer, 2); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[0], 0xff); + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[1], 0xff); + /* Should have only flushed the first two bytes. */ + KUNIT_EXPECT_EQ(test, fake_eeprom->contents[2], 0); + } + + static int eeprom_buffer_test_init(struct kunit *test) + { + struct eeprom_buffer_test *ctx; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + + ctx->fake_eeprom = kunit_kzalloc(test, sizeof(*ctx->fake_eeprom), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->fake_eeprom); + fake_eeprom_init(ctx->fake_eeprom); + + ctx->eeprom_buffer = new_eeprom_buffer(&ctx->fake_eeprom->parent); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->eeprom_buffer); + + test->priv = ctx; + + return 0; + } + + static void eeprom_buffer_test_exit(struct kunit *test) + { + struct eeprom_buffer_test *ctx = test->priv; + + destroy_eeprom_buffer(ctx->eeprom_buffer); + } + +.. _kunit-on-non-uml: + +KUnit on non-UML architectures +============================== + +By default KUnit uses UML as a way to provide dependencies for code under test. +Under most circumstances KUnit's usage of UML should be treated as an +implementation detail of how KUnit works under the hood. Nevertheless, there +are instances where being able to run architecture specific code, or test +against real hardware is desirable. For these reasons KUnit supports running on +other architectures. + +Running existing KUnit tests on non-UML architectures +----------------------------------------------------- + +There are some special considerations when running existing KUnit tests on +non-UML architectures: + +* Hardware may not be deterministic, so a test that always passes or fails + when run under UML may not always do so on real hardware. +* Hardware and VM environments may not be hermetic. KUnit tries its best to + provide a hermetic environment to run tests; however, it cannot manage state + that it doesn't know about outside of the kernel. Consequently, tests that + may be hermetic on UML may not be hermetic on other architectures. +* Some features and tooling may not be supported outside of UML. +* Hardware and VMs are slower than UML. + +None of these are reasons not to run your KUnit tests on real hardware; they are +only things to be aware of when doing so. + +The biggest impediment will likely be that certain KUnit features and +infrastructure may not support your target environment. For example, at this +time the KUnit Wrapper (``tools/testing/kunit/kunit.py``) does not work outside +of UML. Unfortunately, there is no way around this. Using UML (or even just a +particular architecture) allows us to make a lot of assumptions that make it +possible to do things which might otherwise be impossible. + +Nevertheless, all core KUnit framework features are fully supported on all +architectures, and using them is straightforward: all you need to do is to take +your kunitconfig, your Kconfig options for the tests you would like to run, and +merge them into whatever config your are using for your platform. That's it! + +For example, let's say you have the following kunitconfig: + +.. code-block:: none + + CONFIG_KUNIT=y + CONFIG_KUNIT_EXAMPLE_TEST=y + +If you wanted to run this test on an x86 VM, you might add the following config +options to your ``.config``: + +.. code-block:: none + + CONFIG_KUNIT=y + CONFIG_KUNIT_EXAMPLE_TEST=y + CONFIG_SERIAL_8250=y + CONFIG_SERIAL_8250_CONSOLE=y + +All these new options do is enable support for a common serial console needed +for logging. + +Next, you could build a kernel with these tests as follows: + + +.. code-block:: bash + + make ARCH=x86 olddefconfig + make ARCH=x86 + +Once you have built a kernel, you could run it on QEMU as follows: + +.. code-block:: bash + + qemu-system-x86_64 -enable-kvm \ + -m 1024 \ + -kernel arch/x86_64/boot/bzImage \ + -append 'console=ttyS0' \ + --nographic + +Interspersed in the kernel logs you might see the following: + +.. code-block:: none + + TAP version 14 + # Subtest: example + 1..1 + # example_simple_test: initializing + ok 1 - example_simple_test + ok 1 - example + +Congratulations, you just ran a KUnit test on the x86 architecture! + +Writing new tests for other architectures +----------------------------------------- + +The first thing you must do is ask yourself whether it is necessary to write a +KUnit test for a specific architecture, and then whether it is necessary to +write that test for a particular piece of hardware. In general, writing a test +that depends on having access to a particular piece of hardware or software (not +included in the Linux source repo) should be avoided at all costs. + +Even if you only ever plan on running your KUnit test on your hardware +configuration, other people may want to run your tests and may not have access +to your hardware. If you write your test to run on UML, then anyone can run your +tests without knowing anything about your particular setup, and you can still +run your tests on your hardware setup just by compiling for your architecture. + +.. important:: + Always prefer tests that run on UML to tests that only run under a particular + architecture, and always prefer tests that run under QEMU or another easy + (and monitarily free) to obtain software environment to a specific piece of + hardware. + +Nevertheless, there are still valid reasons to write an architecture or hardware +specific test: for example, you might want to test some code that really belongs +in ``arch/some-arch/*``. Even so, try your best to write the test so that it +does not depend on physical hardware: if some of your test cases don't need the +hardware, only require the hardware for tests that actually need it. + +Now that you have narrowed down exactly what bits are hardware specific, the +actual procedure for writing and running the tests is pretty much the same as +writing normal KUnit tests. One special caveat is that you have to reset +hardware state in between test cases; if this is not possible, you may only be +able to run one test case per invocation. + +.. TODO(brendanhiggins@google.com): Add an actual example of an architecture + dependent KUnit test. diff --git a/Documentation/devicetree/bindings/mips/ralink.txt b/Documentation/devicetree/bindings/mips/ralink.txt index a16e8d7fe56c..8cc0ab41578c 100644 --- a/Documentation/devicetree/bindings/mips/ralink.txt +++ b/Documentation/devicetree/bindings/mips/ralink.txt @@ -16,3 +16,17 @@ value must be one of the following values: ralink,mt7620a-soc ralink,mt7620n-soc ralink,mt7628a-soc + ralink,mt7688a-soc + +2. Boards + +GARDENA smart Gateway (MT7688) + +This board is based on the MediaTek MT7688 and equipped with 128 MiB +of DDR and 8 MiB of flash (SPI NOR) and additional 128MiB SPI NAND +storage. + +------------------------------ +Required root node properties: +- compatible = "gardena,smart-gateway-mt7688", "ralink,mt7688a-soc", + "ralink,mt7628a-soc"; diff --git a/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt new file mode 100644 index 000000000000..f3893c4d3c6a --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt @@ -0,0 +1,53 @@ +* Cadence NAND controller + +Required properties: + - compatible : "cdns,hp-nfc" + - reg : Contains two entries, each of which is a tuple consisting of a + physical address and length. The first entry is the address and + length of the controller register set. The second entry is the + address and length of the Slave DMA data port. + - reg-names: should contain "reg" and "sdma" + - #address-cells: should be 1. The cell encodes the chip select connection. + - #size-cells : should be 0. + - interrupts : The interrupt number. + - clocks: phandle of the controller core clock (nf_clk). + +Optional properties: + - dmas: shall reference DMA channel associated to the NAND controller + - cdns,board-delay-ps : Estimated Board delay. The value includes the total + round trip delay for the signals and is used for deciding on values + associated with data read capture. The example formula for SDR mode is + the following: + board delay = RE#PAD delay + PCB trace to device + PCB trace from device + + DQ PAD delay + +Child nodes represent the available NAND chips. + +Required properties of NAND chips: + - reg: shall contain the native Chip Select ids from 0 to max supported by + the cadence nand flash controller + +See Documentation/devicetree/bindings/mtd/nand.txt for more details on +generic bindings. + +Example: + +nand_controller: nand-controller@60000000 { + compatible = "cdns,hp-nfc"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x60000000 0x10000>, <0x80000000 0x10000>; + reg-names = "reg", "sdma"; + clocks = <&nf_clk>; + cdns,board-delay-ps = <4830>; + interrupts = <2 0>; + nand@0 { + reg = <0>; + label = "nand-1"; + }; + nand@1 { + reg = <1>; + label = "nand-2"; + }; + +}; diff --git a/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt b/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt new file mode 100644 index 000000000000..4bdcb92ae381 --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/intel,ixp4xx-flash.txt @@ -0,0 +1,22 @@ +Flash device on Intel IXP4xx SoC + +This flash is regular CFI compatible (Intel or AMD extended) flash chips with +specific big-endian or mixed-endian memory access pattern. + +Required properties: +- compatible : must be "intel,ixp4xx-flash", "cfi-flash"; +- reg : memory address for the flash chip +- bank-width : width in bytes of flash interface, should be <2> + +For the rest of the properties, see mtd-physmap.txt. + +The device tree may optionally contain sub-nodes describing partitions of the +address space. See partition.txt for more detail. + +Example: + +flash@50000000 { + compatible = "intel,ixp4xx-flash", "cfi-flash"; + reg = <0x50000000 0x01000000>; + bank-width = <2>; +}; diff --git a/Documentation/devicetree/bindings/perf/arm-ccn.txt b/Documentation/devicetree/bindings/perf/arm-ccn.txt index 43b5a71a5a9d..1c53b5aa3317 100644 --- a/Documentation/devicetree/bindings/perf/arm-ccn.txt +++ b/Documentation/devicetree/bindings/perf/arm-ccn.txt @@ -6,6 +6,7 @@ Required properties: "arm,ccn-502" "arm,ccn-504" "arm,ccn-508" + "arm,ccn-512" - reg: (standard registers property) physical address and size (16MB) of the configuration registers block diff --git a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt index d77e3f26f9e6..7822a806ea0a 100644 --- a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt +++ b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt @@ -5,6 +5,7 @@ Required properties: - compatible: should be one of: "fsl,imx8-ddr-pmu" "fsl,imx8m-ddr-pmu" + "fsl,imx8mp-ddr-pmu" - reg: physical address and size diff --git a/Documentation/devicetree/bindings/security/tpm/google,cr50.txt b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt new file mode 100644 index 000000000000..cd69c2efdd37 --- /dev/null +++ b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt @@ -0,0 +1,19 @@ +* H1 Secure Microcontroller with Cr50 Firmware on SPI Bus. + +H1 Secure Microcontroller running Cr50 firmware provides several +functions, including TPM-like functionality. It communicates over +SPI using the FIFO protocol described in the PTP Spec, section 6. + +Required properties: +- compatible: Should be "google,cr50". +- spi-max-frequency: Maximum SPI frequency. + +Example: + +&spi0 { + tpm@0 { + compatible = "google,cr50"; + reg = <0>; + spi-max-frequency = <800000>; + }; +}; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 967e78c5ec0a..05b3904a995b 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -343,6 +343,8 @@ patternProperties: description: Freescale Semiconductor "^fujitsu,.*": description: Fujitsu Ltd. + "^gardena,.*": + description: GARDENA GmbH "^gateworks,.*": description: Gateworks Corporation "^gcw,.*": diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst index 70e180e6b93d..207f0d24de69 100644 --- a/Documentation/driver-api/libata.rst +++ b/Documentation/driver-api/libata.rst @@ -250,23 +250,23 @@ High-level taskfile hooks :: - void (*qc_prep) (struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc); int (*qc_issue) (struct ata_queued_cmd *qc); -Higher-level hooks, these two hooks can potentially supercede several of +Higher-level hooks, these two hooks can potentially supersede several of the above taskfile/DMA engine hooks. ``->qc_prep`` is called after the buffers have been DMA-mapped, and is typically used to populate the -hardware's DMA scatter-gather table. Most drivers use the standard -:c:func:`ata_qc_prep` helper function, but more advanced drivers roll their -own. +hardware's DMA scatter-gather table. Some drivers use the standard +:c:func:`ata_bmdma_qc_prep` and :c:func:`ata_bmdma_dumb_qc_prep` helper +functions, but more advanced drivers roll their own. ``->qc_issue`` is used to make a command active, once the hardware and S/G tables have been prepared. IDE BMDMA drivers use the helper function -:c:func:`ata_qc_issue_prot` for taskfile protocol-based dispatch. More +:c:func:`ata_sff_qc_issue` for taskfile protocol-based dispatch. More advanced drivers implement their own ``->qc_issue``. -:c:func:`ata_qc_issue_prot` calls ``->tf_load()``, ``->bmdma_setup()``, and +:c:func:`ata_sff_qc_issue` calls ``->sff_tf_load()``, ``->bmdma_setup()``, and ``->bmdma_start()`` as necessary to initiate a transfer. Exception and probe handling (EH) diff --git a/Documentation/driver-api/nvmem.rst b/Documentation/driver-api/nvmem.rst index d9d958d5c824..287e86819640 100644 --- a/Documentation/driver-api/nvmem.rst +++ b/Documentation/driver-api/nvmem.rst @@ -129,6 +129,8 @@ To facilitate such consumers NVMEM framework provides below apis:: struct nvmem_device *nvmem_device_get(struct device *dev, const char *name); struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *name); + struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)); void nvmem_device_put(struct nvmem_device *nvmem); int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf); diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 8a0700af9596..471a511c7508 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -256,13 +256,8 @@ alternative master keys or to support rotating master keys. Instead, the master keys may be wrapped in userspace, e.g. as is done by the `fscrypt <https://github.com/google/fscrypt>`_ tool. -Including the inode number in the IVs was considered. However, it was -rejected as it would have prevented ext4 filesystems from being -resized, and by itself still wouldn't have been sufficient to prevent -the same key from being directly reused for both XTS and CTS-CBC. - -DIRECT_KEY and per-mode keys ----------------------------- +DIRECT_KEY policies +------------------- The Adiantum encryption mode (see `Encryption modes and usage`_) is suitable for both contents and filenames encryption, and it accepts @@ -285,6 +280,21 @@ IV. Moreover: key derived using the KDF. Users may use the same master key for other v2 encryption policies. +IV_INO_LBLK_64 policies +----------------------- + +When FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 is set in the fscrypt policy, +the encryption keys are derived from the master key, encryption mode +number, and filesystem UUID. This normally results in all files +protected by the same master key sharing a single contents encryption +key and a single filenames encryption key. To still encrypt different +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. + Key identifiers --------------- @@ -308,8 +318,9 @@ If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair. AES-128-CBC was added only for low-powered embedded devices with crypto accelerators such as CAAM or CESA that do not support XTS. To -use AES-128-CBC, CONFIG_CRYPTO_SHA256 (or another SHA-256 -implementation) must be enabled so that ESSIV can be used. +use AES-128-CBC, CONFIG_CRYPTO_ESSIV and CONFIG_CRYPTO_SHA256 (or +another SHA-256 implementation) must be enabled so that ESSIV can be +used. Adiantum is a (primarily) stream cipher-based mode that is fast even on CPUs without dedicated crypto instructions. It's also a true @@ -341,10 +352,16 @@ a little endian number, except that: is encrypted with AES-256 where the AES-256 key is the SHA-256 hash of the file's data encryption key. -- In the "direct key" configuration (FSCRYPT_POLICY_FLAG_DIRECT_KEY - set in the fscrypt_policy), the file's nonce is also appended to the - IV. Currently this is only allowed with the Adiantum encryption - mode. +- With `DIRECT_KEY policies`_, the file's nonce is appended to the IV. + Currently this is only allowed with the Adiantum encryption mode. + +- With `IV_INO_LBLK_64 policies`_, the logical block number is limited + 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. + +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". Filenames encryption -------------------- @@ -354,10 +371,10 @@ the requirements to retain support for efficient directory lookups and filenames of up to 255 bytes, the same IV is used for every filename in a directory. -However, each encrypted directory still uses a unique key; or -alternatively (for the "direct key" configuration) has the file's -nonce included in the IVs. Thus, IV reuse is limited to within a -single directory. +However, each encrypted directory still uses a unique key, or +alternatively has the file's nonce (for `DIRECT_KEY policies`_) or +inode number (for `IV_INO_LBLK_64 policies`_) included in the IVs. +Thus, IV reuse is limited to within a single directory. With CTS-CBC, the IV reuse means that when the plaintext filenames share a common prefix at least as long as the cipher block size (16 @@ -431,12 +448,15 @@ This structure must be initialized as follows: (1) for ``contents_encryption_mode`` and FSCRYPT_MODE_AES_256_CTS (4) for ``filenames_encryption_mode``. -- ``flags`` must contain a value from ``<linux/fscrypt.h>`` which - identifies the amount of NUL-padding to use when encrypting - filenames. If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 (0x3). - Additionally, if the encryption modes are both - FSCRYPT_MODE_ADIANTUM, this can contain - FSCRYPT_POLICY_FLAG_DIRECT_KEY; see `DIRECT_KEY and per-mode keys`_. +- ``flags`` contains optional flags from ``<linux/fscrypt.h>``: + + - FSCRYPT_POLICY_FLAGS_PAD_*: The amount of NUL padding to use when + encrypting filenames. If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 + (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. - For v2 encryption policies, ``__reserved`` must be zeroed. @@ -1089,7 +1109,7 @@ policy structs (see `Setting an encryption policy`_), except that the context structs also contain a nonce. The nonce is randomly generated by the kernel and is used as KDF input or as a tweak to cause different files to be encrypted differently; see `Per-file keys`_ and -`DIRECT_KEY and per-mode keys`_. +`DIRECT_KEY policies`_. Data path changes ----------------- diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index 42a0b6dd9e0b..a95536b6443c 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -226,6 +226,14 @@ To do so, check for FS_VERITY_FL (0x00100000) in the returned flags. The verity flag is not settable via FS_IOC_SETFLAGS. You must use FS_IOC_ENABLE_VERITY instead, since parameters must be provided. +statx +----- + +Since Linux v5.5, the statx() system call sets STATX_ATTR_VERITY if +the file has fs-verity enabled. This can perform better than +FS_IOC_GETFLAGS and FS_IOC_MEASURE_VERITY because it doesn't require +opening the file, and opening verity files can be expensive. + Accessing verity files ====================== @@ -398,7 +406,7 @@ pages have been read into the pagecache. (See `Verifying data`_.) ext4 ---- -ext4 supports fs-verity since Linux TODO and e2fsprogs v1.45.2. +ext4 supports fs-verity since Linux v5.4 and e2fsprogs v1.45.2. To create verity files on an ext4 filesystem, the filesystem must have been formatted with ``-O verity`` or had ``tune2fs -O verity`` run on @@ -434,7 +442,7 @@ also only supports extent-based files. f2fs ---- -f2fs supports fs-verity since Linux TODO and f2fs-tools v1.11.0. +f2fs supports fs-verity since Linux v5.4 and f2fs-tools v1.11.0. To create verity files on an f2fs filesystem, the filesystem must have been formatted with ``-O verity``. diff --git a/Documentation/ioctl/ioctl-number.rst b/Documentation/ioctl/ioctl-number.rst index bef79cd4c6b4..4ef86433bd67 100644 --- a/Documentation/ioctl/ioctl-number.rst +++ b/Documentation/ioctl/ioctl-number.rst @@ -233,6 +233,7 @@ Code Seq# Include File Comments 'f' 00-0F fs/ext4/ext4.h conflict! 'f' 00-0F linux/fs.h conflict! 'f' 00-0F fs/ocfs2/ocfs2_fs.h conflict! +'f' 13-27 linux/fscrypt.h 'f' 81-8F linux/fsverity.h 'g' 00-0F linux/usb/gadgetfs.h 'g' 20-2F linux/usb/g_printer.h diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index 0dd3f748239f..f914e81fd3a6 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -436,6 +436,10 @@ by the driver: encryption. * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream but did not arrive in the expected order. + * ``tx_tls_skip_no_sync_data`` - number of TX packets which were part of + a TLS stream and arrived out-of-order, but skipped the HW offload routine + and went to the regular transmit flow as they were retransmissions of the + connection handshake. * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of a TLS stream dropped, because they arrived out of order and associated record could not be found. diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index af64c4bb4447..a8de2fbc1caa 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -27,6 +27,7 @@ x86-specific Documentation mds microcode resctrl_ui + tsx_async_abort usb-legacy-support i386/index x86_64/index diff --git a/Documentation/x86/tsx_async_abort.rst b/Documentation/x86/tsx_async_abort.rst new file mode 100644 index 000000000000..583ddc185ba2 --- /dev/null +++ b/Documentation/x86/tsx_async_abort.rst @@ -0,0 +1,117 @@ +.. SPDX-License-Identifier: GPL-2.0 + +TSX Async Abort (TAA) mitigation +================================ + +.. _tsx_async_abort: + +Overview +-------- + +TSX Async Abort (TAA) is a side channel attack on internal buffers in some +Intel processors similar to Microachitectural Data Sampling (MDS). In this +case certain loads may speculatively pass invalid data to dependent operations +when an asynchronous abort condition is pending in a Transactional +Synchronization Extensions (TSX) transaction. This includes loads with no +fault or assist condition. Such loads may speculatively expose stale data from +the same uarch data structures as in MDS, with same scope of exposure i.e. +same-thread and cross-thread. This issue affects all current processors that +support TSX. + +Mitigation strategy +------------------- + +a) TSX disable - one of the mitigations is to disable TSX. A new MSR +IA32_TSX_CTRL will be available in future and current processors after +microcode update which can be used to disable TSX. In addition, it +controls the enumeration of the TSX feature bits (RTM and HLE) in CPUID. + +b) Clear CPU buffers - similar to MDS, clearing the CPU buffers mitigates this +vulnerability. More details on this approach can be found in +:ref:`Documentation/admin-guide/hw-vuln/mds.rst <mds>`. + +Kernel internal mitigation modes +-------------------------------- + + ============= ============================================================ + off Mitigation is disabled. Either the CPU is not affected or + tsx_async_abort=off is supplied on the kernel command line. + + tsx disabled Mitigation is enabled. TSX feature is disabled by default at + bootup on processors that support TSX control. + + verw Mitigation is enabled. CPU is affected and MD_CLEAR is + advertised in CPUID. + + ucode needed Mitigation is enabled. CPU is affected and MD_CLEAR is not + advertised in CPUID. That is mainly for virtualization + scenarios where the host has the updated microcode but the + hypervisor does not expose MD_CLEAR in CPUID. It's a best + effort approach without guarantee. + ============= ============================================================ + +If the CPU is affected and the "tsx_async_abort" kernel command line parameter is +not provided then the kernel selects an appropriate mitigation depending on the +status of RTM and MD_CLEAR CPUID bits. + +Below tables indicate the impact of tsx=on|off|auto cmdline options on state of +TAA mitigation, VERW behavior and TSX feature for various combinations of +MSR_IA32_ARCH_CAPABILITIES bits. + +1. "tsx=off" + +========= ========= ============ ============ ============== =================== ====================== +MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=off +---------------------------------- ------------------------------------------------------------------------- +TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation + after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full +========= ========= ============ ============ ============== =================== ====================== + 0 0 0 HW default Yes Same as MDS Same as MDS + 0 0 1 Invalid case Invalid case Invalid case Invalid case + 0 1 0 HW default No Need ucode update Need ucode update + 0 1 1 Disabled Yes TSX disabled TSX disabled + 1 X 1 Disabled X None needed None needed +========= ========= ============ ============ ============== =================== ====================== + +2. "tsx=on" + +========= ========= ============ ============ ============== =================== ====================== +MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=on +---------------------------------- ------------------------------------------------------------------------- +TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation + after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full +========= ========= ============ ============ ============== =================== ====================== + 0 0 0 HW default Yes Same as MDS Same as MDS + 0 0 1 Invalid case Invalid case Invalid case Invalid case + 0 1 0 HW default No Need ucode update Need ucode update + 0 1 1 Enabled Yes None Same as MDS + 1 X 1 Enabled X None needed None needed +========= ========= ============ ============ ============== =================== ====================== + +3. "tsx=auto" + +========= ========= ============ ============ ============== =================== ====================== +MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=auto +---------------------------------- ------------------------------------------------------------------------- +TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation + after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full +========= ========= ============ ============ ============== =================== ====================== + 0 0 0 HW default Yes Same as MDS Same as MDS + 0 0 1 Invalid case Invalid case Invalid case Invalid case + 0 1 0 HW default No Need ucode update Need ucode update + 0 1 1 Disabled Yes TSX disabled TSX disabled + 1 X 1 Enabled X None needed None needed +========= ========= ============ ============ ============== =================== ====================== + +In the tables, TSX_CTRL_MSR is a new bit in MSR_IA32_ARCH_CAPABILITIES that +indicates whether MSR_IA32_TSX_CTRL is supported. + +There are two control bits in IA32_TSX_CTRL MSR: + + Bit 0: When set it disables the Restricted Transactional Memory (RTM) + sub-feature of TSX (will force all transactions to abort on the + XBEGIN instruction). + + Bit 1: When set it disables the enumeration of the RTM and HLE feature + (i.e. it will make CPUID(EAX=7).EBX{bit4} and + CPUID(EAX=7).EBX{bit11} read as 0). diff --git a/MAINTAINERS b/MAINTAINERS index 2a427d1e9f01..a5689e2c1aa5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -643,7 +643,7 @@ F: drivers/net/ethernet/alacritech/* FORCEDETH GIGABIT ETHERNET DRIVER M: Rain River <rain.1986.08.12@gmail.com> -M: Zhu Yanjun <yanjun.zhu@oracle.com> +M: Zhu Yanjun <zyjzyj2000@gmail.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/nvidia/* @@ -2611,6 +2611,7 @@ S: Maintained F: arch/arm64/ X: arch/arm64/boot/dts/ F: Documentation/arm64/ +F: tools/testing/selftests/arm64/ AS3645A LED FLASH CONTROLLER DRIVER M: Sakari Ailus <sakari.ailus@iki.fi> @@ -3053,6 +3054,7 @@ M: Daniel Borkmann <daniel@iogearbox.net> R: Martin KaFai Lau <kafai@fb.com> R: Song Liu <songliubraving@fb.com> R: Yonghong Song <yhs@fb.com> +R: Andrii Nakryiko <andriin@fb.com> L: netdev@vger.kernel.org L: bpf@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git @@ -3260,7 +3262,6 @@ S: Maintained F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE -M: Kevin Cernekee <cernekee@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> L: bcm-kernel-feedback-list@broadcom.com L: linux-mips@vger.kernel.org @@ -3595,6 +3596,13 @@ S: Maintained F: Documentation/devicetree/bindings/media/cdns,*.txt F: drivers/media/platform/cadence/cdns-csi2* +CADENCE NAND DRIVER +M: Piotr Sroka <piotrs@cadence.com> +L: linux-mtd@lists.infradead.org +S: Maintained +F: drivers/mtd/nand/raw/cadence-nand-controller.c +F: Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt + CADET FM/AM RADIO RECEIVER DRIVER M: Hans Verkuil <hverkuil@xs4all.nl> L: linux-media@vger.kernel.org @@ -3737,7 +3745,6 @@ F: drivers/crypto/cavium/cpt/ CAVIUM THUNDERX2 ARM64 SOC M: Robert Richter <rrichter@cavium.com> -M: Jayachandran C <jnair@caviumnetworks.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm64/boot/dts/cavium/thunder2-99xx* @@ -8299,11 +8306,14 @@ F: drivers/hid/intel-ish-hid/ INTEL IOMMU (VT-d) M: David Woodhouse <dwmw2@infradead.org> +M: Lu Baolu <baolu.lu@linux.intel.com> L: iommu@lists.linux-foundation.org -T: git git://git.infradead.org/iommu-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git S: Supported -F: drivers/iommu/intel-iommu.c +F: drivers/iommu/dmar.c +F: drivers/iommu/intel*.[ch] F: include/linux/intel-iommu.h +F: include/linux/intel-svm.h INTEL IOP-ADMA DMA DRIVER R: Dan Williams <dan.j.williams@intel.com> @@ -8562,12 +8572,13 @@ F: include/linux/iova.h IO_URING M: Jens Axboe <axboe@kernel.dk> -L: linux-block@vger.kernel.org -L: linux-fsdevel@vger.kernel.org +L: io-uring@vger.kernel.org T: git git://git.kernel.dk/linux-block T: git git://git.kernel.dk/liburing S: Maintained F: fs/io_uring.c +F: fs/io-wq.c +F: fs/io-wq.h F: include/uapi/linux/io_uring.h IPMI SUBSYSTEM @@ -8918,6 +8929,17 @@ S: Maintained F: tools/testing/selftests/ F: Documentation/dev-tools/kselftest* +KERNEL UNIT TESTING FRAMEWORK (KUnit) +M: Brendan Higgins <brendanhiggins@google.com> +L: linux-kselftest@vger.kernel.org +L: kunit-dev@googlegroups.com +W: https://google.github.io/kunit-docs/third_party/kernel/docs/ +S: Maintained +F: Documentation/dev-tools/kunit/ +F: include/kunit/ +F: lib/kunit/ +F: tools/testing/kunit/ + KERNEL USERMODE HELPER M: Luis Chamberlain <mcgrof@kernel.org> L: linux-kernel@vger.kernel.org @@ -9495,6 +9517,13 @@ F: Documentation/misc-devices/lis3lv02d.rst F: drivers/misc/lis3lv02d/ F: drivers/platform/x86/hp_accel.c +LIST KUNIT TEST +M: David Gow <davidgow@google.com> +L: linux-kselftest@vger.kernel.org +L: kunit-dev@googlegroups.com +S: Maintained +F: lib/list-test.c + LIVE PATCHING M: Josh Poimboeuf <jpoimboe@redhat.com> M: Jiri Kosina <jikos@kernel.org> @@ -10534,15 +10563,13 @@ F: include/linux/vmalloc.h F: mm/ MEMORY TECHNOLOGY DEVICES (MTD) -M: David Woodhouse <dwmw2@infradead.org> -M: Brian Norris <computersforpeace@gmail.com> -M: Marek Vasut <marek.vasut@gmail.com> M: Miquel Raynal <miquel.raynal@bootlin.com> M: Richard Weinberger <richard@nod.at> M: Vignesh Raghavendra <vigneshr@ti.com> L: linux-mtd@lists.infradead.org W: http://www.linux-mtd.infradead.org/ Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ +C: irc://irc.oftc.net/mtd T: git git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git mtd/fixes T: git git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git mtd/next S: Maintained @@ -10873,18 +10900,18 @@ F: arch/mips/include/asm/mach-loongson32/ F: drivers/*/*loongson1* F: drivers/*/*/*loongson1* -MIPS/LOONGSON2 ARCHITECTURE +MIPS/LOONGSON2EF ARCHITECTURE M: Jiaxun Yang <jiaxun.yang@flygoat.com> L: linux-mips@vger.kernel.org S: Maintained -F: arch/mips/loongson64/fuloong-2e/ -F: arch/mips/loongson64/lemote-2f/ -F: arch/mips/include/asm/mach-loongson64/ +F: arch/mips/loongson2ef/ +F: arch/mips/include/asm/mach-loongson2ef/ F: drivers/*/*loongson2* F: drivers/*/*/*loongson2* -MIPS/LOONGSON3 ARCHITECTURE +MIPS/LOONGSON64 ARCHITECTURE M: Huacai Chen <chenhc@lemote.com> +M: Jiaxun Yang <jiaxun.yang@flygoat.com> L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/loongson64/ @@ -11635,6 +11662,7 @@ F: drivers/nvme/target/fcloop.c NVM EXPRESS TARGET DRIVER M: Christoph Hellwig <hch@lst.de> M: Sagi Grimberg <sagi@grimberg.me> +M: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> L: linux-nvme@lists.infradead.org T: git://git.infradead.org/nvme.git W: http://git.infradead.org/nvme.git @@ -13130,12 +13158,14 @@ F: Documentation/filesystems/proc.txt PROC SYSCTL M: Luis Chamberlain <mcgrof@kernel.org> M: Kees Cook <keescook@chromium.org> +M: Iurii Zaikin <yzaikin@google.com> L: linux-kernel@vger.kernel.org L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/proc/proc_sysctl.c F: include/linux/sysctl.h F: kernel/sysctl.c +F: kernel/sysctl-test.c F: tools/testing/selftests/sysctl/ PS3 NETWORK SUPPORT @@ -15292,7 +15322,6 @@ F: arch/arm/boot/dts/spear* F: arch/arm/mach-spear/ SPI NOR SUBSYSTEM -M: Marek Vasut <marek.vasut@gmail.com> M: Tudor Ambarus <tudor.ambarus@microchip.com> L: linux-mtd@lists.infradead.org W: http://www.linux-mtd.infradead.org/ @@ -16589,10 +16618,9 @@ F: drivers/media/pci/tw686x/ UBI FILE SYSTEM (UBIFS) M: Richard Weinberger <richard@nod.at> -M: Artem Bityutskiy <dedekind1@gmail.com> -M: Adrian Hunter <adrian.hunter@intel.com> L: linux-mtd@lists.infradead.org -T: git git://git.infradead.org/ubifs-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git fixes W: http://www.linux-mtd.infradead.org/doc/ubifs.html S: Supported F: Documentation/filesystems/ubifs.txt @@ -16707,11 +16735,11 @@ S: Maintained F: drivers/scsi/ufs/ufs-mediatek* UNSORTED BLOCK IMAGES (UBI) -M: Artem Bityutskiy <dedekind1@gmail.com> M: Richard Weinberger <richard@nod.at> W: http://www.linux-mtd.infradead.org/ L: linux-mtd@lists.infradead.org -T: git git://git.infradead.org/ubifs-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git fixes S: Supported F: drivers/mtd/ubi/ F: include/linux/mtd/ubi.h @@ -17213,6 +17241,7 @@ F: virt/lib/ VIRTIO AND VHOST VSOCK DRIVER M: Stefan Hajnoczi <stefanha@redhat.com> +M: Stefano Garzarella <sgarzare@redhat.com> L: kvm@vger.kernel.org L: virtualization@lists.linux-foundation.org L: netdev@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -917,6 +917,9 @@ ifeq ($(CONFIG_RELR),y) LDFLAGS_vmlinux += --pack-dyn-relocs=relr endif +# make the checker run with the right architecture +CHECKFLAGS += --arch=$(ARCH) + # insure the checker run with the right endianness CHECKFLAGS += $(if $(CONFIG_CPU_BIG_ENDIAN),-mbig-endian,-mlittle-endian) diff --git a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi index 2a6ce87071f9..9e027b9a5f91 100644 --- a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi +++ b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi @@ -328,6 +328,10 @@ pinctrl-0 = <&pinctrl_pwm3>; }; +&snvs_pwrkey { + status = "okay"; +}; + &ssi2 { status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index f3404dd10537..cf628465cd0a 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -230,6 +230,8 @@ accelerometer@1c { compatible = "fsl,mma8451"; reg = <0x1c>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_mma8451_int>; interrupt-parent = <&gpio6>; interrupts = <31 IRQ_TYPE_LEVEL_LOW>; }; @@ -628,6 +630,12 @@ >; }; + pinctrl_mma8451_int: mma8451intgrp { + fsl,pins = < + MX6QDL_PAD_EIM_BCLK__GPIO6_IO31 0xb0b1 + >; + }; + pinctrl_pwm3: pwm1grp { fsl,pins = < MX6QDL_PAD_SD4_DAT1__PWM3_OUT 0x1b0b1 diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index 89d29b50c3f4..91fc0a315c49 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -183,14 +183,12 @@ ov5640: camera@3c { compatible = "ovti,ov5640"; - pinctrl-names = "default"; - pinctrl-0 = <&ov5640_pins>; reg = <0x3c>; clocks = <&clk_ext_camera>; clock-names = "xclk"; DOVDD-supply = <&v2v8>; - powerdown-gpios = <&stmfx_pinctrl 18 GPIO_ACTIVE_HIGH>; - reset-gpios = <&stmfx_pinctrl 19 GPIO_ACTIVE_LOW>; + powerdown-gpios = <&stmfx_pinctrl 18 (GPIO_ACTIVE_HIGH | GPIO_PUSH_PULL)>; + reset-gpios = <&stmfx_pinctrl 19 (GPIO_ACTIVE_LOW | GPIO_PUSH_PULL)>; rotation = <180>; status = "okay"; @@ -223,15 +221,8 @@ joystick_pins: joystick { pins = "gpio0", "gpio1", "gpio2", "gpio3", "gpio4"; - drive-push-pull; bias-pull-down; }; - - ov5640_pins: camera { - pins = "agpio2", "agpio3"; /* stmfx pins 18 & 19 */ - drive-push-pull; - output-low; - }; }; }; }; diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi index 9b11654a0a39..f98e0370c0bc 100644 --- a/arch/arm/boot/dts/stm32mp157c.dtsi +++ b/arch/arm/boot/dts/stm32mp157c.dtsi @@ -932,7 +932,7 @@ interrupt-names = "int0", "int1"; clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>; clock-names = "hclk", "cclk"; - bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>; + bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>; status = "disabled"; }; @@ -945,7 +945,7 @@ interrupt-names = "int0", "int1"; clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>; clock-names = "hclk", "cclk"; - bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>; + bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts index 568b90ece342..3bec3e0a81b2 100644 --- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts +++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts @@ -192,6 +192,7 @@ vqmmc-supply = <®_dldo1>; non-removable; wakeup-source; + keep-power-in-suspend; status = "okay"; brcmf: wifi@1 { diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index 239084cf8192..26cbce135338 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -481,14 +481,18 @@ static void sunxi_mc_smp_cpu_die(unsigned int l_cpu) static int sunxi_cpu_powerdown(unsigned int cpu, unsigned int cluster) { u32 reg; + int gating_bit = cpu; pr_debug("%s: cluster %u cpu %u\n", __func__, cluster, cpu); if (cpu >= SUNXI_CPUS_PER_CLUSTER || cluster >= SUNXI_NR_CLUSTERS) return -EINVAL; + if (is_a83t && cpu == 0) + gating_bit = 4; + /* gate processor power */ reg = readl(prcm_base + PRCM_PWROFF_GATING_REG(cluster)); - reg |= PRCM_PWROFF_GATING_REG_CORE(cpu); + reg |= PRCM_PWROFF_GATING_REG_CORE(gating_bit); writel(reg, prcm_base + PRCM_PWROFF_GATING_REG(cluster)); udelay(20); diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 9a07916af8dd..54d87506d3b5 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/arm-smccc.h> #include <linux/kernel.h> -#include <linux/psci.h> #include <linux/smp.h> #include <asm/cp15.h> @@ -75,11 +74,8 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A72: { struct arm_smccc_res res; - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - break; - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) @@ -90,7 +86,7 @@ static void cpu_v7_spectre_init(void) spectre_v2_method = "hypervisor"; break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3f047afb982c..d66a9727344d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -143,6 +143,8 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_REGS \ + if $(cc-option,-fpatchable-function-entry=2) select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD @@ -266,6 +268,10 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y +config ZONE_DMA + bool "Support DMA zone" if EXPERT + default y + config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y @@ -538,6 +544,16 @@ config ARM64_ERRATUM_1286807 invalidated has been observed by other observers. The workaround repeats the TLBI+DSB operation. +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 + 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 @@ -558,6 +574,22 @@ config ARM64_ERRATUM_1463225 If unsure, say Y. +config ARM64_ERRATUM_1542419 + bool "Neoverse-N1: workaround mis-ordering of instruction fetches" + default y + help + This option adds a workaround for ARM Neoverse-N1 erratum + 1542419. + + Affected Neoverse-N1 cores could execute a stale instruction when + modified by another CPU. The workaround depends on a firmware + counterpart. + + Workaround the issue by hiding the DIC feature from EL0. This + forces user-space to perform cache maintenance. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -845,10 +877,26 @@ config ARM64_PA_BITS default 48 if ARM64_PA_BITS_48 default 52 if ARM64_PA_BITS_52 +choice + prompt "Endianness" + default CPU_LITTLE_ENDIAN + help + Select the endianness of data accesses performed by the CPU. Userspace + applications will need to be compiled and linked for the endianness + that is selected here. + config CPU_BIG_ENDIAN bool "Build big-endian kernel" help - Say Y if you plan on running a kernel in big-endian mode. + Say Y if you plan on running a kernel with a big-endian userspace. + +config CPU_LITTLE_ENDIAN + bool "Build little-endian kernel" + help + Say Y if you plan on running a kernel with a little-endian userspace. + This is usually the case for distributions targeting arm64. + +endchoice config SCHED_MC bool "Multi-core scheduler support" @@ -1597,6 +1645,7 @@ config CMDLINE config CMDLINE_FORCE bool "Always use the default kernel command string" + depends on CMDLINE != "" help Always use the default kernel command string, even if the boot loader passes other arguments to the kernel. diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2c0238ce0551..1fbe24d4fdb6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -95,6 +95,11 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) KBUILD_LDS_MODULE += $(srctree)/arch/arm64/kernel/module.lds endif +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=2 +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts index d98346da01df..078a5010228c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts @@ -127,7 +127,7 @@ status = "okay"; i2c-mux@77 { - compatible = "nxp,pca9847"; + compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index 58b8cd06cae7..23c8fad7932b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -394,7 +394,7 @@ }; sdma2: dma-controller@302c0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x302c0000 0x10000>; interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA2_ROOT>, @@ -405,7 +405,7 @@ }; sdma3: dma-controller@302b0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x302b0000 0x10000>; interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA3_ROOT>, @@ -737,7 +737,7 @@ }; sdma1: dma-controller@30bd0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>, diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 98496f570720..43c4db312146 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -288,7 +288,7 @@ }; sdma3: dma-controller@302b0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x302b0000 0x10000>; interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA3_ROOT>, @@ -299,7 +299,7 @@ }; sdma2: dma-controller@302c0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x302c0000 0x10000>; interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA2_ROOT>, @@ -612,7 +612,7 @@ }; sdma1: dma-controller@30bd0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi index 087b5b6ebe89..32ce14936b01 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi @@ -88,7 +88,7 @@ regulator-name = "0V9_ARM"; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1000000>; - gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>; + gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>; states = <1000000 0x1 900000 0x0>; regulator-always-on; diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index 5bf963830b17..f68a0e64482a 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -58,29 +58,4 @@ alternative_else_nop_endif .endm #endif -/* - * These macros are no-ops when UAO is present. - */ - .macro uaccess_disable_not_uao, tmp1, tmp2 - uaccess_ttbr0_disable \tmp1, \tmp2 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(1) -alternative_else_nop_endif - .endm - - .macro uaccess_enable_not_uao, tmp1, tmp2, tmp3 - uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(0) -alternative_else_nop_endif - .endm - -/* - * Remove the address tag from a virtual address, if present. - */ - .macro untagged_addr, dst, addr - sbfx \dst, \addr, #0, #56 - and \dst, \dst, \addr - .endm - #endif diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index e0e2b1946f42..7d9cc5ec4971 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -29,6 +29,18 @@ SB_BARRIER_INSN"nop\n", \ ARM64_HAS_SB)) +#ifdef CONFIG_ARM64_PSEUDO_NMI +#define pmr_sync() \ + do { \ + extern struct static_key_false gic_pmr_sync; \ + \ + if (static_branch_unlikely(&gic_pmr_sync)) \ + dsb(sy); \ + } while(0) +#else +#define pmr_sync() do {} while (0) +#endif + #define mb() dsb(sy) #define rmb() dsb(ld) #define wmb() dsb(st) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 43da6dd29592..806e9dc2a852 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -11,6 +11,7 @@ #define CTR_L1IP_MASK 3 #define CTR_DMINLINE_SHIFT 16 #define CTR_IMINLINE_SHIFT 0 +#define CTR_IMINLINE_MASK 0xf #define CTR_ERG_SHIFT 20 #define CTR_CWG_SHIFT 24 #define CTR_CWG_MASK 15 @@ -18,7 +19,7 @@ #define CTR_DIC_SHIFT 29 #define CTR_CACHE_MINLINE_MASK \ - (0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT) + (0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT) #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index ac1dbca3d0cd..b92683871119 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -54,7 +54,9 @@ #define ARM64_WORKAROUND_1463225 44 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 +#define ARM64_WORKAROUND_1542419 47 +#define ARM64_WORKAROUND_1319367 48 -#define ARM64_NCAPS 47 +#define ARM64_NCAPS 49 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 9cde5d2e768f..4261d55e8506 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -659,6 +659,20 @@ static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) default: return CONFIG_ARM64_PA_BITS; } } + +/* Check whether hardware update of the Access flag is supported */ +static inline bool cpu_has_hw_af(void) +{ + u64 mmfr1; + + if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) + return false; + + mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + return cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_HADBS_SHIFT); +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 063c964af705..72acd2db167f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -8,7 +8,9 @@ #include <linux/irqflags.h> #include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/ptrace.h> #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ PSR_I_BIT @@ -65,7 +67,7 @@ static inline void local_daif_restore(unsigned long flags) if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); - dsb(sy); + pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; @@ -109,4 +111,19 @@ static inline void local_daif_restore(unsigned long flags) trace_hardirqs_off(); } +/* + * Called by synchronous exception handlers to restore the DAIF bits that were + * modified by taking an exception. + */ +static inline void local_daif_inherit(struct pt_regs *regs) +{ + unsigned long flags = regs->pstate & DAIF_MASK; + + /* + * We can't use local_daif_restore(regs->pstate) here as + * system_has_prio_mask_debugging() won't restore the I bit if it can + * use the pmr instead. + */ + write_sysreg(flags, daif); +} #endif diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index a17393ff6677..4d5f3b5f50cd 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -8,14 +8,15 @@ #define __ASM_EXCEPTION_H #include <asm/esr.h> +#include <asm/kprobes.h> +#include <asm/ptrace.h> #include <linux/interrupt.h> -#define __exception __attribute__((section(".exception.text"))) #ifdef CONFIG_FUNCTION_GRAPH_TRACER #define __exception_irq_entry __irq_entry #else -#define __exception_irq_entry __exception +#define __exception_irq_entry __kprobes #endif static inline u32 disr_to_esr(u64 disr) @@ -31,5 +32,22 @@ 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_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_undefinstr(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); +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); +void do_sve_acc(unsigned int esr, struct pt_regs *regs); +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); +void do_sysinstr(unsigned int esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); +void do_cp15instr(unsigned int esr, struct pt_regs *regs); +void el0_svc_handler(struct pt_regs *regs); +void el0_svc_compat_handler(struct pt_regs *regs); +void do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, + struct pt_regs *regs); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index d48667b04c41..91fa4baa1a93 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -11,9 +11,20 @@ #include <asm/insn.h> #define HAVE_FUNCTION_GRAPH_FP_TEST + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#else #define MCOUNT_ADDR ((unsigned long)_mcount) +#endif + +/* The BL at the callsite's adjusted rec->ip */ #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE +#define FTRACE_PLT_IDX 0 +#define FTRACE_REGS_PLT_IDX 1 +#define NR_FTRACE_PLTS 2 + /* * Currently, gcc tends to save the link register after the local variables * on the stack. This causes the max stack tracer to report the function @@ -44,12 +55,24 @@ extern void return_to_handler(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* + * Adjust addr to point at the BL in the callsite. + * See ftrace_init_nop() for the callsite sequence. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return addr + AARCH64_INSN_SIZE; + /* * addr is the address of the mcount call instruction. * recordmcount does the necessary offset calculation. */ return addr; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #define ftrace_return_address(n) return_address(n) /* diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 39e7780bedd6..bb313dde58a4 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -440,6 +440,9 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type); +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant); u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type, enum aarch64_insn_variant variant, enum aarch64_insn_register Rn, diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 1a59f0ed1ae3..aa4b6521ef14 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -6,6 +6,7 @@ #define __ASM_IRQFLAGS_H #include <asm/alternative.h> +#include <asm/barrier.h> #include <asm/ptrace.h> #include <asm/sysreg.h> @@ -34,14 +35,14 @@ static inline void arch_local_irq_enable(void) } asm volatile(ALTERNATIVE( - "msr daifclr, #2 // arch_local_irq_enable\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", + "msr daifclr, #2 // arch_local_irq_enable", + __msr_s(SYS_ICC_PMR_EL1, "%0"), ARM64_HAS_IRQ_PRIO_MASKING) : : "r" ((unsigned long) GIC_PRIO_IRQON) : "memory"); + + pmr_sync(); } static inline void arch_local_irq_disable(void) @@ -116,14 +117,14 @@ static inline unsigned long arch_local_irq_save(void) static inline void arch_local_irq_restore(unsigned long flags) { asm volatile(ALTERNATIVE( - "msr daif, %0\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", - ARM64_HAS_IRQ_PRIO_MASKING) + "msr daif, %0", + __msr_s(SYS_ICC_PMR_EL1, "%0"), + ARM64_HAS_IRQ_PRIO_MASKING) : : "r" (flags) : "memory"); + + pmr_sync(); } #endif /* __ASM_IRQFLAGS_H */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f656169db8c3..5ecb091c8576 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -600,8 +600,7 @@ static inline void kvm_arm_vhe_guest_enter(void) * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ - if (system_uses_irq_prio_masking()) - dsb(sy); + pmr_sync(); } static inline void kvm_arm_vhe_guest_exit(void) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index c23c47360664..a4f9ca5479b0 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -69,12 +69,6 @@ #define KERNEL_START _text #define KERNEL_END _end -#ifdef CONFIG_ARM64_VA_BITS_52 -#define MAX_USER_VA_BITS 52 -#else -#define MAX_USER_VA_BITS VA_BITS -#endif - /* * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual * address space for the shadow region respectively. They can bloat the stack diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index f80e13cbf8ec..1e93de68c044 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -21,7 +21,7 @@ struct mod_arch_specific { struct mod_plt_sec init; /* for CONFIG_DYNAMIC_FTRACE */ - struct plt_entry *ftrace_trampoline; + struct plt_entry *ftrace_trampolines; }; #endif diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 3df60f97da1f..d9fbd433cc17 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -69,7 +69,7 @@ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT)) +#define PTRS_PER_PGD (1 << (VA_BITS - PGDIR_SHIFT)) /* * Section address mask and size definitions. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 8330810f699e..5d15b4735a0e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -17,7 +17,7 @@ * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space - * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space + * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space * and fixed mappings */ #define VMALLOC_START (MODULES_END) @@ -283,23 +283,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } -#define __HAVE_ARCH_PTE_SAME -static inline int pte_same(pte_t pte_a, pte_t pte_b) -{ - pteval_t lhs, rhs; - - lhs = pte_val(pte_a); - rhs = pte_val(pte_b); - - if (pte_present(pte_a)) - lhs &= ~PTE_RDONLY; - - if (pte_present(pte_b)) - rhs &= ~PTE_RDONLY; - - return (lhs == rhs); -} - /* * Huge pte definitions. */ @@ -882,6 +865,20 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define phys_to_ttbr(addr) (addr) #endif +/* + * On arm64 without hardware Access Flag, copying from user will fail because + * the pte is old and cannot be marked young. So we always end up with zeroed + * page after fork() + CoW for pfn mappings. We don't always have a + * hardware-managed access flag on arm64. + */ +static inline bool arch_faults_on_old_pte(void) +{ + WARN_ON(preemptible()); + + return !cpu_has_hw_af(); +} +#define arch_faults_on_old_pte arch_faults_on_old_pte + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5623685c7d13..5ba63204d078 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -9,7 +9,7 @@ #define __ASM_PROCESSOR_H #define KERNEL_DS UL(-1) -#define USER_DS ((UL(1) << MAX_USER_VA_BITS) - 1) +#define USER_DS ((UL(1) << VA_BITS) - 1) /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is @@ -26,10 +26,12 @@ #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> +#include <linux/thread_info.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> +#include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> @@ -214,6 +216,18 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, regs->sp = sp; } +static inline bool is_ttbr0_addr(unsigned long addr) +{ + /* entry assembly clears tags for TTBR0 addrs */ + return addr < TASK_SIZE; +} + +static inline bool is_ttbr1_addr(unsigned long addr) +{ + /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ + return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; +} + #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index 06d880b3526c..b383b4802a7b 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -66,24 +66,18 @@ struct pt_regs; } \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused); \ ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused) -#endif -#ifndef COND_SYSCALL #define COND_SYSCALL(name) \ asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs) \ { \ return sys_ni_syscall(); \ } -#endif -#ifndef SYS_NI #define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers); -#endif #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 59690613ac31..cee5928e1b7d 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -42,16 +42,6 @@ static inline int __in_irqentry_text(unsigned long ptr) ptr < (unsigned long)&__irqentry_text_end; } -static inline int in_exception_text(unsigned long ptr) -{ - int in; - - in = ptr >= (unsigned long)&__exception_text_start && - ptr < (unsigned long)&__exception_text_end; - - return in ? : __in_irqentry_text(ptr); -} - static inline int in_entry_text(unsigned long ptr) { return ptr >= (unsigned long)&__entry_text_start && diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 097d6bfac0b7..127712b0b970 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -378,20 +378,34 @@ do { \ extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); #define raw_copy_from_user(to, from, n) \ ({ \ - __arch_copy_from_user((to), __uaccess_mask_ptr(from), (n)); \ + unsigned long __acfu_ret; \ + uaccess_enable_not_uao(); \ + __acfu_ret = __arch_copy_from_user((to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __acfu_ret; \ }) extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); #define raw_copy_to_user(to, from, n) \ ({ \ - __arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n)); \ + unsigned long __actu_ret; \ + uaccess_enable_not_uao(); \ + __actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to), \ + (from), (n)); \ + uaccess_disable_not_uao(); \ + __actu_ret; \ }) extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n); #define raw_copy_in_user(to, from, n) \ ({ \ - __arch_copy_in_user(__uaccess_mask_ptr(to), \ - __uaccess_mask_ptr(from), (n)); \ + unsigned long __aciu_ret; \ + uaccess_enable_not_uao(); \ + __aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __aciu_ret; \ }) #define INLINE_COPY_TO_USER @@ -400,8 +414,11 @@ extern unsigned long __must_check __arch_copy_in_user(void __user *to, const voi extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n); static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { - if (access_ok(to, n)) + if (access_ok(to, n)) { + uaccess_enable_not_uao(); n = __arch_clear_user(__uaccess_mask_ptr(to), n); + uaccess_disable_not_uao(); + } return n; } #define clear_user __clear_user diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h index 0c731bfc7c8c..0c20a7c1bee5 100644 --- a/arch/arm64/include/asm/vdso/vsyscall.h +++ b/arch/arm64/include/asm/vdso/vsyscall.h @@ -31,13 +31,6 @@ int __arm64_get_clock_mode(struct timekeeper *tk) #define __arch_get_clock_mode __arm64_get_clock_mode static __always_inline -int __arm64_use_vsyscall(struct vdso_data *vdata) -{ - return !vdata[CS_HRES_COARSE].clock_mode; -} -#define __arch_use_vsyscall __arm64_use_vsyscall - -static __always_inline void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk) { vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK; diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 478491f07b4f..fc6488660f64 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -13,9 +13,9 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) # Object file lists. obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ - entry-fpsimd.o process.o ptrace.o setup.o signal.o \ - sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o cpu_ops.o insn.o \ + entry-common.o entry-fpsimd.o process.o ptrace.o \ + setup.o signal.o sys.o stacktrace.o time.o traps.o \ + io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 214685760e1c..a5bdce8af65b 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -56,6 +56,7 @@ int main(void) DEFINE(S_X24, offsetof(struct pt_regs, regs[24])); DEFINE(S_X26, offsetof(struct pt_regs, regs[26])); DEFINE(S_X28, offsetof(struct pt_regs, regs[28])); + DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 93f34b4eca25..bbdc95ee4642 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -6,7 +6,6 @@ */ #include <linux/arm-smccc.h> -#include <linux/psci.h> #include <linux/types.h> #include <linux/cpu.h> #include <asm/cpu.h> @@ -88,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, } static void -cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused) +cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap) { u64 mask = arm64_ftr_reg_ctrel0.strict_mask; + bool enable_uct_trap = false; /* Trap CTR_EL0 access on this CPU, only if it has a mismatch */ if ((read_cpuid_cachetype() & mask) != (arm64_ftr_reg_ctrel0.sys_val & mask)) + enable_uct_trap = true; + + /* ... or if the system is affected by an erratum */ + if (cap->capability == ARM64_WORKAROUND_1542419) + enable_uct_trap = true; + + if (enable_uct_trap) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); } @@ -167,9 +174,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, } #endif /* CONFIG_KVM_INDIRECT_VECTORS */ -#include <uapi/linux/psci.h> #include <linux/arm-smccc.h> -#include <linux/psci.h> static void call_smc_arch_workaround_1(void) { @@ -213,11 +218,8 @@ static int detect_harden_bp_fw(void) struct arm_smccc_res res; u32 midr = read_cpuid_id(); - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - return -1; - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); switch ((int)res.a0) { @@ -235,7 +237,7 @@ static int detect_harden_bp_fw(void) } break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); switch ((int)res.a0) { @@ -309,11 +311,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt, BUG_ON(nr_inst != 1); - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: insn = aarch64_insn_get_hvc_value(); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: insn = aarch64_insn_get_smc_value(); break; default: @@ -352,12 +354,12 @@ void arm64_set_ssbd_mitigation(bool state) return; } - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); break; @@ -391,20 +393,13 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, goto out_printmsg; } - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { - ssbd_state = ARM64_SSBD_UNKNOWN; - if (!this_cpu_safe) - __ssb_safe = false; - return false; - } - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_2, &res); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_2, &res); break; @@ -650,9 +645,21 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry, return false; } -#ifdef CONFIG_HARDEN_EL2_VECTORS +static bool __maybe_unused +has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT); + const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && has_dic; +} -static const struct midr_range arm64_harden_el2_vectors[] = { +#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367) + +static const struct midr_range ca57_a72[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), {}, @@ -881,7 +888,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "EL2 vector hardening", .capability = ARM64_HARDEN_EL2_VECTORS, - ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors), + ERRATA_MIDR_RANGE_LIST(ca57_a72), }, #endif { @@ -927,6 +934,23 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1542419 + { + /* we depend on the firmware portion for correctness */ + .desc = "ARM erratum 1542419 (kernel portion)", + .capability = ARM64_WORKAROUND_1542419, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_neoverse_n1_erratum_1542419, + .cpu_enable = cpu_enable_trap_ctr_access, + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1319367 + { + .desc = "ARM erratum 1319367", + .capability = ARM64_WORKAROUND_1319367, + ERRATA_MIDR_RANGE_LIST(ca57_a72), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 80f459ad0190..04cf64e9f0c9 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -982,6 +982,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), { /* sentinel */ } }; char const *str = "kpti command line option"; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 05933c065732..56bba746da1c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -329,7 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_cntfrq = arch_timer_get_cntfrq(); /* * Use the effective value of the CTR_EL0 than the raw value - * exposed by the CPU. CTR_E0.IDC field value must be interpreted + * exposed by the CPU. CTR_EL0.IDC field value must be interpreted * with the CLIDR_EL1 fields to avoid triggering false warnings * when there is a mismatch across the CPUs. Keep track of the * effective value of the CTR_EL0 in our internal records for diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c new file mode 100644 index 000000000000..5dce5e56995a --- /dev/null +++ b/arch/arm64/kernel/entry-common.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Exception handling code + * + * Copyright (C) 2019 ARM Ltd. + */ + +#include <linux/context_tracking.h> +#include <linux/ptrace.h> +#include <linux/thread_info.h> + +#include <asm/cpufeature.h> +#include <asm/daifflags.h> +#include <asm/esr.h> +#include <asm/exception.h> +#include <asm/kprobes.h> +#include <asm/mmu.h> +#include <asm/sysreg.h> + +static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_abort); + +static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_pc); + +static void el1_undef(struct pt_regs *regs) +{ + local_daif_inherit(regs); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el1_undef); + +static void el1_inv(struct pt_regs *regs, unsigned long esr) +{ + local_daif_inherit(regs); + bad_mode(regs, 0, esr); +} +NOKPROBE_SYMBOL(el1_inv); + +static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * The CPU masked interrupts, and we are leaving them masked during + * do_debug_exception(). Update PMR as if we had called + * local_mask_daif(). + */ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + do_debug_exception(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_dbg); + +asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_DABT_CUR: + case ESR_ELx_EC_IABT_CUR: + el1_abort(regs, esr); + break; + /* + * We don't handle ESR_ELx_EC_SP_ALIGN, since we will have hit a + * recursive exception when trying to push the initial pt_regs. + */ + case ESR_ELx_EC_PC_ALIGN: + el1_pc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_UNKNOWN: + el1_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_CUR: + case ESR_ELx_EC_SOFTSTP_CUR: + case ESR_ELx_EC_WATCHPT_CUR: + case ESR_ELx_EC_BRK64: + el1_dbg(regs, esr); + break; + default: + el1_inv(regs, esr); + }; +} +NOKPROBE_SYMBOL(el1_sync_handler); + +static void notrace el0_da(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_da); + +static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * We've taken an instruction abort from userspace and not yet + * re-enabled IRQs. If the address is a kernel address, apply + * BP hardening prior to enabling IRQs and pre-emption. + */ + if (!is_ttbr0_addr(far)) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_ia); + +static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_acc); + +static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sve_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_sve_acc); + +static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_exc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_exc); + +static void notrace el0_sys(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sysinstr(esr, regs); +} +NOKPROBE_SYMBOL(el0_sys); + +static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + if (!is_ttbr0_addr(instruction_pointer(regs))) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_pc); + +static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX_NOIRQ); + do_sp_pc_abort(regs->sp, esr, regs); +} +NOKPROBE_SYMBOL(el0_sp); + +static void notrace el0_undef(struct pt_regs *regs) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el0_undef); + +static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + bad_el0_sync(regs, 0, esr); +} +NOKPROBE_SYMBOL(el0_inv); + +static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) +{ + /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ + unsigned long far = read_sysreg(far_el1); + + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + user_exit_irqoff(); + do_debug_exception(far, esr, regs); + local_daif_restore(DAIF_PROCCTX_NOIRQ); +} +NOKPROBE_SYMBOL(el0_dbg); + +static void notrace el0_svc(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc); + +asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC64: + el0_svc(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_SVE: + el0_sve_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC64: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_WFx: + el0_sys(regs, esr); + break; + case ESR_ELx_EC_SP_ALIGN: + el0_sp(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + el0_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BRK64: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_handler); + +#ifdef CONFIG_COMPAT +static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_cp15instr(esr, regs); +} +NOKPROBE_SYMBOL(el0_cp15); + +static void notrace el0_svc_compat(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_compat_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc_compat); + +asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC32: + el0_svc_compat(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC32: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + case ESR_ELx_EC_CP14_MR: + case ESR_ELx_EC_CP14_LS: + case ESR_ELx_EC_CP14_64: + el0_undef(regs); + break; + case ESR_ELx_EC_CP15_32: + case ESR_ELx_EC_CP15_64: + el0_cp15(regs, esr); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BKPT32: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_compat_handler); +#endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 33d003d80121..4fe1514fcbfd 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,10 +7,137 @@ */ #include <linux/linkage.h> +#include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/ftrace.h> #include <asm/insn.h> +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +/* + * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before + * the regular function prologue. For an enabled callsite, ftrace_init_nop() and + * ftrace_make_call() have patched those NOPs to: + * + * MOV X9, LR + * BL <entry> + * + * ... 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. + * + * 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 + * for the callsite and the ftrace entry assembly. This is not sufficient for + * reliable stacktrace: until we create the callsite stack record, its caller + * is missing from the LR and existing chain of frame records. + */ + .macro ftrace_regs_entry, allregs=0 + /* Make room for pt_regs, plus a callee frame */ + sub sp, sp, #(S_FRAME_SIZE + 16) + + /* Save function arguments (and x9 for simplicity) */ + stp x0, x1, [sp, #S_X0] + stp x2, x3, [sp, #S_X2] + stp x4, x5, [sp, #S_X4] + stp x6, x7, [sp, #S_X6] + stp x8, x9, [sp, #S_X8] + + /* Optionally save the callee-saved registers, always save the FP */ + .if \allregs == 1 + stp x10, x11, [sp, #S_X10] + stp x12, x13, [sp, #S_X12] + stp x14, x15, [sp, #S_X14] + stp x16, x17, [sp, #S_X16] + stp x18, x19, [sp, #S_X18] + stp x20, x21, [sp, #S_X20] + stp x22, x23, [sp, #S_X22] + stp x24, x25, [sp, #S_X24] + stp x26, x27, [sp, #S_X26] + stp x28, x29, [sp, #S_X28] + .else + str x29, [sp, #S_FP] + .endif + + /* Save the callsite's SP and LR */ + add x10, sp, #(S_FRAME_SIZE + 16) + stp x9, x10, [sp, #S_LR] + + /* Save the PC after the ftrace callsite */ + str x30, [sp, #S_PC] + + /* Create a frame record for the callsite above pt_regs */ + stp x29, x9, [sp, #S_FRAME_SIZE] + add x29, sp, #S_FRAME_SIZE + + /* Create our frame record within pt_regs. */ + stp x29, x30, [sp, #S_STACKFRAME] + add x29, sp, #S_STACKFRAME + .endm + +ENTRY(ftrace_regs_caller) + ftrace_regs_entry 1 + b ftrace_common +ENDPROC(ftrace_regs_caller) + +ENTRY(ftrace_caller) + ftrace_regs_entry 0 + b ftrace_common +ENDPROC(ftrace_caller) + +ENTRY(ftrace_common) + sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + mov x1, x9 // parent_ip (callsite's LR) + ldr_l x2, function_trace_op // op + mov x3, sp // regs + +GLOBAL(ftrace_call) + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); + nop // If enabled, this will be replaced + // "b ftrace_graph_caller" +#endif + +/* + * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved + * x19-x29 per the AAPCS, and we created frame records upon entry, so we need + * to restore x0-x8, x29, and x30. + */ +ftrace_common_return: + /* Restore function arguments */ + ldp x0, x1, [sp] + ldp x2, x3, [sp, #S_X2] + ldp x4, x5, [sp, #S_X4] + ldp x6, x7, [sp, #S_X6] + ldr x8, [sp, #S_X8] + + /* Restore the callsite's FP, LR, PC */ + ldr x29, [sp, #S_FP] + ldr x30, [sp, #S_LR] + ldr x9, [sp, #S_PC] + + /* Restore the callsite's SP */ + add sp, sp, #S_FRAME_SIZE + 16 + + ret x9 +ENDPROC(ftrace_common) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + ldr x0, [sp, #S_PC] + sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + add x1, sp, #S_LR // parent_ip (callsite's LR) + ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + bl prepare_ftrace_return + b ftrace_common_return +ENDPROC(ftrace_graph_caller) +#else +#endif + +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + /* * Gcc with -pg will put the following code in the beginning of each function: * mov x0, x30 @@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); mcount_exit ENDPROC(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE */ - -ENTRY(ftrace_stub) - ret -ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller) mcount_exit ENDPROC(ftrace_graph_caller) +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +ENTRY(ftrace_stub) + ret +ENDPROC(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * void return_to_handler(void) * diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index cf3bd2976e57..583f71abbe98 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -269,8 +269,10 @@ alternative_else_nop_endif alternative_if ARM64_HAS_IRQ_PRIO_MASKING ldr x20, [sp, #S_PMR_SAVE] msr_s SYS_ICC_PMR_EL1, x20 - /* Ensure priority change is seen by redistributor */ - dsb sy + mrs_s x21, SYS_ICC_CTLR_EL1 + tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE + dsb sy // Ensure priority change is seen by redistributor +.L__skip_pmr_sync\@: alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR @@ -578,76 +580,9 @@ ENDPROC(el1_error_invalid) .align 6 el1_sync: kernel_entry 1 - mrs x1, esr_el1 // read the syndrome register - lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 - b.eq el1_da - cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 - b.eq el1_ia - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - b.eq el1_undef - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el1_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1 - b.eq el1_undef - cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 - b.ge el1_dbg - b el1_inv - -el1_ia: - /* - * Fall through to the Data abort case - */ -el1_da: - /* - * Data abort handling - */ - mrs x3, far_el1 - inherit_daif pstate=x23, tmp=x2 - untagged_addr x0, x3 - mov x2, sp // struct pt_regs - bl do_mem_abort - - kernel_exit 1 -el1_pc: - /* - * PC alignment exception handling. We don't handle SP alignment faults, - * since we will have hit a recursive exception when trying to push the - * initial pt_regs. - */ - mrs x0, far_el1 - inherit_daif pstate=x23, tmp=x2 - mov x2, sp - bl do_sp_pc_abort - ASM_BUG() -el1_undef: - /* - * Undefined instruction - */ - inherit_daif pstate=x23, tmp=x2 mov x0, sp - bl do_undefinstr + bl el1_sync_handler kernel_exit 1 -el1_dbg: - /* - * Debug exception handling - */ - cmp x24, #ESR_ELx_EC_BRK64 // if BRK64 - cinc x24, x24, eq // set bit '0' - tbz x24, #0, el1_inv // EL1 only - gic_prio_kentry_setup tmp=x3 - mrs x0, far_el1 - mov x2, sp // struct pt_regs - bl do_debug_exception - kernel_exit 1 -el1_inv: - // TODO: add support for undefined instructions in kernel mode - inherit_daif pstate=x23, tmp=x2 - mov x0, sp - mov x2, x1 - mov x1, #BAD_SYNC - bl bad_mode - ASM_BUG() ENDPROC(el1_sync) .align 6 @@ -714,71 +649,18 @@ ENDPROC(el1_irq) .align 6 el0_sync: kernel_entry 0 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC64 // SVC in 64-bit state - b.eq el0_svc - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_SVE // SVE access - b.eq el0_sve_acc - cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - ccmp x24, #ESR_ELx_EC_WFx, #4, ne - b.eq el0_sys - cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el0_sp - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv + mov x0, sp + bl el0_sync_handler + b ret_to_user #ifdef CONFIG_COMPAT .align 6 el0_sync_compat: kernel_entry 0, 32 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC32 // SVC in 32-bit state - b.eq el0_svc_compat - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP15_64 // CP15 MRRC/MCRR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP14_MR // CP14 MRC/MCR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_LS // CP14 LDC/STC trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_64 // CP14 MRRC/MCRR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv -el0_svc_compat: - gic_prio_kentry_setup tmp=x1 mov x0, sp - bl el0_svc_compat_handler + bl el0_sync_compat_handler b ret_to_user +ENDPROC(el0_sync) .align 6 el0_irq_compat: @@ -788,139 +670,7 @@ el0_irq_compat: el0_error_compat: kernel_entry 0, 32 b el0_error_naked - -el0_cp15: - /* - * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_cp15instr - b ret_to_user -#endif - -el0_da: - /* - * Data abort handling - */ - mrs x26, far_el1 - ct_user_exit_irqoff - enable_daif - untagged_addr x0, x26 - mov x1, x25 - mov x2, sp - bl do_mem_abort - b ret_to_user -el0_ia: - /* - * Instruction abort handling - */ - mrs x26, far_el1 - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_el0_ia_bp_hardening - b ret_to_user -el0_fpsimd_acc: - /* - * Floating Point or Advanced SIMD access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_acc - b ret_to_user -el0_sve_acc: - /* - * Scalable Vector Extension access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sve_acc - b ret_to_user -el0_fpsimd_exc: - /* - * Floating Point, Advanced SIMD or SVE exception - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_exc - b ret_to_user -el0_sp: - ldr x26, [sp, #S_SP] - b el0_sp_pc -el0_pc: - mrs x26, far_el1 -el0_sp_pc: - /* - * Stack or PC alignment exception handling - */ - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off #endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_sp_pc_abort - b ret_to_user -el0_undef: - /* - * Undefined instruction - */ - ct_user_exit_irqoff - enable_daif - mov x0, sp - bl do_undefinstr - b ret_to_user -el0_sys: - /* - * System instructions, for trapped cache maintenance instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sysinstr - b ret_to_user -el0_dbg: - /* - * Debug exception handling - */ - tbnz x24, #0, el0_inv // EL0 only - mrs x24, far_el1 - gic_prio_kentry_setup tmp=x3 - ct_user_exit_irqoff - mov x0, x24 - mov x1, x25 - mov x2, sp - bl do_debug_exception - enable_da_f - b ret_to_user -el0_inv: - ct_user_exit_irqoff - enable_daif - mov x0, sp - mov x1, #BAD_SYNC - mov x2, x25 - bl bad_el0_sync - b ret_to_user -ENDPROC(el0_sync) .align 6 el0_irq: @@ -999,17 +749,6 @@ finish_ret_to_user: kernel_exit 0 ENDPROC(ret_to_user) -/* - * SVC handler. - */ - .align 6 -el0_svc: - gic_prio_kentry_setup tmp=x1 - mov x0, sp - bl el0_svc_handler - b ret_to_user -ENDPROC(el0_svc) - .popsection // .entry.text #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 37d3912cfe06..3eb338f14386 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -920,7 +920,7 @@ void fpsimd_release_task(struct task_struct *dead_task) * would have disabled the SVE access trap for userspace during * ret_to_user, making an SVE access trap impossible in that case. */ -asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) +void do_sve_acc(unsigned int esr, struct pt_regs *regs) { /* Even if we chose not to use SVE, the hardware could still trap: */ if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { @@ -947,7 +947,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) /* * Trapped FP/ASIMD access. */ -asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) { /* TODO: implement lazy context saving/restoring */ WARN_ON(1); @@ -956,7 +956,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) /* * Raise a SIGFPE for the current process. */ -asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) { unsigned int si_code = FPE_FLTUNK; diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 06e56b470315..8618faa82e6d 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(pc, 0, new, false); } +static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) +{ +#ifdef CONFIG_ARM64_MODULE_PLTS + struct plt_entry *plt = mod->arch.ftrace_trampolines; + + if (addr == FTRACE_ADDR) + return &plt[FTRACE_PLT_IDX]; + if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS)) + return &plt[FTRACE_REGS_PLT_IDX]; +#endif + return NULL; +} + /* * Turn on the call to ftrace_caller() in instrumented function */ @@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline, *dst; struct module *mod; + struct plt_entry *plt; + + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; /* * On kernels that support module PLTs, the offset between the @@ -93,49 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (WARN_ON(!mod)) return -EINVAL; - /* - * There is only one ftrace trampoline per module. For now, - * this is not a problem since on arm64, all dynamic ftrace - * invocations are routed via ftrace_caller(). This will need - * to be revisited if support for multiple ftrace entry points - * is added in the future, but for now, the pr_err() below - * deals with a theoretical issue only. - * - * Note that PLTs are place relative, and plt_entries_equal() - * checks whether they point to the same target. Here, we need - * to check if the actual opcodes are in fact identical, - * regardless of the offset in memory so use memcmp() instead. - */ - dst = mod->arch.ftrace_trampoline; - trampoline = get_plt_entry(addr, dst); - if (memcmp(dst, &trampoline, sizeof(trampoline))) { - if (plt_entry_is_initialized(dst)) { - pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); - return -EINVAL; - } - - /* point the trampoline to our ftrace entry point */ - module_disable_ro(mod); - *dst = trampoline; - module_enable_ro(mod, true); - - /* - * Ensure updated trampoline is visible to instruction - * fetch before we patch in the branch. Although the - * architecture doesn't require an IPI in this case, - * Neoverse-N1 erratum #1542419 does require one - * if the TLB maintenance in module_enable_ro() is - * skipped due to rodata_enabled. It doesn't seem worth - * it to make it conditional given that this is - * certainly not a fast-path. - */ - flush_icache_range((unsigned long)&dst[0], - (unsigned long)&dst[1]); + plt = get_ftrace_plt(mod, addr); + if (!plt) { + pr_err("ftrace: no module PLT for %ps\n", (void *)addr); + return -EINVAL; } - addr = (unsigned long)dst; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ + + addr = (unsigned long)plt; } old = aarch64_insn_gen_nop(); @@ -144,6 +123,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + old = aarch64_insn_gen_branch_imm(pc, old_addr, + AARCH64_INSN_BRANCH_LINK); + new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); + + return ftrace_modify_code(pc, old, new, true); +} + +/* + * The compiler has inserted two NOPs before the regular function prologue. + * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live, + * and x9-x18 are free for our use. + * + * At runtime we want to be able to swing a single NOP <-> BL to enable or + * disable the ftrace call. The BL requires us to save the original LR value, + * so here we insert a <MOV X9, LR> over the first NOP so the instructions + * before the regular prologue are: + * + * | Compiled | Disabled | Enabled | + * +----------+------------+------------+ + * | NOP | MOV X9, LR | MOV X9, LR | + * | NOP | NOP | BL <entry> | + * + * The LR value will be recovered by ftrace_regs_entry, and restored into LR + * before returning to the regular function prologue. When a function is not + * being traced, the MOV is not harmful given x9 is not live per the AAPCS. + * + * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of + * the BL. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + unsigned long pc = rec->ip - AARCH64_INSN_SIZE; + u32 old, new; + + old = aarch64_insn_gen_nop(); + new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9, + AARCH64_INSN_REG_LR, + AARCH64_INSN_VARIANT_64BIT); + return ftrace_modify_code(pc, old, new, true); +} +#endif + /* * Turn off the call to ftrace_caller() in instrumented function */ @@ -156,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS u32 replaced; + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; + /* * 'mod' is only set at module load time, but if we end up * dealing with an out-of-range condition, we can assume it @@ -189,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return -EINVAL; validate = false; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ } else { old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index d801a7094076..513b29c3e735 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } +/* + * MOV (register) is architecturally an alias of ORR (shifted register) where + * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m> + */ +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant) +{ + return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR, + src, 0, variant, + AARCH64_INSN_LOGIC_ORR); +} + u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, enum aarch64_insn_adr_type type) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 416f537bf614..2a11a962e571 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -19,6 +19,14 @@ #include <asm/pgtable.h> #include <asm/sections.h> +enum kaslr_status { + KASLR_ENABLED, + KASLR_DISABLED_CMDLINE, + KASLR_DISABLED_NO_SEED, + KASLR_DISABLED_FDT_REMAP, +}; + +static enum kaslr_status __initdata kaslr_status; u64 __ro_after_init module_alloc_base; u16 __initdata memstart_offset_seed; @@ -91,15 +99,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ early_fixmap_init(); fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); - if (!fdt) + if (!fdt) { + kaslr_status = KASLR_DISABLED_FDT_REMAP; return 0; + } /* * Retrieve (and wipe) the seed from the FDT */ seed = get_kaslr_seed(fdt); - if (!seed) - return 0; /* * Check if 'nokaslr' appears on the command line, and @@ -107,8 +115,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ cmdline = kaslr_get_cmdline(fdt); str = strstr(cmdline, "nokaslr"); - if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) + if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) { + kaslr_status = KASLR_DISABLED_CMDLINE; + return 0; + } + + if (!seed) { + kaslr_status = KASLR_DISABLED_NO_SEED; return 0; + } /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable @@ -170,3 +185,24 @@ u64 __init kaslr_early_init(u64 dt_phys) return offset; } + +static int __init kaslr_init(void) +{ + switch (kaslr_status) { + case KASLR_ENABLED: + pr_info("KASLR enabled\n"); + break; + case KASLR_DISABLED_CMDLINE: + pr_info("KASLR disabled on command line\n"); + break; + case KASLR_DISABLED_NO_SEED: + pr_warn("KASLR disabled due to lack of seed\n"); + break; + case KASLR_DISABLED_FDT_REMAP: + pr_warn("KASLR disabled due to FDT remapping failure\n"); + break; + } + + return 0; +} +core_initcall(kaslr_init) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index b182442b87a3..65b08a74aec6 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -4,6 +4,7 @@ */ #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sort.h> @@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, tramp->sh_type = SHT_NOBITS; tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; tramp->sh_addralign = __alignof__(struct plt_entry); - tramp->sh_size = sizeof(struct plt_entry); + tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); } return 0; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 03ff15bffbb6..1cd1a4d0ed30 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -9,6 +9,7 @@ #include <linux/bitops.h> #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/gfp.h> #include <linux/kasan.h> #include <linux/kernel.h> @@ -470,22 +471,58 @@ overflow: return -ENOEXEC; } -int module_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *me) +static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) { const Elf_Shdr *s, *se; const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { - if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) - apply_alternatives_module((void *)s->sh_addr, s->sh_size); -#ifdef CONFIG_ARM64_MODULE_PLTS - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name)) - me->arch.ftrace_trampoline = (void *)s->sh_addr; -#endif + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; } + return NULL; +} + +static inline void __init_plt(struct plt_entry *plt, unsigned long addr) +{ + *plt = get_plt_entry(addr, plt); +} + +static int module_init_ftrace_plt(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) +{ +#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE) + const Elf_Shdr *s; + struct plt_entry *plts; + + s = find_section(hdr, sechdrs, ".text.ftrace_trampoline"); + if (!s) + return -ENOEXEC; + + plts = (void *)s->sh_addr; + + __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + __init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR); + + mod->arch.ftrace_trampolines = plts; +#endif return 0; } + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + s = find_section(hdr, sechdrs, ".altinstructions"); + if (s) + apply_alternatives_module((void *)s->sh_addr, s->sh_size); + + return module_init_ftrace_plt(hdr, sechdrs, me); +} diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index a0b4f1bca491..e40b65645c86 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -158,133 +158,74 @@ armv8pmu_events_sysfs_show(struct device *dev, return sprintf(page, "event=0x%03llx\n", pmu_attr->id); } -#define ARMV8_EVENT_ATTR(name, config) \ - PMU_EVENT_ATTR(name, armv8_event_attr_##name, \ - config, armv8pmu_events_sysfs_show) - -ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR); -ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL); -ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE); -ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL); -ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED); -ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED); -ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED); -ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN); -ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN); -ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED); -ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED); -ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED); -ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED); -ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED); -ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES); -ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED); -ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS); -ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE); -ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE); -ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB); -ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS); -ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR); -ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC); -ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED); -ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES); -/* Don't expose the chain event in /sys, since it's useless in isolation */ -ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED); -ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND); -ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND); -ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB); -ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB); -ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE); -ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE); -ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL); -ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL); -ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB); -ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB); -ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS); -ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE); -ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS); -ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK); -ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK); -ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD); -ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD); -ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD); -ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP); -ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED); -ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE); -ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION); +#define ARMV8_EVENT_ATTR(name, config) \ + (&((struct perf_pmu_events_attr) { \ + .attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL), \ + .id = config, \ + }).attr.attr) static struct attribute *armv8_pmuv3_event_attrs[] = { - &armv8_event_attr_sw_incr.attr.attr, - &armv8_event_attr_l1i_cache_refill.attr.attr, - &armv8_event_attr_l1i_tlb_refill.attr.attr, - &armv8_event_attr_l1d_cache_refill.attr.attr, - &armv8_event_attr_l1d_cache.attr.attr, - &armv8_event_attr_l1d_tlb_refill.attr.attr, - &armv8_event_attr_ld_retired.attr.attr, - &armv8_event_attr_st_retired.attr.attr, - &armv8_event_attr_inst_retired.attr.attr, - &armv8_event_attr_exc_taken.attr.attr, - &armv8_event_attr_exc_return.attr.attr, - &armv8_event_attr_cid_write_retired.attr.attr, - &armv8_event_attr_pc_write_retired.attr.attr, - &armv8_event_attr_br_immed_retired.attr.attr, - &armv8_event_attr_br_return_retired.attr.attr, - &armv8_event_attr_unaligned_ldst_retired.attr.attr, - &armv8_event_attr_br_mis_pred.attr.attr, - &armv8_event_attr_cpu_cycles.attr.attr, - &armv8_event_attr_br_pred.attr.attr, - &armv8_event_attr_mem_access.attr.attr, - &armv8_event_attr_l1i_cache.attr.attr, - &armv8_event_attr_l1d_cache_wb.attr.attr, - &armv8_event_attr_l2d_cache.attr.attr, - &armv8_event_attr_l2d_cache_refill.attr.attr, - &armv8_event_attr_l2d_cache_wb.attr.attr, - &armv8_event_attr_bus_access.attr.attr, - &armv8_event_attr_memory_error.attr.attr, - &armv8_event_attr_inst_spec.attr.attr, - &armv8_event_attr_ttbr_write_retired.attr.attr, - &armv8_event_attr_bus_cycles.attr.attr, - &armv8_event_attr_l1d_cache_allocate.attr.attr, - &armv8_event_attr_l2d_cache_allocate.attr.attr, - &armv8_event_attr_br_retired.attr.attr, - &armv8_event_attr_br_mis_pred_retired.attr.attr, - &armv8_event_attr_stall_frontend.attr.attr, - &armv8_event_attr_stall_backend.attr.attr, - &armv8_event_attr_l1d_tlb.attr.attr, - &armv8_event_attr_l1i_tlb.attr.attr, - &armv8_event_attr_l2i_cache.attr.attr, - &armv8_event_attr_l2i_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache_allocate.attr.attr, - &armv8_event_attr_l3d_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache.attr.attr, - &armv8_event_attr_l3d_cache_wb.attr.attr, - &armv8_event_attr_l2d_tlb_refill.attr.attr, - &armv8_event_attr_l2i_tlb_refill.attr.attr, - &armv8_event_attr_l2d_tlb.attr.attr, - &armv8_event_attr_l2i_tlb.attr.attr, - &armv8_event_attr_remote_access.attr.attr, - &armv8_event_attr_ll_cache.attr.attr, - &armv8_event_attr_ll_cache_miss.attr.attr, - &armv8_event_attr_dtlb_walk.attr.attr, - &armv8_event_attr_itlb_walk.attr.attr, - &armv8_event_attr_ll_cache_rd.attr.attr, - &armv8_event_attr_ll_cache_miss_rd.attr.attr, - &armv8_event_attr_remote_access_rd.attr.attr, - &armv8_event_attr_sample_pop.attr.attr, - &armv8_event_attr_sample_feed.attr.attr, - &armv8_event_attr_sample_filtrate.attr.attr, - &armv8_event_attr_sample_collision.attr.attr, + ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), + ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), + ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE), + ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL), + ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED), + ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED), + ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED), + ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN), + ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN), + ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED), + ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED), + ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED), + ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED), + ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED), + ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES), + ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED), + ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS), + ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE), + ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE), + ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB), + ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS), + ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR), + ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC), + ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED), + ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES), + /* Don't expose the chain event in /sys, since it's useless in isolation */ + ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED), + ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND), + ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND), + ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB), + ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB), + ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE), + ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE), + ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL), + ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL), + ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB), + ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB), + ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS), + ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE), + ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS), + ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK), + ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK), + ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD), + ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD), + ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD), + ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP), + ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED), + ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE), + ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION), NULL, }; diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index c4452827419b..d1c95dcf1d78 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -455,10 +455,6 @@ int __init arch_populate_kprobe_blacklist(void) (unsigned long)__irqentry_text_end); if (ret) return ret; - ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start, - (unsigned long)__exception_text_end); - if (ret) - return ret; ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start, (unsigned long)__idmap_text_end); if (ret) diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index c9f72b2665f1..43ae4e0c968f 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu) static int cpu_psci_cpu_kill(unsigned int cpu) { - int err, i; + int err; + unsigned long start, end; if (!psci_ops.affinity_info) return 0; @@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu) * while it is dying. So, try again a few times. */ - for (i = 0; i < 10; i++) { + start = jiffies; + end = start + msecs_to_jiffies(100); + do { err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { - pr_info("CPU%d killed.\n", cpu); + pr_info("CPU%d killed (polled %d ms)\n", cpu, + jiffies_to_msecs(jiffies - start)); return 0; } - msleep(10); - pr_info("Retrying again to check for CPU kill\n"); - } + usleep_range(100, 1000); + } while (time_before(jiffies, end)); pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", cpu, err); diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index ea94cf8f9dc6..d6259dac62b6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -2,6 +2,7 @@ // Copyright (C) 2017 Arm Ltd. #define pr_fmt(fmt) "sdei: " fmt +#include <linux/arm-smccc.h> #include <linux/arm_sdei.h> #include <linux/hardirq.h> #include <linux/irqflags.h> @@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit) return 0; } - sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; + sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 if (arm64_kernel_unmapped_at_el0()) { diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index f1cb64959427..3c18c2454089 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -8,6 +8,7 @@ */ #include <linux/compat.h> +#include <linux/cpufeature.h> #include <linux/personality.h> #include <linux/sched.h> #include <linux/sched/signal.h> @@ -17,6 +18,7 @@ #include <asm/cacheflush.h> #include <asm/system_misc.h> +#include <asm/tlbflush.h> #include <asm/unistd.h> static long @@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end) if (fatal_signal_pending(current)) return 0; + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* + * The workaround requires an inner-shareable tlbi. + * We pick the reserved-ASID to minimise the impact. + */ + __tlbi(aside1is, __TLBI_VADDR(0, 0)); + dsb(ish); + } + ret = __flush_cache_user_range(start, start + chunk); if (ret) return ret; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 871c739f060a..9a9d98a443fc 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -154,14 +154,14 @@ static inline void sve_user_discard(void) sve_user_disable(); } -asmlinkage void el0_svc_handler(struct pt_regs *regs) +void el0_svc_handler(struct pt_regs *regs) { sve_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } #ifdef CONFIG_COMPAT -asmlinkage void el0_svc_compat_handler(struct pt_regs *regs) +void el0_svc_compat_handler(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls, compat_sys_call_table); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 34739e80211b..73caf35c2262 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -35,6 +35,7 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/insn.h> +#include <asm/kprobes.h> #include <asm/traps.h> #include <asm/smp.h> #include <asm/stack_pointer.h> @@ -393,7 +394,7 @@ void arm64_notify_segfault(unsigned long addr) force_signal_inject(SIGSEGV, code, addr); } -asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +void do_undefinstr(struct pt_regs *regs) { /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) @@ -405,6 +406,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) BUG_ON(!user_mode(regs)); force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc); } +NOKPROBE_SYMBOL(do_undefinstr); #define __user_cache_maint(insn, address, res) \ if (address >= user_addr_max()) { \ @@ -470,6 +472,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) int rt = ESR_ELx_SYS64_ISS_RT(esr); unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* Hide DIC so that we can trap the unnecessary maintenance...*/ + val &= ~BIT(CTR_DIC_SHIFT); + + /* ... and fake IminLine to reduce the number of traps. */ + val &= ~CTR_IMINLINE_MASK; + val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK; + } + pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); @@ -667,7 +678,7 @@ static const struct sys64_hook cp15_64_hooks[] = { {}, }; -asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) +void do_cp15instr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook, *hook_base; @@ -705,9 +716,10 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_cp15instr); #endif -asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +void do_sysinstr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook; @@ -724,6 +736,7 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_sysinstr); static const char *esr_class_str[] = { [0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC", @@ -793,7 +806,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) * bad_el0_sync handles unexpected, but potentially recoverable synchronous * exceptions taken from EL0. Unlike bad_mode, this returns. */ -asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) { void __user *pc = (void __user *)instruction_pointer(regs); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index aa76f7259668..009057517bdd 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -111,9 +111,6 @@ SECTIONS } .text : { /* Real text segment */ _stext = .; /* Text and read-only data */ - __exception_text_start = .; - *(.exception.text) - __exception_text_end = .; IRQENTRY_TEXT SOFTIRQENTRY_TEXT ENTRY_TEXT diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 799e84a40335..72fbbd86eb5e 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -12,7 +12,7 @@ #include <kvm/arm_psci.h> -#include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> @@ -118,6 +118,20 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) } write_sysreg(val, cptr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; + + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * configured and enabled. We can now restore the guest's S1 + * configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } } static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) @@ -159,6 +173,23 @@ static void __hyp_text __deactivate_traps_nvhe(void) { u64 mdcr_el2 = read_sysreg(mdcr_el2); + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * Set the TCR and SCTLR registers in the exact opposite + * sequence as __activate_traps_nvhe (first prevent walks, + * then force the MMU on). A generous sprinkling of isb() + * ensure that things happen in this exact order. + */ + val = read_sysreg_el1(SYS_TCR); + write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR); + isb(); + val = read_sysreg_el1(SYS_SCTLR); + write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR); + isb(); + } + __deactivate_traps_common(); mdcr_el2 &= MDCR_EL2_HPMN_MASK; @@ -657,7 +688,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) */ if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - dsb(sy); + pmr_sync(); } vcpu = kern_hyp_va(vcpu); @@ -670,18 +701,23 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_save_state_nvhe(host_ctxt); - __activate_vm(kern_hyp_va(vcpu->kvm)); - __activate_traps(vcpu); - - __hyp_vgic_restore_state(vcpu); - __timer_enable_traps(vcpu); - /* * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + * + * Also, and in order to be able to deal with erratum #1319537 (A57) + * and #1319367 (A72), we must ensure that all VM-related sysreg are + * restored before we enable S2 translation. */ __sysreg32_restore_state(vcpu); __sysreg_restore_state_nvhe(guest_ctxt); + + __activate_vm(kern_hyp_va(vcpu->kvm)); + __activate_traps(vcpu); + + __hyp_vgic_restore_state(vcpu); + __timer_enable_traps(vcpu); + __debug_switch_to_guest(vcpu); __set_guest_arch_workaround_state(vcpu); diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 7ddbc849b580..22b8128d19f6 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -117,12 +117,26 @@ 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); - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + + if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + 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) { + /* + * Must only be done for guest registers, hence the context + * test. We're coming from the host, so SCTLR.M is already + * set. Pairs with __activate_traps_nvhe(). + */ + write_sysreg_el1((ctxt->sys_regs[TCR_EL1] | + TCR_EPD1_MASK | TCR_EPD0_MASK), + SYS_TCR); + isb(); + } + write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR); write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0); write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR); write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0); write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1); @@ -135,6 +149,23 @@ 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_const_cap(ARM64_WORKAROUND_1319367) && + ctxt->__hyp_running_vcpu) { + /* + * Must only be done for host registers, hence the context + * test. Pairs with __deactivate_traps_nvhe(). + */ + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * deconfigured and disabled. We can now restore the host's + * S1 configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } + write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR); write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR); diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index eb0efc5557f3..c2bc17ca6430 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -63,6 +63,22 @@ 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_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * For CPUs that are affected by ARM 1319367, we need to + * avoid a host Stage-1 walk while we have the guest's + * VMID set in the VTTBR in order to invalidate TLBs. + * We're guaranteed that the S1 MMU is enabled, so we can + * simply set the EPD bits to avoid any further TLB fill. + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + isb(); + } + __load_guest_stage2(kvm); isb(); } @@ -100,6 +116,13 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { write_sysreg(0, vttbr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + /* Ensure write of the host VMID */ + isb(); + /* Restore the host's TCR_EL1 */ + write_sysreg_el1(cxt->tcr, SYS_TCR); + } } static void __hyp_text __tlb_switch_to_host(struct kvm *kvm, diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 10415572e82f..aeafc03e961a 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -20,7 +20,6 @@ * Alignment fixed up by hardware. */ ENTRY(__arch_clear_user) - uaccess_enable_not_uao x2, x3, x4 mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f @@ -40,7 +39,6 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2 b.mi 5f uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 - uaccess_disable_not_uao x2, x3 ret ENDPROC(__arch_clear_user) EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 680e74409ff9..ebb3c06cbb5d 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -54,10 +54,8 @@ end .req x5 ENTRY(__arch_copy_from_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 // Nothing to copy ret ENDPROC(__arch_copy_from_user) diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 0bedae3f3792..3d8153a1ebce 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -56,10 +56,8 @@ end .req x5 ENTRY(__arch_copy_in_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_in_user) diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 2d88c736e8f2..357eae2c18eb 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -53,10 +53,8 @@ end .req x5 ENTRY(__arch_copy_to_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_to_user) diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c index cbfcbe6470a5..bfa30b75b2b8 100644 --- a/arch/arm64/lib/uaccess_flushcache.c +++ b/arch/arm64/lib/uaccess_flushcache.c @@ -28,7 +28,11 @@ void memcpy_page_flushcache(char *to, struct page *page, size_t offset, unsigned long __copy_user_flushcache(void *to, const void __user *from, unsigned long n) { - unsigned long rc = __arch_copy_from_user(to, from, n); + unsigned long rc; + + uaccess_enable_not_uao(); + rc = __arch_copy_from_user(to, from, n); + uaccess_disable_not_uao(); /* See above */ __clean_dcache_area_pop(to, n - rc); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9fc6db0bcbad..077b02a2d4d3 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -32,7 +32,8 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> -#include <asm/kasan.h> +#include <asm/kprobes.h> +#include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/pgtable.h> @@ -101,18 +102,6 @@ static void mem_abort_decode(unsigned int esr) data_abort_decode(esr); } -static inline bool is_ttbr0_addr(unsigned long addr) -{ - /* entry assembly clears tags for TTBR0 addrs */ - return addr < TASK_SIZE; -} - -static inline bool is_ttbr1_addr(unsigned long addr) -{ - /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ - return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; -} - static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ @@ -318,6 +307,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; + else if (is_el1_instruction_abort(esr)) + msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { @@ -736,8 +727,7 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; -asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, - struct pt_regs *regs) +void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); @@ -753,43 +743,21 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, arm64_notify_die(inf->name, regs, inf->sig, inf->code, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_mem_abort); -asmlinkage void __exception do_el0_irq_bp_hardening(void) +void do_el0_irq_bp_hardening(void) { /* PC has already been checked in entry.S */ arm64_apply_bp_hardening(); } +NOKPROBE_SYMBOL(do_el0_irq_bp_hardening); -asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) -{ - /* - * We've taken an instruction abort from userspace and not yet - * re-enabled IRQs. If the address is a kernel address, apply - * BP hardening prior to enabling IRQs and pre-emption. - */ - if (!is_ttbr0_addr(addr)) - arm64_apply_bp_hardening(); - - local_daif_restore(DAIF_PROCCTX); - do_mem_abort(addr, esr, regs); -} - - -asmlinkage void __exception do_sp_pc_abort(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - if (user_mode(regs)) { - if (!is_ttbr0_addr(instruction_pointer(regs))) - arm64_apply_bp_hardening(); - local_daif_restore(DAIF_PROCCTX); - } - arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_sp_pc_abort); int __init early_brk64(unsigned long addr, unsigned int esr, struct pt_regs *regs); @@ -872,8 +840,7 @@ NOKPROBE_SYMBOL(debug_exception_exit); #ifdef CONFIG_ARM64_ERRATUM_1463225 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (user_mode(regs)) return 0; @@ -892,16 +859,15 @@ cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) return 1; } #else -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { return 0; } #endif /* CONFIG_ARM64_ERRATUM_1463225 */ +NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler); -asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, - unsigned int esr, - struct pt_regs *regs) +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, + struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 45c00a54909c..be9481cdf3b9 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -20,6 +20,7 @@ #include <linux/sort.h> #include <linux/of.h> #include <linux/of_fdt.h> +#include <linux/dma-direct.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/efi.h> @@ -41,6 +42,8 @@ #include <asm/tlb.h> #include <asm/alternative.h> +#define ARM64_ZONE_DMA_BITS 30 + /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() @@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset); struct page *vmemmap __ro_after_init; EXPORT_SYMBOL(vmemmap); +/* + * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of + * memory as some devices, namely the Raspberry Pi 4, have peripherals with + * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 + * bit addressable memory area. + */ phys_addr_t arm64_dma_phys_limit __ro_after_init; +static phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT, + crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void) { } #endif /* CONFIG_CRASH_DUMP */ + /* - * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It - * currently assumes that for memory starting above 4G, 32-bit devices will - * use a DMA offset. + * Return the maximum physical address for a zone with a given address size + * limit. It currently assumes that for memory starting above 4G, 32-bit + * devices will use a DMA offset. */ -static phys_addr_t __init max_zone_dma_phys(void) +static phys_addr_t __init max_zone_phys(unsigned int zone_bits) { - phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); - return min(offset + (1ULL << 32), memblock_end_of_DRAM()); + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits); + return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM()); } #ifdef CONFIG_NUMA @@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); +#endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys()); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); #endif max_zone_pfns[ZONE_NORMAL] = max; @@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { struct memblock_region *reg; unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; - unsigned long max_dma = min; + unsigned long max_dma32 = min; + unsigned long __maybe_unused max_dma = min; memset(zone_size, 0, sizeof(zone_size)); - /* 4GB maximum for 32-bit only capable devices */ -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA max_dma = PFN_DOWN(arm64_dma_phys_limit); - zone_size[ZONE_DMA32] = max_dma - min; + zone_size[ZONE_DMA] = max_dma - min; + max_dma32 = max_dma; +#endif +#ifdef CONFIG_ZONE_DMA32 + max_dma32 = PFN_DOWN(arm64_dma32_phys_limit); + zone_size[ZONE_DMA32] = max_dma32 - max_dma; #endif - zone_size[ZONE_NORMAL] = max - max_dma; + zone_size[ZONE_NORMAL] = max - max_dma32; memcpy(zhole_size, zone_size, sizeof(zhole_size)); @@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (start >= max) continue; - -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA if (start < max_dma) { - unsigned long dma_end = min(end, max_dma); - zhole_size[ZONE_DMA32] -= dma_end - start; + unsigned long dma_end = min_not_zero(end, max_dma); + zhole_size[ZONE_DMA] -= dma_end - start; } #endif - if (end > max_dma) { +#ifdef CONFIG_ZONE_DMA32 + if (start < max_dma32) { + unsigned long dma32_end = min(end, max_dma32); + unsigned long dma32_start = max(start, max_dma); + zhole_size[ZONE_DMA32] -= dma32_end - dma32_start; + } +#endif + if (end > max_dma32) { unsigned long normal_end = min(end, max); - unsigned long normal_start = max(start, max_dma); + unsigned long normal_start = max(start, max_dma32); zhole_size[ZONE_NORMAL] -= normal_end - normal_start; } } @@ -418,11 +443,15 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - /* 4GB maximum for 32-bit only capable devices */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) { + zone_dma_bits = ARM64_ZONE_DMA_BITS; + arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS); + } + if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma_phys_limit = max_zone_dma_phys(); + arm64_dma32_phys_limit = max_zone_phys(32); else - arm64_dma_phys_limit = PHYS_MASK + 1; + arm64_dma32_phys_limit = PHYS_MASK + 1; reserve_crashkernel(); @@ -430,7 +459,7 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - dma_contiguous_reserve(arm64_dma_phys_limit); + dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -534,7 +563,7 @@ static void __init free_unused_memmap(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; @@ -571,7 +600,7 @@ void free_initmem(void) { free_reserved_area(lm_alias(__init_begin), lm_alias(__init_end), - 0, "unused kernel"); + POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This * prevents the region from being reused for kernel modules, which @@ -580,18 +609,6 @@ void free_initmem(void) unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } -#ifdef CONFIG_BLK_DEV_INITRD -void __init free_initrd_mem(unsigned long start, unsigned long end) -{ - unsigned long aligned_start, aligned_end; - - aligned_start = __virt_to_phys(start) & PAGE_MASK; - aligned_end = PAGE_ALIGN(__virt_to_phys(end)); - memblock_free(aligned_start, aligned_end - aligned_start); - free_reserved_area((void *)start, (void *)end, 0, "initrd"); -} -#endif - /* * Dump out memory limit information on panic. */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 60c929f3683b..a9f541912289 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -338,7 +338,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys_addr_t (*pgtable_alloc)(int), int flags) { - unsigned long addr, length, end, next; + unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* @@ -350,9 +350,8 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys &= PAGE_MASK; addr = virt & PAGE_MASK; - length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); + end = PAGE_ALIGN(virt + size); - end = addr + length; do { next = pgd_addr_end(addr, end); alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c index 73bf5ea9ee1b..7ec3161e8517 100644 --- a/arch/m68k/atari/config.c +++ b/arch/m68k/atari/config.c @@ -869,8 +869,28 @@ static const struct resource atari_scsi_tt_rsrc[] __initconst = { }; #endif +/* + * Falcon IDE interface + */ + +#define FALCON_IDE_BASE 0xfff00000 + +static const struct resource atari_falconide_rsrc[] __initconst = { + { + .flags = IORESOURCE_MEM, + .start = FALCON_IDE_BASE, + .end = FALCON_IDE_BASE + 0x39, + }, + { + .flags = IORESOURCE_IRQ, + .start = IRQ_MFP_FSCSI, + .end = IRQ_MFP_FSCSI, + }, +}; + int __init atari_platform_init(void) { + struct platform_device *pdev; int rv = 0; if (!MACH_IS_ATARI) @@ -912,6 +932,13 @@ int __init atari_platform_init(void) atari_scsi_tt_rsrc, ARRAY_SIZE(atari_scsi_tt_rsrc)); #endif + if (ATARIHW_PRESENT(IDE)) { + pdev = platform_device_register_simple("atari-falcon-ide", -1, + atari_falconide_rsrc, ARRAY_SIZE(atari_falconide_rsrc)); + if (IS_ERR(pdev)) + rv = PTR_ERR(pdev); + } + return rv; } diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 9a33c1c006a1..619d30d663a2 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -355,6 +355,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -420,11 +421,15 @@ CONFIG_INPUT_M68K_BEEP=m # CONFIG_LEGACY_PTYS is not set CONFIG_PRINTER=m # CONFIG_HW_RANDOM is not set +CONFIG_I2C=m +CONFIG_I2C_CHARDEV=m +CONFIG_I2C_ICY=m CONFIG_NTP_PPS=y CONFIG_PPS_CLIENT_LDISC=m CONFIG_PPS_CLIENT_PARPORT=m CONFIG_PTP_1588_CLOCK=m -# CONFIG_HWMON is not set +CONFIG_HWMON=m +CONFIG_SENSORS_LTC2990=m CONFIG_FB=y CONFIG_FB_CIRRUS=y CONFIG_FB_AMIGA=y @@ -432,8 +437,6 @@ CONFIG_FB_AMIGA_OCS=y CONFIG_FB_AMIGA_ECS=y CONFIG_FB_AMIGA_AGA=y CONFIG_FB_FM2=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m @@ -490,6 +493,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -560,10 +564,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 7fdbc797a05d..caa0558abcdb 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -334,6 +334,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -393,8 +394,6 @@ CONFIG_PPS_CLIENT_LDISC=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_VGA16 is not set @@ -450,6 +449,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -520,10 +520,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index f1763405a539..2551c7e9ac54 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -350,6 +350,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -417,8 +418,6 @@ CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set CONFIG_FB=y CONFIG_FB_ATARI=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m @@ -472,6 +471,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -542,10 +542,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 91154d6acb31..4ffc1e5646d5 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -332,6 +332,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -390,8 +391,6 @@ CONFIG_NTP_PPS=y CONFIG_PPS_CLIENT_LDISC=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m @@ -443,6 +442,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -513,10 +513,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index c398c4a94d95..806da3d97ca4 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -333,6 +333,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -395,8 +396,6 @@ CONFIG_PPS_CLIENT_LDISC=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set @@ -452,6 +451,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -522,10 +522,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 350d004559be..250da20e291c 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -342,6 +342,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -419,8 +420,6 @@ CONFIG_PTP_1588_CLOCK=m CONFIG_FB=y CONFIG_FB_VALKYRIE=y CONFIG_FB_MAC=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_HID=m @@ -474,6 +473,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -544,10 +544,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index b838dd820348..b764a0368a56 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -386,6 +386,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -480,11 +481,15 @@ CONFIG_SERIAL_PMACZILOG_TTYS=y CONFIG_SERIAL_PMACZILOG_CONSOLE=y CONFIG_PRINTER=m # CONFIG_HW_RANDOM is not set +CONFIG_I2C=m +CONFIG_I2C_CHARDEV=m +CONFIG_I2C_ICY=m CONFIG_NTP_PPS=y CONFIG_PPS_CLIENT_LDISC=m CONFIG_PPS_CLIENT_PARPORT=m CONFIG_PTP_1588_CLOCK=m -# CONFIG_HWMON is not set +CONFIG_HWMON=m +CONFIG_SENSORS_LTC2990=m CONFIG_FB=y CONFIG_FB_CIRRUS=y CONFIG_FB_AMIGA=y @@ -495,8 +500,6 @@ CONFIG_FB_FM2=y CONFIG_FB_ATARI=y CONFIG_FB_VALKYRIE=y CONFIG_FB_MAC=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m @@ -556,6 +559,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -626,10 +630,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 3f8dd61559cf..7800d3a8d46e 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -331,6 +331,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -389,8 +390,6 @@ CONFIG_NTP_PPS=y CONFIG_PPS_CLIENT_LDISC=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m @@ -442,6 +441,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -512,10 +512,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index ae3b2d4f636c..c32dc2d2058d 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -332,6 +332,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -390,8 +391,6 @@ CONFIG_NTP_PPS=y CONFIG_PPS_CLIENT_LDISC=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m @@ -443,6 +442,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -513,10 +513,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index cd61ef14b582..bf0a65ce57e0 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -339,6 +339,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -404,8 +405,6 @@ CONFIG_PPS_CLIENT_PARPORT=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m @@ -461,6 +460,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -531,10 +531,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 151f5371cd3d..5f3cfa2926d2 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -329,6 +329,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -390,8 +391,6 @@ CONFIG_PPS_CLIENT_LDISC=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_HID=m @@ -445,6 +444,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -515,10 +515,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 1dcb0ee1fe98..58354d2018d5 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -329,6 +329,7 @@ CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m CONFIG_DM_ZERO=m @@ -389,8 +390,6 @@ CONFIG_PPS_CLIENT_LDISC=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_HID=m @@ -444,6 +443,7 @@ CONFIG_QNX4FS_FS=m CONFIG_QNX6FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m +CONFIG_EROFS_FS=m CONFIG_NFS_FS=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -514,10 +514,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index e63eb5f06999..f31890078197 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -264,6 +264,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll) { int tmp = Q40_RTC_CTRL; + pll->pll_ctrl = 0; pll->pll_value = tmp & Q40_RTC_PLL_MASK; if (tmp & Q40_RTC_PLL_SIGN) pll->pll_value = -pll->pll_value; diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index 0de839882106..a69b272a3ab0 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -17,6 +17,7 @@ platforms += jazz platforms += jz4740 platforms += lantiq platforms += lasat +platforms += loongson2ef platforms += loongson32 platforms += loongson64 platforms += mti-malta @@ -30,6 +31,7 @@ platforms += ralink platforms += rb532 platforms += sgi-ip22 platforms += sgi-ip27 +platforms += sgi-ip30 platforms += sgi-ip32 platforms += sibyte platforms += sni diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a0bd9bdb5f83..c86be02b6d89 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -7,6 +7,7 @@ config MIPS select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_FORTIFY_SOURCE select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if 64BIT @@ -86,6 +87,8 @@ config MIPS select SYSCTL_EXCEPTION_TRACE select VIRT_TO_BUS select ARCH_HAS_PTE_SPECIAL if !(32BIT && CPU_HAS_RIXI) + select ARCH_HAS_KCOV + select HAVE_GCC_PLUGINS menu "Machine selection" @@ -359,6 +362,8 @@ config MACH_DECSTATION config MACH_JAZZ bool "Jazz family of machines" + select ARC_MEMORY + select ARC_PROMLIB select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select FW_ARC @@ -441,7 +446,7 @@ config LASAT select SYS_SUPPORTS_LITTLE_ENDIAN config MACH_LOONGSON32 - bool "Loongson-1 family of machines" + bool "Loongson 32-bit family of machines" select SYS_SUPPORTS_ZBOOT help This enables support for the Loongson-1 family of machines. @@ -450,18 +455,48 @@ config MACH_LOONGSON32 the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). +config MACH_LOONGSON2EF + bool "Loongson-2E/F family of machines" + select SYS_SUPPORTS_ZBOOT + help + This enables the support of early Loongson-2E/F family of machines. + config MACH_LOONGSON64 - bool "Loongson-2/3 family of machines" + bool "Loongson 64-bit family of machines" + select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO + select GENERIC_ISA_DMA_SUPPORT_BROKEN + select BOOT_ELF32 + select BOARD_SCACHE + select CSRC_R4K + select CEVT_R4K + select CPU_HAS_WB + select FORCE_PCI + select ISA + select I8259 + select IRQ_MIPS_CPU + select NR_CPUS_DEFAULT_4 + select USE_GENERIC_EARLY_PRINTK_8250 + select SYS_HAS_CPU_LOONGSON64 + select SYS_HAS_EARLY_PRINTK + select SYS_SUPPORTS_SMP + select SYS_SUPPORTS_HOTPLUG_CPU + select SYS_SUPPORTS_NUMA + select SYS_SUPPORTS_64BIT_KERNEL + select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_ZBOOT + select LOONGSON_MC146818 + select ZONE_DMA32 + select NUMA help This enables the support of Loongson-2/3 family of machines. - Loongson-2 is a family of single-core CPUs and Loongson-3 is a - family of multi-core CPUs. They are both 64-bit general-purpose - MIPS-compatible CPUs. Loongson-2/3 are developed by the Institute - of Computing Technology (ICT), Chinese Academy of Sciences (CAS) - in the People's Republic of China. The chief architect is Professor - Weiwu Hu. + Loongson-2 and Loongson-3 are 64-bit general-purpose processors with + GS264/GS464/GS464E/GS464V microarchitecture (except old Loongson-2E + and Loongson-2F which will be removed), developed by the Institute + of Computing Technology (ICT), Chinese Academy of Sciences (CAS). config MACH_PISTACHIO bool "IMG Pistachio SoC based boards" @@ -631,6 +666,8 @@ config RALINK config SGI_IP22 bool "SGI IP22 (Indy/Indigo2)" + select ARC_MEMORY + select ARC_PROMLIB select FW_ARC select FW_ARC32 select ARCH_MIGHT_HAVE_PC_SERIO @@ -654,14 +691,7 @@ config SGI_IP22 select SWAP_IO_SPACE select SYS_HAS_CPU_R4X00 select SYS_HAS_CPU_R5000 - # - # Disable EARLY_PRINTK for now since it leads to overwritten prom - # memory during early boot on some machines. - # - # See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com - # for a more details discussion - # - # select SYS_HAS_EARLY_PRINTK + select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN @@ -674,8 +704,10 @@ config SGI_IP22 config SGI_IP27 bool "SGI IP27 (Origin200/2000)" select ARCH_HAS_PHYS_TO_DMA + select ARCH_SPARSEMEM_ENABLE select FW_ARC select FW_ARC64 + select ARC_CMDLINE_ONLY select BOOT_ELF64 select DEFAULT_SGI_PARTITION select SYS_HAS_EARLY_PRINTK @@ -698,6 +730,8 @@ config SGI_IP27 config SGI_IP28 bool "SGI IP28 (Indigo2 R10k)" + select ARC_MEMORY + select ARC_PROMLIB select FW_ARC select FW_ARC64 select ARCH_MIGHT_HAVE_PC_SERIO @@ -719,14 +753,7 @@ config SGI_IP28 select SGI_HAS_ZILOG select SWAP_IO_SPACE select SYS_HAS_CPU_R10000 - # - # Disable EARLY_PRINTK for now since it leads to overwritten prom - # memory during early boot on some machines. - # - # See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com - # for a more details discussion - # - # select SYS_HAS_EARLY_PRINTK + select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select MIPS_L1_CACHE_SHIFT_7 @@ -734,8 +761,37 @@ config SGI_IP28 This is the SGI Indigo2 with R10000 processor. To compile a Linux kernel that runs on these, say Y here. +config SGI_IP30 + bool "SGI IP30 (Octane/Octane2)" + select ARCH_HAS_PHYS_TO_DMA + select FW_ARC + select FW_ARC64 + select BOOT_ELF64 + select CEVT_R4K + select CSRC_R4K + select SYNC_R4K if SMP + select ZONE_DMA32 + select HAVE_PCI + select IRQ_MIPS_CPU + select IRQ_DOMAIN_HIERARCHY + select NR_CPUS_DEFAULT_2 + select PCI_DRIVERS_GENERIC + select PCI_XTALK_BRIDGE + select SYS_HAS_EARLY_PRINTK + select SYS_HAS_CPU_R10000 + select SYS_SUPPORTS_64BIT_KERNEL + select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_SMP + select MIPS_L1_CACHE_SHIFT_7 + select ARC_MEMORY + help + These are the SGI Octane and Octane2 graphics workstations. To + compile a Linux kernel that runs on these, say Y here. + config SGI_IP32 bool "SGI IP32 (O2)" + select ARC_MEMORY + select ARC_PROMLIB select ARCH_HAS_PHYS_TO_DMA select FW_ARC select FW_ARC32 @@ -843,6 +899,8 @@ config SIBYTE_BIGSUR config SNI_RM bool "SNI RM200/300/400" + select ARC_MEMORY + select ARC_PROMLIB select FW_ARC if CPU_LITTLE_ENDIAN select FW_ARC32 if CPU_LITTLE_ENDIAN select FW_SNIPROM if CPU_BIG_ENDIAN @@ -1038,6 +1096,7 @@ source "arch/mips/sibyte/Kconfig" source "arch/mips/txx9/Kconfig" source "arch/mips/vr41xx/Kconfig" source "arch/mips/cavium-octeon/Kconfig" +source "arch/mips/loongson2ef/Kconfig" source "arch/mips/loongson32/Kconfig" source "arch/mips/loongson64/Kconfig" source "arch/mips/netlogic/Kconfig" @@ -1353,19 +1412,18 @@ config MIPS_L1_CACHE_SHIFT config HAVE_STD_PC_SERIAL_PORT bool +config ARC_CMDLINE_ONLY + bool + config ARC_CONSOLE bool "ARC console support" depends on SGI_IP22 || SGI_IP28 || (SNI_RM && CPU_LITTLE_ENDIAN) config ARC_MEMORY bool - depends on MACH_JAZZ || SNI_RM || SGI_IP32 - default y config ARC_PROMLIB bool - depends on MACH_JAZZ || SNI_RM || SGI_IP22 || SGI_IP28 || SGI_IP32 - default y config FW_ARC64 bool @@ -1379,51 +1437,56 @@ choice prompt "CPU type" default CPU_R4X00 -config CPU_LOONGSON3 - bool "Loongson 3 CPU" - depends on SYS_HAS_CPU_LOONGSON3 +config CPU_LOONGSON64 + bool "Loongson 64-bit CPU" + depends on SYS_HAS_CPU_LOONGSON64 select ARCH_HAS_PHYS_TO_DMA select CPU_SUPPORTS_64BIT_KERNEL select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_HUGEPAGES + select CPU_SUPPORTS_MSA select CPU_HAS_LOAD_STORE_LR select WEAK_ORDERING select WEAK_REORDERING_BEYOND_LLSC + select MIPS_ASID_BITS_VARIABLE select MIPS_PGD_C0_CONTEXT select MIPS_L1_CACHE_SHIFT_6 select GPIOLIB select SWIOTLB help - The Loongson 3 processor implements the MIPS64R2 instruction - set with many extensions. + The Loongson GSx64(GS264/GS464/GS464E/GS464V) series of processor + cores implements the MIPS64R2 instruction set with many extensions, + including most 64-bit Loongson-2 (2H, 2K) and Loongson-3 (3A1000, + 3B1000, 3B1500, 3A2000, 3A3000 and 3A4000) processors. However, old + Loongson-2E/2F is not covered here and will be removed in future. config LOONGSON3_ENHANCEMENT - bool "New Loongson 3 CPU Enhancements" + bool "New Loongson-3 CPU Enhancements" default n select CPU_MIPSR2 select CPU_HAS_PREFETCH - depends on CPU_LOONGSON3 + depends on CPU_LOONGSON64 help - New Loongson 3 CPU (since Loongson-3A R2, as opposed to Loongson-3A + New Loongson-3 cores (since Loongson-3A R2, as opposed to Loongson-3A R1, Loongson-3B R1 and Loongson-3B R2) has many enhancements, such as - FTLB, L1-VCache, EI/DI/Wait/Prefetch instruction, DSP/DSPv2 ASE, User + FTLB, L1-VCache, EI/DI/Wait/Prefetch instruction, DSP/DSPr2 ASE, User Local register, Read-Inhibit/Execute-Inhibit, SFB (Store Fill Buffer), Fast TLB refill support, etc. This option enable those enhancements which are not probed at run time. If you want a generic kernel to run on all Loongson 3 machines, please say 'N' here. If you want a high-performance kernel to run on - new Loongson 3 machines only, please say 'Y' here. + new Loongson-3 machines only, please say 'Y' here. config CPU_LOONGSON3_WORKAROUNDS - bool "Old Loongson 3 LLSC Workarounds" + bool "Old Loongson-3 LLSC Workarounds" default y if SMP - depends on CPU_LOONGSON3 + depends on CPU_LOONGSON64 help - Loongson 3 processors have the llsc issues which require workarounds. + Loongson-3 processors have the llsc issues which require workarounds. Without workarounds the system may hang unexpectedly. - Newer Loongson 3 will fix these issues and no workarounds are needed. + Newer Loongson-3 will fix these issues and no workarounds are needed. The workarounds have no significant side effect on them but may decrease the performance of the system so this option should be disabled unless the kernel is intended to be run on old systems. @@ -1433,7 +1496,7 @@ config CPU_LOONGSON3_WORKAROUNDS config CPU_LOONGSON2E bool "Loongson 2E" depends on SYS_HAS_CPU_LOONGSON2E - select CPU_LOONGSON2 + select CPU_LOONGSON2EF help The Loongson 2E processor implements the MIPS III instruction set with many extensions. @@ -1444,7 +1507,7 @@ config CPU_LOONGSON2E config CPU_LOONGSON2F bool "Loongson 2F" depends on SYS_HAS_CPU_LOONGSON2F - select CPU_LOONGSON2 + select CPU_LOONGSON2EF select GPIOLIB help The Loongson 2F processor implements the MIPS III instruction set @@ -1457,7 +1520,7 @@ config CPU_LOONGSON2F config CPU_LOONGSON1B bool "Loongson 1B" depends on SYS_HAS_CPU_LOONGSON1B - select CPU_LOONGSON1 + select CPU_LOONGSON32 select LEDS_GPIO_REGISTER help The Loongson 1B is a 32-bit SoC, which implements the MIPS32 @@ -1467,7 +1530,7 @@ config CPU_LOONGSON1B config CPU_LOONGSON1C bool "Loongson 1C" depends on SYS_HAS_CPU_LOONGSON1C - select CPU_LOONGSON1 + select CPU_LOONGSON32 select LEDS_GPIO_REGISTER help The Loongson 1C is a 32-bit SoC, which implements the MIPS32 @@ -1857,7 +1920,7 @@ config SYS_SUPPORTS_ZBOOT_UART_PROM bool select SYS_SUPPORTS_ZBOOT -config CPU_LOONGSON2 +config CPU_LOONGSON2EF bool select CPU_SUPPORTS_32BIT_KERNEL select CPU_SUPPORTS_64BIT_KERNEL @@ -1866,7 +1929,7 @@ config CPU_LOONGSON2 select ARCH_HAS_PHYS_TO_DMA select CPU_HAS_LOAD_STORE_LR -config CPU_LOONGSON1 +config CPU_LOONGSON32 bool select CPU_MIPS32 select CPU_MIPSR2 @@ -1900,7 +1963,7 @@ config CPU_BMIPS5000 select SYS_SUPPORTS_HOTPLUG_CPU select CPU_HAS_RIXI -config SYS_HAS_CPU_LOONGSON3 +config SYS_HAS_CPU_LOONGSON64 bool select CPU_SUPPORTS_CPUFREQ select CPU_HAS_RIXI @@ -1912,7 +1975,6 @@ config SYS_HAS_CPU_LOONGSON2F bool select CPU_SUPPORTS_CPUFREQ select CPU_SUPPORTS_ADDRWINCFG if 64BIT - select CPU_SUPPORTS_UNCACHED_ACCELERATED config SYS_HAS_CPU_LOONGSON1B bool @@ -2089,8 +2151,6 @@ config CPU_SUPPORTS_ADDRWINCFG config CPU_SUPPORTS_HUGEPAGES bool depends on !(32BIT && (ARCH_PHYS_ADDR_T_64BIT || EVA)) -config CPU_SUPPORTS_UNCACHED_ACCELERATED - bool config MIPS_PGD_C0_CONTEXT bool default y if 64BIT && (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP @@ -2162,7 +2222,7 @@ choice config PAGE_SIZE_4KB bool "4kB" - depends on !CPU_LOONGSON2 && !CPU_LOONGSON3 + depends on !CPU_LOONGSON2EF && !CPU_LOONGSON64 help This option select the standard 4kB Linux page size. On some R3000-family processors this is the only available page size. Using @@ -2554,6 +2614,10 @@ config CPU_R4000_WORKAROUNDS config CPU_R4400_WORKAROUNDS bool +config CPU_R4X00_BUGS64 + bool + default y if SYS_HAS_CPU_R4X00 && 64BIT && (TARGET_ISA_REV < 1) + config MIPS_ASID_SHIFT int default 6 if CPU_R3000 || CPU_TX39XX @@ -2612,20 +2676,11 @@ config CPU_SUPPORTS_MSA config ARCH_FLATMEM_ENABLE def_bool y - depends on !NUMA && !CPU_LOONGSON2 - -config ARCH_DISCONTIGMEM_ENABLE - bool - default y if SGI_IP27 - help - Say Y to support efficient handling of discontiguous physical memory, - for architectures which are either NUMA (Non-Uniform Memory Access) - or have huge holes in the physical address space for other reasons. - See <file:Documentation/vm/numa.rst> for more. + depends on !NUMA && !CPU_LOONGSON2EF config ARCH_SPARSEMEM_ENABLE bool - select SPARSEMEM_STATIC + select SPARSEMEM_STATIC if !SGI_IP27 config NUMA bool "NUMA Support" @@ -2702,7 +2757,7 @@ config NODES_SHIFT config HW_PERF_EVENTS bool "Enable hardware performance counter support for perf events" - depends on PERF_EVENTS && !OPROFILE && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP || CPU_LOONGSON3) + depends on PERF_EVENTS && !OPROFILE && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP || CPU_LOONGSON64) default y help Enable hardware performance counter support for perf events. If diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug index 0c86b2a2adfc..93a2974d2ab7 100644 --- a/arch/mips/Kconfig.debug +++ b/arch/mips/Kconfig.debug @@ -32,7 +32,6 @@ config USE_GENERIC_EARLY_PRINTK_8250 config CMDLINE_BOOL bool "Built-in kernel command line" - default n help For most systems, it is firmware or second stage bootloader that by default specifies the kernel command line options. However, @@ -53,7 +52,6 @@ config CMDLINE_BOOL config CMDLINE string "Default kernel command string" depends on CMDLINE_BOOL - default "" help On some platforms, there is currently no way for the boot loader to pass arguments to the kernel. For these platforms, and for the cases @@ -68,7 +66,6 @@ config CMDLINE config CMDLINE_OVERRIDE bool "Built-in command line overrides firmware arguments" - default n depends on CMDLINE_BOOL help By setting this option to 'Y' you will have your kernel ignore diff --git a/arch/mips/Makefile b/arch/mips/Makefile index cdc09b71febe..0a5eab626260 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -14,6 +14,9 @@ archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/mips/tools elf-entry +ifeq ($(CONFIG_CPU_LOONGSON3_WORKAROUNDS),y) + $(Q)$(MAKE) $(build)=arch/mips/tools loongson3-llsc-check +endif $(Q)$(MAKE) $(build)=arch/mips/boot/tools relocs KBUILD_DEFCONFIG := 32r2el_defconfig diff --git a/arch/mips/Makefile.postlink b/arch/mips/Makefile.postlink index 4eea4188cb20..f03fdc95143e 100644 --- a/arch/mips/Makefile.postlink +++ b/arch/mips/Makefile.postlink @@ -3,7 +3,8 @@ # Post-link MIPS pass # =========================================================================== # -# 1. Insert relocations into vmlinux +# 1. Check that Loongson3 LL/SC workarounds are applied correctly +# 2. Insert relocations into vmlinux PHONY := __archpost __archpost: @@ -11,6 +12,10 @@ __archpost: -include include/config/auto.conf include scripts/Kbuild.include +CMD_LS3_LLSC = arch/mips/tools/loongson3-llsc-check +quiet_cmd_ls3_llsc = LLSCCHK $@ + cmd_ls3_llsc = $(CMD_LS3_LLSC) $@ + CMD_RELOCS = arch/mips/boot/tools/relocs quiet_cmd_relocs = RELOCS $@ cmd_relocs = $(CMD_RELOCS) $@ @@ -19,6 +24,9 @@ quiet_cmd_relocs = RELOCS $@ vmlinux: FORCE @true +ifeq ($(CONFIG_CPU_LOONGSON3_WORKAROUNDS),y) + $(call if_changed,ls3_llsc) +endif ifeq ($(CONFIG_RELOCATABLE),y) $(call if_changed,relocs) endif diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 2e9952311ecd..37b93166bf22 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -25,12 +25,47 @@ 0x30000000 0x30000000>; }; + leds { + compatible = "gpio-leds"; + + led0 { + label = "ci20:red:led0"; + gpios = <&gpc 3 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "none"; + }; + + led1 { + label = "ci20:red:led1"; + gpios = <&gpc 2 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "nand-disk"; + }; + + led2 { + label = "ci20:red:led2"; + gpios = <&gpc 1 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "cpu1"; + }; + + led3 { + label = "ci20:red:led3"; + gpios = <&gpc 0 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "cpu0"; + }; + }; + eth0_power: fixedregulator@0 { compatible = "regulator-fixed"; regulator-name = "eth0_power"; gpio = <&gpb 25 GPIO_ACTIVE_LOW>; enable-active-high; }; + + wlan0_power: fixedregulator@1 { + compatible = "regulator-fixed"; + regulator-name = "wlan0_power"; + gpio = <&gpb 19 GPIO_ACTIVE_LOW>; + enable-active-high; + }; }; &ext { @@ -54,9 +89,18 @@ bus-width = <4>; max-frequency = <50000000>; + non-removable; pinctrl-names = "default"; pinctrl-0 = <&pins_mmc1>; + + brcmf: wifi@1 { +/* reg = <4>;*/ + compatible = "brcm,bcm4330-fmac"; + vcc-supply = <&wlan0_power>; + device-wakeup-gpios = <&gpd 9 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpf 7 GPIO_ACTIVE_LOW>; + }; }; &uart0 { @@ -73,6 +117,23 @@ pinctrl-0 = <&pins_uart1>; }; +&uart2 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_uart2>; + uart-has-rtscts; + + bluetooth { + compatible = "brcm,bcm4330-bt"; + reset-gpios = <&gpf 8 GPIO_ACTIVE_HIGH>; + vcc-supply = <&wlan0_power>; + device-wakeup-gpios = <&gpf 5 GPIO_ACTIVE_HIGH>; + host-wakeup-gpios = <&gpf 6 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpf 4 GPIO_ACTIVE_LOW>; + }; +}; + &uart3 { status = "okay"; @@ -87,6 +148,123 @@ pinctrl-0 = <&pins_uart4>; }; +&i2c0 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c0>; + + clock-frequency = <400000>; + + act8600: act8600@5a { + compatible = "active-semi,act8600"; + reg = <0x5a>; + status = "okay"; + + regulators { + vddcore: SUDCDC1 { + regulator-name = "VDDCORE"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-always-on; + }; + vddmem: SUDCDC2 { + regulator-name = "VDDMEM"; + regulator-min-microvolt = <1500000>; + regulator-max-microvolt = <1500000>; + regulator-always-on; + }; + vcc_33: SUDCDC3 { + regulator-name = "VCC33"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + vcc_50: SUDCDC4 { + regulator-name = "VCC50"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + }; + vcc_25: LDO_REG5 { + regulator-name = "VCC25"; + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; + regulator-always-on; + }; + wifi_io: LDO_REG6 { + regulator-name = "WIFIIO"; + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; + regulator-always-on; + }; + vcc_28: LDO_REG7 { + regulator-name = "VCC28"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-always-on; + }; + vcc_15: LDO_REG8 { + regulator-name = "VCC15"; + regulator-min-microvolt = <1500000>; + regulator-max-microvolt = <1500000>; + regulator-always-on; + }; + vcc_18: LDO_REG9 { + regulator-name = "VCC18"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + }; + vcc_11: LDO_REG10 { + regulator-name = "VCC11"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-always-on; + }; + }; + }; +}; + +&i2c1 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c1>; + +}; + +&i2c2 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c2>; + +}; + +&i2c3 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c3>; + +}; + +&i2c4 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c4>; + + clock-frequency = <400000>; + + rtc@51 { + compatible = "nxp,pcf8563"; + reg = <0x51>; + interrupts = <110>; + }; +}; + &nemc { status = "okay"; @@ -197,6 +375,12 @@ bias-disable; }; + pins_uart2: uart2 { + function = "uart2"; + groups = "uart2-data", "uart2-hwflow"; + bias-disable; + }; + pins_uart3: uart3 { function = "uart3"; groups = "uart3-data", "uart3-hwflow"; @@ -209,6 +393,36 @@ bias-disable; }; + pins_i2c0: i2c0 { + function = "i2c0"; + groups = "i2c0-data"; + bias-disable; + }; + + pins_i2c1: i2c1 { + function = "i2c1"; + groups = "i2c1-data"; + bias-disable; + }; + + pins_i2c2: i2c2 { + function = "i2c2"; + groups = "i2c2-data"; + bias-disable; + }; + + pins_i2c3: i2c3 { + function = "i2c3"; + groups = "i2c3-data"; + bias-disable; + }; + + pins_i2c4: i2c4 { + function = "i2c4"; + groups = "i2c4-data-e"; + bias-disable; + }; + pins_nemc: nemc { function = "nemc"; groups = "nemc-data", "nemc-cle-ale", "nemc-rd-we", "nemc-frd-fwe"; diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index c54bd7cfec55..f928329b034b 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -262,6 +262,92 @@ status = "disabled"; }; + i2c0: i2c@10050000 { + compatible = "ingenic,jz4780-i2c"; + #address-cells = <1>; + #size-cells = <0>; + + reg = <0x10050000 0x1000>; + + interrupt-parent = <&intc>; + interrupts = <60>; + + clocks = <&cgu JZ4780_CLK_SMB0>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c0_data>; + + status = "disabled"; + }; + + i2c1: i2c@10051000 { + compatible = "ingenic,jz4780-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x10051000 0x1000>; + + interrupt-parent = <&intc>; + interrupts = <59>; + + clocks = <&cgu JZ4780_CLK_SMB1>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c1_data>; + + status = "disabled"; + }; + + i2c2: i2c@10052000 { + compatible = "ingenic,jz4780-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x10052000 0x1000>; + + interrupt-parent = <&intc>; + interrupts = <58>; + + clocks = <&cgu JZ4780_CLK_SMB2>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c2_data>; + + status = "disabled"; + }; + + i2c3: i2c@10053000 { + compatible = "ingenic,jz4780-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x10053000 0x1000>; + + interrupt-parent = <&intc>; + interrupts = <57>; + + clocks = <&cgu JZ4780_CLK_SMB3>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c3_data>; + + status = "disabled"; + }; + + i2c4: i2c@10054000 { + compatible = "ingenic,jz4780-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x10054000 0x1000>; + + interrupt-parent = <&intc>; + interrupts = <56>; + + clocks = <&cgu JZ4780_CLK_SMB4>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pins_i2c4_data>; + + status = "disabled"; + }; + watchdog: watchdog@10002000 { compatible = "ingenic,jz4780-watchdog"; reg = <0x10002000 0x10>; diff --git a/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts new file mode 100644 index 000000000000..aa5caaa31104 --- /dev/null +++ b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Stefan Roese <sr@denx.de> + */ + +/dts-v1/; + +/include/ "mt7628a.dtsi" + +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/input/input.h> + +/ { + compatible = "gardena,smart-gateway-mt7688", "ralink,mt7688a-soc", + "ralink,mt7628a-soc"; + model = "GARDENA smart Gateway (MT7688)"; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x8000000>; + }; + + gpio-keys { + compatible = "gpio-keys"; + + pinctrl-names = "default"; + pinctrl-0 = <&pinmux_gpio_gpio>; /* GPIO11 */ + + user_btn1 { + label = "USER_BTN1"; + gpios = <&gpio 11 GPIO_ACTIVE_LOW>; + linux,code =<KEY_PROG1> ; + }; + }; + + leds { + compatible = "gpio-leds"; + + pinctrl-names = "default"; + pinctrl-0 = <&pinmux_pwm0_gpio>, /* GPIO18 */ + <&pinmux_pwm1_gpio>, /* GPIO19 */ + <&pinmux_sdmode_gpio>, /* GPIO22..29 */ + <&pinmux_p0led_an_gpio>; /* GPIO43 */ + /* + * <&pinmux_i2s_gpio> (covers GPIO0..3) is needed here as + * well for GPIO3. But this is already claimed for uart1 + * (see below). So we can't include it in this LED node. + */ + + power_blue { + label = "smartgw:power:blue"; + gpios = <&gpio 18 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + power_green { + label = "smartgw:power:green"; + gpios = <&gpio 19 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + power_red { + label = "smartgw:power:red"; + gpios = <&gpio 22 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + radio_blue { + label = "smartgw:radio:blue"; + gpios = <&gpio 23 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + radio_green { + label = "smartgw:radio:green"; + gpios = <&gpio 24 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + radio_red { + label = "smartgw:radio:red"; + gpios = <&gpio 25 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + internet_blue { + label = "smartgw:internet:blue"; + gpios = <&gpio 26 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + internet_green { + label = "smartgw:internet:green"; + gpios = <&gpio 27 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + internet_red { + label = "smartgw:internet:red"; + gpios = <&gpio 28 GPIO_ACTIVE_HIGH>; + default-state = "off"; + }; + + ethernet_link { + label = "smartgw:eth:link"; + gpios = <&gpio 3 GPIO_ACTIVE_LOW>; + linux,default-trigger = "netdev"; + }; + + ethernet_activity { + label = "smartgw:eth:act"; + gpios = <&gpio 43 GPIO_ACTIVE_LOW>; + linux,default-trigger = "netdev"; + }; + }; + + aliases { + serial0 = &uart0; + }; +}; + +&i2c { + status = "okay"; +}; + +&spi { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pinmux_spi_spi>, <&pinmux_spi_cs1_cs>; + + m25p80@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <40000000>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + label = "uboot"; + reg = <0x0 0xa0000>; + read-only; + }; + + partition@a0000 { + label = "uboot_env0"; + reg = <0xa0000 0x10000>; + }; + + partition@b0000 { + label = "uboot_env1"; + reg = <0xb0000 0x10000>; + }; + + factory: partition@c0000 { + label = "factory"; + reg = <0xc0000 0x10000>; + read-only; + }; + }; + }; + + nand_flash@1 { + compatible = "spi-nand"; + linux,mtd-name = "gd5f"; + reg = <1>; + spi-max-frequency = <40000000>; + }; +}; + +&uart1 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pinmux_i2s_gpio>; /* GPIO0..3 */ + + rts-gpios = <&gpio 1 GPIO_ACTIVE_LOW>; + cts-gpios = <&gpio 2 GPIO_ACTIVE_LOW>; +}; + +&uart2 { + status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pinmux_p2led_an_gpio>, /* GPIO41 */ + <&pinmux_p3led_an_gpio>; /* GPIO40 */ + + rts-gpios = <&gpio 40 GPIO_ACTIVE_LOW>; + cts-gpios = <&gpio 41 GPIO_ACTIVE_LOW>; +}; + +&watchdog { + status = "okay"; +}; diff --git a/arch/mips/boot/dts/ralink/mt7628a.dtsi b/arch/mips/boot/dts/ralink/mt7628a.dtsi index 61f8621e88b3..742bcc1dc2e0 100644 --- a/arch/mips/boot/dts/ralink/mt7628a.dtsi +++ b/arch/mips/boot/dts/ralink/mt7628a.dtsi @@ -199,6 +199,22 @@ status = "disabled"; }; + i2c: i2c@900 { + compatible = "mediatek,mt7621-i2c"; + reg = <0x900 0x100>; + + pinctrl-names = "default"; + pinctrl-0 = <&pinmux_i2c_i2c>; + + resets = <&resetc 16>; + reset-names = "i2c"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + uart0: uartlite@c00 { compatible = "ns16550a"; reg = <0xc00 0x100>; diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 95034bf5ca83..1f742c32a883 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -844,7 +844,7 @@ void __init prom_init(void) * BIST should always be enabled when doing a soft reset. L2 * Cache locking for instance is not cleared unless BIST is * enabled. Unfortunately due to a chip errata G-200 for - * Cn38XX and CN31XX, BIST msut be disabled on these parts. + * Cn38XX and CN31XX, BIST must be disabled on these parts. */ if (OCTEON_IS_MODEL(OCTEON_CN38XX_PASS2) || OCTEON_IS_MODEL(OCTEON_CN31XX)) diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig index 7a7af706e898..1788ae23bff9 100644 --- a/arch/mips/configs/fuloong2e_defconfig +++ b/arch/mips/configs/fuloong2e_defconfig @@ -15,7 +15,7 @@ CONFIG_EXPERT=y # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y CONFIG_PROFILING=y -CONFIG_MACH_LOONGSON64=y +CONFIG_MACH_LOONGSON2EF=y CONFIG_PCI=y CONFIG_MIPS32_O32=y CONFIG_MIPS32_N32=y diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index d44f1469cf64..f9f93427c9bd 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -12,7 +12,7 @@ CONFIG_LOG_BUF_SHIFT=15 CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_PROFILING=y -CONFIG_MACH_LOONGSON64=y +CONFIG_MACH_LOONGSON2EF=y CONFIG_LEMOTE_MACH2F=y CONFIG_KEXEC=y # CONFIG_SECCOMP is not set diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index 90ee0084d786..c16a2330e84d 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -12,7 +12,6 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_LOG_BUF_SHIFT=14 CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y @@ -24,7 +23,6 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_SYSCTL_SYSCALL=y CONFIG_EMBEDDED=y CONFIG_MACH_LOONGSON64=y -CONFIG_LOONGSON_MACH3X=y CONFIG_SMP=y CONFIG_HZ_256=y CONFIG_KEXEC=y diff --git a/arch/mips/fw/arc/Makefile b/arch/mips/fw/arc/Makefile index 31dd7305d643..64d685efcc77 100644 --- a/arch/mips/fw/arc/Makefile +++ b/arch/mips/fw/arc/Makefile @@ -3,8 +3,12 @@ # Makefile for the ARC prom monitor library routines under Linux. # +ifdef CONFIG_ARC_CMDLINE_ONLY +lib-y += cmdline.o +else lib-y += cmdline.o env.o file.o identify.o init.o \ - misc.o salone.o time.o tree.o + misc.o +endif lib-$(CONFIG_ARC_MEMORY) += memory.o lib-$(CONFIG_ARC_CONSOLE) += arc_con.o diff --git a/arch/mips/fw/arc/cmdline.c b/arch/mips/fw/arc/cmdline.c index c0122a1dc587..155c5e911723 100644 --- a/arch/mips/fw/arc/cmdline.c +++ b/arch/mips/fw/arc/cmdline.c @@ -17,6 +17,12 @@ #undef DEBUG_CMDLINE +/* + * A 32-bit ARC PROM pass arguments and environment as 32-bit pointer. + * These macro take care of sign extension. + */ +#define prom_argv(index) ((char *) (long)argv[(index)]) + static char *ignored[] = { "ConsoleIn=", "ConsoleOut=", @@ -32,14 +38,14 @@ static char *used_arc[][2] = { { "OSLoadOptions=", "" } }; -static char * __init move_firmware_args(char* cp) +static char __init *move_firmware_args(int argc, LONG *argv, char *cp) { char *s; int actr, i; actr = 1; /* Always ignore argv[0] */ - while (actr < prom_argc) { + while (actr < argc) { for(i = 0; i < ARRAY_SIZE(used_arc); i++) { int len = strlen(used_arc[i][0]); @@ -64,7 +70,7 @@ static char * __init move_firmware_args(char* cp) return cp; } -void __init prom_init_cmdline(void) +void __init prom_init_cmdline(int argc, LONG *argv) { char *cp; int actr, i; @@ -76,9 +82,9 @@ void __init prom_init_cmdline(void) * Move ARC variables to the beginning to make sure they can be * overridden by later arguments. */ - cp = move_firmware_args(cp); + cp = move_firmware_args(argc, argv, cp); - while (actr < prom_argc) { + while (actr < argc) { for (i = 0; i < ARRAY_SIZE(ignored); i++) { int len = strlen(ignored[i]); diff --git a/arch/mips/fw/arc/env.c b/arch/mips/fw/arc/env.c index 1118a26b32ee..02407a7bb38e 100644 --- a/arch/mips/fw/arc/env.c +++ b/arch/mips/fw/arc/env.c @@ -19,9 +19,3 @@ ArcGetEnvironmentVariable(CHAR *name) { return (CHAR *) ARC_CALL1(get_evar, name); } - -LONG __init -ArcSetEnvironmentVariable(PCHAR name, PCHAR value) -{ - return ARC_CALL2(set_evar, name, value); -} diff --git a/arch/mips/fw/arc/file.c b/arch/mips/fw/arc/file.c index 49fd3ff13fe5..b0d8535c80cc 100644 --- a/arch/mips/fw/arc/file.c +++ b/arch/mips/fw/arc/file.c @@ -13,62 +13,13 @@ #include <asm/sgialib.h> LONG -ArcGetDirectoryEntry(ULONG FileID, struct linux_vdirent *Buffer, - ULONG N, ULONG *Count) -{ - return ARC_CALL4(get_vdirent, FileID, Buffer, N, Count); -} - -LONG -ArcOpen(CHAR *Path, enum linux_omode OpenMode, ULONG *FileID) -{ - return ARC_CALL3(open, Path, OpenMode, FileID); -} - -LONG -ArcClose(ULONG FileID) -{ - return ARC_CALL1(close, FileID); -} - -LONG ArcRead(ULONG FileID, VOID *Buffer, ULONG N, ULONG *Count) { return ARC_CALL4(read, FileID, Buffer, N, Count); } LONG -ArcGetReadStatus(ULONG FileID) -{ - return ARC_CALL1(get_rstatus, FileID); -} - -LONG ArcWrite(ULONG FileID, PVOID Buffer, ULONG N, PULONG Count) { return ARC_CALL4(write, FileID, Buffer, N, Count); } - -LONG -ArcSeek(ULONG FileID, struct linux_bigint *Position, enum linux_seekmode SeekMode) -{ - return ARC_CALL3(seek, FileID, Position, SeekMode); -} - -LONG -ArcMount(char *name, enum linux_mountops op) -{ - return ARC_CALL2(mount, name, op); -} - -LONG -ArcGetFileInformation(ULONG FileID, struct linux_finfo *Information) -{ - return ARC_CALL2(get_finfo, FileID, Information); -} - -LONG ArcSetFileInformation(ULONG FileID, ULONG AttributeFlags, - ULONG AttributeMask) -{ - return ARC_CALL3(set_finfo, FileID, AttributeFlags, AttributeMask); -} diff --git a/arch/mips/fw/arc/identify.c b/arch/mips/fw/arc/identify.c index f90266c02c9d..5527e0f54079 100644 --- a/arch/mips/fw/arc/identify.c +++ b/arch/mips/fw/arc/identify.c @@ -32,10 +32,6 @@ static struct smatch mach_table[] = { .liname = "SGI Indy", .flags = PROM_FLAG_ARCS, }, { - .arcname = "SGI-IP27", - .liname = "SGI Origin", - .flags = PROM_FLAG_ARCS, - }, { .arcname = "SGI-IP28", .liname = "SGI IP28", .flags = PROM_FLAG_ARCS, @@ -87,6 +83,11 @@ const char *get_system_type(void) return system_type; } +static pcomponent * __init ArcGetChild(pcomponent *Current) +{ + return (pcomponent *) ARC_CALL1(child_component, Current); +} + void __init prom_identify_arch(void) { pcomponent *p; @@ -98,13 +99,7 @@ void __init prom_identify_arch(void) */ p = ArcGetChild(PROM_NULL_COMPONENT); if (p == NULL) { -#ifdef CONFIG_SGI_IP27 - /* IP27 PROM misbehaves, seems to not implement ARC - GetChild(). So we just assume it's an IP27. */ - iname = "SGI-IP27"; -#else iname = "Unknown"; -#endif } else iname = (char *) (long) p->iname; diff --git a/arch/mips/fw/arc/init.c b/arch/mips/fw/arc/init.c index 008555969534..f9d1dea9b2ca 100644 --- a/arch/mips/fw/arc/init.c +++ b/arch/mips/fw/arc/init.c @@ -18,8 +18,11 @@ /* Master romvec interface. */ struct linux_romvec *romvec; -int prom_argc; -LONG *_prom_argv, *_prom_envp; + +#if defined(CONFIG_64BIT) && defined(CONFIG_FW_ARC32) +/* stack for calling 32bit ARC prom */ +u64 o32_stk[4096]; +#endif void __init prom_init(void) { @@ -27,10 +30,6 @@ void __init prom_init(void) romvec = ROMVECTOR; - prom_argc = fw_arg0; - _prom_argv = (LONG *) fw_arg1; - _prom_envp = (LONG *) fw_arg2; - if (pb->magic != 0x53435241) { printk(KERN_CRIT "Aieee, bad prom vector magic %08lx\n", (unsigned long) pb->magic); @@ -38,7 +37,7 @@ void __init prom_init(void) ; } - prom_init_cmdline(); + prom_init_cmdline(fw_arg0, (LONG *)fw_arg1); prom_identify_arch(); printk(KERN_INFO "PROMLIB: ARC firmware Version %d Revision %d\n", pb->ver, pb->rev); @@ -49,11 +48,4 @@ void __init prom_init(void) ArcRead(0, &c, 1, &cnt); ArcEnterInteractiveMode(); #endif -#ifdef CONFIG_SGI_IP27 - { - extern const struct plat_smp_ops ip27_smp_ops; - - register_smp_ops(&ip27_smp_ops); - } -#endif } diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index b4328b3b5288..dbbcddc82823 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -158,6 +158,10 @@ void __init prom_meminit(void) } } +void __weak __init prom_cleanup(void) +{ +} + void __init prom_free_prom_memory(void) { int i; @@ -169,4 +173,9 @@ void __init prom_free_prom_memory(void) free_init_pages("prom memory", prom_mem_base[i], prom_mem_base[i] + prom_mem_size[i]); } + /* + * at this point it isn't safe to call PROM functions + * give platforms a way to do PROM cleanups + */ + prom_cleanup(); } diff --git a/arch/mips/fw/arc/misc.c b/arch/mips/fw/arc/misc.c index 19f710117d97..d5b2d5901324 100644 --- a/arch/mips/fw/arc/misc.c +++ b/arch/mips/fw/arc/misc.c @@ -21,47 +21,6 @@ #include <asm/bootinfo.h> VOID __noreturn -ArcHalt(VOID) -{ - bc_disable(); - local_irq_disable(); - ARC_CALL0(halt); - - unreachable(); -} - -VOID __noreturn -ArcPowerDown(VOID) -{ - bc_disable(); - local_irq_disable(); - ARC_CALL0(pdown); - - unreachable(); -} - -/* XXX is this a soft reset basically? XXX */ -VOID __noreturn -ArcRestart(VOID) -{ - bc_disable(); - local_irq_disable(); - ARC_CALL0(restart); - - unreachable(); -} - -VOID __noreturn -ArcReboot(VOID) -{ - bc_disable(); - local_irq_disable(); - ARC_CALL0(reboot); - - unreachable(); -} - -VOID __noreturn ArcEnterInteractiveMode(VOID) { bc_disable(); @@ -71,24 +30,6 @@ ArcEnterInteractiveMode(VOID) unreachable(); } -LONG -ArcSaveConfiguration(VOID) -{ - return ARC_CALL0(cfg_save); -} - -struct linux_sysid * -ArcGetSystemId(VOID) -{ - return (struct linux_sysid *) ARC_CALL0(get_sysid); -} - -VOID __init -ArcFlushAllCaches(VOID) -{ - ARC_CALL0(cache_flush); -} - DISPLAY_STATUS * __init ArcGetDisplayStatus(ULONG FileID) { return (DISPLAY_STATUS *) ARC_CALL1(GetDisplayStatus, FileID); diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c index be381307fbb0..5e9e840a9314 100644 --- a/arch/mips/fw/arc/promlib.c +++ b/arch/mips/fw/arc/promlib.c @@ -11,6 +11,21 @@ #include <asm/bcache.h> #include <asm/setup.h> +#if defined(CONFIG_64BIT) && defined(CONFIG_FW_ARC32) +/* + * For 64bit kernels working with a 32bit ARC PROM pointer arguments + * for ARC calls need to reside in CKEG0/1. But as soon as the kernel + * switches to it's first kernel thread stack is set to an address in + * XKPHYS, so anything on stack can't be used anymore. This is solved + * by using a * static declartion variables are put into BSS, which is + * linked to a CKSEG0 address. Since this is only used on UP platforms + * there is not spinlock needed + */ +#define O32_STATIC static +#else +#define O32_STATIC +#endif + /* * IP22 boardcache is not compatible with board caches. Thus we disable it * during romvec action. Since r4xx0.c is always compiled and linked with your @@ -23,8 +38,10 @@ void prom_putchar(char c) { - ULONG cnt; - CHAR it = c; + O32_STATIC ULONG cnt; + O32_STATIC CHAR it; + + it = c; bc_disable(); ArcWrite(1, &it, 1, &cnt); @@ -33,8 +50,8 @@ void prom_putchar(char c) char prom_getchar(void) { - ULONG cnt; - CHAR c; + O32_STATIC ULONG cnt; + O32_STATIC CHAR c; bc_disable(); ArcRead(0, &c, 1, &cnt); diff --git a/arch/mips/fw/arc/salone.c b/arch/mips/fw/arc/salone.c deleted file mode 100644 index 2d99f44d5576..000000000000 --- a/arch/mips/fw/arc/salone.c +++ /dev/null @@ -1,25 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Routines to load into memory and execute stand-along program images using - * ARCS PROM firmware. - * - * Copyright (C) 1996 David S. Miller (davem@davemloft.net) - */ -#include <linux/init.h> -#include <asm/sgialib.h> - -LONG __init ArcLoad(CHAR *Path, ULONG TopAddr, ULONG *ExecAddr, ULONG *LowAddr) -{ - return ARC_CALL4(load, Path, TopAddr, ExecAddr, LowAddr); -} - -LONG __init ArcInvoke(ULONG ExecAddr, ULONG StackAddr, ULONG Argc, CHAR *Argv[], - CHAR *Envp[]) -{ - return ARC_CALL5(invoke, ExecAddr, StackAddr, Argc, Argv, Envp); -} - -LONG __init ArcExecute(CHAR *Path, LONG Argc, CHAR *Argv[], CHAR *Envp[]) -{ - return ARC_CALL4(exec, Path, Argc, Argv, Envp); -} diff --git a/arch/mips/fw/arc/time.c b/arch/mips/fw/arc/time.c deleted file mode 100644 index 190cdb50b895..000000000000 --- a/arch/mips/fw/arc/time.c +++ /dev/null @@ -1,25 +0,0 @@ -/* - * 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. - * - * Extracting time information from ARCS prom. - * - * Copyright (C) 1996 David S. Miller (davem@davemloft.net) - */ -#include <linux/init.h> - -#include <asm/fw/arc/types.h> -#include <asm/sgialib.h> - -struct linux_tinfo * __init -ArcGetTime(VOID) -{ - return (struct linux_tinfo *) ARC_CALL0(get_tinfo); -} - -ULONG __init -ArcGetRelativeTime(VOID) -{ - return ARC_CALL0(get_rtime); -} diff --git a/arch/mips/fw/arc/tree.c b/arch/mips/fw/arc/tree.c deleted file mode 100644 index 924a37dc2569..000000000000 --- a/arch/mips/fw/arc/tree.c +++ /dev/null @@ -1,127 +0,0 @@ -/* - * 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. - * - * PROM component device tree code. - * - * Copyright (C) 1996 David S. Miller (davem@davemloft.net) - * Copyright (C) 1999 Ralf Baechle (ralf@gnu.org) - * Copyright (C) 1999 Silicon Graphics, Inc. - */ -#include <linux/init.h> -#include <asm/fw/arc/types.h> -#include <asm/sgialib.h> - -#undef DEBUG_PROM_TREE - -pcomponent * __init -ArcGetPeer(pcomponent *Current) -{ - if (Current == PROM_NULL_COMPONENT) - return PROM_NULL_COMPONENT; - - return (pcomponent *) ARC_CALL1(next_component, Current); -} - -pcomponent * __init -ArcGetChild(pcomponent *Current) -{ - return (pcomponent *) ARC_CALL1(child_component, Current); -} - -pcomponent * __init -ArcGetParent(pcomponent *Current) -{ - if (Current == PROM_NULL_COMPONENT) - return PROM_NULL_COMPONENT; - - return (pcomponent *) ARC_CALL1(parent_component, Current); -} - -LONG __init -ArcGetConfigurationData(VOID *Buffer, pcomponent *Current) -{ - return ARC_CALL2(component_data, Buffer, Current); -} - -pcomponent * __init -ArcAddChild(pcomponent *Current, pcomponent *Template, VOID *ConfigurationData) -{ - return (pcomponent *) - ARC_CALL3(child_add, Current, Template, ConfigurationData); -} - -LONG __init -ArcDeleteComponent(pcomponent *ComponentToDelete) -{ - return ARC_CALL1(comp_del, ComponentToDelete); -} - -pcomponent * __init -ArcGetComponent(CHAR *Path) -{ - return (pcomponent *)ARC_CALL1(component_by_path, Path); -} - -#ifdef DEBUG_PROM_TREE - -static char *classes[] = { - "system", "processor", "cache", "adapter", "controller", "peripheral", - "memory" -}; - -static char *types[] = { - "arc", "cpu", "fpu", "picache", "pdcache", "sicache", "sdcache", - "sccache", "memdev", "eisa adapter", "tc adapter", "scsi adapter", - "dti adapter", "multi-func adapter", "disk controller", - "tp controller", "cdrom controller", "worm controller", - "serial controller", "net controller", "display controller", - "parallel controller", "pointer controller", "keyboard controller", - "audio controller", "misc controller", "disk peripheral", - "floppy peripheral", "tp peripheral", "modem peripheral", - "monitor peripheral", "printer peripheral", "pointer peripheral", - "keyboard peripheral", "terminal peripheral", "line peripheral", - "net peripheral", "misc peripheral", "anonymous" -}; - -static char *iflags[] = { - "bogus", "read only", "removable", "console in", "console out", - "input", "output" -}; - -static void __init -dump_component(pcomponent *p) -{ - printk("[%p]:class<%s>type<%s>flags<%s>ver<%d>rev<%d>", - p, classes[p->class], types[p->type], - iflags[p->iflags], p->vers, p->rev); - printk("key<%08lx>\n\tamask<%08lx>cdsize<%d>ilen<%d>iname<%s>\n", - p->key, p->amask, (int)p->cdsize, (int)p->ilen, p->iname); -} - -static void __init -traverse(pcomponent *p, int op) -{ - dump_component(p); - if(ArcGetChild(p)) - traverse(ArcGetChild(p), 1); - if(ArcGetPeer(p) && op) - traverse(ArcGetPeer(p), 1); -} - -void __init -prom_testtree(void) -{ - pcomponent *p; - - p = ArcGetChild(PROM_NULL_COMPONENT); - dump_component(p); - p = ArcGetChild(p); - while(p) { - dump_component(p); - p = ArcGetPeer(p); - } -} - -#endif /* DEBUG_PROM_TREE */ diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index d5b8c4717ded..1de215b283d6 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -20,9 +20,9 @@ #include <asm/smp-ops.h> #include <asm/time.h> -static __initdata const void *fdt; -static __initdata const struct mips_machine *mach; -static __initdata const void *mach_match_data; +static __initconst const void *fdt; +static __initconst const struct mips_machine *mach; +static __initconst const void *mach_match_data; void __init prom_init(void) { diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index bb8658cc7f12..e5ac88392d1f 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -20,157 +20,176 @@ #include <asm/compiler.h> #include <asm/cpu-features.h> #include <asm/cmpxchg.h> +#include <asm/llsc.h> +#include <asm/sync.h> #include <asm/war.h> -/* - * Using a branch-likely instruction to check the result of an sc instruction - * works around a bug present in R10000 CPUs prior to revision 3.0 that could - * cause ll-sc sequences to execute non-atomically. - */ -#if R10000_LLSC_WAR -# define __scbeqz "beqzl" -#else -# define __scbeqz "beqz" -#endif - -#define ATOMIC_INIT(i) { (i) } +#define ATOMIC_OPS(pfx, type) \ +static __always_inline type pfx##_read(const pfx##_t *v) \ +{ \ + return READ_ONCE(v->counter); \ +} \ + \ +static __always_inline void pfx##_set(pfx##_t *v, type i) \ +{ \ + WRITE_ONCE(v->counter, i); \ +} \ + \ +static __always_inline type pfx##_cmpxchg(pfx##_t *v, type o, type n) \ +{ \ + return cmpxchg(&v->counter, o, n); \ +} \ + \ +static __always_inline type pfx##_xchg(pfx##_t *v, type n) \ +{ \ + return xchg(&v->counter, n); \ +} -/* - * atomic_read - read atomic variable - * @v: pointer of type atomic_t - * - * Atomically reads the value of @v. - */ -#define atomic_read(v) READ_ONCE((v)->counter) +#define ATOMIC_INIT(i) { (i) } +ATOMIC_OPS(atomic, int) -/* - * atomic_set - set atomic variable - * @v: pointer of type atomic_t - * @i: required value - * - * Atomically sets the value of @v to @i. - */ -#define atomic_set(v, i) WRITE_ONCE((v)->counter, (i)) +#ifdef CONFIG_64BIT +# define ATOMIC64_INIT(i) { (i) } +ATOMIC_OPS(atomic64, s64) +#endif -#define ATOMIC_OP(op, c_op, asm_op) \ -static __inline__ void atomic_##op(int i, atomic_t * v) \ -{ \ - if (kernel_uses_llsc) { \ - int temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: ll %0, %1 # atomic_" #op " \n" \ - " " #asm_op " %0, %2 \n" \ - " sc %0, %1 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " .set pop \n" \ - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ +#define ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc) \ +static __inline__ void pfx##_##op(type i, pfx##_t * v) \ +{ \ + type temp; \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + v->counter c_op i; \ + raw_local_irq_restore(flags); \ + return; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %0, %1 # " #pfx "_" #op " \n" \ + " " #asm_op " %0, %2 \n" \ + " " #sc " %0, %1 \n" \ + "\t" __SC_BEQZ "%0, 1b \n" \ + " .set pop \n" \ + : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) : __LLSC_CLOBBER); \ } -#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ -static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v) \ -{ \ - int result; \ - \ - if (kernel_uses_llsc) { \ - int temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: ll %1, %2 # atomic_" #op "_return \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " sc %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " .set pop \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - result c_op i; \ - v->counter = result; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ +#define ATOMIC_OP_RETURN(pfx, op, type, c_op, asm_op, ll, sc) \ +static __inline__ type pfx##_##op##_return_relaxed(type i, pfx##_t * v) \ +{ \ + type temp, result; \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + result c_op i; \ + v->counter = result; \ + raw_local_irq_restore(flags); \ + return result; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %1, %2 # " #pfx "_" #op "_return\n" \ + " " #asm_op " %0, %1, %3 \n" \ + " " #sc " %0, %2 \n" \ + "\t" __SC_BEQZ "%0, 1b \n" \ + " " #asm_op " %0, %1, %3 \n" \ + " .set pop \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) : __LLSC_CLOBBER); \ + \ + return result; \ } -#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ -static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v) \ -{ \ - int result; \ - \ - if (kernel_uses_llsc) { \ - int temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: ll %1, %2 # atomic_fetch_" #op " \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " sc %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " .set pop \n" \ - " move %0, %1 \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ +#define ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc) \ +static __inline__ type pfx##_fetch_##op##_relaxed(type i, pfx##_t * v) \ +{ \ + int temp, result; \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + v->counter c_op i; \ + raw_local_irq_restore(flags); \ + return result; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %1, %2 # " #pfx "_fetch_" #op "\n" \ + " " #asm_op " %0, %1, %3 \n" \ + " " #sc " %0, %2 \n" \ + "\t" __SC_BEQZ "%0, 1b \n" \ + " .set pop \n" \ + " move %0, %1 \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) : __LLSC_CLOBBER); \ + \ + return result; \ } -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#undef ATOMIC_OPS +#define ATOMIC_OPS(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_OP_RETURN(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc) -ATOMIC_OPS(add, +=, addu) -ATOMIC_OPS(sub, -=, subu) +ATOMIC_OPS(atomic, add, int, +=, addu, ll, sc) +ATOMIC_OPS(atomic, sub, int, -=, subu, ll, sc) #define atomic_add_return_relaxed atomic_add_return_relaxed #define atomic_sub_return_relaxed atomic_sub_return_relaxed #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed #define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed +#ifdef CONFIG_64BIT +ATOMIC_OPS(atomic64, add, s64, +=, daddu, lld, scd) +ATOMIC_OPS(atomic64, sub, s64, -=, dsubu, lld, scd) +# define atomic64_add_return_relaxed atomic64_add_return_relaxed +# define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +# define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed +# define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed +#endif /* CONFIG_64BIT */ + #undef ATOMIC_OPS -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_OP(pfx, op, type, c_op, asm_op, ll, sc) \ + ATOMIC_FETCH_OP(pfx, op, type, c_op, asm_op, ll, sc) -ATOMIC_OPS(and, &=, and) -ATOMIC_OPS(or, |=, or) -ATOMIC_OPS(xor, ^=, xor) +ATOMIC_OPS(atomic, and, int, &=, and, ll, sc) +ATOMIC_OPS(atomic, or, int, |=, or, ll, sc) +ATOMIC_OPS(atomic, xor, int, ^=, xor, ll, sc) #define atomic_fetch_and_relaxed atomic_fetch_and_relaxed #define atomic_fetch_or_relaxed atomic_fetch_or_relaxed #define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed +#ifdef CONFIG_64BIT +ATOMIC_OPS(atomic64, and, s64, &=, and, lld, scd) +ATOMIC_OPS(atomic64, or, s64, |=, or, lld, scd) +ATOMIC_OPS(atomic64, xor, s64, ^=, xor, lld, scd) +# define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed +# define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed +# define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed +#endif + #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN @@ -184,258 +203,66 @@ ATOMIC_OPS(xor, ^=, xor) * Atomically test @v and subtract @i if @v is greater or equal than @i. * The function returns the old value of @v minus @i. */ -static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) -{ - int result; - - smp_mb__before_llsc(); - - if (kernel_uses_llsc) { - int temp; - - loongson_llsc_mb(); - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_LEVEL" \n" - "1: ll %1, %2 # atomic_sub_if_positive\n" - " .set pop \n" - " subu %0, %1, %3 \n" - " move %1, %0 \n" - " bltz %0, 2f \n" - " .set push \n" - " .set "MIPS_ISA_LEVEL" \n" - " sc %1, %2 \n" - "\t" __scbeqz " %1, 1b \n" - "2: \n" - " .set pop \n" - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) - : "Ir" (i) : __LLSC_CLOBBER); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - result = v->counter; - result -= i; - if (result >= 0) - v->counter = result; - raw_local_irq_restore(flags); - } - - smp_llsc_mb(); - - return result; +#define ATOMIC_SIP_OP(pfx, type, op, ll, sc) \ +static __inline__ int pfx##_sub_if_positive(type i, pfx##_t * v) \ +{ \ + type temp, result; \ + \ + smp_mb__before_atomic(); \ + \ + if (!kernel_uses_llsc) { \ + unsigned long flags; \ + \ + raw_local_irq_save(flags); \ + result = v->counter; \ + result -= i; \ + if (result >= 0) \ + v->counter = result; \ + raw_local_irq_restore(flags); \ + smp_mb__after_atomic(); \ + return result; \ + } \ + \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " #ll " %1, %2 # atomic_sub_if_positive\n" \ + " .set pop \n" \ + " " #op " %0, %1, %3 \n" \ + " move %1, %0 \n" \ + " bltz %0, 2f \n" \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " #sc " %1, %2 \n" \ + " " __SC_BEQZ "%1, 1b \n" \ + "2: " __SYNC(full, loongson3_war) " \n" \ + " .set pop \n" \ + : "=&r" (result), "=&r" (temp), \ + "+" GCC_OFF_SMALL_ASM() (v->counter) \ + : "Ir" (i) \ + : __LLSC_CLOBBER); \ + \ + /* \ + * In the Loongson3 workaround case we already have a \ + * completion barrier at 2: above, which is needed due to the \ + * bltz that can branch to code outside of the LL/SC loop. As \ + * such, we don't need to emit another barrier here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_mb__after_atomic(); \ + \ + return result; \ } -#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -#define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) - -/* - * atomic_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - */ +ATOMIC_SIP_OP(atomic, int, subu, ll, sc) #define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v) #ifdef CONFIG_64BIT - -#define ATOMIC64_INIT(i) { (i) } - -/* - * atomic64_read - read atomic variable - * @v: pointer of type atomic64_t - * - */ -#define atomic64_read(v) READ_ONCE((v)->counter) - -/* - * atomic64_set - set atomic variable - * @v: pointer of type atomic64_t - * @i: required value - */ -#define atomic64_set(v, i) WRITE_ONCE((v)->counter, (i)) - -#define ATOMIC64_OP(op, c_op, asm_op) \ -static __inline__ void atomic64_##op(s64 i, atomic64_t * v) \ -{ \ - if (kernel_uses_llsc) { \ - s64 temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: lld %0, %1 # atomic64_" #op " \n" \ - " " #asm_op " %0, %2 \n" \ - " scd %0, %1 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " .set pop \n" \ - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ -} - -#define ATOMIC64_OP_RETURN(op, c_op, asm_op) \ -static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v) \ -{ \ - s64 result; \ - \ - if (kernel_uses_llsc) { \ - s64 temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: lld %1, %2 # atomic64_" #op "_return\n" \ - " " #asm_op " %0, %1, %3 \n" \ - " scd %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " .set pop \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - result c_op i; \ - v->counter = result; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ -} - -#define ATOMIC64_FETCH_OP(op, c_op, asm_op) \ -static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v) \ -{ \ - s64 result; \ - \ - if (kernel_uses_llsc) { \ - s64 temp; \ - \ - loongson_llsc_mb(); \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set "MIPS_ISA_LEVEL" \n" \ - "1: lld %1, %2 # atomic64_fetch_" #op "\n" \ - " " #asm_op " %0, %1, %3 \n" \ - " scd %0, %2 \n" \ - "\t" __scbeqz " %0, 1b \n" \ - " move %0, %1 \n" \ - " .set pop \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i) : __LLSC_CLOBBER); \ - } else { \ - unsigned long flags; \ - \ - raw_local_irq_save(flags); \ - result = v->counter; \ - v->counter c_op i; \ - raw_local_irq_restore(flags); \ - } \ - \ - return result; \ -} - -#define ATOMIC64_OPS(op, c_op, asm_op) \ - ATOMIC64_OP(op, c_op, asm_op) \ - ATOMIC64_OP_RETURN(op, c_op, asm_op) \ - ATOMIC64_FETCH_OP(op, c_op, asm_op) - -ATOMIC64_OPS(add, +=, daddu) -ATOMIC64_OPS(sub, -=, dsubu) - -#define atomic64_add_return_relaxed atomic64_add_return_relaxed -#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed -#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed -#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed - -#undef ATOMIC64_OPS -#define ATOMIC64_OPS(op, c_op, asm_op) \ - ATOMIC64_OP(op, c_op, asm_op) \ - ATOMIC64_FETCH_OP(op, c_op, asm_op) - -ATOMIC64_OPS(and, &=, and) -ATOMIC64_OPS(or, |=, or) -ATOMIC64_OPS(xor, ^=, xor) - -#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed -#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed -#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed - -#undef ATOMIC64_OPS -#undef ATOMIC64_FETCH_OP -#undef ATOMIC64_OP_RETURN -#undef ATOMIC64_OP - -/* - * atomic64_sub_if_positive - conditionally subtract integer from atomic - * variable - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically test @v and subtract @i if @v is greater or equal than @i. - * The function returns the old value of @v minus @i. - */ -static __inline__ s64 atomic64_sub_if_positive(s64 i, atomic64_t * v) -{ - s64 result; - - smp_mb__before_llsc(); - - if (kernel_uses_llsc) { - s64 temp; - - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_LEVEL" \n" - "1: lld %1, %2 # atomic64_sub_if_positive\n" - " dsubu %0, %1, %3 \n" - " move %1, %0 \n" - " bltz %0, 1f \n" - " scd %1, %2 \n" - "\t" __scbeqz " %1, 1b \n" - "1: \n" - " .set pop \n" - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) - : "Ir" (i)); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - result = v->counter; - result -= i; - if (result >= 0) - v->counter = result; - raw_local_irq_restore(flags); - } - - smp_llsc_mb(); - - return result; -} - -#define atomic64_cmpxchg(v, o, n) \ - ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) -#define atomic64_xchg(v, new) (xchg(&((v)->counter), (new))) - -/* - * atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic64_t - */ +ATOMIC_SIP_OP(atomic64, s64, dsubu, lld, scd) #define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v) +#endif -#endif /* CONFIG_64BIT */ +#undef ATOMIC_SIP_OP #endif /* _ASM_ATOMIC_H */ diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h index 9228f7386220..49ff172a72b9 100644 --- a/arch/mips/include/asm/barrier.h +++ b/arch/mips/include/asm/barrier.h @@ -9,131 +9,26 @@ #define __ASM_BARRIER_H #include <asm/addrspace.h> +#include <asm/sync.h> -/* - * Sync types defined by the MIPS architecture (document MD00087 table 6.5) - * These values are used with the sync instruction to perform memory barriers. - * Types of ordering guarantees available through the SYNC instruction: - * - Completion Barriers - * - Ordering Barriers - * As compared to the completion barrier, the ordering barrier is a - * lighter-weight operation as it does not require the specified instructions - * before the SYNC to be already completed. Instead it only requires that those - * specified instructions which are subsequent to the SYNC in the instruction - * stream are never re-ordered for processing ahead of the specified - * instructions which are before the SYNC in the instruction stream. - * This potentially reduces how many cycles the barrier instruction must stall - * before it completes. - * Implementations that do not use any of the non-zero values of stype to define - * different barriers, such as ordering barriers, must make those stype values - * act the same as stype zero. - */ - -/* - * Completion barriers: - * - Every synchronizable specified memory instruction (loads or stores or both) - * that occurs in the instruction stream before the SYNC instruction must be - * already globally performed before any synchronizable specified memory - * instructions that occur after the SYNC are allowed to be performed, with - * respect to any other processor or coherent I/O module. - * - * - The barrier does not guarantee the order in which instruction fetches are - * performed. - * - * - A stype value of zero will always be defined such that it performs the most - * complete set of synchronization operations that are defined.This means - * stype zero always does a completion barrier that affects both loads and - * stores preceding the SYNC instruction and both loads and stores that are - * subsequent to the SYNC instruction. Non-zero values of stype may be defined - * by the architecture or specific implementations to perform synchronization - * behaviors that are less complete than that of stype zero. If an - * implementation does not use one of these non-zero values to define a - * different synchronization behavior, then that non-zero value of stype must - * act the same as stype zero completion barrier. This allows software written - * for an implementation with a lighter-weight barrier to work on another - * implementation which only implements the stype zero completion barrier. - * - * - A completion barrier is required, potentially in conjunction with SSNOP (in - * Release 1 of the Architecture) or EHB (in Release 2 of the Architecture), - * to guarantee that memory reference results are visible across operating - * mode changes. For example, a completion barrier is required on some - * implementations on entry to and exit from Debug Mode to guarantee that - * memory effects are handled correctly. - */ - -/* - * stype 0 - A completion barrier that affects preceding loads and stores and - * subsequent loads and stores. - * Older instructions which must reach the load/store ordering point before the - * SYNC instruction completes: Loads, Stores - * Younger instructions which must reach the load/store ordering point only - * after the SYNC instruction completes: Loads, Stores - * Older instructions which must be globally performed when the SYNC instruction - * completes: Loads, Stores - */ -#define STYPE_SYNC 0x0 - -/* - * Ordering barriers: - * - Every synchronizable specified memory instruction (loads or stores or both) - * that occurs in the instruction stream before the SYNC instruction must - * reach a stage in the load/store datapath after which no instruction - * re-ordering is possible before any synchronizable specified memory - * instruction which occurs after the SYNC instruction in the instruction - * stream reaches the same stage in the load/store datapath. - * - * - If any memory instruction before the SYNC instruction in program order, - * generates a memory request to the external memory and any memory - * instruction after the SYNC instruction in program order also generates a - * memory request to external memory, the memory request belonging to the - * older instruction must be globally performed before the time the memory - * request belonging to the younger instruction is globally performed. - * - * - The barrier does not guarantee the order in which instruction fetches are - * performed. - */ +static inline void __sync(void) +{ + asm volatile(__SYNC(full, always) ::: "memory"); +} -/* - * stype 0x10 - An ordering barrier that affects preceding loads and stores and - * subsequent loads and stores. - * Older instructions which must reach the load/store ordering point before the - * SYNC instruction completes: Loads, Stores - * Younger instructions which must reach the load/store ordering point only - * after the SYNC instruction completes: Loads, Stores - * Older instructions which must be globally performed when the SYNC instruction - * completes: N/A - */ -#define STYPE_SYNC_MB 0x10 +static inline void rmb(void) +{ + asm volatile(__SYNC(rmb, always) ::: "memory"); +} +#define rmb rmb -/* - * stype 0x14 - A completion barrier specific to global invalidations - * - * When a sync instruction of this type completes any preceding GINVI or GINVT - * operation has been globalized & completed on all coherent CPUs. Anything - * that the GINV* instruction should invalidate will have been invalidated on - * all coherent CPUs when this instruction completes. It is implementation - * specific whether the GINV* instructions themselves will ensure completion, - * or this sync type will. - * - * In systems implementing global invalidates (ie. with Config5.GI == 2 or 3) - * this sync type also requires that previous SYNCI operations have completed. - */ -#define STYPE_GINV 0x14 +static inline void wmb(void) +{ + asm volatile(__SYNC(wmb, always) ::: "memory"); +} +#define wmb wmb -#ifdef CONFIG_CPU_HAS_SYNC -#define __sync() \ - __asm__ __volatile__( \ - ".set push\n\t" \ - ".set noreorder\n\t" \ - ".set mips2\n\t" \ - "sync\n\t" \ - ".set pop" \ - : /* no output */ \ - : /* no input */ \ - : "memory") -#else -#define __sync() do { } while(0) -#endif +#define fast_mb() __sync() #define __fast_iob() \ __asm__ __volatile__( \ @@ -146,17 +41,8 @@ : "m" (*(int *)CKSEG1) \ : "memory") #ifdef CONFIG_CPU_CAVIUM_OCTEON -# define OCTEON_SYNCW_STR ".set push\n.set arch=octeon\nsyncw\nsyncw\n.set pop\n" -# define __syncw() __asm__ __volatile__(OCTEON_SYNCW_STR : : : "memory") - -# define fast_wmb() __syncw() -# define fast_rmb() barrier() -# define fast_mb() __sync() # define fast_iob() do { } while (0) #else /* ! CONFIG_CPU_CAVIUM_OCTEON */ -# define fast_wmb() __sync() -# define fast_rmb() __sync() -# define fast_mb() __sync() # ifdef CONFIG_SGI_IP28 # define fast_iob() \ __asm__ __volatile__( \ @@ -192,23 +78,14 @@ #endif /* !CONFIG_CPU_HAS_WB */ -#define wmb() fast_wmb() -#define rmb() fast_rmb() - #if defined(CONFIG_WEAK_ORDERING) -# ifdef CONFIG_CPU_CAVIUM_OCTEON -# define __smp_mb() __sync() -# define __smp_rmb() barrier() -# define __smp_wmb() __syncw() -# else -# define __smp_mb() __asm__ __volatile__("sync" : : :"memory") -# define __smp_rmb() __asm__ __volatile__("sync" : : :"memory") -# define __smp_wmb() __asm__ __volatile__("sync" : : :"memory") -# endif +# define __smp_mb() __sync() +# define __smp_rmb() rmb() +# define __smp_wmb() wmb() #else -#define __smp_mb() barrier() -#define __smp_rmb() barrier() -#define __smp_wmb() barrier() +# define __smp_mb() barrier() +# define __smp_rmb() barrier() +# define __smp_wmb() barrier() #endif /* @@ -218,13 +95,14 @@ * ordering will be done by smp_llsc_mb() and friends. */ #if defined(CONFIG_WEAK_REORDERING_BEYOND_LLSC) && defined(CONFIG_SMP) -#define __WEAK_LLSC_MB " sync \n" -#define smp_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory") -#define __LLSC_CLOBBER +# define __WEAK_LLSC_MB sync +# define smp_llsc_mb() \ + __asm__ __volatile__(__stringify(__WEAK_LLSC_MB) : : :"memory") +# define __LLSC_CLOBBER #else -#define __WEAK_LLSC_MB " \n" -#define smp_llsc_mb() do { } while (0) -#define __LLSC_CLOBBER "memory" +# define __WEAK_LLSC_MB +# define smp_llsc_mb() do { } while (0) +# define __LLSC_CLOBBER "memory" #endif #ifdef CONFIG_CPU_CAVIUM_OCTEON @@ -241,52 +119,22 @@ #define nudge_writes() mb() #endif -#define __smp_mb__before_atomic() __smp_mb__before_llsc() -#define __smp_mb__after_atomic() smp_llsc_mb() - /* - * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load, - * store or prefetch) in between an LL & SC can cause the SC instruction to - * erroneously succeed, breaking atomicity. Whilst it's unusual to write code - * containing such sequences, this bug bites harder than we might otherwise - * expect due to reordering & speculation: - * - * 1) A memory access appearing prior to the LL in program order may actually - * be executed after the LL - this is the reordering case. - * - * In order to avoid this we need to place a memory barrier (ie. a SYNC - * instruction) prior to every LL instruction, in between it and any earlier - * memory access instructions. - * - * This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later. - * - * 2) If a conditional branch exists between an LL & SC with a target outside - * of the LL-SC loop, for example an exit upon value mismatch in cmpxchg() - * or similar, then misprediction of the branch may allow speculative - * execution of memory accesses from outside of the LL-SC loop. - * - * In order to avoid this we need a memory barrier (ie. a SYNC instruction) - * at each affected branch target, for which we also use loongson_llsc_mb() - * defined below. - * - * This case affects all current Loongson 3 CPUs. - * - * The above described cases cause an error in the cache coherence protocol; - * such that the Invalidate of a competing LL-SC goes 'missing' and SC - * erroneously observes its core still has Exclusive state and lets the SC - * proceed. - * - * Therefore the error only occurs on SMP systems. + * In the Loongson3 LL/SC workaround case, all of our LL/SC loops already have + * a completion barrier immediately preceding the LL instruction. Therefore we + * can skip emitting a barrier from __smp_mb__before_atomic(). */ -#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */ -#define loongson_llsc_mb() __asm__ __volatile__("sync" : : :"memory") +#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS +# define __smp_mb__before_atomic() #else -#define loongson_llsc_mb() do { } while (0) +# define __smp_mb__before_atomic() __smp_mb__before_llsc() #endif +#define __smp_mb__after_atomic() smp_llsc_mb() + static inline void sync_ginv(void) { - asm volatile("sync\t%0" :: "i"(STYPE_GINV)); + asm volatile(__SYNC(ginv, always)); } #include <asm-generic/barrier.h> diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index 985d6a02f9ea..a74769940fbd 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -13,16 +13,55 @@ #error only <linux/bitops.h> can be included directly #endif +#include <linux/bits.h> #include <linux/compiler.h> #include <linux/types.h> #include <asm/barrier.h> #include <asm/byteorder.h> /* sigh ... */ #include <asm/compiler.h> #include <asm/cpu-features.h> +#include <asm/isa-rev.h> #include <asm/llsc.h> #include <asm/sgidefs.h> #include <asm/war.h> +#define __bit_op(mem, insn, inputs...) do { \ + unsigned long temp; \ + \ + asm volatile( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " __LL "%0, %1 \n" \ + " " insn " \n" \ + " " __SC "%0, %1 \n" \ + " " __SC_BEQZ "%0, 1b \n" \ + " .set pop \n" \ + : "=&r"(temp), "+" GCC_OFF_SMALL_ASM()(mem) \ + : inputs \ + : __LLSC_CLOBBER); \ +} while (0) + +#define __test_bit_op(mem, ll_dst, insn, inputs...) ({ \ + unsigned long orig, temp; \ + \ + asm volatile( \ + " .set push \n" \ + " .set " MIPS_ISA_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ + "1: " __LL ll_dst ", %2 \n" \ + " " insn " \n" \ + " " __SC "%1, %2 \n" \ + " " __SC_BEQZ "%1, 1b \n" \ + " .set pop \n" \ + : "=&r"(orig), "=&r"(temp), \ + "+" GCC_OFF_SMALL_ASM()(mem) \ + : inputs \ + : __LLSC_CLOBBER); \ + \ + orig; \ +}) + /* * These are the "slower" versions of the functions and are in bitops.c. * These functions call raw_local_irq_{save,restore}(). @@ -30,8 +69,6 @@ void __mips_set_bit(unsigned long nr, volatile unsigned long *addr); void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr); void __mips_change_bit(unsigned long nr, volatile unsigned long *addr); -int __mips_test_and_set_bit(unsigned long nr, - volatile unsigned long *addr); int __mips_test_and_set_bit_lock(unsigned long nr, volatile unsigned long *addr); int __mips_test_and_clear_bit(unsigned long nr, @@ -52,51 +89,20 @@ int __mips_test_and_change_bit(unsigned long nr, */ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - int bit = nr & SZLONG_MASK; - unsigned long temp; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; - if (kernel_uses_llsc && R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # set_bit \n" - " or %0, %2 \n" - " " __SC "%0, %1 \n" - " beqzl %0, 1b \n" - " .set pop \n" - : "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m) - : __LLSC_CLOBBER); -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) - } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " " __LL "%0, %1 # set_bit \n" - " " __INS "%0, %3, %2, 1 \n" - " " __SC "%0, %1 \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (bit), "r" (~0) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); -#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ - } else if (kernel_uses_llsc) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # set_bit \n" - " or %0, %2 \n" - " " __SC "%0, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); - } else + if (!kernel_uses_llsc) { __mips_set_bit(nr, addr); + return; + } + + if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(bit) && (bit >= 16)) { + __bit_op(*m, __INS "%0, %3, %2, 1", "i"(bit), "r"(~0)); + return; + } + + __bit_op(*m, "or\t%0, %2", "ir"(BIT(bit))); } /* @@ -111,51 +117,20 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) */ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - int bit = nr & SZLONG_MASK; - unsigned long temp; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; - if (kernel_uses_llsc && R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # clear_bit \n" - " and %0, %2 \n" - " " __SC "%0, %1 \n" - " beqzl %0, 1b \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (~(1UL << bit)) - : __LLSC_CLOBBER); -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) - } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " " __LL "%0, %1 # clear_bit \n" - " " __INS "%0, $0, %2, 1 \n" - " " __SC "%0, %1 \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); -#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ - } else if (kernel_uses_llsc) { - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # clear_bit \n" - " and %0, %2 \n" - " " __SC "%0, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (~(1UL << bit)) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); - } else + if (!kernel_uses_llsc) { __mips_clear_bit(nr, addr); + return; + } + + if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(bit)) { + __bit_op(*m, __INS "%0, $0, %2, 1", "i"(bit)); + return; + } + + __bit_op(*m, "and\t%0, %2", "ir"(~BIT(bit))); } /* @@ -183,159 +158,61 @@ static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *ad */ static inline void change_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # change_bit \n" - " xor %0, %2 \n" - " " __SC "%0, %1 \n" - " beqzl %0, 1b \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # change_bit \n" - " xor %0, %2 \n" - " " __SC "%0, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m) - : "ir" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); - } else + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + + if (!kernel_uses_llsc) { __mips_change_bit(nr, addr); + return; + } + + __bit_op(*m, "xor\t%0, %2", "ir"(BIT(bit))); } /* - * test_and_set_bit - Set a bit and return its old value + * test_and_set_bit_lock - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. + * This operation is atomic and implies acquire ordering semantics + * after the memory operation. */ -static inline int test_and_set_bit(unsigned long nr, +static inline int test_and_set_bit_lock(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + unsigned long res, orig; - smp_mb__before_llsc(); - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else - res = __mips_test_and_set_bit(nr, addr); + if (!kernel_uses_llsc) { + res = __mips_test_and_set_bit_lock(nr, addr); + } else { + orig = __test_bit_op(*m, "%0", + "or\t%1, %0, %3", + "ir"(BIT(bit))); + res = (orig & BIT(bit)) != 0; + } smp_llsc_mb(); - return res != 0; + return res; } /* - * test_and_set_bit_lock - Set a bit and return its old value + * test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * - * This operation is atomic and implies acquire ordering semantics - * after the memory operation. + * This operation is atomic and cannot be reordered. + * It also implies a memory barrier. */ -static inline int test_and_set_bit_lock(unsigned long nr, +static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+m" (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_set_bit \n" - " or %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else - res = __mips_test_and_set_bit_lock(nr, addr); - - smp_llsc_mb(); - - return res != 0; + smp_mb__before_atomic(); + return test_and_set_bit_lock(nr, addr); } + /* * test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear @@ -347,71 +224,30 @@ static inline int test_and_set_bit_lock(unsigned long nr, static inline int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; - - smp_mb__before_llsc(); + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + unsigned long res, orig; - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; + smp_mb__before_atomic(); - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_clear_bit \n" - " or %2, %0, %3 \n" - " xor %2, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) - } else if (kernel_uses_llsc && __builtin_constant_p(nr)) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " " __LL "%0, %1 # test_and_clear_bit \n" - " " __EXT "%2, %0, %3, 1 \n" - " " __INS "%0, $0, %3, 1 \n" - " " __SC "%0, %1 \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "ir" (bit) - : __LLSC_CLOBBER); - } while (unlikely(!temp)); -#endif - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_clear_bit \n" - " or %2, %0, %3 \n" - " xor %2, %3 \n" - " " __SC "%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else + if (!kernel_uses_llsc) { res = __mips_test_and_clear_bit(nr, addr); + } else if ((MIPS_ISA_REV >= 2) && __builtin_constant_p(nr)) { + res = __test_bit_op(*m, "%1", + __EXT "%0, %1, %3, 1;" + __INS "%1, $0, %3, 1", + "i"(bit)); + } else { + orig = __test_bit_op(*m, "%0", + "or\t%1, %0, %3;" + "xor\t%1, %1, %3", + "ir"(BIT(bit))); + res = (orig & BIT(bit)) != 0; + } smp_llsc_mb(); - return res != 0; + return res; } /* @@ -425,54 +261,29 @@ static inline int test_and_clear_bit(unsigned long nr, static inline int test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { - int bit = nr & SZLONG_MASK; - unsigned long res; + volatile unsigned long *m = &addr[BIT_WORD(nr)]; + int bit = nr % BITS_PER_LONG; + unsigned long res, orig; - smp_mb__before_llsc(); - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; + smp_mb__before_atomic(); - __asm__ __volatile__( - " .set push \n" - " .set arch=r4000 \n" - "1: " __LL "%0, %1 # test_and_change_bit \n" - " xor %2, %0, %3 \n" - " " __SC "%2, %1 \n" - " beqzl %2, 1b \n" - " and %2, %0, %3 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } else if (kernel_uses_llsc) { - unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); - unsigned long temp; - - loongson_llsc_mb(); - do { - __asm__ __volatile__( - " .set push \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " " __LL "%0, %1 # test_and_change_bit \n" - " xor %2, %0, %3 \n" - " " __SC "\t%2, %1 \n" - " .set pop \n" - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res) - : "r" (1UL << bit) - : __LLSC_CLOBBER); - } while (unlikely(!res)); - - res = temp & (1UL << bit); - } else + if (!kernel_uses_llsc) { res = __mips_test_and_change_bit(nr, addr); + } else { + orig = __test_bit_op(*m, "%0", + "xor\t%1, %0, %3", + "ir"(BIT(bit))); + res = (orig & BIT(bit)) != 0; + } smp_llsc_mb(); - return res != 0; + return res; } +#undef __bit_op +#undef __test_bit_op + #include <asm-generic/bitops/non-atomic.h> /* diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index 34d62229dea5..d41a5057bc69 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -61,7 +61,7 @@ /* * Valid machtype for Loongson family */ -enum loongson_machine_type { +enum loongson2ef_machine_type { MACH_LOONGSON_UNKNOWN, MACH_LEMOTE_FL2E, MACH_LEMOTE_FL2F, @@ -70,7 +70,6 @@ enum loongson_machine_type { MACH_DEXXON_GDIUM2F10, MACH_LEMOTE_NAS, MACH_LEMOTE_LL2F, - MACH_LOONGSON_GENERIC, MACH_LOONGSON_END }; @@ -99,6 +98,7 @@ extern void detect_memory_region(phys_addr_t start, phys_addr_t sz_min, phys_ad extern void prom_init(void); extern void prom_free_prom_memory(void); +extern void prom_cleanup(void); extern void free_init_pages(const char *what, unsigned long begin, unsigned long end); diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index d8ab8b7129b5..d72dc6e1cf3c 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -26,9 +26,8 @@ extern void check_bugs64(void); static inline void check_bugs_early(void) { -#ifdef CONFIG_64BIT - check_bugs64_early(); -#endif + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64_early(); } static inline void check_bugs(void) @@ -37,19 +36,18 @@ static inline void check_bugs(void) cpu_data[cpu].udelay_val = loops_per_jiffy; check_bugs32(); -#ifdef CONFIG_64BIT - check_bugs64(); -#endif + + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64(); } static inline int r4k_daddiu_bug(void) { -#ifdef CONFIG_64BIT + if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + return 0; + WARN_ON(daddiu_bug < 0); return daddiu_bug != 0; -#else - return 0; -#endif } #endif /* _ASM_BUGS_H */ diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index f6136871561d..5b0b3a6777ea 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -11,20 +11,11 @@ #include <linux/bug.h> #include <linux/irqflags.h> #include <asm/compiler.h> +#include <asm/llsc.h> +#include <asm/sync.h> #include <asm/war.h> /* - * Using a branch-likely instruction to check the result of an sc instruction - * works around a bug present in R10000 CPUs prior to revision 3.0 that could - * cause ll-sc sequences to execute non-atomically. - */ -#if R10000_LLSC_WAR -# define __scbeqz "beqzl" -#else -# define __scbeqz "beqz" -#endif - -/* * These functions doesn't exist, so if they are called you'll either: * * - Get an error at compile-time due to __compiletime_error, if supported by @@ -46,18 +37,18 @@ extern unsigned long __xchg_called_with_bad_pointer(void) __typeof(*(m)) __ret; \ \ if (kernel_uses_llsc) { \ - loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ " .set push \n" \ " .set " MIPS_ISA_ARCH_LEVEL " \n" \ + " " __SYNC(full, loongson3_war) " \n" \ "1: " ld " %0, %2 # __xchg_asm \n" \ " .set pop \n" \ " move $1, %z3 \n" \ " .set " MIPS_ISA_ARCH_LEVEL " \n" \ " " st " $1, %1 \n" \ - "\t" __scbeqz " $1, 1b \n" \ + "\t" __SC_BEQZ "$1, 1b \n" \ " .set pop \n" \ : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) \ @@ -103,7 +94,13 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size) ({ \ __typeof__(*(ptr)) __res; \ \ - smp_mb__before_llsc(); \ + /* \ + * In the Loongson3 workaround case __xchg_asm() already \ + * contains a completion barrier prior to the LL, so we don't \ + * need to emit an extra one here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_mb__before_llsc(); \ \ __res = (__typeof__(*(ptr))) \ __xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ @@ -118,25 +115,24 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size) __typeof(*(m)) __ret; \ \ if (kernel_uses_llsc) { \ - loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ " .set push \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ + " " __SYNC(full, loongson3_war) " \n" \ "1: " ld " %0, %2 # __cmpxchg_asm \n" \ " bne %0, %z3, 2f \n" \ " .set pop \n" \ " move $1, %z4 \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ " " st " $1, %1 \n" \ - "\t" __scbeqz " $1, 1b \n" \ + "\t" __SC_BEQZ "$1, 1b \n" \ " .set pop \n" \ - "2: \n" \ + "2: " __SYNC(full, loongson3_war) " \n" \ : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ : GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new) \ : __LLSC_CLOBBER); \ - loongson_llsc_mb(); \ } else { \ unsigned long __flags; \ \ @@ -190,9 +186,23 @@ unsigned long __cmpxchg(volatile void *ptr, unsigned long old, ({ \ __typeof__(*(ptr)) __res; \ \ - smp_mb__before_llsc(); \ + /* \ + * In the Loongson3 workaround case __cmpxchg_asm() already \ + * contains a completion barrier prior to the LL, so we don't \ + * need to emit an extra one here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_mb__before_llsc(); \ + \ __res = cmpxchg_local((ptr), (old), (new)); \ - smp_llsc_mb(); \ + \ + /* \ + * In the Loongson3 workaround case __cmpxchg_asm() already \ + * contains a completion barrier after the SC, so we don't \ + * need to emit an extra one here. \ + */ \ + if (!__SYNC_loongson3_war) \ + smp_llsc_mb(); \ \ __res; \ }) @@ -233,11 +243,11 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, */ local_irq_save(flags); - loongson_llsc_mb(); asm volatile( " .set push \n" " .set " MIPS_ISA_ARCH_LEVEL " \n" /* Load 64 bits from ptr */ + " " __SYNC(full, loongson3_war) " \n" "1: lld %L0, %3 # __cmpxchg64 \n" /* * Split the 64 bit value we loaded into the 2 registers that hold the @@ -269,9 +279,9 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, /* Attempt to store new at ptr */ " scd %L1, %2 \n" /* If we failed, loop! */ - "\t" __scbeqz " %L1, 1b \n" + "\t" __SC_BEQZ "%L1, 1b \n" " .set pop \n" - "2: \n" + "2: " __SYNC(full, loongson3_war) " \n" : "=&r"(ret), "=&r"(tmp), "=" GCC_OFF_SMALL_ASM() (*(unsigned long long *)ptr) @@ -279,7 +289,6 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, "r" (old), "r" (new) : "memory"); - loongson_llsc_mb(); local_irq_restore(flags); return ret; @@ -312,6 +321,4 @@ static inline unsigned long __cmpxchg64(volatile void *ptr, # endif /* !CONFIG_SMP */ #endif /* !CONFIG_64BIT */ -#undef __scbeqz - #endif /* __ASM_CMPXCHG_H */ diff --git a/arch/mips/include/asm/cop2.h b/arch/mips/include/asm/cop2.h index 63b3468ede4c..6b7396a6a115 100644 --- a/arch/mips/include/asm/cop2.h +++ b/arch/mips/include/asm/cop2.h @@ -33,7 +33,7 @@ extern void nlm_cop2_restore(struct nlm_cop2_state *); #define cop2_present 1 #define cop2_lazy_restore 0 -#elif defined(CONFIG_CPU_LOONGSON3) +#elif defined(CONFIG_CPU_LOONGSON64) #define cop2_present 1 #define cop2_lazy_restore 1 diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 7bbb66760a07..c46c59b0f1b4 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -15,18 +15,17 @@ static inline int __pure __get_cpu_type(const int cpu_type) { switch (cpu_type) { -#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2E) || \ - defined(CONFIG_SYS_HAS_CPU_LOONGSON2F) - case CPU_LOONGSON2: +#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2EF) + case CPU_LOONGSON2EF: #endif -#ifdef CONFIG_SYS_HAS_CPU_LOONGSON3 - case CPU_LOONGSON3: +#ifdef CONFIG_SYS_HAS_CPU_LOONGSON64 + case CPU_LOONGSON64: #endif #if defined(CONFIG_SYS_HAS_CPU_LOONGSON1B) || \ defined(CONFIG_SYS_HAS_CPU_LOONGSON1C) - case CPU_LOONGSON1: + case CPU_LOONGSON32: #endif #ifdef CONFIG_SYS_HAS_CPU_MIPS32_R1 diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 7fddcb8350c6..ea830783d663 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -91,7 +91,9 @@ #define PRID_IMP_LOONGSON_32 0x4200 /* Loongson-1 */ #define PRID_IMP_R5432 0x5400 #define PRID_IMP_R5500 0x5500 -#define PRID_IMP_LOONGSON_64 0x6300 /* Loongson-2/3 */ +#define PRID_IMP_LOONGSON_64R 0x6100 /* Reduced Loongson-2 */ +#define PRID_IMP_LOONGSON_64C 0x6300 /* Classic Loongson-2 and Loongson-3 */ +#define PRID_IMP_LOONGSON_64G 0xc000 /* Generic Loongson-2 and Loongson-3 */ #define PRID_IMP_UNKNOWN 0xff00 @@ -310,15 +312,15 @@ enum cpu_type_enum { */ CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K, CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350, - CPU_BMIPS4380, CPU_BMIPS5000, CPU_XBURST, CPU_LOONGSON1, CPU_M14KC, + CPU_BMIPS4380, CPU_BMIPS5000, CPU_XBURST, CPU_LOONGSON32, CPU_M14KC, CPU_M14KEC, CPU_INTERAPTIV, CPU_P5600, CPU_PROAPTIV, CPU_1074K, CPU_M5150, CPU_I6400, CPU_P6600, CPU_M6250, /* * MIPS64 class processors */ - CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, - CPU_LOONGSON3, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, + CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2EF, + CPU_LOONGSON64, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP, CPU_I6500, CPU_QEMU_GENERIC, diff --git a/arch/mips/include/asm/fixmap.h b/arch/mips/include/asm/fixmap.h index 6842ffafd1e7..1784d4348c36 100644 --- a/arch/mips/include/asm/fixmap.h +++ b/arch/mips/include/asm/fixmap.h @@ -70,7 +70,7 @@ enum fixed_addresses { #include <asm-generic/fixmap.h> #define kmap_get_fixmap_pte(vaddr) \ - pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr)), (vaddr)) + pte_offset_kernel(pmd_offset(pud_offset(p4d_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr)), (vaddr)), (vaddr)) /* * Called from pgtable_init() diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index b83b0397462d..110220705e97 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -16,6 +16,7 @@ #include <asm/barrier.h> #include <asm/compiler.h> #include <asm/errno.h> +#include <asm/sync.h> #include <asm/war.h> #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ @@ -32,7 +33,7 @@ " .set arch=r4000 \n" \ "2: sc $1, %2 \n" \ " beqzl $1, 1b \n" \ - __WEAK_LLSC_MB \ + __stringify(__WEAK_LLSC_MB) " \n" \ "3: \n" \ " .insn \n" \ " .set pop \n" \ @@ -50,19 +51,19 @@ "i" (-EFAULT) \ : "memory"); \ } else if (cpu_has_llsc) { \ - loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ " .set push \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ + " " __SYNC(full, loongson3_war) " \n" \ "1: "user_ll("%1", "%4")" # __futex_atomic_op\n" \ " .set pop \n" \ " " insn " \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ "2: "user_sc("$1", "%2")" \n" \ " beqz $1, 1b \n" \ - __WEAK_LLSC_MB \ + __stringify(__WEAK_LLSC_MB) " \n" \ "3: \n" \ " .insn \n" \ " .set pop \n" \ @@ -147,7 +148,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, " .set arch=r4000 \n" "2: sc $1, %2 \n" " beqzl $1, 1b \n" - __WEAK_LLSC_MB + __stringify(__WEAK_LLSC_MB) " \n" "3: \n" " .insn \n" " .set pop \n" @@ -164,13 +165,13 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, "i" (-EFAULT) : "memory"); } else if (cpu_has_llsc) { - loongson_llsc_mb(); __asm__ __volatile__( "# futex_atomic_cmpxchg_inatomic \n" " .set push \n" " .set noat \n" " .set push \n" " .set "MIPS_ISA_ARCH_LEVEL" \n" + " " __SYNC(full, loongson3_war) " \n" "1: "user_ll("%1", "%3")" \n" " bne %1, %z4, 3f \n" " .set pop \n" @@ -178,8 +179,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, " .set "MIPS_ISA_ARCH_LEVEL" \n" "2: "user_sc("$1", "%2")" \n" " beqz $1, 1b \n" - __WEAK_LLSC_MB - "3: \n" + "3: " __SYNC_ELSE(full, loongson3_war, __WEAK_LLSC_MB) "\n" " .insn \n" " .set pop \n" " .section .fixup,\"ax\" \n" @@ -194,7 +194,6 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory"); - loongson_llsc_mb(); } else return -ENOSYS; diff --git a/arch/mips/include/asm/hazards.h b/arch/mips/include/asm/hazards.h index 0fa27446869a..a4f48b0f5541 100644 --- a/arch/mips/include/asm/hazards.h +++ b/arch/mips/include/asm/hazards.h @@ -158,7 +158,7 @@ do { \ } while (0) #elif defined(CONFIG_MIPS_ALCHEMY) || defined(CONFIG_CPU_CAVIUM_OCTEON) || \ - defined(CONFIG_CPU_LOONGSON2) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \ + defined(CONFIG_CPU_LOONGSON2EF) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \ defined(CONFIG_CPU_R10000) || defined(CONFIG_CPU_R5500) || defined(CONFIG_CPU_XLR) /* diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index 2b7b56736372..3f6ce74335b4 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -306,7 +306,7 @@ static inline void iounmap(const volatile void __iomem *addr) #undef __IS_KSEG1 } -#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON3) +#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON64) #define war_io_reorder_wmb() wmb() #else #define war_io_reorder_wmb() barrier() diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h index f0b862a83816..c4728bbdf15b 100644 --- a/arch/mips/include/asm/irqflags.h +++ b/arch/mips/include/asm/irqflags.h @@ -41,7 +41,7 @@ static inline unsigned long arch_local_irq_save(void) " .set push \n" " .set reorder \n" " .set noat \n" -#if defined(CONFIG_CPU_LOONGSON3) || defined (CONFIG_CPU_LOONGSON1) +#if defined(CONFIG_CPU_LOONGSON64) || defined(CONFIG_CPU_LOONGSON32) " mfc0 %[flags], $12 \n" " di \n" #else diff --git a/arch/mips/include/asm/llsc.h b/arch/mips/include/asm/llsc.h index c6d17d171147..c49738bc3bda 100644 --- a/arch/mips/include/asm/llsc.h +++ b/arch/mips/include/asm/llsc.h @@ -9,20 +9,31 @@ #ifndef __ASM_LLSC_H #define __ASM_LLSC_H +#include <asm/isa-rev.h> + #if _MIPS_SZLONG == 32 -#define SZLONG_LOG 5 -#define SZLONG_MASK 31UL #define __LL "ll " #define __SC "sc " #define __INS "ins " #define __EXT "ext " #elif _MIPS_SZLONG == 64 -#define SZLONG_LOG 6 -#define SZLONG_MASK 63UL #define __LL "lld " #define __SC "scd " #define __INS "dins " #define __EXT "dext " #endif +/* + * Using a branch-likely instruction to check the result of an sc instruction + * works around a bug present in R10000 CPUs prior to revision 3.0 that could + * cause ll-sc sequences to execute non-atomically. + */ +#if R10000_LLSC_WAR +# define __SC_BEQZ "beqzl " +#elif MIPS_ISA_REV >= 6 +# define __SC_BEQZ "beqzc " +#else +# define __SC_BEQZ "beqz " +#endif + #endif /* __ASM_LLSC_H */ diff --git a/arch/mips/include/asm/mach-ip22/spaces.h b/arch/mips/include/asm/mach-ip22/spaces.h index 7f9fa6f66059..24fe92cb5313 100644 --- a/arch/mips/include/asm/mach-ip22/spaces.h +++ b/arch/mips/include/asm/mach-ip22/spaces.h @@ -10,17 +10,7 @@ #ifndef _ASM_MACH_IP22_SPACES_H #define _ASM_MACH_IP22_SPACES_H - -#ifdef CONFIG_64BIT - -#define PAGE_OFFSET 0xffffffff80000000UL - -#define CAC_BASE 0xffffffff80000000 -#define IO_BASE 0xffffffffa0000000 -#define UNCAC_BASE 0xffffffffa0000000 -#define MAP_BASE 0xc000000000000000 - -#endif /* CONFIG_64BIT */ +#define PHYS_OFFSET _AC(0x08000000, UL) #include <asm/mach-generic/spaces.h> diff --git a/arch/mips/include/asm/mach-ip27/mmzone.h b/arch/mips/include/asm/mach-ip27/mmzone.h index 1cd6a23a84f2..f463826515df 100644 --- a/arch/mips/include/asm/mach-ip27/mmzone.h +++ b/arch/mips/include/asm/mach-ip27/mmzone.h @@ -6,7 +6,7 @@ #include <asm/sn/arch.h> #include <asm/sn/hub.h> -#define pa_to_nid(addr) NASID_TO_COMPACT_NODEID(NASID_GET(addr)) +#define pa_to_nid(addr) NASID_GET(addr) struct hub_data { kern_vars_t kern_vars; diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h index 965f0793a5f9..be61ddcdacab 100644 --- a/arch/mips/include/asm/mach-ip27/topology.h +++ b/arch/mips/include/asm/mach-ip27/topology.h @@ -7,14 +7,13 @@ #include <asm/mmzone.h> struct cpuinfo_ip27 { - cnodeid_t p_nodeid; /* my node ID in compact-id-space */ nasid_t p_nasid; /* my node ID in numa-as-id-space */ unsigned char p_slice; /* Physical position on node board */ }; extern struct cpuinfo_ip27 sn_cpu_info[NR_CPUS]; -#define cpu_to_node(cpu) (sn_cpu_info[(cpu)].p_nodeid) +#define cpu_to_node(cpu) (cputonasid(cpu)) #define cpumask_of_node(node) ((node) == -1 ? \ cpu_all_mask : \ &hub_data(node)->h_cpus) @@ -23,7 +22,7 @@ extern int pcibus_to_node(struct pci_bus *); #define cpumask_of_pcibus(bus) (cpumask_of_node(pcibus_to_node(bus))) -extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES]; +extern unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES]; #define node_distance(from, to) (__node_distances[(from)][(to)]) diff --git a/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h new file mode 100644 index 000000000000..cfa02f3d25df --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/cpu-feature-overrides.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * IP30/Octane cpu-features overrides. + * + * Copyright (C) 2003 Ralf Baechle <ralf@linux-mips.org> + * 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * 2009 Johannes Dickgreber <tanzy@gmx.de> + * 2015 Joshua Kinard <kumba@gentoo.org> + * + */ +#ifndef __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H +#define __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H + +#include <asm/cpu.h> + +/* + * IP30 only supports R1[024]000 processors, all using the same config + */ +#define cpu_has_tlb 1 +#define cpu_has_tlbinv 0 +#define cpu_has_segments 0 +#define cpu_has_eva 0 +#define cpu_has_htw 0 +#define cpu_has_rixiex 0 +#define cpu_has_maar 0 +#define cpu_has_rw_llb 0 +#define cpu_has_3kex 0 +#define cpu_has_4kex 1 +#define cpu_has_3k_cache 0 +#define cpu_has_4k_cache 1 +#define cpu_has_6k_cache 0 +#define cpu_has_8k_cache 0 +#define cpu_has_tx39_cache 0 +#define cpu_has_fpu 1 +#define cpu_has_nofpuex 0 +#define cpu_has_32fpr 1 +#define cpu_has_counter 1 +#define cpu_has_watch 1 +#define cpu_has_64bits 1 +#define cpu_has_divec 0 +#define cpu_has_vce 0 +#define cpu_has_cache_cdex_p 0 +#define cpu_has_cache_cdex_s 0 +#define cpu_has_prefetch 1 +#define cpu_has_mcheck 0 +#define cpu_has_ejtag 0 +#define cpu_has_llsc 1 +#define cpu_has_mips16 0 +#define cpu_has_mdmx 0 +#define cpu_has_mips3d 0 +#define cpu_has_smartmips 0 +#define cpu_has_rixi 0 +#define cpu_has_xpa 0 +#define cpu_has_vtag_icache 0 +#define cpu_has_dc_aliases 0 +#define cpu_has_ic_fills_f_dc 0 + +#define cpu_icache_snoops_remote_store 1 + +#define cpu_has_mips32r1 0 +#define cpu_has_mips32r2 0 +#define cpu_has_mips64r1 0 +#define cpu_has_mips64r2 0 +#define cpu_has_mips32r6 0 +#define cpu_has_mips64r6 0 + +#define cpu_has_dsp 0 +#define cpu_has_dsp2 0 +#define cpu_has_mipsmt 0 +#define cpu_has_userlocal 0 +#define cpu_has_inclusive_pcaches 1 +#define cpu_hwrena_impl_bits 0 +#define cpu_has_perf_cntr_intr_bit 0 +#define cpu_has_vz 0 +#define cpu_has_fre 0 +#define cpu_has_cdmm 0 + +#define cpu_dcache_line_size() 32 +#define cpu_icache_line_size() 64 +#define cpu_scache_line_size() 128 + +#endif /* __ASM_MACH_IP30_CPU_FEATURE_OVERRIDES_H */ + diff --git a/arch/mips/include/asm/mach-ip30/irq.h b/arch/mips/include/asm/mach-ip30/irq.h new file mode 100644 index 000000000000..e5c3dd965266 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/irq.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HEART IRQ defines + * + * Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de> + * 2014-2016 Joshua Kinard <kumba@gentoo.org> + * + */ + +#ifndef __ASM_MACH_IP30_IRQ_H +#define __ASM_MACH_IP30_IRQ_H + +/* + * HEART has 64 hardware interrupts, but use 128 to leave room for a few + * software interrupts as well (such as the CPU timer interrupt. + */ +#define NR_IRQS 128 + +extern void __init ip30_install_ipi(void); + +/* + * HEART has 64 interrupt vectors available to it, subdivided into five + * priority levels. They are numbered 0 to 63. + */ +#define HEART_NUM_IRQS 64 + +/* + * These are the five interrupt priority levels and their corresponding + * CPU IPx interrupt pins. + * + * Level 4 - Error Interrupts. + * Level 3 - HEART timer interrupt. + * Level 2 - CPU IPI, CPU debug, power putton, general device interrupts. + * Level 1 - General device interrupts. + * Level 0 - General device GFX flow control interrupts. + */ +#define HEART_L4_INT_MASK 0xfff8000000000000ULL /* IP6 */ +#define HEART_L3_INT_MASK 0x0004000000000000ULL /* IP5 */ +#define HEART_L2_INT_MASK 0x0003ffff00000000ULL /* IP4 */ +#define HEART_L1_INT_MASK 0x00000000ffff0000ULL /* IP3 */ +#define HEART_L0_INT_MASK 0x000000000000ffffULL /* IP2 */ + +/* HEART L0 Interrupts (Low Priority) */ +#define HEART_L0_INT_GENERIC 0 +#define HEART_L0_INT_FLOW_CTRL_HWTR_0 1 +#define HEART_L0_INT_FLOW_CTRL_HWTR_1 2 + +/* HEART L2 Interrupts (High Priority) */ +#define HEART_L2_INT_RESCHED_CPU_0 46 +#define HEART_L2_INT_RESCHED_CPU_1 47 +#define HEART_L2_INT_CALL_CPU_0 48 +#define HEART_L2_INT_CALL_CPU_1 49 + +/* HEART L3 Interrupts (Compare/Counter Timer) */ +#define HEART_L3_INT_TIMER 50 + +/* HEART L4 Interrupts (Errors) */ +#define HEART_L4_INT_XWID_ERR_9 51 +#define HEART_L4_INT_XWID_ERR_A 52 +#define HEART_L4_INT_XWID_ERR_B 53 +#define HEART_L4_INT_XWID_ERR_C 54 +#define HEART_L4_INT_XWID_ERR_D 55 +#define HEART_L4_INT_XWID_ERR_E 56 +#define HEART_L4_INT_XWID_ERR_F 57 +#define HEART_L4_INT_XWID_ERR_XBOW 58 +#define HEART_L4_INT_CPU_BUS_ERR_0 59 +#define HEART_L4_INT_CPU_BUS_ERR_1 60 +#define HEART_L4_INT_CPU_BUS_ERR_2 61 +#define HEART_L4_INT_CPU_BUS_ERR_3 62 +#define HEART_L4_INT_HEART_EXCP 63 + +/* + * Power Switch is wired via BaseIO BRIDGE slot #6. + * + * ACFail is wired via BaseIO BRIDGE slot #7. + */ +#define IP30_POWER_IRQ HEART_L2_INT_POWER_BTN + +#include_next <irq.h> + +#define IP30_HEART_L0_IRQ (MIPS_CPU_IRQ_BASE + 2) +#define IP30_HEART_L1_IRQ (MIPS_CPU_IRQ_BASE + 3) +#define IP30_HEART_L2_IRQ (MIPS_CPU_IRQ_BASE + 4) +#define IP30_HEART_TIMER_IRQ (MIPS_CPU_IRQ_BASE + 5) +#define IP30_HEART_ERR_IRQ (MIPS_CPU_IRQ_BASE + 6) + +#endif /* __ASM_MACH_IP30_IRQ_H */ diff --git a/arch/mips/include/asm/mach-ip30/kernel-entry-init.h b/arch/mips/include/asm/mach-ip30/kernel-entry-init.h new file mode 100644 index 000000000000..be0472c977d8 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/kernel-entry-init.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_MACH_IP30_KERNEL_ENTRY_H +#define __ASM_MACH_IP30_KERNEL_ENTRY_H + + .macro kernel_entry_setup + .endm + + .macro smp_slave_setup + move gp, a0 + .endm + +#endif /* __ASM_MACH_IP30_KERNEL_ENTRY_H */ diff --git a/arch/mips/include/asm/mach-ip30/mangle-port.h b/arch/mips/include/asm/mach-ip30/mangle-port.h new file mode 100644 index 000000000000..f3e1262a2d5e --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/mangle-port.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2003, 2004 Ralf Baechle + */ +#ifndef __ASM_MACH_IP30_MANGLE_PORT_H +#define __ASM_MACH_IP30_MANGLE_PORT_H + +#define __swizzle_addr_b(port) ((port)^3) +#define __swizzle_addr_w(port) ((port)^2) +#define __swizzle_addr_l(port) (port) +#define __swizzle_addr_q(port) (port) + +#define ioswabb(a, x) (x) +#define __mem_ioswabb(a, x) (x) +#define ioswabw(a, x) (x) +#define __mem_ioswabw(a, x) cpu_to_le16(x) +#define ioswabl(a, x) (x) +#define __mem_ioswabl(a, x) cpu_to_le32(x) +#define ioswabq(a, x) (x) +#define __mem_ioswabq(a, x) cpu_to_le64(x) + +#endif /* __ASM_MACH_IP30_MANGLE_PORT_H */ diff --git a/arch/mips/include/asm/mach-ip30/spaces.h b/arch/mips/include/asm/mach-ip30/spaces.h new file mode 100644 index 000000000000..c8a302dfbe05 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/spaces.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2016 Joshua Kinard <kumba@gentoo.org> + * + */ +#ifndef _ASM_MACH_IP30_SPACES_H +#define _ASM_MACH_IP30_SPACES_H + +/* + * Memory in IP30/Octane is offset 512MB in the physical address space. + */ +#define PHYS_OFFSET _AC(0x20000000, UL) + +#ifdef CONFIG_64BIT +#define CAC_BASE _AC(0xA800000000000000, UL) +#endif + +#include <asm/mach-generic/spaces.h> + +#endif /* _ASM_MACH_IP30_SPACES_H */ diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h new file mode 100644 index 000000000000..a98ba204f183 --- /dev/null +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org> + */ +#ifndef __ASM_MIPS_MACH_IP30_WAR_H +#define __ASM_MIPS_MACH_IP30_WAR_H + +#define R4600_V1_INDEX_ICACHEOP_WAR 0 +#define R4600_V1_HIT_CACHEOP_WAR 0 +#define R4600_V2_HIT_CACHEOP_WAR 0 +#define MIPS_CACHE_SYNC_WAR 0 +#define BCM1250_M3_WAR 0 +#define SIBYTE_1956_WAR 0 +#define MIPS4K_ICACHE_REFILL_WAR 0 +#define MIPS34K_MISSED_ITLB_WAR 0 +#define R5432_CP0_INTERRUPT_WAR 0 +#define TX49XX_ICACHE_INDEX_INV_WAR 0 +#define ICACHE_REFILLS_WORKAROUND_WAR 0 + +#ifdef CONFIG_CPU_R10000 +#define R10000_LLSC_WAR 1 +#else +#define R10000_LLSC_WAR 0 +#endif + +#endif /* __ASM_MIPS_MACH_IP30_WAR_H */ diff --git a/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h new file mode 100644 index 000000000000..b2ee859ca0b7 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/cpu-feature-overrides.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2009 Wu Zhangjin <wuzhangjin@gmail.com> + * Copyright (C) 2009 Philippe Vachon <philippe@cowpig.ca> + * Copyright (C) 2009 Zhang Le <r0bertz@gentoo.org> + * + * reference: /proc/cpuinfo, + * arch/mips/kernel/cpu-probe.c(cpu_probe_legacy), + * arch/mips/kernel/proc.c(show_cpuinfo), + * loongson2f user manual. + */ + +#ifndef __ASM_MACH_LOONGSON2EF_CPU_FEATURE_OVERRIDES_H +#define __ASM_MACH_LOONGSON2EF_CPU_FEATURE_OVERRIDES_H + +#define cpu_has_32fpr 1 +#define cpu_has_3k_cache 0 +#define cpu_has_4k_cache 1 +#define cpu_has_4kex 1 +#define cpu_has_64bits 1 +#define cpu_has_cache_cdex_p 0 +#define cpu_has_cache_cdex_s 0 +#define cpu_has_counter 1 +#define cpu_has_dc_aliases (PAGE_SIZE < 0x4000) +#define cpu_has_divec 0 +#define cpu_has_ejtag 0 +#define cpu_has_inclusive_pcaches 1 +#define cpu_has_llsc 1 +#define cpu_has_mcheck 0 +#define cpu_has_mdmx 0 +#define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 +#define cpu_has_mips3d 0 +#define cpu_has_mipsmt 0 +#define cpu_has_smartmips 0 +#define cpu_has_tlb 1 +#define cpu_has_tx39_cache 0 +#define cpu_has_vce 0 +#define cpu_has_veic 0 +#define cpu_has_vint 0 +#define cpu_has_vtag_icache 0 +#define cpu_has_watch 1 + +#endif /* __ASM_MACH_LOONGSON64_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536.h index 9795b3361532..9795b3361532 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536.h diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_mfgpt.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_mfgpt.h index 52e8bb0fc04d..52e8bb0fc04d 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_mfgpt.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_mfgpt.h diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_pci.h index a0d4b752899e..a0d4b752899e 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_pci.h diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_vsm.h b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_vsm.h index 70d0153cccc3..70d0153cccc3 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_vsm.h +++ b/arch/mips/include/asm/mach-loongson2ef/cs5536/cs5536_vsm.h diff --git a/arch/mips/include/asm/mach-loongson2ef/loongson.h b/arch/mips/include/asm/mach-loongson2ef/loongson.h new file mode 100644 index 000000000000..5008af0a1a19 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/loongson.h @@ -0,0 +1,326 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2009 Lemote, Inc. + * Author: Wu Zhangjin <wuzhangjin@gmail.com> + */ + +#ifndef __ASM_MACH_LOONGSON2EF_LOONGSON_H +#define __ASM_MACH_LOONGSON2EF_LOONGSON_H + +#include <linux/io.h> +#include <linux/init.h> +#include <linux/irq.h> + +/* loongson internal northbridge initialization */ +extern void bonito_irq_init(void); + +/* machine-specific reboot/halt operation */ +extern void mach_prepare_reboot(void); +extern void mach_prepare_shutdown(void); + +/* environment arguments from bootloader */ +extern u32 cpu_clock_freq; +extern u32 memsize, highmemsize; + +/* loongson-specific command line, env and memory initialization */ +extern void __init prom_init_memory(void); +extern void __init prom_init_machtype(void); +extern void __init prom_init_env(void); +#ifdef CONFIG_LOONGSON_UART_BASE +extern unsigned long _loongson_uart_base, loongson_uart_base; +extern void prom_init_loongson_uart_base(void); +#endif + +static inline void prom_init_uart_base(void) +{ +#ifdef CONFIG_LOONGSON_UART_BASE + prom_init_loongson_uart_base(); +#endif +} + +/* irq operation functions */ +extern void bonito_irqdispatch(void); +extern void __init bonito_irq_init(void); +extern void __init mach_init_irq(void); +extern void mach_irq_dispatch(unsigned int pending); +extern int mach_i8259_irq(void); + +/* We need this in some places... */ +#define delay() ({ \ + int x; \ + for (x = 0; x < 100000; x++) \ + __asm__ __volatile__(""); \ +}) + +#define LOONGSON_REG(x) \ + (*(volatile u32 *)((char *)CKSEG1ADDR(LOONGSON_REG_BASE) + (x))) + +#define LOONGSON_IRQ_BASE 32 +#define LOONGSON2_PERFCNT_IRQ (MIPS_CPU_IRQ_BASE + 6) /* cpu perf counter */ + +#include <linux/interrupt.h> +static inline void do_perfcnt_IRQ(void) +{ +#if IS_ENABLED(CONFIG_OPROFILE) + do_IRQ(LOONGSON2_PERFCNT_IRQ); +#endif +} + +#define LOONGSON_FLASH_BASE 0x1c000000 +#define LOONGSON_FLASH_SIZE 0x02000000 /* 32M */ +#define LOONGSON_FLASH_TOP (LOONGSON_FLASH_BASE+LOONGSON_FLASH_SIZE-1) + +#define LOONGSON_LIO0_BASE 0x1e000000 +#define LOONGSON_LIO0_SIZE 0x01C00000 /* 28M */ +#define LOONGSON_LIO0_TOP (LOONGSON_LIO0_BASE+LOONGSON_LIO0_SIZE-1) + +#define LOONGSON_BOOT_BASE 0x1fc00000 +#define LOONGSON_BOOT_SIZE 0x00100000 /* 1M */ +#define LOONGSON_BOOT_TOP (LOONGSON_BOOT_BASE+LOONGSON_BOOT_SIZE-1) +#define LOONGSON_REG_BASE 0x1fe00000 +#define LOONGSON_REG_SIZE 0x00100000 /* 256Bytes + 256Bytes + ??? */ +#define LOONGSON_REG_TOP (LOONGSON_REG_BASE+LOONGSON_REG_SIZE-1) + +#define LOONGSON_LIO1_BASE 0x1ff00000 +#define LOONGSON_LIO1_SIZE 0x00100000 /* 1M */ +#define LOONGSON_LIO1_TOP (LOONGSON_LIO1_BASE+LOONGSON_LIO1_SIZE-1) + +#define LOONGSON_PCILO0_BASE 0x10000000 +#define LOONGSON_PCILO1_BASE 0x14000000 +#define LOONGSON_PCILO2_BASE 0x18000000 +#define LOONGSON_PCILO_BASE LOONGSON_PCILO0_BASE +#define LOONGSON_PCILO_SIZE 0x0c000000 /* 64M * 3 */ +#define LOONGSON_PCILO_TOP (LOONGSON_PCILO0_BASE+LOONGSON_PCILO_SIZE-1) + +#define LOONGSON_PCICFG_BASE 0x1fe80000 +#define LOONGSON_PCICFG_SIZE 0x00000800 /* 2K */ +#define LOONGSON_PCICFG_TOP (LOONGSON_PCICFG_BASE+LOONGSON_PCICFG_SIZE-1) +#define LOONGSON_PCIIO_BASE 0x1fd00000 + +#define LOONGSON_PCIIO_SIZE 0x00100000 /* 1M */ +#define LOONGSON_PCIIO_TOP (LOONGSON_PCIIO_BASE+LOONGSON_PCIIO_SIZE-1) + +/* Loongson Register Bases */ + +#define LOONGSON_PCICONFIGBASE 0x00 +#define LOONGSON_REGBASE 0x100 + +/* PCI Configuration Registers */ + +#define LOONGSON_PCI_REG(x) LOONGSON_REG(LOONGSON_PCICONFIGBASE + (x)) +#define LOONGSON_PCIDID LOONGSON_PCI_REG(0x00) +#define LOONGSON_PCICMD LOONGSON_PCI_REG(0x04) +#define LOONGSON_PCICLASS LOONGSON_PCI_REG(0x08) +#define LOONGSON_PCILTIMER LOONGSON_PCI_REG(0x0c) +#define LOONGSON_PCIBASE0 LOONGSON_PCI_REG(0x10) +#define LOONGSON_PCIBASE1 LOONGSON_PCI_REG(0x14) +#define LOONGSON_PCIBASE2 LOONGSON_PCI_REG(0x18) +#define LOONGSON_PCIBASE3 LOONGSON_PCI_REG(0x1c) +#define LOONGSON_PCIBASE4 LOONGSON_PCI_REG(0x20) +#define LOONGSON_PCIEXPRBASE LOONGSON_PCI_REG(0x30) +#define LOONGSON_PCIINT LOONGSON_PCI_REG(0x3c) + +#define LOONGSON_PCI_ISR4C LOONGSON_PCI_REG(0x4c) + +#define LOONGSON_PCICMD_PERR_CLR 0x80000000 +#define LOONGSON_PCICMD_SERR_CLR 0x40000000 +#define LOONGSON_PCICMD_MABORT_CLR 0x20000000 +#define LOONGSON_PCICMD_MTABORT_CLR 0x10000000 +#define LOONGSON_PCICMD_TABORT_CLR 0x08000000 +#define LOONGSON_PCICMD_MPERR_CLR 0x01000000 +#define LOONGSON_PCICMD_PERRRESPEN 0x00000040 +#define LOONGSON_PCICMD_ASTEPEN 0x00000080 +#define LOONGSON_PCICMD_SERREN 0x00000100 +#define LOONGSON_PCILTIMER_BUSLATENCY 0x0000ff00 +#define LOONGSON_PCILTIMER_BUSLATENCY_SHIFT 8 + +/* Loongson h/w Configuration */ + +#define LOONGSON_GENCFG_OFFSET 0x4 +#define LOONGSON_GENCFG LOONGSON_REG(LOONGSON_REGBASE + LOONGSON_GENCFG_OFFSET) + +#define LOONGSON_GENCFG_DEBUGMODE 0x00000001 +#define LOONGSON_GENCFG_SNOOPEN 0x00000002 +#define LOONGSON_GENCFG_CPUSELFRESET 0x00000004 + +#define LOONGSON_GENCFG_FORCE_IRQA 0x00000008 +#define LOONGSON_GENCFG_IRQA_ISOUT 0x00000010 +#define LOONGSON_GENCFG_IRQA_FROM_INT1 0x00000020 +#define LOONGSON_GENCFG_BYTESWAP 0x00000040 + +#define LOONGSON_GENCFG_UNCACHED 0x00000080 +#define LOONGSON_GENCFG_PREFETCHEN 0x00000100 +#define LOONGSON_GENCFG_WBEHINDEN 0x00000200 +#define LOONGSON_GENCFG_CACHEALG 0x00000c00 +#define LOONGSON_GENCFG_CACHEALG_SHIFT 10 +#define LOONGSON_GENCFG_PCIQUEUE 0x00001000 +#define LOONGSON_GENCFG_CACHESTOP 0x00002000 +#define LOONGSON_GENCFG_MSTRBYTESWAP 0x00004000 +#define LOONGSON_GENCFG_BUSERREN 0x00008000 +#define LOONGSON_GENCFG_NORETRYTIMEOUT 0x00010000 +#define LOONGSON_GENCFG_SHORTCOPYTIMEOUT 0x00020000 + +/* PCI address map control */ + +#define LOONGSON_PCIMAP LOONGSON_REG(LOONGSON_REGBASE + 0x10) +#define LOONGSON_PCIMEMBASECFG LOONGSON_REG(LOONGSON_REGBASE + 0x14) +#define LOONGSON_PCIMAP_CFG LOONGSON_REG(LOONGSON_REGBASE + 0x18) + +/* GPIO Regs - r/w */ + +#define LOONGSON_GPIODATA LOONGSON_REG(LOONGSON_REGBASE + 0x1c) +#define LOONGSON_GPIOIE LOONGSON_REG(LOONGSON_REGBASE + 0x20) + +/* ICU Configuration Regs - r/w */ + +#define LOONGSON_INTEDGE LOONGSON_REG(LOONGSON_REGBASE + 0x24) +#define LOONGSON_INTSTEER LOONGSON_REG(LOONGSON_REGBASE + 0x28) +#define LOONGSON_INTPOL LOONGSON_REG(LOONGSON_REGBASE + 0x2c) + +/* ICU Enable Regs - IntEn & IntISR are r/o. */ + +#define LOONGSON_INTENSET LOONGSON_REG(LOONGSON_REGBASE + 0x30) +#define LOONGSON_INTENCLR LOONGSON_REG(LOONGSON_REGBASE + 0x34) +#define LOONGSON_INTEN LOONGSON_REG(LOONGSON_REGBASE + 0x38) +#define LOONGSON_INTISR LOONGSON_REG(LOONGSON_REGBASE + 0x3c) + +/* ICU */ +#define LOONGSON_ICU_MBOXES 0x0000000f +#define LOONGSON_ICU_MBOXES_SHIFT 0 +#define LOONGSON_ICU_DMARDY 0x00000010 +#define LOONGSON_ICU_DMAEMPTY 0x00000020 +#define LOONGSON_ICU_COPYRDY 0x00000040 +#define LOONGSON_ICU_COPYEMPTY 0x00000080 +#define LOONGSON_ICU_COPYERR 0x00000100 +#define LOONGSON_ICU_PCIIRQ 0x00000200 +#define LOONGSON_ICU_MASTERERR 0x00000400 +#define LOONGSON_ICU_SYSTEMERR 0x00000800 +#define LOONGSON_ICU_DRAMPERR 0x00001000 +#define LOONGSON_ICU_RETRYERR 0x00002000 +#define LOONGSON_ICU_GPIOS 0x01ff0000 +#define LOONGSON_ICU_GPIOS_SHIFT 16 +#define LOONGSON_ICU_GPINS 0x7e000000 +#define LOONGSON_ICU_GPINS_SHIFT 25 +#define LOONGSON_ICU_MBOX(N) (1<<(LOONGSON_ICU_MBOXES_SHIFT+(N))) +#define LOONGSON_ICU_GPIO(N) (1<<(LOONGSON_ICU_GPIOS_SHIFT+(N))) +#define LOONGSON_ICU_GPIN(N) (1<<(LOONGSON_ICU_GPINS_SHIFT+(N))) + +/* PCI prefetch window base & mask */ + +#define LOONGSON_MEM_WIN_BASE_L LOONGSON_REG(LOONGSON_REGBASE + 0x40) +#define LOONGSON_MEM_WIN_BASE_H LOONGSON_REG(LOONGSON_REGBASE + 0x44) +#define LOONGSON_MEM_WIN_MASK_L LOONGSON_REG(LOONGSON_REGBASE + 0x48) +#define LOONGSON_MEM_WIN_MASK_H LOONGSON_REG(LOONGSON_REGBASE + 0x4c) + +/* PCI_Hit*_Sel_* */ + +#define LOONGSON_PCI_HIT0_SEL_L LOONGSON_REG(LOONGSON_REGBASE + 0x50) +#define LOONGSON_PCI_HIT0_SEL_H LOONGSON_REG(LOONGSON_REGBASE + 0x54) +#define LOONGSON_PCI_HIT1_SEL_L LOONGSON_REG(LOONGSON_REGBASE + 0x58) +#define LOONGSON_PCI_HIT1_SEL_H LOONGSON_REG(LOONGSON_REGBASE + 0x5c) +#define LOONGSON_PCI_HIT2_SEL_L LOONGSON_REG(LOONGSON_REGBASE + 0x60) +#define LOONGSON_PCI_HIT2_SEL_H LOONGSON_REG(LOONGSON_REGBASE + 0x64) + +/* PXArb Config & Status */ + +#define LOONGSON_PXARB_CFG LOONGSON_REG(LOONGSON_REGBASE + 0x68) +#define LOONGSON_PXARB_STATUS LOONGSON_REG(LOONGSON_REGBASE + 0x6c) + +/* Chip Config registor of each physical cpu package, PRid >= Loongson-2F */ +#define LOONGSON_CHIPCFG (void __iomem *)TO_UNCAC(0x1fc00180) + +/* pcimap */ + +#define LOONGSON_PCIMAP_PCIMAP_LO0 0x0000003f +#define LOONGSON_PCIMAP_PCIMAP_LO0_SHIFT 0 +#define LOONGSON_PCIMAP_PCIMAP_LO1 0x00000fc0 +#define LOONGSON_PCIMAP_PCIMAP_LO1_SHIFT 6 +#define LOONGSON_PCIMAP_PCIMAP_LO2 0x0003f000 +#define LOONGSON_PCIMAP_PCIMAP_LO2_SHIFT 12 +#define LOONGSON_PCIMAP_PCIMAP_2 0x00040000 +#define LOONGSON_PCIMAP_WIN(WIN, ADDR) \ + ((((ADDR)>>26) & LOONGSON_PCIMAP_PCIMAP_LO0) << ((WIN)*6)) + +#ifdef CONFIG_CPU_SUPPORTS_CPUFREQ +#include <linux/cpufreq.h> +extern struct cpufreq_frequency_table loongson2_clockmod_table[]; +#endif + +/* + * address windows configuration module + * + * loongson2e do not have this module + */ +#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG + +/* address window config module base address */ +#define LOONGSON_ADDRWINCFG_BASE 0x3ff00000ul +#define LOONGSON_ADDRWINCFG_SIZE 0x180 + +extern unsigned long _loongson_addrwincfg_base; +#define LOONGSON_ADDRWINCFG(offset) \ + (*(volatile u64 *)(_loongson_addrwincfg_base + (offset))) + +#define CPU_WIN0_BASE LOONGSON_ADDRWINCFG(0x00) +#define CPU_WIN1_BASE LOONGSON_ADDRWINCFG(0x08) +#define CPU_WIN2_BASE LOONGSON_ADDRWINCFG(0x10) +#define CPU_WIN3_BASE LOONGSON_ADDRWINCFG(0x18) + +#define CPU_WIN0_MASK LOONGSON_ADDRWINCFG(0x20) +#define CPU_WIN1_MASK LOONGSON_ADDRWINCFG(0x28) +#define CPU_WIN2_MASK LOONGSON_ADDRWINCFG(0x30) +#define CPU_WIN3_MASK LOONGSON_ADDRWINCFG(0x38) + +#define CPU_WIN0_MMAP LOONGSON_ADDRWINCFG(0x40) +#define CPU_WIN1_MMAP LOONGSON_ADDRWINCFG(0x48) +#define CPU_WIN2_MMAP LOONGSON_ADDRWINCFG(0x50) +#define CPU_WIN3_MMAP LOONGSON_ADDRWINCFG(0x58) + +#define PCIDMA_WIN0_BASE LOONGSON_ADDRWINCFG(0x60) +#define PCIDMA_WIN1_BASE LOONGSON_ADDRWINCFG(0x68) +#define PCIDMA_WIN2_BASE LOONGSON_ADDRWINCFG(0x70) +#define PCIDMA_WIN3_BASE LOONGSON_ADDRWINCFG(0x78) + +#define PCIDMA_WIN0_MASK LOONGSON_ADDRWINCFG(0x80) +#define PCIDMA_WIN1_MASK LOONGSON_ADDRWINCFG(0x88) +#define PCIDMA_WIN2_MASK LOONGSON_ADDRWINCFG(0x90) +#define PCIDMA_WIN3_MASK LOONGSON_ADDRWINCFG(0x98) + +#define PCIDMA_WIN0_MMAP LOONGSON_ADDRWINCFG(0xa0) +#define PCIDMA_WIN1_MMAP LOONGSON_ADDRWINCFG(0xa8) +#define PCIDMA_WIN2_MMAP LOONGSON_ADDRWINCFG(0xb0) +#define PCIDMA_WIN3_MMAP LOONGSON_ADDRWINCFG(0xb8) + +#define ADDRWIN_WIN0 0 +#define ADDRWIN_WIN1 1 +#define ADDRWIN_WIN2 2 +#define ADDRWIN_WIN3 3 + +#define ADDRWIN_MAP_DST_DDR 0 +#define ADDRWIN_MAP_DST_PCI 1 +#define ADDRWIN_MAP_DST_LIO 1 + +/* + * s: CPU, PCIDMA + * d: DDR, PCI, LIO + * win: 0, 1, 2, 3 + * src: map source + * dst: map destination + * size: ~mask + 1 + */ +#define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\ + s##_WIN##w##_BASE = (src); \ + s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \ + s##_WIN##w##_MASK = ~(size-1); \ +} while (0) + +#define LOONGSON_ADDRWIN_CPUTOPCI(win, src, dst, size) \ + LOONGSON_ADDRWIN_CFG(CPU, PCI, win, src, dst, size) +#define LOONGSON_ADDRWIN_CPUTODDR(win, src, dst, size) \ + LOONGSON_ADDRWIN_CFG(CPU, DDR, win, src, dst, size) +#define LOONGSON_ADDRWIN_PCITODDR(win, src, dst, size) \ + LOONGSON_ADDRWIN_CFG(PCIDMA, DDR, win, src, dst, size) + +#endif /* ! CONFIG_CPU_SUPPORTS_ADDRWINCFG */ + +#endif /* __ASM_MACH_LOONGSON2EF_LOONGSON_H */ diff --git a/arch/mips/include/asm/mach-loongson64/machine.h b/arch/mips/include/asm/mach-loongson2ef/machine.h index 8ef7ea94a26d..4097267ef186 100644 --- a/arch/mips/include/asm/mach-loongson64/machine.h +++ b/arch/mips/include/asm/mach-loongson2ef/machine.h @@ -4,8 +4,8 @@ * Author: Wu Zhangjin <wuzhangjin@gmail.com> */ -#ifndef __ASM_MACH_LOONGSON64_MACHINE_H -#define __ASM_MACH_LOONGSON64_MACHINE_H +#ifndef __ASM_MACH_LOONGSON2EF_MACHINE_H +#define __ASM_MACH_LOONGSON2EF_MACHINE_H #ifdef CONFIG_LEMOTE_FULOONG2E @@ -20,10 +20,4 @@ #endif -#ifdef CONFIG_LOONGSON_MACH3X - -#define LOONGSON_MACHTYPE MACH_LOONGSON_GENERIC - -#endif /* CONFIG_LOONGSON_MACH3X */ - -#endif /* __ASM_MACH_LOONGSON64_MACHINE_H */ +#endif /* __ASM_MACH_LOONGSON2EF_MACHINE_H */ diff --git a/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h b/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h new file mode 100644 index 000000000000..00d602629a55 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h @@ -0,0 +1,36 @@ +/* + * 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. + * + * Copyright (C) 1998, 2001, 03, 07 by Ralf Baechle (ralf@linux-mips.org) + * + * RTC routines for PC style attached Dallas chip. + */ +#ifndef __ASM_MACH_LOONGSON2EF_MC146818RTC_H +#define __ASM_MACH_LOONGSON2EF_MC146818RTC_H + +#include <linux/io.h> + +#define RTC_PORT(x) (0x70 + (x)) +#define RTC_IRQ 8 + +static inline unsigned char CMOS_READ(unsigned long addr) +{ + outb_p(addr, RTC_PORT(0)); + return inb_p(RTC_PORT(1)); +} + +static inline void CMOS_WRITE(unsigned char data, unsigned long addr) +{ + outb_p(addr, RTC_PORT(0)); + outb_p(data, RTC_PORT(1)); +} + +#define RTC_ALWAYS_BCD 0 + +#ifndef mc146818_decode_year +#define mc146818_decode_year(year) ((year) < 70 ? (year) + 2000 : (year) + 1970) +#endif + +#endif /* __ASM_MACH_LOONGSON2EF_MC146818RTC_H */ diff --git a/arch/mips/include/asm/mach-loongson64/mem.h b/arch/mips/include/asm/mach-loongson2ef/mem.h index ce33c174c04d..d1d759b8974e 100644 --- a/arch/mips/include/asm/mach-loongson64/mem.h +++ b/arch/mips/include/asm/mach-loongson2ef/mem.h @@ -4,8 +4,8 @@ * Author: Wu Zhangjin <wuzhangjin@gmail.com> */ -#ifndef __ASM_MACH_LOONGSON64_MEM_H -#define __ASM_MACH_LOONGSON64_MEM_H +#ifndef __ASM_MACH_LOONGSON2EF_MEM_H +#define __ASM_MACH_LOONGSON2EF_MEM_H /* * high memory space @@ -34,4 +34,4 @@ #define LOONGSON_MMIO_MEM_END 0x80000000 #endif -#endif /* __ASM_MACH_LOONGSON64_MEM_H */ +#endif /* __ASM_MACH_LOONGSON2EF_MEM_H */ diff --git a/arch/mips/include/asm/mach-loongson2ef/pci.h b/arch/mips/include/asm/mach-loongson2ef/pci.h new file mode 100644 index 000000000000..5588c5bc5395 --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/pci.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2008 Zhang Le <r0bertz@gentoo.org> + * Copyright (c) 2009 Wu Zhangjin <wuzhangjin@gmail.com> + */ + +#ifndef __ASM_MACH_LOONGSON2EF_PCI_H_ +#define __ASM_MACH_LOONGSON2EF_PCI_H_ + +extern struct pci_ops loongson_pci_ops; + +/* this is an offset from mips_io_port_base */ +#define LOONGSON_PCI_IO_START 0x00004000UL + +#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG + +/* + * we use address window2 to map cpu address space to pci space + * window2: cpu [1G, 2G] -> pci [1G, 2G] + * why not use window 0 & 1? because they are used by cpu when booting. + * window0: cpu [0, 256M] -> ddr [0, 256M] + * window1: cpu [256M, 512M] -> pci [256M, 512M] + */ + +/* the smallest LOONGSON_CPU_MEM_SRC can be 512M */ +#define LOONGSON_CPU_MEM_SRC 0x40000000ul /* 1G */ +#define LOONGSON_PCI_MEM_DST LOONGSON_CPU_MEM_SRC + +#define LOONGSON_PCI_MEM_START LOONGSON_PCI_MEM_DST +#define LOONGSON_PCI_MEM_END (0x80000000ul-1) /* 2G */ + +#define MMAP_CPUTOPCI_SIZE (LOONGSON_PCI_MEM_END - \ + LOONGSON_PCI_MEM_START + 1) + +#else /* loongson2f/32bit & loongson2e */ + +/* this pci memory space is mapped by pcimap in pci.c */ +#define LOONGSON_PCI_MEM_START LOONGSON_PCILO1_BASE +#define LOONGSON_PCI_MEM_END (LOONGSON_PCILO1_BASE + 0x04000000 * 2) + +/* this is an offset from mips_io_port_base */ +#define LOONGSON_PCI_IO_START 0x00004000UL + +#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */ + +#endif /* !__ASM_MACH_LOONGSON2EF_PCI_H_ */ diff --git a/arch/mips/include/asm/mach-loongson2ef/spaces.h b/arch/mips/include/asm/mach-loongson2ef/spaces.h new file mode 100644 index 000000000000..ba4e8e9b618e --- /dev/null +++ b/arch/mips/include/asm/mach-loongson2ef/spaces.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MACH_LOONGSON2EF_SPACES_H_ +#define __ASM_MACH_LOONGSON2EF_SPACES_H_ + +#if defined(CONFIG_64BIT) +#define CAC_BASE _AC(0x9800000000000000, UL) +#endif /* CONFIG_64BIT */ + +#include <asm/mach-generic/spaces.h> +#endif diff --git a/arch/mips/include/asm/mach-loongson32/prom.h b/arch/mips/include/asm/mach-loongson32/prom.h deleted file mode 100644 index cb789f18d790..000000000000 --- a/arch/mips/include/asm/mach-loongson32/prom.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com> - */ - -#ifndef __ASM_MACH_LOONGSON32_PROM_H -#define __ASM_MACH_LOONGSON32_PROM_H - -#include <linux/io.h> -#include <linux/init.h> -#include <linux/irq.h> - -/* environment arguments from bootloader */ -extern unsigned long memsize, highmemsize; - -/* loongson-specific command line, env and memory initialization */ -extern char *prom_getenv(char *name); -extern void __init prom_init_cmdline(void); - -#endif /* __ASM_MACH_LOONGSON32_PROM_H */ diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h index 4aca25f2ff06..7dc8d75445a9 100644 --- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h @@ -43,11 +43,8 @@ #define cpu_has_vint 0 #define cpu_has_vtag_icache 0 #define cpu_has_watch 1 - -#ifdef CONFIG_CPU_LOONGSON3 #define cpu_has_wsbh 1 #define cpu_has_ic_fills_f_dc 1 #define cpu_hwrena_impl_bits 0xc0000000 -#endif #endif /* __ASM_MACH_LOONGSON64_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index be9f727a9328..73a89913dc38 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -4,8 +4,6 @@ #include <boot_param.h> -#ifdef CONFIG_CPU_LOONGSON3 - /* cpu core interrupt numbers */ #define MIPS_CPU_IRQ_BASE 56 @@ -35,8 +33,6 @@ #define LOONGSON_INT_COREx_INTy(x, y) (1<<(x) | 1<<(y+4)) /* route to int y of core x */ -#endif - extern void fixup_irqs(void); extern void loongson3_ipi_interrupt(struct pt_regs *regs); diff --git a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h index b5e288a12dfe..87a5bfbf8cfe 100644 --- a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h @@ -17,7 +17,6 @@ * Override macros used in arch/mips/kernel/head.S. */ .macro kernel_entry_setup -#ifdef CONFIG_CPU_LOONGSON3 .set push .set mips64 /* Set LPA on LOONGSON3 config3 */ @@ -30,23 +29,29 @@ mtc0 t0, CP0_PAGEGRAIN /* Enable STFill Buffer */ mfc0 t0, CP0_PRID + /* Loongson-3A R4+ */ + andi t1, t0, PRID_IMP_MASK + li t2, PRID_IMP_LOONGSON_64G + beq t1, t2, 1f + nop + /* Loongson-3A R2/R3 */ andi t0, (PRID_IMP_MASK | PRID_REV_MASK) - slti t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2_0) - bnez t0, 1f + slti t0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0) + bnez t0, 2f + nop +1: mfc0 t0, CP0_CONFIG6 or t0, 0x100 mtc0 t0, CP0_CONFIG6 -1: +2: _ehb .set pop -#endif .endm /* * Do SMP slave processor setup. */ .macro smp_slave_setup -#ifdef CONFIG_CPU_LOONGSON3 .set push .set mips64 /* Set LPA on LOONGSON3 config3 */ @@ -59,16 +64,23 @@ mtc0 t0, CP0_PAGEGRAIN /* Enable STFill Buffer */ mfc0 t0, CP0_PRID + /* Loongson-3A R4+ */ + andi t1, t0, PRID_IMP_MASK + li t2, PRID_IMP_LOONGSON_64G + beq t1, t2, 1f + nop + /* Loongson-3A R2/R3 */ andi t0, (PRID_IMP_MASK | PRID_REV_MASK) - slti t0, (PRID_IMP_LOONGSON_64 | PRID_REV_LOONGSON3A_R2_0) - bnez t0, 1f + slti t0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0) + bnez t0, 2f + nop +1: mfc0 t0, CP0_CONFIG6 or t0, 0x100 mtc0 t0, CP0_CONFIG6 -1: +2: _ehb .set pop -#endif .endm #endif /* __ASM_MACH_LOONGSON64_KERNEL_ENTRY_H */ diff --git a/arch/mips/include/asm/mach-loongson64/loongson.h b/arch/mips/include/asm/mach-loongson64/loongson.h index 694a58574ec0..a8fce112a9b0 100644 --- a/arch/mips/include/asm/mach-loongson64/loongson.h +++ b/arch/mips/include/asm/mach-loongson64/loongson.h @@ -12,8 +12,6 @@ #include <linux/irq.h> #include <boot_param.h> -/* loongson internal northbridge initialization */ -extern void bonito_irq_init(void); /* machine-specific reboot/halt operation */ extern void mach_prepare_reboot(void); @@ -26,25 +24,9 @@ extern const struct plat_smp_ops loongson3_smp_ops; /* loongson-specific command line, env and memory initialization */ extern void __init prom_init_memory(void); -extern void __init prom_init_cmdline(void); -extern void __init prom_init_machtype(void); extern void __init prom_init_env(void); -#ifdef CONFIG_LOONGSON_UART_BASE -extern unsigned long _loongson_uart_base[], loongson_uart_base[]; -extern void prom_init_loongson_uart_base(void); -#endif - -static inline void prom_init_uart_base(void) -{ -#ifdef CONFIG_LOONGSON_UART_BASE - prom_init_loongson_uart_base(); -#endif -} /* irq operation functions */ -extern void bonito_irqdispatch(void); -extern void __init bonito_irq_init(void); -extern void __init mach_init_irq(void); extern void mach_irq_dispatch(unsigned int pending); extern int mach_i8259_irq(void); @@ -64,17 +46,6 @@ extern int mach_i8259_irq(void); #define LOONGSON3_REG32(base, x) \ (*(volatile u32 *)((char *)TO_UNCAC(base) + (x))) -#define LOONGSON_IRQ_BASE 32 -#define LOONGSON2_PERFCNT_IRQ (MIPS_CPU_IRQ_BASE + 6) /* cpu perf counter */ - -#include <linux/interrupt.h> -static inline void do_perfcnt_IRQ(void) -{ -#if IS_ENABLED(CONFIG_OPROFILE) - do_IRQ(LOONGSON2_PERFCNT_IRQ); -#endif -} - #define LOONGSON_FLASH_BASE 0x1c000000 #define LOONGSON_FLASH_SIZE 0x02000000 /* 32M */ #define LOONGSON_FLASH_TOP (LOONGSON_FLASH_BASE+LOONGSON_FLASH_SIZE-1) @@ -109,11 +80,7 @@ static inline void do_perfcnt_IRQ(void) #define LOONGSON_PCICFG_SIZE 0x00000800 /* 2K */ #define LOONGSON_PCICFG_TOP (LOONGSON_PCICFG_BASE+LOONGSON_PCICFG_SIZE-1) -#ifdef CONFIG_CPU_LOONGSON3 #define LOONGSON_PCIIO_BASE loongson_sysconf.pci_io_base -#else -#define LOONGSON_PCIIO_BASE 0x1fd00000 -#endif #define LOONGSON_PCIIO_SIZE 0x00100000 /* 1M */ #define LOONGSON_PCIIO_TOP (LOONGSON_PCIIO_BASE+LOONGSON_PCIIO_SIZE-1) @@ -270,86 +237,4 @@ extern u64 loongson_freqctrl[MAX_PACKAGES]; #define LOONGSON_PCIMAP_WIN(WIN, ADDR) \ ((((ADDR)>>26) & LOONGSON_PCIMAP_PCIMAP_LO0) << ((WIN)*6)) -#ifdef CONFIG_CPU_SUPPORTS_CPUFREQ -#include <linux/cpufreq.h> -extern struct cpufreq_frequency_table loongson2_clockmod_table[]; -#endif - -/* - * address windows configuration module - * - * loongson2e do not have this module - */ -#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG - -/* address window config module base address */ -#define LOONGSON_ADDRWINCFG_BASE 0x3ff00000ul -#define LOONGSON_ADDRWINCFG_SIZE 0x180 - -extern unsigned long _loongson_addrwincfg_base; -#define LOONGSON_ADDRWINCFG(offset) \ - (*(volatile u64 *)(_loongson_addrwincfg_base + (offset))) - -#define CPU_WIN0_BASE LOONGSON_ADDRWINCFG(0x00) -#define CPU_WIN1_BASE LOONGSON_ADDRWINCFG(0x08) -#define CPU_WIN2_BASE LOONGSON_ADDRWINCFG(0x10) -#define CPU_WIN3_BASE LOONGSON_ADDRWINCFG(0x18) - -#define CPU_WIN0_MASK LOONGSON_ADDRWINCFG(0x20) -#define CPU_WIN1_MASK LOONGSON_ADDRWINCFG(0x28) -#define CPU_WIN2_MASK LOONGSON_ADDRWINCFG(0x30) -#define CPU_WIN3_MASK LOONGSON_ADDRWINCFG(0x38) - -#define CPU_WIN0_MMAP LOONGSON_ADDRWINCFG(0x40) -#define CPU_WIN1_MMAP LOONGSON_ADDRWINCFG(0x48) -#define CPU_WIN2_MMAP LOONGSON_ADDRWINCFG(0x50) -#define CPU_WIN3_MMAP LOONGSON_ADDRWINCFG(0x58) - -#define PCIDMA_WIN0_BASE LOONGSON_ADDRWINCFG(0x60) -#define PCIDMA_WIN1_BASE LOONGSON_ADDRWINCFG(0x68) -#define PCIDMA_WIN2_BASE LOONGSON_ADDRWINCFG(0x70) -#define PCIDMA_WIN3_BASE LOONGSON_ADDRWINCFG(0x78) - -#define PCIDMA_WIN0_MASK LOONGSON_ADDRWINCFG(0x80) -#define PCIDMA_WIN1_MASK LOONGSON_ADDRWINCFG(0x88) -#define PCIDMA_WIN2_MASK LOONGSON_ADDRWINCFG(0x90) -#define PCIDMA_WIN3_MASK LOONGSON_ADDRWINCFG(0x98) - -#define PCIDMA_WIN0_MMAP LOONGSON_ADDRWINCFG(0xa0) -#define PCIDMA_WIN1_MMAP LOONGSON_ADDRWINCFG(0xa8) -#define PCIDMA_WIN2_MMAP LOONGSON_ADDRWINCFG(0xb0) -#define PCIDMA_WIN3_MMAP LOONGSON_ADDRWINCFG(0xb8) - -#define ADDRWIN_WIN0 0 -#define ADDRWIN_WIN1 1 -#define ADDRWIN_WIN2 2 -#define ADDRWIN_WIN3 3 - -#define ADDRWIN_MAP_DST_DDR 0 -#define ADDRWIN_MAP_DST_PCI 1 -#define ADDRWIN_MAP_DST_LIO 1 - -/* - * s: CPU, PCIDMA - * d: DDR, PCI, LIO - * win: 0, 1, 2, 3 - * src: map source - * dst: map destination - * size: ~mask + 1 - */ -#define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\ - s##_WIN##w##_BASE = (src); \ - s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \ - s##_WIN##w##_MASK = ~(size-1); \ -} while (0) - -#define LOONGSON_ADDRWIN_CPUTOPCI(win, src, dst, size) \ - LOONGSON_ADDRWIN_CFG(CPU, PCI, win, src, dst, size) -#define LOONGSON_ADDRWIN_CPUTODDR(win, src, dst, size) \ - LOONGSON_ADDRWIN_CFG(CPU, DDR, win, src, dst, size) -#define LOONGSON_ADDRWIN_PCITODDR(win, src, dst, size) \ - LOONGSON_ADDRWIN_CFG(PCIDMA, DDR, win, src, dst, size) - -#endif /* ! CONFIG_CPU_SUPPORTS_ADDRWINCFG */ - #endif /* __ASM_MACH_LOONGSON64_LOONGSON_H */ diff --git a/arch/mips/include/asm/mach-loongson64/loongson_regs.h b/arch/mips/include/asm/mach-loongson64/loongson_regs.h new file mode 100644 index 000000000000..363a47a5d26e --- /dev/null +++ b/arch/mips/include/asm/mach-loongson64/loongson_regs.h @@ -0,0 +1,227 @@ +/* + * Read/Write Loongson Extension Registers + */ + +#ifndef _LOONGSON_REGS_H_ +#define _LOONGSON_REGS_H_ + +#include <linux/types.h> +#include <linux/bits.h> + +#include <asm/mipsregs.h> +#include <asm/cpu.h> + +static inline bool cpu_has_cfg(void) +{ + return ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G); +} + +static inline u32 read_cpucfg(u32 reg) +{ + u32 __res; + + __asm__ __volatile__( + "parse_r __res,%0\n\t" + "parse_r reg,%1\n\t" + ".insn \n\t" + ".word (0xc8080118 | (reg << 21) | (__res << 11))\n\t" + :"=r"(__res) + :"r"(reg) + : + ); + return __res; +} + +/* Bit Domains for CFG registers */ +#define LOONGSON_CFG0 0x0 +#define LOONGSON_CFG0_PRID GENMASK(31, 0) + +#define LOONGSON_CFG1 0x1 +#define LOONGSON_CFG1_FP BIT(0) +#define LOONGSON_CFG1_FPREV GENMASK(3, 1) +#define LOONGSON_CFG1_MMI BIT(4) +#define LOONGSON_CFG1_MSA1 BIT(5) +#define LOONGSON_CFG1_MSA2 BIT(6) +#define LOONGSON_CFG1_CGP BIT(7) +#define LOONGSON_CFG1_WRP BIT(8) +#define LOONGSON_CFG1_LSX1 BIT(9) +#define LOONGSON_CFG1_LSX2 BIT(10) +#define LOONGSON_CFG1_LASX BIT(11) +#define LOONGSON_CFG1_R6FXP BIT(12) +#define LOONGSON_CFG1_R6CRCP BIT(13) +#define LOONGSON_CFG1_R6FPP BIT(14) +#define LOONGSON_CFG1_CNT64 BIT(15) +#define LOONGSON_CFG1_LSLDR0 BIT(16) +#define LOONGSON_CFG1_LSPREF BIT(17) +#define LOONGSON_CFG1_LSPREFX BIT(18) +#define LOONGSON_CFG1_LSSYNCI BIT(19) +#define LOONGSON_CFG1_LSUCA BIT(20) +#define LOONGSON_CFG1_LLSYNC BIT(21) +#define LOONGSON_CFG1_TGTSYNC BIT(22) +#define LOONGSON_CFG1_LLEXC BIT(23) +#define LOONGSON_CFG1_SCRAND BIT(24) +#define LOONGSON_CFG1_MUALP BIT(25) +#define LOONGSON_CFG1_KMUALEN BIT(26) +#define LOONGSON_CFG1_ITLBT BIT(27) +#define LOONGSON_CFG1_LSUPERF BIT(28) +#define LOONGSON_CFG1_SFBP BIT(29) +#define LOONGSON_CFG1_CDMAP BIT(30) + +#define LOONGSON_CFG2 0x2 +#define LOONGSON_CFG2_LEXT1 BIT(0) +#define LOONGSON_CFG2_LEXT2 BIT(1) +#define LOONGSON_CFG2_LEXT3 BIT(2) +#define LOONGSON_CFG2_LSPW BIT(3) +#define LOONGSON_CFG2_LBT1 BIT(4) +#define LOONGSON_CFG2_LBT2 BIT(5) +#define LOONGSON_CFG2_LBT3 BIT(6) +#define LOONGSON_CFG2_LBTMMU BIT(7) +#define LOONGSON_CFG2_LPMP BIT(8) +#define LOONGSON_CFG2_LPMPREV GENMASK(11, 9) +#define LOONGSON_CFG2_LAMO BIT(12) +#define LOONGSON_CFG2_LPIXU BIT(13) +#define LOONGSON_CFG2_LPIXUN BIT(14) +#define LOONGSON_CFG2_LZVP BIT(15) +#define LOONGSON_CFG2_LZVREV GENMASK(18, 16) +#define LOONGSON_CFG2_LGFTP BIT(19) +#define LOONGSON_CFG2_LGFTPREV GENMASK(22, 20) +#define LOONGSON_CFG2_LLFTP BIT(23) +#define LOONGSON_CFG2_LLFTPREV GENMASK(26, 24) +#define LOONGSON_CFG2_LCSRP BIT(27) +#define LOONGSON_CFG2_LDISBLIKELY BIT(28) + +#define LOONGSON_CFG3 0x3 +#define LOONGSON_CFG3_LCAMP BIT(0) +#define LOONGSON_CFG3_LCAMREV GENMASK(3, 1) +#define LOONGSON_CFG3_LCAMNUM GENMASK(11, 4) +#define LOONGSON_CFG3_LCAMKW GENMASK(19, 12) +#define LOONGSON_CFG3_LCAMVW GENMASK(27, 20) + +#define LOONGSON_CFG4 0x4 +#define LOONGSON_CFG4_CCFREQ GENMASK(31, 0) + +#define LOONGSON_CFG5 0x5 +#define LOONGSON_CFG5_CFM GENMASK(15, 0) +#define LOONGSON_CFG5_CFD GENMASK(31, 16) + +#define LOONGSON_CFG6 0x6 + +#define LOONGSON_CFG7 0x7 +#define LOONGSON_CFG7_GCCAEQRP BIT(0) +#define LOONGSON_CFG7_UCAWINP BIT(1) + +static inline bool cpu_has_csr(void) +{ + if (cpu_has_cfg()) + return (read_cpucfg(LOONGSON_CFG2) & LOONGSON_CFG2_LCSRP); + + return false; +} + +static inline u32 csr_readl(u32 reg) +{ + u32 __res; + + /* RDCSR reg, val */ + __asm__ __volatile__( + "parse_r __res,%0\n\t" + "parse_r reg,%1\n\t" + ".insn \n\t" + ".word (0xc8000118 | (reg << 21) | (__res << 11))\n\t" + :"=r"(__res) + :"r"(reg) + : + ); + return __res; +} + +static inline u64 csr_readq(u32 reg) +{ + u64 __res; + + /* DWRCSR reg, val */ + __asm__ __volatile__( + "parse_r __res,%0\n\t" + "parse_r reg,%1\n\t" + ".insn \n\t" + ".word (0xc8020118 | (reg << 21) | (__res << 11))\n\t" + :"=r"(__res) + :"r"(reg) + : + ); + return __res; +} + +static inline void csr_writel(u32 val, u32 reg) +{ + /* WRCSR reg, val */ + __asm__ __volatile__( + "parse_r reg,%0\n\t" + "parse_r val,%1\n\t" + ".insn \n\t" + ".word (0xc8010118 | (reg << 21) | (val << 11))\n\t" + : + :"r"(reg),"r"(val) + : + ); +} + +static inline void csr_writeq(u64 val, u32 reg) +{ + /* DWRCSR reg, val */ + __asm__ __volatile__( + "parse_r reg,%0\n\t" + "parse_r val,%1\n\t" + ".insn \n\t" + ".word (0xc8030118 | (reg << 21) | (val << 11))\n\t" + : + :"r"(reg),"r"(val) + : + ); +} + +/* Public CSR Register can also be accessed with regular addresses */ +#define CSR_PUBLIC_MMIO_BASE 0x1fe00000 + +#define MMIO_CSR(x) (void *)TO_UNCAC(CSR_PUBLIC_MMIO_BASE + x) + +#define LOONGSON_CSR_FEATURES 0x8 +#define LOONGSON_CSRF_TEMP BIT(0) +#define LOONGSON_CSRF_NODECNT BIT(1) +#define LOONGSON_CSRF_MSI BIT(2) +#define LOONGSON_CSRF_EXTIOI BIT(3) +#define LOONGSON_CSRF_IPI BIT(4) +#define LOONGSON_CSRF_FREQ BIT(5) + +#define LOONGSON_CSR_VENDOR 0x10 /* Vendor name string, should be "Loongson" */ +#define LOONGSON_CSR_CPUNAME 0x20 /* Processor name string */ +#define LOONGSON_CSR_NODECNT 0x408 +#define LOONGSON_CSR_CPUTEMP 0x428 + +/* PerCore CSR, only accessable by local cores */ +#define LOONGSON_CSR_IPI_STATUS 0x1000 +#define LOONGSON_CSR_IPI_EN 0x1004 +#define LOONGSON_CSR_IPI_SET 0x1008 +#define LOONGSON_CSR_IPI_CLEAR 0x100c +#define LOONGSON_CSR_IPI_SEND 0x1040 +#define CSR_IPI_SEND_IP_SHIFT 0 +#define CSR_IPI_SEND_CPU_SHIFT 16 +#define CSR_IPI_SEND_BLOCK BIT(31) + +static inline u64 drdtime(void) +{ + int rID = 0; + u64 val = 0; + + __asm__ __volatile__( + "parse_r rID,%0\n\t" + "parse_r val,%1\n\t" + ".insn \n\t" + ".word (0xc8090118 | (rID << 21) | (val << 11))\n\t" + :"=r"(rID),"=r"(val) + : + ); + return val; +} + +#endif diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index 62073d60739f..3a25dbd3b3e9 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -6,8 +6,8 @@ * Huacai Chen, chenhc@lemote.com * Xiaofu Meng, Shuangshuang Zhang */ -#ifndef _ASM_MACH_MMZONE_H -#define _ASM_MACH_MMZONE_H +#ifndef _ASM_MACH_LOONGSON64_MMZONE_H +#define _ASM_MACH_LOONGSON64_MMZONE_H #include <boot_param.h> #define NODE_ADDRSPACE_SHIFT 44 @@ -19,30 +19,9 @@ #define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT) #define nid_to_addrbase(nid) ((nid) << NODE_ADDRSPACE_SHIFT) -#define LEVELS_PER_SLICE 128 +extern struct pglist_data *__node_data[]; -struct slice_data { - unsigned long irq_enable_mask[2]; - int level_to_irq[LEVELS_PER_SLICE]; -}; - -struct hub_data { - cpumask_t h_cpus; - unsigned long slice_map; - unsigned long irq_alloc_mask[2]; - struct slice_data slice[2]; -}; - -struct node_data { - struct pglist_data pglist; - struct hub_data hub; - cpumask_t cpumask; -}; - -extern struct node_data *__node_data[]; - -#define NODE_DATA(n) (&__node_data[(n)]->pglist) -#define hub_data(n) (&__node_data[(n)]->hub) +#define NODE_DATA(n) (__node_data[n]) extern void setup_zero_pages(void); extern void __init prom_init_numa_memory(void); diff --git a/arch/mips/include/asm/mach-loongson64/pci.h b/arch/mips/include/asm/mach-loongson64/pci.h index 97f807fb2117..8b59d64a23e8 100644 --- a/arch/mips/include/asm/mach-loongson64/pci.h +++ b/arch/mips/include/asm/mach-loongson64/pci.h @@ -12,39 +12,8 @@ extern struct pci_ops loongson_pci_ops; /* this is an offset from mips_io_port_base */ #define LOONGSON_PCI_IO_START 0x00004000UL -#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG - -/* - * we use address window2 to map cpu address space to pci space - * window2: cpu [1G, 2G] -> pci [1G, 2G] - * why not use window 0 & 1? because they are used by cpu when booting. - * window0: cpu [0, 256M] -> ddr [0, 256M] - * window1: cpu [256M, 512M] -> pci [256M, 512M] - */ - -/* the smallest LOONGSON_CPU_MEM_SRC can be 512M */ -#define LOONGSON_CPU_MEM_SRC 0x40000000ul /* 1G */ -#define LOONGSON_PCI_MEM_DST LOONGSON_CPU_MEM_SRC - -#define LOONGSON_PCI_MEM_START LOONGSON_PCI_MEM_DST -#define LOONGSON_PCI_MEM_END (0x80000000ul-1) /* 2G */ - -#define MMAP_CPUTOPCI_SIZE (LOONGSON_PCI_MEM_END - \ - LOONGSON_PCI_MEM_START + 1) - -#else /* loongson2f/32bit & loongson2e */ - -/* this pci memory space is mapped by pcimap in pci.c */ -#ifdef CONFIG_CPU_LOONGSON3 #define LOONGSON_PCI_MEM_START 0x40000000UL #define LOONGSON_PCI_MEM_END 0x7effffffUL -#else -#define LOONGSON_PCI_MEM_START LOONGSON_PCILO1_BASE -#define LOONGSON_PCI_MEM_END (LOONGSON_PCILO1_BASE + 0x04000000 * 2) -#endif -/* this is an offset from mips_io_port_base */ -#define LOONGSON_PCI_IO_START 0x00004000UL -#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */ #endif /* !__ASM_MACH_LOONGSON64_PCI_H_ */ diff --git a/arch/mips/include/asm/mach-loongson64/topology.h b/arch/mips/include/asm/mach-loongson64/topology.h index 7ff819ab308a..3414a1fd1783 100644 --- a/arch/mips/include/asm/mach-loongson64/topology.h +++ b/arch/mips/include/asm/mach-loongson64/topology.h @@ -5,7 +5,9 @@ #ifdef CONFIG_NUMA #define cpu_to_node(cpu) (cpu_logical_map(cpu) >> 2) -#define cpumask_of_node(node) (&__node_data[(node)]->cpumask) + +extern cpumask_t __node_cpumask[]; +#define cpumask_of_node(node) (&__node_cpumask[node]) struct pci_bus; extern int pcibus_to_node(struct pci_bus *); diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index bdbdc19a2b8f..0d5a30988697 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -689,6 +689,9 @@ #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) +/* Ingenic HPTLB off bits */ +#define XBURST_PAGECTRL_HPTLB_DIS 0xa9000000 + /* Ingenic Config7 bits */ #define MIPS_CONF7_BTB_LOOP_EN (_ULCAST_(1) << 4) @@ -1971,6 +1974,9 @@ do { \ #define read_c0_brcm_sleepcount() __read_32bit_c0_register($22, 7) #define write_c0_brcm_sleepcount(val) __write_32bit_c0_register($22, 7, val) +/* Ingenic page ctrl register */ +#define write_c0_page_ctrl(val) __write_32bit_c0_register($5, 4, val) + /* * Macros to access the guest system control coprocessor */ diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h index ed70994fbbec..9846047b3d3d 100644 --- a/arch/mips/include/asm/module.h +++ b/arch/mips/include/asm/module.h @@ -119,12 +119,12 @@ search_module_dbetables(unsigned long addr) #define MODULE_PROC_FAMILY "RM7000 " #elif defined CONFIG_CPU_SB1 #define MODULE_PROC_FAMILY "SB1 " -#elif defined CONFIG_CPU_LOONGSON1 -#define MODULE_PROC_FAMILY "LOONGSON1 " -#elif defined CONFIG_CPU_LOONGSON2 -#define MODULE_PROC_FAMILY "LOONGSON2 " -#elif defined CONFIG_CPU_LOONGSON3 -#define MODULE_PROC_FAMILY "LOONGSON3 " +#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 diff --git a/arch/mips/include/asm/pci/bridge.h b/arch/mips/include/asm/pci/bridge.h index a92cd30b48c9..3bc630ff9ad4 100644 --- a/arch/mips/include/asm/pci/bridge.h +++ b/arch/mips/include/asm/pci/bridge.h @@ -807,6 +807,7 @@ struct bridge_controller { unsigned long intr_addr; struct irq_domain *domain; unsigned int pci_int[8]; + u32 ioc3_sid[8]; nasid_t nasid; }; diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 166842337eb2..fa77cb71f303 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -96,9 +96,9 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) free_pages((unsigned long)pud, PUD_ORDER); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { - set_pgd(pgd, __pgd((unsigned long)pud)); + set_p4d(p4d, __p4d((unsigned long)pud)); } #define __pud_free_tlb(tlb, x, addr) pud_free((tlb)->mm, x) diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index ba967148b016..1945c8970141 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -16,7 +16,6 @@ #include <asm/cachectl.h> #include <asm/fixmap.h> -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #ifdef CONFIG_HIGHMEM @@ -196,14 +195,11 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) #define pte_page(x) pfn_to_page(pte_pfn(x)) -#define __pgd_offset(address) pgd_index(address) -#define __pud_offset(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -#define __pmd_offset(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) - /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) +#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) /* to find an entry in a page-table-directory */ diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 93a9dce31f25..f92716cfa4f4 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -17,11 +17,12 @@ #include <asm/cachectl.h> #include <asm/fixmap.h> -#define __ARCH_USE_5LEVEL_HACK -#if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48) +#if CONFIG_PGTABLE_LEVELS == 2 #include <asm-generic/pgtable-nopmd.h> -#elif !(defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_MIPS_VA_BITS_48)) +#elif CONFIG_PGTABLE_LEVELS == 3 #include <asm-generic/pgtable-nopud.h> +#else +#include <asm-generic/pgtable-nop4d.h> #endif /* @@ -186,44 +187,49 @@ extern pud_t invalid_pud_table[PTRS_PER_PUD]; /* * Empty pgd entries point to the invalid_pud_table. */ -static inline int pgd_none(pgd_t pgd) +static inline int p4d_none(p4d_t p4d) { - return pgd_val(pgd) == (unsigned long)invalid_pud_table; + return p4d_val(p4d) == (unsigned long)invalid_pud_table; } -static inline int pgd_bad(pgd_t pgd) +static inline int p4d_bad(p4d_t p4d) { - if (unlikely(pgd_val(pgd) & ~PAGE_MASK)) + if (unlikely(p4d_val(p4d) & ~PAGE_MASK)) return 1; return 0; } -static inline int pgd_present(pgd_t pgd) +static inline int p4d_present(p4d_t p4d) { - return pgd_val(pgd) != (unsigned long)invalid_pud_table; + return p4d_val(p4d) != (unsigned long)invalid_pud_table; } -static inline void pgd_clear(pgd_t *pgdp) +static inline void p4d_clear(p4d_t *p4dp) { - pgd_val(*pgdp) = (unsigned long)invalid_pud_table; + p4d_val(*p4dp) = (unsigned long)invalid_pud_table; } #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -static inline unsigned long pgd_page_vaddr(pgd_t pgd) +static inline unsigned long p4d_page_vaddr(p4d_t p4d) { - return pgd_val(pgd); + return p4d_val(p4d); } -static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) +#define p4d_phys(p4d) virt_to_phys((void *)p4d_val(p4d)) +#define p4d_page(p4d) (pfn_to_page(p4d_phys(p4d) >> PAGE_SHIFT)) + +#define p4d_index(address) (((address) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { - return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address); + return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); } -static inline void set_pgd(pgd_t *pgd, pgd_t pgdval) +static inline void set_p4d(p4d_t *p4d, p4d_t p4dval) { - *pgd = pgdval; + *p4d = p4dval; } #endif @@ -314,10 +320,6 @@ static inline void pud_clear(pud_t *pudp) #define pfn_pmd(pfn, prot) __pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot)) #endif -#define __pgd_offset(address) pgd_index(address) -#define __pud_offset(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -#define __pmd_offset(address) pmd_index(address) - /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index f85bd5b15f51..91b89aab1787 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -644,17 +644,6 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, #include <asm-generic/pgtable.h> /* - * uncached accelerated TLB map for video memory access - */ -#ifdef CONFIG_CPU_SUPPORTS_UNCACHED_ACCELERATED -#define __HAVE_PHYS_MEM_ACCESS_PROT - -struct file; -pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#endif - -/* * We provide our own get_unmapped area to cope with the virtual aliasing * constraints placed on us by the cache architecture. */ diff --git a/arch/mips/include/asm/pmon.h b/arch/mips/include/asm/pmon.h deleted file mode 100644 index 6ad519189ce2..000000000000 --- a/arch/mips/include/asm/pmon.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * 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. - * - * Copyright (C) 2004 by Ralf Baechle - * - * The cpustart method is a PMC-Sierra's function to start the secondary CPU. - * Stock PMON 2000 has the smpfork, semlock and semunlock methods instead. - */ -#ifndef _ASM_PMON_H -#define _ASM_PMON_H - -struct callvectors { - int (*open) (char*, int, int); - int (*close) (int); - int (*read) (int, void*, int); - int (*write) (int, void*, int); - off_t (*lseek) (int, off_t, int); - int (*printf) (const char*, ...); - void (*cacheflush) (void); - char* (*gets) (char*); - union { - int (*smpfork) (unsigned long cp, char *sp); - int (*cpustart) (long, void (*)(void), void *, long); - } _s; - int (*semlock) (int sem); - void (*semunlock) (int sem); -}; - -extern struct callvectors *debug_vectors; - -#define pmon_open(name, flags, mode) debug_vectors->open(name, flage, mode) -#define pmon_close(fd) debug_vectors->close(fd) -#define pmon_read(fd, buf, count) debug_vectors->read(fd, buf, count) -#define pmon_write(fd, buf, count) debug_vectors->write(fd, buf, count) -#define pmon_lseek(fd, off, whence) debug_vectors->lseek(fd, off, whence) -#define pmon_printf(fmt...) debug_vectors->printf(fmt) -#define pmon_cacheflush() debug_vectors->cacheflush() -#define pmon_gets(s) debug_vectors->gets(s) -#define pmon_cpustart(n, f, sp, gp) debug_vectors->_s.cpustart(n, f, sp, gp) -#define pmon_smpfork(cp, sp) debug_vectors->_s.smpfork(cp, sp) -#define pmon_semlock(sem) debug_vectors->semlock(sem) -#define pmon_semunlock(sem) debug_vectors->semunlock(sem) - -#endif /* _ASM_PMON_H */ diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index fba18d4a9190..7619ad319400 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -385,7 +385,7 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29]) #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status) -#ifdef CONFIG_CPU_LOONGSON3 +#ifdef CONFIG_CPU_LOONGSON64 /* * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a * tight read loop is executed, because reads take priority over writes & the diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index 7f4a32d3345a..15ab16f99f28 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -15,12 +15,14 @@ #include <linux/stringify.h> #include <asm/asm.h> +#include <asm/asm-eva.h> #include <asm/cacheops.h> #include <asm/compiler.h> #include <asm/cpu-features.h> #include <asm/cpu-type.h> #include <asm/mipsmtregs.h> #include <asm/mmzone.h> +#include <asm/unroll.h> #include <linux/uaccess.h> /* for uaccess_kernel() */ extern void (*r4k_blast_dcache)(void); @@ -39,16 +41,19 @@ extern void (*r4k_blast_icache)(void); */ #define INDEX_BASE CKSEG0 -#define cache_op(op,addr) \ +#define _cache_op(insn, op, addr) \ __asm__ __volatile__( \ " .set push \n" \ " .set noreorder \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ - " cache %0, %1 \n" \ + " " insn("%0", "%1") " \n" \ " .set pop \n" \ : \ : "i" (op), "R" (*(unsigned char *)(addr))) +#define cache_op(op, addr) \ + _cache_op(kernel_cache, op, addr) + static inline void flush_icache_line_indexed(unsigned long addr) { cache_op(Index_Invalidate_I, addr); @@ -67,7 +72,7 @@ static inline void flush_scache_line_indexed(unsigned long addr) static inline void flush_icache_line(unsigned long addr) { switch (boot_cpu_type()) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: cache_op(Hit_Invalidate_I_Loongson2, addr); break; @@ -149,7 +154,7 @@ static inline void flush_scache_line(unsigned long addr) static inline int protected_flush_icache_line(unsigned long addr) { switch (boot_cpu_type()) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: return protected_cache_op(Hit_Invalidate_I_Loongson2, addr); default: @@ -193,338 +198,10 @@ static inline void invalidate_tcache_page(unsigned long addr) cache_op(Page_Invalidate_T, addr); } -#ifndef CONFIG_CPU_MIPSR6 -#define cache16_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x010(%0) \n" \ - " cache %1, 0x020(%0); cache %1, 0x030(%0) \n" \ - " cache %1, 0x040(%0); cache %1, 0x050(%0) \n" \ - " cache %1, 0x060(%0); cache %1, 0x070(%0) \n" \ - " cache %1, 0x080(%0); cache %1, 0x090(%0) \n" \ - " cache %1, 0x0a0(%0); cache %1, 0x0b0(%0) \n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0d0(%0) \n" \ - " cache %1, 0x0e0(%0); cache %1, 0x0f0(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x110(%0) \n" \ - " cache %1, 0x120(%0); cache %1, 0x130(%0) \n" \ - " cache %1, 0x140(%0); cache %1, 0x150(%0) \n" \ - " cache %1, 0x160(%0); cache %1, 0x170(%0) \n" \ - " cache %1, 0x180(%0); cache %1, 0x190(%0) \n" \ - " cache %1, 0x1a0(%0); cache %1, 0x1b0(%0) \n" \ - " cache %1, 0x1c0(%0); cache %1, 0x1d0(%0) \n" \ - " cache %1, 0x1e0(%0); cache %1, 0x1f0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache32_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x020(%0) \n" \ - " cache %1, 0x040(%0); cache %1, 0x060(%0) \n" \ - " cache %1, 0x080(%0); cache %1, 0x0a0(%0) \n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0e0(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x120(%0) \n" \ - " cache %1, 0x140(%0); cache %1, 0x160(%0) \n" \ - " cache %1, 0x180(%0); cache %1, 0x1a0(%0) \n" \ - " cache %1, 0x1c0(%0); cache %1, 0x1e0(%0) \n" \ - " cache %1, 0x200(%0); cache %1, 0x220(%0) \n" \ - " cache %1, 0x240(%0); cache %1, 0x260(%0) \n" \ - " cache %1, 0x280(%0); cache %1, 0x2a0(%0) \n" \ - " cache %1, 0x2c0(%0); cache %1, 0x2e0(%0) \n" \ - " cache %1, 0x300(%0); cache %1, 0x320(%0) \n" \ - " cache %1, 0x340(%0); cache %1, 0x360(%0) \n" \ - " cache %1, 0x380(%0); cache %1, 0x3a0(%0) \n" \ - " cache %1, 0x3c0(%0); cache %1, 0x3e0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache64_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x040(%0) \n" \ - " cache %1, 0x080(%0); cache %1, 0x0c0(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x140(%0) \n" \ - " cache %1, 0x180(%0); cache %1, 0x1c0(%0) \n" \ - " cache %1, 0x200(%0); cache %1, 0x240(%0) \n" \ - " cache %1, 0x280(%0); cache %1, 0x2c0(%0) \n" \ - " cache %1, 0x300(%0); cache %1, 0x340(%0) \n" \ - " cache %1, 0x380(%0); cache %1, 0x3c0(%0) \n" \ - " cache %1, 0x400(%0); cache %1, 0x440(%0) \n" \ - " cache %1, 0x480(%0); cache %1, 0x4c0(%0) \n" \ - " cache %1, 0x500(%0); cache %1, 0x540(%0) \n" \ - " cache %1, 0x580(%0); cache %1, 0x5c0(%0) \n" \ - " cache %1, 0x600(%0); cache %1, 0x640(%0) \n" \ - " cache %1, 0x680(%0); cache %1, 0x6c0(%0) \n" \ - " cache %1, 0x700(%0); cache %1, 0x740(%0) \n" \ - " cache %1, 0x780(%0); cache %1, 0x7c0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache128_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips3 \n" \ - " cache %1, 0x000(%0); cache %1, 0x080(%0) \n" \ - " cache %1, 0x100(%0); cache %1, 0x180(%0) \n" \ - " cache %1, 0x200(%0); cache %1, 0x280(%0) \n" \ - " cache %1, 0x300(%0); cache %1, 0x380(%0) \n" \ - " cache %1, 0x400(%0); cache %1, 0x480(%0) \n" \ - " cache %1, 0x500(%0); cache %1, 0x580(%0) \n" \ - " cache %1, 0x600(%0); cache %1, 0x680(%0) \n" \ - " cache %1, 0x700(%0); cache %1, 0x780(%0) \n" \ - " cache %1, 0x800(%0); cache %1, 0x880(%0) \n" \ - " cache %1, 0x900(%0); cache %1, 0x980(%0) \n" \ - " cache %1, 0xa00(%0); cache %1, 0xa80(%0) \n" \ - " cache %1, 0xb00(%0); cache %1, 0xb80(%0) \n" \ - " cache %1, 0xc00(%0); cache %1, 0xc80(%0) \n" \ - " cache %1, 0xd00(%0); cache %1, 0xd80(%0) \n" \ - " cache %1, 0xe00(%0); cache %1, 0xe80(%0) \n" \ - " cache %1, 0xf00(%0); cache %1, 0xf80(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#else -/* - * MIPS R6 changed the cache opcode and moved to a 8-bit offset field. - * This means we now need to increment the base register before we flush - * more cache lines - */ -#define cache16_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x010(%0)\n" \ - " cache %1, 0x020(%0); cache %1, 0x030(%0)\n" \ - " cache %1, 0x040(%0); cache %1, 0x050(%0)\n" \ - " cache %1, 0x060(%0); cache %1, 0x070(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x090(%0)\n" \ - " cache %1, 0x0a0(%0); cache %1, 0x0b0(%0)\n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0d0(%0)\n" \ - " cache %1, 0x0e0(%0); cache %1, 0x0f0(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x010($1)\n" \ - " cache %1, 0x020($1); cache %1, 0x030($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x050($1)\n" \ - " cache %1, 0x060($1); cache %1, 0x070($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x090($1)\n" \ - " cache %1, 0x0a0($1); cache %1, 0x0b0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0d0($1)\n" \ - " cache %1, 0x0e0($1); cache %1, 0x0f0($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache32_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x020(%0)\n" \ - " cache %1, 0x040(%0); cache %1, 0x060(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x0a0(%0)\n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0e0(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100\n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache64_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x040(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x0c0(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache128_unroll32(base,op) \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noreorder\n" \ - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ - " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ - "i" (op)); -#endif /* CONFIG_CPU_MIPSR6 */ - -/* - * Perform the cache operation specified by op using a user mode virtual - * address while in kernel mode. - */ -#define cache16_unroll32_user(base,op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips0 \n" \ - " .set eva \n" \ - " cachee %1, 0x000(%0); cachee %1, 0x010(%0) \n" \ - " cachee %1, 0x020(%0); cachee %1, 0x030(%0) \n" \ - " cachee %1, 0x040(%0); cachee %1, 0x050(%0) \n" \ - " cachee %1, 0x060(%0); cachee %1, 0x070(%0) \n" \ - " cachee %1, 0x080(%0); cachee %1, 0x090(%0) \n" \ - " cachee %1, 0x0a0(%0); cachee %1, 0x0b0(%0) \n" \ - " cachee %1, 0x0c0(%0); cachee %1, 0x0d0(%0) \n" \ - " cachee %1, 0x0e0(%0); cachee %1, 0x0f0(%0) \n" \ - " cachee %1, 0x100(%0); cachee %1, 0x110(%0) \n" \ - " cachee %1, 0x120(%0); cachee %1, 0x130(%0) \n" \ - " cachee %1, 0x140(%0); cachee %1, 0x150(%0) \n" \ - " cachee %1, 0x160(%0); cachee %1, 0x170(%0) \n" \ - " cachee %1, 0x180(%0); cachee %1, 0x190(%0) \n" \ - " cachee %1, 0x1a0(%0); cachee %1, 0x1b0(%0) \n" \ - " cachee %1, 0x1c0(%0); cachee %1, 0x1d0(%0) \n" \ - " cachee %1, 0x1e0(%0); cachee %1, 0x1f0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache32_unroll32_user(base, op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips0 \n" \ - " .set eva \n" \ - " cachee %1, 0x000(%0); cachee %1, 0x020(%0) \n" \ - " cachee %1, 0x040(%0); cachee %1, 0x060(%0) \n" \ - " cachee %1, 0x080(%0); cachee %1, 0x0a0(%0) \n" \ - " cachee %1, 0x0c0(%0); cachee %1, 0x0e0(%0) \n" \ - " cachee %1, 0x100(%0); cachee %1, 0x120(%0) \n" \ - " cachee %1, 0x140(%0); cachee %1, 0x160(%0) \n" \ - " cachee %1, 0x180(%0); cachee %1, 0x1a0(%0) \n" \ - " cachee %1, 0x1c0(%0); cachee %1, 0x1e0(%0) \n" \ - " cachee %1, 0x200(%0); cachee %1, 0x220(%0) \n" \ - " cachee %1, 0x240(%0); cachee %1, 0x260(%0) \n" \ - " cachee %1, 0x280(%0); cachee %1, 0x2a0(%0) \n" \ - " cachee %1, 0x2c0(%0); cachee %1, 0x2e0(%0) \n" \ - " cachee %1, 0x300(%0); cachee %1, 0x320(%0) \n" \ - " cachee %1, 0x340(%0); cachee %1, 0x360(%0) \n" \ - " cachee %1, 0x380(%0); cachee %1, 0x3a0(%0) \n" \ - " cachee %1, 0x3c0(%0); cachee %1, 0x3e0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); - -#define cache64_unroll32_user(base, op) \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noreorder \n" \ - " .set mips0 \n" \ - " .set eva \n" \ - " cachee %1, 0x000(%0); cachee %1, 0x040(%0) \n" \ - " cachee %1, 0x080(%0); cachee %1, 0x0c0(%0) \n" \ - " cachee %1, 0x100(%0); cachee %1, 0x140(%0) \n" \ - " cachee %1, 0x180(%0); cachee %1, 0x1c0(%0) \n" \ - " cachee %1, 0x200(%0); cachee %1, 0x240(%0) \n" \ - " cachee %1, 0x280(%0); cachee %1, 0x2c0(%0) \n" \ - " cachee %1, 0x300(%0); cachee %1, 0x340(%0) \n" \ - " cachee %1, 0x380(%0); cachee %1, 0x3c0(%0) \n" \ - " cachee %1, 0x400(%0); cachee %1, 0x440(%0) \n" \ - " cachee %1, 0x480(%0); cachee %1, 0x4c0(%0) \n" \ - " cachee %1, 0x500(%0); cachee %1, 0x540(%0) \n" \ - " cachee %1, 0x580(%0); cachee %1, 0x5c0(%0) \n" \ - " cachee %1, 0x600(%0); cachee %1, 0x640(%0) \n" \ - " cachee %1, 0x680(%0); cachee %1, 0x6c0(%0) \n" \ - " cachee %1, 0x700(%0); cachee %1, 0x740(%0) \n" \ - " cachee %1, 0x780(%0); cachee %1, 0x7c0(%0) \n" \ - " .set pop \n" \ - : \ - : "r" (base), \ - "i" (op)); +#define cache_unroll(times, insn, op, addr, lsize) do { \ + int i = 0; \ + unroll(times, _cache_op, insn, op, (addr) + (i++ * (lsize))); \ +} while (0) /* build blast_xxx, blast_xxx_page, blast_xxx_page_indexed */ #define __BUILD_BLAST_CACHE(pfx, desc, indexop, hitop, lsize, extra) \ @@ -539,7 +216,8 @@ static inline void extra##blast_##pfx##cache##lsize(void) \ \ for (ws = 0; ws < ws_end; ws += ws_inc) \ for (addr = start; addr < end; addr += lsize * 32) \ - cache##lsize##_unroll32(addr|ws, indexop); \ + cache_unroll(32, kernel_cache, indexop, \ + addr | ws, lsize); \ } \ \ static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \ @@ -548,7 +226,7 @@ static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \ unsigned long end = page + PAGE_SIZE; \ \ do { \ - cache##lsize##_unroll32(start, hitop); \ + cache_unroll(32, kernel_cache, hitop, start, lsize); \ start += lsize * 32; \ } while (start < end); \ } \ @@ -565,7 +243,8 @@ static inline void extra##blast_##pfx##cache##lsize##_page_indexed(unsigned long \ for (ws = 0; ws < ws_end; ws += ws_inc) \ for (addr = start; addr < end; addr += lsize * 32) \ - cache##lsize##_unroll32(addr|ws, indexop); \ + cache_unroll(32, kernel_cache, indexop, \ + addr | ws, lsize); \ } __BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 16, ) @@ -596,7 +275,7 @@ static inline void blast_##pfx##cache##lsize##_user_page(unsigned long page) \ unsigned long end = page + PAGE_SIZE; \ \ do { \ - cache##lsize##_unroll32_user(start, hitop); \ + cache_unroll(32, user_cache, hitop, start, lsize); \ start += lsize * 32; \ } while (start < end); \ } @@ -688,7 +367,8 @@ static inline void blast_##pfx##cache##lsize##_node(long node) \ \ for (ws = 0; ws < ws_end; ws += ws_inc) \ for (addr = start; addr < end; addr += lsize * 32) \ - cache##lsize##_unroll32(addr|ws, indexop); \ + cache_unroll(32, kernel_cache, indexop, \ + addr | ws, lsize); \ } __BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16) diff --git a/arch/mips/include/asm/sgi/heart.h b/arch/mips/include/asm/sgi/heart.h new file mode 100644 index 000000000000..c423221b4792 --- /dev/null +++ b/arch/mips/include/asm/sgi/heart.h @@ -0,0 +1,272 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HEART chip definitions + * + * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * 2009 Johannes Dickgreber <tanzy@gmx.de> + * 2007-2015 Joshua Kinard <kumba@gentoo.org> + */ +#ifndef __ASM_SGI_HEART_H +#define __ASM_SGI_HEART_H + +#include <linux/types.h> +#include <linux/time.h> + +/* + * There are 8 DIMM slots on an IP30 system + * board, which are grouped into four banks + */ +#define HEART_MEMORY_BANKS 4 + +/* HEART can support up to four CPUs */ +#define HEART_MAX_CPUS 4 + +#define HEART_XKPHYS_BASE ((void *)(IO_BASE | 0x000000000ff00000ULL)) + +/** + * struct ip30_heart_regs - struct that maps IP30 HEART registers. + * @mode: HEART_MODE - Purpose Unknown, machine reset called from here. + * @sdram_mode: HEART_SDRAM_MODE - purpose unknown. + * @mem_refresh: HEART_MEM_REF - purpose unknown. + * @mem_req_arb: HEART_MEM_REQ_ARB - purpose unknown. + * @mem_cfg.q: union for 64bit access to HEART_MEMCFG - 4x 64bit registers. + * @mem_cfg.l: union for 32bit access to HEART_MEMCFG - 8x 32bit registers. + * @fc_mode: HEART_FC_MODE - Purpose Unknown, possibly for GFX flow control. + * @fc_timer_limit: HEART_FC_TIMER_LIMIT - purpose unknown. + * @fc_addr: HEART_FC0_ADDR, HEART_FC1_ADDR - purpose unknown. + * @fc_credit_cnt: HEART_FC0_CR_CNT, HEART_FC1_CR_CNT - purpose unknown. + * @fc_timer: HEART_FC0_TIMER, HEART_FC1_TIMER - purpose unknown. + * @status: HEART_STATUS - HEART status information. + * @bus_err_addr: HEART_BERR_ADDR - likely contains addr of recent SIGBUS. + * @bus_err_misc: HEART_BERR_MISC - purpose unknown. + * @mem_err_addr: HEART_MEMERR_ADDR - likely contains addr of recent mem err. + * @mem_err_data: HEART_MEMERR_DATA - purpose unknown. + * @piur_acc_err: HEART_PIUR_ACC_ERR - likely for access err to HEART regs. + * @mlan_clock_div: HEART_MLAN_CLK_DIV - MicroLAN clock divider. + * @mlan_ctrl: HEART_MLAN_CTL - MicroLAN control. + * @__pad0: 0x0f40 bytes of padding -> next HEART register 0x01000. + * @undefined: Undefined/diag register, write to it triggers PIUR_ACC_ERR. + * @__pad1: 0xeff8 bytes of padding -> next HEART register 0x10000. + * @imr: HEART_IMR0 to HEART_IMR3 - per-cpu interrupt mask register. + * @set_isr: HEART_SET_ISR - set interrupt status register. + * @clear_isr: HEART_CLR_ISR - clear interrupt status register. + * @isr: HEART_ISR - interrupt status register (read-only). + * @imsr: HEART_IMSR - purpose unknown. + * @cause: HEART_CAUSE - HEART cause information. + * @__pad2: 0xffb8 bytes of padding -> next HEART register 0x20000. + * @count: HEART_COUNT - 52-bit counter. + * @__pad3: 0xfff8 bytes of padding -> next HEART register 0x30000. + * @compare: HEART_COMPARE - 24-bit compare. + * @__pad4: 0xfff8 bytes of padding -> next HEART register 0x40000. + * @trigger: HEART_TRIGGER - purpose unknown. + * @__pad5: 0xfff8 bytes of padding -> next HEART register 0x50000. + * @cpuid: HEART_PRID - contains CPU ID of CPU currently accessing HEART. + * @__pad6: 0xfff8 bytes of padding -> next HEART register 0x60000. + * @sync: HEART_SYNC - purpose unknown. + * + * HEART is the main system controller ASIC for IP30 system. It incorporates + * a memory controller, interrupt status/cause/set/clear management, basic + * timer with count/compare, and other functionality. For Linux, not all of + * HEART's functions are fully understood. + * + * Implementation note: All HEART registers are 64bits-wide, but the mem_cfg + * register only reports correct values if queried in 32bits. Hence the need + * for a union. Even though mem_cfg.l has 8 array slots, we only ever query + * up to 4 of those. IP30 has 8 DIMM slots arranged into 4 banks, w/ 2 DIMMs + * per bank. Each 32bit read accesses one of these banks. Perhaps HEART was + * designed to address up to 8 banks (16 DIMMs)? We may never know. + */ +struct ip30_heart_regs { /* 0x0ff00000 */ + u64 mode; /* + 0x00000 */ + /* Memory */ + u64 sdram_mode; /* + 0x00008 */ + u64 mem_refresh; /* + 0x00010 */ + u64 mem_req_arb; /* + 0x00018 */ + union { + u64 q[HEART_MEMORY_BANKS]; /* readq() */ + u32 l[HEART_MEMORY_BANKS * 2]; /* readl() */ + } mem_cfg; /* + 0x00020 */ + /* Flow control (gfx?) */ + u64 fc_mode; /* + 0x00040 */ + u64 fc_timer_limit; /* + 0x00048 */ + u64 fc_addr[2]; /* + 0x00050 */ + u64 fc_credit_cnt[2]; /* + 0x00060 */ + u64 fc_timer[2]; /* + 0x00070 */ + /* Status */ + u64 status; /* + 0x00080 */ + /* Bus error */ + u64 bus_err_addr; /* + 0x00088 */ + u64 bus_err_misc; /* + 0x00090 */ + /* Memory error */ + u64 mem_err_addr; /* + 0x00098 */ + u64 mem_err_data; /* + 0x000a0 */ + /* Misc */ + u64 piur_acc_err; /* + 0x000a8 */ + u64 mlan_clock_div; /* + 0x000b0 */ + u64 mlan_ctrl; /* + 0x000b8 */ + u64 __pad0[0x01e8]; /* + 0x000c0 + 0x0f40 */ + /* Undefined */ + u64 undefined; /* + 0x01000 */ + u64 __pad1[0x1dff]; /* + 0x01008 + 0xeff8 */ + /* Interrupts */ + u64 imr[HEART_MAX_CPUS]; /* + 0x10000 */ + u64 set_isr; /* + 0x10020 */ + u64 clear_isr; /* + 0x10028 */ + u64 isr; /* + 0x10030 */ + u64 imsr; /* + 0x10038 */ + u64 cause; /* + 0x10040 */ + u64 __pad2[0x1ff7]; /* + 0x10048 + 0xffb8 */ + /* Timer */ + u64 count; /* + 0x20000 */ + u64 __pad3[0x1fff]; /* + 0x20008 + 0xfff8 */ + u64 compare; /* + 0x30000 */ + u64 __pad4[0x1fff]; /* + 0x30008 + 0xfff8 */ + u64 trigger; /* + 0x40000 */ + u64 __pad5[0x1fff]; /* + 0x40008 + 0xfff8 */ + /* Misc */ + u64 cpuid; /* + 0x50000 */ + u64 __pad6[0x1fff]; /* + 0x50008 + 0xfff8 */ + u64 sync; /* + 0x60000 */ +}; + + +/* For timer-related bits. */ +#define HEART_NS_PER_CYCLE 80 +#define HEART_CYCLES_PER_SEC (NSEC_PER_SEC / HEART_NS_PER_CYCLE) + + +/* + * XXX: Everything below this comment will either go away or be cleaned + * up to fit in better with Linux. A lot of the bit definitions for + * HEART were derived from IRIX's sys/RACER/heart.h header file. + */ + +/* HEART Masks */ +#define HEART_ATK_MASK 0x0007ffffffffffff /* HEART attack mask */ +#define HEART_ACK_ALL_MASK 0xffffffffffffffff /* Ack everything */ +#define HEART_CLR_ALL_MASK 0x0000000000000000 /* Clear all */ +#define HEART_BR_ERR_MASK 0x7ff8000000000000 /* BRIDGE error mask */ +#define HEART_CPU0_ERR_MASK 0x8ff8000000000000 /* CPU0 error mask */ +#define HEART_CPU1_ERR_MASK 0x97f8000000000000 /* CPU1 error mask */ +#define HEART_CPU2_ERR_MASK 0xa7f8000000000000 /* CPU2 error mask */ +#define HEART_CPU3_ERR_MASK 0xc7f8000000000000 /* CPU3 error mask */ +#define HEART_ERR_MASK 0x1ff /* HEART error mask */ +#define HEART_ERR_MASK_START 51 /* HEART error start */ +#define HEART_ERR_MASK_END 63 /* HEART error end */ + +/* Bits in the HEART_MODE register. */ +#define HM_PROC_DISABLE_SHFT 60 +#define HM_PROC_DISABLE_MSK (0xfUL << HM_PROC_DISABLE_SHFT) +#define HM_PROC_DISABLE(x) (0x1UL << (x) + HM_PROC_DISABLE_SHFT) +#define HM_MAX_PSR (0x7UL << 57) +#define HM_MAX_IOSR (0x7UL << 54) +#define HM_MAX_PEND_IOSR (0x7UL << 51) +#define HM_TRIG_SRC_SEL_MSK (0x7UL << 48) +#define HM_TRIG_HEART_EXC (0x0UL << 48) +#define HM_TRIG_REG_BIT (0x1UL << 48) +#define HM_TRIG_SYSCLK (0x2UL << 48) +#define HM_TRIG_MEMCLK_2X (0x3UL << 48) +#define HM_TRIG_MEMCLK (0x4UL << 48) +#define HM_TRIG_IOCLK (0x5UL << 48) +#define HM_PIU_TEST_MODE (0xfUL << 40) +#define HM_GP_FLAG_MSK (0xfUL << 36) +#define HM_GP_FLAG(x) BIT((x) + 36) +#define HM_MAX_PROC_HYST (0xfUL << 32) +#define HM_LLP_WRST_AFTER_RST BIT(28) +#define HM_LLP_LINK_RST BIT(27) +#define HM_LLP_WARM_RST BIT(26) +#define HM_COR_ECC_LCK BIT(25) +#define HM_REDUCED_PWR BIT(24) +#define HM_COLD_RST BIT(23) +#define HM_SW_RST BIT(22) +#define HM_MEM_FORCE_WR BIT(21) +#define HM_DB_ERR_GEN BIT(20) +#define HM_SB_ERR_GEN BIT(19) +#define HM_CACHED_PIO_EN BIT(18) +#define HM_CACHED_PROM_EN BIT(17) +#define HM_PE_SYS_COR_ERE BIT(16) +#define HM_GLOBAL_ECC_EN BIT(15) +#define HM_IO_COH_EN BIT(14) +#define HM_INT_EN BIT(13) +#define HM_DATA_CHK_EN BIT(12) +#define HM_REF_EN BIT(11) +#define HM_BAD_SYSWR_ERE BIT(10) +#define HM_BAD_SYSRD_ERE BIT(9) +#define HM_SYSSTATE_ERE BIT(8) +#define HM_SYSCMD_ERE BIT(7) +#define HM_NCOR_SYS_ERE BIT(6) +#define HM_COR_SYS_ERE BIT(5) +#define HM_DATA_ELMNT_ERE BIT(4) +#define HM_MEM_ADDR_PROC_ERE BIT(3) +#define HM_MEM_ADDR_IO_ERE BIT(2) +#define HM_NCOR_MEM_ERE BIT(1) +#define HM_COR_MEM_ERE BIT(0) + +/* Bits in the HEART_MEM_REF register. */ +#define HEART_MEMREF_REFS(x) ((0xfUL & (x)) << 16) +#define HEART_MEMREF_PERIOD(x) ((0xffffUL & (x))) +#define HEART_MEMREF_REFS_VAL HEART_MEMREF_REFS(8) +#define HEART_MEMREF_PERIOD_VAL HEART_MEMREF_PERIOD(0x4000) +#define HEART_MEMREF_VAL (HEART_MEMREF_REFS_VAL | \ + HEART_MEMREF_PERIOD_VAL) + +/* Bits in the HEART_MEM_REQ_ARB register. */ +#define HEART_MEMARB_IODIS (1 << 20) +#define HEART_MEMARB_MAXPMWRQS (15 << 16) +#define HEART_MEMARB_MAXPMRRQS (15 << 12) +#define HEART_MEMARB_MAXPMRQS (15 << 8) +#define HEART_MEMARB_MAXRRRQS (15 << 4) +#define HEART_MEMARB_MAXGBRRQS (15) + +/* Bits in the HEART_MEMCFG<x> registers. */ +#define HEART_MEMCFG_VALID 0x80000000 /* Bank is valid */ +#define HEART_MEMCFG_DENSITY 0x01c00000 /* Mem density */ +#define HEART_MEMCFG_SIZE_MASK 0x003f0000 /* Mem size mask */ +#define HEART_MEMCFG_ADDR_MASK 0x000001ff /* Base addr mask */ +#define HEART_MEMCFG_SIZE_SHIFT 16 /* Mem size shift */ +#define HEART_MEMCFG_DENSITY_SHIFT 22 /* Density Shift */ +#define HEART_MEMCFG_UNIT_SHIFT 25 /* Unit Shift, 32MB */ + +/* Bits in the HEART_STATUS register */ +#define HEART_STAT_HSTL_SDRV BIT(14) +#define HEART_STAT_FC_CR_OUT(x) BIT((x) + 12) +#define HEART_STAT_DIR_CNNCT BIT(11) +#define HEART_STAT_TRITON BIT(10) +#define HEART_STAT_R4K BIT(9) +#define HEART_STAT_BIG_ENDIAN BIT(8) +#define HEART_STAT_PROC_SHFT 4 +#define HEART_STAT_PROC_MSK (0xfUL << HEART_STAT_PROC_SHFT) +#define HEART_STAT_PROC_ACTIVE(x) (0x1UL << ((x) + HEART_STAT_PROC_SHFT)) +#define HEART_STAT_WIDGET_ID 0xf + +/* Bits in the HEART_CAUSE register */ +#define HC_PE_SYS_COR_ERR_MSK (0xfUL << 60) +#define HC_PE_SYS_COR_ERR(x) BIT((x) + 60) +#define HC_PIOWDB_OFLOW BIT(44) +#define HC_PIORWRB_OFLOW BIT(43) +#define HC_PIUR_ACC_ERR BIT(42) +#define HC_BAD_SYSWR_ERR BIT(41) +#define HC_BAD_SYSRD_ERR BIT(40) +#define HC_SYSSTATE_ERR_MSK (0xfUL << 36) +#define HC_SYSSTATE_ERR(x) BIT((x) + 36) +#define HC_SYSCMD_ERR_MSK (0xfUL << 32) +#define HC_SYSCMD_ERR(x) BIT((x) + 32) +#define HC_NCOR_SYSAD_ERR_MSK (0xfUL << 28) +#define HC_NCOR_SYSAD_ERR(x) BIT((x) + 28) +#define HC_COR_SYSAD_ERR_MSK (0xfUL << 24) +#define HC_COR_SYSAD_ERR(x) BIT((x) + 24) +#define HC_DATA_ELMNT_ERR_MSK (0xfUL << 20) +#define HC_DATA_ELMNT_ERR(x) BIT((x) + 20) +#define HC_WIDGET_ERR BIT(16) +#define HC_MEM_ADDR_ERR_PROC_MSK (0xfUL << 4) +#define HC_MEM_ADDR_ERR_PROC(x) BIT((x) + 4) +#define HC_MEM_ADDR_ERR_IO BIT(2) +#define HC_NCOR_MEM_ERR BIT(1) +#define HC_COR_MEM_ERR BIT(0) + +extern struct ip30_heart_regs __iomem *heart_regs; + +#define heart_read ____raw_readq +#define heart_write ____raw_writeq + +#endif /* __ASM_SGI_HEART_H */ diff --git a/arch/mips/include/asm/sgi/sgi.h b/arch/mips/include/asm/sgi/sgi.h deleted file mode 100644 index b61557151e3f..000000000000 --- a/arch/mips/include/asm/sgi/sgi.h +++ /dev/null @@ -1,48 +0,0 @@ -/* - * 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. - * - * sgi.h: Definitions specific to SGI machines. - * - * Copyright (C) 1996 David S. Miller (dm@sgi.com) - */ -#ifndef _ASM_SGI_SGI_H -#define _ASM_SGI_SGI_H - -/* UP=UniProcessor MP=MultiProcessor(capable) */ -enum sgi_mach { - ip4, /* R2k UP */ - ip5, /* R2k MP */ - ip6, /* R3k UP */ - ip7, /* R3k MP */ - ip9, /* R3k UP */ - ip12, /* R3kA UP, Indigo */ - ip15, /* R3kA MP */ - ip17, /* R4K UP */ - ip19, /* R4K MP */ - ip20, /* R4K UP, Indigo */ - ip21, /* R8k/TFP MP */ - ip22, /* R4x00 UP, Indy, Indigo2 */ - ip25, /* R10k MP */ - ip26, /* R8k/TFP UP, Indigo2 */ - ip27, /* R10k MP, R12k MP, R14k MP, Origin 200/2k, Onyx2 */ - ip28, /* R10k UP, Indigo2 Impact R10k */ - ip30, /* R10k MP, R12k MP, R14k MP, Octane */ - ip32, /* R5k UP, RM5200 UP, RM7k UP, R10k UP, R12k UP, O2 */ - ip35, /* R14k MP, R16k MP, Origin 300/3k, Onyx3, Fuel, Tezro */ -}; - -extern enum sgi_mach sgimach; -extern void sgi_sysinit(void); - -/* Many I/O space registers are byte sized and are contained within - * one byte per word, specifically the MSB, this macro helps out. - */ -#ifdef __MIPSEL__ -#define SGI_MSB(regaddr) (regaddr) -#else -#define SGI_MSB(regaddr) ((regaddr) | 0x3) -#endif - -#endif /* _ASM_SGI_SGI_H */ diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h index 0d9fad5915fe..80f900417f7e 100644 --- a/arch/mips/include/asm/sgialib.h +++ b/arch/mips/include/asm/sgialib.h @@ -15,14 +15,6 @@ #include <asm/sgiarcs.h> extern struct linux_romvec *romvec; -extern int prom_argc; - -extern LONG *_prom_argv, *_prom_envp; - -/* A 32-bit ARC PROM pass arguments and environment as 32-bit pointer. - These macros take care of sign extension. */ -#define prom_argv(index) ((char *) (long) _prom_argv[(index)]) -#define prom_argc(index) ((char *) (long) _prom_argc[(index)]) extern int prom_flags; @@ -47,12 +39,6 @@ extern void prom_meminit(void); /* PROM device tree library routines. */ #define PROM_NULL_COMPONENT ((pcomponent *) 0) -/* Get sibling component of THIS. */ -extern pcomponent *ArcGetPeer(pcomponent *this); - -/* Get child component of THIS. */ -extern pcomponent *ArcGetChild(pcomponent *this); - /* This is called at prom_init time to identify the * ARC architecture we are running on */ @@ -60,22 +46,16 @@ extern void prom_identify_arch(void); /* Environment variable routines. */ extern PCHAR ArcGetEnvironmentVariable(PCHAR name); -extern LONG ArcSetEnvironmentVariable(PCHAR name, PCHAR value); /* ARCS command line parsing. */ -extern void prom_init_cmdline(void); +extern void prom_init_cmdline(int argc, LONG *argv); /* File operations. */ extern LONG ArcRead(ULONG fd, PVOID buf, ULONG num, PULONG cnt); extern LONG ArcWrite(ULONG fd, PVOID buf, ULONG num, PULONG cnt); /* Misc. routines. */ -extern VOID ArcHalt(VOID) __noreturn; -extern VOID ArcPowerDown(VOID) __noreturn; -extern VOID ArcRestart(VOID) __noreturn; -extern VOID ArcReboot(VOID) __noreturn; extern VOID ArcEnterInteractiveMode(VOID) __noreturn; -extern VOID ArcFlushAllCaches(VOID); extern DISPLAY_STATUS *ArcGetDisplayStatus(ULONG FileID); #endif /* _ASM_SGIALIB_H */ diff --git a/arch/mips/include/asm/sgiarcs.h b/arch/mips/include/asm/sgiarcs.h index 105a9479ac5f..e1512cab180b 100644 --- a/arch/mips/include/asm/sgiarcs.h +++ b/arch/mips/include/asm/sgiarcs.h @@ -12,6 +12,8 @@ #ifndef _ASM_SGIARCS_H #define _ASM_SGIARCS_H +#include <linux/kernel.h> + #include <asm/types.h> #include <asm/fw/arc/types.h> @@ -368,110 +370,65 @@ struct linux_smonblock { #if defined(CONFIG_64BIT) && defined(CONFIG_FW_ARC32) -#define __arc_clobbers \ - "$2", "$3" /* ... */, "$8", "$9", "$10", "$11", \ - "$12", "$13", "$14", "$15", "$16", "$24", "$25", "$31" +extern long call_o32(long vec, void *stack, ...); + +extern u64 o32_stk[4096]; +#define O32_STK (&o32_stk[ARRAY_SIZE(o32_stk)]) #define ARC_CALL0(dest) \ ({ long __res; \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec) \ - : __arc_clobbers, "$4", "$5", "$6", "$7"); \ - (unsigned long) __res; \ + __res = call_o32(__vec, O32_STK); \ + __res; \ }) #define ARC_CALL1(dest, a1) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ + int __a1 = (int) (long) (a1); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1) \ - : __arc_clobbers, "$5", "$6", "$7"); \ - (unsigned long) __res; \ + __res = call_o32(__vec, O32_STK, __a1); \ + __res; \ }) #define ARC_CALL2(dest, a1, a2) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1), "r" (__a2) \ - : __arc_clobbers, "$6", "$7"); \ + __res = call_o32(__vec, O32_STK, __a1, __a2); \ __res; \ }) #define ARC_CALL3(dest, a1, a2, a3) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ - register signed int __a3 __asm__("$6") = (int) (long) (a3); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ + int __a3 = (int) (long) (a3); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1), "r" (__a2), "r" (__a3) \ - : __arc_clobbers, "$7"); \ + __res = call_o32(__vec, O32_STK, __a1, __a2, __a3); \ __res; \ }) #define ARC_CALL4(dest, a1, a2, a3, a4) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ - register signed int __a3 __asm__("$6") = (int) (long) (a3); \ - register signed int __a4 __asm__("$7") = (int) (long) (a4); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ + int __a3 = (int) (long) (a3); \ + int __a4 = (int) (long) (a4); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), "r" (__a1), "r" (__a2), "r" (__a3), \ - "r" (__a4) \ - : __arc_clobbers); \ + __res = call_o32(__vec, O32_STK, __a1, __a2, __a3, __a4); \ __res; \ }) -#define ARC_CALL5(dest, a1, a2, a3, a4, a5) \ +#define ARC_CALL5(dest, a1, a2, a3, a4, a5) \ ({ long __res; \ - register signed int __a1 __asm__("$4") = (int) (long) (a1); \ - register signed int __a2 __asm__("$5") = (int) (long) (a2); \ - register signed int __a3 __asm__("$6") = (int) (long) (a3); \ - register signed int __a4 __asm__("$7") = (int) (long) (a4); \ - register signed int __a5 = (int) (long) (a5); \ + int __a1 = (int) (long) (a1); \ + int __a2 = (int) (long) (a2); \ + int __a3 = (int) (long) (a3); \ + int __a4 = (int) (long) (a4); \ + int __a5 = (int) (long) (a5); \ long __vec = (long) romvec->dest; \ - __asm__ __volatile__( \ - "dsubu\t$29, 32\n\t" \ - "sw\t%7, 16($29)\n\t" \ - "jalr\t%1\n\t" \ - "daddu\t$29, 32\n\t" \ - "move\t%0, $2" \ - : "=r" (__res), "=r" (__vec) \ - : "1" (__vec), \ - "r" (__a1), "r" (__a2), "r" (__a3), "r" (__a4), \ - "r" (__a5) \ - : __arc_clobbers); \ + __res = call_o32(__vec, O32_STK, __a1, __a2, __a3, __a4, __a5); \ __res; \ }) diff --git a/arch/mips/include/asm/sn/agent.h b/arch/mips/include/asm/sn/agent.h index e33d09293019..7e9b3271737a 100644 --- a/arch/mips/include/asm/sn/agent.h +++ b/arch/mips/include/asm/sn/agent.h @@ -26,7 +26,7 @@ #if defined(CONFIG_SGI_IP27) #define HUB_NIC_ADDR(_cpuid) \ - REMOTE_HUB_ADDR(COMPACT_TO_NASID_NODEID(cpu_to_node(_cpuid)), \ + REMOTE_HUB_ADDR(cpu_to_node(_cpuid), \ MD_MLAN_CTL) #endif diff --git a/arch/mips/include/asm/sn/arch.h b/arch/mips/include/asm/sn/arch.h index 3f1fb1454749..f7d3273d9599 100644 --- a/arch/mips/include/asm/sn/arch.h +++ b/arch/mips/include/asm/sn/arch.h @@ -19,44 +19,13 @@ #define cputonasid(cpu) (sn_cpu_info[(cpu)].p_nasid) #define cputoslice(cpu) (sn_cpu_info[(cpu)].p_slice) -#define makespnum(_nasid, _slice) \ - (((_nasid) << CPUS_PER_NODE_SHFT) | (_slice)) #define INVALID_NASID (nasid_t)-1 -#define INVALID_CNODEID (cnodeid_t)-1 #define INVALID_PNODEID (pnodeid_t)-1 #define INVALID_MODULE (moduleid_t)-1 #define INVALID_PARTID (partid_t)-1 extern nasid_t get_nasid(void); -extern cnodeid_t get_cpu_cnode(cpuid_t); extern int get_cpu_slice(cpuid_t); -/* - * NO ONE should access these arrays directly. The only reason we refer to - * them here is to avoid the procedure call that would be required in the - * macros below. (Really want private data members here :-) - */ -extern cnodeid_t nasid_to_compact_node[MAX_NASIDS]; -extern nasid_t compact_to_nasid_node[MAX_COMPACT_NODES]; - -/* - * These macros are used by various parts of the kernel to convert - * between the three different kinds of node numbering. At least some - * of them may change to procedure calls in the future, but the macros - * will continue to work. Don't use the arrays above directly. - */ - -#define NASID_TO_REGION(nnode) \ - ((nnode) >> \ - (is_fine_dirmode() ? NASID_TO_FINEREG_SHFT : NASID_TO_COARSEREG_SHFT)) - -extern cnodeid_t nasid_to_compact_node[MAX_NASIDS]; -extern nasid_t compact_to_nasid_node[MAX_COMPACT_NODES]; -extern cnodeid_t cpuid_to_compact_node[MAXCPUS]; - -#define NASID_TO_COMPACT_NODEID(nnode) (nasid_to_compact_node[nnode]) -#define COMPACT_TO_NASID_NODEID(cnode) (compact_to_nasid_node[cnode]) -#define CPUID_TO_COMPACT_NODEID(cpu) (cpuid_to_compact_node[(cpu)]) - #endif /* _ASM_SN_ARCH_H */ diff --git a/arch/mips/include/asm/sn/gda.h b/arch/mips/include/asm/sn/gda.h index 85fa1b5f639d..d52f81620661 100644 --- a/arch/mips/include/asm/sn/gda.h +++ b/arch/mips/include/asm/sn/gda.h @@ -60,9 +60,7 @@ typedef struct gda { /* Pointer to a mask of nodes with copies * of the kernel. */ char g_padding[56]; /* pad out to 128 bytes */ - nasid_t g_nasidtable[MAX_COMPACT_NODES]; /* NASID of each node, - * indexed by cnodeid. - */ + nasid_t g_nasidtable[MAX_NUMNODES]; /* NASID of each node */ } gda_t; #define GDA ((gda_t*) GDA_ADDR(get_nasid())) diff --git a/arch/mips/include/asm/sn/hub.h b/arch/mips/include/asm/sn/hub.h index 338f7eed74f1..45878fbefbae 100644 --- a/arch/mips/include/asm/sn/hub.h +++ b/arch/mips/include/asm/sn/hub.h @@ -10,8 +10,8 @@ #include <asm/xtalk/xtalk.h> /* ip27-hubio.c */ -extern unsigned long hub_pio_map(cnodeid_t cnode, xwidgetnum_t widget, +extern unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget, unsigned long xtalk_addr, size_t size); -extern void hub_pio_init(cnodeid_t cnode); +extern void hub_pio_init(nasid_t nasid); #endif /* __ASM_SN_HUB_H */ diff --git a/arch/mips/include/asm/sn/ioc3.h b/arch/mips/include/asm/sn/ioc3.h index a947eed48fee..78ef760ddde4 100644 --- a/arch/mips/include/asm/sn/ioc3.h +++ b/arch/mips/include/asm/sn/ioc3.h @@ -590,4 +590,13 @@ struct ioc3_etxd { #define MIDR_DATA_MASK 0x0000ffff +/* subsystem IDs supplied by card detection in pci-xtalk-bridge */ +#define IOC3_SUBSYS_IP27_BASEIO6G 0xc300 +#define IOC3_SUBSYS_IP27_MIO 0xc301 +#define IOC3_SUBSYS_IP27_BASEIO 0xc302 +#define IOC3_SUBSYS_IP29_SYSBOARD 0xc303 +#define IOC3_SUBSYS_IP30_SYSBOARD 0xc304 +#define IOC3_SUBSYS_MENET 0xc305 +#define IOC3_SUBSYS_MENET4 0xc306 + #endif /* MIPS_SN_IOC3_H */ diff --git a/arch/mips/include/asm/sn/mapped_kernel.h b/arch/mips/include/asm/sn/mapped_kernel.h index 2f3efa91c16e..3f1049807018 100644 --- a/arch/mips/include/asm/sn/mapped_kernel.h +++ b/arch/mips/include/asm/sn/mapped_kernel.h @@ -37,10 +37,10 @@ #define MAPPED_KERN_RO_TO_PHYS(x) \ ((unsigned long)MAPPED_ADDR_RO_TO_PHYS(x) | \ - MAPPED_KERN_RO_PHYSBASE(get_compact_nodeid())) + MAPPED_KERN_RO_PHYSBASE(get_nasid())) #define MAPPED_KERN_RW_TO_PHYS(x) \ ((unsigned long)MAPPED_ADDR_RW_TO_PHYS(x) | \ - MAPPED_KERN_RW_PHYSBASE(get_compact_nodeid())) + MAPPED_KERN_RW_PHYSBASE(get_nasid())) #else /* CONFIG_MAPPED_KERNEL */ diff --git a/arch/mips/include/asm/sn/sn0/arch.h b/arch/mips/include/asm/sn/sn0/arch.h index 425a67e6a947..12f4c4649ff0 100644 --- a/arch/mips/include/asm/sn/sn0/arch.h +++ b/arch/mips/include/asm/sn/sn0/arch.h @@ -12,25 +12,11 @@ #define _ASM_SN_SN0_ARCH_H -#ifndef SN0XXL /* 128 cpu SMP max */ -/* - * This is the maximum number of nodes that can be part of a kernel. - * Effectively, it's the maximum number of compact node ids (cnodeid_t). - */ -#define MAX_COMPACT_NODES 64 - /* * MAXCPUS refers to the maximum number of CPUs in a single kernel. * This is not necessarily the same as MAXNODES * CPUS_PER_NODE */ -#define MAXCPUS 128 - -#else /* SN0XXL system */ - -#define MAX_COMPACT_NODES 128 -#define MAXCPUS 256 - -#endif /* SN0XXL */ +#define MAXCPUS (MAX_NUMNODES * CPUS_PER_NODE) /* * This is the maximum number of NASIDS that can be present in a system. @@ -66,7 +52,5 @@ #define SLOT_MIN_MEM_SIZE (32*1024*1024) #define CPUS_PER_NODE 2 /* CPUs on a single hub */ -#define CPUS_PER_NODE_SHFT 1 /* Bits to shift in the node number */ -#define CPUS_PER_SUBNODE 2 /* CPUs on a single hub PI */ #endif /* _ASM_SN_SN0_ARCH_H */ diff --git a/arch/mips/include/asm/sn/sn_private.h b/arch/mips/include/asm/sn/sn_private.h index f09ba846c644..63a2c30d81c6 100644 --- a/arch/mips/include/asm/sn/sn_private.h +++ b/arch/mips/include/asm/sn/sn_private.h @@ -7,14 +7,13 @@ extern nasid_t master_nasid; extern void cpu_node_probe(void); -extern cnodeid_t get_compact_nodeid(void); -extern void hub_rtc_init(cnodeid_t); +extern void hub_rtc_init(nasid_t nasid); extern void cpu_time_init(void); extern void per_cpu_init(void); extern void install_cpu_nmi_handler(int slice); extern void install_ipi(void); extern void setup_replication_mask(void); extern void replicate_kernel_text(void); -extern unsigned long node_getfirstfree(cnodeid_t); +extern unsigned long node_getfirstfree(nasid_t nasid); #endif /* __ASM_SN_SN_PRIVATE_H */ diff --git a/arch/mips/include/asm/sn/types.h b/arch/mips/include/asm/sn/types.h index 6d24d4e8b9ed..203c927e84d1 100644 --- a/arch/mips/include/asm/sn/types.h +++ b/arch/mips/include/asm/sn/types.h @@ -12,13 +12,9 @@ #include <linux/types.h> typedef unsigned long cpuid_t; -typedef unsigned long cnodemask_t; typedef signed short nasid_t; /* node id in numa-as-id space */ -typedef signed short cnodeid_t; /* node id in compact-id space */ typedef signed char partid_t; /* partition ID type */ typedef signed short moduleid_t; /* user-visible module number type */ -typedef signed short cmoduleid_t; /* kernel compact module id type */ -typedef unsigned char clusterid_t; /* Clusterid of the cell */ typedef dev_t vertex_hdl_t; /* hardware graph vertex handle */ diff --git a/arch/mips/include/asm/string.h b/arch/mips/include/asm/string.h index 29030cb398ee..1de3bbce8e88 100644 --- a/arch/mips/include/asm/string.h +++ b/arch/mips/include/asm/string.h @@ -10,127 +10,6 @@ #ifndef _ASM_STRING_H #define _ASM_STRING_H - -/* - * Most of the inline functions are rather naive implementations so I just - * didn't bother updating them for 64-bit ... - */ -#ifdef CONFIG_32BIT - -#ifndef IN_STRING_C - -#define __HAVE_ARCH_STRCPY -static __inline__ char *strcpy(char *__dest, __const__ char *__src) -{ - char *__xdest = __dest; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n" - "1:\tlbu\t$1,(%1)\n\t" - "addiu\t%1,1\n\t" - "sb\t$1,(%0)\n\t" - "bnez\t$1,1b\n\t" - "addiu\t%0,1\n\t" - ".set\tat\n\t" - ".set\treorder" - : "=r" (__dest), "=r" (__src) - : "0" (__dest), "1" (__src) - : "memory"); - - return __xdest; -} - -#define __HAVE_ARCH_STRNCPY -static __inline__ char *strncpy(char *__dest, __const__ char *__src, size_t __n) -{ - char *__xdest = __dest; - - if (__n == 0) - return __xdest; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n" - "1:\tlbu\t$1,(%1)\n\t" - "subu\t%2,1\n\t" - "sb\t$1,(%0)\n\t" - "beqz\t$1,2f\n\t" - "addiu\t%0,1\n\t" - "bnez\t%2,1b\n\t" - "addiu\t%1,1\n" - "2:\n\t" - ".set\tat\n\t" - ".set\treorder" - : "=r" (__dest), "=r" (__src), "=r" (__n) - : "0" (__dest), "1" (__src), "2" (__n) - : "memory"); - - return __xdest; -} - -#define __HAVE_ARCH_STRCMP -static __inline__ int strcmp(__const__ char *__cs, __const__ char *__ct) -{ - int __res; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n\t" - "lbu\t%2,(%0)\n" - "1:\tlbu\t$1,(%1)\n\t" - "addiu\t%0,1\n\t" - "bne\t$1,%2,2f\n\t" - "addiu\t%1,1\n\t" - "bnez\t%2,1b\n\t" - "lbu\t%2,(%0)\n\t" -#if defined(CONFIG_CPU_R3000) - "nop\n\t" -#endif - "move\t%2,$1\n" - "2:\tsubu\t%2,$1\n" - "3:\t.set\tat\n\t" - ".set\treorder" - : "=r" (__cs), "=r" (__ct), "=r" (__res) - : "0" (__cs), "1" (__ct)); - - return __res; -} - -#endif /* !defined(IN_STRING_C) */ - -#define __HAVE_ARCH_STRNCMP -static __inline__ int -strncmp(__const__ char *__cs, __const__ char *__ct, size_t __count) -{ - int __res; - - __asm__ __volatile__( - ".set\tnoreorder\n\t" - ".set\tnoat\n" - "1:\tlbu\t%3,(%0)\n\t" - "beqz\t%2,2f\n\t" - "lbu\t$1,(%1)\n\t" - "subu\t%2,1\n\t" - "bne\t$1,%3,3f\n\t" - "addiu\t%0,1\n\t" - "bnez\t%3,1b\n\t" - "addiu\t%1,1\n" - "2:\n\t" -#if defined(CONFIG_CPU_R3000) - "nop\n\t" -#endif - "move\t%3,$1\n" - "3:\tsubu\t%3,$1\n\t" - ".set\tat\n\t" - ".set\treorder" - : "=r" (__cs), "=r" (__ct), "=r" (__count), "=r" (__res) - : "0" (__cs), "1" (__ct), "2" (__count)); - - return __res; -} -#endif /* CONFIG_32BIT */ - #define __HAVE_ARCH_MEMSET extern void *memset(void *__s, int __c, size_t __count); diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h new file mode 100644 index 000000000000..7c6a1095f556 --- /dev/null +++ b/arch/mips/include/asm/sync.h @@ -0,0 +1,207 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __MIPS_ASM_SYNC_H__ +#define __MIPS_ASM_SYNC_H__ + +/* + * sync types are defined by the MIPS64 Instruction Set documentation in Volume + * II-A of the MIPS Architecture Reference Manual, which can be found here: + * + * https://www.mips.com/?do-download=the-mips64-instruction-set-v6-06 + * + * Two types of barrier are provided: + * + * 1) Completion barriers, which ensure that a memory operation has actually + * completed & often involve stalling the CPU pipeline to do so. + * + * 2) Ordering barriers, which only ensure that affected memory operations + * won't be reordered in the CPU pipeline in a manner that violates the + * restrictions imposed by the barrier. + * + * Ordering barriers can be more efficient than completion barriers, since: + * + * a) Ordering barriers only require memory access instructions which preceed + * them in program order (older instructions) to reach a point in the + * load/store datapath beyond which reordering is not possible before + * allowing memory access instructions which follow them (younger + * instructions) to be performed. That is, older instructions don't + * actually need to complete - they just need to get far enough that all + * other coherent CPUs will observe their completion before they observe + * the effects of younger instructions. + * + * b) Multiple variants of ordering barrier are provided which allow the + * effects to be restricted to different combinations of older or younger + * loads or stores. By way of example, if we only care that stores older + * than a barrier are observed prior to stores that are younger than a + * barrier & don't care about the ordering of loads then the 'wmb' + * ordering barrier can be used. Limiting the barrier's effects to stores + * allows loads to continue unaffected & potentially allows the CPU to + * make progress faster than if younger loads had to wait for older stores + * to complete. + */ + +/* + * No sync instruction at all; used to allow code to nullify the effect of the + * __SYNC() macro without needing lots of #ifdefery. + */ +#define __SYNC_none -1 + +/* + * A full completion barrier; all memory accesses appearing prior to this sync + * instruction in program order must complete before any memory accesses + * appearing after this sync instruction in program order. + */ +#define __SYNC_full 0x00 + +/* + * For now we use a full completion barrier to implement all sync types, until + * we're satisfied that lightweight ordering barriers defined by MIPSr6 are + * sufficient to uphold our desired memory model. + */ +#define __SYNC_aq __SYNC_full +#define __SYNC_rl __SYNC_full +#define __SYNC_mb __SYNC_full + +/* + * ...except on Cavium Octeon CPUs, which have been using the 'wmb' ordering + * barrier since 2010 & omit 'rmb' barriers because the CPUs don't perform + * speculative reads. + */ +#ifdef CONFIG_CPU_CAVIUM_OCTEON +# define __SYNC_rmb __SYNC_none +# define __SYNC_wmb 0x04 +#else +# define __SYNC_rmb __SYNC_full +# define __SYNC_wmb __SYNC_full +#endif + +/* + * A GINV sync is a little different; it doesn't relate directly to loads or + * stores, but instead causes synchronization of an icache or TLB global + * invalidation operation triggered by the ginvi or ginvt instructions + * respectively. In cases where we need to know that a ginvi or ginvt operation + * has been performed by all coherent CPUs, we must issue a sync instruction of + * this type. Once this instruction graduates all coherent CPUs will have + * observed the invalidation. + */ +#define __SYNC_ginv 0x14 + +/* Trivial; indicate that we always need this sync instruction. */ +#define __SYNC_always (1 << 0) + +/* + * Indicate that we need this sync instruction only on systems with weakly + * ordered memory access. In general this is most MIPS systems, but there are + * exceptions which provide strongly ordered memory. + */ +#ifdef CONFIG_WEAK_ORDERING +# define __SYNC_weak_ordering (1 << 1) +#else +# define __SYNC_weak_ordering 0 +#endif + +/* + * Indicate that we need this sync instruction only on systems where LL/SC + * don't implicitly provide a memory barrier. In general this is most MIPS + * systems. + */ +#ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC +# define __SYNC_weak_llsc (1 << 2) +#else +# define __SYNC_weak_llsc 0 +#endif + +/* + * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load, + * store or prefetch) in between an LL & SC can cause the SC instruction to + * erroneously succeed, breaking atomicity. Whilst it's unusual to write code + * containing such sequences, this bug bites harder than we might otherwise + * expect due to reordering & speculation: + * + * 1) A memory access appearing prior to the LL in program order may actually + * be executed after the LL - this is the reordering case. + * + * In order to avoid this we need to place a memory barrier (ie. a SYNC + * instruction) prior to every LL instruction, in between it and any earlier + * memory access instructions. + * + * This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later. + * + * 2) If a conditional branch exists between an LL & SC with a target outside + * of the LL-SC loop, for example an exit upon value mismatch in cmpxchg() + * or similar, then misprediction of the branch may allow speculative + * execution of memory accesses from outside of the LL-SC loop. + * + * In order to avoid this we need a memory barrier (ie. a SYNC instruction) + * at each affected branch target. + * + * This case affects all current Loongson 3 CPUs. + * + * The above described cases cause an error in the cache coherence protocol; + * such that the Invalidate of a competing LL-SC goes 'missing' and SC + * erroneously observes its core still has Exclusive state and lets the SC + * proceed. + * + * Therefore the error only occurs on SMP systems. + */ +#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS +# define __SYNC_loongson3_war (1 << 31) +#else +# define __SYNC_loongson3_war 0 +#endif + +/* + * Some Cavium Octeon CPUs suffer from a bug that causes a single wmb ordering + * barrier to be ineffective, requiring the use of 2 in sequence to provide an + * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use + * optimized memory barrier primitives."). Here we specify that the affected + * sync instructions should be emitted twice. + */ +#ifdef CONFIG_CPU_CAVIUM_OCTEON +# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb)) +#else +# define __SYNC_rpt(type) 1 +#endif + +/* + * The main event. Here we actually emit a sync instruction of a given type, if + * reason is non-zero. + * + * In future we have the option of emitting entries in a fixups-style table + * here that would allow us to opportunistically remove some sync instructions + * when we detect at runtime that we're running on a CPU that doesn't need + * them. + */ +#ifdef CONFIG_CPU_HAS_SYNC +# define ____SYNC(_type, _reason, _else) \ + .if (( _type ) != -1) && ( _reason ); \ + .set push; \ + .set MIPS_ISA_LEVEL_RAW; \ + .rept __SYNC_rpt(_type); \ + sync _type; \ + .endr; \ + .set pop; \ + .else; \ + _else; \ + .endif +#else +# define ____SYNC(_type, _reason, _else) +#endif + +/* + * Preprocessor magic to expand macros used as arguments before we insert them + * into assembly code. + */ +#ifdef __ASSEMBLY__ +# define ___SYNC(type, reason, else) \ + ____SYNC(type, reason, else) +#else +# define ___SYNC(type, reason, else) \ + __stringify(____SYNC(type, reason, else)) +#endif + +#define __SYNC(type, reason) \ + ___SYNC(__SYNC_##type, __SYNC_##reason, ) +#define __SYNC_ELSE(type, reason, else) \ + ___SYNC(__SYNC_##type, __SYNC_##reason, else) + +#endif /* __MIPS_ASM_SYNC_H__ */ diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h new file mode 100644 index 000000000000..c628747d4ecd --- /dev/null +++ b/arch/mips/include/asm/unroll.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_UNROLL_H__ +#define __ASM_UNROLL_H__ + +/* + * Explicitly unroll a loop, for use in cases where doing so is performance + * critical. + * + * Ideally we'd rely upon the compiler to provide this but there's no commonly + * available means to do so. For example GCC's "#pragma GCC unroll" + * functionality would be ideal but is only available from GCC 8 onwards. Using + * -funroll-loops is an option but GCC tends to make poor choices when + * compiling our string functions. -funroll-all-loops leads to massive code + * bloat, even if only applied to the string functions. + */ +#define unroll(times, fn, ...) do { \ + extern void bad_unroll(void) \ + __compiletime_error("Unsupported unroll"); \ + \ + /* \ + * We can't unroll if the number of iterations isn't \ + * compile-time constant. Unfortunately GCC versions \ + * up until 4.6 tend to miss obvious constants & cause \ + * this check to fail, even though they go on to \ + * generate reasonable code for the switch statement, \ + * so we skip the sanity check for those compilers. \ + */ \ + BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 || \ + CONFIG_CLANG_VERSION >= 80000) && \ + !__builtin_constant_p(times)); \ + \ + switch (times) { \ + case 32: fn(__VA_ARGS__); /* fall through */ \ + case 31: fn(__VA_ARGS__); /* fall through */ \ + case 30: fn(__VA_ARGS__); /* fall through */ \ + case 29: fn(__VA_ARGS__); /* fall through */ \ + case 28: fn(__VA_ARGS__); /* fall through */ \ + case 27: fn(__VA_ARGS__); /* fall through */ \ + case 26: fn(__VA_ARGS__); /* fall through */ \ + case 25: fn(__VA_ARGS__); /* fall through */ \ + case 24: fn(__VA_ARGS__); /* fall through */ \ + case 23: fn(__VA_ARGS__); /* fall through */ \ + case 22: fn(__VA_ARGS__); /* fall through */ \ + case 21: fn(__VA_ARGS__); /* fall through */ \ + case 20: fn(__VA_ARGS__); /* fall through */ \ + case 19: fn(__VA_ARGS__); /* fall through */ \ + case 18: fn(__VA_ARGS__); /* fall through */ \ + case 17: fn(__VA_ARGS__); /* fall through */ \ + case 16: fn(__VA_ARGS__); /* fall through */ \ + case 15: fn(__VA_ARGS__); /* fall through */ \ + case 14: fn(__VA_ARGS__); /* fall through */ \ + case 13: fn(__VA_ARGS__); /* fall through */ \ + case 12: fn(__VA_ARGS__); /* fall through */ \ + case 11: fn(__VA_ARGS__); /* fall through */ \ + case 10: fn(__VA_ARGS__); /* fall through */ \ + case 9: fn(__VA_ARGS__); /* fall through */ \ + case 8: fn(__VA_ARGS__); /* fall through */ \ + case 7: fn(__VA_ARGS__); /* fall through */ \ + case 6: fn(__VA_ARGS__); /* fall through */ \ + case 5: fn(__VA_ARGS__); /* fall through */ \ + case 4: fn(__VA_ARGS__); /* fall through */ \ + case 3: fn(__VA_ARGS__); /* fall through */ \ + case 2: fn(__VA_ARGS__); /* fall through */ \ + case 1: fn(__VA_ARGS__); /* fall through */ \ + case 0: break; \ + \ + default: \ + /* \ + * Either the iteration count is unreasonable \ + * or we need to add more cases above. \ + */ \ + bad_unroll(); \ + break; \ + } \ +} while (0) + +#endif /* __ASM_UNROLL_H__ */ diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h index 195314732233..00d41b94ba31 100644 --- a/arch/mips/include/asm/vdso/vsyscall.h +++ b/arch/mips/include/asm/vdso/vsyscall.h @@ -28,13 +28,6 @@ int __mips_get_clock_mode(struct timekeeper *tk) } #define __arch_get_clock_mode __mips_get_clock_mode -static __always_inline -int __mips_use_vsyscall(struct vdso_data *vdata) -{ - return (vdata[CS_HRES_COARSE].clock_mode != VDSO_CLOCK_NONE); -} -#define __arch_use_vsyscall __mips_use_vsyscall - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 89b07ea8d249..d6e97df51cfb 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -80,7 +80,7 @@ obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o -obj-$(CONFIG_64BIT) += cpu-bugs64.o +obj-$(CONFIG_CPU_R4X00_BUGS64) += r4k-bugs64.o obj-$(CONFIG_I8253) += i8253.o diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index f521cbf934e7..c54332697673 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -608,7 +608,7 @@ static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags) if (!(flags & FTLB_EN)) return 1; return 0; - case CPU_LOONGSON3: + case CPU_LOONGSON64: /* Flush ITLB, DTLB, VTLB and FTLB */ write_c0_diag(LOONGSON_DIAG_ITLB | LOONGSON_DIAG_DTLB | LOONGSON_DIAG_VTLB | LOONGSON_DIAG_FTLB); @@ -1526,24 +1526,24 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) MIPS_CPU_LLSC | MIPS_CPU_BP_GHIST; c->tlbsize = 64; break; - case PRID_IMP_LOONGSON_64: /* Loongson-2/3 */ + case PRID_IMP_LOONGSON_64C: /* Loongson-2/3 */ switch (c->processor_id & PRID_REV_MASK) { case PRID_REV_LOONGSON2E: - c->cputype = CPU_LOONGSON2; + c->cputype = CPU_LOONGSON2EF; __cpu_name[cpu] = "ICT Loongson-2"; set_elf_platform(cpu, "loongson2e"); set_isa(c, MIPS_CPU_ISA_III); c->fpu_msk31 |= FPU_CSR_CONDX; break; case PRID_REV_LOONGSON2F: - c->cputype = CPU_LOONGSON2; + c->cputype = CPU_LOONGSON2EF; __cpu_name[cpu] = "ICT Loongson-2"; set_elf_platform(cpu, "loongson2f"); set_isa(c, MIPS_CPU_ISA_III); c->fpu_msk31 |= FPU_CSR_CONDX; break; case PRID_REV_LOONGSON3A_R1: - c->cputype = CPU_LOONGSON3; + c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R1); @@ -1552,7 +1552,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) break; case PRID_REV_LOONGSON3B_R1: case PRID_REV_LOONGSON3B_R2: - c->cputype = CPU_LOONGSON3; + c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3b"); set_isa(c, MIPS_CPU_ISA_M64R1); @@ -1565,12 +1565,13 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) MIPS_CPU_FPU | MIPS_CPU_LLSC | MIPS_CPU_32FPR; c->tlbsize = 64; + set_cpu_asid_mask(c, MIPS_ENTRYHI_ASID); c->writecombine = _CACHE_UNCACHED_ACCELERATED; break; case PRID_IMP_LOONGSON_32: /* Loongson-1 */ decode_configs(c); - c->cputype = CPU_LOONGSON1; + c->cputype = CPU_LOONGSON32; switch (c->processor_id & PRID_REV_MASK) { case PRID_REV_LOONGSON1B: @@ -1903,18 +1904,18 @@ platform: static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { switch (c->processor_id & PRID_IMP_MASK) { - case PRID_IMP_LOONGSON_64: /* Loongson-2/3 */ + case PRID_IMP_LOONGSON_64C: /* Loongson-2/3 */ switch (c->processor_id & PRID_REV_MASK) { case PRID_REV_LOONGSON3A_R2_0: case PRID_REV_LOONGSON3A_R2_1: - c->cputype = CPU_LOONGSON3; + c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); break; case PRID_REV_LOONGSON3A_R3_0: case PRID_REV_LOONGSON3A_R3_1: - c->cputype = CPU_LOONGSON3; + c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); @@ -1927,6 +1928,17 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM | MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2); break; + case PRID_IMP_LOONGSON_64G: + c->cputype = CPU_LOONGSON64; + __cpu_name[cpu] = "ICT Loongson-3"; + set_elf_platform(cpu, "loongson3a"); + set_isa(c, MIPS_CPU_ISA_M64R2); + decode_configs(c); + c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE; + c->writecombine = _CACHE_UNCACHED_ACCELERATED; + c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM | + MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2); + break; default: panic("Unknown Loongson Processor ID!"); break; @@ -1965,13 +1977,30 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu) break; } + switch (c->processor_id & PRID_COMP_MASK) { /* - * The config0 register in the Xburst CPUs with a processor ID of + * The config0 register in the XBurst CPUs with a processor ID of + * PRID_COMP_INGENIC_D1 has an abandoned huge page tlb mode, this + * mode is not compatible with the MIPS standard, it will cause + * tlbmiss and into an infinite loop (line 21 in the tlb-funcs.S) + * when starting the init process. After chip reset, the default + * is HPTLB mode, Write 0xa9000000 to cp0 register 5 sel 4 to + * switch back to VTLB mode to prevent getting stuck. + */ + case PRID_COMP_INGENIC_D1: + write_c0_page_ctrl(XBURST_PAGECTRL_HPTLB_DIS); + break; + /* + * The config0 register in the XBurst CPUs with a processor ID of * PRID_COMP_INGENIC_D0 report themselves as MIPS32r2 compatible, * but they don't actually support this ISA. */ - if ((c->processor_id & PRID_COMP_MASK) == PRID_COMP_INGENIC_D0) + case PRID_COMP_INGENIC_D0: c->isa_level &= ~MIPS_CPU_ISA_M32R2; + break; + default: + break; + } } static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu) diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index efde27c99414..0a43c9125267 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -18,6 +18,7 @@ #include <asm/fpregdef.h> #include <asm/mipsregs.h> #include <asm/stackframe.h> +#include <asm/sync.h> #include <asm/war.h> #include <asm/thread_info.h> @@ -353,8 +354,9 @@ NESTED(ejtag_debug_handler, PT_SIZE, sp) #ifdef CONFIG_SMP 1: PTR_LA k0, ejtag_debug_buffer_spinlock - ll k0, 0(k0) - bnez k0, 1b + __SYNC(full, loongson3_war) +2: ll k0, 0(k0) + bnez k0, 2b PTR_LA k0, ejtag_debug_buffer_spinlock sc k0, 0(k0) beqz k0, 1b @@ -657,7 +659,7 @@ isrdhwr: .set pop END(handle_ri_rdhwr) -#ifdef CONFIG_64BIT +#ifdef CONFIG_CPU_R4X00_BUGS64 /* A temporary overflow handler used by check_daddi(). */ __INIT diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index eb2afc0b8db1..37f8e78e2869 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -173,13 +173,14 @@ void __init check_wait(void) case CPU_CAVIUM_OCTEON2: case CPU_CAVIUM_OCTEON3: case CPU_XBURST: - case CPU_LOONGSON1: + case CPU_LOONGSON32: case CPU_XLR: case CPU_XLP: cpu_wait = r4k_wait; break; - case CPU_LOONGSON3: - if ((c->processor_id & PRID_REV_MASK) >= PRID_REV_LOONGSON3A_R2_0) + case CPU_LOONGSON64: + if ((c->processor_id & (PRID_IMP_MASK | PRID_REV_MASK)) >= + (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0)) cpu_wait = r4k_wait; break; diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index a3e2da8391ea..128fc9999c56 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1623,7 +1623,7 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) raw_event.cntr_mask = raw_id > 127 ? CNTR_ODD : CNTR_EVEN; break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: raw_event.cntr_mask = raw_id > 127 ? CNTR_ODD : CNTR_EVEN; break; } @@ -1764,12 +1764,12 @@ init_hw_perf_events(void) mipspmu.general_event_map = &mipsxxcore_event_map; mipspmu.cache_event_map = &mipsxxcore_cache_map; break; - case CPU_LOONGSON1: + case CPU_LOONGSON32: mipspmu.name = "mips/loongson1"; mipspmu.general_event_map = &mipsxxcore_event_map; mipspmu.cache_event_map = &mipsxxcore_cache_map; break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: mipspmu.name = "mips/loongson3"; mipspmu.general_event_map = &loongson3_event_map; mipspmu.cache_event_map = &loongson3_cache_map; diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index a26f40db15d0..9bf60d7d44d3 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -307,7 +307,7 @@ static int cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl, } /* Barrier ensuring previous cache invalidates are complete */ - uasm_i_sync(pp, STYPE_SYNC); + uasm_i_sync(pp, __SYNC_full); uasm_i_ehb(pp); /* Check whether the pipeline stalled due to the FSB being full */ @@ -397,7 +397,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) if (coupled_coherence) { /* Increment ready_count */ - uasm_i_sync(&p, STYPE_SYNC_MB); + uasm_i_sync(&p, __SYNC_mb); uasm_build_label(&l, p, lbl_incready); uasm_i_ll(&p, t1, 0, r_nc_count); uasm_i_addiu(&p, t2, t1, 1); @@ -406,7 +406,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) uasm_i_addiu(&p, t1, t1, 1); /* Barrier ensuring all CPUs see the updated r_nc_count value */ - uasm_i_sync(&p, STYPE_SYNC_MB); + uasm_i_sync(&p, __SYNC_mb); /* * If this is the last VPE to become ready for non-coherence @@ -473,7 +473,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) Index_Writeback_Inv_D, lbl_flushdcache); /* Barrier ensuring previous cache invalidates are complete */ - uasm_i_sync(&p, STYPE_SYNC); + uasm_i_sync(&p, __SYNC_full); uasm_i_ehb(&p); if (mips_cm_revision() < CM_REV_CM3) { @@ -487,7 +487,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) uasm_i_lw(&p, t0, 0, r_pcohctl); /* Barrier to ensure write to coherence control is complete */ - uasm_i_sync(&p, STYPE_SYNC); + uasm_i_sync(&p, __SYNC_full); uasm_i_ehb(&p); } @@ -534,7 +534,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) } /* Barrier to ensure write to CPC command is complete */ - uasm_i_sync(&p, STYPE_SYNC); + uasm_i_sync(&p, __SYNC_full); uasm_i_ehb(&p); } @@ -572,13 +572,13 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) uasm_i_lw(&p, t0, 0, r_pcohctl); /* Barrier to ensure write to coherence control is complete */ - uasm_i_sync(&p, STYPE_SYNC); + uasm_i_sync(&p, __SYNC_full); uasm_i_ehb(&p); if (coupled_coherence && (state == CPS_PM_NC_WAIT)) { /* Decrement ready_count */ uasm_build_label(&l, p, lbl_decready); - uasm_i_sync(&p, STYPE_SYNC_MB); + uasm_i_sync(&p, __SYNC_mb); uasm_i_ll(&p, t1, 0, r_nc_count); uasm_i_addiu(&p, t2, t1, -1); uasm_i_sc(&p, t2, 0, r_nc_count); @@ -586,7 +586,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) uasm_i_andi(&p, v0, t1, (1 << fls(smp_num_siblings)) - 1); /* Barrier ensuring all CPUs see the updated r_nc_count value */ - uasm_i_sync(&p, STYPE_SYNC_MB); + uasm_i_sync(&p, __SYNC_mb); } if (coupled_coherence && (state == CPS_PM_CLOCK_GATED)) { @@ -608,7 +608,7 @@ static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) uasm_build_label(&l, p, lbl_secondary_cont); /* Barrier ensuring all CPUs see the updated r_nc_count value */ - uasm_i_sync(&p, STYPE_SYNC_MB); + uasm_i_sync(&p, __SYNC_mb); } /* The core is coherent, time to return to C code */ diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/r4k-bugs64.c index 6a7afe7ef4d3..1ff19f1ea5ca 100644 --- a/arch/mips/kernel/cpu-bugs64.c +++ b/arch/mips/kernel/r4k-bugs64.c @@ -242,7 +242,7 @@ static __init void check_daddi(void) panic(bug64hit, !DADDI_WAR ? daddiwar : nowar); } -int daddiu_bug = IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1; +int daddiu_bug = -1; static __init void check_daddiu(void) { @@ -312,14 +312,11 @@ static __init void check_daddiu(void) void __init check_bugs64_early(void) { - if (!IS_ENABLED(CONFIG_CPU_MIPSR6)) { - check_mult_sh(); - check_daddiu(); - } + check_mult_sh(); + check_daddiu(); } void __init check_bugs64(void) { - if (!IS_ENABLED(CONFIG_CPU_MIPSR6)) - check_daddi(); + check_daddi(); } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 5eec13b8d222..c3d4212b5f1d 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -67,7 +67,9 @@ static char __initdata command_line[COMMAND_LINE_SIZE]; char __initdata arcs_cmdline[COMMAND_LINE_SIZE]; #ifdef CONFIG_CMDLINE_BOOL -static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; +static const char builtin_cmdline[] __initconst = CONFIG_CMDLINE; +#else +static const char builtin_cmdline[] __initconst = ""; #endif /* @@ -285,7 +287,7 @@ static unsigned long __init init_initrd(void) * Initialize the bootmem allocator. It also setup initrd related data * if needed. */ -#if defined(CONFIG_SGI_IP27) || (defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_NUMA)) +#if defined(CONFIG_SGI_IP27) || (defined(CONFIG_CPU_LOONGSON64) && defined(CONFIG_NUMA)) static void __init bootmem_init(void) { @@ -538,11 +540,94 @@ static void __init check_kernel_sections_mem(void) } } -#define USE_PROM_CMDLINE IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_BOOTLOADER) -#define USE_DTB_CMDLINE IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB) -#define EXTEND_WITH_PROM IS_ENABLED(CONFIG_MIPS_CMDLINE_DTB_EXTEND) -#define BUILTIN_EXTEND_WITH_PROM \ - IS_ENABLED(CONFIG_MIPS_CMDLINE_BUILTIN_EXTEND) +static void __init bootcmdline_append(const char *s, size_t max) +{ + if (!s[0] || !max) + return; + + if (boot_command_line[0]) + strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); + + strlcat(boot_command_line, s, max); +} + +#ifdef CONFIG_OF_EARLY_FLATTREE + +static int __init bootcmdline_scan_chosen(unsigned long node, const char *uname, + int depth, void *data) +{ + bool *dt_bootargs = data; + const char *p; + int l; + + if (depth != 1 || !data || + (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0)) + return 0; + + p = of_get_flat_dt_prop(node, "bootargs", &l); + if (p != NULL && l > 0) { + bootcmdline_append(p, min(l, COMMAND_LINE_SIZE)); + *dt_bootargs = true; + } + + return 1; +} + +#endif /* CONFIG_OF_EARLY_FLATTREE */ + +static void __init bootcmdline_init(char **cmdline_p) +{ + bool dt_bootargs = false; + + /* + * If CMDLINE_OVERRIDE is enabled then initializing the command line is + * trivial - we simply use the built-in command line unconditionally & + * unmodified. + */ + if (IS_ENABLED(CONFIG_CMDLINE_OVERRIDE)) { + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + return; + } + + /* + * If the user specified a built-in command line & + * MIPS_CMDLINE_BUILTIN_EXTEND, then the built-in command line is + * prepended to arguments from the bootloader or DT so we'll copy them + * to the start of boot_command_line here. Otherwise, empty + * boot_command_line to undo anything early_init_dt_scan_chosen() did. + */ + if (IS_ENABLED(CONFIG_MIPS_CMDLINE_BUILTIN_EXTEND)) + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + else + boot_command_line[0] = 0; + +#ifdef CONFIG_OF_EARLY_FLATTREE + /* + * If we're configured to take boot arguments from DT, look for those + * now. + */ + if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB)) + of_scan_flat_dt(bootcmdline_scan_chosen, &dt_bootargs); +#endif + + /* + * If we didn't get any arguments from DT (regardless of whether that's + * because we weren't configured to look for them, or because we looked + * & found none) then we'll take arguments from the bootloader. + * plat_mem_setup() should have filled arcs_cmdline with arguments from + * the bootloader. + */ + if (IS_ENABLED(CONFIG_MIPS_CMDLINE_DTB_EXTEND) || !dt_bootargs) + bootcmdline_append(arcs_cmdline, COMMAND_LINE_SIZE); + + /* + * If the user specified a built-in command line & we didn't already + * prepend it, we append it to boot_command_line here. + */ + if (IS_ENABLED(CONFIG_CMDLINE_BOOL) && + !IS_ENABLED(CONFIG_MIPS_CMDLINE_BUILTIN_EXTEND)) + bootcmdline_append(builtin_cmdline, COMMAND_LINE_SIZE); +} /* * arch_mem_init - initialize memory management subsystem @@ -570,48 +655,12 @@ static void __init arch_mem_init(char **cmdline_p) { extern void plat_mem_setup(void); - /* - * Initialize boot_command_line to an innocuous but non-empty string in - * order to prevent early_init_dt_scan_chosen() from copying - * CONFIG_CMDLINE into it without our knowledge. We handle - * CONFIG_CMDLINE ourselves below & don't want to duplicate its - * content because repeating arguments can be problematic. - */ - strlcpy(boot_command_line, " ", COMMAND_LINE_SIZE); - /* call board setup routine */ plat_mem_setup(); memblock_set_bottom_up(true); -#if defined(CONFIG_CMDLINE_BOOL) && defined(CONFIG_CMDLINE_OVERRIDE) - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if ((USE_PROM_CMDLINE && arcs_cmdline[0]) || - (USE_DTB_CMDLINE && !boot_command_line[0])) - strlcpy(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE); - - if (EXTEND_WITH_PROM && arcs_cmdline[0]) { - if (boot_command_line[0]) - strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE); - } - -#if defined(CONFIG_CMDLINE_BOOL) - if (builtin_cmdline[0]) { - if (boot_command_line[0]) - strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } - - if (BUILTIN_EXTEND_WITH_PROM && arcs_cmdline[0]) { - if (boot_command_line[0]) - strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE); - } -#endif -#endif + bootcmdline_init(cmdline_p); strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; parse_early_param(); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 712c15de6ab9..9058e9dcf080 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -31,7 +31,6 @@ #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/bootinfo.h> -#include <asm/pmon.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/mipsregs.h> diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 3f16f3823031..c333e5788664 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -37,6 +37,7 @@ #include <asm/signal.h> #include <asm/sim.h> #include <asm/shmparam.h> +#include <asm/sync.h> #include <asm/sysmips.h> #include <asm/switch_to.h> @@ -133,12 +134,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) [efault] "i" (-EFAULT) : "memory"); } else if (cpu_has_llsc) { - loongson_llsc_mb(); __asm__ __volatile__ ( " .set push \n" " .set "MIPS_ISA_ARCH_LEVEL" \n" " li %[err], 0 \n" "1: \n" + " " __SYNC(full, loongson3_war) " \n" user_ll("%[old]", "(%[addr])") " move %[tmp], %[new] \n" "2: \n" diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 342e41de9d64..83f2a437d9e2 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1761,7 +1761,7 @@ static inline void parity_protection_init(void) case CPU_5KC: case CPU_5KE: - case CPU_LOONGSON1: + case CPU_LOONGSON32: write_c0_ecc(0x80000000); back_to_back_c0_hazard(); /* Set the PE bit (bit 31) in the c0_errctl register. */ @@ -2394,7 +2394,7 @@ void __init trap_init(void) else { if (cpu_has_vtag_icache) set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp); - else if (current_cpu_type() == CPU_LOONGSON3) + else if (current_cpu_type() == CPU_LOONGSON64) set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp); else set_except_vector(EXCCODE_RI, handle_ri_rdhwr); diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 97e538a8c1be..7dad7a293eae 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -136,6 +136,7 @@ pgd_t *kvm_pgd_alloc(void) static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache, unsigned long addr) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -145,7 +146,8 @@ static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache, BUG(); return NULL; } - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + pud = pud_offset(p4d, addr); if (pud_none(*pud)) { pmd_t *new_pmd; @@ -204,8 +206,8 @@ static bool kvm_mips_flush_gpa_pmd(pmd_t *pmd, unsigned long start_gpa, { pte_t *pte; unsigned long end = ~0ul; - int i_min = __pmd_offset(start_gpa); - int i_max = __pmd_offset(end_gpa); + int i_min = pmd_index(start_gpa); + int i_max = pmd_index(end_gpa); bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PMD - 1); int i; @@ -232,8 +234,8 @@ static bool kvm_mips_flush_gpa_pud(pud_t *pud, unsigned long start_gpa, { pmd_t *pmd; unsigned long end = ~0ul; - int i_min = __pud_offset(start_gpa); - int i_max = __pud_offset(end_gpa); + int i_min = pud_index(start_gpa); + int i_max = pud_index(end_gpa); bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PUD - 1); int i; @@ -258,6 +260,7 @@ static bool kvm_mips_flush_gpa_pud(pud_t *pud, unsigned long start_gpa, static bool kvm_mips_flush_gpa_pgd(pgd_t *pgd, unsigned long start_gpa, unsigned long end_gpa) { + p4d_t *p4d; pud_t *pud; unsigned long end = ~0ul; int i_min = pgd_index(start_gpa); @@ -269,7 +272,8 @@ static bool kvm_mips_flush_gpa_pgd(pgd_t *pgd, unsigned long start_gpa, if (!pgd_present(pgd[i])) continue; - pud = pud_offset(pgd + i, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d + i, 0); if (i == i_max) end = end_gpa; @@ -334,8 +338,8 @@ static int kvm_mips_##name##_pmd(pmd_t *pmd, unsigned long start, \ int ret = 0; \ pte_t *pte; \ unsigned long cur_end = ~0ul; \ - int i_min = __pmd_offset(start); \ - int i_max = __pmd_offset(end); \ + int i_min = pmd_index(start); \ + int i_max = pmd_index(end); \ int i; \ \ for (i = i_min; i <= i_max; ++i, start = 0) { \ @@ -357,8 +361,8 @@ static int kvm_mips_##name##_pud(pud_t *pud, unsigned long start, \ int ret = 0; \ pmd_t *pmd; \ unsigned long cur_end = ~0ul; \ - int i_min = __pud_offset(start); \ - int i_max = __pud_offset(end); \ + int i_min = pud_index(start); \ + int i_max = pud_index(end); \ int i; \ \ for (i = i_min; i <= i_max; ++i, start = 0) { \ @@ -378,6 +382,7 @@ static int kvm_mips_##name##_pgd(pgd_t *pgd, unsigned long start, \ unsigned long end) \ { \ int ret = 0; \ + p4d_t *p4d; \ pud_t *pud; \ unsigned long cur_end = ~0ul; \ int i_min = pgd_index(start); \ @@ -388,7 +393,8 @@ static int kvm_mips_##name##_pgd(pgd_t *pgd, unsigned long start, \ if (!pgd_present(pgd[i])) \ continue; \ \ - pud = pud_offset(pgd + i, 0); \ + p4d = p4d_offset(pgd, 0); \ + pud = pud_offset(p4d + i, 0); \ if (i == i_max) \ cur_end = end; \ \ @@ -862,8 +868,8 @@ static bool kvm_mips_flush_gva_pmd(pmd_t *pmd, unsigned long start_gva, { pte_t *pte; unsigned long end = ~0ul; - int i_min = __pmd_offset(start_gva); - int i_max = __pmd_offset(end_gva); + int i_min = pmd_index(start_gva); + int i_max = pmd_index(end_gva); bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PMD - 1); int i; @@ -890,8 +896,8 @@ static bool kvm_mips_flush_gva_pud(pud_t *pud, unsigned long start_gva, { pmd_t *pmd; unsigned long end = ~0ul; - int i_min = __pud_offset(start_gva); - int i_max = __pud_offset(end_gva); + int i_min = pud_index(start_gva); + int i_max = pud_index(end_gva); bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PUD - 1); int i; @@ -916,6 +922,7 @@ static bool kvm_mips_flush_gva_pud(pud_t *pud, unsigned long start_gva, static bool kvm_mips_flush_gva_pgd(pgd_t *pgd, unsigned long start_gva, unsigned long end_gva) { + p4d_t *p4d; pud_t *pud; unsigned long end = ~0ul; int i_min = pgd_index(start_gva); @@ -927,7 +934,8 @@ static bool kvm_mips_flush_gva_pgd(pgd_t *pgd, unsigned long start_gva, if (!pgd_present(pgd[i])) continue; - pud = pud_offset(pgd + i, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d + i, 0); if (i == i_max) end = end_gva; diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index 73daa6ad33af..5a11e83dffe6 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -564,6 +564,7 @@ static void kvm_mips_emul_free_gva_pt(pgd_t *pgd) /* Don't free host kernel page tables copied from init_mm.pgd */ const unsigned long end = 0x80000000; unsigned long pgd_va, pud_va, pmd_va; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -576,7 +577,8 @@ static void kvm_mips_emul_free_gva_pt(pgd_t *pgd) pgd_va = (unsigned long)i << PGDIR_SHIFT; if (pgd_va >= end) break; - pud = pud_offset(pgd + i, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d + i, 0); for (j = 0; j < PTRS_PER_PUD; j++) { if (pud_none(pud[j])) continue; diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c index 3b2a1e78a543..116d0bd8b2ae 100644 --- a/arch/mips/lib/bitops.c +++ b/arch/mips/lib/bitops.c @@ -7,6 +7,7 @@ * Copyright (c) 1999, 2000 Silicon Graphics, Inc. */ #include <linux/bitops.h> +#include <linux/bits.h> #include <linux/irqflags.h> #include <linux/export.h> @@ -19,12 +20,11 @@ */ void __mips_set_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *a = (unsigned long *)addr; - unsigned bit = nr & SZLONG_MASK; + volatile unsigned long *a = &addr[BIT_WORD(nr)]; + unsigned int bit = nr % BITS_PER_LONG; unsigned long mask; unsigned long flags; - a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); *a |= mask; @@ -41,12 +41,11 @@ EXPORT_SYMBOL(__mips_set_bit); */ void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *a = (unsigned long *)addr; - unsigned bit = nr & SZLONG_MASK; + volatile unsigned long *a = &addr[BIT_WORD(nr)]; + unsigned int bit = nr % BITS_PER_LONG; unsigned long mask; unsigned long flags; - a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); *a &= ~mask; @@ -63,12 +62,11 @@ EXPORT_SYMBOL(__mips_clear_bit); */ void __mips_change_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *a = (unsigned long *)addr; - unsigned bit = nr & SZLONG_MASK; + volatile unsigned long *a = &addr[BIT_WORD(nr)]; + unsigned int bit = nr % BITS_PER_LONG; unsigned long mask; unsigned long flags; - a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); *a ^= mask; @@ -78,32 +76,6 @@ EXPORT_SYMBOL(__mips_change_bit); /** - * __mips_test_and_set_bit - Set a bit and return its old value. This is - * called by test_and_set_bit() if it cannot find a faster solution. - * @nr: Bit to set - * @addr: Address to count from - */ -int __mips_test_and_set_bit(unsigned long nr, - volatile unsigned long *addr) -{ - unsigned long *a = (unsigned long *)addr; - unsigned bit = nr & SZLONG_MASK; - unsigned long mask; - unsigned long flags; - int res; - - a += nr >> SZLONG_LOG; - mask = 1UL << bit; - raw_local_irq_save(flags); - res = (mask & *a) != 0; - *a |= mask; - raw_local_irq_restore(flags); - return res; -} -EXPORT_SYMBOL(__mips_test_and_set_bit); - - -/** * __mips_test_and_set_bit_lock - Set a bit and return its old value. This is * called by test_and_set_bit_lock() if it cannot find a faster solution. * @nr: Bit to set @@ -112,13 +84,12 @@ EXPORT_SYMBOL(__mips_test_and_set_bit); int __mips_test_and_set_bit_lock(unsigned long nr, volatile unsigned long *addr) { - unsigned long *a = (unsigned long *)addr; - unsigned bit = nr & SZLONG_MASK; + volatile unsigned long *a = &addr[BIT_WORD(nr)]; + unsigned int bit = nr % BITS_PER_LONG; unsigned long mask; unsigned long flags; int res; - a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); res = (mask & *a) != 0; @@ -137,13 +108,12 @@ EXPORT_SYMBOL(__mips_test_and_set_bit_lock); */ int __mips_test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *a = (unsigned long *)addr; - unsigned bit = nr & SZLONG_MASK; + volatile unsigned long *a = &addr[BIT_WORD(nr)]; + unsigned int bit = nr % BITS_PER_LONG; unsigned long mask; unsigned long flags; int res; - a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); res = (mask & *a) != 0; @@ -162,13 +132,12 @@ EXPORT_SYMBOL(__mips_test_and_clear_bit); */ int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *a = (unsigned long *)addr; - unsigned bit = nr & SZLONG_MASK; + volatile unsigned long *a = &addr[BIT_WORD(nr)]; + unsigned int bit = nr % BITS_PER_LONG; unsigned long mask; unsigned long flags; int res; - a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); res = (mask & *a) != 0; diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S index 2ff84f4b1717..fda7b57b826e 100644 --- a/arch/mips/lib/csum_partial.S +++ b/arch/mips/lib/csum_partial.S @@ -279,7 +279,7 @@ EXPORT_SYMBOL(csum_partial) #endif /* odd buffer alignment? */ -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3) +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON64) .set push .set arch=mips32r2 wsbh v1, sum @@ -732,7 +732,7 @@ EXPORT_SYMBOL(csum_partial) addu sum, v1 #endif -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3) +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON64) .set push .set arch=mips32r2 wsbh v1, sum diff --git a/arch/mips/loongson2ef/Kconfig b/arch/mips/loongson2ef/Kconfig new file mode 100644 index 000000000000..595dd48e1e4d --- /dev/null +++ b/arch/mips/loongson2ef/Kconfig @@ -0,0 +1,95 @@ +# SPDX-License-Identifier: GPL-2.0 +if MACH_LOONGSON2EF + +choice + prompt "Machine Type" + +config LEMOTE_FULOONG2E + bool "Lemote Fuloong(2e) mini-PC" + select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO + select CEVT_R4K + select CSRC_R4K + select SYS_HAS_CPU_LOONGSON2E + select DMA_NONCOHERENT + select BOOT_ELF32 + select BOARD_SCACHE + select FORCE_PCI + select I8259 + select ISA + select IRQ_MIPS_CPU + select SYS_SUPPORTS_64BIT_KERNEL + select SYS_SUPPORTS_LITTLE_ENDIAN + select SYS_SUPPORTS_HIGHMEM + select SYS_HAS_EARLY_PRINTK + select USE_GENERIC_EARLY_PRINTK_8250 + select GENERIC_ISA_DMA_SUPPORT_BROKEN + select CPU_HAS_WB + select LOONGSON_MC146818 + help + Lemote Fuloong(2e) mini-PC board based on the Chinese Loongson-2E CPU and + an FPGA northbridge + + Lemote Fuloong(2e) mini PC have a VIA686B south bridge. + +config LEMOTE_MACH2F + bool "Lemote Loongson 2F family machines" + select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO + select BOARD_SCACHE + select BOOT_ELF32 + select CEVT_R4K if ! MIPS_EXTERNAL_TIMER + select CPU_HAS_WB + select CS5536 + select CSRC_R4K if ! MIPS_EXTERNAL_TIMER + select DMA_NONCOHERENT + select GENERIC_ISA_DMA_SUPPORT_BROKEN + select HAVE_CLK + select FORCE_PCI + select I8259 + select IRQ_MIPS_CPU + select ISA + select SYS_HAS_CPU_LOONGSON2F + select SYS_HAS_EARLY_PRINTK + select USE_GENERIC_EARLY_PRINTK_8250 + select SYS_SUPPORTS_64BIT_KERNEL + select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_LITTLE_ENDIAN + select LOONGSON_MC146818 + help + Lemote Loongson 2F family machines utilize the 2F revision of + Loongson processor and the AMD CS5536 south bridge. + + These family machines include fuloong2f mini PC, yeeloong2f notebook, + LingLoong allinone PC and so forth. + +endchoice + +config CS5536 + bool + +config CS5536_MFGPT + bool "CS5536 MFGPT Timer" + depends on CS5536 && !HIGH_RES_TIMERS + select MIPS_EXTERNAL_TIMER + help + This option enables the mfgpt0 timer of AMD CS5536. With this timer + switched on you can not use high resolution timers. + + If you want to enable the Loongson2 CPUFreq Driver, Please enable + this option at first, otherwise, You will get wrong system time. + + If unsure, say Yes. + +config LOONGSON_UART_BASE + bool + default y + depends on EARLY_PRINTK || SERIAL_8250 + +config LOONGSON_MC146818 + bool + default n + +endif # MACH_LOONGSON2EF diff --git a/arch/mips/loongson2ef/Makefile b/arch/mips/loongson2ef/Makefile new file mode 100644 index 000000000000..d4af1605cc9b --- /dev/null +++ b/arch/mips/loongson2ef/Makefile @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Common code for all Loongson based systems +# + +obj-$(CONFIG_MACH_LOONGSON2EF) += common/ + +# +# Lemote Fuloong mini-PC (Loongson 2E-based) +# + +obj-$(CONFIG_LEMOTE_FULOONG2E) += fuloong-2e/ + +# +# Lemote loongson2f family machines +# + +obj-$(CONFIG_LEMOTE_MACH2F) += lemote-2f/ diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform new file mode 100644 index 000000000000..3aca42963f35 --- /dev/null +++ b/arch/mips/loongson2ef/Platform @@ -0,0 +1,32 @@ +# +# Loongson Processors' Support +# + +# Only gcc >= 4.4 have Loongson specific support +cflags-$(CONFIG_CPU_LOONGSON2EF) += -Wa,--trap +cflags-$(CONFIG_CPU_LOONGSON2E) += \ + $(call cc-option,-march=loongson2e,-march=r4600) +cflags-$(CONFIG_CPU_LOONGSON2F) += \ + $(call cc-option,-march=loongson2f,-march=r4600) +# Enable the workarounds for Loongson2f +ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS + ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-nop,),) + $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-nop) + else + cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-nop + endif + ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-jump,),) + $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-jump) + else + cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-jump + endif +endif + +# +# Loongson Machines' Support +# + +platform-$(CONFIG_MACH_LOONGSON2EF) += loongson2ef/ +cflags-$(CONFIG_MACH_LOONGSON2EF) += -I$(srctree)/arch/mips/include/asm/mach-loongson2ef -mno-branch-likely +load-$(CONFIG_LEMOTE_FULOONG2E) += 0xffffffff80100000 +load-$(CONFIG_LEMOTE_MACH2F) += 0xffffffff80200000 diff --git a/arch/mips/loongson64/common/Makefile b/arch/mips/loongson2ef/common/Makefile index 684624f61f5a..d5ab3e543ea3 100644 --- a/arch/mips/loongson64/common/Makefile +++ b/arch/mips/loongson2ef/common/Makefile @@ -3,14 +3,13 @@ # Makefile for loongson based machines. # -obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \ +obj-y += setup.o init.o env.o time.o reset.o irq.o \ bonito-irq.o mem.o machtype.o platform.o serial.o obj-$(CONFIG_PCI) += pci.o # # Serial port support # -obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o obj-$(CONFIG_LOONGSON_MC146818) += rtc.o diff --git a/arch/mips/loongson64/common/bonito-irq.c b/arch/mips/loongson2ef/common/bonito-irq.c index 82352cc25e4c..82352cc25e4c 100644 --- a/arch/mips/loongson64/common/bonito-irq.c +++ b/arch/mips/loongson2ef/common/bonito-irq.c diff --git a/arch/mips/loongson64/common/cs5536/Makefile b/arch/mips/loongson2ef/common/cs5536/Makefile index b32b29661245..b32b29661245 100644 --- a/arch/mips/loongson64/common/cs5536/Makefile +++ b/arch/mips/loongson2ef/common/cs5536/Makefile diff --git a/arch/mips/loongson64/common/cs5536/cs5536_acc.c b/arch/mips/loongson2ef/common/cs5536/cs5536_acc.c index ff50aae72916..ff50aae72916 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_acc.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_acc.c diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ehci.c b/arch/mips/loongson2ef/common/cs5536/cs5536_ehci.c index bd4c39fe6109..bd4c39fe6109 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_ehci.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_ehci.c diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ide.c b/arch/mips/loongson2ef/common/cs5536/cs5536_ide.c index bb933294b092..bb933294b092 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_ide.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_ide.c diff --git a/arch/mips/loongson64/common/cs5536/cs5536_isa.c b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c index 5ad38f86ee62..5ad38f86ee62 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_isa.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c diff --git a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c index 30af1b7c7529..30af1b7c7529 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_mfgpt.c diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c b/arch/mips/loongson2ef/common/cs5536/cs5536_ohci.c index 71a52b120317..71a52b120317 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_ohci.c diff --git a/arch/mips/loongson64/common/cs5536/cs5536_pci.c b/arch/mips/loongson2ef/common/cs5536/cs5536_pci.c index 202c89b568ba..202c89b568ba 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_pci.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_pci.c diff --git a/arch/mips/loongson2ef/common/env.c b/arch/mips/loongson2ef/common/env.c new file mode 100644 index 000000000000..6f20bdf9b242 --- /dev/null +++ b/arch/mips/loongson2ef/common/env.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Based on Ocelot Linux port, which is + * Copyright 2001 MontaVista Software Inc. + * Author: jsun@mvista.com or jsun@junsun.net + * + * Copyright 2003 ICT CAS + * Author: Michael Guo <guoyi@ict.ac.cn> + * + * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology + * Author: Fuxin Zhang, zhangfx@lemote.com + * + * Copyright (C) 2009 Lemote Inc. + * Author: Wu Zhangjin, wuzhangjin@gmail.com + */ +#include <linux/export.h> +#include <asm/bootinfo.h> +#include <asm/fw/fw.h> +#include <loongson.h> + +u32 cpu_clock_freq; +EXPORT_SYMBOL(cpu_clock_freq); + +void __init prom_init_env(void) +{ + /* pmon passes arguments in 32bit pointers */ + unsigned int processor_id; + + cpu_clock_freq = fw_getenvl("cpuclock"); + memsize = fw_getenvl("memsize"); + highmemsize = fw_getenvl("highmemsize"); + + if (memsize == 0) + memsize = 256; + + pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize); + + if (cpu_clock_freq == 0) { + processor_id = (¤t_cpu_data)->processor_id; + switch (processor_id & PRID_REV_MASK) { + case PRID_REV_LOONGSON2E: + cpu_clock_freq = 533080000; + break; + case PRID_REV_LOONGSON2F: + cpu_clock_freq = 797000000; + break; + default: + cpu_clock_freq = 100000000; + break; + } + } + pr_info("CpuClock = %u\n", cpu_clock_freq); +} diff --git a/arch/mips/loongson64/common/init.c b/arch/mips/loongson2ef/common/init.c index 912fe61c4fc7..45512178be77 100644 --- a/arch/mips/loongson64/common/init.c +++ b/arch/mips/loongson2ef/common/init.c @@ -9,6 +9,7 @@ #include <asm/traps.h> #include <asm/smp-ops.h> #include <asm/cacheflush.h> +#include <asm/fw/fw.h> #include <loongson.h> @@ -32,22 +33,17 @@ void __init prom_init(void) ioremap(LOONGSON_ADDRWINCFG_BASE, LOONGSON_ADDRWINCFG_SIZE); #endif - prom_init_cmdline(); + fw_init_cmdline(); + prom_init_machtype(); prom_init_env(); /* init base address of io space */ set_io_port_base((unsigned long) ioremap(LOONGSON_PCIIO_BASE, LOONGSON_PCIIO_SIZE)); - -#ifdef CONFIG_NUMA - prom_init_numa_memory(); -#else prom_init_memory(); -#endif /*init the uart base address */ prom_init_uart_base(); - register_smp_ops(&loongson3_smp_ops); board_nmi_handler_setup = mips_nmi_setup; } diff --git a/arch/mips/loongson64/common/irq.c b/arch/mips/loongson2ef/common/irq.c index 0ea93c1c0a97..0ea93c1c0a97 100644 --- a/arch/mips/loongson64/common/irq.c +++ b/arch/mips/loongson2ef/common/irq.c diff --git a/arch/mips/loongson64/common/machtype.c b/arch/mips/loongson2ef/common/machtype.c index 4e42d929f1c7..82f6de49f20f 100644 --- a/arch/mips/loongson64/common/machtype.c +++ b/arch/mips/loongson2ef/common/machtype.c @@ -23,7 +23,6 @@ static const char *system_types[] = { [MACH_DEXXON_GDIUM2F10] = "dexxon-gdium-2f", [MACH_LEMOTE_NAS] = "lemote-nas-2f", [MACH_LEMOTE_LL2F] = "lemote-lynloong-2f", - [MACH_LOONGSON_GENERIC] = "generic-loongson-machine", [MACH_LOONGSON_END] = NULL, }; diff --git a/arch/mips/loongson2ef/common/mem.c b/arch/mips/loongson2ef/common/mem.c new file mode 100644 index 000000000000..ae21f1c62baa --- /dev/null +++ b/arch/mips/loongson2ef/common/mem.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + */ +#include <linux/fs.h> +#include <linux/fcntl.h> +#include <linux/memblock.h> +#include <linux/mm.h> + +#include <asm/bootinfo.h> + +#include <loongson.h> +#include <mem.h> +#include <pci.h> + + +u32 memsize, highmemsize; + +void __init prom_init_memory(void) +{ + add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM); + + add_memory_region(memsize << 20, LOONGSON_PCI_MEM_START - (memsize << + 20), BOOT_MEM_RESERVED); + +#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG + { + int bit; + + bit = fls(memsize + highmemsize); + if (bit != ffs(memsize + highmemsize)) + bit += 20; + else + bit = bit + 20 - 1; + + /* set cpu window3 to map CPU to DDR: 2G -> 2G */ + LOONGSON_ADDRWIN_CPUTODDR(ADDRWIN_WIN3, 0x80000000ul, + 0x80000000ul, (1 << bit)); + mmiowb(); + } +#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */ + +#ifdef CONFIG_64BIT + if (highmemsize > 0) + add_memory_region(LOONGSON_HIGHMEM_START, + highmemsize << 20, BOOT_MEM_RAM); + + add_memory_region(LOONGSON_PCI_MEM_END + 1, LOONGSON_HIGHMEM_START - + LOONGSON_PCI_MEM_END - 1, BOOT_MEM_RESERVED); + +#endif /* !CONFIG_64BIT */ +} + +/* override of arch/mips/mm/cache.c: __uncached_access */ +int __uncached_access(struct file *file, unsigned long addr) +{ + if (file->f_flags & O_DSYNC) + return 1; + + return addr >= __pa(high_memory) || + ((addr >= LOONGSON_MMIO_MEM_START) && + (addr < LOONGSON_MMIO_MEM_END)); +} diff --git a/arch/mips/loongson64/common/pci.c b/arch/mips/loongson2ef/common/pci.c index c47bb7bf3aa4..200916925e95 100644 --- a/arch/mips/loongson64/common/pci.c +++ b/arch/mips/loongson2ef/common/pci.c @@ -7,7 +7,6 @@ #include <pci.h> #include <loongson.h> -#include <boot_param.h> static struct resource loongson_pci_mem_resource = { .name = "pci memory space", @@ -81,15 +80,8 @@ static int __init pcibios_init(void) setup_pcimap(); loongson_pci_controller.io_map_base = mips_io_port_base; -#ifdef CONFIG_LEFI_FIRMWARE_INTERFACE - loongson_pci_mem_resource.start = loongson_sysconf.pci_mem_start_addr; - loongson_pci_mem_resource.end = loongson_sysconf.pci_mem_end_addr; -#endif register_pci_controller(&loongson_pci_controller); -#ifdef CONFIG_CPU_LOONGSON3 - sbx00_acpi_init(); -#endif return 0; } diff --git a/arch/mips/loongson64/common/platform.c b/arch/mips/loongson2ef/common/platform.c index 0084820cffaa..0084820cffaa 100644 --- a/arch/mips/loongson64/common/platform.c +++ b/arch/mips/loongson2ef/common/platform.c diff --git a/arch/mips/loongson64/common/pm.c b/arch/mips/loongson2ef/common/pm.c index b8aed878d912..11f4cfd581fb 100644 --- a/arch/mips/loongson64/common/pm.c +++ b/arch/mips/loongson2ef/common/pm.c @@ -75,7 +75,7 @@ int __weak wakeup_loongson(void) static void wait_for_wakeup_events(void) { while (!wakeup_loongson()) - LOONGSON_CHIPCFG(0) &= ~0x7; + writel(readl(LOONGSON_CHIPCFG) & ~0x7, LOONGSON_CHIPCFG); } /* @@ -98,15 +98,16 @@ static void loongson_suspend_enter(void) stop_perf_counters(); - cached_cpu_freq = LOONGSON_CHIPCFG(0); + cached_cpu_freq = readl(LOONGSON_CHIPCFG); /* Put CPU into wait mode */ - LOONGSON_CHIPCFG(0) &= ~0x7; + writel(readl(LOONGSON_CHIPCFG) & ~0x7, LOONGSON_CHIPCFG); /* wait for the given events to wakeup cpu from wait mode */ wait_for_wakeup_events(); - LOONGSON_CHIPCFG(0) = cached_cpu_freq; + writel(cached_cpu_freq, LOONGSON_CHIPCFG); + mmiowb(); } diff --git a/arch/mips/loongson64/common/reset.c b/arch/mips/loongson2ef/common/reset.c index ce39e918e4d5..e7c87161ce00 100644 --- a/arch/mips/loongson64/common/reset.c +++ b/arch/mips/loongson2ef/common/reset.c @@ -13,7 +13,6 @@ #include <asm/reboot.h> #include <loongson.h> -#include <boot_param.h> static inline void loongson_reboot(void) { @@ -35,26 +34,15 @@ static inline void loongson_reboot(void) static void loongson_restart(char *command) { -#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE /* do preparation for reboot */ mach_prepare_reboot(); /* reboot via jumping to boot base address */ loongson_reboot(); -#else - void (*fw_restart)(void) = (void *)loongson_sysconf.restart_addr; - - fw_restart(); - while (1) { - if (cpu_wait) - cpu_wait(); - } -#endif } static void loongson_poweroff(void) { -#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE mach_prepare_shutdown(); /* @@ -62,15 +50,6 @@ static void loongson_poweroff(void) * a generic delay loop, machine_hang(), so simply return. */ return; -#else - void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr; - - fw_poweroff(); - while (1) { - if (cpu_wait) - cpu_wait(); - } -#endif } static void loongson_halt(void) diff --git a/arch/mips/loongson64/common/rtc.c b/arch/mips/loongson2ef/common/rtc.c index 8d7628c0f513..8d7628c0f513 100644 --- a/arch/mips/loongson64/common/rtc.c +++ b/arch/mips/loongson2ef/common/rtc.c diff --git a/arch/mips/loongson2ef/common/serial.c b/arch/mips/loongson2ef/common/serial.c new file mode 100644 index 000000000000..ac4f6e3ebc3e --- /dev/null +++ b/arch/mips/loongson2ef/common/serial.c @@ -0,0 +1,86 @@ +/* + * 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. + * + * Copyright (C) 2007 Ralf Baechle (ralf@linux-mips.org) + * + * Copyright (C) 2009 Lemote, Inc. + * Author: Yan hua (yanhua@lemote.com) + * Author: Wu Zhangjin (wuzhangjin@gmail.com) + */ + +#include <linux/io.h> +#include <linux/module.h> +#include <linux/serial_8250.h> + +#include <asm/bootinfo.h> + +#include <loongson.h> +#include <machine.h> + +#define PORT(int, clk) \ +{ \ + .irq = int, \ + .uartclk = clk, \ + .iotype = UPIO_PORT, \ + .flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST, \ + .regshift = 0, \ +} + +#define PORT_M(int, clk) \ +{ \ + .irq = MIPS_CPU_IRQ_BASE + (int), \ + .uartclk = clk, \ + .iotype = UPIO_MEM, \ + .membase = (void __iomem *)NULL, \ + .flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST, \ + .regshift = 0, \ +} + +static struct plat_serial8250_port uart8250_data[MACH_LOONGSON_END + 1] = { + [MACH_LOONGSON_UNKNOWN] = {}, + [MACH_LEMOTE_FL2E] = PORT(4, 1843200), + [MACH_LEMOTE_FL2F] = PORT(3, 1843200), + [MACH_LEMOTE_ML2F7] = PORT_M(3, 3686400), + [MACH_LEMOTE_YL2F89] = PORT_M(3, 3686400), + [MACH_DEXXON_GDIUM2F10] = PORT_M(3, 3686400), + [MACH_LEMOTE_NAS] = PORT_M(3, 3686400), + [MACH_LEMOTE_LL2F] = PORT(3, 1843200), + [MACH_LOONGSON_END] = {}, +}; + +static struct platform_device uart8250_device = { + .name = "serial8250", + .id = PLAT8250_DEV_PLATFORM, +}; + +static int __init serial_init(void) +{ + unsigned char iotype; + + iotype = uart8250_data[mips_machtype].iotype; + + if (UPIO_MEM == iotype) { + uart8250_data[mips_machtype].mapbase = + loongson_uart_base; + uart8250_data[mips_machtype].membase = + (void __iomem *)_loongson_uart_base; + } + else if (UPIO_PORT == iotype) + uart8250_data[mips_machtype].iobase = + loongson_uart_base - LOONGSON_PCIIO_BASE; + + memset(&uart8250_data[mips_machtype + 1], 0, + sizeof(struct plat_serial8250_port)); + uart8250_device.dev.platform_data = &uart8250_data[mips_machtype]; + + return platform_device_register(&uart8250_device); +} +module_init(serial_init); + +static void __exit serial_exit(void) +{ + platform_device_unregister(&uart8250_device); +} +module_exit(serial_exit); diff --git a/arch/mips/loongson64/common/setup.c b/arch/mips/loongson2ef/common/setup.c index bc2da4c140c4..4fd27f4f90ed 100644 --- a/arch/mips/loongson64/common/setup.c +++ b/arch/mips/loongson2ef/common/setup.c @@ -11,11 +11,6 @@ #include <loongson.h> -#ifdef CONFIG_VT -#include <linux/console.h> -#include <linux/screen_info.h> -#endif - static void wbflush_loongson(void) { asm(".set\tpush\n\t" @@ -32,20 +27,4 @@ EXPORT_SYMBOL(__wbflush); void __init plat_mem_setup(void) { -#ifdef CONFIG_VT -#if defined(CONFIG_VGA_CONSOLE) - conswitchp = &vga_con; - - screen_info = (struct screen_info) { - .orig_x = 0, - .orig_y = 25, - .orig_video_cols = 80, - .orig_video_lines = 25, - .orig_video_isVGA = VIDEO_TYPE_VGAC, - .orig_video_points = 16, - }; -#elif defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; -#endif -#endif } diff --git a/arch/mips/loongson64/common/time.c b/arch/mips/loongson2ef/common/time.c index e78760ce475b..585741af42a9 100644 --- a/arch/mips/loongson64/common/time.c +++ b/arch/mips/loongson2ef/common/time.c @@ -18,11 +18,7 @@ void __init plat_time_init(void) /* setup mips r4k timer */ mips_hpt_frequency = cpu_clock_freq / 2; -#ifdef CONFIG_RS780_HPET - setup_hpet_timer(); -#else setup_mfgpt0_timer(); -#endif } void read_persistent_clock64(struct timespec64 *ts) diff --git a/arch/mips/loongson64/common/uart_base.c b/arch/mips/loongson2ef/common/uart_base.c index e88d937f10fe..522bea6ad7b0 100644 --- a/arch/mips/loongson64/common/uart_base.c +++ b/arch/mips/loongson2ef/common/uart_base.c @@ -6,13 +6,14 @@ #include <linux/export.h> #include <asm/bootinfo.h> +#include <asm/setup.h> #include <loongson.h> /* raw */ -unsigned long loongson_uart_base[MAX_UARTS] = {}; +unsigned long loongson_uart_base; /* ioremapped */ -unsigned long _loongson_uart_base[MAX_UARTS] = {}; +unsigned long _loongson_uart_base; EXPORT_SYMBOL(loongson_uart_base); EXPORT_SYMBOL(_loongson_uart_base); @@ -20,16 +21,12 @@ EXPORT_SYMBOL(_loongson_uart_base); void prom_init_loongson_uart_base(void) { switch (mips_machtype) { - case MACH_LOONGSON_GENERIC: - /* The CPU provided serial port (CPU) */ - loongson_uart_base[0] = LOONGSON_REG_BASE + 0x1e0; - break; case MACH_LEMOTE_FL2E: - loongson_uart_base[0] = LOONGSON_PCIIO_BASE + 0x3f8; + loongson_uart_base = LOONGSON_PCIIO_BASE + 0x3f8; break; case MACH_LEMOTE_FL2F: case MACH_LEMOTE_LL2F: - loongson_uart_base[0] = LOONGSON_PCIIO_BASE + 0x2f8; + loongson_uart_base = LOONGSON_PCIIO_BASE + 0x2f8; break; case MACH_LEMOTE_ML2F7: case MACH_LEMOTE_YL2F89: @@ -37,10 +34,10 @@ void prom_init_loongson_uart_base(void) case MACH_LEMOTE_NAS: default: /* The CPU provided serial port (LPC) */ - loongson_uart_base[0] = LOONGSON_LIO1_BASE + 0x3f8; + loongson_uart_base = LOONGSON_LIO1_BASE + 0x3f8; break; } - _loongson_uart_base[0] = - (unsigned long)ioremap_nocache(loongson_uart_base[0], 8); + _loongson_uart_base = TO_UNCAC(loongson_uart_base); + setup_8250_early_printk_port(_loongson_uart_base, 0, 1024); } diff --git a/arch/mips/loongson64/fuloong-2e/Makefile b/arch/mips/loongson2ef/fuloong-2e/Makefile index bb58edb3bea7..bb58edb3bea7 100644 --- a/arch/mips/loongson64/fuloong-2e/Makefile +++ b/arch/mips/loongson2ef/fuloong-2e/Makefile diff --git a/arch/mips/loongson64/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c index e122292bf666..e122292bf666 100644 --- a/arch/mips/loongson64/fuloong-2e/dma.c +++ b/arch/mips/loongson2ef/fuloong-2e/dma.c diff --git a/arch/mips/loongson64/fuloong-2e/irq.c b/arch/mips/loongson2ef/fuloong-2e/irq.c index 32278e7bf85c..32278e7bf85c 100644 --- a/arch/mips/loongson64/fuloong-2e/irq.c +++ b/arch/mips/loongson2ef/fuloong-2e/irq.c diff --git a/arch/mips/loongson64/fuloong-2e/reset.c b/arch/mips/loongson2ef/fuloong-2e/reset.c index 8273de1cf4bb..8273de1cf4bb 100644 --- a/arch/mips/loongson64/fuloong-2e/reset.c +++ b/arch/mips/loongson2ef/fuloong-2e/reset.c diff --git a/arch/mips/loongson64/lemote-2f/Makefile b/arch/mips/loongson2ef/lemote-2f/Makefile index 881a0ec06d1f..881a0ec06d1f 100644 --- a/arch/mips/loongson64/lemote-2f/Makefile +++ b/arch/mips/loongson2ef/lemote-2f/Makefile diff --git a/arch/mips/loongson64/lemote-2f/clock.c b/arch/mips/loongson2ef/lemote-2f/clock.c index 8281334df9c8..414f282c8ab5 100644 --- a/arch/mips/loongson64/lemote-2f/clock.c +++ b/arch/mips/loongson2ef/lemote-2f/clock.c @@ -15,7 +15,7 @@ #include <linux/spinlock.h> #include <asm/clock.h> -#include <asm/mach-loongson64/loongson.h> +#include <asm/mach-loongson2ef/loongson.h> static LIST_HEAD(clock_list); static DEFINE_SPINLOCK(clock_lock); @@ -118,9 +118,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate) clk->rate = rate; - regval = LOONGSON_CHIPCFG(0); + regval = readl(LOONGSON_CHIPCFG); regval = (regval & ~0x7) | (pos->driver_data - 1); - LOONGSON_CHIPCFG(0) = regval; + writel(regval, LOONGSON_CHIPCFG); return ret; } diff --git a/arch/mips/loongson64/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c index abf0e39d7e46..abf0e39d7e46 100644 --- a/arch/mips/loongson64/lemote-2f/dma.c +++ b/arch/mips/loongson2ef/lemote-2f/dma.c diff --git a/arch/mips/loongson64/lemote-2f/ec_kb3310b.c b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.c index d138220e96a2..d138220e96a2 100644 --- a/arch/mips/loongson64/lemote-2f/ec_kb3310b.c +++ b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.c diff --git a/arch/mips/loongson64/lemote-2f/ec_kb3310b.h b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.h index aecdbc9c875a..aecdbc9c875a 100644 --- a/arch/mips/loongson64/lemote-2f/ec_kb3310b.h +++ b/arch/mips/loongson2ef/lemote-2f/ec_kb3310b.h diff --git a/arch/mips/loongson64/lemote-2f/irq.c b/arch/mips/loongson2ef/lemote-2f/irq.c index c58a044c6c07..c58a044c6c07 100644 --- a/arch/mips/loongson64/lemote-2f/irq.c +++ b/arch/mips/loongson2ef/lemote-2f/irq.c diff --git a/arch/mips/loongson64/lemote-2f/machtype.c b/arch/mips/loongson2ef/lemote-2f/machtype.c index 9462a3ab57be..9462a3ab57be 100644 --- a/arch/mips/loongson64/lemote-2f/machtype.c +++ b/arch/mips/loongson2ef/lemote-2f/machtype.c diff --git a/arch/mips/loongson64/lemote-2f/pm.c b/arch/mips/loongson2ef/lemote-2f/pm.c index 3d0027229e3c..3d0027229e3c 100644 --- a/arch/mips/loongson64/lemote-2f/pm.c +++ b/arch/mips/loongson2ef/lemote-2f/pm.c diff --git a/arch/mips/loongson64/lemote-2f/reset.c b/arch/mips/loongson2ef/lemote-2f/reset.c index 0db0934302ea..197dae4ffd23 100644 --- a/arch/mips/loongson64/lemote-2f/reset.c +++ b/arch/mips/loongson2ef/lemote-2f/reset.c @@ -24,7 +24,7 @@ static void reset_cpu(void) * reset cpu to full speed, this is needed when enabling cpu frequency * scalling */ - LOONGSON_CHIPCFG(0) |= 0x7; + writel(readl(LOONGSON_CHIPCFG) | 0x7, LOONGSON_CHIPCFG); } /* reset support for fuloong2f */ diff --git a/arch/mips/loongson32/Kconfig b/arch/mips/loongson32/Kconfig index 6dacc1438906..e27879b4813b 100644 --- a/arch/mips/loongson32/Kconfig +++ b/arch/mips/loongson32/Kconfig @@ -38,7 +38,7 @@ endchoice menuconfig CEVT_CSRC_LS1X bool "Use PWM Timer for clockevent/clocksource" select MIPS_EXTERNAL_TIMER - depends on CPU_LOONGSON1 + depends on CPU_LOONGSON32 help This option changes the default clockevent/clocksource to PWM Timer, and is required by Loongson1 CPUFreq support. diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform index 333215593092..7f8e342f1ef5 100644 --- a/arch/mips/loongson32/Platform +++ b/arch/mips/loongson32/Platform @@ -1,4 +1,4 @@ -cflags-$(CONFIG_CPU_LOONGSON1) += -march=mips32r2 -Wa,--trap +cflags-$(CONFIG_CPU_LOONGSON32) += -march=mips32r2 -Wa,--trap platform-$(CONFIG_MACH_LOONGSON32) += loongson32/ cflags-$(CONFIG_MACH_LOONGSON32) += -I$(srctree)/arch/mips/include/asm/mach-loongson32 -load-$(CONFIG_CPU_LOONGSON1) += 0xffffffff80200000 +load-$(CONFIG_CPU_LOONGSON32) += 0xffffffff80200000 diff --git a/arch/mips/loongson32/common/prom.c b/arch/mips/loongson32/common/prom.c index c4e043ee53ff..73dd25142484 100644 --- a/arch/mips/loongson32/common/prom.c +++ b/arch/mips/loongson32/common/prom.c @@ -5,63 +5,25 @@ * Modified from arch/mips/pnx833x/common/prom.c. */ +#include <linux/io.h> +#include <linux/init.h> #include <linux/serial_reg.h> #include <asm/bootinfo.h> +#include <asm/fw/fw.h> #include <loongson1.h> -#include <prom.h> -int prom_argc; -char **prom_argv, **prom_envp; -unsigned long memsize, highmemsize; - -char *prom_getenv(char *envname) -{ - char **env = prom_envp; - int i; - - i = strlen(envname); - - while (*env) { - if (strncmp(envname, *env, i) == 0 && *(*env + i) == '=') - return *env + i + 1; - env++; - } - - return 0; -} - -static inline unsigned long env_or_default(char *env, unsigned long dfl) -{ - char *str = prom_getenv(env); - return str ? simple_strtol(str, 0, 0) : dfl; -} - -void __init prom_init_cmdline(void) -{ - char *c = &(arcs_cmdline[0]); - int i; - - for (i = 1; i < prom_argc; i++) { - strcpy(c, prom_argv[i]); - c += strlen(prom_argv[i]); - if (i < prom_argc - 1) - *c++ = ' '; - } - *c = 0; -} +unsigned long memsize; void __init prom_init(void) { void __iomem *uart_base; - prom_argc = fw_arg0; - prom_argv = (char **)fw_arg1; - prom_envp = (char **)fw_arg2; - prom_init_cmdline(); + fw_init_cmdline(); - memsize = env_or_default("memsize", DEFAULT_MEMSIZE); - highmemsize = env_or_default("highmemsize", 0x0); + memsize = fw_getenvl("memsize"); + if(!memsize) + memsize = DEFAULT_MEMSIZE; if (strstr(arcs_cmdline, "console=ttyS3")) uart_base = ioremap_nocache(LS1X_UART3_BASE, 0x0f); @@ -77,3 +39,8 @@ void __init prom_init(void) void __init prom_free_prom_memory(void) { } + +void __init plat_mem_setup(void) +{ + add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM); +} diff --git a/arch/mips/loongson32/common/setup.c b/arch/mips/loongson32/common/setup.c index 8b03e18fc4d8..4733fe037176 100644 --- a/arch/mips/loongson32/common/setup.c +++ b/arch/mips/loongson32/common/setup.c @@ -3,15 +3,12 @@ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com> */ +#include <linux/io.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <asm/cpu-info.h> #include <asm/bootinfo.h> -#include <prom.h> - -void __init plat_mem_setup(void) -{ - add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM); -} - const char *get_system_type(void) { unsigned int processor_id = (¤t_cpu_data)->processor_id; diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig index 4c14a11525f4..48b29c198acf 100644 --- a/arch/mips/loongson64/Kconfig +++ b/arch/mips/loongson64/Kconfig @@ -1,119 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 if MACH_LOONGSON64 -choice - prompt "Machine Type" - -config LEMOTE_FULOONG2E - bool "Lemote Fuloong(2e) mini-PC" - select ARCH_SPARSEMEM_ENABLE - select ARCH_MIGHT_HAVE_PC_PARPORT - select ARCH_MIGHT_HAVE_PC_SERIO - select CEVT_R4K - select CSRC_R4K - select SYS_HAS_CPU_LOONGSON2E - select DMA_NONCOHERENT - select BOOT_ELF32 - select BOARD_SCACHE - select HAVE_PCI - select I8259 - select ISA - select IRQ_MIPS_CPU - select SYS_SUPPORTS_64BIT_KERNEL - select SYS_SUPPORTS_LITTLE_ENDIAN - select SYS_SUPPORTS_HIGHMEM - select SYS_HAS_EARLY_PRINTK - select GENERIC_ISA_DMA_SUPPORT_BROKEN - select CPU_HAS_WB - select LOONGSON_MC146818 - help - Lemote Fuloong(2e) mini-PC board based on the Chinese Loongson-2E CPU and - an FPGA northbridge - - Lemote Fuloong(2e) mini PC have a VIA686B south bridge. - -config LEMOTE_MACH2F - bool "Lemote Loongson 2F family machines" - select ARCH_SPARSEMEM_ENABLE - select ARCH_MIGHT_HAVE_PC_PARPORT - select ARCH_MIGHT_HAVE_PC_SERIO - select BOARD_SCACHE - select BOOT_ELF32 - select CEVT_R4K if ! MIPS_EXTERNAL_TIMER - select CPU_HAS_WB - select CS5536 - select CSRC_R4K if ! MIPS_EXTERNAL_TIMER - select DMA_NONCOHERENT - select GENERIC_ISA_DMA_SUPPORT_BROKEN - select HAVE_CLK - select HAVE_PCI - select I8259 - select IRQ_MIPS_CPU - select ISA - select SYS_HAS_CPU_LOONGSON2F - select SYS_HAS_EARLY_PRINTK - select SYS_SUPPORTS_64BIT_KERNEL - select SYS_SUPPORTS_HIGHMEM - select SYS_SUPPORTS_LITTLE_ENDIAN - select LOONGSON_MC146818 - help - Lemote Loongson 2F family machines utilize the 2F revision of - Loongson processor and the AMD CS5536 south bridge. - - These family machines include fuloong2f mini PC, yeeloong2f notebook, - LingLoong allinone PC and so forth. - -config LOONGSON_MACH3X - bool "Generic Loongson 3 family machines" - select ARCH_SPARSEMEM_ENABLE - select ARCH_MIGHT_HAVE_PC_PARPORT - select ARCH_MIGHT_HAVE_PC_SERIO - select GENERIC_ISA_DMA_SUPPORT_BROKEN - select BOOT_ELF32 - select BOARD_SCACHE - select CSRC_R4K - select CEVT_R4K - select CPU_HAS_WB - select FORCE_PCI - select ISA - select I8259 - select IRQ_MIPS_CPU - select NR_CPUS_DEFAULT_4 - select SYS_HAS_CPU_LOONGSON3 - select SYS_HAS_EARLY_PRINTK - select SYS_SUPPORTS_SMP - select SYS_SUPPORTS_HOTPLUG_CPU - select SYS_SUPPORTS_NUMA - select SYS_SUPPORTS_64BIT_KERNEL - select SYS_SUPPORTS_HIGHMEM - select SYS_SUPPORTS_LITTLE_ENDIAN - select LOONGSON_MC146818 - select ZONE_DMA32 - select LEFI_FIRMWARE_INTERFACE - help - Generic Loongson 3 family machines utilize the 3A/3B revision - of Loongson processor and RS780/SBX00 chipset. -endchoice - -config CS5536 - bool - -config CS5536_MFGPT - bool "CS5536 MFGPT Timer" - depends on CS5536 && !HIGH_RES_TIMERS - select MIPS_EXTERNAL_TIMER - help - This option enables the mfgpt0 timer of AMD CS5536. With this timer - switched on you can not use high resolution timers. - - If you want to enable the Loongson2 CPUFreq Driver, Please enable - this option at first, otherwise, You will get wrong system time. - - If unsure, say Yes. - config RS780_HPET bool "RS780/SBX00 HPET Timer" - depends on LOONGSON_MACH3X + depends on MACH_LOONGSON64 select MIPS_EXTERNAL_TIMER help This option enables the hpet timer of AMD RS780/SBX00. @@ -123,16 +13,9 @@ config RS780_HPET If unsure, say Yes. -config LOONGSON_UART_BASE - bool - default y - depends on EARLY_PRINTK || SERIAL_8250 config LOONGSON_MC146818 bool default n -config LEFI_FIRMWARE_INTERFACE - bool - endif # MACH_LOONGSON64 diff --git a/arch/mips/loongson64/Makefile b/arch/mips/loongson64/Makefile index 1a5df773707d..7821891bc5d0 100644 --- a/arch/mips/loongson64/Makefile +++ b/arch/mips/loongson64/Makefile @@ -1,24 +1,13 @@ # SPDX-License-Identifier: GPL-2.0-only # -# Common code for all Loongson based systems +# Makefile for Loongson-3 family machines # +obj-$(CONFIG_MACH_LOONGSON64) += irq.o cop2-ex.o platform.o acpi_init.o dma.o \ + setup.o init.o env.o time.o reset.o \ -obj-$(CONFIG_MACH_LOONGSON64) += common/ - -# -# Lemote Fuloong mini-PC (Loongson 2E-based) -# - -obj-$(CONFIG_LEMOTE_FULOONG2E) += fuloong-2e/ - -# -# Lemote loongson2f family machines -# - -obj-$(CONFIG_LEMOTE_MACH2F) += lemote-2f/ - -# -# All Loongson-3 family machines -# - -obj-$(CONFIG_CPU_LOONGSON3) += loongson-3/ +obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_NUMA) += numa.o +obj-$(CONFIG_RS780_HPET) += hpet.o +obj-$(CONFIG_PCI) += pci.o +obj-$(CONFIG_LOONGSON_MC146818) += rtc.o +obj-$(CONFIG_SUSPEND) += pm.o diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index 9f79908f5063..d5eb94c9edb4 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -2,32 +2,13 @@ # Loongson Processors' Support # -# Only gcc >= 4.4 have Loongson specific support -cflags-$(CONFIG_CPU_LOONGSON2) += -Wa,--trap -cflags-$(CONFIG_CPU_LOONGSON2E) += \ - $(call cc-option,-march=loongson2e,-march=r4600) -cflags-$(CONFIG_CPU_LOONGSON2F) += \ - $(call cc-option,-march=loongson2f,-march=r4600) -# Enable the workarounds for Loongson2f -ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS - ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-nop,),) - $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-nop) - else - cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-nop - endif - ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-jump,),) - $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-jump) - else - cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-jump - endif -endif -cflags-$(CONFIG_CPU_LOONGSON3) += -Wa,--trap +cflags-$(CONFIG_CPU_LOONGSON64) += -Wa,--trap # # Some versions of binutils, not currently mainline as of 2019/02/04, support # an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction -# to work around a CPU bug (see loongson_llsc_mb() in asm/barrier.h for a +# to work around a CPU bug (see __SYNC_loongson3_war in asm/sync.h for a # description). # # We disable this in order to prevent the assembler meddling with the @@ -44,7 +25,7 @@ cflags-$(CONFIG_CPU_LOONGSON3) += -Wa,--trap # binutils does not merge support for the flag then we can revisit & remove # this later - for now it ensures vendor toolchains don't cause problems. # -cflags-$(CONFIG_CPU_LOONGSON3) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,) +cflags-$(CONFIG_CPU_LOONGSON64) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,) # # binutils from v2.25 on and gcc starting from v4.9.0 treat -march=loongson3a @@ -55,14 +36,14 @@ cflags-$(CONFIG_CPU_LOONGSON3) += $(call as-option,-Wa$(comma)-mno-fix-loongson3 # ifeq ($(call cc-ifversion, -ge, 0409, y), y) ifeq ($(call ld-ifversion, -ge, 225000000, y), y) - cflags-$(CONFIG_CPU_LOONGSON3) += \ + cflags-$(CONFIG_CPU_LOONGSON64) += \ $(call cc-option,-march=loongson3a -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) else - cflags-$(CONFIG_CPU_LOONGSON3) += \ + cflags-$(CONFIG_CPU_LOONGSON64) += \ $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) endif else - cflags-$(CONFIG_CPU_LOONGSON3) += \ + cflags-$(CONFIG_CPU_LOONGSON64) += \ $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) endif @@ -76,6 +57,4 @@ cflags-y += $(call cc-option,-mno-loongson-mmi) platform-$(CONFIG_MACH_LOONGSON64) += loongson64/ cflags-$(CONFIG_MACH_LOONGSON64) += -I$(srctree)/arch/mips/include/asm/mach-loongson64 -mno-branch-likely -load-$(CONFIG_LEMOTE_FULOONG2E) += 0xffffffff80100000 -load-$(CONFIG_LEMOTE_MACH2F) += 0xffffffff80200000 -load-$(CONFIG_LOONGSON_MACH3X) += 0xffffffff80200000 +load-$(CONFIG_CPU_LOONGSON64) += 0xffffffff80200000 diff --git a/arch/mips/loongson64/loongson-3/acpi_init.c b/arch/mips/loongson64/acpi_init.c index 8d7c119ddf91..8d7c119ddf91 100644 --- a/arch/mips/loongson64/loongson-3/acpi_init.c +++ b/arch/mips/loongson64/acpi_init.c diff --git a/arch/mips/loongson64/common/cmdline.c b/arch/mips/loongson64/common/cmdline.c deleted file mode 100644 index a735460682cf..000000000000 --- a/arch/mips/loongson64/common/cmdline.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Based on Ocelot Linux port, which is - * Copyright 2001 MontaVista Software Inc. - * Author: jsun@mvista.com or jsun@junsun.net - * - * Copyright 2003 ICT CAS - * Author: Michael Guo <guoyi@ict.ac.cn> - * - * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology - * Author: Fuxin Zhang, zhangfx@lemote.com - * - * Copyright (C) 2009 Lemote Inc. - * Author: Wu Zhangjin, wuzhangjin@gmail.com - */ -#include <asm/bootinfo.h> - -#include <loongson.h> - -void __init prom_init_cmdline(void) -{ - int prom_argc; - /* pmon passes arguments in 32bit pointers */ - int *_prom_argv; - int i; - long l; - - /* firmware arguments are initialized in head.S */ - prom_argc = fw_arg0; - _prom_argv = (int *)fw_arg1; - - /* arg[0] is "g", the rest is boot parameters */ - arcs_cmdline[0] = '\0'; - for (i = 1; i < prom_argc; i++) { - l = (long)_prom_argv[i]; - if (strlen(arcs_cmdline) + strlen(((char *)l) + 1) - >= sizeof(arcs_cmdline)) - break; - strcat(arcs_cmdline, ((char *)l)); - strcat(arcs_cmdline, " "); - } - - prom_init_machtype(); -} diff --git a/arch/mips/loongson64/common/early_printk.c b/arch/mips/loongson64/common/early_printk.c deleted file mode 100644 index 5e2a151aa30c..000000000000 --- a/arch/mips/loongson64/common/early_printk.c +++ /dev/null @@ -1,38 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* early printk support - * - * Copyright (c) 2009 Philippe Vachon <philippe@cowpig.ca> - * Copyright (c) 2009 Lemote Inc. - * Author: Wu Zhangjin, wuzhangjin@gmail.com - */ -#include <linux/serial_reg.h> -#include <asm/setup.h> - -#include <loongson.h> - -#define PORT(base, offset) (u8 *)(base + offset) - -static inline unsigned int serial_in(unsigned char *base, int offset) -{ - return readb(PORT(base, offset)); -} - -static inline void serial_out(unsigned char *base, int offset, int value) -{ - writeb(value, PORT(base, offset)); -} - -void prom_putchar(char c) -{ - int timeout; - unsigned char *uart_base; - - uart_base = (unsigned char *)_loongson_uart_base[0]; - timeout = 1024; - - while (((serial_in(uart_base, UART_LSR) & UART_LSR_THRE) == 0) && - (timeout-- > 0)) - ; - - serial_out(uart_base, UART_TX, c); -} diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c deleted file mode 100644 index 4254ac4ec616..000000000000 --- a/arch/mips/loongson64/common/mem.c +++ /dev/null @@ -1,157 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - */ -#include <linux/fs.h> -#include <linux/fcntl.h> -#include <linux/memblock.h> -#include <linux/mm.h> - -#include <asm/bootinfo.h> - -#include <loongson.h> -#include <boot_param.h> -#include <mem.h> -#include <pci.h> - -#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE - -u32 memsize, highmemsize; - -void __init prom_init_memory(void) -{ - add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM); - - add_memory_region(memsize << 20, LOONGSON_PCI_MEM_START - (memsize << - 20), BOOT_MEM_RESERVED); - -#ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG - { - int bit; - - bit = fls(memsize + highmemsize); - if (bit != ffs(memsize + highmemsize)) - bit += 20; - else - bit = bit + 20 - 1; - - /* set cpu window3 to map CPU to DDR: 2G -> 2G */ - LOONGSON_ADDRWIN_CPUTODDR(ADDRWIN_WIN3, 0x80000000ul, - 0x80000000ul, (1 << bit)); - mmiowb(); - } -#endif /* !CONFIG_CPU_SUPPORTS_ADDRWINCFG */ - -#ifdef CONFIG_64BIT - if (highmemsize > 0) - add_memory_region(LOONGSON_HIGHMEM_START, - highmemsize << 20, BOOT_MEM_RAM); - - add_memory_region(LOONGSON_PCI_MEM_END + 1, LOONGSON_HIGHMEM_START - - LOONGSON_PCI_MEM_END - 1, BOOT_MEM_RESERVED); - -#endif /* !CONFIG_64BIT */ -} - -#else /* CONFIG_LEFI_FIRMWARE_INTERFACE */ - -void __init prom_init_memory(void) -{ - int i; - u32 node_id; - u32 mem_type; - - /* parse memory information */ - for (i = 0; i < loongson_memmap->nr_map; i++) { - node_id = loongson_memmap->map[i].node_id; - mem_type = loongson_memmap->map[i].mem_type; - - if (node_id != 0) - continue; - - switch (mem_type) { - case SYSTEM_RAM_LOW: - memblock_add(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20); - break; - case SYSTEM_RAM_HIGH: - memblock_add(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20); - break; - case SYSTEM_RAM_RESERVED: - memblock_reserve(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20); - break; - } - } -} - -#endif /* CONFIG_LEFI_FIRMWARE_INTERFACE */ - -/* override of arch/mips/mm/cache.c: __uncached_access */ -int __uncached_access(struct file *file, unsigned long addr) -{ - if (file->f_flags & O_DSYNC) - return 1; - - return addr >= __pa(high_memory) || - ((addr >= LOONGSON_MMIO_MEM_START) && - (addr < LOONGSON_MMIO_MEM_END)); -} - -#ifdef CONFIG_CPU_SUPPORTS_UNCACHED_ACCELERATED - -#include <linux/pci.h> -#include <linux/sched.h> -#include <asm/current.h> - -static unsigned long uca_start, uca_end; - -pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot) -{ - unsigned long offset = pfn << PAGE_SHIFT; - unsigned long end = offset + size; - - if (__uncached_access(file, offset)) { - if (uca_start && (offset >= uca_start) && - (end <= uca_end)) - return __pgprot((pgprot_val(vma_prot) & - ~_CACHE_MASK) | - _CACHE_UNCACHED_ACCELERATED); - else - return pgprot_noncached(vma_prot); - } - return vma_prot; -} - -static int __init find_vga_mem_init(void) -{ - struct pci_dev *dev = 0; - struct resource *r; - int idx; - - if (uca_start) - return 0; - - for_each_pci_dev(dev) { - if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) { - for (idx = 0; idx < PCI_NUM_RESOURCES; idx++) { - r = &dev->resource[idx]; - if (!r->start && r->end) - continue; - if (r->flags & IORESOURCE_IO) - continue; - if (r->flags & IORESOURCE_MEM) { - uca_start = r->start; - uca_end = r->end; - return 0; - } - } - } - } - - return 0; -} - -late_initcall(find_vga_mem_init); -#endif /* !CONFIG_CPU_SUPPORTS_UNCACHED_ACCELERATED */ diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c deleted file mode 100644 index 98c3a7feb10f..000000000000 --- a/arch/mips/loongson64/common/serial.c +++ /dev/null @@ -1,117 +0,0 @@ -/* - * 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. - * - * Copyright (C) 2007 Ralf Baechle (ralf@linux-mips.org) - * - * Copyright (C) 2009 Lemote, Inc. - * Author: Yan hua (yanhua@lemote.com) - * Author: Wu Zhangjin (wuzhangjin@gmail.com) - */ - -#include <linux/io.h> -#include <linux/module.h> -#include <linux/serial_8250.h> - -#include <asm/bootinfo.h> - -#include <loongson.h> -#include <machine.h> - -#define PORT(int, clk) \ -{ \ - .irq = int, \ - .uartclk = clk, \ - .iotype = UPIO_PORT, \ - .flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST, \ - .regshift = 0, \ -} - -#define PORT_M(int, clk) \ -{ \ - .irq = MIPS_CPU_IRQ_BASE + (int), \ - .uartclk = clk, \ - .iotype = UPIO_MEM, \ - .membase = (void __iomem *)NULL, \ - .flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST, \ - .regshift = 0, \ -} - -static struct plat_serial8250_port uart8250_data[][MAX_UARTS + 1] = { - [MACH_LOONGSON_UNKNOWN] = {}, - [MACH_LEMOTE_FL2E] = {PORT(4, 1843200), {} }, - [MACH_LEMOTE_FL2F] = {PORT(3, 1843200), {} }, - [MACH_LEMOTE_ML2F7] = {PORT_M(3, 3686400), {} }, - [MACH_LEMOTE_YL2F89] = {PORT_M(3, 3686400), {} }, - [MACH_DEXXON_GDIUM2F10] = {PORT_M(3, 3686400), {} }, - [MACH_LEMOTE_NAS] = {PORT_M(3, 3686400), {} }, - [MACH_LEMOTE_LL2F] = {PORT(3, 1843200), {} }, - [MACH_LOONGSON_GENERIC] = {PORT_M(2, 25000000), {} }, - [MACH_LOONGSON_END] = {}, -}; - -static struct platform_device uart8250_device = { - .name = "serial8250", - .id = PLAT8250_DEV_PLATFORM, -}; - -static int __init serial_init(void) -{ - int i; - unsigned char iotype; - - iotype = uart8250_data[mips_machtype][0].iotype; - - if (UPIO_MEM == iotype) { - uart8250_data[mips_machtype][0].mapbase = - loongson_uart_base[0]; - uart8250_data[mips_machtype][0].membase = - (void __iomem *)_loongson_uart_base[0]; - } - else if (UPIO_PORT == iotype) - uart8250_data[mips_machtype][0].iobase = - loongson_uart_base[0] - LOONGSON_PCIIO_BASE; - - if (loongson_sysconf.uarts[0].uartclk) - uart8250_data[mips_machtype][0].uartclk = - loongson_sysconf.uarts[0].uartclk; - - for (i = 1; i < loongson_sysconf.nr_uarts; i++) { - iotype = loongson_sysconf.uarts[i].iotype; - uart8250_data[mips_machtype][i].iotype = iotype; - loongson_uart_base[i] = loongson_sysconf.uarts[i].uart_base; - - if (UPIO_MEM == iotype) { - uart8250_data[mips_machtype][i].irq = - MIPS_CPU_IRQ_BASE + loongson_sysconf.uarts[i].int_offset; - uart8250_data[mips_machtype][i].mapbase = - loongson_uart_base[i]; - uart8250_data[mips_machtype][i].membase = - ioremap_nocache(loongson_uart_base[i], 8); - } else if (UPIO_PORT == iotype) { - uart8250_data[mips_machtype][i].irq = - loongson_sysconf.uarts[i].int_offset; - uart8250_data[mips_machtype][i].iobase = - loongson_uart_base[i] - LOONGSON_PCIIO_BASE; - } - - uart8250_data[mips_machtype][i].uartclk = - loongson_sysconf.uarts[i].uartclk; - uart8250_data[mips_machtype][i].flags = - UPF_BOOT_AUTOCONF | UPF_SKIP_TEST; - } - - memset(&uart8250_data[mips_machtype][loongson_sysconf.nr_uarts], - 0, sizeof(struct plat_serial8250_port)); - uart8250_device.dev.platform_data = uart8250_data[mips_machtype]; - - return platform_device_register(&uart8250_device); -} -module_init(serial_init); - -static void __exit serial_exit(void) -{ - platform_device_unregister(&uart8250_device); -} -module_exit(serial_exit); diff --git a/arch/mips/loongson64/loongson-3/cop2-ex.c b/arch/mips/loongson64/cop2-ex.c index 9efdfe430ff0..9efdfe430ff0 100644 --- a/arch/mips/loongson64/loongson-3/cop2-ex.c +++ b/arch/mips/loongson64/cop2-ex.c diff --git a/arch/mips/loongson64/loongson-3/dma.c b/arch/mips/loongson64/dma.c index 5e86635f71db..5e86635f71db 100644 --- a/arch/mips/loongson64/loongson-3/dma.c +++ b/arch/mips/loongson64/dma.c diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/env.c index 09d5cf4676ca..0daeb7bcf023 100644 --- a/arch/mips/loongson64/common/env.c +++ b/arch/mips/loongson64/env.c @@ -30,41 +30,13 @@ u64 loongson_freqctrl[MAX_PACKAGES]; unsigned long long smp_group[4]; -#define parse_even_earlier(res, option, p) \ -do { \ - unsigned int tmp __maybe_unused; \ - \ - if (strncmp(option, (char *)p, strlen(option)) == 0) \ - tmp = kstrtou32((char *)p + strlen(option"="), 10, &res); \ -} while (0) +const char *get_system_type(void) +{ + return "Generic Loongson64 System"; +} void __init prom_init_env(void) { - /* pmon passes arguments in 32bit pointers */ - unsigned int processor_id; - -#ifndef CONFIG_LEFI_FIRMWARE_INTERFACE - int *_prom_envp; - long l; - - /* firmware arguments are initialized in head.S */ - _prom_envp = (int *)fw_arg2; - - l = (long)*_prom_envp; - while (l != 0) { - parse_even_earlier(cpu_clock_freq, "cpuclock", l); - parse_even_earlier(memsize, "memsize", l); - parse_even_earlier(highmemsize, "highmemsize", l); - _prom_envp++; - l = (long)*_prom_envp; - } - if (memsize == 0) - memsize = 256; - - loongson_sysconf.nr_uarts = 1; - - pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize); -#else struct boot_params *boot_p; struct loongson_params *loongson_p; struct system_loongson *esys; @@ -182,31 +154,5 @@ void __init prom_init_env(void) if (loongson_sysconf.nr_sensors) memcpy(loongson_sysconf.sensors, esys->sensors, sizeof(struct sensor_device) * loongson_sysconf.nr_sensors); -#endif - if (cpu_clock_freq == 0) { - processor_id = (¤t_cpu_data)->processor_id; - switch (processor_id & PRID_REV_MASK) { - case PRID_REV_LOONGSON2E: - cpu_clock_freq = 533080000; - break; - case PRID_REV_LOONGSON2F: - cpu_clock_freq = 797000000; - break; - case PRID_REV_LOONGSON3A_R1: - case PRID_REV_LOONGSON3A_R2_0: - case PRID_REV_LOONGSON3A_R2_1: - case PRID_REV_LOONGSON3A_R3_0: - case PRID_REV_LOONGSON3A_R3_1: - cpu_clock_freq = 900000000; - break; - case PRID_REV_LOONGSON3B_R1: - case PRID_REV_LOONGSON3B_R2: - cpu_clock_freq = 1000000000; - break; - default: - cpu_clock_freq = 100000000; - break; - } - } pr_info("CpuClock = %u\n", cpu_clock_freq); } diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/hpet.c index ed15430ad64f..ed15430ad64f 100644 --- a/arch/mips/loongson64/loongson-3/hpet.c +++ b/arch/mips/loongson64/hpet.c diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c new file mode 100644 index 000000000000..5ac1a0f35ca4 --- /dev/null +++ b/arch/mips/loongson64/init.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2009 Lemote Inc. + * Author: Wu Zhangjin, wuzhangjin@gmail.com + */ + +#include <linux/memblock.h> +#include <asm/bootinfo.h> +#include <asm/traps.h> +#include <asm/smp-ops.h> +#include <asm/cacheflush.h> +#include <asm/fw/fw.h> + +#include <loongson.h> + +static void __init mips_nmi_setup(void) +{ + void *base; + extern char except_vec_nmi; + + base = (void *)(CAC_BASE + 0x380); + memcpy(base, &except_vec_nmi, 0x80); + flush_icache_range((unsigned long)base, (unsigned long)base + 0x80); +} + +void __init prom_init(void) +{ + fw_init_cmdline(); + prom_init_env(); + + /* init base address of io space */ + set_io_port_base((unsigned long) + ioremap(LOONGSON_PCIIO_BASE, LOONGSON_PCIIO_SIZE)); + + prom_init_numa_memory(); + + /* Hardcode to CPU UART 0 */ + setup_8250_early_printk_port(TO_UNCAC(LOONGSON_REG_BASE + 0x1e0), 0, 1024); + + register_smp_ops(&loongson3_smp_ops); + board_nmi_handler_setup = mips_nmi_setup; +} + +void __init prom_free_prom_memory(void) +{ +} diff --git a/arch/mips/loongson64/loongson-3/irq.c b/arch/mips/loongson64/irq.c index 5605061f5f98..79ad797497e4 100644 --- a/arch/mips/loongson64/loongson-3/irq.c +++ b/arch/mips/loongson64/irq.c @@ -78,8 +78,12 @@ static void ht_irqdispatch(void) #define UNUSED_IPS (CAUSEF_IP5 | CAUSEF_IP4 | CAUSEF_IP1 | CAUSEF_IP0) -void mach_irq_dispatch(unsigned int pending) +asmlinkage void plat_irq_dispatch(void) { + unsigned int pending; + + pending = read_c0_cause() & read_c0_status() & ST0_IM; + if (pending & CAUSEF_IP7) do_IRQ(LOONGSON_TIMER_IRQ); #if defined(CONFIG_SMP) @@ -127,7 +131,7 @@ void irq_router_init(void) LOONGSON_INT_ROUTER_INTEN | (0xffff << 16) | 0x1 << 10; } -void __init mach_init_irq(void) +void __init arch_init_irq(void) { struct irq_chip *chip; diff --git a/arch/mips/loongson64/loongson-3/Makefile b/arch/mips/loongson64/loongson-3/Makefile deleted file mode 100644 index df39598742b2..000000000000 --- a/arch/mips/loongson64/loongson-3/Makefile +++ /dev/null @@ -1,11 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Makefile for Loongson-3 family machines -# -obj-y += irq.o cop2-ex.o platform.o acpi_init.o dma.o - -obj-$(CONFIG_SMP) += smp.o - -obj-$(CONFIG_NUMA) += numa.o - -obj-$(CONFIG_RS780_HPET) += hpet.o diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/numa.c index 8f20d2cb3767..ef94a2278561 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/numa.c @@ -26,12 +26,15 @@ #include <asm/wbflush.h> #include <boot_param.h> -static struct node_data prealloc__node_data[MAX_NUMNODES]; +static struct pglist_data prealloc__node_data[MAX_NUMNODES]; unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES]; EXPORT_SYMBOL(__node_distances); -struct node_data *__node_data[MAX_NUMNODES]; +struct pglist_data *__node_data[MAX_NUMNODES]; EXPORT_SYMBOL(__node_data); +cpumask_t __node_cpumask[MAX_NUMNODES]; +EXPORT_SYMBOL(__node_cpumask); + static void enable_lpa(void) { unsigned long value; @@ -214,7 +217,7 @@ static __init void prom_meminit(void) if (node_online(node)) { szmem(node); node_mem_init(node); - cpumask_clear(&__node_data[(node)]->cpumask); + cpumask_clear(&__node_cpumask[node]); } } memblocks_present(); @@ -228,7 +231,7 @@ static __init void prom_meminit(void) if (loongson_sysconf.reserved_cpus_mask & (1<<cpu)) continue; - cpumask_set_cpu(active_cpu, &__node_data[(node)]->cpumask); + cpumask_set_cpu(active_cpu, &__node_cpumask[node]); pr_info("NUMA: set cpumask cpu %d on node %d\n", active_cpu, node); active_cpu++; diff --git a/arch/mips/loongson64/pci.c b/arch/mips/loongson64/pci.c new file mode 100644 index 000000000000..e84ae20c3290 --- /dev/null +++ b/arch/mips/loongson64/pci.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology + * Author: Fuxin Zhang, zhangfx@lemote.com + */ +#include <linux/pci.h> + +#include <pci.h> +#include <loongson.h> +#include <boot_param.h> + +static struct resource loongson_pci_mem_resource = { + .name = "pci memory space", + .start = LOONGSON_PCI_MEM_START, + .end = LOONGSON_PCI_MEM_END, + .flags = IORESOURCE_MEM, +}; + +static struct resource loongson_pci_io_resource = { + .name = "pci io space", + .start = LOONGSON_PCI_IO_START, + .end = IO_SPACE_LIMIT, + .flags = IORESOURCE_IO, +}; + +static struct pci_controller loongson_pci_controller = { + .pci_ops = &loongson_pci_ops, + .io_resource = &loongson_pci_io_resource, + .mem_resource = &loongson_pci_mem_resource, + .mem_offset = 0x00000000UL, + .io_offset = 0x00000000UL, +}; + + +extern int sbx00_acpi_init(void); + +static int __init pcibios_init(void) +{ + + loongson_pci_controller.io_map_base = mips_io_port_base; + loongson_pci_mem_resource.start = loongson_sysconf.pci_mem_start_addr; + loongson_pci_mem_resource.end = loongson_sysconf.pci_mem_end_addr; + + register_pci_controller(&loongson_pci_controller); + + sbx00_acpi_init(); + + return 0; +} + +arch_initcall(pcibios_init); diff --git a/arch/mips/loongson64/loongson-3/platform.c b/arch/mips/loongson64/platform.c index 13f3404f0030..13f3404f0030 100644 --- a/arch/mips/loongson64/loongson-3/platform.c +++ b/arch/mips/loongson64/platform.c diff --git a/arch/mips/loongson64/pm.c b/arch/mips/loongson64/pm.c new file mode 100644 index 000000000000..7c8556f09781 --- /dev/null +++ b/arch/mips/loongson64/pm.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * loongson-specific suspend support + * + * Copyright (C) 2009 Lemote Inc. + * Author: Wu Zhangjin <wuzhangjin@gmail.com> + */ +#include <linux/suspend.h> +#include <linux/interrupt.h> +#include <linux/pm.h> + +#include <asm/i8259.h> +#include <asm/mipsregs.h> + +#include <loongson.h> + +static unsigned int __maybe_unused cached_master_mask; /* i8259A */ +static unsigned int __maybe_unused cached_slave_mask; +static unsigned int __maybe_unused cached_bonito_irq_mask; /* bonito */ + +void arch_suspend_disable_irqs(void) +{ + /* disable all mips events */ + local_irq_disable(); + +#ifdef CONFIG_I8259 + /* disable all events of i8259A */ + cached_slave_mask = inb(PIC_SLAVE_IMR); + cached_master_mask = inb(PIC_MASTER_IMR); + + outb(0xff, PIC_SLAVE_IMR); + inb(PIC_SLAVE_IMR); + outb(0xff, PIC_MASTER_IMR); + inb(PIC_MASTER_IMR); +#endif + /* disable all events of bonito */ + cached_bonito_irq_mask = LOONGSON_INTEN; + LOONGSON_INTENCLR = 0xffff; + (void)LOONGSON_INTENCLR; +} + +void arch_suspend_enable_irqs(void) +{ + /* enable all mips events */ + local_irq_enable(); +#ifdef CONFIG_I8259 + /* only enable the cached events of i8259A */ + outb(cached_slave_mask, PIC_SLAVE_IMR); + outb(cached_master_mask, PIC_MASTER_IMR); +#endif + /* enable all cached events of bonito */ + LOONGSON_INTENSET = cached_bonito_irq_mask; + (void)LOONGSON_INTENSET; +} + +/* + * Setup the board-specific events for waking up loongson from wait mode + */ +void __weak setup_wakeup_events(void) +{ +} + +void __weak mach_suspend(void) +{ +} + +void __weak mach_resume(void) +{ +} + +static int loongson_pm_enter(suspend_state_t state) +{ + mach_suspend(); + + mach_resume(); + + return 0; +} + +static int loongson_pm_valid_state(suspend_state_t state) +{ + switch (state) { + case PM_SUSPEND_ON: + case PM_SUSPEND_STANDBY: + case PM_SUSPEND_MEM: + return 1; + + default: + return 0; + } +} + +static const struct platform_suspend_ops loongson_pm_ops = { + .valid = loongson_pm_valid_state, + .enter = loongson_pm_enter, +}; + +static int __init loongson_pm_init(void) +{ + suspend_set_ops(&loongson_pm_ops); + + return 0; +} +arch_initcall(loongson_pm_init); diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c new file mode 100644 index 000000000000..88b3bd5fed25 --- /dev/null +++ b/arch/mips/loongson64/reset.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * + * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology + * Author: Fuxin Zhang, zhangfx@lemote.com + * Copyright (C) 2009 Lemote, Inc. + * Author: Zhangjin Wu, wuzhangjin@gmail.com + */ +#include <linux/init.h> +#include <linux/pm.h> + +#include <asm/idle.h> +#include <asm/reboot.h> + +#include <loongson.h> +#include <boot_param.h> + +static inline void loongson_reboot(void) +{ + ((void (*)(void))ioremap_nocache(LOONGSON_BOOT_BASE, 4)) (); +} + +static void loongson_restart(char *command) +{ + + void (*fw_restart)(void) = (void *)loongson_sysconf.restart_addr; + + fw_restart(); + while (1) { + if (cpu_wait) + cpu_wait(); + } +} + +static void loongson_poweroff(void) +{ + void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr; + + fw_poweroff(); + while (1) { + if (cpu_wait) + cpu_wait(); + } +} + +static void loongson_halt(void) +{ + pr_notice("\n\n** You can safely turn off the power now **\n\n"); + while (1) { + if (cpu_wait) + cpu_wait(); + } +} + +static int __init mips_reboot_setup(void) +{ + _machine_restart = loongson_restart; + _machine_halt = loongson_halt; + pm_power_off = loongson_poweroff; + + return 0; +} + +arch_initcall(mips_reboot_setup); diff --git a/arch/mips/loongson64/rtc.c b/arch/mips/loongson64/rtc.c new file mode 100644 index 000000000000..8d7628c0f513 --- /dev/null +++ b/arch/mips/loongson64/rtc.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Lemote Fuloong platform support + * + * Copyright(c) 2010 Arnaud Patard <apatard@mandriva.com> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/platform_device.h> +#include <linux/mc146818rtc.h> + +static struct resource loongson_rtc_resources[] = { + { + .start = RTC_PORT(0), + .end = RTC_PORT(1), + .flags = IORESOURCE_IO, + }, { + .start = RTC_IRQ, + .end = RTC_IRQ, + .flags = IORESOURCE_IRQ, + } +}; + +static struct platform_device loongson_rtc_device = { + .name = "rtc_cmos", + .id = -1, + .resource = loongson_rtc_resources, + .num_resources = ARRAY_SIZE(loongson_rtc_resources), +}; + + +static int __init loongson_rtc_platform_init(void) +{ + platform_device_register(&loongson_rtc_device); + return 0; +} + +device_initcall(loongson_rtc_platform_init); diff --git a/arch/mips/loongson64/setup.c b/arch/mips/loongson64/setup.c new file mode 100644 index 000000000000..4fd27f4f90ed --- /dev/null +++ b/arch/mips/loongson64/setup.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology + * Author: Fuxin Zhang, zhangfx@lemote.com + */ +#include <linux/export.h> +#include <linux/init.h> + +#include <asm/wbflush.h> +#include <asm/bootinfo.h> + +#include <loongson.h> + +static void wbflush_loongson(void) +{ + asm(".set\tpush\n\t" + ".set\tnoreorder\n\t" + ".set mips3\n\t" + "sync\n\t" + "nop\n\t" + ".set\tpop\n\t" + ".set mips0\n\t"); +} + +void (*__wbflush)(void) = wbflush_loongson; +EXPORT_SYMBOL(__wbflush); + +void __init plat_mem_setup(void) +{ +} diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/smp.c index ce68cdaaf33c..de8e0741ce2d 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/smp.c @@ -18,6 +18,7 @@ #include <asm/tlbflush.h> #include <asm/cacheflush.h> #include <loongson.h> +#include <loongson_regs.h> #include <workarounds.h> #include "smp.h" @@ -48,6 +49,62 @@ static uint32_t core0_c0count[NR_CPUS]; __wbflush(); \ } while (0) +u32 (*ipi_read_clear)(int cpu); +void (*ipi_write_action)(int cpu, u32 action); + +static u32 csr_ipi_read_clear(int cpu) +{ + u32 action; + + /* Load the ipi register to figure out what we're supposed to do */ + action = csr_readl(LOONGSON_CSR_IPI_STATUS); + /* Clear the ipi register to clear the interrupt */ + csr_writel(action, LOONGSON_CSR_IPI_CLEAR); + + return action; +} + +static void csr_ipi_write_action(int cpu, u32 action) +{ + unsigned int irq = 0; + + while ((irq = ffs(action))) { + uint32_t val = CSR_IPI_SEND_BLOCK; + val |= (irq - 1); + val |= (cpu << CSR_IPI_SEND_CPU_SHIFT); + csr_writel(val, LOONGSON_CSR_IPI_SEND); + action &= ~BIT(irq - 1); + } +} + +static u32 legacy_ipi_read_clear(int cpu) +{ + u32 action; + + /* Load the ipi register to figure out what we're supposed to do */ + action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]); + /* Clear the ipi register to clear the interrupt */ + loongson3_ipi_write32(action, ipi_clear0_regs[cpu_logical_map(cpu)]); + + return action; +} + +static void legacy_ipi_write_action(int cpu, u32 action) +{ + loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu]); +} + +static void csr_ipi_probe(void) +{ + if (cpu_has_csr() && csr_readl(LOONGSON_CSR_FEATURES) & LOONGSON_CSRF_IPI) { + ipi_read_clear = csr_ipi_read_clear; + ipi_write_action = csr_ipi_write_action; + } else { + ipi_read_clear = legacy_ipi_read_clear; + ipi_write_action = legacy_ipi_write_action; + } +} + static void ipi_set0_regs_init(void) { ipi_set0_regs[0] = (void *) @@ -233,7 +290,7 @@ static void ipi_mailbox_buf_init(void) */ static void loongson3_send_ipi_single(int cpu, unsigned int action) { - loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(cpu)]); + ipi_write_action(cpu_logical_map(cpu), (u32)action); } static void @@ -242,14 +299,14 @@ loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action) unsigned int i; for_each_cpu(i, mask) - loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(i)]); + ipi_write_action(cpu_logical_map(i), (u32)action); } #define IPI_IRQ_OFFSET 6 void loongson3_send_irq_by_ipi(int cpu, int irqs) { - loongson3_ipi_write32(irqs << IPI_IRQ_OFFSET, ipi_set0_regs[cpu_logical_map(cpu)]); + ipi_write_action(cpu_logical_map(cpu), irqs << IPI_IRQ_OFFSET); } void loongson3_ipi_interrupt(struct pt_regs *regs) @@ -257,13 +314,9 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) int i, cpu = smp_processor_id(); unsigned int action, c0count, irqs; - /* Load the ipi register to figure out what we're supposed to do */ - action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]); + action = ipi_read_clear(cpu); irqs = action >> IPI_IRQ_OFFSET; - /* Clear the ipi register to clear the interrupt */ - loongson3_ipi_write32((u32)action, ipi_clear0_regs[cpu_logical_map(cpu)]); - if (action & SMP_RESCHEDULE_YOURSELF) scheduler_ipi(); @@ -372,6 +425,7 @@ static void __init loongson3_smp_setup(void) num++; } + csr_ipi_probe(); ipi_set0_regs_init(); ipi_clear0_regs_init(); ipi_status0_regs_init(); @@ -450,7 +504,7 @@ static void loongson3_cpu_die(unsigned int cpu) * flush all L1 entries at first. Then, another core (usually Core 0) can * safely disable the clock of the target core. loongson3_play_dead() is * called via CKSEG1 (uncached and unmmaped) */ -static void loongson3a_r1_play_dead(int *state_addr) +static void loongson3_type1_play_dead(int *state_addr) { register int val; register long cpuid, core, node, count; @@ -512,7 +566,7 @@ static void loongson3a_r1_play_dead(int *state_addr) : "a1"); } -static void loongson3a_r2r3_play_dead(int *state_addr) +static void loongson3_type2_play_dead(int *state_addr) { register int val; register long cpuid, core, node, count; @@ -532,27 +586,7 @@ static void loongson3a_r2r3_play_dead(int *state_addr) " cache 1, 3(%[addr]) \n" " addiu %[sets], %[sets], -1 \n" " bnez %[sets], 1b \n" - " addiu %[addr], %[addr], 0x40 \n" - " li %[addr], 0x80000000 \n" /* KSEG0 */ - "2: cache 2, 0(%[addr]) \n" /* flush L1 VCache */ - " cache 2, 1(%[addr]) \n" - " cache 2, 2(%[addr]) \n" - " cache 2, 3(%[addr]) \n" - " cache 2, 4(%[addr]) \n" - " cache 2, 5(%[addr]) \n" - " cache 2, 6(%[addr]) \n" - " cache 2, 7(%[addr]) \n" - " cache 2, 8(%[addr]) \n" - " cache 2, 9(%[addr]) \n" - " cache 2, 10(%[addr]) \n" - " cache 2, 11(%[addr]) \n" - " cache 2, 12(%[addr]) \n" - " cache 2, 13(%[addr]) \n" - " cache 2, 14(%[addr]) \n" - " cache 2, 15(%[addr]) \n" - " addiu %[vsets], %[vsets], -1 \n" - " bnez %[vsets], 2b \n" - " addiu %[addr], %[addr], 0x40 \n" + " addiu %[addr], %[addr], 0x20 \n" " li %[val], 0x7 \n" /* *state_addr = CPU_DEAD; */ " sw %[val], (%[state_addr]) \n" " sync \n" @@ -560,8 +594,7 @@ static void loongson3a_r2r3_play_dead(int *state_addr) " .set pop \n" : [addr] "=&r" (addr), [val] "=&r" (val) : [state_addr] "r" (state_addr), - [sets] "r" (cpu_data[smp_processor_id()].dcache.sets), - [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets)); + [sets] "r" (cpu_data[smp_processor_id()].dcache.sets)); __asm__ __volatile__( " .set push \n" @@ -576,6 +609,8 @@ static void loongson3a_r2r3_play_dead(int *state_addr) " andi %[node], %[cpuid], 0xc \n" " dsll %[node], 42 \n" /* get node id */ " or %[base], %[base], %[node] \n" + " dsrl %[node], 30 \n" /* 15:14 */ + " or %[base], %[base], %[node] \n" "1: li %[count], 0x100 \n" /* wait for init loop */ "2: bnez %[count], 2b \n" /* limit mailbox access */ " addiu %[count], -1 \n" @@ -595,7 +630,7 @@ static void loongson3a_r2r3_play_dead(int *state_addr) : "a1"); } -static void loongson3b_play_dead(int *state_addr) +static void loongson3_type3_play_dead(int *state_addr) { register int val; register long cpuid, core, node, count; @@ -615,7 +650,27 @@ static void loongson3b_play_dead(int *state_addr) " cache 1, 3(%[addr]) \n" " addiu %[sets], %[sets], -1 \n" " bnez %[sets], 1b \n" - " addiu %[addr], %[addr], 0x20 \n" + " addiu %[addr], %[addr], 0x40 \n" + " li %[addr], 0x80000000 \n" /* KSEG0 */ + "2: cache 2, 0(%[addr]) \n" /* flush L1 VCache */ + " cache 2, 1(%[addr]) \n" + " cache 2, 2(%[addr]) \n" + " cache 2, 3(%[addr]) \n" + " cache 2, 4(%[addr]) \n" + " cache 2, 5(%[addr]) \n" + " cache 2, 6(%[addr]) \n" + " cache 2, 7(%[addr]) \n" + " cache 2, 8(%[addr]) \n" + " cache 2, 9(%[addr]) \n" + " cache 2, 10(%[addr]) \n" + " cache 2, 11(%[addr]) \n" + " cache 2, 12(%[addr]) \n" + " cache 2, 13(%[addr]) \n" + " cache 2, 14(%[addr]) \n" + " cache 2, 15(%[addr]) \n" + " addiu %[vsets], %[vsets], -1 \n" + " bnez %[vsets], 2b \n" + " addiu %[addr], %[addr], 0x40 \n" " li %[val], 0x7 \n" /* *state_addr = CPU_DEAD; */ " sw %[val], (%[state_addr]) \n" " sync \n" @@ -623,7 +678,8 @@ static void loongson3b_play_dead(int *state_addr) " .set pop \n" : [addr] "=&r" (addr), [val] "=&r" (val) : [state_addr] "r" (state_addr), - [sets] "r" (cpu_data[smp_processor_id()].dcache.sets)); + [sets] "r" (cpu_data[smp_processor_id()].dcache.sets), + [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets)); __asm__ __volatile__( " .set push \n" @@ -638,8 +694,6 @@ static void loongson3b_play_dead(int *state_addr) " andi %[node], %[cpuid], 0xc \n" " dsll %[node], 42 \n" /* get node id */ " or %[base], %[base], %[node] \n" - " dsrl %[node], 30 \n" /* 15:14 */ - " or %[base], %[base], %[node] \n" "1: li %[count], 0x100 \n" /* wait for init loop */ "2: bnez %[count], 2b \n" /* limit mailbox access */ " addiu %[count], -1 \n" @@ -661,30 +715,42 @@ static void loongson3b_play_dead(int *state_addr) void play_dead(void) { - int *state_addr; + int prid_imp, prid_rev, *state_addr; unsigned int cpu = smp_processor_id(); void (*play_dead_at_ckseg1)(int *); idle_task_exit(); - switch (read_c0_prid() & PRID_REV_MASK) { + + prid_imp = read_c0_prid() & PRID_IMP_MASK; + prid_rev = read_c0_prid() & PRID_REV_MASK; + + if (prid_imp == PRID_IMP_LOONGSON_64G) { + play_dead_at_ckseg1 = + (void *)CKSEG1ADDR((unsigned long)loongson3_type3_play_dead); + goto out; + } + + switch (prid_rev) { case PRID_REV_LOONGSON3A_R1: default: play_dead_at_ckseg1 = - (void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead); + (void *)CKSEG1ADDR((unsigned long)loongson3_type1_play_dead); + break; + case PRID_REV_LOONGSON3B_R1: + case PRID_REV_LOONGSON3B_R2: + play_dead_at_ckseg1 = + (void *)CKSEG1ADDR((unsigned long)loongson3_type2_play_dead); break; case PRID_REV_LOONGSON3A_R2_0: case PRID_REV_LOONGSON3A_R2_1: case PRID_REV_LOONGSON3A_R3_0: case PRID_REV_LOONGSON3A_R3_1: play_dead_at_ckseg1 = - (void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead); - break; - case PRID_REV_LOONGSON3B_R1: - case PRID_REV_LOONGSON3B_R2: - play_dead_at_ckseg1 = - (void *)CKSEG1ADDR((unsigned long)loongson3b_play_dead); + (void *)CKSEG1ADDR((unsigned long)loongson3_type3_play_dead); break; } + +out: state_addr = &per_cpu(cpu_state, cpu); mb(); play_dead_at_ckseg1(state_addr); diff --git a/arch/mips/loongson64/loongson-3/smp.h b/arch/mips/loongson64/smp.h index 957bde81e0e4..957bde81e0e4 100644 --- a/arch/mips/loongson64/loongson-3/smp.h +++ b/arch/mips/loongson64/smp.h diff --git a/arch/mips/loongson64/time.c b/arch/mips/loongson64/time.c new file mode 100644 index 000000000000..1245f22cec84 --- /dev/null +++ b/arch/mips/loongson64/time.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology + * Author: Fuxin Zhang, zhangfx@lemote.com + * + * Copyright (C) 2009 Lemote Inc. + * Author: Wu Zhangjin, wuzhangjin@gmail.com + */ +#include <asm/mc146818-time.h> +#include <asm/time.h> +#include <asm/hpet.h> + +#include <loongson.h> + +void __init plat_time_init(void) +{ + /* setup mips r4k timer */ + mips_hpt_frequency = cpu_clock_freq / 2; + +#ifdef CONFIG_RS780_HPET + setup_hpet_timer(); +#endif +} + +void read_persistent_clock64(struct timespec64 *ts) +{ + ts->tv_sec = mc146818_get_cmos_time(); + ts->tv_nsec = 0; +} diff --git a/arch/mips/math-emu/me-debugfs.c b/arch/mips/math-emu/me-debugfs.c index 387724860fa6..d5ad76b2bb67 100644 --- a/arch/mips/math-emu/me-debugfs.c +++ b/arch/mips/math-emu/me-debugfs.c @@ -189,6 +189,7 @@ static int __init debugfs_fpuemu(void) { struct dentry *fpuemu_debugfs_base_dir; struct dentry *fpuemu_debugfs_inst_dir; + char name[32]; fpuemu_debugfs_base_dir = debugfs_create_dir("fpuemustats", mips_debugfs_dir); @@ -225,8 +226,6 @@ do { \ #define FPU_STAT_CREATE_EX(m) \ do { \ - char name[32]; \ - \ adjust_instruction_counter_name(name, #m); \ \ debugfs_create_file(name, 0444, fpuemu_debugfs_inst_dir, \ diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c index 0ca401ddf3b7..15bb8cf59828 100644 --- a/arch/mips/mm/c-r3k.c +++ b/arch/mips/mm/c-r3k.c @@ -241,6 +241,7 @@ static void r3k_flush_cache_page(struct vm_area_struct *vma, int exec = vma->vm_flags & VM_EXEC; struct mm_struct *mm = vma->vm_mm; pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep; @@ -253,7 +254,8 @@ static void r3k_flush_cache_page(struct vm_area_struct *vma, return; pgdp = pgd_offset(mm, addr); - pudp = pud_offset(pgdp, addr); + p4dp = p4d_offset(pgdp, addr); + pudp = pud_offset(p4dp, addr); pmdp = pmd_offset(pudp, addr); ptep = pte_offset(pmdp, addr); diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 89b9c851d822..5f3d0103b95d 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -271,12 +271,14 @@ static inline void tx49_blast_icache32(void) /* I'm in even chunk. blast odd chunks */ for (ws = 0; ws < ws_end; ws += ws_inc) for (addr = start + 0x400; addr < end; addr += 0x400 * 2) - cache32_unroll32(addr|ws, Index_Invalidate_I); + cache_unroll(32, kernel_cache, Index_Invalidate_I, + addr | ws, 32); CACHE32_UNROLL32_ALIGN; /* I'm in odd chunk. blast even chunks */ for (ws = 0; ws < ws_end; ws += ws_inc) for (addr = start; addr < end; addr += 0x400 * 2) - cache32_unroll32(addr|ws, Index_Invalidate_I); + cache_unroll(32, kernel_cache, Index_Invalidate_I, + addr | ws, 32); } static inline void blast_icache32_r4600_v1_page_indexed(unsigned long page) @@ -302,12 +304,14 @@ static inline void tx49_blast_icache32_page_indexed(unsigned long page) /* I'm in even chunk. blast odd chunks */ for (ws = 0; ws < ws_end; ws += ws_inc) for (addr = start + 0x400; addr < end; addr += 0x400 * 2) - cache32_unroll32(addr|ws, Index_Invalidate_I); + cache_unroll(32, kernel_cache, Index_Invalidate_I, + addr | ws, 32); CACHE32_UNROLL32_ALIGN; /* I'm in odd chunk. blast even chunks */ for (ws = 0; ws < ws_end; ws += ws_inc) for (addr = start; addr < end; addr += 0x400 * 2) - cache32_unroll32(addr|ws, Index_Invalidate_I); + cache_unroll(32, kernel_cache, Index_Invalidate_I, + addr | ws, 32); } static void (* r4k_blast_icache_page)(unsigned long addr); @@ -320,7 +324,7 @@ static void r4k_blast_icache_page_setup(void) r4k_blast_icache_page = (void *)cache_noop; else if (ic_lsize == 16) r4k_blast_icache_page = blast_icache16_page; - else if (ic_lsize == 32 && current_cpu_type() == CPU_LOONGSON2) + else if (ic_lsize == 32 && current_cpu_type() == CPU_LOONGSON2EF) r4k_blast_icache_page = loongson2_blast_icache32_page; else if (ic_lsize == 32) r4k_blast_icache_page = blast_icache32_page; @@ -369,7 +373,7 @@ static void r4k_blast_icache_page_indexed_setup(void) else if (TX49XX_ICACHE_INDEX_INV_WAR) r4k_blast_icache_page_indexed = tx49_blast_icache32_page_indexed; - else if (current_cpu_type() == CPU_LOONGSON2) + else if (current_cpu_type() == CPU_LOONGSON2EF) r4k_blast_icache_page_indexed = loongson2_blast_icache32_page_indexed; else @@ -395,7 +399,7 @@ static void r4k_blast_icache_setup(void) r4k_blast_icache = blast_r4600_v1_icache32; else if (TX49XX_ICACHE_INDEX_INV_WAR) r4k_blast_icache = tx49_blast_icache32; - else if (current_cpu_type() == CPU_LOONGSON2) + else if (current_cpu_type() == CPU_LOONGSON2EF) r4k_blast_icache = loongson2_blast_icache32; else r4k_blast_icache = blast_icache32; @@ -465,7 +469,7 @@ static void r4k_blast_scache_node_setup(void) { unsigned long sc_lsize = cpu_scache_line_size(); - if (current_cpu_type() != CPU_LOONGSON3) + if (current_cpu_type() != CPU_LOONGSON64) r4k_blast_scache_node = (void *)cache_noop; else if (sc_lsize == 16) r4k_blast_scache_node = blast_scache16_node; @@ -480,7 +484,7 @@ static void r4k_blast_scache_node_setup(void) static inline void local_r4k___flush_cache_all(void * args) { switch (current_cpu_type()) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: case CPU_R4000SC: case CPU_R4000MC: case CPU_R4400SC: @@ -497,7 +501,7 @@ static inline void local_r4k___flush_cache_all(void * args) r4k_blast_scache(); break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: /* Use get_ebase_cpunum() for both NUMA=y/n */ r4k_blast_scache_node(get_ebase_cpunum() >> 2); break; @@ -650,6 +654,7 @@ static inline void local_r4k_flush_cache_page(void *args) struct mm_struct *mm = vma->vm_mm; int map_coherent = 0; pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep; @@ -664,7 +669,8 @@ static inline void local_r4k_flush_cache_page(void *args) addr &= PAGE_MASK; pgdp = pgd_offset(mm, addr); - pudp = pud_offset(pgdp, addr); + p4dp = p4d_offset(pgdp, addr); + pudp = pud_offset(p4dp, addr); pmdp = pmd_offset(pudp, addr); ptep = pte_offset(pmdp, addr); @@ -770,7 +776,7 @@ static inline void __local_r4k_flush_icache_range(unsigned long start, r4k_blast_icache(); else { switch (boot_cpu_type()) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: protected_loongson2_blast_icache_range(start, end); break; @@ -863,7 +869,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) preempt_disable(); if (cpu_has_inclusive_pcaches) { if (size >= scache_size) { - if (current_cpu_type() != CPU_LOONGSON3) + if (current_cpu_type() != CPU_LOONGSON64) r4k_blast_scache(); else r4k_blast_scache_node(pa_to_nid(addr)); @@ -904,7 +910,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) preempt_disable(); if (cpu_has_inclusive_pcaches) { if (size >= scache_size) { - if (current_cpu_type() != CPU_LOONGSON3) + if (current_cpu_type() != CPU_LOONGSON64) r4k_blast_scache(); else r4k_blast_scache_node(pa_to_nid(addr)); @@ -1224,7 +1230,7 @@ static void probe_pcache(void) c->options |= MIPS_CPU_PREFETCH; break; - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: icache_size = 1 << (12 + ((config & CONF_IC) >> 9)); c->icache.linesz = 16 << ((config & CONF_IB) >> 5); if (prid & 0x3) @@ -1242,7 +1248,7 @@ static void probe_pcache(void) c->dcache.waybit = 0; break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: config1 = read_c0_config1(); lsize = (config1 >> 19) & 7; if (lsize) @@ -1267,7 +1273,8 @@ static void probe_pcache(void) c->dcache.ways * c->dcache.linesz; c->dcache.waybit = 0; - if ((prid & PRID_REV_MASK) >= PRID_REV_LOONGSON3A_R2_0) + if ((c->processor_id & (PRID_IMP_MASK | PRID_REV_MASK)) >= + (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3A_R2_0)) c->options |= MIPS_CPU_PREFETCH; break; @@ -1452,7 +1459,7 @@ static void probe_pcache(void) c->dcache.flags &= ~MIPS_CACHE_ALIASES; break; - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: /* * LOONGSON2 has 4 way icache, but when using indexed cache op, * one op will act on all 4 ways @@ -1478,7 +1485,7 @@ static void probe_vcache(void) struct cpuinfo_mips *c = ¤t_cpu_data; unsigned int config2, lsize; - if (current_cpu_type() != CPU_LOONGSON3) + if (current_cpu_type() != CPU_LOONGSON64) return; config2 = read_c0_config2(); @@ -1653,11 +1660,11 @@ static void setup_scache(void) #endif return; - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: loongson2_sc_init(); return; - case CPU_LOONGSON3: + case CPU_LOONGSON64: loongson3_sc_init(); return; @@ -1926,7 +1933,7 @@ void r4k_cache_init(void) /* Optimization: an L2 flush implicitly flushes the L1 */ current_cpu_data.options |= MIPS_CPU_INCLUSIVE_CACHES; break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: /* Loongson-3 maintains cache coherency by hardware */ __flush_cache_all = cache_noop; __flush_cache_vmap = cache_noop; diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c index b7c8a9d79c35..686867270627 100644 --- a/arch/mips/mm/c-tx39.c +++ b/arch/mips/mm/c-tx39.c @@ -170,6 +170,7 @@ static void tx39_flush_cache_page(struct vm_area_struct *vma, unsigned long page int exec = vma->vm_flags & VM_EXEC; struct mm_struct *mm = vma->vm_mm; pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep; @@ -183,7 +184,8 @@ static void tx39_flush_cache_page(struct vm_area_struct *vma, unsigned long page page &= PAGE_MASK; pgdp = pgd_offset(mm, page); - pudp = pud_offset(pgdp, page); + p4dp = p4d_offset(pgdp, page); + pudp = pud_offset(p4dp, page); pmdp = pmd_offset(pudp, page); ptep = pte_offset(pmdp, page); diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index f589aa8f47d9..1e8d00793784 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -292,8 +292,9 @@ vmalloc_fault: * Do _not_ use "tsk" here. We might be inside * an interrupt in the middle of a task switch.. */ - int offset = __pgd_offset(address); + int offset = pgd_index(address); pgd_t *pgd, *pgd_k; + p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; pte_t *pte_k; @@ -305,8 +306,13 @@ vmalloc_fault: goto no_context; set_pgd(pgd, *pgd_k); - pud = pud_offset(pgd, address); - pud_k = pud_offset(pgd_k, address); + p4d = p4d_offset(pgd, address); + p4d_k = p4d_offset(pgd_k, address); + if (!p4d_present(*p4d_k)) + goto no_context; + + pud = pud_offset(p4d, address); + pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) goto no_context; diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c index cef152234312..77ffece9c270 100644 --- a/arch/mips/mm/hugetlbpage.c +++ b/arch/mips/mm/hugetlbpage.c @@ -25,11 +25,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (pud) pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -40,14 +42,18 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pgd = pgd_offset(mm, addr); if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) - pmd = pmd_offset(pud, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_present(*p4d)) { + pud = pud_offset(p4d, addr); + if (pud_present(*pud)) + pmd = pmd_offset(pud, addr); + } } return (pte_t *) pmd; } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 090fa653dfa9..50f9ed8c6c1b 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -239,9 +239,9 @@ void __init fixrange_init(unsigned long start, unsigned long end, unsigned long vaddr; vaddr = start; - i = __pgd_offset(vaddr); - j = __pud_offset(vaddr); - k = __pmd_offset(vaddr); + i = pgd_index(vaddr); + j = pud_index(vaddr); + k = pmd_index(vaddr); pgd = pgd_base + i; for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) { diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c index 1601d90b087b..8317f337a86e 100644 --- a/arch/mips/mm/ioremap.c +++ b/arch/mips/mm/ioremap.c @@ -78,11 +78,15 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr, flush_cache_all(); BUG_ON(address >= end); do { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; error = -ENOMEM; - pud = pud_alloc(&init_mm, dir, address); + p4d = p4d_alloc(&init_mm, dir, address); + if (!p4d) + break; + pud = pud_alloc(&init_mm, p4d, address); if (!pud) break; pmd = pmd_alloc(&init_mm, pud, address); diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index 56e4f8bffd4c..c5578897a4fa 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -187,7 +187,7 @@ static void set_prefetch_parameters(void) } break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: /* Loongson-3 only support the Pref_Load/Pref_Store. */ pref_bias_clear_store = 128; pref_bias_copy_load = 128; diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c index 6416a531a4c3..37c7a01427d2 100644 --- a/arch/mips/mm/pgtable-32.c +++ b/arch/mips/mm/pgtable-32.c @@ -56,6 +56,7 @@ void __init pagetable_init(void) pgd_t *pgd_base; #ifdef CONFIG_HIGHMEM pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -81,8 +82,9 @@ void __init pagetable_init(void) vaddr = PKMAP_BASE; fixrange_init(vaddr & PMD_MASK, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); - pgd = swapper_pg_dir + __pgd_offset(vaddr); - pud = pud_offset(pgd, vaddr); + pgd = swapper_pg_dir + pgd_index(vaddr); + p4d = p4d_offset(pgd, vaddr); + pud = pud_offset(p4d, vaddr); pmd = pmd_offset(pud, vaddr); pte = pte_offset_kernel(pmd, vaddr); pkmap_page_table = pte; diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index c13e46ced425..d7a9d5f211f0 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -35,10 +35,10 @@ extern void build_tlb_refill_handler(void); static inline void flush_micro_tlb(void) { switch (current_cpu_type()) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: write_c0_diag(LOONGSON_DIAG_ITLB); break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: write_c0_diag(LOONGSON_DIAG_ITLB | LOONGSON_DIAG_DTLB); break; default: @@ -295,6 +295,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) { unsigned long flags; pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep; @@ -320,7 +321,8 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) mtc0_tlbw_hazard(); tlb_probe(); tlb_probe_hazard(); - pudp = pud_offset(pgdp, address); + p4dp = p4d_offset(pgdp, address); + pudp = pud_offset(p4dp, address); pmdp = pmd_offset(pudp, address); idx = read_c0_index(); #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 41bb91f05688..344e6e9ea43b 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -571,8 +571,8 @@ void build_tlb_write_entry(u32 **p, struct uasm_label **l, case CPU_BMIPS4350: case CPU_BMIPS4380: case CPU_BMIPS5000: - case CPU_LOONGSON2: - case CPU_LOONGSON3: + case CPU_LOONGSON2EF: + case CPU_LOONGSON64: case CPU_R5500: if (m4kc_tlbp_war()) uasm_i_nop(p); @@ -1377,7 +1377,7 @@ static void build_r4000_tlb_refill_handler(void) switch (boot_cpu_type()) { default: if (sizeof(long) == 4) { - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: /* Loongson2 ebase is different than r4k, we have more space */ if ((p - tlb_handler) > 64) panic("TLB refill handler space exceeded"); diff --git a/arch/mips/oprofile/Makefile b/arch/mips/oprofile/Makefile index 011cf9f891e7..e10f216d0422 100644 --- a/arch/mips/oprofile/Makefile +++ b/arch/mips/oprofile/Makefile @@ -14,5 +14,5 @@ oprofile-$(CONFIG_CPU_MIPS64) += op_model_mipsxx.o oprofile-$(CONFIG_CPU_R10000) += op_model_mipsxx.o oprofile-$(CONFIG_CPU_SB1) += op_model_mipsxx.o oprofile-$(CONFIG_CPU_XLR) += op_model_mipsxx.o -oprofile-$(CONFIG_CPU_LOONGSON2) += op_model_loongson2.o -oprofile-$(CONFIG_CPU_LOONGSON3) += op_model_loongson3.o +oprofile-$(CONFIG_CPU_LOONGSON2EF) += op_model_loongson2.o +oprofile-$(CONFIG_CPU_LOONGSON64) += op_model_loongson3.o diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c index 2f33992f6dff..03db268cba5c 100644 --- a/arch/mips/oprofile/common.c +++ b/arch/mips/oprofile/common.c @@ -93,7 +93,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) case CPU_P5600: case CPU_I6400: case CPU_M5150: - case CPU_LOONGSON1: + case CPU_LOONGSON32: case CPU_SB1: case CPU_SB1A: case CPU_R10000: @@ -104,10 +104,10 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) lmodel = &op_model_mipsxx_ops; break; - case CPU_LOONGSON2: + case CPU_LOONGSON2EF: lmodel = &op_model_loongson2_ops; break; - case CPU_LOONGSON3: + case CPU_LOONGSON64: lmodel = &op_model_loongson3_ops; break; }; diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index 96c13a0ab078..a537bf98912c 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -420,7 +420,7 @@ static int __init mipsxx_init(void) op_model_mipsxx_ops.cpu_type = "mips/sb1"; break; - case CPU_LOONGSON1: + case CPU_LOONGSON32: op_model_mipsxx_ops.cpu_type = "mips/loongson1"; break; diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile index d6de4cb2e31c..342ce10ef593 100644 --- a/arch/mips/pci/Makefile +++ b/arch/mips/pci/Makefile @@ -35,7 +35,7 @@ obj-$(CONFIG_LASAT) += pci-lasat.o obj-$(CONFIG_MIPS_COBALT) += fixup-cobalt.o obj-$(CONFIG_LEMOTE_FULOONG2E) += fixup-fuloong2e.o ops-loongson2.o obj-$(CONFIG_LEMOTE_MACH2F) += fixup-lemote2f.o ops-loongson2.o -obj-$(CONFIG_LOONGSON_MACH3X) += fixup-loongson3.o ops-loongson3.o +obj-$(CONFIG_MACH_LOONGSON64) += fixup-loongson3.o ops-loongson3.o obj-$(CONFIG_MIPS_MALTA) += fixup-malta.o pci-malta.o obj-$(CONFIG_PMC_MSP7120_GW) += fixup-pmcmsp.o ops-pmcmsp.o obj-$(CONFIG_PMC_MSP7120_EVAL) += fixup-pmcmsp.o ops-pmcmsp.o diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c index 441eb9383b20..8e26b120f994 100644 --- a/arch/mips/pci/pci-ip27.c +++ b/arch/mips/pci/pci-ip27.c @@ -7,21 +7,13 @@ * Copyright (C) 1999, 2000, 04 Ralf Baechle (ralf@linux-mips.org) * Copyright (C) 1999, 2000 Silicon Graphics, Inc. */ +#include <asm/sn/addrs.h> +#include <asm/sn/types.h> +#include <asm/sn/klconfig.h> +#include <asm/sn/hub.h> +#include <asm/sn/ioc3.h> #include <asm/pci/bridge.h> -dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - struct pci_dev *pdev = to_pci_dev(dev); - struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus); - - return bc->baddr + paddr; -} - -phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr & ~(0xffUL << 56); -} - #ifdef CONFIG_NUMA int pcibus_to_node(struct pci_bus *bus) { @@ -31,3 +23,20 @@ int pcibus_to_node(struct pci_bus *bus) } EXPORT_SYMBOL(pcibus_to_node); #endif /* CONFIG_NUMA */ + +static void ip29_fixup_phy(struct pci_dev *dev) +{ + int nasid = pcibus_to_node(dev->bus); + u32 sid; + + if (nasid != 1) + return; /* only needed on second module */ + + /* enable ethernet PHY on IP29 systemboard */ + pci_read_config_dword(dev, PCI_SUBSYSTEM_VENDOR_ID, &sid); + if (sid == (PCI_VENDOR_ID_SGI | (IOC3_SUBSYS_IP29_SYSBOARD) << 16)) + REMOTE_HUB_S(nasid, MD_LED0, 0x09); +} + +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC3, + ip29_fixup_phy); diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c index 7b4d40354ee7..5c1a196be0c5 100644 --- a/arch/mips/pci/pci-xtalk-bridge.c +++ b/arch/mips/pci/pci-xtalk-bridge.c @@ -11,16 +11,38 @@ #include <linux/dma-direct.h> #include <linux/platform_device.h> #include <linux/platform_data/xtalk-bridge.h> +#include <linux/nvmem-consumer.h> +#include <linux/crc16.h> #include <asm/pci/bridge.h> #include <asm/paccess.h> #include <asm/sn/irq_alloc.h> +#include <asm/sn/ioc3.h> + +#define CRC16_INIT 0 +#define CRC16_VALID 0xb001 + +/* + * Common phys<->dma mapping for platforms using pci xtalk bridge + */ +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus); + + return bc->baddr + paddr; +} + +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr & ~(0xffUL << 56); +} /* * Most of the IOC3 PCI config register aren't present * we emulate what is needed for a normal PCI enumeration */ -static int ioc3_cfg_rd(void *addr, int where, int size, u32 *value) +static int ioc3_cfg_rd(void *addr, int where, int size, u32 *value, u32 sid) { u32 cf, shift, mask; @@ -30,6 +52,9 @@ static int ioc3_cfg_rd(void *addr, int where, int size, u32 *value) if (get_dbe(cf, (u32 *)addr)) return PCIBIOS_DEVICE_NOT_FOUND; break; + case 0x2c: + cf = sid; + break; case 0x3c: /* emulate sane interrupt pin value */ cf = 0x00000100; @@ -111,7 +136,8 @@ static int pci_conf0_read_config(struct pci_bus *bus, unsigned int devfn, */ if (cf == (PCI_VENDOR_ID_SGI | (PCI_DEVICE_ID_SGI_IOC3 << 16))) { addr = &bridge->b_type0_cfg_dev[slot].f[fn].l[where >> 2]; - return ioc3_cfg_rd(addr, where, size, value); + return ioc3_cfg_rd(addr, where, size, value, + bc->ioc3_sid[slot]); } addr = &bridge->b_type0_cfg_dev[slot].f[fn].c[where ^ (4 - size)]; @@ -149,7 +175,8 @@ static int pci_conf1_read_config(struct pci_bus *bus, unsigned int devfn, */ if (cf == (PCI_VENDOR_ID_SGI | (PCI_DEVICE_ID_SGI_IOC3 << 16))) { addr = &bridge->b_type1_cfg.c[(fn << 8) | (where & ~3)]; - return ioc3_cfg_rd(addr, where, size, value); + return ioc3_cfg_rd(addr, where, size, value, + bc->ioc3_sid[slot]); } addr = &bridge->b_type1_cfg.c[(fn << 8) | (where ^ (4 - size))]; @@ -279,16 +306,15 @@ static int bridge_set_affinity(struct irq_data *d, const struct cpumask *mask, struct bridge_irq_chip_data *data = d->chip_data; int bit = d->parent_data->hwirq; int pin = d->hwirq; - nasid_t nasid; int ret, cpu; ret = irq_chip_set_affinity_parent(d, mask, force); if (ret >= 0) { cpu = cpumask_first_and(mask, cpu_online_mask); - nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu)); + data->nasid = cpu_to_node(cpu); bridge_write(data->bc, b_int_addr[pin].addr, (((data->bc->intr_addr >> 30) & 0x30000) | - bit | (nasid << 8))); + bit | (data->nasid << 8))); bridge_read(data->bc, b_wid_tflush); } return ret; @@ -426,6 +452,117 @@ static int bridge_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return irq; } +#define IOC3_SID(sid) (PCI_VENDOR_ID_SGI | ((sid) << 16)) + +static void bridge_setup_ip27_baseio6g(struct bridge_controller *bc) +{ + bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP27_BASEIO6G); + bc->ioc3_sid[6] = IOC3_SID(IOC3_SUBSYS_IP27_MIO); +} + +static void bridge_setup_ip27_baseio(struct bridge_controller *bc) +{ + bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP27_BASEIO); +} + +static void bridge_setup_ip29_baseio(struct bridge_controller *bc) +{ + bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP29_SYSBOARD); +} + +static void bridge_setup_ip30_sysboard(struct bridge_controller *bc) +{ + bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP30_SYSBOARD); +} + +static void bridge_setup_menet(struct bridge_controller *bc) +{ + bc->ioc3_sid[0] = IOC3_SID(IOC3_SUBSYS_MENET); + bc->ioc3_sid[1] = IOC3_SID(IOC3_SUBSYS_MENET); + bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_MENET); + bc->ioc3_sid[3] = IOC3_SID(IOC3_SUBSYS_MENET4); +} + +#define BRIDGE_BOARD_SETUP(_partno, _setup) \ + { .match = _partno, .setup = _setup } + +static const struct { + char *match; + void (*setup)(struct bridge_controller *bc); +} bridge_ioc3_devid[] = { + BRIDGE_BOARD_SETUP("030-0734-", bridge_setup_ip27_baseio6g), + BRIDGE_BOARD_SETUP("030-0880-", bridge_setup_ip27_baseio6g), + BRIDGE_BOARD_SETUP("030-1023-", bridge_setup_ip27_baseio), + BRIDGE_BOARD_SETUP("030-1124-", bridge_setup_ip27_baseio), + BRIDGE_BOARD_SETUP("030-1025-", bridge_setup_ip29_baseio), + BRIDGE_BOARD_SETUP("030-1244-", bridge_setup_ip29_baseio), + BRIDGE_BOARD_SETUP("030-1389-", bridge_setup_ip29_baseio), + BRIDGE_BOARD_SETUP("030-0887-", bridge_setup_ip30_sysboard), + BRIDGE_BOARD_SETUP("030-1467-", bridge_setup_ip30_sysboard), + BRIDGE_BOARD_SETUP("030-0873-", bridge_setup_menet), +}; + +static void bridge_setup_board(struct bridge_controller *bc, char *partnum) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(bridge_ioc3_devid); i++) + if (!strncmp(partnum, bridge_ioc3_devid[i].match, + strlen(bridge_ioc3_devid[i].match))) { + bridge_ioc3_devid[i].setup(bc); + } +} + +static int bridge_nvmem_match(struct device *dev, const void *data) +{ + const char *name = dev_name(dev); + const char *prefix = data; + + if (strlen(name) < strlen(prefix)) + return 0; + + return memcmp(prefix, dev_name(dev), strlen(prefix)) == 0; +} + +static int bridge_get_partnum(u64 baddr, char *partnum) +{ + struct nvmem_device *nvmem; + char prefix[24]; + u8 prom[64]; + int i, j; + int ret; + + snprintf(prefix, sizeof(prefix), "bridge-%012llx-0b-", baddr); + + nvmem = nvmem_device_find(prefix, bridge_nvmem_match); + if (IS_ERR(nvmem)) + return PTR_ERR(nvmem); + + ret = nvmem_device_read(nvmem, 0, 64, prom); + nvmem_device_put(nvmem); + + if (ret != 64) + return ret; + + if (crc16(CRC16_INIT, prom, 32) != CRC16_VALID || + crc16(CRC16_INIT, prom + 32, 32) != CRC16_VALID) + return -EINVAL; + + /* Assemble part number */ + j = 0; + for (i = 0; i < 19; i++) + if (prom[i + 11] != ' ') + partnum[j++] = prom[i + 11]; + + for (i = 0; i < 6; i++) + if (prom[i + 32] != ' ') + partnum[j++] = prom[i + 32]; + + partnum[j] = 0; + + return 0; +} + static int bridge_probe(struct platform_device *pdev) { struct xtalk_bridge_platform_data *bd = dev_get_platdata(&pdev->dev); @@ -434,9 +571,14 @@ static int bridge_probe(struct platform_device *pdev) struct pci_host_bridge *host; struct irq_domain *domain, *parent; struct fwnode_handle *fn; + char partnum[26]; int slot; int err; + /* get part number from one wire prom */ + if (bridge_get_partnum(virt_to_phys((void *)bd->bridge_addr), partnum)) + return -EPROBE_DEFER; /* not available yet */ + parent = irq_get_default_host(); if (!parent) return -ENODEV; @@ -517,6 +659,8 @@ static int bridge_probe(struct platform_device *pdev) } bridge_read(bc, b_wid_tflush); /* wait until Bridge PIO complete */ + bridge_setup_board(bc, partnum); + host->dev.parent = dev; host->sysdata = bc; host->busnr = 0; diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c index 3340a5530de3..a15e29dfc7b3 100644 --- a/arch/mips/power/cpu.c +++ b/arch/mips/power/cpu.c @@ -19,8 +19,8 @@ void save_processor_state(void) if (is_fpu_owner()) save_fp(current); - if (cpu_has_dsp) - save_dsp(current); + + save_dsp(current); } void restore_processor_state(void) @@ -29,8 +29,8 @@ void restore_processor_state(void) if (is_fpu_owner()) restore_fp(current); - if (cpu_has_dsp) - restore_dsp(current); + + restore_dsp(current); } int pfn_is_nosave(unsigned long pfn) diff --git a/arch/mips/sgi-ip22/ip22-mc.c b/arch/mips/sgi-ip22/ip22-mc.c index 1944d41507ef..74e5b9e27d6c 100644 --- a/arch/mips/sgi-ip22/ip22-mc.c +++ b/arch/mips/sgi-ip22/ip22-mc.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/export.h> #include <linux/kernel.h> +#include <linux/memblock.h> #include <linux/spinlock.h> #include <asm/io.h> @@ -40,70 +41,36 @@ static inline unsigned int get_bank_config(int bank) return bank % 2 ? res & 0xffff : res >> 16; } -struct mem { - unsigned long addr; - unsigned long size; -}; - +#if defined(CONFIG_SGI_IP28) || defined(CONFIG_32BIT) +static void __init probe_memory(void) +{ + /* prom detects all usable memory */ +} +#else /* - * Detect installed memory, do some sanity checks and notify kernel about it + * Detect installed memory, which PROM misses */ static void __init probe_memory(void) { - int i, j, found, cnt = 0; - struct mem bank[4]; - struct mem space[2] = {{SGIMC_SEG0_BADDR, 0}, {SGIMC_SEG1_BADDR, 0}}; + unsigned long addr, size; + int i; printk(KERN_INFO "MC: Probing memory configuration:\n"); - for (i = 0; i < ARRAY_SIZE(bank); i++) { + for (i = 0; i < 4; i++) { unsigned int tmp = get_bank_config(i); if (!(tmp & SGIMC_MCONFIG_BVALID)) continue; - bank[cnt].size = get_bank_size(tmp); - bank[cnt].addr = get_bank_addr(tmp); + size = get_bank_size(tmp); + addr = get_bank_addr(tmp); printk(KERN_INFO " bank%d: %3ldM @ %08lx\n", - i, bank[cnt].size / 1024 / 1024, bank[cnt].addr); - cnt++; - } + i, size / 1024 / 1024, addr); - /* And you thought bubble sort is dead algorithm... */ - do { - unsigned long addr, size; - - found = 0; - for (i = 1; i < cnt; i++) - if (bank[i-1].addr > bank[i].addr) { - addr = bank[i].addr; - size = bank[i].size; - bank[i].addr = bank[i-1].addr; - bank[i].size = bank[i-1].size; - bank[i-1].addr = addr; - bank[i-1].size = size; - found = 1; - } - } while (found); - - /* Figure out how are memory banks mapped into spaces */ - for (i = 0; i < cnt; i++) { - found = 0; - for (j = 0; j < ARRAY_SIZE(space) && !found; j++) - if (space[j].addr + space[j].size == bank[i].addr) { - space[j].size += bank[i].size; - found = 1; - } - /* There is either hole or overlapping memory */ - if (!found) - printk(KERN_CRIT "MC: Memory configuration mismatch " - "(%08lx), expect Bus Error soon\n", - bank[i].addr); + if (addr >= SGIMC_SEG1_BADDR) + memblock_add(addr, size); } - - for (i = 0; i < ARRAY_SIZE(space); i++) - if (space[i].size) - add_memory_region(space[i].addr, space[i].size, - BOOT_MEM_RAM); } +#endif void __init sgimc_init(void) { @@ -205,10 +172,9 @@ void __init sgimc_init(void) probe_memory(); } -void __init prom_meminit(void) {} -void __init prom_free_prom_memory(void) -{ #ifdef CONFIG_SGI_IP28 +void __init prom_cleanup(void) +{ u32 mconfig1; unsigned long flags; spinlock_t lock; @@ -233,5 +199,5 @@ void __init prom_free_prom_memory(void) sgimc->mconfig1 = mconfig1; iob(); spin_unlock_irqrestore(&lock, flags); -#endif } +#endif diff --git a/arch/mips/sgi-ip27/Kconfig b/arch/mips/sgi-ip27/Kconfig index ef3847e7aee0..e5b6cadbec85 100644 --- a/arch/mips/sgi-ip27/Kconfig +++ b/arch/mips/sgi-ip27/Kconfig @@ -38,10 +38,3 @@ config REPLICATE_KTEXT Say Y here to enable replicating the kernel text across multiple nodes in a NUMA cluster. This trades memory for speed. -config REPLICATE_EXHANDLERS - bool "Exception handler replication support" - depends on SGI_IP27 - help - Say Y here to enable replicating the kernel exception handlers - across multiple nodes in a NUMA cluster. This trades memory for - speed. diff --git a/arch/mips/sgi-ip27/ip27-common.h b/arch/mips/sgi-ip27/ip27-common.h new file mode 100644 index 000000000000..3ffbcf9bfd41 --- /dev/null +++ b/arch/mips/sgi-ip27/ip27-common.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __IP27_COMMON_H +#define __IP27_COMMON_H + +extern void ip27_reboot_setup(void); +extern void hub_rt_clock_event_init(void); +extern const struct plat_smp_ops ip27_smp_ops; + +#endif /* __IP27_COMMON_H */ diff --git a/arch/mips/sgi-ip27/ip27-hubio.c b/arch/mips/sgi-ip27/ip27-hubio.c index 6ebb8845a77c..a538d0ceb61d 100644 --- a/arch/mips/sgi-ip27/ip27-hubio.c +++ b/arch/mips/sgi-ip27/ip27-hubio.c @@ -25,10 +25,9 @@ static int force_fire_and_forget = 1; * @size: size of the PIO mapping * **/ -unsigned long hub_pio_map(cnodeid_t cnode, xwidgetnum_t widget, +unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget, unsigned long xtalk_addr, size_t size) { - nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode); unsigned i; /* use small-window mapping if possible */ @@ -44,7 +43,7 @@ unsigned long hub_pio_map(cnodeid_t cnode, xwidgetnum_t widget, xtalk_addr &= ~(BWIN_SIZE-1); for (i = 0; i < HUB_NUM_BIG_WINDOW; i++) { - if (test_and_set_bit(i, hub_data(cnode)->h_bigwin_used)) + if (test_and_set_bit(i, hub_data(nasid)->h_bigwin_used)) continue; /* @@ -171,13 +170,12 @@ static void hub_set_piomode(nasid_t nasid) * * @hub: hubinfo structure for our hub */ -void hub_pio_init(cnodeid_t cnode) +void hub_pio_init(nasid_t nasid) { - nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode); unsigned i; /* initialize big window piomaps for this hub */ - bitmap_zero(hub_data(cnode)->h_bigwin_used, HUB_NUM_BIG_WINDOW); + bitmap_zero(hub_data(nasid)->h_bigwin_used, HUB_NUM_BIG_WINDOW); for (i = 0; i < HUB_NUM_BIG_WINDOW; i++) IIO_ITTE_DISABLE(nasid, i); diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c index 59d5375c9021..f597e1ee2df7 100644 --- a/arch/mips/sgi-ip27/ip27-init.c +++ b/arch/mips/sgi-ip27/ip27-init.c @@ -13,9 +13,11 @@ #include <linux/mm.h> #include <linux/export.h> #include <linux/cpumask.h> +#include <asm/bootinfo.h> #include <asm/cpu.h> #include <asm/io.h> #include <asm/pgtable.h> +#include <asm/sgialib.h> #include <asm/time.h> #include <asm/sn/types.h> #include <asm/sn/sn0/addrs.h> @@ -36,30 +38,23 @@ #include <asm/sn/sn0/ip27.h> #include <asm/sn/mapped_kernel.h> +#include "ip27-common.h" + #define CPU_NONE (cpuid_t)-1 -static DECLARE_BITMAP(hub_init_mask, MAX_COMPACT_NODES); +static DECLARE_BITMAP(hub_init_mask, MAX_NUMNODES); nasid_t master_nasid = INVALID_NASID; -cnodeid_t nasid_to_compact_node[MAX_NASIDS]; -nasid_t compact_to_nasid_node[MAX_COMPACT_NODES]; -cnodeid_t cpuid_to_compact_node[MAXCPUS]; - -EXPORT_SYMBOL(nasid_to_compact_node); - struct cpuinfo_ip27 sn_cpu_info[NR_CPUS]; EXPORT_SYMBOL_GPL(sn_cpu_info); -extern void pcibr_setup(cnodeid_t); - -static void per_hub_init(cnodeid_t cnode) +static void per_hub_init(nasid_t nasid) { - struct hub_data *hub = hub_data(cnode); - nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode); + struct hub_data *hub = hub_data(nasid); cpumask_set_cpu(smp_processor_id(), &hub->h_cpus); - if (test_and_set_bit(cnode, hub_init_mask)) + if (test_and_set_bit(nasid, hub_init_mask)) return; /* * Set CRB timeout at 5ms, (< PI timeout of 10ms) @@ -67,40 +62,31 @@ static void per_hub_init(cnodeid_t cnode) REMOTE_HUB_S(nasid, IIO_ICTP, 0x800); REMOTE_HUB_S(nasid, IIO_ICTO, 0xff); - hub_rtc_init(cnode); + hub_rtc_init(nasid); -#ifdef CONFIG_REPLICATE_EXHANDLERS - /* - * If this is not a headless node initialization, - * copy over the caliased exception handlers. - */ - if (get_compact_nodeid() == cnode) { - extern char except_vec2_generic, except_vec3_generic; - extern void build_tlb_refill_handler(void); - - memcpy((void *)(CKSEG0 + 0x100), &except_vec2_generic, 0x80); - memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x80); - build_tlb_refill_handler(); - memcpy((void *)(CKSEG0 + 0x100), (void *) CKSEG0, 0x80); - memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x100); + if (nasid) { + /* copy exception handlers from first node to current node */ + memcpy((void *)NODE_OFFSET_TO_K0(nasid, 0), + (void *)CKSEG0, 0x200); __flush_cache_all(); + /* switch to node local exception handlers */ + REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K); } -#endif } void per_cpu_init(void) { int cpu = smp_processor_id(); int slice = LOCAL_HUB_L(PI_CPU_NUM); - cnodeid_t cnode = get_compact_nodeid(); - struct hub_data *hub = hub_data(cnode); + nasid_t nasid = get_nasid(); + struct hub_data *hub = hub_data(nasid); if (test_and_set_bit(slice, &hub->slice_map)) return; clear_c0_status(ST0_IM); - per_hub_init(cnode); + per_hub_init(nasid); cpu_time_init(); install_ipi(); @@ -122,21 +108,13 @@ get_nasid(void) >> NSRI_NODEID_SHFT); } -/* - * Map the physical node id to a virtual node id (virtual node ids are contiguous). - */ -cnodeid_t get_compact_nodeid(void) -{ - return NASID_TO_COMPACT_NODEID(get_nasid()); -} - -extern void ip27_reboot_setup(void); - void __init plat_mem_setup(void) { u64 p, e, n_mode; nasid_t nid; + register_smp_ops(&ip27_smp_ops); + ip27_reboot_setup(); /* @@ -175,3 +153,15 @@ void __init plat_mem_setup(void) ioport_resource.end = ~0UL; set_io_port_base(IO_BASE); } + +const char *get_system_type(void) +{ + return "SGI Origin"; +} + +void __init prom_init(void) +{ + prom_init_cmdline(fw_arg0, (LONG *)fw_arg1); + prom_meminit(); +} + diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 37be04975831..c72ae330ea93 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -73,7 +73,10 @@ static void setup_hub_mask(struct hub_irq_data *hd, const struct cpumask *mask) int cpu; cpu = cpumask_first_and(mask, cpu_online_mask); - nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu)); + if (cpu >= nr_cpu_ids) + cpu = cpumask_any(cpu_online_mask); + + nasid = cpu_to_node(cpu); hd->cpu = cpu; if (!cputoslice(cpu)) { hd->irq_mask[0] = REMOTE_HUB_PTR(nasid, PI_INT_MASK0_A); @@ -137,8 +140,9 @@ static int hub_domain_alloc(struct irq_domain *domain, unsigned int virq, handle_level_irq, NULL, NULL); /* use CPU connected to nearest hub */ - hub = hub_data(NASID_TO_COMPACT_NODEID(info->nasid)); + hub = hub_data(info->nasid); setup_hub_mask(hd, &hub->h_cpus); + info->nasid = cpu_to_node(hd->cpu); /* Make sure it's not already pending when we connect it. */ REMOTE_HUB_CLR_INTR(info->nasid, swlevel); diff --git a/arch/mips/sgi-ip27/ip27-klconfig.c b/arch/mips/sgi-ip27/ip27-klconfig.c index 41171ff0c75e..6cb2160e7689 100644 --- a/arch/mips/sgi-ip27/ip27-klconfig.c +++ b/arch/mips/sgi-ip27/ip27-klconfig.c @@ -73,11 +73,6 @@ lboard_t *find_lboard_class(lboard_t *start, unsigned char brd_type) return (lboard_t *)NULL; } -cnodeid_t get_cpu_cnode(cpuid_t cpu) -{ - return CPUID_TO_COMPACT_NODEID(cpu); -} - klcpu_t *nasid_slice_to_cpuinfo(nasid_t nasid, int slice) { lboard_t *brd; @@ -102,19 +97,14 @@ klcpu_t *sn_get_cpuinfo(cpuid_t cpu) nasid_t nasid; int slice; klcpu_t *acpu; - gda_t *gdap = GDA; - cnodeid_t cnode; if (!(cpu < MAXCPUS)) { printk("sn_get_cpuinfo: illegal cpuid 0x%lx\n", cpu); return NULL; } - cnode = get_cpu_cnode(cpu); - if (cnode == INVALID_CNODEID) - return NULL; - - if ((nasid = gdap->g_nasidtable[cnode]) == INVALID_NASID) + nasid = cputonasid(cpu); + if (nasid == INVALID_NASID) return NULL; for (slice = 0; slice < CPUS_PER_NODE; slice++) { diff --git a/arch/mips/sgi-ip27/ip27-klnuma.c b/arch/mips/sgi-ip27/ip27-klnuma.c index a4f01328de62..ee1c6ff4aa00 100644 --- a/arch/mips/sgi-ip27/ip27-klnuma.c +++ b/arch/mips/sgi-ip27/ip27-klnuma.c @@ -38,13 +38,13 @@ void __init setup_replication_mask(void) #error Kernel replication works with mapped kernel support. No calias support. #endif { - cnodeid_t cnode; + nasid_t nasid; - for_each_online_node(cnode) { - if (cnode == 0) + for_each_online_node(nasid) { + if (nasid == 0) continue; /* Advertise that we have a copy of the kernel */ - cpumask_set_cpu(cnode, &ktext_repmask); + cpumask_set_cpu(nasid, &ktext_repmask); } } #endif @@ -85,7 +85,6 @@ static __init void copy_kernel(nasid_t dest_nasid) void __init replicate_kernel_text(void) { - cnodeid_t cnode; nasid_t client_nasid; nasid_t server_nasid; @@ -94,13 +93,12 @@ void __init replicate_kernel_text(void) /* Record where the master node should get its kernel text */ set_ktext_source(master_nasid, master_nasid); - for_each_online_node(cnode) { - if (cnode == 0) + for_each_online_node(client_nasid) { + if (client_nasid == 0) continue; - client_nasid = COMPACT_TO_NASID_NODEID(cnode); /* Check if this node should get a copy of the kernel */ - if (cpumask_test_cpu(cnode, &ktext_repmask)) { + if (cpumask_test_cpu(client_nasid, &ktext_repmask)) { server_nasid = client_nasid; copy_kernel(server_nasid); } @@ -115,17 +113,16 @@ void __init replicate_kernel_text(void) * data structures on the first couple of pages of the first slot of each * node. If this is the case, getfirstfree(node) > getslotstart(node, 0). */ -unsigned long node_getfirstfree(cnodeid_t cnode) +unsigned long node_getfirstfree(nasid_t nasid) { unsigned long loadbase = REP_BASE; - nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode); unsigned long offset; #ifdef CONFIG_MAPPED_KERNEL loadbase += 16777216; #endif offset = PAGE_ALIGN((unsigned long)(&_end)) - loadbase; - if ((cnode == 0) || (cpumask_test_cpu(cnode, &ktext_repmask))) + if ((nasid == 0) || (cpumask_test_cpu(nasid, &ktext_repmask))) return TO_NODE(nasid, offset) >> PAGE_SHIFT; else return KDM_TO_PHYS(PAGE_ALIGN(SYMMON_STK_ADDR(nasid, 0))) >> PAGE_SHIFT; diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index fb077a947575..563aad5e6398 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -33,7 +33,7 @@ #define SLOT_PFNSHIFT (SLOT_SHIFT - PAGE_SHIFT) #define PFN_NASIDSHFT (NASID_SHFT - PAGE_SHIFT) -struct node_data *__node_data[MAX_COMPACT_NODES]; +struct node_data *__node_data[MAX_NUMNODES]; EXPORT_SYMBOL(__node_data); @@ -44,23 +44,23 @@ static int is_fine_dirmode(void) return ((LOCAL_HUB_L(NI_STATUS_REV_ID) & NSRI_REGIONSIZE_MASK) >> NSRI_REGIONSIZE_SHFT) & REGIONSIZE_FINE; } -static u64 get_region(cnodeid_t cnode) +static u64 get_region(nasid_t nasid) { if (fine_mode) - return COMPACT_TO_NASID_NODEID(cnode) >> NASID_TO_FINEREG_SHFT; + return nasid >> NASID_TO_FINEREG_SHFT; else - return COMPACT_TO_NASID_NODEID(cnode) >> NASID_TO_COARSEREG_SHFT; + return nasid >> NASID_TO_COARSEREG_SHFT; } static u64 region_mask; static void gen_region_mask(u64 *region_mask) { - cnodeid_t cnode; + nasid_t nasid; (*region_mask) = 0; - for_each_online_node(cnode) { - (*region_mask) |= 1ULL << get_region(cnode); + for_each_online_node(nasid) { + (*region_mask) |= 1ULL << get_region(nasid); } } @@ -104,23 +104,18 @@ static void router_recurse(klrou_t *router_a, klrou_t *router_b, int depth) router_a->rou_rflag = 0; } -unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES]; +unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES]; EXPORT_SYMBOL(__node_distances); static int __init compute_node_distance(nasid_t nasid_a, nasid_t nasid_b) { klrou_t *router, *router_a = NULL, *router_b = NULL; lboard_t *brd, *dest_brd; - cnodeid_t cnode; nasid_t nasid; int port; /* Figure out which routers nodes in question are connected to */ - for_each_online_node(cnode) { - nasid = COMPACT_TO_NASID_NODEID(cnode); - - if (nasid == -1) continue; - + for_each_online_node(nasid) { brd = find_lboard_class((lboard_t *)KL_CONFIG_INFO(nasid), KLTYPE_ROUTER); @@ -176,19 +171,16 @@ static int __init compute_node_distance(nasid_t nasid_a, nasid_t nasid_b) static void __init init_topology_matrix(void) { - nasid_t nasid, nasid2; - cnodeid_t row, col; + nasid_t row, col; - for (row = 0; row < MAX_COMPACT_NODES; row++) - for (col = 0; col < MAX_COMPACT_NODES; col++) + for (row = 0; row < MAX_NUMNODES; row++) + for (col = 0; col < MAX_NUMNODES; col++) __node_distances[row][col] = -1; for_each_online_node(row) { - nasid = COMPACT_TO_NASID_NODEID(row); for_each_online_node(col) { - nasid2 = COMPACT_TO_NASID_NODEID(col); __node_distances[row][col] = - compute_node_distance(nasid, nasid2); + compute_node_distance(row, col); } } } @@ -196,12 +188,11 @@ static void __init init_topology_matrix(void) static void __init dump_topology(void) { nasid_t nasid; - cnodeid_t cnode; lboard_t *brd, *dest_brd; int port; int router_num = 0; klrou_t *router; - cnodeid_t row, col; + nasid_t row, col; pr_info("************** Topology ********************\n"); @@ -216,11 +207,7 @@ static void __init dump_topology(void) pr_cont("\n"); } - for_each_online_node(cnode) { - nasid = COMPACT_TO_NASID_NODEID(cnode); - - if (nasid == -1) continue; - + for_each_online_node(nasid) { brd = find_lboard_class((lboard_t *)KL_CONFIG_INFO(nasid), KLTYPE_ROUTER); @@ -254,21 +241,17 @@ static void __init dump_topology(void) } } -static unsigned long __init slot_getbasepfn(cnodeid_t cnode, int slot) +static unsigned long __init slot_getbasepfn(nasid_t nasid, int slot) { - nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode); - return ((unsigned long)nasid << PFN_NASIDSHFT) | (slot << SLOT_PFNSHIFT); } -static unsigned long __init slot_psize_compute(cnodeid_t node, int slot) +static unsigned long __init slot_psize_compute(nasid_t nasid, int slot) { - nasid_t nasid; lboard_t *brd; klmembnk_t *banks; unsigned long size; - nasid = COMPACT_TO_NASID_NODEID(node); /* Find the node board */ brd = find_lboard((lboard_t *)KL_CONFIG_INFO(nasid), KLTYPE_IP27); if (!brd) @@ -298,7 +281,7 @@ static unsigned long __init slot_psize_compute(cnodeid_t node, int slot) static void __init mlreset(void) { - int i; + nasid_t nasid; master_nasid = get_nasid(); fine_mode = is_fine_dirmode(); @@ -321,22 +304,14 @@ static void __init mlreset(void) /* * Set all nodes' calias sizes to 8k */ - for_each_online_node(i) { - nasid_t nasid; - - nasid = COMPACT_TO_NASID_NODEID(i); - + for_each_online_node(nasid) { /* * Always have node 0 in the region mask, otherwise * CALIAS accesses get exceptions since the hub * thinks it is a node 0 address. */ REMOTE_HUB_S(nasid, PI_REGION_PRESENT, (region_mask | 1)); -#ifdef CONFIG_REPLICATE_EXHANDLERS - REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K); -#else REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_0); -#endif #ifdef LATER /* @@ -354,7 +329,7 @@ static void __init szmem(void) { unsigned long slot_psize, slot0sz = 0, nodebytes; /* Hack to detect problem configs */ int slot; - cnodeid_t node; + nasid_t node; for_each_online_node(node) { nodebytes = 0; @@ -384,7 +359,7 @@ static void __init szmem(void) } } -static void __init node_mem_init(cnodeid_t node) +static void __init node_mem_init(nasid_t node) { unsigned long slot_firstpfn = slot_getbasepfn(node, 0); unsigned long slot_freepfn = node_getfirstfree(node); @@ -406,12 +381,8 @@ static void __init node_mem_init(cnodeid_t node) slot_freepfn += PFN_UP(sizeof(struct pglist_data) + sizeof(struct hub_data)); - free_bootmem_with_active_regions(node, end_pfn); - memblock_reserve(slot_firstpfn << PAGE_SHIFT, ((slot_freepfn - slot_firstpfn) << PAGE_SHIFT)); - - sparse_memory_present_with_active_regions(node); } /* @@ -431,19 +402,21 @@ static struct node_data null_node = { */ void __init prom_meminit(void) { - cnodeid_t node; + nasid_t node; mlreset(); szmem(); max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); - for (node = 0; node < MAX_COMPACT_NODES; node++) { + for (node = 0; node < MAX_NUMNODES; node++) { if (node_online(node)) { node_mem_init(node); continue; } __node_data[node] = &null_node; } + + memblocks_present(); } void __init prom_free_prom_memory(void) diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c index 3aae388561d9..daf3670d94e7 100644 --- a/arch/mips/sgi-ip27/ip27-nmi.c +++ b/arch/mips/sgi-ip27/ip27-nmi.c @@ -17,8 +17,6 @@ #define NODE_NUM_CPUS(n) CPUS_PER_NODE #endif -#define CNODEID_NONE (cnodeid_t)-1 - typedef unsigned long machreg_t; static arch_spinlock_t nmi_lock = __ARCH_SPIN_LOCK_UNLOCKED; @@ -152,16 +150,10 @@ void nmi_dump_hub_irq(nasid_t nasid, int slice) * Copy the cpu registers which have been saved in the IP27prom format * into the eframe format for the node under consideration. */ -void nmi_node_eframe_save(cnodeid_t cnode) +void nmi_node_eframe_save(nasid_t nasid) { - nasid_t nasid; int slice; - /* Make sure that we have a valid node */ - if (cnode == CNODEID_NONE) - return; - - nasid = COMPACT_TO_NASID_NODEID(cnode); if (nasid == INVALID_NASID) return; @@ -178,10 +170,10 @@ void nmi_node_eframe_save(cnodeid_t cnode) void nmi_eframes_save(void) { - cnodeid_t cnode; + nasid_t nasid; - for_each_online_node(cnode) - nmi_node_eframe_save(cnode); + for_each_online_node(nasid) + nmi_node_eframe_save(nasid); } void diff --git a/arch/mips/sgi-ip27/ip27-reset.c b/arch/mips/sgi-ip27/ip27-reset.c index e44a15d4f573..74d078247e49 100644 --- a/arch/mips/sgi-ip27/ip27-reset.c +++ b/arch/mips/sgi-ip27/ip27-reset.c @@ -26,6 +26,8 @@ #include <asm/sn/gda.h> #include <asm/sn/sn0/hub.h> +#include "ip27-common.h" + void machine_restart(char *command) __noreturn; void machine_halt(void) __noreturn; void machine_power_off(void) __noreturn; @@ -45,8 +47,7 @@ static void ip27_machine_restart(char *command) #endif #if 0 for_each_online_node(i) - REMOTE_HUB_S(COMPACT_TO_NASID_NODEID(i), PROMOP_REG, - PROMOP_REBOOT); + REMOTE_HUB_S(i, PROMOP_REG, PROMOP_REBOOT); #else LOCAL_HUB_S(NI_PORT_RESET, NPR_PORTRESET | NPR_LOCALRESET); #endif @@ -61,8 +62,7 @@ static void ip27_machine_halt(void) smp_send_stop(); #endif for_each_online_node(i) - REMOTE_HUB_S(COMPACT_TO_NASID_NODEID(i), PROMOP_REG, - PROMOP_RESTART); + REMOTE_HUB_S(i, PROMOP_REG, PROMOP_RESTART); LOCAL_HUB_S(NI_PORT_RESET, NPR_PORTRESET | NPR_LOCALRESET); noreturn; } diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c index 20b81209c6b8..faa0244c8b0c 100644 --- a/arch/mips/sgi-ip27/ip27-smp.c +++ b/arch/mips/sgi-ip27/ip27-smp.c @@ -27,38 +27,19 @@ #include <asm/sn/sn0/hubio.h> #include <asm/sn/sn0/ip27.h> +#include "ip27-common.h" + /* * Takes as first input the PROM assigned cpu id, and the kernel * assigned cpu id as the second. */ -static void alloc_cpupda(cpuid_t cpu, int cpunum) +static void alloc_cpupda(nasid_t nasid, cpuid_t cpu, int cpunum) { - cnodeid_t node = get_cpu_cnode(cpu); - nasid_t nasid = COMPACT_TO_NASID_NODEID(node); - cputonasid(cpunum) = nasid; - sn_cpu_info[cpunum].p_nodeid = node; cputoslice(cpunum) = get_cpu_slice(cpu); } -static nasid_t get_actual_nasid(lboard_t *brd) -{ - klhub_t *hub; - - if (!brd) - return INVALID_NASID; - - /* find out if we are a completely disabled brd. */ - hub = (klhub_t *)find_first_component(brd, KLSTRUCT_HUB); - if (!hub) - return INVALID_NASID; - if (!(hub->hub_info.flags & KLINFO_ENABLE)) /* disabled node brd */ - return hub->hub_info.physid; - else - return brd->brd_nasid; -} - -static int do_cpumask(cnodeid_t cnode, nasid_t nasid, int highest) +static int do_cpumask(nasid_t nasid, int highest) { static int tot_cpus_found = 0; lboard_t *brd; @@ -72,16 +53,13 @@ static int do_cpumask(cnodeid_t cnode, nasid_t nasid, int highest) acpu = (klcpu_t *)find_first_component(brd, KLSTRUCT_CPU); while (acpu) { cpuid = acpu->cpu_info.virtid; - /* cnode is not valid for completely disabled brds */ - if (get_actual_nasid(brd) == brd->brd_nasid) - cpuid_to_compact_node[cpuid] = cnode; - if (cpuid > highest) - highest = cpuid; /* Only let it join in if it's marked enabled */ if ((acpu->cpu_info.flags & KLINFO_ENABLE) && (tot_cpus_found != NR_CPUS)) { + if (cpuid > highest) + highest = cpuid; set_cpu_possible(cpuid, true); - alloc_cpupda(cpuid, tot_cpus_found); + alloc_cpupda(nasid, cpuid, tot_cpus_found); cpus_found++; tot_cpus_found++; } @@ -103,29 +81,13 @@ void cpu_node_probe(void) int i, highest = 0; gda_t *gdap = GDA; - /* - * Initialize the arrays to invalid nodeid (-1) - */ - for (i = 0; i < MAX_COMPACT_NODES; i++) - compact_to_nasid_node[i] = INVALID_NASID; - for (i = 0; i < MAX_NASIDS; i++) - nasid_to_compact_node[i] = INVALID_CNODEID; - for (i = 0; i < MAXCPUS; i++) - cpuid_to_compact_node[i] = INVALID_CNODEID; - - /* - * MCD - this whole "compact node" stuff can probably be dropped, - * as we can handle sparse numbering now - */ nodes_clear(node_online_map); - for (i = 0; i < MAX_COMPACT_NODES; i++) { + for (i = 0; i < MAX_NUMNODES; i++) { nasid_t nasid = gdap->g_nasidtable[i]; if (nasid == INVALID_NASID) break; - compact_to_nasid_node[i] = nasid; - nasid_to_compact_node[nasid] = i; - node_set_online(num_online_nodes()); - highest = do_cpumask(i, nasid, highest); + node_set_online(nasid); + highest = do_cpumask(nasid, highest); } printk("Discovered %d cpus on %d nodes\n", highest + 1, num_online_nodes()); @@ -162,11 +124,10 @@ static void ip27_send_ipi_single(int destid, unsigned int action) irq += cputoslice(destid); /* - * Convert the compact hub number to the NASID to get the correct - * part of the address space. Then set the interrupt bit associated - * with the CPU we want to send the interrupt to. + * Set the interrupt bit associated with the CPU we want to + * send the interrupt to. */ - REMOTE_HUB_SEND_INTR(COMPACT_TO_NASID_NODEID(cpu_to_node(destid)), irq); + REMOTE_HUB_SEND_INTR(cpu_to_node(destid), irq); } static void ip27_send_ipi_mask(const struct cpumask *mask, unsigned int action) @@ -184,8 +145,6 @@ static void ip27_init_cpu(void) static void ip27_smp_finish(void) { - extern void hub_rt_clock_event_init(void); - hub_rt_clock_event_init(); local_irq_enable(); } @@ -208,23 +167,20 @@ static int ip27_boot_secondary(int cpu, struct task_struct *idle) static void __init ip27_smp_setup(void) { - cnodeid_t cnode; + nasid_t nasid; - for_each_online_node(cnode) { - if (cnode == 0) + for_each_online_node(nasid) { + if (nasid == 0) continue; - intr_clear_all(COMPACT_TO_NASID_NODEID(cnode)); + intr_clear_all(nasid); } replicate_kernel_text(); /* - * Assumption to be fixed: we're always booted on logical / physical - * processor 0. While we're always running on logical processor 0 - * this still means this is physical processor zero; it might for - * example be disabled in the firmware. + * PROM sets up system, that boot cpu is always first CPU on nasid 0 */ - alloc_cpupda(0, 0); + alloc_cpupda(0, 0, 0); } static void __init ip27_prepare_cpus(unsigned int max_cpus) diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c index 9b4b9ac621a3..17302bbfa7a6 100644 --- a/arch/mips/sgi-ip27/ip27-timer.c +++ b/arch/mips/sgi-ip27/ip27-timer.c @@ -38,6 +38,8 @@ #include <asm/sn/sn0/hubio.h> #include <asm/pci/bridge.h> +#include "ip27-common.h" + static int rt_next_event(unsigned long delta, struct clock_event_device *evt) { unsigned int cpu = smp_processor_id(); @@ -170,7 +172,7 @@ void cpu_time_init(void) printk("CPU %d clock is %dMHz.\n", smp_processor_id(), cpu->cpu_speed); } -void hub_rtc_init(cnodeid_t cnode) +void hub_rtc_init(nasid_t nasid) { /* @@ -178,7 +180,7 @@ void hub_rtc_init(cnodeid_t cnode) * If this is not the current node then it is a cpuless * node and timeouts will not happen there. */ - if (get_compact_nodeid() == cnode) { + if (get_nasid() == nasid) { LOCAL_HUB_S(PI_RT_EN_A, 1); LOCAL_HUB_S(PI_RT_EN_B, 1); LOCAL_HUB_S(PI_PROF_EN_A, 0); diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c index 4a1f0b0c29e2..5218b900f855 100644 --- a/arch/mips/sgi-ip27/ip27-xtalk.c +++ b/arch/mips/sgi-ip27/ip27-xtalk.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/smp.h> #include <linux/platform_device.h> +#include <linux/platform_data/sgi-w1.h> #include <linux/platform_data/xtalk-bridge.h> #include <asm/sn/addrs.h> #include <asm/sn/types.h> @@ -26,9 +27,35 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) { struct xtalk_bridge_platform_data *bd; + struct sgi_w1_platform_data *wd; struct platform_device *pdev; + struct resource w1_res; unsigned long offset; + offset = NODE_OFFSET(nasid); + + wd = kzalloc(sizeof(*wd), GFP_KERNEL); + if (!wd) + goto no_mem; + + snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx", + offset + (widget << SWIN_SIZE_BITS)); + + memset(&w1_res, 0, sizeof(w1_res)); + w1_res.start = offset + (widget << SWIN_SIZE_BITS) + + offsetof(struct bridge_regs, b_nic); + w1_res.end = w1_res.start + 3; + w1_res.flags = IORESOURCE_MEM; + + pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO); + if (!pdev) { + kfree(wd); + goto no_mem; + } + platform_device_add_resources(pdev, &w1_res, 1); + platform_device_add_data(pdev, wd, sizeof(*wd)); + platform_device_add(pdev); + bd = kzalloc(sizeof(*bd), GFP_KERNEL); if (!bd) goto no_mem; @@ -38,7 +65,6 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) goto no_mem; } - offset = NODE_OFFSET(nasid); bd->bridge_addr = RAW_NODE_SWIN_BASE(nasid, widget); bd->intr_addr = BIT_ULL(47) + 0x01800000 + PI_INT_PEND_MOD; @@ -46,14 +72,14 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) bd->masterwid = masterwid; bd->mem.name = "Bridge PCI MEM"; - bd->mem.start = offset + (widget << SWIN_SIZE_BITS); - bd->mem.end = bd->mem.start + SWIN_SIZE - 1; + bd->mem.start = offset + (widget << SWIN_SIZE_BITS) + BRIDGE_DEVIO0; + bd->mem.end = offset + (widget << SWIN_SIZE_BITS) + SWIN_SIZE - 1; bd->mem.flags = IORESOURCE_MEM; bd->mem_offset = offset; bd->io.name = "Bridge PCI IO"; - bd->io.start = offset + (widget << SWIN_SIZE_BITS); - bd->io.end = bd->io.start + SWIN_SIZE - 1; + bd->io.start = offset + (widget << SWIN_SIZE_BITS) + BRIDGE_DEVIO0; + bd->io.end = offset + (widget << SWIN_SIZE_BITS) + SWIN_SIZE - 1; bd->io.flags = IORESOURCE_IO; bd->io_offset = offset; @@ -81,6 +107,8 @@ static int probe_one_port(nasid_t nasid, int widget, int masterwid) bridge_platform_create(nasid, widget, masterwid); break; default: + pr_info("xtalk:n%d/%d unknown widget (0x%x)\n", + nasid, widget, partnum); break; } @@ -138,14 +166,12 @@ static int xbow_probe(nasid_t nasid) return 0; } -static void xtalk_probe_node(cnodeid_t nid) +static void xtalk_probe_node(nasid_t nasid) { volatile u64 hubreg; - nasid_t nasid; xwidget_part_num_t partnum; widgetreg_t widget_id; - nasid = COMPACT_TO_NASID_NODEID(nid); hubreg = REMOTE_HUB_L(nasid, IIO_LLP_CSR); /* check whether the link is up */ @@ -173,10 +199,10 @@ static void xtalk_probe_node(cnodeid_t nid) static int __init xtalk_init(void) { - cnodeid_t cnode; + nasid_t nasid; - for_each_online_node(cnode) - xtalk_probe_node(cnode); + for_each_online_node(nasid) + xtalk_probe_node(nasid); return 0; } diff --git a/arch/mips/sgi-ip30/Makefile b/arch/mips/sgi-ip30/Makefile new file mode 100644 index 000000000000..18cf561b3d61 --- /dev/null +++ b/arch/mips/sgi-ip30/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the IP30 specific kernel interface routines under Linux. +# + +obj-y := ip30-irq.o ip30-power.o ip30-setup.o ip30-timer.o ip30-xtalk.o + +obj-$(CONFIG_EARLY_PRINTK) += ip30-console.o +obj-$(CONFIG_SMP) += ip30-smp.o diff --git a/arch/mips/sgi-ip30/Platform b/arch/mips/sgi-ip30/Platform new file mode 100644 index 000000000000..2b5695c2049a --- /dev/null +++ b/arch/mips/sgi-ip30/Platform @@ -0,0 +1,8 @@ +# +# SGI-IP30 (Octane/Octane2) +# +ifdef CONFIG_SGI_IP30 +platform-$(CONFIG_SGI_IP30) += sgi-ip30/ +cflags-$(CONFIG_SGI_IP30) += -I$(srctree)/arch/mips/include/asm/mach-ip30 +load-$(CONFIG_SGI_IP30) += 0xa800000020004000 +endif diff --git a/arch/mips/sgi-ip30/ip30-common.h b/arch/mips/sgi-ip30/ip30-common.h new file mode 100644 index 000000000000..d2bcaee712f3 --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-common.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __IP30_COMMON_H +#define __IP30_COMMON_H + +extern struct plat_smp_ops ip30_smp_ops; +extern void __init ip30_per_cpu_init(void); + +#endif /* __IP30_COMMON_H */ diff --git a/arch/mips/sgi-ip30/ip30-console.c b/arch/mips/sgi-ip30/ip30-console.c new file mode 100644 index 000000000000..b91f8c4fdc78 --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-console.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/io.h> + +#include <asm/sn/ioc3.h> + +static inline struct ioc3_uartregs *console_uart(void) +{ + struct ioc3 *ioc3; + + ioc3 = (struct ioc3 *)((void *)(0x900000001f600000)); + return &ioc3->sregs.uarta; +} + +void prom_putchar(char c) +{ + struct ioc3_uartregs *uart = console_uart(); + + while ((readb(&uart->iu_lsr) & 0x20) == 0) + cpu_relax(); + + writeb(c, &uart->iu_thr); +} diff --git a/arch/mips/sgi-ip30/ip30-irq.c b/arch/mips/sgi-ip30/ip30-irq.c new file mode 100644 index 000000000000..d46655b914f1 --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-irq.c @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ip30-irq.c: Highlevel interrupt handling for IP30 architecture. + */ +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/percpu.h> +#include <linux/spinlock.h> +#include <linux/tick.h> +#include <linux/types.h> + +#include <asm/irq_cpu.h> +#include <asm/sgi/heart.h> + +struct heart_irq_data { + u64 *irq_mask; + int cpu; +}; + +static DECLARE_BITMAP(heart_irq_map, HEART_NUM_IRQS); + +static DEFINE_PER_CPU(unsigned long, irq_enable_mask); + +static inline int heart_alloc_int(void) +{ + int bit; + +again: + bit = find_first_zero_bit(heart_irq_map, HEART_NUM_IRQS); + if (bit >= HEART_NUM_IRQS) + return -ENOSPC; + + if (test_and_set_bit(bit, heart_irq_map)) + goto again; + + return bit; +} + +static void ip30_error_irq(struct irq_desc *desc) +{ + u64 pending, mask, cause, error_irqs, err_reg; + int cpu = smp_processor_id(); + int i; + + pending = heart_read(&heart_regs->isr); + mask = heart_read(&heart_regs->imr[cpu]); + cause = heart_read(&heart_regs->cause); + error_irqs = (pending & HEART_L4_INT_MASK & mask); + + /* Bail if there's nothing to process (how did we get here, then?) */ + if (unlikely(!error_irqs)) + return; + + /* Prevent any of the error IRQs from firing again. */ + heart_write(mask & ~(pending), &heart_regs->imr[cpu]); + + /* Ack all error IRQs. */ + heart_write(HEART_L4_INT_MASK, &heart_regs->clear_isr); + + /* + * If we also have a cause value, then something happened, so loop + * through the error IRQs and report a "heart attack" for each one + * and print the value of the HEART cause register. This is really + * primitive right now, but it should hopefully work until a more + * robust error handling routine can be put together. + * + * Refer to heart.h for the HC_* macros to work out the cause + * that got us here. + */ + if (cause) { + pr_alert("IP30: CPU%d: HEART ATTACK! ISR = 0x%.16llx, IMR = 0x%.16llx, CAUSE = 0x%.16llx\n", + cpu, pending, mask, cause); + + if (cause & HC_COR_MEM_ERR) { + err_reg = heart_read(&heart_regs->mem_err_addr); + pr_alert(" HEART_MEMERR_ADDR = 0x%.16llx\n", err_reg); + } + + /* i = 63; i >= 51; i-- */ + for (i = HEART_ERR_MASK_END; i >= HEART_ERR_MASK_START; i--) + if ((pending >> i) & 1) + pr_alert(" HEART Error IRQ #%d\n", i); + + /* XXX: Seems possible to loop forever here, so panic(). */ + panic("IP30: Fatal Error !\n"); + } + + /* Unmask the error IRQs. */ + heart_write(mask, &heart_regs->imr[cpu]); +} + +static void ip30_normal_irq(struct irq_desc *desc) +{ + int cpu = smp_processor_id(); + struct irq_domain *domain; + u64 pend, mask; + int irq; + + pend = heart_read(&heart_regs->isr); + mask = (heart_read(&heart_regs->imr[cpu]) & + (HEART_L0_INT_MASK | HEART_L1_INT_MASK | HEART_L2_INT_MASK)); + + pend &= mask; + if (unlikely(!pend)) + return; + +#ifdef CONFIG_SMP + if (pend & BIT_ULL(HEART_L2_INT_RESCHED_CPU_0)) { + heart_write(BIT_ULL(HEART_L2_INT_RESCHED_CPU_0), + &heart_regs->clear_isr); + scheduler_ipi(); + } else if (pend & BIT_ULL(HEART_L2_INT_RESCHED_CPU_1)) { + heart_write(BIT_ULL(HEART_L2_INT_RESCHED_CPU_1), + &heart_regs->clear_isr); + scheduler_ipi(); + } else if (pend & BIT_ULL(HEART_L2_INT_CALL_CPU_0)) { + heart_write(BIT_ULL(HEART_L2_INT_CALL_CPU_0), + &heart_regs->clear_isr); + generic_smp_call_function_interrupt(); + } else if (pend & BIT_ULL(HEART_L2_INT_CALL_CPU_1)) { + heart_write(BIT_ULL(HEART_L2_INT_CALL_CPU_1), + &heart_regs->clear_isr); + generic_smp_call_function_interrupt(); + } else +#endif + { + domain = irq_desc_get_handler_data(desc); + irq = irq_linear_revmap(domain, __ffs(pend)); + if (irq) + generic_handle_irq(irq); + else + spurious_interrupt(); + } +} + +static void ip30_ack_heart_irq(struct irq_data *d) +{ + heart_write(BIT_ULL(d->hwirq), &heart_regs->clear_isr); +} + +static void ip30_mask_heart_irq(struct irq_data *d) +{ + struct heart_irq_data *hd = irq_data_get_irq_chip_data(d); + unsigned long *mask = &per_cpu(irq_enable_mask, hd->cpu); + + clear_bit(d->hwirq, mask); + heart_write(*mask, &heart_regs->imr[hd->cpu]); +} + +static void ip30_mask_and_ack_heart_irq(struct irq_data *d) +{ + struct heart_irq_data *hd = irq_data_get_irq_chip_data(d); + unsigned long *mask = &per_cpu(irq_enable_mask, hd->cpu); + + clear_bit(d->hwirq, mask); + heart_write(*mask, &heart_regs->imr[hd->cpu]); + heart_write(BIT_ULL(d->hwirq), &heart_regs->clear_isr); +} + +static void ip30_unmask_heart_irq(struct irq_data *d) +{ + struct heart_irq_data *hd = irq_data_get_irq_chip_data(d); + unsigned long *mask = &per_cpu(irq_enable_mask, hd->cpu); + + set_bit(d->hwirq, mask); + heart_write(*mask, &heart_regs->imr[hd->cpu]); +} + +static int ip30_set_heart_irq_affinity(struct irq_data *d, + const struct cpumask *mask, bool force) +{ + struct heart_irq_data *hd = irq_data_get_irq_chip_data(d); + + if (!hd) + return -EINVAL; + + if (irqd_is_started(d)) + ip30_mask_and_ack_heart_irq(d); + + hd->cpu = cpumask_first_and(mask, cpu_online_mask); + + if (irqd_is_started(d)) + ip30_unmask_heart_irq(d); + + irq_data_update_effective_affinity(d, cpumask_of(hd->cpu)); + + return 0; +} + +static struct irq_chip heart_irq_chip = { + .name = "HEART", + .irq_ack = ip30_ack_heart_irq, + .irq_mask = ip30_mask_heart_irq, + .irq_mask_ack = ip30_mask_and_ack_heart_irq, + .irq_unmask = ip30_unmask_heart_irq, + .irq_set_affinity = ip30_set_heart_irq_affinity, +}; + +static int heart_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_alloc_info *info = arg; + struct heart_irq_data *hd; + int hwirq; + + if (nr_irqs > 1 || !info) + return -EINVAL; + + hd = kzalloc(sizeof(*hd), GFP_KERNEL); + if (!hd) + return -ENOMEM; + + hwirq = heart_alloc_int(); + if (hwirq < 0) { + kfree(hd); + return -EAGAIN; + } + irq_domain_set_info(domain, virq, hwirq, &heart_irq_chip, hd, + handle_level_irq, NULL, NULL); + + return 0; +} + +static void heart_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irqd; + + if (nr_irqs > 1) + return; + + irqd = irq_domain_get_irq_data(domain, virq); + clear_bit(irqd->hwirq, heart_irq_map); + if (irqd && irqd->chip_data) + kfree(irqd->chip_data); +} + +static const struct irq_domain_ops heart_domain_ops = { + .alloc = heart_domain_alloc, + .free = heart_domain_free, +}; + +void __init ip30_install_ipi(void) +{ + int cpu = smp_processor_id(); + unsigned long *mask = &per_cpu(irq_enable_mask, cpu); + + set_bit(HEART_L2_INT_RESCHED_CPU_0 + cpu, mask); + heart_write(BIT_ULL(HEART_L2_INT_RESCHED_CPU_0 + cpu), + &heart_regs->clear_isr); + set_bit(HEART_L2_INT_CALL_CPU_0 + cpu, mask); + heart_write(BIT_ULL(HEART_L2_INT_CALL_CPU_0 + cpu), + &heart_regs->clear_isr); + + heart_write(*mask, &heart_regs->imr[cpu]); +} + +void __init arch_init_irq(void) +{ + struct irq_domain *domain; + struct fwnode_handle *fn; + unsigned long *mask; + int i; + + mips_cpu_irq_init(); + + /* Mask all IRQs. */ + heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[0]); + heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[1]); + heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[2]); + heart_write(HEART_CLR_ALL_MASK, &heart_regs->imr[3]); + + /* Ack everything. */ + heart_write(HEART_ACK_ALL_MASK, &heart_regs->clear_isr); + + /* Enable specific HEART error IRQs for each CPU. */ + mask = &per_cpu(irq_enable_mask, 0); + *mask |= HEART_CPU0_ERR_MASK; + heart_write(*mask, &heart_regs->imr[0]); + mask = &per_cpu(irq_enable_mask, 1); + *mask |= HEART_CPU1_ERR_MASK; + heart_write(*mask, &heart_regs->imr[1]); + + /* + * Some HEART bits are reserved by hardware or by software convention. + * Mark these as reserved right away so they won't be accidentally + * used later. + */ + set_bit(HEART_L0_INT_GENERIC, heart_irq_map); + set_bit(HEART_L0_INT_FLOW_CTRL_HWTR_0, heart_irq_map); + set_bit(HEART_L0_INT_FLOW_CTRL_HWTR_1, heart_irq_map); + set_bit(HEART_L2_INT_RESCHED_CPU_0, heart_irq_map); + set_bit(HEART_L2_INT_RESCHED_CPU_1, heart_irq_map); + set_bit(HEART_L2_INT_CALL_CPU_0, heart_irq_map); + set_bit(HEART_L2_INT_CALL_CPU_1, heart_irq_map); + set_bit(HEART_L3_INT_TIMER, heart_irq_map); + + /* Reserve the error interrupts (#51 to #63). */ + for (i = HEART_L4_INT_XWID_ERR_9; i <= HEART_L4_INT_HEART_EXCP; i++) + set_bit(i, heart_irq_map); + + fn = irq_domain_alloc_named_fwnode("HEART"); + WARN_ON(fn == NULL); + if (!fn) + return; + domain = irq_domain_create_linear(fn, HEART_NUM_IRQS, + &heart_domain_ops, NULL); + WARN_ON(domain == NULL); + if (!domain) + return; + + irq_set_default_host(domain); + + irq_set_percpu_devid(IP30_HEART_L0_IRQ); + irq_set_chained_handler_and_data(IP30_HEART_L0_IRQ, ip30_normal_irq, + domain); + irq_set_percpu_devid(IP30_HEART_L1_IRQ); + irq_set_chained_handler_and_data(IP30_HEART_L1_IRQ, ip30_normal_irq, + domain); + irq_set_percpu_devid(IP30_HEART_L2_IRQ); + irq_set_chained_handler_and_data(IP30_HEART_L2_IRQ, ip30_normal_irq, + domain); + irq_set_percpu_devid(IP30_HEART_ERR_IRQ); + irq_set_chained_handler_and_data(IP30_HEART_ERR_IRQ, ip30_error_irq, + domain); +} diff --git a/arch/mips/sgi-ip30/ip30-power.c b/arch/mips/sgi-ip30/ip30-power.c new file mode 100644 index 000000000000..120b3f3d5108 --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-power.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ip30-power.c: Software powerdown and reset handling for IP30 architecture. + * + * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * 2014 Joshua Kinard <kumba@gentoo.org> + * 2009 Johannes Dickgreber <tanzy@gmx.de> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/notifier.h> +#include <linux/delay.h> +#include <linux/rtc/ds1685.h> +#include <linux/interrupt.h> +#include <linux/pm.h> + +#include <asm/reboot.h> +#include <asm/sgi/heart.h> + +static void __noreturn ip30_machine_restart(char *cmd) +{ + /* + * Execute HEART cold reset + * Yes, it's cold-HEARTed! + */ + heart_write((heart_read(&heart_regs->mode) | HM_COLD_RST), + &heart_regs->mode); + unreachable(); +} + +static int __init ip30_reboot_setup(void) +{ + _machine_restart = ip30_machine_restart; + + return 0; +} + +subsys_initcall(ip30_reboot_setup); diff --git a/arch/mips/sgi-ip30/ip30-setup.c b/arch/mips/sgi-ip30/ip30-setup.c new file mode 100644 index 000000000000..44b1607e964d --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-setup.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SGI IP30 miscellaneous setup bits. + * + * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * 2007 Joshua Kinard <kumba@gentoo.org> + * 2009 Johannes Dickgreber <tanzy@gmx.de> + */ + +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/percpu.h> +#include <linux/memblock.h> + +#include <asm/smp-ops.h> +#include <asm/sgialib.h> +#include <asm/time.h> +#include <asm/sgi/heart.h> + +#include "ip30-common.h" + +/* Structure of accessible HEART registers located in XKPHYS space. */ +struct ip30_heart_regs __iomem *heart_regs = HEART_XKPHYS_BASE; + +/* + * ARCS will report up to the first 1GB of + * memory if queried. Anything beyond that + * is marked as reserved. + */ +#define IP30_MAX_PROM_MEMORY _AC(0x40000000, UL) + +/* + * Memory in the Octane starts at 512MB + */ +#define IP30_MEMORY_BASE _AC(0x20000000, UL) + +/* + * If using ARCS to probe for memory, then + * remaining memory will start at this offset. + */ +#define IP30_REAL_MEMORY_START (IP30_MEMORY_BASE + IP30_MAX_PROM_MEMORY) + +#define MEM_SHIFT(x) ((x) >> 20) + +static void __init ip30_mem_init(void) +{ + unsigned long total_mem; + phys_addr_t addr; + phys_addr_t size; + u32 memcfg; + int i; + + total_mem = 0; + for (i = 0; i < HEART_MEMORY_BANKS; i++) { + memcfg = __raw_readl(&heart_regs->mem_cfg.l[i]); + if (!(memcfg & HEART_MEMCFG_VALID)) + continue; + + addr = memcfg & HEART_MEMCFG_ADDR_MASK; + addr <<= HEART_MEMCFG_UNIT_SHIFT; + addr += IP30_MEMORY_BASE; + size = memcfg & HEART_MEMCFG_SIZE_MASK; + size >>= HEART_MEMCFG_SIZE_SHIFT; + size += 1; + size <<= HEART_MEMCFG_UNIT_SHIFT; + + total_mem += size; + + if (addr >= IP30_REAL_MEMORY_START) + memblock_free(addr, size); + else if ((addr + size) > IP30_REAL_MEMORY_START) + memblock_free(IP30_REAL_MEMORY_START, + size - IP30_MAX_PROM_MEMORY); + } + pr_info("Detected %luMB of physical memory.\n", MEM_SHIFT(total_mem)); +} + +/** + * ip30_cpu_time_init - platform time initialization. + */ +static void __init ip30_cpu_time_init(void) +{ + int cpu = smp_processor_id(); + u64 heart_compare; + unsigned int start, end; + int time_diff; + + heart_compare = (heart_read(&heart_regs->count) + + (HEART_CYCLES_PER_SEC / 10)); + start = read_c0_count(); + while ((heart_read(&heart_regs->count) - heart_compare) & 0x800000) + cpu_relax(); + + end = read_c0_count(); + time_diff = (int)end - (int)start; + mips_hpt_frequency = time_diff * 10; + pr_info("IP30: CPU%d: %d MHz CPU detected.\n", cpu, + (mips_hpt_frequency * 2) / 1000000); +} + +void __init ip30_per_cpu_init(void) +{ + /* Disable all interrupts. */ + clear_c0_status(ST0_IM); + + ip30_cpu_time_init(); +#ifdef CONFIG_SMP + ip30_install_ipi(); +#endif + + enable_percpu_irq(IP30_HEART_L0_IRQ, IRQ_TYPE_NONE); + enable_percpu_irq(IP30_HEART_L1_IRQ, IRQ_TYPE_NONE); + enable_percpu_irq(IP30_HEART_L2_IRQ, IRQ_TYPE_NONE); + enable_percpu_irq(IP30_HEART_ERR_IRQ, IRQ_TYPE_NONE); +} + +/** + * plat_mem_setup - despite the name, misc setup happens here. + */ +void __init plat_mem_setup(void) +{ + ip30_mem_init(); + + /* XXX: Hard lock on /sbin/init if this flag isn't specified. */ + prom_flags |= PROM_FLAG_DONT_FREE_TEMP; + +#ifdef CONFIG_SMP + register_smp_ops(&ip30_smp_ops); +#else + ip30_per_cpu_init(); +#endif + + ioport_resource.start = 0; + ioport_resource.end = ~0UL; + set_io_port_base(IO_BASE); +} diff --git a/arch/mips/sgi-ip30/ip30-smp.c b/arch/mips/sgi-ip30/ip30-smp.c new file mode 100644 index 000000000000..4bfe654602b1 --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-smp.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ip30-smp.c: SMP on IP30 architecture. + * Based off of the original IP30 SMP code, with inspiration from ip27-smp.c + * and smp-bmips.c. + * + * Copyright (C) 2005-2007 Stanislaw Skowronek <skylark@unaligned.org> + * 2006-2007, 2014-2015 Joshua Kinard <kumba@gentoo.org> + * 2009 Johannes Dickgreber <tanzy@gmx.de> + */ + +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/sched/task_stack.h> + +#include <asm/time.h> +#include <asm/sgi/heart.h> + +#include "ip30-common.h" + +#define MPCONF_MAGIC 0xbaddeed2 +#define MPCONF_ADDR 0xa800000000000600L +#define MPCONF_SIZE 0x80 +#define MPCONF(x) (MPCONF_ADDR + (x) * MPCONF_SIZE) + +/* HEART can theoretically do 4 CPUs, but only 2 are physically possible */ +#define MP_NCPU 2 + +struct mpconf { + u32 magic; + u32 prid; + u32 physid; + u32 virtid; + u32 scachesz; + u16 fanloads; + u16 res; + void *launch; + void *rendezvous; + u64 res2[3]; + void *stackaddr; + void *lnch_parm; + void *rndv_parm; + u32 idleflag; +}; + +static void ip30_smp_send_ipi_single(int cpu, u32 action) +{ + int irq; + + switch (action) { + case SMP_RESCHEDULE_YOURSELF: + irq = HEART_L2_INT_RESCHED_CPU_0; + break; + case SMP_CALL_FUNCTION: + irq = HEART_L2_INT_CALL_CPU_0; + break; + default: + panic("IP30: Unknown action value in %s!\n", __func__); + } + + irq += cpu; + + /* Poke the other CPU -- it's got mail! */ + heart_write(BIT_ULL(irq), &heart_regs->set_isr); +} + +static void ip30_smp_send_ipi_mask(const struct cpumask *mask, u32 action) +{ + u32 i; + + for_each_cpu(i, mask) + ip30_smp_send_ipi_single(i, action); +} + +static void __init ip30_smp_setup(void) +{ + int i; + int ncpu = 0; + struct mpconf *mpc; + + init_cpu_possible(cpumask_of(0)); + + /* Scan the MPCONF structure and enumerate available CPUs. */ + for (i = 0; i < MP_NCPU; i++) { + mpc = (struct mpconf *)MPCONF(i); + if (mpc->magic == MPCONF_MAGIC) { + set_cpu_possible(i, true); + __cpu_number_map[i] = ++ncpu; + __cpu_logical_map[ncpu] = i; + pr_info("IP30: Slot: %d, PrID: %.8x, PhyID: %d, VirtID: %d\n", + i, mpc->prid, mpc->physid, mpc->virtid); + } + } + pr_info("IP30: Detected %d CPU(s) present.\n", ncpu); + + /* + * Set the coherency algorithm to '5' (cacheable coherent + * exclusive on write). This is needed on IP30 SMP, especially + * for R14000 CPUs, otherwise, instruction bus errors will + * occur upon reaching userland. + */ + change_c0_config(CONF_CM_CMASK, CONF_CM_CACHABLE_COW); +} + +static void __init ip30_smp_prepare_cpus(unsigned int max_cpus) +{ + /* nothing to do here */ +} + +static int __init ip30_smp_boot_secondary(int cpu, struct task_struct *idle) +{ + struct mpconf *mpc = (struct mpconf *)MPCONF(cpu); + + /* Stack pointer (sp). */ + mpc->stackaddr = (void *)__KSTK_TOS(idle); + + /* Global pointer (gp). */ + mpc->lnch_parm = task_thread_info(idle); + + mb(); /* make sure stack and lparm are written */ + + /* Boot CPUx. */ + mpc->launch = smp_bootstrap; + + /* CPUx now executes smp_bootstrap, then ip30_smp_finish */ + return 0; +} + +static void __init ip30_smp_init_cpu(void) +{ + ip30_per_cpu_init(); +} + +static void __init ip30_smp_finish(void) +{ + enable_percpu_irq(get_c0_compare_int(), IRQ_TYPE_NONE); + local_irq_enable(); +} + +struct plat_smp_ops __read_mostly ip30_smp_ops = { + .send_ipi_single = ip30_smp_send_ipi_single, + .send_ipi_mask = ip30_smp_send_ipi_mask, + .smp_setup = ip30_smp_setup, + .prepare_cpus = ip30_smp_prepare_cpus, + .boot_secondary = ip30_smp_boot_secondary, + .init_secondary = ip30_smp_init_cpu, + .smp_finish = ip30_smp_finish, + .prepare_boot_cpu = ip30_smp_init_cpu, +}; diff --git a/arch/mips/sgi-ip30/ip30-timer.c b/arch/mips/sgi-ip30/ip30-timer.c new file mode 100644 index 000000000000..d13e105478ae --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-timer.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ip30-timer.c: Clocksource/clockevent support for the + * HEART chip in SGI Octane (IP30) systems. + * + * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de> + * Copyright (C) 2011 Joshua Kinard <kumba@gentoo.org> + */ + +#include <linux/clocksource.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/sched_clock.h> + +#include <asm/time.h> +#include <asm/cevt-r4k.h> +#include <asm/sgi/heart.h> + +static u64 ip30_heart_counter_read(struct clocksource *cs) +{ + return heart_read(&heart_regs->count); +} + +struct clocksource ip30_heart_clocksource = { + .name = "HEART", + .rating = 400, + .read = ip30_heart_counter_read, + .mask = CLOCKSOURCE_MASK(52), + .flags = (CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_VALID_FOR_HRES), +}; + +static u64 notrace ip30_heart_read_sched_clock(void) +{ + return heart_read(&heart_regs->count); +} + +static void __init ip30_heart_clocksource_init(void) +{ + struct clocksource *cs = &ip30_heart_clocksource; + + clocksource_register_hz(cs, HEART_CYCLES_PER_SEC); + + sched_clock_register(ip30_heart_read_sched_clock, 52, + HEART_CYCLES_PER_SEC); +} + +void __init plat_time_init(void) +{ + int irq = get_c0_compare_int(); + + cp0_timer_irq_installed = 1; + c0_compare_irqaction.percpu_dev_id = &mips_clockevent_device; + c0_compare_irqaction.flags &= ~IRQF_SHARED; + irq_set_handler(irq, handle_percpu_devid_irq); + irq_set_percpu_devid(irq); + setup_percpu_irq(irq, &c0_compare_irqaction); + enable_percpu_irq(irq, IRQ_TYPE_NONE); + + ip30_heart_clocksource_init(); +} diff --git a/arch/mips/sgi-ip30/ip30-xtalk.c b/arch/mips/sgi-ip30/ip30-xtalk.c new file mode 100644 index 000000000000..8a2894645529 --- /dev/null +++ b/arch/mips/sgi-ip30/ip30-xtalk.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ip30-xtalk.c - Very basic Crosstalk (XIO) detection support. + * Copyright (C) 2004-2007 Stanislaw Skowronek <skylark@unaligned.org> + * Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de> + * Copyright (C) 2007, 2014-2016 Joshua Kinard <kumba@gentoo.org> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/platform_device.h> +#include <linux/platform_data/sgi-w1.h> +#include <linux/platform_data/xtalk-bridge.h> + +#include <asm/xtalk/xwidget.h> +#include <asm/pci/bridge.h> + +#define IP30_SWIN_BASE(widget) \ + (0x0000000010000000 | (((unsigned long)(widget)) << 24)) + +#define IP30_RAW_SWIN_BASE(widget) (IO_BASE + IP30_SWIN_BASE(widget)) + +#define IP30_SWIN_SIZE (1 << 24) + +#define IP30_WIDGET_XBOW _AC(0x0, UL) /* XBow is always 0 */ +#define IP30_WIDGET_HEART _AC(0x8, UL) /* HEART is always 8 */ +#define IP30_WIDGET_PCI_BASE _AC(0xf, UL) /* BaseIO PCI is always 15 */ + +#define XTALK_NODEV 0xffffffff + +#define XBOW_REG_LINK_STAT_0 0x114 +#define XBOW_REG_LINK_BLK_SIZE 0x40 +#define XBOW_REG_LINK_ALIVE 0x80000000 + +#define HEART_INTR_ADDR 0x00000080 + +#define xtalk_read __raw_readl + +static void bridge_platform_create(int widget, int masterwid) +{ + struct xtalk_bridge_platform_data *bd; + struct sgi_w1_platform_data *wd; + struct platform_device *pdev; + struct resource w1_res; + + wd = kzalloc(sizeof(*wd), GFP_KERNEL); + if (!wd) + goto no_mem; + + snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx", + IP30_SWIN_BASE(widget)); + + memset(&w1_res, 0, sizeof(w1_res)); + w1_res.start = IP30_SWIN_BASE(widget) + + offsetof(struct bridge_regs, b_nic); + w1_res.end = w1_res.start + 3; + w1_res.flags = IORESOURCE_MEM; + + pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO); + if (!pdev) { + kfree(wd); + goto no_mem; + } + platform_device_add_resources(pdev, &w1_res, 1); + platform_device_add_data(pdev, wd, sizeof(*wd)); + platform_device_add(pdev); + + bd = kzalloc(sizeof(*bd), GFP_KERNEL); + if (!bd) + goto no_mem; + pdev = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO); + if (!pdev) { + kfree(bd); + goto no_mem; + } + + bd->bridge_addr = IP30_RAW_SWIN_BASE(widget); + bd->intr_addr = HEART_INTR_ADDR; + bd->nasid = 0; + bd->masterwid = masterwid; + + bd->mem.name = "Bridge PCI MEM"; + bd->mem.start = IP30_SWIN_BASE(widget) + BRIDGE_DEVIO0; + bd->mem.end = IP30_SWIN_BASE(widget) + IP30_SWIN_SIZE - 1; + bd->mem.flags = IORESOURCE_MEM; + bd->mem_offset = IP30_SWIN_BASE(widget); + + bd->io.name = "Bridge PCI IO"; + bd->io.start = IP30_SWIN_BASE(widget) + BRIDGE_DEVIO0; + bd->io.end = IP30_SWIN_BASE(widget) + IP30_SWIN_SIZE - 1; + bd->io.flags = IORESOURCE_IO; + bd->io_offset = IP30_SWIN_BASE(widget); + + platform_device_add_data(pdev, bd, sizeof(*bd)); + platform_device_add(pdev); + pr_info("xtalk:%x bridge widget\n", widget); + return; + +no_mem: + pr_warn("xtalk:%x bridge create out of memory\n", widget); +} + +static unsigned int __init xbow_widget_active(s8 wid) +{ + unsigned int link_stat; + + link_stat = xtalk_read((void *)(IP30_RAW_SWIN_BASE(IP30_WIDGET_XBOW) + + XBOW_REG_LINK_STAT_0 + + XBOW_REG_LINK_BLK_SIZE * + (wid - 8))); + + return (link_stat & XBOW_REG_LINK_ALIVE) ? 1 : 0; +} + +static void __init xtalk_init_widget(s8 wid, s8 masterwid) +{ + xwidget_part_num_t partnum; + widgetreg_t widget_id; + + if (!xbow_widget_active(wid)) + return; + + widget_id = xtalk_read((void *)(IP30_RAW_SWIN_BASE(wid) + WIDGET_ID)); + + partnum = XWIDGET_PART_NUM(widget_id); + + switch (partnum) { + case BRIDGE_WIDGET_PART_NUM: + case XBRIDGE_WIDGET_PART_NUM: + bridge_platform_create(wid, masterwid); + break; + default: + pr_info("xtalk:%x unknown widget (0x%x)\n", wid, partnum); + break; + } +} + +static int __init ip30_xtalk_init(void) +{ + int i; + + /* + * Walk widget IDs backwards so that BaseIO is probed first. This + * ensures that the BaseIO IOC3 is always detected as eth0. + */ + for (i = IP30_WIDGET_PCI_BASE; i > IP30_WIDGET_HEART; i--) + xtalk_init_widget(i, IP30_WIDGET_HEART); + + return 0; +} + +arch_initcall(ip30_xtalk_init); diff --git a/arch/mips/tools/.gitignore b/arch/mips/tools/.gitignore index 56d34ccccce4..b0209450d9ff 100644 --- a/arch/mips/tools/.gitignore +++ b/arch/mips/tools/.gitignore @@ -1 +1,2 @@ elf-entry +loongson3-llsc-check diff --git a/arch/mips/tools/Makefile b/arch/mips/tools/Makefile index 3baee4bc6775..aaef688749f5 100644 --- a/arch/mips/tools/Makefile +++ b/arch/mips/tools/Makefile @@ -3,3 +3,8 @@ hostprogs-y := elf-entry PHONY += elf-entry elf-entry: $(obj)/elf-entry @: + +hostprogs-$(CONFIG_CPU_LOONGSON3_WORKAROUNDS) += loongson3-llsc-check +PHONY += loongson3-llsc-check +loongson3-llsc-check: $(obj)/loongson3-llsc-check + @: diff --git a/arch/mips/tools/loongson3-llsc-check.c b/arch/mips/tools/loongson3-llsc-check.c new file mode 100644 index 000000000000..0ebddd0ae46f --- /dev/null +++ b/arch/mips/tools/loongson3-llsc-check.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <byteswap.h> +#include <elf.h> +#include <endian.h> +#include <errno.h> +#include <fcntl.h> +#include <inttypes.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#ifdef be32toh +/* If libc provides le{16,32,64}toh() then we'll use them */ +#elif BYTE_ORDER == LITTLE_ENDIAN +# define le16toh(x) (x) +# define le32toh(x) (x) +# define le64toh(x) (x) +#elif BYTE_ORDER == BIG_ENDIAN +# define le16toh(x) bswap_16(x) +# define le32toh(x) bswap_32(x) +# define le64toh(x) bswap_64(x) +#endif + +/* MIPS opcodes, in bits 31:26 of an instruction */ +#define OP_SPECIAL 0x00 +#define OP_REGIMM 0x01 +#define OP_BEQ 0x04 +#define OP_BNE 0x05 +#define OP_BLEZ 0x06 +#define OP_BGTZ 0x07 +#define OP_BEQL 0x14 +#define OP_BNEL 0x15 +#define OP_BLEZL 0x16 +#define OP_BGTZL 0x17 +#define OP_LL 0x30 +#define OP_LLD 0x34 +#define OP_SC 0x38 +#define OP_SCD 0x3c + +/* Bits 20:16 of OP_REGIMM instructions */ +#define REGIMM_BLTZ 0x00 +#define REGIMM_BGEZ 0x01 +#define REGIMM_BLTZL 0x02 +#define REGIMM_BGEZL 0x03 +#define REGIMM_BLTZAL 0x10 +#define REGIMM_BGEZAL 0x11 +#define REGIMM_BLTZALL 0x12 +#define REGIMM_BGEZALL 0x13 + +/* Bits 5:0 of OP_SPECIAL instructions */ +#define SPECIAL_SYNC 0x0f + +static void usage(FILE *f) +{ + fprintf(f, "Usage: loongson3-llsc-check /path/to/vmlinux\n"); +} + +static int se16(uint16_t x) +{ + return (int16_t)x; +} + +static bool is_ll(uint32_t insn) +{ + switch (insn >> 26) { + case OP_LL: + case OP_LLD: + return true; + + default: + return false; + } +} + +static bool is_sc(uint32_t insn) +{ + switch (insn >> 26) { + case OP_SC: + case OP_SCD: + return true; + + default: + return false; + } +} + +static bool is_sync(uint32_t insn) +{ + /* Bits 31:11 should all be zeroes */ + if (insn >> 11) + return false; + + /* Bits 5:0 specify the SYNC special encoding */ + if ((insn & 0x3f) != SPECIAL_SYNC) + return false; + + return true; +} + +static bool is_branch(uint32_t insn, int *off) +{ + switch (insn >> 26) { + case OP_BEQ: + case OP_BEQL: + case OP_BNE: + case OP_BNEL: + case OP_BGTZ: + case OP_BGTZL: + case OP_BLEZ: + case OP_BLEZL: + *off = se16(insn) + 1; + return true; + + case OP_REGIMM: + switch ((insn >> 16) & 0x1f) { + case REGIMM_BGEZ: + case REGIMM_BGEZL: + case REGIMM_BGEZAL: + case REGIMM_BGEZALL: + case REGIMM_BLTZ: + case REGIMM_BLTZL: + case REGIMM_BLTZAL: + case REGIMM_BLTZALL: + *off = se16(insn) + 1; + return true; + + default: + return false; + } + + default: + return false; + } +} + +static int check_ll(uint64_t pc, uint32_t *code, size_t sz) +{ + ssize_t i, max, sc_pos; + int off; + + /* + * Every LL must be preceded by a sync instruction in order to ensure + * that instruction reordering doesn't allow a prior memory access to + * execute after the LL & cause erroneous results. + */ + if (!is_sync(le32toh(code[-1]))) { + fprintf(stderr, "%" PRIx64 ": LL not preceded by sync\n", pc); + return -EINVAL; + } + + /* Find the matching SC instruction */ + max = sz / 4; + for (sc_pos = 0; sc_pos < max; sc_pos++) { + if (is_sc(le32toh(code[sc_pos]))) + break; + } + if (sc_pos >= max) { + fprintf(stderr, "%" PRIx64 ": LL has no matching SC\n", pc); + return -EINVAL; + } + + /* + * Check branches within the LL/SC loop target sync instructions, + * ensuring that speculative execution can't generate memory accesses + * due to instructions outside of the loop. + */ + for (i = 0; i < sc_pos; i++) { + if (!is_branch(le32toh(code[i]), &off)) + continue; + + /* + * If the branch target is within the LL/SC loop then we don't + * need to worry about it. + */ + if ((off >= -i) && (off <= sc_pos)) + continue; + + /* If the branch targets a sync instruction we're all good... */ + if (is_sync(le32toh(code[i + off]))) + continue; + + /* ...but if not, we have a problem */ + fprintf(stderr, "%" PRIx64 ": Branch target not a sync\n", + pc + (i * 4)); + return -EINVAL; + } + + return 0; +} + +static int check_code(uint64_t pc, uint32_t *code, size_t sz) +{ + int err = 0; + + if (sz % 4) { + fprintf(stderr, "%" PRIx64 ": Section size not a multiple of 4\n", + pc); + err = -EINVAL; + sz -= (sz % 4); + } + + if (is_ll(le32toh(code[0]))) { + fprintf(stderr, "%" PRIx64 ": First instruction in section is an LL\n", + pc); + err = -EINVAL; + } + +#define advance() ( \ + code++, \ + pc += 4, \ + sz -= 4 \ +) + + /* + * Skip the first instructionm allowing check_ll to look backwards + * unconditionally. + */ + advance(); + + /* Now scan through the code looking for LL instructions */ + for (; sz; advance()) { + if (is_ll(le32toh(code[0]))) + err |= check_ll(pc, code, sz); + } + + return err; +} + +int main(int argc, char *argv[]) +{ + int vmlinux_fd, status, err, i; + const char *vmlinux_path; + struct stat st; + Elf64_Ehdr *eh; + Elf64_Shdr *sh; + void *vmlinux; + + status = EXIT_FAILURE; + + if (argc < 2) { + usage(stderr); + goto out_ret; + } + + vmlinux_path = argv[1]; + vmlinux_fd = open(vmlinux_path, O_RDONLY); + if (vmlinux_fd == -1) { + perror("Unable to open vmlinux"); + goto out_ret; + } + + err = fstat(vmlinux_fd, &st); + if (err) { + perror("Unable to stat vmlinux"); + goto out_close; + } + + vmlinux = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, vmlinux_fd, 0); + if (vmlinux == MAP_FAILED) { + perror("Unable to mmap vmlinux"); + goto out_close; + } + + eh = vmlinux; + if (memcmp(eh->e_ident, ELFMAG, SELFMAG)) { + fprintf(stderr, "vmlinux is not an ELF?\n"); + goto out_munmap; + } + + if (eh->e_ident[EI_CLASS] != ELFCLASS64) { + fprintf(stderr, "vmlinux is not 64b?\n"); + goto out_munmap; + } + + if (eh->e_ident[EI_DATA] != ELFDATA2LSB) { + fprintf(stderr, "vmlinux is not little endian?\n"); + goto out_munmap; + } + + for (i = 0; i < le16toh(eh->e_shnum); i++) { + sh = vmlinux + le64toh(eh->e_shoff) + (i * le16toh(eh->e_shentsize)); + + if (sh->sh_type != SHT_PROGBITS) + continue; + if (!(sh->sh_flags & SHF_EXECINSTR)) + continue; + + err = check_code(le64toh(sh->sh_addr), + vmlinux + le64toh(sh->sh_offset), + le64toh(sh->sh_size)); + if (err) + goto out_munmap; + } + + status = EXIT_SUCCESS; +out_munmap: + munmap(vmlinux, st.st_size); +out_close: + close(vmlinux_fd); +out_ret: + return status; +} diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 996a934ece7d..e05938997e69 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -75,6 +75,7 @@ CFLAGS_REMOVE_vdso.o = -pg GCOV_PROFILE := n UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n # # Shared build commands. diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 36b834f1c933..dca8f2de8cf5 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -60,7 +60,6 @@ KBUILD_CFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY=1 \ -DFTRACE_PATCHABLE_FUNCTION_SIZE=$(NOP_COUNT) CC_FLAGS_FTRACE := -fpatchable-function-entry=$(NOP_COUNT),$(shell echo $$(($(NOP_COUNT)-1))) -KBUILD_LDS_MODULE += $(srctree)/arch/parisc/kernel/module.lds endif OBJCOPY_FLAGS =-O binary -R .note -R .comment -S diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index ac5f34993b53..1c50093e2ebe 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -43,6 +43,7 @@ #include <linux/elf.h> #include <linux/vmalloc.h> #include <linux/fs.h> +#include <linux/ftrace.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/bug.h> @@ -862,7 +863,7 @@ int module_finalize(const Elf_Ehdr *hdr, const char *strtab = NULL; const Elf_Shdr *s; char *secstrings; - int err, symindex = -1; + int symindex = -1; Elf_Sym *newptr, *oldptr; Elf_Shdr *symhdr = NULL; #ifdef DEBUG @@ -946,11 +947,13 @@ int module_finalize(const Elf_Ehdr *hdr, /* patch .altinstructions */ apply_alternatives(aseg, aseg + s->sh_size, me->name); +#ifdef CONFIG_DYNAMIC_FTRACE /* For 32 bit kernels we're compiling modules with * -ffunction-sections so we must relocate the addresses in the - *__mcount_loc section. + * ftrace callsite section. */ - if (symindex != -1 && !strcmp(secname, "__mcount_loc")) { + if (symindex != -1 && !strcmp(secname, FTRACE_CALLSITE_SECTION)) { + int err; if (s->sh_type == SHT_REL) err = apply_relocate((Elf_Shdr *)sechdrs, strtab, symindex, @@ -962,6 +965,7 @@ int module_finalize(const Elf_Ehdr *hdr, if (err) return err; } +#endif } return 0; } diff --git a/arch/parisc/kernel/module.lds b/arch/parisc/kernel/module.lds deleted file mode 100644 index 1a9a92aca5c8..000000000000 --- a/arch/parisc/kernel/module.lds +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -SECTIONS { - __mcount_loc : { - *(__patchable_function_entries) - } -} diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index c8bb14ff4713..f6c562acc3f8 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -329,13 +329,4 @@ struct vm_area_struct; #endif /* __ASSEMBLY__ */ #include <asm/slice.h> -/* - * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks. - */ -#ifdef CONFIG_PPC32 -#define ARCH_ZONE_DMA_BITS 30 -#else -#define ARCH_ZONE_DMA_BITS 31 -#endif - #endif /* _ASM_POWERPC_PAGE_H */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index be941d382c8d..c95b7fe9f298 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -31,6 +31,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/memremap.h> +#include <linux/dma-direct.h> #include <asm/pgalloc.h> #include <asm/prom.h> @@ -201,10 +202,10 @@ static int __init mark_nonram_nosave(void) * everything else. GFP_DMA32 page allocations automatically fall back to * ZONE_DMA. * - * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to - * inform the generic DMA mapping code. 32-bit only devices (if not handled - * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get - * otherwise served by ZONE_DMA. + * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the + * generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU + * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by + * ZONE_DMA. */ static unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -237,9 +238,18 @@ void __init paging_init(void) printk(KERN_DEBUG "Memory hole size: %ldMB\n", (long int)((top_of_ram - total_ram) >> 20)); + /* + * Allow 30-bit DMA for very limited Broadcom wifi chips on many + * powerbooks. + */ + if (IS_ENABLED(CONFIG_PPC32)) + zone_dma_bits = 30; + else + zone_dma_bits = 31; + #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); + 1UL << (zone_dma_bits - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 02a59946a78a..be3517ef0574 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -1142,6 +1142,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) } /* + * If we have seen a tail call, we need a second pass. + * This is because bpf_jit_emit_common_epilogue() is called + * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen. + */ + if (cgctx.seen & SEEN_TAILCALL) { + cgctx.idx = 0; + if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) { + fp = org_fp; + goto out_addrs; + } + } + + /* * Pretend to build prologue, given the features we've seen. This will * update ctgtx.idx as it pretends to output instructions, then we can * calculate total size from idx. diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 43a81d0ad507..f0df9e48e651 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -246,8 +246,8 @@ choice config MARCH_Z900 bool "IBM zSeries model z800 and z900" - depends on !CC_IS_CLANG select HAVE_MARCH_Z900_FEATURES + depends on $(cc-option,-march=z900) help Select this to enable optimizations for model z800/z900 (2064 and 2066 series). This will enable some optimizations that are not @@ -255,8 +255,8 @@ config MARCH_Z900 config MARCH_Z990 bool "IBM zSeries model z890 and z990" - depends on !CC_IS_CLANG select HAVE_MARCH_Z990_FEATURES + depends on $(cc-option,-march=z990) help Select this to enable optimizations for model z890/z990 (2084 and 2086 series). The kernel will be slightly faster but will not work @@ -264,8 +264,8 @@ config MARCH_Z990 config MARCH_Z9_109 bool "IBM System z9" - depends on !CC_IS_CLANG select HAVE_MARCH_Z9_109_FEATURES + depends on $(cc-option,-march=z9-109) help Select this to enable optimizations for IBM System z9 (2094 and 2096 series). The kernel will be slightly faster but will not work @@ -274,6 +274,7 @@ config MARCH_Z9_109 config MARCH_Z10 bool "IBM System z10" select HAVE_MARCH_Z10_FEATURES + depends on $(cc-option,-march=z10) help Select this to enable optimizations for IBM System z10 (2097 and 2098 series). The kernel will be slightly faster but will not work @@ -282,6 +283,7 @@ config MARCH_Z10 config MARCH_Z196 bool "IBM zEnterprise 114 and 196" select HAVE_MARCH_Z196_FEATURES + depends on $(cc-option,-march=z196) help Select this to enable optimizations for IBM zEnterprise 114 and 196 (2818 and 2817 series). The kernel will be slightly faster but will @@ -290,6 +292,7 @@ config MARCH_Z196 config MARCH_ZEC12 bool "IBM zBC12 and zEC12" select HAVE_MARCH_ZEC12_FEATURES + depends on $(cc-option,-march=zEC12) help Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and 2827 series). The kernel will be slightly faster but will not work on @@ -298,6 +301,7 @@ config MARCH_ZEC12 config MARCH_Z13 bool "IBM z13s and z13" select HAVE_MARCH_Z13_FEATURES + depends on $(cc-option,-march=z13) help Select this to enable optimizations for IBM z13s and z13 (2965 and 2964 series). The kernel will be slightly faster but will not work on @@ -306,6 +310,7 @@ config MARCH_Z13 config MARCH_Z14 bool "IBM z14 ZR1 and z14" select HAVE_MARCH_Z14_FEATURES + depends on $(cc-option,-march=z14) help Select this to enable optimizations for IBM z14 ZR1 and z14 (3907 and 3906 series). The kernel will be slightly faster but will not @@ -314,6 +319,7 @@ config MARCH_Z14 config MARCH_Z15 bool "IBM z15" select HAVE_MARCH_Z15_FEATURES + depends on $(cc-option,-march=z15) help Select this to enable optimizations for IBM z15 (8562 and 8561 series). The kernel will be slightly faster but will not @@ -367,33 +373,39 @@ config TUNE_DEFAULT config TUNE_Z900 bool "IBM zSeries model z800 and z900" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z900) config TUNE_Z990 bool "IBM zSeries model z890 and z990" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z990) config TUNE_Z9_109 bool "IBM System z9" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z9-109) config TUNE_Z10 bool "IBM System z10" + depends on $(cc-option,-mtune=z10) config TUNE_Z196 bool "IBM zEnterprise 114 and 196" + depends on $(cc-option,-mtune=z196) config TUNE_ZEC12 bool "IBM zBC12 and zEC12" + depends on $(cc-option,-mtune=zEC12) config TUNE_Z13 - bool "IBM z13" + bool "IBM z13s and z13" + depends on $(cc-option,-mtune=z13) config TUNE_Z14 - bool "IBM z14" + bool "IBM z14 ZR1 and z14" + depends on $(cc-option,-mtune=z14) config TUNE_Z15 bool "IBM z15" + depends on $(cc-option,-mtune=z15) endchoice diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 5367950510f6..fbd341ea03b8 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = { .diag0c = _diag0c_dma, .diag308_reset = _diag308_reset_dma }; -static struct diag210 _diag210_tmp_dma __section(".dma.data"); +static struct diag210 _diag210_tmp_dma __section(.dma.data); struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma; void _swsusp_reset_dma(void); unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma); diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index d39e0f079217..686fe7aa192f 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out) struct s390_sha_ctx *ctx = shash_desc_ctx(desc); unsigned int bsize = crypto_shash_blocksize(desc->tfm); u64 bits; - unsigned int n, mbl_offset; + unsigned int n; + int mbl_offset; n = ctx->count % bsize; bits = ctx->count * 8; - mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32); + mbl_offset = s390_crypto_shash_parmsize(ctx->func); if (mbl_offset < 0) return -EINVAL; + mbl_offset = mbl_offset / sizeof(u32); + /* set total msg bit length (mbl) in CPACF parmblock */ switch (ctx->func) { case CPACF_KLMD_SHA_1: diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h index c2cf7bcdef9b..1c8a38f762a3 100644 --- a/arch/s390/include/asm/alternative.h +++ b/arch/s390/include/asm/alternative.h @@ -139,10 +139,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end); * without volatile and memory clobber. */ #define alternative(oldinstr, altinstr, facility) \ - asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory") + asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory") #define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \ - asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1, \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1, \ altinstr2, facility2) ::: "memory") #endif /* __ASSEMBLY__ */ diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 713fc9735ffb..a2b11ac00f60 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -9,7 +9,7 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE #define __EMIT_BUG(x) do { \ - asm volatile( \ + asm_inline volatile( \ "0: j 0b+2\n" \ "1:\n" \ ".section .rodata.str,\"aMS\",@progbits,1\n" \ @@ -28,7 +28,7 @@ #else /* CONFIG_DEBUG_BUGVERBOSE */ #define __EMIT_BUG(x) do { \ - asm volatile( \ + asm_inline volatile( \ "0: j 0b+2\n" \ "1:\n" \ ".section __bug_table,\"awM\",@progbits,%1\n" \ diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index 60f907516335..ed5efbb531c4 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -11,6 +11,7 @@ #include <linux/bits.h> #define CR0_CLOCK_COMPARATOR_SIGN BIT(63 - 10) +#define CR0_LOW_ADDRESS_PROTECTION BIT(63 - 35) #define CR0_EMERGENCY_SIGNAL_SUBMASK BIT(63 - 49) #define CR0_EXTERNAL_CALL_SUBMASK BIT(63 - 50) #define CR0_CLOCK_COMPARATOR_SUBMASK BIT(63 - 52) diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 823578c6b9e2..a4d38092530a 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -177,8 +177,6 @@ static inline int devmem_is_allowed(unsigned long pfn) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define ARCH_ZONE_DMA_BITS 31 - #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index bccb8f4a63e2..77606c4acd58 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION2_ENTRY_EMPTY); return (p4d_t *) table; } -#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d) + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!mm_p4d_folded(mm)) + crst_table_free(mm, (unsigned long *) p4d); +} static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { @@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION3_ENTRY_EMPTY); return (pud_t *) table; } -#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud) + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (!mm_pud_folded(mm)) + crst_table_free(mm, (unsigned long *) pud); +} static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) { @@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { + if (mm_pmd_folded(mm)) + return; pgtable_pmd_page_dtor(virt_to_page(pmd)); crst_table_free(mm, (unsigned long *) pmd); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 5ff98d76a66c..7b03037a8475 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -266,11 +266,9 @@ static inline int is_module_addr(void *addr) #endif #define _REGION_ENTRY_BITS 0xfffffffffffff22fUL -#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL /* Bits in the segment table entry */ #define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL -#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL #define _SEGMENT_ENTRY_HARDWARE_BITS 0xfffffffffffffe30UL #define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE 0xfffffffffff00730UL #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ @@ -699,10 +697,8 @@ static inline int pmd_large(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { - if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0) + if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0 || pmd_large(pmd)) return 1; - if (pmd_large(pmd)) - return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0; return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } @@ -710,12 +706,10 @@ static inline int pud_bad(pud_t pud) { unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK; - if (type > _REGION_ENTRY_TYPE_R3) + if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud)) return 1; if (type < _REGION_ENTRY_TYPE_R3) return 0; - if (pud_large(pud)) - return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0; return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0; } @@ -758,18 +752,12 @@ static inline int pmd_write(pmd_t pmd) static inline int pmd_dirty(pmd_t pmd) { - int dirty = 1; - if (pmd_large(pmd)) - dirty = (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; - return dirty; + return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; } static inline int pmd_young(pmd_t pmd) { - int young = 1; - if (pmd_large(pmd)) - young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; - return young; + return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; } static inline int pte_present(pte_t pte) @@ -1173,8 +1161,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { - if (!MACHINE_HAS_NX) - pte_val(entry) &= ~_PAGE_NOEXEC; if (pte_present(entry)) pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) @@ -1191,6 +1177,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); + if (!MACHINE_HAS_NX) + pte_val(__pte) &= ~_PAGE_NOEXEC; return pte_mkyoung(__pte); } @@ -1297,29 +1285,23 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd) static inline pmd_t pmd_mkwrite(pmd_t pmd) { pmd_val(pmd) |= _SEGMENT_ENTRY_WRITE; - if (pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) - return pmd; - pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + if (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; return pmd; } static inline pmd_t pmd_mkclean(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY; - pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; - } + pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY; + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; return pmd; } static inline pmd_t pmd_mkdirty(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | - _SEGMENT_ENTRY_SOFT_DIRTY; - if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; - } + pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_SOFT_DIRTY; + if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; return pmd; } @@ -1333,29 +1315,23 @@ static inline pud_t pud_wrprotect(pud_t pud) static inline pud_t pud_mkwrite(pud_t pud) { pud_val(pud) |= _REGION3_ENTRY_WRITE; - if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY)) - return pud; - pud_val(pud) &= ~_REGION_ENTRY_PROTECT; + if (pud_val(pud) & _REGION3_ENTRY_DIRTY) + pud_val(pud) &= ~_REGION_ENTRY_PROTECT; return pud; } static inline pud_t pud_mkclean(pud_t pud) { - if (pud_large(pud)) { - pud_val(pud) &= ~_REGION3_ENTRY_DIRTY; - pud_val(pud) |= _REGION_ENTRY_PROTECT; - } + pud_val(pud) &= ~_REGION3_ENTRY_DIRTY; + pud_val(pud) |= _REGION_ENTRY_PROTECT; return pud; } static inline pud_t pud_mkdirty(pud_t pud) { - if (pud_large(pud)) { - pud_val(pud) |= _REGION3_ENTRY_DIRTY | - _REGION3_ENTRY_SOFT_DIRTY; - if (pud_val(pud) & _REGION3_ENTRY_WRITE) - pud_val(pud) &= ~_REGION_ENTRY_PROTECT; - } + pud_val(pud) |= _REGION3_ENTRY_DIRTY | _REGION3_ENTRY_SOFT_DIRTY; + if (pud_val(pud) & _REGION3_ENTRY_WRITE) + pud_val(pud) &= ~_REGION_ENTRY_PROTECT; return pud; } @@ -1379,38 +1355,29 @@ static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot) static inline pmd_t pmd_mkyoung(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; - if (pmd_val(pmd) & _SEGMENT_ENTRY_READ) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; - } + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + if (pmd_val(pmd) & _SEGMENT_ENTRY_READ) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; return pmd; } static inline pmd_t pmd_mkold(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; - pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; - } + pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; return pmd; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | - _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | - _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; - pmd_val(pmd) |= massage_pgprot_pmd(newprot); - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) - pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)) - pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; - return pmd; - } - pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | + _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | + _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; pmd_val(pmd) |= massage_pgprot_pmd(newprot); + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)) + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; return pmd; } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 51a0e4a2dc96..881fc37c11c6 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -206,7 +206,7 @@ unsigned long get_wchan(struct task_struct *p); /* Has task runtime instrumentation enabled ? */ #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) -static inline unsigned long current_stack_pointer(void) +static __always_inline unsigned long current_stack_pointer(void) { unsigned long sp; diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index e3f238e8c611..71e3f0146cda 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -276,6 +276,7 @@ struct qdio_outbuf_state { #define CHSC_AC2_MULTI_BUFFER_AVAILABLE 0x0080 #define CHSC_AC2_MULTI_BUFFER_ENABLED 0x0040 #define CHSC_AC2_DATA_DIV_AVAILABLE 0x0010 +#define CHSC_AC2_SNIFFER_AVAILABLE 0x0008 #define CHSC_AC2_DATA_DIV_ENABLED 0x0002 #define CHSC_AC3_FORMAT2_CQ_AVAILABLE 0x8000 diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index c02bff33f6c7..3a37172d5398 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -85,7 +85,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp) static inline void arch_spin_unlock(arch_spinlock_t *lp) { typecheck(int, lp->lock); - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0070", 49) /* NIAI 7 */ " sth %1,%0\n" : "=Q" (((unsigned short *) &lp->lock)[1]) diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 0ae4bbf7779c..fee40212af11 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -38,7 +38,7 @@ static inline unsigned long get_stack_pointer(struct task_struct *task, { if (regs) return (unsigned long) kernel_stack_pointer(regs); - if (task == current) + if (!task || task == current) return current_stack_pointer(); return (unsigned long) task->thread.ksp; } diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 64539c221672..6da8885251d6 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -10,8 +10,9 @@ #ifndef _ASM_S390_TIMEX_H #define _ASM_S390_TIMEX_H -#include <asm/lowcore.h> +#include <linux/preempt.h> #include <linux/time64.h> +#include <asm/lowcore.h> /* The value of the TOD clock for 1.1.1970. */ #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL @@ -179,22 +180,24 @@ static inline cycles_t get_cycles(void) int get_phys_clock(unsigned long *clock); void init_cpu_timer(void); -unsigned long long monotonic_clock(void); extern unsigned char tod_clock_base[16] __aligned(8); /** * get_clock_monotonic - returns current time in clock rate units * - * The caller must ensure that preemption is disabled. * The clock and tod_clock_base get changed via stop_machine. - * Therefore preemption must be disabled when calling this - * function, otherwise the returned value is not guaranteed to - * be monotonic. + * Therefore preemption must be disabled, otherwise the returned + * value is not guaranteed to be monotonic. */ static inline unsigned long long get_tod_clock_monotonic(void) { - return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + unsigned long long tod; + + preempt_disable(); + tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + preempt_enable(); + return tod; } /** diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 7abe6ae261b4..f304802ecf7b 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) ptr += sprintf(ptr, "%%c%i", value); else if (operand->flags & OPERAND_VR) ptr += sprintf(ptr, "%%v%i", value); - else if (operand->flags & OPERAND_PCREL) - ptr += sprintf(ptr, "%lx", (signed int) value - + addr); - else if (operand->flags & OPERAND_SIGNED) + else if (operand->flags & OPERAND_PCREL) { + void *pcrel = (void *)((int)value + addr); + + ptr += sprintf(ptr, "%px", pcrel); + } else if (operand->flags & OPERAND_SIGNED) ptr += sprintf(ptr, "%i", value); else ptr += sprintf(ptr, "%u", value); @@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs) else *ptr++ = ' '; addr = regs->psw.addr + start - 32; - ptr += sprintf(ptr, "%016lx: ", addr); + ptr += sprintf(ptr, "%px: ", (void *)addr); if (start + opsize >= end) break; for (i = 0; i < opsize; i++) @@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len) opsize = insn_length(*code); if (opsize > len) break; - ptr += sprintf(ptr, "%p: ", code); + ptr += sprintf(ptr, "%px: ", code); for (i = 0; i < opsize; i++) ptr += sprintf(ptr, "%02x", code[i]); *ptr++ = '\t'; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index b432d63d0b37..db32a55daaec 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -30,6 +30,7 @@ #include <asm/sclp.h> #include <asm/facility.h> #include <asm/boot_data.h> +#include <asm/switch_to.h> #include "entry.h" static void __init reset_tod_clock(void) @@ -238,7 +239,7 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_VX; __ctl_set_bit(0, 17); } - if (test_facility(130)) { + if (test_facility(130) && !noexec_disabled) { S390_lowcore.machine_flags |= MACHINE_FLAG_NX; __ctl_set_bit(0, 20); } @@ -260,6 +261,24 @@ static inline void save_vector_registers(void) #endif } +static inline void setup_control_registers(void) +{ + unsigned long reg; + + __ctl_store(reg, 0, 0); + reg |= CR0_LOW_ADDRESS_PROTECTION; + reg |= CR0_EMERGENCY_SIGNAL_SUBMASK; + reg |= CR0_EXTERNAL_CALL_SUBMASK; + __ctl_load(reg, 0, 0); +} + +static inline void setup_access_registers(void) +{ + unsigned int acrs[NUM_ACRS] = { 0 }; + + restore_access_regs(acrs); +} + static int __init disable_vector_extension(char *str) { S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX; @@ -268,21 +287,6 @@ static int __init disable_vector_extension(char *str) } early_param("novx", disable_vector_extension); -static int __init noexec_setup(char *str) -{ - bool enabled; - int rc; - - rc = kstrtobool(str, &enabled); - if (!rc && !enabled) { - /* Disable no-execute support */ - S390_lowcore.machine_flags &= ~MACHINE_FLAG_NX; - __ctl_clear_bit(0, 20); - } - return rc; -} -early_param("noexec", noexec_setup); - static int __init cad_setup(char *str) { bool enabled; @@ -332,5 +336,7 @@ void __init startup_init(void) save_vector_registers(); setup_topology(); sclp_early_detect(); + setup_control_registers(); + setup_access_registers(); lockdep_on(); } diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 0d9ee198f4eb..b9e585f528a6 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -26,8 +26,6 @@ ENTRY(startup_continue) 0: larl %r1,tod_clock_base mvc 0(16,%r1),__LC_BOOT_CLOCK larl %r13,.LPG1 # get base - larl %r0,boot_vdso_data - stg %r0,__LC_VDSO_PER_CPU # # Setup stack # @@ -37,19 +35,8 @@ ENTRY(startup_continue) #ifdef CONFIG_KASAN brasl %r14,kasan_early_init #endif -# -# Early machine initialization and detection functions. -# - brasl %r14,startup_init - -# check control registers - stctg %c0,%c15,0(%r15) - oi 6(%r15),0x60 # enable sigp emergency & external call - oi 4(%r15),0x10 # switch on low address proctection - lctlg %c0,%c15,0(%r15) - - lam 0,15,.Laregs-.LPG1(%r13) # load acrs needed by uaccess - brasl %r14,start_kernel # go to C code + brasl %r14,startup_init # s390 specific early init + brasl %r14,start_kernel # common init code # # We returned from start_kernel ?!? PANIK # @@ -59,4 +46,3 @@ ENTRY(startup_continue) .align 16 .LPG1: .Ldw: .quad 0x0002000180000000,0x0000000000000000 -.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 48d48b6187c0..0eb1d1cc53a8 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = { [PERF_COUNT_HW_BUS_CYCLES] = -1, }; -static int __hw_perf_event_init(struct perf_event *event) +static int __hw_perf_event_init(struct perf_event *event, unsigned int type) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; @@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event) int err = 0; u64 ev; - switch (attr->type) { + switch (type) { case PERF_TYPE_RAW: /* Raw events are used to access counters directly, * hence do not permit excludes */ @@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event) static int cpumf_pmu_event_init(struct perf_event *event) { + unsigned int type = event->attr.type; int err; - switch (event->attr.type) { - case PERF_TYPE_HARDWARE: - case PERF_TYPE_HW_CACHE: - case PERF_TYPE_RAW: - err = __hw_perf_event_init(event); - break; - default: + if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) + err = __hw_perf_event_init(event, type); + else if (event->pmu->type == type) + /* Registered as unknown PMU */ + err = __hw_perf_event_init(event, PERF_TYPE_RAW); + else return -ENOENT; - } if (unlikely(err) && event->destroy) event->destroy(event); @@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void) return -ENODEV; cpumf_pmu.attr_groups = cpumf_cf_event_group(); - rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); + rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1); if (rc) pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc); return rc; diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index 2654e348801a..e949ab832ed7 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event) int err = -ENOENT; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d config %#llx " + "%s event %p cpu %d config %#llx type:%u " "sample_type %#llx cf_diag_events %d\n", __func__, - event, event->cpu, attr->config, attr->sample_type, - atomic_read(&cf_diag_events)); + event, event->cpu, attr->config, event->pmu->type, + attr->sample_type, atomic_read(&cf_diag_events)); if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG || - event->attr.type != PERF_TYPE_RAW) + event->attr.type != event->pmu->type) goto out; /* Raw events are used to access counters directly, @@ -693,7 +693,7 @@ static int __init cf_diag_init(void) } debug_register_view(cf_diag_dbg, &debug_sprintf_view); - rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW); + rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1); if (rc) { debug_unregister_view(cf_diag_dbg, &debug_sprintf_view); debug_unregister(cf_diag_dbg); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 3d8b12a9a6ff..69506fdbd9a1 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -156,8 +156,8 @@ static void free_sampling_buffer(struct sf_buffer *sfb) } } - debug_sprintf_event(sfdbg, 5, - "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt); + debug_sprintf_event(sfdbg, 5, "%s freed sdbt %p\n", __func__, + sfb->sdbt); memset(sfb, 0, sizeof(*sfb)); } @@ -212,10 +212,10 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, * the sampling buffer origin. */ if (sfb->sdbt != get_next_sdbt(tail)) { - debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: " - "sampling buffer is not linked: origin=%p" - "tail=%p\n", - (void *) sfb->sdbt, (void *) tail); + debug_sprintf_event(sfdbg, 3, "%s: " + "sampling buffer is not linked: origin %p" + " tail %p\n", __func__, + (void *)sfb->sdbt, (void *)tail); return -EINVAL; } @@ -252,7 +252,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, sfb->tail = tail; debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer" - " settings: sdbt=%lu sdb=%lu\n", + " settings: sdbt %lu sdb %lu\n", sfb->num_sdbt, sfb->num_sdb); return rc; } @@ -293,11 +293,11 @@ static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb) if (rc) { free_sampling_buffer(sfb); debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: " - "realloc_sampling_buffer failed with rc=%i\n", rc); + "realloc_sampling_buffer failed with rc %i\n", rc); } else debug_sprintf_event(sfdbg, 4, - "alloc_sampling_buffer: tear=%p dear=%p\n", - sfb->sdbt, (void *) *sfb->sdbt); + "alloc_sampling_buffer: tear %p dear %p\n", + sfb->sdbt, (void *)*sfb->sdbt); return rc; } @@ -404,8 +404,8 @@ static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc) return 0; debug_sprintf_event(sfdbg, 3, - "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu" - " sample_size=%lu cpuhw=%p\n", + "%s: rate %lu f %lu sdb %lu/%lu" + " sample_size %lu cpuhw %p\n", __func__, SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc), sample_size, cpuhw); @@ -465,8 +465,8 @@ static void sfb_account_overflows(struct cpu_hw_sf *cpuhw, if (num) sfb_account_allocs(num, hwc); - debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu" - " num=%lu\n", OVERFLOW_REG(hwc), ratio, num); + debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow %llu ratio %lu" + " num %lu\n", OVERFLOW_REG(hwc), ratio, num); OVERFLOW_REG(hwc) = 0; } @@ -505,11 +505,11 @@ static void extend_sampling_buffer(struct sf_buffer *sfb, rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC); if (rc) debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc " - "failed with rc=%i\n", rc); + "failed with rc %i\n", rc); if (sfb_has_pending_allocs(sfb, hwc)) debug_sprintf_event(sfdbg, 5, "sfb: extend: " - "req=%lu alloc=%lu remaining=%lu\n", + "req %lu alloc %lu remaining %lu\n", num, sfb->num_sdb - num_old, sfb_pending_allocs(sfb, hwc)); } @@ -538,20 +538,22 @@ static void setup_pmc_cpu(void *flags) err = sf_disable(); if (err) pr_err("Switching off the sampling facility failed " - "with rc=%i\n", err); + "with rc %i\n", err); debug_sprintf_event(sfdbg, 5, - "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf); + "%s: initialized: cpuhw %p\n", __func__, + cpusf); break; case PMC_RELEASE: cpusf->flags &= ~PMU_F_RESERVED; err = sf_disable(); if (err) { pr_err("Switching off the sampling facility failed " - "with rc=%i\n", err); + "with rc %i\n", err); } else deallocate_buffers(cpusf); debug_sprintf_event(sfdbg, 5, - "setup_pmc_cpu: released: cpuhw=%p\n", cpusf); + "%s: released: cpuhw %p\n", __func__, + cpusf); break; } if (err) @@ -744,7 +746,7 @@ static int __hw_perf_event_init_rate(struct perf_event *event, SAMPL_RATE(hwc) = rate; hw_init_period(hwc, SAMPL_RATE(hwc)); debug_sprintf_event(sfdbg, 4, "__hw_perf_event_init_rate:" - "cpu:%d period:%llx freq:%d,%#lx\n", event->cpu, + "cpu:%d period:%#llx freq:%d,%#lx\n", event->cpu, event->attr.sample_period, event->attr.freq, SAMPLE_FREQ_MODE(hwc)); return 0; @@ -963,7 +965,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu) err = lsctl(&cpuhw->lsctl); if (err) { cpuhw->flags &= ~PMU_F_ENABLED; - pr_err("Loading sampling controls failed: op=%i err=%i\n", + pr_err("Loading sampling controls failed: op %i err %i\n", 1, err); return; } @@ -971,8 +973,8 @@ static void cpumsf_pmu_enable(struct pmu *pmu) /* Load current program parameter */ lpp(&S390_lowcore.lpp); - debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i " - "interval:%lx tear=%p dear=%p\n", + debug_sprintf_event(sfdbg, 6, "pmu_enable: es %i cs %i ed %i cd %i " + "interval %#lx tear %p dear %p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed, cpuhw->lsctl.cd, cpuhw->lsctl.interval, (void *) cpuhw->lsctl.tear, @@ -999,13 +1001,14 @@ static void cpumsf_pmu_disable(struct pmu *pmu) err = lsctl(&inactive); if (err) { - pr_err("Loading sampling controls failed: op=%i err=%i\n", + pr_err("Loading sampling controls failed: op %i err %i\n", 2, err); return; } /* Save state of TEAR and DEAR register contents */ - if (!qsi(&si)) { + err = qsi(&si); + if (!err) { /* TEAR/DEAR values are valid only if the sampling facility is * enabled. Note that cpumsf_pmu_disable() might be called even * for a disabled sampling facility because cpumsf_pmu_enable() @@ -1017,7 +1020,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu) } } else debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: " - "qsi() failed with err=%i\n", err); + "qsi() failed with err %i\n", err); cpuhw->flags &= ~PMU_F_ENABLED; } @@ -1130,15 +1133,6 @@ static void perf_event_count_update(struct perf_event *event, u64 count) local64_add(count, &event->count); } -static void debug_sample_entry(struct hws_basic_entry *sample, - struct hws_trailer_entry *te) -{ - debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown " - "sampling data entry: te->f=%i basic.def=%04x " - "(%p)\n", - te->f, sample->def, sample); -} - /* hw_collect_samples() - Walk through a sample-data-block and collect samples * @event: The perf event * @sdbt: Sample-data-block table @@ -1192,7 +1186,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, /* Count discarded samples */ *overflow += 1; } else { - debug_sample_entry(sample, te); + debug_sprintf_event(sfdbg, 4, + "%s: Found unknown" + " sampling data entry: te->f %i" + " basic.def %#4x (%p)\n", __func__, + te->f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1267,9 +1265,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) sampl_overflow += te->overflow; /* Timestamps are valid for full sample-data-blocks only */ - debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p " - "overflow=%llu timestamp=%#llx\n", - sdbt, te->overflow, + debug_sprintf_event(sfdbg, 6, "%s: sdbt %p " + "overflow %llu timestamp %#llx\n", + __func__, sdbt, te->overflow, (te->f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and @@ -1313,9 +1311,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) + sampl_overflow, 1 + num_sdb); if (sampl_overflow || event_overflow) - debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: " - "overflow stats: sample=%llu event=%llu\n", - sampl_overflow, event_overflow); + debug_sprintf_event(sfdbg, 4, "%s: " + "overflow stats: sample %llu event %llu\n", + __func__, sampl_overflow, event_overflow); } #define AUX_SDB_INDEX(aux, i) ((i) % aux->sfb.num_sdb) @@ -1368,7 +1366,7 @@ static void aux_output_end(struct perf_output_handle *handle) te = aux_sdb_trailer(aux, aux->alert_mark); te->flags &= ~SDB_TE_ALERT_REQ_MASK; - debug_sprintf_event(sfdbg, 6, "aux_output_end: collect %lx SDBs\n", i); + debug_sprintf_event(sfdbg, 6, "%s: collect %#lx SDBs\n", __func__, i); } /* @@ -1428,8 +1426,8 @@ static int aux_output_begin(struct perf_output_handle *handle, debug_sprintf_event(sfdbg, 6, "aux_output_begin: " "head->alert_mark->empty_mark (num_alert, range)" - "[%lx -> %lx -> %lx] (%lx, %lx) " - "tear index %lx, tear %lx dear %lx\n", + "[%#lx -> %#lx -> %#lx] (%#lx, %#lx) " + "tear index %#lx, tear %#lx dear %#lx\n", aux->head, aux->alert_mark, aux->empty_mark, AUX_SDB_NUM_ALERT(aux), range, head / CPUM_SF_SDB_PER_TABLE, @@ -1596,13 +1594,13 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) perf_aux_output_end(&cpuhw->handle, size); pr_err("Sample data caused the AUX buffer with %lu " "pages to overflow\n", num_sdb); - debug_sprintf_event(sfdbg, 1, "head %lx range %lx " - "overflow %llx\n", + debug_sprintf_event(sfdbg, 1, "head %#lx range %#lx " + "overflow %#llx\n", aux->head, range, overflow); } else { size = AUX_SDB_NUM_ALERT(aux) << PAGE_SHIFT; perf_aux_output_end(&cpuhw->handle, size); - debug_sprintf_event(sfdbg, 6, "head %lx alert %lx " + debug_sprintf_event(sfdbg, 6, "head %#lx alert %#lx " "already full, try another\n", aux->head, aux->alert_mark); } @@ -1610,7 +1608,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) if (done) debug_sprintf_event(sfdbg, 6, "aux_reset_buffer: " - "[%lx -> %lx -> %lx] (%lx, %lx)\n", + "[%#lx -> %#lx -> %#lx] (%#lx, %#lx)\n", aux->head, aux->alert_mark, aux->empty_mark, AUX_SDB_NUM_ALERT(aux), range); } @@ -1800,7 +1798,7 @@ static int cpumsf_pmu_check_period(struct perf_event *event, u64 value) SAMPL_RATE(&event->hw) = rate; hw_init_period(&event->hw, SAMPL_RATE(&event->hw)); debug_sprintf_event(sfdbg, 4, "cpumsf_pmu_check_period:" - "cpu:%d value:%llx period:%llx freq:%d\n", + "cpu:%d value:%#llx period:%#llx freq:%d\n", event->cpu, value, event->attr.sample_period, do_freq); return 0; @@ -2111,7 +2109,7 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp) sfb_set_limits(min, max); pr_info("The sampling buffer limits have changed to: " - "min=%lu max=%lu (diag=x%lu)\n", + "min %lu max %lu (diag %lu)\n", CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR); return 0; } @@ -2129,7 +2127,7 @@ static const struct kernel_param_ops param_ops_sfb_size = { static void __init pr_cpumsf_err(unsigned int reason) { pr_err("Sampling facility support for perf is not available: " - "reason=%04x\n", reason); + "reason %#x\n", reason); } static int __init init_cpum_sampling_pmu(void) diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index fcb6c2e92b07..1e75cc983546 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct unwind_state state; + unsigned long addr; - unwind_for_each_frame(&state, current, regs, 0) - perf_callchain_store(entry, state.ip); + unwind_for_each_frame(&state, current, regs, 0) { + addr = unwind_get_return_address(&state); + if (!addr || perf_callchain_store(entry, addr)) + return; + } } /* Perf definitions for PMU event attributes in sysfs */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index b0afec673f77..6ccef5f29761 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -40,6 +40,7 @@ #include <asm/stacktrace.h> #include <asm/switch_to.h> #include <asm/runtime_instr.h> +#include <asm/unwind.h> #include "entry.h" asmlinkage void ret_from_fork(void) asm ("ret_from_fork"); @@ -178,9 +179,8 @@ EXPORT_SYMBOL(dump_fpu); unsigned long get_wchan(struct task_struct *p) { - struct stack_frame *sf, *low, *high; - unsigned long return_address; - int count; + struct unwind_state state; + unsigned long ip = 0; if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p)) return 0; @@ -188,26 +188,22 @@ unsigned long get_wchan(struct task_struct *p) if (!try_get_task_stack(p)) return 0; - low = task_stack_page(p); - high = (struct stack_frame *) task_pt_regs(p); - sf = (struct stack_frame *) p->thread.ksp; - if (sf <= low || sf > high) { - return_address = 0; - goto out; - } - for (count = 0; count < 16; count++) { - sf = (struct stack_frame *)READ_ONCE_NOCHECK(sf->back_chain); - if (sf <= low || sf > high) { - return_address = 0; - goto out; + unwind_for_each_frame(&state, p, NULL, 0) { + if (state.stack_info.type != STACK_TYPE_TASK) { + ip = 0; + break; } - return_address = READ_ONCE_NOCHECK(sf->gprs[8]); - if (!in_sched_functions(return_address)) - goto out; + + ip = unwind_get_return_address(&state); + if (!ip) + break; + + if (!in_sched_functions(ip)) + break; } -out: + put_task_stack(p); - return return_address; + return ip; } unsigned long arch_align_stack(unsigned long sp) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 44974654cbd0..6acdcf1d4074 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -724,39 +724,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early) static int smp_add_present_cpu(int cpu); -static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add) +static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail, + bool configured, bool early) { struct pcpu *pcpu; - cpumask_t avail; - int cpu, nr, i, j; + int cpu, nr, i; u16 address; nr = 0; - cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); - cpu = cpumask_first(&avail); - for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) { - if (sclp.has_core_type && info->core[i].type != boot_core_type) + if (sclp.has_core_type && core->type != boot_core_type) + return nr; + cpu = cpumask_first(avail); + address = core->core_id << smp_cpu_mt_shift; + for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) { + if (pcpu_find_address(cpu_present_mask, address + i)) continue; - address = info->core[i].core_id << smp_cpu_mt_shift; - for (j = 0; j <= smp_cpu_mtid; j++) { - if (pcpu_find_address(cpu_present_mask, address + j)) - continue; - pcpu = pcpu_devices + cpu; - pcpu->address = address + j; - pcpu->state = - (cpu >= info->configured*(smp_cpu_mtid + 1)) ? - CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; - smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); - set_cpu_present(cpu, true); - if (sysfs_add && smp_add_present_cpu(cpu) != 0) - set_cpu_present(cpu, false); - else - nr++; - cpu = cpumask_next(cpu, &avail); - if (cpu >= nr_cpu_ids) + pcpu = pcpu_devices + cpu; + pcpu->address = address + i; + if (configured) + pcpu->state = CPU_STATE_CONFIGURED; + else + pcpu->state = CPU_STATE_STANDBY; + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + set_cpu_present(cpu, true); + if (!early && smp_add_present_cpu(cpu) != 0) + set_cpu_present(cpu, false); + else + nr++; + cpumask_clear_cpu(cpu, avail); + cpu = cpumask_next(cpu, avail); + } + return nr; +} + +static int __smp_rescan_cpus(struct sclp_core_info *info, bool early) +{ + struct sclp_core_entry *core; + cpumask_t avail; + bool configured; + u16 core_id; + int nr, i; + + nr = 0; + cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); + /* + * Add IPL core first (which got logical CPU number 0) to make sure + * that all SMT threads get subsequent logical CPU numbers. + */ + if (early) { + core_id = pcpu_devices[0].address >> smp_cpu_mt_shift; + for (i = 0; i < info->configured; i++) { + core = &info->core[i]; + if (core->core_id == core_id) { + nr += smp_add_core(core, &avail, true, early); break; + } } } + for (i = 0; i < info->combined; i++) { + configured = i < info->configured; + nr += smp_add_core(&info->core[i], &avail, configured, early); + } return nr; } @@ -805,7 +833,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ get_online_cpus(); - __smp_rescan_cpus(info, 0); + __smp_rescan_cpus(info, true); put_online_cpus(); memblock_free_early((unsigned long)info, sizeof(*info)); } @@ -1148,7 +1176,7 @@ int __ref smp_rescan_cpus(void) smp_get_core_info(info, 0); get_online_cpus(); mutex_lock(&smp_cpu_state_mutex); - nr = __smp_rescan_cpus(info, 1); + nr = __smp_rescan_cpus(info, false); mutex_unlock(&smp_cpu_state_mutex); put_online_cpus(); kfree(info); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index e8766beee5ad..f9d070d016e3 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -110,15 +110,6 @@ unsigned long long notrace sched_clock(void) } NOKPROBE_SYMBOL(sched_clock); -/* - * Monotonic_clock - returns # of nanoseconds passed since time_init() - */ -unsigned long long monotonic_clock(void) -{ - return sched_clock(); -} -EXPORT_SYMBOL(monotonic_clock); - static void ext_to_timespec64(unsigned char *clk, struct timespec64 *xt) { unsigned long long high, low, rem, sec, nsec; diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index a8204f952315..fa111d3d378f 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -85,12 +85,7 @@ bool unwind_next_frame(struct unwind_state *state) } } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Decode any ftrace redirection */ - if (ip == (unsigned long) return_to_handler) - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - ip, (void *) sp); -#endif + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp); /* Update unwind state */ state->sp = sp; @@ -147,12 +142,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, reuse_sp = false; } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Decode any ftrace redirection */ - if (ip == (unsigned long) return_to_handler) - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - ip, NULL); -#endif + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL); /* Update unwind state */ state->sp = sp; diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 30a7c8c29964..ce1e4bbe53aa 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -74,7 +74,7 @@ static inline int arch_load_niai4(int *lock) { int owner; - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0040", 49) /* NIAI 4 */ " l %0,%1\n" : "=d" (owner) : "Q" (*lock) : "memory"); @@ -85,7 +85,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new) { int expected = old; - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0080", 49) /* NIAI 8 */ " cs %0,%3,%1\n" : "=d" (old), "=Q" (*lock) diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a124f19f7b3c..f0ce22220565 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -118,6 +118,7 @@ void __init paging_init(void) sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); + zone_dma_bits = 31; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS); max_zone_pfns[ZONE_NORMAL] = max_low_pfn; diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 1864a8bb9622..59ad7997fed1 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size) spin_unlock_irqrestore(&s390_kernel_write_lock, flags); } -static int __memcpy_real(void *dest, void *src, size_t count) +static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count) { register unsigned long _dest asm("2") = (unsigned long) dest; register unsigned long _len1 asm("3") = (unsigned long) count; @@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count) return rc; } -static unsigned long _memcpy_real(unsigned long dest, unsigned long src, - unsigned long count) +static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest, + unsigned long src, + unsigned long count) { int irqs_disabled, rc; unsigned long flags; if (!count) return 0; - flags = __arch_local_irq_stnsm(0xf8UL); + flags = arch_local_irq_save(); irqs_disabled = arch_irqs_disabled_flags(flags); if (!irqs_disabled) trace_hardirqs_off(); + __arch_local_irq_stnsm(0xf8); // disable DAT rc = __memcpy_real((void *) dest, (void *) src, (size_t) count); + if (flags & PSW_MASK_DAT) + __arch_local_irq_stosm(0x04); // enable DAT if (!irqs_disabled) trace_hardirqs_on(); __arch_local_irq_ssm(flags); diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 324a23947585..997ffe46e953 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -65,14 +65,14 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. # -CFLAGS_REMOVE_vdso-note.o = -pg CFLAGS_REMOVE_vclock_gettime.o = -pg +CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) -CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) +CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m elf32_sparc -soname linux-gate.so.1 #This makes sure the $(obj) subdirectory exists even though vdso32/ diff --git a/arch/um/configs/kunit_defconfig b/arch/um/configs/kunit_defconfig new file mode 100644 index 000000000000..9235b7d42d38 --- /dev/null +++ b/arch/um/configs/kunit_defconfig @@ -0,0 +1,3 @@ +CONFIG_KUNIT=y +CONFIG_KUNIT_TEST=y +CONFIG_KUNIT_EXAMPLE_TEST=y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d6e1faa28c58..8ef85139553f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1940,6 +1940,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +choice + prompt "TSX enable mode" + depends on CPU_SUP_INTEL + default X86_INTEL_TSX_MODE_OFF + help + Intel's TSX (Transactional Synchronization Extensions) feature + allows to optimize locking protocols through lock elision which + can lead to a noticeable performance boost. + + On the other hand it has been shown that TSX can be exploited + to form side channel attacks (e.g. TAA) and chances are there + will be more of those attacks discovered in the future. + + Therefore TSX is not enabled by default (aka tsx=off). An admin + might override this decision by tsx=on the command line parameter. + Even with TSX enabled, the kernel will attempt to enable the best + possible TAA mitigation setting depending on the microcode available + for the particular machine. + + This option allows to set the default tsx mode between tsx=on, =off + and =auto. See Documentation/admin-guide/kernel-parameters.txt for more + details. + + Say off if not sure, auto if TSX is in use but it should be used on safe + platforms or on if TSX is in use and the security aspect of tsx is not + relevant. + +config X86_INTEL_TSX_MODE_OFF + bool "off" + help + TSX is disabled if possible - equals to tsx=off command line parameter. + +config X86_INTEL_TSX_MODE_ON + bool "on" + help + TSX is always enabled on TSX capable HW - equals the tsx=on command + line parameter. + +config X86_INTEL_TSX_MODE_AUTO + bool "auto" + help + TSX is enabled on TSX capable HW that is believed to be safe against + side channel attacks- equals the tsx=auto command line parameter. +endchoice + config EFI bool "EFI runtime service support" depends on ACPI diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0652d3eed9bd..c4fbe379cc0b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -399,5 +399,7 @@ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 24d6598dea29..4fc61483919a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -312,9 +312,12 @@ struct kvm_rmap_head { struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; + struct list_head lpage_disallowed_link; + bool unsync; u8 mmu_valid_gen; bool mmio_cached; + bool lpage_disallowed; /* Can't be replaced by an equiv large page */ /* * The following two entries are used to key the shadow page in the @@ -859,6 +862,7 @@ struct kvm_arch { */ struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; + struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -933,6 +937,7 @@ struct kvm_arch { bool exception_payload_enabled; struct kvm_pmu_event_filter *pmu_event_filter; + struct task_struct *nx_lpage_recovery_thread; }; struct kvm_vm_stat { @@ -946,6 +951,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong nx_lpage_splits; ulong max_mmu_page_hash_collisions; }; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 6ec319ecb001..084e98da04a7 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -93,6 +93,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -103,6 +115,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 80bc209c0708..5c24a7b35166 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -314,7 +314,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the @@ -337,7 +337,7 @@ static inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 0bc530c4eb13..ad97dc155195 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1463,6 +1463,12 @@ static inline bool arch_has_pfn_modify_check(void) return boot_cpu_has_bug(X86_BUG_L1TF); } +#define arch_faults_on_old_pte arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + return false; +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6e0a3b43d027..54f5d54280f6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -988,4 +988,11 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 9e2dd2b296cd..2b0faf86da1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1586,9 +1586,6 @@ static void setup_local_APIC(void) { int cpu = smp_processor_id(); unsigned int value; -#ifdef CONFIG_X86_32 - int logical_apicid, ldr_apicid; -#endif if (disable_apic) { disable_ioapic_support(); @@ -1626,16 +1623,21 @@ static void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d7a1e5a9331c..890f60083eca 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -30,7 +30,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o +obj-y += intel.o intel_pconfig.o tsx.o obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 91c2561b905f..4c7b0fa15a19 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -105,6 +106,7 @@ void __init check_bugs(void) ssb_select_mitigation(); l1tf_select_mitigation(); mds_select_mitigation(); + taa_select_mitigation(); arch_smt_update(); @@ -269,6 +271,100 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ + if (taa_mitigation == TAA_MITIGATION_OFF) + goto out; + + if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + if (taa_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); + +out: + pr_info("%s\n", taa_strings[taa_mitigation]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -786,13 +882,10 @@ static void update_mds_branch_idle(void) } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" void cpu_bugs_smt_update(void) { - /* Enhanced IBRS implies STIBP. No update required. */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) - return; - mutex_lock(&spec_ctrl_mutex); switch (spectre_v2_user) { @@ -819,6 +912,17 @@ void cpu_bugs_smt_update(void) break; } + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1149,6 +1253,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -1304,11 +1411,24 @@ static ssize_t l1tf_show_state(char *buf) l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); +} #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} #endif static ssize_t mds_show_state(char *buf) @@ -1328,6 +1448,21 @@ static ssize_t mds_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1398,6 +1533,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MDS: return mds_show_state(buf); + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -1434,4 +1575,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9ae7d1bcd4f4..fffe21945374 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1016,13 +1016,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } -#define NO_SPECULATION BIT(0) -#define NO_MELTDOWN BIT(1) -#define NO_SSB BIT(2) -#define NO_L1TF BIT(3) -#define NO_MDS BIT(4) -#define MSBDS_ONLY BIT(5) -#define NO_SWAPGS BIT(6) +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) +#define NO_ITLB_MULTIHIT BIT(7) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1043,27 +1044,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ - VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1073,15 +1074,17 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { * good enough for our purposes. */ + VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT), + /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), {} }; @@ -1092,19 +1095,30 @@ static bool __init cpu_matches(unsigned long which) return m && !!(m->driver_data & which); } -static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +u64 x86_read_arch_cap_msr(void) { u64 ia32_cap = 0; + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + return ia32_cap; +} + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ + if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); + if (cpu_matches(NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1121,6 +1135,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (!cpu_matches(NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); + /* + * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when: + * - TSX is supported or + * - TSX_CTRL is present + * + * TSX_CTRL check is needed for cases when TSX could be disabled before + * the kernel boot e.g. kexec. + * TSX_CTRL check alone is not sufficient for cases when the microcode + * update is not present or running as guest that don't get TSX_CTRL. + */ + if (!(ia32_cap & ARCH_CAP_TAA_NO) && + (cpu_has(c, X86_FEATURE_RTM) || + (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + setup_force_cpu_bug(X86_BUG_TAA); + if (cpu_matches(NO_MELTDOWN)) return; @@ -1554,6 +1583,8 @@ void __init identify_boot_cpu(void) #endif cpu_detect_tlb(&boot_cpu_data); setup_cr_pinning(); + + tsx_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index c0e2407abdd6..38ab6e115eac 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -44,6 +44,22 @@ struct _tlb_table { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +#ifdef CONFIG_CPU_SUP_INTEL +enum tsx_ctrl_states { + TSX_CTRL_ENABLE, + TSX_CTRL_DISABLE, + TSX_CTRL_NOT_SUPPORTED, +}; + +extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; + +extern void __init tsx_init(void); +extern void tsx_enable(void); +extern void tsx_disable(void); +#else +static inline void tsx_init(void) { } +#endif /* CONFIG_CPU_SUP_INTEL */ + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); @@ -62,4 +78,6 @@ unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern u64 x86_read_arch_cap_msr(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c2fdc00df163..11d5c5950e2d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -762,6 +762,11 @@ static void init_intel(struct cpuinfo_x86 *c) detect_tme(c); init_intel_misc_features(c); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 6ea7fdc82f3c..5167bd2bb6b1 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -583,7 +583,7 @@ bool amd_filter_mce(struct mce *m) * - Prevent possible spurious interrupts from the IF bank on Family 0x17 * Models 0x10-0x2F due to Erratum #1114. */ -void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank) +static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank) { int i, num_msrs; u64 hwcr; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 743370ee4983..5f42f25bac8f 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m) if (!(m->status & MCI_STATUS_ADDRV)) return 0; - /* Checks after this one are Intel-specific: */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + /* Checks after this one are Intel/Zhaoxin-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 1; if (!(m->status & MCI_STATUS_MISCV)) @@ -507,10 +508,13 @@ EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { - if (m->cpuvendor == X86_VENDOR_AMD || - m->cpuvendor == X86_VENDOR_HYGON) { + switch (m->cpuvendor) { + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: return amd_mce_is_memory_error(m); - } else if (m->cpuvendor == X86_VENDOR_INTEL) { + + case X86_VENDOR_INTEL: + case X86_VENDOR_ZHAOXIN: /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes * @@ -527,9 +531,10 @@ bool mce_is_memory_error(struct mce *m) return (m->status & 0xef80) == BIT(7) || (m->status & 0xef00) == BIT(8) || (m->status & 0xeffc) == 0xc; - } - return false; + default: + return false; + } } EXPORT_SYMBOL_GPL(mce_is_memory_error); @@ -1127,6 +1132,12 @@ static bool __mc_check_crashing_cpu(int cpu) u64 mcgstatus; mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + + if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { + if (mcgstatus & MCG_STATUS_LMCES) + return false; + } + if (mcgstatus & MCG_STATUS_RIPV) { mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); return true; @@ -1277,9 +1288,10 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* * Check if this MCE is signaled to only this logical processor, - * on Intel only. + * on Intel, Zhaoxin only. */ - if (m.cpuvendor == X86_VENDOR_INTEL) + if (m.cpuvendor == X86_VENDOR_INTEL || + m.cpuvendor == X86_VENDOR_ZHAOXIN) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* @@ -1697,6 +1709,18 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; } + + if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { + /* + * All newer Zhaoxin CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + } + } + if (cfg->monarch_timeout < 0) cfg->monarch_timeout = 0; if (cfg->bootlog != 0) @@ -1760,6 +1784,35 @@ static void mce_centaur_feature_init(struct cpuinfo_x86 *c) } } +static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + + /* + * These CPUs have MCA bank 8 which reports only one error type called + * SVAD (System View Address Decoder). The reporting of that error is + * controlled by IA32_MC8.CTL.0. + * + * If enabled, prefetching on these CPUs will cause SVAD MCE when + * virtual machines start and result in a system panic. Always disable + * bank 8 SVAD error by default. + */ + if ((c->x86 == 7 && c->x86_model == 0x1b) || + (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (this_cpu_read(mce_num_banks) > 8) + mce_banks[8].ctl = 0; + } + + intel_init_cmci(); + intel_init_lmce(); + mce_adjust_timer = cmci_intel_adjust_timer; +} + +static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c) +{ + intel_clear_lmce(); +} + static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) { switch (c->x86_vendor) { @@ -1781,6 +1834,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_centaur_feature_init(c); break; + case X86_VENDOR_ZHAOXIN: + mce_zhaoxin_feature_init(c); + break; + default: break; } @@ -1792,6 +1849,11 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) case X86_VENDOR_INTEL: mce_intel_feature_clear(c); break; + + case X86_VENDOR_ZHAOXIN: + mce_zhaoxin_feature_clear(c); + break; + default: break; } @@ -2014,15 +2076,16 @@ static void mce_disable_error_reporting(void) static void vendor_disable_error_reporting(void) { /* - * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs - * are socket-wide. - * Disabling them for just a single offlined CPU is bad, since it will - * inhibit reporting for all shared resources on the socket like the - * last level cache (LLC), the integrated memory controller (iMC), etc. + * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these + * MSRs are socket-wide. Disabling them for just a single offlined CPU + * is bad, since it will inhibit reporting for all shared resources on + * the socket like the last level cache (LLC), the integrated memory + * controller (iMC), etc. */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || - boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) return; mce_disable_error_reporting(); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 88cd9598fa57..e270d0770134 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -85,8 +85,10 @@ static int cmci_supported(int *banks) * initialization is vendor keyed and this * makes sure none of the backdoors are entered otherwise. */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 0; + if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) return 0; rdmsrl(MSR_IA32_MCG_CAP, cap); @@ -423,7 +425,7 @@ void cmci_disable_bank(int bank) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } -static void intel_init_cmci(void) +void intel_init_cmci(void) { int banks; @@ -442,7 +444,7 @@ static void intel_init_cmci(void) cmci_recheck(); } -static void intel_init_lmce(void) +void intel_init_lmce(void) { u64 val; @@ -455,7 +457,7 @@ static void intel_init_lmce(void) wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); } -static void intel_clear_lmce(void) +void intel_clear_lmce(void) { u64 val; @@ -482,6 +484,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) case INTEL_FAM6_BROADWELL_D: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 43031db429d2..842b273bce31 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -45,11 +45,17 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval); bool mce_intel_cmci_poll(void); void mce_intel_hcpu_update(unsigned long cpu); void cmci_disable_bank(int bank); +void intel_init_cmci(void); +void intel_init_lmce(void); +void intel_clear_lmce(void); #else # define cmci_intel_adjust_timer mce_adjust_timer_default static inline bool mce_intel_cmci_poll(void) { return false; } static inline void mce_intel_hcpu_update(unsigned long cpu) { } static inline void cmci_disable_bank(int bank) { } +static inline void intel_init_cmci(void) { } +static inline void intel_init_lmce(void) { } +static inline void intel_clear_lmce(void) { } #endif void mce_timer_kick(unsigned long interval); diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 6e2becf547c5..d01e0da0163a 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -40,15 +40,58 @@ #define THERMAL_THROTTLING_EVENT 0 #define POWER_LIMIT_EVENT 1 -/* - * Current thermal event state: +/** + * struct _thermal_state - Represent the current thermal event state + * @next_check: Stores the next timestamp, when it is allowed + * to log the next warning message. + * @last_interrupt_time: Stores the timestamp for the last threshold + * high event. + * @therm_work: Delayed workqueue structure + * @count: Stores the current running count for thermal + * or power threshold interrupts. + * @last_count: Stores the previous running count for thermal + * or power threshold interrupts. + * @max_time_ms: This shows the maximum amount of time CPU was + * in throttled state for a single thermal + * threshold high to low state. + * @total_time_ms: This is a cumulative time during which CPU was + * in the throttled state. + * @rate_control_active: Set when a throttling message is logged. + * This is used for the purpose of rate-control. + * @new_event: Stores the last high/low status of the + * THERM_STATUS_PROCHOT or + * THERM_STATUS_POWER_LIMIT. + * @level: Stores whether this _thermal_state instance is + * for a CORE level or for PACKAGE level. + * @sample_index: Index for storing the next sample in the buffer + * temp_samples[]. + * @sample_count: Total number of samples collected in the buffer + * temp_samples[]. + * @average: The last moving average of temperature samples + * @baseline_temp: Temperature at which thermal threshold high + * interrupt was generated. + * @temp_samples: Storage for temperature samples to calculate + * moving average. + * + * This structure is used to represent data related to thermal state for a CPU. + * There is a separate storage for core and package level for each CPU. */ struct _thermal_state { - bool new_event; - int event; u64 next_check; + u64 last_interrupt_time; + struct delayed_work therm_work; unsigned long count; unsigned long last_count; + unsigned long max_time_ms; + unsigned long total_time_ms; + bool rate_control_active; + bool new_event; + u8 level; + u8 sample_index; + u8 sample_count; + u8 average; + u8 baseline_temp; + u8 temp_samples[3]; }; struct thermal_state { @@ -121,8 +164,22 @@ define_therm_throt_device_one_ro(package_throttle_count); define_therm_throt_device_show_func(package_power_limit, count); define_therm_throt_device_one_ro(package_power_limit_count); +define_therm_throt_device_show_func(core_throttle, max_time_ms); +define_therm_throt_device_one_ro(core_throttle_max_time_ms); + +define_therm_throt_device_show_func(package_throttle, max_time_ms); +define_therm_throt_device_one_ro(package_throttle_max_time_ms); + +define_therm_throt_device_show_func(core_throttle, total_time_ms); +define_therm_throt_device_one_ro(core_throttle_total_time_ms); + +define_therm_throt_device_show_func(package_throttle, total_time_ms); +define_therm_throt_device_one_ro(package_throttle_total_time_ms); + static struct attribute *thermal_throttle_attrs[] = { &dev_attr_core_throttle_count.attr, + &dev_attr_core_throttle_max_time_ms.attr, + &dev_attr_core_throttle_total_time_ms.attr, NULL }; @@ -135,6 +192,105 @@ static const struct attribute_group thermal_attr_group = { #define CORE_LEVEL 0 #define PACKAGE_LEVEL 1 +#define THERM_THROT_POLL_INTERVAL HZ +#define THERM_STATUS_PROCHOT_LOG BIT(1) + +static void clear_therm_status_log(int level) +{ + int msr; + u64 msr_val; + + if (level == CORE_LEVEL) + msr = MSR_IA32_THERM_STATUS; + else + msr = MSR_IA32_PACKAGE_THERM_STATUS; + + rdmsrl(msr, msr_val); + wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG); +} + +static void get_therm_status(int level, bool *proc_hot, u8 *temp) +{ + int msr; + u64 msr_val; + + if (level == CORE_LEVEL) + msr = MSR_IA32_THERM_STATUS; + else + msr = MSR_IA32_PACKAGE_THERM_STATUS; + + rdmsrl(msr, msr_val); + if (msr_val & THERM_STATUS_PROCHOT_LOG) + *proc_hot = true; + else + *proc_hot = false; + + *temp = (msr_val >> 16) & 0x7F; +} + +static void throttle_active_work(struct work_struct *work) +{ + struct _thermal_state *state = container_of(to_delayed_work(work), + struct _thermal_state, therm_work); + unsigned int i, avg, this_cpu = smp_processor_id(); + u64 now = get_jiffies_64(); + bool hot; + u8 temp; + + get_therm_status(state->level, &hot, &temp); + /* temperature value is offset from the max so lesser means hotter */ + if (!hot && temp > state->baseline_temp) { + if (state->rate_control_active) + pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n", + this_cpu, + state->level == CORE_LEVEL ? "Core" : "Package", + state->count); + + state->rate_control_active = false; + return; + } + + if (time_before64(now, state->next_check) && + state->rate_control_active) + goto re_arm; + + state->next_check = now + CHECK_INTERVAL; + + if (state->count != state->last_count) { + /* There was one new thermal interrupt */ + state->last_count = state->count; + state->average = 0; + state->sample_count = 0; + state->sample_index = 0; + } + + state->temp_samples[state->sample_index] = temp; + state->sample_count++; + state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples); + if (state->sample_count < ARRAY_SIZE(state->temp_samples)) + goto re_arm; + + avg = 0; + for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i) + avg += state->temp_samples[i]; + + avg /= ARRAY_SIZE(state->temp_samples); + + if (state->average > avg) { + pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n", + this_cpu, + state->level == CORE_LEVEL ? "Core" : "Package", + state->count); + state->rate_control_active = true; + } + + state->average = avg; + +re_arm: + clear_therm_status_log(state->level); + schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); +} + /*** * therm_throt_process - Process thermal throttling event from interrupt * @curr: Whether the condition is current or not (boolean), since the @@ -178,27 +334,33 @@ static void therm_throt_process(bool new_event, int event, int level) if (new_event) state->count++; - if (time_before64(now, state->next_check) && - state->count != state->last_count) + if (event != THERMAL_THROTTLING_EVENT) return; - state->next_check = now + CHECK_INTERVAL; - state->last_count = state->count; + if (new_event && !state->last_interrupt_time) { + bool hot; + u8 temp; + + get_therm_status(state->level, &hot, &temp); + /* + * Ignore short temperature spike as the system is not close + * to PROCHOT. 10C offset is large enough to ignore. It is + * already dropped from the high threshold temperature. + */ + if (temp > 10) + return; - /* if we just entered the thermal event */ - if (new_event) { - if (event == THERMAL_THROTTLING_EVENT) - pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", - this_cpu, - level == CORE_LEVEL ? "Core" : "Package", - state->count); - return; - } - if (old_event) { - if (event == THERMAL_THROTTLING_EVENT) - pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, - level == CORE_LEVEL ? "Core" : "Package"); - return; + state->baseline_temp = temp; + state->last_interrupt_time = now; + schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); + } else if (old_event && state->last_interrupt_time) { + unsigned long throttle_time; + + throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time); + if (throttle_time > state->max_time_ms) + state->max_time_ms = throttle_time; + state->total_time_ms += throttle_time; + state->last_interrupt_time = 0; } } @@ -244,20 +406,47 @@ static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu) if (err) return err; - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_core_power_limit_count.attr, thermal_attr_group.name); + if (err) + goto del_group; + } + if (cpu_has(c, X86_FEATURE_PTS)) { err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_throttle_count.attr, thermal_attr_group.name); - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) + if (err) + goto del_group; + + err = sysfs_add_file_to_group(&dev->kobj, + &dev_attr_package_throttle_max_time_ms.attr, + thermal_attr_group.name); + if (err) + goto del_group; + + err = sysfs_add_file_to_group(&dev->kobj, + &dev_attr_package_throttle_total_time_ms.attr, + thermal_attr_group.name); + if (err) + goto del_group; + + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_power_limit_count.attr, thermal_attr_group.name); + if (err) + goto del_group; + } } + return 0; + +del_group: + sysfs_remove_group(&dev->kobj, &thermal_attr_group); + return err; } @@ -269,15 +458,29 @@ static void thermal_throttle_remove_dev(struct device *dev) /* Get notified when a cpu comes on/off. Be hotplug friendly. */ static int thermal_throttle_online(unsigned int cpu) { + struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + state->package_throttle.level = PACKAGE_LEVEL; + state->core_throttle.level = CORE_LEVEL; + + INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work); + INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work); + return thermal_throttle_add_dev(dev, cpu); } static int thermal_throttle_offline(unsigned int cpu) { + struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + cancel_delayed_work(&state->package_throttle.therm_work); + cancel_delayed_work(&state->core_throttle.therm_work); + + state->package_throttle.rate_control_active = false; + state->core_throttle.rate_control_active = false; + thermal_throttle_remove_dev(dev); return 0; } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index a0e52bd00ecc..3f6b137ef4e6 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -567,7 +567,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) void reload_ucode_amd(void) { struct microcode_amd *mc; - u32 rev, dummy; + u32 rev, dummy __always_unused; mc = (struct microcode_amd *)amd_ucode_patch; @@ -673,7 +673,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct ucode_cpu_info *uci; struct ucode_patch *p; enum ucode_state ret; - u32 rev, dummy; + u32 rev, dummy __always_unused; BUG_ON(raw_smp_processor_id() != cpu); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index cb0fdcaf1415..7019d4b2df0c 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -63,11 +63,6 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); -/* - * Serialize late loading so that CPUs get updated one-by-one. - */ -static DEFINE_RAW_SPINLOCK(update_lock); - struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -566,11 +561,18 @@ static int __reload_late(void *info) if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) return -1; - raw_spin_lock(&update_lock); - apply_microcode_local(&err); - raw_spin_unlock(&update_lock); + /* + * On an SMT system, it suffices to load the microcode on one sibling of + * the core because the microcode engine is shared between the threads. + * Synchronization still needs to take place so that no concurrent + * loading attempts happen on multiple threads of an SMT core. See + * below. + */ + if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu) + apply_microcode_local(&err); + else + goto wait_for_siblings; - /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); ret = -1; @@ -578,14 +580,18 @@ static int __reload_late(void *info) ret = 1; } +wait_for_siblings: + if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC)) + panic("Timeout during microcode update!\n"); + /* - * Increase the wait timeout to a safe value here since we're - * serializing the microcode update and that could take a while on a - * large number of CPUs. And that is fine as the *actual* timeout will - * be determined by the last CPU finished updating and thus cut short. + * At least one thread has completed update on each core. + * For others, simply call the update to make sure the + * per-cpu cpuinfo can be updated with right microcode + * revision. */ - if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus())) - panic("Timeout during microcode update!\n"); + if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu) + apply_microcode_local(&err); return ret; } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce799cfe9434..6a99535d7f37 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -791,6 +791,7 @@ static enum ucode_state apply_microcode_intel(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); + bool bsp = c->cpu_index == boot_cpu_data.cpu_index; struct microcode_intel *mc; enum ucode_state ret; static int prev_rev; @@ -836,7 +837,7 @@ static enum ucode_state apply_microcode_intel(int cpu) return UCODE_ERROR; } - if (rev != prev_rev) { + if (bsp && rev != prev_rev) { pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", rev, mc->hdr.date & 0xffff, @@ -852,7 +853,7 @@ out: c->microcode = rev; /* Update boot_cpu_data's revision too, if we're on the BSP: */ - if (c->cpu_index == boot_cpu_data.cpu_index) + if (bsp) boot_cpu_data.microcode = rev; return ret; diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index efbd54cc4e69..055c8613b531 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } md.priv = of->kn->priv; resid = md.u.rid; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index a46dee8e78db..2e3b06d6bbc6 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, } rdtgrp = rdtgroup_kn_lock_live(of->kn); - rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; - rdt_last_cmd_puts("Directory was removed\n"); goto unlock; } @@ -2648,10 +2646,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, int ret; prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); - rdt_last_cmd_clear(); if (!prdtgrp) { ret = -ENODEV; - rdt_last_cmd_puts("Directory was removed\n"); goto out_unlock; } diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c new file mode 100644 index 000000000000..3e20d322bc98 --- /dev/null +++ b/arch/x86/kernel/cpu/tsx.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Transactional Synchronization Extensions (TSX) control. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Pawan Gupta <pawan.kumar.gupta@linux.intel.com> + */ + +#include <linux/cpufeature.h> + +#include <asm/cmdline.h> + +#include "cpu.h" + +enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; + +void tsx_disable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Force all transactions to immediately abort */ + tsx |= TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is not enumerated in CPUID. + * This is visible to userspace and will ensure they + * do not waste resources trying TSX transactions that + * will always abort. + */ + tsx |= TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +void tsx_enable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Enable the RTM feature in the cpu */ + tsx &= ~TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is enumerated in CPUID. + * This is visible to userspace and will ensure they + * can enumerate and use the TSX feature. + */ + tsx &= ~TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +static bool __init tsx_ctrl_is_supported(void) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); +} + +static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) +{ + if (boot_cpu_has_bug(X86_BUG_TAA)) + return TSX_CTRL_DISABLE; + + return TSX_CTRL_ENABLE; +} + +void __init tsx_init(void) +{ + char arg[5] = {}; + int ret; + + if (!tsx_ctrl_is_supported()) + return; + + ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg)); + if (ret >= 0) { + if (!strcmp(arg, "on")) { + tsx_ctrl_state = TSX_CTRL_ENABLE; + } else if (!strcmp(arg, "off")) { + tsx_ctrl_state = TSX_CTRL_DISABLE; + } else if (!strcmp(arg, "auto")) { + tsx_ctrl_state = x86_get_tsx_auto_mode(); + } else { + tsx_ctrl_state = TSX_CTRL_DISABLE; + pr_err("tsx: invalid option, defaulting to off\n"); + } + } else { + /* tsx= not provided */ + if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO)) + tsx_ctrl_state = x86_get_tsx_auto_mode(); + else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF)) + tsx_ctrl_state = TSX_CTRL_DISABLE; + else + tsx_ctrl_state = TSX_CTRL_ENABLE; + } + + if (tsx_ctrl_state == TSX_CTRL_DISABLE) { + tsx_disable(); + + /* + * tsx_disable() will change the state of the + * RTM CPUID bit. Clear it here since it is now + * expected to be not set. + */ + setup_clear_cpu_cap(X86_FEATURE_RTM); + } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { + + /* + * HW defaults TSX to be enabled at bootup. + * We may still need the TSX enable support + * during init for special cases like + * kexec after TSX is disabled. + */ + tsx_enable(); + + /* + * tsx_enable() will change the state of the + * RTM CPUID bit. Force it here since it is now + * expected to be set. + */ + setup_force_cpu_cap(X86_FEATURE_RTM); + } +} diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 753b8cfe8b8a..87b97897a881 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); + /* + * Handle the case where stack trace is collected _before_ + * cea_exception_stacks had been initialized. + */ + if (!begin) + return false; + end = begin + sizeof(struct cea_exception_stacks); /* Bail if @stack is outside the exception stack area. */ if (stk < begin || stk >= end) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6f6b1d04dadf..4cba91ec8049 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -710,6 +710,8 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3ec4, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c59454c382fd..7e322e2daaf5 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1505,6 +1505,9 @@ void __init tsc_init(void) return; } + if (tsc_clocksource_reliable || no_tsc_watchdog) + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 24c23c66b226..2ce9da58611e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kthread.h> #include <asm/page.h> #include <asm/pat.h> @@ -47,6 +48,35 @@ #include <asm/kvm_page_track.h> #include "trace.h" +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +#ifdef CONFIG_PREEMPT_RT +/* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ +static uint __read_mostly nx_huge_pages_recovery_ratio = 0; +#else +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; +#endif + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -352,6 +382,11 @@ static inline bool spte_ad_need_write_protect(u64 spte) return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK; } +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} + static inline u64 spte_shadow_accessed_mask(u64 spte) { MMU_WARN_ON(is_mmio_spte(spte)); @@ -1190,6 +1225,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -1207,6 +1253,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); +} + static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, struct kvm_memory_slot *slot) { @@ -2792,6 +2845,9 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return list_unstable; } @@ -3013,6 +3069,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -3233,9 +3294,32 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) +{ + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, int map_writable, int level, kvm_pfn_t pfn, - bool prefault) + bool prefault, bool lpage_disallowed) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; @@ -3248,6 +3332,12 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, trace_kvm_mmu_spte_requested(gpa, level, pfn); for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == level) break; @@ -3258,6 +3348,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, it.level - 1, true, ACC_ALL); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -3306,7 +3398,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, * here. */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && + !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; @@ -3550,11 +3642,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - bool force_pt_level = false; + bool force_pt_level; kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + force_pt_level = lpage_disallowed; level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { /* @@ -3588,7 +3683,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault); + r = __direct_map(vcpu, v, write, map_writable, level, pfn, + prefault, false); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); @@ -4174,6 +4270,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; bool map_writable; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); @@ -4184,8 +4282,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); + force_pt_level = + lpage_disallowed || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL); level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { if (level > PT_DIRECTORY_LEVEL && @@ -4214,7 +4313,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault); + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, + prefault, lpage_disallowed); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); @@ -5914,9 +6014,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + !kvm_is_zone_device_pfn(pfn) && + PageTransCompoundMap(pfn_to_page(pfn))) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -6155,10 +6255,59 @@ static void kvm_set_mmio_spte_mask(void) kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); } +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + mutex_lock(&kvm->slots_lock); + kvm_mmu_zap_all_fast(kvm); + mutex_unlock(&kvm->slots_lock); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; +} + int kvm_mmu_module_init(void) { int ret = -ENOMEM; + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + /* * MMU roles use union aliasing which is, generally speaking, an * undefined behavior. However, we supposedly know how compilers behave @@ -6238,3 +6387,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 11f8ec89433b..d55674f44a18 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -210,4 +210,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 7d5cdb3af594..97b21e7fd013 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -614,13 +614,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; int top_level, ret; - gfn_t base_gfn; + gfn_t gfn, base_gfn; direct_access = gw->pte_access; @@ -665,13 +666,25 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - base_gfn = gw->gfn; + /* + * FNAME(page_fault) might have clobbered the bottom bits of + * gw->gfn, restore them from the virtual address. + */ + gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT); + base_gfn = gfn; trace_kvm_mmu_spte_requested(addr, gw->level, pfn); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); - base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel); + + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == hlevel) break; @@ -683,6 +696,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, sp = kvm_mmu_get_page(vcpu, base_gfn, addr, it.level - 1, true, direct_access); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -759,9 +774,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + bool force_pt_level = lpage_disallowed; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -851,7 +868,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (!force_pt_level) transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); + level, pfn, map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 5d21a4ab28cf..04a8212704c1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1268,6 +1268,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block is the one expected to change PID.NDST and the + * wakeup handler expects the vCPU to be on the blocked_vcpu_list that + * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up + * correctly. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + goto after_clear_sn; + } + /* The full case. */ do { old.control = new.control = pi_desc->control; @@ -1283,6 +1295,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); +after_clear_sn: + /* * Clear SN before reading the bitmap. The VT-d firmware * writes the bitmap and reads SN atomically (5.2.3 in the @@ -1291,7 +1305,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) */ smp_mb__after_atomic(); - if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)) + if (!pi_is_pir_empty(pi_desc)) pi_set_on(pi_desc); } @@ -6137,7 +6151,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) if (pi_test_on(&vmx->pi_desc)) { pi_clear_on(&vmx->pi_desc); /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); @@ -6167,7 +6181,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { - return pi_test_on(vcpu_to_pi_desc(vcpu)); + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + return pi_test_on(pi_desc) || + (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc)); } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index bee16687dc0b..5a0f34b1e226 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -355,6 +355,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); +} + static inline void pi_set_sn(struct pi_desc *pi_desc) { set_bit(POSTED_INTR_SN, @@ -373,6 +378,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + static inline int pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ff395f812719..5d530521f11d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -213,6 +213,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, { "largepages", VM_STAT(lpages, .mode = 0444) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -1132,13 +1133,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * - * This list is modified at module load time to reflect the + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) + * extract the supported MSRs from the related const lists. + * msrs_to_save is selected from the msrs_to_save_all to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs * may depend on host virtualization features rather than host cpu features. */ -static u32 msrs_to_save[] = { +static const u32 msrs_to_save_all[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1179,9 +1182,10 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, }; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; static unsigned num_msrs_to_save; -static u32 emulated_msrs[] = { +static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, @@ -1220,7 +1224,7 @@ static u32 emulated_msrs[] = { * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs. * We always support the "true" VMX control MSRs, even if the host * processor does not, so I am putting these registers here rather - * than in msrs_to_save. + * than in msrs_to_save_all. */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, @@ -1239,13 +1243,14 @@ static u32 emulated_msrs[] = { MSR_KVM_POLL_CONTROL, }; +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* * List of msr numbers which are used to expose MSR-based features that * can be used by a hypervisor to validate requested CPU features. */ -static u32 msr_based_features[] = { +static const u32 msr_based_features_all[] = { MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, MSR_IA32_VMX_PINBASED_CTLS, @@ -1270,6 +1275,7 @@ static u32 msr_based_features[] = { MSR_IA32_ARCH_CAPABILITIES, }; +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_features; static u64 kvm_get_arch_capabilities(void) @@ -1280,6 +1286,14 @@ static u64 kvm_get_arch_capabilities(void) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1298,6 +1312,25 @@ static u64 kvm_get_arch_capabilities(void) if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + /* + * On TAA affected systems, export MDS_NO=0 when: + * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1. + * - Updated microcode is present. This is detected by + * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures + * that VERW clears CPU buffers. + * + * When MDS_NO=0 is exported, guests deploy clear CPU buffer + * mitigation and don't complain: + * + * "Vulnerable: Clear CPU buffers attempted, no microcode" + * + * If TSX is disabled on the system, guests are also mitigated against + * TAA and clear CPU buffer mitigation is not required for guests. + */ + if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) && + (data & ARCH_CAP_TSX_CTRL_MSR)) + data &= ~ARCH_CAP_MDS_NO; + return data; } @@ -5090,22 +5123,26 @@ static void kvm_init_msr_list(void) { struct x86_pmu_capability x86_pmu; u32 dummy[2]; - unsigned i, j; + unsigned i; BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, - "Please update the fixed PMCs in msrs_to_save[]"); + "Please update the fixed PMCs in msrs_to_saved_all[]"); perf_get_x86_pmu_capability(&x86_pmu); - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { - if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) + num_msrs_to_save = 0; + num_emulated_msrs = 0; + num_msr_based_features = 0; + + for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { + if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) continue; /* * Even MSRs that are valid in the host may not be exposed * to the guests in some cases. */ - switch (msrs_to_save[i]) { + switch (msrs_to_save_all[i]) { case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported()) continue; @@ -5133,17 +5170,17 @@ static void kvm_init_msr_list(void) break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { if (!kvm_x86_ops->pt_supported() || - msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >= + msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: - if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >= + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) continue; break; case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: - if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) continue; } @@ -5151,34 +5188,25 @@ static void kvm_init_msr_list(void) break; } - if (j < i) - msrs_to_save[j] = msrs_to_save[i]; - j++; + msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; } - num_msrs_to_save = j; - for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i])) continue; - if (j < i) - emulated_msrs[j] = emulated_msrs[i]; - j++; + emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - num_emulated_msrs = j; - for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) { struct kvm_msr_entry msr; - msr.index = msr_based_features[i]; + msr.index = msr_based_features_all[i]; if (kvm_get_msr_feature(&msr)) continue; - if (j < i) - msr_based_features[j] = msr_based_features[i]; - j++; + msr_based_features[num_msr_based_features++] = msr_based_features_all[i]; } - num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -9428,6 +9456,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -9456,6 +9485,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return kvm_x86_ops->vm_init(kvm); } +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); +} + static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); @@ -9557,6 +9591,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(x86_set_memory_region); +void kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ + kvm_mmu_pre_destroy_vm(kvm); +} + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { diff --git a/block/Kconfig b/block/Kconfig index 41c0917ce622..c23094a14a2b 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -32,6 +32,9 @@ config BLK_RQ_ALLOC_TIME config BLK_SCSI_REQUEST bool +config BLK_CGROUP_RWSTAT + bool + config BLK_DEV_BSG bool "Block layer SG support v4" default y @@ -86,6 +89,7 @@ config BLK_DEV_ZONED config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y + select BLK_CGROUP_RWSTAT ---help--- Block layer bio throttling support. It can be used to limit the IO rate to a device. IO rate policies are per cgroup and diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index b89310a022ad..7df14133adc8 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -31,6 +31,7 @@ config IOSCHED_BFQ config BFQ_GROUP_IOSCHED bool "BFQ hierarchical scheduling support" depends on IOSCHED_BFQ && BLK_CGROUP + select BLK_CGROUP_RWSTAT ---help--- Enable hierarchical scheduling in BFQ, using the blkio diff --git a/block/Makefile b/block/Makefile index 9ef57ace90d4..205a5f2fef17 100644 --- a/block/Makefile +++ b/block/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o +obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 86a607cf19a1..cea0ae12f937 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -347,6 +347,14 @@ void bfqg_and_blkg_put(struct bfq_group *bfqg) bfqg_put(bfqg); } +void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq) +{ + struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg); + + blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq)); + blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1); +} + /* @stats = 0 */ static void bfqg_stats_reset(struct bfqg_stats *stats) { @@ -431,6 +439,8 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg) static void bfqg_stats_exit(struct bfqg_stats *stats) { + blkg_rwstat_exit(&stats->bytes); + blkg_rwstat_exit(&stats->ios); #ifdef CONFIG_BFQ_CGROUP_DEBUG blkg_rwstat_exit(&stats->merged); blkg_rwstat_exit(&stats->service_time); @@ -448,6 +458,10 @@ static void bfqg_stats_exit(struct bfqg_stats *stats) static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp) { + if (blkg_rwstat_init(&stats->bytes, gfp) || + blkg_rwstat_init(&stats->ios, gfp)) + return -ENOMEM; + #ifdef CONFIG_BFQ_CGROUP_DEBUG if (blkg_rwstat_init(&stats->merged, gfp) || blkg_rwstat_init(&stats->service_time, gfp) || @@ -1057,18 +1071,35 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of, return bfq_io_set_device_weight(of, buf, nbytes, off); } -#ifdef CONFIG_BFQ_CGROUP_DEBUG -static int bfqg_print_stat(struct seq_file *sf, void *v) +static int bfqg_print_rwstat(struct seq_file *sf, void *v) { - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, - &blkcg_policy_bfq, seq_cft(sf)->private, false); + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, + &blkcg_policy_bfq, seq_cft(sf)->private, true); return 0; } -static int bfqg_print_rwstat(struct seq_file *sf, void *v) +static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) { - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, - &blkcg_policy_bfq, seq_cft(sf)->private, true); + struct blkg_rwstat_sample sum; + + blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum); + return __blkg_prfill_rwstat(sf, pd, &sum); +} + +static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq, + seq_cft(sf)->private, true); + return 0; +} + +#ifdef CONFIG_BFQ_CGROUP_DEBUG +static int bfqg_print_stat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, + &blkcg_policy_bfq, seq_cft(sf)->private, false); return 0; } @@ -1097,15 +1128,6 @@ static u64 bfqg_prfill_stat_recursive(struct seq_file *sf, return __blkg_prfill_u64(sf, pd, sum); } -static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf, - struct blkg_policy_data *pd, int off) -{ - struct blkg_rwstat_sample sum; - - blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum); - return __blkg_prfill_rwstat(sf, pd, &sum); -} - static int bfqg_print_stat_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), @@ -1114,18 +1136,11 @@ static int bfqg_print_stat_recursive(struct seq_file *sf, void *v) return 0; } -static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq, - seq_cft(sf)->private, true); - return 0; -} - static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd, int off) { - u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes); + struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg); + u64 sum = blkg_rwstat_total(&bfqg->stats.bytes); return __blkg_prfill_u64(sf, pd, sum >> 9); } @@ -1142,8 +1157,8 @@ static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf, { struct blkg_rwstat_sample tmp; - blkg_rwstat_recursive_sum(pd->blkg, NULL, - offsetof(struct blkcg_gq, stat_bytes), &tmp); + blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq, + offsetof(struct bfq_group, stats.bytes), &tmp); return __blkg_prfill_u64(sf, pd, (tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9); @@ -1226,13 +1241,13 @@ struct cftype bfq_blkcg_legacy_files[] = { /* statistics, covers only the tasks in the bfqg */ { .name = "bfq.io_service_bytes", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes, + .private = offsetof(struct bfq_group, stats.bytes), + .seq_show = bfqg_print_rwstat, }, { .name = "bfq.io_serviced", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios, + .private = offsetof(struct bfq_group, stats.ios), + .seq_show = bfqg_print_rwstat, }, #ifdef CONFIG_BFQ_CGROUP_DEBUG { @@ -1269,13 +1284,13 @@ struct cftype bfq_blkcg_legacy_files[] = { /* the same statistics which cover the bfqg and its descendants */ { .name = "bfq.io_service_bytes_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes_recursive, + .private = offsetof(struct bfq_group, stats.bytes), + .seq_show = bfqg_print_rwstat_recursive, }, { .name = "bfq.io_serviced_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios_recursive, + .private = offsetof(struct bfq_group, stats.ios), + .seq_show = bfqg_print_rwstat_recursive, }, #ifdef CONFIG_BFQ_CGROUP_DEBUG { diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0319d6339822..ad4af4aaf2ce 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2713,6 +2713,28 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) } } + +static +void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + /* + * To prevent bfqq's service guarantees from being violated, + * bfqq may be left busy, i.e., queued for service, even if + * empty (see comments in __bfq_bfqq_expire() for + * details). But, if no process will send requests to bfqq any + * longer, then there is no point in keeping bfqq queued for + * service. In addition, keeping bfqq queued for service, but + * with no process ref any longer, may have caused bfqq to be + * freed when dequeued from service. But this is assumed to + * never happen. + */ + if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) && + bfqq != bfqd->in_service_queue) + bfq_del_bfqq_busy(bfqd, bfqq, false); + + bfq_put_queue(bfqq); +} + static void bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) @@ -2783,8 +2805,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, */ new_bfqq->pid = -1; bfqq->bic = NULL; - /* release process reference to bfqq */ - bfq_put_queue(bfqq); + bfq_release_process_ref(bfqd, bfqq); } static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, @@ -4899,7 +4920,7 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_put_cooperator(bfqq); - bfq_put_queue(bfqq); /* release process reference */ + bfq_release_process_ref(bfqd, bfqq); } static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) @@ -5001,8 +5022,7 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bfqq = bic_to_bfqq(bic, false); if (bfqq) { - /* release process reference on this queue */ - bfq_put_queue(bfqq); + bfq_release_process_ref(bfqd, bfqq); bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic); bic_set_bfqq(bic, bfqq, false); } @@ -5464,6 +5484,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool idle_timer_disabled = false; unsigned int cmd_flags; +#ifdef CONFIG_BFQ_GROUP_IOSCHED + if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio) + bfqg_stats_update_legacy_io(q, rq); +#endif spin_lock_irq(&bfqd->lock); if (blk_mq_sched_try_insert_merge(q, rq)) { spin_unlock_irq(&bfqd->lock); @@ -5963,7 +5987,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) bfq_put_cooperator(bfqq); - bfq_put_queue(bfqq); + bfq_release_process_ref(bfqq->bfqd, bfqq); return NULL; } diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 5d1a519640f6..8526f20c53bc 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -10,6 +10,8 @@ #include <linux/hrtimer.h> #include <linux/blk-cgroup.h> +#include "blk-cgroup-rwstat.h" + #define BFQ_IOPRIO_CLASSES 3 #define BFQ_CL_IDLE_TIMEOUT (HZ/5) @@ -809,6 +811,9 @@ struct bfq_stat { }; struct bfqg_stats { + /* basic stats */ + struct blkg_rwstat bytes; + struct blkg_rwstat ios; #ifdef CONFIG_BFQ_CGROUP_DEBUG /* number of ios merged */ struct blkg_rwstat merged; @@ -956,6 +961,7 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); /* ---------------- cgroups-support interface ---------------- */ +void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq); void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, unsigned int op); void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op); @@ -1062,6 +1068,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ char pid_str[MAX_PID_STR_LENGTH]; \ + if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \ + break; \ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ blk_add_cgroup_trace_msg((bfqd)->queue, \ bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \ @@ -1078,6 +1086,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ char pid_str[MAX_PID_STR_LENGTH]; \ + if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \ + break; \ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str, \ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ diff --git a/block/bio.c b/block/bio.c index 8f0ed6228fc5..b1170ec18464 100644 --- a/block/bio.c +++ b/block/bio.c @@ -751,7 +751,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page, if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return false; - if (bio->bi_vcnt > 0) { + if (bio->bi_vcnt > 0 && !bio_full(bio, len)) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page_is_mergeable(bv, page, len, off, same_page)) { diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c new file mode 100644 index 000000000000..85d5790ac49b --- /dev/null +++ b/block/blk-cgroup-rwstat.c @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT. + * Do not use in new code. + */ +#include "blk-cgroup-rwstat.h" + +int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) +{ + int i, ret; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); + if (ret) { + while (--i >= 0) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); + return ret; + } + atomic64_set(&rwstat->aux_cnt[i], 0); + } + return 0; +} +EXPORT_SYMBOL_GPL(blkg_rwstat_init); + +void blkg_rwstat_exit(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); +} +EXPORT_SYMBOL_GPL(blkg_rwstat_exit); + +/** + * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat + * @sf: seq_file to print to + * @pd: policy private data of interest + * @rwstat: rwstat to print + * + * Print @rwstat to @sf for the device assocaited with @pd. + */ +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat_sample *rwstat) +{ + static const char *rwstr[] = { + [BLKG_RWSTAT_READ] = "Read", + [BLKG_RWSTAT_WRITE] = "Write", + [BLKG_RWSTAT_SYNC] = "Sync", + [BLKG_RWSTAT_ASYNC] = "Async", + [BLKG_RWSTAT_DISCARD] = "Discard", + }; + const char *dname = blkg_dev_name(pd->blkg); + u64 v; + int i; + + if (!dname) + return 0; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + seq_printf(sf, "%s %s %llu\n", dname, rwstr[i], + rwstat->cnt[i]); + + v = rwstat->cnt[BLKG_RWSTAT_READ] + + rwstat->cnt[BLKG_RWSTAT_WRITE] + + rwstat->cnt[BLKG_RWSTAT_DISCARD]; + seq_printf(sf, "%s Total %llu\n", dname, v); + return v; +} +EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat); + +/** + * blkg_prfill_rwstat - prfill callback for blkg_rwstat + * @sf: seq_file to print to + * @pd: policy private data of interest + * @off: offset to the blkg_rwstat in @pd + * + * prfill callback for printing a blkg_rwstat. + */ +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off) +{ + struct blkg_rwstat_sample rwstat = { }; + + blkg_rwstat_read((void *)pd + off, &rwstat); + return __blkg_prfill_rwstat(sf, pd, &rwstat); +} +EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); + +/** + * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat + * @blkg: blkg of interest + * @pol: blkcg_policy which contains the blkg_rwstat + * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg + * @sum: blkg_rwstat_sample structure containing the results + * + * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its + * online descendants and their aux counts. The caller must be holding the + * queue lock for online tests. + * + * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it + * is at @off bytes into @blkg's blkg_policy_data of the policy. + */ +void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, + int off, struct blkg_rwstat_sample *sum) +{ + struct blkcg_gq *pos_blkg; + struct cgroup_subsys_state *pos_css; + unsigned int i; + + lockdep_assert_held(&blkg->q->queue_lock); + + rcu_read_lock(); + blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { + struct blkg_rwstat *rwstat; + + if (!pos_blkg->online) + continue; + + if (pol) + rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off; + else + rwstat = (void *)pos_blkg + off; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h new file mode 100644 index 000000000000..ee746919c41f --- /dev/null +++ b/block/blk-cgroup-rwstat.h @@ -0,0 +1,149 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT. + * Do not use in new code. + */ +#ifndef _BLK_CGROUP_RWSTAT_H +#define _BLK_CGROUP_RWSTAT_H + +#include <linux/blk-cgroup.h> + +enum blkg_rwstat_type { + BLKG_RWSTAT_READ, + BLKG_RWSTAT_WRITE, + BLKG_RWSTAT_SYNC, + BLKG_RWSTAT_ASYNC, + BLKG_RWSTAT_DISCARD, + + BLKG_RWSTAT_NR, + BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, +}; + +/* + * blkg_[rw]stat->aux_cnt is excluded for local stats but included for + * recursive. Used to carry stats of dead children. + */ +struct blkg_rwstat { + struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; + atomic64_t aux_cnt[BLKG_RWSTAT_NR]; +}; + +struct blkg_rwstat_sample { + u64 cnt[BLKG_RWSTAT_NR]; +}; + +static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, + unsigned int idx) +{ + return atomic64_read(&rwstat->aux_cnt[idx]) + + percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); +} + +int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp); +void blkg_rwstat_exit(struct blkg_rwstat *rwstat); +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat_sample *rwstat); +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off); +void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, + int off, struct blkg_rwstat_sample *sum); + + +/** + * blkg_rwstat_add - add a value to a blkg_rwstat + * @rwstat: target blkg_rwstat + * @op: REQ_OP and flags + * @val: value to add + * + * Add @val to @rwstat. The counters are chosen according to @rw. The + * caller is responsible for synchronizing calls to this function. + */ +static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, + unsigned int op, uint64_t val) +{ + struct percpu_counter *cnt; + + if (op_is_discard(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; + else if (op_is_write(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; + + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); + + if (op_is_sync(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; + + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); +} + +/** + * blkg_rwstat_read - read the current values of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Read the current snapshot of @rwstat and return it in the aux counts. + */ +static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, + struct blkg_rwstat_sample *result) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + result->cnt[i] = + percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); +} + +/** + * blkg_rwstat_total - read the total count of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Return the total count of @rwstat regardless of the IO direction. This + * function can be called without synchronization and takes care of u64 + * atomicity. + */ +static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) +{ + struct blkg_rwstat_sample tmp = { }; + + blkg_rwstat_read(rwstat, &tmp); + return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; +} + +/** + * blkg_rwstat_reset - reset a blkg_rwstat + * @rwstat: blkg_rwstat to reset + */ +static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + percpu_counter_set(&rwstat->cpu_cnt[i], 0); + atomic64_set(&rwstat->aux_cnt[i], 0); + } +} + +/** + * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count + * @to: the destination blkg_rwstat + * @from: the source + * + * Add @from's count including the aux one to @to's aux count. + */ +static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, + struct blkg_rwstat *from) +{ + u64 sum[BLKG_RWSTAT_NR]; + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]), + &to->aux_cnt[i]); +} +#endif /* _BLK_CGROUP_RWSTAT_H */ diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5d21027b1faf..708dea92dac8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -80,8 +80,7 @@ static void blkg_free(struct blkcg_gq *blkg) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); - blkg_rwstat_exit(&blkg->stat_ios); - blkg_rwstat_exit(&blkg->stat_bytes); + free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } @@ -146,7 +145,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, gfp_t gfp_mask) { struct blkcg_gq *blkg; - int i; + int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node); @@ -156,8 +155,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto err_free; - if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) || - blkg_rwstat_init(&blkg->stat_ios, gfp_mask)) + blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); + if (!blkg->iostat_cpu) goto err_free; blkg->q = q; @@ -167,6 +166,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); blkg->blkcg = blkcg; + u64_stats_init(&blkg->iostat.sync); + for_each_possible_cpu(cpu) + u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); + for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; @@ -393,7 +396,6 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; - struct blkcg_gq *parent = blkg->parent; int i; lockdep_assert_held(&blkg->q->queue_lock); @@ -410,11 +412,6 @@ static void blkg_destroy(struct blkcg_gq *blkg) pol->pd_offline_fn(blkg->pd[i]); } - if (parent) { - blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); - blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); - } - blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); @@ -464,7 +461,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; - int i; + int i, cpu; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); @@ -475,8 +472,12 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - blkg_rwstat_reset(&blkg->stat_bytes); - blkg_rwstat_reset(&blkg->stat_ios); + for_each_possible_cpu(cpu) { + struct blkg_iostat_set *bis = + per_cpu_ptr(blkg->iostat_cpu, cpu); + memset(bis, 0, sizeof(*bis)); + } + memset(&blkg->iostat, 0, sizeof(blkg->iostat)); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -560,186 +561,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); -/** - * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat - * @sf: seq_file to print to - * @pd: policy private data of interest - * @rwstat: rwstat to print - * - * Print @rwstat to @sf for the device assocaited with @pd. - */ -u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - const struct blkg_rwstat_sample *rwstat) -{ - static const char *rwstr[] = { - [BLKG_RWSTAT_READ] = "Read", - [BLKG_RWSTAT_WRITE] = "Write", - [BLKG_RWSTAT_SYNC] = "Sync", - [BLKG_RWSTAT_ASYNC] = "Async", - [BLKG_RWSTAT_DISCARD] = "Discard", - }; - const char *dname = blkg_dev_name(pd->blkg); - u64 v; - int i; - - if (!dname) - return 0; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - seq_printf(sf, "%s %s %llu\n", dname, rwstr[i], - rwstat->cnt[i]); - - v = rwstat->cnt[BLKG_RWSTAT_READ] + - rwstat->cnt[BLKG_RWSTAT_WRITE] + - rwstat->cnt[BLKG_RWSTAT_DISCARD]; - seq_printf(sf, "%s Total %llu\n", dname, v); - return v; -} -EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat); - -/** - * blkg_prfill_rwstat - prfill callback for blkg_rwstat - * @sf: seq_file to print to - * @pd: policy private data of interest - * @off: offset to the blkg_rwstat in @pd - * - * prfill callback for printing a blkg_rwstat. - */ -u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - int off) -{ - struct blkg_rwstat_sample rwstat = { }; - - blkg_rwstat_read((void *)pd + off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} -EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); - -static u64 blkg_prfill_rwstat_field(struct seq_file *sf, - struct blkg_policy_data *pd, int off) -{ - struct blkg_rwstat_sample rwstat = { }; - - blkg_rwstat_read((void *)pd->blkg + off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} - -/** - * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes - * @sf: seq_file to print to - * @v: unused - * - * To be used as cftype->seq_show to print blkg->stat_bytes. - * cftype->private must be set to the blkcg_policy. - */ -int blkg_print_stat_bytes(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_bytes), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_bytes); - -/** - * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios - * @sf: seq_file to print to - * @v: unused - * - * To be used as cftype->seq_show to print blkg->stat_ios. cftype->private - * must be set to the blkcg_policy. - */ -int blkg_print_stat_ios(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_ios), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_ios); - -static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf, - struct blkg_policy_data *pd, - int off) -{ - struct blkg_rwstat_sample rwstat; - - blkg_rwstat_recursive_sum(pd->blkg, NULL, off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} - -/** - * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes - * @sf: seq_file to print to - * @v: unused - */ -int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field_recursive, - (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_bytes), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive); - -/** - * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios - * @sf: seq_file to print to - * @v: unused - */ -int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field_recursive, - (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_ios), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive); - -/** - * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat - * @blkg: blkg of interest - * @pol: blkcg_policy which contains the blkg_rwstat - * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg - * @sum: blkg_rwstat_sample structure containing the results - * - * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its - * online descendants and their aux counts. The caller must be holding the - * queue lock for online tests. - * - * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it - * is at @off bytes into @blkg's blkg_policy_data of the policy. - */ -void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, - int off, struct blkg_rwstat_sample *sum) -{ - struct blkcg_gq *pos_blkg; - struct cgroup_subsys_state *pos_css; - unsigned int i; - - lockdep_assert_held(&blkg->q->queue_lock); - - rcu_read_lock(); - blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { - struct blkg_rwstat *rwstat; - - if (!pos_blkg->online) - continue; - - if (pol) - rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off; - else - rwstat = (void *)pos_blkg + off; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); - } - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); - /* Performs queue bypass and policy enabled checks then looks up blkg. */ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, const struct blkcg_policy *pol, @@ -923,20 +744,27 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; + cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + struct blkg_iostat_set *bis = &blkg->iostat; const char *dname; char *buf; - struct blkg_rwstat_sample rwstat; u64 rbytes, wbytes, rios, wios, dbytes, dios; size_t size = seq_get_buf(sf, &buf), off = 0; int i; bool has_stats = false; + unsigned seq; + + spin_lock_irq(&blkg->q->queue_lock); + + if (!blkg->online) + goto skip; dname = blkg_dev_name(blkg); if (!dname) - continue; + goto skip; /* * Hooray string manipulation, count is the size written NOT @@ -946,21 +774,16 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) */ off += scnprintf(buf+off, size-off, "%s ", dname); - spin_lock_irq(&blkg->q->queue_lock); - - blkg_rwstat_recursive_sum(blkg, NULL, - offsetof(struct blkcg_gq, stat_bytes), &rwstat); - rbytes = rwstat.cnt[BLKG_RWSTAT_READ]; - wbytes = rwstat.cnt[BLKG_RWSTAT_WRITE]; - dbytes = rwstat.cnt[BLKG_RWSTAT_DISCARD]; - - blkg_rwstat_recursive_sum(blkg, NULL, - offsetof(struct blkcg_gq, stat_ios), &rwstat); - rios = rwstat.cnt[BLKG_RWSTAT_READ]; - wios = rwstat.cnt[BLKG_RWSTAT_WRITE]; - dios = rwstat.cnt[BLKG_RWSTAT_DISCARD]; + do { + seq = u64_stats_fetch_begin(&bis->sync); - spin_unlock_irq(&blkg->q->queue_lock); + rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; + wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; + dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; + rios = bis->cur.ios[BLKG_IOSTAT_READ]; + wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; + dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; + } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { has_stats = true; @@ -999,6 +822,8 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) seq_commit(sf, -1); } } + skip: + spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); @@ -1294,6 +1119,77 @@ static int blkcg_can_attach(struct cgroup_taskset *tset) return ret; } +static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] = src->bytes[i]; + dst->ios[i] = src->ios[i]; + } +} + +static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] += src->bytes[i]; + dst->ios[i] += src->ios[i]; + } +} + +static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] -= src->bytes[i]; + dst->ios[i] -= src->ios[i]; + } +} + +static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct blkcg_gq *blkg; + + rcu_read_lock(); + + hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + struct blkcg_gq *parent = blkg->parent; + struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); + struct blkg_iostat cur, delta; + unsigned seq; + + /* fetch the current per-cpu values */ + do { + seq = u64_stats_fetch_begin(&bisc->sync); + blkg_iostat_set(&cur, &bisc->cur); + } while (u64_stats_fetch_retry(&bisc->sync, seq)); + + /* propagate percpu delta to global */ + u64_stats_update_begin(&blkg->iostat.sync); + blkg_iostat_set(&delta, &cur); + blkg_iostat_sub(&delta, &bisc->last); + blkg_iostat_add(&blkg->iostat.cur, &delta); + blkg_iostat_add(&bisc->last, &delta); + u64_stats_update_end(&blkg->iostat.sync); + + /* propagate global delta to parent */ + if (parent) { + u64_stats_update_begin(&parent->iostat.sync); + blkg_iostat_set(&delta, &blkg->iostat.cur); + blkg_iostat_sub(&delta, &blkg->iostat.last); + blkg_iostat_add(&parent->iostat.cur, &delta); + blkg_iostat_add(&blkg->iostat.last, &delta); + u64_stats_update_end(&parent->iostat.sync); + } + } + + rcu_read_unlock(); +} + static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; @@ -1326,6 +1222,7 @@ struct cgroup_subsys io_cgrp_subsys = { .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .can_attach = blkcg_can_attach, + .css_rstat_flush = blkcg_rstat_flush, .bind = blkcg_bind, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, diff --git a/block/blk-core.c b/block/blk-core.c index d5e668ec751b..a1e228752083 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -132,6 +132,9 @@ static const char *const blk_op_name[] = { REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), + REQ_OP_NAME(ZONE_OPEN), + REQ_OP_NAME(ZONE_CLOSE), + REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(SCSI_IN), @@ -336,14 +339,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying); */ void blk_cleanup_queue(struct request_queue *q) { + WARN_ON_ONCE(blk_queue_registered(q)); + /* mark @q DYING, no new request or merges will be allowed afterwards */ - mutex_lock(&q->sysfs_lock); blk_set_queue_dying(q); blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); blk_queue_flag_set(QUEUE_FLAG_DYING, q); - mutex_unlock(&q->sysfs_lock); /* * Drain all requests queued before DYING marking. Set DEAD flag to @@ -848,11 +851,7 @@ static inline int blk_partition_remap(struct bio *bio) if (unlikely(bio_check_ro(bio, p))) goto out; - /* - * Zone reset does not include bi_size so bio_sectors() is always 0. - * Include a test for the reset op code and perform the remap if needed. - */ - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) { + if (bio_sectors(bio)) { if (bio_check_eod(bio, part_nr_sects_read(p))) goto out; bio->bi_iter.bi_sector += p->start_sect; @@ -936,6 +935,9 @@ generic_make_request_checks(struct bio *bio) goto not_supported; break; case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: if (!blk_queue_is_zoned(q)) goto not_supported; break; diff --git a/block/blk-exec.c b/block/blk-exec.c index 1db44ca0f4a6..e20a852ae432 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -55,6 +55,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, rq->rq_disk = bd_disk; rq->end_io = done; + blk_account_io_start(rq, true); + /* * don't check dying flag for MQ because the request won't * be reused after dying flag is set diff --git a/block/blk-flush.c b/block/blk-flush.c index 1eec9cbe5a0a..1777346baf06 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -136,6 +136,17 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) blk_mq_add_to_requeue_list(rq, add_front, true); } +static void blk_account_io_flush(struct request *rq) +{ + struct hd_struct *part = &rq->rq_disk->part0; + + part_stat_lock(); + part_stat_inc(part, ios[STAT_FLUSH]); + part_stat_add(part, nsecs[STAT_FLUSH], + ktime_get_ns() - rq->start_time_ns); + part_stat_unlock(); +} + /** * blk_flush_complete_seq - complete flush sequence * @rq: PREFLUSH/FUA request being sequenced @@ -185,7 +196,7 @@ static void blk_flush_complete_seq(struct request *rq, case REQ_FSEQ_DONE: /* - * @rq was previously adjusted by blk_flush_issue() for + * @rq was previously adjusted by blk_insert_flush() for * flush sequencing and may already have gone through the * flush data request completion path. Restore @rq for * normal completion and end it. @@ -212,6 +223,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); struct blk_mq_hw_ctx *hctx; + blk_account_io_flush(flush_rq); + /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); diff --git a/block/blk-iocost.c b/block/blk-iocost.c index a7ed434eae03..e01267f99183 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1057,9 +1057,12 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) atomic64_set(&iocg->active_period, cur_period); /* already activated or breaking leaf-only constraint? */ - for (i = iocg->level; i > 0; i--) - if (!list_empty(&iocg->active_list)) + if (!list_empty(&iocg->active_list)) + goto succeed_unlock; + for (i = iocg->level - 1; i > 0; i--) + if (!list_empty(&iocg->ancestors[i]->active_list)) goto fail_unlock; + if (iocg->child_active_sum) goto fail_unlock; @@ -1101,6 +1104,7 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) ioc_start_period(ioc, now); } +succeed_unlock: spin_unlock_irq(&ioc->lock); return true; diff --git a/block/blk-merge.c b/block/blk-merge.c index 48e6725b32ee..d783bdc4559b 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -293,7 +293,7 @@ split: void __blk_queue_split(struct request_queue *q, struct bio **bio, unsigned int *nr_segs) { - struct bio *split; + struct bio *split = NULL; switch (bio_op(*bio)) { case REQ_OP_DISCARD: @@ -309,6 +309,21 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio, nr_segs); break; default: + /* + * All drivers must accept single-segments bios that are <= + * PAGE_SIZE. This is a quick and dirty check that relies on + * the fact that bi_io_vec[0] is always valid if a bio has data. + * The check might lead to occasional false negatives when bios + * are cloned, but compared to the performance impact of cloned + * bios themselves the loop below doesn't matter anyway. + */ + if (!q->limits.chunk_sectors && + (*bio)->bi_vcnt == 1 && + ((*bio)->bi_io_vec[0].bv_len + + (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) { + *nr_segs = 1; + break; + } split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs); break; } diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index a0d3ce30fa08..062229395a50 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -74,10 +74,8 @@ static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr, if (!entry->show) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->show(ctx, page); + res = entry->show(ctx, page); mutex_unlock(&q->sysfs_lock); return res; } @@ -97,10 +95,8 @@ static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr, if (!entry->store) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->store(ctx, page, length); + res = entry->store(ctx, page, length); mutex_unlock(&q->sysfs_lock); return res; } @@ -120,10 +116,8 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj, if (!entry->show) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->show(hctx, page); + res = entry->show(hctx, page); mutex_unlock(&q->sysfs_lock); return res; } @@ -144,10 +138,8 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj, if (!entry->store) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->store(hctx, page, length); + res = entry->store(hctx, page, length); mutex_unlock(&q->sysfs_lock); return res; } @@ -166,20 +158,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx, static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) { + const size_t size = PAGE_SIZE - 1; unsigned int i, first = 1; - ssize_t ret = 0; + int ret = 0, pos = 0; for_each_cpu(i, hctx->cpumask) { if (first) - ret += sprintf(ret + page, "%u", i); + ret = snprintf(pos + page, size - pos, "%u", i); else - ret += sprintf(ret + page, ", %u", i); + ret = snprintf(pos + page, size - pos, ", %u", i); + + if (ret >= size - pos) + break; first = 0; + pos += ret; } - ret += sprintf(ret + page, "\n"); - return ret; + ret = snprintf(pos + page, size + 1 - pos, "\n"); + return pos + ret; } static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = { diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 008388e82b5c..fbacde454718 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -15,14 +15,6 @@ #include "blk-mq.h" #include "blk-mq-tag.h" -bool blk_mq_has_free_tags(struct blk_mq_tags *tags) -{ - if (!tags) - return true; - - return sbitmap_any_bit_clear(&tags->bitmap_tags.sb); -} - /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 61deab0b5a5a..15bc74acb57e 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -28,7 +28,6 @@ extern void blk_mq_free_tags(struct blk_mq_tags *tags); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); -extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); diff --git a/block/blk-mq.c b/block/blk-mq.c index ec791156e9cc..323c9cb28066 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -93,7 +93,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct mq_inflight { struct hd_struct *part; - unsigned int *inflight; + unsigned int inflight[2]; }; static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, @@ -102,45 +102,29 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, { struct mq_inflight *mi = priv; - /* - * index[0] counts the specific partition that was asked for. - */ if (rq->part == mi->part) - mi->inflight[0]++; + mi->inflight[rq_data_dir(rq)]++; return true; } unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) { - unsigned inflight[2]; - struct mq_inflight mi = { .part = part, .inflight = inflight, }; + struct mq_inflight mi = { .part = part }; - inflight[0] = inflight[1] = 0; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); - return inflight[0]; -} - -static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx, - struct request *rq, void *priv, - bool reserved) -{ - struct mq_inflight *mi = priv; - - if (rq->part == mi->part) - mi->inflight[rq_data_dir(rq)]++; - - return true; + return mi.inflight[0] + mi.inflight[1]; } void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]) { - struct mq_inflight mi = { .part = part, .inflight = inflight, }; + struct mq_inflight mi = { .part = part }; - inflight[0] = inflight[1] = 0; - blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi); + blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); + inflight[0] = mi.inflight[0]; + inflight[1] = mi.inflight[1]; } void blk_freeze_queue_start(struct request_queue *q) @@ -276,12 +260,6 @@ void blk_mq_wake_waiters(struct request_queue *q) blk_mq_tag_wakeup_all(hctx->tags, true); } -bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) -{ - return blk_mq_has_free_tags(hctx->tags); -} -EXPORT_SYMBOL(blk_mq_can_queue); - /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. @@ -663,18 +641,6 @@ bool blk_mq_complete_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_complete_request); -int blk_mq_request_started(struct request *rq) -{ - return blk_mq_rq_state(rq) != MQ_RQ_IDLE; -} -EXPORT_SYMBOL_GPL(blk_mq_request_started); - -int blk_mq_request_completed(struct request *rq) -{ - return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; -} -EXPORT_SYMBOL_GPL(blk_mq_request_completed); - void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; @@ -1064,7 +1030,7 @@ bool blk_mq_get_driver_tag(struct request *rq) bool shared; if (rq->tag != -1) - goto done; + return true; if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag)) data.flags |= BLK_MQ_REQ_RESERVED; @@ -1079,7 +1045,6 @@ bool blk_mq_get_driver_tag(struct request *rq) data.hctx->tags->rqs[rq->tag] = rq; } -done: return rq->tag != -1; } @@ -1486,7 +1451,7 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); -bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { int srcu_idx; bool need_run; @@ -1504,12 +1469,8 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) blk_mq_hctx_has_pending(hctx); hctx_unlock(hctx, srcu_idx); - if (need_run) { + if (need_run) __blk_mq_delay_run_hw_queue(hctx, async, 0); - return true; - } - - return false; } EXPORT_SYMBOL(blk_mq_run_hw_queue); @@ -2789,6 +2750,23 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, int i, j, end; struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx; + if (q->nr_hw_queues < set->nr_hw_queues) { + struct blk_mq_hw_ctx **new_hctxs; + + new_hctxs = kcalloc_node(set->nr_hw_queues, + sizeof(*new_hctxs), GFP_KERNEL, + set->numa_node); + if (!new_hctxs) + return; + if (hctxs) + memcpy(new_hctxs, hctxs, q->nr_hw_queues * + sizeof(*hctxs)); + q->queue_hw_ctx = new_hctxs; + q->nr_hw_queues = set->nr_hw_queues; + kfree(hctxs); + hctxs = new_hctxs; + } + /* protect against switching io scheduler */ mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { @@ -2844,19 +2822,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, mutex_unlock(&q->sysfs_lock); } -/* - * Maximum number of hardware queues we support. For single sets, we'll never - * have more than the CPUs (software queues). For multiple sets, the tag_set - * user may have set ->nr_hw_queues larger. - */ -static unsigned int nr_hw_queues(struct blk_mq_tag_set *set) -{ - if (set->nr_maps == 1) - return nr_cpu_ids; - - return max(set->nr_hw_queues, nr_cpu_ids); -} - struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q, bool elevator_init) @@ -2876,12 +2841,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); - q->nr_queues = nr_hw_queues(set); - q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)), - GFP_KERNEL, set->numa_node); - if (!q->queue_hw_ctx) - goto err_sys_init; - INIT_LIST_HEAD(&q->unused_hctx_list); spin_lock_init(&q->unused_hctx_lock); @@ -2929,7 +2888,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, err_hctxs: kfree(q->queue_hw_ctx); q->nr_hw_queues = 0; -err_sys_init: blk_mq_sysfs_deinit(q); err_poll: blk_stat_free_callback(q->poll_cb); @@ -3030,6 +2988,29 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) } } +static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set, + int cur_nr_hw_queues, int new_nr_hw_queues) +{ + struct blk_mq_tags **new_tags; + + if (cur_nr_hw_queues >= new_nr_hw_queues) + return 0; + + new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *), + GFP_KERNEL, set->numa_node); + if (!new_tags) + return -ENOMEM; + + if (set->tags) + memcpy(new_tags, set->tags, cur_nr_hw_queues * + sizeof(*set->tags)); + kfree(set->tags); + set->tags = new_tags; + set->nr_hw_queues = new_nr_hw_queues; + + return 0; +} + /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the @@ -3083,9 +3064,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; - set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *), - GFP_KERNEL, set->numa_node); - if (!set->tags) + if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0) return -ENOMEM; ret = -ENOMEM; @@ -3126,7 +3105,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; - for (i = 0; i < nr_hw_queues(set); i++) + for (i = 0; i < set->nr_hw_queues; i++) blk_mq_free_map_and_requests(set, i); for (j = 0; j < set->nr_maps; j++) { @@ -3271,10 +3250,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); /* - * Sync with blk_mq_queue_tag_busy_iter. - */ - synchronize_rcu(); - /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done * updating the new sw to hw queue mappings. @@ -3288,6 +3263,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_sysfs_unregister(q); } + if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) < + 0) + goto reregister; + prev_nr_hw_queues = set->nr_hw_queues; set->nr_hw_queues = nr_hw_queues; blk_mq_update_queue_map(set); @@ -3304,6 +3283,7 @@ fallback: blk_mq_map_swqueue(q); } +reregister: list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register(q); blk_mq_debugfs_register_hctxs(q); diff --git a/block/blk-mq.h b/block/blk-mq.h index 32c62c64e6c2..eaaca8fc1c28 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -128,15 +128,6 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_release(struct request_queue *q); -/** - * blk_mq_rq_state() - read the current MQ_RQ_* state of a request - * @rq: target request. - */ -static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) -{ - return READ_ONCE(rq->state); -} - static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 457d9ba3eb20..6e7ec87d49fa 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -42,17 +42,13 @@ static __latent_entropy void blk_done_softirq(struct softirq_action *h) static void trigger_softirq(void *data) { struct request *rq = data; - unsigned long flags; struct list_head *list; - local_irq_save(flags); list = this_cpu_ptr(&blk_cpu_done); list_add_tail(&rq->ipi_list, list); if (list->next == &rq->ipi_list) raise_softirq_irqoff(BLOCK_SOFTIRQ); - - local_irq_restore(flags); } /* diff --git a/block/blk-stat.c b/block/blk-stat.c index 940f15d600f8..7da302ff88d0 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -53,7 +53,7 @@ void blk_stat_add(struct request *rq, u64 now) struct request_queue *q = rq->q; struct blk_stat_callback *cb; struct blk_rq_stat *stat; - int bucket; + int bucket, cpu; u64 value; value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; @@ -61,6 +61,7 @@ void blk_stat_add(struct request *rq, u64 now) blk_throtl_stat_add(rq, value); rcu_read_lock(); + cpu = get_cpu(); list_for_each_entry_rcu(cb, &q->stats->callbacks, list) { if (!blk_stat_is_active(cb)) continue; @@ -69,10 +70,10 @@ void blk_stat_add(struct request *rq, u64 now) if (bucket < 0) continue; - stat = &get_cpu_ptr(cb->cpu_stat)[bucket]; + stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket]; blk_rq_stat_add(stat, value); - put_cpu_ptr(cb->cpu_stat); } + put_cpu(); rcu_read_unlock(); } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 46f5198be017..fca9b158f4a0 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -801,10 +801,6 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page) if (!entry->show) return -EIO; mutex_lock(&q->sysfs_lock); - if (blk_queue_dying(q)) { - mutex_unlock(&q->sysfs_lock); - return -ENOENT; - } res = entry->show(q, page); mutex_unlock(&q->sysfs_lock); return res; @@ -823,10 +819,6 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, q = container_of(kobj, struct request_queue, kobj); mutex_lock(&q->sysfs_lock); - if (blk_queue_dying(q)) { - mutex_unlock(&q->sysfs_lock); - return -ENOENT; - } res = entry->store(q, page, length); mutex_unlock(&q->sysfs_lock); return res; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 18f773e52dfb..98233c9c65a8 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -12,6 +12,7 @@ #include <linux/blktrace_api.h> #include <linux/blk-cgroup.h> #include "blk.h" +#include "blk-cgroup-rwstat.h" /* Max dispatch from a group in 1 round */ static int throtl_grp_quantum = 8; @@ -176,6 +177,9 @@ struct throtl_grp { unsigned int bio_cnt; /* total bios */ unsigned int bad_bio_cnt; /* bios exceeding latency threshold */ unsigned long bio_cnt_reset_time; + + struct blkg_rwstat stat_bytes; + struct blkg_rwstat stat_ios; }; /* We measure latency for request size from <= 4k to >= 1M */ @@ -489,6 +493,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, if (!tg) return NULL; + if (blkg_rwstat_init(&tg->stat_bytes, gfp)) + goto err_free_tg; + + if (blkg_rwstat_init(&tg->stat_ios, gfp)) + goto err_exit_stat_bytes; + throtl_service_queue_init(&tg->service_queue); for (rw = READ; rw <= WRITE; rw++) { @@ -513,6 +523,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD; return &tg->pd; + +err_exit_stat_bytes: + blkg_rwstat_exit(&tg->stat_bytes); +err_free_tg: + kfree(tg); + return NULL; } static void throtl_pd_init(struct blkg_policy_data *pd) @@ -611,6 +627,8 @@ static void throtl_pd_free(struct blkg_policy_data *pd) struct throtl_grp *tg = pd_to_tg(pd); del_timer_sync(&tg->service_queue.pending_timer); + blkg_rwstat_exit(&tg->stat_bytes); + blkg_rwstat_exit(&tg->stat_ios); kfree(tg); } @@ -1464,6 +1482,32 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of, return tg_set_conf(of, buf, nbytes, off, false); } +static int tg_print_rwstat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + blkg_prfill_rwstat, &blkcg_policy_throtl, + seq_cft(sf)->private, true); + return 0; +} + +static u64 tg_prfill_rwstat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct blkg_rwstat_sample sum; + + blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_throtl, off, + &sum); + return __blkg_prfill_rwstat(sf, pd, &sum); +} + +static int tg_print_rwstat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + tg_prfill_rwstat_recursive, &blkcg_policy_throtl, + seq_cft(sf)->private, true); + return 0; +} + static struct cftype throtl_legacy_files[] = { { .name = "throttle.read_bps_device", @@ -1491,23 +1535,23 @@ static struct cftype throtl_legacy_files[] = { }, { .name = "throttle.io_service_bytes", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_bytes, + .private = offsetof(struct throtl_grp, stat_bytes), + .seq_show = tg_print_rwstat, }, { .name = "throttle.io_service_bytes_recursive", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_bytes_recursive, + .private = offsetof(struct throtl_grp, stat_bytes), + .seq_show = tg_print_rwstat_recursive, }, { .name = "throttle.io_serviced", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_ios, + .private = offsetof(struct throtl_grp, stat_ios), + .seq_show = tg_print_rwstat, }, { .name = "throttle.io_serviced_recursive", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_ios_recursive, + .private = offsetof(struct throtl_grp, stat_ios), + .seq_show = tg_print_rwstat_recursive, }, { } /* terminate */ }; @@ -2127,7 +2171,16 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, WARN_ON_ONCE(!rcu_read_lock_held()); /* see throtl_charge_bio() */ - if (bio_flagged(bio, BIO_THROTTLED) || !tg->has_rules[rw]) + if (bio_flagged(bio, BIO_THROTTLED)) + goto out; + + if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) { + blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf, + bio->bi_iter.bi_size); + blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1); + } + + if (!tg->has_rules[rw]) goto out; spin_lock_irq(&q->queue_lock); diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 4bc5f260248a..6fad6f3f6980 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -93,172 +93,85 @@ unsigned int blkdev_nr_zones(struct block_device *bdev) if (!blk_queue_is_zoned(q)) return 0; - return __blkdev_nr_zones(q, bdev->bd_part->nr_sects); + return __blkdev_nr_zones(q, get_capacity(bdev->bd_disk)); } EXPORT_SYMBOL_GPL(blkdev_nr_zones); -/* - * Check that a zone report belongs to this partition, and if yes, fix its start - * sector and write pointer and return true. Return false otherwise. - */ -static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep) -{ - sector_t offset = get_start_sect(bdev); - - if (rep->start < offset) - return false; - - rep->start -= offset; - if (rep->start + rep->len > bdev->bd_part->nr_sects) - return false; - - if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL) - rep->wp = rep->start + rep->len; - else - rep->wp -= offset; - return true; -} - -static int blk_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) -{ - struct request_queue *q = disk->queue; - unsigned int z = 0, n, nrz = *nr_zones; - sector_t capacity = get_capacity(disk); - int ret; - - while (z < nrz && sector < capacity) { - n = nrz - z; - ret = disk->fops->report_zones(disk, sector, &zones[z], &n); - if (ret) - return ret; - if (!n) - break; - sector += blk_queue_zone_sectors(q) * n; - z += n; - } - - WARN_ON(z > *nr_zones); - *nr_zones = z; - - return 0; -} - /** * blkdev_report_zones - Get zones information * @bdev: Target block device * @sector: Sector from which to report zones - * @zones: Array of zone structures where to return the zones information - * @nr_zones: Number of zone structures in the zone array + * @nr_zones: Maximum number of zones to report + * @cb: Callback function called for each reported zone + * @data: Private data for the callback * * Description: - * Get zone information starting from the zone containing @sector. - * The number of zone information reported may be less than the number - * requested by @nr_zones. The number of zones actually reported is - * returned in @nr_zones. - * The caller must use memalloc_noXX_save/restore() calls to control - * memory allocations done within this function (zone array and command - * buffer allocation by the device driver). + * Get zone information starting from the zone containing @sector for at most + * @nr_zones, and call @cb for each zone reported by the device. + * To report all zones in a device starting from @sector, the BLK_ALL_ZONES + * constant can be passed to @nr_zones. + * Returns the number of zones reported by the device, or a negative errno + * value in case of failure. + * + * Note: The caller must use memalloc_noXX_save/restore() calls to control + * memory allocations done within this function. */ int blkdev_report_zones(struct block_device *bdev, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { - struct request_queue *q = bdev_get_queue(bdev); - unsigned int i, nrz; - int ret; - - if (!blk_queue_is_zoned(q)) - return -EOPNOTSUPP; + struct gendisk *disk = bdev->bd_disk; + sector_t capacity = get_capacity(disk); - /* - * A block device that advertized itself as zoned must have a - * report_zones method. If it does not have one defined, the device - * driver has a bug. So warn about that. - */ - if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones)) + if (!blk_queue_is_zoned(bdev_get_queue(bdev)) || + WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; - if (!*nr_zones || sector >= bdev->bd_part->nr_sects) { - *nr_zones = 0; + if (!nr_zones || sector >= capacity) return 0; - } - - nrz = min(*nr_zones, - __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector)); - ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector, - zones, &nrz); - if (ret) - return ret; - - for (i = 0; i < nrz; i++) { - if (!blkdev_report_zone(bdev, zones)) - break; - zones++; - } - *nr_zones = i; - - return 0; + return disk->fops->report_zones(disk, sector, nr_zones, cb, data); } EXPORT_SYMBOL_GPL(blkdev_report_zones); -/* - * Special case of zone reset operation to reset all zones in one command, - * useful for applications like mkfs. - */ -static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask) -{ - struct bio *bio = bio_alloc(gfp_mask, 0); - int ret; - - /* across the zones operations, don't need any sectors */ - bio_set_dev(bio, bdev); - bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0); - - ret = submit_bio_wait(bio); - bio_put(bio); - - return ret; -} - static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev, + sector_t sector, sector_t nr_sectors) { if (!blk_queue_zone_resetall(bdev_get_queue(bdev))) return false; - if (nr_sectors != part_nr_sects_read(bdev->bd_part)) - return false; /* - * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is - * the entire disk, that is, if the blocks device start offset is 0 and - * its capacity is the same as the entire disk. + * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors + * of the applicable zone range is the entire disk. */ - return get_start_sect(bdev) == 0 && - part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk); + return !sector && nr_sectors == get_capacity(bdev->bd_disk); } /** - * blkdev_reset_zones - Reset zones write pointer + * blkdev_zone_mgmt - Execute a zone management operation on a range of zones * @bdev: Target block device - * @sector: Start sector of the first zone to reset - * @nr_sectors: Number of sectors, at least the length of one zone + * @op: Operation to be performed on the zones + * @sector: Start sector of the first zone to operate on + * @nr_sectors: Number of sectors, should be at least the length of one zone and + * must be zone size aligned. * @gfp_mask: Memory allocation flags (for bio_alloc) * * Description: - * Reset the write pointer of the zones contained in the range + * Perform the specified operation on the range of zones specified by * @sector..@sector+@nr_sectors. Specifying the entire disk sector range * is valid, but the specified range should not contain conventional zones. + * The operation to execute on each zone can be a zone reset, open, close + * or finish request. */ -int blkdev_reset_zones(struct block_device *bdev, - sector_t sector, sector_t nr_sectors, - gfp_t gfp_mask) +int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, + sector_t sector, sector_t nr_sectors, + gfp_t gfp_mask) { struct request_queue *q = bdev_get_queue(bdev); - sector_t zone_sectors; + sector_t zone_sectors = blk_queue_zone_sectors(q); + sector_t capacity = get_capacity(bdev->bd_disk); sector_t end_sector = sector + nr_sectors; struct bio *bio = NULL; - struct blk_plug plug; int ret; if (!blk_queue_is_zoned(q)) @@ -267,45 +180,62 @@ int blkdev_reset_zones(struct block_device *bdev, if (bdev_read_only(bdev)) return -EPERM; - if (!nr_sectors || end_sector > bdev->bd_part->nr_sects) + if (!op_is_zone_mgmt(op)) + return -EOPNOTSUPP; + + if (!nr_sectors || end_sector > capacity) /* Out of range */ return -EINVAL; - if (blkdev_allow_reset_all_zones(bdev, nr_sectors)) - return __blkdev_reset_all_zones(bdev, gfp_mask); - /* Check alignment (handle eventual smaller last zone) */ - zone_sectors = blk_queue_zone_sectors(q); if (sector & (zone_sectors - 1)) return -EINVAL; - if ((nr_sectors & (zone_sectors - 1)) && - end_sector != bdev->bd_part->nr_sects) + if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity) return -EINVAL; - blk_start_plug(&plug); while (sector < end_sector) { - bio = blk_next_bio(bio, 0, gfp_mask); - bio->bi_iter.bi_sector = sector; bio_set_dev(bio, bdev); - bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0); + /* + * Special case for the zone reset operation that reset all + * zones, this is useful for applications like mkfs. + */ + if (op == REQ_OP_ZONE_RESET && + blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) { + bio->bi_opf = REQ_OP_ZONE_RESET_ALL; + break; + } + + bio->bi_opf = op; + bio->bi_iter.bi_sector = sector; sector += zone_sectors; /* This may take a while, so be nice to others */ cond_resched(); - } ret = submit_bio_wait(bio); bio_put(bio); - blk_finish_plug(&plug); - return ret; } -EXPORT_SYMBOL_GPL(blkdev_reset_zones); +EXPORT_SYMBOL_GPL(blkdev_zone_mgmt); + +struct zone_report_args { + struct blk_zone __user *zones; +}; + +static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct zone_report_args *args = data; + + if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone))) + return -EFAULT; + return 0; +} /* * BLKREPORTZONE ioctl processing. @@ -315,9 +245,9 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; + struct zone_report_args args; struct request_queue *q; struct blk_zone_report rep; - struct blk_zone *zones; int ret; if (!argp) @@ -339,44 +269,29 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, if (!rep.nr_zones) return -EINVAL; - rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones); - - zones = kvmalloc_array(rep.nr_zones, sizeof(struct blk_zone), - GFP_KERNEL | __GFP_ZERO); - if (!zones) - return -ENOMEM; - - ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones); - if (ret) - goto out; - - if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) { - ret = -EFAULT; - goto out; - } - - if (rep.nr_zones) { - if (copy_to_user(argp + sizeof(struct blk_zone_report), zones, - sizeof(struct blk_zone) * rep.nr_zones)) - ret = -EFAULT; - } - - out: - kvfree(zones); + args.zones = argp + sizeof(struct blk_zone_report); + ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones, + blkdev_copy_zone_to_user, &args); + if (ret < 0) + return ret; - return ret; + rep.nr_zones = ret; + if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) + return -EFAULT; + return 0; } /* - * BLKRESETZONE ioctl processing. + * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. */ -int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct request_queue *q; struct blk_zone_range zrange; + enum req_opf op; if (!argp) return -EINVAL; @@ -397,8 +312,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) return -EFAULT; - return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors, - GFP_KERNEL); + switch (cmd) { + case BLKRESETZONE: + op = REQ_OP_ZONE_RESET; + break; + case BLKOPENZONE: + op = REQ_OP_ZONE_OPEN; + break; + case BLKCLOSEZONE: + op = REQ_OP_ZONE_CLOSE; + break; + case BLKFINISHZONE: + op = REQ_OP_ZONE_FINISH; + break; + default: + return -ENOTTY; + } + + return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors, + GFP_KERNEL); } static inline unsigned long *blk_alloc_zone_bitmap(int node, @@ -408,37 +340,99 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node, GFP_NOIO, node); } +void blk_queue_free_zone_bitmaps(struct request_queue *q) +{ + kfree(q->seq_zones_bitmap); + q->seq_zones_bitmap = NULL; + kfree(q->seq_zones_wlock); + q->seq_zones_wlock = NULL; +} + +struct blk_revalidate_zone_args { + struct gendisk *disk; + unsigned long *seq_zones_bitmap; + unsigned long *seq_zones_wlock; + sector_t sector; +}; + /* - * Allocate an array of struct blk_zone to get nr_zones zone information. - * The allocated array may be smaller than nr_zones. + * Helper function to check the validity of zones of a zoned block device. */ -static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones) +static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, + void *data) { - struct blk_zone *zones; - size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES); + struct blk_revalidate_zone_args *args = data; + struct gendisk *disk = args->disk; + struct request_queue *q = disk->queue; + sector_t zone_sectors = blk_queue_zone_sectors(q); + sector_t capacity = get_capacity(disk); /* - * GFP_KERNEL here is meaningless as the caller task context has - * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones() - * with memalloc_noio_save(). + * All zones must have the same size, with the exception on an eventual + * smaller last zone. */ - zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL); - if (!zones) { - *nr_zones = 0; - return NULL; + if (zone->start + zone_sectors < capacity && + zone->len != zone_sectors) { + pr_warn("%s: Invalid zoned device with non constant zone size\n", + disk->disk_name); + return false; } - *nr_zones = nrz; + if (zone->start + zone->len >= capacity && + zone->len > zone_sectors) { + pr_warn("%s: Invalid zoned device with larger last zone size\n", + disk->disk_name); + return -ENODEV; + } + + /* Check for holes in the zone report */ + if (zone->start != args->sector) { + pr_warn("%s: Zone gap at sectors %llu..%llu\n", + disk->disk_name, args->sector, zone->start); + return -ENODEV; + } - return zones; + /* Check zone type */ + switch (zone->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: + break; + default: + pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n", + disk->disk_name, (int)zone->type, zone->start); + return -ENODEV; + } + + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, args->seq_zones_bitmap); + + args->sector += zone->len; + return 0; } -void blk_queue_free_zone_bitmaps(struct request_queue *q) +static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones, + struct blk_revalidate_zone_args *args) { - kfree(q->seq_zones_bitmap); - q->seq_zones_bitmap = NULL; - kfree(q->seq_zones_wlock); - q->seq_zones_wlock = NULL; + /* + * Ensure that all memory allocations in this context are done as + * if GFP_NOIO was specified. + */ + unsigned int noio_flag = memalloc_noio_save(); + struct request_queue *q = disk->queue; + int ret; + + args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->seq_zones_wlock) + return -ENOMEM; + args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->seq_zones_bitmap) + return -ENOMEM; + + ret = disk->fops->report_zones(disk, 0, nr_zones, + blk_revalidate_zone_cb, args); + memalloc_noio_restore(noio_flag); + return ret; } /** @@ -454,13 +448,12 @@ int blk_revalidate_disk_zones(struct gendisk *disk) { struct request_queue *q = disk->queue; unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk)); - unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; - unsigned int i, rep_nr_zones = 0, z = 0, nrz; - struct blk_zone *zones = NULL; - unsigned int noio_flag; - sector_t sector = 0; + struct blk_revalidate_zone_args args = { .disk = disk }; int ret = 0; + if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) + return -EIO; + /* * BIO based queues do not use a scheduler so only q->nr_zones * needs to be updated so that the sysfs exposed value is correct. @@ -470,78 +463,28 @@ int blk_revalidate_disk_zones(struct gendisk *disk) return 0; } - /* - * Ensure that all memory allocations in this context are done as - * if GFP_NOIO was specified. - */ - noio_flag = memalloc_noio_save(); - - if (!blk_queue_is_zoned(q) || !nr_zones) { - nr_zones = 0; - goto update; - } - - /* Allocate bitmaps */ - ret = -ENOMEM; - seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!seq_zones_wlock) - goto out; - seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!seq_zones_bitmap) - goto out; - - /* Get zone information and initialize seq_zones_bitmap */ - rep_nr_zones = nr_zones; - zones = blk_alloc_zones(&rep_nr_zones); - if (!zones) - goto out; - - while (z < nr_zones) { - nrz = min(nr_zones - z, rep_nr_zones); - ret = blk_report_zones(disk, sector, zones, &nrz); - if (ret) - goto out; - if (!nrz) - break; - for (i = 0; i < nrz; i++) { - if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(z, seq_zones_bitmap); - z++; - } - sector += nrz * blk_queue_zone_sectors(q); - } - - if (WARN_ON(z != nr_zones)) { - ret = -EIO; - goto out; - } + if (nr_zones) + ret = blk_update_zone_info(disk, nr_zones, &args); -update: /* * Install the new bitmaps, making sure the queue is stopped and * all I/Os are completed (i.e. a scheduler is not referencing the * bitmaps). */ blk_mq_freeze_queue(q); - q->nr_zones = nr_zones; - swap(q->seq_zones_wlock, seq_zones_wlock); - swap(q->seq_zones_bitmap, seq_zones_bitmap); - blk_mq_unfreeze_queue(q); - -out: - memalloc_noio_restore(noio_flag); - - kvfree(zones); - kfree(seq_zones_wlock); - kfree(seq_zones_bitmap); - - if (ret) { + if (ret >= 0) { + q->nr_zones = nr_zones; + swap(q->seq_zones_wlock, args.seq_zones_wlock); + swap(q->seq_zones_bitmap, args.seq_zones_bitmap); + ret = 0; + } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); - blk_mq_freeze_queue(q); blk_queue_free_zone_bitmaps(q); - blk_mq_unfreeze_queue(q); } + blk_mq_unfreeze_queue(q); + kfree(args.seq_zones_wlock); + kfree(args.seq_zones_bitmap); return ret; } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); diff --git a/block/blk.h b/block/blk.h index 47fba9362e60..2bea40180b6f 100644 --- a/block/blk.h +++ b/block/blk.h @@ -242,14 +242,11 @@ int blk_dev_init(void); * Contribute to IO statistics IFF: * * a) it's attached to a gendisk, and - * b) the queue had IO stats enabled when this request was started, and - * c) it's a file system request + * b) the queue had IO stats enabled when this request was started */ static inline bool blk_do_io_stat(struct request *rq) { - return rq->rq_disk && - (rq->rq_flags & RQF_IO_STAT) && - !blk_rq_is_passthrough(rq); + return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT); } static inline void req_set_nomerge(struct request_queue *q, struct request *req) diff --git a/block/elevator.c b/block/elevator.c index 076ba7308e65..4eab3d70e880 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -832,3 +832,12 @@ struct request *elv_rb_latter_request(struct request_queue *q, return NULL; } EXPORT_SYMBOL(elv_rb_latter_request); + +static int __init elevator_setup(char *str) +{ + pr_warn("Kernel parameter elevator= does not have any effect anymore.\n" + "Please use sysfs to set IO scheduler for individual devices.\n"); + return 1; +} + +__setup("elevator=", elevator_setup); diff --git a/block/genhd.c b/block/genhd.c index 26b31fcae217..ff6268970ddc 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1385,7 +1385,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) "%lu %lu %lu %u " "%lu %lu %lu %u " "%u %u %u " - "%lu %lu %lu %u\n", + "%lu %lu %lu %u " + "%lu %u" + "\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), part_stat_read(hd, ios[STAT_READ]), @@ -1402,7 +1404,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, ios[STAT_DISCARD]), part_stat_read(hd, merges[STAT_DISCARD]), part_stat_read(hd, sectors[STAT_DISCARD]), - (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD) + (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD), + part_stat_read(hd, ios[STAT_FLUSH]), + (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH) ); } disk_part_iter_exit(&piter); diff --git a/block/ioctl.c b/block/ioctl.c index 15a0eb80ada9..7ac8a66c9787 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -155,48 +155,21 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user } } -/* - * This is an exported API for the block driver, and will not - * acquire bd_mutex. This API should be used in case that - * caller has held bd_mutex already. - */ -int __blkdev_reread_part(struct block_device *bdev) +static int blkdev_reread_part(struct block_device *bdev) { - struct gendisk *disk = bdev->bd_disk; + int ret; - if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains) + if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - lockdep_assert_held(&bdev->bd_mutex); - - return rescan_partitions(disk, bdev); -} -EXPORT_SYMBOL(__blkdev_reread_part); - -/* - * This is an exported API for the block driver, and will - * try to acquire bd_mutex. If bd_mutex has been held already - * in current context, please call __blkdev_reread_part(). - * - * Make sure the held locks in current context aren't required - * in open()/close() handler and I/O path for avoiding ABBA deadlock: - * - bd_mutex is held before calling block driver's open/close - * handler - * - reading partition table may submit I/O to the block device - */ -int blkdev_reread_part(struct block_device *bdev) -{ - int res; - mutex_lock(&bdev->bd_mutex); - res = __blkdev_reread_part(bdev); + ret = bdev_disk_changed(bdev, false); mutex_unlock(&bdev->bd_mutex); - return res; + return ret; } -EXPORT_SYMBOL(blkdev_reread_part); static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, unsigned long arg, unsigned long flags) @@ -532,7 +505,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKREPORTZONE: return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); case BLKRESETZONE: - return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg); + case BLKOPENZONE: + case BLKCLOSEZONE: + case BLKFINISHZONE: + return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg); case BLKGETZONESZ: return put_uint(arg, bdev_zone_sectors(bdev)); case BLKGETNRZONES: diff --git a/block/opal_proto.h b/block/opal_proto.h index 5532412d567c..325cbba2465f 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -76,7 +76,6 @@ enum opal_response_token { * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00 * Section: 6.3 Assigned UIDs */ -#define OPAL_UID_LENGTH 8 #define OPAL_METHOD_LENGTH 8 #define OPAL_MSID_KEYLEN 15 #define OPAL_UID_LENGTH_HALF 4 @@ -108,6 +107,7 @@ enum opal_uid { OPAL_C_PIN_TABLE, OPAL_LOCKING_INFO_TABLE, OPAL_ENTERPRISE_LOCKING_INFO_TABLE, + OPAL_DATASTORE, /* C_PIN_TABLE object ID's */ OPAL_C_PIN_MSID, OPAL_C_PIN_SID, @@ -205,6 +205,10 @@ enum opal_lockingstate { OPAL_LOCKING_LOCKED = 0x03, }; +enum opal_parameter { + OPAL_SUM_SET_LIST = 0x060000, +}; + /* Packets derived from: * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00 * Secion: 3.2.3 ComPackets, Packets & Subpackets diff --git a/block/partition-generic.c b/block/partition-generic.c index aee643ce13d1..1d20c9cf213f 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -127,7 +127,8 @@ ssize_t part_stat_show(struct device *dev, "%8lu %8lu %8llu %8u " "%8lu %8lu %8llu %8u " "%8u %8u %8u " - "%8lu %8lu %8llu %8u" + "%8lu %8lu %8llu %8u " + "%8lu %8u" "\n", part_stat_read(p, ios[STAT_READ]), part_stat_read(p, merges[STAT_READ]), @@ -143,7 +144,9 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, ios[STAT_DISCARD]), part_stat_read(p, merges[STAT_DISCARD]), (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]), - (unsigned int)part_stat_read_msecs(p, STAT_DISCARD)); + (unsigned int)part_stat_read_msecs(p, STAT_DISCARD), + part_stat_read(p, ios[STAT_FLUSH]), + (unsigned int)part_stat_read_msecs(p, STAT_FLUSH)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, @@ -439,12 +442,14 @@ static bool disk_unlock_native_capacity(struct gendisk *disk) } } -static int drop_partitions(struct gendisk *disk, struct block_device *bdev) +int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev) { struct disk_part_iter piter; struct hd_struct *part; int res; + if (!disk_part_scan_enabled(disk)) + return 0; if (bdev->bd_part_count || bdev->bd_super) return -EBUSY; res = invalidate_partition(disk, 0); @@ -459,204 +464,124 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev) return 0; } -static bool part_zone_aligned(struct gendisk *disk, - struct block_device *bdev, - sector_t from, sector_t size) +static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, + struct parsed_partitions *state, int p) { - unsigned int zone_sectors = bdev_zone_sectors(bdev); + sector_t size = state->parts[p].size; + sector_t from = state->parts[p].from; + struct hd_struct *part; - /* - * If this function is called, then the disk is a zoned block device - * (host-aware or host-managed). This can be detected even if the - * zoned block device support is disabled (CONFIG_BLK_DEV_ZONED not - * set). In this case, however, only host-aware devices will be seen - * as a block device is not created for host-managed devices. Without - * zoned block device support, host-aware drives can still be used as - * regular block devices (no zone operation) and their zone size will - * be reported as 0. Allow this case. - */ - if (!zone_sectors) + if (!size) return true; - /* - * Check partition start and size alignement. If the drive has a - * smaller last runt zone, ignore it and allow the partition to - * use it. Check the zone size too: it should be a power of 2 number - * of sectors. - */ - if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) { - u32 rem; - - div_u64_rem(from, zone_sectors, &rem); - if (rem) + if (from >= get_capacity(disk)) { + printk(KERN_WARNING + "%s: p%d start %llu is beyond EOD, ", + disk->disk_name, p, (unsigned long long) from); + if (disk_unlock_native_capacity(disk)) return false; - if ((from + size) < get_capacity(disk)) { - div_u64_rem(size, zone_sectors, &rem); - if (rem) - return false; - } + return true; + } - } else { + if (from + size > get_capacity(disk)) { + printk(KERN_WARNING + "%s: p%d size %llu extends beyond EOD, ", + disk->disk_name, p, (unsigned long long) size); - if (from & (zone_sectors - 1)) - return false; - if ((from + size) < get_capacity(disk) && - (size & (zone_sectors - 1))) + if (disk_unlock_native_capacity(disk)) return false; + /* + * We can not ignore partitions of broken tables created by for + * example camera firmware, but we limit them to the end of the + * disk to avoid creating invalid block devices. + */ + size = get_capacity(disk) - from; + } + + part = add_partition(disk, p, from, size, state->parts[p].flags, + &state->parts[p].info); + if (IS_ERR(part)) { + printk(KERN_ERR " %s: p%d could not be added: %ld\n", + disk->disk_name, p, -PTR_ERR(part)); + return true; } +#ifdef CONFIG_BLK_DEV_MD + if (state->parts[p].flags & ADDPART_FLAG_RAID) + md_autodetect_dev(part_to_dev(part)->devt); +#endif return true; } -int rescan_partitions(struct gendisk *disk, struct block_device *bdev) +int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) { - struct parsed_partitions *state = NULL; - struct hd_struct *part; - int p, highest, res; -rescan: - if (state && !IS_ERR(state)) { - free_partitions(state); - state = NULL; - } + struct parsed_partitions *state; + int ret = -EAGAIN, p, highest; - res = drop_partitions(disk, bdev); - if (res) - return res; + if (!disk_part_scan_enabled(disk)) + return 0; - if (disk->fops->revalidate_disk) - disk->fops->revalidate_disk(disk); - check_disk_size_change(disk, bdev, true); - bdev->bd_invalidated = 0; - if (!get_capacity(disk) || !(state = check_partition(disk, bdev))) + state = check_partition(disk, bdev); + if (!state) return 0; if (IS_ERR(state)) { /* - * I/O error reading the partition table. If any - * partition code tried to read beyond EOD, retry - * after unlocking native capacity. + * I/O error reading the partition table. If we tried to read + * beyond EOD, retry after unlocking the native capacity. */ if (PTR_ERR(state) == -ENOSPC) { printk(KERN_WARNING "%s: partition table beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) - goto rescan; + return -EAGAIN; } return -EIO; } + /* - * If any partition code tried to read beyond EOD, try - * unlocking native capacity even if partition table is - * successfully read as we could be missing some partitions. + * Partitions are not supported on zoned block devices. + */ + if (bdev_is_zoned(bdev)) { + pr_warn("%s: ignoring partition table on zoned block device\n", + disk->disk_name); + ret = 0; + goto out_free_state; + } + + /* + * If we read beyond EOD, try unlocking native capacity even if the + * partition table was successfully read as we could be missing some + * partitions. */ if (state->access_beyond_eod) { printk(KERN_WARNING "%s: partition table partially beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) - goto rescan; + goto out_free_state; } /* tell userspace that the media / partition table may have changed */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - /* Detect the highest partition number and preallocate - * disk->part_tbl. This is an optimization and not strictly - * necessary. + /* + * Detect the highest partition number and preallocate disk->part_tbl. + * This is an optimization and not strictly necessary. */ for (p = 1, highest = 0; p < state->limit; p++) if (state->parts[p].size) highest = p; - disk_expand_part_tbl(disk, highest); - /* add partitions */ - for (p = 1; p < state->limit; p++) { - sector_t size, from; - - size = state->parts[p].size; - if (!size) - continue; - - from = state->parts[p].from; - if (from >= get_capacity(disk)) { - printk(KERN_WARNING - "%s: p%d start %llu is beyond EOD, ", - disk->disk_name, p, (unsigned long long) from); - if (disk_unlock_native_capacity(disk)) - goto rescan; - continue; - } - - if (from + size > get_capacity(disk)) { - printk(KERN_WARNING - "%s: p%d size %llu extends beyond EOD, ", - disk->disk_name, p, (unsigned long long) size); - - if (disk_unlock_native_capacity(disk)) { - /* free state and restart */ - goto rescan; - } else { - /* - * we can not ignore partitions of broken tables - * created by for example camera firmware, but - * we limit them to the end of the disk to avoid - * creating invalid block devices - */ - size = get_capacity(disk) - from; - } - } - - /* - * On a zoned block device, partitions should be aligned on the - * device zone size (i.e. zone boundary crossing not allowed). - * Otherwise, resetting the write pointer of the last zone of - * one partition may impact the following partition. - */ - if (bdev_is_zoned(bdev) && - !part_zone_aligned(disk, bdev, from, size)) { - printk(KERN_WARNING - "%s: p%d start %llu+%llu is not zone aligned\n", - disk->disk_name, p, (unsigned long long) from, - (unsigned long long) size); - continue; - } + for (p = 1; p < state->limit; p++) + if (!blk_add_partition(disk, bdev, state, p)) + goto out_free_state; - part = add_partition(disk, p, from, size, - state->parts[p].flags, - &state->parts[p].info); - if (IS_ERR(part)) { - printk(KERN_ERR " %s: p%d could not be added: %ld\n", - disk->disk_name, p, -PTR_ERR(part)); - continue; - } -#ifdef CONFIG_BLK_DEV_MD - if (state->parts[p].flags & ADDPART_FLAG_RAID) - md_autodetect_dev(part_to_dev(part)->devt); -#endif - } + ret = 0; +out_free_state: free_partitions(state); - return 0; -} - -int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) -{ - int res; - - if (!bdev->bd_invalidated) - return 0; - - res = drop_partitions(disk, bdev); - if (res) - return res; - - set_capacity(disk, 0); - check_disk_size_change(disk, bdev, false); - bdev->bd_invalidated = 0; - /* tell userspace that the media / partition table may have changed */ - kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - - return 0; + return ret; } unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) diff --git a/block/sed-opal.c b/block/sed-opal.c index b4c761973ac1..880cc57a5f6b 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -149,6 +149,8 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = { { 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 }, [OPAL_ENTERPRISE_LOCKING_INFO_TABLE] = { 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 }, + [OPAL_DATASTORE] = + { 0x00, 0x00, 0x10, 0x01, 0x00, 0x00, 0x00, 0x00 }, /* C_PIN_TABLE object ID's */ [OPAL_C_PIN_MSID] = @@ -1139,11 +1141,11 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table, * * the result is provided in dev->resp->tok[4] */ -static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table, +static int generic_get_table_info(struct opal_dev *dev, const u8 *table_uid, u64 column) { u8 uid[OPAL_UID_LENGTH]; - const unsigned int half = OPAL_UID_LENGTH/2; + const unsigned int half = OPAL_UID_LENGTH_HALF; /* sed-opal UIDs can be split in two halves: * first: actual table index @@ -1152,7 +1154,7 @@ static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table, * first part of the target table as relative index into that table */ memcpy(uid, opaluid[OPAL_TABLE_TABLE], half); - memcpy(uid+half, opaluid[table], half); + memcpy(uid + half, table_uid, half); return generic_get_column(dev, uid, column); } @@ -1221,6 +1223,75 @@ static int get_active_key(struct opal_dev *dev, void *data) return get_active_key_cont(dev); } +static int generic_table_write_data(struct opal_dev *dev, const u64 data, + u64 offset, u64 size, const u8 *uid) +{ + const u8 __user *src = (u8 __user *)(uintptr_t)data; + u8 *dst; + u64 len; + size_t off = 0; + int err; + + /* do we fit in the available space? */ + err = generic_get_table_info(dev, uid, OPAL_TABLE_ROWS); + if (err) { + pr_debug("Couldn't get the table size\n"); + return err; + } + + len = response_get_u64(&dev->parsed, 4); + if (size > len || offset > len - size) { + pr_debug("Does not fit in the table (%llu vs. %llu)\n", + offset + size, len); + return -ENOSPC; + } + + /* do the actual transmission(s) */ + while (off < size) { + err = cmd_start(dev, uid, opalmethod[OPAL_SET]); + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_WHERE); + add_token_u64(&err, dev, offset + off); + add_token_u8(&err, dev, OPAL_ENDNAME); + + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_VALUES); + + /* + * The bytestring header is either 1 or 2 bytes, so assume 2. + * There also needs to be enough space to accommodate the + * trailing OPAL_ENDNAME (1 byte) and tokens added by + * cmd_finalize. + */ + len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED), + (size_t)(size - off)); + pr_debug("Write bytes %zu+%llu/%llu\n", off, len, size); + + dst = add_bytestring_header(&err, dev, len); + if (!dst) + break; + + if (copy_from_user(dst, src + off, len)) { + err = -EFAULT; + break; + } + + dev->pos += len; + + add_token_u8(&err, dev, OPAL_ENDNAME); + if (err) + break; + + err = finalize_and_send(dev, parse_and_check_status); + if (err) + break; + + off += len; + } + + return err; +} + static int generic_lr_enable_disable(struct opal_dev *dev, u8 *uid, bool rle, bool wle, bool rl, bool wl) @@ -1583,68 +1654,9 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data) static int write_shadow_mbr(struct opal_dev *dev, void *data) { struct opal_shadow_mbr *shadow = data; - const u8 __user *src; - u8 *dst; - size_t off = 0; - u64 len; - int err = 0; - - /* do we fit in the available shadow mbr space? */ - err = generic_get_table_info(dev, OPAL_MBR, OPAL_TABLE_ROWS); - if (err) { - pr_debug("MBR: could not get shadow size\n"); - return err; - } - - len = response_get_u64(&dev->parsed, 4); - if (shadow->size > len || shadow->offset > len - shadow->size) { - pr_debug("MBR: does not fit in shadow (%llu vs. %llu)\n", - shadow->offset + shadow->size, len); - return -ENOSPC; - } - - /* do the actual transmission(s) */ - src = (u8 __user *)(uintptr_t)shadow->data; - while (off < shadow->size) { - err = cmd_start(dev, opaluid[OPAL_MBR], opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, OPAL_WHERE); - add_token_u64(&err, dev, shadow->offset + off); - add_token_u8(&err, dev, OPAL_ENDNAME); - - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, OPAL_VALUES); - - /* - * The bytestring header is either 1 or 2 bytes, so assume 2. - * There also needs to be enough space to accommodate the - * trailing OPAL_ENDNAME (1 byte) and tokens added by - * cmd_finalize. - */ - len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED), - (size_t)(shadow->size - off)); - pr_debug("MBR: write bytes %zu+%llu/%llu\n", - off, len, shadow->size); - - dst = add_bytestring_header(&err, dev, len); - if (!dst) - break; - if (copy_from_user(dst, src + off, len)) - err = -EFAULT; - dev->pos += len; - - add_token_u8(&err, dev, OPAL_ENDNAME); - if (err) - break; - - err = finalize_and_send(dev, parse_and_check_status); - if (err) - break; - - off += len; - } - return err; + return generic_table_write_data(dev, shadow->data, shadow->offset, + shadow->size, opaluid[OPAL_MBR]); } static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid, @@ -1874,7 +1886,6 @@ static int activate_lsp(struct opal_dev *dev, void *data) { struct opal_lr_act *opal_act = data; u8 user_lr[OPAL_UID_LENGTH]; - u8 uint_3 = 0x83; int err, i; err = cmd_start(dev, opaluid[OPAL_LOCKINGSP_UID], @@ -1887,10 +1898,7 @@ static int activate_lsp(struct opal_dev *dev, void *data) return err; add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, uint_3); - add_token_u8(&err, dev, 6); - add_token_u8(&err, dev, 0); - add_token_u8(&err, dev, 0); + add_token_u64(&err, dev, OPAL_SUM_SET_LIST); add_token_u8(&err, dev, OPAL_STARTLIST); add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH); @@ -1957,6 +1965,113 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data) return 0; } +static int write_table_data(struct opal_dev *dev, void *data) +{ + struct opal_read_write_table *write_tbl = data; + + return generic_table_write_data(dev, write_tbl->data, write_tbl->offset, + write_tbl->size, write_tbl->table_uid); +} + +static int read_table_data_cont(struct opal_dev *dev) +{ + int err; + const char *data_read; + + err = parse_and_check_status(dev); + if (err) + return err; + + dev->prev_d_len = response_get_string(&dev->parsed, 1, &data_read); + dev->prev_data = (void *)data_read; + if (!dev->prev_data) { + pr_debug("%s: Couldn't read data from the table.\n", __func__); + return OPAL_INVAL_PARAM; + } + + return 0; +} + +/* + * IO_BUFFER_LENGTH = 2048 + * sizeof(header) = 56 + * No. of Token Bytes in the Response = 11 + * MAX size of data that can be carried in response buffer + * at a time is : 2048 - (56 + 11) = 1981 = 0x7BD. + */ +#define OPAL_MAX_READ_TABLE (0x7BD) + +static int read_table_data(struct opal_dev *dev, void *data) +{ + struct opal_read_write_table *read_tbl = data; + int err; + size_t off = 0, max_read_size = OPAL_MAX_READ_TABLE; + u64 table_len, len; + u64 offset = read_tbl->offset, read_size = read_tbl->size - 1; + u8 __user *dst; + + err = generic_get_table_info(dev, read_tbl->table_uid, OPAL_TABLE_ROWS); + if (err) { + pr_debug("Couldn't get the table size\n"); + return err; + } + + table_len = response_get_u64(&dev->parsed, 4); + + /* Check if the user is trying to read from the table limits */ + if (read_size > table_len || offset > table_len - read_size) { + pr_debug("Read size exceeds the Table size limits (%llu vs. %llu)\n", + offset + read_size, table_len); + return -EINVAL; + } + + while (off < read_size) { + err = cmd_start(dev, read_tbl->table_uid, opalmethod[OPAL_GET]); + + add_token_u8(&err, dev, OPAL_STARTLIST); + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_STARTROW); + add_token_u64(&err, dev, offset + off); /* start row value */ + add_token_u8(&err, dev, OPAL_ENDNAME); + + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_ENDROW); + + len = min(max_read_size, (size_t)(read_size - off)); + add_token_u64(&err, dev, offset + off + len); /* end row value + */ + add_token_u8(&err, dev, OPAL_ENDNAME); + add_token_u8(&err, dev, OPAL_ENDLIST); + + if (err) { + pr_debug("Error building read table data command.\n"); + break; + } + + err = finalize_and_send(dev, read_table_data_cont); + if (err) + break; + + /* len+1: This includes the NULL terminator at the end*/ + if (dev->prev_d_len > len + 1) { + err = -EOVERFLOW; + break; + } + + dst = (u8 __user *)(uintptr_t)read_tbl->data; + if (copy_to_user(dst + off, dev->prev_data, dev->prev_d_len)) { + pr_debug("Error copying data to userspace\n"); + err = -EFAULT; + break; + } + dev->prev_data = NULL; + + off += len; + } + + return err; +} + static int end_opal_session(struct opal_dev *dev, void *data) { int err = 0; @@ -2443,6 +2558,68 @@ bool opal_unlock_from_suspend(struct opal_dev *dev) } EXPORT_SYMBOL(opal_unlock_from_suspend); +static int opal_read_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + const struct opal_step read_table_steps[] = { + { start_admin1LSP_opal_session, &rw_tbl->key }, + { read_table_data, rw_tbl }, + { end_opal_session, } + }; + int ret = 0; + + if (!rw_tbl->size) + return ret; + + return execute_steps(dev, read_table_steps, + ARRAY_SIZE(read_table_steps)); +} + +static int opal_write_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + const struct opal_step write_table_steps[] = { + { start_admin1LSP_opal_session, &rw_tbl->key }, + { write_table_data, rw_tbl }, + { end_opal_session, } + }; + int ret = 0; + + if (!rw_tbl->size) + return ret; + + return execute_steps(dev, write_table_steps, + ARRAY_SIZE(write_table_steps)); +} + +static int opal_generic_read_write_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + int ret, bit_set; + + mutex_lock(&dev->dev_lock); + setup_opal_dev(dev); + + bit_set = fls64(rw_tbl->flags) - 1; + switch (bit_set) { + case OPAL_READ_TABLE: + ret = opal_read_table(dev, rw_tbl); + break; + case OPAL_WRITE_TABLE: + ret = opal_write_table(dev, rw_tbl); + break; + default: + pr_debug("Invalid bit set in the flag (%016llx).\n", + rw_tbl->flags); + ret = -EINVAL; + break; + } + + mutex_unlock(&dev->dev_lock); + + return ret; +} + int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) { void *p; @@ -2505,6 +2682,9 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) case IOC_OPAL_PSID_REVERT_TPR: ret = opal_reverttper(dev, p, true); break; + case IOC_OPAL_GENERIC_TABLE_RW: + ret = opal_generic_read_write_table(dev, p); + break; default: break; } diff --git a/block/t10-pi.c b/block/t10-pi.c index 9803c7e0376e..f4907d941f03 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -235,16 +235,12 @@ static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter) return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION); } -/** - * Type 3 does not have a reference tag so no remapping is required. - */ +/* Type 3 does not have a reference tag so no remapping is required. */ static void t10_pi_type3_prepare(struct request *rq) { } -/** - * Type 3 does not have a reference tag so no remapping is required. - */ +/* Type 3 does not have a reference tag so no remapping is required. */ static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes) { } diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c index 76d2ce3a1b5b..d16d893bd195 100644 --- a/crypto/asymmetric_keys/asym_tpm.c +++ b/crypto/asymmetric_keys/asym_tpm.c @@ -13,7 +13,7 @@ #include <crypto/sha.h> #include <asm/unaligned.h> #include <keys/asymmetric-subtype.h> -#include <keys/trusted.h> +#include <keys/trusted_tpm.h> #include <crypto/asym_tpm_subtype.h> #include <crypto/public_key.h> @@ -21,10 +21,6 @@ #define TPM_ORD_LOADKEY2 65 #define TPM_ORD_UNBIND 30 #define TPM_ORD_SIGN 60 -#define TPM_LOADKEY2_SIZE 59 -#define TPM_FLUSHSPECIFIC_SIZE 18 -#define TPM_UNBIND_SIZE 63 -#define TPM_SIGN_SIZE 63 #define TPM_RT_KEY 0x00000001 @@ -68,16 +64,13 @@ static int tpm_loadkey2(struct tpm_buf *tb, return ret; /* build the request buffer */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_LOADKEY2_SIZE + keybloblen); - store32(tb, TPM_ORD_LOADKEY2); - store32(tb, keyhandle); - storebytes(tb, keyblob, keybloblen); - store32(tb, authhandle); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_LOADKEY2); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append(tb, keyblob, keybloblen); + tpm_buf_append_u32(tb, authhandle); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -101,12 +94,9 @@ static int tpm_loadkey2(struct tpm_buf *tb, */ static int tpm_flushspecific(struct tpm_buf *tb, uint32_t handle) { - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_COMMAND); - store32(tb, TPM_FLUSHSPECIFIC_SIZE); - store32(tb, TPM_ORD_FLUSHSPECIFIC); - store32(tb, handle); - store32(tb, TPM_RT_KEY); + tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_FLUSHSPECIFIC); + tpm_buf_append_u32(tb, handle); + tpm_buf_append_u32(tb, TPM_RT_KEY); return trusted_tpm_send(tb->data, MAX_BUF_SIZE); } @@ -155,17 +145,14 @@ static int tpm_unbind(struct tpm_buf *tb, return ret; /* build the request buffer */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_UNBIND_SIZE + bloblen); - store32(tb, TPM_ORD_UNBIND); - store32(tb, keyhandle); - store32(tb, bloblen); - storebytes(tb, blob, bloblen); - store32(tb, authhandle); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_UNBIND); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append_u32(tb, bloblen); + tpm_buf_append(tb, blob, bloblen); + tpm_buf_append_u32(tb, authhandle); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -241,17 +228,14 @@ static int tpm_sign(struct tpm_buf *tb, return ret; /* build the request buffer */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_SIGN_SIZE + bloblen); - store32(tb, TPM_ORD_SIGN); - store32(tb, keyhandle); - store32(tb, bloblen); - storebytes(tb, blob, bloblen); - store32(tb, authhandle); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SIGN); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append_u32(tb, bloblen); + tpm_buf_append(tb, blob, bloblen); + tpm_buf_append_u32(tb, authhandle); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -519,7 +503,7 @@ static int tpm_key_decrypt(struct tpm_key *tk, struct kernel_pkey_params *params, const void *in, void *out) { - struct tpm_buf *tb; + struct tpm_buf tb; uint32_t keyhandle; uint8_t srkauth[SHA1_DIGEST_SIZE]; uint8_t keyauth[SHA1_DIGEST_SIZE]; @@ -533,14 +517,14 @@ static int tpm_key_decrypt(struct tpm_key *tk, if (strcmp(params->encoding, "pkcs1")) return -ENOPKG; - tb = kzalloc(sizeof(*tb), GFP_KERNEL); - if (!tb) - return -ENOMEM; + r = tpm_buf_init(&tb, 0, 0); + if (r) + return r; /* TODO: Handle a non-all zero SRK authorization */ memset(srkauth, 0, sizeof(srkauth)); - r = tpm_loadkey2(tb, SRKHANDLE, srkauth, + r = tpm_loadkey2(&tb, SRKHANDLE, srkauth, tk->blob, tk->blob_len, &keyhandle); if (r < 0) { pr_devel("loadkey2 failed (%d)\n", r); @@ -550,16 +534,16 @@ static int tpm_key_decrypt(struct tpm_key *tk, /* TODO: Handle a non-all zero key authorization */ memset(keyauth, 0, sizeof(keyauth)); - r = tpm_unbind(tb, keyhandle, keyauth, + r = tpm_unbind(&tb, keyhandle, keyauth, in, params->in_len, out, params->out_len); if (r < 0) pr_devel("tpm_unbind failed (%d)\n", r); - if (tpm_flushspecific(tb, keyhandle) < 0) + if (tpm_flushspecific(&tb, keyhandle) < 0) pr_devel("flushspecific failed (%d)\n", r); error: - kzfree(tb); + tpm_buf_destroy(&tb); pr_devel("<==%s() = %d\n", __func__, r); return r; } @@ -643,7 +627,7 @@ static int tpm_key_sign(struct tpm_key *tk, struct kernel_pkey_params *params, const void *in, void *out) { - struct tpm_buf *tb; + struct tpm_buf tb; uint32_t keyhandle; uint8_t srkauth[SHA1_DIGEST_SIZE]; uint8_t keyauth[SHA1_DIGEST_SIZE]; @@ -681,15 +665,14 @@ static int tpm_key_sign(struct tpm_key *tk, goto error_free_asn1_wrapped; } - r = -ENOMEM; - tb = kzalloc(sizeof(*tb), GFP_KERNEL); - if (!tb) + r = tpm_buf_init(&tb, 0, 0); + if (r) goto error_free_asn1_wrapped; /* TODO: Handle a non-all zero SRK authorization */ memset(srkauth, 0, sizeof(srkauth)); - r = tpm_loadkey2(tb, SRKHANDLE, srkauth, + r = tpm_loadkey2(&tb, SRKHANDLE, srkauth, tk->blob, tk->blob_len, &keyhandle); if (r < 0) { pr_devel("loadkey2 failed (%d)\n", r); @@ -699,15 +682,15 @@ static int tpm_key_sign(struct tpm_key *tk, /* TODO: Handle a non-all zero key authorization */ memset(keyauth, 0, sizeof(keyauth)); - r = tpm_sign(tb, keyhandle, keyauth, in, in_len, out, params->out_len); + r = tpm_sign(&tb, keyhandle, keyauth, in, in_len, out, params->out_len); if (r < 0) pr_devel("tpm_sign failed (%d)\n", r); - if (tpm_flushspecific(tb, keyhandle) < 0) + if (tpm_flushspecific(&tb, keyhandle) < 0) pr_devel("flushspecific failed (%d)\n", r); error_free_tb: - kzfree(tb); + tpm_buf_destroy(&tb); error_free_asn1_wrapped: kfree(asn1_wrapped); pr_devel("<==%s() = %d\n", __func__, r); diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index 753985c01517..46dc54d18f0b 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -56,7 +56,7 @@ struct acard_sg { __le32 size; /* bit 31 (EOT) max==0x10000 (64k) */ }; -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc); static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int acard_ahci_port_start(struct ata_port *ap); static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); @@ -210,7 +210,7 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl) return si; } -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -248,6 +248,8 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 05c2b32dcc4d..ec6c64fce74a 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -56,6 +56,7 @@ enum board_ids { board_ahci_yes_fbs, /* board IDs for specific chipsets in alphabetical order */ + board_ahci_al, board_ahci_avn, board_ahci_mcp65, board_ahci_mcp77, @@ -167,6 +168,13 @@ static const struct ata_port_info ahci_port_info[] = { .port_ops = &ahci_ops, }, /* by chipsets */ + [board_ahci_al] = { + AHCI_HFLAGS (AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_MSI), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_avn] = { .flags = AHCI_FLAG_COMMON, .pio_mask = ATA_PIO4, @@ -415,6 +423,11 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(ATI, 0x4394), board_ahci_sb700 }, /* ATI SB700/800 */ { PCI_VDEVICE(ATI, 0x4395), board_ahci_sb700 }, /* ATI SB700/800 */ + /* Amazon's Annapurna Labs support */ + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031), + .class = PCI_CLASS_STORAGE_SATA_AHCI, + .class_mask = 0xffffff, + board_ahci_al }, /* AMD */ { PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */ { PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */ diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c index e3163dae5e85..cb55ebc1725b 100644 --- a/drivers/ata/ahci_tegra.c +++ b/drivers/ata/ahci_tegra.c @@ -483,7 +483,6 @@ static int tegra_ahci_probe(struct platform_device *pdev) struct tegra_ahci_priv *tegra; struct resource *res; int ret; - unsigned int i; hpriv = ahci_platform_get_resources(pdev, 0); if (IS_ERR(hpriv)) @@ -543,8 +542,9 @@ static int tegra_ahci_probe(struct platform_device *pdev) if (!tegra->supplies) return -ENOMEM; - for (i = 0; i < tegra->soc->num_supplies; i++) - tegra->supplies[i].supply = tegra->soc->supply_names[i]; + regulator_bulk_set_supply_names(tegra->supplies, + tegra->soc->supply_names, + tegra->soc->num_supplies); ret = devm_regulator_bulk_get(&pdev->dev, tegra->soc->num_supplies, diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index e4da725381d3..3ca7720e7d8f 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -841,6 +841,12 @@ static int piix_broken_suspend(void) }, }, { + .ident = "TECRA M3", + .matches = { + DMI_MATCH(DMI_OEM_STRING, "Tecra M3,"), + }, + }, + { .ident = "TECRA M4", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), @@ -955,18 +961,10 @@ static int piix_broken_suspend(void) { } /* terminate list */ }; - static const char *oemstrs[] = { - "Tecra M3,", - }; - int i; if (dmi_check_system(sysids)) return 1; - for (i = 0; i < ARRAY_SIZE(oemstrs); i++) - if (dmi_find_device(DMI_DEV_TYPE_OEM_STRING, oemstrs[i], NULL)) - return 1; - /* TECRA M4 sometimes forgets its identify and reports bogus * DMI information. As the bogus information is a bit * generic, match as many entries as possible. This manual diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index bff369d9a1a7..ea5bf5f4cbed 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -57,7 +57,7 @@ static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int ahci_port_start(struct ata_port *ap); static void ahci_port_stop(struct ata_port *ap); -static void ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc); static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc); static void ahci_freeze(struct ata_port *ap); static void ahci_thaw(struct ata_port *ap); @@ -1624,7 +1624,7 @@ static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc) return sata_pmp_qc_defer_cmd_switch(qc); } -static void ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -1660,6 +1660,8 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static void ahci_fbs_dec_intr(struct ata_port *ap) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 28c492be0a57..e9017c570bc5 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4980,7 +4980,10 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc) return ATA_DEFER_LINK; } -void ata_noop_qc_prep(struct ata_queued_cmd *qc) { } +enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc) +{ + return AC_ERR_OK; +} /** * ata_sg_init - Associate command with scatter-gather table. @@ -5443,7 +5446,9 @@ void ata_qc_issue(struct ata_queued_cmd *qc) return; } - ap->ops->qc_prep(qc); + qc->err_mask |= ap->ops->qc_prep(qc); + if (unlikely(qc->err_mask)) + goto err; trace_ata_qc_issue(qc); qc->err_mask |= ap->ops->qc_issue(qc); if (unlikely(qc->err_mask)) @@ -6708,6 +6713,9 @@ void ata_host_detach(struct ata_host *host) { int i; + /* Ensure ata_port probe has completed */ + async_synchronize_full(); + for (i = 0; i < host->n_ports; i++) ata_port_detach(host->ports[i]); diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 4ed682da52ae..038db94216a9 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -2679,12 +2679,14 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc) * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); @@ -2697,12 +2699,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg_dumb(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep); diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c index 3aa006c5ed0c..6bd2228bb6ff 100644 --- a/drivers/ata/pata_artop.c +++ b/drivers/ata/pata_artop.c @@ -100,7 +100,7 @@ static void artop6210_load_piomode(struct ata_port *ap, struct ata_device *adev, { struct pci_dev *pdev = to_pci_dev(ap->host->dev); int dn = adev->devno + 2 * ap->port_no; - const u16 timing[2][5] = { + static const u16 timing[2][5] = { { 0x0000, 0x000A, 0x0008, 0x0303, 0x0301 }, { 0x0700, 0x070A, 0x0708, 0x0403, 0x0401 } @@ -154,7 +154,7 @@ static void artop6260_load_piomode (struct ata_port *ap, struct ata_device *adev { struct pci_dev *pdev = to_pci_dev(ap->host->dev); int dn = adev->devno + 2 * ap->port_no; - const u8 timing[2][5] = { + static const u8 timing[2][5] = { { 0x00, 0x0A, 0x08, 0x33, 0x31 }, { 0x70, 0x7A, 0x78, 0x43, 0x41 } diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c index 41e0d6a6cd05..27b0952fde6b 100644 --- a/drivers/ata/pata_falcon.c +++ b/drivers/ata/pata_falcon.c @@ -33,7 +33,6 @@ #define DRV_NAME "pata_falcon" #define DRV_VERSION "0.1.0" -#define ATA_HD_BASE 0xfff00000 #define ATA_HD_CONTROL 0x39 static struct scsi_host_template pata_falcon_sht = { @@ -120,24 +119,22 @@ static struct ata_port_operations pata_falcon_ops = { .set_mode = pata_falcon_set_mode, }; -static int pata_falcon_init_one(void) +static int __init pata_falcon_init_one(struct platform_device *pdev) { + struct resource *res; struct ata_host *host; struct ata_port *ap; - struct platform_device *pdev; void __iomem *base; - if (!MACH_IS_ATARI || !ATARIHW_PRESENT(IDE)) - return -ENODEV; - - pr_info(DRV_NAME ": Atari Falcon PATA controller\n"); + dev_info(&pdev->dev, "Atari Falcon PATA controller\n"); - pdev = platform_device_register_simple(DRV_NAME, 0, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENODEV; - if (!devm_request_mem_region(&pdev->dev, ATA_HD_BASE, 0x40, DRV_NAME)) { - pr_err(DRV_NAME ": resources busy\n"); + if (!devm_request_mem_region(&pdev->dev, res->start, + resource_size(res), DRV_NAME)) { + dev_err(&pdev->dev, "resources busy\n"); return -EBUSY; } @@ -152,7 +149,7 @@ static int pata_falcon_init_one(void) ap->flags |= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_IORDY; ap->flags |= ATA_FLAG_PIO_POLLING; - base = (void __iomem *)ATA_HD_BASE; + base = (void __iomem *)res->start; ap->ioaddr.data_addr = base; ap->ioaddr.error_addr = base + 1 + 1 * 4; ap->ioaddr.feature_addr = base + 1 + 1 * 4; @@ -174,9 +171,26 @@ static int pata_falcon_init_one(void) return ata_host_activate(host, 0, NULL, 0, &pata_falcon_sht); } -module_init(pata_falcon_init_one); +static int __exit pata_falcon_remove_one(struct platform_device *pdev) +{ + struct ata_host *host = platform_get_drvdata(pdev); + + ata_host_detach(host); + + return 0; +} + +static struct platform_driver pata_falcon_driver = { + .remove = __exit_p(pata_falcon_remove_one), + .driver = { + .name = "atari-falcon-ide", + }, +}; + +module_platform_driver_probe(pata_falcon_driver, pata_falcon_init_one); MODULE_AUTHOR("Bartlomiej Zolnierkiewicz"); MODULE_DESCRIPTION("low-level driver for Atari Falcon PATA"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:atari-falcon-ide"); MODULE_VERSION(DRV_VERSION); diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 57f2ec71cfc3..1bfd0154dad5 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -510,7 +510,7 @@ static int pata_macio_cable_detect(struct ata_port *ap) return ATA_CBL_PATA40; } -static void pata_macio_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) { unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE); struct ata_port *ap = qc->ap; @@ -523,7 +523,7 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) __func__, qc, qc->flags, write, qc->dev->devno); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; table = (struct dbdma_cmd *) priv->dma_table_cpu; @@ -568,6 +568,8 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) table->command = cpu_to_le16(DBDMA_STOP); dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi); + + return AC_ERR_OK; } diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c index 4afcb8e63e21..41430f79663c 100644 --- a/drivers/ata/pata_pxa.c +++ b/drivers/ata/pata_pxa.c @@ -44,25 +44,27 @@ static void pxa_ata_dma_irq(void *d) /* * Prepare taskfile for submission. */ -static void pxa_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc) { struct pata_pxa_data *pd = qc->ap->private_data; struct dma_async_tx_descriptor *tx; enum dma_transfer_direction dir; if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM); tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir, DMA_PREP_INTERRUPT); if (!tx) { ata_dev_err(qc->dev, "prep_slave_sg() failed\n"); - return; + return AC_ERR_OK; } tx->callback = pxa_ata_dma_irq; tx->callback_param = pd; pd->dma_cookie = dmaengine_submit(tx); + + return AC_ERR_OK; } /* diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c index cb490531b62e..5db55e1e2a61 100644 --- a/drivers/ata/pdc_adma.c +++ b/drivers/ata/pdc_adma.c @@ -116,7 +116,7 @@ static int adma_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int adma_port_start(struct ata_port *ap); static void adma_port_stop(struct ata_port *ap); -static void adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int adma_qc_issue(struct ata_queued_cmd *qc); static int adma_check_atapi_dma(struct ata_queued_cmd *qc); static void adma_freeze(struct ata_port *ap); @@ -295,7 +295,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc) return i; } -static void adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc) { struct adma_port_priv *pp = qc->ap->private_data; u8 *buf = pp->pkt; @@ -306,7 +306,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) adma_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; buf[i++] = 0; /* Response flags */ buf[i++] = 0; /* reserved */ @@ -371,6 +371,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) printk("%s\n", obuf); } #endif + return AC_ERR_OK; } static inline void adma_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 8e9cb198fcd1..9239615d8a04 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -502,7 +502,7 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, return num_prde; } -static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sata_fsl_port_priv *pp = ap->private_data; @@ -548,6 +548,8 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n", desc_info, ttl_dwords, num_prde); + + return AC_ERR_OK; } static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index 7f99e23bff88..a6b76cc12a66 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -478,7 +478,7 @@ static void inic_fill_sg(struct inic_prd *prd, struct ata_queued_cmd *qc) prd[-1].flags |= PRD_END; } -static void inic_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc) { struct inic_port_priv *pp = qc->ap->private_data; struct inic_pkt *pkt = pp->pkt; @@ -538,6 +538,8 @@ static void inic_qc_prep(struct ata_queued_cmd *qc) inic_fill_sg(prd, qc); pp->cpb_tbl[0] = pp->pkt_dma; + + return AC_ERR_OK; } static unsigned int inic_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index ad385a113391..277f11909fc1 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -592,8 +592,8 @@ static int mv5_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val) static int mv_port_start(struct ata_port *ap); static void mv_port_stop(struct ata_port *ap); static int mv_qc_defer(struct ata_queued_cmd *qc); -static void mv_qc_prep(struct ata_queued_cmd *qc); -static void mv_qc_prep_iie(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc); static unsigned int mv_qc_issue(struct ata_queued_cmd *qc); static int mv_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); @@ -2031,7 +2031,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2043,15 +2043,15 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) switch (tf->protocol) { case ATA_PROT_DMA: if (tf->command == ATA_CMD_DSM) - return; + return AC_ERR_OK; /* fall-thru */ case ATA_PROT_NCQ: break; /* continue below */ case ATA_PROT_PIO: mv_rw_multi_errata_sata24(qc); - return; + return AC_ERR_OK; default: - return; + return AC_ERR_OK; } /* Fill in command request block @@ -2098,12 +2098,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none * of which are defined/used by Linux. If we get here, this * driver needs work. - * - * FIXME: modify libata to give qc_prep a return value and - * return error here. */ - BUG_ON(tf->command); - break; + ata_port_err(ap, "%s: unsupported command: %.2x\n", __func__, + tf->command); + return AC_ERR_INVALID; } mv_crqb_pack_cmd(cw++, tf->nsect, ATA_REG_NSECT, 0); mv_crqb_pack_cmd(cw++, tf->hob_lbal, ATA_REG_LBAL, 0); @@ -2116,8 +2114,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1); /* last */ if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** @@ -2132,7 +2132,7 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep_iie(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2143,9 +2143,9 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) if ((tf->protocol != ATA_PROT_DMA) && (tf->protocol != ATA_PROT_NCQ)) - return; + return AC_ERR_OK; if (tf->command == ATA_CMD_DSM) - return; /* use bmdma for this */ + return AC_ERR_OK; /* use bmdma for this */ /* Fill in Gen IIE command request block */ if (!(tf->flags & ATA_TFLAG_WRITE)) @@ -2186,8 +2186,10 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) ); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 56946012d113..65ec8dff1c51 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -297,7 +297,7 @@ static void nv_ck804_freeze(struct ata_port *ap); static void nv_ck804_thaw(struct ata_port *ap); static int nv_adma_slave_config(struct scsi_device *sdev); static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc); -static void nv_adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc); static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance); static void nv_adma_irq_clear(struct ata_port *ap); @@ -319,7 +319,7 @@ static void nv_mcp55_freeze(struct ata_port *ap); static void nv_swncq_error_handler(struct ata_port *ap); static int nv_swncq_slave_config(struct scsi_device *sdev); static int nv_swncq_port_start(struct ata_port *ap); -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc); static void nv_swncq_fill_sg(struct ata_queued_cmd *qc); static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc); static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis); @@ -1344,7 +1344,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc) return 1; } -static void nv_adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc) { struct nv_adma_port_priv *pp = qc->ap->private_data; struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag]; @@ -1356,7 +1356,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) (qc->flags & ATA_QCFLAG_DMAMAP)); nv_adma_register_mode(qc->ap); ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } cpb->resp_flags = NV_CPB_RESP_DONE; @@ -1388,6 +1388,8 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) cpb->ctl_flags = ctl_flags; wmb(); cpb->resp_flags = 0; + + return AC_ERR_OK; } static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc) @@ -1950,17 +1952,19 @@ static int nv_swncq_port_start(struct ata_port *ap) return 0; } -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc) { if (qc->tf.protocol != ATA_PROT_NCQ) { ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; nv_swncq_fill_sg(qc); + + return AC_ERR_OK; } static void nv_swncq_fill_sg(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 5fd464765ddc..c451d7d1c817 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -139,7 +139,7 @@ static int pdc_sata_scr_write(struct ata_link *link, unsigned int sc_reg, u32 va static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int pdc_common_port_start(struct ata_port *ap); static int pdc_sata_port_start(struct ata_port *ap); -static void pdc_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static int pdc_check_atapi_dma(struct ata_queued_cmd *qc); @@ -633,7 +633,7 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc) prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void pdc_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc) { struct pdc_port_priv *pp = qc->ap->private_data; unsigned int i; @@ -665,6 +665,8 @@ static void pdc_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static int pdc_is_sataii_tx4(unsigned long flags) diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c index c53c5a47204d..ef00ab644afb 100644 --- a/drivers/ata/sata_qstor.c +++ b/drivers/ata/sata_qstor.c @@ -100,7 +100,7 @@ static int qs_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int qs_port_start(struct ata_port *ap); static void qs_host_stop(struct ata_host *host); -static void qs_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc); static unsigned int qs_qc_issue(struct ata_queued_cmd *qc); static int qs_check_atapi_dma(struct ata_queued_cmd *qc); static void qs_freeze(struct ata_port *ap); @@ -260,7 +260,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc) return si; } -static void qs_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc) { struct qs_port_priv *pp = qc->ap->private_data; u8 dflags = QS_DF_PORD, *buf = pp->pkt; @@ -272,7 +272,7 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) qs_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; nelem = qs_fill_sg(qc); @@ -295,6 +295,8 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) /* frame information structure (FIS) */ ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]); + + return AC_ERR_OK; } static inline void qs_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 3495e1733a8e..980aacdbcf3b 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -550,12 +550,14 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc) prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND); } -static void sata_rcar_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sata_rcar_bmdma_fill_sg(qc); + + return AC_ERR_OK; } static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index e6fbae2f645a..75321f1ceba5 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -103,7 +103,7 @@ static void sil_dev_config(struct ata_device *dev); static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val); static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed); -static void sil_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc); static void sil_bmdma_setup(struct ata_queued_cmd *qc); static void sil_bmdma_start(struct ata_queued_cmd *qc); static void sil_bmdma_stop(struct ata_queued_cmd *qc); @@ -317,12 +317,14 @@ static void sil_fill_sg(struct ata_queued_cmd *qc) last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void sil_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sil_fill_sg(qc); + + return AC_ERR_OK; } static unsigned char sil_get_device_cache_line(struct pci_dev *pdev) diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 7bef82de53ca..560070d4f1d0 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -326,7 +326,7 @@ static void sil24_dev_config(struct ata_device *dev); static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val); static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val); static int sil24_qc_defer(struct ata_queued_cmd *qc); -static void sil24_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc); static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc); static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc); static void sil24_pmp_attach(struct ata_port *ap); @@ -830,7 +830,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) return ata_std_qc_defer(qc); } -static void sil24_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sil24_port_priv *pp = ap->private_data; @@ -874,6 +874,8 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc) if (qc->flags & ATA_QCFLAG_DMAMAP) sil24_fill_sg(qc, sge); + + return AC_ERR_OK; } static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 2277ba0c9c7f..2c7b30c5ea3d 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -202,7 +202,7 @@ static void pdc_error_handler(struct ata_port *ap); static void pdc_freeze(struct ata_port *ap); static void pdc_thaw(struct ata_port *ap); static int pdc_port_start(struct ata_port *ap); -static void pdc20621_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static unsigned int pdc20621_dimm_init(struct ata_host *host); @@ -530,7 +530,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc) VPRINTK("ata pkt buf ofs %u, mmio copied\n", i); } -static void pdc20621_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc) { switch (qc->tf.protocol) { case ATA_PROT_DMA: @@ -542,6 +542,8 @@ static void pdc20621_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static void __pdc20621_push_hdma(struct ata_queued_cmd *qc, diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index cc37511de866..6265871a4af2 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -554,12 +554,27 @@ ssize_t __weak cpu_show_mds(struct device *dev, return sprintf(buf, "Not affected\n"); } +ssize_t __weak cpu_show_tsx_async_abort(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_itlb_multihit(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL); static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL); static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL); +static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL); +static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -568,6 +583,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_spec_store_bypass.attr, &dev_attr_l1tf.attr, &dev_attr_mds.attr, + &dev_attr_tsx_async_abort.attr, + &dev_attr_itlb_multihit.attr, NULL }; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 55907c27075b..84c4e1f72cbd 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -872,3 +872,39 @@ int walk_memory_blocks(unsigned long start, unsigned long size, } return ret; } + +struct for_each_memory_block_cb_data { + walk_memory_blocks_func_t func; + void *arg; +}; + +static int for_each_memory_block_cb(struct device *dev, void *data) +{ + struct memory_block *mem = to_memory_block(dev); + struct for_each_memory_block_cb_data *cb_data = data; + + return cb_data->func(mem, cb_data->arg); +} + +/** + * for_each_memory_block - walk through all present memory blocks + * + * @arg: argument passed to func + * @func: callback for each memory block walked + * + * This function walks through all present memory blocks, calling func on + * each memory block. + * + * In case func() returns an error, walking is aborted and the error is + * returned. + */ +int for_each_memory_block(void *arg, walk_memory_blocks_func_t func) +{ + struct for_each_memory_block_cb_data cb_data = { + .func = func, + .arg = arg, + }; + + return bus_for_each_dev(&memory_subsys, NULL, &cb_data, + for_each_memory_block_cb); +} diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 5b248763a672..a18155cdce41 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -786,7 +786,6 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm if (nc->tentative && connection->agreed_pro_version < 92) { rcu_read_unlock(); - mutex_unlock(&sock->mutex); drbd_err(connection, "--dry-run is not supported by peer"); return -EOPNOTSUPP; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f6f77eaa7217..739b372a5112 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -417,18 +417,20 @@ out_free_page: return ret; } -static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos) +static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, + int mode) { /* - * We use punch hole to reclaim the free space used by the - * image a.k.a. discard. However we do not support discard if - * encryption is enabled, because it may give an attacker - * useful information. + * We use fallocate to manipulate the space mappings used by the image + * a.k.a. discard/zerorange. However we do not support this if + * encryption is enabled, because it may give an attacker useful + * information. */ struct file *file = lo->lo_backing_file; - int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; int ret; + mode |= FALLOC_FL_KEEP_SIZE; + if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) { ret = -EOPNOTSUPP; goto out; @@ -596,9 +598,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); - case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - return lo_discard(lo, rq, pos); + /* + * If the caller doesn't want deallocation, call zeroout to + * write zeroes the range. Otherwise, punch them out. + */ + return lo_fallocate(lo, rq, pos, + (rq->cmd_flags & REQ_NOUNMAP) ? + FALLOC_FL_ZERO_RANGE : + FALLOC_FL_PUNCH_HOLE); + case REQ_OP_DISCARD: + return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: if (lo->transfer) return lo_write_transfer(lo, rq, pos); @@ -630,7 +640,9 @@ static void loop_reread_partitions(struct loop_device *lo, { int rc; - rc = blkdev_reread_part(bdev); + mutex_lock(&bdev->bd_mutex); + rc = bdev_disk_changed(bdev, false); + mutex_unlock(&bdev->bd_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); @@ -1154,10 +1166,11 @@ out_unlock: * must be at least one and it can only become zero when the * current holder is released. */ - if (release) - err = __blkdev_reread_part(bdev); - else - err = blkdev_reread_part(bdev); + if (!release) + mutex_lock(&bdev->bd_mutex); + err = bdev_disk_changed(bdev, false); + if (!release) + mutex_unlock(&bdev->bd_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo_number, err); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 964f78cfffa0..f6bafa9a68b9 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -129,7 +129,7 @@ struct mtip_compat_ide_task_request_s { /* * This function check_for_surprise_removal is called * while card is removed from the system and it will - * read the vendor id from the configration space + * read the vendor id from the configuration space * * @pdev Pointer to the pci_dev structure. * diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index a94ee45440b3..57532465fb83 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -993,6 +993,7 @@ static struct socket *nbd_get_socket(struct nbd_device *nbd, unsigned long fd, if (sock->ops->shutdown == sock_no_shutdown) { dev_err(disk_to_dev(nbd->disk), "Unsupported socket: shutdown callout must be supported.\n"); *err = -EINVAL; + sockfd_put(sock); return NULL; } @@ -1031,14 +1032,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, sockfd_put(sock); return -ENOMEM; } + + config->socks = socks; + nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL); if (!nsock) { sockfd_put(sock); return -ENOMEM; } - config->socks = socks; - nsock->fallback_index = -1; nsock->dead = false; mutex_init(&nsock->tx_lock); diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index a235c45e22a7..bc837862b767 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -91,11 +91,13 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); +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); +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) { @@ -103,17 +105,18 @@ static inline int null_zone_init(struct nullb_device *dev) return -EINVAL; } static inline void null_zone_exit(struct nullb_device *dev) {} -static inline int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, - unsigned int *nr_zones) -{ - return -EOPNOTSUPP; -} static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, sector_t sector, sector_t nr_sectors) { return BLK_STS_NOTSUPP; } +static inline size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, + unsigned int len) +{ + return len; +} +#define null_report_zones NULL #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* __NULL_BLK_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 0e7da5015ccd..795fda576824 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -227,7 +227,7 @@ static ssize_t nullb_device_uint_attr_store(unsigned int *val, int result; result = kstrtouint(page, 0, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -241,7 +241,7 @@ static ssize_t nullb_device_ulong_attr_store(unsigned long *val, unsigned long tmp; result = kstrtoul(page, 0, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -255,7 +255,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, int result; result = kstrtobool(page, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -263,7 +263,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, } /* The following macro should only be used with TYPE = {uint, ulong, bool}. */ -#define NULLB_DEVICE_ATTR(NAME, TYPE) \ +#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY) \ static ssize_t \ nullb_device_##NAME##_show(struct config_item *item, char *page) \ { \ @@ -274,31 +274,57 @@ static ssize_t \ nullb_device_##NAME##_store(struct config_item *item, const char *page, \ size_t count) \ { \ - if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags)) \ - return -EBUSY; \ - return nullb_device_##TYPE##_attr_store( \ - &to_nullb_device(item)->NAME, page, count); \ + int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY; \ + struct nullb_device *dev = to_nullb_device(item); \ + TYPE new_value; \ + int ret; \ + \ + ret = nullb_device_##TYPE##_attr_store(&new_value, page, count); \ + if (ret < 0) \ + return ret; \ + if (apply_fn) \ + ret = apply_fn(dev, new_value); \ + else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) \ + ret = -EBUSY; \ + if (ret < 0) \ + return ret; \ + dev->NAME = new_value; \ + return count; \ } \ CONFIGFS_ATTR(nullb_device_, NAME); -NULLB_DEVICE_ATTR(size, ulong); -NULLB_DEVICE_ATTR(completion_nsec, ulong); -NULLB_DEVICE_ATTR(submit_queues, uint); -NULLB_DEVICE_ATTR(home_node, uint); -NULLB_DEVICE_ATTR(queue_mode, uint); -NULLB_DEVICE_ATTR(blocksize, uint); -NULLB_DEVICE_ATTR(irqmode, uint); -NULLB_DEVICE_ATTR(hw_queue_depth, uint); -NULLB_DEVICE_ATTR(index, uint); -NULLB_DEVICE_ATTR(blocking, bool); -NULLB_DEVICE_ATTR(use_per_node_hctx, bool); -NULLB_DEVICE_ATTR(memory_backed, bool); -NULLB_DEVICE_ATTR(discard, bool); -NULLB_DEVICE_ATTR(mbps, uint); -NULLB_DEVICE_ATTR(cache_size, ulong); -NULLB_DEVICE_ATTR(zoned, bool); -NULLB_DEVICE_ATTR(zone_size, ulong); -NULLB_DEVICE_ATTR(zone_nr_conv, uint); +static int nullb_apply_submit_queues(struct nullb_device *dev, + unsigned int submit_queues) +{ + struct nullb *nullb = dev->nullb; + struct blk_mq_tag_set *set; + + if (!nullb) + return 0; + + set = nullb->tag_set; + blk_mq_update_nr_hw_queues(set, submit_queues); + return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM; +} + +NULLB_DEVICE_ATTR(size, ulong, NULL); +NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL); +NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues); +NULLB_DEVICE_ATTR(home_node, uint, NULL); +NULLB_DEVICE_ATTR(queue_mode, uint, NULL); +NULLB_DEVICE_ATTR(blocksize, uint, NULL); +NULLB_DEVICE_ATTR(irqmode, uint, NULL); +NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL); +NULLB_DEVICE_ATTR(index, uint, NULL); +NULLB_DEVICE_ATTR(blocking, bool, NULL); +NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL); +NULLB_DEVICE_ATTR(memory_backed, bool, NULL); +NULLB_DEVICE_ATTR(discard, bool, NULL); +NULLB_DEVICE_ATTR(mbps, uint, NULL); +NULLB_DEVICE_ATTR(cache_size, ulong, NULL); +NULLB_DEVICE_ATTR(zoned, bool, NULL); +NULLB_DEVICE_ATTR(zone_size, ulong, NULL); +NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL); static ssize_t nullb_device_power_show(struct config_item *item, char *page) { @@ -467,7 +493,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item) static ssize_t memb_group_features_show(struct config_item *item, char *page) { - return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n"); + return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n"); } CONFIGFS_ATTR_RO(memb_group_, features); @@ -996,6 +1022,16 @@ next: return 0; } +static void nullb_fill_pattern(struct nullb *nullb, struct page *page, + unsigned int len, unsigned int off) +{ + void *dst; + + dst = kmap_atomic(page); + memset(dst + off, 0xFF, len); + kunmap_atomic(dst); +} + static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n) { size_t temp; @@ -1036,10 +1072,24 @@ static int null_transfer(struct nullb *nullb, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector, bool is_fua) { + struct nullb_device *dev = nullb->dev; + unsigned int valid_len = len; int err = 0; if (!is_write) { - err = copy_from_nullb(nullb, page, off, sector, len); + if (dev->zoned) + valid_len = null_zone_valid_read_len(nullb, + sector, len); + + if (valid_len) { + err = copy_from_nullb(nullb, page, off, + sector, valid_len); + off += valid_len; + len -= valid_len; + } + + if (len) + nullb_fill_pattern(nullb, page, len, off); flush_dcache_page(page); } else { flush_dcache_page(page); @@ -1418,20 +1468,9 @@ static void null_config_discard(struct nullb *nullb) blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q); } -static int null_open(struct block_device *bdev, fmode_t mode) -{ - return 0; -} - -static void null_release(struct gendisk *disk, fmode_t mode) -{ -} - -static const struct block_device_operations null_fops = { - .owner = THIS_MODULE, - .open = null_open, - .release = null_release, - .report_zones = null_zone_report, +static const struct block_device_operations null_ops = { + .owner = THIS_MODULE, + .report_zones = null_report_zones, }; static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) @@ -1532,7 +1571,7 @@ static int null_gendisk_register(struct nullb *nullb) disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO; disk->major = null_major; disk->first_minor = nullb->index; - disk->fops = &null_fops; + disk->fops = &null_ops; disk->private_data = nullb; disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 3d7fdea872f8..d4d88b581822 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -66,22 +66,53 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +int null_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data) { struct nullb *nullb = disk->private_data; struct nullb_device *dev = nullb->dev; - unsigned int zno, nrz = 0; - - zno = null_zone_no(dev, sector); - if (zno < dev->nr_zones) { - nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno); - memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone)); + unsigned int first_zone, i; + struct blk_zone zone; + int error; + + first_zone = null_zone_no(dev, sector); + if (first_zone >= dev->nr_zones) + return 0; + + nr_zones = min(nr_zones, dev->nr_zones - first_zone); + for (i = 0; i < nr_zones; i++) { + /* + * Stacked DM target drivers will remap the zone information by + * modifying the zone information passed to the report callback. + * So use a local copy to avoid corruption of the device zone + * array. + */ + memcpy(&zone, &dev->zones[first_zone + i], + sizeof(struct blk_zone)); + error = cb(&zone, i, data); + if (error) + return error; } - *nr_zones = nrz; + return nr_zones; +} - return 0; +size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, unsigned int len) +{ + struct nullb_device *dev = nullb->dev; + struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)]; + unsigned int nr_sectors = len >> SECTOR_SHIFT; + + /* Read must be below the write pointer position */ + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL || + sector + nr_sectors <= zone->wp) + return len; + + if (sector > zone->wp) + return 0; + + return (zone->wp - sector) << SECTOR_SHIFT; } static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, @@ -118,14 +149,14 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, return BLK_STS_OK; } -static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector) +static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, + 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]; + struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)]; size_t i; - switch (req_op(cmd->rq)) { + switch (op) { case REQ_OP_ZONE_RESET_ALL: for (i = 0; i < dev->nr_zones; i++) { if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL) @@ -141,6 +172,29 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector) zone->cond = BLK_ZONE_COND_EMPTY; zone->wp = zone->start; break; + case REQ_OP_ZONE_OPEN: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + if (zone->cond == BLK_ZONE_COND_FULL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_EXP_OPEN; + break; + case REQ_OP_ZONE_CLOSE: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + if (zone->cond == BLK_ZONE_COND_FULL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_CLOSED; + break; + case REQ_OP_ZONE_FINISH: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_FULL; + zone->wp = zone->start + zone->len; + break; default: return BLK_STS_NOTSUPP; } @@ -155,7 +209,10 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, return null_zone_write(cmd, sector, nr_sectors); case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: - return null_zone_reset(cmd, sector); + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return null_zone_mgmt(cmd, op, sector); default: return BLK_STS_OK; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 39136675dae5..13527a0b4e44 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2087,7 +2087,7 @@ static int rbd_object_map_update_finish(struct rbd_obj_request *obj_req, struct rbd_device *rbd_dev = obj_req->img_request->rbd_dev; struct ceph_osd_data *osd_data; u64 objno; - u8 state, new_state, current_state; + u8 state, new_state, uninitialized_var(current_state); bool has_current_state; void *p; diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index 76b73ddf8fd7..10f6368117d8 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -1000,8 +1000,10 @@ static void rsxx_pci_remove(struct pci_dev *dev) cancel_work_sync(&card->event_work); + destroy_workqueue(card->event_wq); rsxx_destroy_dev(card); rsxx_dma_destroy(card); + destroy_workqueue(card->creg_ctrl.creg_wq); spin_lock_irqsave(&card->irq_lock, flags); rsxx_disable_ier_and_isr(card, CR_INTR_ALL); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 80b850ef1bf6..8d53b8ef545c 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -13,7 +13,6 @@ #include <linux/delay.h> #include <linux/device.h> #include <linux/err.h> -#include <linux/freezer.h> #include <linux/fs.h> #include <linux/hw_random.h> #include <linux/kernel.h> @@ -422,9 +421,7 @@ static int hwrng_fillfn(void *unused) { long rc; - set_freezable(); - - while (!kthread_freezable_should_stop(NULL)) { + while (!kthread_should_stop()) { struct hwrng *rng; rng = get_current_rng(); diff --git a/drivers/char/random.c b/drivers/char/random.c index de434feb873a..01b8868b9bed 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -327,7 +327,6 @@ #include <linux/percpu.h> #include <linux/cryptohash.h> #include <linux/fips.h> -#include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/workqueue.h> #include <linux/irq.h> @@ -2500,8 +2499,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count, * We'll be woken up again once below random_write_wakeup_thresh, * or when the calling thread is about to terminate. */ - wait_event_freezable(random_write_wait, - kthread_should_stop() || + wait_event_interruptible(random_write_wait, kthread_should_stop() || ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits); mix_pool_bytes(poolp, buffer, count); credit_entropy_bits(poolp, entropy); diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index 9c37047f4b56..aacdeed93320 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -67,6 +67,13 @@ config TCG_TIS_SPI within Linux. To compile this driver as a module, choose M here; the module will be called tpm_tis_spi. +config TCG_TIS_SPI_CR50 + bool "Cr50 SPI Interface" + depends on TCG_TIS_SPI + help + If you have a H1 secure module running Cr50 firmware on SPI bus, + say Yes and it will be accessible from within Linux. + config TCG_TIS_I2C_ATMEL tristate "TPM Interface Specification 1.2 Interface (I2C - Atmel)" depends on I2C diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile index c354cdff9c62..5a0d99d4fec0 100644 --- a/drivers/char/tpm/Makefile +++ b/drivers/char/tpm/Makefile @@ -21,7 +21,9 @@ tpm-$(CONFIG_EFI) += eventlog/efi.o tpm-$(CONFIG_OF) += eventlog/of.o obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o obj-$(CONFIG_TCG_TIS) += tpm_tis.o -obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o +obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o +tpm_tis_spi_mod-y := tpm_tis_spi.o +tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index d7a3888ad80f..a438b1206fcb 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/spinlock.h> +#include <linux/suspend.h> #include <linux/freezer.h> #include <linux/tpm_eventlog.h> @@ -394,7 +395,11 @@ int tpm_pm_suspend(struct device *dev) return -ENODEV; if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED) - return 0; + goto suspended; + + if ((chip->flags & TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED) && + !pm_suspend_via_firmware()) + goto suspended; if (!tpm_chip_start(chip)) { if (chip->flags & TPM_CHIP_FLAG_TPM2) @@ -405,6 +410,7 @@ int tpm_pm_suspend(struct device *dev) tpm_chip_stop(chip); } +suspended: return rc; } EXPORT_SYMBOL_GPL(tpm_pm_suspend); @@ -453,62 +459,6 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max) } EXPORT_SYMBOL_GPL(tpm_get_random); -/** - * tpm_seal_trusted() - seal a trusted key payload - * @chip: a &struct tpm_chip instance, %NULL for the default chip - * @options: authentication values and other options - * @payload: the key data in clear and encrypted form - * - * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in - * the keyring subsystem. - * - * Return: same as with tpm_transmit_cmd() - */ -int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - int rc; - - chip = tpm_find_get_ops(chip); - if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2)) - return -ENODEV; - - rc = tpm2_seal_trusted(chip, payload, options); - - tpm_put_ops(chip); - return rc; -} -EXPORT_SYMBOL_GPL(tpm_seal_trusted); - -/** - * tpm_unseal_trusted() - unseal a trusted key - * @chip: a &struct tpm_chip instance, %NULL for the default chip - * @options: authentication values and other options - * @payload: the key data in clear and encrypted form - * - * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in - * the keyring subsystem. - * - * Return: same as with tpm_transmit_cmd() - */ -int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - int rc; - - chip = tpm_find_get_ops(chip); - if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2)) - return -ENODEV; - - rc = tpm2_unseal_trusted(chip, payload, options); - - tpm_put_ops(chip); - - return rc; -} -EXPORT_SYMBOL_GPL(tpm_unseal_trusted); - static int __init tpm_init(void) { int rc; diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index edfa89160010..3b53b3e5ec3e 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -217,6 +217,7 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tpm_chip *chip = to_tpm_chip(dev); + struct tpm1_version *version; ssize_t rc = 0; char *str = buf; cap_t cap; @@ -232,31 +233,31 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr, str += sprintf(str, "Manufacturer: 0x%x\n", be32_to_cpu(cap.manufacturer_id)); - /* Try to get a TPM version 1.2 TPM_CAP_VERSION_INFO */ - rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap, + /* TPM 1.2 */ + if (!tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap, "attempting to determine the 1.2 version", - sizeof(cap.tpm_version_1_2)); - if (!rc) { - str += sprintf(str, - "TCG version: %d.%d\nFirmware version: %d.%d\n", - cap.tpm_version_1_2.Major, - cap.tpm_version_1_2.Minor, - cap.tpm_version_1_2.revMajor, - cap.tpm_version_1_2.revMinor); - } else { - /* Otherwise just use TPM_STRUCT_VER */ - if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap, - "attempting to determine the 1.1 version", - sizeof(cap.tpm_version))) - goto out_ops; - str += sprintf(str, - "TCG version: %d.%d\nFirmware version: %d.%d\n", - cap.tpm_version.Major, - cap.tpm_version.Minor, - cap.tpm_version.revMajor, - cap.tpm_version.revMinor); + sizeof(cap.version2))) { + version = &cap.version2.version; + goto out_print; } + + /* TPM 1.1 */ + if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap, + "attempting to determine the 1.1 version", + sizeof(cap.version1))) { + goto out_ops; + } + + version = &cap.version1; + +out_print: + str += sprintf(str, + "TCG version: %d.%d\nFirmware version: %d.%d\n", + version->major, version->minor, + version->rev_major, version->rev_minor); + rc = str - buf; + out_ops: tpm_put_ops(chip); return rc; diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index a7fea3e0ca86..b9e1547be6b5 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -25,7 +25,6 @@ #include <linux/platform_device.h> #include <linux/io.h> #include <linux/tpm.h> -#include <linux/highmem.h> #include <linux/tpm_eventlog.h> #ifdef CONFIG_X86 @@ -58,123 +57,6 @@ enum tpm_addr { #define TPM_ERR_DISABLED 0x7 #define TPM_ERR_INVALID_POSTINIT 38 -#define TPM_HEADER_SIZE 10 - -enum tpm2_const { - TPM2_PLATFORM_PCR = 24, - TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), -}; - -enum tpm2_timeouts { - TPM2_TIMEOUT_A = 750, - TPM2_TIMEOUT_B = 2000, - TPM2_TIMEOUT_C = 200, - TPM2_TIMEOUT_D = 30, - TPM2_DURATION_SHORT = 20, - TPM2_DURATION_MEDIUM = 750, - TPM2_DURATION_LONG = 2000, - TPM2_DURATION_LONG_LONG = 300000, - TPM2_DURATION_DEFAULT = 120000, -}; - -enum tpm2_structures { - TPM2_ST_NO_SESSIONS = 0x8001, - TPM2_ST_SESSIONS = 0x8002, -}; - -/* Indicates from what layer of the software stack the error comes from */ -#define TSS2_RC_LAYER_SHIFT 16 -#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) - -enum tpm2_return_codes { - TPM2_RC_SUCCESS = 0x0000, - TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ - TPM2_RC_HANDLE = 0x008B, - TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ - TPM2_RC_FAILURE = 0x0101, - TPM2_RC_DISABLED = 0x0120, - TPM2_RC_COMMAND_CODE = 0x0143, - TPM2_RC_TESTING = 0x090A, /* RC_WARN */ - TPM2_RC_REFERENCE_H0 = 0x0910, - TPM2_RC_RETRY = 0x0922, -}; - -enum tpm2_command_codes { - TPM2_CC_FIRST = 0x011F, - TPM2_CC_HIERARCHY_CONTROL = 0x0121, - TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, - TPM2_CC_CREATE_PRIMARY = 0x0131, - TPM2_CC_SEQUENCE_COMPLETE = 0x013E, - TPM2_CC_SELF_TEST = 0x0143, - TPM2_CC_STARTUP = 0x0144, - TPM2_CC_SHUTDOWN = 0x0145, - TPM2_CC_NV_READ = 0x014E, - TPM2_CC_CREATE = 0x0153, - TPM2_CC_LOAD = 0x0157, - TPM2_CC_SEQUENCE_UPDATE = 0x015C, - TPM2_CC_UNSEAL = 0x015E, - TPM2_CC_CONTEXT_LOAD = 0x0161, - TPM2_CC_CONTEXT_SAVE = 0x0162, - TPM2_CC_FLUSH_CONTEXT = 0x0165, - TPM2_CC_VERIFY_SIGNATURE = 0x0177, - TPM2_CC_GET_CAPABILITY = 0x017A, - TPM2_CC_GET_RANDOM = 0x017B, - TPM2_CC_PCR_READ = 0x017E, - TPM2_CC_PCR_EXTEND = 0x0182, - TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, - TPM2_CC_HASH_SEQUENCE_START = 0x0186, - TPM2_CC_CREATE_LOADED = 0x0191, - TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ -}; - -enum tpm2_permanent_handles { - TPM2_RS_PW = 0x40000009, -}; - -enum tpm2_capabilities { - TPM2_CAP_HANDLES = 1, - TPM2_CAP_COMMANDS = 2, - TPM2_CAP_PCRS = 5, - TPM2_CAP_TPM_PROPERTIES = 6, -}; - -enum tpm2_properties { - TPM_PT_TOTAL_COMMANDS = 0x0129, -}; - -enum tpm2_startup_types { - TPM2_SU_CLEAR = 0x0000, - TPM2_SU_STATE = 0x0001, -}; - -enum tpm2_cc_attrs { - TPM2_CC_ATTR_CHANDLES = 25, - TPM2_CC_ATTR_RHANDLE = 28, -}; - -#define TPM_VID_INTEL 0x8086 -#define TPM_VID_WINBOND 0x1050 -#define TPM_VID_STM 0x104A - -enum tpm_chip_flags { - TPM_CHIP_FLAG_TPM2 = BIT(1), - TPM_CHIP_FLAG_IRQ = BIT(2), - TPM_CHIP_FLAG_VIRTUAL = BIT(3), - TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), - TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), -}; - -#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) - -struct tpm_header { - __be16 tag; - __be32 length; - union { - __be32 ordinal; - __be32 return_code; - }; -} __packed; - #define TPM_TAG_RQU_COMMAND 193 struct stclear_flags_t { @@ -186,19 +68,16 @@ struct stclear_flags_t { u8 bGlobalLock; } __packed; -struct tpm_version_t { - u8 Major; - u8 Minor; - u8 revMajor; - u8 revMinor; +struct tpm1_version { + u8 major; + u8 minor; + u8 rev_major; + u8 rev_minor; } __packed; -struct tpm_version_1_2_t { - __be16 tag; - u8 Major; - u8 Minor; - u8 revMajor; - u8 revMinor; +struct tpm1_version2 { + __be16 tag; + struct tpm1_version version; } __packed; struct timeout_t { @@ -243,8 +122,8 @@ typedef union { struct stclear_flags_t stclear_flags; __u8 owned; __be32 num_pcrs; - struct tpm_version_t tpm_version; - struct tpm_version_1_2_t tpm_version_1_2; + struct tpm1_version version1; + struct tpm1_version2 version2; __be32 manufacturer_id; struct timeout_t timeout; struct duration_t duration; @@ -274,102 +153,6 @@ enum tpm_sub_capabilities { * compiler warnings about stack frame size. */ #define TPM_MAX_RNG_DATA 128 -/* A string buffer type for constructing TPM commands. This is based on the - * ideas of string buffer code in security/keys/trusted.h but is heap based - * in order to keep the stack usage minimal. - */ - -enum tpm_buf_flags { - TPM_BUF_OVERFLOW = BIT(0), -}; - -struct tpm_buf { - struct page *data_page; - unsigned int flags; - u8 *data; -}; - -static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - head->tag = cpu_to_be16(tag); - head->length = cpu_to_be32(sizeof(*head)); - head->ordinal = cpu_to_be32(ordinal); -} - -static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - buf->data_page = alloc_page(GFP_HIGHUSER); - if (!buf->data_page) - return -ENOMEM; - - buf->flags = 0; - buf->data = kmap(buf->data_page); - tpm_buf_reset(buf, tag, ordinal); - return 0; -} - -static inline void tpm_buf_destroy(struct tpm_buf *buf) -{ - kunmap(buf->data_page); - __free_page(buf->data_page); -} - -static inline u32 tpm_buf_length(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be32_to_cpu(head->length); -} - -static inline u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -static inline void tpm_buf_append(struct tpm_buf *buf, - const unsigned char *new_data, - unsigned int new_len) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - u32 len = tpm_buf_length(buf); - - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_OVERFLOW) - return; - - if ((len + new_len) > PAGE_SIZE) { - WARN(1, "tpm_buf: overflow\n"); - buf->flags |= TPM_BUF_OVERFLOW; - return; - } - - memcpy(&buf->data[len], new_data, new_len); - head->length = cpu_to_be32(len + new_len); -} - -static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) -{ - tpm_buf_append(buf, &value, 1); -} - -static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) -{ - __be16 value2 = cpu_to_be16(value); - - tpm_buf_append(buf, (u8 *) &value2, 2); -} - -static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) -{ - __be32 value2 = cpu_to_be32(value); - - tpm_buf_append(buf, (u8 *) &value2, 4); -} - extern struct class *tpm_class; extern struct class *tpmrm_class; extern dev_t tpm_devt; @@ -429,11 +212,6 @@ static inline void tpm_add_ppi(struct tpm_chip *chip) } #endif -static inline u32 tpm2_rc_value(u32 rc) -{ - return (rc & BIT(7)) ? rc & 0xff : rc; -} - int tpm2_get_timeouts(struct tpm_chip *chip); int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest, u16 *digest_size_ptr); @@ -441,12 +219,6 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max); void tpm2_flush_context(struct tpm_chip *chip, u32 handle); -int tpm2_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); -int tpm2_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc); diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index 149e953ca369..ca7158fa6e6c 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -343,6 +343,7 @@ int tpm1_get_timeouts(struct tpm_chip *chip) { cap_t cap; unsigned long timeout_old[4], timeout_chip[4], timeout_eff[4]; + unsigned long durations[3]; ssize_t rc; rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, NULL, @@ -427,6 +428,20 @@ int tpm1_get_timeouts(struct tpm_chip *chip) usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_long)); chip->duration[TPM_LONG_LONG] = 0; /* not used under 1.2 */ + /* + * Provide the ability for vendor overrides of duration values in case + * of misreporting. + */ + if (chip->ops->update_durations) + chip->ops->update_durations(chip, durations); + + if (chip->duration_adjusted) { + dev_info(&chip->dev, HW_ERR "Adjusting reported durations."); + chip->duration[TPM_SHORT] = durations[0]; + chip->duration[TPM_MEDIUM] = durations[1]; + chip->duration[TPM_LONG] = durations[2]; + } + /* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above * value wrong and apparently reports msecs rather than usecs. So we * fix up the resulting too-small TPM_SHORT value to make things work. diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index ba9acae83bff..fdb457704aa7 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -13,20 +13,6 @@ #include "tpm.h" #include <crypto/hash_info.h> -#include <keys/trusted-type.h> - -enum tpm2_object_attributes { - TPM2_OA_USER_WITH_AUTH = BIT(6), -}; - -enum tpm2_session_attributes { - TPM2_SA_CONTINUE_SESSION = BIT(0), -}; - -struct tpm2_hash { - unsigned int crypto_id; - unsigned int tpm_id; -}; static struct tpm2_hash tpm2_hash_map[] = { {HASH_ALGO_SHA1, TPM_ALG_SHA1}, @@ -377,299 +363,6 @@ void tpm2_flush_context(struct tpm_chip *chip, u32 handle) tpm_buf_destroy(&buf); } -/** - * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. - * - * @buf: an allocated tpm_buf instance - * @session_handle: session handle - * @nonce: the session nonce, may be NULL if not used - * @nonce_len: the session nonce length, may be 0 if not used - * @attributes: the session attributes - * @hmac: the session HMAC or password, may be NULL if not used - * @hmac_len: the session HMAC or password length, maybe 0 if not used - */ -static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle, - const u8 *nonce, u16 nonce_len, - u8 attributes, - const u8 *hmac, u16 hmac_len) -{ - tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len); - tpm_buf_append_u32(buf, session_handle); - tpm_buf_append_u16(buf, nonce_len); - - if (nonce && nonce_len) - tpm_buf_append(buf, nonce, nonce_len); - - tpm_buf_append_u8(buf, attributes); - tpm_buf_append_u16(buf, hmac_len); - - if (hmac && hmac_len) - tpm_buf_append(buf, hmac, hmac_len); -} - -/** - * tpm2_seal_trusted() - seal the payload of a trusted key - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * - * Return: < 0 on error and 0 on success. - */ -int tpm2_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - unsigned int blob_len; - struct tpm_buf buf; - u32 hash; - int i; - int rc; - - for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) { - if (options->hash == tpm2_hash_map[i].crypto_id) { - hash = tpm2_hash_map[i].tpm_id; - break; - } - } - - if (i == ARRAY_SIZE(tpm2_hash_map)) - return -EINVAL; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, options->keyhandle); - tpm2_buf_append_auth(&buf, TPM2_RS_PW, - NULL /* nonce */, 0, - 0 /* session_attributes */, - options->keyauth /* hmac */, - TPM_DIGEST_SIZE); - - /* sensitive */ - tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); - - tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); - tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); - tpm_buf_append_u16(&buf, payload->key_len + 1); - tpm_buf_append(&buf, payload->key, payload->key_len); - tpm_buf_append_u8(&buf, payload->migratable); - - /* public */ - tpm_buf_append_u16(&buf, 14 + options->policydigest_len); - tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH); - tpm_buf_append_u16(&buf, hash); - - /* policy */ - if (options->policydigest_len) { - tpm_buf_append_u32(&buf, 0); - tpm_buf_append_u16(&buf, options->policydigest_len); - tpm_buf_append(&buf, options->policydigest, - options->policydigest_len); - } else { - tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH); - tpm_buf_append_u16(&buf, 0); - } - - /* public parameters */ - tpm_buf_append_u16(&buf, TPM_ALG_NULL); - tpm_buf_append_u16(&buf, 0); - - /* outside info */ - tpm_buf_append_u16(&buf, 0); - - /* creation PCR */ - tpm_buf_append_u32(&buf, 0); - - if (buf.flags & TPM_BUF_OVERFLOW) { - rc = -E2BIG; - goto out; - } - - rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data"); - if (rc) - goto out; - - blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]); - if (blob_len > MAX_BLOB_SIZE) { - rc = -E2BIG; - goto out; - } - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) { - rc = -EFAULT; - goto out; - } - - memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len); - payload->blob_len = blob_len; - -out: - tpm_buf_destroy(&buf); - - if (rc > 0) { - if (tpm2_rc_value(rc) == TPM2_RC_HASH) - rc = -EINVAL; - else - rc = -EPERM; - } - - return rc; -} - -/** - * tpm2_load_cmd() - execute a TPM2_Load command - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * @blob_handle: returned blob handle - * - * Return: 0 on success. - * -E2BIG on wrong payload size. - * -EPERM on tpm error status. - * < 0 error from tpm_transmit_cmd. - */ -static int tpm2_load_cmd(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options, - u32 *blob_handle) -{ - struct tpm_buf buf; - unsigned int private_len; - unsigned int public_len; - unsigned int blob_len; - int rc; - - private_len = be16_to_cpup((__be16 *) &payload->blob[0]); - if (private_len > (payload->blob_len - 2)) - return -E2BIG; - - public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]); - blob_len = private_len + public_len + 4; - if (blob_len > payload->blob_len) - return -E2BIG; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, options->keyhandle); - tpm2_buf_append_auth(&buf, TPM2_RS_PW, - NULL /* nonce */, 0, - 0 /* session_attributes */, - options->keyauth /* hmac */, - TPM_DIGEST_SIZE); - - tpm_buf_append(&buf, payload->blob, blob_len); - - if (buf.flags & TPM_BUF_OVERFLOW) { - rc = -E2BIG; - goto out; - } - - rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob"); - if (!rc) - *blob_handle = be32_to_cpup( - (__be32 *) &buf.data[TPM_HEADER_SIZE]); - -out: - tpm_buf_destroy(&buf); - - if (rc > 0) - rc = -EPERM; - - return rc; -} - -/** - * tpm2_unseal_cmd() - execute a TPM2_Unload command - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * @blob_handle: blob handle - * - * Return: 0 on success - * -EPERM on tpm error status - * < 0 error from tpm_transmit_cmd - */ -static int tpm2_unseal_cmd(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options, - u32 blob_handle) -{ - struct tpm_buf buf; - u16 data_len; - u8 *data; - int rc; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, blob_handle); - tpm2_buf_append_auth(&buf, - options->policyhandle ? - options->policyhandle : TPM2_RS_PW, - NULL /* nonce */, 0, - TPM2_SA_CONTINUE_SESSION, - options->blobauth /* hmac */, - TPM_DIGEST_SIZE); - - rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing"); - if (rc > 0) - rc = -EPERM; - - if (!rc) { - data_len = be16_to_cpup( - (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); - if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { - rc = -EFAULT; - goto out; - } - - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) { - rc = -EFAULT; - goto out; - } - data = &buf.data[TPM_HEADER_SIZE + 6]; - - memcpy(payload->key, data, data_len - 1); - payload->key_len = data_len - 1; - payload->migratable = data[data_len - 1]; - } - -out: - tpm_buf_destroy(&buf); - return rc; -} - -/** - * tpm2_unseal_trusted() - unseal the payload of a trusted key - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * - * Return: Same as with tpm_transmit_cmd. - */ -int tpm2_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - u32 blob_handle; - int rc; - - rc = tpm2_load_cmd(chip, payload, options, &blob_handle); - if (rc) - return rc; - - rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); - tpm2_flush_context(chip, blob_handle); - return rc; -} - struct tpm2_get_cap_out { u8 more_data; __be32 subcap_id; @@ -939,6 +632,10 @@ static int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) chip->cc_attrs_tbl = devm_kcalloc(&chip->dev, 4, nr_commands, GFP_KERNEL); + if (!chip->cc_attrs_tbl) { + rc = -ENOMEM; + goto out; + } rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); if (rc) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index e59f1f91d7f3..a9dcf31eadd2 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -22,6 +22,7 @@ #include "tpm.h" #define ACPI_SIG_TPM2 "TPM2" +#define TPM_CRB_MAX_RESOURCES 3 static const guid_t crb_acpi_start_guid = GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714, @@ -91,7 +92,6 @@ enum crb_status { struct crb_priv { u32 sm; const char *hid; - void __iomem *iobase; struct crb_regs_head __iomem *regs_h; struct crb_regs_tail __iomem *regs_t; u8 __iomem *cmd; @@ -434,21 +434,27 @@ static const struct tpm_class_ops tpm_crb = { static int crb_check_resource(struct acpi_resource *ares, void *data) { - struct resource *io_res = data; + struct resource *iores_array = data; struct resource_win win; struct resource *res = &(win.res); + int i; if (acpi_dev_resource_memory(ares, res) || acpi_dev_resource_address_space(ares, &win)) { - *io_res = *res; - io_res->name = NULL; + for (i = 0; i < TPM_CRB_MAX_RESOURCES + 1; ++i) { + if (resource_type(iores_array + i) != IORESOURCE_MEM) { + iores_array[i] = *res; + iores_array[i].name = NULL; + break; + } + } } return 1; } -static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, - struct resource *io_res, u64 start, u32 size) +static void __iomem *crb_map_res(struct device *dev, struct resource *iores, + void __iomem **iobase_ptr, u64 start, u32 size) { struct resource new_res = { .start = start, @@ -460,10 +466,16 @@ static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, if (start != new_res.start) return (void __iomem *) ERR_PTR(-EINVAL); - if (!resource_contains(io_res, &new_res)) + if (!iores) return devm_ioremap_resource(dev, &new_res); - return priv->iobase + (new_res.start - io_res->start); + if (!*iobase_ptr) { + *iobase_ptr = devm_ioremap_resource(dev, iores); + if (IS_ERR(*iobase_ptr)) + return *iobase_ptr; + } + + return *iobase_ptr + (new_res.start - iores->start); } /* @@ -490,9 +502,13 @@ static u64 crb_fixup_cmd_size(struct device *dev, struct resource *io_res, static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, struct acpi_table_tpm2 *buf) { - struct list_head resources; - struct resource io_res; + struct list_head acpi_resource_list; + struct resource iores_array[TPM_CRB_MAX_RESOURCES + 1] = { {0} }; + void __iomem *iobase_array[TPM_CRB_MAX_RESOURCES] = {NULL}; struct device *dev = &device->dev; + struct resource *iores; + void __iomem **iobase_ptr; + int i; u32 pa_high, pa_low; u64 cmd_pa; u32 cmd_size; @@ -501,21 +517,41 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, u32 rsp_size; int ret; - INIT_LIST_HEAD(&resources); - ret = acpi_dev_get_resources(device, &resources, crb_check_resource, - &io_res); + INIT_LIST_HEAD(&acpi_resource_list); + ret = acpi_dev_get_resources(device, &acpi_resource_list, + crb_check_resource, iores_array); if (ret < 0) return ret; - acpi_dev_free_resource_list(&resources); + acpi_dev_free_resource_list(&acpi_resource_list); - if (resource_type(&io_res) != IORESOURCE_MEM) { + if (resource_type(iores_array) != IORESOURCE_MEM) { dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n"); return -EINVAL; + } else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) == + IORESOURCE_MEM) { + dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n"); + memset(iores_array + TPM_CRB_MAX_RESOURCES, + 0, sizeof(*iores_array)); + iores_array[TPM_CRB_MAX_RESOURCES].flags = 0; } - priv->iobase = devm_ioremap_resource(dev, &io_res); - if (IS_ERR(priv->iobase)) - return PTR_ERR(priv->iobase); + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (buf->control_address >= iores_array[i].start && + buf->control_address + sizeof(struct crb_regs_tail) - 1 <= + iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + priv->regs_t = crb_map_res(dev, iores, iobase_ptr, buf->control_address, + sizeof(struct crb_regs_tail)); + + if (IS_ERR(priv->regs_t)) + return PTR_ERR(priv->regs_t); /* The ACPI IO region starts at the head area and continues to include * the control area, as one nice sane region except for some older @@ -523,9 +559,10 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, */ if ((priv->sm == ACPI_TPM2_COMMAND_BUFFER) || (priv->sm == ACPI_TPM2_MEMORY_MAPPED)) { - if (buf->control_address == io_res.start + + if (iores && + buf->control_address == iores->start + sizeof(*priv->regs_h)) - priv->regs_h = priv->iobase; + priv->regs_h = *iobase_ptr; else dev_warn(dev, FW_BUG "Bad ACPI memory layout"); } @@ -534,13 +571,6 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, if (ret) return ret; - priv->regs_t = crb_map_res(dev, priv, &io_res, buf->control_address, - sizeof(struct crb_regs_tail)); - if (IS_ERR(priv->regs_t)) { - ret = PTR_ERR(priv->regs_t); - goto out_relinquish_locality; - } - /* * PTT HW bug w/a: wake up the device to access * possibly not retained registers. @@ -552,13 +582,26 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, pa_high = ioread32(&priv->regs_t->ctrl_cmd_pa_high); pa_low = ioread32(&priv->regs_t->ctrl_cmd_pa_low); cmd_pa = ((u64)pa_high << 32) | pa_low; - cmd_size = crb_fixup_cmd_size(dev, &io_res, cmd_pa, - ioread32(&priv->regs_t->ctrl_cmd_size)); + cmd_size = ioread32(&priv->regs_t->ctrl_cmd_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; iores_array[i].end; ++i) { + if (cmd_pa >= iores_array[i].start && + cmd_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + cmd_size = crb_fixup_cmd_size(dev, iores, cmd_pa, cmd_size); dev_dbg(dev, "cmd_hi = %X cmd_low = %X cmd_size %X\n", pa_high, pa_low, cmd_size); - priv->cmd = crb_map_res(dev, priv, &io_res, cmd_pa, cmd_size); + priv->cmd = crb_map_res(dev, iores, iobase_ptr, cmd_pa, cmd_size); if (IS_ERR(priv->cmd)) { ret = PTR_ERR(priv->cmd); goto out; @@ -566,11 +609,25 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, memcpy_fromio(&__rsp_pa, &priv->regs_t->ctrl_rsp_pa, 8); rsp_pa = le64_to_cpu(__rsp_pa); - rsp_size = crb_fixup_cmd_size(dev, &io_res, rsp_pa, - ioread32(&priv->regs_t->ctrl_rsp_size)); + rsp_size = ioread32(&priv->regs_t->ctrl_rsp_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (rsp_pa >= iores_array[i].start && + rsp_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + rsp_size = crb_fixup_cmd_size(dev, iores, rsp_pa, rsp_size); if (cmd_pa != rsp_pa) { - priv->rsp = crb_map_res(dev, priv, &io_res, rsp_pa, rsp_size); + priv->rsp = crb_map_res(dev, iores, iobase_ptr, + rsp_pa, rsp_size); ret = PTR_ERR_OR_ZERO(priv->rsp); goto out; } diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index e4fdde93ed4c..e7df342a317d 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -286,7 +286,7 @@ static int tpm_tis_plat_probe(struct platform_device *pdev) } tpm_info.res = *res; - tpm_info.irq = platform_get_irq(pdev, 0); + tpm_info.irq = platform_get_irq_optional(pdev, 0); if (tpm_info.irq <= 0) { if (pdev != force_pdev) tpm_info.irq = -1; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 270f43acbb77..8af2cee1a762 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -506,6 +506,84 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) return rc; } +struct tis_vendor_durations_override { + u32 did_vid; + struct tpm1_version version; + unsigned long durations[3]; +}; + +static const struct tis_vendor_durations_override vendor_dur_overrides[] = { + /* STMicroelectronics 0x104a */ + { 0x0000104a, + { 1, 2, 8, 28 }, + { (2 * 60 * HZ), (2 * 60 * HZ), (2 * 60 * HZ) } }, +}; + +static void tpm_tis_update_durations(struct tpm_chip *chip, + unsigned long *duration_cap) +{ + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); + struct tpm1_version *version; + u32 did_vid; + int i, rc; + cap_t cap; + + chip->duration_adjusted = false; + + if (chip->ops->clk_enable != NULL) + chip->ops->clk_enable(chip, true); + + rc = tpm_tis_read32(priv, TPM_DID_VID(0), &did_vid); + if (rc < 0) { + dev_warn(&chip->dev, "%s: failed to read did_vid. %d\n", + __func__, rc); + goto out; + } + + /* Try to get a TPM version 1.2 or 1.1 TPM_CAP_VERSION_INFO */ + rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap, + "attempting to determine the 1.2 version", + sizeof(cap.version2)); + if (!rc) { + version = &cap.version2.version; + } else { + rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap, + "attempting to determine the 1.1 version", + sizeof(cap.version1)); + + if (rc) + goto out; + + version = &cap.version1; + } + + for (i = 0; i != ARRAY_SIZE(vendor_dur_overrides); i++) { + if (vendor_dur_overrides[i].did_vid != did_vid) + continue; + + if ((version->major == + vendor_dur_overrides[i].version.major) && + (version->minor == + vendor_dur_overrides[i].version.minor) && + (version->rev_major == + vendor_dur_overrides[i].version.rev_major) && + (version->rev_minor == + vendor_dur_overrides[i].version.rev_minor)) { + + memcpy(duration_cap, + vendor_dur_overrides[i].durations, + sizeof(vendor_dur_overrides[i].durations)); + + chip->duration_adjusted = true; + goto out; + } + } + +out: + if (chip->ops->clk_enable != NULL) + chip->ops->clk_enable(chip, false); +} + struct tis_vendor_timeout_override { u32 did_vid; unsigned long timeout_us[4]; @@ -842,6 +920,7 @@ static const struct tpm_class_ops tpm_tis = { .send = tpm_tis_send, .cancel = tpm_tis_ready, .update_timeouts = tpm_tis_update_timeouts, + .update_durations = tpm_tis_update_durations, .req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_canceled = tpm_tis_req_canceled, diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi.c index 19513e622053..d1754fd6c573 100644 --- a/drivers/char/tpm/tpm_tis_spi.c +++ b/drivers/char/tpm/tpm_tis_spi.c @@ -20,42 +20,64 @@ * Dorn and Kyleen Hall and Jarko Sakkinnen. */ +#include <linux/acpi.h> +#include <linux/completion.h> #include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/slab.h> -#include <linux/interrupt.h> -#include <linux/wait.h> -#include <linux/acpi.h> -#include <linux/freezer.h> +#include <linux/of_device.h> #include <linux/spi/spi.h> -#include <linux/gpio.h> -#include <linux/of_irq.h> -#include <linux/of_gpio.h> #include <linux/tpm.h> + #include "tpm.h" #include "tpm_tis_core.h" +#include "tpm_tis_spi.h" #define MAX_SPI_FRAMESIZE 64 -struct tpm_tis_spi_phy { - struct tpm_tis_data priv; - struct spi_device *spi_device; - u8 *iobuf; -}; - -static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data) +/* + * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short, + * keep trying to read from the device until MISO goes high indicating the + * wait state has ended. + * + * [1] https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ + */ +static int tpm_tis_spi_flow_control(struct tpm_tis_spi_phy *phy, + struct spi_transfer *spi_xfer) { - return container_of(data, struct tpm_tis_spi_phy, priv); + struct spi_message m; + int ret, i; + + if ((phy->iobuf[3] & 0x01) == 0) { + // handle SPI wait states + phy->iobuf[0] = 0; + + for (i = 0; i < TPM_RETRY; i++) { + spi_xfer->len = 1; + spi_message_init(&m); + spi_message_add_tail(spi_xfer, &m); + ret = spi_sync_locked(phy->spi_device, &m); + if (ret < 0) + return ret; + if (phy->iobuf[0] & 0x01) + break; + } + + if (i == TPM_RETRY) + return -ETIMEDOUT; + } + + return 0; } -static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, - u8 *in, const u8 *out) +int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, + u8 *in, const u8 *out) { struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); int ret = 0; - int i; struct spi_message m; struct spi_transfer spi_xfer; u8 transfer_len; @@ -82,26 +104,9 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, if (ret < 0) goto exit; - if ((phy->iobuf[3] & 0x01) == 0) { - // handle SPI wait states - phy->iobuf[0] = 0; - - for (i = 0; i < TPM_RETRY; i++) { - spi_xfer.len = 1; - spi_message_init(&m); - spi_message_add_tail(&spi_xfer, &m); - ret = spi_sync_locked(phy->spi_device, &m); - if (ret < 0) - goto exit; - if (phy->iobuf[0] & 0x01) - break; - } - - if (i == TPM_RETRY) { - ret = -ETIMEDOUT; - goto exit; - } - } + ret = phy->flow_control(phy, &spi_xfer); + if (ret < 0) + goto exit; spi_xfer.cs_change = 0; spi_xfer.len = transfer_len; @@ -117,6 +122,7 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, spi_message_init(&m); spi_message_add_tail(&spi_xfer, &m); + reinit_completion(&phy->ready); ret = spi_sync_locked(phy->spi_device, &m); if (ret < 0) goto exit; @@ -146,7 +152,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr, return tpm_tis_spi_transfer(data, addr, len, NULL, value); } -static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result) +int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result) { __le16 result_le; int rc; @@ -159,7 +165,7 @@ static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result) return rc; } -static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result) +int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result) { __le32 result_le; int rc; @@ -172,7 +178,7 @@ static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result) return rc; } -static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value) +int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value) { __le32 value_le; int rc; @@ -184,6 +190,18 @@ static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value) return rc; } +int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, + int irq, const struct tpm_tis_phy_ops *phy_ops) +{ + phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); + if (!phy->iobuf) + return -ENOMEM; + + phy->spi_device = spi; + + return tpm_tis_core_init(&spi->dev, &phy->priv, irq, phy_ops, NULL); +} + static const struct tpm_tis_phy_ops tpm_spi_phy_ops = { .read_bytes = tpm_tis_spi_read_bytes, .write_bytes = tpm_tis_spi_write_bytes, @@ -202,11 +220,7 @@ static int tpm_tis_spi_probe(struct spi_device *dev) if (!phy) return -ENOMEM; - phy->spi_device = dev; - - phy->iobuf = devm_kmalloc(&dev->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); - if (!phy->iobuf) - return -ENOMEM; + phy->flow_control = tpm_tis_spi_flow_control; /* If the SPI device has an IRQ then use that */ if (dev->irq > 0) @@ -214,11 +228,27 @@ static int tpm_tis_spi_probe(struct spi_device *dev) else irq = -1; - return tpm_tis_core_init(&dev->dev, &phy->priv, irq, &tpm_spi_phy_ops, - NULL); + init_completion(&phy->ready); + return tpm_tis_spi_init(dev, phy, irq, &tpm_spi_phy_ops); +} + +typedef int (*tpm_tis_spi_probe_func)(struct spi_device *); + +static int tpm_tis_spi_driver_probe(struct spi_device *spi) +{ + const struct spi_device_id *spi_dev_id = spi_get_device_id(spi); + tpm_tis_spi_probe_func probe_func; + + probe_func = of_device_get_match_data(&spi->dev); + if (!probe_func && spi_dev_id) + probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data; + if (!probe_func) + return -ENODEV; + + return probe_func(spi); } -static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume); +static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_spi_resume); static int tpm_tis_spi_remove(struct spi_device *dev) { @@ -230,15 +260,17 @@ static int tpm_tis_spi_remove(struct spi_device *dev) } static const struct spi_device_id tpm_tis_spi_id[] = { - {"tpm_tis_spi", 0}, + { "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe }, + { "cr50", (unsigned long)cr50_spi_probe }, {} }; MODULE_DEVICE_TABLE(spi, tpm_tis_spi_id); static const struct of_device_id of_tis_spi_match[] = { - { .compatible = "st,st33htpm-spi", }, - { .compatible = "infineon,slb9670", }, - { .compatible = "tcg,tpm_tis-spi", }, + { .compatible = "st,st33htpm-spi", .data = tpm_tis_spi_probe }, + { .compatible = "infineon,slb9670", .data = tpm_tis_spi_probe }, + { .compatible = "tcg,tpm_tis-spi", .data = tpm_tis_spi_probe }, + { .compatible = "google,cr50", .data = cr50_spi_probe }, {} }; MODULE_DEVICE_TABLE(of, of_tis_spi_match); @@ -251,13 +283,12 @@ MODULE_DEVICE_TABLE(acpi, acpi_tis_spi_match); static struct spi_driver tpm_tis_spi_driver = { .driver = { - .owner = THIS_MODULE, .name = "tpm_tis_spi", .pm = &tpm_tis_pm, .of_match_table = of_match_ptr(of_tis_spi_match), .acpi_match_table = ACPI_PTR(acpi_tis_spi_match), }, - .probe = tpm_tis_spi_probe, + .probe = tpm_tis_spi_driver_probe, .remove = tpm_tis_spi_remove, .id_table = tpm_tis_spi_id, }; diff --git a/drivers/char/tpm/tpm_tis_spi.h b/drivers/char/tpm/tpm_tis_spi.h new file mode 100644 index 000000000000..bba73979c368 --- /dev/null +++ b/drivers/char/tpm/tpm_tis_spi.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 Infineon Technologies AG + * Copyright (C) 2016 STMicroelectronics SAS + */ + +#ifndef TPM_TIS_SPI_H +#define TPM_TIS_SPI_H + +#include "tpm_tis_core.h" + +struct tpm_tis_spi_phy { + struct tpm_tis_data priv; + struct spi_device *spi_device; + int (*flow_control)(struct tpm_tis_spi_phy *phy, + struct spi_transfer *xfer); + struct completion ready; + unsigned long wake_after; + + u8 *iobuf; +}; + +static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data) +{ + return container_of(data, struct tpm_tis_spi_phy, priv); +} + +extern int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, + int irq, const struct tpm_tis_phy_ops *phy_ops); + +extern int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, + u8 *in, const u8 *out); + +extern int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result); +extern int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result); +extern int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value); + +#ifdef CONFIG_TCG_TIS_SPI_CR50 +extern int cr50_spi_probe(struct spi_device *spi); +#else +static inline int cr50_spi_probe(struct spi_device *spi) +{ + return -ENODEV; +} +#endif + +#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_TCG_TIS_SPI_CR50) +extern int tpm_tis_spi_resume(struct device *dev); +#else +#define tpm_tis_spi_resume NULL +#endif + +#endif diff --git a/drivers/char/tpm/tpm_tis_spi_cr50.c b/drivers/char/tpm/tpm_tis_spi_cr50.c new file mode 100644 index 000000000000..37d72e818335 --- /dev/null +++ b/drivers/char/tpm/tpm_tis_spi_cr50.c @@ -0,0 +1,322 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2016 Google, Inc + * + * This device driver implements a TCG PTP FIFO interface over SPI for chips + * with Cr50 firmware. + * It is based on tpm_tis_spi driver by Peter Huewe and Christophe Ricard. + */ + +#include <linux/completion.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/pm.h> +#include <linux/spi/spi.h> +#include <linux/wait.h> + +#include "tpm_tis_core.h" +#include "tpm_tis_spi.h" + +/* + * Cr50 timing constants: + * - can go to sleep not earlier than after CR50_SLEEP_DELAY_MSEC. + * - needs up to CR50_WAKE_START_DELAY_USEC to wake after sleep. + * - requires waiting for "ready" IRQ, if supported; or waiting for at least + * CR50_NOIRQ_ACCESS_DELAY_MSEC between transactions, if IRQ is not supported. + * - waits for up to CR50_FLOW_CONTROL for flow control 'ready' indication. + */ +#define CR50_SLEEP_DELAY_MSEC 1000 +#define CR50_WAKE_START_DELAY_USEC 1000 +#define CR50_NOIRQ_ACCESS_DELAY msecs_to_jiffies(2) +#define CR50_READY_IRQ_TIMEOUT msecs_to_jiffies(TPM2_TIMEOUT_A) +#define CR50_FLOW_CONTROL msecs_to_jiffies(TPM2_TIMEOUT_A) +#define MAX_IRQ_CONFIRMATION_ATTEMPTS 3 + +#define TPM_CR50_FW_VER(l) (0x0f90 | ((l) << 12)) +#define TPM_CR50_MAX_FW_VER_LEN 64 + +struct cr50_spi_phy { + struct tpm_tis_spi_phy spi_phy; + + struct mutex time_track_mutex; + unsigned long last_access; + + unsigned long access_delay; + + unsigned int irq_confirmation_attempt; + bool irq_needs_confirmation; + bool irq_confirmed; +}; + +static inline struct cr50_spi_phy *to_cr50_spi_phy(struct tpm_tis_spi_phy *phy) +{ + return container_of(phy, struct cr50_spi_phy, spi_phy); +} + +/* + * The cr50 interrupt handler just signals waiting threads that the + * interrupt was asserted. It does not do any processing triggered + * by interrupts but is instead used to avoid fixed delays. + */ +static irqreturn_t cr50_spi_irq_handler(int dummy, void *dev_id) +{ + struct cr50_spi_phy *cr50_phy = dev_id; + + cr50_phy->irq_confirmed = true; + complete(&cr50_phy->spi_phy.ready); + + return IRQ_HANDLED; +} + +/* + * Cr50 needs to have at least some delay between consecutive + * transactions. Make sure we wait. + */ +static void cr50_ensure_access_delay(struct cr50_spi_phy *phy) +{ + unsigned long allowed_access = phy->last_access + phy->access_delay; + unsigned long time_now = jiffies; + struct device *dev = &phy->spi_phy.spi_device->dev; + + /* + * Note: There is a small chance, if Cr50 is not accessed in a few days, + * that time_in_range will not provide the correct result after the wrap + * around for jiffies. In this case, we'll have an unneeded short delay, + * which is fine. + */ + if (time_in_range_open(time_now, phy->last_access, allowed_access)) { + unsigned long remaining, timeout = allowed_access - time_now; + + remaining = wait_for_completion_timeout(&phy->spi_phy.ready, + timeout); + if (!remaining && phy->irq_confirmed) + dev_warn(dev, "Timeout waiting for TPM ready IRQ\n"); + } + + if (phy->irq_needs_confirmation) { + unsigned int attempt = ++phy->irq_confirmation_attempt; + + if (phy->irq_confirmed) { + phy->irq_needs_confirmation = false; + phy->access_delay = CR50_READY_IRQ_TIMEOUT; + dev_info(dev, "TPM ready IRQ confirmed on attempt %u\n", + attempt); + } else if (attempt > MAX_IRQ_CONFIRMATION_ATTEMPTS) { + phy->irq_needs_confirmation = false; + dev_warn(dev, "IRQ not confirmed - will use delays\n"); + } + } +} + +/* + * Cr50 might go to sleep if there is no SPI activity for some time and + * miss the first few bits/bytes on the bus. In such case, wake it up + * by asserting CS and give it time to start up. + */ +static bool cr50_needs_waking(struct cr50_spi_phy *phy) +{ + /* + * Note: There is a small chance, if Cr50 is not accessed in a few days, + * that time_in_range will not provide the correct result after the wrap + * around for jiffies. In this case, we'll probably timeout or read + * incorrect value from TPM_STS and just retry the operation. + */ + return !time_in_range_open(jiffies, phy->last_access, + phy->spi_phy.wake_after); +} + +static void cr50_wake_if_needed(struct cr50_spi_phy *cr50_phy) +{ + struct tpm_tis_spi_phy *phy = &cr50_phy->spi_phy; + + if (cr50_needs_waking(cr50_phy)) { + /* Assert CS, wait 1 msec, deassert CS */ + struct spi_transfer spi_cs_wake = { .delay_usecs = 1000 }; + + spi_sync_transfer(phy->spi_device, &spi_cs_wake, 1); + /* Wait for it to fully wake */ + usleep_range(CR50_WAKE_START_DELAY_USEC, + CR50_WAKE_START_DELAY_USEC * 2); + } + + /* Reset the time when we need to wake Cr50 again */ + phy->wake_after = jiffies + msecs_to_jiffies(CR50_SLEEP_DELAY_MSEC); +} + +/* + * Flow control: clock the bus and wait for cr50 to set LSB before + * sending/receiving data. TCG PTP spec allows it to happen during + * the last byte of header, but cr50 never does that in practice, + * and earlier versions had a bug when it was set too early, so don't + * check for it during header transfer. + */ +static int cr50_spi_flow_control(struct tpm_tis_spi_phy *phy, + struct spi_transfer *spi_xfer) +{ + struct device *dev = &phy->spi_device->dev; + unsigned long timeout = jiffies + CR50_FLOW_CONTROL; + struct spi_message m; + int ret; + + spi_xfer->len = 1; + + do { + spi_message_init(&m); + spi_message_add_tail(spi_xfer, &m); + ret = spi_sync_locked(phy->spi_device, &m); + if (ret < 0) + return ret; + + if (time_after(jiffies, timeout)) { + dev_warn(dev, "Timeout during flow control\n"); + return -EBUSY; + } + } while (!(phy->iobuf[0] & 0x01)); + + return 0; +} + +static int tpm_tis_spi_cr50_transfer(struct tpm_tis_data *data, u32 addr, u16 len, + u8 *in, const u8 *out) +{ + struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); + struct cr50_spi_phy *cr50_phy = to_cr50_spi_phy(phy); + int ret; + + mutex_lock(&cr50_phy->time_track_mutex); + /* + * Do this outside of spi_bus_lock in case cr50 is not the + * only device on that spi bus. + */ + cr50_ensure_access_delay(cr50_phy); + cr50_wake_if_needed(cr50_phy); + + ret = tpm_tis_spi_transfer(data, addr, len, in, out); + + cr50_phy->last_access = jiffies; + mutex_unlock(&cr50_phy->time_track_mutex); + + return ret; +} + +static int tpm_tis_spi_cr50_read_bytes(struct tpm_tis_data *data, u32 addr, + u16 len, u8 *result) +{ + return tpm_tis_spi_cr50_transfer(data, addr, len, result, NULL); +} + +static int tpm_tis_spi_cr50_write_bytes(struct tpm_tis_data *data, u32 addr, + u16 len, const u8 *value) +{ + return tpm_tis_spi_cr50_transfer(data, addr, len, NULL, value); +} + +static const struct tpm_tis_phy_ops tpm_spi_cr50_phy_ops = { + .read_bytes = tpm_tis_spi_cr50_read_bytes, + .write_bytes = tpm_tis_spi_cr50_write_bytes, + .read16 = tpm_tis_spi_read16, + .read32 = tpm_tis_spi_read32, + .write32 = tpm_tis_spi_write32, +}; + +static void cr50_print_fw_version(struct tpm_tis_data *data) +{ + struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); + int i, len = 0; + char fw_ver[TPM_CR50_MAX_FW_VER_LEN + 1]; + char fw_ver_block[4]; + + /* + * Write anything to TPM_CR50_FW_VER to start from the beginning + * of the version string + */ + tpm_tis_write8(data, TPM_CR50_FW_VER(data->locality), 0); + + /* Read the string, 4 bytes at a time, until we get '\0' */ + do { + tpm_tis_read_bytes(data, TPM_CR50_FW_VER(data->locality), 4, + fw_ver_block); + for (i = 0; i < 4 && fw_ver_block[i]; ++len, ++i) + fw_ver[len] = fw_ver_block[i]; + } while (i == 4 && len < TPM_CR50_MAX_FW_VER_LEN); + fw_ver[len] = '\0'; + + dev_info(&phy->spi_device->dev, "Cr50 firmware version: %s\n", fw_ver); +} + +int cr50_spi_probe(struct spi_device *spi) +{ + struct tpm_tis_spi_phy *phy; + struct cr50_spi_phy *cr50_phy; + int ret; + struct tpm_chip *chip; + + cr50_phy = devm_kzalloc(&spi->dev, sizeof(*cr50_phy), GFP_KERNEL); + if (!cr50_phy) + return -ENOMEM; + + phy = &cr50_phy->spi_phy; + phy->flow_control = cr50_spi_flow_control; + phy->wake_after = jiffies; + init_completion(&phy->ready); + + cr50_phy->access_delay = CR50_NOIRQ_ACCESS_DELAY; + cr50_phy->last_access = jiffies; + mutex_init(&cr50_phy->time_track_mutex); + + if (spi->irq > 0) { + ret = devm_request_irq(&spi->dev, spi->irq, + cr50_spi_irq_handler, + IRQF_TRIGGER_RISING | IRQF_ONESHOT, + "cr50_spi", cr50_phy); + if (ret < 0) { + if (ret == -EPROBE_DEFER) + return ret; + dev_warn(&spi->dev, "Requesting IRQ %d failed: %d\n", + spi->irq, ret); + /* + * This is not fatal, the driver will fall back to + * delays automatically, since ready will never + * be completed without a registered irq handler. + * So, just fall through. + */ + } else { + /* + * IRQ requested, let's verify that it is actually + * triggered, before relying on it. + */ + cr50_phy->irq_needs_confirmation = true; + } + } else { + dev_warn(&spi->dev, + "No IRQ - will use delays between transactions.\n"); + } + + ret = tpm_tis_spi_init(spi, phy, -1, &tpm_spi_cr50_phy_ops); + if (ret) + return ret; + + cr50_print_fw_version(&phy->priv); + + chip = dev_get_drvdata(&spi->dev); + chip->flags |= TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED; + + return 0; +} + +#ifdef CONFIG_PM_SLEEP +int tpm_tis_spi_resume(struct device *dev) +{ + struct tpm_chip *chip = dev_get_drvdata(dev); + struct tpm_tis_data *data = dev_get_drvdata(&chip->dev); + struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); + /* + * Jiffies not increased during suspend, so we need to reset + * the time to wake Cr50 after resume. + */ + phy->wake_after = jiffies; + + return tpm_tis_resume(dev); +} +#endif diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 7270e7b69262..3259426f01dc 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1325,24 +1325,24 @@ static void set_console_size(struct port *port, u16 rows, u16 cols) port->cons.ws.ws_col = cols; } -static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock) +static int fill_queue(struct virtqueue *vq, spinlock_t *lock) { struct port_buffer *buf; - unsigned int nr_added_bufs; + int nr_added_bufs; int ret; nr_added_bufs = 0; do { buf = alloc_buf(vq->vdev, PAGE_SIZE, 0); if (!buf) - break; + return -ENOMEM; spin_lock_irq(lock); ret = add_inbuf(vq, buf); if (ret < 0) { spin_unlock_irq(lock); free_buf(buf, true); - break; + return ret; } nr_added_bufs++; spin_unlock_irq(lock); @@ -1362,7 +1362,6 @@ static int add_port(struct ports_device *portdev, u32 id) char debugfs_name[16]; struct port *port; dev_t devt; - unsigned int nr_added_bufs; int err; port = kmalloc(sizeof(*port), GFP_KERNEL); @@ -1421,11 +1420,13 @@ static int add_port(struct ports_device *portdev, u32 id) spin_lock_init(&port->outvq_lock); init_waitqueue_head(&port->waitqueue); - /* Fill the in_vq with buffers so the host can send us data. */ - nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock); - if (!nr_added_bufs) { + /* We can safely ignore ENOSPC because it means + * the queue already has buffers. Buffers are removed + * only by virtcons_remove(), not by unplug_port() + */ + err = fill_queue(port->in_vq, &port->inbuf_lock); + if (err < 0 && err != -ENOSPC) { dev_err(port->dev, "Error allocating inbufs\n"); - err = -ENOMEM; goto free_device; } @@ -2059,14 +2060,11 @@ static int virtcons_probe(struct virtio_device *vdev) INIT_WORK(&portdev->control_work, &control_work_handler); if (multiport) { - unsigned int nr_added_bufs; - spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); - nr_added_bufs = fill_queue(portdev->c_ivq, - &portdev->c_ivq_lock); - if (!nr_added_bufs) { + err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); + if (err < 0) { dev_err(&vdev->dev, "Error allocating buffers for control queue\n"); /* @@ -2077,7 +2075,7 @@ static int virtcons_probe(struct virtio_device *vdev) VIRTIO_CONSOLE_DEVICE_READY, 0); /* Device was functional: we need full cleanup. */ virtcons_remove(vdev); - return -ENOMEM; + return err; } } else { /* diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c index 87083b3a2769..37c22667e831 100644 --- a/drivers/clk/at91/clk-main.c +++ b/drivers/clk/at91/clk-main.c @@ -297,7 +297,10 @@ static int clk_main_probe_frequency(struct regmap *regmap) regmap_read(regmap, AT91_CKGR_MCFR, &mcfr); if (mcfr & AT91_PMC_MAINRDY) return 0; - usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT); + if (system_state < SYSTEM_RUNNING) + udelay(MAINF_LOOP_MIN_WAIT); + else + usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT); } while (time_before(prep_time, timeout)); return -ETIMEDOUT; diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c index 9790ddfa5b3c..86238d5ecb4d 100644 --- a/drivers/clk/at91/sam9x60.c +++ b/drivers/clk/at91/sam9x60.c @@ -43,6 +43,7 @@ static const struct clk_pll_characteristics upll_characteristics = { }; static const struct clk_programmable_layout sam9x60_programmable_layout = { + .pres_mask = 0xff, .pres_shift = 8, .css_mask = 0x1f, .have_slck_mck = 0, diff --git a/drivers/clk/at91/sckc.c b/drivers/clk/at91/sckc.c index 9bfe9a28294a..fac0ca56d42d 100644 --- a/drivers/clk/at91/sckc.c +++ b/drivers/clk/at91/sckc.c @@ -76,7 +76,10 @@ static int clk_slow_osc_prepare(struct clk_hw *hw) writel(tmp | osc->bits->cr_osc32en, sckcr); - usleep_range(osc->startup_usec, osc->startup_usec + 1); + if (system_state < SYSTEM_RUNNING) + udelay(osc->startup_usec); + else + usleep_range(osc->startup_usec, osc->startup_usec + 1); return 0; } @@ -187,7 +190,10 @@ static int clk_slow_rc_osc_prepare(struct clk_hw *hw) writel(readl(sckcr) | osc->bits->cr_rcen, sckcr); - usleep_range(osc->startup_usec, osc->startup_usec + 1); + if (system_state < SYSTEM_RUNNING) + udelay(osc->startup_usec); + else + usleep_range(osc->startup_usec, osc->startup_usec + 1); return 0; } @@ -288,7 +294,10 @@ static int clk_sam9x5_slow_set_parent(struct clk_hw *hw, u8 index) writel(tmp, sckcr); - usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1); + if (system_state < SYSTEM_RUNNING) + udelay(SLOWCK_SW_TIME_USEC); + else + usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1); return 0; } @@ -533,7 +542,10 @@ static int clk_sama5d4_slow_osc_prepare(struct clk_hw *hw) return 0; } - usleep_range(osc->startup_usec, osc->startup_usec + 1); + if (system_state < SYSTEM_RUNNING) + udelay(osc->startup_usec); + else + usleep_range(osc->startup_usec, osc->startup_usec + 1); osc->prepared = true; return 0; diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c index 1c1bb39bb04e..b1318e6b655b 100644 --- a/drivers/clk/clk-ast2600.c +++ b/drivers/clk/clk-ast2600.c @@ -266,10 +266,11 @@ static int aspeed_g6_clk_enable(struct clk_hw *hw) /* Enable clock */ if (gate->flags & CLK_GATE_SET_TO_DISABLE) { - regmap_write(gate->map, get_clock_reg(gate), clk); - } else { - /* Use set to clear register */ + /* Clock is clear to enable, so use set to clear register */ regmap_write(gate->map, get_clock_reg(gate) + 0x04, clk); + } else { + /* Clock is set to enable, so use write to set register */ + regmap_write(gate->map, get_clock_reg(gate), clk); } if (gate->reset_idx >= 0) { diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c index 067ab876911d..172589e94f60 100644 --- a/drivers/clk/imx/clk-imx8mm.c +++ b/drivers/clk/imx/clk-imx8mm.c @@ -638,7 +638,7 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) clks[IMX8MM_CLK_A53_DIV], clks[IMX8MM_CLK_A53_SRC], clks[IMX8MM_ARM_PLL_OUT], - clks[IMX8MM_CLK_24M]); + clks[IMX8MM_SYS_PLL1_800M]); imx_check_clocks(clks, ARRAY_SIZE(clks)); diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index 47a4b44ba3cb..58b5acee3830 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -610,7 +610,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) clks[IMX8MN_CLK_A53_DIV], clks[IMX8MN_CLK_A53_SRC], clks[IMX8MN_ARM_PLL_OUT], - clks[IMX8MN_CLK_24M]); + clks[IMX8MN_SYS_PLL1_800M]); imx_check_clocks(clks, ARRAY_SIZE(clks)); diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c index ea4c791f106d..b3af61cc6fb9 100644 --- a/drivers/clk/meson/g12a.c +++ b/drivers/clk/meson/g12a.c @@ -343,6 +343,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x3, .shift = 0, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk_dyn0_sel", @@ -353,8 +354,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = { { .hw = &g12a_fclk_div3.hw }, }, .num_parents = 3, - /* This sub-tree is used a parking clock */ - .flags = CLK_SET_RATE_NO_REPARENT, + .flags = CLK_SET_RATE_PARENT, }, }; @@ -410,6 +410,7 @@ static struct clk_regmap g12a_cpu_clk_postmux0 = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 2, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk_dyn0", @@ -466,6 +467,7 @@ static struct clk_regmap g12a_cpu_clk_dyn = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 10, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk_dyn", @@ -485,6 +487,7 @@ static struct clk_regmap g12a_cpu_clk = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 11, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk", @@ -504,6 +507,7 @@ static struct clk_regmap g12b_cpu_clk = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 11, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk", @@ -523,6 +527,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x3, .shift = 0, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk_dyn0_sel", @@ -533,6 +538,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = { { .hw = &g12a_fclk_div3.hw }, }, .num_parents = 3, + .flags = CLK_SET_RATE_PARENT, }, }; @@ -567,6 +573,7 @@ static struct clk_regmap g12b_cpub_clk_postmux0 = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x1, .shift = 2, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk_dyn0", @@ -644,6 +651,7 @@ static struct clk_regmap g12b_cpub_clk_dyn = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x1, .shift = 10, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk_dyn", @@ -663,6 +671,7 @@ static struct clk_regmap g12b_cpub_clk = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x1, .shift = 11, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk", diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 7cfb998eeb3e..1f9c056e684c 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -935,6 +935,7 @@ static struct clk_regmap gxbb_sar_adc_clk_div = { &gxbb_sar_adc_clk_sel.hw }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, }, }; diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c index 7670cc596c74..31466cd1842f 100644 --- a/drivers/clk/samsung/clk-exynos5420.c +++ b/drivers/clk/samsung/clk-exynos5420.c @@ -165,12 +165,18 @@ static const unsigned long exynos5x_clk_regs[] __initconst = { GATE_BUS_CPU, GATE_SCLK_CPU, CLKOUT_CMU_CPU, + CPLL_CON0, + DPLL_CON0, EPLL_CON0, EPLL_CON1, EPLL_CON2, RPLL_CON0, RPLL_CON1, RPLL_CON2, + IPLL_CON0, + SPLL_CON0, + VPLL_CON0, + MPLL_CON0, SRC_TOP0, SRC_TOP1, SRC_TOP2, @@ -1172,8 +1178,6 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = { GATE(CLK_SCLK_ISP_SENSOR2, "sclk_isp_sensor2", "dout_isp_sensor2", GATE_TOP_SCLK_ISP, 12, CLK_SET_RATE_PARENT, 0), - GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0), - /* CDREX */ GATE(CLK_CLKM_PHY0, "clkm_phy0", "dout_sclk_cdrex", GATE_BUS_CDREX0, 0, 0, 0), @@ -1248,6 +1252,15 @@ static struct exynos5_subcmu_reg_dump exynos5x_gsc_suspend_regs[] = { { DIV2_RATIO0, 0, 0x30 }, /* DIV dout_gscl_blk_300 */ }; +static const struct samsung_gate_clock exynos5x_g3d_gate_clks[] __initconst = { + GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0), +}; + +static struct exynos5_subcmu_reg_dump exynos5x_g3d_suspend_regs[] = { + { GATE_IP_G3D, 0x3ff, 0x3ff }, /* G3D gates */ + { SRC_TOP5, 0, BIT(16) }, /* MUX mout_user_aclk_g3d */ +}; + static const struct samsung_div_clock exynos5x_mfc_div_clks[] __initconst = { DIV(0, "dout_mfc_blk", "mout_user_aclk333", DIV4_RATIO, 0, 2), }; @@ -1320,6 +1333,14 @@ static const struct exynos5_subcmu_info exynos5x_gsc_subcmu = { .pd_name = "GSC", }; +static const struct exynos5_subcmu_info exynos5x_g3d_subcmu = { + .gate_clks = exynos5x_g3d_gate_clks, + .nr_gate_clks = ARRAY_SIZE(exynos5x_g3d_gate_clks), + .suspend_regs = exynos5x_g3d_suspend_regs, + .nr_suspend_regs = ARRAY_SIZE(exynos5x_g3d_suspend_regs), + .pd_name = "G3D", +}; + static const struct exynos5_subcmu_info exynos5x_mfc_subcmu = { .div_clks = exynos5x_mfc_div_clks, .nr_div_clks = ARRAY_SIZE(exynos5x_mfc_div_clks), @@ -1351,6 +1372,7 @@ static const struct exynos5_subcmu_info exynos5800_mau_subcmu = { static const struct exynos5_subcmu_info *exynos5x_subcmus[] = { &exynos5x_disp_subcmu, &exynos5x_gsc_subcmu, + &exynos5x_g3d_subcmu, &exynos5x_mfc_subcmu, &exynos5x_mscl_subcmu, }; @@ -1358,6 +1380,7 @@ static const struct exynos5_subcmu_info *exynos5x_subcmus[] = { static const struct exynos5_subcmu_info *exynos5800_subcmus[] = { &exynos5x_disp_subcmu, &exynos5x_gsc_subcmu, + &exynos5x_g3d_subcmu, &exynos5x_mfc_subcmu, &exynos5x_mscl_subcmu, &exynos5800_mau_subcmu, diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c index 7824c2ba3d8e..4b1aa9382ad2 100644 --- a/drivers/clk/samsung/clk-exynos5433.c +++ b/drivers/clk/samsung/clk-exynos5433.c @@ -13,6 +13,7 @@ #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/slab.h> #include <dt-bindings/clock/exynos5433.h> @@ -5584,6 +5585,8 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev) data->clk_save = samsung_clk_alloc_reg_dump(info->clk_regs, info->nr_clk_regs); + if (!data->clk_save) + return -ENOMEM; data->nr_clk_save = info->nr_clk_regs; data->clk_suspend = info->suspend_regs; data->nr_clk_suspend = info->nr_suspend_regs; @@ -5592,12 +5595,19 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev) if (data->nr_pclks > 0) { data->pclks = devm_kcalloc(dev, sizeof(struct clk *), data->nr_pclks, GFP_KERNEL); - + if (!data->pclks) { + kfree(data->clk_save); + return -ENOMEM; + } for (i = 0; i < data->nr_pclks; i++) { struct clk *clk = of_clk_get(dev->of_node, i); - if (IS_ERR(clk)) + if (IS_ERR(clk)) { + kfree(data->clk_save); + while (--i >= 0) + clk_put(data->pclks[i]); return PTR_ERR(clk); + } data->pclks[i] = clk; } } diff --git a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c index dcac1391767f..ef29582676f6 100644 --- a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c +++ b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c @@ -1224,7 +1224,7 @@ static int sun9i_a80_ccu_probe(struct platform_device *pdev) /* Enforce d1 = 0, d2 = 0 for Audio PLL */ val = readl(reg + SUN9I_A80_PLL_AUDIO_REG); - val &= (BIT(16) & BIT(18)); + val &= ~(BIT(16) | BIT(18)); writel(val, reg + SUN9I_A80_PLL_AUDIO_REG); /* Enforce P = 1 for both CPU cluster PLLs */ diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c index d3a43381a792..27201fd26e44 100644 --- a/drivers/clk/sunxi/clk-sunxi.c +++ b/drivers/clk/sunxi/clk-sunxi.c @@ -1080,8 +1080,8 @@ static struct clk ** __init sunxi_divs_clk_setup(struct device_node *node, rate_hw, rate_ops, gate_hw, &clk_gate_ops, clkflags | - data->div[i].critical ? - CLK_IS_CRITICAL : 0); + (data->div[i].critical ? + CLK_IS_CRITICAL : 0)); WARN_ON(IS_ERR(clk_data->clks[i])); } diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c index a01ca9395179..f65e16c4f3c4 100644 --- a/drivers/clk/ti/clk-dra7-atl.c +++ b/drivers/clk/ti/clk-dra7-atl.c @@ -174,7 +174,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node) struct clk_init_data init = { NULL }; const char **parent_names = NULL; struct clk *clk; - int ret; clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL); if (!clk_hw) { @@ -207,11 +206,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node) clk = ti_clk_register(NULL, &clk_hw->hw, node->name); if (!IS_ERR(clk)) { - ret = ti_clk_add_alias(NULL, clk, node->name); - if (ret) { - clk_unregister(clk); - goto cleanup; - } of_clk_add_provider(node, of_clk_src_simple_get, clk); kfree(parent_names); return; diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index 975995eea15c..b0c0690a5a12 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -100,11 +100,12 @@ static bool _omap4_is_timeout(union omap4_timeout *time, u32 timeout) * can be from a timer that requires pm_runtime access, which * will eventually bring us here with timekeeping_suspended, * during both suspend entry and resume paths. This happens - * at least on am43xx platform. + * at least on am43xx platform. Account for flakeyness + * with udelay() by multiplying the timeout value by 2. */ if (unlikely(_early_timeout || timekeeping_suspended)) { if (time->cycles++ < timeout) { - udelay(1); + udelay(1 * 2); return false; } } else { diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index 354b27d14a19..62812f80b5cc 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -328,12 +328,13 @@ static int sh_mtu2_register(struct sh_mtu2_channel *ch, const char *name) return 0; } +static const unsigned int sh_mtu2_channel_offsets[] = { + 0x300, 0x380, 0x000, +}; + static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index, struct sh_mtu2_device *mtu) { - static const unsigned int channel_offsets[] = { - 0x300, 0x380, 0x000, - }; char name[6]; int irq; int ret; @@ -356,7 +357,7 @@ static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index, return ret; } - ch->base = mtu->mapbase + channel_offsets[index]; + ch->base = mtu->mapbase + sh_mtu2_channel_offsets[index]; ch->index = index; return sh_mtu2_register(ch, dev_name(&mtu->pdev->dev)); @@ -408,7 +409,12 @@ static int sh_mtu2_setup(struct sh_mtu2_device *mtu, } /* Allocate and setup the channels. */ - mtu->num_channels = 3; + ret = platform_irq_count(pdev); + if (ret < 0) + goto err_unmap; + + mtu->num_channels = min_t(unsigned int, ret, + ARRAY_SIZE(sh_mtu2_channel_offsets)); mtu->channels = kcalloc(mtu->num_channels, sizeof(*mtu->channels), GFP_KERNEL); diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c index a562f491b0f8..9318edcd8963 100644 --- a/drivers/clocksource/timer-mediatek.c +++ b/drivers/clocksource/timer-mediatek.c @@ -268,15 +268,12 @@ static int __init mtk_syst_init(struct device_node *node) ret = timer_of_init(node, &to); if (ret) - goto err; + return ret; clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), TIMER_SYNC_TICKS, 0xffffffff); return 0; -err: - timer_of_cleanup(&to); - return ret; } static int __init mtk_gpt_init(struct device_node *node) @@ -293,7 +290,7 @@ static int __init mtk_gpt_init(struct device_node *node) ret = timer_of_init(node, &to); if (ret) - goto err; + return ret; /* Configure clock source */ mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN); @@ -311,9 +308,6 @@ static int __init mtk_gpt_init(struct device_node *node) mtk_gpt_enable_irq(&to, TIMER_CLK_EVT); return 0; -err: - timer_of_cleanup(&to); - return ret; } TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init); TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 53a51c169451..8ab31702cf6a 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -847,11 +847,9 @@ static void intel_pstate_hwp_force_min_perf(int cpu) value |= HWP_MAX_PERF(min_perf); value |= HWP_MIN_PERF(min_perf); - /* Set EPP/EPB to min */ + /* Set EPP to min */ if (boot_cpu_has(X86_FEATURE_HWP_EPP)) value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE); - else - intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE); wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c index 890813e0bb76..e9caa9586982 100644 --- a/drivers/cpufreq/loongson2_cpufreq.c +++ b/drivers/cpufreq/loongson2_cpufreq.c @@ -23,7 +23,7 @@ #include <asm/clock.h> #include <asm/idle.h> -#include <asm/mach-loongson64/loongson.h> +#include <asm/mach-loongson2ef/loongson.h> static uint nowait; diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index 9cd70d1a5622..a479023fa036 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -967,29 +967,29 @@ static int sdei_get_conduit(struct platform_device *pdev) if (np) { if (of_property_read_string(np, "method", &method)) { pr_warn("missing \"method\" property\n"); - return CONDUIT_INVALID; + return SMCCC_CONDUIT_NONE; } if (!strcmp("hvc", method)) { sdei_firmware_call = &sdei_smccc_hvc; - return CONDUIT_HVC; + return SMCCC_CONDUIT_HVC; } else if (!strcmp("smc", method)) { sdei_firmware_call = &sdei_smccc_smc; - return CONDUIT_SMC; + return SMCCC_CONDUIT_SMC; } pr_warn("invalid \"method\" property: %s\n", method); } else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) { if (acpi_psci_use_hvc()) { sdei_firmware_call = &sdei_smccc_hvc; - return CONDUIT_HVC; + return SMCCC_CONDUIT_HVC; } else { sdei_firmware_call = &sdei_smccc_smc; - return CONDUIT_SMC; + return SMCCC_CONDUIT_SMC; } } - return CONDUIT_INVALID; + return SMCCC_CONDUIT_NONE; } static int sdei_probe(struct platform_device *pdev) diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index 84f4ff351c62..b3b6c15e7b36 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -53,10 +53,18 @@ bool psci_tos_resident_on(int cpu) } struct psci_operations psci_ops = { - .conduit = PSCI_CONDUIT_NONE, + .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; @@ -212,13 +220,13 @@ static unsigned long psci_migrate_info_up_cpu(void) 0, 0, 0); } -static void set_conduit(enum psci_conduit conduit) +static void set_conduit(enum arm_smccc_conduit conduit) { switch (conduit) { - case PSCI_CONDUIT_HVC: + case SMCCC_CONDUIT_HVC: invoke_psci_fn = __invoke_psci_fn_hvc; break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: invoke_psci_fn = __invoke_psci_fn_smc; break; default: @@ -240,9 +248,9 @@ static int get_set_conduit_method(struct device_node *np) } if (!strcmp("hvc", method)) { - set_conduit(PSCI_CONDUIT_HVC); + set_conduit(SMCCC_CONDUIT_HVC); } else if (!strcmp("smc", method)) { - set_conduit(PSCI_CONDUIT_SMC); + set_conduit(SMCCC_CONDUIT_SMC); } else { pr_warn("invalid \"method\" property: %s\n", method); return -EINVAL; @@ -583,9 +591,9 @@ int __init psci_acpi_init(void) pr_info("probing for conduit method from ACPI.\n"); if (acpi_psci_use_hvc()) - set_conduit(PSCI_CONDUIT_HVC); + set_conduit(SMCCC_CONDUIT_HVC); else - set_conduit(PSCI_CONDUIT_SMC); + set_conduit(SMCCC_CONDUIT_SMC); return psci_probe(); } diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 38e096e6925f..92d0ff63b3ea 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -298,7 +298,7 @@ config GPIO_IXP4XX config GPIO_LOONGSON bool "Loongson-2/3 GPIO support" - depends on CPU_LOONGSON2 || CPU_LOONGSON3 + depends on CPU_LOONGSON2EF || CPU_LOONGSON64 help driver for GPIO functionality on Loongson-2F/3A/3B processors. diff --git a/drivers/gpio/gpio-bd70528.c b/drivers/gpio/gpio-bd70528.c index 0c1ead12d883..4ba4d4a67881 100644 --- a/drivers/gpio/gpio-bd70528.c +++ b/drivers/gpio/gpio-bd70528.c @@ -25,13 +25,13 @@ static int bd70528_set_debounce(struct bd70528_gpio *bdgpio, case 0: val = BD70528_DEBOUNCE_DISABLE; break; - case 1 ... 15: + case 1 ... 15000: val = BD70528_DEBOUNCE_15MS; break; - case 16 ... 30: + case 15001 ... 30000: val = BD70528_DEBOUNCE_30MS; break; - case 31 ... 50: + case 30001 ... 50000: val = BD70528_DEBOUNCE_50MS; break; default: diff --git a/drivers/gpio/gpio-loongson.c b/drivers/gpio/gpio-loongson.c index 00943170ce36..a42145873cc9 100644 --- a/drivers/gpio/gpio-loongson.c +++ b/drivers/gpio/gpio-loongson.c @@ -22,7 +22,7 @@ #define STLS2F_N_GPIO 4 #define STLS3A_N_GPIO 16 -#ifdef CONFIG_CPU_LOONGSON3 +#ifdef CONFIG_CPU_LOONGSON64 #define LOONGSON_N_GPIO STLS3A_N_GPIO #else #define LOONGSON_N_GPIO STLS2F_N_GPIO diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c index faf86ea9c51a..642c6321c22a 100644 --- a/drivers/gpio/gpio-max77620.c +++ b/drivers/gpio/gpio-max77620.c @@ -192,13 +192,13 @@ static int max77620_gpio_set_debounce(struct max77620_gpio *mgpio, case 0: val = MAX77620_CNFG_GPIO_DBNC_None; break; - case 1000 ... 8000: + case 1 ... 8000: val = MAX77620_CNFG_GPIO_DBNC_8ms; break; - case 9000 ... 16000: + case 8001 ... 16000: val = MAX77620_CNFG_GPIO_DBNC_16ms; break; - case 17000 ... 32000: + case 16001 ... 32000: val = MAX77620_CNFG_GPIO_DBNC_32ms; break; default: diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 609ed16ae933..59ccfd24627d 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1304,11 +1304,28 @@ late_initcall_sync(acpi_gpio_handle_deferred_request_irqs); static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = { { + /* + * The Minix Neo Z83-4 has a micro-USB-B id-pin handler for + * a non existing micro-USB-B connector which puts the HDMI + * DDC pins in GPIO mode, breaking HDMI support. + */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MINIX"), DMI_MATCH(DMI_PRODUCT_NAME, "Z83-4"), } }, + { + /* + * The Terra Pad 1061 has a micro-USB-B id-pin handler, which + * instead of controlling the actual micro-USB-B turns the 5V + * boost for its USB-A connector off. The actual micro-USB-B + * connector is wired for charging only. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Wortmann_AG"), + DMI_MATCH(DMI_PRODUCT_NAME, "TERRA_PAD_1061"), + } + }, {} /* Terminating entry */ }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 6614d8a6f4c8..2cdaf3b2a721 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -604,8 +604,11 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr) continue; } - for (i = 0; i < num_entities; i++) + for (i = 0; i < num_entities; i++) { + mutex_lock(&ctx->adev->lock_reset); drm_sched_entity_fini(&ctx->entities[0][i].entity); + mutex_unlock(&ctx->adev->lock_reset); + } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5a1939dbd4e3..7a6c837c0a85 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2885,6 +2885,13 @@ fence_driver_init: DRM_INFO("amdgpu: acceleration disabled, skipping benchmarks\n"); } + /* + * Register gpu instance before amdgpu_device_enable_mgpu_fan_boost. + * Otherwise the mgpu fan boost feature will be skipped due to the + * gpu instance is counted less. + */ + amdgpu_register_gpu_instance(adev); + /* enable clockgating, etc. after ib tests, etc. since some blocks require * explicit gating rather than handling it automatically. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 1d4aaa9580f4..82efc1e22e61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -511,7 +511,7 @@ uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, * Also, don't allow GTT domain if the BO doens't have USWC falg set. */ if (adev->asic_type >= CHIP_CARRIZO && - adev->asic_type <= CHIP_RAVEN && + adev->asic_type < CHIP_RAVEN && (adev->flags & AMD_IS_APU) && (bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) && amdgpu_bo_support_uswc(bo_flags) && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 2a00a36106b2..b19157b19fa0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1013,9 +1013,10 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, /* Navi14 */ - {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, + {0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, + {0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, + {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, /* Renoir */ {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 6ee4021910e2..6d19183b478b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -289,6 +289,7 @@ struct amdgpu_gfx { uint32_t mec2_feature_version; bool mec_fw_write_wait; bool me_fw_write_wait; + bool cp_fw_write_wait; struct amdgpu_ring gfx_ring[AMDGPU_MAX_GFX_RINGS]; unsigned num_gfx_rings; struct amdgpu_ring compute_ring[AMDGPU_MAX_COMPUTE_RINGS]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d55f5baa83d3..a73206784cba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -190,7 +190,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) pm_runtime_put_autosuspend(dev->dev); } - amdgpu_register_gpu_instance(adev); out: if (r) { /* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */ @@ -650,15 +649,19 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return -ENOMEM; alloc_size = info->read_mmr_reg.count * sizeof(*regs); - for (i = 0; i < info->read_mmr_reg.count; i++) + amdgpu_gfx_off_ctrl(adev, false); + for (i = 0; i < info->read_mmr_reg.count; i++) { if (amdgpu_asic_read_register(adev, se_num, sh_num, info->read_mmr_reg.dword_offset + i, ®s[i])) { DRM_DEBUG_KMS("unallowed offset %#x\n", info->read_mmr_reg.dword_offset + i); kfree(regs); + amdgpu_gfx_off_ctrl(adev, true); return -EFAULT; } + } + amdgpu_gfx_off_ctrl(adev, true); n = copy_to_user(out, regs, min(size, alloc_size)); kfree(regs); return n ? -EFAULT : 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 4d71537a960d..a46090071034 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -950,21 +950,7 @@ static void psp_print_fw_hdr(struct psp_context *psp, struct amdgpu_firmware_info *ucode) { struct amdgpu_device *adev = psp->adev; - const struct sdma_firmware_header_v1_0 *sdma_hdr = - (const struct sdma_firmware_header_v1_0 *) - adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data; - const struct gfx_firmware_header_v1_0 *ce_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; - const struct gfx_firmware_header_v1_0 *pfp_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; - const struct gfx_firmware_header_v1_0 *me_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; - const struct gfx_firmware_header_v1_0 *mec_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; - const struct rlc_firmware_header_v2_0 *rlc_hdr = - (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; - const struct smc_firmware_header_v1_0 *smc_hdr = - (const struct smc_firmware_header_v1_0 *)adev->pm.fw->data; + struct common_firmware_header *hdr; switch (ucode->ucode_id) { case AMDGPU_UCODE_ID_SDMA0: @@ -975,25 +961,33 @@ static void psp_print_fw_hdr(struct psp_context *psp, case AMDGPU_UCODE_ID_SDMA5: case AMDGPU_UCODE_ID_SDMA6: case AMDGPU_UCODE_ID_SDMA7: - amdgpu_ucode_print_sdma_hdr(&sdma_hdr->header); + hdr = (struct common_firmware_header *) + adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data; + amdgpu_ucode_print_sdma_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_CE: - amdgpu_ucode_print_gfx_hdr(&ce_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.ce_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_PFP: - amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.pfp_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_ME: - amdgpu_ucode_print_gfx_hdr(&me_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.me_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_MEC1: - amdgpu_ucode_print_gfx_hdr(&mec_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.mec_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_RLC_G: - amdgpu_ucode_print_rlc_hdr(&rlc_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.rlc_fw->data; + amdgpu_ucode_print_rlc_hdr(hdr); break; case AMDGPU_UCODE_ID_SMC: - amdgpu_ucode_print_smc_hdr(&smc_hdr->header); + hdr = (struct common_firmware_header *)adev->pm.fw->data; + amdgpu_ucode_print_smc_hdr(hdr); break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 8dfc775626a7..53090eae0082 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -564,6 +564,32 @@ static void gfx_v10_0_free_microcode(struct amdgpu_device *adev) kfree(adev->gfx.rlc.register_list_format); } +static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev) +{ + adev->gfx.cp_fw_write_wait = false; + + switch (adev->asic_type) { + case CHIP_NAVI10: + case CHIP_NAVI12: + case CHIP_NAVI14: + if ((adev->gfx.me_fw_version >= 0x00000046) && + (adev->gfx.me_feature_version >= 27) && + (adev->gfx.pfp_fw_version >= 0x00000068) && + (adev->gfx.pfp_feature_version >= 27) && + (adev->gfx.mec_fw_version >= 0x0000005b) && + (adev->gfx.mec_feature_version >= 27)) + adev->gfx.cp_fw_write_wait = true; + break; + default: + break; + } + + if (adev->gfx.cp_fw_write_wait == false) + DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \ + GRBM requires 1-cycle delay in cp firmware\n"); +} + + static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev) { const struct rlc_firmware_header_v2_1 *rlc_hdr; @@ -832,6 +858,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) } } + gfx_v10_0_check_fw_write_wait(adev); out: if (err) { dev_err(adev->dev, @@ -4765,6 +4792,24 @@ static void gfx_v10_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, gfx_v10_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20); } +static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, + uint32_t reg0, uint32_t reg1, + uint32_t ref, uint32_t mask) +{ + int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX); + struct amdgpu_device *adev = ring->adev; + bool fw_version_ok = false; + + fw_version_ok = adev->gfx.cp_fw_write_wait; + + if (fw_version_ok) + gfx_v10_0_wait_reg_mem(ring, usepfp, 0, 1, reg0, reg1, + ref, mask, 0x20); + else + amdgpu_ring_emit_reg_write_reg_wait_helper(ring, reg0, reg1, + ref, mask); +} + static void gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, uint32_t me, uint32_t pipe, @@ -5155,6 +5200,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { .emit_tmz = gfx_v10_0_ring_emit_tmz, .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, }; static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = { @@ -5188,6 +5234,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = { .pad_ib = amdgpu_ring_generic_pad_ib, .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, }; static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { @@ -5218,6 +5265,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { .emit_rreg = gfx_v10_0_ring_emit_rreg, .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, }; static void gfx_v10_0_set_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index dcadc73bffd2..97cf0b536873 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -973,6 +973,13 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev) adev->gfx.me_fw_write_wait = false; adev->gfx.mec_fw_write_wait = false; + if ((adev->gfx.mec_fw_version < 0x000001a5) || + (adev->gfx.mec_feature_version < 46) || + (adev->gfx.pfp_fw_version < 0x000000b7) || + (adev->gfx.pfp_feature_version < 46)) + DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \ + GRBM requires 1-cycle delay in cp firmware\n"); + switch (adev->asic_type) { case CHIP_VEGA10: if ((adev->gfx.me_fw_version >= 0x0000009c) && @@ -1031,8 +1038,13 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) case CHIP_VEGA20: break; case CHIP_RAVEN: - if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) - &&((adev->gfx.rlc_fw_version != 106 && + /* Disable GFXOFF on original raven. There are combinations + * of sbios and platforms that are not stable. + */ + if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)) + adev->pm.pp_feature &= ~PP_GFXOFF_MASK; + else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) + &&((adev->gfx.rlc_fw_version != 106 && adev->gfx.rlc_fw_version < 531) || (adev->gfx.rlc_fw_version == 53815) || (adev->gfx.rlc_feature_version < 1) || @@ -1044,6 +1056,12 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) AMD_PG_SUPPORT_CP | AMD_PG_SUPPORT_RLC_SMU_HS; break; + case CHIP_RENOIR: + if (adev->pm.pp_feature & PP_GFXOFF_MASK) + adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG | + AMD_PG_SUPPORT_CP | + AMD_PG_SUPPORT_RLC_SMU_HS; + break; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 354e6200ca9a..5c7d5f73f54f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -344,11 +344,9 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid), upper_32_bits(pd_addr)); - amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req); - - /* wait for the invalidate to complete */ - amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_ack + eng, - 1 << vmid, 1 << vmid); + amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng, + hub->vm_inv_eng0_ack + eng, + req, 1 << vmid); return pd_addr; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 0cf7ef44b4b5..9ed178fa241c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -219,6 +219,15 @@ static void mmhub_v9_4_init_cache_regs(struct amdgpu_device *adev, int hubid) hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp); tmp = mmVML2PF0_VM_L2_CNTL3_DEFAULT; + if (adev->gmc.translate_further) { + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 12); + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 9); + } else { + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 9); + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 6); + } WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2PF0_VM_L2_CNTL3, hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index f6e81680dd7e..8493bfbbc148 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1173,6 +1173,16 @@ static void sdma_v5_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); } +static void sdma_v5_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, + uint32_t reg0, uint32_t reg1, + uint32_t ref, uint32_t mask) +{ + amdgpu_ring_emit_wreg(ring, reg0, ref); + /* wait for a cycle to reset vm_inv_eng*_ack */ + amdgpu_ring_emit_reg_wait(ring, reg0, 0, 0); + amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask); +} + static int sdma_v5_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1588,7 +1598,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = { 6 + /* sdma_v5_0_ring_emit_pipeline_sync */ /* sdma_v5_0_ring_emit_vm_flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + - SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 + + 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 = sdma_v5_0_ring_emit_ib, @@ -1602,6 +1612,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = { .pad_ib = sdma_v5_0_ring_pad_ib, .emit_wreg = sdma_v5_0_ring_emit_wreg, .emit_reg_wait = sdma_v5_0_ring_emit_reg_wait, + .emit_reg_write_reg_wait = sdma_v5_0_ring_emit_reg_write_reg_wait, .init_cond_exec = sdma_v5_0_ring_init_cond_exec, .patch_cond_exec = sdma_v5_0_ring_patch_cond_exec, .preempt_ib = sdma_v5_0_ring_preempt_ib, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index f8ab80c8801b..4ccfcdf8f16a 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1186,11 +1186,6 @@ static int soc15_common_early_init(void *handle) AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG; adev->external_rev_id = adev->rev_id + 0x91; - - if (adev->pm.pp_feature & PP_GFXOFF_MASK) - adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG | - AMD_PG_SUPPORT_CP | - AMD_PG_SUPPORT_RLC_SMU_HS; break; default: /* FIXME: not supported yet */ 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 a52f0b13a2c8..4139f129eafb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -688,7 +688,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) */ if (adev->flags & AMD_IS_APU && adev->asic_type >= CHIP_CARRIZO && - adev->asic_type <= CHIP_RAVEN) + adev->asic_type < CHIP_RAVEN) init_data.flags.gpu_vm_support = true; if (amdgpu_dc_feature_mask & DC_FBC_MASK) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 9c58670d5414..ca20b150afcc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2767,15 +2767,6 @@ void core_link_enable_stream( CONTROLLER_DP_TEST_PATTERN_VIDEOMODE, COLOR_DEPTH_UNDEFINED); - /* This second call is needed to reconfigure the DIG - * as a workaround for the incorrect value being applied - * from transmitter control. - */ - if (!dc_is_virtual_signal(pipe_ctx->stream->signal)) - stream->link->link_enc->funcs->setup( - stream->link->link_enc, - pipe_ctx->stream->signal); - #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT if (pipe_ctx->stream->timing.flags.DSC) { if (dc_is_dp_signal(pipe_ctx->stream->signal) || 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 dfb208285a9c..6b2f2f1a1c9c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1107,6 +1107,11 @@ struct stream_encoder *dcn20_stream_encoder_create( if (!enc1) return NULL; + if (ASICREV_IS_NAVI14_M(ctx->asic_id.hw_internal_rev)) { + if (eng_id >= ENGINE_ID_DIGD) + eng_id++; + } + dcn20_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id, &stream_enc_regs[eng_id], &se_shift, &se_mask); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 34f95e0e3ea4..203ce4b1028f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3478,18 +3478,31 @@ static int smu7_get_pp_table_entry(struct pp_hwmgr *hwmgr, static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query) { + struct amdgpu_device *adev = hwmgr->adev; int i; u32 tmp = 0; if (!query) return -EINVAL; - smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0); - tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0); - *query = tmp; + /* + * PPSMC_MSG_GetCurrPkgPwr is not supported on: + * - Hawaii + * - Bonaire + * - Fiji + * - Tonga + */ + if ((adev->asic_type != CHIP_HAWAII) && + (adev->asic_type != CHIP_BONAIRE) && + (adev->asic_type != CHIP_FIJI) && + (adev->asic_type != CHIP_TONGA)) { + smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0); + tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0); + *query = tmp; - if (tmp != 0) - return 0; + if (tmp != 0) + return 0; + } smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogStart); cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 0b461404af6b..328e258a6895 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -205,7 +205,7 @@ static struct smu_11_0_cmn2aisc_mapping navi10_workload_map[PP_SMC_POWER_PROFILE WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT), + WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; @@ -759,6 +759,12 @@ static int navi10_force_clk_levels(struct smu_context *smu, case SMU_UCLK: case SMU_DCEFCLK: case SMU_FCLK: + /* There is only 2 levels for fine grained DPM */ + if (navi10_is_support_fine_grained_dpm(smu, clk_type)) { + soft_max_level = (soft_max_level >= 1 ? 1 : 0); + soft_min_level = (soft_min_level >= 1 ? 1 : 0); + } + ret = smu_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq); if (ret) return size; diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index bbd8ebd58434..92c393f613d3 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -219,7 +219,7 @@ static struct smu_11_0_cmn2aisc_mapping vega20_workload_map[PP_SMC_POWER_PROFILE WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT), + WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 3ef2ac52ce94..2dd2cd87cdbb 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1581,8 +1581,11 @@ static void commit_tail(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; const struct drm_mode_config_helper_funcs *funcs; + struct drm_crtc_state *new_crtc_state; + struct drm_crtc *crtc; ktime_t start; s64 commit_time_ms; + unsigned int i, new_self_refresh_mask = 0; funcs = dev->mode_config.helper_private; @@ -1602,6 +1605,15 @@ static void commit_tail(struct drm_atomic_state *old_state) drm_atomic_helper_wait_for_dependencies(old_state); + /* + * We cannot safely access new_crtc_state after + * drm_atomic_helper_commit_hw_done() so figure out which crtc's have + * self-refresh active beforehand: + */ + for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i) + if (new_crtc_state->self_refresh_active) + new_self_refresh_mask |= BIT(i); + if (funcs && funcs->atomic_commit_tail) funcs->atomic_commit_tail(old_state); else @@ -1610,7 +1622,8 @@ static void commit_tail(struct drm_atomic_state *old_state) commit_time_ms = ktime_ms_delta(ktime_get(), start); if (commit_time_ms > 0) drm_self_refresh_helper_update_avg_times(old_state, - (unsigned long)commit_time_ms); + (unsigned long)commit_time_ms, + new_self_refresh_mask); drm_atomic_helper_commit_cleanup_done(old_state); diff --git a/drivers/gpu/drm/drm_self_refresh_helper.c b/drivers/gpu/drm/drm_self_refresh_helper.c index 68f4765a5896..dd33fec5aabd 100644 --- a/drivers/gpu/drm/drm_self_refresh_helper.c +++ b/drivers/gpu/drm/drm_self_refresh_helper.c @@ -133,29 +133,33 @@ out_drop_locks: * drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages * @state: the state which has just been applied to hardware * @commit_time_ms: the amount of time in ms that this commit took to complete + * @new_self_refresh_mask: bitmask of crtc's that have self_refresh_active in + * new state * * Called after &drm_mode_config_funcs.atomic_commit_tail, this function will * update the average entry/exit self refresh times on self refresh transitions. * These averages will be used when calculating how long to delay before * entering self refresh mode after activity. */ -void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, - unsigned int commit_time_ms) +void +drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, + unsigned int commit_time_ms, + unsigned int new_self_refresh_mask) { struct drm_crtc *crtc; - struct drm_crtc_state *old_crtc_state, *new_crtc_state; + struct drm_crtc_state *old_crtc_state; int i; - for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { + for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) { + bool new_self_refresh_active = new_self_refresh_mask & BIT(i); struct drm_self_refresh_data *sr_data = crtc->self_refresh_data; struct ewma_psr_time *time; if (old_crtc_state->self_refresh_active == - new_crtc_state->self_refresh_active) + new_self_refresh_active) continue; - if (new_crtc_state->self_refresh_active) + if (new_self_refresh_active) time = &sr_data->entry_avg_ms; else time = &sr_data->exit_avg_ms; diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index d3fb75bb9eb1..7cb2257bbb93 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -201,6 +201,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc) crtc_state->update_wm_post = false; crtc_state->fb_changed = false; crtc_state->fifo_changed = false; + crtc_state->preload_luts = false; crtc_state->wm.need_postvbl_update = false; crtc_state->fb_bits = 0; crtc_state->update_planes = 0; diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 71a0201437a9..aa1e2c670bc4 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -990,6 +990,55 @@ void intel_color_commit(const struct intel_crtc_state *crtc_state) dev_priv->display.color_commit(crtc_state); } +static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct intel_atomic_state *state = + to_intel_atomic_state(new_crtc_state->base.state); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + + return !old_crtc_state->base.gamma_lut && + !old_crtc_state->base.degamma_lut; +} + +static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct intel_atomic_state *state = + to_intel_atomic_state(new_crtc_state->base.state); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + + /* + * CGM_PIPE_MODE is itself single buffered. We'd have to + * somehow split it out from chv_load_luts() if we wanted + * the ability to preload the CGM LUTs/CSC without tearing. + */ + if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode) + return false; + + return !old_crtc_state->base.gamma_lut; +} + +static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct intel_atomic_state *state = + to_intel_atomic_state(new_crtc_state->base.state); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + + /* + * The hardware degamma is active whenever the pipe + * CSC is active. Thus even if the old state has no + * software degamma we need to avoid clobbering the + * linear hardware degamma mid scanout. + */ + return !old_crtc_state->csc_enable && + !old_crtc_state->base.gamma_lut; +} + int intel_color_check(struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); @@ -1133,6 +1182,8 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } @@ -1185,6 +1236,8 @@ static int chv_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = chv_can_preload_luts(crtc_state); + return 0; } @@ -1224,6 +1277,8 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } @@ -1281,6 +1336,8 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } @@ -1319,6 +1376,8 @@ static int glk_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = glk_can_preload_luts(crtc_state); + return 0; } @@ -1368,6 +1427,8 @@ static int icl_color_check(struct intel_crtc_state *crtc_state) crtc_state->csc_mode = icl_csc_mode(crtc_state); + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index e6e8d4a82044..0a08354a6183 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -864,6 +864,13 @@ load_detect: out: intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref); + + /* + * Make sure the refs for power wells enabled during detect are + * dropped to avoid a new detect cycle triggered by HPD polling. + */ + intel_display_power_flush_work(dev_priv); + return status; } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index dfff6f4357b8..af50f05f4e9d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -2504,6 +2504,9 @@ u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, * the highest stride limits of them all. */ crtc = intel_get_crtc_for_pipe(dev_priv, PIPE_A); + if (!crtc) + return 0; + plane = to_intel_plane(crtc->base.primary); return plane->max_stride(plane, pixel_format, modifier, @@ -13740,6 +13743,11 @@ static void intel_update_crtc(struct intel_crtc *crtc, /* vblanks work again, re-enable pipe CRC. */ intel_crtc_enable_pipe_crc(crtc); } else { + if (new_crtc_state->preload_luts && + (new_crtc_state->base.color_mgmt_changed || + new_crtc_state->update_pipe)) + intel_color_load_luts(new_crtc_state); + intel_pre_plane_update(old_crtc_state, new_crtc_state); if (new_crtc_state->update_pipe) @@ -14034,6 +14042,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { if (new_crtc_state->base.active && !needs_modeset(new_crtc_state) && + !new_crtc_state->preload_luts && (new_crtc_state->base.color_mgmt_changed || new_crtc_state->update_pipe)) intel_color_load_luts(new_crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 12099760d99e..c002f234ff31 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4896,6 +4896,9 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume) power_domains->initializing = true; + /* Must happen before power domain init on VLV/CHV */ + intel_update_rawclk(i915); + if (INTEL_GEN(i915) >= 11) { icl_display_core_init(i915, resume); } else if (IS_CANNONLAKE(i915)) { diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 449abaea619f..4075b0387c87 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -761,6 +761,7 @@ struct intel_crtc_state { bool update_wm_pre, update_wm_post; /* watermarks are updated */ bool fb_changed; /* fb on any of the planes is changed */ bool fifo_changed; /* FIFO split is changed */ + bool preload_luts; /* Pipe source size (ie. panel fitter input size) * All planes will be positioned inside this space, diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 57e9f0ba331b..9b15ac4f2fb6 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1256,6 +1256,9 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, u32 unused) { struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *i915 = + to_i915(intel_dig_port->base.base.dev); + enum phy phy = intel_port_to_phy(i915, intel_dig_port->base.port); u32 ret; ret = DP_AUX_CH_CTL_SEND_BUSY | @@ -1268,7 +1271,8 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) | DP_AUX_CH_CTL_SYNC_PULSE_SKL(32); - if (intel_dig_port->tc_mode == TC_PORT_TBT_ALT) + if (intel_phy_is_tc(i915, phy) && + intel_dig_port->tc_mode == TC_PORT_TBT_ALT) ret |= DP_AUX_CH_CTL_TBT_IO; return ret; @@ -5436,6 +5440,12 @@ out: if (status != connector_status_connected && !intel_dp->is_mst) intel_dp_unset_edid(intel_dp); + /* + * Make sure the refs for power wells enabled during detect are + * dropped to avoid a new detect cycle triggered by HPD polling. + */ + intel_display_power_flush_work(dev_priv); + return status; } diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index d59eee5c5d9c..b5c588e511dd 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -235,6 +235,11 @@ static int intelfb_create(struct drm_fb_helper *helper, info->apertures->ranges[0].base = ggtt->gmadr.start; info->apertures->ranges[0].size = ggtt->mappable_end; + /* Our framebuffer is the entirety of fbdev's system memory */ + info->fix.smem_start = + (unsigned long)(ggtt->gmadr.start + vma->node.start); + info->fix.smem_len = vma->node.size; + vaddr = i915_vma_pin_iomap(vma); if (IS_ERR(vaddr)) { DRM_ERROR("Failed to remap framebuffer into virtual memory\n"); @@ -244,10 +249,6 @@ static int intelfb_create(struct drm_fb_helper *helper, info->screen_base = vaddr; info->screen_size = vma->node.size; - /* Our framebuffer is the entirety of fbdev's system memory */ - info->fix.smem_start = (unsigned long)info->screen_base; - info->fix.smem_len = info->screen_size; - drm_fb_helper_fill_info(info, &ifbdev->helper, sizes); /* If the object is shmemfs backed, it will have given us zeroed pages. diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index e02f0faecf02..b030f7ae3302 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -2565,6 +2565,12 @@ out: if (status != connector_status_connected) cec_notifier_phys_addr_invalidate(intel_hdmi->cec_notifier); + /* + * Make sure the refs for power wells enabled during detect are + * dropped to avoid a new detect cycle triggered by HPD polling. + */ + intel_display_power_flush_work(dev_priv); + return status; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 1cdfe05514c3..e41fd94ae5a9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -319,6 +319,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx) free_engines(rcu_access_pointer(ctx->engines)); mutex_destroy(&ctx->engines_mutex); + kfree(ctx->jump_whitelist); + if (ctx->timeline) intel_timeline_put(ctx->timeline); @@ -441,6 +443,9 @@ __create_context(struct drm_i915_private *i915) for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++) ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES; + ctx->jump_whitelist = NULL; + ctx->jump_whitelist_cmds = 0; + return ctx; err_free: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index 260d59cc3de8..00537b9d7006 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -192,6 +192,13 @@ struct i915_gem_context { * per vm, which may be one per context or shared with the global GTT) */ struct radix_tree_root handles_vma; + + /** jump_whitelist: Bit array for tracking cmds during cmdparsing + * Guarded by struct_mutex + */ + unsigned long *jump_whitelist; + /** jump_whitelist_cmds: No of cmd slots available */ + u32 jump_whitelist_cmds; }; #endif /* __I915_GEM_CONTEXT_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index b5f6937369ea..e635e1e5f4d3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -296,7 +296,9 @@ static inline u64 gen8_noncanonical_addr(u64 address) static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) { - return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len; + return intel_engine_requires_cmd_parser(eb->engine) || + (intel_engine_using_cmd_parser(eb->engine) && + eb->args->batch_len); } static int eb_create(struct i915_execbuffer *eb) @@ -1955,40 +1957,94 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq) return 0; } -static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master) +static struct i915_vma * +shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = eb->i915; + struct i915_vma * const vma = *eb->vma; + struct i915_address_space *vm; + u64 flags; + + /* + * PPGTT backed shadow buffers must be mapped RO, to prevent + * post-scan tampering + */ + if (CMDPARSER_USES_GGTT(dev_priv)) { + flags = PIN_GLOBAL; + vm = &dev_priv->ggtt.vm; + } else if (vma->vm->has_read_only) { + flags = PIN_USER; + vm = vma->vm; + i915_gem_object_set_readonly(obj); + } else { + DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n"); + return ERR_PTR(-EINVAL); + } + + return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags); +} + +static struct i915_vma *eb_parse(struct i915_execbuffer *eb) { struct intel_engine_pool_node *pool; struct i915_vma *vma; + u64 batch_start; + u64 shadow_batch_start; int err; pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len); if (IS_ERR(pool)) return ERR_CAST(pool); - err = intel_engine_cmd_parser(eb->engine, + vma = shadow_batch_pin(eb, pool->obj); + if (IS_ERR(vma)) + goto err; + + batch_start = gen8_canonical_addr(eb->batch->node.start) + + eb->batch_start_offset; + + shadow_batch_start = gen8_canonical_addr(vma->node.start); + + err = intel_engine_cmd_parser(eb->gem_context, + eb->engine, eb->batch->obj, - pool->obj, + batch_start, eb->batch_start_offset, eb->batch_len, - is_master); + pool->obj, + shadow_batch_start); + if (err) { - if (err == -EACCES) /* unhandled chained batch */ + i915_vma_unpin(vma); + + /* + * Unsafe GGTT-backed buffers can still be submitted safely + * as non-secure. + * For PPGTT backing however, we have no choice but to forcibly + * reject unsafe buffers + */ + if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES)) + /* Execute original buffer non-secure */ vma = NULL; else vma = ERR_PTR(err); goto err; } - vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0); - if (IS_ERR(vma)) - goto err; - eb->vma[eb->buffer_count] = i915_vma_get(vma); eb->flags[eb->buffer_count] = __EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF; vma->exec_flags = &eb->flags[eb->buffer_count]; eb->buffer_count++; + eb->batch_start_offset = 0; + eb->batch = vma; + + if (CMDPARSER_USES_GGTT(eb->i915)) + eb->batch_flags |= I915_DISPATCH_SECURE; + + /* eb->batch_len unchanged */ + vma->private = pool; return vma; @@ -2421,6 +2477,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, struct drm_i915_gem_exec_object2 *exec, struct drm_syncobj **fences) { + struct drm_i915_private *i915 = to_i915(dev); struct i915_execbuffer eb; struct dma_fence *in_fence = NULL; struct dma_fence *exec_fence = NULL; @@ -2432,7 +2489,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS & ~__EXEC_OBJECT_UNKNOWN_FLAGS); - eb.i915 = to_i915(dev); + eb.i915 = i915; eb.file = file; eb.args = args; if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) @@ -2452,8 +2509,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { + if (INTEL_GEN(i915) >= 11) + return -ENODEV; + + /* Return -EPERM to trigger fallback code on old binaries. */ + if (!HAS_SECURE_BATCHES(i915)) + return -EPERM; + if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN)) - return -EPERM; + return -EPERM; eb.batch_flags |= I915_DISPATCH_SECURE; } @@ -2530,34 +2594,19 @@ i915_gem_do_execbuffer(struct drm_device *dev, goto err_vma; } + if (eb.batch_len == 0) + eb.batch_len = eb.batch->size - eb.batch_start_offset; + if (eb_use_cmdparser(&eb)) { struct i915_vma *vma; - vma = eb_parse(&eb, drm_is_current_master(file)); + vma = eb_parse(&eb); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err_vma; } - - if (vma) { - /* - * Batch parsed and accepted: - * - * Set the DISPATCH_SECURE bit to remove the NON_SECURE - * bit from MI_BATCH_BUFFER_START commands issued in - * the dispatch_execbuffer implementations. We - * specifically don't want that set on batches the - * command parser has accepted. - */ - eb.batch_flags |= I915_DISPATCH_SECURE; - eb.batch_start_offset = 0; - eb.batch = vma; - } } - if (eb.batch_len == 0) - eb.batch_len = eb.batch->size - eb.batch_start_offset; - /* * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure * batch" bit. Hence we need to pin secure batches into the global gtt. diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 6b3b50f0f6d9..abfbac49b8e8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -671,8 +671,28 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, obj->mm.dirty = false; for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) + if (obj->mm.dirty && trylock_page(page)) { + /* + * As this may not be anonymous memory (e.g. shmem) + * but exist on a real mapping, we have to lock + * the page in order to dirty it -- holding + * the page reference is not sufficient to + * prevent the inode from being truncated. + * Play safe and take the lock. + * + * However...! + * + * The mmu-notifier can be invalidated for a + * migrate_page, that is alreadying holding the lock + * on the page. Such a try_to_unmap() will result + * in us calling put_pages() and so recursively try + * to lock the page. We avoid that deadlock with + * a trylock_page() and in exchange we risk missing + * some page dirtying. + */ set_page_dirty(page); + unlock_page(page); + } mark_page_accessed(page); put_page(page); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_engine_pool.c index 4cd54c569911..379a91780bd4 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.c @@ -103,6 +103,8 @@ node_create(struct intel_engine_pool *pool, size_t sz) return ERR_CAST(obj); } + i915_gem_object_set_readonly(obj); + node->obj = obj; return node; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index a82cea95c2f2..9dd8c299cb2d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -475,12 +475,13 @@ struct intel_engine_cs { struct intel_engine_hangcheck hangcheck; -#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0) +#define I915_ENGINE_USING_CMD_PARSER BIT(0) #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_REQUIRES_CMD_PARSER BIT(7) unsigned int flags; /* @@ -541,9 +542,15 @@ struct intel_engine_cs { }; static inline bool -intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine) +intel_engine_using_cmd_parser(const struct intel_engine_cs *engine) { - return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER; + return engine->flags & I915_ENGINE_USING_CMD_PARSER; +} + +static inline bool +intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine) +{ + return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER; } static inline bool diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 1363e069ec83..fac75afed35b 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -38,6 +38,9 @@ static int __gt_unpark(struct intel_wakeref *wf) gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ); GEM_BUG_ON(!gt->awake); + if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL); + intel_enable_gt_powersave(i915); i915_update_gfx_val(i915); @@ -67,6 +70,11 @@ static int __gt_park(struct intel_wakeref *wf) if (INTEL_GEN(i915) >= 6) gen6_rps_idle(i915); + if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) { + i915_rc6_ctx_wa_check(i915); + intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL); + } + /* Everything switched off, flush any residual interrupt just in case */ intel_synchronize_irq(i915); diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 728704bbbe18..cea184a7dde9 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -199,14 +199,6 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = { MOCS_ENTRY(15, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \ L3_3_WB), \ - /* Bypass LLC - Uncached (EHL+) */ \ - MOCS_ENTRY(16, \ - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ - L3_1_UC), \ - /* Bypass LLC - L3 (Read-Only) (EHL+) */ \ - MOCS_ENTRY(17, \ - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ - L3_3_WB), \ /* Self-Snoop - L3 + LLC */ \ MOCS_ENTRY(18, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \ @@ -270,7 +262,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = { L3_1_UC), /* HW Special Case (Displayable) */ MOCS_ENTRY(61, - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), + LE_1_UC | LE_TC_1_LLC, L3_3_WB), }; diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 13044c027f27..4bfaefdf548d 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -498,8 +498,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id) goto out_free_gem; } - i915_gem_object_put(obj); - ret = dma_buf_fd(dmabuf, DRM_CLOEXEC | DRM_RDWR); if (ret < 0) { gvt_vgpu_err("create dma-buf fd failed ret:%d\n", ret); @@ -524,6 +522,8 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id) file_count(dmabuf->file), kref_read(&obj->base.refcount)); + i915_gem_object_put(obj); + return dmabuf_fd; out_free_dmabuf: diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 24555102e198..f24096e27bef 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -53,13 +53,11 @@ * granting userspace undue privileges. There are three categories of privilege. * * First, commands which are explicitly defined as privileged or which should - * only be used by the kernel driver. The parser generally rejects such - * commands, though it may allow some from the drm master process. + * only be used by the kernel driver. The parser rejects such commands * * Second, commands which access registers. To support correct/enhanced * userspace functionality, particularly certain OpenGL extensions, the parser - * provides a whitelist of registers which userspace may safely access (for both - * normal and drm master processes). + * provides a whitelist of registers which userspace may safely access * * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc). * The parser always rejects such commands. @@ -84,9 +82,9 @@ * in the per-engine command tables. * * Other command table entries map fairly directly to high level categories - * mentioned above: rejected, master-only, register whitelist. The parser - * implements a number of checks, including the privileged memory checks, via a - * general bitmasking mechanism. + * mentioned above: rejected, register whitelist. The parser implements a number + * of checks, including the privileged memory checks, via a general bitmasking + * mechanism. */ /* @@ -104,8 +102,6 @@ struct drm_i915_cmd_descriptor { * CMD_DESC_REJECT: The command is never allowed * CMD_DESC_REGISTER: The command should be checked against the * register whitelist for the appropriate ring - * CMD_DESC_MASTER: The command is allowed if the submitting process - * is the DRM master */ u32 flags; #define CMD_DESC_FIXED (1<<0) @@ -113,7 +109,6 @@ struct drm_i915_cmd_descriptor { #define CMD_DESC_REJECT (1<<2) #define CMD_DESC_REGISTER (1<<3) #define CMD_DESC_BITMASK (1<<4) -#define CMD_DESC_MASTER (1<<5) /* * The command's unique identification bits and the bitmask to get them. @@ -194,7 +189,7 @@ struct drm_i915_cmd_table { #define CMD(op, opm, f, lm, fl, ...) \ { \ .flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \ - .cmd = { (op), ~0u << (opm) }, \ + .cmd = { (op & ~0u << (opm)), ~0u << (opm) }, \ .length = { (lm) }, \ __VA_ARGS__ \ } @@ -209,14 +204,13 @@ struct drm_i915_cmd_table { #define R CMD_DESC_REJECT #define W CMD_DESC_REGISTER #define B CMD_DESC_BITMASK -#define M CMD_DESC_MASTER /* Command Mask Fixed Len Action ---------------------------------------------------------- */ -static const struct drm_i915_cmd_descriptor common_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = { CMD( MI_NOOP, SMI, F, 1, S ), CMD( MI_USER_INTERRUPT, SMI, F, 1, R ), - CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, R ), CMD( MI_ARB_CHECK, SMI, F, 1, S ), CMD( MI_REPORT_HEAD, SMI, F, 1, S ), CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), @@ -246,7 +240,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ), }; -static const struct drm_i915_cmd_descriptor render_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = { CMD( MI_FLUSH, SMI, F, 1, S ), CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_PREDICATE, SMI, F, 1, S ), @@ -313,7 +307,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( MI_URB_ATOMIC_ALLOC, SMI, F, 1, S ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_RS_CONTEXT, SMI, F, 1, S ), - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), @@ -330,7 +324,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS, S3D, !F, 0x1FF, S ), }; -static const struct drm_i915_cmd_descriptor video_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -374,7 +368,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = { CMD( MFX_WAIT, SMFX, F, 1, S ), }; -static const struct drm_i915_cmd_descriptor vecs_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -412,7 +406,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = { }}, ), }; -static const struct drm_i915_cmd_descriptor blt_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = { CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B, .bits = {{ @@ -446,10 +440,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = { }; static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = { - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), }; +/* + * For Gen9 we can still rely on the h/w to enforce cmd security, and only + * need to re-enforce the register access checks. We therefore only need to + * teach the cmdparser how to find the end of each command, and identify + * register accesses. The table doesn't need to reject any commands, and so + * the only commands listed here are: + * 1) Those that touch registers + * 2) Those that do not have the default 8-bit length + * + * Note that the default MI length mask chosen for this table is 0xFF, not + * the 0x3F used on older devices. This is because the vast majority of MI + * cmds on Gen9 use a standard 8-bit Length field. + * All the Gen9 blitter instructions are standard 0xFF length mask, and + * none allow access to non-general registers, so in fact no BLT cmds are + * included in the table at all. + * + */ +static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = { + CMD( MI_NOOP, SMI, F, 1, S ), + CMD( MI_USER_INTERRUPT, SMI, F, 1, S ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, S ), + CMD( MI_FLUSH, SMI, F, 1, S ), + CMD( MI_ARB_CHECK, SMI, F, 1, S ), + CMD( MI_REPORT_HEAD, SMI, F, 1, S ), + CMD( MI_ARB_ON_OFF, SMI, F, 1, S ), + CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, S ), + CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), + CMD( MI_UPDATE_GTT, SMI, !F, 0x3FF, S ), + CMD( MI_STORE_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_FLUSH_DW, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), + + /* + * We allow BB_START but apply further checks. We just sanitize the + * basic fields here. + */ +#define MI_BB_START_OPERAND_MASK GENMASK(SMI-1, 0) +#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1) + CMD( MI_BATCH_BUFFER_START_GEN8, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_BB_START_OPERAND_MASK, + .expected = MI_BB_START_OPERAND_EXPECT, + }}, ), +}; + static const struct drm_i915_cmd_descriptor noop_desc = CMD(MI_NOOP, SMI, F, 1, S); @@ -463,40 +511,44 @@ static const struct drm_i915_cmd_descriptor noop_desc = #undef R #undef W #undef B -#undef M -static const struct drm_i915_cmd_table gen7_render_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table gen7_render_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, }; -static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, { hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) }, }; -static const struct drm_i915_cmd_table gen7_video_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { video_cmds, ARRAY_SIZE(video_cmds) }, +static const struct drm_i915_cmd_table gen7_video_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) }, }; -static const struct drm_i915_cmd_table hsw_vebox_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { vecs_cmds, ARRAY_SIZE(vecs_cmds) }, +static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) }, }; -static const struct drm_i915_cmd_table gen7_blt_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, }; -static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, { hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) }, }; +static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = { + { gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) }, +}; + + /* * Register whitelists, sorted by increasing register offset. */ @@ -612,17 +664,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = { REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), }; -static const struct drm_i915_reg_descriptor ivb_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)), -}; - -static const struct drm_i915_reg_descriptor hsw_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), +static const struct drm_i915_reg_descriptor gen9_blt_regs[] = { + REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE), + REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE), + REG32(BCS_SWCTRL), + REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), + REG64_IDX(BCS_GPR, 0), + REG64_IDX(BCS_GPR, 1), + REG64_IDX(BCS_GPR, 2), + REG64_IDX(BCS_GPR, 3), + REG64_IDX(BCS_GPR, 4), + REG64_IDX(BCS_GPR, 5), + REG64_IDX(BCS_GPR, 6), + REG64_IDX(BCS_GPR, 7), + REG64_IDX(BCS_GPR, 8), + REG64_IDX(BCS_GPR, 9), + REG64_IDX(BCS_GPR, 10), + REG64_IDX(BCS_GPR, 11), + REG64_IDX(BCS_GPR, 12), + REG64_IDX(BCS_GPR, 13), + REG64_IDX(BCS_GPR, 14), + REG64_IDX(BCS_GPR, 15), }; #undef REG64 @@ -631,28 +693,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = { struct drm_i915_reg_table { const struct drm_i915_reg_descriptor *regs; int num_regs; - bool master; }; static const struct drm_i915_reg_table ivb_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, }; static const struct drm_i915_reg_table ivb_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, }; static const struct drm_i915_reg_table hsw_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, + { hsw_render_regs, ARRAY_SIZE(hsw_render_regs) }, }; static const struct drm_i915_reg_table hsw_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, +}; + +static const struct drm_i915_reg_table gen9_blt_reg_tables[] = { + { gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) }, }; static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) @@ -710,6 +771,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header) return 0; } +static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header) +{ + u32 client = cmd_header >> INSTR_CLIENT_SHIFT; + + if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT) + return 0xFF; + + DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header); + return 0; +} + static bool validate_cmds_sorted(const struct intel_engine_cs *engine, const struct drm_i915_cmd_table *cmd_tables, int cmd_table_count) @@ -867,18 +939,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) int cmd_table_count; int ret; - if (!IS_GEN(engine->i915, 7)) + if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) && + engine->class == COPY_ENGINE_CLASS)) return; switch (engine->class) { case RENDER_CLASS: if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_render_ring_cmds; + cmd_tables = hsw_render_ring_cmd_table; cmd_table_count = - ARRAY_SIZE(hsw_render_ring_cmds); + ARRAY_SIZE(hsw_render_ring_cmd_table); } else { - cmd_tables = gen7_render_cmds; - cmd_table_count = ARRAY_SIZE(gen7_render_cmds); + cmd_tables = gen7_render_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table); } if (IS_HASWELL(engine->i915)) { @@ -888,36 +961,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) engine->reg_tables = ivb_render_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables); } - engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask; break; case VIDEO_DECODE_CLASS: - cmd_tables = gen7_video_cmds; - cmd_table_count = ARRAY_SIZE(gen7_video_cmds); + cmd_tables = gen7_video_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table); engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; case COPY_ENGINE_CLASS: - if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_blt_ring_cmds; - cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); + engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; + if (IS_GEN(engine->i915, 9)) { + cmd_tables = gen9_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table); + engine->get_cmd_length_mask = + gen9_blt_get_cmd_length_mask; + + /* BCS Engine unsafe without parser */ + engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER; + } else if (IS_HASWELL(engine->i915)) { + cmd_tables = hsw_blt_ring_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table); } else { - cmd_tables = gen7_blt_cmds; - cmd_table_count = ARRAY_SIZE(gen7_blt_cmds); + cmd_tables = gen7_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table); } - if (IS_HASWELL(engine->i915)) { + if (IS_GEN(engine->i915, 9)) { + engine->reg_tables = gen9_blt_reg_tables; + engine->reg_table_count = + ARRAY_SIZE(gen9_blt_reg_tables); + } else if (IS_HASWELL(engine->i915)) { engine->reg_tables = hsw_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables); } else { engine->reg_tables = ivb_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables); } - - engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; break; case VIDEO_ENHANCEMENT_CLASS: - cmd_tables = hsw_vebox_cmds; - cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds); + cmd_tables = hsw_vebox_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table); /* VECS can use the same length_mask function as VCS */ engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; @@ -943,7 +1026,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) return; } - engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER; + engine->flags |= I915_ENGINE_USING_CMD_PARSER; } /** @@ -955,7 +1038,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) */ void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine) { - if (!intel_engine_needs_cmd_parser(engine)) + if (!intel_engine_using_cmd_parser(engine)) return; fini_hash_table(engine); @@ -1029,22 +1112,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr) } static const struct drm_i915_reg_descriptor * -find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) +find_reg(const struct intel_engine_cs *engine, u32 addr) { const struct drm_i915_reg_table *table = engine->reg_tables; + const struct drm_i915_reg_descriptor *reg = NULL; int count = engine->reg_table_count; - for (; count > 0; ++table, --count) { - if (!table->master || is_master) { - const struct drm_i915_reg_descriptor *reg; + for (; !reg && (count > 0); ++table, --count) + reg = __find_reg(table->regs, table->num_regs, addr); - reg = __find_reg(table->regs, table->num_regs, addr); - if (reg != NULL) - return reg; - } - } - - return NULL; + return reg; } /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */ @@ -1128,8 +1205,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, - const u32 *cmd, u32 length, - const bool is_master) + const u32 *cmd, u32 length) { if (desc->flags & CMD_DESC_SKIP) return true; @@ -1139,12 +1215,6 @@ static bool check_cmd(const struct intel_engine_cs *engine, return false; } - if ((desc->flags & CMD_DESC_MASTER) && !is_master) { - DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n", - *cmd); - return false; - } - if (desc->flags & CMD_DESC_REGISTER) { /* * Get the distance between individual register offset @@ -1158,7 +1228,7 @@ static bool check_cmd(const struct intel_engine_cs *engine, offset += step) { const u32 reg_addr = cmd[offset] & desc->reg.mask; const struct drm_i915_reg_descriptor *reg = - find_reg(engine, is_master, reg_addr); + find_reg(engine, reg_addr); if (!reg) { DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n", @@ -1236,16 +1306,112 @@ static bool check_cmd(const struct intel_engine_cs *engine, return true; } +static int check_bbstart(const struct i915_gem_context *ctx, + u32 *cmd, u32 offset, u32 length, + u32 batch_len, + u64 batch_start, + u64 shadow_batch_start) +{ + u64 jump_offset, jump_target; + u32 target_cmd_offset, target_cmd_index; + + /* For igt compatibility on older platforms */ + if (CMDPARSER_USES_GGTT(ctx->i915)) { + DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n"); + return -EACCES; + } + + if (length != 3) { + DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n", + length); + return -EINVAL; + } + + jump_target = *(u64*)(cmd+1); + jump_offset = jump_target - batch_start; + + /* + * Any underflow of jump_target is guaranteed to be outside the range + * of a u32, so >= test catches both too large and too small + */ + if (jump_offset >= batch_len) { + DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n", + jump_target); + return -EINVAL; + } + + /* + * This cannot overflow a u32 because we already checked jump_offset + * is within the BB, and the batch_len is a u32 + */ + target_cmd_offset = lower_32_bits(jump_offset); + target_cmd_index = target_cmd_offset / sizeof(u32); + + *(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset; + + if (target_cmd_index == offset) + return 0; + + if (ctx->jump_whitelist_cmds <= target_cmd_index) { + DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n"); + return -EINVAL; + } else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) { + DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n", + jump_target); + return -EINVAL; + } + + return 0; +} + +static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len) +{ + const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32)); + const u32 exact_size = BITS_TO_LONGS(batch_cmds); + u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds)); + unsigned long *next_whitelist; + + if (CMDPARSER_USES_GGTT(ctx->i915)) + return; + + if (batch_cmds <= ctx->jump_whitelist_cmds) { + bitmap_zero(ctx->jump_whitelist, batch_cmds); + return; + } + +again: + next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL); + if (next_whitelist) { + kfree(ctx->jump_whitelist); + ctx->jump_whitelist = next_whitelist; + ctx->jump_whitelist_cmds = + next_size * BITS_PER_BYTE * sizeof(long); + return; + } + + if (next_size > exact_size) { + next_size = exact_size; + goto again; + } + + DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n"); + bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds); + + return; +} + #define LENGTH_BIAS 2 /** * i915_parse_cmds() - parse a submitted batch buffer for privilege violations + * @ctx: the context in which the batch is to execute * @engine: the engine on which the batch is to execute * @batch_obj: the batch buffer in question - * @shadow_batch_obj: copy of the batch buffer in question + * @batch_start: Canonical base address of batch * @batch_start_offset: byte offset in the batch at which execution starts * @batch_len: length of the commands in batch_obj - * @is_master: is the submitting process the drm master? + * @shadow_batch_obj: copy of the batch buffer in question + * @shadow_batch_start: Canonical base address of shadow_batch_obj * * Parses the specified batch buffer looking for privilege violations as * described in the overview. @@ -1253,14 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine, * Return: non-zero if the parser finds violations or otherwise fails; -EACCES * if the batch appears legal but should use hardware parsing */ -int intel_engine_cmd_parser(struct intel_engine_cs *engine, + +int intel_engine_cmd_parser(struct i915_gem_context *ctx, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 batch_start, u32 batch_start_offset, u32 batch_len, - bool is_master) + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start) { - u32 *cmd, *batch_end; + u32 *cmd, *batch_end, offset = 0; struct drm_i915_cmd_descriptor default_desc = noop_desc; const struct drm_i915_cmd_descriptor *desc = &default_desc; bool needs_clflush_after = false; @@ -1274,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, return PTR_ERR(cmd); } + init_whitelist(ctx, batch_len); + /* * We use the batch length as size because the shadow object is as * large or larger and copy_batch() will write MI_NOPs to the extra @@ -1283,31 +1454,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, do { u32 length; - if (*cmd == MI_BATCH_BUFFER_END) { - if (needs_clflush_after) { - void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping); - drm_clflush_virt_range(ptr, - (void *)(cmd + 1) - ptr); - } + if (*cmd == MI_BATCH_BUFFER_END) break; - } desc = find_cmd(engine, *cmd, desc, &default_desc); if (!desc) { DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n", *cmd); ret = -EINVAL; - break; - } - - /* - * If the batch buffer contains a chained batch, return an - * error that tells the caller to abort and dispatch the - * workload as a non-secure batch. - */ - if (desc->cmd.value == MI_BATCH_BUFFER_START) { - ret = -EACCES; - break; + goto err; } if (desc->flags & CMD_DESC_FIXED) @@ -1321,22 +1476,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, length, batch_end - cmd); ret = -EINVAL; - break; + goto err; } - if (!check_cmd(engine, desc, cmd, length, is_master)) { + if (!check_cmd(engine, desc, cmd, length)) { ret = -EACCES; + goto err; + } + + if (desc->cmd.value == MI_BATCH_BUFFER_START) { + ret = check_bbstart(ctx, cmd, offset, length, + batch_len, batch_start, + shadow_batch_start); + + if (ret) + goto err; break; } + if (ctx->jump_whitelist_cmds > offset) + set_bit(offset, ctx->jump_whitelist); + cmd += length; + offset += length; if (cmd >= batch_end) { DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); ret = -EINVAL; - break; + goto err; } } while (1); + if (needs_clflush_after) { + void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping); + + drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr); + } + +err: i915_gem_object_unpin_map(shadow_batch_obj); return ret; } @@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) /* If the command parser is not enabled, report 0 - unsupported */ for_each_uabi_engine(engine, dev_priv) { - if (intel_engine_needs_cmd_parser(engine)) { + if (intel_engine_using_cmd_parser(engine)) { active = true; break; } @@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) * the parser enabled. * 9. Don't whitelist or handle oacontrol specially, as ownership * for oacontrol state is moving to i915-perf. + * 10. Support for Gen9 BCS Parsing */ - return 9; + return 10; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index bb6f86c7067a..3d717e282908 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -364,9 +364,6 @@ static int i915_driver_modeset_probe(struct drm_device *dev) if (ret) goto cleanup_vga_client; - /* must happen before intel_power_domains_init_hw() on VLV/CHV */ - intel_update_rawclk(dev_priv); - intel_power_domains_init_hw(dev_priv, false); intel_csr_ucode_init(dev_priv); @@ -1850,6 +1847,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) i915_gem_suspend_late(dev_priv); + i915_rc6_ctx_wa_suspend(dev_priv); + intel_uncore_suspend(&dev_priv->uncore); intel_power_domains_suspend(dev_priv, @@ -2053,6 +2052,8 @@ static int i915_drm_resume_early(struct drm_device *dev) intel_power_domains_resume(dev_priv); + i915_rc6_ctx_wa_resume(dev_priv); + intel_gt_sanitize(&dev_priv->gt, true); enable_rpm_wakeref_asserts(&dev_priv->runtime_pm); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 953e1d12c23c..89b6112bd66b 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -593,6 +593,8 @@ struct intel_rps { struct intel_rc6 { bool enabled; + bool ctx_corrupted; + intel_wakeref_t ctx_corrupted_wakeref; u64 prev_hw_residency[4]; u64 cur_residency[4]; }; @@ -2075,9 +2077,16 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define VEBOX_MASK(dev_priv) \ ENGINE_INSTANCES_MASK(dev_priv, VECS0, I915_MAX_VECS) +/* + * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution + * All later gens can run the final buffer from the ppgtt + */ +#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7) + #define HAS_LLC(dev_priv) (INTEL_INFO(dev_priv)->has_llc) #define HAS_SNOOP(dev_priv) (INTEL_INFO(dev_priv)->has_snoop) #define HAS_EDRAM(dev_priv) ((dev_priv)->edram_size_mb) +#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6) #define HAS_WT(dev_priv) ((IS_HASWELL(dev_priv) || \ IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv)) @@ -2110,10 +2119,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, /* Early gen2 have a totally busted CS tlb and require pinned batches. */ #define HAS_BROKEN_CS_TLB(dev_priv) (IS_I830(dev_priv) || IS_I845G(dev_priv)) +#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv) \ + (IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9)) + /* WaRsDisableCoarsePowerGating:skl,cnl */ #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \ - (IS_CANNONLAKE(dev_priv) || \ - IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv)) + (IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9)) #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4) #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \ @@ -2284,6 +2295,14 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj, unsigned long flags); #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0) +struct i915_vma * __must_check +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags); + void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv); static inline int __must_check @@ -2393,12 +2412,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); -int intel_engine_cmd_parser(struct intel_engine_cs *engine, +int intel_engine_cmd_parser(struct i915_gem_context *cxt, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 user_batch_start, u32 batch_start_offset, u32 batch_len, - bool is_master); + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start); /* intel_device_info.c */ static inline struct intel_device_info * diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index d0f94f239919..98305d987ac1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -964,6 +964,20 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct i915_address_space *vm = &dev_priv->ggtt.vm; + + return i915_gem_object_pin(obj, vm, view, size, alignment, + flags | PIN_GLOBAL); +} + +struct i915_vma * +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags) +{ + struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct i915_vma *vma; int ret; @@ -1038,7 +1052,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, return ERR_PTR(ret); } - ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL); + ret = i915_vma_pin(vma, size, alignment, flags); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 5d9101376a3d..9f1517af5b7f 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -62,7 +62,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, value = !!(i915->caps.scheduler & I915_SCHEDULER_CAP_SEMAPHORES); break; case I915_PARAM_HAS_SECURE_BATCHES: - value = capable(CAP_SYS_ADMIN); + value = HAS_SECURE_BATCHES(i915) && capable(CAP_SYS_ADMIN); break; case I915_PARAM_CMD_PARSER_VERSION: value = i915_cmd_parser_get_version(i915); diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 8e251e719390..212acaef581e 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -843,8 +843,8 @@ create_event_attributes(struct i915_pmu *pmu) const char *name; const char *unit; } events[] = { - __event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "MHz"), - __event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "MHz"), + __event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "M"), + __event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "M"), __event(I915_PMU_INTERRUPTS, "interrupts", NULL), __event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"), }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2abd199093c5..f8ee9aba3955 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -471,6 +471,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ECOCHK_PPGTT_WT_HSW (0x2 << 3) #define ECOCHK_PPGTT_WB_HSW (0x3 << 3) +#define GEN8_RC6_CTX_INFO _MMIO(0x8504) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1 << 13) #define ECOBITS_PPGTT_CACHE64B (3 << 8) @@ -555,6 +557,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) */ #define BCS_SWCTRL _MMIO(0x22200) +/* There are 16 GPR registers */ +#define BCS_GPR(n) _MMIO(0x22600 + (n) * 8) +#define BCS_GPR_UDW(n) _MMIO(0x22600 + (n) * 8 + 4) + #define GPGPU_THREADS_DISPATCHED _MMIO(0x2290) #define GPGPU_THREADS_DISPATCHED_UDW _MMIO(0x2290 + 4) #define HS_INVOCATION_COUNT _MMIO(0x2300) @@ -7211,6 +7217,10 @@ enum { #define TGL_DMC_DEBUG_DC5_COUNT _MMIO(0x101084) #define TGL_DMC_DEBUG_DC6_COUNT _MMIO(0x101088) +/* Display Internal Timeout Register */ +#define RM_TIMEOUT _MMIO(0x42060) +#define MMIO_TIMEOUT_US(us) ((us) << 0) + /* interrupts */ #define DE_MASTER_IRQ_CONTROL (1 << 31) #define DE_SPRITEB_FLIP_DONE (1 << 29) diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 7b84ebca2901..3eba8a2b39c2 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -177,9 +177,37 @@ static inline int rq_prio(const struct i915_request *rq) return rq->sched.attr.priority | __NO_PREEMPTION; } -static void kick_submission(struct intel_engine_cs *engine, int prio) +static inline bool need_preempt(int prio, int active) { - const struct i915_request *inflight = *engine->execlists.active; + /* + * Allow preemption of low -> normal -> high, but we do + * not allow low priority tasks to preempt other low priority + * tasks under the impression that latency for low priority + * tasks does not matter (as much as background throughput), + * so kiss. + */ + return prio >= max(I915_PRIORITY_NORMAL, active); +} + +static void kick_submission(struct intel_engine_cs *engine, + const struct i915_request *rq, + int prio) +{ + const struct i915_request *inflight; + + /* + * We only need to kick the tasklet once for the high priority + * new context we add into the queue. + */ + if (prio <= engine->execlists.queue_priority_hint) + return; + + rcu_read_lock(); + + /* Nothing currently active? We're overdue for a submission! */ + inflight = execlists_active(&engine->execlists); + if (!inflight) + goto unlock; /* * If we are already the currently executing context, don't @@ -188,10 +216,15 @@ static void kick_submission(struct intel_engine_cs *engine, int prio) * tasklet, i.e. we have not change the priority queue * sufficiently to oust the running context. */ - if (!inflight || !i915_scheduler_need_preempt(prio, rq_prio(inflight))) - return; + if (inflight->hw_context == rq->hw_context) + goto unlock; - tasklet_hi_schedule(&engine->execlists.tasklet); + engine->execlists.queue_priority_hint = prio; + if (need_preempt(prio, rq_prio(inflight))) + tasklet_hi_schedule(&engine->execlists.tasklet); + +unlock: + rcu_read_unlock(); } static void __i915_schedule(struct i915_sched_node *node, @@ -317,13 +350,8 @@ static void __i915_schedule(struct i915_sched_node *node, list_move_tail(&node->link, cache.priolist); } - if (prio <= engine->execlists.queue_priority_hint) - continue; - - engine->execlists.queue_priority_hint = prio; - /* Defer (tasklet) submission until after all of our updates. */ - kick_submission(engine, prio); + kick_submission(engine, node_to_request(node), prio); } spin_unlock(&engine->active.lock); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 75ee027abb80..2efe1d12d5a9 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -126,6 +126,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv) */ I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) | PWM1_GATING_DIS | PWM2_GATING_DIS); + + /* + * Lower the display internal timeout. + * This is needed to avoid any hard hangs when DSI port PLL + * is off and a MMIO access is attempted by any privilege + * application, using batch buffers or any other means. + */ + I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950)); } static void glk_init_clock_gating(struct drm_i915_private *dev_priv) @@ -8544,6 +8552,100 @@ static void intel_init_emon(struct drm_i915_private *dev_priv) dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK); } +static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv) +{ + return !I915_READ(GEN8_RC6_CTX_INFO); +} + +static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + DRM_INFO("RC6 context corrupted, disabling runtime power management\n"); + i915->gt_pm.rc6.ctx_corrupted = true; + i915->gt_pm.rc6.ctx_corrupted_wakeref = + intel_runtime_pm_get(&i915->runtime_pm); + } +} + +static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915) +{ + if (i915->gt_pm.rc6.ctx_corrupted) { + intel_runtime_pm_put(&i915->runtime_pm, + i915->gt_pm.rc6.ctx_corrupted_wakeref); + i915->gt_pm.rc6.ctx_corrupted = false; + } +} + +/** + * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to clean up the RC6 CTX WA before system suspend. + */ +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915) +{ + if (i915->gt_pm.rc6.ctx_corrupted) + intel_runtime_pm_put(&i915->runtime_pm, + i915->gt_pm.rc6.ctx_corrupted_wakeref); +} + +/** + * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to re-init the RC6 CTX WA after system resume. + */ +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915) +{ + if (!i915->gt_pm.rc6.ctx_corrupted) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + i915->gt_pm.rc6.ctx_corrupted_wakeref = + intel_runtime_pm_get(&i915->runtime_pm); + return; + } + + DRM_INFO("RC6 context restored, re-enabling runtime power management\n"); + i915->gt_pm.rc6.ctx_corrupted = false; +} + +static void intel_disable_rc6(struct drm_i915_private *dev_priv); + +/** + * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption + * @i915: i915 device + * + * Check if an RC6 CTX corruption has happened since the last check and if so + * disable RC6 and runtime power management. + * + * Return false if no context corruption has happened since the last call of + * this function, true otherwise. +*/ +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return false; + + if (i915->gt_pm.rc6.ctx_corrupted) + return false; + + if (!i915_rc6_ctx_corrupted(i915)) + return false; + + DRM_NOTE("RC6 context corruption, disabling runtime power management\n"); + + intel_disable_rc6(i915); + i915->gt_pm.rc6.ctx_corrupted = true; + i915->gt_pm.rc6.ctx_corrupted_wakeref = + intel_runtime_pm_get_noresume(&i915->runtime_pm); + + return true; +} + void intel_init_gt_powersave(struct drm_i915_private *dev_priv) { struct intel_rps *rps = &dev_priv->gt_pm.rps; @@ -8557,6 +8659,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv) pm_runtime_get(&dev_priv->drm.pdev->dev); } + i915_rc6_ctx_wa_init(dev_priv); + /* Initialize RPS limits (for userspace) */ if (IS_CHERRYVIEW(dev_priv)) cherryview_init_gt_powersave(dev_priv); @@ -8595,6 +8699,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv) if (IS_VALLEYVIEW(dev_priv)) valleyview_cleanup_gt_powersave(dev_priv); + i915_rc6_ctx_wa_cleanup(dev_priv); + if (!HAS_RC6(dev_priv)) pm_runtime_put(&dev_priv->drm.pdev->dev); } @@ -8623,7 +8729,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915) i915->gt_pm.llc_pstate.enabled = false; } -static void intel_disable_rc6(struct drm_i915_private *dev_priv) +static void __intel_disable_rc6(struct drm_i915_private *dev_priv) { lockdep_assert_held(&dev_priv->gt_pm.rps.lock); @@ -8642,6 +8748,15 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv) dev_priv->gt_pm.rc6.enabled = false; } +static void intel_disable_rc6(struct drm_i915_private *dev_priv) +{ + struct intel_rps *rps = &dev_priv->gt_pm.rps; + + mutex_lock(&rps->lock); + __intel_disable_rc6(dev_priv); + mutex_unlock(&rps->lock); +} + static void intel_disable_rps(struct drm_i915_private *dev_priv) { lockdep_assert_held(&dev_priv->gt_pm.rps.lock); @@ -8667,7 +8782,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv) { mutex_lock(&dev_priv->gt_pm.rps.lock); - intel_disable_rc6(dev_priv); + __intel_disable_rc6(dev_priv); intel_disable_rps(dev_priv); if (HAS_LLC(dev_priv)) intel_disable_llc_pstate(dev_priv); @@ -8694,6 +8809,9 @@ static void intel_enable_rc6(struct drm_i915_private *dev_priv) if (dev_priv->gt_pm.rc6.enabled) return; + if (dev_priv->gt_pm.rc6.ctx_corrupted) + return; + if (IS_CHERRYVIEW(dev_priv)) cherryview_enable_rc6(dev_priv); else if (IS_VALLEYVIEW(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h index e3573e1e16e3..0f7390c850ec 100644 --- a/drivers/gpu/drm/i915/intel_pm.h +++ b/drivers/gpu/drm/i915/intel_pm.h @@ -36,6 +36,9 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv); void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv); void intel_enable_gt_powersave(struct drm_i915_private *dev_priv); void intel_disable_gt_powersave(struct drm_i915_private *dev_priv); +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915); void gen6_rps_busy(struct drm_i915_private *dev_priv); void gen6_rps_idle(struct drm_i915_private *dev_priv); void gen6_rps_boost(struct i915_request *rq); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 460fd98e40a7..a0b382a637a6 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -1958,6 +1958,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev) case 0x682C: si_pi->cac_weights = cac_weights_cape_verde_pro; si_pi->dte_data = dte_data_sun_xt; + update_dte_from_pl2 = true; break; case 0x6825: case 0x6827: diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 04c721d0d3b9..b89439ed210d 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -488,7 +488,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, WARN_ON(!tcon->quirks->has_channel_0); - tcon->dclk_min_div = 6; + tcon->dclk_min_div = 1; tcon->dclk_max_div = 127; sun4i_tcon0_mode_set_common(tcon, mode); diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index d9c55e30f986..04c088131e04 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -447,8 +447,12 @@ static int i2c_hid_hwreset(struct i2c_client *client) if (ret) { dev_err(&client->dev, "failed to reset device.\n"); i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); + goto out_unlock; } + /* At least some SIS devices need this after reset */ + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); + out_unlock: mutex_unlock(&ihid->reset_lock); return ret; diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h index 4a7f8d363220..203d27d198b8 100644 --- a/drivers/hid/wacom.h +++ b/drivers/hid/wacom.h @@ -202,6 +202,21 @@ static inline void wacom_schedule_work(struct wacom_wac *wacom_wac, } } +/* + * Convert a signed 32-bit integer to an unsigned n-bit integer. Undoes + * the normally-helpful work of 'hid_snto32' for fields that use signed + * ranges for questionable reasons. + */ +static inline __u32 wacom_s32tou(s32 value, __u8 n) +{ + switch (n) { + case 8: return ((__u8)value); + case 16: return ((__u16)value); + case 32: return ((__u32)value); + } + return value & (1 << (n - 1)) ? value & (~(~0U << n)) : value; +} + extern const struct hid_device_id wacom_ids[]; void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 2b0a5b8ca6e6..ccb74529bc78 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2303,7 +2303,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field case HID_DG_TOOLSERIALNUMBER: if (value) { wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); - wacom_wac->serial[0] |= (__u32)value; + wacom_wac->serial[0] |= wacom_s32tou(value, field->report_size); } return; case HID_DG_TWIST: @@ -2319,15 +2319,17 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field return; case WACOM_HID_WD_SERIALHI: if (value) { + __u32 raw_value = wacom_s32tou(value, field->report_size); + wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF); - wacom_wac->serial[0] |= ((__u64)value) << 32; + wacom_wac->serial[0] |= ((__u64)raw_value) << 32; /* * Non-USI EMR devices may contain additional tool type * information here. See WACOM_HID_WD_TOOLTYPE case for * more details. */ if (value >> 20 == 1) { - wacom_wac->id[0] |= value & 0xFFFFF; + wacom_wac->id[0] |= raw_value & 0xFFFFF; } } return; @@ -2339,7 +2341,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field * bitwise OR so the complete value can be built * up over time :( */ - wacom_wac->id[0] |= value; + wacom_wac->id[0] |= wacom_s32tou(value, field->report_size); return; case WACOM_HID_WD_OFFSETLEFT: if (features->offset_left && value != features->offset_left) diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c index fa9d34af87ac..f72803a02391 100644 --- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -626,6 +626,9 @@ static void intel_th_gth_switch(struct intel_th_device *thdev, if (!count) dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n"); + /* De-assert the trigger */ + iowrite32(0, gth->base + REG_CTS_CTL); + intel_th_gth_stop(gth, output, false); intel_th_gth_start(gth, output); } diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index fc9f15f36ad4..6d240dfae9d9 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -164,7 +164,7 @@ struct msc { }; static LIST_HEAD(msu_buffer_list); -static struct mutex msu_buffer_mutex; +static DEFINE_MUTEX(msu_buffer_mutex); /** * struct msu_buffer_entry - internal MSU buffer bookkeeping @@ -327,7 +327,7 @@ static size_t msc_win_total_sz(struct msc_window *win) struct msc_block_desc *bdesc = sg_virt(sg); if (msc_block_wrapped(bdesc)) - return win->nr_blocks << PAGE_SHIFT; + return (size_t)win->nr_blocks << PAGE_SHIFT; size += msc_total_sz(bdesc); if (msc_block_last_written(bdesc)) @@ -1848,9 +1848,14 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf, len = cp - buf; mode = kstrndup(buf, len, GFP_KERNEL); + if (!mode) + return -ENOMEM; + i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode); - if (i >= 0) + if (i >= 0) { + kfree(mode); goto found; + } /* Buffer sinks only work with a usable IRQ */ if (!msc->do_irq) { diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 91dfeba62485..03ca5b1bef9f 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -200,6 +200,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)&intel_th_2x, }, { + /* Comet Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x06a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { /* Ice Lake NNPI */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5), .driver_data = (kernel_ulong_t)&intel_th_2x, @@ -209,6 +214,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Jasper Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 9cb2aa1e20ef..62a1c92ab803 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -39,6 +39,7 @@ struct i2c_acpi_lookup { int index; u32 speed; u32 min_speed; + u32 force_speed; }; /** @@ -285,6 +286,19 @@ i2c_acpi_match_device(const struct acpi_device_id *matches, return acpi_match_device(matches, &client->dev); } +static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = { + /* + * These Silead touchscreen controllers only work at 400KHz, for + * some reason they do not work at 100KHz. On some devices the ACPI + * tables list another device at their bus as only being capable + * of 100KHz, testing has shown that these other devices work fine + * at 400KHz (as can be expected of any recent i2c hw) so we force + * the speed of the bus to 400 KHz if a Silead device is present. + */ + { "MSSL1680", 0 }, + {} +}; + static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level, void *data, void **return_value) { @@ -303,6 +317,9 @@ static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level, if (lookup->speed <= lookup->min_speed) lookup->min_speed = lookup->speed; + if (acpi_match_device_ids(adev, i2c_acpi_force_400khz_device_ids) == 0) + lookup->force_speed = 400000; + return AE_OK; } @@ -340,7 +357,16 @@ u32 i2c_acpi_find_bus_speed(struct device *dev) return 0; } - return lookup.min_speed != UINT_MAX ? lookup.min_speed : 0; + if (lookup.force_speed) { + if (lookup.force_speed != lookup.min_speed) + dev_warn(dev, FW_BUG "DSDT uses known not-working I2C bus speed %d, forcing it to %d\n", + lookup.min_speed, lookup.force_speed); + return lookup.force_speed; + } else if (lookup.min_speed != UINT_MAX) { + return lookup.min_speed; + } else { + return 0; + } } EXPORT_SYMBOL_GPL(i2c_acpi_find_bus_speed); diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index 6f632d543fcc..7eb41990bd6d 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -245,14 +245,14 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action, } client = of_i2c_register_device(adap, rd->dn); - put_device(&adap->dev); - if (IS_ERR(client)) { dev_err(&adap->dev, "failed to create client for '%pOF'\n", rd->dn); + put_device(&adap->dev); of_node_clear_flag(rd->dn, OF_POPULATED); return notifier_from_errno(PTR_ERR(client)); } + put_device(&adap->dev); break; case OF_RECONFIG_CHANGE_REMOVE: /* already depopulated? */ diff --git a/drivers/ide/falconide.c b/drivers/ide/falconide.c index a5a07ccb81a7..dbeb2605e5f6 100644 --- a/drivers/ide/falconide.c +++ b/drivers/ide/falconide.c @@ -15,6 +15,7 @@ #include <linux/blkdev.h> #include <linux/ide.h> #include <linux/init.h> +#include <linux/platform_device.h> #include <asm/setup.h> #include <asm/atarihw.h> @@ -25,13 +26,7 @@ #define DRV_NAME "falconide" /* - * Base of the IDE interface - */ - -#define ATA_HD_BASE 0xfff00000 - - /* - * Offsets from the above base + * Offsets from base address */ #define ATA_HD_CONTROL 0x39 @@ -114,18 +109,18 @@ static const struct ide_port_info falconide_port_info = { .chipset = ide_generic, }; -static void __init falconide_setup_ports(struct ide_hw *hw) +static void __init falconide_setup_ports(struct ide_hw *hw, unsigned long base) { int i; memset(hw, 0, sizeof(*hw)); - hw->io_ports.data_addr = ATA_HD_BASE; + hw->io_ports.data_addr = base; for (i = 1; i < 8; i++) - hw->io_ports_array[i] = ATA_HD_BASE + 1 + i * 4; + hw->io_ports_array[i] = base + 1 + i * 4; - hw->io_ports.ctl_addr = ATA_HD_BASE + ATA_HD_CONTROL; + hw->io_ports.ctl_addr = base + ATA_HD_CONTROL; hw->irq = IRQ_MFP_IDE; } @@ -134,23 +129,29 @@ static void __init falconide_setup_ports(struct ide_hw *hw) * Probe for a Falcon IDE interface */ -static int __init falconide_init(void) +static int __init falconide_init(struct platform_device *pdev) { + struct resource *res; struct ide_host *host; struct ide_hw hw, *hws[] = { &hw }; + unsigned long base; int rc; - if (!MACH_IS_ATARI || !ATARIHW_PRESENT(IDE)) - return -ENODEV; + dev_info(&pdev->dev, "Atari Falcon IDE controller\n"); - printk(KERN_INFO "ide: Falcon IDE controller\n"); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENODEV; - if (!request_mem_region(ATA_HD_BASE, 0x40, DRV_NAME)) { - printk(KERN_ERR "%s: resources busy\n", DRV_NAME); + if (!devm_request_mem_region(&pdev->dev, res->start, + resource_size(res), DRV_NAME)) { + dev_err(&pdev->dev, "resources busy\n"); return -EBUSY; } - falconide_setup_ports(&hw); + base = (unsigned long)res->start; + + falconide_setup_ports(&hw, base); host = ide_host_alloc(&falconide_port_info, hws, 1); if (host == NULL) { @@ -169,10 +170,29 @@ static int __init falconide_init(void) err_free: ide_host_free(host); err: - release_mem_region(ATA_HD_BASE, 0x40); + release_mem_region(res->start, resource_size(res)); return rc; } -module_init(falconide_init); +static int falconide_remove(struct platform_device *pdev) +{ + struct ide_host *host = dev_get_drvdata(&pdev->dev); + + ide_host_remove(host); + + return 0; +} + +static struct platform_driver ide_falcon_driver = { + .remove = falconide_remove, + .driver = { + .name = "atari-falcon-ide", + }, +}; + +module_platform_driver_probe(ide_falcon_driver, falconide_init); +MODULE_AUTHOR("Geert Uytterhoeven"); +MODULE_DESCRIPTION("low-level driver for Atari Falcon IDE"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:atari-falcon-ide"); diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 663f8a5012d6..73aee5949b6b 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -1399,7 +1399,7 @@ static int stm32_adc_dma_start(struct iio_dev *indio_dev) cookie = dmaengine_submit(desc); ret = dma_submit_error(cookie); if (ret) { - dmaengine_terminate_all(adc->dma_chan); + dmaengine_terminate_sync(adc->dma_chan); return ret; } @@ -1477,7 +1477,7 @@ static void __stm32_adc_buffer_predisable(struct iio_dev *indio_dev) stm32_adc_conv_irq_disable(adc); if (adc->dma_chan) - dmaengine_terminate_all(adc->dma_chan); + dmaengine_terminate_sync(adc->dma_chan); if (stm32_adc_set_trig(indio_dev, NULL)) dev_err(&indio_dev->dev, "Can't clear trigger\n"); diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index b99d73887c9f..8743b2f376e2 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -317,8 +317,11 @@ static int adis16480_set_freq(struct iio_dev *indio_dev, int val, int val2) struct adis16480 *st = iio_priv(indio_dev); unsigned int t, reg; + if (val < 0 || val2 < 0) + return -EINVAL; + t = val * 1000 + val2 / 1000; - if (t <= 0) + if (t == 0) return -EINVAL; /* diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index b17f060b52fc..868281b8adb0 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -114,54 +114,63 @@ static const struct inv_mpu6050_hw hw_info[] = { .name = "MPU6050", .reg = ®_set_6050, .config = &chip_config_6050, + .fifo_size = 1024, }, { .whoami = INV_MPU6500_WHOAMI_VALUE, .name = "MPU6500", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_MPU6515_WHOAMI_VALUE, .name = "MPU6515", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_MPU6000_WHOAMI_VALUE, .name = "MPU6000", .reg = ®_set_6050, .config = &chip_config_6050, + .fifo_size = 1024, }, { .whoami = INV_MPU9150_WHOAMI_VALUE, .name = "MPU9150", .reg = ®_set_6050, .config = &chip_config_6050, + .fifo_size = 1024, }, { .whoami = INV_MPU9250_WHOAMI_VALUE, .name = "MPU9250", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_MPU9255_WHOAMI_VALUE, .name = "MPU9255", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_ICM20608_WHOAMI_VALUE, .name = "ICM20608", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_ICM20602_WHOAMI_VALUE, .name = "ICM20602", .reg = ®_set_icm20602, .config = &chip_config_6050, + .fifo_size = 1008, }, }; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h index db1c6904388b..51235677c534 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h @@ -100,12 +100,14 @@ struct inv_mpu6050_chip_config { * @name: name of the chip. * @reg: register map of the chip. * @config: configuration of the chip. + * @fifo_size: size of the FIFO in bytes. */ struct inv_mpu6050_hw { u8 whoami; u8 *name; const struct inv_mpu6050_reg_map *reg; const struct inv_mpu6050_chip_config *config; + size_t fifo_size; }; /* diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 5f9a5de0bab4..72d8c5790076 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -180,9 +180,6 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) "failed to ack interrupt\n"); goto flush_fifo; } - /* handle fifo overflow by reseting fifo */ - if (int_status & INV_MPU6050_BIT_FIFO_OVERFLOW_INT) - goto flush_fifo; if (!(int_status & INV_MPU6050_BIT_RAW_DATA_RDY_INT)) { dev_warn(regmap_get_device(st->map), "spurious interrupt with status 0x%x\n", int_status); @@ -211,6 +208,18 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) if (result) goto end_session; fifo_count = get_unaligned_be16(&data[0]); + + /* + * Handle fifo overflow by resetting fifo. + * Reset if there is only 3 data set free remaining to mitigate + * possible delay between reading fifo count and fifo data. + */ + nb = 3 * bytes_per_datum; + if (fifo_count >= st->hw->fifo_size - nb) { + dev_warn(regmap_get_device(st->map), "fifo overflow reset\n"); + goto flush_fifo; + } + /* compute and process all complete datum */ nb = fifo_count / bytes_per_datum; inv_mpu6050_update_period(st, pf->timestamp, nb); diff --git a/drivers/iio/proximity/srf04.c b/drivers/iio/proximity/srf04.c index 8b50d56b0a03..01eb8cc63076 100644 --- a/drivers/iio/proximity/srf04.c +++ b/drivers/iio/proximity/srf04.c @@ -110,7 +110,7 @@ static int srf04_read(struct srf04_data *data) udelay(data->cfg->trigger_pulse_us); gpiod_set_value(data->gpiod_trig, 0); - /* it cannot take more than 20 ms */ + /* it should not take more than 20 ms until echo is rising */ ret = wait_for_completion_killable_timeout(&data->rising, HZ/50); if (ret < 0) { mutex_unlock(&data->lock); @@ -120,7 +120,8 @@ static int srf04_read(struct srf04_data *data) return -ETIMEDOUT; } - ret = wait_for_completion_killable_timeout(&data->falling, HZ/50); + /* it cannot take more than 50 ms until echo is falling */ + ret = wait_for_completion_killable_timeout(&data->falling, HZ/20); if (ret < 0) { mutex_unlock(&data->lock); return ret; @@ -135,19 +136,19 @@ static int srf04_read(struct srf04_data *data) dt_ns = ktime_to_ns(ktime_dt); /* - * measuring more than 3 meters is beyond the capabilities of - * the sensor + * measuring more than 6,45 meters is beyond the capabilities of + * the supported sensors * ==> filter out invalid results for not measuring echos of * another us sensor * * formula: - * distance 3 m - * time = ---------- = --------- = 9404389 ns - * speed 319 m/s + * distance 6,45 * 2 m + * time = ---------- = ------------ = 40438871 ns + * speed 319 m/s * * using a minimum speed at -20 °C of 319 m/s */ - if (dt_ns > 9404389) + if (dt_ns > 40438871) return -EIO; time_ns = dt_ns; @@ -159,20 +160,20 @@ static int srf04_read(struct srf04_data *data) * with Temp in °C * and speed in m/s * - * use 343 m/s as ultrasonic speed at 20 °C here in absence of the + * use 343,5 m/s as ultrasonic speed at 20 °C here in absence of the * temperature * * therefore: - * time 343 - * distance = ------ * ----- - * 10^6 2 + * time 343,5 time * 106 + * distance = ------ * ------- = ------------ + * 10^6 2 617176 * with time in ns * and distance in mm (one way) * - * because we limit to 3 meters the multiplication with 343 just + * because we limit to 6,45 meters the multiplication with 106 just * fits into 32 bit */ - distance_mm = time_ns * 343 / 2000000; + distance_mm = time_ns * 106 / 617176; return distance_mm; } diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 71cb9525c074..26b792bb1027 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1489,7 +1489,6 @@ static int __init hfi1_mod_init(void) goto bail_dev; } - hfi1_compute_tid_rdma_flow_wt(); /* * These must be called before the driver is registered with * the PCI subsystem. diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 61aa5504d7c3..61362bd6d3ce 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -319,7 +319,9 @@ int pcie_speeds(struct hfi1_devdata *dd) /* * bus->max_bus_speed is set from the bridge's linkcap Max Link Speed */ - if (parent && dd->pcidev->bus->max_bus_speed != PCIE_SPEED_8_0GT) { + if (parent && + (dd->pcidev->bus->max_bus_speed == PCIE_SPEED_2_5GT || + dd->pcidev->bus->max_bus_speed == PCIE_SPEED_5_0GT)) { dd_dev_info(dd, "Parent PCIe bridge does not support Gen3\n"); dd->link_gen3_capable = 0; } diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 513a8aac9ccd..1a3c647675a7 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -2209,15 +2209,15 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, if (qp->s_flags & RVT_S_WAIT_RNR) goto bail_stop; rdi = ib_to_rvt(qp->ibqp.device); - if (qp->s_rnr_retry == 0 && - !((rdi->post_parms[wqe->wr.opcode].flags & - RVT_OPERATION_IGN_RNR_CNT) && - qp->s_rnr_retry_cnt == 0)) { - status = IB_WC_RNR_RETRY_EXC_ERR; - goto class_b; + if (!(rdi->post_parms[wqe->wr.opcode].flags & + RVT_OPERATION_IGN_RNR_CNT)) { + if (qp->s_rnr_retry == 0) { + status = IB_WC_RNR_RETRY_EXC_ERR; + goto class_b; + } + if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0) + qp->s_rnr_retry--; } - if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0) - qp->s_rnr_retry--; /* * The last valid PSN is the previous PSN. For TID RDMA WRITE diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index f21fca3617d5..e53f542b60af 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -107,8 +107,6 @@ static u32 mask_generation(u32 a) * C - Capcode */ -static u32 tid_rdma_flow_wt; - static void tid_rdma_trigger_resume(struct work_struct *work); static void hfi1_kern_exp_rcv_free_flows(struct tid_rdma_request *req); static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req, @@ -136,6 +134,26 @@ static void update_r_next_psn_fecn(struct hfi1_packet *packet, struct tid_rdma_flow *flow, bool fecn); +static void validate_r_tid_ack(struct hfi1_qp_priv *priv) +{ + if (priv->r_tid_ack == HFI1_QP_WQE_INVALID) + priv->r_tid_ack = priv->r_tid_tail; +} + +static void tid_rdma_schedule_ack(struct rvt_qp *qp) +{ + struct hfi1_qp_priv *priv = qp->priv; + + priv->s_flags |= RVT_S_ACK_PENDING; + hfi1_schedule_tid_send(qp); +} + +static void tid_rdma_trigger_ack(struct rvt_qp *qp) +{ + validate_r_tid_ack(qp->priv); + tid_rdma_schedule_ack(qp); +} + static u64 tid_rdma_opfn_encode(struct tid_rdma_params *p) { return @@ -3005,10 +3023,7 @@ nak_psn: qpriv->s_nak_state = IB_NAK_PSN_ERROR; /* We are NAK'ing the next expected PSN */ qpriv->s_nak_psn = mask_psn(flow->flow_state.r_next_psn); - qpriv->s_flags |= RVT_S_ACK_PENDING; - if (qpriv->r_tid_ack == HFI1_QP_WQE_INVALID) - qpriv->r_tid_ack = qpriv->r_tid_tail; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); } goto unlock; } @@ -3371,18 +3386,17 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe, return sizeof(ohdr->u.tid_rdma.w_req) / sizeof(u32); } -void hfi1_compute_tid_rdma_flow_wt(void) +static u32 hfi1_compute_tid_rdma_flow_wt(struct rvt_qp *qp) { /* * Heuristic for computing the RNR timeout when waiting on the flow * queue. Rather than a computationaly expensive exact estimate of when * a flow will be available, we assume that if a QP is at position N in * the flow queue it has to wait approximately (N + 1) * (number of - * segments between two sync points), assuming PMTU of 4K. The rationale - * for this is that flows are released and recycled at each sync point. + * segments between two sync points). The rationale for this is that + * flows are released and recycled at each sync point. */ - tid_rdma_flow_wt = MAX_TID_FLOW_PSN * enum_to_mtu(OPA_MTU_4096) / - TID_RDMA_MAX_SEGMENT_SIZE; + return (MAX_TID_FLOW_PSN * qp->pmtu) >> TID_RDMA_SEGMENT_SHIFT; } static u32 position_in_queue(struct hfi1_qp_priv *qpriv, @@ -3505,7 +3519,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx) if (qpriv->flow_state.index >= RXE_NUM_TID_FLOWS) { ret = hfi1_kern_setup_hw_flow(qpriv->rcd, qp); if (ret) { - to_seg = tid_rdma_flow_wt * + to_seg = hfi1_compute_tid_rdma_flow_wt(qp) * position_in_queue(qpriv, &rcd->flow_queue); break; @@ -3526,7 +3540,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx) /* * If overtaking req->acked_tail, send an RNR NAK. Because the * QP is not queued in this case, and the issue can only be - * caused due a delay in scheduling the second leg which we + * caused by a delay in scheduling the second leg which we * cannot estimate, we use a rather arbitrary RNR timeout of * (MAX_FLOWS / 2) segments */ @@ -3534,8 +3548,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx) MAX_FLOWS)) { ret = -EAGAIN; to_seg = MAX_FLOWS >> 1; - qpriv->s_flags |= RVT_S_ACK_PENDING; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); break; } @@ -4335,8 +4348,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet) trace_hfi1_tid_req_rcv_write_data(qp, 0, e->opcode, e->psn, e->lpsn, req); trace_hfi1_tid_write_rsp_rcv_data(qp); - if (priv->r_tid_ack == HFI1_QP_WQE_INVALID) - priv->r_tid_ack = priv->r_tid_tail; + validate_r_tid_ack(priv); if (opcode == TID_OP(WRITE_DATA_LAST)) { release_rdma_sge_mr(e); @@ -4375,8 +4387,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet) } done: - priv->s_flags |= RVT_S_ACK_PENDING; - hfi1_schedule_tid_send(qp); + tid_rdma_schedule_ack(qp); exit: priv->r_next_psn_kdeth = flow->flow_state.r_next_psn; if (fecn) @@ -4388,10 +4399,7 @@ send_nak: if (!priv->s_nak_state) { priv->s_nak_state = IB_NAK_PSN_ERROR; priv->s_nak_psn = flow->flow_state.r_next_psn; - priv->s_flags |= RVT_S_ACK_PENDING; - if (priv->r_tid_ack == HFI1_QP_WQE_INVALID) - priv->r_tid_ack = priv->r_tid_tail; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); } goto done; } @@ -4939,8 +4947,7 @@ void hfi1_rc_rcv_tid_rdma_resync(struct hfi1_packet *packet) qpriv->resync = true; /* RESYNC request always gets a TID RDMA ACK. */ qpriv->s_nak_state = 0; - qpriv->s_flags |= RVT_S_ACK_PENDING; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); bail: if (fecn) qp->s_flags |= RVT_S_ECN; diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.h b/drivers/infiniband/hw/hfi1/tid_rdma.h index 1c536185261e..6e82df2190b7 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.h +++ b/drivers/infiniband/hw/hfi1/tid_rdma.h @@ -17,6 +17,7 @@ #define TID_RDMA_MIN_SEGMENT_SIZE BIT(18) /* 256 KiB (for now) */ #define TID_RDMA_MAX_SEGMENT_SIZE BIT(18) /* 256 KiB (for now) */ #define TID_RDMA_MAX_PAGES (BIT(18) >> PAGE_SHIFT) +#define TID_RDMA_SEGMENT_SHIFT 18 /* * Bit definitions for priv->s_flags. @@ -274,8 +275,6 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe, struct ib_other_headers *ohdr, u32 *bth1, u32 *bth2, u32 *len); -void hfi1_compute_tid_rdma_flow_wt(void); - void hfi1_rc_rcv_tid_rdma_write_req(struct hfi1_packet *packet); u32 hfi1_build_tid_rdma_write_resp(struct rvt_qp *qp, struct rvt_ack_entry *e, diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h index 86783276fb1f..3bb8f78fb7b0 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.h +++ b/drivers/infiniband/hw/hns/hns_roce_hem.h @@ -59,7 +59,7 @@ enum { #define HNS_ROCE_HEM_CHUNK_LEN \ ((256 - sizeof(struct list_head) - 2 * sizeof(int)) / \ - (sizeof(struct scatterlist))) + (sizeof(struct scatterlist) + sizeof(void *))) #define check_whether_bt_num_3(type, hop_num) \ (type < HEM_TYPE_MTT && hop_num == 2) diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 9591457eb768..43ea2c13b212 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -376,7 +376,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq, srq->max = roundup_pow_of_two(srq_init_attr->attr.max_wr + 1); srq->max_gs = srq_init_attr->attr.max_sge; - srq_desc_size = max(16, 16 * srq->max_gs); + srq_desc_size = roundup_pow_of_two(max(16, 16 * srq->max_gs)); srq->wqe_shift = ilog2(srq_desc_size); diff --git a/drivers/input/ff-memless.c b/drivers/input/ff-memless.c index 1cb40c7475af..8229a9006917 100644 --- a/drivers/input/ff-memless.c +++ b/drivers/input/ff-memless.c @@ -489,6 +489,15 @@ static void ml_ff_destroy(struct ff_device *ff) { struct ml_device *ml = ff->private; + /* + * Even though we stop all playing effects when tearing down + * an input device (via input_device_flush() that calls into + * input_ff_flush() that stops and erases all effects), we + * do not actually stop the timer, and therefore we should + * do it here. + */ + del_timer_sync(&ml->timer); + kfree(ml->private); } diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c index f28a7158b2ef..bbf9ae9f3f0c 100644 --- a/drivers/input/rmi4/rmi_f11.c +++ b/drivers/input/rmi4/rmi_f11.c @@ -510,7 +510,6 @@ struct f11_data { struct rmi_2d_sensor_platform_data sensor_pdata; unsigned long *abs_mask; unsigned long *rel_mask; - unsigned long *result_bits; }; enum f11_finger_state { @@ -1057,7 +1056,7 @@ static int rmi_f11_initialize(struct rmi_function *fn) /* ** init instance data, fill in values and create any sysfs files */ - f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 3, + f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 2, GFP_KERNEL); if (!f11) return -ENOMEM; @@ -1076,8 +1075,6 @@ static int rmi_f11_initialize(struct rmi_function *fn) + sizeof(struct f11_data)); f11->rel_mask = (unsigned long *)((char *)f11 + sizeof(struct f11_data) + mask_size); - f11->result_bits = (unsigned long *)((char *)f11 - + sizeof(struct f11_data) + mask_size * 2); set_bit(fn->irq_pos, f11->abs_mask); set_bit(fn->irq_pos + 1, f11->rel_mask); @@ -1284,8 +1281,8 @@ static irqreturn_t rmi_f11_attention(int irq, void *ctx) valid_bytes = f11->sensor.attn_size; memcpy(f11->sensor.data_pkt, drvdata->attn_data.data, valid_bytes); - drvdata->attn_data.data += f11->sensor.attn_size; - drvdata->attn_data.size -= f11->sensor.attn_size; + drvdata->attn_data.data += valid_bytes; + drvdata->attn_data.size -= valid_bytes; } else { error = rmi_read_block(rmi_dev, data_base_addr, f11->sensor.data_pkt, diff --git a/drivers/input/rmi4/rmi_f12.c b/drivers/input/rmi4/rmi_f12.c index d20a5d6780d1..7e97944f7616 100644 --- a/drivers/input/rmi4/rmi_f12.c +++ b/drivers/input/rmi4/rmi_f12.c @@ -55,6 +55,9 @@ struct f12_data { const struct rmi_register_desc_item *data15; u16 data15_offset; + + unsigned long *abs_mask; + unsigned long *rel_mask; }; static int rmi_f12_read_sensor_tuning(struct f12_data *f12) @@ -209,8 +212,8 @@ static irqreturn_t rmi_f12_attention(int irq, void *ctx) valid_bytes = sensor->attn_size; memcpy(sensor->data_pkt, drvdata->attn_data.data, valid_bytes); - drvdata->attn_data.data += sensor->attn_size; - drvdata->attn_data.size -= sensor->attn_size; + drvdata->attn_data.data += valid_bytes; + drvdata->attn_data.size -= valid_bytes; } else { retval = rmi_read_block(rmi_dev, f12->data_addr, sensor->data_pkt, sensor->pkt_size); @@ -291,9 +294,18 @@ static int rmi_f12_write_control_regs(struct rmi_function *fn) static int rmi_f12_config(struct rmi_function *fn) { struct rmi_driver *drv = fn->rmi_dev->driver; + struct f12_data *f12 = dev_get_drvdata(&fn->dev); + struct rmi_2d_sensor *sensor; int ret; - drv->set_irq_bits(fn->rmi_dev, fn->irq_mask); + sensor = &f12->sensor; + + if (!sensor->report_abs) + drv->clear_irq_bits(fn->rmi_dev, f12->abs_mask); + else + drv->set_irq_bits(fn->rmi_dev, f12->abs_mask); + + drv->clear_irq_bits(fn->rmi_dev, f12->rel_mask); ret = rmi_f12_write_control_regs(fn); if (ret) @@ -315,9 +327,12 @@ static int rmi_f12_probe(struct rmi_function *fn) struct rmi_device_platform_data *pdata = rmi_get_platform_data(rmi_dev); struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev); u16 data_offset = 0; + int mask_size; rmi_dbg(RMI_DEBUG_FN, &fn->dev, "%s\n", __func__); + mask_size = BITS_TO_LONGS(drvdata->irq_count) * sizeof(unsigned long); + ret = rmi_read(fn->rmi_dev, query_addr, &buf); if (ret < 0) { dev_err(&fn->dev, "Failed to read general info register: %d\n", @@ -332,10 +347,19 @@ static int rmi_f12_probe(struct rmi_function *fn) return -ENODEV; } - f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data), GFP_KERNEL); + f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data) + mask_size * 2, + GFP_KERNEL); if (!f12) return -ENOMEM; + f12->abs_mask = (unsigned long *)((char *)f12 + + sizeof(struct f12_data)); + f12->rel_mask = (unsigned long *)((char *)f12 + + sizeof(struct f12_data) + mask_size); + + set_bit(fn->irq_pos, f12->abs_mask); + set_bit(fn->irq_pos + 1, f12->rel_mask); + f12->has_dribble = !!(buf & BIT(3)); if (fn->dev.of_node) { diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c index 710b02595486..897105b9a98b 100644 --- a/drivers/input/rmi4/rmi_f54.c +++ b/drivers/input/rmi4/rmi_f54.c @@ -359,7 +359,7 @@ static const struct vb2_ops rmi_f54_queue_ops = { static const struct vb2_queue rmi_f54_queue = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, .io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ, - .buf_struct_size = sizeof(struct vb2_buffer), + .buf_struct_size = sizeof(struct vb2_v4l2_buffer), .ops = &rmi_f54_queue_ops, .mem_ops = &vb2_vmalloc_memops, .timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC, @@ -601,7 +601,7 @@ static int rmi_f54_config(struct rmi_function *fn) { struct rmi_driver *drv = fn->rmi_dev->driver; - drv->set_irq_bits(fn->rmi_dev, fn->irq_mask); + drv->clear_irq_bits(fn->rmi_dev, fn->irq_mask); return 0; } @@ -730,6 +730,7 @@ static void rmi_f54_remove(struct rmi_function *fn) video_unregister_device(&f54->vdev); v4l2_device_unregister(&f54->v4l2); + destroy_workqueue(f54->workqueue); } struct rmi_function_handler rmi_f54_handler = { diff --git a/drivers/input/touchscreen/cyttsp4_core.c b/drivers/input/touchscreen/cyttsp4_core.c index 4b22d49a0f49..6bcffc930384 100644 --- a/drivers/input/touchscreen/cyttsp4_core.c +++ b/drivers/input/touchscreen/cyttsp4_core.c @@ -1990,11 +1990,6 @@ static int cyttsp4_mt_probe(struct cyttsp4 *cd) /* get sysinfo */ md->si = &cd->sysinfo; - if (!md->si) { - dev_err(dev, "%s: Fail get sysinfo pointer from core p=%p\n", - __func__, md->si); - goto error_get_sysinfo; - } rc = cyttsp4_setup_input_device(cd); if (rc) @@ -2004,8 +1999,6 @@ static int cyttsp4_mt_probe(struct cyttsp4 *cd) error_init_input: input_free_device(md->input); -error_get_sysinfo: - input_set_drvdata(md->input, NULL); error_alloc_failed: dev_err(dev, "%s failed.\n", __func__); return rc; diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 7b971228df38..c498796adc07 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -405,8 +405,12 @@ void icc_set_tag(struct icc_path *path, u32 tag) if (!path) return; + mutex_lock(&icc_lock); + for (i = 0; i < path->num_nodes; i++) path->reqs[i].tag = tag; + + mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_set_tag); diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c index 910081d6ddc0..b4966d8f3348 100644 --- a/drivers/interconnect/qcom/qcs404.c +++ b/drivers/interconnect/qcom/qcs404.c @@ -433,7 +433,8 @@ static int qnoc_probe(struct platform_device *pdev) if (!qp) return -ENOMEM; - data = devm_kcalloc(dev, num_nodes, sizeof(*node), GFP_KERNEL); + data = devm_kzalloc(dev, struct_size(data, nodes, num_nodes), + GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c index 57955596bb59..502a6c22b41e 100644 --- a/drivers/interconnect/qcom/sdm845.c +++ b/drivers/interconnect/qcom/sdm845.c @@ -790,7 +790,8 @@ static int qnoc_probe(struct platform_device *pdev) if (!qp) return -ENOMEM; - data = devm_kcalloc(&pdev->dev, num_nodes, sizeof(*node), GFP_KERNEL); + data = devm_kzalloc(&pdev->dev, struct_size(data, nodes, num_nodes), + GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 1edc99335a94..6bb1f682f78b 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -87,6 +87,15 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); +/* + * Global static key controlling whether an update to PMR allowing more + * interrupts requires to be propagated to the redistributor (DSB SY). + * And this needs to be exported for modules to be able to enable + * interrupts... + */ +DEFINE_STATIC_KEY_FALSE(gic_pmr_sync); +EXPORT_SYMBOL(gic_pmr_sync); + /* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */ static refcount_t *ppi_nmi_refs; @@ -1502,6 +1511,17 @@ static void gic_enable_nmi_support(void) for (i = 0; i < gic_data.ppi_nr; i++) refcount_set(&ppi_nmi_refs[i], 0); + /* + * Linux itself doesn't use 1:N distribution, so has no need to + * set PMHE. The only reason to have it set is if EL3 requires it + * (and we can't change it). + */ + if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) + static_branch_enable(&gic_pmr_sync); + + pr_info("%s ICC_PMR_EL1 synchronisation\n", + static_branch_unlikely(&gic_pmr_sync) ? "Forcing" : "Relaxing"); + static_branch_enable(&supports_pseudo_nmis); if (static_branch_likely(&supports_deactivate_key)) diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index aa98953f4462..d6d5ab23c088 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -38,9 +38,9 @@ config MD_AUTODETECT default y ---help--- If you say Y here, then the kernel will try to autodetect raid - arrays as part of its boot process. + arrays as part of its boot process. - If you don't use raid and say Y, this autodetection can cause + If you don't use raid and say Y, this autodetection can cause a several-second delay in the boot time due to various synchronisation steps that are part of this step. @@ -290,7 +290,7 @@ config DM_SNAPSHOT depends on BLK_DEV_DM select DM_BUFIO ---help--- - Allow volume managers to take writable snapshots of a device. + Allow volume managers to take writable snapshots of a device. config DM_THIN_PROVISIONING tristate "Thin provisioning target" @@ -298,7 +298,7 @@ config DM_THIN_PROVISIONING select DM_PERSISTENT_DATA select DM_BIO_PRISON ---help--- - Provides thin provisioning and snapshots that share a data store. + Provides thin provisioning and snapshots that share a data store. config DM_CACHE tristate "Cache target (EXPERIMENTAL)" @@ -307,23 +307,23 @@ config DM_CACHE select DM_PERSISTENT_DATA select DM_BIO_PRISON ---help--- - dm-cache attempts to improve performance of a block device by - moving frequently used data to a smaller, higher performance - device. Different 'policy' plugins can be used to change the - algorithms used to select which blocks are promoted, demoted, - cleaned etc. It supports writeback and writethrough modes. + dm-cache attempts to improve performance of a block device by + moving frequently used data to a smaller, higher performance + device. Different 'policy' plugins can be used to change the + algorithms used to select which blocks are promoted, demoted, + cleaned etc. It supports writeback and writethrough modes. config DM_CACHE_SMQ tristate "Stochastic MQ Cache Policy (EXPERIMENTAL)" depends on DM_CACHE default y ---help--- - A cache policy that uses a multiqueue ordered by recent hits - to select which blocks should be promoted and demoted. - This is meant to be a general purpose policy. It prioritises - reads over writes. This SMQ policy (vs MQ) offers the promise - of less memory utilization, improved performance and increased - adaptability in the face of changing workloads. + A cache policy that uses a multiqueue ordered by recent hits + to select which blocks should be promoted and demoted. + This is meant to be a general purpose policy. It prioritises + reads over writes. This SMQ policy (vs MQ) offers the promise + of less memory utilization, improved performance and increased + adaptability in the face of changing workloads. config DM_WRITECACHE tristate "Writecache target" @@ -343,9 +343,9 @@ config DM_ERA select DM_PERSISTENT_DATA select DM_BIO_PRISON ---help--- - dm-era tracks which parts of a block device are written to - over time. Useful for maintaining cache coherency when using - vendor snapshots. + dm-era tracks which parts of a block device are written to + over time. Useful for maintaining cache coherency when using + vendor snapshots. config DM_CLONE tristate "Clone target (EXPERIMENTAL)" @@ -353,20 +353,20 @@ config DM_CLONE default n select DM_PERSISTENT_DATA ---help--- - dm-clone produces a one-to-one copy of an existing, read-only source - device into a writable destination device. The cloned device is - visible/mountable immediately and the copy of the source device to the - destination device happens in the background, in parallel with user - I/O. + dm-clone produces a one-to-one copy of an existing, read-only source + device into a writable destination device. The cloned device is + visible/mountable immediately and the copy of the source device to the + destination device happens in the background, in parallel with user + I/O. - If unsure, say N. + If unsure, say N. config DM_MIRROR tristate "Mirror target" depends on BLK_DEV_DM ---help--- - Allow volume managers to mirror logical volumes, also - needed for live data migration tools such as 'pvmove'. + Allow volume managers to mirror logical volumes, also + needed for live data migration tools such as 'pvmove'. config DM_LOG_USERSPACE tristate "Mirror userspace logging" @@ -483,7 +483,7 @@ config DM_FLAKEY tristate "Flakey target" depends on BLK_DEV_DM ---help--- - A target that intermittently fails I/O for debugging purposes. + A target that intermittently fails I/O for debugging purposes. config DM_VERITY tristate "Verity target support" diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile index d26b35195825..fd714628da6a 100644 --- a/drivers/md/bcache/Makefile +++ b/drivers/md/bcache/Makefile @@ -5,5 +5,3 @@ obj-$(CONFIG_BCACHE) += bcache.o bcache-y := alloc.o bset.o btree.o closure.o debug.o extents.o\ io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\ util.o writeback.o - -CFLAGS_request.o += -Iblock diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 6f776823b9ba..a1df0d95151c 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -377,7 +377,10 @@ retry_invalidate: if (!fifo_full(&ca->free_inc)) goto retry_invalidate; - bch_prio_write(ca); + if (bch_prio_write(ca, false) < 0) { + ca->invalidate_needs_gc = 1; + wake_up_gc(ca->set); + } } } out: diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 013e35a9e317..9198c1b480d9 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -582,6 +582,7 @@ struct cache_set { */ wait_queue_head_t btree_cache_wait; struct task_struct *btree_cache_alloc_lock; + spinlock_t btree_cannibalize_lock; /* * When we free a btree node, we increment the gen of the bucket the @@ -723,6 +724,7 @@ struct cache_set { unsigned int gc_always_rewrite:1; unsigned int shrinker_disabled:1; unsigned int copy_gc_enabled:1; + unsigned int idle_max_writeback_rate_enabled:1; #define BUCKET_HASH_BITS 12 struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; @@ -977,7 +979,7 @@ bool bch_cached_dev_error(struct cached_dev *dc); __printf(2, 3) bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...); -void bch_prio_write(struct cache *ca); +int bch_prio_write(struct cache *ca, bool wait); void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent); extern struct workqueue_struct *bcache_wq; diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 08768796b543..cffcdc9feefb 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -155,6 +155,7 @@ int __bch_keylist_realloc(struct keylist *l, unsigned int u64s) return 0; } +/* Pop the top key of keylist by pointing l->top to its previous key */ struct bkey *bch_keylist_pop(struct keylist *l) { struct bkey *k = l->keys; @@ -168,6 +169,7 @@ struct bkey *bch_keylist_pop(struct keylist *l) return l->top = k; } +/* Pop the bottom key of keylist and update l->top_p */ void bch_keylist_pop_front(struct keylist *l) { l->top_p -= bkey_u64s(l->keys); @@ -309,7 +311,6 @@ void bch_btree_keys_free(struct btree_keys *b) t->tree = NULL; t->data = NULL; } -EXPORT_SYMBOL(bch_btree_keys_free); int bch_btree_keys_alloc(struct btree_keys *b, unsigned int page_order, @@ -342,7 +343,6 @@ err: bch_btree_keys_free(b); return -ENOMEM; } -EXPORT_SYMBOL(bch_btree_keys_alloc); void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops, bool *expensive_debug_checks) @@ -361,7 +361,6 @@ void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops, * any more. */ } -EXPORT_SYMBOL(bch_btree_keys_init); /* Binary tree stuff for auxiliary search trees */ @@ -678,7 +677,6 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic) bch_bset_build_unwritten_tree(b); } -EXPORT_SYMBOL(bch_bset_init_next); /* * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to @@ -732,7 +730,6 @@ void bch_bset_build_written_tree(struct btree_keys *b) j = inorder_next(j, t->size)) make_bfloat(t, j); } -EXPORT_SYMBOL(bch_bset_build_written_tree); /* Insert */ @@ -780,7 +777,6 @@ fix_right: do { j = j * 2 + 1; } while (j < t->size); } -EXPORT_SYMBOL(bch_bset_fix_invalidated_key); static void bch_bset_fix_lookup_table(struct btree_keys *b, struct bset_tree *t, @@ -855,7 +851,6 @@ bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r) return b->ops->key_merge(b, l, r); } -EXPORT_SYMBOL(bch_bkey_try_merge); void bch_bset_insert(struct btree_keys *b, struct bkey *where, struct bkey *insert) @@ -875,7 +870,6 @@ void bch_bset_insert(struct btree_keys *b, struct bkey *where, bkey_copy(where, insert); bch_bset_fix_lookup_table(b, t, where); } -EXPORT_SYMBOL(bch_bset_insert); unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, struct bkey *replace_key) @@ -931,7 +925,6 @@ copy: bkey_copy(m, k); merged: return status; } -EXPORT_SYMBOL(bch_btree_insert_key); /* Lookup */ @@ -1077,7 +1070,6 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, return i.l; } -EXPORT_SYMBOL(__bch_bset_search); /* Btree iterator */ @@ -1132,7 +1124,6 @@ struct bkey *bch_btree_iter_init(struct btree_keys *b, { return __bch_btree_iter_init(b, iter, search, b->set); } -EXPORT_SYMBOL(bch_btree_iter_init); static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, btree_iter_cmp_fn *cmp) @@ -1165,7 +1156,6 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter) return __bch_btree_iter_next(iter, btree_iter_cmp); } -EXPORT_SYMBOL(bch_btree_iter_next); struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, struct btree_keys *b, ptr_filter_fn fn) @@ -1196,7 +1186,6 @@ int bch_bset_sort_state_init(struct bset_sort_state *state, return mempool_init_page_pool(&state->pool, 1, page_order); } -EXPORT_SYMBOL(bch_bset_sort_state_init); static void btree_mergesort(struct btree_keys *b, struct bset *out, struct btree_iter *iter, @@ -1313,7 +1302,6 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } -EXPORT_SYMBOL(bch_btree_sort_partial); void bch_btree_sort_and_fix_extents(struct btree_keys *b, struct btree_iter *iter, @@ -1366,7 +1354,6 @@ void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state) out: bch_bset_build_written_tree(b); } -EXPORT_SYMBOL(bch_btree_sort_lazy); void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *stats) { diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ba434d9ac720..14d6c33b0957 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -543,6 +543,11 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref) set_btree_node_dirty(b); + /* + * w->journal is always the oldest journal pin of all bkeys + * in the leaf node, to make sure the oldest jset seq won't + * be increased before this btree node is flushed. + */ if (journal_ref) { if (w->journal && journal_pin_cmp(b->c, w->journal, journal_ref)) { @@ -723,6 +728,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink, * IO can always make forward progress: */ nr /= c->btree_pages; + if (nr == 0) + nr = 1; nr = min_t(unsigned long, nr, mca_can_free(c)); i = 0; @@ -884,15 +891,17 @@ out: static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op) { - struct task_struct *old; - - old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current); - if (old && old != current) { + spin_lock(&c->btree_cannibalize_lock); + if (likely(c->btree_cache_alloc_lock == NULL)) { + c->btree_cache_alloc_lock = current; + } else if (c->btree_cache_alloc_lock != current) { if (op) prepare_to_wait(&c->btree_cache_wait, &op->wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&c->btree_cannibalize_lock); return -EINTR; } + spin_unlock(&c->btree_cannibalize_lock); return 0; } @@ -927,10 +936,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, */ static void bch_cannibalize_unlock(struct cache_set *c) { + spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { c->btree_cache_alloc_lock = NULL; wake_up(&c->btree_cache_wait); } + spin_unlock(&c->btree_cannibalize_lock); } static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op, diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index c12cd809ab19..0164a1fe94a9 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -45,7 +45,6 @@ void closure_sub(struct closure *cl, int v) { closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining)); } -EXPORT_SYMBOL(closure_sub); /* * closure_put - decrement a closure's refcount @@ -54,7 +53,6 @@ void closure_put(struct closure *cl) { closure_put_after_sub(cl, atomic_dec_return(&cl->remaining)); } -EXPORT_SYMBOL(closure_put); /* * closure_wake_up - wake up all closures on a wait list, without memory barrier @@ -76,7 +74,6 @@ void __closure_wake_up(struct closure_waitlist *wait_list) closure_sub(cl, CLOSURE_WAITING + 1); } } -EXPORT_SYMBOL(__closure_wake_up); /** * closure_wait - add a closure to a waitlist @@ -96,7 +93,6 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl) return true; } -EXPORT_SYMBOL(closure_wait); struct closure_syncer { struct task_struct *task; @@ -131,7 +127,6 @@ void __sched __closure_sync(struct closure *cl) __set_current_state(TASK_RUNNING); } -EXPORT_SYMBOL(__closure_sync); #ifdef CONFIG_BCACHE_CLOSURES_DEBUG @@ -149,7 +144,6 @@ void closure_debug_create(struct closure *cl) list_add(&cl->all, &closure_list); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL(closure_debug_create); void closure_debug_destroy(struct closure *cl) { @@ -162,7 +156,6 @@ void closure_debug_destroy(struct closure *cl) list_del(&cl->all); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL(closure_debug_destroy); static struct dentry *closure_debug; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 41adcd1546f1..73478a91a342 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -62,18 +62,6 @@ static void bch_data_insert_keys(struct closure *cl) struct bkey *replace_key = op->replace ? &op->replace_key : NULL; int ret; - /* - * If we're looping, might already be waiting on - * another journal write - can't wait on more than one journal write at - * a time - * - * XXX: this looks wrong - */ -#if 0 - while (atomic_read(&s->cl.remaining) & CLOSURE_WAITING) - closure_sync(&s->cl); -#endif - if (!op->replace) journal_ref = bch_journal(op->c, &op->insert_keys, op->flush_journal ? cl : NULL); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 20ed838e9413..77e9869345e7 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -92,10 +92,11 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev, pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u", sb->version, sb->flags, sb->seq, sb->keys); - err = "Not a bcache superblock"; + err = "Not a bcache superblock (bad offset)"; if (sb->offset != SB_SECTOR) goto err; + err = "Not a bcache superblock (bad magic)"; if (memcmp(sb->magic, bcache_magic, 16)) goto err; @@ -529,12 +530,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op, closure_sync(cl); } -void bch_prio_write(struct cache *ca) +int bch_prio_write(struct cache *ca, bool wait) { int i; struct bucket *b; struct closure cl; + pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu", + fifo_used(&ca->free[RESERVE_PRIO]), + fifo_used(&ca->free[RESERVE_NONE]), + fifo_used(&ca->free_inc)); + + /* + * Pre-check if there are enough free buckets. In the non-blocking + * scenario it's better to fail early rather than starting to allocate + * buckets and do a cleanup later in case of failure. + */ + if (!wait) { + size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) + + fifo_used(&ca->free[RESERVE_NONE]); + if (prio_buckets(ca) > avail) + return -ENOMEM; + } + closure_init_stack(&cl); lockdep_assert_held(&ca->set->bucket_lock); @@ -544,9 +562,6 @@ void bch_prio_write(struct cache *ca) atomic_long_add(ca->sb.bucket_size * prio_buckets(ca), &ca->meta_sectors_written); - //pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free), - // fifo_used(&ca->free_inc), fifo_used(&ca->unused)); - for (i = prio_buckets(ca) - 1; i >= 0; --i) { long bucket; struct prio_set *p = ca->disk_buckets; @@ -564,7 +579,7 @@ void bch_prio_write(struct cache *ca) p->magic = pset_magic(&ca->sb); p->csum = bch_crc64(&p->magic, bucket_bytes(ca) - 8); - bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true); + bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait); BUG_ON(bucket == -1); mutex_unlock(&ca->set->bucket_lock); @@ -593,6 +608,7 @@ void bch_prio_write(struct cache *ca) ca->prio_last_buckets[i] = ca->prio_buckets[i]; } + return 0; } static void prio_read(struct cache *ca, uint64_t bucket) @@ -761,20 +777,28 @@ static inline int idx_to_first_minor(int idx) static void bcache_device_free(struct bcache_device *d) { + struct gendisk *disk = d->disk; + lockdep_assert_held(&bch_register_lock); - pr_info("%s stopped", d->disk->disk_name); + if (disk) + pr_info("%s stopped", disk->disk_name); + else + pr_err("bcache device (NULL gendisk) stopped"); if (d->c) bcache_device_detach(d); - if (d->disk && d->disk->flags & GENHD_FL_UP) - del_gendisk(d->disk); - if (d->disk && d->disk->queue) - blk_cleanup_queue(d->disk->queue); - if (d->disk) { + + if (disk) { + if (disk->flags & GENHD_FL_UP) + del_gendisk(disk); + + if (disk->queue) + blk_cleanup_queue(disk->queue); + ida_simple_remove(&bcache_device_idx, - first_minor_to_idx(d->disk->first_minor)); - put_disk(d->disk); + first_minor_to_idx(disk->first_minor)); + put_disk(disk); } bioset_exit(&d->bio_split); @@ -1769,6 +1793,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) sema_init(&c->sb_write_mutex, 1); mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); + spin_lock_init(&c->btree_cannibalize_lock); init_waitqueue_head(&c->bucket_wait); init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1); @@ -1809,6 +1834,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->congested_read_threshold_us = 2000; c->congested_write_threshold_us = 20000; c->error_limit = DEFAULT_IO_ERROR_LIMIT; + c->idle_max_writeback_rate_enabled = 1; WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags)); return c; @@ -1954,7 +1980,7 @@ static int run_cache_set(struct cache_set *c) mutex_lock(&c->bucket_lock); for_each_cache(ca, c, i) - bch_prio_write(ca); + bch_prio_write(ca, true); mutex_unlock(&c->bucket_lock); err = "cannot allocate new UUID bucket"; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 627dcea0f5b6..733e2ddf3c78 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -134,6 +134,7 @@ rw_attribute(expensive_debug_checks); rw_attribute(cache_replacement_policy); rw_attribute(btree_shrinker_disabled); rw_attribute(copy_gc_enabled); +rw_attribute(idle_max_writeback_rate); rw_attribute(gc_after_writeback); rw_attribute(size); @@ -747,6 +748,8 @@ SHOW(__bch_cache_set) sysfs_printf(gc_always_rewrite, "%i", c->gc_always_rewrite); sysfs_printf(btree_shrinker_disabled, "%i", c->shrinker_disabled); sysfs_printf(copy_gc_enabled, "%i", c->copy_gc_enabled); + sysfs_printf(idle_max_writeback_rate, "%i", + c->idle_max_writeback_rate_enabled); sysfs_printf(gc_after_writeback, "%i", c->gc_after_writeback); sysfs_printf(io_disable, "%i", test_bit(CACHE_SET_IO_DISABLE, &c->flags)); @@ -864,6 +867,9 @@ STORE(__bch_cache_set) sysfs_strtoul_bool(gc_always_rewrite, c->gc_always_rewrite); sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled); sysfs_strtoul_bool(copy_gc_enabled, c->copy_gc_enabled); + sysfs_strtoul_bool(idle_max_writeback_rate, + c->idle_max_writeback_rate_enabled); + /* * write gc_after_writeback here may overwrite an already set * BCH_DO_AUTO_GC, it doesn't matter because this flag will be @@ -954,6 +960,7 @@ static struct attribute *bch_cache_set_internal_files[] = { &sysfs_gc_always_rewrite, &sysfs_btree_shrinker_disabled, &sysfs_copy_gc_enabled, + &sysfs_idle_max_writeback_rate, &sysfs_gc_after_writeback, &sysfs_io_disable, &sysfs_cutoff_writeback, diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index d60268fe49e1..4a40f9eadeaf 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -122,6 +122,10 @@ static void __update_writeback_rate(struct cached_dev *dc) static bool set_at_max_writeback_rate(struct cache_set *c, struct cached_dev *dc) { + /* Don't sst max writeback rate if it is disabled */ + if (!c->idle_max_writeback_rate_enabled) + return false; + /* Don't set max writeback rate if gc is running */ if (!c->gc_mark_valid) return false; diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c index b5389890bbc3..1f8f98efd97a 100644 --- a/drivers/md/dm-bio-prison-v1.c +++ b/drivers/md/dm-bio-prison-v1.c @@ -150,11 +150,10 @@ static int bio_detain(struct dm_bio_prison *prison, struct dm_bio_prison_cell **cell_result) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __bio_detain(prison, key, inmate, cell_prealloc, cell_result); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -198,11 +197,9 @@ void dm_cell_release(struct dm_bio_prison *prison, struct dm_bio_prison_cell *cell, struct bio_list *bios) { - unsigned long flags; - - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); __cell_release(prison, cell, bios); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); } EXPORT_SYMBOL_GPL(dm_cell_release); @@ -250,12 +247,10 @@ void dm_cell_visit_release(struct dm_bio_prison *prison, void *context, struct dm_bio_prison_cell *cell) { - unsigned long flags; - - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); visit_fn(context, cell); rb_erase(&cell->node, &prison->cells); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); } EXPORT_SYMBOL_GPL(dm_cell_visit_release); @@ -275,11 +270,10 @@ int dm_cell_promote_or_release(struct dm_bio_prison *prison, struct dm_bio_prison_cell *cell) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __promote_or_release(prison, cell); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -379,10 +373,9 @@ EXPORT_SYMBOL_GPL(dm_deferred_entry_dec); int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work) { int r = 1; - unsigned long flags; unsigned next_entry; - spin_lock_irqsave(&ds->lock, flags); + spin_lock_irq(&ds->lock); if ((ds->sweeper == ds->current_entry) && !ds->entries[ds->current_entry].count) r = 0; @@ -392,7 +385,7 @@ int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work) if (!ds->entries[next_entry].count) ds->current_entry = next_entry; } - spin_unlock_irqrestore(&ds->lock, flags); + spin_unlock_irq(&ds->lock); return r; } diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c index b092cdc8e1ae..8ee019eda32d 100644 --- a/drivers/md/dm-bio-prison-v2.c +++ b/drivers/md/dm-bio-prison-v2.c @@ -177,11 +177,10 @@ bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 **cell_result) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __get(prison, key, lock_level, inmate, cell_prealloc, cell_result); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -261,11 +260,10 @@ int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 **cell_result) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __lock(prison, key, lock_level, cell_prealloc, cell_result); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -285,11 +283,9 @@ void dm_cell_quiesce_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 *cell, struct work_struct *continuation) { - unsigned long flags; - - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); __quiesce(prison, cell, continuation); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); } EXPORT_SYMBOL_GPL(dm_cell_quiesce_v2); @@ -309,11 +305,10 @@ int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison, unsigned new_lock_level) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __promote(prison, cell, new_lock_level); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -342,11 +337,10 @@ bool dm_cell_unlock_v2(struct dm_bio_prison_v2 *prison, struct bio_list *bios) { bool r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __unlock(prison, cell, bios); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 8346e6d1816c..2d32821b3a5b 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -74,22 +74,19 @@ static bool __iot_idle_for(struct io_tracker *iot, unsigned long jifs) static bool iot_idle_for(struct io_tracker *iot, unsigned long jifs) { bool r; - unsigned long flags; - spin_lock_irqsave(&iot->lock, flags); + spin_lock_irq(&iot->lock); r = __iot_idle_for(iot, jifs); - spin_unlock_irqrestore(&iot->lock, flags); + spin_unlock_irq(&iot->lock); return r; } static void iot_io_begin(struct io_tracker *iot, sector_t len) { - unsigned long flags; - - spin_lock_irqsave(&iot->lock, flags); + spin_lock_irq(&iot->lock); iot->in_flight += len; - spin_unlock_irqrestore(&iot->lock, flags); + spin_unlock_irq(&iot->lock); } static void __iot_io_end(struct io_tracker *iot, sector_t len) @@ -172,7 +169,6 @@ static void __commit(struct work_struct *_ws) { struct batcher *b = container_of(_ws, struct batcher, commit_work); blk_status_t r; - unsigned long flags; struct list_head work_items; struct work_struct *ws, *tmp; struct continuation *k; @@ -186,12 +182,12 @@ static void __commit(struct work_struct *_ws) * We have to grab these before the commit_op to avoid a race * condition. */ - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); list_splice_init(&b->work_items, &work_items); bio_list_merge(&bios, &b->bios); bio_list_init(&b->bios); b->commit_scheduled = false; - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); r = b->commit_op(b->commit_context); @@ -238,13 +234,12 @@ static void async_commit(struct batcher *b) static void continue_after_commit(struct batcher *b, struct continuation *k) { - unsigned long flags; bool commit_scheduled; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); commit_scheduled = b->commit_scheduled; list_add_tail(&k->ws.entry, &b->work_items); - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (commit_scheduled) async_commit(b); @@ -255,13 +250,12 @@ static void continue_after_commit(struct batcher *b, struct continuation *k) */ static void issue_after_commit(struct batcher *b, struct bio *bio) { - unsigned long flags; bool commit_scheduled; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); commit_scheduled = b->commit_scheduled; bio_list_add(&b->bios, bio); - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (commit_scheduled) async_commit(b); @@ -273,12 +267,11 @@ static void issue_after_commit(struct batcher *b, struct bio *bio) static void schedule_commit(struct batcher *b) { bool immediate; - unsigned long flags; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); immediate = !list_empty(&b->work_items) || !bio_list_empty(&b->bios); b->commit_scheduled = true; - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (immediate) async_commit(b); @@ -630,23 +623,19 @@ static struct per_bio_data *init_per_bio_data(struct bio *bio) static void defer_bio(struct cache *cache, struct bio *bio) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_add(&cache->deferred_bios, bio); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); wake_deferred_bio_worker(cache); } static void defer_bios(struct cache *cache, struct bio_list *bios) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_merge(&cache->deferred_bios, bios); bio_list_init(bios); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); wake_deferred_bio_worker(cache); } @@ -756,33 +745,27 @@ static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock) static void set_discard(struct cache *cache, dm_dblock_t b) { - unsigned long flags; - BUG_ON(from_dblock(b) >= from_dblock(cache->discard_nr_blocks)); atomic_inc(&cache->stats.discard_count); - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); set_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static void clear_discard(struct cache *cache, dm_dblock_t b) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); clear_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static bool is_discarded(struct cache *cache, dm_dblock_t b) { int r; - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); r = test_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); return r; } @@ -790,12 +773,10 @@ static bool is_discarded(struct cache *cache, dm_dblock_t b) static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b) { int r; - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); r = test_bit(from_dblock(oblock_to_dblock(cache, b)), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); return r; } @@ -827,17 +808,16 @@ static void remap_to_cache(struct cache *cache, struct bio *bio, static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) { - unsigned long flags; struct per_bio_data *pb; - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); if (cache->need_tick_bio && !op_is_flush(bio->bi_opf) && bio_op(bio) != REQ_OP_DISCARD) { pb = get_per_bio_data(bio); pb->tick = true; cache->need_tick_bio = false; } - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, @@ -1889,17 +1869,16 @@ static void process_deferred_bios(struct work_struct *ws) { struct cache *cache = container_of(ws, struct cache, deferred_bio_worker); - unsigned long flags; bool commit_needed = false; struct bio_list bios; struct bio *bio; bio_list_init(&bios); - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_merge(&bios, &cache->deferred_bios); bio_list_init(&cache->deferred_bios); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); while ((bio = bio_list_pop(&bios))) { if (bio->bi_opf & REQ_PREFLUSH) diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index 6bc8c1d1c351..08c552e5e41b 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -712,7 +712,7 @@ static int __metadata_commit(struct dm_clone_metadata *cmd) static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) { int r; - unsigned long word, flags; + unsigned long word; word = 0; do { @@ -736,9 +736,9 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) return r; /* Update the changed flag */ - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); dmap->changed = 0; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); return 0; } @@ -746,7 +746,6 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) { int r = -EPERM; - unsigned long flags; struct dirty_map *dmap, *next_dmap; down_write(&cmd->lock); @@ -770,9 +769,9 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) } /* Swap dirty bitmaps */ - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); cmd->current_dmap = next_dmap; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); /* * No one is accessing the old dirty bitmap anymore, so we can flush @@ -817,9 +816,9 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, { int r = 0; struct dirty_map *dmap; - unsigned long word, region_nr, flags; + unsigned long word, region_nr; - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); if (cmd->read_only) { r = -EPERM; @@ -836,7 +835,7 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, } } out: - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); return r; } @@ -903,13 +902,11 @@ out: void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd) { - unsigned long flags; - down_write(&cmd->lock); - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); cmd->read_only = 1; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); if (!cmd->fail_io) dm_bm_set_read_only(cmd->bm); @@ -919,13 +916,11 @@ void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd) void dm_clone_metadata_set_read_write(struct dm_clone_metadata *cmd) { - unsigned long flags; - down_write(&cmd->lock); - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); cmd->read_only = 0; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); if (!cmd->fail_io) dm_bm_set_read_write(cmd->bm); diff --git a/drivers/md/dm-clone-metadata.h b/drivers/md/dm-clone-metadata.h index 434bff08508b..3fe50a781c11 100644 --- a/drivers/md/dm-clone-metadata.h +++ b/drivers/md/dm-clone-metadata.h @@ -44,7 +44,9 @@ int dm_clone_set_region_hydrated(struct dm_clone_metadata *cmd, unsigned long re * @start: Starting region number * @nr_regions: Number of regions in the range * - * This function doesn't block, so it's safe to call it from interrupt context. + * This function doesn't block, but since it uses spin_lock_irq()/spin_unlock_irq() + * it's NOT safe to call it from any context where interrupts are disabled, e.g., + * from interrupt context. */ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, unsigned long nr_regions); diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 4ca8f1977222..b3d89072d21c 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -332,8 +332,6 @@ static void submit_bios(struct bio_list *bios) */ static void issue_bio(struct clone *clone, struct bio *bio) { - unsigned long flags; - if (!bio_triggers_commit(clone, bio)) { generic_make_request(bio); return; @@ -352,9 +350,9 @@ static void issue_bio(struct clone *clone, struct bio *bio) * Batch together any bios that trigger commits and then issue a single * commit for them in process_deferred_flush_bios(). */ - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_add(&clone->deferred_flush_bios, bio); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); wake_worker(clone); } @@ -469,7 +467,7 @@ static void complete_discard_bio(struct clone *clone, struct bio *bio, bool succ static void process_discard_bio(struct clone *clone, struct bio *bio) { - unsigned long rs, re, flags; + unsigned long rs, re; bio_region_range(clone, bio, &rs, &re); BUG_ON(re > clone->nr_regions); @@ -501,9 +499,9 @@ static void process_discard_bio(struct clone *clone, struct bio *bio) /* * Defer discard processing. */ - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_add(&clone->deferred_discard_bios, bio); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); wake_worker(clone); } @@ -554,6 +552,12 @@ struct hash_table_bucket { #define bucket_unlock_irqrestore(bucket, flags) \ spin_unlock_irqrestore(&(bucket)->lock, flags) +#define bucket_lock_irq(bucket) \ + spin_lock_irq(&(bucket)->lock) + +#define bucket_unlock_irq(bucket) \ + spin_unlock_irq(&(bucket)->lock) + static int hash_table_init(struct clone *clone) { unsigned int i, sz; @@ -851,7 +855,6 @@ static void hydration_overwrite(struct dm_clone_region_hydration *hd, struct bio */ static void hydrate_bio_region(struct clone *clone, struct bio *bio) { - unsigned long flags; unsigned long region_nr; struct hash_table_bucket *bucket; struct dm_clone_region_hydration *hd, *hd2; @@ -859,19 +862,19 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) region_nr = bio_to_region(clone, bio); bucket = get_hash_table_bucket(clone, region_nr); - bucket_lock_irqsave(bucket, flags); + bucket_lock_irq(bucket); hd = __hash_find(bucket, region_nr); if (hd) { /* Someone else is hydrating the region */ bio_list_add(&hd->deferred_bios, bio); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); return; } if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) { /* The region has been hydrated */ - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); issue_bio(clone, bio); return; } @@ -880,16 +883,16 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) * We must allocate a hydration descriptor and start the hydration of * the corresponding region. */ - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); hd = alloc_hydration(clone); hydration_init(hd, region_nr); - bucket_lock_irqsave(bucket, flags); + bucket_lock_irq(bucket); /* Check if the region has been hydrated in the meantime. */ if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) { - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); free_hydration(hd); issue_bio(clone, bio); return; @@ -899,7 +902,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) if (hd2 != hd) { /* Someone else started the region's hydration. */ bio_list_add(&hd2->deferred_bios, bio); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); free_hydration(hd); return; } @@ -911,7 +914,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) */ if (unlikely(get_clone_mode(clone) >= CM_READ_ONLY)) { hlist_del(&hd->h); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); free_hydration(hd); bio_io_error(bio); return; @@ -925,11 +928,11 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) * to the destination device. */ if (is_overwrite_bio(clone, bio)) { - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); hydration_overwrite(hd, bio); } else { bio_list_add(&hd->deferred_bios, bio); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); hydration_copy(hd, 1); } } @@ -996,7 +999,6 @@ static unsigned long __start_next_hydration(struct clone *clone, unsigned long offset, struct batch_info *batch) { - unsigned long flags; struct hash_table_bucket *bucket; struct dm_clone_region_hydration *hd; unsigned long nr_regions = clone->nr_regions; @@ -1010,13 +1012,13 @@ static unsigned long __start_next_hydration(struct clone *clone, break; bucket = get_hash_table_bucket(clone, offset); - bucket_lock_irqsave(bucket, flags); + bucket_lock_irq(bucket); if (!dm_clone_is_region_hydrated(clone->cmd, offset) && !__hash_find(bucket, offset)) { hydration_init(hd, offset); __insert_region_hydration(bucket, hd); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); /* Batch hydration */ __batch_hydration(batch, hd); @@ -1024,7 +1026,7 @@ static unsigned long __start_next_hydration(struct clone *clone, return (offset + 1); } - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); } while (++offset < nr_regions); @@ -1140,13 +1142,13 @@ static void process_deferred_discards(struct clone *clone) int r = -EPERM; struct bio *bio; struct blk_plug plug; - unsigned long rs, re, flags; + unsigned long rs, re; struct bio_list discards = BIO_EMPTY_LIST; - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_merge(&discards, &clone->deferred_discard_bios); bio_list_init(&clone->deferred_discard_bios); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); if (bio_list_empty(&discards)) return; @@ -1176,13 +1178,12 @@ out: static void process_deferred_bios(struct clone *clone) { - unsigned long flags; struct bio_list bios = BIO_EMPTY_LIST; - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_merge(&bios, &clone->deferred_bios); bio_list_init(&clone->deferred_bios); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); if (bio_list_empty(&bios)) return; @@ -1193,7 +1194,6 @@ static void process_deferred_bios(struct clone *clone) static void process_deferred_flush_bios(struct clone *clone) { struct bio *bio; - unsigned long flags; struct bio_list bios = BIO_EMPTY_LIST; struct bio_list bio_completions = BIO_EMPTY_LIST; @@ -1201,13 +1201,13 @@ static void process_deferred_flush_bios(struct clone *clone) * If there are any deferred flush bios, we must commit the metadata * before issuing them or signaling their completion. */ - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_merge(&bios, &clone->deferred_flush_bios); bio_list_init(&clone->deferred_flush_bios); bio_list_merge(&bio_completions, &clone->deferred_flush_completions); bio_list_init(&clone->deferred_flush_completions); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_clone_changed_this_transaction(clone->cmd) && need_commit_due_to_time(clone))) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f87f6495652f..eb9782fc93fe 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2700,21 +2700,18 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, - 1, devname); + cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, + cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1, devname); else cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus(), devname); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c index 8288887b7f94..eb37584427a4 100644 --- a/drivers/md/dm-dust.c +++ b/drivers/md/dm-dust.c @@ -17,6 +17,7 @@ struct badblock { struct rb_node node; sector_t bb; + unsigned char wr_fail_cnt; }; struct dust_device { @@ -101,7 +102,8 @@ static int dust_remove_block(struct dust_device *dd, unsigned long long block) return 0; } -static int dust_add_block(struct dust_device *dd, unsigned long long block) +static int dust_add_block(struct dust_device *dd, unsigned long long block, + unsigned char wr_fail_cnt) { struct badblock *bblock; unsigned long flags; @@ -115,6 +117,7 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block) spin_lock_irqsave(&dd->dust_lock, flags); bblock->bb = block; + bblock->wr_fail_cnt = wr_fail_cnt; if (!dust_rb_insert(&dd->badblocklist, bblock)) { if (!dd->quiet_mode) { DMERR("%s: block %llu already in badblocklist", @@ -126,8 +129,10 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block) } dd->badblock_count++; - if (!dd->quiet_mode) - DMINFO("%s: badblock added at block %llu", __func__, block); + if (!dd->quiet_mode) { + DMINFO("%s: badblock added at block %llu with write fail count %hhu", + __func__, block, wr_fail_cnt); + } spin_unlock_irqrestore(&dd->dust_lock, flags); return 0; @@ -163,22 +168,27 @@ static int dust_map_read(struct dust_device *dd, sector_t thisblock, bool fail_read_on_bb) { unsigned long flags; - int ret = DM_MAPIO_REMAPPED; + int r = DM_MAPIO_REMAPPED; if (fail_read_on_bb) { thisblock >>= dd->sect_per_block_shift; spin_lock_irqsave(&dd->dust_lock, flags); - ret = __dust_map_read(dd, thisblock); + r = __dust_map_read(dd, thisblock); spin_unlock_irqrestore(&dd->dust_lock, flags); } - return ret; + return r; } -static void __dust_map_write(struct dust_device *dd, sector_t thisblock) +static int __dust_map_write(struct dust_device *dd, sector_t thisblock) { struct badblock *bblk = dust_rb_search(&dd->badblocklist, thisblock); + if (bblk && bblk->wr_fail_cnt > 0) { + bblk->wr_fail_cnt--; + return DM_MAPIO_KILL; + } + if (bblk) { rb_erase(&bblk->node, &dd->badblocklist); dd->badblock_count--; @@ -189,37 +199,40 @@ static void __dust_map_write(struct dust_device *dd, sector_t thisblock) (unsigned long long)thisblock); } } + + return DM_MAPIO_REMAPPED; } static int dust_map_write(struct dust_device *dd, sector_t thisblock, bool fail_read_on_bb) { unsigned long flags; + int ret = DM_MAPIO_REMAPPED; if (fail_read_on_bb) { thisblock >>= dd->sect_per_block_shift; spin_lock_irqsave(&dd->dust_lock, flags); - __dust_map_write(dd, thisblock); + ret = __dust_map_write(dd, thisblock); spin_unlock_irqrestore(&dd->dust_lock, flags); } - return DM_MAPIO_REMAPPED; + return ret; } static int dust_map(struct dm_target *ti, struct bio *bio) { struct dust_device *dd = ti->private; - int ret; + int r; bio_set_dev(bio, dd->dev->bdev); bio->bi_iter.bi_sector = dd->start + dm_target_offset(ti, bio->bi_iter.bi_sector); if (bio_data_dir(bio) == READ) - ret = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); + r = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); else - ret = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); + r = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); - return ret; + return r; } static bool __dust_clear_badblocks(struct rb_root *tree, @@ -375,8 +388,10 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv, struct dust_device *dd = ti->private; sector_t size = i_size_read(dd->dev->bdev->bd_inode) >> SECTOR_SHIFT; bool invalid_msg = false; - int result = -EINVAL; + int r = -EINVAL; unsigned long long tmp, block; + unsigned char wr_fail_cnt; + unsigned int tmp_ui; unsigned long flags; char dummy; @@ -388,45 +403,69 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv, } else if (!strcasecmp(argv[0], "disable")) { DMINFO("disabling read failures on bad sectors"); dd->fail_read_on_bb = false; - result = 0; + r = 0; } else if (!strcasecmp(argv[0], "enable")) { DMINFO("enabling read failures on bad sectors"); dd->fail_read_on_bb = true; - result = 0; + r = 0; } else if (!strcasecmp(argv[0], "countbadblocks")) { spin_lock_irqsave(&dd->dust_lock, flags); DMINFO("countbadblocks: %llu badblock(s) found", dd->badblock_count); spin_unlock_irqrestore(&dd->dust_lock, flags); - result = 0; + r = 0; } else if (!strcasecmp(argv[0], "clearbadblocks")) { - result = dust_clear_badblocks(dd); + r = dust_clear_badblocks(dd); } else if (!strcasecmp(argv[0], "quiet")) { if (!dd->quiet_mode) dd->quiet_mode = true; else dd->quiet_mode = false; - result = 0; + r = 0; } else { invalid_msg = true; } } else if (argc == 2) { if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) - return result; + return r; block = tmp; sector_div(size, dd->sect_per_block); if (block > size) { DMERR("selected block value out of range"); - return result; + return r; } if (!strcasecmp(argv[0], "addbadblock")) - result = dust_add_block(dd, block); + r = dust_add_block(dd, block, 0); else if (!strcasecmp(argv[0], "removebadblock")) - result = dust_remove_block(dd, block); + r = dust_remove_block(dd, block); else if (!strcasecmp(argv[0], "queryblock")) - result = dust_query_block(dd, block); + r = dust_query_block(dd, block); + else + invalid_msg = true; + + } else if (argc == 3) { + if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) + return r; + + if (sscanf(argv[2], "%u%c", &tmp_ui, &dummy) != 1) + return r; + + block = tmp; + if (tmp_ui > 255) { + DMERR("selected write fail count out of range"); + return r; + } + wr_fail_cnt = tmp_ui; + sector_div(size, dd->sect_per_block); + if (block > size) { + DMERR("selected block value out of range"); + return r; + } + + if (!strcasecmp(argv[0], "addbadblock")) + r = dust_add_block(dd, block, wr_fail_cnt); else invalid_msg = true; @@ -436,7 +475,7 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv, if (invalid_msg) DMERR("unrecognized message '%s' received", argv[0]); - return result; + return r; } static void dust_status(struct dm_target *ti, status_type_t type, @@ -499,12 +538,12 @@ static struct target_type dust_target = { static int __init dm_dust_init(void) { - int result = dm_register_target(&dust_target); + int r = dm_register_target(&dust_target); - if (result < 0) - DMERR("dm_register_target failed %d", result); + if (r < 0) + DMERR("dm_register_target failed %d", r); - return result; + return r; } static void __exit dm_dust_exit(void) diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 2900fbde89b3..a2cc9e45cbba 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -280,7 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio) struct flakey_c *fc = ti->private; bio_set_dev(bio, fc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector); } @@ -322,8 +322,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); pb->bio_submitted = false; - /* Do not fail reset zone */ - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) goto map_bio; /* Are we alive ? */ @@ -384,7 +383,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) return DM_ENDIO_DONE; if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { @@ -460,21 +459,15 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev } #ifdef CONFIG_BLK_DEV_ZONED -static int flakey_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +static int flakey_report_zones(struct dm_target *ti, + struct dm_report_zones_args *args, unsigned int nr_zones) { struct flakey_c *fc = ti->private; - int ret; + sector_t sector = flakey_map_sector(ti, args->next_sector); - /* Do report and remap it */ - ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector), - zones, nr_zones); - if (ret != 0) - return ret; - - if (*nr_zones) - dm_remap_zone_report(ti, fc->start, zones, nr_zones); - return 0; + args->start = fc->start; + return blkdev_report_zones(fc->dev->bdev, sector, nr_zones, + dm_report_zones_cb, args); } #endif diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index dab4446fe7d8..b225b3e445fa 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -53,6 +53,7 @@ #define SB_VERSION_1 1 #define SB_VERSION_2 2 #define SB_VERSION_3 3 +#define SB_VERSION_4 4 #define SB_SECTORS 8 #define MAX_SECTORS_PER_BLOCK 8 @@ -73,6 +74,7 @@ struct superblock { #define SB_FLAG_HAVE_JOURNAL_MAC 0x1 #define SB_FLAG_RECALCULATING 0x2 #define SB_FLAG_DIRTY_BITMAP 0x4 +#define SB_FLAG_FIXED_PADDING 0x8 #define JOURNAL_ENTRY_ROUNDUP 8 @@ -250,6 +252,7 @@ struct dm_integrity_c { bool journal_uptodate; bool just_formatted; bool recalculate_flag; + bool fix_padding; struct alg_spec internal_hash_alg; struct alg_spec journal_crypt_alg; @@ -463,7 +466,9 @@ static void wraparound_section(struct dm_integrity_c *ic, unsigned *sec_ptr) static void sb_set_version(struct dm_integrity_c *ic) { - if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP)) + if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) + ic->sb->version = SB_VERSION_4; + else if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP)) ic->sb->version = SB_VERSION_3; else if (ic->meta_dev || ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) ic->sb->version = SB_VERSION_2; @@ -2955,6 +2960,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, arg_count += !!ic->internal_hash_alg.alg_string; arg_count += !!ic->journal_crypt_alg.alg_string; arg_count += !!ic->journal_mac_alg.alg_string; + arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0; DMEMIT("%s %llu %u %c %u", ic->dev->name, (unsigned long long)ic->start, ic->tag_size, ic->mode, arg_count); if (ic->meta_dev) @@ -2974,6 +2980,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, DMEMIT(" sectors_per_bit:%llu", (unsigned long long)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit); DMEMIT(" bitmap_flush_interval:%u", jiffies_to_msecs(ic->bitmap_flush_interval)); } + if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0) + DMEMIT(" fix_padding"); #define EMIT_ALG(a, n) \ do { \ @@ -3042,8 +3050,14 @@ static int calculate_device_limits(struct dm_integrity_c *ic) if (!ic->meta_dev) { sector_t last_sector, last_area, last_offset; - ic->metadata_run = roundup((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block), - (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS)) >> SECTOR_SHIFT; + /* we have to maintain excessive padding for compatibility with existing volumes */ + __u64 metadata_run_padding = + ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING) ? + (__u64)(METADATA_PADDING_SECTORS << SECTOR_SHIFT) : + (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS); + + ic->metadata_run = round_up((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block), + metadata_run_padding) >> SECTOR_SHIFT; if (!(ic->metadata_run & (ic->metadata_run - 1))) ic->log2_metadata_run = __ffs(ic->metadata_run); else @@ -3086,6 +3100,8 @@ static int initialize_superblock(struct dm_integrity_c *ic, unsigned journal_sec journal_sections = 1; if (!ic->meta_dev) { + if (ic->fix_padding) + ic->sb->flags |= cpu_to_le32(SB_FLAG_FIXED_PADDING); ic->sb->journal_sections = cpu_to_le32(journal_sections); if (!interleave_sectors) interleave_sectors = DEFAULT_INTERLEAVE_SECTORS; @@ -3725,6 +3741,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } else if (!strcmp(opt_string, "recalculate")) { ic->recalculate_flag = true; + } else if (!strcmp(opt_string, "fix_padding")) { + ic->fix_padding = true; } else { r = -EINVAL; ti->error = "Invalid argument"; @@ -3867,7 +3885,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) should_write_sb = true; } - if (!ic->sb->version || ic->sb->version > SB_VERSION_3) { + if (!ic->sb->version || ic->sb->version > SB_VERSION_4) { r = -EINVAL; ti->error = "Unknown version"; goto bad; @@ -4182,7 +4200,7 @@ static void dm_integrity_dtr(struct dm_target *ti) static struct target_type integrity_target = { .name = "integrity", - .version = {1, 3, 0}, + .version = {1, 4, 0}, .module = THIS_MODULE, .features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY, .ctr = dm_integrity_ctr, diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index ecefe6703736..8d07fdf63a47 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -90,7 +90,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio) struct linear_c *lc = ti->private; bio_set_dev(bio, lc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = linear_map_sector(ti, bio->bi_iter.bi_sector); } @@ -136,21 +136,15 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev } #ifdef CONFIG_BLK_DEV_ZONED -static int linear_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +static int linear_report_zones(struct dm_target *ti, + struct dm_report_zones_args *args, unsigned int nr_zones) { - struct linear_c *lc = (struct linear_c *) ti->private; - int ret; - - /* Do report and remap it */ - ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector), - zones, nr_zones); - if (ret != 0) - return ret; + struct linear_c *lc = ti->private; + sector_t sector = linear_map_sector(ti, args->next_sector); - if (*nr_zones) - dm_remap_zone_report(ti, lc->start, zones, nr_zones); - return 0; + args->start = lc->start; + return blkdev_report_zones(lc->dev->bdev, sector, nr_zones, + dm_report_zones_cb, args); } #endif diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index b0aa595e4375..c412eaa975fc 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -209,6 +209,7 @@ struct raid_dev { #define RT_FLAG_RS_SUSPENDED 5 #define RT_FLAG_RS_IN_SYNC 6 #define RT_FLAG_RS_RESYNCING 7 +#define RT_FLAG_RS_GROW 8 /* Array elements of 64 bit needed for rebuild/failed disk bits */ #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8) @@ -241,6 +242,9 @@ struct raid_set { struct raid_type *raid_type; struct dm_target_callbacks callbacks; + sector_t array_sectors; + sector_t dev_sectors; + /* Optional raid4/5/6 journal device */ struct journal_dev { struct dm_dev *dev; @@ -616,7 +620,6 @@ static int raid10_format_to_md_layout(struct raid_set *rs, } else if (algorithm == ALGORITHM_RAID10_FAR) { f = copies; - r = !RAID10_OFFSET; if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) r |= RAID10_USE_FAR_SETS; @@ -1615,13 +1618,12 @@ static int _check_data_dev_sectors(struct raid_set *rs) } /* Calculate the sectors per device and per array used for @rs */ -static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev) +static int rs_set_dev_and_array_sectors(struct raid_set *rs, sector_t sectors, bool use_mddev) { int delta_disks; unsigned int data_stripes; + sector_t array_sectors = sectors, dev_sectors = sectors; struct mddev *mddev = &rs->md; - struct md_rdev *rdev; - sector_t array_sectors = rs->ti->len, dev_sectors = rs->ti->len; if (use_mddev) { delta_disks = mddev->delta_disks; @@ -1656,12 +1658,9 @@ static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev) /* Striped layouts */ array_sectors = (data_stripes + delta_disks) * dev_sectors; - rdev_for_each(rdev, mddev) - if (!test_bit(Journal, &rdev->flags)) - rdev->sectors = dev_sectors; - mddev->array_sectors = array_sectors; mddev->dev_sectors = dev_sectors; + rs_set_rdev_sectors(rs); return _check_data_dev_sectors(rs); bad: @@ -1670,7 +1669,7 @@ bad: } /* Setup recovery on @rs */ -static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) +static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) { /* raid0 does not recover */ if (rs_is_raid0(rs)) @@ -1691,22 +1690,6 @@ static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) ? MaxSector : dev_sectors; } -/* Setup recovery on @rs based on raid type, device size and 'nosync' flag */ -static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) -{ - if (!dev_sectors) - /* New raid set or 'sync' flag provided */ - __rs_setup_recovery(rs, 0); - else if (dev_sectors == MaxSector) - /* Prevent recovery */ - __rs_setup_recovery(rs, MaxSector); - else if (__rdev_sectors(rs) < dev_sectors) - /* Grown raid set */ - __rs_setup_recovery(rs, __rdev_sectors(rs)); - else - __rs_setup_recovery(rs, MaxSector); -} - static void do_table_event(struct work_struct *ws) { struct raid_set *rs = container_of(ws, struct raid_set, md.event_work); @@ -2474,7 +2457,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) return -EINVAL; } - /* Enable bitmap creation for RAID levels != 0 */ + /* Enable bitmap creation on @rs unless no metadevs or raid0 or journaled raid4/5/6 set. */ mddev->bitmap_info.offset = (rt_is_raid0(rs->raid_type) || rs->journal_dev.dev) ? 0 : to_sector(4096); mddev->bitmap_info.default_offset = mddev->bitmap_info.offset; @@ -2911,7 +2894,7 @@ static int rs_setup_reshape(struct raid_set *rs) /* Remove disk(s) */ } else if (rs->delta_disks < 0) { - r = rs_set_dev_and_array_sectors(rs, true); + r = rs_set_dev_and_array_sectors(rs, rs->ti->len, true); mddev->reshape_backwards = 1; /* removing disk(s) -> backward reshape */ /* Change layout and/or chunk size */ @@ -3008,7 +2991,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) bool resize = false; struct raid_type *rt; unsigned int num_raid_params, num_raid_devs; - sector_t calculated_dev_sectors, rdev_sectors, reshape_sectors; + sector_t sb_array_sectors, rdev_sectors, reshape_sectors; struct raid_set *rs = NULL; const char *arg; struct rs_layout rs_layout; @@ -3067,11 +3050,13 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) * * Any existing superblock will overwrite the array and device sizes */ - r = rs_set_dev_and_array_sectors(rs, false); + r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false); if (r) goto bad; - calculated_dev_sectors = rs->md.dev_sectors; + /* Memorize just calculated, potentially larger sizes to grow the raid set in preresume */ + rs->array_sectors = rs->md.array_sectors; + rs->dev_sectors = rs->md.dev_sectors; /* * Backup any new raid set level, layout, ... @@ -3084,6 +3069,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) goto bad; + /* All in-core metadata now as of current superblocks after calling analyse_superblocks() */ + sb_array_sectors = rs->md.array_sectors; rdev_sectors = __rdev_sectors(rs); if (!rdev_sectors) { ti->error = "Invalid rdev size"; @@ -3093,8 +3080,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) reshape_sectors = _get_reshape_sectors(rs); - if (calculated_dev_sectors != rdev_sectors) - resize = calculated_dev_sectors != (reshape_sectors ? rdev_sectors - reshape_sectors : rdev_sectors); + if (rs->dev_sectors != rdev_sectors) { + resize = (rs->dev_sectors != rdev_sectors - reshape_sectors); + if (rs->dev_sectors > rdev_sectors - reshape_sectors) + set_bit(RT_FLAG_RS_GROW, &rs->runtime_flags); + } INIT_WORK(&rs->md.event_work, do_table_event); ti->private = rs; @@ -3121,13 +3111,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); rs_set_new(rs); } else if (rs_is_recovering(rs)) { - /* Rebuild particular devices */ - if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { - set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - rs_setup_recovery(rs, MaxSector); - } /* A recovering raid set may be resized */ - ; /* skip setup rs */ + goto size_check; } else if (rs_is_reshaping(rs)) { /* Have to reject size change request during reshape */ if (resize) { @@ -3171,6 +3156,9 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) rs_setup_recovery(rs, MaxSector); rs_set_new(rs); } else if (rs_reshape_requested(rs)) { + /* Only request grow on raid set size extensions, not on reshapes. */ + clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags); + /* * No need to check for 'ongoing' takeover here, because takeover * is an instant operation as oposed to an ongoing reshape. @@ -3201,13 +3189,31 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) } rs_set_cur(rs); } else { +size_check: /* May not set recovery when a device rebuild is requested */ if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { - rs_setup_recovery(rs, MaxSector); + clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags); set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - } else - rs_setup_recovery(rs, test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ? - 0 : (resize ? calculated_dev_sectors : MaxSector)); + rs_setup_recovery(rs, MaxSector); + } else if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) { + /* + * Set raid set to current size, i.e. size as of + * superblocks to grow to larger size in preresume. + */ + r = rs_set_dev_and_array_sectors(rs, sb_array_sectors, false); + if (r) + goto bad; + + rs_setup_recovery(rs, rs->md.recovery_cp < rs->md.dev_sectors ? rs->md.recovery_cp : rs->md.dev_sectors); + } else { + /* This is no size change or it is shrinking, update size and record in superblocks */ + r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false); + if (r) + goto bad; + + if (sb_array_sectors > rs->array_sectors) + set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); + } rs_set_cur(rs); } @@ -3406,10 +3412,9 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev) /* Helper to return resync/reshape progress for @rs and runtime flags for raid set in sync / resynching */ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, - sector_t resync_max_sectors) + enum sync_state state, sector_t resync_max_sectors) { sector_t r; - enum sync_state state; struct mddev *mddev = &rs->md; clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); @@ -3420,8 +3425,6 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - state = decipher_sync_action(mddev, recovery); - if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery)) r = mddev->recovery_cp; else @@ -3439,18 +3442,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, /* * In case we are recovering, the array is not in sync * and health chars should show the recovering legs. + * + * Already retrieved recovery offset from curr_resync_completed above. */ ; - else if (state == st_resync) - /* - * If "resync" is occurring, the raid set - * is or may be out of sync hence the health - * characters shall be 'a'. - */ - set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - else if (state == st_reshape) + + else if (state == st_resync || state == st_reshape) /* - * If "reshape" is occurring, the raid set + * If "resync/reshape" is occurring, the raid set * is or may be out of sync hence the health * characters shall be 'a'. */ @@ -3464,22 +3463,22 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - else { - struct md_rdev *rdev; - + else if (test_bit(MD_RECOVERY_NEEDED, &recovery)) /* * We are idle and recovery is needed, prevent 'A' chars race * caused by components still set to in-sync by constructor. */ - if (test_bit(MD_RECOVERY_NEEDED, &recovery)) - set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); + set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); + else { /* - * The raid set may be doing an initial sync, or it may - * be rebuilding individual components. If all the - * devices are In_sync, then it is the raid set that is - * being initialized. + * We are idle and the raid set may be doing an initial + * sync, or it may be rebuilding individual components. + * If all the devices are In_sync, then it is the raid set + * that is being initialized. */ + struct md_rdev *rdev; + set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); rdev_for_each(rdev, mddev) if (!test_bit(Journal, &rdev->flags) && @@ -3512,7 +3511,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, unsigned int rebuild_disks; unsigned int write_mostly_params = 0; sector_t progress, resync_max_sectors, resync_mismatches; - const char *sync_action; + enum sync_state state; struct raid_type *rt; switch (type) { @@ -3526,14 +3525,14 @@ static void raid_status(struct dm_target *ti, status_type_t type, /* Access most recent mddev properties for status output */ smp_rmb(); - recovery = rs->md.recovery; /* Get sensible max sectors even if raid set not yet started */ resync_max_sectors = test_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags) ? mddev->resync_max_sectors : mddev->dev_sectors; - progress = rs_get_progress(rs, recovery, resync_max_sectors); + recovery = rs->md.recovery; + state = decipher_sync_action(mddev, recovery); + progress = rs_get_progress(rs, recovery, state, resync_max_sectors); resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ? atomic64_read(&mddev->resync_mismatches) : 0; - sync_action = sync_str(decipher_sync_action(&rs->md, recovery)); /* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */ for (i = 0; i < rs->raid_disks; i++) @@ -3561,7 +3560,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, * See Documentation/admin-guide/device-mapper/dm-raid.rst for * information on each of these states. */ - DMEMIT(" %s", sync_action); + DMEMIT(" %s", sync_str(state)); /* * v1.5.0+: @@ -3955,11 +3954,22 @@ static int raid_preresume(struct dm_target *ti) if (r) return r; - /* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */ - if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap && - mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) { - r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors, - to_bytes(rs->requested_bitmap_chunk_sectors), 0); + /* We are extending the raid set size, adjust mddev/md_rdev sizes and set capacity. */ + if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) { + mddev->array_sectors = rs->array_sectors; + mddev->dev_sectors = rs->dev_sectors; + rs_set_rdev_sectors(rs); + rs_set_capacity(rs); + } + + /* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) or grown device size */ + if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap && + (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags) || + (rs->requested_bitmap_chunk_sectors && + mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) { + int chunksize = to_bytes(rs->requested_bitmap_chunk_sectors) ?: mddev->bitmap_info.chunksize; + + r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors, chunksize, 0); if (r) DMERR("Failed to resize bitmap"); } @@ -3968,8 +3978,10 @@ static int raid_preresume(struct dm_target *ti) /* Be prepared for mddev_resume() in raid_resume() */ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) { - set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); mddev->resync_min = mddev->recovery_cp; + if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) + mddev->resync_max_sectors = mddev->dev_sectors; } /* Check for any reshape request unless new raid set */ @@ -4017,7 +4029,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 14, 0}, + .version = {1, 15, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 8547d7594338..63bbcc20f49a 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -55,19 +55,6 @@ static void trigger_event(struct work_struct *work) dm_table_event(sc->ti->table); } -static inline struct stripe_c *alloc_context(unsigned int stripes) -{ - size_t len; - - if (dm_array_too_big(sizeof(struct stripe_c), sizeof(struct stripe), - stripes)) - return NULL; - - len = sizeof(struct stripe_c) + (sizeof(struct stripe) * stripes); - - return kmalloc(len, GFP_KERNEL); -} - /* * Parse a single <dev> <sector> pair */ @@ -142,7 +129,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) return -EINVAL; } - sc = alloc_context(stripes); + sc = kmalloc(struct_size(sc, stripe, stripes), GFP_KERNEL); if (!sc) { ti->error = "Memory allocation for striped context " "failed"; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 52e049554f5c..2ae0c1913766 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -918,21 +918,15 @@ bool dm_table_supports_dax(struct dm_table *t, static bool dm_table_does_not_support_partial_completion(struct dm_table *t); -struct verify_rq_based_data { - unsigned sq_count; - unsigned mq_count; -}; - -static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - struct verify_rq_based_data *v = data; + struct block_device *bdev = dev->bdev; + struct request_queue *q = bdev_get_queue(bdev); - if (queue_is_mq(q)) - v->mq_count++; - else - v->sq_count++; + /* request-based cannot stack on partitions! */ + if (bdev != bdev->bd_contains) + return false; return queue_is_mq(q); } @@ -941,7 +935,6 @@ static int dm_table_determine_type(struct dm_table *t) { unsigned i; unsigned bio_based = 0, request_based = 0, hybrid = 0; - struct verify_rq_based_data v = {.sq_count = 0, .mq_count = 0}; struct dm_target *tgt; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); @@ -1045,14 +1038,10 @@ verify_rq_based: /* Non-request-stackable devices can't be used for request-based dm */ if (!tgt->type->iterate_devices || - !tgt->type->iterate_devices(tgt, device_is_rq_based, &v)) { + !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) { DMERR("table load rejected: including non-request-stackable devices"); return -EINVAL; } - if (v.sq_count > 0) { - DMERR("table load rejected: not all devices are blk-mq request-stackable"); - return -EINVAL; - } return 0; } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index fcd887703f95..5a2c494cb552 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -609,13 +609,12 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, blk_status_t error) { struct bio_list bios; - unsigned long flags; bio_list_init(&bios); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); __merge_bio_list(&bios, master); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); error_bio_list(&bios, error); } @@ -623,15 +622,14 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, static void requeue_deferred_cells(struct thin_c *tc) { struct pool *pool = tc->pool; - unsigned long flags; struct list_head cells; struct dm_bio_prison_cell *cell, *tmp; INIT_LIST_HEAD(&cells); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_splice_init(&tc->deferred_cells, &cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); list_for_each_entry_safe(cell, tmp, &cells, user_list) cell_requeue(pool, cell); @@ -640,14 +638,13 @@ static void requeue_deferred_cells(struct thin_c *tc) static void requeue_io(struct thin_c *tc) { struct bio_list bios; - unsigned long flags; bio_list_init(&bios); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); __merge_bio_list(&bios, &tc->deferred_bio_list); __merge_bio_list(&bios, &tc->retry_on_resume_list); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); error_bio_list(&bios, BLK_STS_DM_REQUEUE); requeue_deferred_cells(tc); @@ -756,7 +753,6 @@ static void inc_all_io_entry(struct pool *pool, struct bio *bio) static void issue(struct thin_c *tc, struct bio *bio) { struct pool *pool = tc->pool; - unsigned long flags; if (!bio_triggers_commit(tc, bio)) { generic_make_request(bio); @@ -777,9 +773,9 @@ static void issue(struct thin_c *tc, struct bio *bio) * Batch together any bios that trigger commits and then issue a * single commit for them in process_deferred_bios(). */ - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_list_add(&pool->deferred_flush_bios, bio); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); } static void remap_to_origin_and_issue(struct thin_c *tc, struct bio *bio) @@ -886,12 +882,15 @@ static void cell_defer_no_holder(struct thin_c *tc, struct dm_bio_prison_cell *c { struct pool *pool = tc->pool; unsigned long flags; + int has_work; spin_lock_irqsave(&tc->lock, flags); cell_release_no_holder(pool, cell, &tc->deferred_bio_list); + has_work = !bio_list_empty(&tc->deferred_bio_list); spin_unlock_irqrestore(&tc->lock, flags); - wake_worker(pool); + if (has_work) + wake_worker(pool); } static void thin_defer_bio(struct thin_c *tc, struct bio *bio); @@ -960,7 +959,6 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m) static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) { struct pool *pool = tc->pool; - unsigned long flags; /* * If the bio has the REQ_FUA flag set we must commit the metadata @@ -985,9 +983,9 @@ static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) * Batch together any bios that trigger commits and then issue a * single commit for them in process_deferred_bios(). */ - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_list_add(&pool->deferred_flush_completions, bio); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); } static void process_prepared_mapping(struct dm_thin_new_mapping *m) @@ -1226,14 +1224,13 @@ static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m) static void process_prepared(struct pool *pool, struct list_head *head, process_mapping_fn *fn) { - unsigned long flags; struct list_head maps; struct dm_thin_new_mapping *m, *tmp; INIT_LIST_HEAD(&maps); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); list_splice_init(head, &maps); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); list_for_each_entry_safe(m, tmp, &maps, list) (*fn)(m); @@ -1510,14 +1507,12 @@ static int commit(struct pool *pool) static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks) { - unsigned long flags; - if (free_blocks <= pool->low_water_blocks && !pool->low_water_triggered) { DMWARN("%s: reached low water mark for data device: sending event.", dm_device_name(pool->pool_md)); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->low_water_triggered = true; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); dm_table_event(pool->ti->table); } } @@ -1593,11 +1588,10 @@ static void retry_on_resume(struct bio *bio) { struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook)); struct thin_c *tc = h->tc; - unsigned long flags; - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_add(&tc->retry_on_resume_list, bio); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); } static blk_status_t should_error_unserviceable_bio(struct pool *pool) @@ -2170,7 +2164,6 @@ static void __sort_thin_deferred_bios(struct thin_c *tc) static void process_thin_deferred_bios(struct thin_c *tc) { struct pool *pool = tc->pool; - unsigned long flags; struct bio *bio; struct bio_list bios; struct blk_plug plug; @@ -2184,10 +2177,10 @@ static void process_thin_deferred_bios(struct thin_c *tc) bio_list_init(&bios); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); if (bio_list_empty(&tc->deferred_bio_list)) { - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); return; } @@ -2196,7 +2189,7 @@ static void process_thin_deferred_bios(struct thin_c *tc) bio_list_merge(&bios, &tc->deferred_bio_list); bio_list_init(&tc->deferred_bio_list); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); blk_start_plug(&plug); while ((bio = bio_list_pop(&bios))) { @@ -2206,10 +2199,10 @@ static void process_thin_deferred_bios(struct thin_c *tc) * prepared mappings to process. */ if (ensure_next_mapping(pool)) { - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_add(&tc->deferred_bio_list, bio); bio_list_merge(&tc->deferred_bio_list, &bios); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); break; } @@ -2264,16 +2257,15 @@ static unsigned sort_cells(struct pool *pool, struct list_head *cells) static void process_thin_deferred_cells(struct thin_c *tc) { struct pool *pool = tc->pool; - unsigned long flags; struct list_head cells; struct dm_bio_prison_cell *cell; unsigned i, j, count; INIT_LIST_HEAD(&cells); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_splice_init(&tc->deferred_cells, &cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); if (list_empty(&cells)) return; @@ -2294,9 +2286,9 @@ static void process_thin_deferred_cells(struct thin_c *tc) for (j = i; j < count; j++) list_add(&pool->cell_sort_array[j]->user_list, &cells); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_splice(&cells, &tc->deferred_cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); return; } @@ -2349,7 +2341,6 @@ static struct thin_c *get_next_thin(struct pool *pool, struct thin_c *tc) static void process_deferred_bios(struct pool *pool) { - unsigned long flags; struct bio *bio; struct bio_list bios, bio_completions; struct thin_c *tc; @@ -2368,13 +2359,13 @@ static void process_deferred_bios(struct pool *pool) bio_list_init(&bios); bio_list_init(&bio_completions); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_list_merge(&bios, &pool->deferred_flush_bios); bio_list_init(&pool->deferred_flush_bios); bio_list_merge(&bio_completions, &pool->deferred_flush_completions); bio_list_init(&pool->deferred_flush_completions); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool))) @@ -2657,12 +2648,11 @@ static void metadata_operation_failed(struct pool *pool, const char *op, int r) */ static void thin_defer_bio(struct thin_c *tc, struct bio *bio) { - unsigned long flags; struct pool *pool = tc->pool; - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_add(&tc->deferred_bio_list, bio); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); wake_worker(pool); } @@ -2678,13 +2668,12 @@ static void thin_defer_bio_with_throttle(struct thin_c *tc, struct bio *bio) static void thin_defer_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell) { - unsigned long flags; struct pool *pool = tc->pool; throttle_lock(&pool->throttle); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_add_tail(&cell->user_list, &tc->deferred_cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); throttle_unlock(&pool->throttle); wake_worker(pool); @@ -2810,15 +2799,14 @@ static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits) static void requeue_bios(struct pool *pool) { - unsigned long flags; struct thin_c *tc; rcu_read_lock(); list_for_each_entry_rcu(tc, &pool->active_thins, list) { - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_merge(&tc->deferred_bio_list, &tc->retry_on_resume_list); bio_list_init(&tc->retry_on_resume_list); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); } rcu_read_unlock(); } @@ -3412,15 +3400,14 @@ static int pool_map(struct dm_target *ti, struct bio *bio) int r; struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; /* * As this is a singleton target, ti->begin is always zero. */ - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_set_dev(bio, pt->data_dev->bdev); r = DM_MAPIO_REMAPPED; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); return r; } @@ -3591,7 +3578,6 @@ static void pool_resume(struct dm_target *ti) { struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; /* * Must requeue active_thins' bios and then resume @@ -3600,10 +3586,10 @@ static void pool_resume(struct dm_target *ti) requeue_bios(pool); pool_resume_active_thins(pool); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->low_water_triggered = false; pool->suspended = false; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); do_waker(&pool->waker.work); } @@ -3612,11 +3598,10 @@ static void pool_presuspend(struct dm_target *ti) { struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->suspended = true; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); pool_suspend_active_thins(pool); } @@ -3625,13 +3610,12 @@ static void pool_presuspend_undo(struct dm_target *ti) { struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; pool_resume_active_thins(pool); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->suspended = false; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); } static void pool_postsuspend(struct dm_target *ti) @@ -4110,11 +4094,10 @@ static void thin_put(struct thin_c *tc) static void thin_dtr(struct dm_target *ti) { struct thin_c *tc = ti->private; - unsigned long flags; - spin_lock_irqsave(&tc->pool->lock, flags); + spin_lock_irq(&tc->pool->lock); list_del_rcu(&tc->list); - spin_unlock_irqrestore(&tc->pool->lock, flags); + spin_unlock_irq(&tc->pool->lock); synchronize_rcu(); thin_put(tc); @@ -4150,7 +4133,6 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) struct thin_c *tc; struct dm_dev *pool_dev, *origin_dev; struct mapped_device *pool_md; - unsigned long flags; mutex_lock(&dm_thin_pool_table.mutex); @@ -4244,9 +4226,9 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) mutex_unlock(&dm_thin_pool_table.mutex); - spin_lock_irqsave(&tc->pool->lock, flags); + spin_lock_irq(&tc->pool->lock); if (tc->pool->suspended) { - spin_unlock_irqrestore(&tc->pool->lock, flags); + spin_unlock_irq(&tc->pool->lock); mutex_lock(&dm_thin_pool_table.mutex); /* reacquire for __pool_dec */ ti->error = "Unable to activate thin device while pool is suspended"; r = -EINVAL; @@ -4255,7 +4237,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) refcount_set(&tc->refcount, 1); init_completion(&tc->can_destroy); list_add_tail_rcu(&tc->list, &tc->pool->active_thins); - spin_unlock_irqrestore(&tc->pool->lock, flags); + spin_unlock_irq(&tc->pool->lock); /* * This synchronize_rcu() call is needed here otherwise we risk a * wake_worker() call finding no bios to process (because the newly diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index d06b8aa41e26..7d727a72aa13 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1218,7 +1218,8 @@ bio_copy: } } while (bio->bi_iter.bi_size); - if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) + if (unlikely(bio->bi_opf & REQ_FUA || + wc->uncommitted_blocks >= wc->autocommit_blocks)) writecache_flush(wc); else writecache_schedule_autocommit(wc); @@ -1561,7 +1562,7 @@ static void writecache_writeback(struct work_struct *work) { struct dm_writecache *wc = container_of(work, struct dm_writecache, writeback_work); struct blk_plug plug; - struct wc_entry *f, *g, *e = NULL; + struct wc_entry *f, *uninitialized_var(g), *e = NULL; struct rb_node *node, *next_node; struct list_head skipped; struct writeback_list wbl; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 595a73110e17..22b3cb0050a7 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -554,6 +554,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { dmz_release_mblock(zmd, mblk); + dmz_check_bdev(zmd->dev); return ERR_PTR(-EIO); } @@ -625,6 +626,8 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, ret = submit_bio_wait(bio); bio_put(bio); + if (ret) + dmz_check_bdev(zmd->dev); return ret; } @@ -691,6 +694,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { clear_bit(DMZ_META_ERROR, &mblk->state); + dmz_check_bdev(zmd->dev); ret = -EIO; } nr_mblks_submitted--; @@ -768,7 +772,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) /* If there are no dirty metadata blocks, just flush the device cache */ if (list_empty(&write_list)) { ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO, NULL); - goto out; + goto err; } /* @@ -778,7 +782,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_log_dirty_mblocks(zmd, &write_list); if (ret) - goto out; + goto err; /* * The log is on disk. It is now safe to update in place @@ -786,11 +790,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary); if (ret) - goto out; + goto err; ret = dmz_write_sb(zmd, zmd->mblk_primary); if (ret) - goto out; + goto err; while (!list_empty(&write_list)) { mblk = list_first_entry(&write_list, struct dmz_mblock, link); @@ -805,16 +809,20 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) zmd->sb_gen++; out: - if (ret && !list_empty(&write_list)) { - spin_lock(&zmd->mblk_lock); - list_splice(&write_list, &zmd->mblk_dirty_list); - spin_unlock(&zmd->mblk_lock); - } - dmz_unlock_flush(zmd); up_write(&zmd->mblk_sem); return ret; + +err: + if (!list_empty(&write_list)) { + spin_lock(&zmd->mblk_lock); + list_splice(&write_list, &zmd->mblk_dirty_list); + spin_unlock(&zmd->mblk_lock); + } + if (!dmz_check_bdev(zmd->dev)) + ret = -EIO; + goto out; } /* @@ -1080,9 +1088,10 @@ static int dmz_load_sb(struct dmz_metadata *zmd) /* * Initialize a zone descriptor. */ -static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone, - struct blk_zone *blkz) +static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data) { + struct dmz_metadata *zmd = data; + struct dm_zone *zone = &zmd->zones[idx]; struct dmz_dev *dev = zmd->dev; /* Ignore the eventual last runt (smaller) zone */ @@ -1096,26 +1105,29 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone, atomic_set(&zone->refcount, 0); zone->chunk = DMZ_MAP_UNMAPPED; - if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) { + switch (blkz->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: set_bit(DMZ_RND, &zone->flags); zmd->nr_rnd_zones++; - } else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ || - blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) { + break; + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: set_bit(DMZ_SEQ, &zone->flags); - } else + break; + default: return -ENXIO; - - if (blkz->cond == BLK_ZONE_COND_OFFLINE) - set_bit(DMZ_OFFLINE, &zone->flags); - else if (blkz->cond == BLK_ZONE_COND_READONLY) - set_bit(DMZ_READ_ONLY, &zone->flags); + } if (dmz_is_rnd(zone)) zone->wp_block = 0; else zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start); - if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) { + if (blkz->cond == BLK_ZONE_COND_OFFLINE) + set_bit(DMZ_OFFLINE, &zone->flags); + else if (blkz->cond == BLK_ZONE_COND_READONLY) + set_bit(DMZ_READ_ONLY, &zone->flags); + else { zmd->nr_useable_zones++; if (dmz_is_rnd(zone)) { zmd->nr_rnd_zones++; @@ -1139,23 +1151,13 @@ static void dmz_drop_zones(struct dmz_metadata *zmd) } /* - * The size of a zone report in number of zones. - * This results in 4096*64B=256KB report zones commands. - */ -#define DMZ_REPORT_NR_ZONES 4096 - -/* * Allocate and initialize zone descriptors using the zone * information from disk. */ static int dmz_init_zones(struct dmz_metadata *zmd) { struct dmz_dev *dev = zmd->dev; - struct dm_zone *zone; - struct blk_zone *blkz; - unsigned int nr_blkz; - sector_t sector = 0; - int i, ret = 0; + int ret; /* Init */ zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3; @@ -1169,54 +1171,38 @@ static int dmz_init_zones(struct dmz_metadata *zmd) dmz_dev_info(dev, "Using %zu B for zone information", sizeof(struct dm_zone) * dev->nr_zones); - /* Get zone information */ - nr_blkz = DMZ_REPORT_NR_ZONES; - blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL); - if (!blkz) { - ret = -ENOMEM; - goto out; - } - /* - * Get zone information and initialize zone descriptors. - * At the same time, determine where the super block - * should be: first block of the first randomly writable - * zone. + * Get zone information and initialize zone descriptors. At the same + * time, determine where the super block should be: first block of the + * first randomly writable zone. */ - zone = zmd->zones; - while (sector < dev->capacity) { - /* Get zone information */ - nr_blkz = DMZ_REPORT_NR_ZONES; - ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz); - if (ret) { - dmz_dev_err(dev, "Report zones failed %d", ret); - goto out; - } + ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone, + zmd); + if (ret < 0) { + dmz_drop_zones(zmd); + return ret; + } - if (!nr_blkz) - break; + return 0; +} - /* Process report */ - for (i = 0; i < nr_blkz; i++) { - ret = dmz_init_zone(zmd, zone, &blkz[i]); - if (ret) - goto out; - sector += dev->zone_nr_sectors; - zone++; - } - } +static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx, + void *data) +{ + struct dm_zone *zone = data; - /* The entire zone configuration of the disk should now be known */ - if (sector < dev->capacity) { - dmz_dev_err(dev, "Failed to get correct zone information"); - ret = -ENXIO; - } -out: - kfree(blkz); - if (ret) - dmz_drop_zones(zmd); + clear_bit(DMZ_OFFLINE, &zone->flags); + clear_bit(DMZ_READ_ONLY, &zone->flags); + if (blkz->cond == BLK_ZONE_COND_OFFLINE) + set_bit(DMZ_OFFLINE, &zone->flags); + else if (blkz->cond == BLK_ZONE_COND_READONLY) + set_bit(DMZ_READ_ONLY, &zone->flags); - return ret; + if (dmz_is_seq(zone)) + zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start); + else + zone->wp_block = 0; + return 0; } /* @@ -1224,9 +1210,7 @@ out: */ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) { - unsigned int nr_blkz = 1; unsigned int noio_flag; - struct blk_zone blkz; int ret; /* @@ -1236,29 +1220,19 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) * GFP_NOIO was specified. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), - &blkz, &nr_blkz); + ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1, + dmz_update_zone_cb, zone); memalloc_noio_restore(noio_flag); - if (!nr_blkz) + + if (ret == 0) ret = -EIO; - if (ret) { + if (ret < 0) { dmz_dev_err(zmd->dev, "Get zone %u report failed", dmz_id(zmd, zone)); + dmz_check_bdev(zmd->dev); return ret; } - clear_bit(DMZ_OFFLINE, &zone->flags); - clear_bit(DMZ_READ_ONLY, &zone->flags); - if (blkz.cond == BLK_ZONE_COND_OFFLINE) - set_bit(DMZ_OFFLINE, &zone->flags); - else if (blkz.cond == BLK_ZONE_COND_READONLY) - set_bit(DMZ_READ_ONLY, &zone->flags); - - if (dmz_is_seq(zone)) - zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start); - else - zone->wp_block = 0; - return 0; } @@ -1312,9 +1286,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone) if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) { struct dmz_dev *dev = zmd->dev; - ret = blkdev_reset_zones(dev->bdev, - dmz_start_sect(zmd, zone), - dev->zone_nr_sectors, GFP_NOIO); + ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET, + dmz_start_sect(zmd, zone), + dev->zone_nr_sectors, GFP_NOIO); if (ret) { dmz_dev_err(dev, "Reset zone %u failed %d", dmz_id(zmd, zone), ret); diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index d240d7ca8a8a..e7ace908a9b7 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -82,6 +82,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", dmz_id(zmd, zone), (unsigned long long)wp_block, (unsigned long long)block, nr_blocks, ret); + dmz_check_bdev(zrc->dev); return ret; } @@ -489,12 +490,7 @@ static void dmz_reclaim_work(struct work_struct *work) ret = dmz_do_reclaim(zrc); if (ret) { dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret); - if (ret == -EIO) - /* - * LLD might be performing some error handling sequence - * at the underlying device. To not interfere, do not - * attempt to schedule the next reclaim run immediately. - */ + if (!dmz_check_bdev(zrc->dev)) return; } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index d3bcc4197f5d..4574e0dedbd6 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -80,6 +80,8 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) bio->bi_status = status; + if (bio->bi_status != BLK_STS_OK) + bioctx->target->dev->flags |= DMZ_CHECK_BDEV; if (refcount_dec_and_test(&bioctx->ref)) { struct dm_zone *zone = bioctx->zone; @@ -565,32 +567,52 @@ out: } /* - * Check the backing device availability. If it's on the way out, + * Check if the backing device is being removed. If it's on the way out, * start failing I/O. Reclaim and metadata components also call this * function to cleanly abort operation in the event of such failure. */ bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev) { - struct gendisk *disk; + if (dmz_dev->flags & DMZ_BDEV_DYING) + return true; - if (!(dmz_dev->flags & DMZ_BDEV_DYING)) { - disk = dmz_dev->bdev->bd_disk; - if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { - dmz_dev_warn(dmz_dev, "Backing device queue dying"); - dmz_dev->flags |= DMZ_BDEV_DYING; - } else if (disk->fops->check_events) { - if (disk->fops->check_events(disk, 0) & - DISK_EVENT_MEDIA_CHANGE) { - dmz_dev_warn(dmz_dev, "Backing device offline"); - dmz_dev->flags |= DMZ_BDEV_DYING; - } - } + if (dmz_dev->flags & DMZ_CHECK_BDEV) + return !dmz_check_bdev(dmz_dev); + + if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { + dmz_dev_warn(dmz_dev, "Backing device queue dying"); + dmz_dev->flags |= DMZ_BDEV_DYING; } return dmz_dev->flags & DMZ_BDEV_DYING; } /* + * Check the backing device availability. This detects such events as + * backing device going offline due to errors, media removals, etc. + * This check is less efficient than dmz_bdev_is_dying() and should + * only be performed as a part of error handling. + */ +bool dmz_check_bdev(struct dmz_dev *dmz_dev) +{ + struct gendisk *disk; + + dmz_dev->flags &= ~DMZ_CHECK_BDEV; + + if (dmz_bdev_is_dying(dmz_dev)) + return false; + + disk = dmz_dev->bdev->bd_disk; + if (disk->fops->check_events && + disk->fops->check_events(disk, 0) & DISK_EVENT_MEDIA_CHANGE) { + dmz_dev_warn(dmz_dev, "Backing device offline"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } + + return !(dmz_dev->flags & DMZ_BDEV_DYING); +} + +/* * Process a new BIO. */ static int dmz_map(struct dm_target *ti, struct bio *bio) @@ -902,8 +924,8 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) { struct dmz_target *dmz = ti->private; - if (dmz_bdev_is_dying(dmz->dev)) - return -ENODEV; + if (!dmz_check_bdev(dmz->dev)) + return -EIO; *bdev = dmz->dev->bdev; diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h index d8e70b0ade35..5b5e493d479c 100644 --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -72,6 +72,7 @@ struct dmz_dev { /* Device flags. */ #define DMZ_BDEV_DYING (1 << 0) +#define DMZ_CHECK_BDEV (2 << 0) /* * Zone descriptor. @@ -255,5 +256,6 @@ void dmz_schedule_reclaim(struct dmz_reclaim *zrc); * Functions defined in dm-zoned-target.c */ bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev); +bool dmz_check_bdev(struct dmz_dev *dmz_dev); #endif /* DM_ZONED_H */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1a5e328c443a..e8f9661a10a1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -440,14 +440,48 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } +#ifdef CONFIG_BLK_DEV_ZONED +int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data) +{ + struct dm_report_zones_args *args = data; + sector_t sector_diff = args->tgt->begin - args->start; + + /* + * Ignore zones beyond the target range. + */ + if (zone->start >= args->start + args->tgt->len) + return 0; + + /* + * Remap the start sector and write pointer position of the zone + * to match its position in the target range. + */ + zone->start += sector_diff; + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { + if (zone->cond == BLK_ZONE_COND_FULL) + zone->wp = zone->start + zone->len; + else if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->wp = zone->start; + else + zone->wp += sector_diff; + } + + args->next_sector = zone->start + zone->len; + return args->orig_cb(zone, args->zone_idx++, args->orig_data); +} +EXPORT_SYMBOL_GPL(dm_report_zones_cb); + static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { -#ifdef CONFIG_BLK_DEV_ZONED struct mapped_device *md = disk->private_data; - struct dm_target *tgt; struct dm_table *map; int srcu_idx, ret; + struct dm_report_zones_args args = { + .next_sector = sector, + .orig_data = data, + .orig_cb = cb, + }; if (dm_suspended_md(md)) return -EAGAIN; @@ -456,38 +490,30 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, if (!map) return -EIO; - tgt = dm_table_find_target(map, sector); - if (!tgt) { - ret = -EIO; - goto out; - } + do { + struct dm_target *tgt; - /* - * If we are executing this, we already know that the block device - * is a zoned device and so each target should have support for that - * type of drive. A missing report_zones method means that the target - * driver has a problem. - */ - if (WARN_ON(!tgt->type->report_zones)) { - ret = -EIO; - goto out; - } + tgt = dm_table_find_target(map, args.next_sector); + if (WARN_ON_ONCE(!tgt->type->report_zones)) { + ret = -EIO; + goto out; + } - /* - * blkdev_report_zones() will loop and call this again to cover all the - * zones of the target, eventually moving on to the next target. - * So there is no need to loop here trying to fill the entire array - * of zones. - */ - ret = tgt->type->report_zones(tgt, sector, zones, nr_zones); + args.tgt = tgt; + ret = tgt->type->report_zones(tgt, &args, nr_zones); + if (ret < 0) + goto out; + } while (args.zone_idx < nr_zones && + args.next_sector < get_capacity(disk)); + ret = args.zone_idx; out: dm_put_live_table(md, srcu_idx); return ret; -#else - return -ENOTSUPP; -#endif } +#else +#define dm_blk_report_zones NULL +#endif /* CONFIG_BLK_DEV_ZONED */ static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) @@ -1174,7 +1200,8 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, /* * A target may call dm_accept_partial_bio only from the map routine. It is - * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET. + * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET, + * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH. * * dm_accept_partial_bio informs the dm that the target only wants to process * additional n_sectors sectors of the bio and the rest of the data should be @@ -1212,54 +1239,6 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) } EXPORT_SYMBOL_GPL(dm_accept_partial_bio); -/* - * The zone descriptors obtained with a zone report indicate - * zone positions within the underlying device of the target. The zone - * descriptors must be remapped to match their position within the dm device. - * The caller target should obtain the zones information using - * blkdev_report_zones() to ensure that remapping for partition offset is - * already handled. - */ -void dm_remap_zone_report(struct dm_target *ti, sector_t start, - struct blk_zone *zones, unsigned int *nr_zones) -{ -#ifdef CONFIG_BLK_DEV_ZONED - struct blk_zone *zone; - unsigned int nrz = *nr_zones; - int i; - - /* - * Remap the start sector and write pointer position of the zones in - * the array. Since we may have obtained from the target underlying - * device more zones that the target size, also adjust the number - * of zones. - */ - for (i = 0; i < nrz; i++) { - zone = zones + i; - if (zone->start >= start + ti->len) { - memset(zone, 0, sizeof(struct blk_zone) * (nrz - i)); - break; - } - - zone->start = zone->start + ti->begin - start; - if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) - continue; - - if (zone->cond == BLK_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; - else if (zone->cond == BLK_ZONE_COND_EMPTY) - zone->wp = zone->start; - else - zone->wp = zone->wp + ti->begin - start; - } - - *nr_zones = i; -#else /* !CONFIG_BLK_DEV_ZONED */ - *nr_zones = 0; -#endif -} -EXPORT_SYMBOL_GPL(dm_remap_zone_report); - static blk_qc_t __map_bio(struct dm_target_io *tio) { int r; @@ -1627,7 +1606,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, ci.sector_count = 0; error = __send_empty_flush(&ci); /* dec_pending submits any data associated with flush */ - } else if (bio_op(bio) == REQ_OP_ZONE_RESET) { + } else if (op_is_zone_mgmt(bio_op(bio))) { ci.bio = bio; ci.sector_count = 0; error = __split_and_process_non_flush(&ci); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index b092c7b5282f..3ad18246fcb3 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, memcpy(page_address(store.sb_page), page_address(bitmap->storage.sb_page), sizeof(bitmap_super_t)); + spin_lock_irq(&bitmap->counts.lock); md_bitmap_file_unmap(&bitmap->storage); bitmap->storage = store; @@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, blocks = min(old_counts.chunks << old_counts.chunkshift, chunks << chunkshift); - spin_lock_irq(&bitmap->counts.lock); /* For cluster raid, need to pre-allocate bitmap */ if (mddev_is_clustered(bitmap->mddev)) { unsigned long page; diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index c766c559d36d..26c75c0199fa 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) sector_t start_sector, end_sector, data_offset; sector_t bio_sector = bio->bi_iter.bi_sector; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } tmp_dev = which_dev(mddev, bio_sector); start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 6780938d2991..152f9e65a226 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } mp_bh = mempool_alloc(&conf->pool, GFP_NOIO); diff --git a/drivers/md/md.c b/drivers/md/md.c index 1be7abeb24fd..805b33e27496 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws) } } -void md_flush_request(struct mddev *mddev, struct bio *bio) +/* + * Manages consolidation of flushes and submitting any flushes needed for + * a bio with REQ_PREFLUSH. Returns true if the bio is finished or is + * being finished in another context. Returns false if the flushing is + * complete but still needs the I/O portion of the bio to be processed. + */ +bool md_flush_request(struct mddev *mddev, struct bio *bio) { ktime_t start = ktime_get_boottime(); spin_lock_irq(&mddev->lock); @@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + return false; } } + return true; } EXPORT_SYMBOL(md_flush_request); @@ -1098,6 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; mdp_super_t *sb; int ret; + bool spare_disk = true; /* * Calculate the position of the superblock (512byte sectors), @@ -1148,8 +1156,18 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor else rdev->desc_nr = sb->this_disk.number; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == LEVEL_MULTIPATH || + (rdev->desc_nr >= 0 && + sb->disks[rdev->desc_nr].state & + ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))) + spare_disk = false; + if (!refdev) { - ret = 1; + if (!spare_disk) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; mdp_super_t *refsb = page_address(refdev->sb_page); @@ -1165,7 +1183,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor } ev1 = md_event(sb); ev2 = md_event(refsb); - if (ev1 > ev2) + + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -1525,6 +1544,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sector_t sectors; char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; int bmask; + bool spare_disk = true; /* * Calculate the position of the superblock in 512byte sectors. @@ -1658,8 +1678,19 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sb->level != 0) return -EINVAL; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) || + (rdev->desc_nr >= 0 && + rdev->desc_nr < le32_to_cpu(sb->max_dev) && + (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || + le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))) + spare_disk = false; + if (!refdev) { - ret = 1; + if (!spare_disk) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; struct mdp_superblock_1 *refsb = page_address(refdev->sb_page); @@ -1676,7 +1707,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ ev1 = le64_to_cpu(sb->events); ev2 = le64_to_cpu(refsb->events); - if (ev1 > ev2) + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -3597,7 +3628,7 @@ abort_free: * Check a full RAID array for plausibility */ -static void analyze_sbs(struct mddev *mddev) +static int analyze_sbs(struct mddev *mddev) { int i; struct md_rdev *rdev, *freshest, *tmp; @@ -3618,6 +3649,12 @@ static void analyze_sbs(struct mddev *mddev) md_kick_rdev_from_array(rdev); } + /* Cannot find a valid fresh disk */ + if (!freshest) { + pr_warn("md: cannot find a valid disk\n"); + return -EINVAL; + } + super_types[mddev->major_version]. validate_super(mddev, freshest); @@ -3652,6 +3689,8 @@ static void analyze_sbs(struct mddev *mddev) clear_bit(In_sync, &rdev->flags); } } + + return 0; } /* Read a fixed-point number. @@ -5570,7 +5609,9 @@ int md_run(struct mddev *mddev) if (!mddev->raid_disks) { if (!mddev->persistent) return -EINVAL; - analyze_sbs(mddev); + err = analyze_sbs(mddev); + if (err) + return -EINVAL; } if (mddev->level != LEVEL_NONE) diff --git a/drivers/md/md.h b/drivers/md/md.h index c5e3ff398b59..5f86f8adb0a4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -550,7 +550,7 @@ struct md_personality int level; struct list_head list; struct module *owner; - bool (*make_request)(struct mddev *mddev, struct bio *bio); + bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio); /* * start up works that do NOT require md_thread. tasks that * requires md_thread should go into start() @@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); extern int mddev_congested(struct mddev *mddev, int bits); -extern void md_flush_request(struct mddev *mddev, struct bio *bio); +extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); extern int md_super_wait(struct mddev *mddev); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 1e772287b1c8..b7c20979bd19 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) unsigned chunk_sects; unsigned sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) { raid0_handle_discard(mddev, bio); @@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) tmp_dev = map_sector(mddev, zone, sector, §or); break; default: - WARN("md/raid0:%s: Invalid layout\n", mdname(mddev)); + WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); bio_io_error(bio); return true; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0466ee2453b4..a409ab6f30bc 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -819,6 +819,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio) else generic_make_request(bio); bio = next; + cond_resched(); } } @@ -1567,10 +1568,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio) { sector_t sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } /* * There is a limit to the maximum size, but diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 299c7b1c9718..ec136e44aef7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -191,7 +191,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) out_free_pages: while (--j >= 0) - resync_free_pages(&rps[j * 2]); + resync_free_pages(&rps[j]); j = 0; out_free_bio: @@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) int chunk_sects = chunk_mask + 1; int sectors = bio_sectors(bio); - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (!md_write_start(mddev, bio)) return false; diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 18a4064a61a8..cab5b1352892 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1404,7 +1404,7 @@ int ppl_init_log(struct r5conf *conf) atomic64_set(&ppl_conf->seq, 0); INIT_LIST_HEAD(&ppl_conf->no_mem_stripes); spin_lock_init(&ppl_conf->no_mem_stripes_lock); - ppl_conf->write_hint = RWF_WRITE_LIFE_NOT_SET; + ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET; if (!mddev->external) { ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid)); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 223e97ab27e6..f0fc538bfe59 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1134,7 +1134,7 @@ again: bi->bi_iter.bi_size = STRIPE_SIZE; bi->bi_write_hint = sh->dev[i].write_hint; if (!rrdev) - sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET; + sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -1187,7 +1187,7 @@ again: rbi->bi_io_vec[0].bv_offset = 0; rbi->bi_iter.bi_size = STRIPE_SIZE; rbi->bi_write_hint = sh->dev[i].write_hint; - sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET; + sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (ret == 0) return true; if (ret == -ENODEV) { - md_flush_request(mddev, bi); - return true; + if (md_flush_request(mddev, bi)) + return true; } /* ret == -EAGAIN, fallback */ /* diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c index e7d1920729fb..0ae986c42bc8 100644 --- a/drivers/mmc/host/sdhci-of-at91.c +++ b/drivers/mmc/host/sdhci-of-at91.c @@ -358,7 +358,7 @@ static int sdhci_at91_probe(struct platform_device *pdev) pm_runtime_use_autosuspend(&pdev->dev); /* HS200 is broken at this moment */ - host->quirks2 = SDHCI_QUIRK2_BROKEN_HS200; + host->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200; ret = sdhci_add_host(host); if (ret) diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c index 79a53cb8507b..00a79489067c 100644 --- a/drivers/mtd/chips/cfi_cmdset_0001.c +++ b/drivers/mtd/chips/cfi_cmdset_0001.c @@ -1353,7 +1353,7 @@ static int do_point_onechip (struct map_info *map, struct flchip *chip, loff_t a { unsigned long cmd_addr; struct cfi_private *cfi = map->fldrv_priv; - int ret = 0; + int ret; adr += chip->start; @@ -1383,7 +1383,7 @@ static int cfi_intelext_point(struct mtd_info *mtd, loff_t from, size_t len, struct cfi_private *cfi = map->fldrv_priv; unsigned long ofs, last_end = 0; int chipnum; - int ret = 0; + int ret; if (!map->virt) return -EINVAL; @@ -1550,7 +1550,7 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip, { struct cfi_private *cfi = map->fldrv_priv; map_word status, write_cmd; - int ret=0; + int ret; adr += chip->start; @@ -1624,7 +1624,7 @@ static int cfi_intelext_write_words (struct mtd_info *mtd, loff_t to , size_t le { struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; - int ret = 0; + int ret; int chipnum; unsigned long ofs; @@ -1871,7 +1871,7 @@ static int cfi_intelext_writev (struct mtd_info *mtd, const struct kvec *vecs, struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize; - int ret = 0; + int ret; int chipnum; unsigned long ofs, vec_seek, i; size_t len = 0; diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c index cf8c8be40a9c..04b383bc3947 100644 --- a/drivers/mtd/chips/cfi_cmdset_0002.c +++ b/drivers/mtd/chips/cfi_cmdset_0002.c @@ -123,19 +123,23 @@ static int cfi_use_status_reg(struct cfi_private *cfi) (extp->SoftwareFeatures & poll_mask) == CFI_POLL_STATUS_REG; } -static void cfi_check_err_status(struct map_info *map, struct flchip *chip, - unsigned long adr) +static int cfi_check_err_status(struct map_info *map, struct flchip *chip, + unsigned long adr) { struct cfi_private *cfi = map->fldrv_priv; map_word status; if (!cfi_use_status_reg(cfi)) - return; + return 0; cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi, cfi->device_type, NULL); status = map_read(map, adr); + /* The error bits are invalid while the chip's busy */ + if (!map_word_bitsset(map, status, CMD(CFI_SR_DRB))) + return 0; + if (map_word_bitsset(map, status, CMD(0x3a))) { unsigned long chipstatus = MERGESTATUS(status); @@ -151,7 +155,12 @@ static void cfi_check_err_status(struct map_info *map, struct flchip *chip, if (chipstatus & CFI_SR_SLSB) pr_err("%s sector write protected, status %lx\n", map->name, chipstatus); + + /* Erase/Program status bits are set on the operation failure */ + if (chipstatus & (CFI_SR_ESB | CFI_SR_PSB)) + return 1; } + return 0; } /* #define DEBUG_CFI_FEATURES */ @@ -785,7 +794,6 @@ static struct mtd_info *cfi_amdstd_setup(struct mtd_info *mtd) kfree(mtd->eraseregions); kfree(mtd); kfree(cfi->cmdset_priv); - kfree(cfi->cfiq); return NULL; } @@ -848,20 +856,16 @@ static int __xipram chip_good(struct map_info *map, struct flchip *chip, if (cfi_use_status_reg(cfi)) { map_word ready = CMD(CFI_SR_DRB); - map_word err = CMD(CFI_SR_PSB | CFI_SR_ESB); + /* * For chips that support status register, check device - * ready bit and Erase/Program status bit to know if - * operation succeeded. + * ready bit */ cfi_send_gen_cmd(0x70, cfi->addr_unlock1, chip->start, map, cfi, cfi->device_type, NULL); curd = map_read(map, addr); - if (map_word_andequal(map, curd, ready, ready)) - return !map_word_bitsset(map, curd, err); - - return 0; + return map_word_andequal(map, curd, ready, ready); } oldd = map_read(map, addr); @@ -1699,8 +1703,11 @@ static int __xipram do_write_oneword_once(struct map_info *map, break; } - if (chip_good(map, chip, adr, datum)) + if (chip_good(map, chip, adr, datum)) { + if (cfi_check_err_status(map, chip, adr)) + ret = -EIO; break; + } /* Latency issues. Drop the lock, wait a while and retry */ UDELAY(map, chip, adr, 1); @@ -1713,7 +1720,7 @@ static int __xipram do_write_oneword_start(struct map_info *map, struct flchip *chip, unsigned long adr, int mode) { - int ret = 0; + int ret; mutex_lock(&chip->mutex); @@ -1773,7 +1780,6 @@ static int __xipram do_write_oneword_retry(struct map_info *map, ret = do_write_oneword_once(map, chip, adr, datum, mode, cfi); if (ret) { /* reset on all failures. */ - cfi_check_err_status(map, chip, adr); map_write(map, CMD(0xF0), chip->start); /* FIXME - should have reset delay before continuing */ @@ -1791,7 +1797,7 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip, unsigned long adr, map_word datum, int mode) { - int ret = 0; + int ret; adr += chip->start; @@ -1815,7 +1821,7 @@ static int cfi_amdstd_write_words(struct mtd_info *mtd, loff_t to, size_t len, { struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; - int ret = 0; + int ret; int chipnum; unsigned long ofs, chipstart; DECLARE_WAITQUEUE(wait, current); @@ -1970,12 +1976,17 @@ static int __xipram do_write_buffer_wait(struct map_info *map, */ if (time_after(jiffies, timeo) && !chip_good(map, chip, adr, datum)) { + pr_err("MTD %s(): software timeout, address:0x%.8lx.\n", + __func__, adr); ret = -EIO; break; } - if (chip_good(map, chip, adr, datum)) + if (chip_good(map, chip, adr, datum)) { + if (cfi_check_err_status(map, chip, adr)) + ret = -EIO; break; + } /* Latency issues. Drop the lock, wait a while and retry */ UDELAY(map, chip, adr, 1); @@ -2014,7 +2025,7 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip, int len) { struct cfi_private *cfi = map->fldrv_priv; - int ret = -EIO; + int ret; unsigned long cmd_adr; int z, words; map_word datum; @@ -2071,12 +2082,8 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip, chip->word_write_time); ret = do_write_buffer_wait(map, chip, adr, datum); - if (ret) { - cfi_check_err_status(map, chip, adr); + if (ret) do_write_buffer_reset(map, chip, cfi); - pr_err("MTD %s(): software timeout, address:0x%.8lx.\n", - __func__, adr); - } xip_enable(map, chip, adr); @@ -2095,7 +2102,7 @@ static int cfi_amdstd_write_buffers(struct mtd_info *mtd, loff_t to, size_t len, struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize; - int ret = 0; + int ret; int chipnum; unsigned long ofs; @@ -2232,7 +2239,7 @@ static int do_panic_write_oneword(struct map_info *map, struct flchip *chip, struct cfi_private *cfi = map->fldrv_priv; int retry_cnt = 0; map_word oldd; - int ret = 0; + int ret; int i; adr += chip->start; @@ -2271,9 +2278,9 @@ retry: udelay(1); } - if (!chip_good(map, chip, adr, datum)) { + if (!chip_good(map, chip, adr, datum) || + cfi_check_err_status(map, chip, adr)) { /* reset on all failures. */ - cfi_check_err_status(map, chip, adr); map_write(map, CMD(0xF0), chip->start); /* FIXME - should have reset delay before continuing */ @@ -2307,7 +2314,7 @@ static int cfi_amdstd_panic_write(struct mtd_info *mtd, loff_t to, size_t len, struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; unsigned long ofs, chipstart; - int ret = 0; + int ret; int chipnum; chipnum = to >> cfi->chipshift; @@ -2411,7 +2418,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip) unsigned long timeo = jiffies + HZ; unsigned long int adr; DECLARE_WAITQUEUE(wait, current); - int ret = 0; + int ret; int retry_cnt = 0; adr = cfi->addr_unlock1; @@ -2467,8 +2474,11 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip) chip->erase_suspended = 0; } - if (chip_good(map, chip, adr, map_word_ff(map))) + if (chip_good(map, chip, adr, map_word_ff(map))) { + if (cfi_check_err_status(map, chip, adr)) + ret = -EIO; break; + } if (time_after(jiffies, timeo)) { printk(KERN_WARNING "MTD %s(): software timeout\n", @@ -2483,7 +2493,6 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip) /* Did we succeed? */ if (ret) { /* reset on all failures. */ - cfi_check_err_status(map, chip, adr); map_write(map, CMD(0xF0), chip->start); /* FIXME - should have reset delay before continuing */ @@ -2508,7 +2517,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip, struct cfi_private *cfi = map->fldrv_priv; unsigned long timeo = jiffies + HZ; DECLARE_WAITQUEUE(wait, current); - int ret = 0; + int ret; int retry_cnt = 0; adr += chip->start; @@ -2564,8 +2573,11 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip, chip->erase_suspended = 0; } - if (chip_good(map, chip, adr, map_word_ff(map))) + if (chip_good(map, chip, adr, map_word_ff(map))) { + if (cfi_check_err_status(map, chip, adr)) + ret = -EIO; break; + } if (time_after(jiffies, timeo)) { printk(KERN_WARNING "MTD %s(): software timeout\n", @@ -2580,7 +2592,6 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip, /* Did we succeed? */ if (ret) { /* reset on all failures. */ - cfi_check_err_status(map, chip, adr); map_write(map, CMD(0xF0), chip->start); /* FIXME - should have reset delay before continuing */ diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c index e752067526a5..54edae63b92d 100644 --- a/drivers/mtd/chips/cfi_cmdset_0020.c +++ b/drivers/mtd/chips/cfi_cmdset_0020.c @@ -611,7 +611,7 @@ static int cfi_staa_write_buffers (struct mtd_info *mtd, loff_t to, struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; int wbufsize = cfi_interleave(cfi) << cfi->cfiq->MaxBufWriteSize; - int ret = 0; + int ret; int chipnum; unsigned long ofs; @@ -895,7 +895,7 @@ static int cfi_staa_erase_varsize(struct mtd_info *mtd, { struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; unsigned long adr, len; - int chipnum, ret = 0; + int chipnum, ret; int i, first; struct mtd_erase_region_info *regions = mtd->eraseregions; @@ -1132,7 +1132,7 @@ static int cfi_staa_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len) struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; unsigned long adr; - int chipnum, ret = 0; + int chipnum, ret; #ifdef DEBUG_LOCK_BITS int ofs_factor = cfi->interleave * cfi->device_type; #endif @@ -1279,7 +1279,7 @@ static int cfi_staa_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len) struct map_info *map = mtd->priv; struct cfi_private *cfi = map->fldrv_priv; unsigned long adr; - int chipnum, ret = 0; + int chipnum, ret; #ifdef DEBUG_LOCK_BITS int ofs_factor = cfi->interleave * cfi->device_type; #endif diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c index e3b266ee06af..e2d4db05aeb3 100644 --- a/drivers/mtd/chips/cfi_util.c +++ b/drivers/mtd/chips/cfi_util.c @@ -26,7 +26,7 @@ void cfi_udelay(int us) { if (us >= 1000) { - msleep((us+999)/1000); + msleep(DIV_ROUND_UP(us, 1000)); } else { udelay(us); cond_resched(); diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c index b20d02b4f830..77c872fd3d83 100644 --- a/drivers/mtd/devices/mchp23k256.c +++ b/drivers/mtd/devices/mchp23k256.c @@ -64,15 +64,17 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len, struct spi_transfer transfer[2] = {}; struct spi_message message; unsigned char command[MAX_CMD_SIZE]; - int ret; + int ret, cmd_len; spi_message_init(&message); + cmd_len = mchp23k256_cmdsz(flash); + command[0] = MCHP23K256_CMD_WRITE; mchp23k256_addr2cmd(flash, to, command); transfer[0].tx_buf = command; - transfer[0].len = mchp23k256_cmdsz(flash); + transfer[0].len = cmd_len; spi_message_add_tail(&transfer[0], &message); transfer[1].tx_buf = buf; @@ -88,8 +90,8 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len, if (ret) return ret; - if (retlen && message.actual_length > sizeof(command)) - *retlen += message.actual_length - sizeof(command); + if (retlen && message.actual_length > cmd_len) + *retlen += message.actual_length - cmd_len; return 0; } @@ -101,16 +103,18 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len, struct spi_transfer transfer[2] = {}; struct spi_message message; unsigned char command[MAX_CMD_SIZE]; - int ret; + int ret, cmd_len; spi_message_init(&message); + cmd_len = mchp23k256_cmdsz(flash); + memset(&transfer, 0, sizeof(transfer)); command[0] = MCHP23K256_CMD_READ; mchp23k256_addr2cmd(flash, from, command); transfer[0].tx_buf = command; - transfer[0].len = mchp23k256_cmdsz(flash); + transfer[0].len = cmd_len; spi_message_add_tail(&transfer[0], &message); transfer[1].rx_buf = buf; @@ -126,8 +130,8 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len, if (ret) return ret; - if (retlen && message.actual_length > sizeof(command)) - *retlen += message.actual_length - sizeof(command); + if (retlen && message.actual_length > cmd_len) + *retlen += message.actual_length - cmd_len; return 0; } diff --git a/drivers/mtd/devices/spear_smi.c b/drivers/mtd/devices/spear_smi.c index 986f81d2f93e..79dcca16481d 100644 --- a/drivers/mtd/devices/spear_smi.c +++ b/drivers/mtd/devices/spear_smi.c @@ -592,6 +592,26 @@ static int spear_mtd_read(struct mtd_info *mtd, loff_t from, size_t len, return 0; } +/* + * The purpose of this function is to ensure a memcpy_toio() with byte writes + * only. Its structure is inspired from the ARM implementation of _memcpy_toio() + * which also does single byte writes but cannot be used here as this is just an + * implementation detail and not part of the API. Not mentioning the comment + * stating that _memcpy_toio() should be optimized. + */ +static void spear_smi_memcpy_toio_b(volatile void __iomem *dest, + const void *src, size_t len) +{ + const unsigned char *from = src; + + while (len) { + len--; + writeb(*from, dest); + from++; + dest++; + } +} + static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank, void __iomem *dest, const void *src, size_t len) { @@ -614,7 +634,23 @@ static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank, ctrlreg1 = readl(dev->io_base + SMI_CR1); writel((ctrlreg1 | WB_MODE) & ~SW_MODE, dev->io_base + SMI_CR1); - memcpy_toio(dest, src, len); + /* + * In Write Burst mode (WB_MODE), the specs states that writes must be: + * - incremental + * - of the same size + * The ARM implementation of memcpy_toio() will optimize the number of + * I/O by using as much 4-byte writes as possible, surrounded by + * 2-byte/1-byte access if: + * - the destination is not 4-byte aligned + * - the length is not a multiple of 4-byte. + * Avoid this alternance of write access size by using our own 'byte + * access' helper if at least one of the two conditions above is true. + */ + if (IS_ALIGNED(len, sizeof(u32)) && + IS_ALIGNED((uintptr_t)dest, sizeof(u32))) + memcpy_toio(dest, src, len); + else + spear_smi_memcpy_toio_b(dest, src, len); writel(ctrlreg1, dev->io_base + SMI_CR1); @@ -777,9 +813,6 @@ static int spear_smi_probe_config_dt(struct platform_device *pdev, /* Fill structs for each subnode (flash device) */ while ((pp = of_get_next_child(np, pp))) { - struct spear_smi_flash_info *flash_info; - - flash_info = &pdata->board_flash_info[i]; pdata->np[i] = pp; /* Read base-addr and size from DT */ @@ -933,7 +966,6 @@ static int spear_smi_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { ret = -ENODEV; - dev_err(&pdev->dev, "invalid smi irq\n"); goto err; } diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c index f4d1667daaf9..1888523d9745 100644 --- a/drivers/mtd/devices/st_spi_fsm.c +++ b/drivers/mtd/devices/st_spi_fsm.c @@ -255,7 +255,6 @@ struct stfsm_seq { struct stfsm { struct device *dev; void __iomem *base; - struct resource *region; struct mtd_info mtd; struct mutex lock; struct flash_info *info; diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index bc82305ebb4c..b28225a7c4f3 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -96,6 +96,17 @@ config MTD_PHYSMAP_GEMINI platforms, some detection and setting up parallel mode on the external interface. +config MTD_PHYSMAP_IXP4XX + bool "Intel IXP4xx OF-based physical memory map handling" + depends on MTD_PHYSMAP_OF + depends on ARM + select MTD_COMPLEX_MAPPINGS + select MTD_CFI_BE_BYTE_SWAP if CPU_BIG_ENDIAN + default ARCH_IXP4XX + help + This provides some extra DT physmap parsing for the Intel IXP4xx + platforms, some elaborate endianness handling in particular. + config MTD_PHYSMAP_GPIO_ADDR bool "GPIO-assisted Flash Chip Support" depends on MTD_PHYSMAP diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile index 1146009f41df..c0da86a5d26f 100644 --- a/drivers/mtd/maps/Makefile +++ b/drivers/mtd/maps/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_MTD_PXA2XX) += pxa2xx-flash.o physmap-objs-y += physmap-core.o physmap-objs-$(CONFIG_MTD_PHYSMAP_VERSATILE) += physmap-versatile.o physmap-objs-$(CONFIG_MTD_PHYSMAP_GEMINI) += physmap-gemini.o +physmap-objs-$(CONFIG_MTD_PHYSMAP_IXP4XX) += physmap-ixp4xx.o physmap-objs := $(physmap-objs-y) obj-$(CONFIG_MTD_PHYSMAP) += physmap.o obj-$(CONFIG_MTD_PISMO) += pismo.o diff --git a/drivers/mtd/maps/l440gx.c b/drivers/mtd/maps/l440gx.c index 876f12f40018..0eeadfeb620d 100644 --- a/drivers/mtd/maps/l440gx.c +++ b/drivers/mtd/maps/l440gx.c @@ -86,7 +86,7 @@ static int __init init_l440gx(void) return -ENOMEM; } simple_map_init(&l440gx_map); - printk(KERN_NOTICE "window_addr = 0x%08lx\n", (unsigned long)l440gx_map.virt); + pr_debug("window_addr = %p\n", l440gx_map.virt); /* Setup the pm iobase resource * This code should move into some kind of generic bridge diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c index 21b556afc305..a9f7964e2edb 100644 --- a/drivers/mtd/maps/physmap-core.c +++ b/drivers/mtd/maps/physmap-core.c @@ -41,6 +41,7 @@ #include <linux/gpio/consumer.h> #include "physmap-gemini.h" +#include "physmap-ixp4xx.h" #include "physmap-versatile.h" struct physmap_flash_info { @@ -370,6 +371,10 @@ static int physmap_flash_of_init(struct platform_device *dev) if (err) return err; + err = of_flash_probe_ixp4xx(dev, dp, &info->maps[i]); + if (err) + return err; + err = of_flash_probe_versatile(dev, dp, &info->maps[i]); if (err) return err; diff --git a/drivers/mtd/maps/physmap-ixp4xx.c b/drivers/mtd/maps/physmap-ixp4xx.c new file mode 100644 index 000000000000..6a054229a8a0 --- /dev/null +++ b/drivers/mtd/maps/physmap-ixp4xx.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel IXP4xx OF physmap add-on + * Copyright (C) 2019 Linus Walleij <linus.walleij@linaro.org> + * + * Based on the ixp4xx.c map driver, originally written by: + * Intel Corporation + * Deepak Saxena <dsaxena@mvista.com> + * Copyright (C) 2002 Intel Corporation + * Copyright (C) 2003-2004 MontaVista Software, Inc. + */ +#include <linux/export.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/mtd/map.h> +#include <linux/mtd/xip.h> +#include "physmap-ixp4xx.h" + +/* + * Read/write a 16 bit word from flash address 'addr'. + * + * When the cpu is in little-endian mode it swizzles the address lines + * ('address coherency') so we need to undo the swizzling to ensure commands + * and the like end up on the correct flash address. + * + * To further complicate matters, due to the way the expansion bus controller + * handles 32 bit reads, the byte stream ABCD is stored on the flash as: + * D15 D0 + * +---+---+ + * | A | B | 0 + * +---+---+ + * | C | D | 2 + * +---+---+ + * This means that on LE systems each 16 bit word must be swapped. Note that + * this requires CONFIG_MTD_CFI_BE_BYTE_SWAP to be enabled to 'unswap' the CFI + * data and other flash commands which are always in D7-D0. + */ +#ifndef CONFIG_CPU_BIG_ENDIAN + +static inline u16 flash_read16(void __iomem *addr) +{ + return be16_to_cpu(__raw_readw((void __iomem *)((unsigned long)addr ^ 0x2))); +} + +static inline void flash_write16(u16 d, void __iomem *addr) +{ + __raw_writew(cpu_to_be16(d), (void __iomem *)((unsigned long)addr ^ 0x2)); +} + +#define BYTE0(h) ((h) & 0xFF) +#define BYTE1(h) (((h) >> 8) & 0xFF) + +#else + +static inline u16 flash_read16(const void __iomem *addr) +{ + return __raw_readw(addr); +} + +static inline void flash_write16(u16 d, void __iomem *addr) +{ + __raw_writew(d, addr); +} + +#define BYTE0(h) (((h) >> 8) & 0xFF) +#define BYTE1(h) ((h) & 0xFF) +#endif + +static map_word ixp4xx_read16(struct map_info *map, unsigned long ofs) +{ + map_word val; + + val.x[0] = flash_read16(map->virt + ofs); + return val; +} + +/* + * The IXP4xx expansion bus only allows 16-bit wide acceses + * when attached to a 16-bit wide device (such as the 28F128J3A), + * so we can't just memcpy_fromio(). + */ +static void ixp4xx_copy_from(struct map_info *map, void *to, + unsigned long from, ssize_t len) +{ + u8 *dest = (u8 *) to; + void __iomem *src = map->virt + from; + + if (len <= 0) + return; + + if (from & 1) { + *dest++ = BYTE1(flash_read16(src-1)); + src++; + --len; + } + + while (len >= 2) { + u16 data = flash_read16(src); + *dest++ = BYTE0(data); + *dest++ = BYTE1(data); + src += 2; + len -= 2; + } + + if (len > 0) + *dest++ = BYTE0(flash_read16(src)); +} + +static void ixp4xx_write16(struct map_info *map, map_word d, unsigned long adr) +{ + flash_write16(d.x[0], map->virt + adr); +} + +int of_flash_probe_ixp4xx(struct platform_device *pdev, + struct device_node *np, + struct map_info *map) +{ + struct device *dev = &pdev->dev; + + /* Multiplatform guard */ + if (!of_device_is_compatible(np, "intel,ixp4xx-flash")) + return 0; + + map->read = ixp4xx_read16; + map->write = ixp4xx_write16; + map->copy_from = ixp4xx_copy_from; + map->copy_to = NULL; + + dev_info(dev, "initialized Intel IXP4xx-specific physmap control\n"); + + return 0; +} diff --git a/drivers/mtd/maps/physmap-ixp4xx.h b/drivers/mtd/maps/physmap-ixp4xx.h new file mode 100644 index 000000000000..b0fc49b7f3ed --- /dev/null +++ b/drivers/mtd/maps/physmap-ixp4xx.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/of.h> +#include <linux/mtd/map.h> + +#ifdef CONFIG_MTD_PHYSMAP_IXP4XX +int of_flash_probe_ixp4xx(struct platform_device *pdev, + struct device_node *np, + struct map_info *map); +#else +static inline +int of_flash_probe_ixp4xx(struct platform_device *pdev, + struct device_node *np, + struct map_info *map) +{ + return 0; +} +#endif diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 975aed94f06c..b841008a9eb7 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -174,7 +174,7 @@ static ssize_t mtdchar_read(struct file *file, char __user *buf, size_t count, break; case MTD_FILE_MODE_RAW: { - struct mtd_oob_ops ops; + struct mtd_oob_ops ops = {}; ops.mode = MTD_OPS_RAW; ops.datbuf = kbuf; @@ -268,7 +268,7 @@ static ssize_t mtdchar_write(struct file *file, const char __user *buf, size_t c case MTD_FILE_MODE_RAW: { - struct mtd_oob_ops ops; + struct mtd_oob_ops ops = {}; ops.mode = MTD_OPS_RAW; ops.datbuf = kbuf; @@ -350,7 +350,7 @@ static int mtdchar_writeoob(struct file *file, struct mtd_info *mtd, uint32_t __user *retp) { struct mtd_file_info *mfi = file->private_data; - struct mtd_oob_ops ops; + struct mtd_oob_ops ops = {}; uint32_t retlen; int ret = 0; @@ -394,7 +394,7 @@ static int mtdchar_readoob(struct file *file, struct mtd_info *mtd, uint32_t __user *retp) { struct mtd_file_info *mfi = file->private_data; - struct mtd_oob_ops ops; + struct mtd_oob_ops ops = {}; int ret = 0; if (length > 4096) @@ -587,7 +587,7 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd, struct mtd_write_req __user *argp) { struct mtd_write_req req; - struct mtd_oob_ops ops; + struct mtd_oob_ops ops = {}; const void __user *usr_data, *usr_oob; int ret; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 6cc7ecb0c788..5fac4355b9c2 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -382,33 +382,21 @@ static struct dentry *dfs_dir_mtd; static void mtd_debugfs_populate(struct mtd_info *mtd) { struct device *dev = &mtd->dev; - struct dentry *root, *dent; + struct dentry *root; if (IS_ERR_OR_NULL(dfs_dir_mtd)) return; root = debugfs_create_dir(dev_name(dev), dfs_dir_mtd); - if (IS_ERR_OR_NULL(root)) { - dev_dbg(dev, "won't show data in debugfs\n"); - return; - } - mtd->dbg.dfs_dir = root; - if (mtd->dbg.partid) { - dent = debugfs_create_file("partid", 0400, root, mtd, - &mtd_partid_debug_fops); - if (IS_ERR_OR_NULL(dent)) - dev_err(dev, "can't create debugfs entry for partid\n"); - } + if (mtd->dbg.partid) + debugfs_create_file("partid", 0400, root, mtd, + &mtd_partid_debug_fops); - if (mtd->dbg.partname) { - dent = debugfs_create_file("partname", 0400, root, mtd, - &mtd_partname_debug_fops); - if (IS_ERR_OR_NULL(dent)) - dev_err(dev, - "can't create debugfs entry for partname\n"); - } + if (mtd->dbg.partname) + debugfs_create_file("partname", 0400, root, mtd, + &mtd_partname_debug_fops); } #ifndef CONFIG_MMU diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c index f92414eb4c86..58eefa43af14 100644 --- a/drivers/mtd/mtdswap.c +++ b/drivers/mtd/mtdswap.c @@ -1257,7 +1257,6 @@ DEFINE_SHOW_ATTRIBUTE(mtdswap); static int mtdswap_add_debugfs(struct mtdswap_dev *d) { struct dentry *root = d->mtd->dbg.dfs_dir; - struct dentry *dent; if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; @@ -1265,12 +1264,7 @@ static int mtdswap_add_debugfs(struct mtdswap_dev *d) if (IS_ERR_OR_NULL(root)) return -1; - dent = debugfs_create_file("mtdswap_stats", S_IRUSR, root, d, - &mtdswap_fops); - if (!dent) { - dev_err(d->dev, "debugfs_create_file failed\n"); - return -1; - } + debugfs_create_file("mtdswap_stats", S_IRUSR, root, d, &mtdswap_fops); return 0; } diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index e59de3f60cf6..74fb91adeb46 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -450,6 +450,13 @@ config MTD_NAND_PLATFORM devices. You will need to provide platform-specific functions via platform_data. +config MTD_NAND_CADENCE + tristate "Support Cadence NAND (HPNFC) controller" + depends on OF || COMPILE_TEST + help + Enable the driver for NAND flash on platforms using a Cadence NAND + controller. + comment "Misc" config MTD_SM_COMMON diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile index a98721988e61..2d136b158fb7 100644 --- a/drivers/mtd/nand/raw/Makefile +++ b/drivers/mtd/nand/raw/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_MTD_NAND_MXIC) += mxic_nand.o obj-$(CONFIG_MTD_NAND_TEGRA) += tegra_nand.o obj-$(CONFIG_MTD_NAND_STM32_FMC2) += stm32_fmc2_nand.o obj-$(CONFIG_MTD_NAND_MESON) += meson_nand.o +obj-$(CONFIG_MTD_NAND_CADENCE) += cadence-nand-controller.o nand-objs := nand_base.o nand_legacy.o nand_bbt.o nand_timings.o nand_ids.o nand-objs += nand_onfi.o diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 15ef30b368a5..1a66b1cd51c0 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -117,6 +117,18 @@ enum flash_dma_reg { FLASH_DMA_CURRENT_DESC_EXT, }; +/* flash_dma registers v0*/ +static const u16 flash_dma_regs_v0[] = { + [FLASH_DMA_REVISION] = 0x00, + [FLASH_DMA_FIRST_DESC] = 0x04, + [FLASH_DMA_CTRL] = 0x08, + [FLASH_DMA_MODE] = 0x0c, + [FLASH_DMA_STATUS] = 0x10, + [FLASH_DMA_INTERRUPT_DESC] = 0x14, + [FLASH_DMA_ERROR_STATUS] = 0x18, + [FLASH_DMA_CURRENT_DESC] = 0x1c, +}; + /* flash_dma registers v1*/ static const u16 flash_dma_regs_v1[] = { [FLASH_DMA_REVISION] = 0x00, @@ -597,6 +609,8 @@ static void brcmnand_flash_dma_revision_init(struct brcmnand_controller *ctrl) /* flash_dma register offsets */ if (ctrl->nand_version >= 0x0703) ctrl->flash_dma_offsets = flash_dma_regs_v4; + else if (ctrl->nand_version == 0x0602) + ctrl->flash_dma_offsets = flash_dma_regs_v0; else ctrl->flash_dma_offsets = flash_dma_regs_v1; } @@ -918,7 +932,7 @@ static inline void disable_ctrl_irqs(struct brcmnand_controller *ctrl) return; if (has_flash_dma(ctrl)) { - ctrl->flash_dma_base = 0; + ctrl->flash_dma_base = NULL; disable_irq(ctrl->dma_irq); } @@ -1673,8 +1687,11 @@ static void brcmnand_dma_run(struct brcmnand_host *host, dma_addr_t desc) flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC, lower_32_bits(desc)); (void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC); - flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC_EXT, upper_32_bits(desc)); - (void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC_EXT); + if (ctrl->nand_version > 0x0602) { + flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC_EXT, + upper_32_bits(desc)); + (void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC_EXT); + } /* Start FLASH_DMA engine */ ctrl->dma_pending = true; diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c new file mode 100644 index 000000000000..3a36285a8d8a --- /dev/null +++ b/drivers/mtd/nand/raw/cadence-nand-controller.c @@ -0,0 +1,3030 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Cadence NAND flash controller driver + * + * Copyright (C) 2019 Cadence + * + * Author: Piotr Sroka <piotrs@cadence.com> + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/dma-mapping.h> +#include <linux/dmaengine.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/mtd/mtd.h> +#include <linux/mtd/rawnand.h> +#include <linux/of_device.h> +#include <linux/iopoll.h> + +/* + * HPNFC can work in 3 modes: + * - PIO - can work in master or slave DMA + * - CDMA - needs Master DMA for accessing command descriptors. + * - Generic mode - can use only slave DMA. + * CDMA and PIO modes can be used to execute only base commands. + * Generic mode can be used to execute any command + * on NAND flash memory. Driver uses CDMA mode for + * block erasing, page reading, page programing. + * Generic mode is used for executing rest of commands. + */ + +#define MAX_OOB_SIZE_PER_SECTOR 32 +#define MAX_ADDRESS_CYC 6 +#define MAX_ERASE_ADDRESS_CYC 3 +#define MAX_DATA_SIZE 0xFFFC +#define DMA_DATA_SIZE_ALIGN 8 + +/* Register definition. */ +/* + * Command register 0. + * Writing data to this register will initiate a new transaction + * of the NF controller. + */ +#define CMD_REG0 0x0000 +/* Command type field mask. */ +#define CMD_REG0_CT GENMASK(31, 30) +/* Command type CDMA. */ +#define CMD_REG0_CT_CDMA 0uL +/* Command type generic. */ +#define CMD_REG0_CT_GEN 3uL +/* Command thread number field mask. */ +#define CMD_REG0_TN GENMASK(27, 24) + +/* Command register 2. */ +#define CMD_REG2 0x0008 +/* Command register 3. */ +#define CMD_REG3 0x000C +/* Pointer register to select which thread status will be selected. */ +#define CMD_STATUS_PTR 0x0010 +/* Command status register for selected thread. */ +#define CMD_STATUS 0x0014 + +/* Interrupt status register. */ +#define INTR_STATUS 0x0110 +#define INTR_STATUS_SDMA_ERR BIT(22) +#define INTR_STATUS_SDMA_TRIGG BIT(21) +#define INTR_STATUS_UNSUPP_CMD BIT(19) +#define INTR_STATUS_DDMA_TERR BIT(18) +#define INTR_STATUS_CDMA_TERR BIT(17) +#define INTR_STATUS_CDMA_IDL BIT(16) + +/* Interrupt enable register. */ +#define INTR_ENABLE 0x0114 +#define INTR_ENABLE_INTR_EN BIT(31) +#define INTR_ENABLE_SDMA_ERR_EN BIT(22) +#define INTR_ENABLE_SDMA_TRIGG_EN BIT(21) +#define INTR_ENABLE_UNSUPP_CMD_EN BIT(19) +#define INTR_ENABLE_DDMA_TERR_EN BIT(18) +#define INTR_ENABLE_CDMA_TERR_EN BIT(17) +#define INTR_ENABLE_CDMA_IDLE_EN BIT(16) + +/* Controller internal state. */ +#define CTRL_STATUS 0x0118 +#define CTRL_STATUS_INIT_COMP BIT(9) +#define CTRL_STATUS_CTRL_BUSY BIT(8) + +/* Command Engine threads state. */ +#define TRD_STATUS 0x0120 + +/* Command Engine interrupt thread error status. */ +#define TRD_ERR_INT_STATUS 0x0128 +/* Command Engine interrupt thread error enable. */ +#define TRD_ERR_INT_STATUS_EN 0x0130 +/* Command Engine interrupt thread complete status. */ +#define TRD_COMP_INT_STATUS 0x0138 + +/* + * Transfer config 0 register. + * Configures data transfer parameters. + */ +#define TRAN_CFG_0 0x0400 +/* Offset value from the beginning of the page. */ +#define TRAN_CFG_0_OFFSET GENMASK(31, 16) +/* Numbers of sectors to transfer within singlNF device's page. */ +#define TRAN_CFG_0_SEC_CNT GENMASK(7, 0) + +/* + * Transfer config 1 register. + * Configures data transfer parameters. + */ +#define TRAN_CFG_1 0x0404 +/* Size of last data sector. */ +#define TRAN_CFG_1_LAST_SEC_SIZE GENMASK(31, 16) +/* Size of not-last data sector. */ +#define TRAN_CFG_1_SECTOR_SIZE GENMASK(15, 0) + +/* ECC engine configuration register 0. */ +#define ECC_CONFIG_0 0x0428 +/* Correction strength. */ +#define ECC_CONFIG_0_CORR_STR GENMASK(10, 8) +/* Enable erased pages detection mechanism. */ +#define ECC_CONFIG_0_ERASE_DET_EN BIT(1) +/* Enable controller ECC check bits generation and correction. */ +#define ECC_CONFIG_0_ECC_EN BIT(0) + +/* ECC engine configuration register 1. */ +#define ECC_CONFIG_1 0x042C + +/* Multiplane settings register. */ +#define MULTIPLANE_CFG 0x0434 +/* Cache operation settings. */ +#define CACHE_CFG 0x0438 + +/* DMA settings register. */ +#define DMA_SETINGS 0x043C +/* Enable SDMA error report on access unprepared slave DMA interface. */ +#define DMA_SETINGS_SDMA_ERR_RSP BIT(17) + +/* Transferred data block size for the slave DMA module. */ +#define SDMA_SIZE 0x0440 + +/* Thread number associated with transferred data block + * for the slave DMA module. + */ +#define SDMA_TRD_NUM 0x0444 +/* Thread number mask. */ +#define SDMA_TRD_NUM_SDMA_TRD GENMASK(2, 0) + +#define CONTROL_DATA_CTRL 0x0494 +/* Thread number mask. */ +#define CONTROL_DATA_CTRL_SIZE GENMASK(15, 0) + +#define CTRL_VERSION 0x800 +#define CTRL_VERSION_REV GENMASK(7, 0) + +/* Available hardware features of the controller. */ +#define CTRL_FEATURES 0x804 +/* Support for NV-DDR2/3 work mode. */ +#define CTRL_FEATURES_NVDDR_2_3 BIT(28) +/* Support for NV-DDR work mode. */ +#define CTRL_FEATURES_NVDDR BIT(27) +/* Support for asynchronous work mode. */ +#define CTRL_FEATURES_ASYNC BIT(26) +/* Support for asynchronous work mode. */ +#define CTRL_FEATURES_N_BANKS GENMASK(25, 24) +/* Slave and Master DMA data width. */ +#define CTRL_FEATURES_DMA_DWITH64 BIT(21) +/* Availability of Control Data feature.*/ +#define CTRL_FEATURES_CONTROL_DATA BIT(10) + +/* BCH Engine identification register 0 - correction strengths. */ +#define BCH_CFG_0 0x838 +#define BCH_CFG_0_CORR_CAP_0 GENMASK(7, 0) +#define BCH_CFG_0_CORR_CAP_1 GENMASK(15, 8) +#define BCH_CFG_0_CORR_CAP_2 GENMASK(23, 16) +#define BCH_CFG_0_CORR_CAP_3 GENMASK(31, 24) + +/* BCH Engine identification register 1 - correction strengths. */ +#define BCH_CFG_1 0x83C +#define BCH_CFG_1_CORR_CAP_4 GENMASK(7, 0) +#define BCH_CFG_1_CORR_CAP_5 GENMASK(15, 8) +#define BCH_CFG_1_CORR_CAP_6 GENMASK(23, 16) +#define BCH_CFG_1_CORR_CAP_7 GENMASK(31, 24) + +/* BCH Engine identification register 2 - sector sizes. */ +#define BCH_CFG_2 0x840 +#define BCH_CFG_2_SECT_0 GENMASK(15, 0) +#define BCH_CFG_2_SECT_1 GENMASK(31, 16) + +/* BCH Engine identification register 3. */ +#define BCH_CFG_3 0x844 + +/* Ready/Busy# line status. */ +#define RBN_SETINGS 0x1004 + +/* Common settings. */ +#define COMMON_SET 0x1008 +/* 16 bit device connected to the NAND Flash interface. */ +#define COMMON_SET_DEVICE_16BIT BIT(8) + +/* Skip_bytes registers. */ +#define SKIP_BYTES_CONF 0x100C +#define SKIP_BYTES_MARKER_VALUE GENMASK(31, 16) +#define SKIP_BYTES_NUM_OF_BYTES GENMASK(7, 0) + +#define SKIP_BYTES_OFFSET 0x1010 +#define SKIP_BYTES_OFFSET_VALUE GENMASK(23, 0) + +/* Timings configuration. */ +#define ASYNC_TOGGLE_TIMINGS 0x101c +#define ASYNC_TOGGLE_TIMINGS_TRH GENMASK(28, 24) +#define ASYNC_TOGGLE_TIMINGS_TRP GENMASK(20, 16) +#define ASYNC_TOGGLE_TIMINGS_TWH GENMASK(12, 8) +#define ASYNC_TOGGLE_TIMINGS_TWP GENMASK(4, 0) + +#define TIMINGS0 0x1024 +#define TIMINGS0_TADL GENMASK(31, 24) +#define TIMINGS0_TCCS GENMASK(23, 16) +#define TIMINGS0_TWHR GENMASK(15, 8) +#define TIMINGS0_TRHW GENMASK(7, 0) + +#define TIMINGS1 0x1028 +#define TIMINGS1_TRHZ GENMASK(31, 24) +#define TIMINGS1_TWB GENMASK(23, 16) +#define TIMINGS1_TVDLY GENMASK(7, 0) + +#define TIMINGS2 0x102c +#define TIMINGS2_TFEAT GENMASK(25, 16) +#define TIMINGS2_CS_HOLD_TIME GENMASK(13, 8) +#define TIMINGS2_CS_SETUP_TIME GENMASK(5, 0) + +/* Configuration of the resynchronization of slave DLL of PHY. */ +#define DLL_PHY_CTRL 0x1034 +#define DLL_PHY_CTRL_DLL_RST_N BIT(24) +#define DLL_PHY_CTRL_EXTENDED_WR_MODE BIT(17) +#define DLL_PHY_CTRL_EXTENDED_RD_MODE BIT(16) +#define DLL_PHY_CTRL_RS_HIGH_WAIT_CNT GENMASK(11, 8) +#define DLL_PHY_CTRL_RS_IDLE_CNT GENMASK(7, 0) + +/* Register controlling DQ related timing. */ +#define PHY_DQ_TIMING 0x2000 +/* Register controlling DSQ related timing. */ +#define PHY_DQS_TIMING 0x2004 +#define PHY_DQS_TIMING_DQS_SEL_OE_END GENMASK(3, 0) +#define PHY_DQS_TIMING_PHONY_DQS_SEL BIT(16) +#define PHY_DQS_TIMING_USE_PHONY_DQS BIT(20) + +/* Register controlling the gate and loopback control related timing. */ +#define PHY_GATE_LPBK_CTRL 0x2008 +#define PHY_GATE_LPBK_CTRL_RDS GENMASK(24, 19) + +/* Register holds the control for the master DLL logic. */ +#define PHY_DLL_MASTER_CTRL 0x200C +#define PHY_DLL_MASTER_CTRL_BYPASS_MODE BIT(23) + +/* Register holds the control for the slave DLL logic. */ +#define PHY_DLL_SLAVE_CTRL 0x2010 + +/* This register handles the global control settings for the PHY. */ +#define PHY_CTRL 0x2080 +#define PHY_CTRL_SDR_DQS BIT(14) +#define PHY_CTRL_PHONY_DQS GENMASK(9, 4) + +/* + * This register handles the global control settings + * for the termination selects for reads. + */ +#define PHY_TSEL 0x2084 + +/* Generic command layout. */ +#define GCMD_LAY_CS GENMASK_ULL(11, 8) +/* + * This bit informs the minicotroller if it has to wait for tWB + * after sending the last CMD/ADDR/DATA in the sequence. + */ +#define GCMD_LAY_TWB BIT_ULL(6) +/* Type of generic instruction. */ +#define GCMD_LAY_INSTR GENMASK_ULL(5, 0) + +/* Generic CMD sequence type. */ +#define GCMD_LAY_INSTR_CMD 0 +/* Generic ADDR sequence type. */ +#define GCMD_LAY_INSTR_ADDR 1 +/* Generic data transfer sequence type. */ +#define GCMD_LAY_INSTR_DATA 2 + +/* Input part of generic command type of input is command. */ +#define GCMD_LAY_INPUT_CMD GENMASK_ULL(23, 16) + +/* Generic command address sequence - address fields. */ +#define GCMD_LAY_INPUT_ADDR GENMASK_ULL(63, 16) +/* Generic command address sequence - address size. */ +#define GCMD_LAY_INPUT_ADDR_SIZE GENMASK_ULL(13, 11) + +/* Transfer direction field of generic command data sequence. */ +#define GCMD_DIR BIT_ULL(11) +/* Read transfer direction of generic command data sequence. */ +#define GCMD_DIR_READ 0 +/* Write transfer direction of generic command data sequence. */ +#define GCMD_DIR_WRITE 1 + +/* ECC enabled flag of generic command data sequence - ECC enabled. */ +#define GCMD_ECC_EN BIT_ULL(12) +/* Generic command data sequence - sector size. */ +#define GCMD_SECT_SIZE GENMASK_ULL(31, 16) +/* Generic command data sequence - sector count. */ +#define GCMD_SECT_CNT GENMASK_ULL(39, 32) +/* Generic command data sequence - last sector size. */ +#define GCMD_LAST_SIZE GENMASK_ULL(55, 40) + +/* CDMA descriptor fields. */ +/* Erase command type of CDMA descriptor. */ +#define CDMA_CT_ERASE 0x1000 +/* Program page command type of CDMA descriptor. */ +#define CDMA_CT_WR 0x2100 +/* Read page command type of CDMA descriptor. */ +#define CDMA_CT_RD 0x2200 + +/* Flash pointer memory shift. */ +#define CDMA_CFPTR_MEM_SHIFT 24 +/* Flash pointer memory mask. */ +#define CDMA_CFPTR_MEM GENMASK(26, 24) + +/* + * Command DMA descriptor flags. If set causes issue interrupt after + * the completion of descriptor processing. + */ +#define CDMA_CF_INT BIT(8) +/* + * Command DMA descriptor flags - the next descriptor + * address field is valid and descriptor processing should continue. + */ +#define CDMA_CF_CONT BIT(9) +/* DMA master flag of command DMA descriptor. */ +#define CDMA_CF_DMA_MASTER BIT(10) + +/* Operation complete status of command descriptor. */ +#define CDMA_CS_COMP BIT(15) +/* Operation complete status of command descriptor. */ +/* Command descriptor status - operation fail. */ +#define CDMA_CS_FAIL BIT(14) +/* Command descriptor status - page erased. */ +#define CDMA_CS_ERP BIT(11) +/* Command descriptor status - timeout occurred. */ +#define CDMA_CS_TOUT BIT(10) +/* + * Maximum amount of correction applied to one ECC sector. + * It is part of command descriptor status. + */ +#define CDMA_CS_MAXERR GENMASK(9, 2) +/* Command descriptor status - uncorrectable ECC error. */ +#define CDMA_CS_UNCE BIT(1) +/* Command descriptor status - descriptor error. */ +#define CDMA_CS_ERR BIT(0) + +/* Status of operation - OK. */ +#define STAT_OK 0 +/* Status of operation - FAIL. */ +#define STAT_FAIL 2 +/* Status of operation - uncorrectable ECC error. */ +#define STAT_ECC_UNCORR 3 +/* Status of operation - page erased. */ +#define STAT_ERASED 5 +/* Status of operation - correctable ECC error. */ +#define STAT_ECC_CORR 6 +/* Status of operation - unsuspected state. */ +#define STAT_UNKNOWN 7 +/* Status of operation - operation is not completed yet. */ +#define STAT_BUSY 0xFF + +#define BCH_MAX_NUM_CORR_CAPS 8 +#define BCH_MAX_NUM_SECTOR_SIZES 2 + +struct cadence_nand_timings { + u32 async_toggle_timings; + u32 timings0; + u32 timings1; + u32 timings2; + u32 dll_phy_ctrl; + u32 phy_ctrl; + u32 phy_dqs_timing; + u32 phy_gate_lpbk_ctrl; +}; + +/* Command DMA descriptor. */ +struct cadence_nand_cdma_desc { + /* Next descriptor address. */ + u64 next_pointer; + + /* Flash address is a 32-bit address comprising of BANK and ROW ADDR. */ + u32 flash_pointer; + /*field appears in HPNFC version 13*/ + u16 bank; + u16 rsvd0; + + /* Operation the controller needs to perform. */ + u16 command_type; + u16 rsvd1; + /* Flags for operation of this command. */ + u16 command_flags; + u16 rsvd2; + + /* System/host memory address required for data DMA commands. */ + u64 memory_pointer; + + /* Status of operation. */ + u32 status; + u32 rsvd3; + + /* Address pointer to sync buffer location. */ + u64 sync_flag_pointer; + + /* Controls the buffer sync mechanism. */ + u32 sync_arguments; + u32 rsvd4; + + /* Control data pointer. */ + u64 ctrl_data_ptr; +}; + +/* Interrupt status. */ +struct cadence_nand_irq_status { + /* Thread operation complete status. */ + u32 trd_status; + /* Thread operation error. */ + u32 trd_error; + /* Controller status. */ + u32 status; +}; + +/* Cadence NAND flash controller capabilities get from driver data. */ +struct cadence_nand_dt_devdata { + /* Skew value of the output signals of the NAND Flash interface. */ + u32 if_skew; + /* It informs if slave DMA interface is connected to DMA engine. */ + unsigned int has_dma:1; +}; + +/* Cadence NAND flash controller capabilities read from registers. */ +struct cdns_nand_caps { + /* Maximum number of banks supported by hardware. */ + u8 max_banks; + /* Slave and Master DMA data width in bytes (4 or 8). */ + u8 data_dma_width; + /* Control Data feature supported. */ + bool data_control_supp; + /* Is PHY type DLL. */ + bool is_phy_type_dll; +}; + +struct cdns_nand_ctrl { + struct device *dev; + struct nand_controller controller; + struct cadence_nand_cdma_desc *cdma_desc; + /* IP capability. */ + const struct cadence_nand_dt_devdata *caps1; + struct cdns_nand_caps caps2; + u8 ctrl_rev; + dma_addr_t dma_cdma_desc; + u8 *buf; + u32 buf_size; + u8 curr_corr_str_idx; + + /* Register interface. */ + void __iomem *reg; + + struct { + void __iomem *virt; + dma_addr_t dma; + } io; + + int irq; + /* Interrupts that have happened. */ + struct cadence_nand_irq_status irq_status; + /* Interrupts we are waiting for. */ + struct cadence_nand_irq_status irq_mask; + struct completion complete; + /* Protect irq_mask and irq_status. */ + spinlock_t irq_lock; + + int ecc_strengths[BCH_MAX_NUM_CORR_CAPS]; + struct nand_ecc_step_info ecc_stepinfos[BCH_MAX_NUM_SECTOR_SIZES]; + struct nand_ecc_caps ecc_caps; + + int curr_trans_type; + + struct dma_chan *dmac; + + u32 nf_clk_rate; + /* + * Estimated Board delay. The value includes the total + * round trip delay for the signals and is used for deciding on values + * associated with data read capture. + */ + u32 board_delay; + + struct nand_chip *selected_chip; + + unsigned long assigned_cs; + struct list_head chips; +}; + +struct cdns_nand_chip { + struct cadence_nand_timings timings; + struct nand_chip chip; + u8 nsels; + struct list_head node; + + /* + * part of oob area of NAND flash memory page. + * This part is available for user to read or write. + */ + u32 avail_oob_size; + + /* Sector size. There are few sectors per mtd->writesize */ + u32 sector_size; + u32 sector_count; + + /* Offset of BBM. */ + u8 bbm_offs; + /* Number of bytes reserved for BBM. */ + u8 bbm_len; + /* ECC strength index. */ + u8 corr_str_idx; + + u8 cs[]; +}; + +struct ecc_info { + int (*calc_ecc_bytes)(int step_size, int strength); + int max_step_size; +}; + +static inline struct +cdns_nand_chip *to_cdns_nand_chip(struct nand_chip *chip) +{ + return container_of(chip, struct cdns_nand_chip, chip); +} + +static inline struct +cdns_nand_ctrl *to_cdns_nand_ctrl(struct nand_controller *controller) +{ + return container_of(controller, struct cdns_nand_ctrl, controller); +} + +static bool +cadence_nand_dma_buf_ok(struct cdns_nand_ctrl *cdns_ctrl, const void *buf, + u32 buf_len) +{ + u8 data_dma_width = cdns_ctrl->caps2.data_dma_width; + + return buf && virt_addr_valid(buf) && + likely(IS_ALIGNED((uintptr_t)buf, data_dma_width)) && + likely(IS_ALIGNED(buf_len, DMA_DATA_SIZE_ALIGN)); +} + +static int cadence_nand_wait_for_value(struct cdns_nand_ctrl *cdns_ctrl, + u32 reg_offset, u32 timeout_us, + u32 mask, bool is_clear) +{ + u32 val; + int ret; + + ret = readl_relaxed_poll_timeout(cdns_ctrl->reg + reg_offset, + val, !(val & mask) == is_clear, + 10, timeout_us); + + if (ret < 0) { + dev_err(cdns_ctrl->dev, + "Timeout while waiting for reg %x with mask %x is clear %d\n", + reg_offset, mask, is_clear); + } + + return ret; +} + +static int cadence_nand_set_ecc_enable(struct cdns_nand_ctrl *cdns_ctrl, + bool enable) +{ + u32 reg; + + if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_CTRL_BUSY, true)) + return -ETIMEDOUT; + + reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0); + + if (enable) + reg |= ECC_CONFIG_0_ECC_EN; + else + reg &= ~ECC_CONFIG_0_ECC_EN; + + writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0); + + return 0; +} + +static void cadence_nand_set_ecc_strength(struct cdns_nand_ctrl *cdns_ctrl, + u8 corr_str_idx) +{ + u32 reg; + + if (cdns_ctrl->curr_corr_str_idx == corr_str_idx) + return; + + reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0); + reg &= ~ECC_CONFIG_0_CORR_STR; + reg |= FIELD_PREP(ECC_CONFIG_0_CORR_STR, corr_str_idx); + writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0); + + cdns_ctrl->curr_corr_str_idx = corr_str_idx; +} + +static int cadence_nand_get_ecc_strength_idx(struct cdns_nand_ctrl *cdns_ctrl, + u8 strength) +{ + int i, corr_str_idx = -1; + + for (i = 0; i < BCH_MAX_NUM_CORR_CAPS; i++) { + if (cdns_ctrl->ecc_strengths[i] == strength) { + corr_str_idx = i; + break; + } + } + + return corr_str_idx; +} + +static int cadence_nand_set_skip_marker_val(struct cdns_nand_ctrl *cdns_ctrl, + u16 marker_value) +{ + u32 reg; + + if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_CTRL_BUSY, true)) + return -ETIMEDOUT; + + reg = readl_relaxed(cdns_ctrl->reg + SKIP_BYTES_CONF); + reg &= ~SKIP_BYTES_MARKER_VALUE; + reg |= FIELD_PREP(SKIP_BYTES_MARKER_VALUE, + marker_value); + + writel_relaxed(reg, cdns_ctrl->reg + SKIP_BYTES_CONF); + + return 0; +} + +static int cadence_nand_set_skip_bytes_conf(struct cdns_nand_ctrl *cdns_ctrl, + u8 num_of_bytes, + u32 offset_value, + int enable) +{ + u32 reg, skip_bytes_offset; + + if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_CTRL_BUSY, true)) + return -ETIMEDOUT; + + if (!enable) { + num_of_bytes = 0; + offset_value = 0; + } + + reg = readl_relaxed(cdns_ctrl->reg + SKIP_BYTES_CONF); + reg &= ~SKIP_BYTES_NUM_OF_BYTES; + reg |= FIELD_PREP(SKIP_BYTES_NUM_OF_BYTES, + num_of_bytes); + skip_bytes_offset = FIELD_PREP(SKIP_BYTES_OFFSET_VALUE, + offset_value); + + writel_relaxed(reg, cdns_ctrl->reg + SKIP_BYTES_CONF); + writel_relaxed(skip_bytes_offset, cdns_ctrl->reg + SKIP_BYTES_OFFSET); + + return 0; +} + +/* Functions enables/disables hardware detection of erased data */ +static void cadence_nand_set_erase_detection(struct cdns_nand_ctrl *cdns_ctrl, + bool enable, + u8 bitflips_threshold) +{ + u32 reg; + + reg = readl_relaxed(cdns_ctrl->reg + ECC_CONFIG_0); + + if (enable) + reg |= ECC_CONFIG_0_ERASE_DET_EN; + else + reg &= ~ECC_CONFIG_0_ERASE_DET_EN; + + writel_relaxed(reg, cdns_ctrl->reg + ECC_CONFIG_0); + writel_relaxed(bitflips_threshold, cdns_ctrl->reg + ECC_CONFIG_1); +} + +static int cadence_nand_set_access_width16(struct cdns_nand_ctrl *cdns_ctrl, + bool bit_bus16) +{ + u32 reg; + + if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_CTRL_BUSY, true)) + return -ETIMEDOUT; + + reg = readl_relaxed(cdns_ctrl->reg + COMMON_SET); + + if (!bit_bus16) + reg &= ~COMMON_SET_DEVICE_16BIT; + else + reg |= COMMON_SET_DEVICE_16BIT; + writel_relaxed(reg, cdns_ctrl->reg + COMMON_SET); + + return 0; +} + +static void +cadence_nand_clear_interrupt(struct cdns_nand_ctrl *cdns_ctrl, + struct cadence_nand_irq_status *irq_status) +{ + writel_relaxed(irq_status->status, cdns_ctrl->reg + INTR_STATUS); + writel_relaxed(irq_status->trd_status, + cdns_ctrl->reg + TRD_COMP_INT_STATUS); + writel_relaxed(irq_status->trd_error, + cdns_ctrl->reg + TRD_ERR_INT_STATUS); +} + +static void +cadence_nand_read_int_status(struct cdns_nand_ctrl *cdns_ctrl, + struct cadence_nand_irq_status *irq_status) +{ + irq_status->status = readl_relaxed(cdns_ctrl->reg + INTR_STATUS); + irq_status->trd_status = readl_relaxed(cdns_ctrl->reg + + TRD_COMP_INT_STATUS); + irq_status->trd_error = readl_relaxed(cdns_ctrl->reg + + TRD_ERR_INT_STATUS); +} + +static u32 irq_detected(struct cdns_nand_ctrl *cdns_ctrl, + struct cadence_nand_irq_status *irq_status) +{ + cadence_nand_read_int_status(cdns_ctrl, irq_status); + + return irq_status->status || irq_status->trd_status || + irq_status->trd_error; +} + +static void cadence_nand_reset_irq(struct cdns_nand_ctrl *cdns_ctrl) +{ + unsigned long flags; + + spin_lock_irqsave(&cdns_ctrl->irq_lock, flags); + memset(&cdns_ctrl->irq_status, 0, sizeof(cdns_ctrl->irq_status)); + memset(&cdns_ctrl->irq_mask, 0, sizeof(cdns_ctrl->irq_mask)); + spin_unlock_irqrestore(&cdns_ctrl->irq_lock, flags); +} + +/* + * This is the interrupt service routine. It handles all interrupts + * sent to this device. + */ +static irqreturn_t cadence_nand_isr(int irq, void *dev_id) +{ + struct cdns_nand_ctrl *cdns_ctrl = dev_id; + struct cadence_nand_irq_status irq_status; + irqreturn_t result = IRQ_NONE; + + spin_lock(&cdns_ctrl->irq_lock); + + if (irq_detected(cdns_ctrl, &irq_status)) { + /* Handle interrupt. */ + /* First acknowledge it. */ + cadence_nand_clear_interrupt(cdns_ctrl, &irq_status); + /* Status in the device context for someone to read. */ + cdns_ctrl->irq_status.status |= irq_status.status; + cdns_ctrl->irq_status.trd_status |= irq_status.trd_status; + cdns_ctrl->irq_status.trd_error |= irq_status.trd_error; + /* Notify anyone who cares that it happened. */ + complete(&cdns_ctrl->complete); + /* Tell the OS that we've handled this. */ + result = IRQ_HANDLED; + } + spin_unlock(&cdns_ctrl->irq_lock); + + return result; +} + +static void cadence_nand_set_irq_mask(struct cdns_nand_ctrl *cdns_ctrl, + struct cadence_nand_irq_status *irq_mask) +{ + writel_relaxed(INTR_ENABLE_INTR_EN | irq_mask->status, + cdns_ctrl->reg + INTR_ENABLE); + + writel_relaxed(irq_mask->trd_error, + cdns_ctrl->reg + TRD_ERR_INT_STATUS_EN); +} + +static void +cadence_nand_wait_for_irq(struct cdns_nand_ctrl *cdns_ctrl, + struct cadence_nand_irq_status *irq_mask, + struct cadence_nand_irq_status *irq_status) +{ + unsigned long timeout = msecs_to_jiffies(10000); + unsigned long time_left; + + time_left = wait_for_completion_timeout(&cdns_ctrl->complete, + timeout); + + *irq_status = cdns_ctrl->irq_status; + if (time_left == 0) { + /* Timeout error. */ + dev_err(cdns_ctrl->dev, "timeout occurred:\n"); + dev_err(cdns_ctrl->dev, "\tstatus = 0x%x, mask = 0x%x\n", + irq_status->status, irq_mask->status); + dev_err(cdns_ctrl->dev, + "\ttrd_status = 0x%x, trd_status mask = 0x%x\n", + irq_status->trd_status, irq_mask->trd_status); + dev_err(cdns_ctrl->dev, + "\t trd_error = 0x%x, trd_error mask = 0x%x\n", + irq_status->trd_error, irq_mask->trd_error); + } +} + +/* Execute generic command on NAND controller. */ +static int cadence_nand_generic_cmd_send(struct cdns_nand_ctrl *cdns_ctrl, + u8 chip_nr, + u64 mini_ctrl_cmd) +{ + u32 mini_ctrl_cmd_l, mini_ctrl_cmd_h, reg; + + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_CS, chip_nr); + mini_ctrl_cmd_l = mini_ctrl_cmd & 0xFFFFFFFF; + mini_ctrl_cmd_h = mini_ctrl_cmd >> 32; + + if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_CTRL_BUSY, true)) + return -ETIMEDOUT; + + cadence_nand_reset_irq(cdns_ctrl); + + writel_relaxed(mini_ctrl_cmd_l, cdns_ctrl->reg + CMD_REG2); + writel_relaxed(mini_ctrl_cmd_h, cdns_ctrl->reg + CMD_REG3); + + /* Select generic command. */ + reg = FIELD_PREP(CMD_REG0_CT, CMD_REG0_CT_GEN); + /* Thread number. */ + reg |= FIELD_PREP(CMD_REG0_TN, 0); + + /* Issue command. */ + writel_relaxed(reg, cdns_ctrl->reg + CMD_REG0); + + return 0; +} + +/* Wait for data on slave DMA interface. */ +static int cadence_nand_wait_on_sdma(struct cdns_nand_ctrl *cdns_ctrl, + u8 *out_sdma_trd, + u32 *out_sdma_size) +{ + struct cadence_nand_irq_status irq_mask, irq_status; + + irq_mask.trd_status = 0; + irq_mask.trd_error = 0; + irq_mask.status = INTR_STATUS_SDMA_TRIGG + | INTR_STATUS_SDMA_ERR + | INTR_STATUS_UNSUPP_CMD; + + cadence_nand_set_irq_mask(cdns_ctrl, &irq_mask); + cadence_nand_wait_for_irq(cdns_ctrl, &irq_mask, &irq_status); + if (irq_status.status == 0) { + dev_err(cdns_ctrl->dev, "Timeout while waiting for SDMA\n"); + return -ETIMEDOUT; + } + + if (irq_status.status & INTR_STATUS_SDMA_TRIGG) { + *out_sdma_size = readl_relaxed(cdns_ctrl->reg + SDMA_SIZE); + *out_sdma_trd = readl_relaxed(cdns_ctrl->reg + SDMA_TRD_NUM); + *out_sdma_trd = + FIELD_GET(SDMA_TRD_NUM_SDMA_TRD, *out_sdma_trd); + } else { + dev_err(cdns_ctrl->dev, "SDMA error - irq_status %x\n", + irq_status.status); + return -EIO; + } + + return 0; +} + +static void cadence_nand_get_caps(struct cdns_nand_ctrl *cdns_ctrl) +{ + u32 reg; + + reg = readl_relaxed(cdns_ctrl->reg + CTRL_FEATURES); + + cdns_ctrl->caps2.max_banks = 1 << FIELD_GET(CTRL_FEATURES_N_BANKS, reg); + + if (FIELD_GET(CTRL_FEATURES_DMA_DWITH64, reg)) + cdns_ctrl->caps2.data_dma_width = 8; + else + cdns_ctrl->caps2.data_dma_width = 4; + + if (reg & CTRL_FEATURES_CONTROL_DATA) + cdns_ctrl->caps2.data_control_supp = true; + + if (reg & (CTRL_FEATURES_NVDDR_2_3 + | CTRL_FEATURES_NVDDR)) + cdns_ctrl->caps2.is_phy_type_dll = true; +} + +/* Prepare CDMA descriptor. */ +static void +cadence_nand_cdma_desc_prepare(struct cdns_nand_ctrl *cdns_ctrl, + char nf_mem, u32 flash_ptr, char *mem_ptr, + char *ctrl_data_ptr, u16 ctype) +{ + struct cadence_nand_cdma_desc *cdma_desc = cdns_ctrl->cdma_desc; + + memset(cdma_desc, 0, sizeof(struct cadence_nand_cdma_desc)); + + /* Set fields for one descriptor. */ + cdma_desc->flash_pointer = flash_ptr; + if (cdns_ctrl->ctrl_rev >= 13) + cdma_desc->bank = nf_mem; + else + cdma_desc->flash_pointer |= (nf_mem << CDMA_CFPTR_MEM_SHIFT); + + cdma_desc->command_flags |= CDMA_CF_DMA_MASTER; + cdma_desc->command_flags |= CDMA_CF_INT; + + cdma_desc->memory_pointer = (uintptr_t)mem_ptr; + cdma_desc->status = 0; + cdma_desc->sync_flag_pointer = 0; + cdma_desc->sync_arguments = 0; + + cdma_desc->command_type = ctype; + cdma_desc->ctrl_data_ptr = (uintptr_t)ctrl_data_ptr; +} + +static u8 cadence_nand_check_desc_error(struct cdns_nand_ctrl *cdns_ctrl, + u32 desc_status) +{ + if (desc_status & CDMA_CS_ERP) + return STAT_ERASED; + + if (desc_status & CDMA_CS_UNCE) + return STAT_ECC_UNCORR; + + if (desc_status & CDMA_CS_ERR) { + dev_err(cdns_ctrl->dev, ":CDMA desc error flag detected.\n"); + return STAT_FAIL; + } + + if (FIELD_GET(CDMA_CS_MAXERR, desc_status)) + return STAT_ECC_CORR; + + return STAT_FAIL; +} + +static int cadence_nand_cdma_finish(struct cdns_nand_ctrl *cdns_ctrl) +{ + struct cadence_nand_cdma_desc *desc_ptr = cdns_ctrl->cdma_desc; + u8 status = STAT_BUSY; + + if (desc_ptr->status & CDMA_CS_FAIL) { + status = cadence_nand_check_desc_error(cdns_ctrl, + desc_ptr->status); + dev_err(cdns_ctrl->dev, ":CDMA error %x\n", desc_ptr->status); + } else if (desc_ptr->status & CDMA_CS_COMP) { + /* Descriptor finished with no errors. */ + if (desc_ptr->command_flags & CDMA_CF_CONT) { + dev_info(cdns_ctrl->dev, "DMA unsupported flag is set"); + status = STAT_UNKNOWN; + } else { + /* Last descriptor. */ + status = STAT_OK; + } + } + + return status; +} + +static int cadence_nand_cdma_send(struct cdns_nand_ctrl *cdns_ctrl, + u8 thread) +{ + u32 reg; + int status; + + /* Wait for thread ready. */ + status = cadence_nand_wait_for_value(cdns_ctrl, TRD_STATUS, + 1000000, + BIT(thread), true); + if (status) + return status; + + cadence_nand_reset_irq(cdns_ctrl); + + writel_relaxed((u32)cdns_ctrl->dma_cdma_desc, + cdns_ctrl->reg + CMD_REG2); + writel_relaxed(0, cdns_ctrl->reg + CMD_REG3); + + /* Select CDMA mode. */ + reg = FIELD_PREP(CMD_REG0_CT, CMD_REG0_CT_CDMA); + /* Thread number. */ + reg |= FIELD_PREP(CMD_REG0_TN, thread); + /* Issue command. */ + writel_relaxed(reg, cdns_ctrl->reg + CMD_REG0); + + return 0; +} + +/* Send SDMA command and wait for finish. */ +static u32 +cadence_nand_cdma_send_and_wait(struct cdns_nand_ctrl *cdns_ctrl, + u8 thread) +{ + struct cadence_nand_irq_status irq_mask, irq_status = {0}; + int status; + + irq_mask.trd_status = BIT(thread); + irq_mask.trd_error = BIT(thread); + irq_mask.status = INTR_STATUS_CDMA_TERR; + + cadence_nand_set_irq_mask(cdns_ctrl, &irq_mask); + + status = cadence_nand_cdma_send(cdns_ctrl, thread); + if (status) + return status; + + cadence_nand_wait_for_irq(cdns_ctrl, &irq_mask, &irq_status); + + if (irq_status.status == 0 && irq_status.trd_status == 0 && + irq_status.trd_error == 0) { + dev_err(cdns_ctrl->dev, "CDMA command timeout\n"); + return -ETIMEDOUT; + } + if (irq_status.status & irq_mask.status) { + dev_err(cdns_ctrl->dev, "CDMA command failed\n"); + return -EIO; + } + + return 0; +} + +/* + * ECC size depends on configured ECC strength and on maximum supported + * ECC step size. + */ +static int cadence_nand_calc_ecc_bytes(int max_step_size, int strength) +{ + int nbytes = DIV_ROUND_UP(fls(8 * max_step_size) * strength, 8); + + return ALIGN(nbytes, 2); +} + +#define CADENCE_NAND_CALC_ECC_BYTES(max_step_size) \ + static int \ + cadence_nand_calc_ecc_bytes_##max_step_size(int step_size, \ + int strength)\ + {\ + return cadence_nand_calc_ecc_bytes(max_step_size, strength);\ + } + +CADENCE_NAND_CALC_ECC_BYTES(256) +CADENCE_NAND_CALC_ECC_BYTES(512) +CADENCE_NAND_CALC_ECC_BYTES(1024) +CADENCE_NAND_CALC_ECC_BYTES(2048) +CADENCE_NAND_CALC_ECC_BYTES(4096) + +/* Function reads BCH capabilities. */ +static int cadence_nand_read_bch_caps(struct cdns_nand_ctrl *cdns_ctrl) +{ + struct nand_ecc_caps *ecc_caps = &cdns_ctrl->ecc_caps; + int max_step_size = 0, nstrengths, i; + u32 reg; + + reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_0); + cdns_ctrl->ecc_strengths[0] = FIELD_GET(BCH_CFG_0_CORR_CAP_0, reg); + cdns_ctrl->ecc_strengths[1] = FIELD_GET(BCH_CFG_0_CORR_CAP_1, reg); + cdns_ctrl->ecc_strengths[2] = FIELD_GET(BCH_CFG_0_CORR_CAP_2, reg); + cdns_ctrl->ecc_strengths[3] = FIELD_GET(BCH_CFG_0_CORR_CAP_3, reg); + + reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_1); + cdns_ctrl->ecc_strengths[4] = FIELD_GET(BCH_CFG_1_CORR_CAP_4, reg); + cdns_ctrl->ecc_strengths[5] = FIELD_GET(BCH_CFG_1_CORR_CAP_5, reg); + cdns_ctrl->ecc_strengths[6] = FIELD_GET(BCH_CFG_1_CORR_CAP_6, reg); + cdns_ctrl->ecc_strengths[7] = FIELD_GET(BCH_CFG_1_CORR_CAP_7, reg); + + reg = readl_relaxed(cdns_ctrl->reg + BCH_CFG_2); + cdns_ctrl->ecc_stepinfos[0].stepsize = + FIELD_GET(BCH_CFG_2_SECT_0, reg); + + cdns_ctrl->ecc_stepinfos[1].stepsize = + FIELD_GET(BCH_CFG_2_SECT_1, reg); + + nstrengths = 0; + for (i = 0; i < BCH_MAX_NUM_CORR_CAPS; i++) { + if (cdns_ctrl->ecc_strengths[i] != 0) + nstrengths++; + } + + ecc_caps->nstepinfos = 0; + for (i = 0; i < BCH_MAX_NUM_SECTOR_SIZES; i++) { + /* ECC strengths are common for all step infos. */ + cdns_ctrl->ecc_stepinfos[i].nstrengths = nstrengths; + cdns_ctrl->ecc_stepinfos[i].strengths = + cdns_ctrl->ecc_strengths; + + if (cdns_ctrl->ecc_stepinfos[i].stepsize != 0) + ecc_caps->nstepinfos++; + + if (cdns_ctrl->ecc_stepinfos[i].stepsize > max_step_size) + max_step_size = cdns_ctrl->ecc_stepinfos[i].stepsize; + } + ecc_caps->stepinfos = &cdns_ctrl->ecc_stepinfos[0]; + + switch (max_step_size) { + case 256: + ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_256; + break; + case 512: + ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_512; + break; + case 1024: + ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_1024; + break; + case 2048: + ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_2048; + break; + case 4096: + ecc_caps->calc_ecc_bytes = &cadence_nand_calc_ecc_bytes_4096; + break; + default: + dev_err(cdns_ctrl->dev, + "Unsupported sector size(ecc step size) %d\n", + max_step_size); + return -EIO; + } + + return 0; +} + +/* Hardware initialization. */ +static int cadence_nand_hw_init(struct cdns_nand_ctrl *cdns_ctrl) +{ + int status; + u32 reg; + + status = cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_INIT_COMP, false); + if (status) + return status; + + reg = readl_relaxed(cdns_ctrl->reg + CTRL_VERSION); + cdns_ctrl->ctrl_rev = FIELD_GET(CTRL_VERSION_REV, reg); + + dev_info(cdns_ctrl->dev, + "%s: cadence nand controller version reg %x\n", + __func__, reg); + + /* Disable cache and multiplane. */ + writel_relaxed(0, cdns_ctrl->reg + MULTIPLANE_CFG); + writel_relaxed(0, cdns_ctrl->reg + CACHE_CFG); + + /* Clear all interrupts. */ + writel_relaxed(0xFFFFFFFF, cdns_ctrl->reg + INTR_STATUS); + + cadence_nand_get_caps(cdns_ctrl); + cadence_nand_read_bch_caps(cdns_ctrl); + + /* + * Set IO width access to 8. + * It is because during SW device discovering width access + * is expected to be 8. + */ + status = cadence_nand_set_access_width16(cdns_ctrl, false); + + return status; +} + +#define TT_MAIN_OOB_AREAS 2 +#define TT_RAW_PAGE 3 +#define TT_BBM 4 +#define TT_MAIN_OOB_AREA_EXT 5 + +/* Prepare size of data to transfer. */ +static void +cadence_nand_prepare_data_size(struct nand_chip *chip, + int transfer_type) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + u32 sec_size = 0, offset = 0, sec_cnt = 1; + u32 last_sec_size = cdns_chip->sector_size; + u32 data_ctrl_size = 0; + u32 reg = 0; + + if (cdns_ctrl->curr_trans_type == transfer_type) + return; + + switch (transfer_type) { + case TT_MAIN_OOB_AREA_EXT: + sec_cnt = cdns_chip->sector_count; + sec_size = cdns_chip->sector_size; + data_ctrl_size = cdns_chip->avail_oob_size; + break; + case TT_MAIN_OOB_AREAS: + sec_cnt = cdns_chip->sector_count; + last_sec_size = cdns_chip->sector_size + + cdns_chip->avail_oob_size; + sec_size = cdns_chip->sector_size; + break; + case TT_RAW_PAGE: + last_sec_size = mtd->writesize + mtd->oobsize; + break; + case TT_BBM: + offset = mtd->writesize + cdns_chip->bbm_offs; + last_sec_size = 8; + break; + } + + reg = 0; + reg |= FIELD_PREP(TRAN_CFG_0_OFFSET, offset); + reg |= FIELD_PREP(TRAN_CFG_0_SEC_CNT, sec_cnt); + writel_relaxed(reg, cdns_ctrl->reg + TRAN_CFG_0); + + reg = 0; + reg |= FIELD_PREP(TRAN_CFG_1_LAST_SEC_SIZE, last_sec_size); + reg |= FIELD_PREP(TRAN_CFG_1_SECTOR_SIZE, sec_size); + writel_relaxed(reg, cdns_ctrl->reg + TRAN_CFG_1); + + if (cdns_ctrl->caps2.data_control_supp) { + reg = readl_relaxed(cdns_ctrl->reg + CONTROL_DATA_CTRL); + reg &= ~CONTROL_DATA_CTRL_SIZE; + reg |= FIELD_PREP(CONTROL_DATA_CTRL_SIZE, data_ctrl_size); + writel_relaxed(reg, cdns_ctrl->reg + CONTROL_DATA_CTRL); + } + + cdns_ctrl->curr_trans_type = transfer_type; +} + +static int +cadence_nand_cdma_transfer(struct cdns_nand_ctrl *cdns_ctrl, u8 chip_nr, + int page, void *buf, void *ctrl_dat, u32 buf_size, + u32 ctrl_dat_size, enum dma_data_direction dir, + bool with_ecc) +{ + dma_addr_t dma_buf, dma_ctrl_dat = 0; + u8 thread_nr = chip_nr; + int status; + u16 ctype; + + if (dir == DMA_FROM_DEVICE) + ctype = CDMA_CT_RD; + else + ctype = CDMA_CT_WR; + + cadence_nand_set_ecc_enable(cdns_ctrl, with_ecc); + + dma_buf = dma_map_single(cdns_ctrl->dev, buf, buf_size, dir); + if (dma_mapping_error(cdns_ctrl->dev, dma_buf)) { + dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n"); + return -EIO; + } + + if (ctrl_dat && ctrl_dat_size) { + dma_ctrl_dat = dma_map_single(cdns_ctrl->dev, ctrl_dat, + ctrl_dat_size, dir); + if (dma_mapping_error(cdns_ctrl->dev, dma_ctrl_dat)) { + dma_unmap_single(cdns_ctrl->dev, dma_buf, + buf_size, dir); + dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n"); + return -EIO; + } + } + + cadence_nand_cdma_desc_prepare(cdns_ctrl, chip_nr, page, + (void *)dma_buf, (void *)dma_ctrl_dat, + ctype); + + status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr); + + dma_unmap_single(cdns_ctrl->dev, dma_buf, + buf_size, dir); + + if (ctrl_dat && ctrl_dat_size) + dma_unmap_single(cdns_ctrl->dev, dma_ctrl_dat, + ctrl_dat_size, dir); + if (status) + return status; + + return cadence_nand_cdma_finish(cdns_ctrl); +} + +static void cadence_nand_set_timings(struct cdns_nand_ctrl *cdns_ctrl, + struct cadence_nand_timings *t) +{ + writel_relaxed(t->async_toggle_timings, + cdns_ctrl->reg + ASYNC_TOGGLE_TIMINGS); + writel_relaxed(t->timings0, cdns_ctrl->reg + TIMINGS0); + writel_relaxed(t->timings1, cdns_ctrl->reg + TIMINGS1); + writel_relaxed(t->timings2, cdns_ctrl->reg + TIMINGS2); + + if (cdns_ctrl->caps2.is_phy_type_dll) + writel_relaxed(t->dll_phy_ctrl, cdns_ctrl->reg + DLL_PHY_CTRL); + + writel_relaxed(t->phy_ctrl, cdns_ctrl->reg + PHY_CTRL); + + if (cdns_ctrl->caps2.is_phy_type_dll) { + writel_relaxed(0, cdns_ctrl->reg + PHY_TSEL); + writel_relaxed(2, cdns_ctrl->reg + PHY_DQ_TIMING); + writel_relaxed(t->phy_dqs_timing, + cdns_ctrl->reg + PHY_DQS_TIMING); + writel_relaxed(t->phy_gate_lpbk_ctrl, + cdns_ctrl->reg + PHY_GATE_LPBK_CTRL); + writel_relaxed(PHY_DLL_MASTER_CTRL_BYPASS_MODE, + cdns_ctrl->reg + PHY_DLL_MASTER_CTRL); + writel_relaxed(0, cdns_ctrl->reg + PHY_DLL_SLAVE_CTRL); + } +} + +static int cadence_nand_select_target(struct nand_chip *chip) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + + if (chip == cdns_ctrl->selected_chip) + return 0; + + if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_CTRL_BUSY, true)) + return -ETIMEDOUT; + + cadence_nand_set_timings(cdns_ctrl, &cdns_chip->timings); + + cadence_nand_set_ecc_strength(cdns_ctrl, + cdns_chip->corr_str_idx); + + cadence_nand_set_erase_detection(cdns_ctrl, true, + chip->ecc.strength); + + cdns_ctrl->curr_trans_type = -1; + cdns_ctrl->selected_chip = chip; + + return 0; +} + +static int cadence_nand_erase(struct nand_chip *chip, u32 page) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + int status; + u8 thread_nr = cdns_chip->cs[chip->cur_cs]; + + cadence_nand_cdma_desc_prepare(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, NULL, NULL, + CDMA_CT_ERASE); + status = cadence_nand_cdma_send_and_wait(cdns_ctrl, thread_nr); + if (status) { + dev_err(cdns_ctrl->dev, "erase operation failed\n"); + return -EIO; + } + + status = cadence_nand_cdma_finish(cdns_ctrl); + if (status) + return status; + + return 0; +} + +static int cadence_nand_read_bbm(struct nand_chip *chip, int page, u8 *buf) +{ + int status; + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + + cadence_nand_prepare_data_size(chip, TT_BBM); + + cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0); + + /* + * Read only bad block marker from offset + * defined by a memory manufacturer. + */ + status = cadence_nand_cdma_transfer(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, cdns_ctrl->buf, NULL, + mtd->oobsize, + 0, DMA_FROM_DEVICE, false); + if (status) { + dev_err(cdns_ctrl->dev, "read BBM failed\n"); + return -EIO; + } + + memcpy(buf + cdns_chip->bbm_offs, cdns_ctrl->buf, cdns_chip->bbm_len); + + return 0; +} + +static int cadence_nand_write_page(struct nand_chip *chip, + const u8 *buf, int oob_required, + int page) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int status; + u16 marker_val = 0xFFFF; + + status = cadence_nand_select_target(chip); + if (status) + return status; + + cadence_nand_set_skip_bytes_conf(cdns_ctrl, cdns_chip->bbm_len, + mtd->writesize + + cdns_chip->bbm_offs, + 1); + + if (oob_required) { + marker_val = *(u16 *)(chip->oob_poi + + cdns_chip->bbm_offs); + } else { + /* Set oob data to 0xFF. */ + memset(cdns_ctrl->buf + mtd->writesize, 0xFF, + cdns_chip->avail_oob_size); + } + + cadence_nand_set_skip_marker_val(cdns_ctrl, marker_val); + + cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREA_EXT); + + if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, mtd->writesize) && + cdns_ctrl->caps2.data_control_supp) { + u8 *oob; + + if (oob_required) + oob = chip->oob_poi; + else + oob = cdns_ctrl->buf + mtd->writesize; + + status = cadence_nand_cdma_transfer(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, (void *)buf, oob, + mtd->writesize, + cdns_chip->avail_oob_size, + DMA_TO_DEVICE, true); + if (status) { + dev_err(cdns_ctrl->dev, "write page failed\n"); + return -EIO; + } + + return 0; + } + + if (oob_required) { + /* Transfer the data to the oob area. */ + memcpy(cdns_ctrl->buf + mtd->writesize, chip->oob_poi, + cdns_chip->avail_oob_size); + } + + memcpy(cdns_ctrl->buf, buf, mtd->writesize); + + cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREAS); + + return cadence_nand_cdma_transfer(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, cdns_ctrl->buf, NULL, + mtd->writesize + + cdns_chip->avail_oob_size, + 0, DMA_TO_DEVICE, true); +} + +static int cadence_nand_write_oob(struct nand_chip *chip, int page) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct mtd_info *mtd = nand_to_mtd(chip); + + memset(cdns_ctrl->buf, 0xFF, mtd->writesize); + + return cadence_nand_write_page(chip, cdns_ctrl->buf, 1, page); +} + +static int cadence_nand_write_page_raw(struct nand_chip *chip, + const u8 *buf, int oob_required, + int page) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int writesize = mtd->writesize; + int oobsize = mtd->oobsize; + int ecc_steps = chip->ecc.steps; + int ecc_size = chip->ecc.size; + int ecc_bytes = chip->ecc.bytes; + void *tmp_buf = cdns_ctrl->buf; + int oob_skip = cdns_chip->bbm_len; + size_t size = writesize + oobsize; + int i, pos, len; + int status = 0; + + status = cadence_nand_select_target(chip); + if (status) + return status; + + /* + * Fill the buffer with 0xff first except the full page transfer. + * This simplifies the logic. + */ + if (!buf || !oob_required) + memset(tmp_buf, 0xff, size); + + cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0); + + /* Arrange the buffer for syndrome payload/ecc layout. */ + if (buf) { + for (i = 0; i < ecc_steps; i++) { + pos = i * (ecc_size + ecc_bytes); + len = ecc_size; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(tmp_buf + pos, buf, len); + buf += len; + if (len < ecc_size) { + len = ecc_size - len; + memcpy(tmp_buf + writesize + oob_skip, buf, + len); + buf += len; + } + } + } + + if (oob_required) { + const u8 *oob = chip->oob_poi; + u32 oob_data_offset = (cdns_chip->sector_count - 1) * + (cdns_chip->sector_size + chip->ecc.bytes) + + cdns_chip->sector_size + oob_skip; + + /* BBM at the beginning of the OOB area. */ + memcpy(tmp_buf + writesize, oob, oob_skip); + + /* OOB free. */ + memcpy(tmp_buf + oob_data_offset, oob, + cdns_chip->avail_oob_size); + oob += cdns_chip->avail_oob_size; + + /* OOB ECC. */ + for (i = 0; i < ecc_steps; i++) { + pos = ecc_size + i * (ecc_size + ecc_bytes); + if (i == (ecc_steps - 1)) + pos += cdns_chip->avail_oob_size; + + len = ecc_bytes; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(tmp_buf + pos, oob, len); + oob += len; + if (len < ecc_bytes) { + len = ecc_bytes - len; + memcpy(tmp_buf + writesize + oob_skip, oob, + len); + oob += len; + } + } + } + + cadence_nand_prepare_data_size(chip, TT_RAW_PAGE); + + return cadence_nand_cdma_transfer(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, cdns_ctrl->buf, NULL, + mtd->writesize + + mtd->oobsize, + 0, DMA_TO_DEVICE, false); +} + +static int cadence_nand_write_oob_raw(struct nand_chip *chip, + int page) +{ + return cadence_nand_write_page_raw(chip, NULL, true, page); +} + +static int cadence_nand_read_page(struct nand_chip *chip, + u8 *buf, int oob_required, int page) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int status = 0; + int ecc_err_count = 0; + + status = cadence_nand_select_target(chip); + if (status) + return status; + + cadence_nand_set_skip_bytes_conf(cdns_ctrl, cdns_chip->bbm_len, + mtd->writesize + + cdns_chip->bbm_offs, 1); + + /* + * If data buffer can be accessed by DMA and data_control feature + * is supported then transfer data and oob directly. + */ + if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, mtd->writesize) && + cdns_ctrl->caps2.data_control_supp) { + u8 *oob; + + if (oob_required) + oob = chip->oob_poi; + else + oob = cdns_ctrl->buf + mtd->writesize; + + cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREA_EXT); + status = cadence_nand_cdma_transfer(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, buf, oob, + mtd->writesize, + cdns_chip->avail_oob_size, + DMA_FROM_DEVICE, true); + /* Otherwise use bounce buffer. */ + } else { + cadence_nand_prepare_data_size(chip, TT_MAIN_OOB_AREAS); + status = cadence_nand_cdma_transfer(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, cdns_ctrl->buf, + NULL, mtd->writesize + + cdns_chip->avail_oob_size, + 0, DMA_FROM_DEVICE, true); + + memcpy(buf, cdns_ctrl->buf, mtd->writesize); + if (oob_required) + memcpy(chip->oob_poi, + cdns_ctrl->buf + mtd->writesize, + mtd->oobsize); + } + + switch (status) { + case STAT_ECC_UNCORR: + mtd->ecc_stats.failed++; + ecc_err_count++; + break; + case STAT_ECC_CORR: + ecc_err_count = FIELD_GET(CDMA_CS_MAXERR, + cdns_ctrl->cdma_desc->status); + mtd->ecc_stats.corrected += ecc_err_count; + break; + case STAT_ERASED: + case STAT_OK: + break; + default: + dev_err(cdns_ctrl->dev, "read page failed\n"); + return -EIO; + } + + if (oob_required) + if (cadence_nand_read_bbm(chip, page, chip->oob_poi)) + return -EIO; + + return ecc_err_count; +} + +/* Reads OOB data from the device. */ +static int cadence_nand_read_oob(struct nand_chip *chip, int page) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + + return cadence_nand_read_page(chip, cdns_ctrl->buf, 1, page); +} + +static int cadence_nand_read_page_raw(struct nand_chip *chip, + u8 *buf, int oob_required, int page) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + struct mtd_info *mtd = nand_to_mtd(chip); + int oob_skip = cdns_chip->bbm_len; + int writesize = mtd->writesize; + int ecc_steps = chip->ecc.steps; + int ecc_size = chip->ecc.size; + int ecc_bytes = chip->ecc.bytes; + void *tmp_buf = cdns_ctrl->buf; + int i, pos, len; + int status = 0; + + status = cadence_nand_select_target(chip); + if (status) + return status; + + cadence_nand_set_skip_bytes_conf(cdns_ctrl, 0, 0, 0); + + cadence_nand_prepare_data_size(chip, TT_RAW_PAGE); + status = cadence_nand_cdma_transfer(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + page, cdns_ctrl->buf, NULL, + mtd->writesize + + mtd->oobsize, + 0, DMA_FROM_DEVICE, false); + + switch (status) { + case STAT_ERASED: + case STAT_OK: + break; + default: + dev_err(cdns_ctrl->dev, "read raw page failed\n"); + return -EIO; + } + + /* Arrange the buffer for syndrome payload/ecc layout. */ + if (buf) { + for (i = 0; i < ecc_steps; i++) { + pos = i * (ecc_size + ecc_bytes); + len = ecc_size; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(buf, tmp_buf + pos, len); + buf += len; + if (len < ecc_size) { + len = ecc_size - len; + memcpy(buf, tmp_buf + writesize + oob_skip, + len); + buf += len; + } + } + } + + if (oob_required) { + u8 *oob = chip->oob_poi; + u32 oob_data_offset = (cdns_chip->sector_count - 1) * + (cdns_chip->sector_size + chip->ecc.bytes) + + cdns_chip->sector_size + oob_skip; + + /* OOB free. */ + memcpy(oob, tmp_buf + oob_data_offset, + cdns_chip->avail_oob_size); + + /* BBM at the beginning of the OOB area. */ + memcpy(oob, tmp_buf + writesize, oob_skip); + + oob += cdns_chip->avail_oob_size; + + /* OOB ECC */ + for (i = 0; i < ecc_steps; i++) { + pos = ecc_size + i * (ecc_size + ecc_bytes); + len = ecc_bytes; + + if (i == (ecc_steps - 1)) + pos += cdns_chip->avail_oob_size; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(oob, tmp_buf + pos, len); + oob += len; + if (len < ecc_bytes) { + len = ecc_bytes - len; + memcpy(oob, tmp_buf + writesize + oob_skip, + len); + oob += len; + } + } + } + + return 0; +} + +static int cadence_nand_read_oob_raw(struct nand_chip *chip, + int page) +{ + return cadence_nand_read_page_raw(chip, NULL, true, page); +} + +static void cadence_nand_slave_dma_transfer_finished(void *data) +{ + struct completion *finished = data; + + complete(finished); +} + +static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl, + void *buf, + dma_addr_t dev_dma, size_t len, + enum dma_data_direction dir) +{ + DECLARE_COMPLETION_ONSTACK(finished); + struct dma_chan *chan; + struct dma_device *dma_dev; + dma_addr_t src_dma, dst_dma, buf_dma; + struct dma_async_tx_descriptor *tx; + dma_cookie_t cookie; + + chan = cdns_ctrl->dmac; + dma_dev = chan->device; + + buf_dma = dma_map_single(dma_dev->dev, buf, len, dir); + if (dma_mapping_error(dma_dev->dev, buf_dma)) { + dev_err(cdns_ctrl->dev, "Failed to map DMA buffer\n"); + goto err; + } + + if (dir == DMA_FROM_DEVICE) { + src_dma = cdns_ctrl->io.dma; + dst_dma = buf_dma; + } else { + src_dma = buf_dma; + dst_dma = cdns_ctrl->io.dma; + } + + tx = dmaengine_prep_dma_memcpy(cdns_ctrl->dmac, dst_dma, src_dma, len, + DMA_CTRL_ACK | DMA_PREP_INTERRUPT); + if (!tx) { + dev_err(cdns_ctrl->dev, "Failed to prepare DMA memcpy\n"); + goto err_unmap; + } + + tx->callback = cadence_nand_slave_dma_transfer_finished; + tx->callback_param = &finished; + + cookie = dmaengine_submit(tx); + if (dma_submit_error(cookie)) { + dev_err(cdns_ctrl->dev, "Failed to do DMA tx_submit\n"); + goto err_unmap; + } + + dma_async_issue_pending(cdns_ctrl->dmac); + wait_for_completion(&finished); + + dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir); + + return 0; + +err_unmap: + dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir); + +err: + dev_dbg(cdns_ctrl->dev, "Fall back to CPU I/O\n"); + + return -EIO; +} + +static int cadence_nand_read_buf(struct cdns_nand_ctrl *cdns_ctrl, + u8 *buf, int len) +{ + u8 thread_nr = 0; + u32 sdma_size; + int status; + + /* Wait until slave DMA interface is ready to data transfer. */ + status = cadence_nand_wait_on_sdma(cdns_ctrl, &thread_nr, &sdma_size); + if (status) + return status; + + if (!cdns_ctrl->caps1->has_dma) { + int len_in_words = len >> 2; + + /* read alingment data */ + ioread32_rep(cdns_ctrl->io.virt, buf, len_in_words); + if (sdma_size > len) { + /* read rest data from slave DMA interface if any */ + ioread32_rep(cdns_ctrl->io.virt, cdns_ctrl->buf, + sdma_size / 4 - len_in_words); + /* copy rest of data */ + memcpy(buf + (len_in_words << 2), cdns_ctrl->buf, + len - (len_in_words << 2)); + } + return 0; + } + + if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, len)) { + status = cadence_nand_slave_dma_transfer(cdns_ctrl, buf, + cdns_ctrl->io.dma, + len, DMA_FROM_DEVICE); + if (status == 0) + return 0; + + dev_warn(cdns_ctrl->dev, + "Slave DMA transfer failed. Try again using bounce buffer."); + } + + /* If DMA transfer is not possible or failed then use bounce buffer. */ + status = cadence_nand_slave_dma_transfer(cdns_ctrl, cdns_ctrl->buf, + cdns_ctrl->io.dma, + sdma_size, DMA_FROM_DEVICE); + + if (status) { + dev_err(cdns_ctrl->dev, "Slave DMA transfer failed"); + return status; + } + + memcpy(buf, cdns_ctrl->buf, len); + + return 0; +} + +static int cadence_nand_write_buf(struct cdns_nand_ctrl *cdns_ctrl, + const u8 *buf, int len) +{ + u8 thread_nr = 0; + u32 sdma_size; + int status; + + /* Wait until slave DMA interface is ready to data transfer. */ + status = cadence_nand_wait_on_sdma(cdns_ctrl, &thread_nr, &sdma_size); + if (status) + return status; + + if (!cdns_ctrl->caps1->has_dma) { + int len_in_words = len >> 2; + + iowrite32_rep(cdns_ctrl->io.virt, buf, len_in_words); + if (sdma_size > len) { + /* copy rest of data */ + memcpy(cdns_ctrl->buf, buf + (len_in_words << 2), + len - (len_in_words << 2)); + /* write all expected by nand controller data */ + iowrite32_rep(cdns_ctrl->io.virt, cdns_ctrl->buf, + sdma_size / 4 - len_in_words); + } + + return 0; + } + + if (cadence_nand_dma_buf_ok(cdns_ctrl, buf, len)) { + status = cadence_nand_slave_dma_transfer(cdns_ctrl, (void *)buf, + cdns_ctrl->io.dma, + len, DMA_TO_DEVICE); + if (status == 0) + return 0; + + dev_warn(cdns_ctrl->dev, + "Slave DMA transfer failed. Try again using bounce buffer."); + } + + /* If DMA transfer is not possible or failed then use bounce buffer. */ + memcpy(cdns_ctrl->buf, buf, len); + + status = cadence_nand_slave_dma_transfer(cdns_ctrl, cdns_ctrl->buf, + cdns_ctrl->io.dma, + sdma_size, DMA_TO_DEVICE); + + if (status) + dev_err(cdns_ctrl->dev, "Slave DMA transfer failed"); + + return status; +} + +static int cadence_nand_force_byte_access(struct nand_chip *chip, + bool force_8bit) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + int status; + + /* + * Callers of this function do not verify if the NAND is using a 16-bit + * an 8-bit bus for normal operations, so we need to take care of that + * here by leaving the configuration unchanged if the NAND does not have + * the NAND_BUSWIDTH_16 flag set. + */ + if (!(chip->options & NAND_BUSWIDTH_16)) + return 0; + + status = cadence_nand_set_access_width16(cdns_ctrl, !force_8bit); + + return status; +} + +static int cadence_nand_cmd_opcode(struct nand_chip *chip, + const struct nand_subop *subop) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + const struct nand_op_instr *instr; + unsigned int op_id = 0; + u64 mini_ctrl_cmd = 0; + int ret; + + instr = &subop->instrs[op_id]; + + if (instr->delay_ns > 0) + mini_ctrl_cmd |= GCMD_LAY_TWB; + + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR, + GCMD_LAY_INSTR_CMD); + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_CMD, + instr->ctx.cmd.opcode); + + ret = cadence_nand_generic_cmd_send(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + mini_ctrl_cmd); + if (ret) + dev_err(cdns_ctrl->dev, "send cmd %x failed\n", + instr->ctx.cmd.opcode); + + return ret; +} + +static int cadence_nand_cmd_address(struct nand_chip *chip, + const struct nand_subop *subop) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + const struct nand_op_instr *instr; + unsigned int op_id = 0; + u64 mini_ctrl_cmd = 0; + unsigned int offset, naddrs; + u64 address = 0; + const u8 *addrs; + int ret; + int i; + + instr = &subop->instrs[op_id]; + + if (instr->delay_ns > 0) + mini_ctrl_cmd |= GCMD_LAY_TWB; + + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR, + GCMD_LAY_INSTR_ADDR); + + offset = nand_subop_get_addr_start_off(subop, op_id); + naddrs = nand_subop_get_num_addr_cyc(subop, op_id); + addrs = &instr->ctx.addr.addrs[offset]; + + for (i = 0; i < naddrs; i++) + address |= (u64)addrs[i] << (8 * i); + + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_ADDR, + address); + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INPUT_ADDR_SIZE, + naddrs - 1); + + ret = cadence_nand_generic_cmd_send(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + mini_ctrl_cmd); + if (ret) + dev_err(cdns_ctrl->dev, "send address %llx failed\n", address); + + return ret; +} + +static int cadence_nand_cmd_erase(struct nand_chip *chip, + const struct nand_subop *subop) +{ + unsigned int op_id; + + if (subop->instrs[0].ctx.cmd.opcode == NAND_CMD_ERASE1) { + int i; + const struct nand_op_instr *instr = NULL; + unsigned int offset, naddrs; + const u8 *addrs; + u32 page = 0; + + instr = &subop->instrs[1]; + offset = nand_subop_get_addr_start_off(subop, 1); + naddrs = nand_subop_get_num_addr_cyc(subop, 1); + addrs = &instr->ctx.addr.addrs[offset]; + + for (i = 0; i < naddrs; i++) + page |= (u32)addrs[i] << (8 * i); + + return cadence_nand_erase(chip, page); + } + + /* + * If it is not an erase operation then handle operation + * by calling exec_op function. + */ + for (op_id = 0; op_id < subop->ninstrs; op_id++) { + int ret; + const struct nand_operation nand_op = { + .cs = chip->cur_cs, + .instrs = &subop->instrs[op_id], + .ninstrs = 1}; + ret = chip->controller->ops->exec_op(chip, &nand_op, false); + if (ret) + return ret; + } + + return 0; +} + +static int cadence_nand_cmd_data(struct nand_chip *chip, + const struct nand_subop *subop) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + const struct nand_op_instr *instr; + unsigned int offset, op_id = 0; + u64 mini_ctrl_cmd = 0; + int len = 0; + int ret; + + instr = &subop->instrs[op_id]; + + if (instr->delay_ns > 0) + mini_ctrl_cmd |= GCMD_LAY_TWB; + + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAY_INSTR, + GCMD_LAY_INSTR_DATA); + + if (instr->type == NAND_OP_DATA_OUT_INSTR) + mini_ctrl_cmd |= FIELD_PREP(GCMD_DIR, + GCMD_DIR_WRITE); + + len = nand_subop_get_data_len(subop, op_id); + offset = nand_subop_get_data_start_off(subop, op_id); + mini_ctrl_cmd |= FIELD_PREP(GCMD_SECT_CNT, 1); + mini_ctrl_cmd |= FIELD_PREP(GCMD_LAST_SIZE, len); + if (instr->ctx.data.force_8bit) { + ret = cadence_nand_force_byte_access(chip, true); + if (ret) { + dev_err(cdns_ctrl->dev, + "cannot change byte access generic data cmd failed\n"); + return ret; + } + } + + ret = cadence_nand_generic_cmd_send(cdns_ctrl, + cdns_chip->cs[chip->cur_cs], + mini_ctrl_cmd); + if (ret) { + dev_err(cdns_ctrl->dev, "send generic data cmd failed\n"); + return ret; + } + + if (instr->type == NAND_OP_DATA_IN_INSTR) { + void *buf = instr->ctx.data.buf.in + offset; + + ret = cadence_nand_read_buf(cdns_ctrl, buf, len); + } else { + const void *buf = instr->ctx.data.buf.out + offset; + + ret = cadence_nand_write_buf(cdns_ctrl, buf, len); + } + + if (ret) { + dev_err(cdns_ctrl->dev, "data transfer failed for generic command\n"); + return ret; + } + + if (instr->ctx.data.force_8bit) { + ret = cadence_nand_force_byte_access(chip, false); + if (ret) { + dev_err(cdns_ctrl->dev, + "cannot change byte access generic data cmd failed\n"); + } + } + + return ret; +} + +static int cadence_nand_cmd_waitrdy(struct nand_chip *chip, + const struct nand_subop *subop) +{ + int status; + unsigned int op_id = 0; + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + const struct nand_op_instr *instr = &subop->instrs[op_id]; + u32 timeout_us = instr->ctx.waitrdy.timeout_ms * 1000; + + status = cadence_nand_wait_for_value(cdns_ctrl, RBN_SETINGS, + timeout_us, + BIT(cdns_chip->cs[chip->cur_cs]), + false); + return status; +} + +static const struct nand_op_parser cadence_nand_op_parser = NAND_OP_PARSER( + NAND_OP_PARSER_PATTERN( + cadence_nand_cmd_erase, + NAND_OP_PARSER_PAT_CMD_ELEM(false), + NAND_OP_PARSER_PAT_ADDR_ELEM(false, MAX_ERASE_ADDRESS_CYC), + NAND_OP_PARSER_PAT_CMD_ELEM(false), + NAND_OP_PARSER_PAT_WAITRDY_ELEM(false)), + NAND_OP_PARSER_PATTERN( + cadence_nand_cmd_opcode, + NAND_OP_PARSER_PAT_CMD_ELEM(false)), + NAND_OP_PARSER_PATTERN( + cadence_nand_cmd_address, + NAND_OP_PARSER_PAT_ADDR_ELEM(false, MAX_ADDRESS_CYC)), + NAND_OP_PARSER_PATTERN( + cadence_nand_cmd_data, + NAND_OP_PARSER_PAT_DATA_IN_ELEM(false, MAX_DATA_SIZE)), + NAND_OP_PARSER_PATTERN( + cadence_nand_cmd_data, + NAND_OP_PARSER_PAT_DATA_OUT_ELEM(false, MAX_DATA_SIZE)), + NAND_OP_PARSER_PATTERN( + cadence_nand_cmd_waitrdy, + NAND_OP_PARSER_PAT_WAITRDY_ELEM(false)) + ); + +static int cadence_nand_exec_op(struct nand_chip *chip, + const struct nand_operation *op, + bool check_only) +{ + int status = cadence_nand_select_target(chip); + + if (status) + return status; + + return nand_op_parser_exec_op(chip, &cadence_nand_op_parser, op, + check_only); +} + +static int cadence_nand_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobregion) +{ + struct nand_chip *chip = mtd_to_nand(mtd); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + + if (section) + return -ERANGE; + + oobregion->offset = cdns_chip->bbm_len; + oobregion->length = cdns_chip->avail_oob_size + - cdns_chip->bbm_len; + + return 0; +} + +static int cadence_nand_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobregion) +{ + struct nand_chip *chip = mtd_to_nand(mtd); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + + if (section) + return -ERANGE; + + oobregion->offset = cdns_chip->avail_oob_size; + oobregion->length = chip->ecc.total; + + return 0; +} + +static const struct mtd_ooblayout_ops cadence_nand_ooblayout_ops = { + .free = cadence_nand_ooblayout_free, + .ecc = cadence_nand_ooblayout_ecc, +}; + +static int calc_cycl(u32 timing, u32 clock) +{ + if (timing == 0 || clock == 0) + return 0; + + if ((timing % clock) > 0) + return timing / clock; + else + return timing / clock - 1; +} + +/* Calculate max data valid window. */ +static inline u32 calc_tdvw_max(u32 trp_cnt, u32 clk_period, u32 trhoh_min, + u32 board_delay_skew_min, u32 ext_mode) +{ + if (ext_mode == 0) + clk_period /= 2; + + return (trp_cnt + 1) * clk_period + trhoh_min + + board_delay_skew_min; +} + +/* Calculate data valid window. */ +static inline u32 calc_tdvw(u32 trp_cnt, u32 clk_period, u32 trhoh_min, + u32 trea_max, u32 ext_mode) +{ + if (ext_mode == 0) + clk_period /= 2; + + return (trp_cnt + 1) * clk_period + trhoh_min - trea_max; +} + +static int +cadence_nand_setup_data_interface(struct nand_chip *chip, int chipnr, + const struct nand_data_interface *conf) +{ + const struct nand_sdr_timings *sdr; + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + struct cadence_nand_timings *t = &cdns_chip->timings; + u32 reg; + u32 board_delay = cdns_ctrl->board_delay; + u32 clk_period = DIV_ROUND_DOWN_ULL(1000000000000ULL, + cdns_ctrl->nf_clk_rate); + u32 tceh_cnt, tcs_cnt, tadl_cnt, tccs_cnt; + u32 tfeat_cnt, trhz_cnt, tvdly_cnt; + u32 trhw_cnt, twb_cnt, twh_cnt = 0, twhr_cnt; + u32 twp_cnt = 0, trp_cnt = 0, trh_cnt = 0; + u32 if_skew = cdns_ctrl->caps1->if_skew; + u32 board_delay_skew_min = board_delay - if_skew; + u32 board_delay_skew_max = board_delay + if_skew; + u32 dqs_sampl_res, phony_dqs_mod; + u32 tdvw, tdvw_min, tdvw_max; + u32 ext_rd_mode, ext_wr_mode; + u32 dll_phy_dqs_timing = 0, phony_dqs_timing = 0, rd_del_sel = 0; + u32 sampling_point; + + sdr = nand_get_sdr_timings(conf); + if (IS_ERR(sdr)) + return PTR_ERR(sdr); + + memset(t, 0, sizeof(*t)); + /* Sampling point calculation. */ + + if (cdns_ctrl->caps2.is_phy_type_dll) + phony_dqs_mod = 2; + else + phony_dqs_mod = 1; + + dqs_sampl_res = clk_period / phony_dqs_mod; + + tdvw_min = sdr->tREA_max + board_delay_skew_max; + /* + * The idea of those calculation is to get the optimum value + * for tRP and tRH timings. If it is NOT possible to sample data + * with optimal tRP/tRH settings, the parameters will be extended. + * If clk_period is 50ns (the lowest value) this condition is met + * for asynchronous timing modes 1, 2, 3, 4 and 5. + * If clk_period is 20ns the condition is met only + * for asynchronous timing mode 5. + */ + if (sdr->tRC_min <= clk_period && + sdr->tRP_min <= (clk_period / 2) && + sdr->tREH_min <= (clk_period / 2)) { + /* Performance mode. */ + ext_rd_mode = 0; + tdvw = calc_tdvw(trp_cnt, clk_period, sdr->tRHOH_min, + sdr->tREA_max, ext_rd_mode); + tdvw_max = calc_tdvw_max(trp_cnt, clk_period, sdr->tRHOH_min, + board_delay_skew_min, + ext_rd_mode); + /* + * Check if data valid window and sampling point can be found + * and is not on the edge (ie. we have hold margin). + * If not extend the tRP timings. + */ + if (tdvw > 0) { + if (tdvw_max <= tdvw_min || + (tdvw_max % dqs_sampl_res) == 0) { + /* + * No valid sampling point so the RE pulse need + * to be widen widening by half clock cycle. + */ + ext_rd_mode = 1; + } + } else { + /* + * There is no valid window + * to be able to sample data the tRP need to be widen. + * Very safe calculations are performed here. + */ + trp_cnt = (sdr->tREA_max + board_delay_skew_max + + dqs_sampl_res) / clk_period; + ext_rd_mode = 1; + } + + } else { + /* Extended read mode. */ + u32 trh; + + ext_rd_mode = 1; + trp_cnt = calc_cycl(sdr->tRP_min, clk_period); + trh = sdr->tRC_min - ((trp_cnt + 1) * clk_period); + if (sdr->tREH_min >= trh) + trh_cnt = calc_cycl(sdr->tREH_min, clk_period); + else + trh_cnt = calc_cycl(trh, clk_period); + + tdvw = calc_tdvw(trp_cnt, clk_period, sdr->tRHOH_min, + sdr->tREA_max, ext_rd_mode); + /* + * Check if data valid window and sampling point can be found + * or if it is at the edge check if previous is valid + * - if not extend the tRP timings. + */ + if (tdvw > 0) { + tdvw_max = calc_tdvw_max(trp_cnt, clk_period, + sdr->tRHOH_min, + board_delay_skew_min, + ext_rd_mode); + + if ((((tdvw_max / dqs_sampl_res) + * dqs_sampl_res) <= tdvw_min) || + (((tdvw_max % dqs_sampl_res) == 0) && + (((tdvw_max / dqs_sampl_res - 1) + * dqs_sampl_res) <= tdvw_min))) { + /* + * Data valid window width is lower than + * sampling resolution and do not hit any + * sampling point to be sure the sampling point + * will be found the RE low pulse width will be + * extended by one clock cycle. + */ + trp_cnt = trp_cnt + 1; + } + } else { + /* + * There is no valid window to be able to sample data. + * The tRP need to be widen. + * Very safe calculations are performed here. + */ + trp_cnt = (sdr->tREA_max + board_delay_skew_max + + dqs_sampl_res) / clk_period; + } + } + + tdvw_max = calc_tdvw_max(trp_cnt, clk_period, + sdr->tRHOH_min, + board_delay_skew_min, ext_rd_mode); + + if (sdr->tWC_min <= clk_period && + (sdr->tWP_min + if_skew) <= (clk_period / 2) && + (sdr->tWH_min + if_skew) <= (clk_period / 2)) { + ext_wr_mode = 0; + } else { + u32 twh; + + ext_wr_mode = 1; + twp_cnt = calc_cycl(sdr->tWP_min + if_skew, clk_period); + if ((twp_cnt + 1) * clk_period < (sdr->tALS_min + if_skew)) + twp_cnt = calc_cycl(sdr->tALS_min + if_skew, + clk_period); + + twh = (sdr->tWC_min - (twp_cnt + 1) * clk_period); + if (sdr->tWH_min >= twh) + twh = sdr->tWH_min; + + twh_cnt = calc_cycl(twh + if_skew, clk_period); + } + + reg = FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TRH, trh_cnt); + reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TRP, trp_cnt); + reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TWH, twh_cnt); + reg |= FIELD_PREP(ASYNC_TOGGLE_TIMINGS_TWP, twp_cnt); + t->async_toggle_timings = reg; + dev_dbg(cdns_ctrl->dev, "ASYNC_TOGGLE_TIMINGS_SDR\t%x\n", reg); + + tadl_cnt = calc_cycl((sdr->tADL_min + if_skew), clk_period); + tccs_cnt = calc_cycl((sdr->tCCS_min + if_skew), clk_period); + twhr_cnt = calc_cycl((sdr->tWHR_min + if_skew), clk_period); + trhw_cnt = calc_cycl((sdr->tRHW_min + if_skew), clk_period); + reg = FIELD_PREP(TIMINGS0_TADL, tadl_cnt); + + /* + * If timing exceeds delay field in timing register + * then use maximum value. + */ + if (FIELD_FIT(TIMINGS0_TCCS, tccs_cnt)) + reg |= FIELD_PREP(TIMINGS0_TCCS, tccs_cnt); + else + reg |= TIMINGS0_TCCS; + + reg |= FIELD_PREP(TIMINGS0_TWHR, twhr_cnt); + reg |= FIELD_PREP(TIMINGS0_TRHW, trhw_cnt); + t->timings0 = reg; + dev_dbg(cdns_ctrl->dev, "TIMINGS0_SDR\t%x\n", reg); + + /* The following is related to single signal so skew is not needed. */ + trhz_cnt = calc_cycl(sdr->tRHZ_max, clk_period); + trhz_cnt = trhz_cnt + 1; + twb_cnt = calc_cycl((sdr->tWB_max + board_delay), clk_period); + /* + * Because of the two stage syncflop the value must be increased by 3 + * first value is related with sync, second value is related + * with output if delay. + */ + twb_cnt = twb_cnt + 3 + 5; + /* + * The following is related to the we edge of the random data input + * sequence so skew is not needed. + */ + tvdly_cnt = calc_cycl(500000 + if_skew, clk_period); + reg = FIELD_PREP(TIMINGS1_TRHZ, trhz_cnt); + reg |= FIELD_PREP(TIMINGS1_TWB, twb_cnt); + reg |= FIELD_PREP(TIMINGS1_TVDLY, tvdly_cnt); + t->timings1 = reg; + dev_dbg(cdns_ctrl->dev, "TIMINGS1_SDR\t%x\n", reg); + + tfeat_cnt = calc_cycl(sdr->tFEAT_max, clk_period); + if (tfeat_cnt < twb_cnt) + tfeat_cnt = twb_cnt; + + tceh_cnt = calc_cycl(sdr->tCEH_min, clk_period); + tcs_cnt = calc_cycl((sdr->tCS_min + if_skew), clk_period); + + reg = FIELD_PREP(TIMINGS2_TFEAT, tfeat_cnt); + reg |= FIELD_PREP(TIMINGS2_CS_HOLD_TIME, tceh_cnt); + reg |= FIELD_PREP(TIMINGS2_CS_SETUP_TIME, tcs_cnt); + t->timings2 = reg; + dev_dbg(cdns_ctrl->dev, "TIMINGS2_SDR\t%x\n", reg); + + if (cdns_ctrl->caps2.is_phy_type_dll) { + reg = DLL_PHY_CTRL_DLL_RST_N; + if (ext_wr_mode) + reg |= DLL_PHY_CTRL_EXTENDED_WR_MODE; + if (ext_rd_mode) + reg |= DLL_PHY_CTRL_EXTENDED_RD_MODE; + + reg |= FIELD_PREP(DLL_PHY_CTRL_RS_HIGH_WAIT_CNT, 7); + reg |= FIELD_PREP(DLL_PHY_CTRL_RS_IDLE_CNT, 7); + t->dll_phy_ctrl = reg; + dev_dbg(cdns_ctrl->dev, "DLL_PHY_CTRL_SDR\t%x\n", reg); + } + + /* Sampling point calculation. */ + if ((tdvw_max % dqs_sampl_res) > 0) + sampling_point = tdvw_max / dqs_sampl_res; + else + sampling_point = (tdvw_max / dqs_sampl_res - 1); + + if (sampling_point * dqs_sampl_res > tdvw_min) { + dll_phy_dqs_timing = + FIELD_PREP(PHY_DQS_TIMING_DQS_SEL_OE_END, 4); + dll_phy_dqs_timing |= PHY_DQS_TIMING_USE_PHONY_DQS; + phony_dqs_timing = sampling_point / phony_dqs_mod; + + if ((sampling_point % 2) > 0) { + dll_phy_dqs_timing |= PHY_DQS_TIMING_PHONY_DQS_SEL; + if ((tdvw_max % dqs_sampl_res) == 0) + /* + * Calculation for sampling point at the edge + * of data and being odd number. + */ + phony_dqs_timing = (tdvw_max / dqs_sampl_res) + / phony_dqs_mod - 1; + + if (!cdns_ctrl->caps2.is_phy_type_dll) + phony_dqs_timing--; + + } else { + phony_dqs_timing--; + } + rd_del_sel = phony_dqs_timing + 3; + } else { + dev_warn(cdns_ctrl->dev, + "ERROR : cannot find valid sampling point\n"); + } + + reg = FIELD_PREP(PHY_CTRL_PHONY_DQS, phony_dqs_timing); + if (cdns_ctrl->caps2.is_phy_type_dll) + reg |= PHY_CTRL_SDR_DQS; + t->phy_ctrl = reg; + dev_dbg(cdns_ctrl->dev, "PHY_CTRL_REG_SDR\t%x\n", reg); + + if (cdns_ctrl->caps2.is_phy_type_dll) { + dev_dbg(cdns_ctrl->dev, "PHY_TSEL_REG_SDR\t%x\n", 0); + dev_dbg(cdns_ctrl->dev, "PHY_DQ_TIMING_REG_SDR\t%x\n", 2); + dev_dbg(cdns_ctrl->dev, "PHY_DQS_TIMING_REG_SDR\t%x\n", + dll_phy_dqs_timing); + t->phy_dqs_timing = dll_phy_dqs_timing; + + reg = FIELD_PREP(PHY_GATE_LPBK_CTRL_RDS, rd_del_sel); + dev_dbg(cdns_ctrl->dev, "PHY_GATE_LPBK_CTRL_REG_SDR\t%x\n", + reg); + t->phy_gate_lpbk_ctrl = reg; + + dev_dbg(cdns_ctrl->dev, "PHY_DLL_MASTER_CTRL_REG_SDR\t%lx\n", + PHY_DLL_MASTER_CTRL_BYPASS_MODE); + dev_dbg(cdns_ctrl->dev, "PHY_DLL_SLAVE_CTRL_REG_SDR\t%x\n", 0); + } + + return 0; +} + +int cadence_nand_attach_chip(struct nand_chip *chip) +{ + struct cdns_nand_ctrl *cdns_ctrl = to_cdns_nand_ctrl(chip->controller); + struct cdns_nand_chip *cdns_chip = to_cdns_nand_chip(chip); + u32 ecc_size = cdns_chip->sector_count * chip->ecc.bytes; + struct mtd_info *mtd = nand_to_mtd(chip); + u32 max_oob_data_size; + int ret; + + if (chip->options & NAND_BUSWIDTH_16) { + ret = cadence_nand_set_access_width16(cdns_ctrl, true); + if (ret) + return ret; + } + + chip->bbt_options |= NAND_BBT_USE_FLASH; + chip->bbt_options |= NAND_BBT_NO_OOB; + chip->ecc.mode = NAND_ECC_HW; + + chip->options |= NAND_NO_SUBPAGE_WRITE; + + cdns_chip->bbm_offs = chip->badblockpos; + if (chip->options & NAND_BUSWIDTH_16) { + cdns_chip->bbm_offs &= ~0x01; + cdns_chip->bbm_len = 2; + } else { + cdns_chip->bbm_len = 1; + } + + ret = nand_ecc_choose_conf(chip, + &cdns_ctrl->ecc_caps, + mtd->oobsize - cdns_chip->bbm_len); + if (ret) { + dev_err(cdns_ctrl->dev, "ECC configuration failed\n"); + return ret; + } + + dev_dbg(cdns_ctrl->dev, + "chosen ECC settings: step=%d, strength=%d, bytes=%d\n", + chip->ecc.size, chip->ecc.strength, chip->ecc.bytes); + + /* Error correction configuration. */ + cdns_chip->sector_size = chip->ecc.size; + cdns_chip->sector_count = mtd->writesize / cdns_chip->sector_size; + + cdns_chip->avail_oob_size = mtd->oobsize - ecc_size; + + max_oob_data_size = MAX_OOB_SIZE_PER_SECTOR; + + if (cdns_chip->avail_oob_size > max_oob_data_size) + cdns_chip->avail_oob_size = max_oob_data_size; + + if ((cdns_chip->avail_oob_size + cdns_chip->bbm_len + ecc_size) + > mtd->oobsize) + cdns_chip->avail_oob_size -= 4; + + ret = cadence_nand_get_ecc_strength_idx(cdns_ctrl, chip->ecc.strength); + if (ret < 0) + return -EINVAL; + + cdns_chip->corr_str_idx = (u8)ret; + + if (cadence_nand_wait_for_value(cdns_ctrl, CTRL_STATUS, + 1000000, + CTRL_STATUS_CTRL_BUSY, true)) + return -ETIMEDOUT; + + cadence_nand_set_ecc_strength(cdns_ctrl, + cdns_chip->corr_str_idx); + + cadence_nand_set_erase_detection(cdns_ctrl, true, + chip->ecc.strength); + + /* Override the default read operations. */ + chip->ecc.read_page = cadence_nand_read_page; + chip->ecc.read_page_raw = cadence_nand_read_page_raw; + chip->ecc.write_page = cadence_nand_write_page; + chip->ecc.write_page_raw = cadence_nand_write_page_raw; + chip->ecc.read_oob = cadence_nand_read_oob; + chip->ecc.write_oob = cadence_nand_write_oob; + chip->ecc.read_oob_raw = cadence_nand_read_oob_raw; + chip->ecc.write_oob_raw = cadence_nand_write_oob_raw; + + if ((mtd->writesize + mtd->oobsize) > cdns_ctrl->buf_size) + cdns_ctrl->buf_size = mtd->writesize + mtd->oobsize; + + /* Is 32-bit DMA supported? */ + ret = dma_set_mask(cdns_ctrl->dev, DMA_BIT_MASK(32)); + if (ret) { + dev_err(cdns_ctrl->dev, "no usable DMA configuration\n"); + return ret; + } + + mtd_set_ooblayout(mtd, &cadence_nand_ooblayout_ops); + + return 0; +} + +static const struct nand_controller_ops cadence_nand_controller_ops = { + .attach_chip = cadence_nand_attach_chip, + .exec_op = cadence_nand_exec_op, + .setup_data_interface = cadence_nand_setup_data_interface, +}; + +static int cadence_nand_chip_init(struct cdns_nand_ctrl *cdns_ctrl, + struct device_node *np) +{ + struct cdns_nand_chip *cdns_chip; + struct mtd_info *mtd; + struct nand_chip *chip; + int nsels, ret, i; + u32 cs; + + nsels = of_property_count_elems_of_size(np, "reg", sizeof(u32)); + if (nsels <= 0) { + dev_err(cdns_ctrl->dev, "missing/invalid reg property\n"); + return -EINVAL; + } + + /* Allocate the nand chip structure. */ + cdns_chip = devm_kzalloc(cdns_ctrl->dev, sizeof(*cdns_chip) + + (nsels * sizeof(u8)), + GFP_KERNEL); + if (!cdns_chip) { + dev_err(cdns_ctrl->dev, "could not allocate chip structure\n"); + return -ENOMEM; + } + + cdns_chip->nsels = nsels; + + for (i = 0; i < nsels; i++) { + /* Retrieve CS id. */ + ret = of_property_read_u32_index(np, "reg", i, &cs); + if (ret) { + dev_err(cdns_ctrl->dev, + "could not retrieve reg property: %d\n", + ret); + return ret; + } + + if (cs >= cdns_ctrl->caps2.max_banks) { + dev_err(cdns_ctrl->dev, + "invalid reg value: %u (max CS = %d)\n", + cs, cdns_ctrl->caps2.max_banks); + return -EINVAL; + } + + if (test_and_set_bit(cs, &cdns_ctrl->assigned_cs)) { + dev_err(cdns_ctrl->dev, + "CS %d already assigned\n", cs); + return -EINVAL; + } + + cdns_chip->cs[i] = cs; + } + + chip = &cdns_chip->chip; + chip->controller = &cdns_ctrl->controller; + nand_set_flash_node(chip, np); + + mtd = nand_to_mtd(chip); + mtd->dev.parent = cdns_ctrl->dev; + + /* + * Default to HW ECC engine mode. If the nand-ecc-mode property is given + * in the DT node, this entry will be overwritten in nand_scan_ident(). + */ + chip->ecc.mode = NAND_ECC_HW; + + ret = nand_scan(chip, cdns_chip->nsels); + if (ret) { + dev_err(cdns_ctrl->dev, "could not scan the nand chip\n"); + return ret; + } + + ret = mtd_device_register(mtd, NULL, 0); + if (ret) { + dev_err(cdns_ctrl->dev, + "failed to register mtd device: %d\n", ret); + nand_cleanup(chip); + return ret; + } + + list_add_tail(&cdns_chip->node, &cdns_ctrl->chips); + + return 0; +} + +static void cadence_nand_chips_cleanup(struct cdns_nand_ctrl *cdns_ctrl) +{ + struct cdns_nand_chip *entry, *temp; + + list_for_each_entry_safe(entry, temp, &cdns_ctrl->chips, node) { + nand_release(&entry->chip); + list_del(&entry->node); + } +} + +static int cadence_nand_chips_init(struct cdns_nand_ctrl *cdns_ctrl) +{ + struct device_node *np = cdns_ctrl->dev->of_node; + struct device_node *nand_np; + int max_cs = cdns_ctrl->caps2.max_banks; + int nchips, ret; + + nchips = of_get_child_count(np); + + if (nchips > max_cs) { + dev_err(cdns_ctrl->dev, + "too many NAND chips: %d (max = %d CS)\n", + nchips, max_cs); + return -EINVAL; + } + + for_each_child_of_node(np, nand_np) { + ret = cadence_nand_chip_init(cdns_ctrl, nand_np); + if (ret) { + of_node_put(nand_np); + cadence_nand_chips_cleanup(cdns_ctrl); + return ret; + } + } + + return 0; +} + +static void +cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl) +{ + /* Disable interrupts. */ + writel_relaxed(INTR_ENABLE_INTR_EN, cdns_ctrl->reg + INTR_ENABLE); +} + +static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl) +{ + dma_cap_mask_t mask; + int ret; + + cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev, + sizeof(*cdns_ctrl->cdma_desc), + &cdns_ctrl->dma_cdma_desc, + GFP_KERNEL); + if (!cdns_ctrl->dma_cdma_desc) + return -ENOMEM; + + cdns_ctrl->buf_size = SZ_16K; + cdns_ctrl->buf = kmalloc(cdns_ctrl->buf_size, GFP_KERNEL); + if (!cdns_ctrl->buf) { + ret = -ENOMEM; + goto free_buf_desc; + } + + if (devm_request_irq(cdns_ctrl->dev, cdns_ctrl->irq, cadence_nand_isr, + IRQF_SHARED, "cadence-nand-controller", + cdns_ctrl)) { + dev_err(cdns_ctrl->dev, "Unable to allocate IRQ\n"); + ret = -ENODEV; + goto free_buf; + } + + spin_lock_init(&cdns_ctrl->irq_lock); + init_completion(&cdns_ctrl->complete); + + ret = cadence_nand_hw_init(cdns_ctrl); + if (ret) + goto disable_irq; + + dma_cap_zero(mask); + dma_cap_set(DMA_MEMCPY, mask); + + if (cdns_ctrl->caps1->has_dma) { + cdns_ctrl->dmac = dma_request_channel(mask, NULL, NULL); + if (!cdns_ctrl->dmac) { + dev_err(cdns_ctrl->dev, + "Unable to get a DMA channel\n"); + ret = -EBUSY; + goto disable_irq; + } + } + + nand_controller_init(&cdns_ctrl->controller); + INIT_LIST_HEAD(&cdns_ctrl->chips); + + cdns_ctrl->controller.ops = &cadence_nand_controller_ops; + cdns_ctrl->curr_corr_str_idx = 0xFF; + + ret = cadence_nand_chips_init(cdns_ctrl); + if (ret) { + dev_err(cdns_ctrl->dev, "Failed to register MTD: %d\n", + ret); + goto dma_release_chnl; + } + + kfree(cdns_ctrl->buf); + cdns_ctrl->buf = kzalloc(cdns_ctrl->buf_size, GFP_KERNEL); + if (!cdns_ctrl->buf) { + ret = -ENOMEM; + goto dma_release_chnl; + } + + return 0; + +dma_release_chnl: + if (cdns_ctrl->dmac) + dma_release_channel(cdns_ctrl->dmac); + +disable_irq: + cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl); + +free_buf: + kfree(cdns_ctrl->buf); + +free_buf_desc: + dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc), + cdns_ctrl->cdma_desc, cdns_ctrl->dma_cdma_desc); + + return ret; +} + +/* Driver exit point. */ +static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl) +{ + cadence_nand_chips_cleanup(cdns_ctrl); + cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl); + kfree(cdns_ctrl->buf); + dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc), + cdns_ctrl->cdma_desc, cdns_ctrl->dma_cdma_desc); + + if (cdns_ctrl->dmac) + dma_release_channel(cdns_ctrl->dmac); +} + +struct cadence_nand_dt { + struct cdns_nand_ctrl cdns_ctrl; + struct clk *clk; +}; + +static const struct cadence_nand_dt_devdata cadence_nand_default = { + .if_skew = 0, + .has_dma = 1, +}; + +static const struct of_device_id cadence_nand_dt_ids[] = { + { + .compatible = "cdns,hp-nfc", + .data = &cadence_nand_default + }, {} +}; + +MODULE_DEVICE_TABLE(of, cadence_nand_dt_ids); + +static int cadence_nand_dt_probe(struct platform_device *ofdev) +{ + struct resource *res; + struct cadence_nand_dt *dt; + struct cdns_nand_ctrl *cdns_ctrl; + int ret; + const struct of_device_id *of_id; + const struct cadence_nand_dt_devdata *devdata; + u32 val; + + of_id = of_match_device(cadence_nand_dt_ids, &ofdev->dev); + if (of_id) { + ofdev->id_entry = of_id->data; + devdata = of_id->data; + } else { + pr_err("Failed to find the right device id.\n"); + return -ENOMEM; + } + + dt = devm_kzalloc(&ofdev->dev, sizeof(*dt), GFP_KERNEL); + if (!dt) + return -ENOMEM; + + cdns_ctrl = &dt->cdns_ctrl; + cdns_ctrl->caps1 = devdata; + + cdns_ctrl->dev = &ofdev->dev; + cdns_ctrl->irq = platform_get_irq(ofdev, 0); + if (cdns_ctrl->irq < 0) + return cdns_ctrl->irq; + + dev_info(cdns_ctrl->dev, "IRQ: nr %d\n", cdns_ctrl->irq); + + cdns_ctrl->reg = devm_platform_ioremap_resource(ofdev, 0); + if (IS_ERR(cdns_ctrl->reg)) { + dev_err(&ofdev->dev, "devm_ioremap_resource res 0 failed\n"); + return PTR_ERR(cdns_ctrl->reg); + } + + res = platform_get_resource(ofdev, IORESOURCE_MEM, 1); + cdns_ctrl->io.dma = res->start; + cdns_ctrl->io.virt = devm_ioremap_resource(&ofdev->dev, res); + if (IS_ERR(cdns_ctrl->io.virt)) { + dev_err(cdns_ctrl->dev, "devm_ioremap_resource res 1 failed\n"); + return PTR_ERR(cdns_ctrl->io.virt); + } + + dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk"); + if (IS_ERR(dt->clk)) + return PTR_ERR(dt->clk); + + cdns_ctrl->nf_clk_rate = clk_get_rate(dt->clk); + + ret = of_property_read_u32(ofdev->dev.of_node, + "cdns,board-delay-ps", &val); + if (ret) { + val = 4830; + dev_info(cdns_ctrl->dev, + "missing cdns,board-delay-ps property, %d was set\n", + val); + } + cdns_ctrl->board_delay = val; + + ret = cadence_nand_init(cdns_ctrl); + if (ret) + return ret; + + platform_set_drvdata(ofdev, dt); + return 0; +} + +static int cadence_nand_dt_remove(struct platform_device *ofdev) +{ + struct cadence_nand_dt *dt = platform_get_drvdata(ofdev); + + cadence_nand_remove(&dt->cdns_ctrl); + + return 0; +} + +static struct platform_driver cadence_nand_dt_driver = { + .probe = cadence_nand_dt_probe, + .remove = cadence_nand_dt_remove, + .driver = { + .name = "cadence-nand-controller", + .of_match_table = cadence_nand_dt_ids, + }, +}; + +module_platform_driver(cadence_nand_dt_driver); + +MODULE_AUTHOR("Piotr Sroka <piotrs@cadence.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Driver for Cadence NAND flash controller"); + diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c index 5e14836f6bd5..8b779a899dcf 100644 --- a/drivers/mtd/nand/raw/denali_dt.c +++ b/drivers/mtd/nand/raw/denali_dt.c @@ -102,47 +102,6 @@ static int denali_dt_chip_init(struct denali_controller *denali, return denali_chip_init(denali, dchip); } -/* Backward compatibility for old platforms */ -static int denali_dt_legacy_chip_init(struct denali_controller *denali) -{ - struct denali_chip *dchip; - int nsels, i; - - nsels = denali->nbanks; - - dchip = devm_kzalloc(denali->dev, struct_size(dchip, sels, nsels), - GFP_KERNEL); - if (!dchip) - return -ENOMEM; - - dchip->nsels = nsels; - - for (i = 0; i < nsels; i++) - dchip->sels[i].bank = i; - - nand_set_flash_node(&dchip->chip, denali->dev->of_node); - - return denali_chip_init(denali, dchip); -} - -/* - * Check the DT binding. - * The new binding expects chip subnodes in the controller node. - * So, #address-cells = <1>; #size-cells = <0>; are required. - * Check the #size-cells to distinguish the binding. - */ -static bool denali_dt_is_legacy_binding(struct device_node *np) -{ - u32 cells; - int ret; - - ret = of_property_read_u32(np, "#size-cells", &cells); - if (ret) - return true; - - return cells != 0; -} - static int denali_dt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -167,10 +126,8 @@ static int denali_dt_probe(struct platform_device *pdev) denali->dev = dev; denali->irq = platform_get_irq(pdev, 0); - if (denali->irq < 0) { - dev_err(dev, "no irq defined\n"); + if (denali->irq < 0) return denali->irq; - } res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg"); denali->reg = devm_ioremap_resource(dev, res); @@ -213,17 +170,11 @@ static int denali_dt_probe(struct platform_device *pdev) if (ret) goto out_disable_clk_ecc; - if (denali_dt_is_legacy_binding(dev->of_node)) { - ret = denali_dt_legacy_chip_init(denali); - if (ret) + for_each_child_of_node(dev->of_node, np) { + ret = denali_dt_chip_init(denali, np); + if (ret) { + of_node_put(np); goto out_remove_denali; - } else { - for_each_child_of_node(dev->of_node, np) { - ret = denali_dt_chip_init(denali, np); - if (ret) { - of_node_put(np); - goto out_remove_denali; - } } } diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c index 6a4626a8bf95..0b48be54ba6f 100644 --- a/drivers/mtd/nand/raw/hisi504_nand.c +++ b/drivers/mtd/nand/raw/hisi504_nand.c @@ -751,10 +751,8 @@ static int hisi_nfc_probe(struct platform_device *pdev) mtd = nand_to_mtd(chip); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "no IRQ resource defined\n"); + if (irq < 0) return -ENXIO; - } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); host->iobase = devm_ioremap_resource(dev, res); diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index 78b31f845c50..241b58b83240 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -773,7 +773,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { - dev_err(&pdev->dev, "failed to get platform irq\n"); res = -EINVAL; goto release_dma_chan; } diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index fc49e13d81ec..fb5abdcfb007 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2862,10 +2862,8 @@ static int marvell_nfc_probe(struct platform_device *pdev) return PTR_ERR(nfc->regs); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "failed to retrieve irq\n"); + if (irq < 0) return irq; - } nfc->core_clk = devm_clk_get(&pdev->dev, "core"); diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 1b82b687e5a5..9f17b5b8efbf 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -1399,10 +1399,8 @@ static int meson_nfc_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "no NFC IRQ resource\n"); + if (irq < 0) return -EINVAL; - } ret = meson_nfc_clk_init(nfc); if (ret) { diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/raw/mtk_ecc.c index 74595b644b7c..75f1fa3d4d35 100644 --- a/drivers/mtd/nand/raw/mtk_ecc.c +++ b/drivers/mtd/nand/raw/mtk_ecc.c @@ -527,10 +527,8 @@ static int mtk_ecc_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "failed to get irq: %d\n", irq); + if (irq < 0) return irq; - } ret = dma_set_mask(dev, DMA_BIT_MASK(32)); if (ret) { diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c index 373d47d1ba4c..b8305e39ab51 100644 --- a/drivers/mtd/nand/raw/mtk_nand.c +++ b/drivers/mtd/nand/raw/mtk_nand.c @@ -1540,7 +1540,6 @@ static int mtk_nfc_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(dev, "no nfi irq resource\n"); ret = -EINVAL; goto clk_disable; } diff --git a/drivers/mtd/nand/raw/mxic_nand.c b/drivers/mtd/nand/raw/mxic_nand.c index 9d49e6c845e1..ed7a4e021bf5 100644 --- a/drivers/mtd/nand/raw/mxic_nand.c +++ b/drivers/mtd/nand/raw/mxic_nand.c @@ -524,10 +524,8 @@ static int mxic_nfc_probe(struct platform_device *pdev) nand_chip->controller = &nfc->controller; irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(&pdev->dev, "failed to retrieve irq\n"); + if (irq < 0) return irq; - } mxic_nfc_hw_init(nfc); diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 5c2c30a7dffa..f64e3b6605c6 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -292,12 +292,16 @@ int nand_bbm_get_next_page(struct nand_chip *chip, int page) struct mtd_info *mtd = nand_to_mtd(chip); int last_page = ((mtd->erasesize - mtd->writesize) >> chip->page_shift) & chip->pagemask; + unsigned int bbm_flags = NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE + | NAND_BBM_LASTPAGE; + if (page == 0 && !(chip->options & bbm_flags)) + return 0; if (page == 0 && chip->options & NAND_BBM_FIRSTPAGE) return 0; - else if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE) + if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE) return 1; - else if (page <= last_page && chip->options & NAND_BBM_LASTPAGE) + if (page <= last_page && chip->options & NAND_BBM_LASTPAGE) return last_page; return -EINVAL; diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c index 8ca9fad6e6ad..56654030ec7f 100644 --- a/drivers/mtd/nand/raw/nand_micron.c +++ b/drivers/mtd/nand/raw/nand_micron.c @@ -446,8 +446,10 @@ static int micron_nand_init(struct nand_chip *chip) if (ret) goto err_free_manuf_data; + chip->options |= NAND_BBM_FIRSTPAGE; + if (mtd->writesize == 2048) - chip->options |= NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE; + chip->options |= NAND_BBM_SECONDPAGE; ondie = micron_supports_on_die_ecc(chip); diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index 6ec65f48501c..ad77c112a78a 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -1967,10 +1967,8 @@ static int omap_nand_attach_chip(struct nand_chip *chip) case NAND_OMAP_PREFETCH_IRQ: info->gpmc_irq_fifo = platform_get_irq(info->pdev, 0); - if (info->gpmc_irq_fifo <= 0) { - dev_err(dev, "Error getting fifo IRQ\n"); + if (info->gpmc_irq_fifo <= 0) return -ENODEV; - } err = devm_request_irq(dev, info->gpmc_irq_fifo, omap_nand_irq, IRQF_SHARED, "gpmc-nand-fifo", info); @@ -1982,10 +1980,8 @@ static int omap_nand_attach_chip(struct nand_chip *chip) } info->gpmc_irq_count = platform_get_irq(info->pdev, 1); - if (info->gpmc_irq_count <= 0) { - dev_err(dev, "Error getting IRQ count\n"); + if (info->gpmc_irq_count <= 0) return -ENODEV; - } err = devm_request_irq(dev, info->gpmc_irq_count, omap_nand_irq, IRQF_SHARED, "gpmc-nand-count", info); diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c index e509c93737c4..058e99d0cbcf 100644 --- a/drivers/mtd/nand/raw/sh_flctl.c +++ b/drivers/mtd/nand/raw/sh_flctl.c @@ -1129,10 +1129,8 @@ static int flctl_probe(struct platform_device *pdev) flctl->fifo = res->start + 0x24; /* FLDTFIFO */ irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(&pdev->dev, "failed to get flste irq data: %d\n", irq); + if (irq < 0) return irq; - } ret = devm_request_irq(&pdev->dev, irq, flctl_handle_flste, IRQF_SHARED, "flste", flctl); diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 8cc852dc7d54..9e63800f768a 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1880,11 +1880,8 @@ static int stm32_fmc2_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq < 0) { - if (irq != -EPROBE_DEFER) - dev_err(dev, "IRQ error missing or invalid\n"); + if (irq < 0) return irq; - } ret = devm_request_irq(dev, irq, stm32_fmc2_irq, 0, dev_name(dev), fmc2); diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index 89773293c64d..37a4ac0dd85b 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -2071,10 +2071,8 @@ static int sunxi_nfc_probe(struct platform_device *pdev) return PTR_ERR(nfc->regs); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "failed to retrieve irq\n"); + if (irq < 0) return irq; - } nfc->ahb_clk = devm_clk_get(dev, "ahb"); if (IS_ERR(nfc->ahb_clk)) { diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c index 009c1da8574c..2b7cabbb680c 100644 --- a/drivers/mtd/spi-nor/aspeed-smc.c +++ b/drivers/mtd/spi-nor/aspeed-smc.c @@ -320,7 +320,8 @@ static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops) mutex_unlock(&chip->controller->mutex); } -static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, + size_t len) { struct aspeed_smc_chip *chip = nor->priv; @@ -331,8 +332,8 @@ static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return 0; } -static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, - int len) +static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { struct aspeed_smc_chip *chip = nor->priv; @@ -746,6 +747,15 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip) return 0; } +static const struct spi_nor_controller_ops aspeed_smc_controller_ops = { + .prepare = aspeed_smc_prep, + .unprepare = aspeed_smc_unprep, + .read_reg = aspeed_smc_read_reg, + .write_reg = aspeed_smc_write_reg, + .read = aspeed_smc_read_user, + .write = aspeed_smc_write_user, +}; + static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, struct device_node *np, struct resource *r) { @@ -805,12 +815,7 @@ static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, nor->dev = dev; nor->priv = chip; spi_nor_set_flash_node(nor, child); - nor->read = aspeed_smc_read_user; - nor->write = aspeed_smc_write_user; - nor->read_reg = aspeed_smc_read_reg; - nor->write_reg = aspeed_smc_write_reg; - nor->prepare = aspeed_smc_prep; - nor->unprepare = aspeed_smc_unprep; + nor->controller_ops = &aspeed_smc_controller_ops; ret = aspeed_smc_chip_setup_init(chip, r); if (ret) diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index 7bef63947b29..06f997247d0f 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -285,7 +285,7 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev) return IRQ_HANDLED; } -static unsigned int cqspi_calc_rdreg(struct spi_nor *nor, const u8 opcode) +static unsigned int cqspi_calc_rdreg(struct spi_nor *nor) { struct cqspi_flash_pdata *f_pdata = nor->priv; u32 rdreg = 0; @@ -354,27 +354,27 @@ static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg) return cqspi_wait_idle(cqspi); } -static int cqspi_command_read(struct spi_nor *nor, - const u8 *txbuf, const unsigned n_tx, - u8 *rxbuf, const unsigned n_rx) +static int cqspi_command_read(struct spi_nor *nor, u8 opcode, + u8 *rxbuf, size_t n_rx) { struct cqspi_flash_pdata *f_pdata = nor->priv; struct cqspi_st *cqspi = f_pdata->cqspi; void __iomem *reg_base = cqspi->iobase; unsigned int rdreg; unsigned int reg; - unsigned int read_len; + size_t read_len; int status; if (!n_rx || n_rx > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) { - dev_err(nor->dev, "Invalid input argument, len %d rxbuf 0x%p\n", + dev_err(nor->dev, + "Invalid input argument, len %zu rxbuf 0x%p\n", n_rx, rxbuf); return -EINVAL; } - reg = txbuf[0] << CQSPI_REG_CMDCTRL_OPCODE_LSB; + reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB; - rdreg = cqspi_calc_rdreg(nor, txbuf[0]); + rdreg = cqspi_calc_rdreg(nor); writel(rdreg, reg_base + CQSPI_REG_RD_INSTR); reg |= (0x1 << CQSPI_REG_CMDCTRL_RD_EN_LSB); @@ -404,19 +404,19 @@ static int cqspi_command_read(struct spi_nor *nor, } static int cqspi_command_write(struct spi_nor *nor, const u8 opcode, - const u8 *txbuf, const unsigned n_tx) + const u8 *txbuf, size_t n_tx) { struct cqspi_flash_pdata *f_pdata = nor->priv; struct cqspi_st *cqspi = f_pdata->cqspi; void __iomem *reg_base = cqspi->iobase; unsigned int reg; unsigned int data; - u32 write_len; + size_t write_len; int ret; if (n_tx > CQSPI_STIG_DATA_LEN_MAX || (n_tx && !txbuf)) { dev_err(nor->dev, - "Invalid input argument, cmdlen %d txbuf 0x%p\n", + "Invalid input argument, cmdlen %zu txbuf 0x%p\n", n_tx, txbuf); return -EINVAL; } @@ -470,7 +470,7 @@ static int cqspi_read_setup(struct spi_nor *nor) unsigned int reg; reg = nor->read_opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB; - reg |= cqspi_calc_rdreg(nor, nor->read_opcode); + reg |= cqspi_calc_rdreg(nor); /* Setup dummy clock cycles */ dummy_clk = nor->read_dummy; @@ -603,7 +603,7 @@ static int cqspi_write_setup(struct spi_nor *nor) /* Set opcode. */ reg = nor->program_opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB; writel(reg, reg_base + CQSPI_REG_WR_INSTR); - reg = cqspi_calc_rdreg(nor, nor->program_opcode); + reg = cqspi_calc_rdreg(nor); writel(reg, reg_base + CQSPI_REG_RD_INSTR); reg = readl(reg_base + CQSPI_REG_SIZE); @@ -1050,7 +1050,7 @@ static int cqspi_erase(struct spi_nor *nor, loff_t offs) return ret; /* Send write enable, then erase commands. */ - ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0); + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREN, NULL, 0); if (ret) return ret; @@ -1080,18 +1080,19 @@ static void cqspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops) mutex_unlock(&cqspi->bus_mutex); } -static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len) { int ret; ret = cqspi_set_protocol(nor, 0); if (!ret) - ret = cqspi_command_read(nor, &opcode, 1, buf, len); + ret = cqspi_command_read(nor, opcode, buf, len); return ret; } -static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { int ret; @@ -1216,6 +1217,16 @@ static void cqspi_request_mmap_dma(struct cqspi_st *cqspi) init_completion(&cqspi->rx_dma_complete); } +static const struct spi_nor_controller_ops cqspi_controller_ops = { + .prepare = cqspi_prep, + .unprepare = cqspi_unprep, + .read_reg = cqspi_read_reg, + .write_reg = cqspi_write_reg, + .read = cqspi_read, + .write = cqspi_write, + .erase = cqspi_erase, +}; + static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np) { struct platform_device *pdev = cqspi->pdev; @@ -1265,14 +1276,7 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np) nor->dev = dev; spi_nor_set_flash_node(nor, np); nor->priv = f_pdata; - - nor->read_reg = cqspi_read_reg; - nor->write_reg = cqspi_write_reg; - nor->read = cqspi_read; - nor->write = cqspi_write; - nor->erase = cqspi_erase; - nor->prepare = cqspi_prep; - nor->unprepare = cqspi_unprep; + nor->controller_ops = &cqspi_controller_ops; mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%s.%d", dev_name(dev), cs); @@ -1366,10 +1370,8 @@ static int cqspi_probe(struct platform_device *pdev) /* Obtain IRQ line. */ irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "Cannot obtain IRQ.\n"); + if (irq < 0) return -ENXIO; - } pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c index 6dac9dd8bf42..a1258216f89d 100644 --- a/drivers/mtd/spi-nor/hisi-sfc.c +++ b/drivers/mtd/spi-nor/hisi-sfc.c @@ -177,7 +177,7 @@ static void hisi_spi_nor_unprep(struct spi_nor *nor, enum spi_nor_ops ops) } static int hisi_spi_nor_op_reg(struct spi_nor *nor, - u8 opcode, int len, u8 optype) + u8 opcode, size_t len, u8 optype) { struct hifmc_priv *priv = nor->priv; struct hifmc_host *host = priv->host; @@ -200,7 +200,7 @@ static int hisi_spi_nor_op_reg(struct spi_nor *nor, } static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, - int len) + size_t len) { struct hifmc_priv *priv = nor->priv; struct hifmc_host *host = priv->host; @@ -215,7 +215,7 @@ static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, } static int hisi_spi_nor_write_reg(struct spi_nor *nor, u8 opcode, - u8 *buf, int len) + const u8 *buf, size_t len) { struct hifmc_priv *priv = nor->priv; struct hifmc_host *host = priv->host; @@ -311,6 +311,15 @@ static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to, return len; } +static const struct spi_nor_controller_ops hisi_controller_ops = { + .prepare = hisi_spi_nor_prep, + .unprepare = hisi_spi_nor_unprep, + .read_reg = hisi_spi_nor_read_reg, + .write_reg = hisi_spi_nor_write_reg, + .read = hisi_spi_nor_read, + .write = hisi_spi_nor_write, +}; + /** * Get spi flash device information and register it as a mtd device. */ @@ -357,14 +366,8 @@ static int hisi_spi_nor_register(struct device_node *np, } priv->host = host; nor->priv = priv; + nor->controller_ops = &hisi_controller_ops; - nor->prepare = hisi_spi_nor_prep; - nor->unprepare = hisi_spi_nor_unprep; - nor->read_reg = hisi_spi_nor_read_reg; - nor->write_reg = hisi_spi_nor_write_reg; - nor->read = hisi_spi_nor_read; - nor->write = hisi_spi_nor_write; - nor->erase = NULL; ret = spi_nor_scan(nor, NULL, &hwcaps); if (ret) return ret; diff --git a/drivers/mtd/spi-nor/intel-spi-pci.c b/drivers/mtd/spi-nor/intel-spi-pci.c index 3cda8e7a68f8..3d8987baea2a 100644 --- a/drivers/mtd/spi-nor/intel-spi-pci.c +++ b/drivers/mtd/spi-nor/intel-spi-pci.c @@ -20,6 +20,10 @@ static const struct intel_spi_boardinfo bxt_info = { .type = INTEL_SPI_BXT, }; +static const struct intel_spi_boardinfo cnl_info = { + .type = INTEL_SPI_CNL, +}; + static int intel_spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -61,6 +65,7 @@ static void intel_spi_pci_remove(struct pci_dev *pdev) static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x02a4), (unsigned long)&bxt_info }, + { PCI_VDEVICE(INTEL, 0x06a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x18e0), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x19e0), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x34a4), (unsigned long)&bxt_info }, @@ -68,6 +73,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa224), (unsigned long)&bxt_info }, + { PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info }, { }, }; MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids); diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c index 43e55a2e9b27..61d2a0ad2131 100644 --- a/drivers/mtd/spi-nor/intel-spi.c +++ b/drivers/mtd/spi-nor/intel-spi.c @@ -108,6 +108,10 @@ #define BXT_FREG_NUM 12 #define BXT_PR_NUM 6 +#define CNL_PR 0x84 +#define CNL_FREG_NUM 6 +#define CNL_PR_NUM 5 + #define LVSCC 0xc4 #define UVSCC 0xc8 #define ERASE_OPCODE_SHIFT 8 @@ -187,12 +191,16 @@ static void intel_spi_dump_regs(struct intel_spi *ispi) dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i, readl(ispi->pregs + PR(i))); - value = readl(ispi->sregs + SSFSTS_CTL); - dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value); - dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n", - readl(ispi->sregs + PREOP_OPTYPE)); - dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", readl(ispi->sregs + OPMENU0)); - dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", readl(ispi->sregs + OPMENU1)); + if (ispi->sregs) { + value = readl(ispi->sregs + SSFSTS_CTL); + dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value); + dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n", + readl(ispi->sregs + PREOP_OPTYPE)); + dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", + readl(ispi->sregs + OPMENU0)); + dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", + readl(ispi->sregs + OPMENU1)); + } if (ispi->info->type == INTEL_SPI_BYT) dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR)); @@ -340,6 +348,13 @@ static int intel_spi_init(struct intel_spi *ispi) ispi->erase_64k = true; break; + case INTEL_SPI_CNL: + ispi->sregs = NULL; + ispi->pregs = ispi->base + CNL_PR; + ispi->nregions = CNL_FREG_NUM; + ispi->pr_num = CNL_PR_NUM; + break; + default: return -EINVAL; } @@ -367,6 +382,11 @@ static int intel_spi_init(struct intel_spi *ispi) !(uvscc & ERASE_64K_OPCODE_MASK)) ispi->erase_64k = false; + if (ispi->sregs == NULL && (ispi->swseq_reg || ispi->swseq_erase)) { + dev_err(ispi->dev, "software sequencer not supported, but required\n"); + return -EINVAL; + } + /* * Some controllers can only do basic operations using hardware * sequencer. All other operations are supposed to be carried out @@ -383,7 +403,7 @@ static int intel_spi_init(struct intel_spi *ispi) val = readl(ispi->base + HSFSTS_CTL); ispi->locked = !!(val & HSFSTS_CTL_FLOCKDN); - if (ispi->locked) { + if (ispi->locked && ispi->sregs) { /* * BIOS programs allowed opcodes and then locks down the * register. So read back what opcodes it decided to support. @@ -426,7 +446,7 @@ static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode, int optype) return 0; } -static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len) +static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, size_t len) { u32 val, status; int ret; @@ -469,7 +489,7 @@ static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len) return 0; } -static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len, +static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, size_t len, int optype) { u32 val = 0, status; @@ -535,7 +555,8 @@ static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len, return 0; } -static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, + size_t len) { struct intel_spi *ispi = nor->priv; int ret; @@ -555,7 +576,8 @@ static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return intel_spi_read_block(ispi, buf, len); } -static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { struct intel_spi *ispi = nor->priv; int ret; @@ -864,6 +886,14 @@ static void intel_spi_fill_partition(struct intel_spi *ispi, } } +static const struct spi_nor_controller_ops intel_spi_controller_ops = { + .read_reg = intel_spi_read_reg, + .write_reg = intel_spi_write_reg, + .read = intel_spi_read, + .write = intel_spi_write, + .erase = intel_spi_erase, +}; + struct intel_spi *intel_spi_probe(struct device *dev, struct resource *mem, const struct intel_spi_boardinfo *info) { @@ -897,11 +927,7 @@ struct intel_spi *intel_spi_probe(struct device *dev, ispi->nor.dev = ispi->dev; ispi->nor.priv = ispi; - ispi->nor.read_reg = intel_spi_read_reg; - ispi->nor.write_reg = intel_spi_write_reg; - ispi->nor.read = intel_spi_read; - ispi->nor.write = intel_spi_write; - ispi->nor.erase = intel_spi_erase; + ispi->nor.controller_ops = &intel_spi_controller_ops; ret = spi_nor_scan(&ispi->nor, NULL, &hwcaps); if (ret) { diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c index 34db01ab6cab..b1691680d174 100644 --- a/drivers/mtd/spi-nor/mtk-quadspi.c +++ b/drivers/mtd/spi-nor/mtk-quadspi.c @@ -151,9 +151,9 @@ static int mtk_nor_execute_cmd(struct mtk_nor *mtk_nor, u8 cmdval) } static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op, - u8 *tx, int txlen, u8 *rx, int rxlen) + const u8 *tx, size_t txlen, u8 *rx, size_t rxlen) { - int len = 1 + txlen + rxlen; + size_t len = 1 + txlen + rxlen; int i, ret, idx; if (len > MTK_NOR_MAX_SHIFT) @@ -193,7 +193,7 @@ static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op, } /* Do a WRSR (Write Status Register) command */ -static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, u8 sr) +static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, const u8 sr) { writeb(sr, mtk_nor->base + MTK_NOR_PRGDATA5_REG); writeb(8, mtk_nor->base + MTK_NOR_CNT_REG); @@ -354,7 +354,7 @@ static ssize_t mtk_nor_write(struct spi_nor *nor, loff_t to, size_t len, return len; } -static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len) { int ret; struct mtk_nor *mtk_nor = nor->priv; @@ -376,8 +376,8 @@ static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return ret; } -static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, - int len) +static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { int ret; struct mtk_nor *mtk_nor = nor->priv; @@ -419,6 +419,13 @@ static int mtk_nor_enable_clk(struct mtk_nor *mtk_nor) return 0; } +static const struct spi_nor_controller_ops mtk_controller_ops = { + .read_reg = mtk_nor_read_reg, + .write_reg = mtk_nor_write_reg, + .read = mtk_nor_read, + .write = mtk_nor_write, +}; + static int mtk_nor_init(struct mtk_nor *mtk_nor, struct device_node *flash_node) { @@ -438,12 +445,8 @@ static int mtk_nor_init(struct mtk_nor *mtk_nor, nor->dev = mtk_nor->dev; nor->priv = mtk_nor; spi_nor_set_flash_node(nor, flash_node); + nor->controller_ops = &mtk_controller_ops; - /* fill the hooks to spi nor */ - nor->read = mtk_nor_read; - nor->read_reg = mtk_nor_read_reg; - nor->write = mtk_nor_write; - nor->write_reg = mtk_nor_write_reg; nor->mtd.name = "mtk_nor"; /* initialized with NULL */ ret = spi_nor_scan(nor, NULL, &hwcaps); diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c index 4a871587392b..9a5b1a7c636a 100644 --- a/drivers/mtd/spi-nor/nxp-spifi.c +++ b/drivers/mtd/spi-nor/nxp-spifi.c @@ -123,7 +123,8 @@ static int nxp_spifi_set_memory_mode_on(struct nxp_spifi *spifi) return ret; } -static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, + size_t len) { struct nxp_spifi *spifi = nor->priv; u32 cmd; @@ -145,7 +146,8 @@ static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return nxp_spifi_wait_for_cmd(spifi); } -static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { struct nxp_spifi *spifi = nor->priv; u32 cmd; @@ -263,9 +265,18 @@ static int nxp_spifi_setup_memory_cmd(struct nxp_spifi *spifi) static void nxp_spifi_dummy_id_read(struct spi_nor *nor) { u8 id[SPI_NOR_MAX_ID_LEN]; - nor->read_reg(nor, SPINOR_OP_RDID, id, SPI_NOR_MAX_ID_LEN); + nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id, + SPI_NOR_MAX_ID_LEN); } +static const struct spi_nor_controller_ops nxp_spifi_controller_ops = { + .read_reg = nxp_spifi_read_reg, + .write_reg = nxp_spifi_write_reg, + .read = nxp_spifi_read, + .write = nxp_spifi_write, + .erase = nxp_spifi_erase, +}; + static int nxp_spifi_setup_flash(struct nxp_spifi *spifi, struct device_node *np) { @@ -332,11 +343,7 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi, spifi->nor.dev = spifi->dev; spi_nor_set_flash_node(&spifi->nor, np); spifi->nor.priv = spifi; - spifi->nor.read = nxp_spifi_read; - spifi->nor.write = nxp_spifi_write; - spifi->nor.erase = nxp_spifi_erase; - spifi->nor.read_reg = nxp_spifi_read_reg; - spifi->nor.write_reg = nxp_spifi_write_reg; + spifi->nor.controller_ops = &nxp_spifi_controller_ops; /* * The first read on a hard reset isn't reliable so do a diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 7acf4a93b592..f4afe123e9dc 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -338,7 +338,7 @@ static ssize_t spi_nor_read_data(struct spi_nor *nor, loff_t from, size_t len, if (nor->spimem) return spi_nor_spimem_read_data(nor, from, len, buf); - return nor->read(nor, from, len, buf); + return nor->controller_ops->read(nor, from, len, buf); } /** @@ -385,239 +385,172 @@ static ssize_t spi_nor_write_data(struct spi_nor *nor, loff_t to, size_t len, if (nor->spimem) return spi_nor_spimem_write_data(nor, to, len, buf); - return nor->write(nor, to, len, buf); + return nor->controller_ops->write(nor, to, len, buf); } -/* - * Read the status register, returning its value in the location - * Return the status register value. - * Returns negative if error occurred. +/** + * spi_nor_write_enable() - Set write enable latch with Write Enable command. + * @nor: pointer to 'struct spi_nor'. + * + * Return: 0 on success, -errno otherwise. */ -static int read_sr(struct spi_nor *nor) +static int spi_nor_write_enable(struct spi_nor *nor) { int ret; if (nor->spimem) { struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 1), + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1)); + SPI_MEM_OP_NO_DATA); ret = spi_mem_exec_op(nor->spimem, &op); } else { - ret = nor->read_reg(nor, SPINOR_OP_RDSR, nor->bouncebuf, 1); + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREN, + NULL, 0); } - if (ret < 0) { - pr_err("error %d reading SR\n", (int) ret); - return ret; - } + if (ret) + dev_dbg(nor->dev, "error %d on Write Enable\n", ret); - return nor->bouncebuf[0]; + return ret; } -/* - * Read the flag status register, returning its value in the location - * Return the status register value. - * Returns negative if error occurred. +/** + * spi_nor_write_disable() - Send Write Disable instruction to the chip. + * @nor: pointer to 'struct spi_nor'. + * + * Return: 0 on success, -errno otherwise. */ -static int read_fsr(struct spi_nor *nor) +static int spi_nor_write_disable(struct spi_nor *nor) { int ret; if (nor->spimem) { struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 1), + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1)); + SPI_MEM_OP_NO_DATA); ret = spi_mem_exec_op(nor->spimem, &op); } else { - ret = nor->read_reg(nor, SPINOR_OP_RDFSR, nor->bouncebuf, 1); + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRDI, + NULL, 0); } - if (ret < 0) { - pr_err("error %d reading FSR\n", ret); - return ret; - } + if (ret) + dev_dbg(nor->dev, "error %d on Write Disable\n", ret); - return nor->bouncebuf[0]; + return ret; } -/* - * Read configuration register, returning its value in the - * location. Return the configuration register value. - * Returns negative if error occurred. +/** + * spi_nor_read_sr() - Read the Status Register. + * @nor: pointer to 'struct spi_nor'. + * @sr: pointer to a DMA-able buffer where the value of the + * Status Register will be written. + * + * Return: 0 on success, -errno otherwise. */ -static int read_cr(struct spi_nor *nor) +static int spi_nor_read_sr(struct spi_nor *nor, u8 *sr) { int ret; if (nor->spimem) { struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 1), + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1)); + SPI_MEM_OP_DATA_IN(1, sr, 1)); ret = spi_mem_exec_op(nor->spimem, &op); } else { - ret = nor->read_reg(nor, SPINOR_OP_RDCR, nor->bouncebuf, 1); + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR, + sr, 1); } - if (ret < 0) { - dev_err(nor->dev, "error %d reading CR\n", ret); - return ret; - } + if (ret) + dev_dbg(nor->dev, "error %d reading SR\n", ret); - return nor->bouncebuf[0]; + return ret; } -/* - * Write status register 1 byte - * Returns negative if error occurred. +/** + * spi_nor_read_fsr() - Read the Flag Status Register. + * @nor: pointer to 'struct spi_nor' + * @fsr: pointer to a DMA-able buffer where the value of the + * Flag Status Register will be written. + * + * Return: 0 on success, -errno otherwise. */ -static int write_sr(struct spi_nor *nor, u8 val) +static int spi_nor_read_fsr(struct spi_nor *nor, u8 *fsr) { - nor->bouncebuf[0] = val; - if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1)); - - return spi_mem_exec_op(nor->spimem, &op); - } - - return nor->write_reg(nor, SPINOR_OP_WRSR, nor->bouncebuf, 1); -} + int ret; -/* - * Set write enable latch with Write Enable command. - * Returns negative if error occurred. - */ -static int write_enable(struct spi_nor *nor) -{ if (nor->spimem) { struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 1), + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + SPI_MEM_OP_DATA_IN(1, fsr, 1)); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDFSR, + fsr, 1); } - return nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0); + if (ret) + dev_dbg(nor->dev, "error %d reading FSR\n", ret); + + return ret; } -/* - * Send write disable instruction to the chip. +/** + * spi_nor_read_cr() - Read the Configuration Register using the + * SPINOR_OP_RDCR (35h) command. + * @nor: pointer to 'struct spi_nor' + * @cr: pointer to a DMA-able buffer where the value of the + * Configuration Register will be written. + * + * Return: 0 on success, -errno otherwise. */ -static int write_disable(struct spi_nor *nor) +static int spi_nor_read_cr(struct spi_nor *nor, u8 *cr) { + int ret; + if (nor->spimem) { struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 1), + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_NO_DATA); + SPI_MEM_OP_DATA_IN(1, cr, 1)); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDCR, cr, 1); } - return nor->write_reg(nor, SPINOR_OP_WRDI, NULL, 0); -} - -static struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd) -{ - return mtd->priv; -} - - -static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size) -{ - size_t i; - - for (i = 0; i < size; i++) - if (table[i][0] == opcode) - return table[i][1]; - - /* No conversion found, keep input op code. */ - return opcode; -} - -static u8 spi_nor_convert_3to4_read(u8 opcode) -{ - static const u8 spi_nor_3to4_read[][2] = { - { SPINOR_OP_READ, SPINOR_OP_READ_4B }, - { SPINOR_OP_READ_FAST, SPINOR_OP_READ_FAST_4B }, - { SPINOR_OP_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B }, - { SPINOR_OP_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B }, - { SPINOR_OP_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B }, - { SPINOR_OP_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B }, - { SPINOR_OP_READ_1_1_8, SPINOR_OP_READ_1_1_8_4B }, - { SPINOR_OP_READ_1_8_8, SPINOR_OP_READ_1_8_8_4B }, - - { SPINOR_OP_READ_1_1_1_DTR, SPINOR_OP_READ_1_1_1_DTR_4B }, - { SPINOR_OP_READ_1_2_2_DTR, SPINOR_OP_READ_1_2_2_DTR_4B }, - { SPINOR_OP_READ_1_4_4_DTR, SPINOR_OP_READ_1_4_4_DTR_4B }, - }; - - return spi_nor_convert_opcode(opcode, spi_nor_3to4_read, - ARRAY_SIZE(spi_nor_3to4_read)); -} - -static u8 spi_nor_convert_3to4_program(u8 opcode) -{ - static const u8 spi_nor_3to4_program[][2] = { - { SPINOR_OP_PP, SPINOR_OP_PP_4B }, - { SPINOR_OP_PP_1_1_4, SPINOR_OP_PP_1_1_4_4B }, - { SPINOR_OP_PP_1_4_4, SPINOR_OP_PP_1_4_4_4B }, - { SPINOR_OP_PP_1_1_8, SPINOR_OP_PP_1_1_8_4B }, - { SPINOR_OP_PP_1_8_8, SPINOR_OP_PP_1_8_8_4B }, - }; - - return spi_nor_convert_opcode(opcode, spi_nor_3to4_program, - ARRAY_SIZE(spi_nor_3to4_program)); -} - -static u8 spi_nor_convert_3to4_erase(u8 opcode) -{ - static const u8 spi_nor_3to4_erase[][2] = { - { SPINOR_OP_BE_4K, SPINOR_OP_BE_4K_4B }, - { SPINOR_OP_BE_32K, SPINOR_OP_BE_32K_4B }, - { SPINOR_OP_SE, SPINOR_OP_SE_4B }, - }; - - return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase, - ARRAY_SIZE(spi_nor_3to4_erase)); -} - -static void spi_nor_set_4byte_opcodes(struct spi_nor *nor) -{ - nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode); - nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode); - nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode); - - if (!spi_nor_has_uniform_erase(nor)) { - struct spi_nor_erase_map *map = &nor->params.erase_map; - struct spi_nor_erase_type *erase; - int i; + if (ret) + dev_dbg(nor->dev, "error %d reading CR\n", ret); - for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) { - erase = &map->erase_type[i]; - erase->opcode = - spi_nor_convert_3to4_erase(erase->opcode); - } - } + return ret; } +/** + * macronix_set_4byte() - Set 4-byte address mode for Macronix flashes. + * @nor: pointer to 'struct spi_nor'. + * @enable: true to enter the 4-byte address mode, false to exit the 4-byte + * address mode. + * + * Return: 0 on success, -errno otherwise. + */ static int macronix_set_4byte(struct spi_nor *nor, bool enable) { + int ret; + if (nor->spimem) { struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(enable ? @@ -628,26 +561,55 @@ static int macronix_set_4byte(struct spi_nor *nor, bool enable) SPI_MEM_OP_NO_DUMMY, SPI_MEM_OP_NO_DATA); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, + enable ? SPINOR_OP_EN4B : + SPINOR_OP_EX4B, + NULL, 0); } - return nor->write_reg(nor, enable ? SPINOR_OP_EN4B : SPINOR_OP_EX4B, - NULL, 0); + if (ret) + dev_dbg(nor->dev, "error %d setting 4-byte mode\n", ret); + + return ret; } +/** + * st_micron_set_4byte() - Set 4-byte address mode for ST and Micron flashes. + * @nor: pointer to 'struct spi_nor'. + * @enable: true to enter the 4-byte address mode, false to exit the 4-byte + * address mode. + * + * Return: 0 on success, -errno otherwise. + */ static int st_micron_set_4byte(struct spi_nor *nor, bool enable) { int ret; - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + return ret; + ret = macronix_set_4byte(nor, enable); - write_disable(nor); + if (ret) + return ret; - return ret; + return spi_nor_write_disable(nor); } +/** + * spansion_set_4byte() - Set 4-byte address mode for Spansion flashes. + * @nor: pointer to 'struct spi_nor'. + * @enable: true to enter the 4-byte address mode, false to exit the 4-byte + * address mode. + * + * Return: 0 on success, -errno otherwise. + */ static int spansion_set_4byte(struct spi_nor *nor, bool enable) { + int ret; + nor->bouncebuf[0] = enable << 7; if (nor->spimem) { @@ -657,14 +619,29 @@ static int spansion_set_4byte(struct spi_nor *nor, bool enable) SPI_MEM_OP_NO_DUMMY, SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1)); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_BRWR, + nor->bouncebuf, 1); } - return nor->write_reg(nor, SPINOR_OP_BRWR, nor->bouncebuf, 1); + if (ret) + dev_dbg(nor->dev, "error %d setting 4-byte mode\n", ret); + + return ret; } +/** + * spi_nor_write_ear() - Write Extended Address Register. + * @nor: pointer to 'struct spi_nor'. + * @ear: value to write to the Extended Address Register. + * + * Return: 0 on success, -errno otherwise. + */ static int spi_nor_write_ear(struct spi_nor *nor, u8 ear) { + int ret; + nor->bouncebuf[0] = ear; if (nor->spimem) { @@ -674,12 +651,26 @@ static int spi_nor_write_ear(struct spi_nor *nor, u8 ear) SPI_MEM_OP_NO_DUMMY, SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1)); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREAR, + nor->bouncebuf, 1); } - return nor->write_reg(nor, SPINOR_OP_WREAR, nor->bouncebuf, 1); + if (ret) + dev_dbg(nor->dev, "error %d writing EAR\n", ret); + + return ret; } +/** + * winbond_set_4byte() - Set 4-byte address mode for Winbond flashes. + * @nor: pointer to 'struct spi_nor'. + * @enable: true to enter the 4-byte address mode, false to exit the 4-byte + * address mode. + * + * Return: 0 on success, -errno otherwise. + */ static int winbond_set_4byte(struct spi_nor *nor, bool enable) { int ret; @@ -693,15 +684,29 @@ static int winbond_set_4byte(struct spi_nor *nor, bool enable) * Register to be set to 1, so all 3-byte-address reads come from the * second 16M. We must clear the register to enable normal behavior. */ - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + return ret; + ret = spi_nor_write_ear(nor, 0); - write_disable(nor); + if (ret) + return ret; - return ret; + return spi_nor_write_disable(nor); } +/** + * spi_nor_xread_sr() - Read the Status Register on S3AN flashes. + * @nor: pointer to 'struct spi_nor'. + * @sr: pointer to a DMA-able buffer where the value of the + * Status Register will be written. + * + * Return: 0 on success, -errno otherwise. + */ static int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr) { + int ret; + if (nor->spimem) { struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_XRDSR, 1), @@ -709,27 +714,44 @@ static int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr) SPI_MEM_OP_NO_DUMMY, SPI_MEM_OP_DATA_IN(1, sr, 1)); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_XRDSR, + sr, 1); } - return nor->read_reg(nor, SPINOR_OP_XRDSR, sr, 1); + if (ret) + dev_dbg(nor->dev, "error %d reading XRDSR\n", ret); + + return ret; } +/** + * s3an_sr_ready() - Query the Status Register of the S3AN flash to see if the + * flash is ready for new commands. + * @nor: pointer to 'struct spi_nor'. + * + * Return: 0 on success, -errno otherwise. + */ static int s3an_sr_ready(struct spi_nor *nor) { int ret; ret = spi_nor_xread_sr(nor, nor->bouncebuf); - if (ret < 0) { - dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret); + if (ret) return ret; - } return !!(nor->bouncebuf[0] & XSR_RDY); } -static int spi_nor_clear_sr(struct spi_nor *nor) +/** + * spi_nor_clear_sr() - Clear the Status Register. + * @nor: pointer to 'struct spi_nor'. + */ +static void spi_nor_clear_sr(struct spi_nor *nor) { + int ret; + if (nor->spimem) { struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLSR, 1), @@ -737,20 +759,33 @@ static int spi_nor_clear_sr(struct spi_nor *nor) SPI_MEM_OP_NO_DUMMY, SPI_MEM_OP_NO_DATA); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CLSR, + NULL, 0); } - return nor->write_reg(nor, SPINOR_OP_CLSR, NULL, 0); + if (ret) + dev_dbg(nor->dev, "error %d clearing SR\n", ret); } +/** + * spi_nor_sr_ready() - Query the Status Register to see if the flash is ready + * for new commands. + * @nor: pointer to 'struct spi_nor'. + * + * Return: 0 on success, -errno otherwise. + */ static int spi_nor_sr_ready(struct spi_nor *nor) { - int sr = read_sr(nor); - if (sr < 0) - return sr; + int ret = spi_nor_read_sr(nor, nor->bouncebuf); + + if (ret) + return ret; - if (nor->flags & SNOR_F_USE_CLSR && sr & (SR_E_ERR | SR_P_ERR)) { - if (sr & SR_E_ERR) + if (nor->flags & SNOR_F_USE_CLSR && + nor->bouncebuf[0] & (SR_E_ERR | SR_P_ERR)) { + if (nor->bouncebuf[0] & SR_E_ERR) dev_err(nor->dev, "Erase Error occurred\n"); else dev_err(nor->dev, "Programming Error occurred\n"); @@ -759,11 +794,17 @@ static int spi_nor_sr_ready(struct spi_nor *nor) return -EIO; } - return !(sr & SR_WIP); + return !(nor->bouncebuf[0] & SR_WIP); } -static int spi_nor_clear_fsr(struct spi_nor *nor) +/** + * spi_nor_clear_fsr() - Clear the Flag Status Register. + * @nor: pointer to 'struct spi_nor'. + */ +static void spi_nor_clear_fsr(struct spi_nor *nor) { + int ret; + if (nor->spimem) { struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLFSR, 1), @@ -771,25 +812,37 @@ static int spi_nor_clear_fsr(struct spi_nor *nor) SPI_MEM_OP_NO_DUMMY, SPI_MEM_OP_NO_DATA); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CLFSR, + NULL, 0); } - return nor->write_reg(nor, SPINOR_OP_CLFSR, NULL, 0); + if (ret) + dev_dbg(nor->dev, "error %d clearing FSR\n", ret); } +/** + * spi_nor_fsr_ready() - Query the Flag Status Register to see if the flash is + * ready for new commands. + * @nor: pointer to 'struct spi_nor'. + * + * Return: 0 on success, -errno otherwise. + */ static int spi_nor_fsr_ready(struct spi_nor *nor) { - int fsr = read_fsr(nor); - if (fsr < 0) - return fsr; + int ret = spi_nor_read_fsr(nor, nor->bouncebuf); - if (fsr & (FSR_E_ERR | FSR_P_ERR)) { - if (fsr & FSR_E_ERR) + if (ret) + return ret; + + if (nor->bouncebuf[0] & (FSR_E_ERR | FSR_P_ERR)) { + if (nor->bouncebuf[0] & FSR_E_ERR) dev_err(nor->dev, "Erase operation failed.\n"); else dev_err(nor->dev, "Program operation failed.\n"); - if (fsr & FSR_PT_ERR) + if (nor->bouncebuf[0] & FSR_PT_ERR) dev_err(nor->dev, "Attempted to modify a protected sector.\n"); @@ -797,9 +850,15 @@ static int spi_nor_fsr_ready(struct spi_nor *nor) return -EIO; } - return fsr & FSR_READY; + return nor->bouncebuf[0] & FSR_READY; } +/** + * spi_nor_ready() - Query the flash to see if it is ready for new commands. + * @nor: pointer to 'struct spi_nor'. + * + * Return: 0 on success, -errno otherwise. + */ static int spi_nor_ready(struct spi_nor *nor) { int sr, fsr; @@ -816,9 +875,13 @@ static int spi_nor_ready(struct spi_nor *nor) return sr && fsr; } -/* - * Service routine to read status register until ready, or timeout occurs. - * Returns non-zero if error. +/** + * spi_nor_wait_till_ready_with_timeout() - Service routine to read the + * Status Register until ready, or timeout occurs. + * @nor: pointer to "struct spi_nor". + * @timeout_jiffies: jiffies to wait until timeout. + * + * Return: 0 on success, -errno otherwise. */ static int spi_nor_wait_till_ready_with_timeout(struct spi_nor *nor, unsigned long timeout_jiffies) @@ -841,24 +904,305 @@ static int spi_nor_wait_till_ready_with_timeout(struct spi_nor *nor, cond_resched(); } - dev_err(nor->dev, "flash operation timed out\n"); + dev_dbg(nor->dev, "flash operation timed out\n"); return -ETIMEDOUT; } +/** + * spi_nor_wait_till_ready() - Wait for a predefined amount of time for the + * flash to be ready, or timeout occurs. + * @nor: pointer to "struct spi_nor". + * + * Return: 0 on success, -errno otherwise. + */ static int spi_nor_wait_till_ready(struct spi_nor *nor) { return spi_nor_wait_till_ready_with_timeout(nor, DEFAULT_READY_WAIT_JIFFIES); } -/* - * Erase the whole flash memory +/** + * spi_nor_write_sr() - Write the Status Register. + * @nor: pointer to 'struct spi_nor'. + * @sr: pointer to DMA-able buffer to write to the Status Register. + * @len: number of bytes to write to the Status Register. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_sr(struct spi_nor *nor, const u8 *sr, size_t len) +{ + int ret; + + ret = spi_nor_write_enable(nor); + if (ret) + return ret; + + if (nor->spimem) { + struct spi_mem_op op = + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1), + SPI_MEM_OP_NO_ADDR, + SPI_MEM_OP_NO_DUMMY, + SPI_MEM_OP_DATA_OUT(len, sr, 1)); + + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR, + sr, len); + } + + if (ret) { + dev_dbg(nor->dev, "error %d writing SR\n", ret); + return ret; + } + + return spi_nor_wait_till_ready(nor); +} + +/** + * spi_nor_write_sr1_and_check() - Write one byte to the Status Register 1 and + * ensure that the byte written match the received value. + * @nor: pointer to a 'struct spi_nor'. + * @sr1: byte value to be written to the Status Register. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_sr1_and_check(struct spi_nor *nor, u8 sr1) +{ + int ret; + + nor->bouncebuf[0] = sr1; + + ret = spi_nor_write_sr(nor, nor->bouncebuf, 1); + if (ret) + return ret; + + ret = spi_nor_read_sr(nor, nor->bouncebuf); + if (ret) + return ret; + + if (nor->bouncebuf[0] != sr1) { + dev_dbg(nor->dev, "SR1: read back test failed\n"); + return -EIO; + } + + return 0; +} + +/** + * spi_nor_write_16bit_sr_and_check() - Write the Status Register 1 and the + * Status Register 2 in one shot. Ensure that the byte written in the Status + * Register 1 match the received value, and that the 16-bit Write did not + * affect what was already in the Status Register 2. + * @nor: pointer to a 'struct spi_nor'. + * @sr1: byte value to be written to the Status Register 1. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_16bit_sr_and_check(struct spi_nor *nor, u8 sr1) +{ + int ret; + u8 *sr_cr = nor->bouncebuf; + u8 cr_written; + + /* Make sure we don't overwrite the contents of Status Register 2. */ + if (!(nor->flags & SNOR_F_NO_READ_CR)) { + ret = spi_nor_read_cr(nor, &sr_cr[1]); + if (ret) + return ret; + } else if (nor->params.quad_enable) { + /* + * If the Status Register 2 Read command (35h) is not + * supported, we should at least be sure we don't + * change the value of the SR2 Quad Enable bit. + * + * We can safely assume that when the Quad Enable method is + * set, the value of the QE bit is one, as a consequence of the + * nor->params.quad_enable() call. + * + * We can safely assume that the Quad Enable bit is present in + * the Status Register 2 at BIT(1). According to the JESD216 + * revB standard, BFPT DWORDS[15], bits 22:20, the 16-bit + * Write Status (01h) command is available just for the cases + * in which the QE bit is described in SR2 at BIT(1). + */ + sr_cr[1] = SR2_QUAD_EN_BIT1; + } else { + sr_cr[1] = 0; + } + + sr_cr[0] = sr1; + + ret = spi_nor_write_sr(nor, sr_cr, 2); + if (ret) + return ret; + + if (nor->flags & SNOR_F_NO_READ_CR) + return 0; + + cr_written = sr_cr[1]; + + ret = spi_nor_read_cr(nor, &sr_cr[1]); + if (ret) + return ret; + + if (cr_written != sr_cr[1]) { + dev_dbg(nor->dev, "CR: read back test failed\n"); + return -EIO; + } + + return 0; +} + +/** + * spi_nor_write_16bit_cr_and_check() - Write the Status Register 1 and the + * Configuration Register in one shot. Ensure that the byte written in the + * Configuration Register match the received value, and that the 16-bit Write + * did not affect what was already in the Status Register 1. + * @nor: pointer to a 'struct spi_nor'. + * @cr: byte value to be written to the Configuration Register. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_16bit_cr_and_check(struct spi_nor *nor, u8 cr) +{ + int ret; + u8 *sr_cr = nor->bouncebuf; + u8 sr_written; + + /* Keep the current value of the Status Register 1. */ + ret = spi_nor_read_sr(nor, sr_cr); + if (ret) + return ret; + + sr_cr[1] = cr; + + ret = spi_nor_write_sr(nor, sr_cr, 2); + if (ret) + return ret; + + sr_written = sr_cr[0]; + + ret = spi_nor_read_sr(nor, sr_cr); + if (ret) + return ret; + + if (sr_written != sr_cr[0]) { + dev_dbg(nor->dev, "SR: Read back test failed\n"); + return -EIO; + } + + if (nor->flags & SNOR_F_NO_READ_CR) + return 0; + + ret = spi_nor_read_cr(nor, &sr_cr[1]); + if (ret) + return ret; + + if (cr != sr_cr[1]) { + dev_dbg(nor->dev, "CR: read back test failed\n"); + return -EIO; + } + + return 0; +} + +/** + * spi_nor_write_sr_and_check() - Write the Status Register 1 and ensure that + * the byte written match the received value without affecting other bits in the + * Status Register 1 and 2. + * @nor: pointer to a 'struct spi_nor'. + * @sr1: byte value to be written to the Status Register. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_sr_and_check(struct spi_nor *nor, u8 sr1) +{ + if (nor->flags & SNOR_F_HAS_16BIT_SR) + return spi_nor_write_16bit_sr_and_check(nor, sr1); + + return spi_nor_write_sr1_and_check(nor, sr1); +} + +/** + * spi_nor_write_sr2() - Write the Status Register 2 using the + * SPINOR_OP_WRSR2 (3eh) command. + * @nor: pointer to 'struct spi_nor'. + * @sr2: pointer to DMA-able buffer to write to the Status Register 2. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_sr2(struct spi_nor *nor, const u8 *sr2) +{ + int ret; + + ret = spi_nor_write_enable(nor); + if (ret) + return ret; + + if (nor->spimem) { + struct spi_mem_op op = + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 1), + SPI_MEM_OP_NO_ADDR, + SPI_MEM_OP_NO_DUMMY, + SPI_MEM_OP_DATA_OUT(1, sr2, 1)); + + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR2, + sr2, 1); + } + + if (ret) { + dev_dbg(nor->dev, "error %d writing SR2\n", ret); + return ret; + } + + return spi_nor_wait_till_ready(nor); +} + +/** + * spi_nor_read_sr2() - Read the Status Register 2 using the + * SPINOR_OP_RDSR2 (3fh) command. + * @nor: pointer to 'struct spi_nor'. + * @sr2: pointer to DMA-able buffer where the value of the + * Status Register 2 will be written. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2) +{ + int ret; + + if (nor->spimem) { + struct spi_mem_op op = + SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 1), + SPI_MEM_OP_NO_ADDR, + SPI_MEM_OP_NO_DUMMY, + SPI_MEM_OP_DATA_IN(1, sr2, 1)); + + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR2, + sr2, 1); + } + + if (ret) + dev_dbg(nor->dev, "error %d reading SR2\n", ret); + + return ret; +} + +/** + * spi_nor_erase_chip() - Erase the entire flash memory. + * @nor: pointer to 'struct spi_nor'. * - * Returns 0 if successful, non-zero otherwise. + * Return: 0 on success, -errno otherwise. */ -static int erase_chip(struct spi_nor *nor) +static int spi_nor_erase_chip(struct spi_nor *nor) { + int ret; + dev_dbg(nor->dev, " %lldKiB\n", (long long)(nor->mtd.size >> 10)); if (nor->spimem) { @@ -868,10 +1212,99 @@ static int erase_chip(struct spi_nor *nor) SPI_MEM_OP_NO_DUMMY, SPI_MEM_OP_NO_DATA); - return spi_mem_exec_op(nor->spimem, &op); + ret = spi_mem_exec_op(nor->spimem, &op); + } else { + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_CHIP_ERASE, + NULL, 0); } - return nor->write_reg(nor, SPINOR_OP_CHIP_ERASE, NULL, 0); + if (ret) + dev_dbg(nor->dev, "error %d erasing chip\n", ret); + + return ret; +} + +static struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd) +{ + return mtd->priv; +} + +static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + if (table[i][0] == opcode) + return table[i][1]; + + /* No conversion found, keep input op code. */ + return opcode; +} + +static u8 spi_nor_convert_3to4_read(u8 opcode) +{ + static const u8 spi_nor_3to4_read[][2] = { + { SPINOR_OP_READ, SPINOR_OP_READ_4B }, + { SPINOR_OP_READ_FAST, SPINOR_OP_READ_FAST_4B }, + { SPINOR_OP_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B }, + { SPINOR_OP_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B }, + { SPINOR_OP_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B }, + { SPINOR_OP_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B }, + { SPINOR_OP_READ_1_1_8, SPINOR_OP_READ_1_1_8_4B }, + { SPINOR_OP_READ_1_8_8, SPINOR_OP_READ_1_8_8_4B }, + + { SPINOR_OP_READ_1_1_1_DTR, SPINOR_OP_READ_1_1_1_DTR_4B }, + { SPINOR_OP_READ_1_2_2_DTR, SPINOR_OP_READ_1_2_2_DTR_4B }, + { SPINOR_OP_READ_1_4_4_DTR, SPINOR_OP_READ_1_4_4_DTR_4B }, + }; + + return spi_nor_convert_opcode(opcode, spi_nor_3to4_read, + ARRAY_SIZE(spi_nor_3to4_read)); +} + +static u8 spi_nor_convert_3to4_program(u8 opcode) +{ + static const u8 spi_nor_3to4_program[][2] = { + { SPINOR_OP_PP, SPINOR_OP_PP_4B }, + { SPINOR_OP_PP_1_1_4, SPINOR_OP_PP_1_1_4_4B }, + { SPINOR_OP_PP_1_4_4, SPINOR_OP_PP_1_4_4_4B }, + { SPINOR_OP_PP_1_1_8, SPINOR_OP_PP_1_1_8_4B }, + { SPINOR_OP_PP_1_8_8, SPINOR_OP_PP_1_8_8_4B }, + }; + + return spi_nor_convert_opcode(opcode, spi_nor_3to4_program, + ARRAY_SIZE(spi_nor_3to4_program)); +} + +static u8 spi_nor_convert_3to4_erase(u8 opcode) +{ + static const u8 spi_nor_3to4_erase[][2] = { + { SPINOR_OP_BE_4K, SPINOR_OP_BE_4K_4B }, + { SPINOR_OP_BE_32K, SPINOR_OP_BE_32K_4B }, + { SPINOR_OP_SE, SPINOR_OP_SE_4B }, + }; + + return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase, + ARRAY_SIZE(spi_nor_3to4_erase)); +} + +static void spi_nor_set_4byte_opcodes(struct spi_nor *nor) +{ + nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode); + nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode); + nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode); + + if (!spi_nor_has_uniform_erase(nor)) { + struct spi_nor_erase_map *map = &nor->params.erase_map; + struct spi_nor_erase_type *erase; + int i; + + for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) { + erase = &map->erase_type[i]; + erase->opcode = + spi_nor_convert_3to4_erase(erase->opcode); + } + } } static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops) @@ -880,10 +1313,9 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops) mutex_lock(&nor->lock); - if (nor->prepare) { - ret = nor->prepare(nor, ops); + if (nor->controller_ops && nor->controller_ops->prepare) { + ret = nor->controller_ops->prepare(nor, ops); if (ret) { - dev_err(nor->dev, "failed in the preparation.\n"); mutex_unlock(&nor->lock); return ret; } @@ -893,8 +1325,8 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops) static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops) { - if (nor->unprepare) - nor->unprepare(nor, ops); + if (nor->controller_ops && nor->controller_ops->unprepare) + nor->controller_ops->unprepare(nor, ops); mutex_unlock(&nor->lock); } @@ -935,9 +1367,6 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) addr = spi_nor_convert_addr(nor, addr); - if (nor->erase) - return nor->erase(nor, addr); - if (nor->spimem) { struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->erase_opcode, 1), @@ -946,6 +1375,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) SPI_MEM_OP_NO_DATA); return spi_mem_exec_op(nor->spimem, &op); + } else if (nor->controller_ops->erase) { + return nor->controller_ops->erase(nor, addr); } /* @@ -957,8 +1388,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) addr >>= 8; } - return nor->write_reg(nor, nor->erase_opcode, nor->bouncebuf, - nor->addr_width); + return nor->controller_ops->write_reg(nor, nor->erase_opcode, + nor->bouncebuf, nor->addr_width); } /** @@ -1208,7 +1639,9 @@ static int spi_nor_erase_multi_sectors(struct spi_nor *nor, u64 addr, u32 len) list_for_each_entry_safe(cmd, next, &erase_list, list) { nor->erase_opcode = cmd->opcode; while (cmd->count) { - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + goto destroy_erase_cmd_list; ret = spi_nor_erase_sector(nor, addr); if (ret) @@ -1263,12 +1696,13 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr) if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) { unsigned long timeout; - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + goto erase_err; - if (erase_chip(nor)) { - ret = -EIO; + ret = spi_nor_erase_chip(nor); + if (ret) goto erase_err; - } /* * Scale the timeout linearly with the size of the flash, with @@ -1291,7 +1725,9 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr) /* "sector"-at-a-time erase */ } else if (spi_nor_has_uniform_erase(nor)) { while (len) { - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + goto erase_err; ret = spi_nor_erase_sector(nor, addr); if (ret) @@ -1312,7 +1748,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr) goto erase_err; } - write_disable(nor); + ret = spi_nor_write_disable(nor); erase_err: spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_ERASE); @@ -1320,27 +1756,6 @@ erase_err: return ret; } -/* Write status register and ensure bits in mask match written values */ -static int write_sr_and_check(struct spi_nor *nor, u8 status_new, u8 mask) -{ - int ret; - - write_enable(nor); - ret = write_sr(nor, status_new); - if (ret) - return ret; - - ret = spi_nor_wait_till_ready(nor); - if (ret) - return ret; - - ret = read_sr(nor); - if (ret < 0) - return ret; - - return ((ret & mask) != (status_new & mask)) ? -EIO : 0; -} - static void stm_get_locked_range(struct spi_nor *nor, u8 sr, loff_t *ofs, uint64_t *len) { @@ -1433,16 +1848,18 @@ static int stm_is_unlocked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len, static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len) { struct mtd_info *mtd = &nor->mtd; - int status_old, status_new; + int ret, status_old, status_new; u8 mask = SR_BP2 | SR_BP1 | SR_BP0; u8 shift = ffs(mask) - 1, pow, val; loff_t lock_len; bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB; bool use_top; - status_old = read_sr(nor); - if (status_old < 0) - return status_old; + ret = spi_nor_read_sr(nor, nor->bouncebuf); + if (ret) + return ret; + + status_old = nor->bouncebuf[0]; /* If nothing in our range is unlocked, we don't need to do anything */ if (stm_is_locked_sr(nor, ofs, len, status_old)) @@ -1502,7 +1919,7 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len) if ((status_new & mask) < (status_old & mask)) return -EINVAL; - return write_sr_and_check(nor, status_new, mask); + return spi_nor_write_sr_and_check(nor, status_new); } /* @@ -1513,16 +1930,18 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len) static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len) { struct mtd_info *mtd = &nor->mtd; - int status_old, status_new; + int ret, status_old, status_new; u8 mask = SR_BP2 | SR_BP1 | SR_BP0; u8 shift = ffs(mask) - 1, pow, val; loff_t lock_len; bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB; bool use_top; - status_old = read_sr(nor); - if (status_old < 0) - return status_old; + ret = spi_nor_read_sr(nor, nor->bouncebuf); + if (ret) + return ret; + + status_old = nor->bouncebuf[0]; /* If nothing in our range is locked, we don't need to do anything */ if (stm_is_unlocked_sr(nor, ofs, len, status_old)) @@ -1585,7 +2004,7 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len) if ((status_new & mask) > (status_old & mask)) return -EINVAL; - return write_sr_and_check(nor, status_new, mask); + return spi_nor_write_sr_and_check(nor, status_new); } /* @@ -1597,13 +2016,13 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len) */ static int stm_is_locked(struct spi_nor *nor, loff_t ofs, uint64_t len) { - int status; + int ret; - status = read_sr(nor); - if (status < 0) - return status; + ret = spi_nor_read_sr(nor, nor->bouncebuf); + if (ret) + return ret; - return stm_is_locked_sr(nor, ofs, len, status); + return stm_is_locked_sr(nor, ofs, len, nor->bouncebuf[0]); } static const struct spi_nor_locking_ops stm_locking_ops = { @@ -1657,242 +2076,59 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len) return ret; } -/* - * Write status Register and configuration register with 2 bytes - * The first byte will be written to the status register, while the - * second byte will be written to the configuration register. - * Return negative if error occurred. - */ -static int write_sr_cr(struct spi_nor *nor, u8 *sr_cr) -{ - int ret; - - write_enable(nor); - - if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(2, sr_cr, 1)); - - ret = spi_mem_exec_op(nor->spimem, &op); - } else { - ret = nor->write_reg(nor, SPINOR_OP_WRSR, sr_cr, 2); - } - - if (ret < 0) { - dev_err(nor->dev, - "error while writing configuration register\n"); - return -EINVAL; - } - - ret = spi_nor_wait_till_ready(nor); - if (ret) { - dev_err(nor->dev, - "timeout while writing configuration register\n"); - return ret; - } - - return 0; -} - -/** - * macronix_quad_enable() - set QE bit in Status Register. - * @nor: pointer to a 'struct spi_nor' - * - * Set the Quad Enable (QE) bit in the Status Register. - * - * bit 6 of the Status Register is the QE bit for Macronix like QSPI memories. - * - * Return: 0 on success, -errno otherwise. - */ -static int macronix_quad_enable(struct spi_nor *nor) -{ - int ret, val; - - val = read_sr(nor); - if (val < 0) - return val; - if (val & SR_QUAD_EN_MX) - return 0; - - write_enable(nor); - - write_sr(nor, val | SR_QUAD_EN_MX); - - ret = spi_nor_wait_till_ready(nor); - if (ret) - return ret; - - ret = read_sr(nor); - if (!(ret > 0 && (ret & SR_QUAD_EN_MX))) { - dev_err(nor->dev, "Macronix Quad bit not set\n"); - return -EINVAL; - } - - return 0; -} - /** - * spansion_quad_enable() - set QE bit in Configuraiton Register. + * spi_nor_sr1_bit6_quad_enable() - Set the Quad Enable BIT(6) in the Status + * Register 1. * @nor: pointer to a 'struct spi_nor' * - * Set the Quad Enable (QE) bit in the Configuration Register. - * This function is kept for legacy purpose because it has been used for a - * long time without anybody complaining but it should be considered as - * deprecated and maybe buggy. - * First, this function doesn't care about the previous values of the Status - * and Configuration Registers when it sets the QE bit (bit 1) in the - * Configuration Register: all other bits are cleared, which may have unwanted - * side effects like removing some block protections. - * Secondly, it uses the Read Configuration Register (35h) instruction though - * some very old and few memories don't support this instruction. If a pull-up - * resistor is present on the MISO/IO1 line, we might still be able to pass the - * "read back" test because the QSPI memory doesn't recognize the command, - * so leaves the MISO/IO1 line state unchanged, hence read_cr() returns 0xFF. - * - * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI - * memories. + * Bit 6 of the Status Register 1 is the QE bit for Macronix like QSPI memories. * * Return: 0 on success, -errno otherwise. */ -static int spansion_quad_enable(struct spi_nor *nor) +static int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor) { - u8 *sr_cr = nor->bouncebuf; int ret; - sr_cr[0] = 0; - sr_cr[1] = CR_QUAD_EN_SPAN; - ret = write_sr_cr(nor, sr_cr); + ret = spi_nor_read_sr(nor, nor->bouncebuf); if (ret) return ret; - /* read back and check it */ - ret = read_cr(nor); - if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) { - dev_err(nor->dev, "Spansion Quad bit not set\n"); - return -EINVAL; - } - - return 0; -} - -/** - * spansion_no_read_cr_quad_enable() - set QE bit in Configuration Register. - * @nor: pointer to a 'struct spi_nor' - * - * Set the Quad Enable (QE) bit in the Configuration Register. - * This function should be used with QSPI memories not supporting the Read - * Configuration Register (35h) instruction. - * - * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI - * memories. - * - * Return: 0 on success, -errno otherwise. - */ -static int spansion_no_read_cr_quad_enable(struct spi_nor *nor) -{ - u8 *sr_cr = nor->bouncebuf; - int ret; + if (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6) + return 0; - /* Keep the current value of the Status Register. */ - ret = read_sr(nor); - if (ret < 0) { - dev_err(nor->dev, "error while reading status register\n"); - return -EINVAL; - } - sr_cr[0] = ret; - sr_cr[1] = CR_QUAD_EN_SPAN; + nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6; - return write_sr_cr(nor, sr_cr); + return spi_nor_write_sr1_and_check(nor, nor->bouncebuf[0]); } /** - * spansion_read_cr_quad_enable() - set QE bit in Configuration Register. - * @nor: pointer to a 'struct spi_nor' - * - * Set the Quad Enable (QE) bit in the Configuration Register. - * This function should be used with QSPI memories supporting the Read - * Configuration Register (35h) instruction. + * spi_nor_sr2_bit1_quad_enable() - set the Quad Enable BIT(1) in the Status + * Register 2. + * @nor: pointer to a 'struct spi_nor'. * - * bit 1 of the Configuration Register is the QE bit for Spansion like QSPI - * memories. + * Bit 1 of the Status Register 2 is the QE bit for Spansion like QSPI memories. * * Return: 0 on success, -errno otherwise. */ -static int spansion_read_cr_quad_enable(struct spi_nor *nor) +static int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor) { - struct device *dev = nor->dev; - u8 *sr_cr = nor->bouncebuf; int ret; - /* Check current Quad Enable bit value. */ - ret = read_cr(nor); - if (ret < 0) { - dev_err(dev, "error while reading configuration register\n"); - return -EINVAL; - } - - if (ret & CR_QUAD_EN_SPAN) - return 0; + if (nor->flags & SNOR_F_NO_READ_CR) + return spi_nor_write_16bit_cr_and_check(nor, SR2_QUAD_EN_BIT1); - sr_cr[1] = ret | CR_QUAD_EN_SPAN; - - /* Keep the current value of the Status Register. */ - ret = read_sr(nor); - if (ret < 0) { - dev_err(dev, "error while reading status register\n"); - return -EINVAL; - } - sr_cr[0] = ret; - - ret = write_sr_cr(nor, sr_cr); + ret = spi_nor_read_cr(nor, nor->bouncebuf); if (ret) return ret; - /* Read back and check it. */ - ret = read_cr(nor); - if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) { - dev_err(nor->dev, "Spansion Quad bit not set\n"); - return -EINVAL; - } - - return 0; -} - -static int spi_nor_write_sr2(struct spi_nor *nor, u8 *sr2) -{ - if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 1), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(1, sr2, 1)); - - return spi_mem_exec_op(nor->spimem, &op); - } - - return nor->write_reg(nor, SPINOR_OP_WRSR2, sr2, 1); -} - -static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2) -{ - if (nor->spimem) { - struct spi_mem_op op = - SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 1), - SPI_MEM_OP_NO_ADDR, - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(1, sr2, 1)); - - return spi_mem_exec_op(nor->spimem, &op); - } + if (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1) + return 0; - return nor->read_reg(nor, SPINOR_OP_RDSR2, sr2, 1); + return spi_nor_write_16bit_cr_and_check(nor, nor->bouncebuf[0]); } /** - * sr2_bit7_quad_enable() - set QE bit in Status Register 2. + * spi_nor_sr2_bit7_quad_enable() - set QE bit in Status Register 2. * @nor: pointer to a 'struct spi_nor' * * Set the Quad Enable (QE) bit in the Status Register 2. @@ -1903,10 +2139,11 @@ static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2) * * Return: 0 on success, -errno otherwise. */ -static int sr2_bit7_quad_enable(struct spi_nor *nor) +static int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor) { u8 *sr2 = nor->bouncebuf; int ret; + u8 sr2_written; /* Check current Quad Enable bit value. */ ret = spi_nor_read_sr2(nor, sr2); @@ -1918,117 +2155,23 @@ static int sr2_bit7_quad_enable(struct spi_nor *nor) /* Update the Quad Enable bit. */ *sr2 |= SR2_QUAD_EN_BIT7; - write_enable(nor); - ret = spi_nor_write_sr2(nor, sr2); - if (ret < 0) { - dev_err(nor->dev, "error while writing status register 2\n"); - return -EINVAL; - } - - ret = spi_nor_wait_till_ready(nor); - if (ret < 0) { - dev_err(nor->dev, "timeout while writing status register 2\n"); + if (ret) return ret; - } + + sr2_written = *sr2; /* Read back and check it. */ ret = spi_nor_read_sr2(nor, sr2); - if (!(ret > 0 && (*sr2 & SR2_QUAD_EN_BIT7))) { - dev_err(nor->dev, "SR2 Quad bit not set\n"); - return -EINVAL; - } - - return 0; -} - -/** - * spi_nor_clear_sr_bp() - clear the Status Register Block Protection bits. - * @nor: pointer to a 'struct spi_nor' - * - * Read-modify-write function that clears the Block Protection bits from the - * Status Register without affecting other bits. - * - * Return: 0 on success, -errno otherwise. - */ -static int spi_nor_clear_sr_bp(struct spi_nor *nor) -{ - int ret; - u8 mask = SR_BP2 | SR_BP1 | SR_BP0; - - ret = read_sr(nor); - if (ret < 0) { - dev_err(nor->dev, "error while reading status register\n"); - return ret; - } - - write_enable(nor); - - ret = write_sr(nor, ret & ~mask); - if (ret) { - dev_err(nor->dev, "write to status register failed\n"); - return ret; - } - - ret = spi_nor_wait_till_ready(nor); if (ret) - dev_err(nor->dev, "timeout while writing status register\n"); - return ret; -} - -/** - * spi_nor_spansion_clear_sr_bp() - clear the Status Register Block Protection - * bits on spansion flashes. - * @nor: pointer to a 'struct spi_nor' - * - * Read-modify-write function that clears the Block Protection bits from the - * Status Register without affecting other bits. The function is tightly - * coupled with the spansion_quad_enable() function. Both assume that the Write - * Register with 16 bits, together with the Read Configuration Register (35h) - * instructions are supported. - * - * Return: 0 on success, -errno otherwise. - */ -static int spi_nor_spansion_clear_sr_bp(struct spi_nor *nor) -{ - int ret; - u8 mask = SR_BP2 | SR_BP1 | SR_BP0; - u8 *sr_cr = nor->bouncebuf; - - /* Check current Quad Enable bit value. */ - ret = read_cr(nor); - if (ret < 0) { - dev_err(nor->dev, - "error while reading configuration register\n"); return ret; - } - - /* - * When the configuration register Quad Enable bit is one, only the - * Write Status (01h) command with two data bytes may be used. - */ - if (ret & CR_QUAD_EN_SPAN) { - sr_cr[1] = ret; - ret = read_sr(nor); - if (ret < 0) { - dev_err(nor->dev, - "error while reading status register\n"); - return ret; - } - sr_cr[0] = ret & ~mask; - - ret = write_sr_cr(nor, sr_cr); - if (ret) - dev_err(nor->dev, "16-bit write register failed\n"); - return ret; + if (*sr2 != sr2_written) { + dev_dbg(nor->dev, "SR2: Read back test failed\n"); + return -EIO; } - /* - * If the Quad Enable bit is zero, use the Write Status (01h) command - * with one data byte. - */ - return spi_nor_clear_sr_bp(nor); + return 0; } /* Used when the "_ext_id" is two bytes at most */ @@ -2136,7 +2279,7 @@ static void gd25q256_default_init(struct spi_nor *nor) * indicate the quad_enable method for this case, we need * to set it in the default_init fixup hook. */ - nor->params.quad_enable = macronix_quad_enable; + nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable; } static struct spi_nor_fixups gd25q256_fixups = { @@ -2179,6 +2322,8 @@ static const struct flash_info spi_nor_ids[] = { { "en25q64", INFO(0x1c3017, 0, 64 * 1024, 128, SECT_4K) }, { "en25q80a", INFO(0x1c3014, 0, 64 * 1024, 16, SECT_4K | SPI_NOR_DUAL_READ) }, + { "en25qh16", INFO(0x1c7015, 0, 64 * 1024, 32, + SECT_4K | SPI_NOR_DUAL_READ) }, { "en25qh32", INFO(0x1c7016, 0, 64 * 1024, 64, 0) }, { "en25qh64", INFO(0x1c7017, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ) }, @@ -2267,6 +2412,10 @@ static const struct flash_info spi_nor_ids[] = { SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "is25wp128", INFO(0x9d7018, 0, 64 * 1024, 256, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, + { "is25wp256", INFO(0x9d7019, 0, 64 * 1024, 512, + SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | + SPI_NOR_4B_OPCODES) + .fixups = &is25lp256_fixups }, /* Macronix */ { "mx25l512e", INFO(0xc22010, 0, 64 * 1024, 1, SECT_4K) }, @@ -2482,6 +2631,8 @@ static const struct flash_info spi_nor_ids[] = { { "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "w25q256jvm", INFO(0xef7019, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, + { "w25q256jw", INFO(0xef6019, 0, 64 * 1024, 512, + SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "w25m512jv", INFO(0xef7119, 0, 64 * 1024, 1024, SECT_4K | SPI_NOR_QUAD_READ | SPI_NOR_DUAL_READ) }, @@ -2520,11 +2671,11 @@ static const struct flash_info *spi_nor_read_id(struct spi_nor *nor) tmp = spi_mem_exec_op(nor->spimem, &op); } else { - tmp = nor->read_reg(nor, SPINOR_OP_RDID, id, - SPI_NOR_MAX_ID_LEN); + tmp = nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id, + SPI_NOR_MAX_ID_LEN); } - if (tmp < 0) { - dev_err(nor->dev, "error %d reading JEDEC ID\n", tmp); + if (tmp) { + dev_dbg(nor->dev, "error %d reading JEDEC ID\n", tmp); return ERR_PTR(tmp); } @@ -2544,7 +2695,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct spi_nor *nor = mtd_to_spi_nor(mtd); - int ret; + ssize_t ret; dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len); @@ -2583,7 +2734,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf) { struct spi_nor *nor = mtd_to_spi_nor(mtd); - size_t actual; + size_t actual = 0; int ret; dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len); @@ -2592,26 +2743,28 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len, if (ret) return ret; - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + goto out; nor->sst_write_second = false; - actual = to % 2; /* Start write from odd address. */ - if (actual) { + if (to % 2) { nor->program_opcode = SPINOR_OP_BP; /* write one byte. */ ret = spi_nor_write_data(nor, to, 1, buf); if (ret < 0) - goto sst_write_err; - WARN(ret != 1, "While writing 1 byte written %i bytes\n", - (int)ret); + goto out; + WARN(ret != 1, "While writing 1 byte written %i bytes\n", ret); ret = spi_nor_wait_till_ready(nor); if (ret) - goto sst_write_err; + goto out; + + to++; + actual++; } - to += actual; /* Write out most of the data here. */ for (; actual < len - 1; actual += 2) { @@ -2620,39 +2773,44 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len, /* write two bytes. */ ret = spi_nor_write_data(nor, to, 2, buf + actual); if (ret < 0) - goto sst_write_err; - WARN(ret != 2, "While writing 2 bytes written %i bytes\n", - (int)ret); + goto out; + WARN(ret != 2, "While writing 2 bytes written %i bytes\n", ret); ret = spi_nor_wait_till_ready(nor); if (ret) - goto sst_write_err; + goto out; to += 2; nor->sst_write_second = true; } nor->sst_write_second = false; - write_disable(nor); + ret = spi_nor_write_disable(nor); + if (ret) + goto out; + ret = spi_nor_wait_till_ready(nor); if (ret) - goto sst_write_err; + goto out; /* Write out trailing byte if it exists. */ if (actual != len) { - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + goto out; nor->program_opcode = SPINOR_OP_BP; ret = spi_nor_write_data(nor, to, 1, buf + actual); if (ret < 0) - goto sst_write_err; - WARN(ret != 1, "While writing 1 byte written %i bytes\n", - (int)ret); + goto out; + WARN(ret != 1, "While writing 1 byte written %i bytes\n", ret); ret = spi_nor_wait_till_ready(nor); if (ret) - goto sst_write_err; - write_disable(nor); + goto out; + actual += 1; + + ret = spi_nor_write_disable(nor); } -sst_write_err: +out: *retlen += actual; spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE); return ret; @@ -2701,7 +2859,10 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len, addr = spi_nor_convert_addr(nor, addr); - write_enable(nor); + ret = spi_nor_write_enable(nor); + if (ret) + goto write_err; + ret = spi_nor_write_data(nor, addr, page_remain, buf + i); if (ret < 0) goto write_err; @@ -2722,13 +2883,21 @@ write_err: static int spi_nor_check(struct spi_nor *nor) { if (!nor->dev || - (!nor->spimem && - (!nor->read || !nor->write || !nor->read_reg || - !nor->write_reg))) { + (!nor->spimem && !nor->controller_ops) || + (!nor->spimem && nor->controller_ops && + (!nor->controller_ops->read || + !nor->controller_ops->write || + !nor->controller_ops->read_reg || + !nor->controller_ops->write_reg))) { pr_err("spi-nor: please fill all the necessary fields!\n"); return -EINVAL; } + if (nor->spimem && nor->controller_ops) { + dev_err(nor->dev, "nor->spimem and nor->controller_ops are mutually exclusive, please set just one of them.\n"); + return -EINVAL; + } + return 0; } @@ -2738,10 +2907,8 @@ static int s3an_nor_setup(struct spi_nor *nor, int ret; ret = spi_nor_xread_sr(nor, nor->bouncebuf); - if (ret < 0) { - dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret); + if (ret) return ret; - } nor->erase_opcode = SPINOR_OP_XSE; nor->program_opcode = SPINOR_OP_XPP; @@ -2865,7 +3032,7 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps) */ static int spi_nor_read_raw(struct spi_nor *nor, u32 addr, size_t len, u8 *buf) { - int ret; + ssize_t ret; while (len) { ret = spi_nor_read_data(nor, addr, len, buf); @@ -3489,20 +3656,39 @@ static int spi_nor_parse_bfpt(struct spi_nor *nor, break; case BFPT_DWORD15_QER_SR2_BIT1_BUGGY: + /* + * Writing only one byte to the Status Register has the + * side-effect of clearing Status Register 2. + */ case BFPT_DWORD15_QER_SR2_BIT1_NO_RD: - params->quad_enable = spansion_no_read_cr_quad_enable; + /* + * Read Configuration Register (35h) instruction is not + * supported. + */ + nor->flags |= SNOR_F_HAS_16BIT_SR | SNOR_F_NO_READ_CR; + params->quad_enable = spi_nor_sr2_bit1_quad_enable; break; case BFPT_DWORD15_QER_SR1_BIT6: - params->quad_enable = macronix_quad_enable; + nor->flags &= ~SNOR_F_HAS_16BIT_SR; + params->quad_enable = spi_nor_sr1_bit6_quad_enable; break; case BFPT_DWORD15_QER_SR2_BIT7: - params->quad_enable = sr2_bit7_quad_enable; + nor->flags &= ~SNOR_F_HAS_16BIT_SR; + params->quad_enable = spi_nor_sr2_bit7_quad_enable; break; case BFPT_DWORD15_QER_SR2_BIT1: - params->quad_enable = spansion_read_cr_quad_enable; + /* + * JESD216 rev B or later does not specify if writing only one + * byte to the Status Register clears or not the Status + * Register 2, so let's be cautious and keep the default + * assumption of a 16-bit Write Status (01h) command. + */ + nor->flags |= SNOR_F_HAS_16BIT_SR; + + params->quad_enable = spi_nor_sr2_bit1_quad_enable; break; default: @@ -4101,7 +4287,7 @@ static int spi_nor_parse_sfdp(struct spi_nor *nor, err = spi_nor_read_sfdp(nor, sizeof(header), psize, param_headers); if (err < 0) { - dev_err(dev, "failed to read SFDP parameter headers\n"); + dev_dbg(dev, "failed to read SFDP parameter headers\n"); goto exit; } } @@ -4348,7 +4534,7 @@ static int spi_nor_default_setup(struct spi_nor *nor, /* Select the (Fast) Read command. */ err = spi_nor_select_read(nor, shared_mask); if (err) { - dev_err(nor->dev, + dev_dbg(nor->dev, "can't select read settings supported by both the SPI controller and memory.\n"); return err; } @@ -4356,7 +4542,7 @@ static int spi_nor_default_setup(struct spi_nor *nor, /* Select the Page Program command. */ err = spi_nor_select_pp(nor, shared_mask); if (err) { - dev_err(nor->dev, + dev_dbg(nor->dev, "can't select write settings supported by both the SPI controller and memory.\n"); return err; } @@ -4364,7 +4550,7 @@ static int spi_nor_default_setup(struct spi_nor *nor, /* Select the Sector Erase command. */ err = spi_nor_select_erase(nor); if (err) { - dev_err(nor->dev, + dev_dbg(nor->dev, "can't select erase settings supported by both the SPI controller and memory.\n"); return err; } @@ -4381,12 +4567,32 @@ static int spi_nor_setup(struct spi_nor *nor, return nor->params.setup(nor, hwcaps); } +static void atmel_set_default_init(struct spi_nor *nor) +{ + nor->flags |= SNOR_F_HAS_LOCK; +} + +static void intel_set_default_init(struct spi_nor *nor) +{ + nor->flags |= SNOR_F_HAS_LOCK; +} + +static void issi_set_default_init(struct spi_nor *nor) +{ + nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable; +} + static void macronix_set_default_init(struct spi_nor *nor) { - nor->params.quad_enable = macronix_quad_enable; + nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable; nor->params.set_4byte = macronix_set_4byte; } +static void sst_set_default_init(struct spi_nor *nor) +{ + nor->flags |= SNOR_F_HAS_LOCK; +} + static void st_micron_set_default_init(struct spi_nor *nor) { nor->flags |= SNOR_F_HAS_LOCK; @@ -4408,6 +4614,18 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor) { /* Init flash parameters based on MFR */ switch (JEDEC_MFR(nor->info)) { + case SNOR_MFR_ATMEL: + atmel_set_default_init(nor); + break; + + case SNOR_MFR_INTEL: + intel_set_default_init(nor); + break; + + case SNOR_MFR_ISSI: + issi_set_default_init(nor); + break; + case SNOR_MFR_MACRONIX: macronix_set_default_init(nor); break; @@ -4417,6 +4635,10 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor) st_micron_set_default_init(nor); break; + case SNOR_MFR_SST: + sst_set_default_init(nor); + break; + case SNOR_MFR_WINBOND: winbond_set_default_init(nor); break; @@ -4465,9 +4687,11 @@ static void spi_nor_info_init_params(struct spi_nor *nor) u8 i, erase_mask; /* Initialize legacy flash parameters and settings. */ - params->quad_enable = spansion_quad_enable; + params->quad_enable = spi_nor_sr2_bit1_quad_enable; params->set_4byte = spansion_set_4byte; params->setup = spi_nor_default_setup; + /* Default to 16-bit Write Status (01h) Command */ + nor->flags |= SNOR_F_HAS_16BIT_SR; /* Set SPI NOR sizes. */ params->size = (u64)info->sector_size * info->n_sectors; @@ -4675,25 +4899,36 @@ static int spi_nor_quad_enable(struct spi_nor *nor) return nor->params.quad_enable(nor); } +/** + * spi_nor_unlock_all() - Unlocks the entire flash memory array. + * @nor: pointer to a 'struct spi_nor'. + * + * Some SPI NOR flashes are write protected by default after a power-on reset + * cycle, in order to avoid inadvertent writes during power-up. Backward + * compatibility imposes to unlock the entire flash memory array at power-up + * by default. + */ +static int spi_nor_unlock_all(struct spi_nor *nor) +{ + if (nor->flags & SNOR_F_HAS_LOCK) + return spi_nor_unlock(&nor->mtd, 0, nor->params.size); + + return 0; +} + static int spi_nor_init(struct spi_nor *nor) { int err; - if (nor->clear_sr_bp) { - if (nor->params.quad_enable == spansion_quad_enable) - nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp; - - err = nor->clear_sr_bp(nor); - if (err) { - dev_err(nor->dev, - "fail to clear block protection bits\n"); - return err; - } + err = spi_nor_quad_enable(nor); + if (err) { + dev_dbg(nor->dev, "quad mode not supported\n"); + return err; } - err = spi_nor_quad_enable(nor); + err = spi_nor_unlock_all(nor); if (err) { - dev_err(nor->dev, "quad mode not supported\n"); + dev_dbg(nor->dev, "Failed to unlock the entire flash memory array\n"); return err; } @@ -4761,7 +4996,7 @@ static int spi_nor_set_addr_width(struct spi_nor *nor) } if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) { - dev_err(nor->dev, "address width is too large: %u\n", + dev_dbg(nor->dev, "address width is too large: %u\n", nor->addr_width); return -EINVAL; } @@ -4879,16 +5114,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, if (info->flags & SPI_NOR_HAS_LOCK) nor->flags |= SNOR_F_HAS_LOCK; - /* - * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up - * with the software protection bits set. - */ - if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL || - JEDEC_MFR(nor->info) == SNOR_MFR_INTEL || - JEDEC_MFR(nor->info) == SNOR_MFR_SST || - nor->info->flags & SPI_NOR_HAS_LOCK) - nor->clear_sr_bp = spi_nor_clear_sr_bp; - /* Init flash parameters based on flash_info struct and SFDP */ spi_nor_init_params(nor); diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index a1dff92ceedf..0f847d510950 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -509,11 +509,9 @@ static const struct file_operations eraseblk_count_fops = { */ int ubi_debugfs_init_dev(struct ubi_device *ubi) { - int err, n; unsigned long ubi_num = ubi->ubi_num; - const char *fname; - struct dentry *dent; struct ubi_debug_info *d = &ubi->dbg; + int n; if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; @@ -522,95 +520,52 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi) ubi->ubi_num); if (n == UBI_DFS_DIR_LEN) { /* The array size is too small */ - fname = UBI_DFS_DIR_NAME; - dent = ERR_PTR(-EINVAL); - goto out; + return -EINVAL; } - fname = d->dfs_dir_name; - dent = debugfs_create_dir(fname, dfs_rootdir); - if (IS_ERR_OR_NULL(dent)) - goto out; - d->dfs_dir = dent; - - fname = "chk_gen"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_gen = dent; - - fname = "chk_io"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_io = dent; - - fname = "chk_fastmap"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_fastmap = dent; - - fname = "tst_disable_bgt"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_disable_bgt = dent; - - fname = "tst_emulate_bitflips"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_emulate_bitflips = dent; - - fname = "tst_emulate_io_failures"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_emulate_io_failures = dent; - - fname = "tst_emulate_power_cut"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_emulate_power_cut = dent; - - fname = "tst_emulate_power_cut_min"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_power_cut_min = dent; - - fname = "tst_emulate_power_cut_max"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_power_cut_max = dent; - - fname = "detailed_erase_block_info"; - dent = debugfs_create_file(fname, S_IRUSR, d->dfs_dir, (void *)ubi_num, - &eraseblk_count_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; + d->dfs_dir = debugfs_create_dir(d->dfs_dir_name, dfs_rootdir); - return 0; + d->dfs_chk_gen = debugfs_create_file("chk_gen", S_IWUSR, d->dfs_dir, + (void *)ubi_num, &dfs_fops); -out_remove: - debugfs_remove_recursive(d->dfs_dir); -out: - err = dent ? PTR_ERR(dent) : -ENODEV; - ubi_err(ubi, "cannot create \"%s\" debugfs file or directory, error %d\n", - fname, err); - return err; + d->dfs_chk_io = debugfs_create_file("chk_io", S_IWUSR, d->dfs_dir, + (void *)ubi_num, &dfs_fops); + + d->dfs_chk_fastmap = debugfs_create_file("chk_fastmap", S_IWUSR, + d->dfs_dir, (void *)ubi_num, + &dfs_fops); + + d->dfs_disable_bgt = debugfs_create_file("tst_disable_bgt", S_IWUSR, + d->dfs_dir, (void *)ubi_num, + &dfs_fops); + + d->dfs_emulate_bitflips = debugfs_create_file("tst_emulate_bitflips", + S_IWUSR, d->dfs_dir, + (void *)ubi_num, + &dfs_fops); + + d->dfs_emulate_io_failures = debugfs_create_file("tst_emulate_io_failures", + S_IWUSR, d->dfs_dir, + (void *)ubi_num, + &dfs_fops); + + d->dfs_emulate_power_cut = debugfs_create_file("tst_emulate_power_cut", + S_IWUSR, d->dfs_dir, + (void *)ubi_num, + &dfs_fops); + + d->dfs_power_cut_min = debugfs_create_file("tst_emulate_power_cut_min", + S_IWUSR, d->dfs_dir, + (void *)ubi_num, &dfs_fops); + + d->dfs_power_cut_max = debugfs_create_file("tst_emulate_power_cut_max", + S_IWUSR, d->dfs_dir, + (void *)ubi_num, &dfs_fops); + + debugfs_create_file("detailed_erase_block_info", S_IRUSR, d->dfs_dir, + (void *)ubi_num, &eraseblk_count_fops); + + return 0; } /** diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 480f9459b402..62f65573eb04 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2083,8 +2083,7 @@ static int bond_miimon_inspect(struct bonding *bond) ignore_updelay = !rcu_dereference(bond->curr_active_slave); bond_for_each_slave_rcu(bond, slave, iter) { - slave->new_link = BOND_LINK_NOCHANGE; - slave->link_new_state = slave->link; + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); link_state = bond_check_dev_link(bond, slave->dev, 0); @@ -2118,7 +2117,7 @@ static int bond_miimon_inspect(struct bonding *bond) } if (slave->delay <= 0) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; continue; } @@ -2155,7 +2154,7 @@ static int bond_miimon_inspect(struct bonding *bond) slave->delay = 0; if (slave->delay <= 0) { - slave->new_link = BOND_LINK_UP; + bond_propose_link_state(slave, BOND_LINK_UP); commit++; ignore_updelay = false; continue; @@ -2193,7 +2192,7 @@ static void bond_miimon_commit(struct bonding *bond) struct slave *slave, *primary; bond_for_each_slave(bond, slave, iter) { - switch (slave->new_link) { + switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: /* For 802.3ad mode, check current slave speed and * duplex again in case its port was disabled after @@ -2265,8 +2264,8 @@ static void bond_miimon_commit(struct bonding *bond) default: slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", - slave->new_link); - slave->new_link = BOND_LINK_NOCHANGE; + slave->link_new_state); + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); continue; } @@ -2674,13 +2673,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) bond_for_each_slave_rcu(bond, slave, iter) { unsigned long trans_start = dev_trans_start(slave->dev); - slave->new_link = BOND_LINK_NOCHANGE; + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, trans_start, 1) && bond_time_in_interval(bond, slave->last_rx, 1)) { - slave->new_link = BOND_LINK_UP; + bond_propose_link_state(slave, BOND_LINK_UP); slave_state_changed = 1; /* primary_slave has no meaning in round-robin @@ -2705,7 +2704,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) if (!bond_time_in_interval(bond, trans_start, 2) || !bond_time_in_interval(bond, slave->last_rx, 2)) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; if (slave->link_failure_count < UINT_MAX) @@ -2736,8 +2735,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) goto re_arm; bond_for_each_slave(bond, slave, iter) { - if (slave->new_link != BOND_LINK_NOCHANGE) - slave->link = slave->new_link; + if (slave->link_new_state != BOND_LINK_NOCHANGE) + slave->link = slave->link_new_state; } if (slave_state_changed) { @@ -2760,9 +2759,9 @@ re_arm: } /* Called to inspect slaves for active-backup mode ARP monitor link state - * changes. Sets new_link in slaves to specify what action should take - * place for the slave. Returns 0 if no changes are found, >0 if changes - * to link states must be committed. + * changes. Sets proposed link state in slaves to specify what action + * should take place for the slave. Returns 0 if no changes are found, >0 + * if changes to link states must be committed. * * Called with rcu_read_lock held. */ @@ -2774,12 +2773,12 @@ static int bond_ab_arp_inspect(struct bonding *bond) int commit = 0; bond_for_each_slave_rcu(bond, slave, iter) { - slave->new_link = BOND_LINK_NOCHANGE; + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); last_rx = slave_last_rx(bond, slave); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_rx, 1)) { - slave->new_link = BOND_LINK_UP; + bond_propose_link_state(slave, BOND_LINK_UP); commit++; } continue; @@ -2807,7 +2806,7 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (!bond_is_active_slave(slave) && !rcu_access_pointer(bond->current_arp_slave) && !bond_time_in_interval(bond, last_rx, 3)) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } @@ -2820,7 +2819,7 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (bond_is_active_slave(slave) && (!bond_time_in_interval(bond, trans_start, 2) || !bond_time_in_interval(bond, last_rx, 2))) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } } @@ -2840,7 +2839,7 @@ static void bond_ab_arp_commit(struct bonding *bond) struct slave *slave; bond_for_each_slave(bond, slave, iter) { - switch (slave->new_link) { + switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: continue; @@ -2890,8 +2889,9 @@ static void bond_ab_arp_commit(struct bonding *bond) continue; default: - slave_err(bond->dev, slave->dev, "impossible: new_link %d on slave\n", - slave->new_link); + slave_err(bond->dev, slave->dev, + "impossible: link_new_state %d on slave\n", + slave->link_new_state); continue; } diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 606b7d8ffe13..8e9f5620c9a2 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -52,6 +52,7 @@ #define CONTROL_EX_PDR BIT(8) /* control register */ +#define CONTROL_SWR BIT(15) #define CONTROL_TEST BIT(7) #define CONTROL_CCE BIT(6) #define CONTROL_DISABLE_AR BIT(5) @@ -97,6 +98,9 @@ #define BTR_TSEG2_SHIFT 12 #define BTR_TSEG2_MASK (0x7 << BTR_TSEG2_SHIFT) +/* interrupt register */ +#define INT_STS_PENDING 0x8000 + /* brp extension register */ #define BRP_EXT_BRPE_MASK 0x0f #define BRP_EXT_BRPE_SHIFT 0 @@ -569,6 +573,26 @@ static void c_can_configure_msg_objects(struct net_device *dev) IF_MCONT_RCV_EOB); } +static int c_can_software_reset(struct net_device *dev) +{ + struct c_can_priv *priv = netdev_priv(dev); + int retry = 0; + + if (priv->type != BOSCH_D_CAN) + return 0; + + priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_SWR | CONTROL_INIT); + while (priv->read_reg(priv, C_CAN_CTRL_REG) & CONTROL_SWR) { + msleep(20); + if (retry++ > 100) { + netdev_err(dev, "CCTRL: software reset failed\n"); + return -EIO; + } + } + + return 0; +} + /* * Configure C_CAN chip: * - enable/disable auto-retransmission @@ -578,6 +602,11 @@ static void c_can_configure_msg_objects(struct net_device *dev) static int c_can_chip_config(struct net_device *dev) { struct c_can_priv *priv = netdev_priv(dev); + int err; + + err = c_can_software_reset(dev); + if (err) + return err; /* enable automatic retransmission */ priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_ENABLE_AR); @@ -886,6 +915,9 @@ static int c_can_handle_state_change(struct net_device *dev, struct can_berr_counter bec; switch (error_type) { + case C_CAN_NO_ERROR: + priv->can.state = CAN_STATE_ERROR_ACTIVE; + break; case C_CAN_ERROR_WARNING: /* error warning state */ priv->can.can_stats.error_warning++; @@ -916,6 +948,13 @@ static int c_can_handle_state_change(struct net_device *dev, ERR_CNT_RP_SHIFT; switch (error_type) { + case C_CAN_NO_ERROR: + /* error warning state */ + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = CAN_ERR_CRTL_ACTIVE; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + break; case C_CAN_ERROR_WARNING: /* error warning state */ cf->can_id |= CAN_ERR_CRTL; @@ -1029,10 +1068,16 @@ static int c_can_poll(struct napi_struct *napi, int quota) u16 curr, last = priv->last_status; int work_done = 0; - priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG); - /* Ack status on C_CAN. D_CAN is self clearing */ - if (priv->type != BOSCH_D_CAN) - priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED); + /* Only read the status register if a status interrupt was pending */ + if (atomic_xchg(&priv->sie_pending, 0)) { + priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG); + /* Ack status on C_CAN. D_CAN is self clearing */ + if (priv->type != BOSCH_D_CAN) + priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED); + } else { + /* no change detected ... */ + curr = last; + } /* handle state changes */ if ((curr & STATUS_EWARN) && (!(last & STATUS_EWARN))) { @@ -1054,11 +1099,17 @@ static int c_can_poll(struct napi_struct *napi, int quota) /* handle bus recovery events */ if ((!(curr & STATUS_BOFF)) && (last & STATUS_BOFF)) { netdev_dbg(dev, "left bus off state\n"); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + work_done += c_can_handle_state_change(dev, C_CAN_ERROR_PASSIVE); } + if ((!(curr & STATUS_EPASS)) && (last & STATUS_EPASS)) { netdev_dbg(dev, "left error passive state\n"); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + work_done += c_can_handle_state_change(dev, C_CAN_ERROR_WARNING); + } + + if ((!(curr & STATUS_EWARN)) && (last & STATUS_EWARN)) { + netdev_dbg(dev, "left error warning state\n"); + work_done += c_can_handle_state_change(dev, C_CAN_NO_ERROR); } /* handle lec errors on the bus */ @@ -1083,10 +1134,16 @@ static irqreturn_t c_can_isr(int irq, void *dev_id) { struct net_device *dev = (struct net_device *)dev_id; struct c_can_priv *priv = netdev_priv(dev); + int reg_int; - if (!priv->read_reg(priv, C_CAN_INT_REG)) + reg_int = priv->read_reg(priv, C_CAN_INT_REG); + if (!reg_int) return IRQ_NONE; + /* save for later use */ + if (reg_int & INT_STS_PENDING) + atomic_set(&priv->sie_pending, 1); + /* disable all interrupts and schedule the NAPI */ c_can_irq_control(priv, false); napi_schedule(&priv->napi); diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h index 8acdc7fa4792..d5567a7c1c6d 100644 --- a/drivers/net/can/c_can/c_can.h +++ b/drivers/net/can/c_can/c_can.h @@ -198,6 +198,7 @@ struct c_can_priv { struct net_device *dev; struct device *device; atomic_t tx_active; + atomic_t sie_pending; unsigned long tx_dir; int last_status; u16 (*read_reg) (const struct c_can_priv *priv, enum reg index); diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index ac86be52b461..1c88c361938c 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -848,6 +848,7 @@ void of_can_transceiver(struct net_device *dev) return; ret = of_property_read_u32(dn, "max-bitrate", &priv->bitrate_max); + of_node_put(dn); if ((ret && ret != -EINVAL) || (!ret && !priv->bitrate_max)) netdev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit.\n"); } diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index dc5695dffc2e..57f9a2f51085 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -677,6 +677,7 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr) struct can_frame *cf; bool rx_errors = false, tx_errors = false; u32 timestamp; + int err; timestamp = priv->read(®s->timer) << 16; @@ -725,7 +726,9 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr) if (tx_errors) dev->stats.tx_errors++; - can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + if (err) + dev->stats.rx_fifo_errors++; } static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) @@ -738,6 +741,7 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) int flt; struct can_berr_counter bec; u32 timestamp; + int err; timestamp = priv->read(®s->timer) << 16; @@ -769,7 +773,9 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) if (unlikely(new_state == CAN_STATE_BUS_OFF)) can_bus_off(dev); - can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + if (err) + dev->stats.rx_fifo_errors++; } static inline struct flexcan_priv *rx_offload_to_priv(struct can_rx_offload *offload) @@ -1188,6 +1194,7 @@ static int flexcan_chip_start(struct net_device *dev) reg_mecr = priv->read(®s->mecr); reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS; priv->write(reg_mecr, ®s->mecr); + reg_mecr |= FLEXCAN_MECR_ECCDIS; reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK | FLEXCAN_MECR_FANCEI_MSK); priv->write(reg_mecr, ®s->mecr); diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index 6ac4c35f247a..38ea5e600fb8 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -107,7 +107,7 @@ static int m_can_plat_probe(struct platform_device *pdev) mcan_class->is_peripheral = false; - platform_set_drvdata(pdev, mcan_class->dev); + platform_set_drvdata(pdev, mcan_class->net); m_can_init_ram(mcan_class); @@ -166,8 +166,6 @@ static int __maybe_unused m_can_runtime_resume(struct device *dev) if (err) clk_disable_unprepare(mcan_class->hclk); - m_can_class_resume(dev); - return err; } diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index e6a668ee7730..84cae167e42f 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -107,37 +107,95 @@ static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b) return cb_b->timestamp - cb_a->timestamp; } -static struct sk_buff *can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n) +/** + * can_rx_offload_offload_one() - Read one CAN frame from HW + * @offload: pointer to rx_offload context + * @n: number of mailbox to read + * + * The task of this function is to read a CAN frame from mailbox @n + * from the device and return the mailbox's content as a struct + * sk_buff. + * + * If the struct can_rx_offload::skb_queue exceeds the maximal queue + * length (struct can_rx_offload::skb_queue_len_max) or no skb can be + * allocated, the mailbox contents is discarded by reading it into an + * overflow buffer. This way the mailbox is marked as free by the + * driver. + * + * Return: A pointer to skb containing the CAN frame on success. + * + * NULL if the mailbox @n is empty. + * + * ERR_PTR() in case of an error + */ +static struct sk_buff * +can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n) { - struct sk_buff *skb = NULL; + struct sk_buff *skb = NULL, *skb_error = NULL; struct can_rx_offload_cb *cb; struct can_frame *cf; int ret; - /* If queue is full or skb not available, read to discard mailbox */ - if (likely(skb_queue_len(&offload->skb_queue) <= - offload->skb_queue_len_max)) + if (likely(skb_queue_len(&offload->skb_queue) < + offload->skb_queue_len_max)) { skb = alloc_can_skb(offload->dev, &cf); + if (unlikely(!skb)) + skb_error = ERR_PTR(-ENOMEM); /* skb alloc failed */ + } else { + skb_error = ERR_PTR(-ENOBUFS); /* skb_queue is full */ + } - if (!skb) { + /* If queue is full or skb not available, drop by reading into + * overflow buffer. + */ + if (unlikely(skb_error)) { struct can_frame cf_overflow; u32 timestamp; ret = offload->mailbox_read(offload, &cf_overflow, ×tamp, n); - if (ret) - offload->dev->stats.rx_dropped++; - return NULL; + /* Mailbox was empty. */ + if (unlikely(!ret)) + return NULL; + + /* Mailbox has been read and we're dropping it or + * there was a problem reading the mailbox. + * + * Increment error counters in any case. + */ + offload->dev->stats.rx_dropped++; + offload->dev->stats.rx_fifo_errors++; + + /* There was a problem reading the mailbox, propagate + * error value. + */ + if (unlikely(ret < 0)) + return ERR_PTR(ret); + + return skb_error; } cb = can_rx_offload_get_cb(skb); ret = offload->mailbox_read(offload, cf, &cb->timestamp, n); - if (!ret) { + + /* Mailbox was empty. */ + if (unlikely(!ret)) { kfree_skb(skb); return NULL; } + /* There was a problem reading the mailbox, propagate error value. */ + if (unlikely(ret < 0)) { + kfree_skb(skb); + + offload->dev->stats.rx_dropped++; + offload->dev->stats.rx_fifo_errors++; + + return ERR_PTR(ret); + } + + /* Mailbox was read. */ return skb; } @@ -157,8 +215,8 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 pen continue; skb = can_rx_offload_offload_one(offload, i); - if (!skb) - break; + if (IS_ERR_OR_NULL(skb)) + continue; __skb_queue_add_sort(&skb_queue, skb, can_rx_offload_compare); } @@ -188,7 +246,13 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload) struct sk_buff *skb; int received = 0; - while ((skb = can_rx_offload_offload_one(offload, 0))) { + while (1) { + skb = can_rx_offload_offload_one(offload, 0); + if (IS_ERR(skb)) + continue; + if (!skb) + break; + skb_queue_tail(&offload->skb_queue, skb); received++; } @@ -207,8 +271,10 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, unsigned long flags; if (skb_queue_len(&offload->skb_queue) > - offload->skb_queue_len_max) - return -ENOMEM; + offload->skb_queue_len_max) { + kfree_skb(skb); + return -ENOBUFS; + } cb = can_rx_offload_get_cb(skb); cb->timestamp = timestamp; @@ -250,8 +316,10 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb) { if (skb_queue_len(&offload->skb_queue) > - offload->skb_queue_len_max) - return -ENOMEM; + offload->skb_queue_len_max) { + kfree_skb(skb); + return -ENOBUFS; + } skb_queue_tail(&offload->skb_queue, skb); can_rx_offload_schedule(offload); diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index bb6032211043..0a9f42e5fedf 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -617,6 +617,7 @@ err_free_chan: sl->tty = NULL; tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); + free_netdev(sl->dev); err_exit: rtnl_unlock(); diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index bee9f7b8dad6..bb20a9b75cc6 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -717,6 +717,7 @@ static void mcp251x_restart_work_handler(struct work_struct *ws) if (priv->after_suspend) { mcp251x_hw_reset(spi); mcp251x_setup(net, spi); + priv->force_quit = 0; if (priv->after_suspend & AFTER_SUSPEND_RESTART) { mcp251x_set_normal_mode(spi); } else if (priv->after_suspend & AFTER_SUSPEND_UP) { @@ -728,7 +729,6 @@ static void mcp251x_restart_work_handler(struct work_struct *ws) mcp251x_hw_sleep(spi); } priv->after_suspend = 0; - priv->force_quit = 0; } if (priv->restart_tx) { diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index f8b19eef5d26..31ad364a89bb 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -73,6 +73,7 @@ MODULE_VERSION(HECC_MODULE_VERSION); */ #define HECC_MAX_RX_MBOX (HECC_MAX_MAILBOXES - HECC_MAX_TX_MBOX) #define HECC_RX_FIRST_MBOX (HECC_MAX_MAILBOXES - 1) +#define HECC_RX_LAST_MBOX (HECC_MAX_TX_MBOX) /* TI HECC module registers */ #define HECC_CANME 0x0 /* Mailbox enable */ @@ -82,7 +83,7 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_CANTA 0x10 /* Transmission acknowledge */ #define HECC_CANAA 0x14 /* Abort acknowledge */ #define HECC_CANRMP 0x18 /* Receive message pending */ -#define HECC_CANRML 0x1C /* Remote message lost */ +#define HECC_CANRML 0x1C /* Receive message lost */ #define HECC_CANRFP 0x20 /* Remote frame pending */ #define HECC_CANGAM 0x24 /* SECC only:Global acceptance mask */ #define HECC_CANMC 0x28 /* Master control */ @@ -149,6 +150,8 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_BUS_ERROR (HECC_CANES_FE | HECC_CANES_BE |\ HECC_CANES_CRCE | HECC_CANES_SE |\ HECC_CANES_ACKE) +#define HECC_CANES_FLAGS (HECC_BUS_ERROR | HECC_CANES_BO |\ + HECC_CANES_EP | HECC_CANES_EW) #define HECC_CANMCF_RTR BIT(4) /* Remote transmit request */ @@ -382,8 +385,18 @@ static void ti_hecc_start(struct net_device *ndev) hecc_set_bit(priv, HECC_CANMIM, mbx_mask); } - /* Prevent message over-write & Enable interrupts */ - hecc_write(priv, HECC_CANOPC, HECC_SET_REG); + /* Enable tx interrupts */ + hecc_set_bit(priv, HECC_CANMIM, BIT(HECC_MAX_TX_MBOX) - 1); + + /* Prevent message over-write to create a rx fifo, but not for + * the lowest priority mailbox, since that allows detecting + * overflows instead of the hardware silently dropping the + * messages. + */ + mbx_mask = ~BIT(HECC_RX_LAST_MBOX); + hecc_write(priv, HECC_CANOPC, mbx_mask); + + /* Enable interrupts */ if (priv->use_hecc1int) { hecc_write(priv, HECC_CANMIL, HECC_SET_REG); hecc_write(priv, HECC_CANGIM, HECC_CANGIM_DEF_MASK | @@ -400,6 +413,9 @@ static void ti_hecc_stop(struct net_device *ndev) { struct ti_hecc_priv *priv = netdev_priv(ndev); + /* Disable the CPK; stop sending, erroring and acking */ + hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_CCR); + /* Disable interrupts and disable mailboxes */ hecc_write(priv, HECC_CANGIM, 0); hecc_write(priv, HECC_CANMIM, 0); @@ -508,8 +524,6 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev) hecc_set_bit(priv, HECC_CANME, mbx_mask); spin_unlock_irqrestore(&priv->mbx_lock, flags); - hecc_clear_bit(priv, HECC_CANMD, mbx_mask); - hecc_set_bit(priv, HECC_CANMIM, mbx_mask); hecc_write(priv, HECC_CANTRS, mbx_mask); return NETDEV_TX_OK; @@ -526,8 +540,10 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload, u32 *timestamp, unsigned int mbxno) { struct ti_hecc_priv *priv = rx_offload_to_priv(offload); - u32 data; + u32 data, mbx_mask; + int ret = 1; + mbx_mask = BIT(mbxno); data = hecc_read_mbx(priv, mbxno, HECC_CANMID); if (data & HECC_CANMID_IDE) cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG; @@ -548,7 +564,25 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload, *timestamp = hecc_read_stamp(priv, mbxno); - return 1; + /* Check for FIFO overrun. + * + * All but the last RX mailbox have activated overwrite + * protection. So skip check for overrun, if we're not + * handling the last RX mailbox. + * + * As the overwrite protection for the last RX mailbox is + * disabled, the CAN core might update while we're reading + * it. This means the skb might be inconsistent. + * + * Return an error to let rx-offload discard this CAN frame. + */ + if (unlikely(mbxno == HECC_RX_LAST_MBOX && + hecc_read(priv, HECC_CANRML) & mbx_mask)) + ret = -ENOBUFS; + + hecc_write(priv, HECC_CANRMP, mbx_mask); + + return ret; } static int ti_hecc_error(struct net_device *ndev, int int_status, @@ -558,92 +592,73 @@ static int ti_hecc_error(struct net_device *ndev, int int_status, struct can_frame *cf; struct sk_buff *skb; u32 timestamp; + int err; - /* propagate the error condition to the can stack */ - skb = alloc_can_err_skb(ndev, &cf); - if (!skb) { - if (printk_ratelimit()) - netdev_err(priv->ndev, - "%s: alloc_can_err_skb() failed\n", - __func__); - return -ENOMEM; - } - - if (int_status & HECC_CANGIF_WLIF) { /* warning level int */ - if ((int_status & HECC_CANGIF_BOIF) == 0) { - priv->can.state = CAN_STATE_ERROR_WARNING; - ++priv->can.can_stats.error_warning; - cf->can_id |= CAN_ERR_CRTL; - if (hecc_read(priv, HECC_CANTEC) > 96) - cf->data[1] |= CAN_ERR_CRTL_TX_WARNING; - if (hecc_read(priv, HECC_CANREC) > 96) - cf->data[1] |= CAN_ERR_CRTL_RX_WARNING; - } - hecc_set_bit(priv, HECC_CANES, HECC_CANES_EW); - netdev_dbg(priv->ndev, "Error Warning interrupt\n"); - hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR); - } - - if (int_status & HECC_CANGIF_EPIF) { /* error passive int */ - if ((int_status & HECC_CANGIF_BOIF) == 0) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - ++priv->can.can_stats.error_passive; - cf->can_id |= CAN_ERR_CRTL; - if (hecc_read(priv, HECC_CANTEC) > 127) - cf->data[1] |= CAN_ERR_CRTL_TX_PASSIVE; - if (hecc_read(priv, HECC_CANREC) > 127) - cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE; + if (err_status & HECC_BUS_ERROR) { + /* propagate the error condition to the can stack */ + skb = alloc_can_err_skb(ndev, &cf); + if (!skb) { + if (net_ratelimit()) + netdev_err(priv->ndev, + "%s: alloc_can_err_skb() failed\n", + __func__); + return -ENOMEM; } - hecc_set_bit(priv, HECC_CANES, HECC_CANES_EP); - netdev_dbg(priv->ndev, "Error passive interrupt\n"); - hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR); - } - - /* Need to check busoff condition in error status register too to - * ensure warning interrupts don't hog the system - */ - if ((int_status & HECC_CANGIF_BOIF) || (err_status & HECC_CANES_BO)) { - priv->can.state = CAN_STATE_BUS_OFF; - cf->can_id |= CAN_ERR_BUSOFF; - hecc_set_bit(priv, HECC_CANES, HECC_CANES_BO); - hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR); - /* Disable all interrupts in bus-off to avoid int hog */ - hecc_write(priv, HECC_CANGIM, 0); - ++priv->can.can_stats.bus_off; - can_bus_off(ndev); - } - if (err_status & HECC_BUS_ERROR) { ++priv->can.can_stats.bus_error; cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT; - if (err_status & HECC_CANES_FE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_FE); + if (err_status & HECC_CANES_FE) cf->data[2] |= CAN_ERR_PROT_FORM; - } - if (err_status & HECC_CANES_BE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_BE); + if (err_status & HECC_CANES_BE) cf->data[2] |= CAN_ERR_PROT_BIT; - } - if (err_status & HECC_CANES_SE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_SE); + if (err_status & HECC_CANES_SE) cf->data[2] |= CAN_ERR_PROT_STUFF; - } - if (err_status & HECC_CANES_CRCE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE); + if (err_status & HECC_CANES_CRCE) cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ; - } - if (err_status & HECC_CANES_ACKE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE); + if (err_status & HECC_CANES_ACKE) cf->data[3] = CAN_ERR_PROT_LOC_ACK; - } + + timestamp = hecc_read(priv, HECC_CANLNT); + err = can_rx_offload_queue_sorted(&priv->offload, skb, + timestamp); + if (err) + ndev->stats.rx_fifo_errors++; } - timestamp = hecc_read(priv, HECC_CANLNT); - can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + hecc_write(priv, HECC_CANES, HECC_CANES_FLAGS); return 0; } +static void ti_hecc_change_state(struct net_device *ndev, + enum can_state rx_state, + enum can_state tx_state) +{ + struct ti_hecc_priv *priv = netdev_priv(ndev); + struct can_frame *cf; + struct sk_buff *skb; + u32 timestamp; + int err; + + skb = alloc_can_err_skb(priv->ndev, &cf); + if (unlikely(!skb)) { + priv->can.state = max(tx_state, rx_state); + return; + } + + can_change_state(priv->ndev, cf, tx_state, rx_state); + + if (max(tx_state, rx_state) != CAN_STATE_BUS_OFF) { + cf->data[6] = hecc_read(priv, HECC_CANTEC); + cf->data[7] = hecc_read(priv, HECC_CANREC); + } + + timestamp = hecc_read(priv, HECC_CANLNT); + err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + if (err) + ndev->stats.rx_fifo_errors++; +} + static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) { struct net_device *ndev = (struct net_device *)dev_id; @@ -651,6 +666,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) struct net_device_stats *stats = &ndev->stats; u32 mbxno, mbx_mask, int_status, err_status, stamp; unsigned long flags, rx_pending; + u32 handled = 0; int_status = hecc_read(priv, priv->use_hecc1int ? @@ -660,17 +676,66 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) return IRQ_NONE; err_status = hecc_read(priv, HECC_CANES); - if (err_status & (HECC_BUS_ERROR | HECC_CANES_BO | - HECC_CANES_EP | HECC_CANES_EW)) + if (unlikely(err_status & HECC_CANES_FLAGS)) ti_hecc_error(ndev, int_status, err_status); + if (unlikely(int_status & HECC_CANGIM_DEF_MASK)) { + enum can_state rx_state, tx_state; + u32 rec = hecc_read(priv, HECC_CANREC); + u32 tec = hecc_read(priv, HECC_CANTEC); + + if (int_status & HECC_CANGIF_WLIF) { + handled |= HECC_CANGIF_WLIF; + rx_state = rec >= tec ? CAN_STATE_ERROR_WARNING : 0; + tx_state = rec <= tec ? CAN_STATE_ERROR_WARNING : 0; + netdev_dbg(priv->ndev, "Error Warning interrupt\n"); + ti_hecc_change_state(ndev, rx_state, tx_state); + } + + if (int_status & HECC_CANGIF_EPIF) { + handled |= HECC_CANGIF_EPIF; + rx_state = rec >= tec ? CAN_STATE_ERROR_PASSIVE : 0; + tx_state = rec <= tec ? CAN_STATE_ERROR_PASSIVE : 0; + netdev_dbg(priv->ndev, "Error passive interrupt\n"); + ti_hecc_change_state(ndev, rx_state, tx_state); + } + + if (int_status & HECC_CANGIF_BOIF) { + handled |= HECC_CANGIF_BOIF; + rx_state = CAN_STATE_BUS_OFF; + tx_state = CAN_STATE_BUS_OFF; + netdev_dbg(priv->ndev, "Bus off interrupt\n"); + + /* Disable all interrupts */ + hecc_write(priv, HECC_CANGIM, 0); + can_bus_off(ndev); + ti_hecc_change_state(ndev, rx_state, tx_state); + } + } else if (unlikely(priv->can.state != CAN_STATE_ERROR_ACTIVE)) { + enum can_state new_state, tx_state, rx_state; + u32 rec = hecc_read(priv, HECC_CANREC); + u32 tec = hecc_read(priv, HECC_CANTEC); + + if (rec >= 128 || tec >= 128) + new_state = CAN_STATE_ERROR_PASSIVE; + else if (rec >= 96 || tec >= 96) + new_state = CAN_STATE_ERROR_WARNING; + else + new_state = CAN_STATE_ERROR_ACTIVE; + + if (new_state < priv->can.state) { + rx_state = rec >= tec ? new_state : 0; + tx_state = rec <= tec ? new_state : 0; + ti_hecc_change_state(ndev, rx_state, tx_state); + } + } + if (int_status & HECC_CANGIF_GMIF) { while (priv->tx_tail - priv->tx_head > 0) { mbxno = get_tx_tail_mb(priv); mbx_mask = BIT(mbxno); if (!(mbx_mask & hecc_read(priv, HECC_CANTA))) break; - hecc_clear_bit(priv, HECC_CANMIM, mbx_mask); hecc_write(priv, HECC_CANTA, mbx_mask); spin_lock_irqsave(&priv->mbx_lock, flags); hecc_clear_bit(priv, HECC_CANME, mbx_mask); @@ -695,16 +760,15 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) while ((rx_pending = hecc_read(priv, HECC_CANRMP))) { can_rx_offload_irq_offload_timestamp(&priv->offload, rx_pending); - hecc_write(priv, HECC_CANRMP, rx_pending); } } /* clear all interrupt conditions - read back to avoid spurious ints */ if (priv->use_hecc1int) { - hecc_write(priv, HECC_CANGIF1, HECC_SET_REG); + hecc_write(priv, HECC_CANGIF1, handled); int_status = hecc_read(priv, HECC_CANGIF1); } else { - hecc_write(priv, HECC_CANGIF0, HECC_SET_REG); + hecc_write(priv, HECC_CANGIF0, handled); int_status = hecc_read(priv, HECC_CANGIF0); } @@ -877,7 +941,7 @@ static int ti_hecc_probe(struct platform_device *pdev) priv->offload.mailbox_read = ti_hecc_mailbox_read; priv->offload.mb_first = HECC_RX_FIRST_MBOX; - priv->offload.mb_last = HECC_MAX_TX_MBOX; + priv->offload.mb_last = HECC_RX_LAST_MBOX; err = can_rx_offload_add_timestamp(ndev, &priv->offload); if (err) { dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n"); diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index bd6eb9967630..2f74f6704c12 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -623,6 +623,7 @@ static int gs_can_open(struct net_device *netdev) rc); usb_unanchor_urb(urb); + usb_free_urb(urb); break; } diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 19a702ac49e4..21faa2ec4632 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -876,9 +876,8 @@ static void mcba_usb_disconnect(struct usb_interface *intf) netdev_info(priv->netdev, "device disconnected\n"); unregister_candev(priv->netdev); - free_candev(priv->netdev); - mcba_urb_unlink(priv); + free_candev(priv->netdev); } static struct usb_driver mcba_usb_driver = { diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 617da295b6c1..d2539c95adb6 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -100,7 +100,7 @@ struct pcan_usb_msg_context { u8 *end; u8 rec_cnt; u8 rec_idx; - u8 rec_data_idx; + u8 rec_ts_idx; struct net_device *netdev; struct pcan_usb *pdev; }; @@ -436,8 +436,8 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, } if ((n & PCAN_USB_ERROR_BUS_LIGHT) == 0) { /* no error (back to active state) */ - mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE; - return 0; + new_state = CAN_STATE_ERROR_ACTIVE; + break; } break; @@ -460,9 +460,9 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, } if ((n & PCAN_USB_ERROR_BUS_HEAVY) == 0) { - /* no error (back to active state) */ - mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE; - return 0; + /* no error (back to warning state) */ + new_state = CAN_STATE_ERROR_WARNING; + break; } break; @@ -501,6 +501,11 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, mc->pdev->dev.can.can_stats.error_warning++; break; + case CAN_STATE_ERROR_ACTIVE: + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = CAN_ERR_CRTL_ACTIVE; + break; + default: /* CAN_STATE_MAX (trick to handle other errors) */ cf->can_id |= CAN_ERR_CRTL; @@ -547,10 +552,15 @@ static int pcan_usb_decode_status(struct pcan_usb_msg_context *mc, mc->ptr += PCAN_USB_CMD_ARGS; if (status_len & PCAN_USB_STATUSLEN_TIMESTAMP) { - int err = pcan_usb_decode_ts(mc, !mc->rec_idx); + int err = pcan_usb_decode_ts(mc, !mc->rec_ts_idx); if (err) return err; + + /* Next packet in the buffer will have a timestamp on a single + * byte + */ + mc->rec_ts_idx++; } switch (f) { @@ -632,10 +642,13 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len) cf->can_dlc = get_can_dlc(rec_len); - /* first data packet timestamp is a word */ - if (pcan_usb_decode_ts(mc, !mc->rec_data_idx)) + /* Only first packet timestamp is a word */ + if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx)) goto decode_failed; + /* Next packet in the buffer will have a timestamp on a single byte */ + mc->rec_ts_idx++; + /* read data */ memset(cf->data, 0x0, sizeof(cf->data)); if (status_len & PCAN_USB_STATUSLEN_RTR) { @@ -688,7 +701,6 @@ static int pcan_usb_decode_msg(struct peak_usb_device *dev, u8 *ibuf, u32 lbuf) /* handle normal can frames here */ } else { err = pcan_usb_decode_data(&mc, sl); - mc.rec_data_idx++; } } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 65dce642b86b..0b7766b715fd 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -750,7 +750,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, dev = netdev_priv(netdev); /* allocate a buffer large enough to send commands */ - dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); + dev->cmd_buf = kzalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); if (!dev->cmd_buf) { err = -ENOMEM; goto lbl_free_candev; diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index d596a2ad7f78..8fa224b28218 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -996,9 +996,8 @@ static void usb_8dev_disconnect(struct usb_interface *intf) netdev_info(priv->netdev, "device disconnected\n"); unregister_netdev(priv->netdev); - free_candev(priv->netdev); - unlink_all_urbs(priv); + free_candev(priv->netdev); } } diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 911b34316c9d..7c482b2d78d2 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -1599,7 +1599,6 @@ static const struct xcan_devtype_data xcan_zynq_data = { static const struct xcan_devtype_data xcan_axi_data = { .cantype = XAXI_CAN, - .flags = XCAN_FLAG_TXFEMP, .bittiming_const = &xcan_bittiming_const, .btr_ts2_shift = XCAN_BTR_TS2_SHIFT, .btr_sjw_shift = XCAN_BTR_SJW_SHIFT, diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index d44651ad520c..69fc13046ac7 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1215,10 +1215,10 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) struct bcm_sf2_priv *priv = platform_get_drvdata(pdev); priv->wol_ports_mask = 0; + /* Disable interrupts */ + bcm_sf2_intr_disable(priv); dsa_unregister_switch(priv->dev->ds); bcm_sf2_cfp_exit(priv->dev->ds); - /* Disable all ports and interrupts */ - bcm_sf2_sw_suspend(priv->dev->ds); bcm_sf2_mdio_unregister(priv); return 0; diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c index 073cbd0bb91b..d838c174dc0d 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.c +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -273,6 +273,19 @@ static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip, int pin; int err; + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests to enable time stamping on both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + pin = ptp_find_pin(chip->ptp_clock, PTP_PF_EXTTS, rq->extts.index); if (pin < 0) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 0f138280315a..1de51811fcb4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1996,8 +1996,6 @@ static void reset_umac(struct bcmgenet_priv *priv) /* issue soft reset with (rg)mii loopback to ensure a stable rxclk */ bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD); - udelay(2); - bcmgenet_umac_writel(priv, 0, UMAC_CMD); } static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) @@ -2614,8 +2612,10 @@ static void bcmgenet_irq_task(struct work_struct *work) spin_unlock_irq(&priv->lock); if (status & UMAC_IRQ_PHY_DET_R && - priv->dev->phydev->autoneg != AUTONEG_ENABLE) + priv->dev->phydev->autoneg != AUTONEG_ENABLE) { phy_init_hw(priv->dev->phydev); + genphy_config_aneg(priv->dev->phydev); + } /* Link UP/DOWN event */ if (status & UMAC_IRQ_LINK_EVENT) @@ -2879,12 +2879,6 @@ static int bcmgenet_open(struct net_device *dev) if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); - ret = bcmgenet_mii_connect(dev); - if (ret) { - netdev_err(dev, "failed to connect to PHY\n"); - goto err_clk_disable; - } - /* take MAC out of reset */ bcmgenet_umac_reset(priv); @@ -2894,12 +2888,6 @@ static int bcmgenet_open(struct net_device *dev) reg = bcmgenet_umac_readl(priv, UMAC_CMD); priv->crc_fwd_en = !!(reg & CMD_CRC_FWD); - ret = bcmgenet_mii_config(dev, true); - if (ret) { - netdev_err(dev, "unsupported PHY\n"); - goto err_disconnect_phy; - } - bcmgenet_set_hw_addr(priv, dev->dev_addr); if (priv->internal_phy) { @@ -2915,7 +2903,7 @@ static int bcmgenet_open(struct net_device *dev) ret = bcmgenet_init_dma(priv); if (ret) { netdev_err(dev, "failed to initialize DMA\n"); - goto err_disconnect_phy; + goto err_clk_disable; } /* Always enable ring 16 - descriptor ring */ @@ -2938,19 +2926,25 @@ static int bcmgenet_open(struct net_device *dev) goto err_irq0; } + ret = bcmgenet_mii_probe(dev); + if (ret) { + netdev_err(dev, "failed to connect to PHY\n"); + goto err_irq1; + } + bcmgenet_netif_start(dev); netif_tx_start_all_queues(dev); return 0; +err_irq1: + free_irq(priv->irq1, priv); err_irq0: free_irq(priv->irq0, priv); err_fini_dma: bcmgenet_dma_teardown(priv); bcmgenet_fini_dma(priv); -err_disconnect_phy: - phy_disconnect(dev->phydev); err_clk_disable: if (priv->internal_phy) bcmgenet_power_down(priv, GENET_POWER_PASSIVE); @@ -3631,8 +3625,6 @@ static int bcmgenet_resume(struct device *d) if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); - phy_init_hw(dev->phydev); - bcmgenet_umac_reset(priv); init_umac(priv); @@ -3641,7 +3633,10 @@ static int bcmgenet_resume(struct device *d) if (priv->wolopts) clk_disable_unprepare(priv->clk_wol); + phy_init_hw(dev->phydev); + /* Speed settings must be restored */ + genphy_config_aneg(dev->phydev); bcmgenet_mii_config(priv->dev, false); bcmgenet_set_hw_addr(priv, dev->dev_addr); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 7fbf573d8d52..dbc69d8fa05f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -720,8 +720,8 @@ GENET_IO_MACRO(rbuf, GENET_RBUF_OFF); /* MDIO routines */ int bcmgenet_mii_init(struct net_device *dev); -int bcmgenet_mii_connect(struct net_device *dev); int bcmgenet_mii_config(struct net_device *dev, bool init); +int bcmgenet_mii_probe(struct net_device *dev); void bcmgenet_mii_exit(struct net_device *dev); void bcmgenet_phy_power_set(struct net_device *dev, bool enable); void bcmgenet_mii_setup(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 17bb8d60a157..dbe18cdf6c1b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -173,46 +173,6 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) bcmgenet_fixed_phy_link_update); } -int bcmgenet_mii_connect(struct net_device *dev) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device_node *dn = priv->pdev->dev.of_node; - struct phy_device *phydev; - u32 phy_flags = 0; - int ret; - - /* Communicate the integrated PHY revision */ - if (priv->internal_phy) - phy_flags = priv->gphy_rev; - - /* Initialize link state variables that bcmgenet_mii_setup() uses */ - priv->old_link = -1; - priv->old_speed = -1; - priv->old_duplex = -1; - priv->old_pause = -1; - - if (dn) { - phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, - phy_flags, priv->phy_interface); - if (!phydev) { - pr_err("could not attach to PHY\n"); - return -ENODEV; - } - } else { - phydev = dev->phydev; - phydev->dev_flags = phy_flags; - - ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, - priv->phy_interface); - if (ret) { - pr_err("could not attach to PHY\n"); - return -ENODEV; - } - } - - return 0; -} - int bcmgenet_mii_config(struct net_device *dev, bool init) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -221,8 +181,38 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) const char *phy_name = NULL; u32 id_mode_dis = 0; u32 port_ctrl; + int bmcr = -1; + int ret; u32 reg; + /* MAC clocking workaround during reset of umac state machines */ + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + if (reg & CMD_SW_RESET) { + /* An MII PHY must be isolated to prevent TXC contention */ + if (priv->phy_interface == PHY_INTERFACE_MODE_MII) { + ret = phy_read(phydev, MII_BMCR); + if (ret >= 0) { + bmcr = ret; + ret = phy_write(phydev, MII_BMCR, + bmcr | BMCR_ISOLATE); + } + if (ret) { + netdev_err(dev, "failed to isolate PHY\n"); + return ret; + } + } + /* Switch MAC clocking to RGMII generated clock */ + bcmgenet_sys_writel(priv, PORT_MODE_EXT_GPHY, SYS_PORT_CTRL); + /* Ensure 5 clks with Rx disabled + * followed by 5 clks with Reset asserted + */ + udelay(4); + reg &= ~(CMD_SW_RESET | CMD_LCL_LOOP_EN); + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + /* Ensure 5 more clocks before Rx is enabled */ + udelay(2); + } + priv->ext_phy = !priv->internal_phy && (priv->phy_interface != PHY_INTERFACE_MODE_MOCA); @@ -254,6 +244,9 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) phy_set_max_speed(phydev, SPEED_100); bcmgenet_sys_writel(priv, PORT_MODE_EXT_EPHY, SYS_PORT_CTRL); + /* Restore the MII PHY after isolation */ + if (bmcr >= 0) + phy_write(phydev, MII_BMCR, bmcr); break; case PHY_INTERFACE_MODE_REVMII: @@ -306,21 +299,71 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } - if (init) { - linkmode_copy(phydev->advertising, phydev->supported); + if (init) + dev_info(kdev, "configuring instance for %s\n", phy_name); - /* The internal PHY has its link interrupts routed to the - * Ethernet MAC ISRs. On GENETv5 there is a hardware issue - * that prevents the signaling of link UP interrupts when - * the link operates at 10Mbps, so fallback to polling for - * those versions of GENET. - */ - if (priv->internal_phy && !GENET_IS_V5(priv)) - phydev->irq = PHY_IGNORE_INTERRUPT; + return 0; +} - dev_info(kdev, "configuring instance for %s\n", phy_name); +int bcmgenet_mii_probe(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; + struct phy_device *phydev; + u32 phy_flags = 0; + int ret; + + /* Communicate the integrated PHY revision */ + if (priv->internal_phy) + phy_flags = priv->gphy_rev; + + /* Initialize link state variables that bcmgenet_mii_setup() uses */ + priv->old_link = -1; + priv->old_speed = -1; + priv->old_duplex = -1; + priv->old_pause = -1; + + if (dn) { + phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, + phy_flags, priv->phy_interface); + if (!phydev) { + pr_err("could not attach to PHY\n"); + return -ENODEV; + } + } else { + phydev = dev->phydev; + phydev->dev_flags = phy_flags; + + ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, + priv->phy_interface); + if (ret) { + pr_err("could not attach to PHY\n"); + return -ENODEV; + } } + /* Configure port multiplexer based on what the probed PHY device since + * reading the 'max-speed' property determines the maximum supported + * PHY speed which is needed for bcmgenet_mii_config() to configure + * things appropriately. + */ + ret = bcmgenet_mii_config(dev, true); + if (ret) { + phy_disconnect(dev->phydev); + return ret; + } + + linkmode_copy(phydev->advertising, phydev->supported); + + /* The internal PHY has its link interrupts routed to the + * Ethernet MAC ISRs. On GENETv5 there is a hardware issue + * that prevents the signaling of link UP interrupts when + * the link operates at 10Mbps, so fallback to polling for + * those versions of GENET. + */ + if (priv->internal_phy && !GENET_IS_V5(priv)) + dev->phydev->irq = PHY_IGNORE_INTERRUPT; + return 0; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 77f3511b97de..ca3aa1250dd1 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6280,6 +6280,10 @@ static int tg3_ptp_enable(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + if (rq->perout.index != 0) return -EINVAL; diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 0e5de88fd6e8..cdd7e5da4a74 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1499,7 +1499,7 @@ static int octeon_mgmt_probe(struct platform_device *pdev) netdev->ethtool_ops = &octeon_mgmt_ethtool_ops; netdev->min_mtu = 64 - OCTEON_MGMT_RX_HEADROOM; - netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM; + netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM - VLAN_HLEN; mac = of_get_mac_address(pdev->dev.of_node); diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index f1a0c4dceda0..f37c9a08c4cf 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -763,6 +763,7 @@ static int ep93xx_eth_remove(struct platform_device *pdev) { struct net_device *dev; struct ep93xx_priv *ep; + struct resource *mem; dev = platform_get_drvdata(pdev); if (dev == NULL) @@ -778,8 +779,8 @@ static int ep93xx_eth_remove(struct platform_device *pdev) iounmap(ep->base_addr); if (ep->res != NULL) { - release_resource(ep->res); - kfree(ep->res); + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + release_mem_region(mem->start, resource_size(mem)); } free_netdev(dev); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index e736ce2c58ca..a8f4c69252ff 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2524,6 +2524,7 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev) struct gemini_ethernet_port *port = platform_get_drvdata(pdev); gemini_port_remove(port); + free_netdev(port->netdev); return 0; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 19379bae0144..bf5add954181 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -2232,8 +2232,16 @@ err_set_cdan: err_service_reg: free_channel(priv, channel); err_alloc_ch: - if (err == -EPROBE_DEFER) + if (err == -EPROBE_DEFER) { + for (i = 0; i < priv->num_channels; i++) { + channel = priv->channel[i]; + nctx = &channel->nctx; + dpaa2_io_service_deregister(channel->dpio, nctx, dev); + free_channel(priv, channel); + } + priv->num_channels = 0; return err; + } if (cpumask_empty(&priv->dpio_cpumask)) { dev_err(dev, "No cpu with an affine DPIO/DPCON\n"); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 22c01b224baa..4bb30761abfc 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3636,6 +3636,11 @@ fec_drv_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); struct device_node *np = pdev->dev.of_node; + int ret; + + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) + return ret; cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -3643,13 +3648,17 @@ fec_drv_remove(struct platform_device *pdev) fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); - pm_runtime_put(&pdev->dev); - pm_runtime_disable(&pdev->dev); + if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); free_netdev(ndev); + clk_disable_unprepare(fep->clk_ahb); + clk_disable_unprepare(fep->clk_ipg); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; } diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 0a9a7ee2a866..f4889431f9b7 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -393,12 +393,13 @@ static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc, static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses, u64 iov_offset, u64 iov_len) { + u64 last_page = (iov_offset + iov_len - 1) / PAGE_SIZE; + u64 first_page = iov_offset / PAGE_SIZE; dma_addr_t dma; - u64 addr; + u64 page; - for (addr = iov_offset; addr < iov_offset + iov_len; - addr += PAGE_SIZE) { - dma = page_buses[addr / PAGE_SIZE]; + for (page = first_page; page <= last_page; page++) { + dma = page_buses[page]; dma_sync_single_for_device(dev, dma, PAGE_SIZE, DMA_TO_DEVICE); } } diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 6d0457eb4faa..08339278c722 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -199,7 +199,6 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags) ring->q = q; ring->flags = flags; - spin_lock_init(&ring->lock); ring->coal_param = q->handle->coal_param; assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index e9c67c06bfd2..6ab9458302e1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -274,9 +274,6 @@ struct hnae_ring { /* statistic */ struct ring_stats stats; - /* ring lock for poll one */ - spinlock_t lock; - dma_addr_t desc_dma_addr; u32 buf_size; /* size for hnae_desc->addr, preset by AE */ u16 desc_num; /* total number of desc */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index a48396dd4ebb..14ab20491fd0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -943,15 +943,6 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h) return u > c ? (h > c && h <= u) : (h > c || h <= u); } -/* netif_tx_lock will turn down the performance, set only when necessary */ -#ifdef CONFIG_NET_POLL_CONTROLLER -#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock) -#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock) -#else -#define NETIF_TX_LOCK(ring) -#define NETIF_TX_UNLOCK(ring) -#endif - /* reclaim all desc in one budget * return error or number of desc left */ @@ -965,21 +956,16 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, int head; int bytes, pkts; - NETIF_TX_LOCK(ring); - head = readl_relaxed(ring->io_base + RCB_REG_HEAD); rmb(); /* make sure head is ready before touch any data */ - if (is_ring_empty(ring) || head == ring->next_to_clean) { - NETIF_TX_UNLOCK(ring); + if (is_ring_empty(ring) || head == ring->next_to_clean) return 0; /* no data to poll */ - } if (!is_valid_clean_head(ring, head)) { netdev_err(ndev, "wrong head (%d, %d-%d)\n", head, ring->next_to_use, ring->next_to_clean); ring->stats.io_err_cnt++; - NETIF_TX_UNLOCK(ring); return -EIO; } @@ -994,8 +980,6 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, ring->stats.tx_pkts += pkts; ring->stats.tx_bytes += bytes; - NETIF_TX_UNLOCK(ring); - dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); netdev_tx_completed_queue(dev_queue, pkts, bytes); @@ -1055,16 +1039,12 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data) int head; int bytes, pkts; - NETIF_TX_LOCK(ring); - head = ring->next_to_use; /* ntu :soft setted ring position*/ bytes = 0; pkts = 0; while (head != ring->next_to_clean) hns_nic_reclaim_one_desc(ring, &bytes, &pkts); - NETIF_TX_UNLOCK(ring); - dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); netdev_tx_reset_queue(dev_queue); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 75ccc1e7076b..a0998937727d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HNAE3_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 2110fa3b4479..5d468ed404a6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HNS3_ENET_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 680c3508876d..52c9d204fe3d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -70,11 +70,6 @@ static const struct hns3_stats hns3_rxq_stats[] = { #define HNS3_NIC_LB_TEST_TX_CNT_ERR 2 #define HNS3_NIC_LB_TEST_RX_CNT_ERR 3 -struct hns3_link_mode_mapping { - u32 hns3_link_mode; - u32 ethtool_link_mode; -}; - static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) { struct hnae3_handle *h = hns3_get_handle(ndev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 4821fe08b5e4..1426eb5ddf3d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_CMD_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index c063301d6060..a1790af73096 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -124,7 +124,7 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets, if (ret) return ret; - for (i = 0; i < HNAE3_MAX_TC; i++) { + for (i = 0; i < hdev->tc_max; i++) { switch (ets->tc_tsa[i]) { case IEEE_8021QAZ_TSA_STRICT: if (hdev->tm_info.tc_info[i].tc_sch_mode != @@ -318,6 +318,7 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; u8 i, j, pfc_map, *prio_tc; + int ret; if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) @@ -347,7 +348,21 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) hclge_tm_pfc_info_update(hdev); - return hclge_pause_setup_hw(hdev, false); + ret = hclge_pause_setup_hw(hdev, false); + if (ret) + return ret; + + ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT); + if (ret) + return ret; + + ret = hclge_buffer_alloc(hdev); + if (ret) { + hclge_notify_client(hdev, HNAE3_UP_CLIENT); + return ret; + } + + return hclge_notify_client(hdev, HNAE3_UP_CLIENT); } /* DCBX configuration */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h index 278f21e02736..b04702e65689 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_DCB_H__ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e02e01bd9eff..c052bb33b3d3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3587,12 +3587,28 @@ static int hclge_set_rst_done(struct hclge_dev *hdev) { struct hclge_pf_rst_done_cmd *req; struct hclge_desc desc; + int ret; req = (struct hclge_pf_rst_done_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PF_RST_DONE, false); req->pf_rst_done |= HCLGE_PF_RESET_DONE_BIT; - return hclge_cmd_send(&hdev->hw, &desc, 1); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + /* To be compatible with the old firmware, which does not support + * command HCLGE_OPC_PF_RST_DONE, just print a warning and + * return success + */ + if (ret == -EOPNOTSUPP) { + dev_warn(&hdev->pdev->dev, + "current firmware does not support command(0x%x)!\n", + HCLGE_OPC_PF_RST_DONE); + return 0; + } else if (ret) { + dev_err(&hdev->pdev->dev, "assert PF reset done fail %d!\n", + ret); + } + + return ret; } static int hclge_reset_prepare_up(struct hclge_dev *hdev) @@ -6247,11 +6263,23 @@ static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, func_id = hclge_get_port_number(HOST_PORT, 0, vfid, 0); req = (struct hclge_mac_vlan_switch_cmd *)desc.data; + + /* read current config parameter */ hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_SWITCH_PARAM, - false); + true); req->roce_sel = HCLGE_MAC_VLAN_NIC_SEL; req->func_id = cpu_to_le32(func_id); - req->switch_param = switch_param; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "read mac vlan switch parameter fail, ret = %d\n", ret); + return ret; + } + + /* modify and write new config parameter */ + hclge_cmd_reuse_desc(&desc, false); + req->switch_param = (req->switch_param & param_mask) | switch_param; req->param_mask = param_mask; ret = hclge_cmd_send(&hdev->hw, &desc, 1); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index c3d56b872ed7..615cde1cbf0b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_MAIN_H @@ -166,7 +166,7 @@ enum HLCGE_PORT_TYPE { #define HCLGE_GLOBAL_RESET_BIT 0 #define HCLGE_CORE_RESET_BIT 1 #define HCLGE_IMP_RESET_BIT 2 -#define HCLGE_RESET_INT_M GENMASK(2, 0) +#define HCLGE_RESET_INT_M GENMASK(7, 5) #define HCLGE_FUN_RST_ING 0x20C00 #define HCLGE_FUN_RST_ING_B 0 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h index ef095d9c566f..dd9a1218a7b0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_MDIO_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 818610988d34..260f22d19d81 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_TM_H diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index f59d9a8e35e2..0686ded7ad3a 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2878,10 +2878,15 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter, if (test_bit(0, &adapter->resetting) && adapter->reset_reason == VNIC_RESET_MOBILITY) { - struct irq_desc *desc = irq_to_desc(scrq->irq); - struct irq_chip *chip = irq_desc_get_chip(desc); + u64 val = (0xff000000) | scrq->hw_irq; - chip->irq_eoi(&desc->irq_data); + rc = plpar_hcall_norets(H_EOI, val); + /* H_EOI would fail with rc = H_FUNCTION when running + * in XIVE mode which is expected, but not an error. + */ + if (rc && (rc != H_FUNCTION)) + dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n", + val, rc); } rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 530613f31527..69a2daaca5c5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -20,6 +20,8 @@ /* API version 1.7 implements additional link and PHY-specific APIs */ #define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 +/* API version 1.9 for X722 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_X722 0x0009 /* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */ #define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006 diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index d37c6e0e5f08..7560f06768e0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1876,7 +1876,8 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE) hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU; - if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE && + hw->mac.type != I40E_MAC_X722) { __le32 tmp; memcpy(&tmp, resp->link_type, sizeof(tmp)); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index a05dfecdd9b4..d07e1a890428 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -689,8 +689,6 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) i40e_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -769,12 +767,8 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, i40e_update_tx_stats(tx_ring, completed_frames, total_bytes); out_xmit: - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { - if (tx_ring->next_to_clean == tx_ring->next_to_use) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); - else - xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); - } + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); xmit_done = i40e_xmit_zc(tx_ring, budget); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8f310e520b06..821987da5698 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -314,7 +314,7 @@ iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx) q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx), - q_vector->rx.current_itr); + q_vector->rx.current_itr >> 1); q_vector->rx.current_itr = q_vector->rx.target_itr; } @@ -340,7 +340,7 @@ iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx) q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx), - q_vector->tx.target_itr); + q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; } diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index fc624b73d05d..2fde9653a608 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -1036,7 +1036,7 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) struct ice_aqc_query_txsched_res_resp *buf; enum ice_status status = 0; __le16 max_sibl; - u8 i; + u16 i; if (hw->layer_info) return status; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9148c62d9ac5..ed7e667d7eb2 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5675,8 +5675,8 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, * should have been handled by the upper layers. */ if (tx_ring->launchtime_enable) { - ts = ns_to_timespec64(first->skb->tstamp); - first->skb->tstamp = 0; + ts = ktime_to_timespec64(first->skb->tstamp); + first->skb->tstamp = ktime_set(0, 0); context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32); } else { context_desc->seqnum_seed = 0; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index fd3071f55bd3..c39e921757ba 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -521,6 +521,19 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests failing to enable both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + if (on) { pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS, rq->extts.index); @@ -551,6 +564,10 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp, return 0; case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + if (on) { pin = ptp_find_pin(igb->ptp_clock, PTP_PF_PEROUT, rq->perout.index); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 8e424dfab12e..24888676f69b 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -824,8 +824,8 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, * should have been handled by the upper layers. */ if (tx_ring->launchtime_enable) { - ts = ns_to_timespec64(first->skb->tstamp); - first->skb->tstamp = 0; + ts = ktime_to_timespec64(first->skb->tstamp); + first->skb->tstamp = ktime_set(0, 0); context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32); } else { context_desc->launch_time = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 100ac89b345d..d6feaacfbf89 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -622,8 +622,6 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) if (tx_desc) { ixgbe_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -691,12 +689,8 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, if (xsk_frames) xsk_umem_complete_tx(umem, xsk_frames); - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { - if (tx_ring->next_to_clean == tx_ring->next_to_use) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); - else - xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); - } + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 206dc5dc1df8..5c1f389e3320 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 CGX driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 CGX driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h index fb3ba4968a9b..473d9751601f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 CGX driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 CGX driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index e332e82fc066..413c3f254cf8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 76a4575d18ff..75439fce0505 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 8d6d90fdfb73..5d4df315a0e1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index b2ce957605bb..da649f6a5573 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index c9d60b0554c0..5222e4228905 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 09a8d61f3144..1ea92a2e7cfe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index f920dac74e6c..84a39063a8bb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index d8313e2ee600..a1202e53710c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1745,6 +1745,7 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, err = mlx4_en_get_flow(dev, cmd, cmd->fs.location); break; case ETHTOOL_GRXCLSRLALL: + cmd->data = MAX_NUM_OF_FS_RULES; while ((!err || err == -ENOENT) && priority < cmd->rule_cnt) { err = mlx4_en_get_flow(dev, cmd, i); if (!err) @@ -1811,6 +1812,7 @@ static int mlx4_en_set_channels(struct net_device *dev, struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_tx_count; int port_up = 0; int xdp_count; int err = 0; @@ -1825,13 +1827,12 @@ static int mlx4_en_set_channels(struct net_device *dev, mutex_lock(&mdev->state_lock); xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0; - if (channel->tx_count * priv->prof->num_up + xdp_count > - priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) { + total_tx_count = channel->tx_count * priv->prof->num_up + xdp_count; + if (total_tx_count > MAX_TX_RINGS) { err = -EINVAL; en_err(priv, "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", - channel->tx_count * priv->prof->num_up + xdp_count, - MAX_TX_RINGS); + total_tx_count, MAX_TX_RINGS); goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 40ec5acf79c0..70fd246840e2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -91,6 +91,7 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_count; int port_up = 0; int err = 0; @@ -104,6 +105,14 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) MLX4_EN_NUM_UP_HIGH; new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up * new_prof.num_up; + total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP]; + if (total_count > MAX_TX_RINGS) { + err = -EINVAL; + en_err(priv, + "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", + total_count, MAX_TX_RINGS); + goto out; + } err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index fce9b3a24347..d44ac666e730 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -514,8 +514,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_rq_desc_sz = dev_cap->max_rq_desc_sz; /* * Subtract 1 from the limit because we need to allocate a - * spare CQE so the HCA HW can tell the difference between an - * empty CQ and a full CQ. + * spare CQE to enable resizing the CQ. */ dev->caps.max_cqes = dev_cap->max_cq_sz - 1; dev->caps.reserved_cqs = dev_cap->reserved_cqs; @@ -4011,6 +4010,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_params_unregister; devlink_params_publish(devlink); + devlink_reload_enable(devlink); pci_save_state(pdev); return 0; @@ -4122,6 +4122,8 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; + devlink_reload_disable(devlink); + if (mlx4_is_slave(dev)) persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 13af72556987..745ab6cd7c30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -239,12 +239,15 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, if (max_encap_size < ipv4_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv4_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -355,12 +358,15 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, if (max_encap_size < ipv6_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv6_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 327c93a7bd55..95601269fa2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -708,9 +708,9 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings, u32 eth_proto_cap, - u8 connector_type) + u8 connector_type, bool ext) { - if (!connector_type || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { + if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR) | MLX5E_PROT_MASK(MLX5E_10GBASE_SR) | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) @@ -842,9 +842,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = { [MLX5E_PORT_OTHER] = PORT_OTHER, }; -static u8 get_connector_port(u32 eth_proto, u8 connector_type) +static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext) { - if (connector_type && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) + if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) return ptys2connector_type[connector_type]; if (eth_proto & @@ -945,9 +945,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; link_ksettings->base.port = get_connector_port(eth_proto_oper, - connector_type); + connector_type, ext); ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin, - connector_type); + connector_type, ext); get_lp_advertising(mdev, eth_proto_lp, link_ksettings); if (an_status == MLX5_AN_COMPLETE) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 772bfdbdeb9c..2a56e66f58d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4252,9 +4252,12 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: + return features; case IPPROTO_IPIP: case IPPROTO_IPV6: - return features; + if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP)) + return features; + break; case IPPROTO_UDP: udph = udp_hdr(skb); port = be16_to_cpu(udph->dest); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fda0b37075e8..f90a9f8e0fc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3268,7 +3268,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - if (netdev_port_same_parent_id(priv->netdev, out_dev)) { + if (encap) { + parse_attr->mirred_ifindex[attr->out_count] = + out_dev->ifindex; + parse_attr->tun_info[attr->out_count] = dup_tun_info(info); + if (!parse_attr->tun_info[attr->out_count]) + return -ENOMEM; + encap = false; + attr->dests[attr->out_count].flags |= + MLX5_ESW_DEST_ENCAP; + attr->out_count++; + /* attr->dests[].rep is resolved when we + * handle encap + */ + } else if (netdev_port_same_parent_id(priv->netdev, out_dev)) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); struct net_device *uplink_upper; @@ -3310,19 +3323,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, attr->dests[attr->out_count].rep = rpriv->rep; attr->dests[attr->out_count].mdev = out_priv->mdev; attr->out_count++; - } else if (encap) { - parse_attr->mirred_ifindex[attr->out_count] = - out_dev->ifindex; - parse_attr->tun_info[attr->out_count] = dup_tun_info(info); - if (!parse_attr->tun_info[attr->out_count]) - return -ENOMEM; - encap = false; - attr->dests[attr->out_count].flags |= - MLX5_ESW_DEST_ENCAP; - attr->out_count++; - /* attr->dests[].rep is resolved when we - * handle encap - */ } else if (parse_attr->filter_dev != priv->netdev) { /* All mlx5 devices are called to configure * high level device filters. Therefore, the @@ -4000,9 +4000,8 @@ int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, struct tc_cls_matchall_offload *ma) { struct netlink_ext_ack *extack = ma->common.extack; - int prio = TC_H_MAJ(ma->common.prio) >> 16; - if (prio != 1) { + if (ma->common.prio != 1) { NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 30aae76b6a1d..60fddf8afc99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2117,7 +2117,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, unlock: mutex_unlock(&esw->state_lock); - return 0; + return err; } int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 369499e88fe8..9004a07e457a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1079,7 +1079,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) MLX5_CAP_GEN(dev, max_flow_counter_15_0); fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size); - esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(2^%d))\n", + esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(%d))\n", MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size), max_flow_counter, ESW_OFFLOADS_NUM_GROUPS, fdb_max); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 7879e1746297..366bda1bb1c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -183,7 +183,8 @@ static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, u32 port_mask, port_value; if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source)) - return spec->flow_context.flow_source == MLX5_VPORT_UPLINK; + return spec->flow_context.flow_source == + MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; port_mask = MLX5_GET(fte_match_param, spec->match_criteria, misc_parameters.source_port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3bbb49354829..791e14ac26f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -579,7 +579,7 @@ static void del_sw_flow_group(struct fs_node *node) rhashtable_destroy(&fg->ftes_hash); ida_destroy(&fg->fte_allocator); - if (ft->autogroup.active) + if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size) ft->autogroup.num_groups--; err = rhltable_remove(&ft->fgs_hash, &fg->hash, @@ -1126,6 +1126,8 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, ft->autogroup.active = true; ft->autogroup.required_groups = max_num_groups; + /* We save place for flow groups in addition to max types */ + ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1); return ft; } @@ -1328,8 +1330,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft return ERR_PTR(-ENOENT); if (ft->autogroup.num_groups < ft->autogroup.required_groups) - /* We save place for flow groups in addition to max types */ - group_size = ft->max_fte / (ft->autogroup.required_groups + 1); + group_size = ft->autogroup.group_size; /* ft->max_fte == ft->autogroup.max_types */ if (group_size == 0) @@ -1356,7 +1357,8 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft if (IS_ERR(fg)) goto out; - ft->autogroup.num_groups++; + if (group_size == ft->autogroup.group_size) + ft->autogroup.num_groups++; out: return fg; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 00717eba2256..c2621b911563 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -162,6 +162,7 @@ struct mlx5_flow_table { struct { bool active; unsigned int required_groups; + unsigned int group_size; unsigned int num_groups; } autogroup; /* Protect fwd_rules */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 0059b290e095..43f97601b500 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -236,6 +236,19 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp, if (!MLX5_PPS_CAP(mdev)) return -EOPNOTSUPP; + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests to enable time stamping on both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + if (rq->extts.index >= clock->ptp_info.n_pins) return -EINVAL; @@ -290,6 +303,10 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, if (!MLX5_PPS_CAP(mdev)) return -EOPNOTSUPP; + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + if (rq->perout.index >= clock->ptp_info.n_pins) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e47dd7c1b909..50ab88d80033 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1566,6 +1566,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF}, /* ConnectX-6 VF */ { PCI_VDEVICE(MELLANOX, 0x101d) }, /* ConnectX-6 Dx */ { PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */ + { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index b74b7d0f6590..004c56c2fc0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -1577,6 +1577,7 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action) break; case DR_ACTION_TYP_MODIFY_HDR: mlx5dr_icm_free_chunk(action->rewrite.chunk); + kfree(action->rewrite.data); refcount_dec(&action->rewrite.dmn->refcount); break; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index e8b656075c6f..bd1699e62142 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -595,6 +595,18 @@ static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule, } } +static u16 dr_get_bits_per_mask(u16 byte_mask) +{ + u16 bits = 0; + + while (byte_mask) { + byte_mask = byte_mask & (byte_mask - 1); + bits++; + } + + return bits; +} + static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, struct mlx5dr_domain *dmn, struct mlx5dr_domain_rx_tx *nic_dmn) @@ -607,6 +619,9 @@ static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, if (!ctrl->may_grow) return false; + if (dr_get_bits_per_mask(htbl->byte_mask) * BITS_PER_BYTE <= htbl->chunk_size) + return false; + if (ctrl->num_of_collisions >= ctrl->increase_threshold && (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold) return true; @@ -1096,6 +1111,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, if (htbl) mlx5dr_htbl_put(htbl); + kfree(hw_ste_arr); + return 0; free_ste: 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 5df8436b2ae3..51803eef13dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -700,6 +700,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, unsigned int irqn; void *cqc, *in; __be64 *pas; + int vector; u32 i; cq = kzalloc(sizeof(*cq), GFP_KERNEL); @@ -728,7 +729,8 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + vector = smp_processor_id() % mlx5_comp_vectors_count(mdev); + err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); if (err) { kvfree(in); goto err_cqwq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 4efe1b0be4a8..3cbf74b44d1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -560,18 +560,6 @@ bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste) return !refcount_read(&ste->refcount); } -static u16 get_bits_per_mask(u16 byte_mask) -{ - u16 bits = 0; - - while (byte_mask) { - byte_mask = byte_mask & (byte_mask - 1); - bits++; - } - - return bits; -} - /* Init one ste as a pattern for ste data array */ void mlx5dr_ste_set_formatted_ste(u16 gvmi, struct mlx5dr_domain_rx_tx *nic_dmn, @@ -620,20 +608,12 @@ int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher, struct mlx5dr_ste_htbl *next_htbl; if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) { - u32 bits_in_mask; u8 next_lu_type; u16 byte_mask; next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type); byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask); - /* Don't allocate table more than required, - * the size of the table defined via the byte_mask, so no need - * to allocate more than that. - */ - bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE; - log_table_size = min(log_table_size, bits_in_mask); - next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, log_table_size, next_lu_type, @@ -671,7 +651,7 @@ static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl) htbl->ctrl.may_grow = true; - if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1) + if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask) htbl->ctrl.may_grow = false; /* Threshold is 50%, one is added to table of size 1 */ diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 67990406cba2..29e95d0a6ad1 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -66,6 +66,8 @@ retry: return err; if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) { + fsm_state_err = min_t(enum mlxfw_fsm_state_err, + fsm_state_err, MLXFW_FSM_STATE_ERR_MAX); pr_err("Firmware flash failed: %s\n", mlxfw_fsm_state_err_str[fsm_state_err]); NL_SET_ERR_MSG_MOD(extack, "Firmware flash failed"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 4421ab22182f..0a0884d86d44 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1189,6 +1189,9 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (mlxsw_driver->params_register) devlink_params_publish(devlink); + if (!reload) + devlink_reload_enable(devlink); + return 0; err_thermal_init: @@ -1249,6 +1252,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); + if (!reload) + devlink_reload_disable(devlink); if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a330b369e899..39d600c8b92d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -994,7 +994,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) if (d) return l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else - return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN; + return RT_TABLE_MAIN; } static struct mlxsw_sp_rif * @@ -1598,27 +1598,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_ipip_entry *ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); - enum mlxsw_sp_l3proto ul_proto; - union mlxsw_sp_l3addr saddr; - u32 ul_tb_id; if (!ipip_entry) return 0; - /* For flat configuration cases, moving overlay to a different VRF might - * cause local address conflict, and the conflicting tunnels need to be - * demoted. - */ - ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); - ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; - saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); - if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto, - saddr, ul_tb_id, - ipip_entry)) { - mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); - return 0; - } - return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, true, false, false, extack); } diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index 57b26c2acf87..e8fe9a90fe4f 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -429,6 +429,10 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, int pulse_width = 0; int perout_bit = 0; + /* Reject requests with unsupported flags */ + if (perout->flags) + return -EOPNOTSUPP; + if (!on) { lan743x_ptp_perout_off(adapter); return 0; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 344539c0d3aa..672ea1342add 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1680,9 +1680,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev, struct ocelot_port *ocelot_port = netdev_priv(dev); int err = 0; - if (!ocelot_netdevice_dev_check(dev)) - return 0; - switch (event) { case NETDEV_CHANGEUPPER: if (netif_is_bridge_master(info->upper_dev)) { @@ -1719,12 +1716,16 @@ static int ocelot_netdevice_event(struct notifier_block *unused, struct net_device *dev = netdev_notifier_info_to_dev(ptr); int ret = 0; + if (!ocelot_netdevice_dev_check(dev)) + return 0; + if (event == NETDEV_PRECHANGEUPPER && netif_is_lag_master(info->upper_dev)) { struct netdev_lag_upper_info *lag_upper_info = info->upper_info; struct netlink_ext_ack *extack; - if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { + if (lag_upper_info && + lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { extack = netdev_notifier_info_to_extack(&info->info); NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type"); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index e40773c01a44..06ac806052bc 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -523,7 +523,7 @@ void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset); #define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri)) #define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0) -void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 mask, +void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, u32 offset); #define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) #define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi)) diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 8d1c208f778f..a220cc7c947a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1208,8 +1208,16 @@ enum qede_remove_mode { static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) { struct net_device *ndev = pci_get_drvdata(pdev); - struct qede_dev *edev = netdev_priv(ndev); - struct qed_dev *cdev = edev->cdev; + struct qede_dev *edev; + struct qed_dev *cdev; + + if (!ndev) { + dev_info(&pdev->dev, "Device has already been removed\n"); + return; + } + + edev = netdev_priv(ndev); + cdev = edev->cdev; DP_INFO(edev, "Starting qede_remove\n"); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 5ecf61df78bd..baac016f3ec0 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -363,7 +363,7 @@ qcaspi_receive(struct qcaspi *qca) netdev_dbg(net_dev, "qcaspi_receive: SPI_REG_RDBUF_BYTE_AVA: Value: %08x\n", available); - if (available > QCASPI_HW_BUF_LEN) { + if (available > QCASPI_HW_BUF_LEN + QCASPI_HW_PKT_LEN) { /* This could only happen by interferences on the SPI line. * So retry later ... */ @@ -496,7 +496,6 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event) u16 signature = 0; u16 spi_config; u16 wrbuf_space = 0; - static u16 reset_count; if (event == QCASPI_EVENT_CPUON) { /* Read signature twice, if not valid @@ -549,13 +548,13 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event) qca->sync = QCASPI_SYNC_RESET; qca->stats.trig_reset++; - reset_count = 0; + qca->reset_count = 0; break; case QCASPI_SYNC_RESET: - reset_count++; + qca->reset_count++; netdev_dbg(qca->net_dev, "sync: waiting for CPU on, count %u.\n", - reset_count); - if (reset_count >= QCASPI_RESET_TIMEOUT) { + qca->reset_count); + if (qca->reset_count >= QCASPI_RESET_TIMEOUT) { /* reset did not seem to take place, try again */ qca->sync = QCASPI_SYNC_UNKNOWN; qca->stats.reset_timeout++; diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index eb9af45fcc5e..d13a67e20d65 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -94,6 +94,7 @@ struct qcaspi { unsigned int intr_req; unsigned int intr_svc; + u16 reset_count; #ifdef CONFIG_DEBUG_FS struct dentry *device_root; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 9c54b715228e..06de59521fc4 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -57,10 +57,10 @@ static int rmnet_unregister_real_device(struct net_device *real_dev, if (port->nr_rmnet_devs) return -EINVAL; - kfree(port); - netdev_rx_handler_unregister(real_dev); + kfree(port); + /* release reference on real_dev */ dev_put(real_dev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 5064c292b873..c33c438850cc 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -916,6 +916,9 @@ static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value) static int r8168g_mdio_read(struct rtl8169_private *tp, int reg) { + if (reg == 0x1f) + return tp->ocp_base == OCP_STD_PHY_BASE ? 0 : tp->ocp_base >> 4; + if (tp->ocp_base != OCP_STD_PHY_BASE) reg -= 0x10; @@ -7176,8 +7179,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1; } - /* RTL8168e-vl has a HW issue with TSO */ - if (tp->mac_version == RTL_GIGA_MAC_VER_34) { + /* RTL8168e-vl and one RTL8168c variant are known to have a + * HW issue with TSO. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_34 || + tp->mac_version == RTL_GIGA_MAC_VER_22) { dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index a9c89d5d8898..9f88b5db4f89 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -955,6 +955,8 @@ enum RAVB_QUEUE { #define NUM_RX_QUEUE 2 #define NUM_TX_QUEUE 2 +#define RX_BUF_SZ (2048 - ETH_FCS_LEN + sizeof(__sum16)) + /* TX descriptors per packet */ #define NUM_TX_DESC_GEN2 2 #define NUM_TX_DESC_GEN3 1 @@ -1018,7 +1020,6 @@ struct ravb_private { u32 dirty_rx[NUM_RX_QUEUE]; /* Producer ring indices */ u32 cur_tx[NUM_TX_QUEUE]; u32 dirty_tx[NUM_TX_QUEUE]; - u32 rx_buf_sz; /* Based on MTU+slack. */ struct napi_struct napi[NUM_RX_QUEUE]; struct work_struct work; /* MII transceiver section. */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index de9aa8c47f1c..3f165c137236 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -230,7 +230,7 @@ static void ravb_ring_free(struct net_device *ndev, int q) le32_to_cpu(desc->dptr))) dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - priv->rx_buf_sz, + RX_BUF_SZ, DMA_FROM_DEVICE); } ring_size = sizeof(struct ravb_ex_rx_desc) * @@ -293,9 +293,9 @@ static void ravb_ring_format(struct net_device *ndev, int q) for (i = 0; i < priv->num_rx_ring[q]; i++) { /* RX descriptor */ rx_desc = &priv->rx_ring[q][i]; - rx_desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); + rx_desc->ds_cc = cpu_to_le16(RX_BUF_SZ); dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, - priv->rx_buf_sz, + RX_BUF_SZ, DMA_FROM_DEVICE); /* We just set the data size to 0 for a failed mapping which * should prevent DMA from happening... @@ -342,9 +342,6 @@ static int ravb_ring_init(struct net_device *ndev, int q) int ring_size; int i; - priv->rx_buf_sz = (ndev->mtu <= 1492 ? PKT_BUF_SZ : ndev->mtu) + - ETH_HLEN + VLAN_HLEN + sizeof(__sum16); - /* Allocate RX and TX skb rings */ priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q], sizeof(*priv->rx_skb[q]), GFP_KERNEL); @@ -354,7 +351,7 @@ static int ravb_ring_init(struct net_device *ndev, int q) goto error; for (i = 0; i < priv->num_rx_ring[q]; i++) { - skb = netdev_alloc_skb(ndev, priv->rx_buf_sz + RAVB_ALIGN - 1); + skb = netdev_alloc_skb(ndev, RX_BUF_SZ + RAVB_ALIGN - 1); if (!skb) goto error; ravb_set_buffer_align(skb); @@ -584,7 +581,7 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) skb = priv->rx_skb[q][entry]; priv->rx_skb[q][entry] = NULL; dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - priv->rx_buf_sz, + RX_BUF_SZ, DMA_FROM_DEVICE); get_ts &= (q == RAVB_NC) ? RAVB_RXTSTAMP_TYPE_V2_L2_EVENT : @@ -617,11 +614,11 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; desc = &priv->rx_ring[q][entry]; - desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); + desc->ds_cc = cpu_to_le16(RX_BUF_SZ); if (!priv->rx_skb[q][entry]) { skb = netdev_alloc_skb(ndev, - priv->rx_buf_sz + + RX_BUF_SZ + RAVB_ALIGN - 1); if (!skb) break; /* Better luck next round. */ @@ -1801,10 +1798,15 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) static int ravb_change_mtu(struct net_device *ndev, int new_mtu) { - if (netif_running(ndev)) - return -EBUSY; + struct ravb_private *priv = netdev_priv(ndev); ndev->mtu = new_mtu; + + if (netif_running(ndev)) { + synchronize_irq(priv->emac_irq); + ravb_emac_init(ndev); + } + netdev_update_features(ndev); return 0; diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index 9a42580693cb..6984bd5b7da9 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -182,6 +182,13 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp, struct net_device *ndev = priv->ndev; unsigned long flags; + /* Reject requests with unsupported flags */ + if (req->flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + if (req->index) return -EINVAL; @@ -211,6 +218,10 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp, unsigned long flags; int error = 0; + /* Reject requests with unsupported flags */ + if (req->flags) + return -EOPNOTSUPP; + if (req->index) return -EINVAL; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 02ed6d1b716c..af15a737c675 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1531,7 +1531,8 @@ void efx_ptp_remove(struct efx_nic *efx) (void)efx_ptp_disable(efx); cancel_work_sync(&efx->ptp_data->work); - cancel_work_sync(&efx->ptp_data->pps_work); + if (efx->ptp_data->pps_workwq) + cancel_work_sync(&efx->ptp_data->pps_work); skb_queue_purge(&efx->ptp_data->rxq); skb_queue_purge(&efx->ptp_data->txq); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index ddcc191febdb..6e47be63a43c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1226,7 +1226,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) dwmac_mux: sun8i_dwmac_unset_syscon(gmac); dwmac_exit: - sun8i_dwmac_exit(pdev, plat_dat->bsp_priv); + stmmac_pltfr_remove(pdev); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 5a7b0aca1d31..66e60c7e9850 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -432,7 +432,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw, * bits used depends on the hardware configuration * selected at core configuration time. */ - int bit_nr = bitrev32(~crc32_le(~0, ha->addr, + u32 bit_nr = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)) >> (32 - mcbitslog2); /* The most significant bit determines the register to * use (H/L) while the other 5 bits determine the bit diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index 775db776b3cc..23fecf68f781 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ // Copyright (c) 2017 Synopsys, Inc. and/or its affiliates. // stmmac Support for 5.xx Ethernet QoS cores diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 99037386080a..9d08a934fe4f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ /* * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates. * stmmac XGMAC definitions. diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 5031398e612c..070bd7d1ae4c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -224,6 +224,7 @@ static void dwxgmac2_config_cbs(struct mac_device_info *hw, writel(low_credit, ioaddr + XGMAC_MTL_TCx_LOCREDIT(queue)); value = readl(ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); + value &= ~XGMAC_TSA; value |= XGMAC_CC | XGMAC_CBS; writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); } @@ -463,7 +464,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw, value |= XGMAC_FILTER_HMC; netdev_for_each_mc_addr(ha, dev) { - int nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >> + u32 nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >> (32 - mcbitslog2)); mc_filter[nr >> 5] |= (1 << (nr & 0x1F)); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c index ae48154f933c..bd5838ce1e8a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c @@ -288,7 +288,8 @@ static int dwxgmac2_get_rx_hash(struct dma_desc *p, u32 *hash, static int dwxgmac2_get_rx_header_len(struct dma_desc *p, unsigned int *len) { - *len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL; + if (le32_to_cpu(p->des3) & XGMAC_RDES3_L34T) + *len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL; return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 965cbe3e6f51..f70ca5300b82 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -369,7 +369,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13; dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12; dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11; - dma_cap->av &= !(hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10; + dma_cap->av &= !((hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10); dma_cap->arpoffsel = (hw_cap & XGMAC_HWFEAT_ARPOFFSEL) >> 9; dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8; dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7; @@ -470,6 +470,7 @@ static void dwxgmac2_enable_tso(void __iomem *ioaddr, bool en, u32 chan) static void dwxgmac2_qmode(void __iomem *ioaddr, u32 channel, u8 qmode) { u32 value = readl(ioaddr + XGMAC_MTL_TXQ_OPMODE(channel)); + u32 flow = readl(ioaddr + XGMAC_RX_FLOW_CTRL); value &= ~XGMAC_TXQEN; if (qmode != MTL_QUEUE_AVB) { @@ -477,6 +478,7 @@ static void dwxgmac2_qmode(void __iomem *ioaddr, u32 channel, u8 qmode) writel(0, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(channel)); } else { value |= 0x1 << XGMAC_TXQEN_SHIFT; + writel(flow & (~XGMAC_RFE), ioaddr + XGMAC_RX_FLOW_CTRL); } writel(value, ioaddr + XGMAC_MTL_TXQ_OPMODE(channel)); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index ddb851d99618..9010d881b12e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ // Copyright (c) 2018 Synopsys, Inc. and/or its affiliates. // stmmac HW Interface Callbacks diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index a223584f5f9a..252cf48c5816 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -176,6 +176,7 @@ #define MMC_XGMAC_RX_PKT_SMD_ERR 0x22c #define MMC_XGMAC_RX_PKT_ASSEMBLY_OK 0x230 #define MMC_XGMAC_RX_FPE_FRAG 0x234 +#define MMC_XGMAC_RX_IPC_INTR_MASK 0x25c static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) { @@ -333,8 +334,9 @@ static void dwxgmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr) { - writel(MMC_DEFAULT_MASK, mmcaddr + MMC_RX_INTR_MASK); - writel(MMC_DEFAULT_MASK, mmcaddr + MMC_TX_INTR_MASK); + writel(0x0, mmcaddr + MMC_RX_INTR_MASK); + writel(0x0, mmcaddr + MMC_TX_INTR_MASK); + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_IPC_INTR_MASK); } static void dwxgmac_read_mmc_reg(void __iomem *addr, u32 reg, u32 *dest) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4e9c848c67cc..f826365c979d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2996,6 +2996,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) stmmac_set_desc_addr(priv, first, des); tmp_pay_len = pay_len; des += proto_hdr_len; + pay_len = 0; } stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue); @@ -3023,6 +3024,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* Only the last descriptor gets to point to the skb. */ tx_q->tx_skbuff[tx_q->cur_tx] = skb; + /* Manage tx mitigation */ + tx_q->tx_count_frames += nfrags + 1; + if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && + !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en)) { + stmmac_tx_timer_arm(priv, queue); + } else { + desc = &tx_q->dma_tx[tx_q->cur_tx]; + tx_q->tx_count_frames = 0; + stmmac_set_tx_ic(priv, desc); + priv->xstats.tx_set_ic_bit++; + } + /* We've used all descriptors we need for this skb, however, * advance cur_tx so that it references a fresh descriptor. * ndo_start_xmit will fill this descriptor the next time it's @@ -3040,19 +3054,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_tso_frames++; priv->xstats.tx_tso_nfrags += nfrags; - /* Manage tx mitigation */ - tx_q->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && - !(priv->synopsys_id >= DWMAC_CORE_4_00 && - (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - priv->hwts_tx_en)) { - stmmac_tx_timer_arm(priv, queue); - } else { - tx_q->tx_count_frames = 0; - stmmac_set_tx_ic(priv, desc); - priv->xstats.tx_set_ic_bit++; - } - if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -3224,6 +3225,27 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Only the last descriptor gets to point to the skb. */ tx_q->tx_skbuff[entry] = skb; + /* According to the coalesce parameter the IC bit for the latest + * segment is reset and the timer re-started to clean the tx status. + * This approach takes care about the fragments: desc is the first + * element in case of no SG. + */ + tx_q->tx_count_frames += nfrags + 1; + if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && + !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en)) { + stmmac_tx_timer_arm(priv, queue); + } else { + if (likely(priv->extend_desc)) + desc = &tx_q->dma_etx[entry].basic; + else + desc = &tx_q->dma_tx[entry]; + + tx_q->tx_count_frames = 0; + stmmac_set_tx_ic(priv, desc); + priv->xstats.tx_set_ic_bit++; + } + /* We've used all descriptors we need for this skb, however, * advance cur_tx so that it references a fresh descriptor. * ndo_start_xmit will fill this descriptor the next time it's @@ -3259,23 +3281,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += skb->len; - /* According to the coalesce parameter the IC bit for the latest - * segment is reset and the timer re-started to clean the tx status. - * This approach takes care about the fragments: desc is the first - * element in case of no SG. - */ - tx_q->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && - !(priv->synopsys_id >= DWMAC_CORE_4_00 && - (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - priv->hwts_tx_en)) { - stmmac_tx_timer_arm(priv, queue); - } else { - tx_q->tx_count_frames = 0; - stmmac_set_tx_ic(priv, desc); - priv->xstats.tx_set_ic_bit++; - } - if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -3506,8 +3511,6 @@ read_again: if (unlikely(status & dma_own)) break; - count++; - rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE); next_entry = rx_q->cur_rx; @@ -3534,6 +3537,7 @@ read_again: goto read_again; if (unlikely(error)) { dev_kfree_skb(skb); + count++; continue; } @@ -3573,6 +3577,7 @@ read_again: skb = napi_alloc_skb(&ch->rx_napi, len); if (!skb) { priv->dev->stats.rx_dropped++; + count++; continue; } @@ -3638,6 +3643,7 @@ read_again: priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += len; + count++; } if (status & rx_not_ls) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index df638b18b72c..0989e2bb6ee3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -140,6 +140,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + cfg = &priv->pps[rq->perout.index]; cfg->start.tv_sec = rq->perout.start.sec; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index e4ac3c401432..ac3f658105c0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -6,7 +6,9 @@ * Author: Jose Abreu <joabreu@synopsys.com> */ +#include <linux/bitrev.h> #include <linux/completion.h> +#include <linux/crc32.h> #include <linux/ethtool.h> #include <linux/ip.h> #include <linux/phy.h> @@ -485,12 +487,48 @@ static int stmmac_filter_check(struct stmmac_priv *priv) return -EOPNOTSUPP; } +static bool stmmac_hash_check(struct stmmac_priv *priv, unsigned char *addr) +{ + int mc_offset = 32 - priv->hw->mcast_bits_log2; + struct netdev_hw_addr *ha; + u32 hash, hash_nr; + + /* First compute the hash for desired addr */ + hash = bitrev32(~crc32_le(~0, addr, 6)) >> mc_offset; + hash_nr = hash >> 5; + hash = 1 << (hash & 0x1f); + + /* Now, check if it collides with any existing one */ + netdev_for_each_mc_addr(ha, priv->dev) { + u32 nr = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)) >> mc_offset; + if (((nr >> 5) == hash_nr) && ((1 << (nr & 0x1f)) == hash)) + return false; + } + + /* No collisions, address is good to go */ + return true; +} + +static bool stmmac_perfect_check(struct stmmac_priv *priv, unsigned char *addr) +{ + struct netdev_hw_addr *ha; + + /* Check if it collides with any existing one */ + netdev_for_each_uc_addr(ha, priv->dev) { + if (!memcmp(ha->addr, addr, ETH_ALEN)) + return false; + } + + /* No collisions, address is good to go */ + return true; +} + static int stmmac_test_hfilt(struct stmmac_priv *priv) { - unsigned char gd_addr[ETH_ALEN] = {0x01, 0xee, 0xdd, 0xcc, 0xbb, 0xaa}; - unsigned char bd_addr[ETH_ALEN] = {0x01, 0x01, 0x02, 0x03, 0x04, 0x05}; + unsigned char gd_addr[ETH_ALEN] = {0xf1, 0xee, 0xdd, 0xcc, 0xbb, 0xaa}; + unsigned char bd_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; ret = stmmac_filter_check(priv); if (ret) @@ -499,6 +537,16 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv) if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) return -EOPNOTSUPP; + while (--tries) { + /* We only need to check the bd_addr for collisions */ + bd_addr[ETH_ALEN - 1] = tries; + if (stmmac_hash_check(priv, bd_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; + ret = dev_mc_add(priv->dev, gd_addr); if (ret) return ret; @@ -523,13 +571,25 @@ cleanup: static int stmmac_test_pfilt(struct stmmac_priv *priv) { - unsigned char gd_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77}; - unsigned char bd_addr[ETH_ALEN] = {0x08, 0x00, 0x22, 0x33, 0x44, 0x55}; + unsigned char gd_addr[ETH_ALEN] = {0xf0, 0x01, 0x44, 0x55, 0x66, 0x77}; + unsigned char bd_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) + return -EOPNOTSUPP; + + while (--tries) { + /* We only need to check the bd_addr for collisions */ + bd_addr[ETH_ALEN - 1] = tries; + if (stmmac_perfect_check(priv, bd_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; ret = dev_uc_add(priv->dev, gd_addr); if (ret) @@ -553,39 +613,31 @@ cleanup: return ret; } -static int stmmac_dummy_sync(struct net_device *netdev, const u8 *addr) -{ - return 0; -} - -static void stmmac_test_set_rx_mode(struct net_device *netdev) -{ - /* As we are in test mode of ethtool we already own the rtnl lock - * so no address will change from user. We can just call the - * ndo_set_rx_mode() callback directly */ - if (netdev->netdev_ops->ndo_set_rx_mode) - netdev->netdev_ops->ndo_set_rx_mode(netdev); -} - static int stmmac_test_mcfilt(struct stmmac_priv *priv) { - unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77}; - unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77}; + unsigned char uc_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff}; + unsigned char mc_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; if (stmmac_filter_check(priv)) return -EOPNOTSUPP; - if (!priv->hw->multicast_filter_bins) + if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) return -EOPNOTSUPP; - /* Remove all MC addresses */ - __dev_mc_unsync(priv->dev, NULL); - stmmac_test_set_rx_mode(priv->dev); + while (--tries) { + /* We only need to check the mc_addr for collisions */ + mc_addr[ETH_ALEN - 1] = tries; + if (stmmac_hash_check(priv, mc_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; ret = dev_uc_add(priv->dev, uc_addr); if (ret) - goto cleanup; + return ret; attr.dst = uc_addr; @@ -602,30 +654,34 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv) cleanup: dev_uc_del(priv->dev, uc_addr); - __dev_mc_sync(priv->dev, stmmac_dummy_sync, NULL); - stmmac_test_set_rx_mode(priv->dev); return ret; } static int stmmac_test_ucfilt(struct stmmac_priv *priv) { - unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77}; - unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77}; + unsigned char uc_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff}; + unsigned char mc_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; if (stmmac_filter_check(priv)) return -EOPNOTSUPP; - if (!priv->hw->multicast_filter_bins) + if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) return -EOPNOTSUPP; - /* Remove all UC addresses */ - __dev_uc_unsync(priv->dev, NULL); - stmmac_test_set_rx_mode(priv->dev); + while (--tries) { + /* We only need to check the uc_addr for collisions */ + uc_addr[ETH_ALEN - 1] = tries; + if (stmmac_perfect_check(priv, uc_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; ret = dev_mc_add(priv->dev, mc_addr); if (ret) - goto cleanup; + return ret; attr.dst = mc_addr; @@ -642,8 +698,6 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv) cleanup: dev_mc_del(priv->dev, mc_addr); - __dev_uc_sync(priv->dev, stmmac_dummy_sync, NULL); - stmmac_test_set_rx_mode(priv->dev); return ret; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 670ef682f268..fb547f37af1e 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -609,7 +609,8 @@ struct nvsp_5_send_indirect_table { /* The number of entries in the send indirection table */ u32 count; - /* The offset of the send indirection table from top of this struct. + /* The offset of the send indirection table from the beginning of + * struct nvsp_message. * The send indirection table tells which channel to put the send * traffic on. Each entry is a channel number. */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d22a36fc7a7c..eab83e71567a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1178,20 +1178,39 @@ static int netvsc_receive(struct net_device *ndev, } static void netvsc_send_table(struct net_device *ndev, - const struct nvsp_message *nvmsg) + struct netvsc_device *nvscdev, + const struct nvsp_message *nvmsg, + u32 msglen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - u32 count, *tab; + u32 count, offset, *tab; int i; count = nvmsg->msg.v5_msg.send_table.count; + offset = nvmsg->msg.v5_msg.send_table.offset; + if (count != VRSS_SEND_TAB_SIZE) { netdev_err(ndev, "Received wrong send-table size:%u\n", count); return; } - tab = (u32 *)((unsigned long)&nvmsg->msg.v5_msg.send_table + - nvmsg->msg.v5_msg.send_table.offset); + /* If negotiated version <= NVSP_PROTOCOL_VERSION_6, the offset may be + * wrong due to a host bug. So fix the offset here. + */ + if (nvscdev->nvsp_version <= NVSP_PROTOCOL_VERSION_6 && + msglen >= sizeof(struct nvsp_message_header) + + sizeof(union nvsp_6_message_uber) + count * sizeof(u32)) + offset = sizeof(struct nvsp_message_header) + + sizeof(union nvsp_6_message_uber); + + /* Boundary check for all versions */ + if (offset > msglen - count * sizeof(u32)) { + netdev_err(ndev, "Received send-table offset too big:%u\n", + offset); + return; + } + + tab = (void *)nvmsg + offset; for (i = 0; i < count; i++) net_device_ctx->tx_table[i] = tab[i]; @@ -1209,12 +1228,14 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc ? "added" : "removed"); } -static void netvsc_receive_inband(struct net_device *ndev, - const struct nvsp_message *nvmsg) +static void netvsc_receive_inband(struct net_device *ndev, + struct netvsc_device *nvscdev, + const struct nvsp_message *nvmsg, + u32 msglen) { switch (nvmsg->hdr.msg_type) { case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: - netvsc_send_table(ndev, nvmsg); + netvsc_send_table(ndev, nvscdev, nvmsg, msglen); break; case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: @@ -1232,6 +1253,7 @@ static int netvsc_process_raw_pkt(struct hv_device *device, { struct vmbus_channel *channel = nvchan->channel; const struct nvsp_message *nvmsg = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); trace_nvsp_recv(ndev, channel, nvmsg); @@ -1247,7 +1269,7 @@ static int netvsc_process_raw_pkt(struct hv_device *device, break; case VM_PKT_DATA_INBAND: - netvsc_receive_inband(ndev, nvmsg); + netvsc_receive_inband(ndev, net_device, nvmsg, msglen); break; default: diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 54ca6681ba31..44c2d857a7fa 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -708,6 +708,7 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) goto err_debugfs_exit; devlink_params_publish(devlink); + devlink_reload_enable(devlink); return nsim_dev; err_debugfs_exit: @@ -732,6 +733,7 @@ static void nsim_dev_destroy(struct nsim_dev *nsim_dev) { struct devlink *devlink = priv_to_devlink(nsim_dev); + devlink_reload_disable(devlink); nsim_bpf_dev_exit(nsim_dev); nsim_dev_debugfs_exit(nsim_dev); nsim_dev_traps_exit(devlink); diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 6580094161a9..8f241b57fcf6 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -469,6 +469,19 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests to enable time stamping on both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + index = rq->extts.index; if (index >= N_EXT_TS) return -EINVAL; @@ -491,6 +504,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp, return 0; case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; if (rq->perout.index >= N_PER_OUT) return -EINVAL; return periodic_output(clock, rq, on, rq->perout.index); diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/phy/mdio-sun4i.c index 58d6504495e0..f798de3276dc 100644 --- a/drivers/net/phy/mdio-sun4i.c +++ b/drivers/net/phy/mdio-sun4i.c @@ -145,8 +145,11 @@ err_out_free_mdiobus: static int sun4i_mdio_remove(struct platform_device *pdev) { struct mii_bus *bus = platform_get_drvdata(pdev); + struct sun4i_mdio_data *data = bus->priv; mdiobus_unregister(bus); + if (data->regulator) + regulator_disable(data->regulator); mdiobus_free(bus); return 0; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 2e29ab841b4d..dbacb0031877 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -64,11 +64,12 @@ static int mdiobus_register_reset(struct mdio_device *mdiodev) if (mdiodev->dev.of_node) reset = devm_reset_control_get_exclusive(&mdiodev->dev, "phy"); - if (PTR_ERR(reset) == -ENOENT || - PTR_ERR(reset) == -ENOTSUPP) - reset = NULL; - else if (IS_ERR(reset)) - return PTR_ERR(reset); + if (IS_ERR(reset)) { + if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP) + reset = NULL; + else + return PTR_ERR(reset); + } mdiodev->reset_ctrl = reset; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a578f7ebf715..536236fdb232 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -601,6 +601,8 @@ static int phylink_register_sfp(struct phylink *pl, * Create a new phylink instance, and parse the link parameters found in @np. * This will parse in-band modes, fixed-link or SFP configuration. * + * Note: the rtnl lock must not be held when calling this function. + * * Returns a pointer to a &struct phylink, or an error-pointer value. Users * must use IS_ERR() to check for errors from this function. */ @@ -678,6 +680,8 @@ EXPORT_SYMBOL_GPL(phylink_create); * * Destroy a phylink instance. Any PHY that has been attached must have been * cleaned up via phylink_disconnect_phy() prior to calling this function. + * + * Note: the rtnl lock must not be held when calling this function. */ void phylink_destroy(struct phylink *pl) { @@ -1254,7 +1258,13 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, pl->link_config.duplex = our_kset.base.duplex; pl->link_config.an_enabled = our_kset.base.autoneg != AUTONEG_DISABLE; - if (!test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) { + /* If we have a PHY, phylib will call our link state function if the + * mode has changed, which will trigger a resolve and update the MAC + * configuration. For a fixed link, this isn't able to change any + * parameters, which just leaves inband mode. + */ + if (pl->link_an_mode == MLO_AN_INBAND && + !test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) { phylink_mac_config(pl, &pl->link_config); phylink_mac_an_restart(pl); } @@ -1334,15 +1344,16 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, if (pause->tx_pause) config->pause |= MLO_PAUSE_TX; - if (!test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) { + /* If we have a PHY, phylib will call our link state function if the + * mode has changed, which will trigger a resolve and update the MAC + * configuration. + */ + if (pl->phydev) { + phy_set_asym_pause(pl->phydev, pause->rx_pause, + pause->tx_pause); + } else if (!test_bit(PHYLINK_DISABLE_STOPPED, + &pl->phylink_disable_state)) { switch (pl->link_an_mode) { - case MLO_AN_PHY: - /* Silently mark the carrier down, and then trigger a resolve */ - if (pl->netdev) - netif_carrier_off(pl->netdev); - phylink_run_resolve(pl); - break; - case MLO_AN_FIXED: /* Should we allow fixed links to change against the config? */ phylink_resolve_flow(pl, config); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index cac64b96d545..4d479e3c817d 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -855,6 +855,7 @@ err_free_chan: sl->tty = NULL; tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); + free_netdev(sl->dev); err_exit: rtnl_unlock(); diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 011bd4cb546e..af3994e0853b 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -196,7 +196,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) /* Get the MAC address */ ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); - if (ret < 0) { + if (ret < ETH_ALEN) { netdev_err(dev->net, "Failed to read MAC address: %d\n", ret); goto free; } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 00cab3f43a4c..c2c82e6391b4 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -578,8 +578,8 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size) /* read current mtu value from device */ err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE, USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE, - 0, iface_no, &max_datagram_size, 2); - if (err < 0) { + 0, iface_no, &max_datagram_size, sizeof(max_datagram_size)); + if (err != sizeof(max_datagram_size)) { dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n"); goto out; } @@ -590,7 +590,7 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size) max_datagram_size = cpu_to_le16(ctx->max_datagram_size); err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE, USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE, - 0, iface_no, &max_datagram_size, 2); + 0, iface_no, &max_datagram_size, sizeof(max_datagram_size)); if (err < 0) dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n"); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 596428ec71df..4196c0e32740 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1362,6 +1362,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ @@ -1370,6 +1371,8 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ + {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ + {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index d4a95b50bda6..b2507c59ba8b 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4283,10 +4283,10 @@ static int rtl8152_close(struct net_device *netdev) unregister_pm_notifier(&tp->pm_notifier); #endif tasklet_disable(&tp->tx_tl); - napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); + napi_disable(&tp->napi); netif_stop_queue(netdev); res = usb_autopm_get_interface(tp->intf); @@ -4552,10 +4552,10 @@ static int rtl8152_pre_reset(struct usb_interface *intf) netif_stop_queue(netdev); tasklet_disable(&tp->tx_tl); - napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); + napi_disable(&tp->napi); if (netif_carrier_ok(netdev)) { mutex_lock(&tp->control); tp->rtl_ops.disable(tp); @@ -4673,7 +4673,7 @@ static int rtl8152_system_resume(struct r8152 *tp) netif_device_attach(netdev); - if (netif_running(netdev) && netdev->flags & IFF_UP) { + if (netif_running(netdev) && (netdev->flags & IFF_UP)) { tp->rtl_ops.up(tp); netif_carrier_off(netdev); set_bit(WORK_ENABLE, &tp->flags); @@ -5244,9 +5244,15 @@ static int rtl8152_set_tunable(struct net_device *netdev, } if (tp->rx_copybreak != val) { - napi_disable(&tp->napi); - tp->rx_copybreak = val; - napi_enable(&tp->napi); + if (netdev->flags & IFF_UP) { + mutex_lock(&tp->control); + napi_disable(&tp->napi); + tp->rx_copybreak = val; + napi_enable(&tp->napi); + mutex_unlock(&tp->control); + } else { + tp->rx_copybreak = val; + } } break; default: @@ -5274,9 +5280,15 @@ static int rtl8152_set_ringparam(struct net_device *netdev, return -EINVAL; if (tp->rx_pending != ring->rx_pending) { - napi_disable(&tp->napi); - tp->rx_pending = ring->rx_pending; - napi_enable(&tp->napi); + if (netdev->flags & IFF_UP) { + mutex_lock(&tp->control); + napi_disable(&tp->napi); + tp->rx_pending = ring->rx_pending; + napi_enable(&tp->napi); + mutex_unlock(&tp->control); + } else { + tp->rx_pending = ring->rx_pending; + } } return 0; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 8894027429d6..d80f71f82a6d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -251,27 +251,23 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room; unsigned int mss = skb_shinfo(skb)->gso_size; - u16 length, iv_len, amsdu_pad; + u16 length, amsdu_pad; u8 *start_hdr; struct iwl_tso_hdr_page *hdr_page; struct page **page_ptr; struct tso_t tso; - /* if the packet is protected, then it must be CCMP or GCMP */ - iv_len = ieee80211_has_protected(hdr->frame_control) ? - IEEE80211_CCMP_HDR_LEN : 0; - trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr, start_len, 0); ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb); snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb); - total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len - iv_len; + total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len; amsdu_pad = 0; /* total amount of header we may need for this A-MSDU */ hdr_room = DIV_ROUND_UP(total_len, mss) * - (3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len; + (3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)); /* Our device supports 9 segments at most, it will fit in 1 page */ hdr_page = get_page_hdr(trans, hdr_room); @@ -282,14 +278,12 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, start_hdr = hdr_page->pos; page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs); *page_ptr = hdr_page->page; - memcpy(hdr_page->pos, skb->data + hdr_len, iv_len); - hdr_page->pos += iv_len; /* - * Pull the ieee80211 header + IV to be able to use TSO core, + * Pull the ieee80211 header to be able to use TSO core, * we will restore it for the tx_status flow. */ - skb_pull(skb, hdr_len + iv_len); + skb_pull(skb, hdr_len); /* * Remove the length of all the headers that we don't actually @@ -364,8 +358,8 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, } } - /* re -add the WiFi header and IV */ - skb_push(skb, hdr_len + iv_len); + /* re -add the WiFi header */ + skb_push(skb, hdr_len); return 0; diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 1cd113c8d7cb..ad0abb1f0bae 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -259,7 +259,7 @@ static void fdp_nci_i2c_read_device_properties(struct device *dev, *fw_vsc_cfg, len); if (r) { - devm_kfree(dev, fw_vsc_cfg); + devm_kfree(dev, *fw_vsc_cfg); goto vsc_read_err; } } else { diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 307bd2afbe05..4d1909aecd6c 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -220,8 +220,10 @@ static irqreturn_t nxp_nci_i2c_irq_thread_fn(int irq, void *phy_id) if (r == -EREMOTEIO) { phy->hard_fault = r; - skb = NULL; - } else if (r < 0) { + if (info->mode == NXP_NCI_MODE_FW) + nxp_nci_fw_recv_frame(phy->ndev, NULL); + } + if (r < 0) { nfc_err(&client->dev, "Read failed with error %d\n", r); goto exit_irq_handled; } diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 145ddf3f0a45..604dba4f18af 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -783,7 +783,7 @@ static int port100_send_frame_async(struct port100 *dev, struct sk_buff *out, rc = port100_submit_urb_for_ack(dev, GFP_KERNEL); if (rc) - usb_unlink_urb(dev->out_urb); + usb_kill_urb(dev->out_urb); exit: mutex_unlock(&dev->out_urb_lock); diff --git a/drivers/nfc/st21nfca/core.c b/drivers/nfc/st21nfca/core.c index f9ac176cf257..2ce17932a073 100644 --- a/drivers/nfc/st21nfca/core.c +++ b/drivers/nfc/st21nfca/core.c @@ -708,6 +708,7 @@ static int st21nfca_hci_complete_target_discovered(struct nfc_hci_dev *hdev, NFC_PROTO_FELICA_MASK; } else { kfree_skb(nfcid_skb); + nfcid_skb = NULL; /* P2P in type A */ r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_F_GATE, ST21NFCA_RF_READER_F_NFCID1, diff --git a/drivers/nubus/nubus.c b/drivers/nubus/nubus.c index bb0d63a44f41..f70ba58dbc55 100644 --- a/drivers/nubus/nubus.c +++ b/drivers/nubus/nubus.c @@ -163,7 +163,7 @@ unsigned char *nubus_dirptr(const struct nubus_dirent *nd) void nubus_get_rsrc_mem(void *dest, const struct nubus_dirent *dirent, unsigned int len) { - unsigned char *t = (unsigned char *)dest; + unsigned char *t = dest; unsigned char *p = nubus_dirptr(dirent); while (len) { diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 2b36f052bfb9..c6439638a419 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -23,6 +23,16 @@ config NVME_MULTIPATH /dev/nvmeXnY device will show up for each NVMe namespaces, even if it is accessible through multiple controllers. +config NVME_HWMON + bool "NVMe hardware monitoring" + depends on (NVME_CORE=y && HWMON=y) || (NVME_CORE=m && HWMON) + help + This provides support for NVMe hardware monitoring. If enabled, + a hardware monitoring device will be created for each NVMe drive + in the system. + + If unsure, say N. + config NVME_FABRICS tristate diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index 8a4b671c5f0c..fc7b26be692d 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -14,6 +14,7 @@ nvme-core-$(CONFIG_TRACING) += trace.o nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o nvme-core-$(CONFIG_NVM) += lightnvm.o nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS) += fault_inject.o +nvme-core-$(CONFIG_NVME_HWMON) += hwmon.o nvme-y += pci.o diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fa7ba09dca77..8e8527408db3 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -283,6 +283,8 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(req); + nvme_cleanup_cmd(req); + if (nvme_req(req)->ctrl->kas) nvme_req(req)->ctrl->comp_seen = true; @@ -313,7 +315,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) if (blk_mq_request_completed(req)) return true; - nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; + nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(req); return true; } @@ -611,8 +613,14 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, struct nvme_dsm_range *range; struct bio *bio; - range = kmalloc_array(segments, sizeof(*range), - GFP_ATOMIC | __GFP_NOWARN); + /* + * Some devices do not consider the DSM 'Number of Ranges' field when + * determining how much data to DMA. Always allocate memory for maximum + * number of segments to prevent device reading beyond end of buffer. + */ + static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES; + + range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN); if (!range) { /* * If we fail allocation our range, fallback to the controller @@ -626,7 +634,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, } __rq_for_each_bio(bio, req) { - u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); + u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector); u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; if (n < segments) { @@ -652,7 +660,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, req->special_vec.bv_page = virt_to_page(range); req->special_vec.bv_offset = offset_in_page(range); - req->special_vec.bv_len = sizeof(*range) * segments; + req->special_vec.bv_len = alloc_size; req->rq_flags |= RQF_SPECIAL_PAYLOAD; return BLK_STS_OK; @@ -667,7 +675,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes; cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id); cmnd->write_zeroes.slba = - cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); + cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->write_zeroes.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); cmnd->write_zeroes.control = 0; @@ -691,7 +699,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read); cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id); - cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); + cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) @@ -1647,7 +1655,7 @@ static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type) static void nvme_set_chunk_size(struct nvme_ns *ns) { - u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9)); + u32 chunk_size = nvme_lba_to_sect(ns, ns->noiob); blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size)); } @@ -1684,8 +1692,7 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) { - u32 max_sectors; - unsigned short bs = 1 << ns->lba_shift; + u64 max_blocks; if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) || (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES)) @@ -1701,11 +1708,12 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) * nvme_init_identify() if available. */ if (ns->ctrl->max_hw_sectors == UINT_MAX) - max_sectors = ((u32)(USHRT_MAX + 1) * bs) >> 9; + max_blocks = (u64)USHRT_MAX + 1; else - max_sectors = ((u32)(ns->ctrl->max_hw_sectors + 1) * bs) >> 9; + max_blocks = ns->ctrl->max_hw_sectors + 1; - blk_queue_max_write_zeroes_sectors(disk->queue, max_sectors); + blk_queue_max_write_zeroes_sectors(disk->queue, + nvme_lba_to_sect(ns, max_blocks)); } static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, @@ -1748,7 +1756,7 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) static void nvme_update_disk_info(struct gendisk *disk, struct nvme_ns *ns, struct nvme_id_ns *id) { - sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9); + sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze)); unsigned short bs = 1 << ns->lba_shift; u32 atomic_bs, phys_bs, io_opt; @@ -2796,6 +2804,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->oncs = le16_to_cpu(id->oncs); ctrl->mtfa = le16_to_cpu(id->mtfa); ctrl->oaes = le32_to_cpu(id->oaes); + ctrl->wctemp = le16_to_cpu(id->wctemp); + ctrl->cctemp = le16_to_cpu(id->cctemp); + atomic_set(&ctrl->abort_limit, id->acl + 1); ctrl->vwc = id->vwc; if (id->mdts) @@ -2895,6 +2906,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret < 0) return ret; + if (!ctrl->identified) + nvme_hwmon_init(ctrl); + ctrl->identified = true; return 0; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 265f89e11d8b..679a721ae229 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1224,7 +1224,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, lsreq->rqstlen = sizeof(*assoc_rqst); lsreq->rspaddr = assoc_acc; lsreq->rsplen = sizeof(*assoc_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req(ctrl->rport, lsop); if (ret) @@ -1264,7 +1264,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, if (fcret) { ret = -EBADF; dev_err(ctrl->dev, - "q %d connect failed: %s\n", + "q %d Create Association LS failed: %s\n", queue->qnum, validation_errors[fcret]); } else { ctrl->association_id = @@ -1332,7 +1332,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, lsreq->rqstlen = sizeof(*conn_rqst); lsreq->rspaddr = conn_acc; lsreq->rsplen = sizeof(*conn_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req(ctrl->rport, lsop); if (ret) @@ -1363,7 +1363,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (fcret) { ret = -EBADF; dev_err(ctrl->dev, - "q %d connect failed: %s\n", + "q %d Create I/O Connection LS failed: %s\n", queue->qnum, validation_errors[fcret]); } else { queue->connection_id = @@ -1376,7 +1376,7 @@ out_free_buffer: out_no_memory: if (ret) dev_err(ctrl->dev, - "queue %d connect command failed (%d).\n", + "queue %d connect I/O queue failed (%d).\n", queue->qnum, ret); return ret; } @@ -1413,8 +1413,8 @@ nvme_fc_disconnect_assoc_done(struct nvmefc_ls_req *lsreq, int status) static void nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) { - struct fcnvme_ls_disconnect_rqst *discon_rqst; - struct fcnvme_ls_disconnect_acc *discon_acc; + struct fcnvme_ls_disconnect_assoc_rqst *discon_rqst; + struct fcnvme_ls_disconnect_assoc_acc *discon_acc; struct nvmefc_ls_req_op *lsop; struct nvmefc_ls_req *lsreq; int ret; @@ -1430,11 +1430,11 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) lsreq = &lsop->ls_req; lsreq->private = (void *)&lsop[1]; - discon_rqst = (struct fcnvme_ls_disconnect_rqst *) + discon_rqst = (struct fcnvme_ls_disconnect_assoc_rqst *) (lsreq->private + ctrl->lport->ops->lsrqst_priv_sz); - discon_acc = (struct fcnvme_ls_disconnect_acc *)&discon_rqst[1]; + discon_acc = (struct fcnvme_ls_disconnect_assoc_acc *)&discon_rqst[1]; - discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT; + discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT_ASSOC; discon_rqst->desc_list_len = cpu_to_be32( sizeof(struct fcnvme_lsdesc_assoc_id) + sizeof(struct fcnvme_lsdesc_disconn_cmd)); @@ -1451,22 +1451,17 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) discon_rqst->discon_cmd.desc_len = fcnvme_lsdesc_len( sizeof(struct fcnvme_lsdesc_disconn_cmd)); - discon_rqst->discon_cmd.scope = FCNVME_DISCONN_ASSOCIATION; - discon_rqst->discon_cmd.id = cpu_to_be64(ctrl->association_id); lsreq->rqstaddr = discon_rqst; lsreq->rqstlen = sizeof(*discon_rqst); lsreq->rspaddr = discon_acc; lsreq->rsplen = sizeof(*discon_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req_async(ctrl->rport, lsop, nvme_fc_disconnect_assoc_done); if (ret) kfree(lsop); - - /* only meaningful part to terminating the association */ - ctrl->association_id = 0; } @@ -1662,7 +1657,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) (freq->rcv_rsplen / 4) || be32_to_cpu(op->rsp_iu.xfrd_len) != freq->transferred_length || - op->rsp_iu.status_code || + op->rsp_iu.ersp_result || sqe->common.command_id != cqe->command_id)) { status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1); dev_info(ctrl->ctrl.device, @@ -1672,7 +1667,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) ctrl->cnum, be16_to_cpu(op->rsp_iu.iu_len), be32_to_cpu(op->rsp_iu.xfrd_len), freq->transferred_length, - op->rsp_iu.status_code, + op->rsp_iu.ersp_result, sqe->common.command_id, cqe->command_id); goto done; @@ -1731,9 +1726,14 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl, op->rq = rq; op->rqno = rqno; - cmdiu->scsi_id = NVME_CMD_SCSI_ID; + cmdiu->format_id = NVME_CMD_FORMAT_ID; cmdiu->fc_id = NVME_CMD_FC_ID; cmdiu->iu_len = cpu_to_be16(sizeof(*cmdiu) / sizeof(u32)); + if (queue->qnum) + cmdiu->rsv_cat = fccmnd_set_cat_css(0, + (NVME_CC_CSS_NVM >> NVME_CC_CSS_SHIFT)); + else + cmdiu->rsv_cat = fccmnd_set_cat_admin(0); op->fcp_req.cmddma = fc_dma_map_single(ctrl->lport->dev, &op->cmd_iu, sizeof(op->cmd_iu), DMA_TO_DEVICE); @@ -2173,8 +2173,6 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq, fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents, rq_dma_dir(rq)); - nvme_cleanup_cmd(rq); - sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE); freq->sg_cnt = 0; @@ -2305,6 +2303,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (!(op->flags & FCOP_FLAGS_AEN)) nvme_fc_unmap_data(ctrl, op->rq, op); + nvme_cleanup_cmd(op->rq); nvme_fc_ctrl_put(ctrl); if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE && @@ -2695,7 +2694,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) /* warn if maxcmd is lower than queue_size */ dev_warn(ctrl->ctrl.device, "queue_size %zu > ctrl maxcmd %u, reducing " - "to queue_size\n", + "to maxcmd\n", opts->queue_size, ctrl->ctrl.maxcmd); opts->queue_size = ctrl->ctrl.maxcmd; } @@ -2703,7 +2702,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (opts->queue_size > ctrl->ctrl.sqsize + 1) { /* warn if sqsize is lower than queue_size */ dev_warn(ctrl->ctrl.device, - "queue_size %zu > ctrl sqsize %u, clamping down\n", + "queue_size %zu > ctrl sqsize %u, reducing " + "to sqsize\n", opts->queue_size, ctrl->ctrl.sqsize + 1); opts->queue_size = ctrl->ctrl.sqsize + 1; } @@ -2739,6 +2739,7 @@ out_term_aen_ops: out_disconnect_admin_queue: /* send a Disconnect(association) LS to fc-nvme target */ nvme_fc_xmt_disconnect_assoc(ctrl); + ctrl->association_id = 0; out_delete_hw_queue: __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); out_free_queue: @@ -2830,6 +2831,8 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) if (ctrl->association_id) nvme_fc_xmt_disconnect_assoc(ctrl); + ctrl->association_id = 0; + if (ctrl->ctrl.tagset) { nvme_fc_delete_hw_io_queues(ctrl); nvme_fc_free_io_queues(ctrl); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c new file mode 100644 index 000000000000..a5af21f5d370 --- /dev/null +++ b/drivers/nvme/host/hwmon.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVM Express hardware monitoring support + * Copyright (c) 2019, Guenter Roeck + */ + +#include <linux/hwmon.h> +#include <asm/unaligned.h> + +#include "nvme.h" + +/* These macros should be moved to linux/temperature.h */ +#define MILLICELSIUS_TO_KELVIN(t) DIV_ROUND_CLOSEST((t) + 273150, 1000) +#define KELVIN_TO_MILLICELSIUS(t) ((t) * 1000L - 273150) + +struct nvme_hwmon_data { + struct nvme_ctrl *ctrl; + struct nvme_smart_log log; + struct mutex read_lock; +}; + +static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, + long *temp) +{ + unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT; + u32 status; + int ret; + + if (under) + threshold |= NVME_TEMP_THRESH_TYPE_UNDER; + + ret = nvme_get_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0, + &status); + if (ret > 0) + return -EIO; + if (ret < 0) + return ret; + *temp = KELVIN_TO_MILLICELSIUS(status & NVME_TEMP_THRESH_MASK); + + return 0; +} + +static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, + long temp) +{ + unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT; + int ret; + + temp = MILLICELSIUS_TO_KELVIN(temp); + threshold |= clamp_val(temp, 0, NVME_TEMP_THRESH_MASK); + + if (under) + threshold |= NVME_TEMP_THRESH_TYPE_UNDER; + + ret = nvme_set_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0, + NULL); + if (ret > 0) + return -EIO; + + return ret; +} + +static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) +{ + int ret; + + ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, + &data->log, sizeof(data->log), 0); + + return ret <= 0 ? ret : -EIO; +} + +static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct nvme_hwmon_data *data = dev_get_drvdata(dev); + struct nvme_smart_log *log = &data->log; + int temp; + int err; + + /* + * First handle attributes which don't require us to read + * the smart log. + */ + switch (attr) { + case hwmon_temp_max: + return nvme_get_temp_thresh(data->ctrl, channel, false, val); + case hwmon_temp_min: + return nvme_get_temp_thresh(data->ctrl, channel, true, val); + case hwmon_temp_crit: + *val = KELVIN_TO_MILLICELSIUS(data->ctrl->cctemp); + return 0; + default: + break; + } + + mutex_lock(&data->read_lock); + err = nvme_hwmon_get_smart_log(data); + if (err) + goto unlock; + + switch (attr) { + case hwmon_temp_input: + if (!channel) + temp = get_unaligned_le16(log->temperature); + else + temp = le16_to_cpu(log->temp_sensor[channel - 1]); + *val = KELVIN_TO_MILLICELSIUS(temp); + break; + case hwmon_temp_alarm: + *val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE); + break; + default: + err = -EOPNOTSUPP; + break; + } +unlock: + mutex_unlock(&data->read_lock); + return err; +} + +static int nvme_hwmon_write(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long val) +{ + struct nvme_hwmon_data *data = dev_get_drvdata(dev); + + switch (attr) { + case hwmon_temp_max: + return nvme_set_temp_thresh(data->ctrl, channel, false, val); + case hwmon_temp_min: + return nvme_set_temp_thresh(data->ctrl, channel, true, val); + default: + break; + } + + return -EOPNOTSUPP; +} + +static const char * const nvme_hwmon_sensor_names[] = { + "Composite", + "Sensor 1", + "Sensor 2", + "Sensor 3", + "Sensor 4", + "Sensor 5", + "Sensor 6", + "Sensor 7", + "Sensor 8", +}; + +static int nvme_hwmon_read_string(struct device *dev, + enum hwmon_sensor_types type, u32 attr, + int channel, const char **str) +{ + *str = nvme_hwmon_sensor_names[channel]; + return 0; +} + +static umode_t nvme_hwmon_is_visible(const void *_data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + const struct nvme_hwmon_data *data = _data; + + switch (attr) { + case hwmon_temp_crit: + if (!channel && data->ctrl->cctemp) + return 0444; + break; + case hwmon_temp_max: + case hwmon_temp_min: + if ((!channel && data->ctrl->wctemp) || + (channel && data->log.temp_sensor[channel - 1])) { + if (data->ctrl->quirks & + NVME_QUIRK_NO_TEMP_THRESH_CHANGE) + return 0444; + return 0644; + } + break; + case hwmon_temp_alarm: + if (!channel) + return 0444; + break; + case hwmon_temp_input: + case hwmon_temp_label: + if (!channel || data->log.temp_sensor[channel - 1]) + return 0444; + break; + default: + break; + } + return 0; +} + +static const struct hwmon_channel_info *nvme_hwmon_info[] = { + HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ), + HWMON_CHANNEL_INFO(temp, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_CRIT | HWMON_T_LABEL | HWMON_T_ALARM, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL), + NULL +}; + +static const struct hwmon_ops nvme_hwmon_ops = { + .is_visible = nvme_hwmon_is_visible, + .read = nvme_hwmon_read, + .read_string = nvme_hwmon_read_string, + .write = nvme_hwmon_write, +}; + +static const struct hwmon_chip_info nvme_hwmon_chip_info = { + .ops = &nvme_hwmon_ops, + .info = nvme_hwmon_info, +}; + +void nvme_hwmon_init(struct nvme_ctrl *ctrl) +{ + struct device *dev = ctrl->dev; + struct nvme_hwmon_data *data; + struct device *hwmon; + int err; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return; + + data->ctrl = ctrl; + mutex_init(&data->read_lock); + + err = nvme_hwmon_get_smart_log(data); + if (err) { + dev_warn(dev, "Failed to read smart log (error %d)\n", err); + devm_kfree(dev, data); + return; + } + + hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data, + &nvme_hwmon_chip_info, + NULL); + if (IS_ERR(hwmon)) { + dev_warn(dev, "Failed to instantiate hwmon device\n"); + devm_kfree(dev, data); + } +} diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fc99a40c1ec4..797c18337d96 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -95,6 +95,7 @@ void nvme_failover_req(struct request *req) } break; case NVME_SC_HOST_PATH_ERROR: + case NVME_SC_HOST_ABORTED_CMD: /* * Temporary transport disruption in talking to the controller. * Try to send on a new path. @@ -158,9 +159,11 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) struct nvme_ns *ns; mutex_lock(&ctrl->scan_lock); + down_read(&ctrl->namespaces_rwsem); list_for_each_entry(ns, &ctrl->namespaces, list) if (nvme_mpath_clear_current_path(ns)) kblockd_schedule_work(&ns->head->requeue_work); + up_read(&ctrl->namespaces_rwsem); mutex_unlock(&ctrl->scan_lock); } @@ -444,8 +447,14 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) { struct nvme_ana_group_desc *desc = base + offset; - u32 nr_nsids = le32_to_cpu(desc->nnsids); - size_t nsid_buf_size = nr_nsids * sizeof(__le32); + u32 nr_nsids; + size_t nsid_buf_size; + + if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc))) + return -EINVAL; + + nr_nsids = le32_to_cpu(desc->nnsids); + nsid_buf_size = nr_nsids * sizeof(__le32); if (WARN_ON_ONCE(desc->grpid == 0)) return -EINVAL; @@ -465,8 +474,6 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, return error; offset += nsid_buf_size; - if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc))) - return -EINVAL; } return 0; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 22e8401352c2..3b9cbe0668fa 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -115,6 +115,11 @@ enum nvme_quirks { * Prevent tag overlap between queues */ NVME_QUIRK_SHARED_TAGS = (1 << 13), + + /* + * Don't change the value of the temperature threshold feature + */ + NVME_QUIRK_NO_TEMP_THRESH_CHANGE = (1 << 14), }; /* @@ -231,6 +236,8 @@ struct nvme_ctrl { u16 kas; u8 npss; u8 apsta; + u16 wctemp; + u16 cctemp; u32 oaes; u32 aen_result; u32 ctratt; @@ -419,9 +426,20 @@ static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl) return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); } -static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) +/* + * Convert a 512B sector number to a device logical block number. + */ +static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector) +{ + return sector >> (ns->lba_shift - SECTOR_SHIFT); +} + +/* + * Convert a device logical block number to a 512B sector number. + */ +static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba) { - return (sector >> (ns->lba_shift - 9)); + return lba << (ns->lba_shift - SECTOR_SHIFT); } static inline void nvme_end_request(struct request *req, __le16 status, @@ -446,6 +464,11 @@ static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl) put_device(ctrl->device); } +static inline bool nvme_is_aen_req(u16 qid, __u16 command_id) +{ + return !qid && command_id >= NVME_AQ_BLK_MQ_DEPTH; +} + void nvme_complete_rq(struct request *req); bool nvme_cancel_request(struct request *req, void *data, bool reserved); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, @@ -652,4 +675,10 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) return dev_to_disk(dev)->private_data; } +#ifdef CONFIG_NVME_HWMON +void nvme_hwmon_init(struct nvme_ctrl *ctrl); +#else +static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { } +#endif + #endif /* _NVME_H */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 869f462e6b6e..dcaad5831cee 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -925,7 +925,6 @@ static void nvme_pci_complete_rq(struct request *req) struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_dev *dev = iod->nvmeq->dev; - nvme_cleanup_cmd(req); if (blk_integrity_rq(req)) dma_unmap_page(dev->dev, iod->meta_dma, rq_integrity_vec(req)->bv_len, rq_data_dir(req)); @@ -968,8 +967,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvmeq->qid == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { + if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) { nvme_complete_async_event(&nvmeq->dev->ctrl, cqe->status, &cqe->result); return; @@ -2982,7 +2980,7 @@ static int nvme_suspend(struct device *dev) /* * Clearing npss forces a controller reset on resume. The - * correct value will be resdicovered then. + * correct value will be rediscovered then. */ ret = nvme_disable_prepare_reset(ndev, true); ctrl->npss = 0; @@ -3082,7 +3080,8 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_DEALLOCATE_ZEROES, }, { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | - NVME_QUIRK_MEDIUM_PRIO_SQ }, + NVME_QUIRK_MEDIUM_PRIO_SQ | + NVME_QUIRK_NO_TEMP_THRESH_CHANGE }, { PCI_VDEVICE(INTEL, 0xf1a6), /* Intel 760p/Pro 7600p */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f19a28b4e997..dce59459ed41 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1160,8 +1160,6 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, } ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq)); - - nvme_cleanup_cmd(rq); sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE); } @@ -1501,8 +1499,8 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_rdma_queue_idx(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + if (unlikely(nvme_is_aen_req(nvme_rdma_queue_idx(queue), + cqe->command_id))) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else @@ -1768,7 +1766,6 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, if (unlikely(err < 0)) { dev_err(queue->ctrl->ctrl.device, "Failed to map data (%d)\n", err); - nvme_cleanup_cmd(rq); goto err; } @@ -1779,18 +1776,19 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, req->mr ? &req->reg_wr.wr : NULL); - if (unlikely(err)) { - nvme_rdma_unmap_data(queue, rq); - goto err; - } + if (unlikely(err)) + goto err_unmap; return BLK_STS_OK; +err_unmap: + nvme_rdma_unmap_data(queue, rq); err: if (err == -ENOMEM || err == -EAGAIN) ret = BLK_STS_RESOURCE; else ret = BLK_STS_IOERR; + nvme_cleanup_cmd(rq); unmap_qe: ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command), DMA_TO_DEVICE); @@ -2133,8 +2131,16 @@ err_unreg_client: static void __exit nvme_rdma_cleanup_module(void) { + struct nvme_rdma_ctrl *ctrl; + nvmf_unregister_transport(&nvme_rdma_transport); ib_unregister_client(&nvme_rdma_ib_client); + + mutex_lock(&nvme_rdma_ctrl_mutex); + list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) + nvme_delete_ctrl(&ctrl->ctrl); + mutex_unlock(&nvme_rdma_ctrl_mutex); + flush_workqueue(nvme_delete_wq); } module_init(nvme_rdma_init_module); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 7544be84ab35..6d43b23a0fc8 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -491,8 +491,8 @@ static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_tcp_queue_id(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + if (unlikely(nvme_is_aen_req(nvme_tcp_queue_id(queue), + cqe->command_id))) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 831a062d27cb..56c21b501185 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -31,7 +31,7 @@ u64 nvmet_get_log_page_offset(struct nvme_command *cmd) static void nvmet_execute_get_log_page_noop(struct nvmet_req *req) { - nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len)); + nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->transfer_len)); } static void nvmet_execute_get_log_page_error(struct nvmet_req *req) @@ -134,7 +134,7 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req) u16 status = NVME_SC_INTERNAL; unsigned long flags; - if (req->data_len != sizeof(*log)) + if (req->transfer_len != sizeof(*log)) goto out; log = kzalloc(sizeof(*log), GFP_KERNEL); @@ -196,7 +196,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req) u16 status = NVME_SC_INTERNAL; size_t len; - if (req->data_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32)) + if (req->transfer_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32)) goto out; mutex_lock(&ctrl->lock); @@ -206,7 +206,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req) len = ctrl->nr_changed_ns * sizeof(__le32); status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len); if (!status) - status = nvmet_zero_sgl(req, len, req->data_len - len); + status = nvmet_zero_sgl(req, len, req->transfer_len - len); ctrl->nr_changed_ns = 0; nvmet_clear_aen_bit(req, NVME_AEN_BIT_NS_ATTR); mutex_unlock(&ctrl->lock); @@ -282,6 +282,36 @@ out: nvmet_req_complete(req, status); } +static void nvmet_execute_get_log_page(struct nvmet_req *req) +{ + if (!nvmet_check_data_len(req, nvmet_get_log_page_len(req->cmd))) + return; + + switch (req->cmd->get_log_page.lid) { + case NVME_LOG_ERROR: + return nvmet_execute_get_log_page_error(req); + case NVME_LOG_SMART: + return nvmet_execute_get_log_page_smart(req); + case NVME_LOG_FW_SLOT: + /* + * We only support a single firmware slot which always is + * active, so we can zero out the whole firmware slot log and + * still claim to fully implement this mandatory log page. + */ + return nvmet_execute_get_log_page_noop(req); + case NVME_LOG_CHANGED_NS: + return nvmet_execute_get_log_changed_ns(req); + case NVME_LOG_CMD_EFFECTS: + return nvmet_execute_get_log_cmd_effects_ns(req); + case NVME_LOG_ANA: + return nvmet_execute_get_log_page_ana(req); + } + pr_err("unhandled lid %d on qid %d\n", + req->cmd->get_log_page.lid, req->sq->qid); + req->error_loc = offsetof(struct nvme_get_log_page_command, lid); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); +} + static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -565,6 +595,28 @@ out: nvmet_req_complete(req, status); } +static void nvmet_execute_identify(struct nvmet_req *req) +{ + if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE)) + return; + + switch (req->cmd->identify.cns) { + case NVME_ID_CNS_NS: + return nvmet_execute_identify_ns(req); + case NVME_ID_CNS_CTRL: + return nvmet_execute_identify_ctrl(req); + case NVME_ID_CNS_NS_ACTIVE_LIST: + return nvmet_execute_identify_nslist(req); + case NVME_ID_CNS_NS_DESC_LIST: + return nvmet_execute_identify_desclist(req); + } + + pr_err("unhandled identify cns %d on qid %d\n", + req->cmd->identify.cns, req->sq->qid); + req->error_loc = offsetof(struct nvme_identify, cns); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); +} + /* * A "minimum viable" abort implementation: the command is mandatory in the * spec, but we are not required to do any useful work. We couldn't really @@ -574,6 +626,8 @@ out: */ static void nvmet_execute_abort(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; nvmet_set_result(req, 1); nvmet_req_complete(req, 0); } @@ -658,6 +712,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_NUM_QUEUES: nvmet_set_result(req, @@ -721,6 +778,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { /* * These features are mandatory in the spec, but we don't @@ -785,6 +845,9 @@ void nvmet_execute_async_event(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; + if (!nvmet_check_data_len(req, 0)) + return; + mutex_lock(&ctrl->lock); if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) { mutex_unlock(&ctrl->lock); @@ -801,6 +864,9 @@ void nvmet_execute_keep_alive(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; + if (!nvmet_check_data_len(req, 0)) + return; + pr_debug("ctrl %d update keep-alive timer for %d secs\n", ctrl->cntlid, ctrl->kato); @@ -813,77 +879,36 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) struct nvme_command *cmd = req->cmd; u16 ret; + if (nvme_is_fabrics(cmd)) + return nvmet_parse_fabrics_cmd(req); + if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) + return nvmet_parse_discovery_cmd(req); + ret = nvmet_check_ctrl_status(req, cmd); if (unlikely(ret)) return ret; switch (cmd->common.opcode) { case nvme_admin_get_log_page: - req->data_len = nvmet_get_log_page_len(cmd); - - switch (cmd->get_log_page.lid) { - case NVME_LOG_ERROR: - req->execute = nvmet_execute_get_log_page_error; - return 0; - case NVME_LOG_SMART: - req->execute = nvmet_execute_get_log_page_smart; - return 0; - case NVME_LOG_FW_SLOT: - /* - * We only support a single firmware slot which always - * is active, so we can zero out the whole firmware slot - * log and still claim to fully implement this mandatory - * log page. - */ - req->execute = nvmet_execute_get_log_page_noop; - return 0; - case NVME_LOG_CHANGED_NS: - req->execute = nvmet_execute_get_log_changed_ns; - return 0; - case NVME_LOG_CMD_EFFECTS: - req->execute = nvmet_execute_get_log_cmd_effects_ns; - return 0; - case NVME_LOG_ANA: - req->execute = nvmet_execute_get_log_page_ana; - return 0; - } - break; + req->execute = nvmet_execute_get_log_page; + return 0; case nvme_admin_identify: - req->data_len = NVME_IDENTIFY_DATA_SIZE; - switch (cmd->identify.cns) { - case NVME_ID_CNS_NS: - req->execute = nvmet_execute_identify_ns; - return 0; - case NVME_ID_CNS_CTRL: - req->execute = nvmet_execute_identify_ctrl; - return 0; - case NVME_ID_CNS_NS_ACTIVE_LIST: - req->execute = nvmet_execute_identify_nslist; - return 0; - case NVME_ID_CNS_NS_DESC_LIST: - req->execute = nvmet_execute_identify_desclist; - return 0; - } - break; + req->execute = nvmet_execute_identify; + return 0; case nvme_admin_abort_cmd: req->execute = nvmet_execute_abort; - req->data_len = 0; return 0; case nvme_admin_set_features: req->execute = nvmet_execute_set_features; - req->data_len = 0; return 0; case nvme_admin_get_features: req->execute = nvmet_execute_get_features; - req->data_len = 0; return 0; case nvme_admin_async_event: req->execute = nvmet_execute_async_event; - req->data_len = 0; return 0; case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; - req->data_len = 0; return 0; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 3a67e244e568..28438b833c1b 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -892,14 +892,10 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, } if (unlikely(!req->sq->ctrl)) - /* will return an error for any Non-connect command: */ + /* will return an error for any non-connect command: */ status = nvmet_parse_connect_cmd(req); else if (likely(req->sq->qid != 0)) status = nvmet_parse_io_cmd(req); - else if (nvme_is_fabrics(req->cmd)) - status = nvmet_parse_fabrics_cmd(req); - else if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) - status = nvmet_parse_discovery_cmd(req); else status = nvmet_parse_admin_cmd(req); @@ -930,15 +926,17 @@ void nvmet_req_uninit(struct nvmet_req *req) } EXPORT_SYMBOL_GPL(nvmet_req_uninit); -void nvmet_req_execute(struct nvmet_req *req) +bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len) { - if (unlikely(req->data_len != req->transfer_len)) { + if (unlikely(data_len != req->transfer_len)) { req->error_loc = offsetof(struct nvme_common_command, dptr); nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); - } else - req->execute(req); + return false; + } + + return true; } -EXPORT_SYMBOL_GPL(nvmet_req_execute); +EXPORT_SYMBOL_GPL(nvmet_check_data_len); int nvmet_req_alloc_sgl(struct nvmet_req *req) { @@ -966,7 +964,7 @@ int nvmet_req_alloc_sgl(struct nvmet_req *req) } req->sg = sgl_alloc(req->transfer_len, GFP_KERNEL, &req->sg_cnt); - if (!req->sg) + if (unlikely(!req->sg)) return -ENOMEM; return 0; diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 3764a8900850..0c2274b21e15 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -157,7 +157,7 @@ static size_t discovery_log_entries(struct nvmet_req *req) return entries; } -static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) +static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) { const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry); struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -171,6 +171,16 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) u16 status = 0; void *buffer; + if (!nvmet_check_data_len(req, data_len)) + return; + + if (req->cmd->get_log_page.lid != NVME_LOG_DISC) { + req->error_loc = + offsetof(struct nvme_get_log_page_command, lid); + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + goto out; + } + /* Spec requires dword aligned offsets */ if (offset & 0x3) { status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; @@ -227,20 +237,35 @@ out: nvmet_req_complete(req, status); } -static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req) +static void nvmet_execute_disc_identify(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; + const char model[] = "Linux"; u16 status = 0; + if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE)) + return; + + if (req->cmd->identify.cns != NVME_ID_CNS_CTRL) { + req->error_loc = offsetof(struct nvme_identify, cns); + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + goto out; + } + id = kzalloc(sizeof(*id), GFP_KERNEL); if (!id) { status = NVME_SC_INTERNAL; goto out; } + memset(id->sn, ' ', sizeof(id->sn)); + bin2hex(id->sn, &ctrl->subsys->serial, + min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2)); memset(id->fr, ' ', sizeof(id->fr)); - strncpy((char *)id->fr, UTS_RELEASE, sizeof(id->fr)); + memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' '); + memcpy_and_pad(id->fr, sizeof(id->fr), + UTS_RELEASE, strlen(UTS_RELEASE), ' '); /* no limit on data transfer sizes for now */ id->mdts = 0; @@ -273,6 +298,9 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_KATO: stat = nvmet_set_feat_kato(req); @@ -296,6 +324,9 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_KATO: nvmet_get_feat_kato(req); @@ -328,47 +359,22 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) switch (cmd->common.opcode) { case nvme_admin_set_features: req->execute = nvmet_execute_disc_set_features; - req->data_len = 0; return 0; case nvme_admin_get_features: req->execute = nvmet_execute_disc_get_features; - req->data_len = 0; return 0; case nvme_admin_async_event: req->execute = nvmet_execute_async_event; - req->data_len = 0; return 0; case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; - req->data_len = 0; return 0; case nvme_admin_get_log_page: - req->data_len = nvmet_get_log_page_len(cmd); - - switch (cmd->get_log_page.lid) { - case NVME_LOG_DISC: - req->execute = nvmet_execute_get_disc_log_page; - return 0; - default: - pr_err("unsupported get_log_page lid %d\n", - cmd->get_log_page.lid); - req->error_loc = - offsetof(struct nvme_get_log_page_command, lid); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; - } + req->execute = nvmet_execute_disc_get_log_page; + return 0; case nvme_admin_identify: - req->data_len = NVME_IDENTIFY_DATA_SIZE; - switch (cmd->identify.cns) { - case NVME_ID_CNS_CTRL: - req->execute = - nvmet_execute_identify_disc_ctrl; - return 0; - default: - pr_err("unsupported identify cns %d\n", - cmd->identify.cns); - req->error_loc = offsetof(struct nvme_identify, cns); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; - } + req->execute = nvmet_execute_disc_identify; + return 0; default: pr_err("unhandled cmd %d\n", cmd->common.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index d16b55ffe79f..f7297473d9eb 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -12,6 +12,9 @@ static void nvmet_execute_prop_set(struct nvmet_req *req) u64 val = le64_to_cpu(req->cmd->prop_set.value); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + if (req->cmd->prop_set.attrib & 1) { req->error_loc = offsetof(struct nvmf_property_set_command, attrib); @@ -38,6 +41,9 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) u16 status = 0; u64 val = 0; + if (!nvmet_check_data_len(req, 0)) + return; + if (req->cmd->prop_get.attrib & 1) { switch (le32_to_cpu(req->cmd->prop_get.offset)) { case NVME_REG_CAP: @@ -82,11 +88,9 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) switch (cmd->fabrics.fctype) { case nvme_fabrics_type_property_set: - req->data_len = 0; req->execute = nvmet_execute_prop_set; break; case nvme_fabrics_type_property_get: - req->data_len = 0; req->execute = nvmet_execute_prop_get; break; default: @@ -147,6 +151,9 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) struct nvmet_ctrl *ctrl = NULL; u16 status = 0; + if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data))) + return; + d = kmalloc(sizeof(*d), GFP_KERNEL); if (!d) { status = NVME_SC_INTERNAL; @@ -211,6 +218,9 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) u16 qid = le16_to_cpu(c->qid); u16 status = 0; + if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data))) + return; + d = kmalloc(sizeof(*d), GFP_KERNEL); if (!d) { status = NVME_SC_INTERNAL; @@ -281,7 +291,6 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } - req->data_len = sizeof(struct nvmf_connect_data); if (cmd->connect.qid == 0) req->execute = nvmet_execute_admin_connect; else diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index ce8d819f86cc..a0db6371b43e 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1495,20 +1495,20 @@ static void nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_ls_iod *iod) { - struct fcnvme_ls_disconnect_rqst *rqst = - (struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf; - struct fcnvme_ls_disconnect_acc *acc = - (struct fcnvme_ls_disconnect_acc *)iod->rspbuf; + struct fcnvme_ls_disconnect_assoc_rqst *rqst = + (struct fcnvme_ls_disconnect_assoc_rqst *)iod->rqstbuf; + struct fcnvme_ls_disconnect_assoc_acc *acc = + (struct fcnvme_ls_disconnect_assoc_acc *)iod->rspbuf; struct nvmet_fc_tgt_assoc *assoc; int ret = 0; memset(acc, 0, sizeof(*acc)); - if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_rqst)) + if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_assoc_rqst)) ret = VERR_DISCONN_LEN; else if (rqst->desc_list_len != fcnvme_lsdesc_len( - sizeof(struct fcnvme_ls_disconnect_rqst))) + sizeof(struct fcnvme_ls_disconnect_assoc_rqst))) ret = VERR_DISCONN_RQST_LEN; else if (rqst->associd.desc_tag != cpu_to_be32(FCNVME_LSDESC_ASSOC_ID)) ret = VERR_ASSOC_ID; @@ -1523,8 +1523,11 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, fcnvme_lsdesc_len( sizeof(struct fcnvme_lsdesc_disconn_cmd))) ret = VERR_DISCONN_CMD_LEN; - else if ((rqst->discon_cmd.scope != FCNVME_DISCONN_ASSOCIATION) && - (rqst->discon_cmd.scope != FCNVME_DISCONN_CONNECTION)) + /* + * As the standard changed on the LS, check if old format and scope + * something other than Association (e.g. 0). + */ + else if (rqst->discon_cmd.rsvd8[0]) ret = VERR_DISCONN_SCOPE; else { /* match an active association */ @@ -1556,8 +1559,8 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, nvmet_fc_format_rsp_hdr(acc, FCNVME_LS_ACC, fcnvme_lsdesc_len( - sizeof(struct fcnvme_ls_disconnect_acc)), - FCNVME_LS_DISCONNECT); + sizeof(struct fcnvme_ls_disconnect_assoc_acc)), + FCNVME_LS_DISCONNECT_ASSOC); /* release get taken in nvmet_fc_find_target_assoc */ nvmet_fc_tgt_a_put(iod->assoc); @@ -1632,7 +1635,7 @@ nvmet_fc_handle_ls_rqst(struct nvmet_fc_tgtport *tgtport, /* Creates an IO Queue/Connection */ nvmet_fc_ls_create_connection(tgtport, iod); break; - case FCNVME_LS_DISCONNECT: + case FCNVME_LS_DISCONNECT_ASSOC: /* Terminate a Queue/Connection or the Association */ nvmet_fc_ls_disconnect(tgtport, iod); break; @@ -2015,7 +2018,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) } /* data transfer complete, resume with nvmet layer */ - nvmet_req_execute(&fod->req); + fod->req.execute(&fod->req); break; case NVMET_FCOP_READDATA: @@ -2231,7 +2234,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, * can invoke the nvmet_layer now. If read data, cmd completion will * push the data */ - nvmet_req_execute(&fod->req); + fod->req.execute(&fod->req); return; transport_error: @@ -2299,7 +2302,7 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port, /* validate iu, so the connection id can be used to find the queue */ if ((cmdiubuf_len != sizeof(*cmdiu)) || - (cmdiu->scsi_id != NVME_CMD_SCSI_ID) || + (cmdiu->format_id != NVME_CMD_FORMAT_ID) || (cmdiu->fc_id != NVME_CMD_FC_ID) || (be16_to_cpu(cmdiu->iu_len) != (sizeof(*cmdiu)/4))) return -EIO; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 32008d85172b..b6fca0e421ef 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -147,8 +147,12 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) int sg_cnt = req->sg_cnt; struct bio *bio; struct scatterlist *sg; + struct blk_plug plug; sector_t sector; - int op, op_flags = 0, i; + int op, i; + + if (!nvmet_check_data_len(req, nvmet_rw_len(req))) + return; if (!req->sg_cnt) { nvmet_req_complete(req, 0); @@ -156,21 +160,20 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) } if (req->cmd->rw.opcode == nvme_cmd_write) { - op = REQ_OP_WRITE; - op_flags = REQ_SYNC | REQ_IDLE; + op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA)) - op_flags |= REQ_FUA; + op |= REQ_FUA; } else { op = REQ_OP_READ; } if (is_pci_p2pdma_page(sg_page(req->sg))) - op_flags |= REQ_NOMERGE; + op |= REQ_NOMERGE; sector = le64_to_cpu(req->cmd->rw.slba); sector <<= (req->ns->blksize_shift - 9); - if (req->data_len <= NVMET_MAX_INLINE_DATA_LEN) { + if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { bio = &req->b.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { @@ -180,8 +183,9 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) bio->bi_iter.bi_sector = sector; bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; - bio_set_op_attrs(bio, op, op_flags); + bio->bi_opf = op; + blk_start_plug(&plug); for_each_sg(req->sg, sg, req->sg_cnt, i) { while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset) != sg->length) { @@ -190,7 +194,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES)); bio_set_dev(bio, req->ns->bdev); bio->bi_iter.bi_sector = sector; - bio_set_op_attrs(bio, op, op_flags); + bio->bi_opf = op; bio_chain(bio, prev); submit_bio(prev); @@ -201,12 +205,16 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) } submit_bio(bio); + blk_finish_plug(&plug); } static void nvmet_bdev_execute_flush(struct nvmet_req *req) { struct bio *bio = &req->b.inline_bio; + if (!nvmet_check_data_len(req, 0)) + return; + bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); bio_set_dev(bio, req->ns->bdev); bio->bi_private = req; @@ -261,12 +269,10 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req) if (bio) { bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; - if (status) { - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); - } else { + if (status) + bio_io_error(bio); + else submit_bio(bio); - } } else { nvmet_req_complete(req, status); } @@ -274,6 +280,9 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req) static void nvmet_bdev_execute_dsm(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, nvmet_dsm_len(req))) + return; + switch (le32_to_cpu(req->cmd->dsm.attributes)) { case NVME_DSMGMT_AD: nvmet_bdev_execute_discard(req); @@ -295,6 +304,9 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) sector_t nr_sector; int ret; + if (!nvmet_check_data_len(req, 0)) + return; + sector = le64_to_cpu(write_zeroes->slba) << (req->ns->blksize_shift - 9); nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) << @@ -319,20 +331,15 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req) case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_bdev_execute_rw; - req->data_len = nvmet_rw_len(req); return 0; case nvme_cmd_flush: req->execute = nvmet_bdev_execute_flush; - req->data_len = 0; return 0; case nvme_cmd_dsm: req->execute = nvmet_bdev_execute_dsm; - req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) * - sizeof(struct nvme_dsm_range); return 0; case nvme_cmd_write_zeroes: req->execute = nvmet_bdev_execute_write_zeroes; - req->data_len = 0; return 0; default: pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode, diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 05453f5d1448..caebfce06605 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -126,7 +126,7 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) mempool_free(req->f.bvec, req->ns->bvec_pool); } - if (unlikely(ret != req->data_len)) + if (unlikely(ret != req->transfer_len)) status = errno_to_nvme_status(req, ret); nvmet_req_complete(req, status); } @@ -146,7 +146,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) is_sync = true; pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift; - if (unlikely(pos + req->data_len > req->ns->size)) { + if (unlikely(pos + req->transfer_len > req->ns->size)) { nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC)); return true; } @@ -173,7 +173,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) nr_bvec--; } - if (WARN_ON_ONCE(total_len != req->data_len)) { + if (WARN_ON_ONCE(total_len != req->transfer_len)) { ret = -EIO; goto complete; } @@ -232,6 +232,9 @@ static void nvmet_file_execute_rw(struct nvmet_req *req) { ssize_t nr_bvec = req->sg_cnt; + if (!nvmet_check_data_len(req, nvmet_rw_len(req))) + return; + if (!req->sg_cnt || !nr_bvec) { nvmet_req_complete(req, 0); return; @@ -273,6 +276,8 @@ static void nvmet_file_flush_work(struct work_struct *w) static void nvmet_file_execute_flush(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; INIT_WORK(&req->f.work, nvmet_file_flush_work); schedule_work(&req->f.work); } @@ -331,6 +336,8 @@ static void nvmet_file_dsm_work(struct work_struct *w) static void nvmet_file_execute_dsm(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, nvmet_dsm_len(req))) + return; INIT_WORK(&req->f.work, nvmet_file_dsm_work); schedule_work(&req->f.work); } @@ -359,6 +366,8 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w) static void nvmet_file_execute_write_zeroes(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work); schedule_work(&req->f.work); } @@ -371,20 +380,15 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req) case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_file_execute_rw; - req->data_len = nvmet_rw_len(req); return 0; case nvme_cmd_flush: req->execute = nvmet_file_execute_flush; - req->data_len = 0; return 0; case nvme_cmd_dsm: req->execute = nvmet_file_execute_dsm; - req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) * - sizeof(struct nvme_dsm_range); return 0; case nvme_cmd_write_zeroes: req->execute = nvmet_file_execute_write_zeroes; - req->data_len = 0; return 0; default: pr_err("unhandled cmd for file ns %d on qid %d\n", diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 11f5aea97d1b..a758bb3d5dd4 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -76,7 +76,6 @@ static void nvme_loop_complete_rq(struct request *req) { struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); - nvme_cleanup_cmd(req); sg_free_table_chained(&iod->sg_table, SG_CHUNK_SIZE); nvme_complete_rq(req); } @@ -102,8 +101,8 @@ static void nvme_loop_queue_response(struct nvmet_req *req) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_loop_queue_idx(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { + if (unlikely(nvme_is_aen_req(nvme_loop_queue_idx(queue), + cqe->command_id))) { nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); } else { @@ -126,7 +125,7 @@ static void nvme_loop_execute_work(struct work_struct *work) struct nvme_loop_iod *iod = container_of(work, struct nvme_loop_iod, work); - nvmet_req_execute(&iod->req); + iod->req.execute(&iod->req); } static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index c51f8dd01dc4..46df45e837c9 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -304,8 +304,6 @@ struct nvmet_req { } f; }; int sg_cnt; - /* data length as parsed from the command: */ - size_t data_len; /* data length as parsed from the SGL descriptor: */ size_t transfer_len; @@ -375,7 +373,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req); bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops); void nvmet_req_uninit(struct nvmet_req *req); -void nvmet_req_execute(struct nvmet_req *req); +bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len); void nvmet_req_complete(struct nvmet_req *req, u16 status); int nvmet_req_alloc_sgl(struct nvmet_req *req); void nvmet_req_free_sgl(struct nvmet_req *req); @@ -495,6 +493,12 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req) req->ns->blksize_shift; } +static inline u32 nvmet_dsm_len(struct nvmet_req *req) +{ + return (le32_to_cpu(req->cmd->dsm.nr) + 1) * + sizeof(struct nvme_dsm_range); +} + u16 errno_to_nvme_status(struct nvmet_req *req, int errno); /* Convert a 32-bit number to a 16-bit 0's based number */ diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 36d906a7f70d..37d262a65877 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -603,7 +603,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc) return; } - nvmet_req_execute(&rsp->req); + rsp->req.execute(&rsp->req); } static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len, @@ -672,13 +672,13 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp, return 0; ret = nvmet_req_alloc_sgl(&rsp->req); - if (ret < 0) + if (unlikely(ret < 0)) goto error_out; ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, 0, addr, key, nvmet_data_dir(&rsp->req)); - if (ret < 0) + if (unlikely(ret < 0)) goto error_out; rsp->n_rdma += ret; @@ -746,7 +746,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp) queue->cm_id->port_num, &rsp->read_cqe, NULL)) nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR); } else { - nvmet_req_execute(&rsp->req); + rsp->req.execute(&rsp->req); } return true; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index d535080b781f..af674fc0bb1e 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -320,7 +320,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl; u32 len = le32_to_cpu(sgl->length); - if (!cmd->req.data_len) + if (!len) return 0; if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) | @@ -813,13 +813,11 @@ free_crypto: static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd, struct nvmet_req *req) { + size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); int ret; - /* recover the expected data transfer length */ - req->data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); - if (!nvme_is_write(cmd->req.cmd) || - req->data_len > cmd->req.port->inline_data_size) { + data_len > cmd->req.port->inline_data_size) { nvmet_prepare_receive_pdu(queue); return; } @@ -932,7 +930,7 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) goto out; } - nvmet_req_execute(&queue->cmd->req); + queue->cmd->req.execute(&queue->cmd->req); out: nvmet_prepare_receive_pdu(queue); return ret; @@ -1052,7 +1050,7 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) nvmet_tcp_prep_recv_ddgst(cmd); return 0; } - nvmet_req_execute(&cmd->req); + cmd->req.execute(&cmd->req); } nvmet_prepare_receive_pdu(queue); @@ -1092,7 +1090,7 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) && cmd->rbytes_done == cmd->req.transfer_len) - nvmet_req_execute(&cmd->req); + cmd->req.execute(&cmd->req); ret = 0; out: nvmet_prepare_receive_pdu(queue); diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 057d1ff87d5d..9f1ee9c766ec 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -76,33 +76,6 @@ static struct bus_type nvmem_bus_type = { .name = "nvmem", }; -static struct nvmem_device *of_nvmem_find(struct device_node *nvmem_np) -{ - struct device *d; - - if (!nvmem_np) - return NULL; - - d = bus_find_device_by_of_node(&nvmem_bus_type, nvmem_np); - - if (!d) - return NULL; - - return to_nvmem_device(d); -} - -static struct nvmem_device *nvmem_find(const char *name) -{ - struct device *d; - - d = bus_find_device_by_name(&nvmem_bus_type, NULL, name); - - if (!d) - return NULL; - - return to_nvmem_device(d); -} - static void nvmem_cell_drop(struct nvmem_cell *cell) { blocking_notifier_call_chain(&nvmem_notifier, NVMEM_CELL_REMOVE, cell); @@ -532,13 +505,16 @@ int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) } EXPORT_SYMBOL(devm_nvmem_unregister); -static struct nvmem_device *__nvmem_device_get(struct device_node *np, - const char *nvmem_name) +static struct nvmem_device *__nvmem_device_get(void *data, + int (*match)(struct device *dev, const void *data)) { struct nvmem_device *nvmem = NULL; + struct device *dev; mutex_lock(&nvmem_mutex); - nvmem = np ? of_nvmem_find(np) : nvmem_find(nvmem_name); + dev = bus_find_device(&nvmem_bus_type, NULL, data, match); + if (dev) + nvmem = to_nvmem_device(dev); mutex_unlock(&nvmem_mutex); if (!nvmem) return ERR_PTR(-EPROBE_DEFER); @@ -587,7 +563,7 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *id) if (!nvmem_np) return ERR_PTR(-ENOENT); - return __nvmem_device_get(nvmem_np, NULL); + return __nvmem_device_get(nvmem_np, device_match_of_node); } EXPORT_SYMBOL_GPL(of_nvmem_device_get); #endif @@ -613,10 +589,26 @@ struct nvmem_device *nvmem_device_get(struct device *dev, const char *dev_name) } - return __nvmem_device_get(NULL, dev_name); + return __nvmem_device_get((void *)dev_name, device_match_name); } EXPORT_SYMBOL_GPL(nvmem_device_get); +/** + * nvmem_device_find() - Find nvmem device with matching function + * + * @data: Data to pass to match function + * @match: Callback function to check device + * + * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_device + * on success. + */ +struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)) +{ + return __nvmem_device_get(data, match); +} +EXPORT_SYMBOL_GPL(nvmem_device_find); + static int devm_nvmem_device_match(struct device *dev, void *res, void *data) { struct nvmem_device **nvmem = res; @@ -710,7 +702,8 @@ nvmem_cell_get_from_lookup(struct device *dev, const char *con_id) if ((strcmp(lookup->dev_id, dev_id) == 0) && (strcmp(lookup->con_id, con_id) == 0)) { /* This is the right entry. */ - nvmem = __nvmem_device_get(NULL, lookup->nvmem_name); + nvmem = __nvmem_device_get((void *)lookup->nvmem_name, + device_match_name); if (IS_ERR(nvmem)) { /* Provider may not be registered yet. */ cell = ERR_CAST(nvmem); @@ -780,7 +773,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) if (!nvmem_np) return ERR_PTR(-EINVAL); - nvmem = __nvmem_device_get(nvmem_np, NULL); + nvmem = __nvmem_device_get(nvmem_np, device_match_of_node); of_node_put(nvmem_np); if (IS_ERR(nvmem)) return ERR_CAST(nvmem); diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c index 8f8606b9bc9e..1b8e337a29ca 100644 --- a/drivers/perf/arm-cci.c +++ b/drivers/perf/arm-cci.c @@ -1642,7 +1642,6 @@ static struct cci_pmu *cci_pmu_alloc(struct device *dev) static int cci_pmu_probe(struct platform_device *pdev) { - struct resource *res; struct cci_pmu *cci_pmu; int i, ret, irq; @@ -1650,8 +1649,7 @@ static int cci_pmu_probe(struct platform_device *pdev) if (IS_ERR(cci_pmu)) return PTR_ERR(cci_pmu); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - cci_pmu->base = devm_ioremap_resource(&pdev->dev, res); + cci_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(cci_pmu->base)) return -ENOMEM; diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c index 6fc0273b6129..fea354d6fb29 100644 --- a/drivers/perf/arm-ccn.c +++ b/drivers/perf/arm-ccn.c @@ -1477,8 +1477,7 @@ static int arm_ccn_probe(struct platform_device *pdev) ccn->dev = &pdev->dev; platform_set_drvdata(pdev, ccn); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ccn->base = devm_ioremap_resource(ccn->dev, res); + ccn->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ccn->base)) return PTR_ERR(ccn->base); @@ -1537,6 +1536,7 @@ static int arm_ccn_remove(struct platform_device *pdev) static const struct of_device_id arm_ccn_match[] = { { .compatible = "arm,ccn-502", }, { .compatible = "arm,ccn-504", }, + { .compatible = "arm,ccn-512", }, {}, }; MODULE_DEVICE_TABLE(of, arm_ccn_match); diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index abcf54f7d19c..773128f411f1 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -727,7 +727,7 @@ static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu) static int smmu_pmu_probe(struct platform_device *pdev) { struct smmu_pmu *smmu_pmu; - struct resource *res_0, *res_1; + struct resource *res_0; u32 cfgr, reg_size; u64 ceid_64[2]; int irq, err; @@ -764,8 +764,7 @@ static int smmu_pmu_probe(struct platform_device *pdev) /* Determine if page 1 is present */ if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) { - res_1 = platform_get_resource(pdev, IORESOURCE_MEM, 1); - smmu_pmu->reloc_base = devm_ioremap_resource(dev, res_1); + smmu_pmu->reloc_base = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(smmu_pmu->reloc_base)) return PTR_ERR(smmu_pmu->reloc_base); } else { diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index ce7345745b42..55083c67b2bb 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -45,7 +45,8 @@ static DEFINE_IDA(ddr_ida); /* DDR Perf hardware feature */ -#define DDR_CAP_AXI_ID_FILTER 0x1 /* support AXI ID filter */ +#define DDR_CAP_AXI_ID_FILTER 0x1 /* support AXI ID filter */ +#define DDR_CAP_AXI_ID_FILTER_ENHANCED 0x3 /* support enhanced AXI ID filter */ struct fsl_ddr_devtype_data { unsigned int quirks; /* quirks needed for different DDR Perf core */ @@ -57,9 +58,14 @@ static const struct fsl_ddr_devtype_data imx8m_devtype_data = { .quirks = DDR_CAP_AXI_ID_FILTER, }; +static const struct fsl_ddr_devtype_data imx8mp_devtype_data = { + .quirks = DDR_CAP_AXI_ID_FILTER_ENHANCED, +}; + static const struct of_device_id imx_ddr_pmu_dt_ids[] = { { .compatible = "fsl,imx8-ddr-pmu", .data = &imx8_devtype_data}, { .compatible = "fsl,imx8m-ddr-pmu", .data = &imx8m_devtype_data}, + { .compatible = "fsl,imx8mp-ddr-pmu", .data = &imx8mp_devtype_data}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, imx_ddr_pmu_dt_ids); @@ -78,6 +84,61 @@ struct ddr_pmu { int id; }; +enum ddr_perf_filter_capabilities { + PERF_CAP_AXI_ID_FILTER = 0, + PERF_CAP_AXI_ID_FILTER_ENHANCED, + PERF_CAP_AXI_ID_FEAT_MAX, +}; + +static u32 ddr_perf_filter_cap_get(struct ddr_pmu *pmu, int cap) +{ + u32 quirks = pmu->devtype_data->quirks; + + switch (cap) { + case PERF_CAP_AXI_ID_FILTER: + return !!(quirks & DDR_CAP_AXI_ID_FILTER); + case PERF_CAP_AXI_ID_FILTER_ENHANCED: + quirks &= DDR_CAP_AXI_ID_FILTER_ENHANCED; + return quirks == DDR_CAP_AXI_ID_FILTER_ENHANCED; + default: + WARN(1, "unknown filter cap %d\n", cap); + } + + return 0; +} + +static ssize_t ddr_perf_filter_cap_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ddr_pmu *pmu = dev_get_drvdata(dev); + struct dev_ext_attribute *ea = + container_of(attr, struct dev_ext_attribute, attr); + int cap = (long)ea->var; + + return snprintf(buf, PAGE_SIZE, "%u\n", + ddr_perf_filter_cap_get(pmu, cap)); +} + +#define PERF_EXT_ATTR_ENTRY(_name, _func, _var) \ + (&((struct dev_ext_attribute) { \ + __ATTR(_name, 0444, _func, NULL), (void *)_var \ + }).attr.attr) + +#define PERF_FILTER_EXT_ATTR_ENTRY(_name, _var) \ + PERF_EXT_ATTR_ENTRY(_name, ddr_perf_filter_cap_show, _var) + +static struct attribute *ddr_perf_filter_cap_attr[] = { + PERF_FILTER_EXT_ATTR_ENTRY(filter, PERF_CAP_AXI_ID_FILTER), + PERF_FILTER_EXT_ATTR_ENTRY(enhanced_filter, PERF_CAP_AXI_ID_FILTER_ENHANCED), + NULL, +}; + +static struct attribute_group ddr_perf_filter_cap_attr_group = { + .name = "caps", + .attrs = ddr_perf_filter_cap_attr, +}; + static ssize_t ddr_perf_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -175,9 +236,40 @@ static const struct attribute_group *attr_groups[] = { &ddr_perf_events_attr_group, &ddr_perf_format_attr_group, &ddr_perf_cpumask_attr_group, + &ddr_perf_filter_cap_attr_group, NULL, }; +static bool ddr_perf_is_filtered(struct perf_event *event) +{ + return event->attr.config == 0x41 || event->attr.config == 0x42; +} + +static u32 ddr_perf_filter_val(struct perf_event *event) +{ + return event->attr.config1; +} + +static bool ddr_perf_filters_compatible(struct perf_event *a, + struct perf_event *b) +{ + if (!ddr_perf_is_filtered(a)) + return true; + if (!ddr_perf_is_filtered(b)) + return true; + return ddr_perf_filter_val(a) == ddr_perf_filter_val(b); +} + +static bool ddr_perf_is_enhanced_filtered(struct perf_event *event) +{ + unsigned int filt; + struct ddr_pmu *pmu = to_ddr_pmu(event->pmu); + + filt = pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED; + return (filt == DDR_CAP_AXI_ID_FILTER_ENHANCED) && + ddr_perf_is_filtered(event); +} + static u32 ddr_perf_alloc_counter(struct ddr_pmu *pmu, int event) { int i; @@ -209,27 +301,17 @@ static void ddr_perf_free_counter(struct ddr_pmu *pmu, int counter) static u32 ddr_perf_read_counter(struct ddr_pmu *pmu, int counter) { - return readl_relaxed(pmu->base + COUNTER_READ + counter * 4); -} - -static bool ddr_perf_is_filtered(struct perf_event *event) -{ - return event->attr.config == 0x41 || event->attr.config == 0x42; -} + struct perf_event *event = pmu->events[counter]; + void __iomem *base = pmu->base; -static u32 ddr_perf_filter_val(struct perf_event *event) -{ - return event->attr.config1; -} - -static bool ddr_perf_filters_compatible(struct perf_event *a, - struct perf_event *b) -{ - if (!ddr_perf_is_filtered(a)) - return true; - if (!ddr_perf_is_filtered(b)) - return true; - return ddr_perf_filter_val(a) == ddr_perf_filter_val(b); + /* + * return bytes instead of bursts from ddr transaction for + * axid-read and axid-write event if PMU core supports enhanced + * filter. + */ + base += ddr_perf_is_enhanced_filtered(event) ? COUNTER_DPCR1 : + COUNTER_READ; + return readl_relaxed(base + counter * 4); } static int ddr_perf_event_init(struct perf_event *event) diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index e42d4464c2cf..453f1c6a16ca 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -243,8 +243,6 @@ MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match); static int hisi_ddrc_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *ddrc_pmu) { - struct resource *res; - /* * Use the SCCL_ID and DDRC channel ID to identify the * DDRC PMU, while SCCL_ID is in MPIDR[aff2]. @@ -263,8 +261,7 @@ static int hisi_ddrc_pmu_init_data(struct platform_device *pdev, /* DDRC PMUs only share the same SCCL */ ddrc_pmu->ccl_id = -1; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ddrc_pmu->base = devm_ioremap_resource(&pdev->dev, res); + ddrc_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ddrc_pmu->base)) { dev_err(&pdev->dev, "ioremap failed for ddrc_pmu resource\n"); return PTR_ERR(ddrc_pmu->base); diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c index f28063873e11..6a1dd72d8abb 100644 --- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -234,7 +234,6 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *hha_pmu) { unsigned long long id; - struct resource *res; acpi_status status; status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), @@ -256,8 +255,7 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, /* HHA PMUs only share the same SCCL */ hha_pmu->ccl_id = -1; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hha_pmu->base = devm_ioremap_resource(&pdev->dev, res); + hha_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hha_pmu->base)) { dev_err(&pdev->dev, "ioremap failed for hha_pmu resource\n"); return PTR_ERR(hha_pmu->base); diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c index 078b8dc57250..1151e99b241c 100644 --- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -233,7 +233,6 @@ static int hisi_l3c_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *l3c_pmu) { unsigned long long id; - struct resource *res; acpi_status status; status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), @@ -259,8 +258,7 @@ static int hisi_l3c_pmu_init_data(struct platform_device *pdev, return -EINVAL; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - l3c_pmu->base = devm_ioremap_resource(&pdev->dev, res); + l3c_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(l3c_pmu->base)) { dev_err(&pdev->dev, "ioremap failed for l3c_pmu resource\n"); return PTR_ERR(l3c_pmu->base); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c index 79f76f8dda8e..96183e31b96a 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c @@ -15,6 +15,7 @@ #include <linux/errno.h> #include <linux/interrupt.h> +#include <asm/cputype.h> #include <asm/local64.h> #include "hisi_uncore_pmu.h" @@ -338,8 +339,10 @@ void hisi_uncore_pmu_disable(struct pmu *pmu) /* * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1. - * If multi-threading is supported, CCL_ID is the low 3-bits in MPIDR[Aff2] - * and SCCL_ID is the upper 5-bits of Aff2 field; if not, SCCL_ID + * If multi-threading is supported, On Huawei Kunpeng 920 SoC whose cpu + * core is tsv110, CCL_ID is the low 3-bits in MPIDR[Aff2] and SCCL_ID + * is the upper 5-bits of Aff2 field; while for other cpu types, SCCL_ID + * is in MPIDR[Aff3] and CCL_ID is in MPIDR[Aff2], if not, SCCL_ID * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1]. */ static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id) @@ -347,12 +350,19 @@ static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id) u64 mpidr = read_cpuid_mpidr(); if (mpidr & MPIDR_MT_BITMASK) { - int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2); - - if (sccl_id) - *sccl_id = aff2 >> 3; - if (ccl_id) - *ccl_id = aff2 & 0x7; + if (read_cpuid_part_number() == HISI_CPU_PART_TSV110) { + int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2); + + if (sccl_id) + *sccl_id = aff2 >> 3; + if (ccl_id) + *ccl_id = aff2 & 0x7; + } else { + if (sccl_id) + *sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3); + if (ccl_id) + *ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2); + } } else { if (sccl_id) *sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2); diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c index 43d76c85da56..51b31d6ff2c4 100644 --- a/drivers/perf/thunderx2_pmu.c +++ b/drivers/perf/thunderx2_pmu.c @@ -16,23 +16,36 @@ * they need to be sampled before overflow(i.e, at every 2 seconds). */ -#define TX2_PMU_MAX_COUNTERS 4 +#define TX2_PMU_DMC_L3C_MAX_COUNTERS 4 +#define TX2_PMU_CCPI2_MAX_COUNTERS 8 +#define TX2_PMU_MAX_COUNTERS TX2_PMU_CCPI2_MAX_COUNTERS + + #define TX2_PMU_DMC_CHANNELS 8 #define TX2_PMU_L3_TILES 16 #define TX2_PMU_HRTIMER_INTERVAL (2 * NSEC_PER_SEC) -#define GET_EVENTID(ev) ((ev->hw.config) & 0x1f) -#define GET_COUNTERID(ev) ((ev->hw.idx) & 0x3) +#define GET_EVENTID(ev, mask) ((ev->hw.config) & mask) +#define GET_COUNTERID(ev, mask) ((ev->hw.idx) & mask) /* 1 byte per counter(4 counters). * Event id is encoded in bits [5:1] of a byte, */ #define DMC_EVENT_CFG(idx, val) ((val) << (((idx) * 8) + 1)) +/* bits[3:0] to select counters, are indexed from 8 to 15. */ +#define CCPI2_COUNTER_OFFSET 8 + #define L3C_COUNTER_CTL 0xA8 #define L3C_COUNTER_DATA 0xAC #define DMC_COUNTER_CTL 0x234 #define DMC_COUNTER_DATA 0x240 +#define CCPI2_PERF_CTL 0x108 +#define CCPI2_COUNTER_CTL 0x10C +#define CCPI2_COUNTER_SEL 0x12c +#define CCPI2_COUNTER_DATA_L 0x130 +#define CCPI2_COUNTER_DATA_H 0x134 + /* L3C event IDs */ #define L3_EVENT_READ_REQ 0xD #define L3_EVENT_WRITEBACK_REQ 0xE @@ -51,15 +64,28 @@ #define DMC_EVENT_READ_TXNS 0xF #define DMC_EVENT_MAX 0x10 +#define CCPI2_EVENT_REQ_PKT_SENT 0x3D +#define CCPI2_EVENT_SNOOP_PKT_SENT 0x65 +#define CCPI2_EVENT_DATA_PKT_SENT 0x105 +#define CCPI2_EVENT_GIC_PKT_SENT 0x12D +#define CCPI2_EVENT_MAX 0x200 + +#define CCPI2_PERF_CTL_ENABLE BIT(0) +#define CCPI2_PERF_CTL_START BIT(1) +#define CCPI2_PERF_CTL_RESET BIT(4) +#define CCPI2_EVENT_LEVEL_RISING_EDGE BIT(10) +#define CCPI2_EVENT_TYPE_EDGE_SENSITIVE BIT(11) + enum tx2_uncore_type { PMU_TYPE_L3C, PMU_TYPE_DMC, + PMU_TYPE_CCPI2, PMU_TYPE_INVALID, }; /* - * pmu on each socket has 2 uncore devices(dmc and l3c), - * each device has 4 counters. + * Each socket has 3 uncore devices associated with a PMU. The DMC and + * L3C have 4 32-bit counters and the CCPI2 has 8 64-bit counters. */ struct tx2_uncore_pmu { struct hlist_node hpnode; @@ -69,8 +95,10 @@ struct tx2_uncore_pmu { int node; int cpu; u32 max_counters; + u32 counters_mask; u32 prorate_factor; u32 max_events; + u32 events_mask; u64 hrtimer_interval; void __iomem *base; DECLARE_BITMAP(active_counters, TX2_PMU_MAX_COUNTERS); @@ -79,6 +107,7 @@ struct tx2_uncore_pmu { struct hrtimer hrtimer; const struct attribute_group **attr_groups; enum tx2_uncore_type type; + enum hrtimer_restart (*hrtimer_callback)(struct hrtimer *cb); void (*init_cntr_base)(struct perf_event *event, struct tx2_uncore_pmu *tx2_pmu); void (*stop_event)(struct perf_event *event); @@ -92,7 +121,21 @@ static inline struct tx2_uncore_pmu *pmu_to_tx2_pmu(struct pmu *pmu) return container_of(pmu, struct tx2_uncore_pmu, pmu); } -PMU_FORMAT_ATTR(event, "config:0-4"); +#define TX2_PMU_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t \ +__tx2_pmu_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ + \ +static struct device_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __tx2_pmu_##_var##_show, NULL) + +TX2_PMU_FORMAT_ATTR(event, event, "config:0-4"); +TX2_PMU_FORMAT_ATTR(event_ccpi2, event, "config:0-9"); static struct attribute *l3c_pmu_format_attrs[] = { &format_attr_event.attr, @@ -104,6 +147,11 @@ static struct attribute *dmc_pmu_format_attrs[] = { NULL, }; +static struct attribute *ccpi2_pmu_format_attrs[] = { + &format_attr_event_ccpi2.attr, + NULL, +}; + static const struct attribute_group l3c_pmu_format_attr_group = { .name = "format", .attrs = l3c_pmu_format_attrs, @@ -114,6 +162,11 @@ static const struct attribute_group dmc_pmu_format_attr_group = { .attrs = dmc_pmu_format_attrs, }; +static const struct attribute_group ccpi2_pmu_format_attr_group = { + .name = "format", + .attrs = ccpi2_pmu_format_attrs, +}; + /* * sysfs event attributes */ @@ -164,6 +217,19 @@ static struct attribute *dmc_pmu_events_attrs[] = { NULL, }; +TX2_EVENT_ATTR(req_pktsent, CCPI2_EVENT_REQ_PKT_SENT); +TX2_EVENT_ATTR(snoop_pktsent, CCPI2_EVENT_SNOOP_PKT_SENT); +TX2_EVENT_ATTR(data_pktsent, CCPI2_EVENT_DATA_PKT_SENT); +TX2_EVENT_ATTR(gic_pktsent, CCPI2_EVENT_GIC_PKT_SENT); + +static struct attribute *ccpi2_pmu_events_attrs[] = { + &tx2_pmu_event_attr_req_pktsent.attr.attr, + &tx2_pmu_event_attr_snoop_pktsent.attr.attr, + &tx2_pmu_event_attr_data_pktsent.attr.attr, + &tx2_pmu_event_attr_gic_pktsent.attr.attr, + NULL, +}; + static const struct attribute_group l3c_pmu_events_attr_group = { .name = "events", .attrs = l3c_pmu_events_attrs, @@ -174,6 +240,11 @@ static const struct attribute_group dmc_pmu_events_attr_group = { .attrs = dmc_pmu_events_attrs, }; +static const struct attribute_group ccpi2_pmu_events_attr_group = { + .name = "events", + .attrs = ccpi2_pmu_events_attrs, +}; + /* * sysfs cpumask attributes */ @@ -213,6 +284,13 @@ static const struct attribute_group *dmc_pmu_attr_groups[] = { NULL }; +static const struct attribute_group *ccpi2_pmu_attr_groups[] = { + &ccpi2_pmu_format_attr_group, + &pmu_cpumask_attr_group, + &ccpi2_pmu_events_attr_group, + NULL +}; + static inline u32 reg_readl(unsigned long addr) { return readl((void __iomem *)addr); @@ -245,33 +323,58 @@ static void init_cntr_base_l3c(struct perf_event *event, struct tx2_uncore_pmu *tx2_pmu) { struct hw_perf_event *hwc = &event->hw; + u32 cmask; + + tx2_pmu = pmu_to_tx2_pmu(event->pmu); + cmask = tx2_pmu->counters_mask; /* counter ctrl/data reg offset at 8 */ hwc->config_base = (unsigned long)tx2_pmu->base - + L3C_COUNTER_CTL + (8 * GET_COUNTERID(event)); + + L3C_COUNTER_CTL + (8 * GET_COUNTERID(event, cmask)); hwc->event_base = (unsigned long)tx2_pmu->base - + L3C_COUNTER_DATA + (8 * GET_COUNTERID(event)); + + L3C_COUNTER_DATA + (8 * GET_COUNTERID(event, cmask)); } static void init_cntr_base_dmc(struct perf_event *event, struct tx2_uncore_pmu *tx2_pmu) { struct hw_perf_event *hwc = &event->hw; + u32 cmask; + + tx2_pmu = pmu_to_tx2_pmu(event->pmu); + cmask = tx2_pmu->counters_mask; hwc->config_base = (unsigned long)tx2_pmu->base + DMC_COUNTER_CTL; /* counter data reg offset at 0xc */ hwc->event_base = (unsigned long)tx2_pmu->base - + DMC_COUNTER_DATA + (0xc * GET_COUNTERID(event)); + + DMC_COUNTER_DATA + (0xc * GET_COUNTERID(event, cmask)); +} + +static void init_cntr_base_ccpi2(struct perf_event *event, + struct tx2_uncore_pmu *tx2_pmu) +{ + struct hw_perf_event *hwc = &event->hw; + u32 cmask; + + cmask = tx2_pmu->counters_mask; + + hwc->config_base = (unsigned long)tx2_pmu->base + + CCPI2_COUNTER_CTL + (4 * GET_COUNTERID(event, cmask)); + hwc->event_base = (unsigned long)tx2_pmu->base; } static void uncore_start_event_l3c(struct perf_event *event, int flags) { - u32 val; + u32 val, emask; struct hw_perf_event *hwc = &event->hw; + struct tx2_uncore_pmu *tx2_pmu; + + tx2_pmu = pmu_to_tx2_pmu(event->pmu); + emask = tx2_pmu->events_mask; /* event id encoded in bits [07:03] */ - val = GET_EVENTID(event) << 3; + val = GET_EVENTID(event, emask) << 3; reg_writel(val, hwc->config_base); local64_set(&hwc->prev_count, 0); reg_writel(0, hwc->event_base); @@ -284,10 +387,17 @@ static inline void uncore_stop_event_l3c(struct perf_event *event) static void uncore_start_event_dmc(struct perf_event *event, int flags) { - u32 val; + u32 val, cmask, emask; struct hw_perf_event *hwc = &event->hw; - int idx = GET_COUNTERID(event); - int event_id = GET_EVENTID(event); + struct tx2_uncore_pmu *tx2_pmu; + int idx, event_id; + + tx2_pmu = pmu_to_tx2_pmu(event->pmu); + cmask = tx2_pmu->counters_mask; + emask = tx2_pmu->events_mask; + + idx = GET_COUNTERID(event, cmask); + event_id = GET_EVENTID(event, emask); /* enable and start counters. * 8 bits for each counter, bits[05:01] of a counter to set event type. @@ -302,9 +412,14 @@ static void uncore_start_event_dmc(struct perf_event *event, int flags) static void uncore_stop_event_dmc(struct perf_event *event) { - u32 val; + u32 val, cmask; struct hw_perf_event *hwc = &event->hw; - int idx = GET_COUNTERID(event); + struct tx2_uncore_pmu *tx2_pmu; + int idx; + + tx2_pmu = pmu_to_tx2_pmu(event->pmu); + cmask = tx2_pmu->counters_mask; + idx = GET_COUNTERID(event, cmask); /* clear event type(bits[05:01]) to stop counter */ val = reg_readl(hwc->config_base); @@ -312,27 +427,72 @@ static void uncore_stop_event_dmc(struct perf_event *event) reg_writel(val, hwc->config_base); } +static void uncore_start_event_ccpi2(struct perf_event *event, int flags) +{ + u32 emask; + struct hw_perf_event *hwc = &event->hw; + struct tx2_uncore_pmu *tx2_pmu; + + tx2_pmu = pmu_to_tx2_pmu(event->pmu); + emask = tx2_pmu->events_mask; + + /* Bit [09:00] to set event id. + * Bits [10], set level to rising edge. + * Bits [11], set type to edge sensitive. + */ + reg_writel((CCPI2_EVENT_TYPE_EDGE_SENSITIVE | + CCPI2_EVENT_LEVEL_RISING_EDGE | + GET_EVENTID(event, emask)), hwc->config_base); + + /* reset[4], enable[0] and start[1] counters */ + reg_writel(CCPI2_PERF_CTL_RESET | + CCPI2_PERF_CTL_START | + CCPI2_PERF_CTL_ENABLE, + hwc->event_base + CCPI2_PERF_CTL); + local64_set(&event->hw.prev_count, 0ULL); +} + +static void uncore_stop_event_ccpi2(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* disable and stop counter */ + reg_writel(0, hwc->event_base + CCPI2_PERF_CTL); +} + static void tx2_uncore_event_update(struct perf_event *event) { - s64 prev, delta, new = 0; + u64 prev, delta, new = 0; struct hw_perf_event *hwc = &event->hw; struct tx2_uncore_pmu *tx2_pmu; enum tx2_uncore_type type; u32 prorate_factor; + u32 cmask, emask; tx2_pmu = pmu_to_tx2_pmu(event->pmu); type = tx2_pmu->type; + cmask = tx2_pmu->counters_mask; + emask = tx2_pmu->events_mask; prorate_factor = tx2_pmu->prorate_factor; - - new = reg_readl(hwc->event_base); - prev = local64_xchg(&hwc->prev_count, new); - - /* handles rollover of 32 bit counter */ - delta = (u32)(((1UL << 32) - prev) + new); + if (type == PMU_TYPE_CCPI2) { + reg_writel(CCPI2_COUNTER_OFFSET + + GET_COUNTERID(event, cmask), + hwc->event_base + CCPI2_COUNTER_SEL); + new = reg_readl(hwc->event_base + CCPI2_COUNTER_DATA_H); + new = (new << 32) + + reg_readl(hwc->event_base + CCPI2_COUNTER_DATA_L); + prev = local64_xchg(&hwc->prev_count, new); + delta = new - prev; + } else { + new = reg_readl(hwc->event_base); + prev = local64_xchg(&hwc->prev_count, new); + /* handles rollover of 32 bit counter */ + delta = (u32)(((1UL << 32) - prev) + new); + } /* DMC event data_transfers granularity is 16 Bytes, convert it to 64 */ if (type == PMU_TYPE_DMC && - GET_EVENTID(event) == DMC_EVENT_DATA_TRANSFERS) + GET_EVENTID(event, emask) == DMC_EVENT_DATA_TRANSFERS) delta = delta/4; /* L3C and DMC has 16 and 8 interleave channels respectively. @@ -351,6 +511,7 @@ static enum tx2_uncore_type get_tx2_pmu_type(struct acpi_device *adev) } devices[] = { {"CAV901D", PMU_TYPE_L3C}, {"CAV901F", PMU_TYPE_DMC}, + {"CAV901E", PMU_TYPE_CCPI2}, {"", PMU_TYPE_INVALID} }; @@ -380,7 +541,8 @@ static bool tx2_uncore_validate_event(struct pmu *pmu, * Make sure the group of events can be scheduled at once * on the PMU. */ -static bool tx2_uncore_validate_event_group(struct perf_event *event) +static bool tx2_uncore_validate_event_group(struct perf_event *event, + int max_counters) { struct perf_event *sibling, *leader = event->group_leader; int counters = 0; @@ -403,7 +565,7 @@ static bool tx2_uncore_validate_event_group(struct perf_event *event) * If the group requires more counters than the HW has, * it cannot ever be scheduled. */ - return counters <= TX2_PMU_MAX_COUNTERS; + return counters <= max_counters; } @@ -439,7 +601,7 @@ static int tx2_uncore_event_init(struct perf_event *event) hwc->config = event->attr.config; /* Validate the group */ - if (!tx2_uncore_validate_event_group(event)) + if (!tx2_uncore_validate_event_group(event, tx2_pmu->max_counters)) return -EINVAL; return 0; @@ -456,6 +618,10 @@ static void tx2_uncore_event_start(struct perf_event *event, int flags) tx2_pmu->start_event(event, flags); perf_event_update_userpage(event); + /* No hrtimer needed for CCPI2, 64-bit counters */ + if (!tx2_pmu->hrtimer_callback) + return; + /* Start timer for first event */ if (bitmap_weight(tx2_pmu->active_counters, tx2_pmu->max_counters) == 1) { @@ -510,15 +676,23 @@ static void tx2_uncore_event_del(struct perf_event *event, int flags) { struct tx2_uncore_pmu *tx2_pmu = pmu_to_tx2_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; + u32 cmask; + cmask = tx2_pmu->counters_mask; tx2_uncore_event_stop(event, PERF_EF_UPDATE); /* clear the assigned counter */ - free_counter(tx2_pmu, GET_COUNTERID(event)); + free_counter(tx2_pmu, GET_COUNTERID(event, cmask)); perf_event_update_userpage(event); tx2_pmu->events[hwc->idx] = NULL; hwc->idx = -1; + + if (!tx2_pmu->hrtimer_callback) + return; + + if (bitmap_empty(tx2_pmu->active_counters, tx2_pmu->max_counters)) + hrtimer_cancel(&tx2_pmu->hrtimer); } static void tx2_uncore_event_read(struct perf_event *event) @@ -580,8 +754,12 @@ static int tx2_uncore_pmu_add_dev(struct tx2_uncore_pmu *tx2_pmu) cpu_online_mask); tx2_pmu->cpu = cpu; - hrtimer_init(&tx2_pmu->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - tx2_pmu->hrtimer.function = tx2_hrtimer_callback; + + if (tx2_pmu->hrtimer_callback) { + hrtimer_init(&tx2_pmu->hrtimer, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); + tx2_pmu->hrtimer.function = tx2_pmu->hrtimer_callback; + } ret = tx2_uncore_pmu_register(tx2_pmu); if (ret) { @@ -653,10 +831,13 @@ static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev, switch (tx2_pmu->type) { case PMU_TYPE_L3C: - tx2_pmu->max_counters = TX2_PMU_MAX_COUNTERS; + tx2_pmu->max_counters = TX2_PMU_DMC_L3C_MAX_COUNTERS; + tx2_pmu->counters_mask = 0x3; tx2_pmu->prorate_factor = TX2_PMU_L3_TILES; tx2_pmu->max_events = L3_EVENT_MAX; + tx2_pmu->events_mask = 0x1f; tx2_pmu->hrtimer_interval = TX2_PMU_HRTIMER_INTERVAL; + tx2_pmu->hrtimer_callback = tx2_hrtimer_callback; tx2_pmu->attr_groups = l3c_pmu_attr_groups; tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL, "uncore_l3c_%d", tx2_pmu->node); @@ -665,10 +846,13 @@ static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev, tx2_pmu->stop_event = uncore_stop_event_l3c; break; case PMU_TYPE_DMC: - tx2_pmu->max_counters = TX2_PMU_MAX_COUNTERS; + tx2_pmu->max_counters = TX2_PMU_DMC_L3C_MAX_COUNTERS; + tx2_pmu->counters_mask = 0x3; tx2_pmu->prorate_factor = TX2_PMU_DMC_CHANNELS; tx2_pmu->max_events = DMC_EVENT_MAX; + tx2_pmu->events_mask = 0x1f; tx2_pmu->hrtimer_interval = TX2_PMU_HRTIMER_INTERVAL; + tx2_pmu->hrtimer_callback = tx2_hrtimer_callback; tx2_pmu->attr_groups = dmc_pmu_attr_groups; tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL, "uncore_dmc_%d", tx2_pmu->node); @@ -676,6 +860,21 @@ static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev, tx2_pmu->start_event = uncore_start_event_dmc; tx2_pmu->stop_event = uncore_stop_event_dmc; break; + case PMU_TYPE_CCPI2: + /* CCPI2 has 8 counters */ + tx2_pmu->max_counters = TX2_PMU_CCPI2_MAX_COUNTERS; + tx2_pmu->counters_mask = 0x7; + tx2_pmu->prorate_factor = 1; + tx2_pmu->max_events = CCPI2_EVENT_MAX; + tx2_pmu->events_mask = 0x1ff; + tx2_pmu->attr_groups = ccpi2_pmu_attr_groups; + tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL, + "uncore_ccpi2_%d", tx2_pmu->node); + tx2_pmu->init_cntr_base = init_cntr_base_ccpi2; + tx2_pmu->start_event = uncore_start_event_ccpi2; + tx2_pmu->stop_event = uncore_stop_event_ccpi2; + tx2_pmu->hrtimer_callback = NULL; + break; case PMU_TYPE_INVALID: devm_kfree(dev, tx2_pmu); return NULL; @@ -744,7 +943,9 @@ static int tx2_uncore_pmu_offline_cpu(unsigned int cpu, if (cpu != tx2_pmu->cpu) return 0; - hrtimer_cancel(&tx2_pmu->hrtimer); + if (tx2_pmu->hrtimer_callback) + hrtimer_cancel(&tx2_pmu->hrtimer); + cpumask_copy(&cpu_online_mask_temp, cpu_online_mask); cpumask_clear_cpu(cpu, &cpu_online_mask_temp); new_cpu = cpumask_any_and( diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c index 7e328d6385c3..46ee6807d533 100644 --- a/drivers/perf/xgene_pmu.c +++ b/drivers/perf/xgene_pmu.c @@ -1282,25 +1282,21 @@ static int acpi_pmu_probe_active_mcb_mcu_l3c(struct xgene_pmu *xgene_pmu, struct platform_device *pdev) { void __iomem *csw_csr, *mcba_csr, *mcbb_csr; - struct resource *res; unsigned int reg; - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - csw_csr = devm_ioremap_resource(&pdev->dev, res); + csw_csr = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(csw_csr)) { dev_err(&pdev->dev, "ioremap failed for CSW CSR resource\n"); return PTR_ERR(csw_csr); } - res = platform_get_resource(pdev, IORESOURCE_MEM, 2); - mcba_csr = devm_ioremap_resource(&pdev->dev, res); + mcba_csr = devm_platform_ioremap_resource(pdev, 2); if (IS_ERR(mcba_csr)) { dev_err(&pdev->dev, "ioremap failed for MCBA CSR resource\n"); return PTR_ERR(mcba_csr); } - res = platform_get_resource(pdev, IORESOURCE_MEM, 3); - mcbb_csr = devm_ioremap_resource(&pdev->dev, res); + mcbb_csr = devm_platform_ioremap_resource(pdev, 3); if (IS_ERR(mcbb_csr)) { dev_err(&pdev->dev, "ioremap failed for MCBB CSR resource\n"); return PTR_ERR(mcbb_csr); @@ -1332,13 +1328,11 @@ static int acpi_pmu_v3_probe_active_mcb_mcu_l3c(struct xgene_pmu *xgene_pmu, struct platform_device *pdev) { void __iomem *csw_csr; - struct resource *res; unsigned int reg; u32 mcb0routing; u32 mcb1routing; - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - csw_csr = devm_ioremap_resource(&pdev->dev, res); + csw_csr = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(csw_csr)) { dev_err(&pdev->dev, "ioremap failed for CSW CSR resource\n"); return PTR_ERR(csw_csr); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index c6251eac8946..2c419fa5d1c1 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -147,6 +147,7 @@ struct chv_pin_context { * @pctldesc: Pin controller description * @pctldev: Pointer to the pin controller device * @chip: GPIO chip in this pin controller + * @irqchip: IRQ chip in this pin controller * @regs: MMIO registers * @intr_lines: Stores mapping between 16 HW interrupt wires and GPIO * offset (in GPIO number space) @@ -162,6 +163,7 @@ struct chv_pinctrl { struct pinctrl_desc pctldesc; struct pinctrl_dev *pctldev; struct gpio_chip chip; + struct irq_chip irqchip; void __iomem *regs; unsigned intr_lines[16]; const struct chv_community *community; @@ -1466,16 +1468,6 @@ static int chv_gpio_irq_type(struct irq_data *d, unsigned int type) return 0; } -static struct irq_chip chv_gpio_irqchip = { - .name = "chv-gpio", - .irq_startup = chv_gpio_irq_startup, - .irq_ack = chv_gpio_irq_ack, - .irq_mask = chv_gpio_irq_mask, - .irq_unmask = chv_gpio_irq_unmask, - .irq_set_type = chv_gpio_irq_type, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - static void chv_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); @@ -1559,7 +1551,7 @@ static void chv_init_irq_valid_mask(struct gpio_chip *chip, intsel >>= CHV_PADCTRL0_INTSEL_SHIFT; if (intsel >= community->nirqs) - clear_bit(i, valid_mask); + clear_bit(desc->number, valid_mask); } } @@ -1625,7 +1617,15 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) } } - ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0, + pctrl->irqchip.name = "chv-gpio"; + pctrl->irqchip.irq_startup = chv_gpio_irq_startup; + pctrl->irqchip.irq_ack = chv_gpio_irq_ack; + pctrl->irqchip.irq_mask = chv_gpio_irq_mask; + pctrl->irqchip.irq_unmask = chv_gpio_irq_unmask; + pctrl->irqchip.irq_set_type = chv_gpio_irq_type; + pctrl->irqchip.flags = IRQCHIP_SKIP_SET_WAKE; + + ret = gpiochip_irqchip_add(chip, &pctrl->irqchip, 0, handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add IRQ chip\n"); @@ -1642,7 +1642,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) } } - gpiochip_set_chained_irqchip(chip, &chv_gpio_irqchip, irq, + gpiochip_set_chained_irqchip(chip, &pctrl->irqchip, irq, chv_gpio_irq_handler); return 0; } diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index bc013599a9a3..83981ad66a71 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -52,6 +52,7 @@ #define PADCFG0_GPIROUTNMI BIT(17) #define PADCFG0_PMODE_SHIFT 10 #define PADCFG0_PMODE_MASK GENMASK(13, 10) +#define PADCFG0_PMODE_GPIO 0 #define PADCFG0_GPIORXDIS BIT(9) #define PADCFG0_GPIOTXDIS BIT(8) #define PADCFG0_GPIORXSTATE BIT(1) @@ -332,7 +333,7 @@ static void intel_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s, cfg1 = readl(intel_get_padcfg(pctrl, pin, PADCFG1)); mode = (cfg0 & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT; - if (!mode) + if (mode == PADCFG0_PMODE_GPIO) seq_puts(s, "GPIO "); else seq_printf(s, "mode %d ", mode); @@ -458,6 +459,11 @@ static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input) writel(value, padcfg0); } +static int intel_gpio_get_gpio_mode(void __iomem *padcfg0) +{ + return (readl(padcfg0) & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT; +} + static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) { u32 value; @@ -491,7 +497,20 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, } padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0); + + /* + * If pin is already configured in GPIO mode, we assume that + * firmware provides correct settings. In such case we avoid + * potential glitches on the pin. Otherwise, for the pin in + * alternative mode, consumer has to supply respective flags. + */ + if (intel_gpio_get_gpio_mode(padcfg0) == PADCFG0_PMODE_GPIO) { + raw_spin_unlock_irqrestore(&pctrl->lock, flags); + return 0; + } + intel_gpio_set_gpio_mode(padcfg0); + /* Disable TX buffer and enable RX (this will be input) */ __intel_gpio_set_direction(padcfg0, true); diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c index 564660028fcc..ccdf0bb21414 100644 --- a/drivers/pinctrl/pinctrl-stmfx.c +++ b/drivers/pinctrl/pinctrl-stmfx.c @@ -585,19 +585,6 @@ static int stmfx_pinctrl_gpio_function_enable(struct stmfx_pinctrl *pctl) return stmfx_function_enable(pctl->stmfx, func); } -static int stmfx_pinctrl_gpio_init_valid_mask(struct gpio_chip *gc, - unsigned long *valid_mask, - unsigned int ngpios) -{ - struct stmfx_pinctrl *pctl = gpiochip_get_data(gc); - u32 n; - - for_each_clear_bit(n, &pctl->gpio_valid_mask, ngpios) - clear_bit(n, valid_mask); - - return 0; -} - static int stmfx_pinctrl_probe(struct platform_device *pdev) { struct stmfx *stmfx = dev_get_drvdata(pdev->dev.parent); @@ -660,7 +647,6 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) pctl->gpio_chip.ngpio = pctl->pctl_desc.npins; pctl->gpio_chip.can_sleep = true; pctl->gpio_chip.of_node = np; - pctl->gpio_chip.init_valid_mask = stmfx_pinctrl_gpio_init_valid_mask; ret = devm_gpiochip_add_data(pctl->dev, &pctl->gpio_chip, pctl); if (ret) { diff --git a/drivers/platform/mips/Kconfig b/drivers/platform/mips/Kconfig index 62ea1934fb6a..f4d0a86c00d0 100644 --- a/drivers/platform/mips/Kconfig +++ b/drivers/platform/mips/Kconfig @@ -17,8 +17,8 @@ menuconfig MIPS_PLATFORM_DEVICES if MIPS_PLATFORM_DEVICES config CPU_HWMON - tristate "Loongson CPU HWMon Driver" - depends on LOONGSON_MACH3X + tristate "Loongson-3 CPU HWMon Driver" + depends on CONFIG_MACH_LOONGSON64 select HWMON default y help diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c index a7f184bb47e0..0d27cb7a9e3c 100644 --- a/drivers/platform/mips/cpu_hwmon.c +++ b/drivers/platform/mips/cpu_hwmon.c @@ -9,6 +9,9 @@ #include <loongson.h> #include <boot_param.h> #include <loongson_hwmon.h> +#include <loongson_regs.h> + +static int csr_temp_enable = 0; /* * Loongson-3 series cpu has two sensors inside, @@ -20,8 +23,14 @@ int loongson3_cpu_temp(int cpu) { u32 reg, prid_rev; + if (csr_temp_enable) { + reg = (csr_readl(LOONGSON_CSR_CPUTEMP) & 0xff); + goto out; + } + reg = LOONGSON_CHIPTEMP(cpu); prid_rev = read_c0_prid() & PRID_REV_MASK; + switch (prid_rev) { case PRID_REV_LOONGSON3A_R1: reg = (reg >> 8) & 0xff; @@ -34,9 +43,12 @@ int loongson3_cpu_temp(int cpu) break; case PRID_REV_LOONGSON3A_R3_0: case PRID_REV_LOONGSON3A_R3_1: + default: reg = (reg & 0xffff)*731/0x4000 - 273; break; } + +out: return (int)reg * 1000; } @@ -159,9 +171,12 @@ static int __init loongson_hwmon_init(void) pr_info("Loongson Hwmon Enter...\n"); + if (cpu_has_csr()) + csr_temp_enable = csr_readl(LOONGSON_CSR_FEATURES) & LOONGSON_CSRF_TEMP; + cpu_hwmon_dev = hwmon_device_register(NULL); if (IS_ERR(cpu_hwmon_dev)) { - ret = -ENOMEM; + ret = PTR_ERR(cpu_hwmon_dev); pr_err("hwmon_device_register fail!\n"); goto fail_hwmon_device_register; } diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 67d0199840fd..9d72ab593f13 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -149,11 +149,21 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) err = -EFAULT; break; } - if (((req.extts.flags & ~PTP_EXTTS_VALID_FLAGS) || - req.extts.rsv[0] || req.extts.rsv[1]) && - cmd == PTP_EXTTS_REQUEST2) { - err = -EINVAL; - break; + if (cmd == PTP_EXTTS_REQUEST2) { + /* Tell the drivers to check the flags carefully. */ + req.extts.flags |= PTP_STRICT_FLAGS; + /* Make sure no reserved bit is set. */ + if ((req.extts.flags & ~PTP_EXTTS_VALID_FLAGS) || + req.extts.rsv[0] || req.extts.rsv[1]) { + err = -EINVAL; + break; + } + /* Ensure one of the rising/falling edge bits is set. */ + if ((req.extts.flags & PTP_ENABLE_FEATURE) && + (req.extts.flags & PTP_EXTTS_EDGES) == 0) { + err = -EINVAL; + break; + } } else if (cmd == PTP_EXTTS_REQUEST) { req.extts.flags &= PTP_EXTTS_V1_VALID_FLAGS; req.extts.rsv[0] = 0; diff --git a/drivers/pwm/pwm-bcm-iproc.c b/drivers/pwm/pwm-bcm-iproc.c index 56c38cfae92c..1f829edd8ee7 100644 --- a/drivers/pwm/pwm-bcm-iproc.c +++ b/drivers/pwm/pwm-bcm-iproc.c @@ -187,6 +187,7 @@ static int iproc_pwmc_apply(struct pwm_chip *chip, struct pwm_device *pwm, static const struct pwm_ops iproc_pwm_ops = { .apply = iproc_pwmc_apply, .get_state = iproc_pwmc_get_state, + .owner = THIS_MODULE, }; static int iproc_pwmc_probe(struct platform_device *pdev) diff --git a/drivers/reset/core.c b/drivers/reset/core.c index 213ff40dda11..3c9a64c1b7a8 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -76,7 +76,6 @@ static const char *rcdev_name(struct reset_controller_dev *rcdev) * of_reset_simple_xlate - translate reset_spec to the reset line number * @rcdev: a pointer to the reset controller device * @reset_spec: reset line specifier as found in the device tree - * @flags: a flags pointer to fill in (optional) * * This simple translation function should be used for reset controllers * with 1:1 mapping, where reset lines can be indexed by number without gaps. @@ -748,6 +747,7 @@ static void reset_control_array_put(struct reset_control_array *resets) for (i = 0; i < resets->num_rstcs; i++) __reset_control_put_internal(resets->rstc[i]); mutex_unlock(&reset_list_mutex); + kfree(resets); } /** @@ -825,9 +825,10 @@ int __device_reset(struct device *dev, bool optional) } EXPORT_SYMBOL_GPL(__device_reset); -/** +/* * APIs to manage an array of reset controls. */ + /** * of_reset_control_get_count - Count number of resets available with a device * diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 5542d9eadfe0..7d079154f849 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -116,7 +116,9 @@ int dasd_scan_partitions(struct dasd_block *block) return -ENODEV; } - rc = blkdev_reread_part(bdev); + mutex_lock(&bdev->bd_mutex); + rc = bdev_disk_changed(bdev, false); + mutex_unlock(&bdev->bd_mutex); if (rc) DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, rc %d", rc); diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile index f6a8db04177c..23eae4188876 100644 --- a/drivers/s390/cio/Makefile +++ b/drivers/s390/cio/Makefile @@ -5,7 +5,7 @@ # The following is required for define_trace.h to find ./trace.h CFLAGS_trace.o := -I$(src) -CFLAGS_vfio_ccw_fsm.o := -I$(src) +CFLAGS_vfio_ccw_trace.o := -I$(src) obj-y += airq.o blacklist.o chsc.o cio.o css.o chp.o idset.o isc.o \ fcx.o itcw.o crw.o ccwreq.o trace.o ioasm.o @@ -21,5 +21,5 @@ qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o obj-$(CONFIG_QDIO) += qdio.o vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \ - vfio_ccw_async.o + vfio_ccw_async.o vfio_ccw_trace.o obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index a58b45df95d7..64cc14e47e35 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -252,9 +252,6 @@ struct qdio_q { /* input or output queue */ int is_input_q; - /* list of thinint input queues */ - struct list_head entry; - /* upper-layer program handler */ qdio_handler_t (*handler); @@ -272,6 +269,7 @@ struct qdio_irq { struct qib qib; u32 *dsci; /* address of device state change indicator */ struct ccw_device *cdev; + struct list_head entry; /* list of thinint devices */ struct dentry *debugfs_dev; struct dentry *debugfs_perf; @@ -317,13 +315,15 @@ struct qdio_irq { #define qperf(__qdev, __attr) ((__qdev)->perf_stat.(__attr)) -#define qperf_inc(__q, __attr) \ +#define QDIO_PERF_STAT_INC(__irq, __attr) \ ({ \ - struct qdio_irq *qdev = (__q)->irq_ptr; \ + struct qdio_irq *qdev = __irq; \ if (qdev->perf_stat_enabled) \ (qdev->perf_stat.__attr)++; \ }) +#define qperf_inc(__q, __attr) QDIO_PERF_STAT_INC((__q)->irq_ptr, __attr) + static inline void account_sbals_error(struct qdio_q *q, int count) { q->q_stats.nr_sbal_error += count; @@ -355,14 +355,10 @@ static inline int multicast_outbound(struct qdio_q *q) for (i = 0; i < irq_ptr->nr_output_qs && \ ({ q = irq_ptr->output_qs[i]; 1; }); i++) -#define prev_buf(bufnr) \ - ((bufnr + QDIO_MAX_BUFFERS_MASK) & QDIO_MAX_BUFFERS_MASK) -#define next_buf(bufnr) \ - ((bufnr + 1) & QDIO_MAX_BUFFERS_MASK) -#define add_buf(bufnr, inc) \ - ((bufnr + inc) & QDIO_MAX_BUFFERS_MASK) -#define sub_buf(bufnr, dec) \ - ((bufnr - dec) & QDIO_MAX_BUFFERS_MASK) +#define add_buf(bufnr, inc) QDIO_BUFNR((bufnr) + (inc)) +#define next_buf(bufnr) add_buf(bufnr, 1) +#define sub_buf(bufnr, dec) QDIO_BUFNR((bufnr) - (dec)) +#define prev_buf(bufnr) sub_buf(bufnr, 1) #define queue_irqs_enabled(q) \ (test_bit(QDIO_QUEUE_IRQS_DISABLED, &q->u.in.queue_irq_state) == 0) @@ -375,8 +371,8 @@ extern u64 last_ai_time; void qdio_setup_thinint(struct qdio_irq *irq_ptr); int qdio_establish_thinint(struct qdio_irq *irq_ptr); void qdio_shutdown_thinint(struct qdio_irq *irq_ptr); -void tiqdio_add_input_queues(struct qdio_irq *irq_ptr); -void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr); +void tiqdio_add_device(struct qdio_irq *irq_ptr); +void tiqdio_remove_device(struct qdio_irq *irq_ptr); void tiqdio_inbound_processing(unsigned long q); int tiqdio_allocate_memory(void); void tiqdio_free_memory(void); diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 5b63c505a2f7..2b797cbb9d57 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -131,7 +131,7 @@ again: case 96: /* not all buffers processed */ qperf_inc(q, eqbs_partial); - DBF_DEV_EVENT(DBF_WARN, q->irq_ptr, "EQBS part:%02x", + DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "EQBS part:%02x", tmp_count); return count - tmp_count; case 97: @@ -423,9 +423,6 @@ static inline void account_sbals(struct qdio_q *q, unsigned int count) static void process_buffer_error(struct qdio_q *q, unsigned int start, int count) { - unsigned char state = (q->is_input_q) ? SLSB_P_INPUT_NOT_INIT : - SLSB_P_OUTPUT_NOT_INIT; - q->qdio_error = QDIO_ERROR_SLSB_STATE; /* special handling for no target buffer empty */ @@ -433,7 +430,7 @@ static void process_buffer_error(struct qdio_q *q, unsigned int start, q->sbal[start]->element[15].sflags == 0x10) { qperf_inc(q, target_full); DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x", start); - goto set; + return; } DBF_ERROR("%4x BUF ERROR", SCH_NO(q)); @@ -442,13 +439,6 @@ static void process_buffer_error(struct qdio_q *q, unsigned int start, DBF_ERROR("F14:%2x F15:%2x", q->sbal[start]->element[14].sflags, q->sbal[start]->element[15].sflags); - -set: - /* - * Interrupts may be avoided as long as the error is present - * so change the buffer state immediately to avoid starvation. - */ - set_buf_states(q, start, state, count); } static inline void inbound_primed(struct qdio_q *q, unsigned int start, @@ -530,6 +520,11 @@ static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start) return count; case SLSB_P_INPUT_ERROR: process_buffer_error(q, start, count); + /* + * Interrupts may be avoided as long as the error is present + * so change the buffer state immediately to avoid starvation. + */ + set_buf_states(q, start, SLSB_P_INPUT_NOT_INIT, count); if (atomic_sub_return(count, &q->nr_buf_used) == 0) qperf_inc(q, inbound_queue_full); if (q->irq_ptr->perf_stat_enabled) @@ -963,7 +958,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr) /* skip if polling is enabled or already in work */ if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED, &q->u.in.queue_irq_state)) { - qperf_inc(q, int_discarded); + QDIO_PERF_STAT_INC(irq_ptr, int_discarded); continue; } q->u.in.queue_start_poll(q->irq_ptr->cdev, q->nr, @@ -1162,7 +1157,7 @@ int qdio_shutdown(struct ccw_device *cdev, int how) */ qdio_set_state(irq_ptr, QDIO_IRQ_STATE_STOPPED); - tiqdio_remove_input_queues(irq_ptr); + tiqdio_remove_device(irq_ptr); qdio_shutdown_queues(cdev); qdio_shutdown_debug_entries(irq_ptr); @@ -1284,6 +1279,7 @@ int qdio_allocate(struct qdio_initialize *init_data) init_data->no_output_qs)) goto out_rel; + INIT_LIST_HEAD(&irq_ptr->entry); init_data->cdev->private->qdio_data = irq_ptr; qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE); return 0; @@ -1428,7 +1424,7 @@ int qdio_activate(struct ccw_device *cdev) } if (is_thinint_irq(irq_ptr)) - tiqdio_add_input_queues(irq_ptr); + tiqdio_add_device(irq_ptr); /* wait for subchannel to become active */ msleep(5); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index cd164886132f..dc430bd86ade 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -150,7 +150,6 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues) return -ENOMEM; } irq_ptr_qs[i] = q; - INIT_LIST_HEAD(&q->entry); } return 0; } @@ -179,7 +178,6 @@ static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr, q->mask = 1 << (31 - i); q->nr = i; q->handler = handler; - INIT_LIST_HEAD(&q->entry); } static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr, diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c index 93ee067c10ca..7c4e4ec08a12 100644 --- a/drivers/s390/cio/qdio_thinint.c +++ b/drivers/s390/cio/qdio_thinint.c @@ -39,14 +39,6 @@ struct indicator_t { static LIST_HEAD(tiq_list); static DEFINE_MUTEX(tiq_list_lock); -/* Adapter interrupt definitions */ -static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating); - -static struct airq_struct tiqdio_airq = { - .handler = tiqdio_thinint_handler, - .isc = QDIO_AIRQ_ISC, -}; - static struct indicator_t *q_indicators; u64 last_ai_time; @@ -74,26 +66,20 @@ static void put_indicator(u32 *addr) atomic_dec(&ind->count); } -void tiqdio_add_input_queues(struct qdio_irq *irq_ptr) +void tiqdio_add_device(struct qdio_irq *irq_ptr) { mutex_lock(&tiq_list_lock); - list_add_rcu(&irq_ptr->input_qs[0]->entry, &tiq_list); + list_add_rcu(&irq_ptr->entry, &tiq_list); mutex_unlock(&tiq_list_lock); } -void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr) +void tiqdio_remove_device(struct qdio_irq *irq_ptr) { - struct qdio_q *q; - - q = irq_ptr->input_qs[0]; - if (!q) - return; - mutex_lock(&tiq_list_lock); - list_del_rcu(&q->entry); + list_del_rcu(&irq_ptr->entry); mutex_unlock(&tiq_list_lock); synchronize_rcu(); - INIT_LIST_HEAD(&q->entry); + INIT_LIST_HEAD(&irq_ptr->entry); } static inline int has_multiple_inq_on_dsci(struct qdio_irq *irq_ptr) @@ -154,7 +140,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq) /* skip if polling is enabled or already in work */ if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED, &q->u.in.queue_irq_state)) { - qperf_inc(q, int_discarded); + QDIO_PERF_STAT_INC(irq, int_discarded); continue; } @@ -182,7 +168,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq) static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating) { u32 si_used = clear_shared_ind(); - struct qdio_q *q; + struct qdio_irq *irq; last_ai_time = S390_lowcore.int_clock; inc_irq_stat(IRQIO_QAI); @@ -190,12 +176,8 @@ static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating) /* protect tiq_list entries, only changed in activate or shutdown */ rcu_read_lock(); - /* check for work on all inbound thinint queues */ - list_for_each_entry_rcu(q, &tiq_list, entry) { - struct qdio_irq *irq; - + list_for_each_entry_rcu(irq, &tiq_list, entry) { /* only process queues from changed sets */ - irq = q->irq_ptr; if (unlikely(references_shared_dsci(irq))) { if (!si_used) continue; @@ -204,11 +186,16 @@ static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating) tiqdio_call_inq_handlers(irq); - qperf_inc(q, adapter_int); + QDIO_PERF_STAT_INC(irq, adapter_int); } rcu_read_unlock(); } +static struct airq_struct tiqdio_airq = { + .handler = tiqdio_thinint_handler, + .isc = QDIO_AIRQ_ISC, +}; + static int set_subchannel_ind(struct qdio_irq *irq_ptr, int reset) { struct chsc_scssc_area *scssc = (void *)irq_ptr->chsc_page; diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h index 7cdc38049033..ba31240ce965 100644 --- a/drivers/s390/cio/vfio_ccw_cp.h +++ b/drivers/s390/cio/vfio_ccw_cp.h @@ -15,6 +15,7 @@ #include <asm/scsw.h> #include "orb.h" +#include "vfio_ccw_trace.h" /* * Max length for ccw chain. diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index 4a1e727c62d9..23e61aa638e4 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -15,9 +15,6 @@ #include "ioasm.h" #include "vfio_ccw_private.h" -#define CREATE_TRACE_POINTS -#include "vfio_ccw_trace.h" - static int fsm_io_helper(struct vfio_ccw_private *private) { struct subchannel *sch; @@ -321,8 +318,8 @@ static void fsm_io_request(struct vfio_ccw_private *private, } err_out: - trace_vfio_ccw_io_fctl(scsw->cmd.fctl, schid, - io_region->ret_code, errstr); + trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid, + io_region->ret_code, errstr); } /* @@ -344,6 +341,10 @@ static void fsm_async_request(struct vfio_ccw_private *private, /* should not happen? */ cmd_region->ret_code = -EINVAL; } + + trace_vfio_ccw_fsm_async_request(get_schid(private), + cmd_region->command, + cmd_region->ret_code); } /* diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index bbe9babf767b..9b9bb4982972 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -135,6 +135,7 @@ extern fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS]; static inline void vfio_ccw_fsm_event(struct vfio_ccw_private *private, int event) { + trace_vfio_ccw_fsm_event(private->sch->schid, private->state, event); vfio_ccw_jumptable[private->state][event](private, event); } diff --git a/drivers/s390/cio/vfio_ccw_trace.c b/drivers/s390/cio/vfio_ccw_trace.c new file mode 100644 index 000000000000..8c671d2519f6 --- /dev/null +++ b/drivers/s390/cio/vfio_ccw_trace.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tracepoint definitions for vfio_ccw + * + * Copyright IBM Corp. 2019 + * Author(s): Eric Farman <farman@linux.ibm.com> + */ + +#define CREATE_TRACE_POINTS +#include "vfio_ccw_trace.h" + +EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_async_request); +EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_event); +EXPORT_TRACEPOINT_SYMBOL(vfio_ccw_fsm_io_request); diff --git a/drivers/s390/cio/vfio_ccw_trace.h b/drivers/s390/cio/vfio_ccw_trace.h index b1da53ddec1f..30162a318a8a 100644 --- a/drivers/s390/cio/vfio_ccw_trace.h +++ b/drivers/s390/cio/vfio_ccw_trace.h @@ -7,6 +7,8 @@ * Halil Pasic <pasic@linux.vnet.ibm.com> */ +#include "cio.h" + #undef TRACE_SYSTEM #define TRACE_SYSTEM vfio_ccw @@ -15,28 +17,88 @@ #include <linux/tracepoint.h> -TRACE_EVENT(vfio_ccw_io_fctl, +TRACE_EVENT(vfio_ccw_fsm_async_request, + TP_PROTO(struct subchannel_id schid, + int command, + int errno), + TP_ARGS(schid, command, errno), + + TP_STRUCT__entry( + __field(u8, cssid) + __field(u8, ssid) + __field(u16, sch_no) + __field(int, command) + __field(int, errno) + ), + + TP_fast_assign( + __entry->cssid = schid.cssid; + __entry->ssid = schid.ssid; + __entry->sch_no = schid.sch_no; + __entry->command = command; + __entry->errno = errno; + ), + + TP_printk("schid=%x.%x.%04x command=0x%x errno=%d", + __entry->cssid, + __entry->ssid, + __entry->sch_no, + __entry->command, + __entry->errno) +); + +TRACE_EVENT(vfio_ccw_fsm_event, + TP_PROTO(struct subchannel_id schid, int state, int event), + TP_ARGS(schid, state, event), + + TP_STRUCT__entry( + __field(u8, cssid) + __field(u8, ssid) + __field(u16, schno) + __field(int, state) + __field(int, event) + ), + + TP_fast_assign( + __entry->cssid = schid.cssid; + __entry->ssid = schid.ssid; + __entry->schno = schid.sch_no; + __entry->state = state; + __entry->event = event; + ), + + TP_printk("schid=%x.%x.%04x state=%d event=%d", + __entry->cssid, __entry->ssid, __entry->schno, + __entry->state, + __entry->event) +); + +TRACE_EVENT(vfio_ccw_fsm_io_request, TP_PROTO(int fctl, struct subchannel_id schid, int errno, char *errstr), TP_ARGS(fctl, schid, errno, errstr), TP_STRUCT__entry( + __field(u8, cssid) + __field(u8, ssid) + __field(u16, sch_no) __field(int, fctl) - __field_struct(struct subchannel_id, schid) __field(int, errno) __field(char*, errstr) ), TP_fast_assign( + __entry->cssid = schid.cssid; + __entry->ssid = schid.ssid; + __entry->sch_no = schid.sch_no; __entry->fctl = fctl; - __entry->schid = schid; __entry->errno = errno; __entry->errstr = errstr; ), - TP_printk("schid=%x.%x.%04x fctl=%x errno=%d info=%s", - __entry->schid.cssid, - __entry->schid.ssid, - __entry->schid.sch_no, + TP_printk("schid=%x.%x.%04x fctl=0x%x errno=%d info=%s", + __entry->cssid, + __entry->ssid, + __entry->sch_no, __entry->fctl, __entry->errno, __entry->errstr) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 9de3d46b3253..d78d77686d7b 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -715,36 +715,18 @@ out: static void *_copy_key_from_user(void __user *ukey, size_t keylen) { - void *kkey; - if (!ukey || keylen < MINKEYBLOBSIZE || keylen > KEYBLOBBUFSIZE) return ERR_PTR(-EINVAL); - kkey = kmalloc(keylen, GFP_KERNEL); - if (!kkey) - return ERR_PTR(-ENOMEM); - if (copy_from_user(kkey, ukey, keylen)) { - kfree(kkey); - return ERR_PTR(-EFAULT); - } - return kkey; + return memdup_user(ukey, keylen); } static void *_copy_apqns_from_user(void __user *uapqns, size_t nr_apqns) { - void *kapqns = NULL; - size_t nbytes; - - if (uapqns && nr_apqns > 0) { - nbytes = nr_apqns * sizeof(struct pkey_apqn); - kapqns = kmalloc(nbytes, GFP_KERNEL); - if (!kapqns) - return ERR_PTR(-ENOMEM); - if (copy_from_user(kapqns, uapqns, nbytes)) - return ERR_PTR(-EFAULT); - } + if (!uapqns || nr_apqns == 0) + return NULL; - return kapqns; + return memdup_user(uapqns, nr_apqns * sizeof(struct pkey_apqn)); } static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index e4b55f9aa062..65e31df37b1f 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -839,6 +839,7 @@ struct qeth_card { struct service_level qeth_service_level; struct qdio_ssqd_desc ssqd; debug_info_t *debug; + struct mutex sbp_lock; struct mutex conf_mutex; struct mutex discipline_mutex; struct napi_struct napi; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index dda274351c21..83794d7494d4 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -901,30 +901,30 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev, CCW_DEVID(cdev), dstat, cstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 64, 1); - return 1; + return -EIO; } if (dstat & DEV_STAT_UNIT_CHECK) { if (sense[SENSE_RESETTING_EVENT_BYTE] & SENSE_RESETTING_EVENT_FLAG) { QETH_CARD_TEXT(card, 2, "REVIND"); - return 1; + return -EIO; } if (sense[SENSE_COMMAND_REJECT_BYTE] & SENSE_COMMAND_REJECT_FLAG) { QETH_CARD_TEXT(card, 2, "CMDREJi"); - return 1; + return -EIO; } if ((sense[2] == 0xaf) && (sense[3] == 0xfe)) { QETH_CARD_TEXT(card, 2, "AFFE"); - return 1; + return -EIO; } if ((!sense[0]) && (!sense[1]) && (!sense[2]) && (!sense[3])) { QETH_CARD_TEXT(card, 2, "ZEROSEN"); return 0; } QETH_CARD_TEXT(card, 2, "DGENCHK"); - return 1; + return -EIO; } return 0; } diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index bd8143e51747..4bccdce19b5a 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -467,10 +467,14 @@ static void qeth_l2_set_promisc_mode(struct qeth_card *card) if (card->info.promisc_mode == enable) return; - if (qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE)) + if (qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE)) { qeth_setadp_promisc_mode(card, enable); - else if (card->options.sbp.reflect_promisc) - qeth_l2_promisc_to_bridge(card, enable); + } else { + mutex_lock(&card->sbp_lock); + if (card->options.sbp.reflect_promisc) + qeth_l2_promisc_to_bridge(card, enable); + mutex_unlock(&card->sbp_lock); + } } /* New MAC address is added to the hash table and marked to be written on card @@ -631,6 +635,7 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev) int rc; qeth_l2_vnicc_set_defaults(card); + mutex_init(&card->sbp_lock); if (gdev->dev.type == &qeth_generic_devtype) { rc = qeth_l2_create_device_attributes(&gdev->dev); @@ -804,10 +809,12 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev) } else card->info.hwtrap = 0; + mutex_lock(&card->sbp_lock); qeth_bridgeport_query_support(card); if (card->options.sbp.supported_funcs) dev_info(&card->gdev->dev, "The device represents a Bridge Capable Port\n"); + mutex_unlock(&card->sbp_lock); qeth_l2_register_dev_addr(card); @@ -1162,9 +1169,9 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) /* Role should not change by itself, but if it did, */ /* information from the hardware is authoritative. */ - mutex_lock(&data->card->conf_mutex); + mutex_lock(&data->card->sbp_lock); data->card->options.sbp.role = entry->role; - mutex_unlock(&data->card->conf_mutex); + mutex_unlock(&data->card->sbp_lock); snprintf(env_locrem, sizeof(env_locrem), "BRIDGEPORT=statechange"); snprintf(env_role, sizeof(env_role), "ROLE=%s", @@ -1230,9 +1237,9 @@ static void qeth_bridge_host_event_worker(struct work_struct *work) : (data->hostevs.lost_event_mask == 0x02) ? "Bridge port state change" : "Unknown reason"); - mutex_lock(&data->card->conf_mutex); + mutex_lock(&data->card->sbp_lock); data->card->options.sbp.hostnotification = 0; - mutex_unlock(&data->card->conf_mutex); + mutex_unlock(&data->card->sbp_lock); qeth_bridge_emit_host_event(data->card, anev_abort, 0, NULL, NULL); } else diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index f2c3b127b1e4..e2bcb26105a3 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -24,6 +24,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, if (qeth_l2_vnicc_is_in_use(card)) return sprintf(buf, "n/a (VNIC characteristics)\n"); + mutex_lock(&card->sbp_lock); if (qeth_card_hw_is_reachable(card) && card->options.sbp.supported_funcs) rc = qeth_bridgeport_query_ports(card, @@ -57,6 +58,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, else rc = sprintf(buf, "%s\n", word); } + mutex_unlock(&card->sbp_lock); return rc; } @@ -91,6 +93,7 @@ static ssize_t qeth_bridge_port_role_store(struct device *dev, return -EINVAL; mutex_lock(&card->conf_mutex); + mutex_lock(&card->sbp_lock); if (qeth_l2_vnicc_is_in_use(card)) rc = -EBUSY; @@ -104,6 +107,7 @@ static ssize_t qeth_bridge_port_role_store(struct device *dev, } else card->options.sbp.role = role; + mutex_unlock(&card->sbp_lock); mutex_unlock(&card->conf_mutex); return rc ? rc : count; @@ -158,6 +162,7 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, return rc; mutex_lock(&card->conf_mutex); + mutex_lock(&card->sbp_lock); if (qeth_l2_vnicc_is_in_use(card)) rc = -EBUSY; @@ -168,6 +173,7 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, } else card->options.sbp.hostnotification = enable; + mutex_unlock(&card->sbp_lock); mutex_unlock(&card->conf_mutex); return rc ? rc : count; @@ -223,6 +229,7 @@ static ssize_t qeth_bridgeport_reflect_store(struct device *dev, return -EINVAL; mutex_lock(&card->conf_mutex); + mutex_lock(&card->sbp_lock); if (qeth_l2_vnicc_is_in_use(card)) rc = -EBUSY; @@ -234,6 +241,7 @@ static ssize_t qeth_bridgeport_reflect_store(struct device *dev, rc = 0; } + mutex_unlock(&card->sbp_lock); mutex_unlock(&card->conf_mutex); return rc ? rc : count; @@ -269,6 +277,8 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) return; if (!card->options.sbp.supported_funcs) return; + + mutex_lock(&card->sbp_lock); if (card->options.sbp.role != QETH_SBP_ROLE_NONE) { /* Conditional to avoid spurious error messages */ qeth_bridgeport_setrole(card, card->options.sbp.role); @@ -280,8 +290,10 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) rc = qeth_bridgeport_an_set(card, 1); if (rc) card->options.sbp.hostnotification = 0; - } else + } else { qeth_bridgeport_an_set(card, 0); + } + mutex_unlock(&card->sbp_lock); } /* VNIC CHARS support */ diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h index 87659cfc9066..2b9302cd0117 100644 --- a/drivers/s390/net/qeth_l3.h +++ b/drivers/s390/net/qeth_l3.h @@ -13,8 +13,6 @@ #include "qeth_core.h" #include <linux/hashtable.h> -#define QETH_SNIFF_AVAIL 0x0008 - enum qeth_ip_types { QETH_IP_TYPE_NORMAL, QETH_IP_TYPE_VIPA, diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index 2f73b33c9347..c6204520114e 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -228,7 +228,7 @@ static ssize_t qeth_l3_dev_sniffer_store(struct device *dev, break; case 1: qdio_get_ssqd_desc(CARD_DDEV(card), &card->ssqd); - if (card->ssqd.qdioac2 & QETH_SNIFF_AVAIL) { + if (card->ssqd.qdioac2 & CHSC_AC2_SNIFFER_AVAILABLE) { card->options.sniffer = i; if (card->qdio.init_pool.buf_count != QETH_IN_BUF_COUNT_MAX) diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index 6afad68e5ba2..238240984bc1 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -76,9 +76,11 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha) * ensures no active vp_list traversal while the vport is removed * from the queue) */ - for (i = 0; i < 10 && atomic_read(&vha->vref_count); i++) - wait_event_timeout(vha->vref_waitq, - atomic_read(&vha->vref_count), HZ); + for (i = 0; i < 10; i++) { + if (wait_event_timeout(vha->vref_waitq, + !atomic_read(&vha->vref_count), HZ) > 0) + break; + } spin_lock_irqsave(&ha->vport_slock, flags); if (atomic_read(&vha->vref_count)) { diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 337162ac3a77..726ad4cbf4a6 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1119,9 +1119,11 @@ qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) qla2x00_mark_all_devices_lost(vha, 0); - for (i = 0; i < 10; i++) - wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), - HZ); + for (i = 0; i < 10; i++) { + if (wait_event_timeout(vha->fcport_waitQ, + test_fcport_count(vha), HZ) > 0) + break; + } flush_workqueue(vha->hw->wq); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 5447738906ac..91c007d26c1e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1883,7 +1883,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost) { unsigned int cmd_size, sgl_size; - sgl_size = scsi_mq_inline_sgl_size(shost); + sgl_size = max_t(unsigned int, sizeof(struct scatterlist), + scsi_mq_inline_sgl_size(shost)); cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size; if (scsi_host_get_prot(shost)) cmd_size += sizeof(struct scsi_data_buffer) + diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index ebb40160539f..470ee6dc3f7e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1291,9 +1291,17 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd) case REQ_OP_WRITE: return sd_setup_read_write_cmnd(cmd); case REQ_OP_ZONE_RESET: - return sd_zbc_setup_reset_cmnd(cmd, false); + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, + false); case REQ_OP_ZONE_RESET_ALL: - return sd_zbc_setup_reset_cmnd(cmd, true); + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, + true); + case REQ_OP_ZONE_OPEN: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_OPEN_ZONE, false); + case REQ_OP_ZONE_CLOSE: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_CLOSE_ZONE, false); + case REQ_OP_ZONE_FINISH: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_FINISH_ZONE, false); default: WARN_ON_ONCE(1); return BLK_STS_NOTSUPP; @@ -1961,6 +1969,9 @@ static int sd_done(struct scsi_cmnd *SCpnt) case REQ_OP_WRITE_SAME: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: if (!result) { good_bytes = blk_rq_bytes(req); scsi_set_resid(SCpnt, 0); diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 1eab779f812b..42fd3f00e4a5 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -209,11 +209,12 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp) extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); extern void sd_zbc_print_zones(struct scsi_disk *sdkp); -extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all); +blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, + unsigned char op, bool all); extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); -extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); +int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); #else /* CONFIG_BLK_DEV_ZONED */ @@ -225,8 +226,9 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {} -static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, - bool all) +static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, + unsigned char op, + bool all) { return BLK_STS_TARGET; } diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index de4019dc0f0b..0e5ede48f045 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -19,34 +19,27 @@ #include "sd.h" -/** - * sd_zbc_parse_report - Convert a zone descriptor to a struct blk_zone, - * @sdkp: The disk the report originated from - * @buf: Address of the report zone descriptor - * @zone: the destination zone structure - * - * All LBA sized values are converted to 512B sectors unit. - */ -static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, - struct blk_zone *zone) +static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, + unsigned int idx, report_zones_cb cb, void *data) { struct scsi_device *sdp = sdkp->device; + struct blk_zone zone = { 0 }; - memset(zone, 0, sizeof(struct blk_zone)); - - zone->type = buf[0] & 0x0f; - zone->cond = (buf[1] >> 4) & 0xf; + zone.type = buf[0] & 0x0f; + zone.cond = (buf[1] >> 4) & 0xf; if (buf[1] & 0x01) - zone->reset = 1; + zone.reset = 1; if (buf[1] & 0x02) - zone->non_seq = 1; - - zone->len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8])); - zone->start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16])); - zone->wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24])); - if (zone->type != ZBC_ZONE_TYPE_CONV && - zone->cond == ZBC_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; + zone.non_seq = 1; + + zone.len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8])); + zone.start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16])); + zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24])); + if (zone.type != ZBC_ZONE_TYPE_CONV && + zone.cond == ZBC_ZONE_COND_FULL) + zone.wp = zone.start + zone.len; + + return cb(&zone, idx, data); } /** @@ -104,11 +97,6 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf, return 0; } -/* - * Maximum number of zones to get with one report zones command. - */ -#define SD_ZBC_REPORT_MAX_ZONES 8192U - /** * Allocate a buffer for report zones reply. * @sdkp: The target disk @@ -138,82 +126,94 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, * sure that the allocated buffer can always be mapped by limiting the * number of pages allocated to the HBA max segments limit. */ - nr_zones = min(nr_zones, SD_ZBC_REPORT_MAX_ZONES); - bufsize = roundup((nr_zones + 1) * 64, 512); + nr_zones = min(nr_zones, sdkp->nr_zones); + bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE); bufsize = min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT); bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT); - buf = vzalloc(bufsize); - if (buf) - *buflen = bufsize; + while (bufsize >= SECTOR_SIZE) { + buf = __vmalloc(bufsize, + GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY, + PAGE_KERNEL); + if (buf) { + *buflen = bufsize; + return buf; + } + bufsize >>= 1; + } - return buf; + return NULL; } /** - * sd_zbc_report_zones - Disk report zones operation. - * @disk: The target disk - * @sector: Start 512B sector of the report - * @zones: Array of zone descriptors - * @nr_zones: Number of descriptors in the array - * - * Execute a report zones command on the target disk. + * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors. + * @sdkp: The target disk */ +static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp) +{ + return logical_to_sectors(sdkp->device, sdkp->zone_blocks); +} + int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { struct scsi_disk *sdkp = scsi_disk(disk); - unsigned int i, nrz = *nr_zones; + unsigned int nr, i; unsigned char *buf; - size_t buflen = 0, offset = 0; - int ret = 0; + size_t offset, buflen = 0; + int zone_idx = 0; + int ret; if (!sd_is_zoned(sdkp)) /* Not a zoned device */ return -EOPNOTSUPP; - buf = sd_zbc_alloc_report_buffer(sdkp, nrz, &buflen); + buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen); if (!buf) return -ENOMEM; - ret = sd_zbc_do_report_zones(sdkp, buf, buflen, - sectors_to_logical(sdkp->device, sector), true); - if (ret) - goto out; + while (zone_idx < nr_zones && sector < get_capacity(disk)) { + ret = sd_zbc_do_report_zones(sdkp, buf, buflen, + sectors_to_logical(sdkp->device, sector), true); + if (ret) + goto out; + + offset = 0; + nr = min(nr_zones, get_unaligned_be32(&buf[0]) / 64); + if (!nr) + break; + + for (i = 0; i < nr && zone_idx < nr_zones; i++) { + offset += 64; + ret = sd_zbc_parse_report(sdkp, buf + offset, zone_idx, + cb, data); + if (ret) + goto out; + zone_idx++; + } - nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64); - for (i = 0; i < nrz; i++) { - offset += 64; - sd_zbc_parse_report(sdkp, buf + offset, zones); - zones++; + sector += sd_zbc_zone_sectors(sdkp) * i; } - *nr_zones = nrz; - + ret = zone_idx; out: kvfree(buf); - return ret; } /** - * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors. - * @sdkp: The target disk - */ -static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp) -{ - return logical_to_sectors(sdkp->device, sdkp->zone_blocks); -} - -/** - * sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command. + * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations + * can be RESET WRITE POINTER, OPEN, CLOSE or FINISH. * @cmd: the command to setup - * @all: Reset all zones control. + * @op: Operation to be performed + * @all: All zones control * - * Called from sd_init_command() for a REQ_OP_ZONE_RESET request. + * Called from sd_init_command() for REQ_OP_ZONE_RESET, REQ_OP_ZONE_RESET_ALL, + * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE or REQ_OP_ZONE_FINISH requests. */ -blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all) +blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, + unsigned char op, bool all) { struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); @@ -234,7 +234,7 @@ blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all) cmd->cmd_len = 16; memset(cmd->cmnd, 0, cmd->cmd_len); cmd->cmnd[0] = ZBC_OUT; - cmd->cmnd[1] = ZO_RESET_WRITE_POINTER; + cmd->cmnd[1] = op; if (all) cmd->cmnd[14] = 0x1; else @@ -263,25 +263,16 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, int result = cmd->result; struct request *rq = cmd->request; - switch (req_op(rq)) { - case REQ_OP_ZONE_RESET: - case REQ_OP_ZONE_RESET_ALL: - - if (result && - sshdr->sense_key == ILLEGAL_REQUEST && - sshdr->asc == 0x24) - /* - * INVALID FIELD IN CDB error: reset of a conventional - * zone was attempted. Nothing to worry about, so be - * quiet about the error. - */ - rq->rq_flags |= RQF_QUIET; - break; - - case REQ_OP_WRITE: - case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE_SAME: - break; + if (op_is_zone_mgmt(req_op(rq)) && + result && + sshdr->sense_key == ILLEGAL_REQUEST && + sshdr->asc == 0x24) { + /* + * INVALID FIELD IN CDB error: a zone management command was + * attempted on a conventional zone. Nothing to worry about, + * so be quiet about the error. + */ + rq->rq_flags |= RQF_QUIET; } } @@ -344,32 +335,18 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp, * Returns the zone size in number of blocks upon success or an error code * upon failure. */ -static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks) +static int sd_zbc_check_zones(struct scsi_disk *sdkp, unsigned char *buf, + u32 *zblocks) { - size_t bufsize, buflen; - unsigned int noio_flag; u64 zone_blocks = 0; - sector_t max_lba, block = 0; - unsigned char *buf; + sector_t max_lba; unsigned char *rec; int ret; - u8 same; - - /* Do all memory allocations as if GFP_NOIO was specified */ - noio_flag = memalloc_noio_save(); - - /* Get a buffer */ - buf = sd_zbc_alloc_report_buffer(sdkp, SD_ZBC_REPORT_MAX_ZONES, - &bufsize); - if (!buf) { - ret = -ENOMEM; - goto out; - } - /* Do a report zone to get max_lba and the same field */ - ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, 0, false); + /* Do a report zone to get max_lba and the size of the first zone */ + ret = sd_zbc_do_report_zones(sdkp, buf, SD_BUF_SIZE, 0, false); if (ret) - goto out_free; + return ret; if (sdkp->rc_basis == 0) { /* The max_lba field is the capacity of this device */ @@ -384,82 +361,27 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks) } } - /* - * Check same field: for any value other than 0, we know that all zones - * have the same size. - */ - same = buf[4] & 0x0f; - if (same > 0) { - rec = &buf[64]; - zone_blocks = get_unaligned_be64(&rec[8]); - goto out; - } - - /* - * Check the size of all zones: all zones must be of - * equal size, except the last zone which can be smaller - * than other zones. - */ - do { - - /* Parse REPORT ZONES header */ - buflen = min_t(size_t, get_unaligned_be32(&buf[0]) + 64, - bufsize); - rec = buf + 64; - - /* Parse zone descriptors */ - while (rec < buf + buflen) { - u64 this_zone_blocks = get_unaligned_be64(&rec[8]); - - if (zone_blocks == 0) { - zone_blocks = this_zone_blocks; - } else if (this_zone_blocks != zone_blocks && - (block + this_zone_blocks < sdkp->capacity - || this_zone_blocks > zone_blocks)) { - zone_blocks = 0; - goto out; - } - block += this_zone_blocks; - rec += 64; - } - - if (block < sdkp->capacity) { - ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, block, - true); - if (ret) - goto out_free; - } - - } while (block < sdkp->capacity); - -out: - if (!zone_blocks) { - if (sdkp->first_scan) - sd_printk(KERN_NOTICE, sdkp, - "Devices with non constant zone " - "size are not supported\n"); - ret = -ENODEV; - } else if (!is_power_of_2(zone_blocks)) { + /* Parse REPORT ZONES header */ + rec = buf + 64; + zone_blocks = get_unaligned_be64(&rec[8]); + if (!zone_blocks || !is_power_of_2(zone_blocks)) { if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Devices with non power of 2 zone " "size are not supported\n"); - ret = -ENODEV; - } else if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) { + return -ENODEV; + } + + if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) { if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Zone size too large\n"); - ret = -EFBIG; - } else { - *zblocks = zone_blocks; - ret = 0; + return -EFBIG; } -out_free: - memalloc_noio_restore(noio_flag); - kvfree(buf); + *zblocks = zone_blocks; - return ret; + return 0; } int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) @@ -485,7 +407,7 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) * Check zone size: only devices with a constant zone size (except * an eventual last runt zone) that is a power of 2 are supported. */ - ret = sd_zbc_check_zones(sdkp, &zone_blocks); + ret = sd_zbc_check_zones(sdkp, buf, &zone_blocks); if (ret != 0) goto err; diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index d9231bd3c691..98b9d9a902ae 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -249,13 +249,13 @@ static struct genpd_power_state imx6_pm_domain_pu_state = { }; static struct imx_pm_domain imx_gpc_domains[] = { - [GPC_PGC_DOMAIN_ARM] { + [GPC_PGC_DOMAIN_ARM] = { .base = { .name = "ARM", .flags = GENPD_FLAG_ALWAYS_ON, }, }, - [GPC_PGC_DOMAIN_PU] { + [GPC_PGC_DOMAIN_PU] = { .base = { .name = "PU", .power_off = imx6_pm_domain_power_off, @@ -266,7 +266,7 @@ static struct imx_pm_domain imx_gpc_domains[] = { .reg_offs = 0x260, .cntr_pdn_bit = 0, }, - [GPC_PGC_DOMAIN_DISPLAY] { + [GPC_PGC_DOMAIN_DISPLAY] = { .base = { .name = "DISPLAY", .power_off = imx6_pm_domain_power_off, @@ -275,7 +275,7 @@ static struct imx_pm_domain imx_gpc_domains[] = { .reg_offs = 0x240, .cntr_pdn_bit = 4, }, - [GPC_PGC_DOMAIN_PCI] { + [GPC_PGC_DOMAIN_PCI] = { .base = { .name = "PCI", .power_off = imx6_pm_domain_power_off, diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig index f518273cfbe3..c8c80df090d1 100644 --- a/drivers/soundwire/Kconfig +++ b/drivers/soundwire/Kconfig @@ -5,6 +5,7 @@ menuconfig SOUNDWIRE tristate "SoundWire support" + depends on ACPI || OF help SoundWire is a 2-Pin interface with data and clock line ratified by the MIPI Alliance. SoundWire is used for transporting data diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index f1e38a293967..13c54eac0cc3 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -900,7 +900,7 @@ static int intel_register_dai(struct sdw_intel *sdw) /* Create PCM DAIs */ stream = &cdns->pcm; - ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, stream->num_in, + ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, cdns->pcm.num_in, off, stream->num_ch_in, true); if (ret) return ret; @@ -931,7 +931,7 @@ static int intel_register_dai(struct sdw_intel *sdw) if (ret) return ret; - off += cdns->pdm.num_bd; + off += cdns->pdm.num_out; ret = intel_create_dai(cdns, dais, INTEL_PDI_BD, cdns->pdm.num_bd, off, stream->num_ch_bd, false); if (ret) diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c index 48a63ca130d2..6473fa602f82 100644 --- a/drivers/soundwire/slave.c +++ b/drivers/soundwire/slave.c @@ -128,7 +128,8 @@ int sdw_of_find_slaves(struct sdw_bus *bus) struct device_node *node; for_each_child_of_node(bus->dev->of_node, node) { - int link_id, sdw_version, ret, len; + int link_id, ret, len; + unsigned int sdw_version; const char *compat = NULL; struct sdw_slave_id id; const __be32 *addr; diff --git a/drivers/thunderbolt/nhi_ops.c b/drivers/thunderbolt/nhi_ops.c index 61cd09cef943..6795851aac95 100644 --- a/drivers/thunderbolt/nhi_ops.c +++ b/drivers/thunderbolt/nhi_ops.c @@ -80,7 +80,6 @@ static void icl_nhi_lc_mailbox_cmd(struct tb_nhi *nhi, enum icl_lc_mailbox_cmd c { u32 data; - pci_read_config_dword(nhi->pdev, VS_CAP_19, &data); data = (cmd << VS_CAP_19_CMD_SHIFT) & VS_CAP_19_CMD_MASK; pci_write_config_dword(nhi->pdev, VS_CAP_19, data | VS_CAP_19_VALID); } diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 410bf1bceeee..5ea8db667e83 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -896,12 +896,13 @@ int tb_dp_port_set_hops(struct tb_port *port, unsigned int video, */ bool tb_dp_port_is_enabled(struct tb_port *port) { - u32 data; + u32 data[2]; - if (tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1)) + if (tb_port_read(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data))) return false; - return !!(data & (TB_DP_VIDEO_EN | TB_DP_AUX_EN)); + return !!(data[0] & (TB_DP_VIDEO_EN | TB_DP_AUX_EN)); } /** @@ -914,19 +915,21 @@ bool tb_dp_port_is_enabled(struct tb_port *port) */ int tb_dp_port_enable(struct tb_port *port, bool enable) { - u32 data; + u32 data[2]; int ret; - ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1); + ret = tb_port_read(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data)); if (ret) return ret; if (enable) - data |= TB_DP_VIDEO_EN | TB_DP_AUX_EN; + data[0] |= TB_DP_VIDEO_EN | TB_DP_AUX_EN; else - data &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN); + data[0] &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN); - return tb_port_write(port, &data, TB_CFG_PORT, port->cap_adap, 1); + return tb_port_write(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data)); } /* switch utility functions */ @@ -1031,13 +1034,6 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val) if (sw->authorized) goto unlock; - /* - * Make sure there is no PCIe rescan ongoing when a new PCIe - * tunnel is created. Otherwise the PCIe rescan code might find - * the new tunnel too early. - */ - pci_lock_rescan_remove(); - switch (val) { /* Approve switch */ case 1: @@ -1057,8 +1053,6 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val) break; } - pci_unlock_rescan_remove(); - if (!ret) { sw->authorized = val; /* Notify status change to the userspace */ diff --git a/drivers/video/fbdev/c2p_core.h b/drivers/video/fbdev/c2p_core.h index e1035a865fb9..45a6d895a7d7 100644 --- a/drivers/video/fbdev/c2p_core.h +++ b/drivers/video/fbdev/c2p_core.h @@ -29,7 +29,7 @@ static inline void _transp(u32 d[], unsigned int i1, unsigned int i2, extern void c2p_unsupported(void); -static inline u32 get_mask(unsigned int n) +static __always_inline u32 get_mask(unsigned int n) { switch (n) { case 1: @@ -57,7 +57,7 @@ static inline u32 get_mask(unsigned int n) * Transpose operations on 8 32-bit words */ -static inline void transp8(u32 d[], unsigned int n, unsigned int m) +static __always_inline void transp8(u32 d[], unsigned int n, unsigned int m) { u32 mask = get_mask(n); @@ -99,7 +99,7 @@ static inline void transp8(u32 d[], unsigned int n, unsigned int m) * Transpose operations on 4 32-bit words */ -static inline void transp4(u32 d[], unsigned int n, unsigned int m) +static __always_inline void transp4(u32 d[], unsigned int n, unsigned int m) { u32 mask = get_mask(n); @@ -126,7 +126,7 @@ static inline void transp4(u32 d[], unsigned int n, unsigned int m) * Transpose operations on 4 32-bit words (reverse order) */ -static inline void transp4x(u32 d[], unsigned int n, unsigned int m) +static __always_inline void transp4x(u32 d[], unsigned int n, unsigned int m) { u32 mask = get_mask(n); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 226fbb995fb0..e05679c478e2 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -772,6 +772,13 @@ static unsigned long shrink_free_pages(struct virtio_balloon *vb, return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER; } +static unsigned long leak_balloon_pages(struct virtio_balloon *vb, + unsigned long pages_to_free) +{ + return leak_balloon(vb, pages_to_free * VIRTIO_BALLOON_PAGES_PER_PAGE) / + VIRTIO_BALLOON_PAGES_PER_PAGE; +} + static unsigned long shrink_balloon_pages(struct virtio_balloon *vb, unsigned long pages_to_free) { @@ -782,11 +789,10 @@ static unsigned long shrink_balloon_pages(struct virtio_balloon *vb, * VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it * multiple times to deflate pages till reaching pages_to_free. */ - while (vb->num_pages && pages_to_free) { - pages_freed += leak_balloon(vb, pages_to_free) / - VIRTIO_BALLOON_PAGES_PER_PAGE; - pages_to_free -= pages_freed; - } + while (vb->num_pages && pages_freed < pages_to_free) + pages_freed += leak_balloon_pages(vb, + pages_to_free - pages_freed); + update_balloon_size(vb); return pages_freed; @@ -799,7 +805,7 @@ static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker, struct virtio_balloon *vb = container_of(shrinker, struct virtio_balloon, shrinker); - pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE; + pages_to_free = sc->nr_to_scan; if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) pages_freed = shrink_free_pages(vb, pages_to_free); @@ -820,7 +826,7 @@ static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker, unsigned long count; count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE; - count += vb->num_free_page_blocks >> VIRTIO_BALLOON_FREE_PAGE_ORDER; + count += vb->num_free_page_blocks << VIRTIO_BALLOON_FREE_PAGE_ORDER; return count; } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index a8041e451e9e..867c7ebd3f10 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -583,7 +583,7 @@ unmap_release: kfree(desc); END_USE(vq); - return -EIO; + return -ENOMEM; } static bool virtqueue_kick_prepare_split(struct virtqueue *_vq) @@ -1085,7 +1085,7 @@ unmap_release: kfree(desc); END_USE(vq); - return -EIO; + return -ENOMEM; } static inline int virtqueue_add_packed(struct virtqueue *_vq, diff --git a/drivers/watchdog/bd70528_wdt.c b/drivers/watchdog/bd70528_wdt.c index b0152fef4fc7..bc60e036627a 100644 --- a/drivers/watchdog/bd70528_wdt.c +++ b/drivers/watchdog/bd70528_wdt.c @@ -288,3 +288,4 @@ module_platform_driver(bd70528_wdt); MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>"); MODULE_DESCRIPTION("BD70528 watchdog driver"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:bd70528-wdt"); diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index 9393be584e72..808eeb4779e4 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -26,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/timer.h> +#include <linux/compat.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/io.h> @@ -473,6 +474,11 @@ static long cpwd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; } +static long cpwd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return cpwd_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} + static ssize_t cpwd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -497,7 +503,7 @@ static ssize_t cpwd_read(struct file *file, char __user *buffer, static const struct file_operations cpwd_fops = { .owner = THIS_MODULE, .unlocked_ioctl = cpwd_ioctl, - .compat_ioctl = compat_ptr_ioctl, + .compat_ioctl = cpwd_compat_ioctl, .open = cpwd_open, .write = cpwd_write, .read = cpwd_read, diff --git a/drivers/watchdog/imx_sc_wdt.c b/drivers/watchdog/imx_sc_wdt.c index 7ea5cf54e94a..8ed89f032ebf 100644 --- a/drivers/watchdog/imx_sc_wdt.c +++ b/drivers/watchdog/imx_sc_wdt.c @@ -99,8 +99,14 @@ static int imx_sc_wdt_set_pretimeout(struct watchdog_device *wdog, { struct arm_smccc_res res; + /* + * SCU firmware calculates pretimeout based on current time + * stamp instead of watchdog timeout stamp, need to convert + * the pretimeout to SCU firmware's timeout value. + */ arm_smccc_smc(IMX_SIP_TIMER, IMX_SIP_TIMER_SET_PRETIME_WDOG, - pretimeout * 1000, 0, 0, 0, 0, 0, &res); + (wdog->timeout - pretimeout) * 1000, 0, 0, 0, + 0, 0, &res); if (res.a0) return -EACCES; diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c index d17c1a6ed723..5a9ca10fbcfa 100644 --- a/drivers/watchdog/meson_gxbb_wdt.c +++ b/drivers/watchdog/meson_gxbb_wdt.c @@ -89,8 +89,8 @@ static unsigned int meson_gxbb_wdt_get_timeleft(struct watchdog_device *wdt_dev) reg = readl(data->reg_base + GXBB_WDT_TCNT_REG); - return ((reg >> GXBB_WDT_TCNT_CNT_SHIFT) - - (reg & GXBB_WDT_TCNT_SETUP_MASK)) / 1000; + return ((reg & GXBB_WDT_TCNT_SETUP_MASK) - + (reg >> GXBB_WDT_TCNT_CNT_SHIFT)) / 1000; } static const struct watchdog_ops meson_gxbb_wdt_ops = { diff --git a/drivers/watchdog/pm8916_wdt.c b/drivers/watchdog/pm8916_wdt.c index 2d3652004e39..1213179f863c 100644 --- a/drivers/watchdog/pm8916_wdt.c +++ b/drivers/watchdog/pm8916_wdt.c @@ -163,9 +163,17 @@ static int pm8916_wdt_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq > 0) { - if (devm_request_irq(dev, irq, pm8916_wdt_isr, 0, "pm8916_wdt", - wdt)) - irq = 0; + err = devm_request_irq(dev, irq, pm8916_wdt_isr, 0, + "pm8916_wdt", wdt); + if (err) + return err; + + wdt->wdev.info = &pm8916_wdt_pt_ident; + } else { + if (irq == -EPROBE_DEFER) + return -EPROBE_DEFER; + + wdt->wdev.info = &pm8916_wdt_ident; } /* Configure watchdog to hard-reset mode */ @@ -177,7 +185,6 @@ static int pm8916_wdt_probe(struct platform_device *pdev) return err; } - wdt->wdev.info = (irq > 0) ? &pm8916_wdt_pt_ident : &pm8916_wdt_ident, wdt->wdev.ops = &pm8916_wdt_ops, wdt->wdev.parent = dev; wdt->wdev.min_timeout = PM8916_WDT_MIN_TIMEOUT; diff --git a/fs/Kconfig b/fs/Kconfig index 2501e6f1f965..7b623e9fc1b0 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -322,4 +322,7 @@ source "fs/nls/Kconfig" source "fs/dlm/Kconfig" source "fs/unicode/Kconfig" +config IO_WQ + bool + endmenu diff --git a/fs/Makefile b/fs/Makefile index 14231b4cf383..1148c555c4d3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o obj-$(CONFIG_IO_URING) += io_uring.o +obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ diff --git a/fs/affs/affs.h b/fs/affs/affs.h index a92eb6ae2ae2..a755bef7c4c7 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -43,8 +43,8 @@ struct affs_ext_key { */ struct affs_inode_info { atomic_t i_opencnt; - struct semaphore i_link_lock; /* Protects internal inode access. */ - struct semaphore i_ext_lock; /* Protects internal inode access. */ + struct mutex i_link_lock; /* Protects internal inode access. */ + struct mutex i_ext_lock; /* Protects internal inode access. */ #define i_hash_lock i_ext_lock u32 i_blkcnt; /* block count */ u32 i_extcnt; /* extended block count */ @@ -293,30 +293,30 @@ affs_adjust_bitmapchecksum(struct buffer_head *bh, u32 val) static inline void affs_lock_link(struct inode *inode) { - down(&AFFS_I(inode)->i_link_lock); + mutex_lock(&AFFS_I(inode)->i_link_lock); } static inline void affs_unlock_link(struct inode *inode) { - up(&AFFS_I(inode)->i_link_lock); + mutex_unlock(&AFFS_I(inode)->i_link_lock); } static inline void affs_lock_dir(struct inode *inode) { - down(&AFFS_I(inode)->i_hash_lock); + mutex_lock_nested(&AFFS_I(inode)->i_hash_lock, SINGLE_DEPTH_NESTING); } static inline void affs_unlock_dir(struct inode *inode) { - up(&AFFS_I(inode)->i_hash_lock); + mutex_unlock(&AFFS_I(inode)->i_hash_lock); } static inline void affs_lock_ext(struct inode *inode) { - down(&AFFS_I(inode)->i_ext_lock); + mutex_lock(&AFFS_I(inode)->i_ext_lock); } static inline void affs_unlock_ext(struct inode *inode) { - up(&AFFS_I(inode)->i_ext_lock); + mutex_unlock(&AFFS_I(inode)->i_ext_lock); } diff --git a/fs/affs/super.c b/fs/affs/super.c index cc463ae47c12..47107c6712a6 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -121,8 +121,8 @@ static void init_once(void *foo) { struct affs_inode_info *ei = (struct affs_inode_info *) foo; - sema_init(&ei->i_link_lock, 1); - sema_init(&ei->i_ext_lock, 1); + mutex_init(&ei->i_link_lock); + mutex_init(&ei->i_ext_lock); inode_init_once(&ei->vfs_inode); } @@ -561,14 +561,9 @@ affs_remount(struct super_block *sb, int *flags, char *data) int root_block; unsigned long mount_flags; int res = 0; - char *new_opts; char volume[32]; char *prefix = NULL; - new_opts = kstrdup(data, GFP_KERNEL); - if (data && !new_opts) - return -ENOMEM; - pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data); sync_filesystem(sb); @@ -579,7 +574,6 @@ affs_remount(struct super_block *sb, int *flags, char *data) &blocksize, &prefix, volume, &mount_flags)) { kfree(prefix); - kfree(new_opts); return -EINVAL; } diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 6cdd7047c809..2dca8df1a18d 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -312,7 +312,6 @@ void afs_break_callbacks(struct afs_server *server, size_t count, _enter("%p,%zu,", server, count); ASSERT(server != NULL); - ASSERTCMP(count, <=, AFSCBMAX); /* TODO: Sort the callback break list by volume ID */ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index cc12772d0a4d..497f979018c2 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -803,7 +803,12 @@ success: continue; if (cookie->inodes[i]) { - afs_vnode_commit_status(&fc, AFS_FS_I(cookie->inodes[i]), + struct afs_vnode *iv = AFS_FS_I(cookie->inodes[i]); + + if (test_bit(AFS_VNODE_UNSET, &iv->flags)) + continue; + + afs_vnode_commit_status(&fc, iv, scb->cb_break, NULL, scb); continue; } diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 0e5269374ac1..61498d9f06ef 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -637,6 +637,7 @@ long afs_wait_for_call_to_complete(struct afs_call *call, call->need_attention = false; __set_current_state(TASK_RUNNING); afs_deliver_to_call(call); + timeout = rtt2; continue; } diff --git a/fs/afs/super.c b/fs/afs/super.c index f18911e8d770..488641b1a418 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -435,6 +435,7 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) /* fill in the superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; if (!as->dyn_root) @@ -2179,7 +2179,7 @@ SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, #ifdef CONFIG_COMPAT struct __compat_aio_sigset { - compat_sigset_t __user *sigmask; + compat_uptr_t sigmask; compat_size_t sigsetsize; }; @@ -2193,7 +2193,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, struct old_timespec32 __user *, timeout, const struct __compat_aio_sigset __user *, usig) { - struct __compat_aio_sigset ksig = { NULL, }; + struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; @@ -2204,7 +2204,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; - ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize); + ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; @@ -2228,7 +2228,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, struct __kernel_timespec __user *, timeout, const struct __compat_aio_sigset __user *, usig) { - struct __compat_aio_sigset ksig = { NULL, }; + struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; @@ -2239,7 +2239,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; - ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize); + ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index 2866fabf497f..91f5787dae7c 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -459,9 +459,10 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb, */ how &= ~AUTOFS_EXP_LEAVES; found = should_expire(expired, mnt, timeout, how); - if (!found || found != expired) - /* Something has changed, continue */ + if (found != expired) { // something has changed, continue + dput(found); goto next; + } if (expired != dentry) dput(dentry); diff --git a/fs/block_dev.c b/fs/block_dev.c index 9c073dbdc1b0..ee63c2732fa2 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1403,11 +1403,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty) "resized disk %s\n", bdev->bd_disk ? bdev->bd_disk->disk_name : ""); } - - if (!bdev->bd_disk) - return; - if (disk_part_scan_enabled(bdev->bd_disk)) - bdev->bd_invalidated = 1; + bdev->bd_invalidated = 1; } /** @@ -1420,8 +1416,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty) * and adjusts it if it differs. When shrinking the bdev size, its all caches * are freed. */ -void check_disk_size_change(struct gendisk *disk, struct block_device *bdev, - bool verbose) +static void check_disk_size_change(struct gendisk *disk, + struct block_device *bdev, bool verbose) { loff_t disk_size, bdev_size; @@ -1437,6 +1433,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev, if (bdev_size > disk_size) flush_disk(bdev, false); } + bdev->bd_invalidated = 0; } /** @@ -1466,7 +1463,6 @@ int revalidate_disk(struct gendisk *disk) mutex_lock(&bdev->bd_mutex); check_disk_size_change(disk, bdev, ret == 0); - bdev->bd_invalidated = 0; mutex_unlock(&bdev->bd_mutex); bdput(bdev); } @@ -1512,6 +1508,45 @@ EXPORT_SYMBOL(bd_set_size); static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); +int bdev_disk_changed(struct block_device *bdev, bool invalidate) +{ + struct gendisk *disk = bdev->bd_disk; + int ret; + + lockdep_assert_held(&bdev->bd_mutex); + +rescan: + ret = blk_drop_partitions(disk, bdev); + if (ret) + return ret; + + if (invalidate) + set_capacity(disk, 0); + else if (disk->fops->revalidate_disk) + disk->fops->revalidate_disk(disk); + + check_disk_size_change(disk, bdev, !invalidate); + + if (get_capacity(disk)) { + ret = blk_add_partitions(disk, bdev); + if (ret == -EAGAIN) + goto rescan; + } else { + /* + * Tell userspace that the media / partition table may have + * changed. + */ + kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); + } + + return ret; +} +/* + * Only exported for for loop and dasd for historic reasons. Don't use in new + * code! + */ +EXPORT_SYMBOL_GPL(bdev_disk_changed); + /* * bd_mutex locking: * @@ -1594,12 +1629,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) * The latter is necessary to prevent ghost * partitions on a removed medium. */ - if (bdev->bd_invalidated) { - if (!ret) - rescan_partitions(disk, bdev); - else if (ret == -ENOMEDIUM) - invalidate_partitions(disk, bdev); - } + if (bdev->bd_invalidated && + (!ret || ret == -ENOMEDIUM)) + bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_clear; @@ -1632,12 +1664,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ - if (bdev->bd_invalidated) { - if (!ret) - rescan_partitions(bdev->bd_disk, bdev); - else if (ret == -ENOMEDIUM) - invalidate_partitions(bdev->bd_disk, bdev); - } + if (bdev->bd_invalidated && + (!ret || ret == -ENOMEDIUM)) + bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_unlock_bdev; } diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 38651fae7f21..75b6d10c9845 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -5,6 +5,8 @@ config BTRFS_FS select CRYPTO select CRYPTO_CRC32C select LIBCRC32C + select CRYPTO_XXHASH + select CRYPTO_SHA256 select ZLIB_INFLATE select ZLIB_DEFLATE select LZO_COMPRESS diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 2e9e13ffbd08..1d32a07bb2d1 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -53,24 +53,12 @@ struct btrfs_workqueue { struct __btrfs_workqueue *high; }; -static void normal_work_helper(struct btrfs_work *work); - -#define BTRFS_WORK_HELPER(name) \ -noinline_for_stack void btrfs_##name(struct work_struct *arg) \ -{ \ - struct btrfs_work *work = container_of(arg, struct btrfs_work, \ - normal_work); \ - normal_work_helper(work); \ -} - -struct btrfs_fs_info * -btrfs_workqueue_owner(const struct __btrfs_workqueue *wq) +struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq) { return wq->fs_info; } -struct btrfs_fs_info * -btrfs_work_owner(const struct btrfs_work *work) +struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work) { return work->wq->fs_info; } @@ -89,29 +77,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq) return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2; } -BTRFS_WORK_HELPER(worker_helper); -BTRFS_WORK_HELPER(delalloc_helper); -BTRFS_WORK_HELPER(flush_delalloc_helper); -BTRFS_WORK_HELPER(cache_helper); -BTRFS_WORK_HELPER(submit_helper); -BTRFS_WORK_HELPER(fixup_helper); -BTRFS_WORK_HELPER(endio_helper); -BTRFS_WORK_HELPER(endio_meta_helper); -BTRFS_WORK_HELPER(endio_meta_write_helper); -BTRFS_WORK_HELPER(endio_raid56_helper); -BTRFS_WORK_HELPER(endio_repair_helper); -BTRFS_WORK_HELPER(rmw_helper); -BTRFS_WORK_HELPER(endio_write_helper); -BTRFS_WORK_HELPER(freespace_write_helper); -BTRFS_WORK_HELPER(delayed_meta_helper); -BTRFS_WORK_HELPER(readahead_helper); -BTRFS_WORK_HELPER(qgroup_rescan_helper); -BTRFS_WORK_HELPER(extent_refs_helper); -BTRFS_WORK_HELPER(scrub_helper); -BTRFS_WORK_HELPER(scrubwrc_helper); -BTRFS_WORK_HELPER(scrubnc_helper); -BTRFS_WORK_HELPER(scrubparity_helper); - static struct __btrfs_workqueue * __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, unsigned int flags, int limit_active, int thresh) @@ -252,16 +217,16 @@ out: } } -static void run_ordered_work(struct __btrfs_workqueue *wq) +static void run_ordered_work(struct __btrfs_workqueue *wq, + struct btrfs_work *self) { struct list_head *list = &wq->ordered_list; struct btrfs_work *work; spinlock_t *lock = &wq->list_lock; unsigned long flags; + bool free_self = false; while (1) { - void *wtag; - spin_lock_irqsave(lock, flags); if (list_empty(list)) break; @@ -287,22 +252,53 @@ static void run_ordered_work(struct __btrfs_workqueue *wq) list_del(&work->ordered_list); spin_unlock_irqrestore(lock, flags); - /* - * We don't want to call the ordered free functions with the - * lock held though. Save the work as tag for the trace event, - * because the callback could free the structure. - */ - wtag = work; - work->ordered_free(work); - trace_btrfs_all_work_done(wq->fs_info, wtag); + if (work == self) { + /* + * This is the work item that the worker is currently + * executing. + * + * The kernel workqueue code guarantees non-reentrancy + * of work items. I.e., if a work item with the same + * address and work function is queued twice, the second + * execution is blocked until the first one finishes. A + * work item may be freed and recycled with the same + * work function; the workqueue code assumes that the + * original work item cannot depend on the recycled work + * item in that case (see find_worker_executing_work()). + * + * Note that different types of Btrfs work can depend on + * each other, and one type of work on one Btrfs + * filesystem may even depend on the same type of work + * on another Btrfs filesystem via, e.g., a loop device. + * Therefore, we must not allow the current work item to + * be recycled until we are really done, otherwise we + * break the above assumption and can deadlock. + */ + free_self = true; + } else { + /* + * We don't want to call the ordered free functions with + * the lock held. + */ + work->ordered_free(work); + /* NB: work must not be dereferenced past this point. */ + trace_btrfs_all_work_done(wq->fs_info, work); + } } spin_unlock_irqrestore(lock, flags); + + if (free_self) { + self->ordered_free(self); + /* NB: self must not be dereferenced past this point. */ + trace_btrfs_all_work_done(wq->fs_info, self); + } } -static void normal_work_helper(struct btrfs_work *work) +static void btrfs_work_helper(struct work_struct *normal_work) { + struct btrfs_work *work = container_of(normal_work, struct btrfs_work, + normal_work); struct __btrfs_workqueue *wq; - void *wtag; int need_order = 0; /* @@ -316,29 +312,26 @@ static void normal_work_helper(struct btrfs_work *work) if (work->ordered_func) need_order = 1; wq = work->wq; - /* Safe for tracepoints in case work gets freed by the callback */ - wtag = work; trace_btrfs_work_sched(work); thresh_exec_hook(wq); work->func(work); if (need_order) { set_bit(WORK_DONE_BIT, &work->flags); - run_ordered_work(wq); + run_ordered_work(wq, work); + } else { + /* NB: work must not be dereferenced past this point. */ + trace_btrfs_all_work_done(wq->fs_info, work); } - if (!need_order) - trace_btrfs_all_work_done(wq->fs_info, wtag); } -void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func, - btrfs_func_t func, - btrfs_func_t ordered_func, - btrfs_func_t ordered_free) +void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func, + btrfs_func_t ordered_func, btrfs_func_t ordered_free) { work->func = func; work->ordered_func = ordered_func; work->ordered_free = ordered_free; - INIT_WORK(&work->normal_work, uniq_func); + INIT_WORK(&work->normal_work, btrfs_work_helper); INIT_LIST_HEAD(&work->ordered_list); work->flags = 0; } diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 7861c9feba5f..a4434301d84d 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -29,49 +29,20 @@ struct btrfs_work { unsigned long flags; }; -#define BTRFS_WORK_HELPER_PROTO(name) \ -void btrfs_##name(struct work_struct *arg) - -BTRFS_WORK_HELPER_PROTO(worker_helper); -BTRFS_WORK_HELPER_PROTO(delalloc_helper); -BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper); -BTRFS_WORK_HELPER_PROTO(cache_helper); -BTRFS_WORK_HELPER_PROTO(submit_helper); -BTRFS_WORK_HELPER_PROTO(fixup_helper); -BTRFS_WORK_HELPER_PROTO(endio_helper); -BTRFS_WORK_HELPER_PROTO(endio_meta_helper); -BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper); -BTRFS_WORK_HELPER_PROTO(endio_raid56_helper); -BTRFS_WORK_HELPER_PROTO(endio_repair_helper); -BTRFS_WORK_HELPER_PROTO(rmw_helper); -BTRFS_WORK_HELPER_PROTO(endio_write_helper); -BTRFS_WORK_HELPER_PROTO(freespace_write_helper); -BTRFS_WORK_HELPER_PROTO(delayed_meta_helper); -BTRFS_WORK_HELPER_PROTO(readahead_helper); -BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper); -BTRFS_WORK_HELPER_PROTO(extent_refs_helper); -BTRFS_WORK_HELPER_PROTO(scrub_helper); -BTRFS_WORK_HELPER_PROTO(scrubwrc_helper); -BTRFS_WORK_HELPER_PROTO(scrubnc_helper); -BTRFS_WORK_HELPER_PROTO(scrubparity_helper); - - struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, unsigned int flags, int limit_active, int thresh); -void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper, - btrfs_func_t func, - btrfs_func_t ordered_func, - btrfs_func_t ordered_free); +void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func, + btrfs_func_t ordered_func, btrfs_func_t ordered_free); void btrfs_queue_work(struct btrfs_workqueue *wq, struct btrfs_work *work); void btrfs_destroy_workqueue(struct btrfs_workqueue *wq); void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max); void btrfs_set_work_high_priority(struct btrfs_work *work); -struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work); -struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq); +struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work); +struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq); bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq); #endif diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 670700cb1110..6934a5b8708f 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -120,12 +120,12 @@ u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags) return get_alloc_profile(fs_info, orig_flags); } -void btrfs_get_block_group(struct btrfs_block_group_cache *cache) +void btrfs_get_block_group(struct btrfs_block_group *cache) { atomic_inc(&cache->count); } -void btrfs_put_block_group(struct btrfs_block_group_cache *cache) +void btrfs_put_block_group(struct btrfs_block_group *cache) { if (atomic_dec_and_test(&cache->count)) { WARN_ON(cache->pinned > 0); @@ -149,22 +149,21 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache) * This adds the block group to the fs_info rb tree for the block group cache */ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, - struct btrfs_block_group_cache *block_group) + struct btrfs_block_group *block_group) { struct rb_node **p; struct rb_node *parent = NULL; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; spin_lock(&info->block_group_cache_lock); p = &info->block_group_cache_tree.rb_node; while (*p) { parent = *p; - cache = rb_entry(parent, struct btrfs_block_group_cache, - cache_node); - if (block_group->key.objectid < cache->key.objectid) { + cache = rb_entry(parent, struct btrfs_block_group, cache_node); + if (block_group->start < cache->start) { p = &(*p)->rb_left; - } else if (block_group->key.objectid > cache->key.objectid) { + } else if (block_group->start > cache->start) { p = &(*p)->rb_right; } else { spin_unlock(&info->block_group_cache_lock); @@ -176,8 +175,8 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, rb_insert_color(&block_group->cache_node, &info->block_group_cache_tree); - if (info->first_logical_byte > block_group->key.objectid) - info->first_logical_byte = block_group->key.objectid; + if (info->first_logical_byte > block_group->start) + info->first_logical_byte = block_group->start; spin_unlock(&info->block_group_cache_lock); @@ -188,10 +187,10 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, * This will return the block group at or after bytenr if contains is 0, else * it will return the block group that contains the bytenr */ -static struct btrfs_block_group_cache *block_group_cache_tree_search( +static struct btrfs_block_group *block_group_cache_tree_search( struct btrfs_fs_info *info, u64 bytenr, int contains) { - struct btrfs_block_group_cache *cache, *ret = NULL; + struct btrfs_block_group *cache, *ret = NULL; struct rb_node *n; u64 end, start; @@ -199,13 +198,12 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search( n = info->block_group_cache_tree.rb_node; while (n) { - cache = rb_entry(n, struct btrfs_block_group_cache, - cache_node); - end = cache->key.objectid + cache->key.offset - 1; - start = cache->key.objectid; + cache = rb_entry(n, struct btrfs_block_group, cache_node); + end = cache->start + cache->length - 1; + start = cache->start; if (bytenr < start) { - if (!contains && (!ret || start < ret->key.objectid)) + if (!contains && (!ret || start < ret->start)) ret = cache; n = n->rb_left; } else if (bytenr > start) { @@ -221,8 +219,8 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search( } if (ret) { btrfs_get_block_group(ret); - if (bytenr == 0 && info->first_logical_byte > ret->key.objectid) - info->first_logical_byte = ret->key.objectid; + if (bytenr == 0 && info->first_logical_byte > ret->start) + info->first_logical_byte = ret->start; } spin_unlock(&info->block_group_cache_lock); @@ -232,7 +230,7 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search( /* * Return the block group that starts at or after bytenr */ -struct btrfs_block_group_cache *btrfs_lookup_first_block_group( +struct btrfs_block_group *btrfs_lookup_first_block_group( struct btrfs_fs_info *info, u64 bytenr) { return block_group_cache_tree_search(info, bytenr, 0); @@ -241,14 +239,14 @@ struct btrfs_block_group_cache *btrfs_lookup_first_block_group( /* * Return the block group that contains the given bytenr */ -struct btrfs_block_group_cache *btrfs_lookup_block_group( +struct btrfs_block_group *btrfs_lookup_block_group( struct btrfs_fs_info *info, u64 bytenr) { return block_group_cache_tree_search(info, bytenr, 1); } -struct btrfs_block_group_cache *btrfs_next_block_group( - struct btrfs_block_group_cache *cache) +struct btrfs_block_group *btrfs_next_block_group( + struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; struct rb_node *node; @@ -257,7 +255,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group( /* If our block group was removed, we need a full search. */ if (RB_EMPTY_NODE(&cache->cache_node)) { - const u64 next_bytenr = cache->key.objectid + cache->key.offset; + const u64 next_bytenr = cache->start + cache->length; spin_unlock(&fs_info->block_group_cache_lock); btrfs_put_block_group(cache); @@ -266,8 +264,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group( node = rb_next(&cache->cache_node); btrfs_put_block_group(cache); if (node) { - cache = rb_entry(node, struct btrfs_block_group_cache, - cache_node); + cache = rb_entry(node, struct btrfs_block_group, cache_node); btrfs_get_block_group(cache); } else cache = NULL; @@ -277,7 +274,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group( bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) { - struct btrfs_block_group_cache *bg; + struct btrfs_block_group *bg; bool ret = true; bg = btrfs_lookup_block_group(fs_info, bytenr); @@ -300,7 +297,7 @@ bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) { - struct btrfs_block_group_cache *bg; + struct btrfs_block_group *bg; bg = btrfs_lookup_block_group(fs_info, bytenr); ASSERT(bg); @@ -314,7 +311,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) btrfs_put_block_group(bg); } -void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg) +void btrfs_wait_nocow_writers(struct btrfs_block_group *bg) { wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers)); } @@ -322,7 +319,7 @@ void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg) void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, const u64 start) { - struct btrfs_block_group_cache *bg; + struct btrfs_block_group *bg; bg = btrfs_lookup_block_group(fs_info, start); ASSERT(bg); @@ -331,7 +328,7 @@ void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, btrfs_put_block_group(bg); } -void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) +void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg) { struct btrfs_space_info *space_info = bg->space_info; @@ -357,7 +354,7 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) } struct btrfs_caching_control *btrfs_get_caching_control( - struct btrfs_block_group_cache *cache) + struct btrfs_block_group *cache) { struct btrfs_caching_control *ctl; @@ -392,7 +389,7 @@ void btrfs_put_caching_control(struct btrfs_caching_control *ctl) * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using * any of the information in this block group. */ -void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache, +void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes) { struct btrfs_caching_control *caching_ctl; @@ -401,13 +398,13 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache if (!caching_ctl) return; - wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache) || + wait_event(caching_ctl->wait, btrfs_block_group_done(cache) || (cache->free_space_ctl->free_space >= num_bytes)); btrfs_put_caching_control(caching_ctl); } -int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache) +int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) { struct btrfs_caching_control *caching_ctl; int ret = 0; @@ -416,7 +413,7 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache) if (!caching_ctl) return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0; - wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache)); + wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); if (cache->cached == BTRFS_CACHE_ERROR) ret = -EIO; btrfs_put_caching_control(caching_ctl); @@ -424,11 +421,11 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache) } #ifdef CONFIG_BTRFS_DEBUG -static void fragment_free_space(struct btrfs_block_group_cache *block_group) +static void fragment_free_space(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; - u64 start = block_group->key.objectid; - u64 len = block_group->key.offset; + u64 start = block_group->start; + u64 len = block_group->length; u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ? fs_info->nodesize : fs_info->sectorsize; u64 step = chunk << 1; @@ -450,8 +447,7 @@ static void fragment_free_space(struct btrfs_block_group_cache *block_group) * used yet since their free space will be released as soon as the transaction * commits. */ -u64 add_new_free_space(struct btrfs_block_group_cache *block_group, - u64 start, u64 end) +u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end) { struct btrfs_fs_info *info = block_group->fs_info; u64 extent_start, extent_end, size, total_added = 0; @@ -491,7 +487,7 @@ u64 add_new_free_space(struct btrfs_block_group_cache *block_group, static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) { - struct btrfs_block_group_cache *block_group = caching_ctl->block_group; + struct btrfs_block_group *block_group = caching_ctl->block_group; struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *extent_root = fs_info->extent_root; struct btrfs_path *path; @@ -507,7 +503,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) if (!path) return -ENOMEM; - last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET); + last = max_t(u64, block_group->start, BTRFS_SUPER_INFO_OFFSET); #ifdef CONFIG_BTRFS_DEBUG /* @@ -587,13 +583,12 @@ next: goto next; } - if (key.objectid < block_group->key.objectid) { + if (key.objectid < block_group->start) { path->slots[0]++; continue; } - if (key.objectid >= block_group->key.objectid + - block_group->key.offset) + if (key.objectid >= block_group->start + block_group->length) break; if (key.type == BTRFS_EXTENT_ITEM_KEY || @@ -617,8 +612,7 @@ next: ret = 0; total_found += add_new_free_space(block_group, last, - block_group->key.objectid + - block_group->key.offset); + block_group->start + block_group->length); caching_ctl->progress = (u64)-1; out: @@ -628,7 +622,7 @@ out: static noinline void caching_thread(struct btrfs_work *work) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_caching_control *caching_ctl; int ret; @@ -656,8 +650,7 @@ static noinline void caching_thread(struct btrfs_work *work) spin_lock(&block_group->space_info->lock); spin_lock(&block_group->lock); - bytes_used = block_group->key.offset - - btrfs_block_group_used(&block_group->item); + bytes_used = block_group->length - block_group->used; block_group->space_info->bytes_used += bytes_used >> 1; spin_unlock(&block_group->lock); spin_unlock(&block_group->space_info->lock); @@ -677,8 +670,7 @@ static noinline void caching_thread(struct btrfs_work *work) btrfs_put_block_group(block_group); } -int btrfs_cache_block_group(struct btrfs_block_group_cache *cache, - int load_cache_only) +int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only) { DEFINE_WAIT(wait); struct btrfs_fs_info *fs_info = cache->fs_info; @@ -693,10 +685,9 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache, mutex_init(&caching_ctl->mutex); init_waitqueue_head(&caching_ctl->wait); caching_ctl->block_group = cache; - caching_ctl->progress = cache->key.objectid; + caching_ctl->progress = cache->start; refcount_set(&caching_ctl->count, 1); - btrfs_init_work(&caching_ctl->work, btrfs_cache_helper, - caching_thread, NULL, NULL); + btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL); spin_lock(&cache->lock); /* @@ -763,8 +754,7 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache, spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); - bytes_used = cache->key.offset - - btrfs_block_group_used(&cache->item); + bytes_used = cache->length - cache->used; cache->space_info->bytes_used += bytes_used >> 1; spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); @@ -833,27 +823,36 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) * * - RAID56 - in case there's neither RAID5 nor RAID6 profile block group * in the whole filesystem + * + * - RAID1C34 - same as above for RAID1C3 and RAID1C4 block groups */ static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags) { - if (flags & BTRFS_BLOCK_GROUP_RAID56_MASK) { + bool found_raid56 = false; + bool found_raid1c34 = false; + + if ((flags & BTRFS_BLOCK_GROUP_RAID56_MASK) || + (flags & BTRFS_BLOCK_GROUP_RAID1C3) || + (flags & BTRFS_BLOCK_GROUP_RAID1C4)) { struct list_head *head = &fs_info->space_info; struct btrfs_space_info *sinfo; list_for_each_entry_rcu(sinfo, head, list) { - bool found = false; - down_read(&sinfo->groups_sem); if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID5])) - found = true; + found_raid56 = true; if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID6])) - found = true; + found_raid56 = true; + if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C3])) + found_raid1c34 = true; + if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C4])) + found_raid1c34 = true; up_read(&sinfo->groups_sem); - - if (found) - return; } - btrfs_clear_fs_incompat(fs_info, RAID56); + if (found_raid56) + btrfs_clear_fs_incompat(fs_info, RAID56); + if (found_raid1c34) + btrfs_clear_fs_incompat(fs_info, RAID1C34); } } @@ -863,7 +862,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = fs_info->extent_root; struct btrfs_path *path; - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_free_cluster *cluster; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_key key; @@ -886,10 +885,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, * remove it. */ btrfs_free_excluded_extents(block_group); - btrfs_free_ref_tree_range(fs_info, block_group->key.objectid, - block_group->key.offset); + btrfs_free_ref_tree_range(fs_info, block_group->start, + block_group->length); - memcpy(&key, &block_group->key, sizeof(key)); index = btrfs_bg_flags_to_raid_index(block_group->flags); factor = btrfs_bg_type_to_factor(block_group->flags); @@ -967,8 +965,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, } key.objectid = BTRFS_FREE_SPACE_OBJECTID; - key.offset = block_group->key.objectid; key.type = 0; + key.offset = block_group->start; ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); if (ret < 0) @@ -987,7 +985,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, &fs_info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); - if (fs_info->first_logical_byte == block_group->key.objectid) + if (fs_info->first_logical_byte == block_group->start) fs_info->first_logical_byte = (u64)-1; spin_unlock(&fs_info->block_group_cache_lock); @@ -1048,19 +1046,21 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) { WARN_ON(block_group->space_info->total_bytes - < block_group->key.offset); + < block_group->length); WARN_ON(block_group->space_info->bytes_readonly - < block_group->key.offset); + < block_group->length); WARN_ON(block_group->space_info->disk_total - < block_group->key.offset * factor); + < block_group->length * factor); } - block_group->space_info->total_bytes -= block_group->key.offset; - block_group->space_info->bytes_readonly -= block_group->key.offset; - block_group->space_info->disk_total -= block_group->key.offset * factor; + block_group->space_info->total_bytes -= block_group->length; + block_group->space_info->bytes_readonly -= block_group->length; + block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); - memcpy(&key, &block_group->key, sizeof(key)); + key.objectid = block_group->start; + key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; + key.offset = block_group->length; mutex_lock(&fs_info->chunk_mutex); spin_lock(&block_group->lock); @@ -1180,7 +1180,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( * data in this block group. That check should be done by relocation routine, * not this function. */ -static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force) +static int inc_block_group_ro(struct btrfs_block_group *cache, int force) { struct btrfs_space_info *sinfo = cache->space_info; u64 num_bytes; @@ -1209,8 +1209,8 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force) goto out; } - num_bytes = cache->key.offset - cache->reserved - cache->pinned - - cache->bytes_super - btrfs_block_group_used(&cache->item); + num_bytes = cache->length - cache->reserved - cache->pinned - + cache->bytes_super - cache->used; sinfo_used = btrfs_space_info_used(sinfo, true); /* @@ -1231,8 +1231,7 @@ out: spin_unlock(&sinfo->lock); if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) { btrfs_info(cache->fs_info, - "unable to make block group %llu ro", - cache->key.objectid); + "unable to make block group %llu ro", cache->start); btrfs_info(cache->fs_info, "sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu", sinfo_used, num_bytes, min_allocable_bytes); @@ -1247,7 +1246,7 @@ out: */ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; int ret = 0; @@ -1261,7 +1260,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) int trimming; block_group = list_first_entry(&fs_info->unused_bgs, - struct btrfs_block_group_cache, + struct btrfs_block_group, bg_list); list_del_init(&block_group->bg_list); @@ -1279,8 +1278,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) down_write(&space_info->groups_sem); spin_lock(&block_group->lock); if (block_group->reserved || block_group->pinned || - btrfs_block_group_used(&block_group->item) || - block_group->ro || + block_group->used || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have @@ -1308,7 +1306,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * properly if we fail to join the transaction. */ trans = btrfs_start_trans_remove_block_group(fs_info, - block_group->key.objectid); + block_group->start); if (IS_ERR(trans)) { btrfs_dec_block_group_ro(block_group); ret = PTR_ERR(trans); @@ -1319,8 +1317,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * We could have pending pinned extents for this block group, * just delete them, we don't care about them anymore. */ - start = block_group->key.objectid; - end = start + block_group->key.offset - 1; + start = block_group->start; + end = start + block_group->length - 1; /* * Hold the unused_bg_unpin_mutex lock to avoid racing with * btrfs_finish_extent_commit(). If we are at transaction N, @@ -1375,7 +1373,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * Btrfs_remove_chunk will abort the transaction if things go * horribly wrong. */ - ret = btrfs_remove_chunk(trans, block_group->key.objectid); + ret = btrfs_remove_chunk(trans, block_group->start); if (ret) { if (trimming) @@ -1410,7 +1408,7 @@ next: spin_unlock(&fs_info->unused_bgs_lock); } -void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg) +void btrfs_mark_bg_unused(struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; @@ -1478,7 +1476,7 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info, read_extent_buffer(leaf, &bg, btrfs_item_ptr_offset(leaf, slot), sizeof(bg)); - flags = btrfs_block_group_flags(&bg) & + flags = btrfs_stack_block_group_flags(&bg) & BTRFS_BLOCK_GROUP_TYPE_MASK; if (flags != (em->map_lookup->type & @@ -1518,7 +1516,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) write_sequnlock(&fs_info->profiles_lock); } -static int exclude_super_stripes(struct btrfs_block_group_cache *cache) +static int exclude_super_stripes(struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; u64 bytenr; @@ -1526,10 +1524,10 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache) int stripe_len; int i, nr, ret; - if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) { - stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid; + if (cache->start < BTRFS_SUPER_INFO_OFFSET) { + stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->start; cache->bytes_super += stripe_len; - ret = btrfs_add_excluded_extent(fs_info, cache->key.objectid, + ret = btrfs_add_excluded_extent(fs_info, cache->start, stripe_len); if (ret) return ret; @@ -1537,7 +1535,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache) for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { bytenr = btrfs_sb_offset(i); - ret = btrfs_rmap_block(fs_info, cache->key.objectid, + ret = btrfs_rmap_block(fs_info, cache->start, bytenr, &logical, &nr, &stripe_len); if (ret) return ret; @@ -1545,21 +1543,19 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache) while (nr--) { u64 start, len; - if (logical[nr] > cache->key.objectid + - cache->key.offset) + if (logical[nr] > cache->start + cache->length) continue; - if (logical[nr] + stripe_len <= cache->key.objectid) + if (logical[nr] + stripe_len <= cache->start) continue; start = logical[nr]; - if (start < cache->key.objectid) { - start = cache->key.objectid; + if (start < cache->start) { + start = cache->start; len = (logical[nr] + stripe_len) - start; } else { len = min_t(u64, stripe_len, - cache->key.objectid + - cache->key.offset - start); + cache->start + cache->length - start); } cache->bytes_super += len; @@ -1575,7 +1571,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache) return 0; } -static void link_block_group(struct btrfs_block_group_cache *cache) +static void link_block_group(struct btrfs_block_group *cache) { struct btrfs_space_info *space_info = cache->space_info; int index = btrfs_bg_flags_to_raid_index(cache->flags); @@ -1591,10 +1587,10 @@ static void link_block_group(struct btrfs_block_group_cache *cache) btrfs_sysfs_add_block_group_type(cache); } -static struct btrfs_block_group_cache *btrfs_create_block_group_cache( +static struct btrfs_block_group *btrfs_create_block_group_cache( struct btrfs_fs_info *fs_info, u64 start, u64 size) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; cache = kzalloc(sizeof(*cache), GFP_NOFS); if (!cache) @@ -1607,9 +1603,8 @@ static struct btrfs_block_group_cache *btrfs_create_block_group_cache( return NULL; } - cache->key.objectid = start; - cache->key.offset = size; - cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; + cache->start = start; + cache->length = size; cache->fs_info = fs_info; cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start); @@ -1640,7 +1635,7 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) { struct extent_map_tree *map_tree = &fs_info->mapping_tree; struct extent_map *em; - struct btrfs_block_group_cache *bg; + struct btrfs_block_group *bg; u64 start = 0; int ret = 0; @@ -1665,15 +1660,14 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) free_extent_map(em); break; } - if (bg->key.objectid != em->start || - bg->key.offset != em->len || + if (bg->start != em->start || bg->length != em->len || (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) != (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) { btrfs_err(fs_info, "chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx", em->start, em->len, em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK, - bg->key.objectid, bg->key.offset, + bg->start, bg->length, bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK); ret = -EUCLEAN; free_extent_map(em); @@ -1687,22 +1681,117 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) return ret; } +static int read_one_block_group(struct btrfs_fs_info *info, + struct btrfs_path *path, + const struct btrfs_key *key, + int need_clear) +{ + struct extent_buffer *leaf = path->nodes[0]; + struct btrfs_block_group *cache; + struct btrfs_space_info *space_info; + struct btrfs_block_group_item bgi; + const bool mixed = btrfs_fs_incompat(info, MIXED_GROUPS); + int slot = path->slots[0]; + int ret; + + ASSERT(key->type == BTRFS_BLOCK_GROUP_ITEM_KEY); + + cache = btrfs_create_block_group_cache(info, key->objectid, key->offset); + if (!cache) + return -ENOMEM; + + if (need_clear) { + /* + * When we mount with old space cache, we need to + * set BTRFS_DC_CLEAR and set dirty flag. + * + * a) Setting 'BTRFS_DC_CLEAR' makes sure that we + * truncate the old free space cache inode and + * setup a new one. + * b) Setting 'dirty flag' makes sure that we flush + * the new space cache info onto disk. + */ + if (btrfs_test_opt(info, SPACE_CACHE)) + cache->disk_cache_state = BTRFS_DC_CLEAR; + } + read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), + sizeof(bgi)); + cache->used = btrfs_stack_block_group_used(&bgi); + cache->flags = btrfs_stack_block_group_flags(&bgi); + if (!mixed && ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) && + (cache->flags & BTRFS_BLOCK_GROUP_DATA))) { + btrfs_err(info, +"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", + cache->start); + ret = -EINVAL; + goto error; + } + + /* + * We need to exclude the super stripes now so that the space info has + * super bytes accounted for, otherwise we'll think we have more space + * than we actually do. + */ + ret = exclude_super_stripes(cache); + if (ret) { + /* We may have excluded something, so call this just in case. */ + btrfs_free_excluded_extents(cache); + goto error; + } + + /* + * Check for two cases, either we are full, and therefore don't need + * to bother with the caching work since we won't find any space, or we + * are empty, and we can just add all the space in and be done with it. + * This saves us _a_lot_ of time, particularly in the full case. + */ + if (key->offset == cache->used) { + cache->last_byte_to_unpin = (u64)-1; + cache->cached = BTRFS_CACHE_FINISHED; + btrfs_free_excluded_extents(cache); + } else if (cache->used == 0) { + cache->last_byte_to_unpin = (u64)-1; + cache->cached = BTRFS_CACHE_FINISHED; + add_new_free_space(cache, key->objectid, + key->objectid + key->offset); + btrfs_free_excluded_extents(cache); + } + + ret = btrfs_add_block_group_cache(info, cache); + if (ret) { + btrfs_remove_free_space_cache(cache); + goto error; + } + trace_btrfs_add_block_group(info, cache, 0); + btrfs_update_space_info(info, cache->flags, key->offset, + cache->used, cache->bytes_super, &space_info); + + cache->space_info = space_info; + + link_block_group(cache); + + set_avail_alloc_bits(info, cache->flags); + if (btrfs_chunk_readonly(info, cache->start)) { + inc_block_group_ro(cache, 1); + } else if (cache->used == 0) { + ASSERT(list_empty(&cache->bg_list)); + btrfs_mark_bg_unused(cache); + } + return 0; +error: + btrfs_put_block_group(cache); + return ret; +} + int btrfs_read_block_groups(struct btrfs_fs_info *info) { struct btrfs_path *path; int ret; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; struct btrfs_space_info *space_info; struct btrfs_key key; - struct btrfs_key found_key; - struct extent_buffer *leaf; int need_clear = 0; u64 cache_gen; - u64 feature; - int mixed; - - feature = btrfs_super_incompat_flags(info->super_copy); - mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS); key.objectid = 0; key.offset = 0; @@ -1726,108 +1815,13 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) if (ret != 0) goto error; - leaf = path->nodes[0]; - btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - - cache = btrfs_create_block_group_cache(info, found_key.objectid, - found_key.offset); - if (!cache) { - ret = -ENOMEM; - goto error; - } - - if (need_clear) { - /* - * When we mount with old space cache, we need to - * set BTRFS_DC_CLEAR and set dirty flag. - * - * a) Setting 'BTRFS_DC_CLEAR' makes sure that we - * truncate the old free space cache inode and - * setup a new one. - * b) Setting 'dirty flag' makes sure that we flush - * the new space cache info onto disk. - */ - if (btrfs_test_opt(info, SPACE_CACHE)) - cache->disk_cache_state = BTRFS_DC_CLEAR; - } - - read_extent_buffer(leaf, &cache->item, - btrfs_item_ptr_offset(leaf, path->slots[0]), - sizeof(cache->item)); - cache->flags = btrfs_block_group_flags(&cache->item); - if (!mixed && - ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) && - (cache->flags & BTRFS_BLOCK_GROUP_DATA))) { - btrfs_err(info, -"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", - cache->key.objectid); - btrfs_put_block_group(cache); - ret = -EINVAL; + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + ret = read_one_block_group(info, path, &key, need_clear); + if (ret < 0) goto error; - } - - key.objectid = found_key.objectid + found_key.offset; + key.objectid += key.offset; + key.offset = 0; btrfs_release_path(path); - - /* - * We need to exclude the super stripes now so that the space - * info has super bytes accounted for, otherwise we'll think - * we have more space than we actually do. - */ - ret = exclude_super_stripes(cache); - if (ret) { - /* - * We may have excluded something, so call this just in - * case. - */ - btrfs_free_excluded_extents(cache); - btrfs_put_block_group(cache); - goto error; - } - - /* - * Check for two cases, either we are full, and therefore - * don't need to bother with the caching work since we won't - * find any space, or we are empty, and we can just add all - * the space in and be done with it. This saves us _a_lot_ of - * time, particularly in the full case. - */ - if (found_key.offset == btrfs_block_group_used(&cache->item)) { - cache->last_byte_to_unpin = (u64)-1; - cache->cached = BTRFS_CACHE_FINISHED; - btrfs_free_excluded_extents(cache); - } else if (btrfs_block_group_used(&cache->item) == 0) { - cache->last_byte_to_unpin = (u64)-1; - cache->cached = BTRFS_CACHE_FINISHED; - add_new_free_space(cache, found_key.objectid, - found_key.objectid + - found_key.offset); - btrfs_free_excluded_extents(cache); - } - - ret = btrfs_add_block_group_cache(info, cache); - if (ret) { - btrfs_remove_free_space_cache(cache); - btrfs_put_block_group(cache); - goto error; - } - - trace_btrfs_add_block_group(info, cache, 0); - btrfs_update_space_info(info, cache->flags, found_key.offset, - btrfs_block_group_used(&cache->item), - cache->bytes_super, &space_info); - - cache->space_info = space_info; - - link_block_group(cache); - - set_avail_alloc_bits(info, cache->flags); - if (btrfs_chunk_readonly(info, cache->key.objectid)) { - inc_block_group_ro(cache, 1); - } else if (btrfs_block_group_used(&cache->item) == 0) { - ASSERT(list_empty(&cache->bg_list)); - btrfs_mark_bg_unused(cache); - } } list_for_each_entry_rcu(space_info, &info->space_info, list) { @@ -1861,7 +1855,7 @@ error: void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_root *extent_root = fs_info->extent_root; struct btrfs_block_group_item item; struct btrfs_key key; @@ -1872,14 +1866,19 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) while (!list_empty(&trans->new_bgs)) { block_group = list_first_entry(&trans->new_bgs, - struct btrfs_block_group_cache, + struct btrfs_block_group, bg_list); if (ret) goto next; spin_lock(&block_group->lock); - memcpy(&item, &block_group->item, sizeof(item)); - memcpy(&key, &block_group->key, sizeof(key)); + btrfs_set_stack_block_group_used(&item, block_group->used); + btrfs_set_stack_block_group_chunk_objectid(&item, + BTRFS_FIRST_CHUNK_TREE_OBJECTID); + btrfs_set_stack_block_group_flags(&item, block_group->flags); + key.objectid = block_group->start; + key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; + key.offset = block_group->length; spin_unlock(&block_group->lock); ret = btrfs_insert_item(trans, extent_root, &key, &item, @@ -1902,7 +1901,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, u64 type, u64 chunk_offset, u64 size) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; int ret; btrfs_set_log_full_commit(trans); @@ -1911,11 +1910,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, if (!cache) return -ENOMEM; - btrfs_set_block_group_used(&cache->item, bytes_used); - btrfs_set_block_group_chunk_objectid(&cache->item, - BTRFS_FIRST_CHUNK_TREE_OBJECTID); - btrfs_set_block_group_flags(&cache->item, type); - + cache->used = bytes_used; cache->flags = type; cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; @@ -2022,8 +2017,17 @@ static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags) return flags; } -int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache) - +/* + * Mark one block group RO, can be called several times for the same block + * group. + * + * @cache: the destination block group + * @do_chunk_alloc: whether need to do chunk pre-allocation, this is to + * ensure we still have some free space after marking this + * block group RO. + */ +int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, + bool do_chunk_alloc) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_trans_handle *trans; @@ -2053,25 +2057,29 @@ again: goto again; } - /* - * if we are changing raid levels, try to allocate a corresponding - * block group with the new raid level. - */ - alloc_flags = update_block_group_flags(fs_info, cache->flags); - if (alloc_flags != cache->flags) { - ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); + if (do_chunk_alloc) { /* - * ENOSPC is allowed here, we may have enough space - * already allocated at the new raid level to - * carry on + * If we are changing raid levels, try to allocate a + * corresponding block group with the new raid level. */ - if (ret == -ENOSPC) - ret = 0; - if (ret < 0) - goto out; + alloc_flags = update_block_group_flags(fs_info, cache->flags); + if (alloc_flags != cache->flags) { + ret = btrfs_chunk_alloc(trans, alloc_flags, + CHUNK_ALLOC_FORCE); + /* + * ENOSPC is allowed here, we may have enough space + * already allocated at the new raid level to carry on + */ + if (ret == -ENOSPC) + ret = 0; + if (ret < 0) + goto out; + } } - ret = inc_block_group_ro(cache, 0); + ret = inc_block_group_ro(cache, !do_chunk_alloc); + if (!do_chunk_alloc) + goto unlock_out; if (!ret) goto out; alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags); @@ -2086,13 +2094,14 @@ out: check_system_chunk(trans, alloc_flags); mutex_unlock(&fs_info->chunk_mutex); } +unlock_out: mutex_unlock(&fs_info->ro_block_group_mutex); btrfs_end_transaction(trans); return ret; } -void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache) +void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) { struct btrfs_space_info *sinfo = cache->space_info; u64 num_bytes; @@ -2102,9 +2111,8 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache) spin_lock(&sinfo->lock); spin_lock(&cache->lock); if (!--cache->ro) { - num_bytes = cache->key.offset - cache->reserved - - cache->pinned - cache->bytes_super - - btrfs_block_group_used(&cache->item); + num_bytes = cache->length - cache->reserved - + cache->pinned - cache->bytes_super - cache->used; sinfo->bytes_readonly -= num_bytes; list_del_init(&cache->ro_list); } @@ -2114,15 +2122,21 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache) static int write_one_cache_group(struct btrfs_trans_handle *trans, struct btrfs_path *path, - struct btrfs_block_group_cache *cache) + struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; struct btrfs_root *extent_root = fs_info->extent_root; unsigned long bi; struct extent_buffer *leaf; + struct btrfs_block_group_item bgi; + struct btrfs_key key; + + key.objectid = cache->start; + key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; + key.offset = cache->length; - ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1); + ret = btrfs_search_slot(trans, extent_root, &key, path, 0, 1); if (ret) { if (ret > 0) ret = -ENOENT; @@ -2131,7 +2145,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans, leaf = path->nodes[0]; bi = btrfs_item_ptr_offset(leaf, path->slots[0]); - write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item)); + btrfs_set_stack_block_group_used(&bgi, cache->used); + btrfs_set_stack_block_group_chunk_objectid(&bgi, + BTRFS_FIRST_CHUNK_TREE_OBJECTID); + btrfs_set_stack_block_group_flags(&bgi, cache->flags); + write_extent_buffer(leaf, &bgi, bi, sizeof(bgi)); btrfs_mark_buffer_dirty(leaf); fail: btrfs_release_path(path); @@ -2139,7 +2157,7 @@ fail: } -static int cache_save_setup(struct btrfs_block_group_cache *block_group, +static int cache_save_setup(struct btrfs_block_group *block_group, struct btrfs_trans_handle *trans, struct btrfs_path *path) { @@ -2157,7 +2175,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, * If this block group is smaller than 100 megs don't bother caching the * block group. */ - if (block_group->key.offset < (100 * SZ_1M)) { + if (block_group->length < (100 * SZ_1M)) { spin_lock(&block_group->lock); block_group->disk_cache_state = BTRFS_DC_WRITTEN; spin_unlock(&block_group->lock); @@ -2258,7 +2276,7 @@ again: * taking up quite a bit since it's not folded into the other space * cache. */ - num_pages = div_u64(block_group->key.offset, SZ_256M); + num_pages = div_u64(block_group->length, SZ_256M); if (!num_pages) num_pages = 1; @@ -2303,7 +2321,7 @@ out: int btrfs_setup_space_cache(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *cache, *tmp; + struct btrfs_block_group *cache, *tmp; struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_path *path; @@ -2341,7 +2359,7 @@ int btrfs_setup_space_cache(struct btrfs_trans_handle *trans) int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; struct btrfs_transaction *cur_trans = trans->transaction; int ret = 0; int should_put; @@ -2378,8 +2396,7 @@ again: while (!list_empty(&dirty)) { bool drop_reserve = true; - cache = list_first_entry(&dirty, - struct btrfs_block_group_cache, + cache = list_first_entry(&dirty, struct btrfs_block_group, dirty_list); /* * This can happen if something re-dirties a block group that @@ -2504,7 +2521,7 @@ again: int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; struct btrfs_transaction *cur_trans = trans->transaction; int ret = 0; int should_put; @@ -2534,7 +2551,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) spin_lock(&cur_trans->dirty_bgs_lock); while (!list_empty(&cur_trans->dirty_bgs)) { cache = list_first_entry(&cur_trans->dirty_bgs, - struct btrfs_block_group_cache, + struct btrfs_block_group, dirty_list); /* @@ -2616,7 +2633,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) * to use it without any locking */ while (!list_empty(io)) { - cache = list_first_entry(io, struct btrfs_block_group_cache, + cache = list_first_entry(io, struct btrfs_block_group, io_list); list_del_init(&cache->io_list); btrfs_wait_cache_io(trans, cache, path); @@ -2631,7 +2648,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, int alloc) { struct btrfs_fs_info *info = trans->fs_info; - struct btrfs_block_group_cache *cache = NULL; + struct btrfs_block_group *cache = NULL; u64 total = num_bytes; u64 old_val; u64 byte_in_group; @@ -2662,11 +2679,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, * is because we need the unpinning stage to actually add the * space back to the block group, otherwise we will leak space. */ - if (!alloc && cache->cached == BTRFS_CACHE_NO) + if (!alloc && !btrfs_block_group_done(cache)) btrfs_cache_block_group(cache, 1); - byte_in_group = bytenr - cache->key.objectid; - WARN_ON(byte_in_group > cache->key.offset); + byte_in_group = bytenr - cache->start; + WARN_ON(byte_in_group > cache->length); spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); @@ -2675,11 +2692,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, cache->disk_cache_state < BTRFS_DC_CLEAR) cache->disk_cache_state = BTRFS_DC_CLEAR; - old_val = btrfs_block_group_used(&cache->item); - num_bytes = min(total, cache->key.offset - byte_in_group); + old_val = cache->used; + num_bytes = min(total, cache->length - byte_in_group); if (alloc) { old_val += num_bytes; - btrfs_set_block_group_used(&cache->item, old_val); + cache->used = old_val; cache->reserved -= num_bytes; cache->space_info->bytes_reserved -= num_bytes; cache->space_info->bytes_used += num_bytes; @@ -2688,7 +2705,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&cache->space_info->lock); } else { old_val -= num_bytes; - btrfs_set_block_group_used(&cache->item, old_val); + cache->used = old_val; cache->pinned += num_bytes; btrfs_space_info_update_bytes_pinned(info, cache->space_info, num_bytes); @@ -2746,7 +2763,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, * reservation and the block group has become read only we cannot make the * reservation and return -EAGAIN, otherwise this function always succeeds. */ -int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, +int btrfs_add_reserved_bytes(struct btrfs_block_group *cache, u64 ram_bytes, u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; @@ -2782,7 +2799,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, * A and before transaction A commits you free that leaf, you call this with * reserve set to 0 in order to clear the reservation. */ -void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, +void btrfs_free_reserved_bytes(struct btrfs_block_group *cache, u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; @@ -2988,9 +3005,7 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type) } /* - * If @is_allocation is true, reserve space in the system space info necessary - * for allocating a chunk, otherwise if it's false, reserve space necessary for - * removing a chunk. + * Reserve space in the system space for allocating or removing a chunk */ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) { @@ -3047,7 +3062,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) void btrfs_put_block_group_cache(struct btrfs_fs_info *info) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; u64 last = 0; while (1) { @@ -3075,7 +3090,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) spin_unlock(&block_group->lock); ASSERT(block_group->io_ctl.inode == NULL); iput(inode); - last = block_group->key.objectid + block_group->key.offset; + last = block_group->start + block_group->length; btrfs_put_block_group(block_group); } } @@ -3087,7 +3102,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) */ int btrfs_free_block_groups(struct btrfs_fs_info *info) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_caching_control *caching_ctl; struct rb_node *n; @@ -3104,7 +3119,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) spin_lock(&info->unused_bgs_lock); while (!list_empty(&info->unused_bgs)) { block_group = list_first_entry(&info->unused_bgs, - struct btrfs_block_group_cache, + struct btrfs_block_group, bg_list); list_del_init(&block_group->bg_list); btrfs_put_block_group(block_group); @@ -3113,7 +3128,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) spin_lock(&info->block_group_cache_lock); while ((n = rb_last(&info->block_group_cache_tree)) != NULL) { - block_group = rb_entry(n, struct btrfs_block_group_cache, + block_group = rb_entry(n, struct btrfs_block_group, cache_node); rb_erase(&block_group->cache_node, &info->block_group_cache_tree); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index c391800388dd..9b409676c4b2 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -34,7 +34,7 @@ struct btrfs_caching_control { struct mutex mutex; wait_queue_head_t wait; struct btrfs_work work; - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; u64 progress; refcount_t count; }; @@ -42,14 +42,15 @@ struct btrfs_caching_control { /* Once caching_thread() finds this much free space, it will wake up waiters. */ #define CACHING_CTL_WAKE_UP SZ_2M -struct btrfs_block_group_cache { - struct btrfs_key key; - struct btrfs_block_group_item item; +struct btrfs_block_group { struct btrfs_fs_info *fs_info; struct inode *inode; spinlock_t lock; + u64 start; + u64 length; u64 pinned; u64 reserved; + u64 used; u64 delalloc_bytes; u64 bytes_super; u64 flags; @@ -159,7 +160,7 @@ struct btrfs_block_group_cache { #ifdef CONFIG_BTRFS_DEBUG static inline int btrfs_should_fragment_free_space( - struct btrfs_block_group_cache *block_group) + struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; @@ -170,29 +171,29 @@ static inline int btrfs_should_fragment_free_space( } #endif -struct btrfs_block_group_cache *btrfs_lookup_first_block_group( +struct btrfs_block_group *btrfs_lookup_first_block_group( struct btrfs_fs_info *info, u64 bytenr); -struct btrfs_block_group_cache *btrfs_lookup_block_group( +struct btrfs_block_group *btrfs_lookup_block_group( struct btrfs_fs_info *info, u64 bytenr); -struct btrfs_block_group_cache *btrfs_next_block_group( - struct btrfs_block_group_cache *cache); -void btrfs_get_block_group(struct btrfs_block_group_cache *cache); -void btrfs_put_block_group(struct btrfs_block_group_cache *cache); +struct btrfs_block_group *btrfs_next_block_group( + struct btrfs_block_group *cache); +void btrfs_get_block_group(struct btrfs_block_group *cache); +void btrfs_put_block_group(struct btrfs_block_group *cache); void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, const u64 start); -void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg); +void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg); bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); -void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg); -void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache, +void btrfs_wait_nocow_writers(struct btrfs_block_group *bg); +void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes); -int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache); -int btrfs_cache_block_group(struct btrfs_block_group_cache *cache, +int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache); +int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only); void btrfs_put_caching_control(struct btrfs_caching_control *ctl); struct btrfs_caching_control *btrfs_get_caching_control( - struct btrfs_block_group_cache *cache); -u64 add_new_free_space(struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *cache); +u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end); struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( struct btrfs_fs_info *fs_info, @@ -200,21 +201,22 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( int btrfs_remove_block_group(struct btrfs_trans_handle *trans, u64 group_start, struct extent_map *em); void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info); -void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg); +void btrfs_mark_bg_unused(struct btrfs_block_group *bg); int btrfs_read_block_groups(struct btrfs_fs_info *info); int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, u64 type, u64 chunk_offset, u64 size); void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans); -int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache); -void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache); +int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, + bool do_chunk_alloc); +void btrfs_dec_block_group_ro(struct btrfs_block_group *cache); int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans); int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans); int btrfs_setup_space_cache(struct btrfs_trans_handle *trans); int btrfs_update_block_group(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, int alloc); -int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, +int btrfs_add_reserved_bytes(struct btrfs_block_group *cache, u64 ram_bytes, u64 num_bytes, int delalloc); -void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, +void btrfs_free_reserved_bytes(struct btrfs_block_group *cache, u64 num_bytes, int delalloc); int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, enum btrfs_chunk_alloc_enum force); @@ -239,8 +241,7 @@ static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info) return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); } -static inline int btrfs_block_group_cache_done( - struct btrfs_block_group_cache *cache) +static inline int btrfs_block_group_done(struct btrfs_block_group *cache) { smp_mb(); return cache->cached == BTRFS_CACHE_FINISHED || diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index f853835c409c..4e12a477d32e 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -63,9 +63,6 @@ struct btrfs_inode { /* held while logging the inode in tree-log.c */ struct mutex log_mutex; - /* held while doing delalloc reservations */ - struct mutex delalloc_mutex; - /* used to order data wrt metadata */ struct btrfs_ordered_inode_tree ordered_tree; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b05b361e2062..ee834ef7beb4 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -29,6 +29,41 @@ #include "extent_io.h" #include "extent_map.h" +int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, + u64 start, struct page **pages, unsigned long *out_pages, + unsigned long *total_in, unsigned long *total_out); +int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb); +int zlib_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, unsigned long start_byte, size_t srclen, + size_t destlen); +struct list_head *zlib_alloc_workspace(unsigned int level); +void zlib_free_workspace(struct list_head *ws); +struct list_head *zlib_get_workspace(unsigned int level); + +int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, + u64 start, struct page **pages, unsigned long *out_pages, + unsigned long *total_in, unsigned long *total_out); +int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb); +int lzo_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, unsigned long start_byte, size_t srclen, + size_t destlen); +struct list_head *lzo_alloc_workspace(unsigned int level); +void lzo_free_workspace(struct list_head *ws); + +int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, + u64 start, struct page **pages, unsigned long *out_pages, + unsigned long *total_in, unsigned long *total_out); +int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb); +int zstd_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, unsigned long start_byte, size_t srclen, + size_t destlen); +void zstd_init_workspace_manager(void); +void zstd_cleanup_workspace_manager(void); +struct list_head *zstd_alloc_workspace(unsigned int level); +void zstd_free_workspace(struct list_head *ws); +struct list_head *zstd_get_workspace(unsigned int level); +void zstd_put_workspace(struct list_head *ws); + static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" }; const char* btrfs_compress_type2str(enum btrfs_compression_type type) @@ -39,6 +74,8 @@ const char* btrfs_compress_type2str(enum btrfs_compression_type type) case BTRFS_COMPRESS_ZSTD: case BTRFS_COMPRESS_NONE: return btrfs_compress_types[type]; + default: + break; } return NULL; @@ -60,6 +97,70 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len) return false; } +static int compression_compress_pages(int type, struct list_head *ws, + struct address_space *mapping, u64 start, struct page **pages, + unsigned long *out_pages, unsigned long *total_in, + unsigned long *total_out) +{ + switch (type) { + case BTRFS_COMPRESS_ZLIB: + return zlib_compress_pages(ws, mapping, start, pages, + out_pages, total_in, total_out); + case BTRFS_COMPRESS_LZO: + return lzo_compress_pages(ws, mapping, start, pages, + out_pages, total_in, total_out); + case BTRFS_COMPRESS_ZSTD: + return zstd_compress_pages(ws, mapping, start, pages, + out_pages, total_in, total_out); + case BTRFS_COMPRESS_NONE: + default: + /* + * This can't happen, the type is validated several times + * before we get here. As a sane fallback, return what the + * callers will understand as 'no compression happened'. + */ + return -E2BIG; + } +} + +static int compression_decompress_bio(int type, struct list_head *ws, + struct compressed_bio *cb) +{ + switch (type) { + case BTRFS_COMPRESS_ZLIB: return zlib_decompress_bio(ws, cb); + case BTRFS_COMPRESS_LZO: return lzo_decompress_bio(ws, cb); + case BTRFS_COMPRESS_ZSTD: return zstd_decompress_bio(ws, cb); + case BTRFS_COMPRESS_NONE: + default: + /* + * This can't happen, the type is validated several times + * before we get here. + */ + BUG(); + } +} + +static int compression_decompress(int type, struct list_head *ws, + unsigned char *data_in, struct page *dest_page, + unsigned long start_byte, size_t srclen, size_t destlen) +{ + switch (type) { + case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page, + start_byte, srclen, destlen); + case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_page, + start_byte, srclen, destlen); + case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page, + start_byte, srclen, destlen); + case BTRFS_COMPRESS_NONE: + default: + /* + * This can't happen, the type is validated several times + * before we get here. + */ + BUG(); + } +} + static int btrfs_decompress_bio(struct compressed_bio *cb); static inline int compressed_bio_size(struct btrfs_fs_info *fs_info, @@ -311,7 +412,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long compressed_len, struct page **compressed_pages, unsigned long nr_pages, - unsigned int write_flags) + unsigned int write_flags, + struct cgroup_subsys_state *blkcg_css) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct bio *bio = NULL; @@ -320,7 +422,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, int pg_index = 0; struct page *page; u64 first_byte = disk_start; - struct block_device *bdev; blk_status_t ret; int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; @@ -339,13 +440,15 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, cb->orig_bio = NULL; cb->nr_pages = nr_pages; - bdev = fs_info->fs_devices->latest_bdev; - bio = btrfs_bio_alloc(first_byte); - bio_set_dev(bio, bdev); bio->bi_opf = REQ_OP_WRITE | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; + + if (blkcg_css) { + bio->bi_opf |= REQ_CGROUP_PUNT; + bio_associate_blkg_from_css(bio, blkcg_css); + } refcount_set(&cb->pending_bios, 1); /* create and submit bios for the compressed pages */ @@ -378,14 +481,13 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, BUG_ON(ret); /* -ENOMEM */ } - ret = btrfs_map_bio(fs_info, bio, 0, 1); + ret = btrfs_map_bio(fs_info, bio, 0); if (ret) { bio->bi_status = ret; bio_endio(bio); } bio = btrfs_bio_alloc(first_byte); - bio_set_dev(bio, bdev); bio->bi_opf = REQ_OP_WRITE | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; @@ -409,7 +511,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, BUG_ON(ret); /* -ENOMEM */ } - ret = btrfs_map_bio(fs_info, bio, 0, 1); + ret = btrfs_map_bio(fs_info, bio, 0); if (ret) { bio->bi_status = ret; bio_endio(bio); @@ -553,7 +655,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, unsigned long nr_pages; unsigned long pg_index; struct page *page; - struct block_device *bdev; struct bio *comp_bio; u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9; u64 em_len; @@ -604,8 +705,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, if (!cb->compressed_pages) goto fail1; - bdev = fs_info->fs_devices->latest_bdev; - for (pg_index = 0; pg_index < nr_pages; pg_index++) { cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS | __GFP_HIGHMEM); @@ -624,7 +723,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, cb->len = bio->bi_iter.bi_size; comp_bio = btrfs_bio_alloc(cur_disk_byte); - bio_set_dev(comp_bio, bdev); comp_bio->bi_opf = REQ_OP_READ; comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; @@ -668,14 +766,13 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, fs_info->sectorsize); sums += csum_size * nr_sectors; - ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0); + ret = btrfs_map_bio(fs_info, comp_bio, mirror_num); if (ret) { comp_bio->bi_status = ret; bio_endio(comp_bio); } comp_bio = btrfs_bio_alloc(cur_disk_byte); - bio_set_dev(comp_bio, bdev); comp_bio->bi_opf = REQ_OP_READ; comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; @@ -693,7 +790,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, BUG_ON(ret); /* -ENOMEM */ } - ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0); + ret = btrfs_map_bio(fs_info, comp_bio, mirror_num); if (ret) { comp_bio->bi_status = ret; bio_endio(comp_bio); @@ -764,26 +861,6 @@ struct heuristic_ws { static struct workspace_manager heuristic_wsm; -static void heuristic_init_workspace_manager(void) -{ - btrfs_init_workspace_manager(&heuristic_wsm, &btrfs_heuristic_compress); -} - -static void heuristic_cleanup_workspace_manager(void) -{ - btrfs_cleanup_workspace_manager(&heuristic_wsm); -} - -static struct list_head *heuristic_get_workspace(unsigned int level) -{ - return btrfs_get_workspace(&heuristic_wsm, level); -} - -static void heuristic_put_workspace(struct list_head *ws) -{ - btrfs_put_workspace(&heuristic_wsm, ws); -} - static void free_heuristic_ws(struct list_head *ws) { struct heuristic_ws *workspace; @@ -824,12 +901,7 @@ fail: } const struct btrfs_compress_op btrfs_heuristic_compress = { - .init_workspace_manager = heuristic_init_workspace_manager, - .cleanup_workspace_manager = heuristic_cleanup_workspace_manager, - .get_workspace = heuristic_get_workspace, - .put_workspace = heuristic_put_workspace, - .alloc_workspace = alloc_heuristic_ws, - .free_workspace = free_heuristic_ws, + .workspace_manager = &heuristic_wsm, }; static const struct btrfs_compress_op * const btrfs_compress_op[] = { @@ -840,13 +912,44 @@ static const struct btrfs_compress_op * const btrfs_compress_op[] = { &btrfs_zstd_compress, }; -void btrfs_init_workspace_manager(struct workspace_manager *wsm, - const struct btrfs_compress_op *ops) +static struct list_head *alloc_workspace(int type, unsigned int level) { - struct list_head *workspace; + switch (type) { + case BTRFS_COMPRESS_NONE: return alloc_heuristic_ws(level); + case BTRFS_COMPRESS_ZLIB: return zlib_alloc_workspace(level); + case BTRFS_COMPRESS_LZO: return lzo_alloc_workspace(level); + case BTRFS_COMPRESS_ZSTD: return zstd_alloc_workspace(level); + default: + /* + * This can't happen, the type is validated several times + * before we get here. + */ + BUG(); + } +} - wsm->ops = ops; +static void free_workspace(int type, struct list_head *ws) +{ + switch (type) { + case BTRFS_COMPRESS_NONE: return free_heuristic_ws(ws); + case BTRFS_COMPRESS_ZLIB: return zlib_free_workspace(ws); + case BTRFS_COMPRESS_LZO: return lzo_free_workspace(ws); + case BTRFS_COMPRESS_ZSTD: return zstd_free_workspace(ws); + default: + /* + * This can't happen, the type is validated several times + * before we get here. + */ + BUG(); + } +} + +static void btrfs_init_workspace_manager(int type) +{ + struct workspace_manager *wsm; + struct list_head *workspace; + wsm = btrfs_compress_op[type]->workspace_manager; INIT_LIST_HEAD(&wsm->idle_ws); spin_lock_init(&wsm->ws_lock); atomic_set(&wsm->total_ws, 0); @@ -856,7 +959,7 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm, * Preallocate one workspace for each compression type so we can * guarantee forward progress in the worst case */ - workspace = wsm->ops->alloc_workspace(0); + workspace = alloc_workspace(type, 0); if (IS_ERR(workspace)) { pr_warn( "BTRFS: cannot preallocate compression workspace, will try later\n"); @@ -867,14 +970,16 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm, } } -void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman) +static void btrfs_cleanup_workspace_manager(int type) { + struct workspace_manager *wsman; struct list_head *ws; + wsman = btrfs_compress_op[type]->workspace_manager; while (!list_empty(&wsman->idle_ws)) { ws = wsman->idle_ws.next; list_del(ws); - wsman->ops->free_workspace(ws); + free_workspace(type, ws); atomic_dec(&wsman->total_ws); } } @@ -885,9 +990,9 @@ void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman) * Preallocation makes a forward progress guarantees and we do not return * errors. */ -struct list_head *btrfs_get_workspace(struct workspace_manager *wsm, - unsigned int level) +struct list_head *btrfs_get_workspace(int type, unsigned int level) { + struct workspace_manager *wsm; struct list_head *workspace; int cpus = num_online_cpus(); unsigned nofs_flag; @@ -897,6 +1002,7 @@ struct list_head *btrfs_get_workspace(struct workspace_manager *wsm, wait_queue_head_t *ws_wait; int *free_ws; + wsm = btrfs_compress_op[type]->workspace_manager; idle_ws = &wsm->idle_ws; ws_lock = &wsm->ws_lock; total_ws = &wsm->total_ws; @@ -932,7 +1038,7 @@ again: * context of btrfs_compress_bio/btrfs_compress_pages */ nofs_flag = memalloc_nofs_save(); - workspace = wsm->ops->alloc_workspace(level); + workspace = alloc_workspace(type, level); memalloc_nofs_restore(nofs_flag); if (IS_ERR(workspace)) { @@ -965,21 +1071,34 @@ again: static struct list_head *get_workspace(int type, int level) { - return btrfs_compress_op[type]->get_workspace(level); + switch (type) { + case BTRFS_COMPRESS_NONE: return btrfs_get_workspace(type, level); + case BTRFS_COMPRESS_ZLIB: return zlib_get_workspace(level); + case BTRFS_COMPRESS_LZO: return btrfs_get_workspace(type, level); + case BTRFS_COMPRESS_ZSTD: return zstd_get_workspace(level); + default: + /* + * This can't happen, the type is validated several times + * before we get here. + */ + BUG(); + } } /* * put a workspace struct back on the list or free it if we have enough * idle ones sitting around */ -void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws) +void btrfs_put_workspace(int type, struct list_head *ws) { + struct workspace_manager *wsm; struct list_head *idle_ws; spinlock_t *ws_lock; atomic_t *total_ws; wait_queue_head_t *ws_wait; int *free_ws; + wsm = btrfs_compress_op[type]->workspace_manager; idle_ws = &wsm->idle_ws; ws_lock = &wsm->ws_lock; total_ws = &wsm->total_ws; @@ -995,7 +1114,7 @@ void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws) } spin_unlock(ws_lock); - wsm->ops->free_workspace(ws); + free_workspace(type, ws); atomic_dec(total_ws); wake: cond_wake_up(ws_wait); @@ -1003,7 +1122,18 @@ wake: static void put_workspace(int type, struct list_head *ws) { - return btrfs_compress_op[type]->put_workspace(ws); + switch (type) { + case BTRFS_COMPRESS_NONE: return btrfs_put_workspace(type, ws); + case BTRFS_COMPRESS_ZLIB: return btrfs_put_workspace(type, ws); + case BTRFS_COMPRESS_LZO: return btrfs_put_workspace(type, ws); + case BTRFS_COMPRESS_ZSTD: return zstd_put_workspace(ws); + default: + /* + * This can't happen, the type is validated several times + * before we get here. + */ + BUG(); + } } /* @@ -1042,10 +1172,8 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping, level = btrfs_compress_set_level(type, level); workspace = get_workspace(type, level); - ret = btrfs_compress_op[type]->compress_pages(workspace, mapping, - start, pages, - out_pages, - total_in, total_out); + ret = compression_compress_pages(type, workspace, mapping, start, pages, + out_pages, total_in, total_out); put_workspace(type, workspace); return ret; } @@ -1071,7 +1199,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb) int type = cb->compress_type; workspace = get_workspace(type, 0); - ret = btrfs_compress_op[type]->decompress_bio(workspace, cb); + ret = compression_decompress_bio(type, workspace, cb); put_workspace(type, workspace); return ret; @@ -1089,9 +1217,8 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page, int ret; workspace = get_workspace(type, 0); - ret = btrfs_compress_op[type]->decompress(workspace, data_in, - dest_page, start_byte, - srclen, destlen); + ret = compression_decompress(type, workspace, data_in, dest_page, + start_byte, srclen, destlen); put_workspace(type, workspace); return ret; @@ -1099,18 +1226,18 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page, void __init btrfs_init_compress(void) { - int i; - - for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++) - btrfs_compress_op[i]->init_workspace_manager(); + btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE); + btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB); + btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO); + zstd_init_workspace_manager(); } void __cold btrfs_exit_compress(void) { - int i; - - for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++) - btrfs_compress_op[i]->cleanup_workspace_manager(); + btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_NONE); + btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_ZLIB); + btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_LZO); + zstd_cleanup_workspace_manager(); } /* diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 4cb8be9ff88b..d253f7aa8ed5 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -93,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long compressed_len, struct page **compressed_pages, unsigned long nr_pages, - unsigned int write_flags); + unsigned int write_flags, + struct cgroup_subsys_state *blkcg_css); blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags); @@ -104,11 +105,10 @@ enum btrfs_compression_type { BTRFS_COMPRESS_ZLIB = 1, BTRFS_COMPRESS_LZO = 2, BTRFS_COMPRESS_ZSTD = 3, - BTRFS_COMPRESS_TYPES = 3, + BTRFS_NR_COMPRESS_TYPES = 4, }; struct workspace_manager { - const struct btrfs_compress_op *ops; struct list_head idle_ws; spinlock_t ws_lock; /* Number of free workspaces */ @@ -119,50 +119,18 @@ struct workspace_manager { wait_queue_head_t ws_wait; }; -void btrfs_init_workspace_manager(struct workspace_manager *wsm, - const struct btrfs_compress_op *ops); -struct list_head *btrfs_get_workspace(struct workspace_manager *wsm, - unsigned int level); -void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws); -void btrfs_cleanup_workspace_manager(struct workspace_manager *wsm); +struct list_head *btrfs_get_workspace(int type, unsigned int level); +void btrfs_put_workspace(int type, struct list_head *ws); struct btrfs_compress_op { - void (*init_workspace_manager)(void); - - void (*cleanup_workspace_manager)(void); - - struct list_head *(*get_workspace)(unsigned int level); - - void (*put_workspace)(struct list_head *ws); - - struct list_head *(*alloc_workspace)(unsigned int level); - - void (*free_workspace)(struct list_head *workspace); - - int (*compress_pages)(struct list_head *workspace, - struct address_space *mapping, - u64 start, - struct page **pages, - unsigned long *out_pages, - unsigned long *total_in, - unsigned long *total_out); - - int (*decompress_bio)(struct list_head *workspace, - struct compressed_bio *cb); - - int (*decompress)(struct list_head *workspace, - unsigned char *data_in, - struct page *dest_page, - unsigned long start_byte, - size_t srclen, size_t destlen); - + struct workspace_manager *workspace_manager; /* Maximum level supported by the compression algorithm */ unsigned int max_level; unsigned int default_level; }; /* The heuristic workspaces are managed via the 0th workspace manager */ -#define BTRFS_NR_WORKSPACE_MANAGERS (BTRFS_COMPRESS_TYPES + 1) +#define BTRFS_NR_WORKSPACE_MANAGERS BTRFS_NR_COMPRESS_TYPES extern const struct btrfs_compress_op btrfs_heuristic_compress; extern const struct btrfs_compress_op btrfs_zlib_compress; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index e59cde204b2f..5b6e86aaf2e1 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -32,8 +32,13 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, static const struct btrfs_csums { u16 size; const char *name; + const char *driver; } btrfs_csums[] = { [BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" }, + [BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" }, + [BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" }, + [BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b", + .driver = "blake2b-256" }, }; int btrfs_super_csum_size(const struct btrfs_super_block *s) @@ -51,34 +56,25 @@ const char *btrfs_super_csum_name(u16 csum_type) return btrfs_csums[csum_type].name; } -struct btrfs_path *btrfs_alloc_path(void) +/* + * Return driver name if defined, otherwise the name that's also a valid driver + * name + */ +const char *btrfs_super_csum_driver(u16 csum_type) { - return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS); + /* csum type is validated at mount time */ + return btrfs_csums[csum_type].driver ?: + btrfs_csums[csum_type].name; } -/* - * set all locked nodes in the path to blocking locks. This should - * be done before scheduling - */ -noinline void btrfs_set_path_blocking(struct btrfs_path *p) +size_t __const btrfs_get_num_csums(void) { - int i; - for (i = 0; i < BTRFS_MAX_LEVEL; i++) { - if (!p->nodes[i] || !p->locks[i]) - continue; - /* - * If we currently have a spinning reader or writer lock this - * will bump the count of blocking holders and drop the - * spinlock. - */ - if (p->locks[i] == BTRFS_READ_LOCK) { - btrfs_set_lock_blocking_read(p->nodes[i]); - p->locks[i] = BTRFS_READ_LOCK_BLOCKING; - } else if (p->locks[i] == BTRFS_WRITE_LOCK) { - btrfs_set_lock_blocking_write(p->nodes[i]); - p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING; - } - } + return ARRAY_SIZE(btrfs_csums); +} + +struct btrfs_path *btrfs_alloc_path(void) +{ + return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS); } /* this also releases the path */ @@ -1125,7 +1121,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV) parent_start = buf->start; - extent_buffer_get(cow); + atomic_inc(&cow->refs); ret = tree_mod_log_insert_root(root->node, cow, 1); BUG_ON(ret < 0); rcu_assign_pointer(root->node, cow); @@ -1563,7 +1559,7 @@ static int comp_keys(const struct btrfs_disk_key *disk, /* * same as comp_keys only with two btrfs_key's */ -int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2) +int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2) { if (k1->objectid > k2->objectid) return 1; @@ -2036,7 +2032,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, /* update the path */ if (left) { if (btrfs_header_nritems(left) > orig_slot) { - extent_buffer_get(left); + atomic_inc(&left->refs); /* left was locked after cow */ path->nodes[level] = left; path->slots[level + 1] -= 1; @@ -2379,32 +2375,6 @@ static noinline void unlock_up(struct btrfs_path *path, int level, } /* - * This releases any locks held in the path starting at level and - * going all the way up to the root. - * - * btrfs_search_slot will keep the lock held on higher nodes in a few - * corner cases, such as COW of the block at slot zero in the node. This - * ignores those rules, and it should only be called when there are no - * more updates to be done higher up in the tree. - */ -noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level) -{ - int i; - - if (path->keep_locks) - return; - - for (i = level; i < BTRFS_MAX_LEVEL; i++) { - if (!path->nodes[i]) - continue; - if (!path->locks[i]) - continue; - btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]); - path->locks[i] = 0; - } -} - -/* * helper function for btrfs_search_slot. The goal is to find a block * in cache without setting the path to blocking. If we find the block * we return zero and the path is unchanged. @@ -2652,7 +2622,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root, } else { b = root->commit_root; - extent_buffer_get(b); + atomic_inc(&b->refs); } level = btrfs_header_level(b); /* @@ -2785,12 +2755,10 @@ again: } while (b) { + int dec = 0; + level = btrfs_header_level(b); - /* - * setup the path here so we can release it under lock - * contention with the cow code - */ if (cow) { bool last_level = (level == (BTRFS_MAX_LEVEL - 1)); @@ -2861,73 +2829,7 @@ cow_done: if (ret < 0) goto done; - if (level != 0) { - int dec = 0; - if (ret && slot > 0) { - dec = 1; - slot -= 1; - } - p->slots[level] = slot; - err = setup_nodes_for_search(trans, root, p, b, level, - ins_len, &write_lock_level); - if (err == -EAGAIN) - goto again; - if (err) { - ret = err; - goto done; - } - b = p->nodes[level]; - slot = p->slots[level]; - - /* - * slot 0 is special, if we change the key - * we have to update the parent pointer - * which means we must have a write lock - * on the parent - */ - if (slot == 0 && ins_len && - write_lock_level < level + 1) { - write_lock_level = level + 1; - btrfs_release_path(p); - goto again; - } - - unlock_up(p, level, lowest_unlock, - min_write_lock_level, &write_lock_level); - - if (level == lowest_level) { - if (dec) - p->slots[level]++; - goto done; - } - - err = read_block_for_search(root, p, &b, level, - slot, key); - if (err == -EAGAIN) - goto again; - if (err) { - ret = err; - goto done; - } - - if (!p->skip_locking) { - level = btrfs_header_level(b); - if (level <= write_lock_level) { - if (!btrfs_try_tree_write_lock(b)) { - btrfs_set_path_blocking(p); - btrfs_tree_lock(b); - } - p->locks[level] = BTRFS_WRITE_LOCK; - } else { - if (!btrfs_tree_read_lock_atomic(b)) { - btrfs_set_path_blocking(p); - btrfs_tree_read_lock(b); - } - p->locks[level] = BTRFS_READ_LOCK; - } - p->nodes[level] = b; - } - } else { + if (level == 0) { p->slots[level] = slot; if (ins_len > 0 && btrfs_leaf_free_space(b) < ins_len) { @@ -2952,6 +2854,67 @@ cow_done: min_write_lock_level, NULL); goto done; } + if (ret && slot > 0) { + dec = 1; + slot--; + } + p->slots[level] = slot; + err = setup_nodes_for_search(trans, root, p, b, level, ins_len, + &write_lock_level); + if (err == -EAGAIN) + goto again; + if (err) { + ret = err; + goto done; + } + b = p->nodes[level]; + slot = p->slots[level]; + + /* + * Slot 0 is special, if we change the key we have to update + * the parent pointer which means we must have a write lock on + * the parent + */ + if (slot == 0 && ins_len && write_lock_level < level + 1) { + write_lock_level = level + 1; + btrfs_release_path(p); + goto again; + } + + unlock_up(p, level, lowest_unlock, min_write_lock_level, + &write_lock_level); + + if (level == lowest_level) { + if (dec) + p->slots[level]++; + goto done; + } + + err = read_block_for_search(root, p, &b, level, slot, key); + if (err == -EAGAIN) + goto again; + if (err) { + ret = err; + goto done; + } + + if (!p->skip_locking) { + level = btrfs_header_level(b); + if (level <= write_lock_level) { + if (!btrfs_try_tree_write_lock(b)) { + btrfs_set_path_blocking(p); + btrfs_tree_lock(b); + } + p->locks[level] = BTRFS_WRITE_LOCK; + } else { + if (!btrfs_tree_read_lock_atomic(b)) { + btrfs_set_path_blocking(p); + btrfs_tree_read_lock(b); + } + p->locks[level] = BTRFS_READ_LOCK; + } + p->nodes[level] = b; + } } ret = 1; done: @@ -3008,6 +2971,8 @@ again: p->locks[level] = BTRFS_READ_LOCK; while (b) { + int dec = 0; + level = btrfs_header_level(b); p->nodes[level] = b; @@ -3028,47 +2993,45 @@ again: if (ret < 0) goto done; - if (level != 0) { - int dec = 0; - if (ret && slot > 0) { - dec = 1; - slot -= 1; - } + if (level == 0) { p->slots[level] = slot; unlock_up(p, level, lowest_unlock, 0, NULL); + goto done; + } - if (level == lowest_level) { - if (dec) - p->slots[level]++; - goto done; - } + if (ret && slot > 0) { + dec = 1; + slot--; + } + p->slots[level] = slot; + unlock_up(p, level, lowest_unlock, 0, NULL); - err = read_block_for_search(root, p, &b, level, - slot, key); - if (err == -EAGAIN) - goto again; - if (err) { - ret = err; - goto done; - } + if (level == lowest_level) { + if (dec) + p->slots[level]++; + goto done; + } - level = btrfs_header_level(b); - if (!btrfs_tree_read_lock_atomic(b)) { - btrfs_set_path_blocking(p); - btrfs_tree_read_lock(b); - } - b = tree_mod_log_rewind(fs_info, p, b, time_seq); - if (!b) { - ret = -ENOMEM; - goto done; - } - p->locks[level] = BTRFS_READ_LOCK; - p->nodes[level] = b; - } else { - p->slots[level] = slot; - unlock_up(p, level, lowest_unlock, 0, NULL); + err = read_block_for_search(root, p, &b, level, slot, key); + if (err == -EAGAIN) + goto again; + if (err) { + ret = err; + goto done; + } + + level = btrfs_header_level(b); + if (!btrfs_tree_read_lock_atomic(b)) { + btrfs_set_path_blocking(p); + btrfs_tree_read_lock(b); + } + b = tree_mod_log_rewind(fs_info, p, b, time_seq); + if (!b) { + ret = -ENOMEM; goto done; } + p->locks[level] = BTRFS_READ_LOCK; + p->nodes[level] = b; } ret = 1; done: @@ -3433,7 +3396,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, free_extent_buffer(old); add_root_to_dirty_list(root); - extent_buffer_get(c); + atomic_inc(&c->refs); path->nodes[level] = c; path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; path->slots[level] = 0; @@ -4966,7 +4929,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, root_sub_used(root, leaf->len); - extent_buffer_get(leaf); + atomic_inc(&leaf->refs); btrfs_free_tree_block(trans, root, leaf, 0, 1); free_extent_buffer_stale(leaf); } @@ -5047,7 +5010,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, * for possible call to del_ptr below */ slot = path->slots[1]; - extent_buffer_get(leaf); + atomic_inc(&leaf->refs); btrfs_set_path_blocking(path); wret = push_leaf_left(trans, root, path, 1, 1, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index fe2b8765d9e6..b2e8fd8a8e59 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -28,6 +28,7 @@ #include <linux/dynamic_debug.h> #include <linux/refcount.h> #include <linux/crc32c.h> +#include "extent-io-tree.h" #include "extent_io.h" #include "extent_map.h" #include "async-thread.h" @@ -38,7 +39,7 @@ struct btrfs_transaction; struct btrfs_pending_snapshot; struct btrfs_delayed_ref_root; struct btrfs_space_info; -struct btrfs_block_group_cache; +struct btrfs_block_group; extern struct kmem_cache *btrfs_trans_handle_cachep; extern struct kmem_cache *btrfs_bit_radix_cachep; extern struct kmem_cache *btrfs_path_cachep; @@ -56,9 +57,9 @@ struct btrfs_ref; * filesystem data as well that can be used to read data in order to repair * read errors on other disks. * - * Current value is derived from RAID1 with 2 copies. + * Current value is derived from RAID1C4 with 4 copies. */ -#define BTRFS_MAX_MIRRORS (2 + 1) +#define BTRFS_MAX_MIRRORS (4 + 1) #define BTRFS_MAX_LEVEL 8 @@ -291,7 +292,8 @@ struct btrfs_super_block { BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \ BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ BTRFS_FEATURE_INCOMPAT_NO_HOLES | \ - BTRFS_FEATURE_INCOMPAT_METADATA_UUID) + BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \ + BTRFS_FEATURE_INCOMPAT_RAID1C34) #define BTRFS_FEATURE_INCOMPAT_SAFE_SET \ (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) @@ -413,7 +415,7 @@ struct btrfs_free_cluster { /* We did a full search and couldn't create a cluster */ bool fragmented; - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; /* * when a cluster is allocated from a block group, we put the * cluster onto a list in the block group so that it can @@ -476,8 +478,8 @@ struct btrfs_swapfile_pin { void *ptr; struct inode *inode; /* - * If true, ptr points to a struct btrfs_block_group_cache. Otherwise, - * ptr points to a struct btrfs_device. + * If true, ptr points to a struct btrfs_block_group. Otherwise, ptr + * points to a struct btrfs_device. */ bool is_block_group; }; @@ -722,7 +724,6 @@ struct btrfs_fs_info { struct btrfs_workqueue *endio_meta_write_workers; struct btrfs_workqueue *endio_write_workers; struct btrfs_workqueue *endio_freespace_worker; - struct btrfs_workqueue *submit_workers; struct btrfs_workqueue *caching_workers; struct btrfs_workqueue *readahead_workers; @@ -1519,18 +1520,18 @@ static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb, } /* struct btrfs_block_group_item */ -BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item, +BTRFS_SETGET_STACK_FUNCS(stack_block_group_used, struct btrfs_block_group_item, used, 64); -BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item, +BTRFS_SETGET_FUNCS(block_group_used, struct btrfs_block_group_item, used, 64); -BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid, +BTRFS_SETGET_STACK_FUNCS(stack_block_group_chunk_objectid, struct btrfs_block_group_item, chunk_objectid, 64); -BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid, +BTRFS_SETGET_FUNCS(block_group_chunk_objectid, struct btrfs_block_group_item, chunk_objectid, 64); -BTRFS_SETGET_FUNCS(disk_block_group_flags, +BTRFS_SETGET_FUNCS(block_group_flags, struct btrfs_block_group_item, flags, 64); -BTRFS_SETGET_STACK_FUNCS(block_group_flags, +BTRFS_SETGET_STACK_FUNCS(stack_block_group_flags, struct btrfs_block_group_item, flags, 64); /* struct btrfs_free_space_info */ @@ -2163,6 +2164,9 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, int btrfs_super_csum_size(const struct btrfs_super_block *s); const char *btrfs_super_csum_name(u16 csum_type); +const char *btrfs_super_csum_driver(u16 csum_type); +size_t __const btrfs_get_num_csums(void); + /* * The leaf data grows from end-to-front in the node. @@ -2397,7 +2401,7 @@ static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info, int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info, u64 start, u64 num_bytes); -void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache); +void btrfs_free_excluded_extents(struct btrfs_block_group *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, unsigned long count); void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, @@ -2453,8 +2457,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref); int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr); -void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache); -void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache); +void btrfs_get_block_group_trimming(struct btrfs_block_group *cache); +void btrfs_put_block_group_trimming(struct btrfs_block_group *cache); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); enum btrfs_reserve_flush_enum { @@ -2507,7 +2511,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root); /* ctree.c */ int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key, int level, int *slot); -int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); +int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); int btrfs_previous_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid, int type); @@ -2567,8 +2571,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, void btrfs_release_path(struct btrfs_path *p); struct btrfs_path *btrfs_alloc_path(void); void btrfs_free_path(struct btrfs_path *p); -void btrfs_set_path_blocking(struct btrfs_path *p); -void btrfs_unlock_up_safe(struct btrfs_path *p, int level); int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int slot, int nr); @@ -2870,10 +2872,9 @@ int btrfs_drop_inode(struct inode *inode); int __init btrfs_init_cachep(void); void __cold btrfs_destroy_cachep(void); struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *new, - struct btrfs_path *path); + struct btrfs_root *root, struct btrfs_path *path); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *was_new); + struct btrfs_root *root); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, u64 end, int create); @@ -2909,7 +2910,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int btrfs_ioctl_get_supported_features(void __user *arg); void btrfs_sync_inode_flags_to_i_flags(struct inode *inode); -int btrfs_is_empty_uuid(u8 *uuid); +int __pure btrfs_is_empty_uuid(u8 *uuid); int btrfs_defrag_file(struct inode *inode, struct file *file, struct btrfs_ioctl_defrag_range_args *range, u64 newer_than, unsigned long max_pages); @@ -3143,7 +3144,7 @@ __cold void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function, unsigned int line, int errno, const char *fmt, ...); -const char *btrfs_decode_error(int errno); +const char * __attribute_const__ btrfs_decode_error(int errno); __cold void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index db9f2c58eb4a..4cdac4d834f5 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -307,7 +307,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) unsigned nr_extents; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL; int ret = 0; - bool delalloc_lock = true; /* * If we are a free space inode we need to not flush since we will be in @@ -320,7 +319,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) */ if (btrfs_is_free_space_inode(inode)) { flush = BTRFS_RESERVE_NO_FLUSH; - delalloc_lock = false; } else { if (current->journal_info) flush = BTRFS_RESERVE_FLUSH_LIMIT; @@ -329,9 +327,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) schedule_timeout(1); } - if (delalloc_lock) - mutex_lock(&inode->delalloc_mutex); - num_bytes = ALIGN(num_bytes, fs_info->sectorsize); /* @@ -348,10 +343,12 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) &qgroup_reserve); ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true); if (ret) - goto out_fail; + return ret; ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve, flush); - if (ret) - goto out_qgroup; + if (ret) { + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve); + return ret; + } /* * Now we need to update our outstanding extents and csum bytes _first_ @@ -375,15 +372,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) block_rsv->qgroup_rsv_reserved += qgroup_reserve; spin_unlock(&block_rsv->lock); - if (delalloc_lock) - mutex_unlock(&inode->delalloc_mutex); return 0; -out_qgroup: - btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve); -out_fail: - if (delalloc_lock) - mutex_unlock(&inode->delalloc_mutex); - return ret; } /** diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 1f7f39b10bd0..d3e15e1d4a91 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -12,6 +12,7 @@ #include "transaction.h" #include "ctree.h" #include "qgroup.h" +#include "locking.h" #define BTRFS_DELAYED_WRITEBACK 512 #define BTRFS_DELAYED_BACKGROUND 128 @@ -1367,8 +1368,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root, return -ENOMEM; async_work->delayed_root = delayed_root; - btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper, - btrfs_async_run_delayed_root, NULL, NULL); + btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL, + NULL); async_work->nr = nr; btrfs_queue_work(fs_info->delayed_workers, &async_work->work); @@ -1949,12 +1950,19 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) } inode_id = delayed_nodes[n - 1]->inode_id + 1; - - for (i = 0; i < n; i++) - refcount_inc(&delayed_nodes[i]->refs); + for (i = 0; i < n; i++) { + /* + * Don't increase refs in case the node is dead and + * about to be removed from the tree in the loop below + */ + if (!refcount_inc_not_zero(&delayed_nodes[i]->refs)) + delayed_nodes[i] = NULL; + } spin_unlock(&root->inode_lock); for (i = 0; i < n; i++) { + if (!delayed_nodes[i]) + continue; __btrfs_kill_delayed_node(delayed_nodes[i]); btrfs_release_delayed_node(delayed_nodes[i]); } diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 48890826b5e6..f639dde2a679 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -986,7 +986,7 @@ static int btrfs_dev_replace_kthread(void *data) return 0; } -int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace) +int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace) { if (!dev_replace->is_valid) return 0; diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index 78c5d8f1adda..60b70dacc299 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -17,6 +17,6 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info); void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info); int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info); -int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace); +int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace); #endif diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 402b61bf345c..e0edfdc9c82b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -205,7 +205,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, u64 len, int create) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_map_tree *em_tree = &inode->extent_tree; struct extent_map *em; int ret; @@ -213,7 +212,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode, read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, start, len); if (em) { - em->bdev = fs_info->fs_devices->latest_bdev; read_unlock(&em_tree->lock); goto out; } @@ -228,7 +226,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode, em->len = (u64)-1; em->block_len = (u64)-1; em->block_start = 0; - em->bdev = fs_info->fs_devices->latest_bdev; write_lock(&em_tree->lock); ret = add_extent_mapping(em_tree, em, 0); @@ -352,6 +349,9 @@ static bool btrfs_supported_super_csum(u16 csum_type) { switch (csum_type) { case BTRFS_CSUM_TYPE_CRC32: + case BTRFS_CSUM_TYPE_XXHASH: + case BTRFS_CSUM_TYPE_SHA256: + case BTRFS_CSUM_TYPE_BLAKE2: return true; default: return false; @@ -545,9 +545,11 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) ret = btrfs_check_leaf_full(eb); if (ret < 0) { + btrfs_print_tree(eb, 0); btrfs_err(fs_info, "block=%llu write time tree block corruption detected", eb->start); + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); return ret; } write_extent_buffer(eb, result, 0, csum_size); @@ -608,7 +610,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, /* the pending IO might have been the only thing that kept this buffer * in memory. Make sure we have a ref for all this other checks */ - extent_buffer_get(eb); + atomic_inc(&eb->refs); reads_done = atomic_dec_and_test(&eb->io_pages); if (!reads_done) @@ -706,43 +708,31 @@ static void end_workqueue_bio(struct bio *bio) struct btrfs_end_io_wq *end_io_wq = bio->bi_private; struct btrfs_fs_info *fs_info; struct btrfs_workqueue *wq; - btrfs_work_func_t func; fs_info = end_io_wq->info; end_io_wq->status = bio->bi_status; if (bio_op(bio) == REQ_OP_WRITE) { - if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) { + if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) wq = fs_info->endio_meta_write_workers; - func = btrfs_endio_meta_write_helper; - } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) { + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) wq = fs_info->endio_freespace_worker; - func = btrfs_freespace_write_helper; - } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) { + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) wq = fs_info->endio_raid56_workers; - func = btrfs_endio_raid56_helper; - } else { + else wq = fs_info->endio_write_workers; - func = btrfs_endio_write_helper; - } } else { - if (unlikely(end_io_wq->metadata == - BTRFS_WQ_ENDIO_DIO_REPAIR)) { + if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR)) wq = fs_info->endio_repair_workers; - func = btrfs_endio_repair_helper; - } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) { + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) wq = fs_info->endio_raid56_workers; - func = btrfs_endio_raid56_helper; - } else if (end_io_wq->metadata) { + else if (end_io_wq->metadata) wq = fs_info->endio_meta_workers; - func = btrfs_endio_meta_helper; - } else { + else wq = fs_info->endio_workers; - func = btrfs_endio_helper; - } } - btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL); + btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL); btrfs_queue_work(wq, &end_io_wq->work); } @@ -803,8 +793,13 @@ static void run_one_async_done(struct btrfs_work *work) return; } - ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, - async->mirror_num, 1); + /* + * All of the bios that pass through here are from async helpers. + * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context. + * This changes nothing when cgroups aren't in use. + */ + async->bio->bi_opf |= REQ_CGROUP_PUNT; + ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num); if (ret) { async->bio->bi_status = ret; bio_endio(async->bio); @@ -835,8 +830,8 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, async->mirror_num = mirror_num; async->submit_bio_start = submit_bio_start; - btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start, - run_one_async_done, run_one_async_free); + btrfs_init_work(&async->work, run_one_async_start, run_one_async_done, + run_one_async_free); async->bio_offset = bio_offset; @@ -904,12 +899,12 @@ static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, BTRFS_WQ_ENDIO_METADATA); if (ret) goto out_w_error; - ret = btrfs_map_bio(fs_info, bio, mirror_num, 0); + ret = btrfs_map_bio(fs_info, bio, mirror_num); } else if (!async) { ret = btree_csum_one_bio(bio); if (ret) goto out_w_error; - ret = btrfs_map_bio(fs_info, bio, mirror_num, 0); + ret = btrfs_map_bio(fs_info, bio, mirror_num); } else { /* * kthread helpers are used to submit writes so that @@ -1657,8 +1652,8 @@ static void end_workqueue_fn(struct btrfs_work *work) bio->bi_status = end_io_wq->status; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; - kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); bio_endio(bio); + kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); } static int cleaner_kthread(void *arg) @@ -1753,7 +1748,7 @@ static int transaction_kthread(void *arg) } now = ktime_get_seconds(); - if (cur->state < TRANS_STATE_BLOCKED && + if (cur->state < TRANS_STATE_COMMIT_START && !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) && (now < cur->start_time || now - cur->start_time < fs_info->commit_interval)) { @@ -1792,18 +1787,18 @@ sleep: } /* - * this will find the highest generation in the array of - * root backups. The index of the highest array is returned, - * or -1 if we can't find anything. + * This will find the highest generation in the array of root backups. The + * index of the highest array is returned, or -EINVAL if we can't find + * anything. * * We check to make sure the array is valid by comparing the * generation of the latest root in the array with the generation * in the super block. If they don't match we pitch it. */ -static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen) +static int find_newest_super_backup(struct btrfs_fs_info *info) { + const u64 newest_gen = btrfs_super_generation(info->super_copy); u64 cur; - int newest_index = -1; struct btrfs_root_backup *root_backup; int i; @@ -1811,37 +1806,10 @@ static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen) root_backup = info->super_copy->super_roots + i; cur = btrfs_backup_tree_root_gen(root_backup); if (cur == newest_gen) - newest_index = i; + return i; } - /* check to see if we actually wrapped around */ - if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) { - root_backup = info->super_copy->super_roots; - cur = btrfs_backup_tree_root_gen(root_backup); - if (cur == newest_gen) - newest_index = 0; - } - return newest_index; -} - - -/* - * find the oldest backup so we know where to store new entries - * in the backup array. This will set the backup_root_index - * field in the fs_info struct - */ -static void find_oldest_super_backup(struct btrfs_fs_info *info, - u64 newest_gen) -{ - int newest_index = -1; - - newest_index = find_newest_super_backup(info, newest_gen); - /* if there was garbage in there, just move along */ - if (newest_index == -1) { - info->backup_root_index = 0; - } else { - info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS; - } + return -EINVAL; } /* @@ -1851,22 +1819,8 @@ static void find_oldest_super_backup(struct btrfs_fs_info *info, */ static void backup_super_roots(struct btrfs_fs_info *info) { - int next_backup; + const int next_backup = info->backup_root_index; struct btrfs_root_backup *root_backup; - int last_backup; - - next_backup = info->backup_root_index; - last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) % - BTRFS_NUM_BACKUP_ROOTS; - - /* - * just overwrite the last backup if we're at the same generation - * this happens only at umount - */ - root_backup = info->super_for_commit->super_roots + last_backup; - if (btrfs_backup_tree_root_gen(root_backup) == - btrfs_header_generation(info->tree_root->node)) - next_backup = last_backup; root_backup = info->super_for_commit->super_roots + next_backup; @@ -1939,40 +1893,31 @@ static void backup_super_roots(struct btrfs_fs_info *info) } /* - * this copies info out of the root backup array and back into - * the in-memory super block. It is meant to help iterate through - * the array, so you send it the number of backups you've already - * tried and the last backup index you used. + * read_backup_root - Reads a backup root based on the passed priority. Prio 0 + * is the newest, prio 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots * - * this returns -1 when it has tried all the backups + * fs_info - filesystem whose backup roots need to be read + * priority - priority of backup root required + * + * Returns backup root index on success and -EINVAL otherwise. */ -static noinline int next_root_backup(struct btrfs_fs_info *info, - struct btrfs_super_block *super, - int *num_backups_tried, int *backup_index) +static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority) { + int backup_index = find_newest_super_backup(fs_info); + struct btrfs_super_block *super = fs_info->super_copy; struct btrfs_root_backup *root_backup; - int newest = *backup_index; - - if (*num_backups_tried == 0) { - u64 gen = btrfs_super_generation(super); - newest = find_newest_super_backup(info, gen); - if (newest == -1) - return -1; + if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) { + if (priority == 0) + return backup_index; - *backup_index = newest; - *num_backups_tried = 1; - } else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) { - /* we've tried all the backups, all done */ - return -1; + backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority; + backup_index %= BTRFS_NUM_BACKUP_ROOTS; } else { - /* jump to the next oldest backup */ - newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) % - BTRFS_NUM_BACKUP_ROOTS; - *backup_index = newest; - *num_backups_tried += 1; + return -EINVAL; } - root_backup = super->super_roots + newest; + + root_backup = super->super_roots + backup_index; btrfs_set_super_generation(super, btrfs_backup_tree_root_gen(root_backup)); @@ -1982,12 +1927,13 @@ static noinline int next_root_backup(struct btrfs_fs_info *info, btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup)); /* - * fixme: the total bytes and num_devices need to match or we should + * Fixme: the total bytes and num_devices need to match or we should * need a fsck */ btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup)); btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup)); - return 0; + + return backup_index; } /* helper to cleanup workers */ @@ -2002,7 +1948,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) btrfs_destroy_workqueue(fs_info->rmw_workers); btrfs_destroy_workqueue(fs_info->endio_write_workers); btrfs_destroy_workqueue(fs_info->endio_freespace_worker); - btrfs_destroy_workqueue(fs_info->submit_workers); btrfs_destroy_workqueue(fs_info->delayed_workers); btrfs_destroy_workqueue(fs_info->caching_workers); btrfs_destroy_workqueue(fs_info->readahead_workers); @@ -2028,7 +1973,7 @@ static void free_root_extent_buffers(struct btrfs_root *root) } /* helper to cleanup tree roots */ -static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) +static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root) { free_root_extent_buffers(info->tree_root); @@ -2037,7 +1982,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) free_root_extent_buffers(info->csum_root); free_root_extent_buffers(info->quota_root); free_root_extent_buffers(info->uuid_root); - if (chunk_root) + if (free_chunk_root) free_root_extent_buffers(info->chunk_root); free_root_extent_buffers(info->free_space_root); } @@ -2167,16 +2112,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, fs_info->caching_workers = btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0); - /* - * a higher idle thresh on the submit workers makes it much more - * likely that bios will be send down in a sane order to the - * devices - */ - fs_info->submit_workers = - btrfs_alloc_workqueue(fs_info, "submit", flags, - min_t(u64, fs_devices->num_devices, - max_active), 64); - fs_info->fixup_workers = btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0); @@ -2215,7 +2150,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0); if (!(fs_info->workers && fs_info->delalloc_workers && - fs_info->submit_workers && fs_info->flush_workers && + fs_info->flush_workers && fs_info->endio_workers && fs_info->endio_meta_workers && fs_info->endio_meta_write_workers && fs_info->endio_repair_workers && @@ -2233,13 +2168,13 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) { struct crypto_shash *csum_shash; - const char *csum_name = btrfs_super_csum_name(csum_type); + const char *csum_driver = btrfs_super_csum_driver(csum_type); - csum_shash = crypto_alloc_shash(csum_name, 0, 0); + csum_shash = crypto_alloc_shash(csum_driver, 0, 0); if (IS_ERR(csum_shash)) { btrfs_err(fs_info, "error allocating %s hash for checksum", - csum_name); + csum_driver); return PTR_ERR(csum_shash); } @@ -2589,7 +2524,101 @@ out: return ret; } -int open_ctree(struct super_block *sb, +static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) +{ + int backup_index = find_newest_super_backup(fs_info); + struct btrfs_super_block *sb = fs_info->super_copy; + struct btrfs_root *tree_root = fs_info->tree_root; + bool handle_error = false; + int ret = 0; + int i; + + for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { + u64 generation; + int level; + + if (handle_error) { + if (!IS_ERR(tree_root->node)) + free_extent_buffer(tree_root->node); + tree_root->node = NULL; + + if (!btrfs_test_opt(fs_info, USEBACKUPROOT)) + break; + + free_root_pointers(fs_info, 0); + + /* + * Don't use the log in recovery mode, it won't be + * valid + */ + btrfs_set_super_log_root(sb, 0); + + /* We can't trust the free space cache either */ + btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE); + + ret = read_backup_root(fs_info, i); + backup_index = ret; + if (ret < 0) + return ret; + } + generation = btrfs_super_generation(sb); + level = btrfs_super_root_level(sb); + tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb), + generation, level, NULL); + if (IS_ERR(tree_root->node) || + !extent_buffer_uptodate(tree_root->node)) { + handle_error = true; + + if (IS_ERR(tree_root->node)) + ret = PTR_ERR(tree_root->node); + else if (!extent_buffer_uptodate(tree_root->node)) + ret = -EUCLEAN; + + btrfs_warn(fs_info, "failed to read tree root"); + continue; + } + + btrfs_set_root_node(&tree_root->root_item, tree_root->node); + tree_root->commit_root = btrfs_root_node(tree_root); + btrfs_set_root_refs(&tree_root->root_item, 1); + + /* + * No need to hold btrfs_root::objectid_mutex since the fs + * hasn't been fully initialised and we are the only user + */ + ret = btrfs_find_highest_objectid(tree_root, + &tree_root->highest_objectid); + if (ret < 0) { + handle_error = true; + continue; + } + + ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + ret = btrfs_read_roots(fs_info); + if (ret < 0) { + handle_error = true; + continue; + } + + /* All successful */ + fs_info->generation = generation; + fs_info->last_trans_committed = generation; + + /* Always begin writing backup roots after the one being used */ + if (backup_index < 0) { + fs_info->backup_root_index = 0; + } else { + fs_info->backup_root_index = backup_index + 1; + fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS; + } + break; + } + + return ret; +} + +int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options) { @@ -2607,8 +2636,6 @@ int open_ctree(struct super_block *sb, struct btrfs_root *chunk_root; int ret; int err = -EINVAL; - int num_backups_tried = 0; - int backup_index = 0; int clear_free_space_tree = 0; int level; @@ -2879,13 +2906,6 @@ int open_ctree(struct super_block *sb, set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); /* - * run through our array of backup supers and setup - * our ring pointer to the oldest one - */ - generation = btrfs_super_generation(disk_super); - find_oldest_super_backup(fs_info, generation); - - /* * In the long term, we'll store the compression type in the super * block, and it'll be used for per file compression control. */ @@ -3031,44 +3051,9 @@ int open_ctree(struct super_block *sb, goto fail_tree_roots; } -retry_root_backup: - generation = btrfs_super_generation(disk_super); - level = btrfs_super_root_level(disk_super); - - tree_root->node = read_tree_block(fs_info, - btrfs_super_root(disk_super), - generation, level, NULL); - if (IS_ERR(tree_root->node) || - !extent_buffer_uptodate(tree_root->node)) { - btrfs_warn(fs_info, "failed to read tree root"); - if (!IS_ERR(tree_root->node)) - free_extent_buffer(tree_root->node); - tree_root->node = NULL; - goto recovery_tree_root; - } - - btrfs_set_root_node(&tree_root->root_item, tree_root->node); - tree_root->commit_root = btrfs_root_node(tree_root); - btrfs_set_root_refs(&tree_root->root_item, 1); - - mutex_lock(&tree_root->objectid_mutex); - ret = btrfs_find_highest_objectid(tree_root, - &tree_root->highest_objectid); - if (ret) { - mutex_unlock(&tree_root->objectid_mutex); - goto recovery_tree_root; - } - - ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); - - mutex_unlock(&tree_root->objectid_mutex); - - ret = btrfs_read_roots(fs_info); + ret = init_tree_roots(fs_info); if (ret) - goto recovery_tree_root; - - fs_info->generation = generation; - fs_info->last_trans_committed = generation; + goto fail_tree_roots; ret = btrfs_verify_dev_extents(fs_info); if (ret) { @@ -3336,7 +3321,7 @@ fail_block_groups: btrfs_put_block_group_cache(fs_info); fail_tree_roots: - free_root_pointers(fs_info, 1); + free_root_pointers(fs_info, true); invalidate_inode_pages2(fs_info->btree_inode->i_mapping); fail_sb_buffer: @@ -3363,24 +3348,6 @@ fail: btrfs_free_stripe_hash_table(fs_info); btrfs_close_devices(fs_info->fs_devices); return err; - -recovery_tree_root: - if (!btrfs_test_opt(fs_info, USEBACKUPROOT)) - goto fail_tree_roots; - - free_root_pointers(fs_info, 0); - - /* don't use the log in recovery mode, it won't be valid */ - btrfs_set_super_log_root(disk_super, 0); - - /* we can't trust the free space cache either */ - btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE); - - ret = next_root_backup(fs_info, fs_info->super_copy, - &num_backups_tried, &backup_index); - if (ret == -1) - goto fail_block_groups; - goto retry_root_backup; } ALLOW_ERROR_INJECTION(open_ctree, ERRNO); @@ -3974,7 +3941,7 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info) return btrfs_commit_transaction(trans); } -void close_ctree(struct btrfs_fs_info *fs_info) +void __cold close_ctree(struct btrfs_fs_info *fs_info) { int ret; @@ -4062,7 +4029,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) btrfs_free_block_groups(fs_info); clear_bit(BTRFS_FS_OPEN, &fs_info->flags); - free_root_pointers(fs_info, 1); + free_root_pointers(fs_info, true); iput(fs_info->btree_inode); @@ -4439,7 +4406,7 @@ again: return 0; } -static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache) +static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) { struct inode *inode; @@ -4456,12 +4423,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache) void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; spin_lock(&cur_trans->dirty_bgs_lock); while (!list_empty(&cur_trans->dirty_bgs)) { cache = list_first_entry(&cur_trans->dirty_bgs, - struct btrfs_block_group_cache, + struct btrfs_block_group, dirty_list); if (!list_empty(&cache->io_list)) { @@ -4489,7 +4456,7 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, */ while (!list_empty(&cur_trans->io_bgs)) { cache = list_first_entry(&cur_trans->io_bgs, - struct btrfs_block_group_cache, + struct btrfs_block_group, io_list); list_del_init(&cache->io_list); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index a6958103d87e..76f123ebb292 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -49,10 +49,10 @@ struct extent_buffer *btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, u64 bytenr); void btrfs_clean_tree_block(struct extent_buffer *buf); -int open_ctree(struct super_block *sb, +int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options); -void close_ctree(struct btrfs_fs_info *fs_info); +void __cold close_ctree(struct btrfs_fs_info *fs_info); int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors); struct buffer_head *btrfs_read_dev_super(struct block_device *bdev); int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index ddf28ecf17f9..72e312cae69d 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -87,7 +87,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(sb, &key, root, NULL); + inode = btrfs_iget(sb, &key, root); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto fail; @@ -214,7 +214,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child) key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root, NULL)); + return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root)); fail: btrfs_free_path(path); return ERR_PTR(ret); diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h new file mode 100644 index 000000000000..a3febe746c79 --- /dev/null +++ b/fs/btrfs/extent-io-tree.h @@ -0,0 +1,248 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef BTRFS_EXTENT_IO_TREE_H +#define BTRFS_EXTENT_IO_TREE_H + +struct extent_changeset; +struct io_failure_record; + +/* Bits for the extent state */ +#define EXTENT_DIRTY (1U << 0) +#define EXTENT_UPTODATE (1U << 1) +#define EXTENT_LOCKED (1U << 2) +#define EXTENT_NEW (1U << 3) +#define EXTENT_DELALLOC (1U << 4) +#define EXTENT_DEFRAG (1U << 5) +#define EXTENT_BOUNDARY (1U << 6) +#define EXTENT_NODATASUM (1U << 7) +#define EXTENT_CLEAR_META_RESV (1U << 8) +#define EXTENT_NEED_WAIT (1U << 9) +#define EXTENT_DAMAGED (1U << 10) +#define EXTENT_NORESERVE (1U << 11) +#define EXTENT_QGROUP_RESERVED (1U << 12) +#define EXTENT_CLEAR_DATA_RESV (1U << 13) +#define EXTENT_DELALLOC_NEW (1U << 14) +#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \ + EXTENT_CLEAR_DATA_RESV) +#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING) + +/* + * Redefined bits above which are used only in the device allocation tree, + * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV + * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit + * manipulation functions + */ +#define CHUNK_ALLOCATED EXTENT_DIRTY +#define CHUNK_TRIMMED EXTENT_DEFRAG + +enum { + IO_TREE_FS_INFO_FREED_EXTENTS0, + IO_TREE_FS_INFO_FREED_EXTENTS1, + IO_TREE_INODE_IO, + IO_TREE_INODE_IO_FAILURE, + IO_TREE_RELOC_BLOCKS, + IO_TREE_TRANS_DIRTY_PAGES, + IO_TREE_ROOT_DIRTY_LOG_PAGES, + IO_TREE_SELFTEST, +}; + +struct extent_io_tree { + struct rb_root state; + struct btrfs_fs_info *fs_info; + void *private_data; + u64 dirty_bytes; + bool track_uptodate; + + /* Who owns this io tree, should be one of IO_TREE_* */ + u8 owner; + + spinlock_t lock; + const struct extent_io_ops *ops; +}; + +struct extent_state { + u64 start; + u64 end; /* inclusive */ + struct rb_node rb_node; + + /* ADD NEW ELEMENTS AFTER THIS */ + wait_queue_head_t wq; + refcount_t refs; + unsigned state; + + struct io_failure_record *failrec; + +#ifdef CONFIG_BTRFS_DEBUG + struct list_head leak_list; +#endif +}; + +int __init extent_state_cache_init(void); +void __cold extent_state_cache_exit(void); + +void extent_io_tree_init(struct btrfs_fs_info *fs_info, + struct extent_io_tree *tree, unsigned int owner, + void *private_data); +void extent_io_tree_release(struct extent_io_tree *tree); + +int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + struct extent_state **cached); + +static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end) +{ + return lock_extent_bits(tree, start, end, NULL); +} + +int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end); + +int __init extent_io_init(void); +void __cold extent_io_exit(void); + +u64 count_range_bits(struct extent_io_tree *tree, + u64 *start, u64 search_end, + u64 max_bytes, unsigned bits, int contig); + +void free_extent_state(struct extent_state *state); +int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, int filled, + struct extent_state *cached_state); +int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, struct extent_changeset *changeset); +int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, int wake, int delete, + struct extent_state **cached); +int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, int wake, int delete, + struct extent_state **cached, gfp_t mask, + struct extent_changeset *changeset); + +static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end) +{ + return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL); +} + +static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached) +{ + return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached, + GFP_NOFS, NULL); +} + +static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree, + u64 start, u64 end, struct extent_state **cached) +{ + return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached, + GFP_ATOMIC, NULL); +} + +static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start, + u64 end, unsigned bits) +{ + int wake = 0; + + if (bits & EXTENT_LOCKED) + wake = 1; + + return clear_extent_bit(tree, start, end, bits, wake, 0, NULL); +} + +int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, struct extent_changeset *changeset); +int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, u64 *failed_start, + struct extent_state **cached_state, gfp_t mask); +int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits); + +static inline int set_extent_bits(struct extent_io_tree *tree, u64 start, + u64 end, unsigned bits) +{ + return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS); +} + +static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached_state) +{ + return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0, + cached_state, GFP_NOFS, NULL); +} + +static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start, + u64 end, gfp_t mask) +{ + return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL, + NULL, mask); +} + +static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached) +{ + return clear_extent_bit(tree, start, end, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING, 0, 0, cached); +} + +int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, unsigned clear_bits, + struct extent_state **cached_state); + +static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start, + u64 end, unsigned int extra_bits, + struct extent_state **cached_state) +{ + return set_extent_bit(tree, start, end, + EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits, + NULL, cached_state, GFP_NOFS); +} + +static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached_state) +{ + return set_extent_bit(tree, start, end, + EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG, + NULL, cached_state, GFP_NOFS); +} + +static inline int set_extent_new(struct extent_io_tree *tree, u64 start, + u64 end) +{ + return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL, + GFP_NOFS); +} + +static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached_state, gfp_t mask) +{ + return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL, + cached_state, mask); +} + +int find_first_extent_bit(struct extent_io_tree *tree, u64 start, + u64 *start_ret, u64 *end_ret, unsigned bits, + struct extent_state **cached_state); +void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start, + u64 *start_ret, u64 *end_ret, unsigned bits); +int extent_invalidatepage(struct extent_io_tree *tree, + struct page *page, unsigned long offset); +bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start, + u64 *end, u64 max_bytes, + struct extent_state **cached_state); + +/* This should be reworked in the future and put elsewhere. */ +int get_state_failrec(struct extent_io_tree *tree, u64 start, + struct io_failure_record **failrec); +int set_state_failrec(struct extent_io_tree *tree, u64 start, + struct io_failure_record *failrec); +void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, + u64 end); +int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, + struct io_failure_record **failrec_ret); +int free_io_failure(struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, + struct io_failure_record *rec); +int clean_io_failure(struct btrfs_fs_info *fs_info, + struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, u64 start, + struct page *page, u64 ino, unsigned int pg_offset); + +#endif /* BTRFS_EXTENT_IO_TREE_H */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 49cb26fa7c63..153f71a5bba9 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -54,7 +54,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, static int find_next_key(struct btrfs_path *path, int level, struct btrfs_key *key); -static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits) +static int block_group_bits(struct btrfs_block_group *cache, u64 bits) { return (cache->flags & bits) == bits; } @@ -70,13 +70,13 @@ int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info, return 0; } -void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache) +void btrfs_free_excluded_extents(struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; u64 start, end; - start = cache->key.objectid; - end = start + cache->key.offset - 1; + start = cache->start; + end = start + cache->length - 1; clear_extent_bits(&fs_info->freed_extents[0], start, end, EXTENT_UPTODATE); @@ -1306,8 +1306,10 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 *actual_bytes) { - int ret; + int ret = 0; u64 discarded_bytes = 0; + u64 end = bytenr + num_bytes; + u64 cur = bytenr; struct btrfs_bio *bbio = NULL; @@ -1316,15 +1318,23 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, * associated to its stripes that don't go away while we are discarding. */ btrfs_bio_counter_inc_blocked(fs_info); - /* Tell the block device(s) that the sectors can be discarded */ - ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes, - &bbio, 0); - /* Error condition is -ENOMEM */ - if (!ret) { - struct btrfs_bio_stripe *stripe = bbio->stripes; + while (cur < end) { + struct btrfs_bio_stripe *stripe; int i; + num_bytes = end - cur; + /* Tell the block device(s) that the sectors can be discarded */ + ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur, + &num_bytes, &bbio, 0); + /* + * Error can be -ENOMEM, -ENOENT (no such chunk mapping) or + * -EOPNOTSUPP. For any such error, @num_bytes is not updated, + * thus we can't continue anyway. + */ + if (ret < 0) + goto out; + stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; struct request_queue *req_q; @@ -1341,10 +1351,19 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe->physical, stripe->length, &bytes); - if (!ret) + if (!ret) { discarded_bytes += bytes; - else if (ret != -EOPNOTSUPP) - break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */ + } else if (ret != -EOPNOTSUPP) { + /* + * Logic errors or -ENOMEM, or -EIO, but + * unlikely to happen. + * + * And since there are two loops, explicitly + * go to out to avoid confusion. + */ + btrfs_put_bbio(bbio); + goto out; + } /* * Just in case we get back EOPNOTSUPP for some reason, @@ -1354,7 +1373,9 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, ret = 0; } btrfs_put_bbio(bbio); + cur += num_bytes; } +out: btrfs_bio_counter_dec(fs_info); if (actual_bytes) @@ -2516,7 +2537,7 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; int readonly = 0; block_group = btrfs_lookup_block_group(fs_info, bytenr); @@ -2546,7 +2567,7 @@ static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data) static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; u64 bytenr; spin_lock(&fs_info->block_group_cache_lock); @@ -2560,13 +2581,13 @@ static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start) if (!cache) return 0; - bytenr = cache->key.objectid; + bytenr = cache->start; btrfs_put_block_group(cache); return bytenr; } -static int pin_down_extent(struct btrfs_block_group_cache *cache, +static int pin_down_extent(struct btrfs_block_group *cache, u64 bytenr, u64 num_bytes, int reserved) { struct btrfs_fs_info *fs_info = cache->fs_info; @@ -2590,13 +2611,12 @@ static int pin_down_extent(struct btrfs_block_group_cache *cache, return 0; } -/* - * this function must be called within transaction - */ int btrfs_pin_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, int reserved) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; + + ASSERT(fs_info->running_transaction); cache = btrfs_lookup_block_group(fs_info, bytenr); BUG_ON(!cache); /* Logic error */ @@ -2613,7 +2633,7 @@ int btrfs_pin_extent(struct btrfs_fs_info *fs_info, int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; int ret; cache = btrfs_lookup_block_group(fs_info, bytenr); @@ -2640,7 +2660,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, u64 start, u64 num_bytes) { int ret; - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_caching_control *caching_ctl; block_group = btrfs_lookup_block_group(fs_info, start); @@ -2652,7 +2672,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, if (!caching_ctl) { /* Logic error */ - BUG_ON(!btrfs_block_group_cache_done(block_group)); + BUG_ON(!btrfs_block_group_done(block_group)); ret = btrfs_remove_free_space(block_group, start, num_bytes); } else { mutex_lock(&caching_ctl->mutex); @@ -2717,7 +2737,7 @@ int btrfs_exclude_logged_extents(struct extent_buffer *eb) } static void -btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg) +btrfs_inc_block_group_reservations(struct btrfs_block_group *bg) { atomic_inc(&bg->reservations); } @@ -2726,14 +2746,14 @@ void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info) { struct btrfs_caching_control *next; struct btrfs_caching_control *caching_ctl; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; down_write(&fs_info->commit_root_sem); list_for_each_entry_safe(caching_ctl, next, &fs_info->caching_block_groups, list) { cache = caching_ctl->block_group; - if (btrfs_block_group_cache_done(cache)) { + if (btrfs_block_group_done(cache)) { cache->last_byte_to_unpin = (u64)-1; list_del_init(&caching_ctl->list); btrfs_put_caching_control(caching_ctl); @@ -2785,7 +2805,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end, const bool return_free_space) { - struct btrfs_block_group_cache *cache = NULL; + struct btrfs_block_group *cache = NULL; struct btrfs_space_info *space_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; struct btrfs_free_cluster *cluster = NULL; @@ -2797,7 +2817,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, while (start <= end) { readonly = false; if (!cache || - start >= cache->key.objectid + cache->key.offset) { + start >= cache->start + cache->length) { if (cache) btrfs_put_block_group(cache); total_unpinned = 0; @@ -2810,7 +2830,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, empty_cluster <<= 1; } - len = cache->key.objectid + cache->key.offset - start; + len = cache->start + cache->length - start; len = min(len, end + 1 - start); if (start < cache->last_byte_to_unpin) { @@ -2880,7 +2900,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *block_group, *tmp; + struct btrfs_block_group *block_group, *tmp; struct list_head *deleted_bgs; struct extent_io_tree *unpin; u64 start; @@ -2926,8 +2946,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) ret = -EROFS; if (!trans->aborted) ret = btrfs_discard_extent(fs_info, - block_group->key.objectid, - block_group->key.offset, + block_group->start, + block_group->length, &trimmed); list_del_init(&block_group->bg_list); @@ -3262,7 +3282,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, } if (last_ref && btrfs_header_generation(buf) == trans->transid) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); @@ -3349,15 +3369,14 @@ enum btrfs_loop_type { }; static inline void -btrfs_lock_block_group(struct btrfs_block_group_cache *cache, +btrfs_lock_block_group(struct btrfs_block_group *cache, int delalloc) { if (delalloc) down_read(&cache->data_rwsem); } -static inline void -btrfs_grab_block_group(struct btrfs_block_group_cache *cache, +static inline void btrfs_grab_block_group(struct btrfs_block_group *cache, int delalloc) { btrfs_get_block_group(cache); @@ -3365,12 +3384,12 @@ btrfs_grab_block_group(struct btrfs_block_group_cache *cache, down_read(&cache->data_rwsem); } -static struct btrfs_block_group_cache * -btrfs_lock_cluster(struct btrfs_block_group_cache *block_group, +static struct btrfs_block_group *btrfs_lock_cluster( + struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, int delalloc) { - struct btrfs_block_group_cache *used_bg = NULL; + struct btrfs_block_group *used_bg = NULL; spin_lock(&cluster->refill_lock); while (1) { @@ -3404,7 +3423,7 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group, } static inline void -btrfs_release_block_group(struct btrfs_block_group_cache *cache, +btrfs_release_block_group(struct btrfs_block_group *cache, int delalloc) { if (delalloc) @@ -3475,12 +3494,12 @@ struct find_free_extent_ctl { * Return >0 to inform caller that we find nothing * Return 0 means we have found a location and set ffe_ctl->found_offset. */ -static int find_free_extent_clustered(struct btrfs_block_group_cache *bg, +static int find_free_extent_clustered(struct btrfs_block_group *bg, struct btrfs_free_cluster *last_ptr, struct find_free_extent_ctl *ffe_ctl, - struct btrfs_block_group_cache **cluster_bg_ret) + struct btrfs_block_group **cluster_bg_ret) { - struct btrfs_block_group_cache *cluster_bg; + struct btrfs_block_group *cluster_bg; u64 aligned_cluster; u64 offset; int ret; @@ -3493,7 +3512,7 @@ static int find_free_extent_clustered(struct btrfs_block_group_cache *bg, goto release_cluster; offset = btrfs_alloc_from_cluster(cluster_bg, last_ptr, - ffe_ctl->num_bytes, cluster_bg->key.objectid, + ffe_ctl->num_bytes, cluster_bg->start, &ffe_ctl->max_extent_size); if (offset) { /* We have a block, we're done */ @@ -3579,7 +3598,7 @@ refill_cluster: * Return 0 when we found an free extent and set ffe_ctrl->found_offset * Return -EAGAIN to inform caller that we need to re-search this block group */ -static int find_free_extent_unclustered(struct btrfs_block_group_cache *bg, +static int find_free_extent_unclustered(struct btrfs_block_group *bg, struct btrfs_free_cluster *last_ptr, struct find_free_extent_ctl *ffe_ctl) { @@ -3781,7 +3800,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info, { int ret = 0; struct btrfs_free_cluster *last_ptr = NULL; - struct btrfs_block_group_cache *block_group = NULL; + struct btrfs_block_group *block_group = NULL; struct find_free_extent_ctl ffe_ctl = {0}; struct btrfs_space_info *space_info; bool use_cluster = true; @@ -3904,7 +3923,7 @@ search: continue; btrfs_grab_block_group(block_group, delalloc); - ffe_ctl.search_start = block_group->key.objectid; + ffe_ctl.search_start = block_group->start; /* * this can happen if we end up cycling through all the @@ -3935,7 +3954,7 @@ search: } have_block_group: - ffe_ctl.cached = btrfs_block_group_cache_done(block_group); + ffe_ctl.cached = btrfs_block_group_done(block_group); if (unlikely(!ffe_ctl.cached)) { ffe_ctl.have_caching_bg = true; ret = btrfs_cache_block_group(block_group, 0); @@ -3951,7 +3970,7 @@ have_block_group: * lets look there */ if (last_ptr && use_cluster) { - struct btrfs_block_group_cache *cluster_bg = NULL; + struct btrfs_block_group *cluster_bg = NULL; ret = find_free_extent_clustered(block_group, last_ptr, &ffe_ctl, &cluster_bg); @@ -3984,7 +4003,7 @@ checks: /* move on to the next group */ if (ffe_ctl.search_start + num_bytes > - block_group->key.objectid + block_group->key.offset) { + block_group->start + block_group->length) { btrfs_add_free_space(block_group, ffe_ctl.found_offset, num_bytes); goto loop; @@ -4133,7 +4152,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len, int pin, int delalloc) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; int ret = 0; cache = btrfs_lookup_block_group(fs_info, start); @@ -4366,7 +4385,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; /* @@ -5436,7 +5455,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, btrfs_assert_tree_locked(parent); parent_level = btrfs_header_level(parent); - extent_buffer_get(parent); + atomic_inc(&parent->refs); path->nodes[parent_level] = parent; path->slots[parent_level] = btrfs_header_nritems(parent); @@ -5480,7 +5499,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, */ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; u64 free_bytes = 0; int factor; @@ -5498,9 +5517,8 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo) } factor = btrfs_bg_type_to_factor(block_group->flags); - free_bytes += (block_group->key.offset - - btrfs_block_group_used(&block_group->item)) * - factor; + free_bytes += (block_group->length - + block_group->used) * factor; spin_unlock(&block_group->lock); } @@ -5623,7 +5641,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed) */ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) { - struct btrfs_block_group_cache *cache = NULL; + struct btrfs_block_group *cache = NULL; struct btrfs_device *device; struct list_head *devices; u64 group_trimmed; @@ -5647,16 +5665,16 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) cache = btrfs_lookup_first_block_group(fs_info, range->start); for (; cache; cache = btrfs_next_block_group(cache)) { - if (cache->key.objectid >= range_end) { + if (cache->start >= range_end) { btrfs_put_block_group(cache); break; } - start = max(range->start, cache->key.objectid); - end = min(range_end, cache->key.objectid + cache->key.offset); + start = max(range->start, cache->start); + end = min(range_end, cache->start + cache->length); if (end - start >= range->minlen) { - if (!btrfs_block_group_cache_done(cache)) { + if (!btrfs_block_group_done(cache)) { ret = btrfs_cache_block_group(cache, 0); if (ret) { bg_failed++; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index cceaf05aada2..eb8bd0258360 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -14,6 +14,7 @@ #include <linux/prefetch.h> #include <linux/cleancache.h> #include "extent_io.h" +#include "extent-io-tree.h" #include "extent_map.h" #include "ctree.h" #include "btrfs_inode.h" @@ -59,12 +60,23 @@ void btrfs_leak_debug_del(struct list_head *entry) spin_unlock_irqrestore(&leak_lock, flags); } -static inline -void btrfs_leak_debug_check(void) +static inline void btrfs_extent_buffer_leak_debug_check(void) { - struct extent_state *state; struct extent_buffer *eb; + while (!list_empty(&buffers)) { + eb = list_entry(buffers.next, struct extent_buffer, leak_list); + pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n", + eb->start, eb->len, atomic_read(&eb->refs), eb->bflags); + list_del(&eb->leak_list); + kmem_cache_free(extent_buffer_cache, eb); + } +} + +static inline void btrfs_extent_state_leak_debug_check(void) +{ + struct extent_state *state; + while (!list_empty(&states)) { state = list_entry(states.next, struct extent_state, leak_list); pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n", @@ -74,14 +86,6 @@ void btrfs_leak_debug_check(void) list_del(&state->leak_list); kmem_cache_free(extent_state_cache, state); } - - while (!list_empty(&buffers)) { - eb = list_entry(buffers.next, struct extent_buffer, leak_list); - pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n", - eb->start, eb->len, atomic_read(&eb->refs), eb->bflags); - list_del(&eb->leak_list); - kmem_cache_free(extent_buffer_cache, eb); - } } #define btrfs_debug_check_extent_io_range(tree, start, end) \ @@ -105,7 +109,8 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller, #else #define btrfs_leak_debug_add(new, head) do {} while (0) #define btrfs_leak_debug_del(entry) do {} while (0) -#define btrfs_leak_debug_check() do {} while (0) +#define btrfs_extent_buffer_leak_debug_check() do {} while (0) +#define btrfs_extent_state_leak_debug_check() do {} while (0) #define btrfs_debug_check_extent_io_range(c, s, e) do {} while (0) #endif @@ -196,19 +201,23 @@ static int __must_check flush_write_bio(struct extent_page_data *epd) return ret; } -int __init extent_io_init(void) +int __init extent_state_cache_init(void) { extent_state_cache = kmem_cache_create("btrfs_extent_state", sizeof(struct extent_state), 0, SLAB_MEM_SPREAD, NULL); if (!extent_state_cache) return -ENOMEM; + return 0; +} +int __init extent_io_init(void) +{ extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer", sizeof(struct extent_buffer), 0, SLAB_MEM_SPREAD, NULL); if (!extent_buffer_cache) - goto free_state_cache; + return -ENOMEM; if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE, offsetof(struct btrfs_io_bio, bio), @@ -226,23 +235,24 @@ free_bioset: free_buffer_cache: kmem_cache_destroy(extent_buffer_cache); extent_buffer_cache = NULL; + return -ENOMEM; +} -free_state_cache: +void __cold extent_state_cache_exit(void) +{ + btrfs_extent_state_leak_debug_check(); kmem_cache_destroy(extent_state_cache); - extent_state_cache = NULL; - return -ENOMEM; } void __cold extent_io_exit(void) { - btrfs_leak_debug_check(); + btrfs_extent_buffer_leak_debug_check(); /* * Make sure all delayed rcu free are flushed before we * destroy caches. */ rcu_barrier(); - kmem_cache_destroy(extent_state_cache); kmem_cache_destroy(extent_buffer_cache); bioset_exit(&btrfs_bioset); } @@ -1676,9 +1686,9 @@ out: * * true is returned if we find something, false if nothing was in the tree */ -static noinline bool find_delalloc_range(struct extent_io_tree *tree, - u64 *start, u64 *end, u64 max_bytes, - struct extent_state **cached_state) +bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start, + u64 *end, u64 max_bytes, + struct extent_state **cached_state) { struct rb_node *node; struct extent_state *state; @@ -1796,8 +1806,8 @@ again: /* step one, find a bunch of delalloc bytes starting at start */ delalloc_start = *start; delalloc_end = 0; - found = find_delalloc_range(tree, &delalloc_start, &delalloc_end, - max_bytes, &cached_state); + found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end, + max_bytes, &cached_state); if (!found || delalloc_end <= *start) { *start = delalloc_start; *end = delalloc_end; @@ -1899,7 +1909,7 @@ static int __process_pages_contig(struct address_space *mapping, if (page_ops & PAGE_SET_PRIVATE2) SetPagePrivate2(pages[i]); - if (pages[i] == locked_page) { + if (locked_page && pages[i] == locked_page) { put_page(pages[i]); pages_locked++; continue; @@ -2014,8 +2024,8 @@ out: * set the private field for a given byte offset in the tree. If there isn't * an extent_state there already, this does nothing. */ -static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start, - struct io_failure_record *failrec) +int set_state_failrec(struct extent_io_tree *tree, u64 start, + struct io_failure_record *failrec) { struct rb_node *node; struct extent_state *state; @@ -2042,8 +2052,8 @@ out: return ret; } -static noinline int get_state_failrec(struct extent_io_tree *tree, u64 start, - struct io_failure_record **failrec) +int get_state_failrec(struct extent_io_tree *tree, u64 start, + struct io_failure_record **failrec) { struct rb_node *node; struct extent_state *state; @@ -2534,7 +2544,6 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, bio = btrfs_io_bio_alloc(1); bio->bi_end_io = endio_func; bio->bi_iter.bi_sector = failrec->logical >> 9; - bio_set_dev(bio, fs_info->fs_devices->latest_bdev); bio->bi_iter.bi_size = 0; bio->bi_private = data; @@ -2920,7 +2929,6 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) * a contiguous page to the previous one * @size: portion of page that we want to write * @offset: starting offset in the page - * @bdev: attach newly created bios to this bdev * @bio_ret: must be valid pointer, newly allocated bio will be stored there * @end_io_func: end_io callback for new bio * @mirror_num: desired mirror to read/write @@ -2931,7 +2939,6 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, struct writeback_control *wbc, struct page *page, u64 offset, size_t size, unsigned long pg_offset, - struct block_device *bdev, struct bio **bio_ret, bio_end_io_t end_io_func, int mirror_num, @@ -2977,13 +2984,16 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, } bio = btrfs_bio_alloc(offset); - bio_set_dev(bio, bdev); bio_add_page(bio, page, page_size, pg_offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; bio->bi_write_hint = page->mapping->host->i_write_hint; bio->bi_opf = opf; if (wbc) { + struct block_device *bdev; + + bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev; + bio_set_dev(bio, bdev); wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, page, page_size); } @@ -3065,7 +3075,6 @@ static int __do_readpage(struct extent_io_tree *tree, u64 block_start; u64 cur_end; struct extent_map *em; - struct block_device *bdev; int ret = 0; int nr = 0; size_t pg_offset = 0; @@ -3142,7 +3151,6 @@ static int __do_readpage(struct extent_io_tree *tree, offset = em->block_start + extent_offset; disk_io_size = iosize; } - bdev = em->bdev; block_start = em->block_start; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) block_start = EXTENT_MAP_HOLE; @@ -3232,7 +3240,7 @@ static int __do_readpage(struct extent_io_tree *tree, ret = submit_extent_page(REQ_OP_READ | read_flags, tree, NULL, page, offset, disk_io_size, - pg_offset, bdev, bio, + pg_offset, bio, end_bio_extent_readpage, mirror_num, *bio_flags, this_bio_flag, @@ -3409,7 +3417,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, struct extent_page_data *epd, loff_t i_size, unsigned long nr_written, - unsigned int write_flags, int *nr_ret) + int *nr_ret) { struct extent_io_tree *tree = epd->tree; u64 start = page_offset(page); @@ -3420,11 +3428,11 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, u64 block_start; u64 iosize; struct extent_map *em; - struct block_device *bdev; size_t pg_offset = 0; size_t blocksize; int ret = 0; int nr = 0; + const unsigned int write_flags = wbc_to_write_flags(wbc); bool compressed; ret = btrfs_writepage_cow_fixup(page, start, page_end); @@ -3478,7 +3486,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, iosize = min(em_end - cur, end - cur + 1); iosize = ALIGN(iosize, blocksize); offset = em->block_start + extent_offset; - bdev = em->bdev; block_start = em->block_start; compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); free_extent_map(em); @@ -3520,7 +3527,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc, page, offset, iosize, pg_offset, - bdev, &epd->bio, + &epd->bio, end_bio_extent_writepage, 0, 0, 0, false); if (ret) { @@ -3558,11 +3565,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, size_t pg_offset = 0; loff_t i_size = i_size_read(inode); unsigned long end_index = i_size >> PAGE_SHIFT; - unsigned int write_flags = 0; unsigned long nr_written = 0; - write_flags = wbc_to_write_flags(wbc); - trace___extent_writepage(page, inode, wbc); WARN_ON(!PageLocked(page)); @@ -3600,7 +3604,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, } ret = __extent_writepage_io(inode, page, wbc, epd, - i_size, nr_written, write_flags, &nr); + i_size, nr_written, &nr); if (ret == 1) goto done_unlocked; @@ -3849,7 +3853,6 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, struct extent_page_data *epd) { struct btrfs_fs_info *fs_info = eb->fs_info; - struct block_device *bdev = fs_info->fs_devices->latest_bdev; struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree; u64 offset = eb->start; u32 nritems; @@ -3884,7 +3887,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, clear_page_dirty_for_io(p); set_page_writeback(p); ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc, - p, offset, PAGE_SIZE, 0, bdev, + p, offset, PAGE_SIZE, 0, &epd->bio, end_bio_extent_buffer_writepage, 0, 0, 0, false); @@ -4121,7 +4124,7 @@ retry: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - done_index = page->index; + done_index = page->index + 1; /* * At this point we hold neither the i_pages lock nor * the page lock: the page may be truncated or @@ -4156,16 +4159,6 @@ retry: ret = __extent_writepage(page, wbc, epd); if (ret < 0) { - /* - * done_index is set past this page, - * so media errors will not choke - * background writeout for the entire - * file. This has consequences for - * range_cyclic semantics (ie. it may - * not be suitable for data integrity - * writeout). - */ - done_index = page->index + 1; done = 1; break; } @@ -4240,8 +4233,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end, .nr_to_write = nr_pages * 2, .range_start = start, .range_end = end + 1, + /* We're called from an async helper function */ + .punt_to_cgroup = 1, + .no_cgroup_owner = 1, }; + wbc_attach_fdatawrite_inode(&wbc_writepages, inode); while (start <= end) { page = find_get_page(mapping, start >> PAGE_SHIFT); if (clear_page_dirty_for_io(page)) @@ -4256,11 +4253,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end, } ASSERT(ret <= 0); - if (ret < 0) { + if (ret == 0) + ret = flush_write_bio(&epd); + else end_write_bio(&epd, ret); - return ret; - } - ret = flush_write_bio(&epd); + + wbc_detach_inode(&wbc_writepages); return ret; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index cf3424d58fec..a8551a1f56e2 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -7,35 +7,6 @@ #include <linux/refcount.h> #include "ulist.h" -/* bits for the extent state */ -#define EXTENT_DIRTY (1U << 0) -#define EXTENT_UPTODATE (1U << 1) -#define EXTENT_LOCKED (1U << 2) -#define EXTENT_NEW (1U << 3) -#define EXTENT_DELALLOC (1U << 4) -#define EXTENT_DEFRAG (1U << 5) -#define EXTENT_BOUNDARY (1U << 6) -#define EXTENT_NODATASUM (1U << 7) -#define EXTENT_CLEAR_META_RESV (1U << 8) -#define EXTENT_NEED_WAIT (1U << 9) -#define EXTENT_DAMAGED (1U << 10) -#define EXTENT_NORESERVE (1U << 11) -#define EXTENT_QGROUP_RESERVED (1U << 12) -#define EXTENT_CLEAR_DATA_RESV (1U << 13) -#define EXTENT_DELALLOC_NEW (1U << 14) -#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \ - EXTENT_CLEAR_DATA_RESV) -#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING) - -/* - * Redefined bits above which are used only in the device allocation tree, - * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV - * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit - * manipulation functions - */ -#define CHUNK_ALLOCATED EXTENT_DIRTY -#define CHUNK_TRIMMED EXTENT_DEFRAG - /* * flags for bio submission. The high bits indicate the compression * type for this bio @@ -89,12 +60,11 @@ enum { #define BITMAP_LAST_BYTE_MASK(nbits) \ (BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1))) -struct extent_state; struct btrfs_root; struct btrfs_inode; struct btrfs_io_bio; struct io_failure_record; - +struct extent_io_tree; typedef blk_status_t (extent_submit_bio_start_t)(void *private_data, struct bio *bio, u64 bio_offset); @@ -111,47 +81,6 @@ struct extent_io_ops { int mirror); }; -enum { - IO_TREE_FS_INFO_FREED_EXTENTS0, - IO_TREE_FS_INFO_FREED_EXTENTS1, - IO_TREE_INODE_IO, - IO_TREE_INODE_IO_FAILURE, - IO_TREE_RELOC_BLOCKS, - IO_TREE_TRANS_DIRTY_PAGES, - IO_TREE_ROOT_DIRTY_LOG_PAGES, - IO_TREE_SELFTEST, -}; - -struct extent_io_tree { - struct rb_root state; - struct btrfs_fs_info *fs_info; - void *private_data; - u64 dirty_bytes; - bool track_uptodate; - - /* Who owns this io tree, should be one of IO_TREE_* */ - u8 owner; - - spinlock_t lock; - const struct extent_io_ops *ops; -}; - -struct extent_state { - u64 start; - u64 end; /* inclusive */ - struct rb_node rb_node; - - /* ADD NEW ELEMENTS AFTER THIS */ - wait_queue_head_t wq; - refcount_t refs; - unsigned state; - - struct io_failure_record *failrec; - -#ifdef CONFIG_BTRFS_DEBUG - struct list_head leak_list; -#endif -}; #define INLINE_EXTENT_BUFFER_PAGES 16 #define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE) @@ -259,152 +188,11 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, u64 start, u64 len, int create); -void extent_io_tree_init(struct btrfs_fs_info *fs_info, - struct extent_io_tree *tree, unsigned int owner, - void *private_data); -void extent_io_tree_release(struct extent_io_tree *tree); int try_release_extent_mapping(struct page *page, gfp_t mask); int try_release_extent_buffer(struct page *page); -int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - struct extent_state **cached); -static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end) -{ - return lock_extent_bits(tree, start, end, NULL); -} - -int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end); int extent_read_full_page(struct extent_io_tree *tree, struct page *page, get_extent_t *get_extent, int mirror_num); -int __init extent_io_init(void); -void __cold extent_io_exit(void); - -u64 count_range_bits(struct extent_io_tree *tree, - u64 *start, u64 search_end, - u64 max_bytes, unsigned bits, int contig); - -void free_extent_state(struct extent_state *state); -int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int filled, - struct extent_state *cached_state); -int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, struct extent_changeset *changeset); -int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int wake, int delete, - struct extent_state **cached); -int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int wake, int delete, - struct extent_state **cached, gfp_t mask, - struct extent_changeset *changeset); - -static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end) -{ - return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL); -} - -static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached) -{ - return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached, - GFP_NOFS, NULL); -} - -static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree, - u64 start, u64 end, struct extent_state **cached) -{ - return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached, - GFP_ATOMIC, NULL); -} - -static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start, - u64 end, unsigned bits) -{ - int wake = 0; - - if (bits & EXTENT_LOCKED) - wake = 1; - - return clear_extent_bit(tree, start, end, bits, wake, 0, NULL); -} - -int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, struct extent_changeset *changeset); -int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, u64 *failed_start, - struct extent_state **cached_state, gfp_t mask); -int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits); - -static inline int set_extent_bits(struct extent_io_tree *tree, u64 start, - u64 end, unsigned bits) -{ - return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS); -} - -static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached_state) -{ - return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0, - cached_state, GFP_NOFS, NULL); -} - -static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start, - u64 end, gfp_t mask) -{ - return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL, - NULL, mask); -} - -static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached) -{ - return clear_extent_bit(tree, start, end, - EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING, 0, 0, cached); -} - -int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, unsigned clear_bits, - struct extent_state **cached_state); - -static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start, - u64 end, unsigned int extra_bits, - struct extent_state **cached_state) -{ - return set_extent_bit(tree, start, end, - EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits, - NULL, cached_state, GFP_NOFS); -} - -static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached_state) -{ - return set_extent_bit(tree, start, end, - EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG, - NULL, cached_state, GFP_NOFS); -} - -static inline int set_extent_new(struct extent_io_tree *tree, u64 start, - u64 end) -{ - return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL, - GFP_NOFS); -} - -static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached_state, gfp_t mask) -{ - return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL, - cached_state, mask); -} - -int find_first_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits, - struct extent_state **cached_state); -void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits); -int extent_invalidatepage(struct extent_io_tree *tree, - struct page *page, unsigned long offset); int extent_write_full_page(struct page *page, struct writeback_control *wbc); int extent_write_locked_range(struct inode *inode, u64 start, u64 end, int mode); @@ -442,11 +230,6 @@ static inline int num_extent_pages(const struct extent_buffer *eb) (eb->start >> PAGE_SHIFT); } -static inline void extent_buffer_get(struct extent_buffer *eb) -{ - atomic_inc(&eb->refs); -} - static inline int extent_buffer_uptodate(struct extent_buffer *eb) { return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); @@ -508,10 +291,6 @@ struct btrfs_inode; int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, u64 length, u64 logical, struct page *page, unsigned int pg_offset, int mirror_num); -int clean_io_failure(struct btrfs_fs_info *fs_info, - struct extent_io_tree *failure_tree, - struct extent_io_tree *io_tree, u64 start, - struct page *page, u64 ino, unsigned int pg_offset); void end_extent_writepage(struct page *page, int err, u64 start, u64 end); int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num); @@ -535,19 +314,12 @@ struct io_failure_record { }; -void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, - u64 end); -int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, - struct io_failure_record **failrec_ret); bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages, struct io_failure_record *failrec, int fail_mirror); struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, struct page *page, int pg_offset, int icsum, bio_end_io_t *endio_func, void *data); -int free_io_failure(struct extent_io_tree *failure_tree, - struct extent_io_tree *io_tree, - struct io_failure_record *rec); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS bool find_lock_delalloc_range(struct inode *inode, struct page *locked_page, u64 *start, @@ -555,5 +327,4 @@ bool find_lock_delalloc_range(struct inode *inode, #endif struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, u64 start); - #endif diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 9d30acca55e1..6f417ff68980 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -214,9 +214,13 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next) ASSERT(next->block_start != EXTENT_MAP_DELALLOC && prev->block_start != EXTENT_MAP_DELALLOC); + if (prev->map_lookup || next->map_lookup) + ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) && + test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags)); + if (extent_map_end(prev) == next->start && prev->flags == next->flags && - prev->bdev == next->bdev && + prev->map_lookup == next->map_lookup && ((next->block_start == EXTENT_MAP_HOLE && prev->block_start == EXTENT_MAP_HOLE) || (next->block_start == EXTENT_MAP_INLINE && diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index 473f039fcd7c..8e217337dff9 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -42,15 +42,8 @@ struct extent_map { u64 block_len; u64 generation; unsigned long flags; - union { - struct block_device *bdev; - - /* - * used for chunk mappings - * flags & EXTENT_FLAG_FS_MAPPING must be set - */ - struct map_lookup *map_lookup; - }; + /* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */ + struct map_lookup *map_lookup; refcount_t refs; unsigned int compress_type; struct list_head list; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 1a599f50837b..3270a40b0777 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -945,7 +945,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, u8 type = btrfs_file_extent_type(leaf, fi); int compress_type = btrfs_file_extent_compression(leaf, fi); - em->bdev = fs_info->fs_devices->latest_bdev; btrfs_item_key_to_cpu(leaf, &key, slot); extent_start = key.offset; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 435a502a3226..0cb43b682789 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -296,7 +296,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, key.objectid = defrag->ino; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL); + inode = btrfs_iget(fs_info->sb, &key, inode_root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto cleanup; @@ -667,7 +667,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, } split->generation = gen; - split->bdev = em->bdev; split->flags = flags; split->compress_type = em->compress_type; replace_extent_mapping(em_tree, em, split, modified); @@ -680,7 +679,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, split->start = start + len; split->len = em->start + em->len - (start + len); - split->bdev = em->bdev; split->flags = flags; split->compress_type = em->compress_type; split->generation = gen; @@ -1636,6 +1634,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, break; } + only_release_metadata = false; sector_offset = pos & (fs_info->sectorsize - 1); reserve_bytes = round_up(write_bytes + sector_offset, fs_info->sectorsize); @@ -1791,7 +1790,6 @@ again: set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, EXTENT_NORESERVE, NULL, NULL, GFP_NOFS); - only_release_metadata = false; } btrfs_drop_pages(pages, num_pages); @@ -1903,9 +1901,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, (iocb->ki_flags & IOCB_NOWAIT)) return -EOPNOTSUPP; - if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) return -EAGAIN; + } else { inode_lock(inode); } @@ -2359,7 +2358,6 @@ out: hole_em->block_start = EXTENT_MAP_HOLE; hole_em->block_len = 0; hole_em->orig_block_len = 0; - hole_em->bdev = fs_info->fs_devices->latest_bdev; hole_em->compress_type = BTRFS_COMPRESS_NONE; hole_em->generation = trans->transid; @@ -3350,29 +3348,30 @@ out: return ret; } -static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) +static loff_t find_desired_extent(struct inode *inode, loff_t offset, + int whence) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *em = NULL; struct extent_state *cached_state = NULL; + loff_t i_size = inode->i_size; u64 lockstart; u64 lockend; u64 start; u64 len; int ret = 0; - if (inode->i_size == 0) + if (i_size == 0 || offset >= i_size) return -ENXIO; /* - * *offset can be negative, in this case we start finding DATA/HOLE from + * offset can be negative, in this case we start finding DATA/HOLE from * the very start of the file. */ - start = max_t(loff_t, 0, *offset); + start = max_t(loff_t, 0, offset); lockstart = round_down(start, fs_info->sectorsize); - lockend = round_up(i_size_read(inode), - fs_info->sectorsize); + lockend = round_up(i_size, fs_info->sectorsize); if (lockend <= lockstart) lockend = lockstart + fs_info->sectorsize; lockend--; @@ -3381,7 +3380,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); - while (start < inode->i_size) { + while (start < i_size) { em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len); if (IS_ERR(em)) { ret = PTR_ERR(em); @@ -3404,46 +3403,39 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) cond_resched(); } free_extent_map(em); - if (!ret) { - if (whence == SEEK_DATA && start >= inode->i_size) - ret = -ENXIO; - else - *offset = min_t(loff_t, start, inode->i_size); - } unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); - return ret; + if (ret) { + offset = ret; + } else { + if (whence == SEEK_DATA && start >= i_size) + offset = -ENXIO; + else + offset = min_t(loff_t, start, i_size); + } + + return offset; } static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; - int ret; - inode_lock(inode); switch (whence) { - case SEEK_END: - case SEEK_CUR: - offset = generic_file_llseek(file, offset, whence); - goto out; + default: + return generic_file_llseek(file, offset, whence); case SEEK_DATA: case SEEK_HOLE: - if (offset >= i_size_read(inode)) { - inode_unlock(inode); - return -ENXIO; - } - - ret = find_desired_extent(inode, &offset, whence); - if (ret) { - inode_unlock(inode); - return ret; - } + inode_lock_shared(inode); + offset = find_desired_extent(inode, offset, whence); + inode_unlock_shared(inode); + break; } - offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes); -out: - inode_unlock(inode); - return offset; + if (offset < 0) + return offset; + + return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } static int btrfs_file_open(struct inode *inode, struct file *filp) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index d54dcd0ab230..3283da419200 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -78,7 +78,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, * sure NOFS is set to keep us from deadlocking. */ nofs_flag = memalloc_nofs_save(); - inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path); + inode = btrfs_iget_path(fs_info->sb, &location, root, path); btrfs_release_path(path); memalloc_nofs_restore(nofs_flag); if (IS_ERR(inode)) @@ -91,8 +91,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, return inode; } -struct inode *lookup_free_space_inode( - struct btrfs_block_group_cache *block_group, +struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = block_group->fs_info; @@ -107,7 +106,7 @@ struct inode *lookup_free_space_inode( return inode; inode = __lookup_free_space_inode(fs_info->tree_root, path, - block_group->key.objectid); + block_group->start); if (IS_ERR(inode)) return inode; @@ -190,7 +189,7 @@ static int __create_free_space_inode(struct btrfs_root *root, } int create_free_space_inode(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path) { int ret; @@ -201,7 +200,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans, return ret; return __create_free_space_inode(trans->fs_info->tree_root, trans, path, - ino, block_group->key.objectid); + ino, block_group->start); } int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, @@ -224,7 +223,7 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, } int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct inode *inode) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -385,6 +384,12 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode if (uptodate && !PageUptodate(page)) { btrfs_readpage(NULL, page); lock_page(page); + if (page->mapping != inode->i_mapping) { + btrfs_err(BTRFS_I(inode)->root->fs_info, + "free space cache page truncated"); + io_ctl_drop_pages(io_ctl); + return -EIO; + } if (!PageUptodate(page)) { btrfs_err(BTRFS_I(inode)->root->fs_info, "error reading free space cache"); @@ -814,7 +819,7 @@ free_cache: goto out; } -int load_free_space_cache(struct btrfs_block_group_cache *block_group) +int load_free_space_cache(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; @@ -822,7 +827,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group) struct btrfs_path *path; int ret = 0; bool matched; - u64 used = btrfs_block_group_used(&block_group->item); + u64 used = block_group->used; /* * If this block group has been marked to be cleared for one reason or @@ -876,13 +881,13 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group) spin_unlock(&block_group->lock); ret = __load_free_space_cache(fs_info->tree_root, inode, ctl, - path, block_group->key.objectid); + path, block_group->start); btrfs_free_path(path); if (ret <= 0) goto out; spin_lock(&ctl->tree_lock); - matched = (ctl->free_space == (block_group->key.offset - used - + matched = (ctl->free_space == (block_group->length - used - block_group->bytes_super)); spin_unlock(&ctl->tree_lock); @@ -890,7 +895,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group) __btrfs_remove_free_space_cache(ctl); btrfs_warn(fs_info, "block group %llu has wrong amount of free space", - block_group->key.objectid); + block_group->start); ret = -1; } out: @@ -903,7 +908,7 @@ out: btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuilding it now", - block_group->key.objectid); + block_group->start); } iput(inode); @@ -913,7 +918,7 @@ out: static noinline_for_stack int write_cache_extent_entries(struct btrfs_io_ctl *io_ctl, struct btrfs_free_space_ctl *ctl, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, int *entries, int *bitmaps, struct list_head *bitmap_list) { @@ -1041,7 +1046,7 @@ fail: } static noinline_for_stack int write_pinned_extent_entries( - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_io_ctl *io_ctl, int *entries) { @@ -1061,9 +1066,9 @@ static noinline_for_stack int write_pinned_extent_entries( */ unpin = block_group->fs_info->pinned_extents; - start = block_group->key.objectid; + start = block_group->start; - while (start < block_group->key.objectid + block_group->key.offset) { + while (start < block_group->start + block_group->length) { ret = find_first_extent_bit(unpin, start, &extent_start, &extent_end, EXTENT_DIRTY, NULL); @@ -1071,13 +1076,12 @@ static noinline_for_stack int write_pinned_extent_entries( return 0; /* This pinned extent is out of our range */ - if (extent_start >= block_group->key.objectid + - block_group->key.offset) + if (extent_start >= block_group->start + block_group->length) return 0; extent_start = max(extent_start, start); - extent_end = min(block_group->key.objectid + - block_group->key.offset, extent_end + 1); + extent_end = min(block_group->start + block_group->length, + extent_end + 1); len = extent_end - extent_start; *entries += 1; @@ -1141,7 +1145,7 @@ cleanup_write_cache_enospc(struct inode *inode, static int __btrfs_wait_cache_io(struct btrfs_root *root, struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_io_ctl *io_ctl, struct btrfs_path *path, u64 offset) { @@ -1168,7 +1172,7 @@ out: #ifdef DEBUG btrfs_err(root->fs_info, "failed to write free space cache for block group %llu", - block_group->key.objectid); + block_group->start); #endif } } @@ -1210,12 +1214,12 @@ static int btrfs_wait_cache_io_root(struct btrfs_root *root, } int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path) { return __btrfs_wait_cache_io(block_group->fs_info->tree_root, trans, block_group, &block_group->io_ctl, - path, block_group->key.objectid); + path, block_group->start); } /** @@ -1231,7 +1235,7 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, */ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, struct btrfs_free_space_ctl *ctl, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_io_ctl *io_ctl, struct btrfs_trans_handle *trans) { @@ -1369,7 +1373,7 @@ out_unlock: } int btrfs_write_out_cache(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1394,7 +1398,7 @@ int btrfs_write_out_cache(struct btrfs_trans_handle *trans, #ifdef DEBUG btrfs_err(fs_info, "failed to write free space cache for block group %llu", - block_group->key.objectid); + block_group->start); #endif spin_lock(&block_group->lock); block_group->disk_cache_state = BTRFS_DC_ERROR; @@ -1647,11 +1651,11 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl, static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) { - struct btrfs_block_group_cache *block_group = ctl->private; + struct btrfs_block_group *block_group = ctl->private; u64 max_bytes; u64 bitmap_bytes; u64 extent_bytes; - u64 size = block_group->key.offset; + u64 size = block_group->length; u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit; u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg); @@ -1991,7 +1995,7 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl, static bool use_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info) { - struct btrfs_block_group_cache *block_group = ctl->private; + struct btrfs_block_group *block_group = ctl->private; struct btrfs_fs_info *fs_info = block_group->fs_info; bool forced = false; @@ -2028,7 +2032,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl, * so allow those block groups to still be allowed to have a bitmap * entry. */ - if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->key.offset) + if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->length) return false; return true; @@ -2043,7 +2047,7 @@ static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info) { struct btrfs_free_space *bitmap_info; - struct btrfs_block_group_cache *block_group = NULL; + struct btrfs_block_group *block_group = NULL; int added = 0; u64 bytes, offset, bytes_added; int ret; @@ -2380,7 +2384,7 @@ out: return ret; } -int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, +int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { return __btrfs_add_free_space(block_group->fs_info, @@ -2388,7 +2392,7 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, bytenr, size); } -int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, +int btrfs_remove_free_space(struct btrfs_block_group *block_group, u64 offset, u64 bytes) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; @@ -2478,7 +2482,7 @@ out: return ret; } -void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, +void btrfs_dump_free_space(struct btrfs_block_group *block_group, u64 bytes) { struct btrfs_fs_info *fs_info = block_group->fs_info; @@ -2503,14 +2507,14 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, "%d blocks of free space at or bigger than bytes is", count); } -void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group) +void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; spin_lock_init(&ctl->tree_lock); ctl->unit = fs_info->sectorsize; - ctl->start = block_group->key.objectid; + ctl->start = block_group->start; ctl->private = block_group; ctl->op = &free_space_op; INIT_LIST_HEAD(&ctl->trimming_ranges); @@ -2532,7 +2536,7 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group) */ static int __btrfs_return_cluster_to_free_space( - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; @@ -2598,7 +2602,7 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl) spin_unlock(&ctl->tree_lock); } -void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group) +void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_cluster *cluster; @@ -2620,7 +2624,7 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group) } -u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, +u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 offset, u64 bytes, u64 empty_size, u64 *max_extent_size) { @@ -2674,7 +2678,7 @@ out: * cluster and remove the cluster from it. */ int btrfs_return_cluster_to_free_space( - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster) { struct btrfs_free_space_ctl *ctl; @@ -2708,7 +2712,7 @@ int btrfs_return_cluster_to_free_space( return ret; } -static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, +static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, struct btrfs_free_space *entry, u64 bytes, u64 min_start, @@ -2741,7 +2745,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, * if it couldn't find anything suitably large, or a logical disk offset * if things worked out */ -u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, +u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 bytes, u64 min_start, u64 *max_extent_size) { @@ -2827,7 +2831,7 @@ out: return ret; } -static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group, +static int btrfs_bitmap_cluster(struct btrfs_block_group *block_group, struct btrfs_free_space *entry, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, @@ -2909,7 +2913,7 @@ again: * extent of cont1_bytes, and other clusters of at least min_bytes. */ static noinline int -setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group, +setup_cluster_no_bitmap(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, struct list_head *bitmaps, u64 offset, u64 bytes, u64 cont1_bytes, u64 min_bytes) @@ -3000,7 +3004,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group, * that we have already failed to find extents that will work. */ static noinline int -setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, +setup_cluster_bitmap(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, struct list_head *bitmaps, u64 offset, u64 bytes, u64 cont1_bytes, u64 min_bytes) @@ -3050,7 +3054,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, * returns zero and sets up cluster if things worked out, otherwise * it returns -enospc */ -int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group, +int btrfs_find_space_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size) { @@ -3141,7 +3145,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster) cluster->block_group = NULL; } -static int do_trimming(struct btrfs_block_group_cache *block_group, +static int do_trimming(struct btrfs_block_group *block_group, u64 *total_trimmed, u64 start, u64 bytes, u64 reserved_start, u64 reserved_bytes, struct btrfs_trim_range *trim_entry) @@ -3186,7 +3190,7 @@ static int do_trimming(struct btrfs_block_group_cache *block_group, return ret; } -static int trim_no_bitmap(struct btrfs_block_group_cache *block_group, +static int trim_no_bitmap(struct btrfs_block_group *block_group, u64 *total_trimmed, u64 start, u64 end, u64 minlen) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; @@ -3271,7 +3275,7 @@ out: return ret; } -static int trim_bitmaps(struct btrfs_block_group_cache *block_group, +static int trim_bitmaps(struct btrfs_block_group *block_group, u64 *total_trimmed, u64 start, u64 end, u64 minlen) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; @@ -3352,12 +3356,12 @@ next: return ret; } -void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache) +void btrfs_get_block_group_trimming(struct btrfs_block_group *cache) { atomic_inc(&cache->trimming); } -void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group) +void btrfs_put_block_group_trimming(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct extent_map_tree *em_tree; @@ -3373,7 +3377,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group) mutex_lock(&fs_info->chunk_mutex); em_tree = &fs_info->mapping_tree; write_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, block_group->key.objectid, + em = lookup_extent_mapping(em_tree, block_group->start, 1); BUG_ON(!em); /* logic error, can't happen */ remove_extent_mapping(em_tree, em); @@ -3392,7 +3396,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group) } } -int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group, +int btrfs_trim_block_group(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen) { int ret; @@ -3590,7 +3594,7 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root, * how the free space cache loading stuff works, so you can get really weird * configurations. */ -int test_add_free_space_entry(struct btrfs_block_group_cache *cache, +int test_add_free_space_entry(struct btrfs_block_group *cache, u64 offset, u64 bytes, bool bitmap) { struct btrfs_free_space_ctl *ctl = cache->free_space_ctl; @@ -3658,7 +3662,7 @@ again: * just used to check the absence of space, so if there is free space in the * range at all we will return 1. */ -int test_check_exists(struct btrfs_block_group_cache *cache, +int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes) { struct btrfs_free_space_ctl *ctl = cache->free_space_ctl; diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 39c32c8fc24f..ba9a23241101 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -50,24 +50,23 @@ struct btrfs_io_ctl { unsigned check_crcs:1; }; -struct inode *lookup_free_space_inode( - struct btrfs_block_group_cache *block_group, +struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group, struct btrfs_path *path); int create_free_space_inode(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path); int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct inode *inode); -int load_free_space_cache(struct btrfs_block_group_cache *block_group); +int load_free_space_cache(struct btrfs_block_group *block_group); int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path); int btrfs_write_out_cache(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path); struct inode *lookup_free_ino_inode(struct btrfs_root *root, struct btrfs_path *path); @@ -81,42 +80,40 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root, struct btrfs_path *path, struct inode *inode); -void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group); +void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group); int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, struct btrfs_free_space_ctl *ctl, u64 bytenr, u64 size); -int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, +int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); -int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, +int btrfs_remove_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl); -void btrfs_remove_free_space_cache(struct btrfs_block_group_cache - *block_group); -u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, +void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group); +u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 offset, u64 bytes, u64 empty_size, u64 *max_extent_size); u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root); -void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, +void btrfs_dump_free_space(struct btrfs_block_group *block_group, u64 bytes); -int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group, +int btrfs_find_space_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size); void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); -u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, +u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 bytes, u64 min_start, u64 *max_extent_size); int btrfs_return_cluster_to_free_space( - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster); -int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group, +int btrfs_trim_block_group(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen); /* Support functions for running our sanity tests */ #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -int test_add_free_space_entry(struct btrfs_block_group_cache *cache, +int test_add_free_space_entry(struct btrfs_block_group *cache, u64 offset, u64 bytes, bool bitmap); -int test_check_exists(struct btrfs_block_group_cache *cache, - u64 offset, u64 bytes); +int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes); #endif #endif diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 48a03f5240f5..258cb3fae17a 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -13,10 +13,10 @@ #include "block-group.h" static int __add_block_group_free_space(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path); -void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache) +void set_free_space_tree_thresholds(struct btrfs_block_group *cache) { u32 bitmap_range; size_t bitmap_size; @@ -27,8 +27,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache) * exceeds that required for using bitmaps. */ bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS; - num_bitmaps = div_u64(cache->key.offset + bitmap_range - 1, - bitmap_range); + num_bitmaps = div_u64(cache->length + bitmap_range - 1, bitmap_range); bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE; total_bitmap_size = num_bitmaps * bitmap_size; cache->bitmap_high_thresh = div_u64(total_bitmap_size, @@ -45,7 +44,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache) } static int add_new_free_space_info(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_root *root = trans->fs_info->free_space_root; @@ -54,9 +53,9 @@ static int add_new_free_space_info(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; int ret; - key.objectid = block_group->key.objectid; + key.objectid = block_group->start; key.type = BTRFS_FREE_SPACE_INFO_KEY; - key.offset = block_group->key.offset; + key.offset = block_group->length; ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info)); if (ret) @@ -78,7 +77,7 @@ out: EXPORT_FOR_TESTS struct btrfs_free_space_info *search_free_space_info( struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, int cow) { struct btrfs_fs_info *fs_info = block_group->fs_info; @@ -86,16 +85,16 @@ struct btrfs_free_space_info *search_free_space_info( struct btrfs_key key; int ret; - key.objectid = block_group->key.objectid; + key.objectid = block_group->start; key.type = BTRFS_FREE_SPACE_INFO_KEY; - key.offset = block_group->key.offset; + key.offset = block_group->length; ret = btrfs_search_slot(trans, root, &key, path, 0, cow); if (ret < 0) return ERR_PTR(ret); if (ret != 0) { btrfs_warn(fs_info, "missing free space info for %llu", - block_group->key.objectid); + block_group->start); ASSERT(0); return ERR_PTR(-ENOENT); } @@ -180,7 +179,7 @@ static void le_bitmap_set(unsigned long *map, unsigned int start, int len) EXPORT_FOR_TESTS int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -197,7 +196,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, int done = 0, nr; int ret; - bitmap_size = free_space_bitmap_size(block_group->key.offset, + bitmap_size = free_space_bitmap_size(block_group->length, fs_info->sectorsize); bitmap = alloc_bitmap(bitmap_size); if (!bitmap) { @@ -205,8 +204,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, goto out; } - start = block_group->key.objectid; - end = block_group->key.objectid + block_group->key.offset; + start = block_group->start; + end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; @@ -224,8 +223,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { - ASSERT(found_key.objectid == block_group->key.objectid); - ASSERT(found_key.offset == block_group->key.offset); + ASSERT(found_key.objectid == block_group->start); + ASSERT(found_key.offset == block_group->length); done = 1; break; } else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) { @@ -271,7 +270,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", - block_group->key.objectid, extent_count, + block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; @@ -320,7 +319,7 @@ out: EXPORT_FOR_TESTS int convert_free_space_to_extents(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -336,7 +335,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, int done = 0, nr; int ret; - bitmap_size = free_space_bitmap_size(block_group->key.offset, + bitmap_size = free_space_bitmap_size(block_group->length, fs_info->sectorsize); bitmap = alloc_bitmap(bitmap_size); if (!bitmap) { @@ -344,8 +343,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, goto out; } - start = block_group->key.objectid; - end = block_group->key.objectid + block_group->key.offset; + start = block_group->start; + end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; @@ -363,8 +362,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { - ASSERT(found_key.objectid == block_group->key.objectid); - ASSERT(found_key.offset == block_group->key.offset); + ASSERT(found_key.objectid == block_group->start); + ASSERT(found_key.offset == block_group->length); done = 1; break; } else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) { @@ -413,7 +412,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); - nrbits = div_u64(block_group->key.offset, block_group->fs_info->sectorsize); + nrbits = div_u64(block_group->length, block_group->fs_info->sectorsize); start_bit = find_next_bit_le(bitmap, nrbits, 0); while (start_bit < nrbits) { @@ -437,7 +436,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", - block_group->key.objectid, extent_count, + block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; @@ -453,7 +452,7 @@ out: } static int update_free_space_extent_count(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, int new_extents) { @@ -491,7 +490,7 @@ out: } EXPORT_FOR_TESTS -int free_space_test_bit(struct btrfs_block_group_cache *block_group, +int free_space_test_bit(struct btrfs_block_group *block_group, struct btrfs_path *path, u64 offset) { struct extent_buffer *leaf; @@ -513,7 +512,7 @@ int free_space_test_bit(struct btrfs_block_group_cache *block_group, return !!extent_buffer_test_bit(leaf, ptr, i); } -static void free_space_set_bits(struct btrfs_block_group_cache *block_group, +static void free_space_set_bits(struct btrfs_block_group *block_group, struct btrfs_path *path, u64 *start, u64 *size, int bit) { @@ -581,7 +580,7 @@ static int free_space_next_bitmap(struct btrfs_trans_handle *trans, * the bitmap. */ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size, int remove) { @@ -597,7 +596,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans, * Read the bit for the block immediately before the extent of space if * that block is within the block group. */ - if (start > block_group->key.objectid) { + if (start > block_group->start) { u64 prev_block = start - block_group->fs_info->sectorsize; key.objectid = prev_block; @@ -649,7 +648,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans, * Read the bit for the block immediately after the extent of space if * that block is within the block group. */ - if (end < block_group->key.objectid + block_group->key.offset) { + if (end < block_group->start + block_group->length) { /* The next block may be in the next bitmap. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (end >= key.objectid + key.offset) { @@ -694,7 +693,7 @@ out: } static int remove_free_space_extent(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { @@ -781,7 +780,7 @@ out: EXPORT_FOR_TESTS int __remove_from_free_space_tree(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_free_space_info *info; @@ -812,7 +811,7 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans, int remove_from_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_path *path; int ret; @@ -846,7 +845,7 @@ out: } static int add_free_space_extent(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { @@ -880,7 +879,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans, new_key.offset = size; /* Search for a neighbor on the left. */ - if (start == block_group->key.objectid) + if (start == block_group->start) goto right; key.objectid = start - 1; key.type = (u8)-1; @@ -900,8 +899,8 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans, found_start = key.objectid; found_end = key.objectid + key.offset; - ASSERT(found_start >= block_group->key.objectid && - found_end > block_group->key.objectid); + ASSERT(found_start >= block_group->start && + found_end > block_group->start); ASSERT(found_start < start && found_end <= start); /* @@ -920,7 +919,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans, right: /* Search for a neighbor on the right. */ - if (end == block_group->key.objectid + block_group->key.offset) + if (end == block_group->start + block_group->length) goto insert; key.objectid = end; key.type = (u8)-1; @@ -940,8 +939,8 @@ right: found_start = key.objectid; found_end = key.objectid + key.offset; - ASSERT(found_start >= block_group->key.objectid && - found_end > block_group->key.objectid); + ASSERT(found_start >= block_group->start && + found_end > block_group->start); ASSERT((found_start < start && found_end <= start) || (found_start >= end && found_end > end)); @@ -974,7 +973,7 @@ out: EXPORT_FOR_TESTS int __add_to_free_space_tree(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_free_space_info *info; @@ -1005,7 +1004,7 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans, int add_to_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_path *path; int ret; @@ -1043,7 +1042,7 @@ out: * through the normal add/remove hooks. */ static int populate_free_space_tree(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group) + struct btrfs_block_group *block_group) { struct btrfs_root *extent_root = trans->fs_info->extent_root; struct btrfs_path *path, *path2; @@ -1075,7 +1074,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans, * BLOCK_GROUP_ITEM, so an extent may precede the block group that it's * contained in. */ - key.objectid = block_group->key.objectid; + key.objectid = block_group->start; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = 0; @@ -1084,8 +1083,8 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans, goto out_locked; ASSERT(ret == 0); - start = block_group->key.objectid; - end = block_group->key.objectid + block_group->key.offset; + start = block_group->start; + end = block_group->start + block_group->length; while (1) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); @@ -1109,7 +1108,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans, else start += key.offset; } else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) { - if (key.objectid != block_group->key.objectid) + if (key.objectid != block_group->start) break; } @@ -1140,7 +1139,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *free_space_root; - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct rb_node *node; int ret; @@ -1159,7 +1158,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) node = rb_first(&fs_info->block_group_cache_tree); while (node) { - block_group = rb_entry(node, struct btrfs_block_group_cache, + block_group = rb_entry(node, struct btrfs_block_group, cache_node); ret = populate_free_space_tree(trans, block_group); if (ret) @@ -1265,7 +1264,7 @@ abort: } static int __add_block_group_free_space(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path) { int ret; @@ -1277,12 +1276,12 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans, return ret; return __add_to_free_space_tree(trans, block_group, path, - block_group->key.objectid, - block_group->key.offset); + block_group->start, + block_group->length); } int add_block_group_free_space(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group) + struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path = NULL; @@ -1312,7 +1311,7 @@ out: } int remove_block_group_free_space(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group) + struct btrfs_block_group *block_group) { struct btrfs_root *root = trans->fs_info->free_space_root; struct btrfs_path *path; @@ -1336,8 +1335,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans, goto out; } - start = block_group->key.objectid; - end = block_group->key.objectid + block_group->key.offset; + start = block_group->start; + end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; @@ -1355,8 +1354,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { - ASSERT(found_key.objectid == block_group->key.objectid); - ASSERT(found_key.offset == block_group->key.offset); + ASSERT(found_key.objectid == block_group->start); + ASSERT(found_key.offset == block_group->length); done = 1; nr++; path->slots[0]--; @@ -1391,7 +1390,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, struct btrfs_path *path, u32 expected_extent_count) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_root *root; struct btrfs_key key; @@ -1407,7 +1406,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, fs_info = block_group->fs_info; root = fs_info->free_space_root; - end = block_group->key.objectid + block_group->key.offset; + end = block_group->start + block_group->length; while (1) { ret = btrfs_next_item(root, path); @@ -1454,7 +1453,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", - block_group->key.objectid, extent_count, + block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; @@ -1472,7 +1471,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, struct btrfs_path *path, u32 expected_extent_count) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_root *root; struct btrfs_key key; @@ -1485,7 +1484,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, fs_info = block_group->fs_info; root = fs_info->free_space_root; - end = block_group->key.objectid + block_group->key.offset; + end = block_group->start + block_group->length; while (1) { ret = btrfs_next_item(root, path); @@ -1516,7 +1515,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", - block_group->key.objectid, extent_count, + block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; @@ -1532,7 +1531,7 @@ out: int load_free_space_tree(struct btrfs_caching_control *caching_ctl) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; struct btrfs_free_space_info *info; struct btrfs_path *path; u32 extent_count, flags; diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h index 360d50e1cdea..dc2463e4cfe3 100644 --- a/fs/btrfs/free-space-tree.h +++ b/fs/btrfs/free-space-tree.h @@ -16,14 +16,14 @@ struct btrfs_caching_control; #define BTRFS_FREE_SPACE_BITMAP_SIZE 256 #define BTRFS_FREE_SPACE_BITMAP_BITS (BTRFS_FREE_SPACE_BITMAP_SIZE * BITS_PER_BYTE) -void set_free_space_tree_thresholds(struct btrfs_block_group_cache *block_group); +void set_free_space_tree_thresholds(struct btrfs_block_group *block_group); int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info); int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info); int load_free_space_tree(struct btrfs_caching_control *caching_ctl); int add_block_group_free_space(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group); + struct btrfs_block_group *block_group); int remove_block_group_free_space(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group); + struct btrfs_block_group *block_group); int add_to_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size); int remove_from_free_space_tree(struct btrfs_trans_handle *trans, @@ -32,21 +32,21 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans, #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct btrfs_free_space_info * search_free_space_info(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, int cow); int __add_to_free_space_tree(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size); int __remove_from_free_space_tree(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size); int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path); int convert_free_space_to_extents(struct btrfs_trans_handle *trans, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct btrfs_path *path); -int free_space_test_bit(struct btrfs_block_group_cache *block_group, +int free_space_test_bit(struct btrfs_block_group *block_group, struct btrfs_path *path, u64 offset); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c3f386b7cc0b..56032c518b26 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -368,6 +368,7 @@ struct async_chunk { u64 end; unsigned int write_flags; struct list_head extents; + struct cgroup_subsys_state *blkcg_css; struct btrfs_work work; atomic_t *pending; }; @@ -474,6 +475,7 @@ static noinline int compress_file_range(struct async_chunk *async_chunk) u64 start = async_chunk->start; u64 end = async_chunk->end; u64 actual_end; + u64 i_size; int ret = 0; struct page **pages = NULL; unsigned long nr_pages; @@ -488,7 +490,19 @@ static noinline int compress_file_range(struct async_chunk *async_chunk) inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1, SZ_16K); - actual_end = min_t(u64, i_size_read(inode), end + 1); + /* + * We need to save i_size before now because it could change in between + * us evaluating the size and assigning it. This is because we lock and + * unlock the page in truncate and fallocate, and then modify the i_size + * later on. + * + * The barriers are to emulate READ_ONCE, remove that once i_size_read + * does that for us. + */ + barrier(); + i_size = i_size_read(inode); + barrier(); + actual_end = min_t(u64, i_size, end + 1); again: will_compress = 0; nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1; @@ -699,10 +713,12 @@ cleanup_and_bail_uncompressed: * to our extent and set things up for the async work queue to run * cow_file_range to do the normal delalloc dance. */ - if (page_offset(async_chunk->locked_page) >= start && - page_offset(async_chunk->locked_page) <= end) + if (async_chunk->locked_page && + (page_offset(async_chunk->locked_page) >= start && + page_offset(async_chunk->locked_page)) <= end) { __set_page_dirty_nobuffers(async_chunk->locked_page); /* unlocked later on in the async handlers */ + } if (redirty) extent_range_redirty_for_io(inode, start, end); @@ -782,7 +798,7 @@ retry: async_extent->start + async_extent->ram_size - 1, WB_SYNC_ALL); - else if (ret) + else if (ret && async_chunk->locked_page) unlock_page(async_chunk->locked_page); kfree(async_extent); cond_resched(); @@ -865,7 +881,8 @@ retry: ins.objectid, ins.offset, async_extent->pages, async_extent->nr_pages, - async_chunk->write_flags)) { + async_chunk->write_flags, + async_chunk->blkcg_css)) { struct page *p = async_extent->pages[0]; const u64 start = async_extent->start; const u64 end = start + async_extent->ram_size - 1; @@ -1183,6 +1200,8 @@ static noinline void async_cow_free(struct btrfs_work *work) async_chunk = container_of(work, struct async_chunk, work); if (async_chunk->inode) btrfs_add_delayed_iput(async_chunk->inode); + if (async_chunk->blkcg_css) + css_put(async_chunk->blkcg_css); /* * Since the pointer to 'pending' is at the beginning of the array of * async_chunk's, freeing it ensures the whole array has been freed. @@ -1191,12 +1210,14 @@ static noinline void async_cow_free(struct btrfs_work *work) kvfree(async_chunk->pending); } -static int cow_file_range_async(struct inode *inode, struct page *locked_page, +static int cow_file_range_async(struct inode *inode, + struct writeback_control *wbc, + struct page *locked_page, u64 start, u64 end, int *page_started, - unsigned long *nr_written, - unsigned int write_flags) + unsigned long *nr_written) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc); struct async_cow *ctx; struct async_chunk *async_chunk; unsigned long nr_pages; @@ -1205,6 +1226,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, int i; bool should_compress; unsigned nofs_flag; + const unsigned int write_flags = wbc_to_write_flags(wbc); unlock_extent(&BTRFS_I(inode)->io_tree, start, end); @@ -1251,14 +1273,45 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, async_chunk[i].inode = inode; async_chunk[i].start = start; async_chunk[i].end = cur_end; - async_chunk[i].locked_page = locked_page; async_chunk[i].write_flags = write_flags; INIT_LIST_HEAD(&async_chunk[i].extents); - btrfs_init_work(&async_chunk[i].work, - btrfs_delalloc_helper, - async_cow_start, async_cow_submit, - async_cow_free); + /* + * The locked_page comes all the way from writepage and its + * the original page we were actually given. As we spread + * this large delalloc region across multiple async_chunk + * structs, only the first struct needs a pointer to locked_page + * + * This way we don't need racey decisions about who is supposed + * to unlock it. + */ + if (locked_page) { + /* + * Depending on the compressibility, the pages might or + * might not go through async. We want all of them to + * be accounted against wbc once. Let's do it here + * before the paths diverge. wbc accounting is used + * only for foreign writeback detection and doesn't + * need full accuracy. Just account the whole thing + * against the first page. + */ + wbc_account_cgroup_owner(wbc, locked_page, + cur_end - start); + async_chunk[i].locked_page = locked_page; + locked_page = NULL; + } else { + async_chunk[i].locked_page = NULL; + } + + if (blkcg_css != blkcg_root_css) { + css_get(blkcg_css); + async_chunk[i].blkcg_css = blkcg_css; + } else { + async_chunk[i].blkcg_css = NULL; + } + + btrfs_init_work(&async_chunk[i].work, async_cow_start, + async_cow_submit, async_cow_free); nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE); atomic_add(nr_pages, &fs_info->async_delalloc_pages); @@ -1684,7 +1737,6 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, { int ret; int force_cow = need_force_cow(inode, start, end); - unsigned int write_flags = wbc_to_write_flags(wbc); if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, @@ -1699,9 +1751,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, } else { set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &BTRFS_I(inode)->runtime_flags); - ret = cow_file_range_async(inode, locked_page, start, end, - page_started, nr_written, - write_flags); + ret = cow_file_range_async(inode, wbc, locked_page, start, end, + page_started, nr_written); } if (ret) btrfs_cleanup_ordered_extents(inode, locked_page, start, @@ -2097,7 +2148,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, } mapit: - ret = btrfs_map_bio(fs_info, bio, mirror_num, 0); + ret = btrfs_map_bio(fs_info, bio, mirror_num); out: if (ret) { @@ -2201,12 +2252,16 @@ again: mapping_set_error(page->mapping, ret); end_extent_writepage(page, ret, page_start, page_end); ClearPageChecked(page); - goto out; + goto out_reserved; } ClearPageChecked(page); set_page_dirty(page); +out_reserved: btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); + if (ret) + btrfs_delalloc_release_space(inode, data_reserved, page_start, + PAGE_SIZE, true); out: unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state); @@ -2247,8 +2302,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end) SetPageChecked(page); get_page(page); - btrfs_init_work(&fixup->work, btrfs_fixup_helper, - btrfs_writepage_fixup_worker, NULL, NULL); + btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL); fixup->page = page; btrfs_queue_work(fs_info->fixup_workers, &fixup->work); return -EBUSY; @@ -2662,7 +2716,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path, key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(fs_info->sb, &key, root, NULL); + inode = btrfs_iget(fs_info->sb, &key, root); if (IS_ERR(inode)) { srcu_read_unlock(&fs_info->subvol_srcu, index); return 0; @@ -2986,7 +3040,7 @@ out_kfree: static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info, u64 start, u64 len) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); ASSERT(cache); @@ -3014,7 +3068,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) int compress_type = 0; int ret = 0; u64 logical_len = ordered_extent->len; - bool nolock; + bool freespace_inode; bool truncated = false; bool range_locked = false; bool clear_new_delalloc_bytes = false; @@ -3025,7 +3079,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags)) clear_new_delalloc_bytes = true; - nolock = btrfs_is_free_space_inode(BTRFS_I(inode)); + freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode)); if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) { ret = -EIO; @@ -3056,8 +3110,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset, ordered_extent->len); btrfs_ordered_update_i_size(inode, 0, ordered_extent); - if (nolock) - trans = btrfs_join_transaction_nolock(root); + if (freespace_inode) + trans = btrfs_join_transaction_spacecache(root); else trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { @@ -3091,8 +3145,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) EXTENT_DEFRAG, 0, 0, &cached_state); } - if (nolock) - trans = btrfs_join_transaction_nolock(root); + if (freespace_inode) + trans = btrfs_join_transaction_spacecache(root); else trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { @@ -3241,7 +3295,6 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ordered_extent *ordered_extent = NULL; struct btrfs_workqueue *wq; - btrfs_work_func_t func; trace_btrfs_writepage_end_io_hook(page, start, end, uptodate); @@ -3250,16 +3303,12 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, end - start + 1, uptodate)) return; - if (btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (btrfs_is_free_space_inode(BTRFS_I(inode))) wq = fs_info->endio_freespace_worker; - func = btrfs_freespace_write_helper; - } else { + else wq = fs_info->endio_write_workers; - func = btrfs_endio_write_helper; - } - btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL, - NULL); + btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL); btrfs_queue_work(wq, &ordered_extent->work); } @@ -3518,7 +3567,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) found_key.objectid = found_key.offset; found_key.type = BTRFS_INODE_ITEM_KEY; found_key.offset = 0; - inode = btrfs_iget(fs_info->sb, &found_key, root, NULL); + inode = btrfs_iget(fs_info->sb, &found_key, root); ret = PTR_ERR_OR_ZERO(inode); if (ret && ret != -ENOENT) goto out; @@ -5140,7 +5189,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) hole_em->block_len = 0; hole_em->orig_block_len = 0; hole_em->ram_bytes = hole_size; - hole_em->bdev = fs_info->fs_devices->latest_bdev; hole_em->compress_type = BTRFS_COMPRESS_NONE; hole_em->generation = fs_info->generation; @@ -5737,12 +5785,14 @@ static struct inode *btrfs_iget_locked(struct super_block *s, return inode; } -/* Get an inode object given its location and corresponding root. - * Returns in *is_new if the inode was read from disk +/* + * Get an inode object given its location and corresponding root. + * Path can be preallocated to prevent recursing back to iget through + * allocator. NULL is also valid but may require an additional allocation + * later. */ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *new, - struct btrfs_path *path) + struct btrfs_root *root, struct btrfs_path *path) { struct inode *inode; @@ -5757,8 +5807,6 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, if (!ret) { inode_tree_add(inode); unlock_new_inode(inode); - if (new) - *new = 1; } else { iget_failed(inode); /* @@ -5776,9 +5824,9 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, } struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *new) + struct btrfs_root *root) { - return btrfs_iget_path(s, location, root, new, NULL); + return btrfs_iget_path(s, location, root, NULL); } static struct inode *new_simple_dir(struct super_block *s, @@ -5844,7 +5892,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) return ERR_PTR(ret); if (location.type == BTRFS_INODE_ITEM_KEY) { - inode = btrfs_iget(dir->i_sb, &location, root, NULL); + inode = btrfs_iget(dir->i_sb, &location, root); if (IS_ERR(inode)) return inode; @@ -5869,7 +5917,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) else inode = new_simple_dir(dir->i_sb, &location, sub_root); } else { - inode = btrfs_iget(dir->i_sb, &location, sub_root, NULL); + inode = btrfs_iget(dir->i_sb, &location, sub_root); } srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -6918,8 +6966,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, start, len); - if (em) - em->bdev = fs_info->fs_devices->latest_bdev; read_unlock(&em_tree->lock); if (em) { @@ -6935,7 +6981,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, err = -ENOMEM; goto out; } - em->bdev = fs_info->fs_devices->latest_bdev; em->start = EXTENT_MAP_HOLE; em->orig_start = EXTENT_MAP_HOLE; em->len = (u64)-1; @@ -7194,7 +7239,6 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, err = -ENOMEM; goto out; } - em->bdev = NULL; ASSERT(hole_em); /* @@ -7554,7 +7598,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, { struct extent_map_tree *em_tree; struct extent_map *em; - struct btrfs_root *root = BTRFS_I(inode)->root; int ret; ASSERT(type == BTRFS_ORDERED_PREALLOC || @@ -7572,7 +7615,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, em->len = len; em->block_len = block_len; em->block_start = block_start; - em->bdev = root->fs_info->fs_devices->latest_bdev; em->orig_block_len = orig_block_len; em->ram_bytes = ram_bytes; em->generation = -1; @@ -7611,6 +7653,8 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em, struct inode *inode, u64 start, u64 len) { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + if (em->block_start == EXTENT_MAP_HOLE || test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) return -ENOENT; @@ -7620,7 +7664,7 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em, bh_result->b_blocknr = (em->block_start + (start - em->start)) >> inode->i_blkbits; bh_result->b_size = len; - bh_result->b_bdev = em->bdev; + bh_result->b_bdev = fs_info->fs_devices->latest_bdev; set_buffer_mapped(bh_result); return 0; @@ -7703,7 +7747,7 @@ skip_cow: bh_result->b_blocknr = (em->block_start + (start - em->start)) >> inode->i_blkbits; bh_result->b_size = len; - bh_result->b_bdev = em->bdev; + bh_result->b_bdev = fs_info->fs_devices->latest_bdev; set_buffer_mapped(bh_result); if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) @@ -7845,7 +7889,7 @@ static inline blk_status_t submit_dio_repair_bio(struct inode *inode, if (ret) return ret; - ret = btrfs_map_bio(fs_info, bio, mirror_num, 0); + ret = btrfs_map_bio(fs_info, bio, mirror_num); return ret; } @@ -8198,18 +8242,14 @@ static void __endio_write_update_ordered(struct inode *inode, struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ordered_extent *ordered = NULL; struct btrfs_workqueue *wq; - btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; u64 last_offset; - if (btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (btrfs_is_free_space_inode(BTRFS_I(inode))) wq = fs_info->endio_freespace_worker; - func = btrfs_freespace_write_helper; - } else { + else wq = fs_info->endio_write_workers; - func = btrfs_endio_write_helper; - } while (ordered_offset < offset + bytes) { last_offset = ordered_offset; @@ -8217,9 +8257,8 @@ static void __endio_write_update_ordered(struct inode *inode, &ordered_offset, ordered_bytes, uptodate)) { - btrfs_init_work(&ordered->work, func, - finish_ordered_fn, - NULL, NULL); + btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, + NULL); btrfs_queue_work(wq, &ordered->work); } /* @@ -8376,7 +8415,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, goto err; } map: - ret = btrfs_map_bio(fs_info, bio, 0, 0); + ret = btrfs_map_bio(fs_info, bio, 0); err: return ret; } @@ -9308,7 +9347,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->io_failure_tree.track_uptodate = true; atomic_set(&ei->sync_writers, 0); mutex_init(&ei->log_mutex); - mutex_init(&ei->delalloc_mutex); btrfs_ordered_inode_tree_init(&ei->ordered_tree); INIT_LIST_HEAD(&ei->delalloc_inodes); INIT_LIST_HEAD(&ei->delayed_iput); @@ -9537,6 +9575,9 @@ static int btrfs_rename_exchange(struct inode *old_dir, goto out_notrans; } + if (dest != root) + btrfs_record_root_in_trans(trans, dest); + /* * We need to find a free sequence number both in the source and * in the destination directory for the exchange. @@ -9731,6 +9772,18 @@ out_fail: commit_transaction = true; } if (commit_transaction) { + /* + * We may have set commit_transaction when logging the new name + * in the destination root, in which case we left the source + * root context in the list of log contextes. So make sure we + * remove it to avoid invalid memory accesses, since the context + * was allocated in our stack frame. + */ + if (sync_log_root) { + mutex_lock(&root->log_mutex); + list_del_init(&ctx_root.list); + mutex_unlock(&root->log_mutex); + } ret = btrfs_commit_transaction(trans); } else { int ret2; @@ -9744,6 +9797,9 @@ out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); + ASSERT(list_empty(&ctx_root.list)); + ASSERT(list_empty(&ctx_dest.list)); + return ret; } @@ -10088,8 +10144,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode init_completion(&work->completion); INIT_LIST_HEAD(&work->list); work->inode = inode; - btrfs_init_work(&work->work, btrfs_flush_delalloc_helper, - btrfs_run_delalloc_work, NULL, NULL); + btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL); return work; } @@ -10422,7 +10477,6 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, em->block_len = ins.offset; em->orig_block_len = ins.offset; em->ram_bytes = ins.offset; - em->bdev = fs_info->fs_devices->latest_bdev; set_bit(EXTENT_FLAG_PREALLOC, &em->flags); em->generation = trans->transid; @@ -10778,7 +10832,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, start = 0; while (start < isize) { u64 logical_block_start, physical_block_start; - struct btrfs_block_group_cache *bg; + struct btrfs_block_group *bg; u64 len = isize - start; em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7c145a41decd..a1ee0b775e65 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -479,10 +479,9 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg) return put_user(inode->i_generation, arg); } -static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) +static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, + void __user *arg) { - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_device *device; struct request_queue *q; struct fstrim_range range; @@ -541,7 +540,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) return 0; } -int btrfs_is_empty_uuid(u8 *uuid) +int __pure btrfs_is_empty_uuid(u8 *uuid) { int i; @@ -1409,7 +1408,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, return -EINVAL; if (do_compress) { - if (range->compress_type > BTRFS_COMPRESS_TYPES) + if (range->compress_type >= BTRFS_NR_COMPRESS_TYPES) return -EINVAL; if (range->compress_type) compress_type = range->compress_type; @@ -2462,7 +2461,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, goto out; } - temp_inode = btrfs_iget(sb, &key2, root, NULL); + temp_inode = btrfs_iget(sb, &key2, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); goto out; @@ -4032,16 +4031,15 @@ out: static void get_block_group_info(struct list_head *groups_list, struct btrfs_ioctl_space_info *space) { - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; space->total_bytes = 0; space->used_bytes = 0; space->flags = 0; list_for_each_entry(block_group, groups_list, list) { space->flags = block_group->flags; - space->total_bytes += block_group->key.offset; - space->used_bytes += - btrfs_block_group_used(&block_group->item); + space->total_bytes += block_group->length; + space->used_bytes += block_group->used; } } @@ -4195,9 +4193,6 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root, u64 transid; int ret; - btrfs_warn(root->fs_info, - "START_SYNC ioctl is deprecated and will be removed in kernel 5.7"); - trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT) @@ -4225,9 +4220,6 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info, { u64 transid; - btrfs_warn(fs_info, - "WAIT_SYNC ioctl is deprecated and will be removed in kernel 5.7"); - if (argp) { if (copy_from_user(&transid, argp, sizeof(transid))) return -EFAULT; @@ -4958,10 +4950,9 @@ drop_write: return ret; } -static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg) +static long btrfs_ioctl_quota_rescan_status(struct btrfs_fs_info *fs_info, + void __user *arg) { - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_quota_rescan_args *qsa; int ret = 0; @@ -4984,11 +4975,9 @@ static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg) return ret; } -static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg) +static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info, + void __user *arg) { - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -5160,10 +5149,9 @@ out: return ret; } -static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg) +static int btrfs_ioctl_get_fslabel(struct btrfs_fs_info *fs_info, + void __user *arg) { - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); size_t len; int ret; char label[BTRFS_LABEL_SIZE]; @@ -5247,10 +5235,9 @@ int btrfs_ioctl_get_supported_features(void __user *arg) return 0; } -static int btrfs_ioctl_get_features(struct file *file, void __user *arg) +static int btrfs_ioctl_get_features(struct btrfs_fs_info *fs_info, + void __user *arg) { - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_super_block *super_block = fs_info->super_copy; struct btrfs_ioctl_feature_flags features; @@ -5451,11 +5438,11 @@ long btrfs_ioctl(struct file *file, unsigned int case FS_IOC_GETVERSION: return btrfs_ioctl_getversion(file, argp); case FS_IOC_GETFSLABEL: - return btrfs_ioctl_get_fslabel(file, argp); + return btrfs_ioctl_get_fslabel(fs_info, argp); case FS_IOC_SETFSLABEL: return btrfs_ioctl_set_fslabel(file, argp); case FITRIM: - return btrfs_ioctl_fitrim(file, argp); + return btrfs_ioctl_fitrim(fs_info, argp); case BTRFS_IOC_SNAP_CREATE: return btrfs_ioctl_snap_create(file, argp, 0); case BTRFS_IOC_SNAP_CREATE_V2: @@ -5560,15 +5547,15 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_QUOTA_RESCAN: return btrfs_ioctl_quota_rescan(file, argp); case BTRFS_IOC_QUOTA_RESCAN_STATUS: - return btrfs_ioctl_quota_rescan_status(file, argp); + return btrfs_ioctl_quota_rescan_status(fs_info, argp); case BTRFS_IOC_QUOTA_RESCAN_WAIT: - return btrfs_ioctl_quota_rescan_wait(file, argp); + return btrfs_ioctl_quota_rescan_wait(fs_info, argp); case BTRFS_IOC_DEV_REPLACE: return btrfs_ioctl_dev_replace(fs_info, argp); case BTRFS_IOC_GET_SUPPORTED_FEATURES: return btrfs_ioctl_get_supported_features(argp); case BTRFS_IOC_GET_FEATURES: - return btrfs_ioctl_get_features(file, argp); + return btrfs_ioctl_get_features(fs_info, argp); case BTRFS_IOC_SET_FEATURES: return btrfs_ioctl_set_features(file, argp); case FS_IOC_FSGETXATTR: diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 7f9a578a1a20..571c4826c428 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -13,65 +13,164 @@ #include "extent_io.h" #include "locking.h" +/* + * Extent buffer locking + * ===================== + * + * The locks use a custom scheme that allows to do more operations than are + * available fromt current locking primitives. The building blocks are still + * rwlock and wait queues. + * + * Required semantics: + * + * - reader/writer exclusion + * - writer/writer exclusion + * - reader/reader sharing + * - spinning lock semantics + * - blocking lock semantics + * - try-lock semantics for readers and writers + * - one level nesting, allowing read lock to be taken by the same thread that + * already has write lock + * + * The extent buffer locks (also called tree locks) manage access to eb data + * related to the storage in the b-tree (keys, items, but not the individual + * members of eb). + * We want concurrency of many readers and safe updates. The underlying locking + * is done by read-write spinlock and the blocking part is implemented using + * counters and wait queues. + * + * spinning semantics - the low-level rwlock is held so all other threads that + * want to take it are spinning on it. + * + * blocking semantics - the low-level rwlock is not held but the counter + * denotes how many times the blocking lock was held; + * sleeping is possible + * + * Write lock always allows only one thread to access the data. + * + * + * Debugging + * --------- + * + * There are additional state counters that are asserted in various contexts, + * removed from non-debug build to reduce extent_buffer size and for + * performance reasons. + * + * + * Lock nesting + * ------------ + * + * A write operation on a tree might indirectly start a look up on the same + * tree. This can happen when btrfs_cow_block locks the tree and needs to + * lookup free extents. + * + * btrfs_cow_block + * .. + * alloc_tree_block_no_bg_flush + * btrfs_alloc_tree_block + * btrfs_reserve_extent + * .. + * load_free_space_cache + * .. + * btrfs_lookup_file_extent + * btrfs_search_slot + * + * + * Locking pattern - spinning + * -------------------------- + * + * The simple locking scenario, the +--+ denotes the spinning section. + * + * +- btrfs_tree_lock + * | - extent_buffer::rwlock is held + * | - no heavy operations should happen, eg. IO, memory allocations, large + * | structure traversals + * +- btrfs_tree_unock +* +* + * Locking pattern - blocking + * -------------------------- + * + * The blocking write uses the following scheme. The +--+ denotes the spinning + * section. + * + * +- btrfs_tree_lock + * | + * +- btrfs_set_lock_blocking_write + * + * - allowed: IO, memory allocations, etc. + * + * -- btrfs_tree_unlock - note, no explicit unblocking necessary + * + * + * Blocking read is similar. + * + * +- btrfs_tree_read_lock + * | + * +- btrfs_set_lock_blocking_read + * + * - heavy operations allowed + * + * +- btrfs_tree_read_unlock_blocking + * | + * +- btrfs_tree_read_unlock + * + */ + #ifdef CONFIG_BTRFS_DEBUG -static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) +static inline void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { WARN_ON(eb->spinning_writers); eb->spinning_writers++; } -static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) +static inline void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { WARN_ON(eb->spinning_writers != 1); eb->spinning_writers--; } -static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb) +static inline void btrfs_assert_no_spinning_writers(struct extent_buffer *eb) { WARN_ON(eb->spinning_writers); } -static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) +static inline void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { atomic_inc(&eb->spinning_readers); } -static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb) +static inline void btrfs_assert_spinning_readers_put(struct extent_buffer *eb) { WARN_ON(atomic_read(&eb->spinning_readers) == 0); atomic_dec(&eb->spinning_readers); } -static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) +static inline void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { atomic_inc(&eb->read_locks); } -static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) +static inline void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { atomic_dec(&eb->read_locks); } -static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) +static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { BUG_ON(!atomic_read(&eb->read_locks)); } -static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) +static inline void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { eb->write_locks++; } -static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) +static inline void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { eb->write_locks--; } -void btrfs_assert_tree_locked(struct extent_buffer *eb) -{ - BUG_ON(!eb->write_locks); -} - #else static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { } static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { } @@ -81,11 +180,19 @@ static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { } static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { } static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { } static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { } -void btrfs_assert_tree_locked(struct extent_buffer *eb) { } static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { } static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { } #endif +/* + * Mark already held read lock as blocking. Can be nested in write lock by the + * same thread. + * + * Use when there are potentially long operations ahead so other thread waiting + * on the lock will not actively spin but sleep instead. + * + * The rwlock is released and blocking reader counter is increased. + */ void btrfs_set_lock_blocking_read(struct extent_buffer *eb) { trace_btrfs_set_lock_blocking_read(eb); @@ -102,6 +209,14 @@ void btrfs_set_lock_blocking_read(struct extent_buffer *eb) read_unlock(&eb->lock); } +/* + * Mark already held write lock as blocking. + * + * Use when there are potentially long operations ahead so other threads + * waiting on the lock will not actively spin but sleep instead. + * + * The rwlock is released and blocking writers is set. + */ void btrfs_set_lock_blocking_write(struct extent_buffer *eb) { trace_btrfs_set_lock_blocking_write(eb); @@ -115,14 +230,19 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb) if (eb->blocking_writers == 0) { btrfs_assert_spinning_writers_put(eb); btrfs_assert_tree_locked(eb); - eb->blocking_writers++; + WRITE_ONCE(eb->blocking_writers, 1); write_unlock(&eb->lock); } } /* - * take a spinning read lock. This will wait for any blocking - * writers + * Lock the extent buffer for read. Wait for any writers (spinning or blocking). + * Can be nested in write lock by the same thread. + * + * Use when the locked section does only lightweight actions and busy waiting + * would be cheaper than making other threads do the wait/wake loop. + * + * The rwlock is held upon exit. */ void btrfs_tree_read_lock(struct extent_buffer *eb) { @@ -134,23 +254,24 @@ again: read_lock(&eb->lock); BUG_ON(eb->blocking_writers == 0 && current->pid == eb->lock_owner); - if (eb->blocking_writers && current->pid == eb->lock_owner) { - /* - * This extent is already write-locked by our thread. We allow - * an additional read lock to be added because it's for the same - * thread. btrfs_find_all_roots() depends on this as it may be - * called on a partly (write-)locked tree. - */ - BUG_ON(eb->lock_nested); - eb->lock_nested = true; - read_unlock(&eb->lock); - trace_btrfs_tree_read_lock(eb, start_ns); - return; - } if (eb->blocking_writers) { + if (current->pid == eb->lock_owner) { + /* + * This extent is already write-locked by our thread. + * We allow an additional read lock to be added because + * it's for the same thread. btrfs_find_all_roots() + * depends on this as it may be called on a partly + * (write-)locked tree. + */ + BUG_ON(eb->lock_nested); + eb->lock_nested = true; + read_unlock(&eb->lock); + trace_btrfs_tree_read_lock(eb, start_ns); + return; + } read_unlock(&eb->lock); wait_event(eb->write_lock_wq, - eb->blocking_writers == 0); + READ_ONCE(eb->blocking_writers) == 0); goto again; } btrfs_assert_tree_read_locks_get(eb); @@ -159,17 +280,19 @@ again: } /* - * take a spinning read lock. - * returns 1 if we get the read lock and 0 if we don't - * this won't wait for blocking writers + * Lock extent buffer for read, optimistically expecting that there are no + * contending blocking writers. If there are, don't wait. + * + * Return 1 if the rwlock has been taken, 0 otherwise */ int btrfs_tree_read_lock_atomic(struct extent_buffer *eb) { - if (eb->blocking_writers) + if (READ_ONCE(eb->blocking_writers)) return 0; read_lock(&eb->lock); - if (eb->blocking_writers) { + /* Refetch value after lock */ + if (READ_ONCE(eb->blocking_writers)) { read_unlock(&eb->lock); return 0; } @@ -180,18 +303,20 @@ int btrfs_tree_read_lock_atomic(struct extent_buffer *eb) } /* - * returns 1 if we get the read lock and 0 if we don't - * this won't wait for blocking writers + * Try-lock for read. Don't block or wait for contending writers. + * + * Retrun 1 if the rwlock has been taken, 0 otherwise */ int btrfs_try_tree_read_lock(struct extent_buffer *eb) { - if (eb->blocking_writers) + if (READ_ONCE(eb->blocking_writers)) return 0; if (!read_trylock(&eb->lock)) return 0; - if (eb->blocking_writers) { + /* Refetch value after lock */ + if (READ_ONCE(eb->blocking_writers)) { read_unlock(&eb->lock); return 0; } @@ -202,16 +327,19 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb) } /* - * returns 1 if we get the read lock and 0 if we don't - * this won't wait for blocking writers or readers + * Try-lock for write. May block until the lock is uncontended, but does not + * wait until it is free. + * + * Retrun 1 if the rwlock has been taken, 0 otherwise */ int btrfs_try_tree_write_lock(struct extent_buffer *eb) { - if (eb->blocking_writers || atomic_read(&eb->blocking_readers)) + if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) return 0; write_lock(&eb->lock); - if (eb->blocking_writers || atomic_read(&eb->blocking_readers)) { + /* Refetch value after lock */ + if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) { write_unlock(&eb->lock); return 0; } @@ -223,7 +351,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb) } /* - * drop a spinning read lock + * Release read lock. Must be used only if the lock is in spinning mode. If + * the read lock is nested, must pair with read lock before the write unlock. + * + * The rwlock is not held upon exit. */ void btrfs_tree_read_unlock(struct extent_buffer *eb) { @@ -245,7 +376,11 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb) } /* - * drop a blocking read lock + * Release read lock, previously set to blocking by a pairing call to + * btrfs_set_lock_blocking_read(). Can be nested in write lock by the same + * thread. + * + * State of rwlock is unchanged, last reader wakes waiting threads. */ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) { @@ -269,8 +404,10 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) } /* - * take a spinning write lock. This will wait for both - * blocking readers or writers + * Lock for write. Wait for all blocking and spinning readers and writers. This + * starts context where reader lock could be nested by the same thread. + * + * The rwlock is held for write upon exit. */ void btrfs_tree_lock(struct extent_buffer *eb) { @@ -282,9 +419,11 @@ void btrfs_tree_lock(struct extent_buffer *eb) WARN_ON(eb->lock_owner == current->pid); again: wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0); - wait_event(eb->write_lock_wq, eb->blocking_writers == 0); + wait_event(eb->write_lock_wq, READ_ONCE(eb->blocking_writers) == 0); write_lock(&eb->lock); - if (atomic_read(&eb->blocking_readers) || eb->blocking_writers) { + /* Refetch value after lock */ + if (atomic_read(&eb->blocking_readers) || + READ_ONCE(eb->blocking_writers)) { write_unlock(&eb->lock); goto again; } @@ -295,10 +434,19 @@ again: } /* - * drop a spinning or a blocking write lock. + * Release the write lock, either blocking or spinning (ie. there's no need + * for an explicit blocking unlock, like btrfs_tree_read_unlock_blocking). + * This also ends the context for nesting, the read lock must have been + * released already. + * + * Tasks blocked and waiting are woken, rwlock is not held upon exit. */ void btrfs_tree_unlock(struct extent_buffer *eb) { + /* + * This is read both locked and unlocked but always by the same thread + * that already owns the lock so we don't need to use READ_ONCE + */ int blockers = eb->blocking_writers; BUG_ON(blockers > 1); @@ -310,7 +458,8 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { btrfs_assert_no_spinning_writers(eb); - eb->blocking_writers--; + /* Unlocked write */ + WRITE_ONCE(eb->blocking_writers, 0); /* * We need to order modifying blocking_writers above with * actually waking up the sleepers to ensure they see the @@ -322,3 +471,55 @@ void btrfs_tree_unlock(struct extent_buffer *eb) write_unlock(&eb->lock); } } + +/* + * Set all locked nodes in the path to blocking locks. This should be done + * before scheduling + */ +void btrfs_set_path_blocking(struct btrfs_path *p) +{ + int i; + + for (i = 0; i < BTRFS_MAX_LEVEL; i++) { + if (!p->nodes[i] || !p->locks[i]) + continue; + /* + * If we currently have a spinning reader or writer lock this + * will bump the count of blocking holders and drop the + * spinlock. + */ + if (p->locks[i] == BTRFS_READ_LOCK) { + btrfs_set_lock_blocking_read(p->nodes[i]); + p->locks[i] = BTRFS_READ_LOCK_BLOCKING; + } else if (p->locks[i] == BTRFS_WRITE_LOCK) { + btrfs_set_lock_blocking_write(p->nodes[i]); + p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING; + } + } +} + +/* + * This releases any locks held in the path starting at level and going all the + * way up to the root. + * + * btrfs_search_slot will keep the lock held on higher nodes in a few corner + * cases, such as COW of the block at slot zero in the node. This ignores + * those rules, and it should only be called when there are no more updates to + * be done higher up in the tree. + */ +void btrfs_unlock_up_safe(struct btrfs_path *path, int level) +{ + int i; + + if (path->keep_locks) + return; + + for (i = level; i < BTRFS_MAX_LEVEL; i++) { + if (!path->nodes[i]) + continue; + if (!path->locks[i]) + continue; + btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]); + path->locks[i] = 0; + } +} diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index b775a4207ed9..21a285883e89 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -6,6 +6,8 @@ #ifndef BTRFS_LOCKING_H #define BTRFS_LOCKING_H +#include "extent_io.h" + #define BTRFS_WRITE_LOCK 1 #define BTRFS_READ_LOCK 2 #define BTRFS_WRITE_LOCK_BLOCKING 3 @@ -19,11 +21,20 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb); void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb); void btrfs_set_lock_blocking_read(struct extent_buffer *eb); void btrfs_set_lock_blocking_write(struct extent_buffer *eb); -void btrfs_assert_tree_locked(struct extent_buffer *eb); int btrfs_try_tree_read_lock(struct extent_buffer *eb); int btrfs_try_tree_write_lock(struct extent_buffer *eb); int btrfs_tree_read_lock_atomic(struct extent_buffer *eb); +#ifdef CONFIG_BTRFS_DEBUG +static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { + BUG_ON(!eb->write_locks); +} +#else +static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { } +#endif + +void btrfs_set_path_blocking(struct btrfs_path *p); +void btrfs_unlock_up_safe(struct btrfs_path *path, int level); static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw) { diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index acad4174f68d..aa9cd11f4b78 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -63,27 +63,7 @@ struct workspace { static struct workspace_manager wsm; -static void lzo_init_workspace_manager(void) -{ - btrfs_init_workspace_manager(&wsm, &btrfs_lzo_compress); -} - -static void lzo_cleanup_workspace_manager(void) -{ - btrfs_cleanup_workspace_manager(&wsm); -} - -static struct list_head *lzo_get_workspace(unsigned int level) -{ - return btrfs_get_workspace(&wsm, level); -} - -static void lzo_put_workspace(struct list_head *ws) -{ - btrfs_put_workspace(&wsm, ws); -} - -static void lzo_free_workspace(struct list_head *ws) +void lzo_free_workspace(struct list_head *ws) { struct workspace *workspace = list_entry(ws, struct workspace, list); @@ -93,7 +73,7 @@ static void lzo_free_workspace(struct list_head *ws) kfree(workspace); } -static struct list_head *lzo_alloc_workspace(unsigned int level) +struct list_head *lzo_alloc_workspace(unsigned int level) { struct workspace *workspace; @@ -131,13 +111,9 @@ static inline size_t read_compress_length(const char *buf) return le32_to_cpu(dlen); } -static int lzo_compress_pages(struct list_head *ws, - struct address_space *mapping, - u64 start, - struct page **pages, - unsigned long *out_pages, - unsigned long *total_in, - unsigned long *total_out) +int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, + u64 start, struct page **pages, unsigned long *out_pages, + unsigned long *total_in, unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0; @@ -303,7 +279,7 @@ out: return ret; } -static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) +int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0, ret2; @@ -444,10 +420,9 @@ done: return ret; } -static int lzo_decompress(struct list_head *ws, unsigned char *data_in, - struct page *dest_page, - unsigned long start_byte, - size_t srclen, size_t destlen) +int lzo_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, unsigned long start_byte, size_t srclen, + size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); size_t in_len; @@ -508,15 +483,7 @@ out: } const struct btrfs_compress_op btrfs_lzo_compress = { - .init_workspace_manager = lzo_init_workspace_manager, - .cleanup_workspace_manager = lzo_cleanup_workspace_manager, - .get_workspace = lzo_get_workspace, - .put_workspace = lzo_put_workspace, - .alloc_workspace = lzo_alloc_workspace, - .free_workspace = lzo_free_workspace, - .compress_pages = lzo_compress_pages, - .decompress_bio = lzo_decompress_bio, - .decompress = lzo_decompress, + .workspace_manager = &wsm, .max_level = 1, .default_level = 1, }; diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h index 7d564924dfeb..72bab64ecf60 100644 --- a/fs/btrfs/misc.h +++ b/fs/btrfs/misc.h @@ -47,4 +47,15 @@ static inline u64 div_factor_fine(u64 num, int factor) return div_u64(num, 100); } +/* Copy of is_power_of_two that is 64bit safe */ +static inline bool is_power_of_two_u64(u64 n) +{ + return n != 0 && (n & (n - 1)) == 0; +} + +static inline bool has_single_bit_set(u64 n) +{ + return is_power_of_two_u64(n); +} + #endif diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 24b6c72b9a59..fb09bc2f8e4d 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -547,7 +547,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, spin_unlock(&root->ordered_extent_lock); btrfs_init_work(&ordered->flush_work, - btrfs_flush_delalloc_helper, btrfs_run_ordered_extent_work, NULL, NULL); list_add_tail(&ordered->work_list, &works); btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work); @@ -573,12 +572,11 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, return count; } -u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, +void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, const u64 range_start, const u64 range_len) { struct btrfs_root *root; struct list_head splice; - u64 total_done = 0; u64 done; INIT_LIST_HEAD(&splice); @@ -598,7 +596,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, done = btrfs_wait_ordered_extents(root, nr, range_start, range_len); btrfs_put_fs_root(root); - total_done += done; spin_lock(&fs_info->ordered_root_lock); if (nr != U64_MAX) { @@ -608,8 +605,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, list_splice_tail(&splice, &fs_info->ordered_roots); spin_unlock(&fs_info->ordered_root_lock); mutex_unlock(&fs_info->ordered_operations_mutex); - - return total_done; } /* diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 5204171ea962..4eb0319a86d7 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -186,7 +186,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u8 *sum, int len); u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, const u64 range_start, const u64 range_len); -u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, +void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, const u64 range_start, const u64 range_len); void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, struct btrfs_inode *inode, u64 start, diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 9cb50577d982..873b6b694107 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -266,9 +266,9 @@ void btrfs_print_leaf(struct extent_buffer *l) struct btrfs_block_group_item); pr_info( "\t\tblock group used %llu chunk_objectid %llu flags %llu\n", - btrfs_disk_block_group_used(l, bi), - btrfs_disk_block_group_chunk_objectid(l, bi), - btrfs_disk_block_group_flags(l, bi)); + btrfs_block_group_used(l, bi), + btrfs_block_group_chunk_objectid(l, bi), + btrfs_block_group_flags(l, bi)); break; case BTRFS_CHUNK_ITEM_KEY: print_chunk(l, btrfs_item_ptr(l, i, diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 1e664e0b59b8..deb59e7cfcac 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -416,11 +416,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans, key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - parent_inode = btrfs_iget(sb, &key, parent_root, NULL); + parent_inode = btrfs_iget(sb, &key, parent_root); if (IS_ERR(parent_inode)) return PTR_ERR(parent_inode); - child_inode = btrfs_iget(sb, &key, root, NULL); + child_inode = btrfs_iget(sb, &key, root); if (IS_ERR(child_inode)) { iput(parent_inode); return PTR_ERR(child_inode); @@ -437,8 +437,6 @@ void __init btrfs_props_init(void) { int i; - hash_init(prop_handlers_ht); - for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) { struct prop_handler *p = &prop_handlers[i]; u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name)); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3ad151655eb8..93aeb2e539a4 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1811,7 +1811,7 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, btrfs_item_key_to_cpu(dst_path->nodes[dst_level], &key, 0); /* For src_path */ - extent_buffer_get(src_eb); + atomic_inc(&src_eb->refs); src_path->nodes[root_level] = src_eb; src_path->slots[root_level] = dst_path->slots[root_level]; src_path->locks[root_level] = 0; @@ -2067,7 +2067,7 @@ static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans, goto out; } /* For dst_path */ - extent_buffer_get(dst_eb); + atomic_inc(&dst_eb->refs); dst_path->nodes[level] = dst_eb; dst_path->slots[level] = 0; dst_path->locks[level] = 0; @@ -2126,7 +2126,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, * walk back up the tree (adjusting slot pointers as we go) * and restart the search process. */ - extent_buffer_get(root_eb); /* For path */ + atomic_inc(&root_eb->refs); /* For path */ path->nodes[root_level] = root_eb; path->slots[root_level] = 0; path->locks[root_level] = 0; /* so release_path doesn't try to unlock */ @@ -3277,10 +3277,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - memset(&fs_info->qgroup_rescan_work, 0, - sizeof(fs_info->qgroup_rescan_work)); btrfs_init_work(&fs_info->qgroup_rescan_work, - btrfs_qgroup_rescan_helper, btrfs_qgroup_rescan_worker, NULL, NULL); return 0; } @@ -3826,7 +3823,7 @@ out: */ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *subvol_root, - struct btrfs_block_group_cache *bg, + struct btrfs_block_group *bg, struct extent_buffer *subvol_parent, int subvol_slot, struct extent_buffer *reloc_parent, int reloc_slot, u64 last_snapshot) diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 46ba7bd2961c..236f12224d52 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -408,7 +408,7 @@ void btrfs_qgroup_init_swapped_blocks( void btrfs_qgroup_clean_swapped_blocks(struct btrfs_root *root); int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *subvol_root, - struct btrfs_block_group_cache *bg, + struct btrfs_block_group *bg, struct extent_buffer *subvol_parent, int subvol_slot, struct extent_buffer *reloc_parent, int reloc_slot, u64 last_snapshot); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 57a2ac721985..a8e53c8e7b01 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -190,7 +190,7 @@ static void scrub_parity_work(struct btrfs_work *work); static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func) { - btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL); + btrfs_init_work(&rbio->work, work_func, NULL, NULL); btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work); } @@ -671,8 +671,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index) */ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio) { - int bucket = rbio_bucket(rbio); - struct btrfs_stripe_hash *h = rbio->fs_info->stripe_hash_table->table + bucket; + struct btrfs_stripe_hash *h; struct btrfs_raid_bio *cur; struct btrfs_raid_bio *pending; unsigned long flags; @@ -680,64 +679,63 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio) struct btrfs_raid_bio *cache_drop = NULL; int ret = 0; + h = rbio->fs_info->stripe_hash_table->table + rbio_bucket(rbio); + spin_lock_irqsave(&h->lock, flags); list_for_each_entry(cur, &h->hash_list, hash_list) { - if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) { - spin_lock(&cur->bio_list_lock); - - /* can we steal this cached rbio's pages? */ - if (bio_list_empty(&cur->bio_list) && - list_empty(&cur->plug_list) && - test_bit(RBIO_CACHE_BIT, &cur->flags) && - !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) { - list_del_init(&cur->hash_list); - refcount_dec(&cur->refs); - - steal_rbio(cur, rbio); - cache_drop = cur; - spin_unlock(&cur->bio_list_lock); + if (cur->bbio->raid_map[0] != rbio->bbio->raid_map[0]) + continue; - goto lockit; - } + spin_lock(&cur->bio_list_lock); - /* can we merge into the lock owner? */ - if (rbio_can_merge(cur, rbio)) { - merge_rbio(cur, rbio); - spin_unlock(&cur->bio_list_lock); - freeit = rbio; - ret = 1; - goto out; - } + /* Can we steal this cached rbio's pages? */ + if (bio_list_empty(&cur->bio_list) && + list_empty(&cur->plug_list) && + test_bit(RBIO_CACHE_BIT, &cur->flags) && + !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) { + list_del_init(&cur->hash_list); + refcount_dec(&cur->refs); + steal_rbio(cur, rbio); + cache_drop = cur; + spin_unlock(&cur->bio_list_lock); - /* - * we couldn't merge with the running - * rbio, see if we can merge with the - * pending ones. We don't have to - * check for rmw_locked because there - * is no way they are inside finish_rmw - * right now - */ - list_for_each_entry(pending, &cur->plug_list, - plug_list) { - if (rbio_can_merge(pending, rbio)) { - merge_rbio(pending, rbio); - spin_unlock(&cur->bio_list_lock); - freeit = rbio; - ret = 1; - goto out; - } - } + goto lockit; + } - /* no merging, put us on the tail of the plug list, - * our rbio will be started with the currently - * running rbio unlocks - */ - list_add_tail(&rbio->plug_list, &cur->plug_list); + /* Can we merge into the lock owner? */ + if (rbio_can_merge(cur, rbio)) { + merge_rbio(cur, rbio); spin_unlock(&cur->bio_list_lock); + freeit = rbio; ret = 1; goto out; } + + + /* + * We couldn't merge with the running rbio, see if we can merge + * with the pending ones. We don't have to check for rmw_locked + * because there is no way they are inside finish_rmw right now + */ + list_for_each_entry(pending, &cur->plug_list, plug_list) { + if (rbio_can_merge(pending, rbio)) { + merge_rbio(pending, rbio); + spin_unlock(&cur->bio_list_lock); + freeit = rbio; + ret = 1; + goto out; + } + } + + /* + * No merging, put us on the tail of the plug list, our rbio + * will be started with the currently running rbio unlocks + */ + list_add_tail(&rbio->plug_list, &cur->plug_list); + spin_unlock(&cur->bio_list_lock); + ret = 1; + goto out; } lockit: refcount_inc(&rbio->refs); @@ -1743,8 +1741,7 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule) plug = container_of(cb, struct btrfs_plug_cb, cb); if (from_schedule) { - btrfs_init_work(&plug->work, btrfs_rmw_helper, - unplug_work, NULL, NULL); + btrfs_init_work(&plug->work, unplug_work, NULL, NULL); btrfs_queue_work(plug->info->rmw_workers, &plug->work); return; diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index ee6f60547a8d..243a2e44526e 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -227,7 +227,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical, struct btrfs_fs_info *fs_info = dev->fs_info; int ret; struct reada_zone *zone; - struct btrfs_block_group_cache *cache = NULL; + struct btrfs_block_group *cache = NULL; u64 start; u64 end; int i; @@ -248,8 +248,8 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical, if (!cache) return NULL; - start = cache->key.objectid; - end = start + cache->key.offset - 1; + start = cache->start; + end = start + cache->length - 1; btrfs_put_block_group(cache); zone = kzalloc(sizeof(*zone), GFP_KERNEL); @@ -752,21 +752,19 @@ static int reada_start_machine_dev(struct btrfs_device *dev) static void reada_start_machine_worker(struct btrfs_work *work) { struct reada_machine_work *rmw; - struct btrfs_fs_info *fs_info; int old_ioprio; rmw = container_of(work, struct reada_machine_work, work); - fs_info = rmw->fs_info; - - kfree(rmw); old_ioprio = IOPRIO_PRIO_VALUE(task_nice_ioclass(current), task_nice_ioprio(current)); set_task_ioprio(current, BTRFS_IOPRIO_READA); - __reada_start_machine(fs_info); + __reada_start_machine(rmw->fs_info); set_task_ioprio(current, old_ioprio); - atomic_dec(&fs_info->reada_works_cnt); + atomic_dec(&rmw->fs_info->reada_works_cnt); + + kfree(rmw); } static void __reada_start_machine(struct btrfs_fs_info *fs_info) @@ -821,8 +819,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info) /* FIXME we cannot handle this properly right now */ BUG(); } - btrfs_init_work(&rmw->work, btrfs_readahead_helper, - reada_start_machine_worker, NULL, NULL); + btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL); rmw->fs_info = fs_info; btrfs_queue_work(fs_info->readahead_workers, &rmw->work); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 5cd42b66818c..d897a8e5e430 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -147,7 +147,7 @@ struct file_extent_cluster { struct reloc_control { /* block group to relocate */ - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; /* extent tree */ struct btrfs_root *extent_root; /* inode for moving data */ @@ -1560,11 +1560,10 @@ again: return NULL; } -static int in_block_group(u64 bytenr, - struct btrfs_block_group_cache *block_group) +static int in_block_group(u64 bytenr, struct btrfs_block_group *block_group) { - if (bytenr >= block_group->key.objectid && - bytenr < block_group->key.objectid + block_group->key.offset) + if (bytenr >= block_group->start && + bytenr < block_group->start + block_group->length) return 1; return 0; } @@ -2246,7 +2245,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) { level = btrfs_root_level(root_item); - extent_buffer_get(reloc_root->node); + atomic_inc(&reloc_root->node->refs); path->nodes[level] = reloc_root->node; path->slots[level] = 0; } else { @@ -3195,7 +3194,6 @@ static noinline_for_stack int setup_extent_mapping(struct inode *inode, u64 start, u64 end, u64 block_start) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; struct extent_map *em; int ret = 0; @@ -3208,7 +3206,6 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end, em->len = end + 1 - start; em->block_len = em->len; em->block_start = block_start; - em->bdev = fs_info->fs_devices->latest_bdev; set_bit(EXTENT_FLAG_PINNED, &em->flags); lock_extent(&BTRFS_I(inode)->io_tree, start, end); @@ -3544,7 +3541,7 @@ static int block_use_full_backref(struct reloc_control *rc, } static int delete_block_group_cache(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *block_group, + struct btrfs_block_group *block_group, struct inode *inode, u64 ino) { @@ -3560,7 +3557,7 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info, key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(fs_info->sb, &key, root, NULL); + inode = btrfs_iget(fs_info->sb, &key, root); if (IS_ERR(inode)) return -ENOENT; @@ -3863,7 +3860,7 @@ int find_next_extent(struct reloc_control *rc, struct btrfs_path *path, u64 start, end, last; int ret; - last = rc->block_group->key.objectid + rc->block_group->key.offset; + last = rc->block_group->start + rc->block_group->length; while (1) { cond_resched(); if (rc->search_start >= last) { @@ -3980,7 +3977,7 @@ int prepare_to_relocate(struct reloc_control *rc) return -ENOMEM; memset(&rc->cluster, 0, sizeof(rc->cluster)); - rc->search_start = rc->block_group->key.objectid; + rc->search_start = rc->block_group->start; rc->extents_found = 0; rc->nodes_relocated = 0; rc->merging_rsv_size = 0; @@ -4219,7 +4216,7 @@ out: */ static noinline_for_stack struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *group) + struct btrfs_block_group *group) { struct inode *inode = NULL; struct btrfs_trans_handle *trans; @@ -4246,9 +4243,9 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info, key.objectid = objectid; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(fs_info->sb, &key, root, NULL); + inode = btrfs_iget(fs_info->sb, &key, root); BUG_ON(IS_ERR(inode)); - BTRFS_I(inode)->index_cnt = group->key.objectid; + BTRFS_I(inode)->index_cnt = group->start; err = btrfs_orphan_add(trans, BTRFS_I(inode)); out: @@ -4283,7 +4280,7 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info) * Print the block group being relocated */ static void describe_relocation(struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *block_group) + struct btrfs_block_group *block_group) { char buf[128] = {'\0'}; @@ -4291,7 +4288,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info, btrfs_info(fs_info, "relocating block group %llu flags %s", - block_group->key.objectid, buf); + block_group->start, buf); } /* @@ -4299,7 +4296,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info, */ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) { - struct btrfs_block_group_cache *bg; + struct btrfs_block_group *bg; struct btrfs_root *extent_root = fs_info->extent_root; struct reloc_control *rc; struct inode *inode; @@ -4326,7 +4323,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) rc->extent_root = extent_root; rc->block_group = bg; - ret = btrfs_inc_block_group_ro(rc->block_group); + ret = btrfs_inc_block_group_ro(rc->block_group, true); if (ret) { err = ret; goto out; @@ -4364,8 +4361,8 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) btrfs_wait_block_group_reservations(rc->block_group); btrfs_wait_nocow_writers(rc->block_group); btrfs_wait_ordered_roots(fs_info, U64_MAX, - rc->block_group->key.objectid, - rc->block_group->key.offset); + rc->block_group->start, + rc->block_group->length); while (1) { mutex_lock(&fs_info->cleaner_mutex); @@ -4405,7 +4402,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) WARN_ON(rc->block_group->pinned > 0); WARN_ON(rc->block_group->reserved > 0); - WARN_ON(btrfs_block_group_used(&rc->block_group->item) > 0); + WARN_ON(rc->block_group->used > 0); out: if (err && rw) btrfs_dec_block_group_ro(rc->block_group); @@ -4688,7 +4685,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, node->new_bytenr != buf->start); drop_node_buffer(node); - extent_buffer_get(cow); + atomic_inc(&cow->refs); node->eb = cow; node->new_bytenr = cow->start; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index f7d4e03f4c5d..21de630b0730 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -389,8 +389,7 @@ static struct full_stripe_lock *search_full_stripe_lock( * * Caller must ensure @cache is a RAID56 block group. */ -static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache, - u64 bytenr) +static u64 get_full_stripe_logical(struct btrfs_block_group *cache, u64 bytenr) { u64 ret; @@ -404,8 +403,8 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache, * round_down() can only handle power of 2, while RAID56 full * stripe length can be 64KiB * n, so we need to manually round down. */ - ret = div64_u64(bytenr - cache->key.objectid, cache->full_stripe_len) * - cache->full_stripe_len + cache->key.objectid; + ret = div64_u64(bytenr - cache->start, cache->full_stripe_len) * + cache->full_stripe_len + cache->start; return ret; } @@ -423,7 +422,7 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache, static int lock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr, bool *locked_ret) { - struct btrfs_block_group_cache *bg_cache; + struct btrfs_block_group *bg_cache; struct btrfs_full_stripe_locks_tree *locks_root; struct full_stripe_lock *existing; u64 fstripe_start; @@ -470,7 +469,7 @@ out: static int unlock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr, bool locked) { - struct btrfs_block_group_cache *bg_cache; + struct btrfs_block_group *bg_cache; struct btrfs_full_stripe_locks_tree *locks_root; struct full_stripe_lock *fstripe_lock; u64 fstripe_start; @@ -598,8 +597,8 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx( sbio->index = i; sbio->sctx = sctx; sbio->page_count = 0; - btrfs_init_work(&sbio->work, btrfs_scrub_helper, - scrub_bio_end_io_worker, NULL, NULL); + btrfs_init_work(&sbio->work, scrub_bio_end_io_worker, NULL, + NULL); if (i != SCRUB_BIOS_PER_SCTX - 1) sctx->bios[i]->next_free = i + 1; @@ -1720,8 +1719,7 @@ static void scrub_wr_bio_end_io(struct bio *bio) sbio->status = bio->bi_status; sbio->bio = bio; - btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper, - scrub_wr_bio_end_io_worker, NULL, NULL); + btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL); btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work); } @@ -2149,14 +2147,13 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) scrub_write_block_to_dev_replace(sblock); } - scrub_block_put(sblock); - if (sctx->is_dev_replace && sctx->flush_all_writes) { mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); mutex_unlock(&sctx->wr_lock); } + scrub_block_put(sblock); scrub_pending_bio_dec(sctx); } @@ -2204,8 +2201,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) raid56_add_scrub_pages(rbio, spage->page, spage->logical); } - btrfs_init_work(&sblock->work, btrfs_scrub_helper, - scrub_missing_raid56_worker, NULL, NULL); + btrfs_init_work(&sblock->work, scrub_missing_raid56_worker, NULL, NULL); scrub_block_get(sblock); scrub_pending_bio_inc(sctx); raid56_submit_missing_rbio(rbio); @@ -2743,8 +2739,8 @@ static void scrub_parity_bio_endio(struct bio *bio) bio_put(bio); - btrfs_init_work(&sparity->work, btrfs_scrubparity_helper, - scrub_parity_bio_endio_worker, NULL, NULL); + btrfs_init_work(&sparity->work, scrub_parity_bio_endio_worker, NULL, + NULL); btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work); } @@ -3420,7 +3416,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, u64 chunk_offset, u64 length, u64 dev_offset, - struct btrfs_block_group_cache *cache) + struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = sctx->fs_info; struct extent_map_tree *map_tree = &fs_info->mapping_tree; @@ -3484,7 +3480,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, struct extent_buffer *l; struct btrfs_key key; struct btrfs_key found_key; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; path = btrfs_alloc_path(); @@ -3563,46 +3559,26 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * -> btrfs_scrub_pause() */ scrub_pause_on(fs_info); - ret = btrfs_inc_block_group_ro(cache); - if (!ret && sctx->is_dev_replace) { - /* - * If we are doing a device replace wait for any tasks - * that started delalloc right before we set the block - * group to RO mode, as they might have just allocated - * an extent from it or decided they could do a nocow - * write. And if any such tasks did that, wait for their - * ordered extents to complete and then commit the - * current transaction, so that we can later see the new - * extent items in the extent tree - the ordered extents - * create delayed data references (for cow writes) when - * they complete, which will be run and insert the - * corresponding extent items into the extent tree when - * we commit the transaction they used when running - * inode.c:btrfs_finish_ordered_io(). We later use - * the commit root of the extent tree to find extents - * to copy from the srcdev into the tgtdev, and we don't - * want to miss any new extents. - */ - btrfs_wait_block_group_reservations(cache); - btrfs_wait_nocow_writers(cache); - ret = btrfs_wait_ordered_roots(fs_info, U64_MAX, - cache->key.objectid, - cache->key.offset); - if (ret > 0) { - struct btrfs_trans_handle *trans; - - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - ret = PTR_ERR(trans); - else - ret = btrfs_commit_transaction(trans); - if (ret) { - scrub_pause_off(fs_info); - btrfs_put_block_group(cache); - break; - } - } - } + + /* + * Don't do chunk preallocation for scrub. + * + * This is especially important for SYSTEM bgs, or we can hit + * -EFBIG from btrfs_finish_chunk_alloc() like: + * 1. The only SYSTEM bg is marked RO. + * Since SYSTEM bg is small, that's pretty common. + * 2. New SYSTEM bg will be allocated + * Due to regular version will allocate new chunk. + * 3. New SYSTEM bg is empty and will get cleaned up + * Before cleanup really happens, it's marked RO again. + * 4. Empty SYSTEM bg get scrubbed + * We go back to 2. + * + * This can easily boost the amount of SYSTEM chunks if cleaner + * thread can't be triggered fast enough, and use up all space + * of btrfs_super_block::sys_chunk_array + */ + ret = btrfs_inc_block_group_ro(cache, false); scrub_pause_off(fs_info); if (ret == 0) { @@ -3623,7 +3599,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, break; } - down_write(&fs_info->dev_replace.rwsem); + down_write(&dev_replace->rwsem); dev_replace->cursor_right = found_key.offset + length; dev_replace->cursor_left = found_key.offset; dev_replace->item_needs_writeback = 1; @@ -3664,10 +3640,10 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, scrub_pause_off(fs_info); - down_write(&fs_info->dev_replace.rwsem); + down_write(&dev_replace->rwsem); dev_replace->cursor_left = dev_replace->cursor_right; dev_replace->item_needs_writeback = 1; - up_write(&fs_info->dev_replace.rwsem); + up_write(&dev_replace->rwsem); if (ro_set) btrfs_dec_block_group_ro(cache); @@ -3681,7 +3657,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, */ spin_lock(&cache->lock); if (!cache->removed && !cache->ro && cache->reserved == 0 && - btrfs_block_group_used(&cache->item) == 0) { + cache->used == 0) { spin_unlock(&cache->lock); btrfs_mark_bg_unused(cache); } else { diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 123ac54af071..ae2db5eb1549 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -25,6 +25,14 @@ #include "compression.h" /* + * Maximum number of references an extent can have in order for us to attempt to + * issue clone operations instead of write operations. This currently exists to + * avoid hitting limitations of the backreference walking code (taking a lot of + * time and using too much memory for extents with large number of references). + */ +#define SEND_MAX_EXTENT_REFS 64 + +/* * A fs_path is a helper to dynamically build path names with unknown size. * It reallocates the internal buffer on demand. * It allows fast adding of path elements on the right side (normal path) and @@ -1248,12 +1256,20 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_) */ if (found->root == bctx->sctx->send_root) { /* - * TODO for the moment we don't accept clones from the inode - * that is currently send. We may change this when - * BTRFS_IOC_CLONE_RANGE supports cloning from and to the same - * file. + * If the source inode was not yet processed we can't issue a + * clone operation, as the source extent does not exist yet at + * the destination of the stream. */ - if (ino >= bctx->cur_objectid) + if (ino > bctx->cur_objectid) + return 0; + /* + * We clone from the inode currently being sent as long as the + * source extent is already processed, otherwise we could try + * to clone from an extent that does not exist yet at the + * destination of the stream. + */ + if (ino == bctx->cur_objectid && + offset >= bctx->sctx->cur_inode_next_write_offset) return 0; } @@ -1302,6 +1318,7 @@ static int find_extent_clone(struct send_ctx *sctx, struct clone_root *cur_clone_root; struct btrfs_key found_key; struct btrfs_path *tmp_path; + struct btrfs_extent_item *ei; int compressed; u32 i; @@ -1349,7 +1366,6 @@ static int find_extent_clone(struct send_ctx *sctx, ret = extent_from_logical(fs_info, disk_byte, tmp_path, &found_key, &flags); up_read(&fs_info->commit_root_sem); - btrfs_release_path(tmp_path); if (ret < 0) goto out; @@ -1358,6 +1374,21 @@ static int find_extent_clone(struct send_ctx *sctx, goto out; } + ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0], + struct btrfs_extent_item); + /* + * Backreference walking (iterate_extent_inodes() below) is currently + * too expensive when an extent has a large number of references, both + * in time spent and used memory. So for now just fallback to write + * operations instead of clone operations when an extent has more than + * a certain amount of references. + */ + if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) { + ret = -ENOENT; + goto out; + } + btrfs_release_path(tmp_path); + /* * Setup the clone roots. */ @@ -4779,7 +4810,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(fs_info->sb, &key, root, NULL); + inode = btrfs_iget(fs_info->sb, &key, root); if (IS_ERR(inode)) return PTR_ERR(inode); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 98dc092a905e..f09aa6ee9113 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -10,7 +10,7 @@ #include "transaction.h" #include "block-group.h" -u64 btrfs_space_info_used(struct btrfs_space_info *s_info, +u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, bool may_use_included) { ASSERT(s_info); @@ -58,7 +58,6 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) spin_lock_init(&space_info->lock); space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; space_info->force_alloc = CHUNK_ALLOC_NO_FORCE; - init_waitqueue_head(&space_info->wait); INIT_LIST_HEAD(&space_info->ro_bgs); INIT_LIST_HEAD(&space_info->tickets); INIT_LIST_HEAD(&space_info->priority_tickets); @@ -285,7 +284,7 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info, struct btrfs_space_info *info, u64 bytes, int dump_block_groups) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; int index = 0; spin_lock(&info->lock); @@ -301,8 +300,7 @@ again: spin_lock(&cache->lock); btrfs_info(fs_info, "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s", - cache->key.objectid, cache->key.offset, - btrfs_block_group_used(&cache->item), cache->pinned, + cache->start, cache->length, cache->used, cache->pinned, cache->reserved, cache->ro ? "[readonly]" : ""); btrfs_dump_free_space(cache, bytes); spin_unlock(&cache->lock); @@ -893,6 +891,15 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, while (ticket->bytes > 0 && ticket->error == 0) { ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE); if (ret) { + /* + * Delete us from the list. After we unlock the space + * info, we don't want the async reclaim job to reserve + * space for this ticket. If that would happen, then the + * ticket's task would not known that space was reserved + * despite getting an error, resulting in a space leak + * (bytes_may_use counter of our space_info). + */ + list_del_init(&ticket->list); ticket->error = -EINTR; break; } @@ -945,12 +952,24 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, spin_lock(&space_info->lock); ret = ticket->error; if (ticket->bytes || ticket->error) { + /* + * Need to delete here for priority tickets. For regular tickets + * 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); if (!ret) ret = -ENOSPC; } spin_unlock(&space_info->lock); ASSERT(list_empty(&ticket->list)); + /* + * Check that we can't have an error set if the reservation succeeded, + * as that would confuse tasks and lead them to error out without + * releasing reserved space (if an error happens the expectation is that + * space wasn't reserved at all). + */ + ASSERT(!(ticket->bytes == 0 && ticket->error)); return ret; } diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 8867e84aa33d..1a349e3f9cc1 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -63,7 +63,6 @@ struct btrfs_space_info { struct rw_semaphore groups_sem; /* for block groups in our same type */ struct list_head block_groups[BTRFS_NR_RAID_TYPES]; - wait_queue_head_t wait; struct kobject kobj; struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES]; @@ -116,7 +115,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, struct btrfs_space_info **space_info); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); -u64 btrfs_space_info_used(struct btrfs_space_info *s_info, +u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, bool may_use_included); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); void btrfs_dump_space_info(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 1b151af25772..a98c3c71fc54 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -66,7 +66,7 @@ static struct file_system_type btrfs_root_fs_type; static int btrfs_remount(struct super_block *sb, int *flags, char *data); -const char *btrfs_decode_error(int errno) +const char * __attribute_const__ btrfs_decode_error(int errno) { char *errstr = "unknown"; @@ -187,7 +187,7 @@ static struct ratelimit_state printk_limits[] = { RATELIMIT_STATE_INIT(printk_limits[7], DEFAULT_RATELIMIT_INTERVAL, 100), }; -void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) +void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) { char lvl[PRINTK_MAX_SINGLE_HEADER_LEN + 1] = "\0"; struct va_format vaf; @@ -1219,7 +1219,7 @@ static int btrfs_fill_super(struct super_block *sb, key.objectid = BTRFS_FIRST_FREE_OBJECTID; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL); + inode = btrfs_iget(sb, &key, fs_info->fs_root); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto fail_close; @@ -1669,7 +1669,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, btrfs_workqueue_set_max(fs_info->workers, new_pool_size); btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); - btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size); @@ -1936,6 +1935,10 @@ static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, num_stripes = nr_devices; else if (type & BTRFS_BLOCK_GROUP_RAID1) num_stripes = 2; + else if (type & BTRFS_BLOCK_GROUP_RAID1C3) + num_stripes = 3; + else if (type & BTRFS_BLOCK_GROUP_RAID1C4) + num_stripes = 4; else if (type & BTRFS_BLOCK_GROUP_RAID10) num_stripes = 4; @@ -2022,7 +2025,6 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); struct btrfs_super_block *disk_super = fs_info->super_copy; - struct list_head *head = &fs_info->space_info; struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; @@ -2036,7 +2038,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) int mixed = 0; rcu_read_lock(); - list_for_each_entry_rcu(found, head, list) { + list_for_each_entry_rcu(found, &fs_info->space_info, list) { if (found->flags & BTRFS_BLOCK_GROUP_DATA) { int i; @@ -2360,10 +2362,14 @@ static int __init init_btrfs_fs(void) if (err) goto free_cachep; - err = extent_map_init(); + err = extent_state_cache_init(); if (err) goto free_extent_io; + err = extent_map_init(); + if (err) + goto free_extent_state_cache; + err = ordered_data_init(); if (err) goto free_extent_map; @@ -2422,6 +2428,8 @@ free_ordered_data: ordered_data_exit(); free_extent_map: extent_map_exit(); +free_extent_state_cache: + extent_state_cache_exit(); free_extent_io: extent_io_exit(); free_cachep: @@ -2442,6 +2450,7 @@ static void __exit exit_btrfs_fs(void) btrfs_prelim_ref_exit(); ordered_data_exit(); extent_map_exit(); + extent_state_cache_exit(); extent_io_exit(); btrfs_interface_exit(); btrfs_end_io_wq_exit(); @@ -2456,3 +2465,6 @@ module_exit(exit_btrfs_fs) MODULE_LICENSE("GPL"); MODULE_SOFTDEP("pre: crc32c"); +MODULE_SOFTDEP("pre: xxhash64"); +MODULE_SOFTDEP("pre: sha256"); +MODULE_SOFTDEP("pre: blake2b-256"); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index f6d3c80f2e28..5ebbe8a5ee76 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -9,6 +9,7 @@ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/bug.h> +#include <crypto/hash.h> #include "ctree.h" #include "disk-io.h" @@ -258,6 +259,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA); BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES); BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID); BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE); +BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34); static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(mixed_backref), @@ -272,6 +274,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(no_holes), BTRFS_FEAT_ATTR_PTR(metadata_uuid), BTRFS_FEAT_ATTR_PTR(free_space_tree), + BTRFS_FEAT_ATTR_PTR(raid1c34), NULL }; @@ -295,8 +298,30 @@ static ssize_t rmdir_subvol_show(struct kobject *kobj, } BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show); +static ssize_t supported_checksums_show(struct kobject *kobj, + struct kobj_attribute *a, char *buf) +{ + ssize_t ret = 0; + int i; + + for (i = 0; i < btrfs_get_num_csums(); i++) { + /* + * This "trick" only works as long as 'enum btrfs_csum_type' has + * no holes in it + */ + ret += snprintf(buf + ret, PAGE_SIZE - ret, "%s%s", + (i == 0 ? "" : " "), btrfs_super_csum_name(i)); + + } + + ret += snprintf(buf + ret, PAGE_SIZE - ret, "\n"); + return ret; +} +BTRFS_ATTR(static_feature, supported_checksums, supported_checksums_show); + static struct attribute *btrfs_supported_static_feature_attrs[] = { BTRFS_ATTR_PTR(static_feature, rmdir_subvol), + BTRFS_ATTR_PTR(static_feature, supported_checksums), NULL }; @@ -372,16 +397,16 @@ static ssize_t raid_bytes_show(struct kobject *kobj, { struct btrfs_space_info *sinfo = to_space_info(kobj->parent); - struct btrfs_block_group_cache *block_group; + struct btrfs_block_group *block_group; int index = btrfs_bg_flags_to_raid_index(to_raid_kobj(kobj)->flags); u64 val = 0; down_read(&sinfo->groups_sem); list_for_each_entry(block_group, &sinfo->block_groups[index], list) { if (&attr->attr == BTRFS_ATTR_PTR(raid, total_bytes)) - val += block_group->key.offset; + val += block_group->length; else - val += btrfs_block_group_used(&block_group->item); + val += block_group->used; } up_read(&sinfo->groups_sem); return snprintf(buf, PAGE_SIZE, "%llu\n", val); @@ -604,6 +629,19 @@ static ssize_t btrfs_metadata_uuid_show(struct kobject *kobj, BTRFS_ATTR(, metadata_uuid, btrfs_metadata_uuid_show); +static ssize_t btrfs_checksum_show(struct kobject *kobj, + struct kobj_attribute *a, char *buf) +{ + struct btrfs_fs_info *fs_info = to_fs_info(kobj); + u16 csum_type = btrfs_super_csum_type(fs_info->super_copy); + + return snprintf(buf, PAGE_SIZE, "%s (%s)\n", + btrfs_super_csum_name(csum_type), + crypto_shash_driver_name(fs_info->csum_shash)); +} + +BTRFS_ATTR(, checksum, btrfs_checksum_show); + static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, label), BTRFS_ATTR_PTR(, nodesize), @@ -611,6 +649,7 @@ static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, clone_alignment), BTRFS_ATTR_PTR(, quota_override), BTRFS_ATTR_PTR(, metadata_uuid), + BTRFS_ATTR_PTR(, checksum), NULL, }; @@ -822,7 +861,7 @@ static void init_feature_attrs(void) * Create a sysfs entry for a given block group type at path * /sys/fs/btrfs/UUID/allocation/data/TYPE */ -void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache) +void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_space_info *space_info = cache->space_info; diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 610e9c36a94c..e10c3adfc30f 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -32,7 +32,7 @@ int __init btrfs_init_sysfs(void); void __cold btrfs_exit_sysfs(void); int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info); void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info); -void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache); +void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache); int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info); void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info); diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 99fe9bf3fdac..a7aca4141788 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -202,11 +202,11 @@ void btrfs_free_dummy_root(struct btrfs_root *root) kfree(root); } -struct btrfs_block_group_cache * +struct btrfs_block_group * btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long length) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; cache = kzalloc(sizeof(*cache), GFP_KERNEL); if (!cache) @@ -218,9 +218,8 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, return NULL; } - cache->key.objectid = 0; - cache->key.offset = length; - cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; + cache->start = 0; + cache->length = length; cache->full_stripe_len = fs_info->sectorsize; cache->fs_info = fs_info; @@ -233,7 +232,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, return cache; } -void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache) +void btrfs_free_dummy_block_group(struct btrfs_block_group *cache) { if (!cache) return; diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h index ee277bbd939b..9e52527357d8 100644 --- a/fs/btrfs/tests/btrfs-tests.h +++ b/fs/btrfs/tests/btrfs-tests.h @@ -41,9 +41,9 @@ struct inode *btrfs_new_test_inode(void); struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize); void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info); void btrfs_free_dummy_root(struct btrfs_root *root); -struct btrfs_block_group_cache * +struct btrfs_block_group * btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long length); -void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache); +void btrfs_free_dummy_block_group(struct btrfs_block_group *cache); void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); #else diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index 43ec7060fcd2..aebdf23f0cdd 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -17,7 +17,7 @@ * entry and remove space from either end and the middle, and make sure we can * remove space that covers adjacent extent entries. */ -static int test_extents(struct btrfs_block_group_cache *cache) +static int test_extents(struct btrfs_block_group *cache) { int ret = 0; @@ -87,8 +87,7 @@ static int test_extents(struct btrfs_block_group_cache *cache) return 0; } -static int test_bitmaps(struct btrfs_block_group_cache *cache, - u32 sectorsize) +static int test_bitmaps(struct btrfs_block_group *cache, u32 sectorsize) { u64 next_bitmap_offset; int ret; @@ -156,7 +155,7 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache, } /* This is the high grade jackassery */ -static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache, +static int test_bitmaps_and_extents(struct btrfs_block_group *cache, u32 sectorsize) { u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize); @@ -331,7 +330,7 @@ static bool test_use_bitmap(struct btrfs_free_space_ctl *ctl, /* Used by test_steal_space_from_bitmap_to_extent(). */ static int -check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache, +check_num_extents_and_bitmaps(const struct btrfs_block_group *cache, const int num_extents, const int num_bitmaps) { @@ -351,7 +350,7 @@ check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache, } /* Used by test_steal_space_from_bitmap_to_extent(). */ -static int check_cache_empty(struct btrfs_block_group_cache *cache) +static int check_cache_empty(struct btrfs_block_group *cache) { u64 offset; u64 max_extent_size; @@ -393,7 +392,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache) * requests. */ static int -test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache, +test_steal_space_from_bitmap_to_extent(struct btrfs_block_group *cache, u32 sectorsize) { int ret; @@ -829,7 +828,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache, int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize) { struct btrfs_fs_info *fs_info; - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; struct btrfs_root *root = NULL; int ret = -ENOMEM; diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index bc92df977630..1a846bf6e197 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -18,7 +18,7 @@ struct free_space_extent { static int __check_free_space_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, const struct free_space_extent * const extents, unsigned int num_extents) @@ -48,7 +48,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans, if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) { if (path->slots[0] != 0) goto invalid; - end = cache->key.objectid + cache->key.offset; + end = cache->start + cache->length; i = 0; while (++path->slots[0] < btrfs_header_nritems(path->nodes[0])) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); @@ -107,7 +107,7 @@ invalid: static int check_free_space_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, const struct free_space_extent * const extents, unsigned int num_extents) @@ -150,12 +150,12 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans, static int test_empty_block_group(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid, cache->key.offset}, + {cache->start, cache->length}, }; return check_free_space_extents(trans, fs_info, cache, path, @@ -164,7 +164,7 @@ static int test_empty_block_group(struct btrfs_trans_handle *trans, static int test_remove_all(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { @@ -172,8 +172,8 @@ static int test_remove_all(struct btrfs_trans_handle *trans, int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid, - cache->key.offset); + cache->start, + cache->length); if (ret) { test_err("could not remove free space"); return ret; @@ -185,18 +185,17 @@ static int test_remove_all(struct btrfs_trans_handle *trans, static int test_remove_beginning(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid + alignment, - cache->key.offset - alignment}, + {cache->start + alignment, cache->length - alignment}, }; int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid, alignment); + cache->start, alignment); if (ret) { test_err("could not remove free space"); return ret; @@ -209,19 +208,18 @@ static int test_remove_beginning(struct btrfs_trans_handle *trans, static int test_remove_end(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid, cache->key.offset - alignment}, + {cache->start, cache->length - alignment}, }; int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid + - cache->key.offset - alignment, - alignment); + cache->start + cache->length - alignment, + alignment); if (ret) { test_err("could not remove free space"); return ret; @@ -233,19 +231,18 @@ static int test_remove_end(struct btrfs_trans_handle *trans, static int test_remove_middle(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid, alignment}, - {cache->key.objectid + 2 * alignment, - cache->key.offset - 2 * alignment}, + {cache->start, alignment}, + {cache->start + 2 * alignment, cache->length - 2 * alignment}, }; int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid + alignment, + cache->start + alignment, alignment); if (ret) { test_err("could not remove free space"); @@ -258,24 +255,23 @@ static int test_remove_middle(struct btrfs_trans_handle *trans, static int test_merge_left(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid, 2 * alignment}, + {cache->start, 2 * alignment}, }; int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid, - cache->key.offset); + cache->start, cache->length); if (ret) { test_err("could not remove free space"); return ret; } - ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid, + ret = __add_to_free_space_tree(trans, cache, path, cache->start, alignment); if (ret) { test_err("could not add free space"); @@ -283,7 +279,7 @@ static int test_merge_left(struct btrfs_trans_handle *trans, } ret = __add_to_free_space_tree(trans, cache, path, - cache->key.objectid + alignment, + cache->start + alignment, alignment); if (ret) { test_err("could not add free space"); @@ -296,25 +292,24 @@ static int test_merge_left(struct btrfs_trans_handle *trans, static int test_merge_right(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid + alignment, 2 * alignment}, + {cache->start + alignment, 2 * alignment}, }; int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid, - cache->key.offset); + cache->start, cache->length); if (ret) { test_err("could not remove free space"); return ret; } ret = __add_to_free_space_tree(trans, cache, path, - cache->key.objectid + 2 * alignment, + cache->start + 2 * alignment, alignment); if (ret) { test_err("could not add free space"); @@ -322,7 +317,7 @@ static int test_merge_right(struct btrfs_trans_handle *trans, } ret = __add_to_free_space_tree(trans, cache, path, - cache->key.objectid + alignment, + cache->start + alignment, alignment); if (ret) { test_err("could not add free space"); @@ -335,24 +330,23 @@ static int test_merge_right(struct btrfs_trans_handle *trans, static int test_merge_both(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid, 3 * alignment}, + {cache->start, 3 * alignment}, }; int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid, - cache->key.offset); + cache->start, cache->length); if (ret) { test_err("could not remove free space"); return ret; } - ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid, + ret = __add_to_free_space_tree(trans, cache, path, cache->start, alignment); if (ret) { test_err("could not add free space"); @@ -360,16 +354,14 @@ static int test_merge_both(struct btrfs_trans_handle *trans, } ret = __add_to_free_space_tree(trans, cache, path, - cache->key.objectid + 2 * alignment, - alignment); + cache->start + 2 * alignment, alignment); if (ret) { test_err("could not add free space"); return ret; } ret = __add_to_free_space_tree(trans, cache, path, - cache->key.objectid + alignment, - alignment); + cache->start + alignment, alignment); if (ret) { test_err("could not add free space"); return ret; @@ -381,26 +373,25 @@ static int test_merge_both(struct btrfs_trans_handle *trans, static int test_merge_none(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct btrfs_block_group_cache *cache, + struct btrfs_block_group *cache, struct btrfs_path *path, u32 alignment) { const struct free_space_extent extents[] = { - {cache->key.objectid, alignment}, - {cache->key.objectid + 2 * alignment, alignment}, - {cache->key.objectid + 4 * alignment, alignment}, + {cache->start, alignment}, + {cache->start + 2 * alignment, alignment}, + {cache->start + 4 * alignment, alignment}, }; int ret; ret = __remove_from_free_space_tree(trans, cache, path, - cache->key.objectid, - cache->key.offset); + cache->start, cache->length); if (ret) { test_err("could not remove free space"); return ret; } - ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid, + ret = __add_to_free_space_tree(trans, cache, path, cache->start, alignment); if (ret) { test_err("could not add free space"); @@ -408,16 +399,14 @@ static int test_merge_none(struct btrfs_trans_handle *trans, } ret = __add_to_free_space_tree(trans, cache, path, - cache->key.objectid + 4 * alignment, - alignment); + cache->start + 4 * alignment, alignment); if (ret) { test_err("could not add free space"); return ret; } ret = __add_to_free_space_tree(trans, cache, path, - cache->key.objectid + 2 * alignment, - alignment); + cache->start + 2 * alignment, alignment); if (ret) { test_err("could not add free space"); return ret; @@ -429,7 +418,7 @@ static int test_merge_none(struct btrfs_trans_handle *trans, typedef int (*test_func_t)(struct btrfs_trans_handle *, struct btrfs_fs_info *, - struct btrfs_block_group_cache *, + struct btrfs_block_group *, struct btrfs_path *, u32 alignment); @@ -438,7 +427,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, { struct btrfs_fs_info *fs_info; struct btrfs_root *root = NULL; - struct btrfs_block_group_cache *cache = NULL; + struct btrfs_block_group *cache = NULL; struct btrfs_trans_handle trans; struct btrfs_path *path = NULL; int ret; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8624bdee8c5b..cfc08ef9b876 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -24,9 +24,79 @@ #define BTRFS_ROOT_TRANS_TAG 0 +/* + * Transaction states and transitions + * + * No running transaction (fs tree blocks are not modified) + * | + * | To next stage: + * | Call start_transaction() variants. Except btrfs_join_transaction_nostart(). + * V + * Transaction N [[TRANS_STATE_RUNNING]] + * | + * | New trans handles can be attached to transaction N by calling all + * | start_transaction() variants. + * | + * | To next stage: + * | Call btrfs_commit_transaction() on any trans handle attached to + * | transaction N + * V + * Transaction N [[TRANS_STATE_COMMIT_START]] + * | + * | Will wait for previous running transaction to completely finish if there + * | is one + * | + * | Then one of the following happes: + * | - Wait for all other trans handle holders to release. + * | The btrfs_commit_transaction() caller will do the commit work. + * | - Wait for current transaction to be committed by others. + * | Other btrfs_commit_transaction() caller will do the commit work. + * | + * | At this stage, only btrfs_join_transaction*() variants can attach + * | to this running transaction. + * | All other variants will wait for current one to finish and attach to + * | transaction N+1. + * | + * | To next stage: + * | Caller is chosen to commit transaction N, and all other trans handle + * | haven been released. + * V + * Transaction N [[TRANS_STATE_COMMIT_DOING]] + * | + * | The heavy lifting transaction work is started. + * | From running delayed refs (modifying extent tree) to creating pending + * | snapshots, running qgroups. + * | In short, modify supporting trees to reflect modifications of subvolume + * | trees. + * | + * | At this stage, all start_transaction() calls will wait for this + * | transaction to finish and attach to transaction N+1. + * | + * | To next stage: + * | Until all supporting trees are updated. + * V + * Transaction N [[TRANS_STATE_UNBLOCKED]] + * | Transaction N+1 + * | All needed trees are modified, thus we only [[TRANS_STATE_RUNNING]] + * | need to write them back to disk and update | + * | super blocks. | + * | | + * | At this stage, new transaction is allowed to | + * | start. | + * | All new start_transaction() calls will be | + * | attached to transid N+1. | + * | | + * | To next stage: | + * | Until all tree blocks are super blocks are | + * | written to block devices | + * V | + * Transaction N [[TRANS_STATE_COMPLETED]] V + * All tree blocks and super blocks are written. Transaction N+1 + * This transaction is finished and all its [[TRANS_STATE_COMMIT_START]] + * data structures will be cleaned up. | Life goes on + */ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { [TRANS_STATE_RUNNING] = 0U, - [TRANS_STATE_BLOCKED] = __TRANS_START, [TRANS_STATE_COMMIT_START] = (__TRANS_START | __TRANS_ATTACH), [TRANS_STATE_COMMIT_DOING] = (__TRANS_START | __TRANS_ATTACH | @@ -63,10 +133,10 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) * discard the physical locations of the block groups. */ while (!list_empty(&transaction->deleted_bgs)) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; cache = list_first_entry(&transaction->deleted_bgs, - struct btrfs_block_group_cache, + struct btrfs_block_group, bg_list); list_del_init(&cache->bg_list); btrfs_put_block_group_trimming(cache); @@ -383,7 +453,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, static inline int is_transaction_blocked(struct btrfs_transaction *trans) { - return (trans->state >= TRANS_STATE_BLOCKED && + return (trans->state >= TRANS_STATE_COMMIT_START && trans->state < TRANS_STATE_UNBLOCKED && !trans->aborted); } @@ -570,7 +640,7 @@ again: INIT_LIST_HEAD(&h->new_bgs); smp_mb(); - if (cur_trans->state >= TRANS_STATE_BLOCKED && + if (cur_trans->state >= TRANS_STATE_COMMIT_START && may_wait_transaction(fs_info, type)) { current->journal_info = h; btrfs_commit_transaction(h); @@ -659,7 +729,7 @@ struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root) true); } -struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root) +struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root) { return start_transaction(root, 0, TRANS_JOIN_NOLOCK, BTRFS_RESERVE_NO_FLUSH, true); @@ -798,7 +868,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans) struct btrfs_transaction *cur_trans = trans->transaction; smp_mb(); - if (cur_trans->state >= TRANS_STATE_BLOCKED || + if (cur_trans->state >= TRANS_STATE_COMMIT_START || cur_trans->delayed_refs.flushing) return 1; @@ -831,7 +901,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_transaction *cur_trans = trans->transaction; - int lock = (trans->type != TRANS_JOIN_NOLOCK); int err = 0; if (refcount_read(&trans->use_count) > 1) { @@ -847,13 +916,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_chunk_metadata(trans); - if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { - if (throttle) - return btrfs_commit_transaction(trans); - else - wake_up_process(info->transaction_kthread); - } - if (trans->type & __TRANS_FREEZABLE) sb_end_intwrite(info->sb); @@ -990,7 +1052,7 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info, return werr; } -int btrfs_wait_extents(struct btrfs_fs_info *fs_info, +static int btrfs_wait_extents(struct btrfs_fs_info *fs_info, struct extent_io_tree *dirty_pages) { bool errors = false; @@ -1875,7 +1937,7 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_block_group_cache *block_group, *tmp; + struct btrfs_block_group *block_group, *tmp; list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { btrfs_delayed_refs_rsv_release(fs_info, 1); @@ -1949,6 +2011,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) struct btrfs_transaction *prev_trans = NULL; int ret; + ASSERT(refcount_read(&trans->use_count) == 1); + /* Stop the commit early if ->aborted is set */ if (unlikely(READ_ONCE(cur_trans->aborted))) { ret = cur_trans->aborted; diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 2c5a6f6e5bb0..49f7196368f5 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -13,7 +13,6 @@ enum btrfs_trans_state { TRANS_STATE_RUNNING, - TRANS_STATE_BLOCKED, TRANS_STATE_COMMIT_START, TRANS_STATE_COMMIT_DOING, TRANS_STATE_UNBLOCKED, @@ -184,7 +183,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( unsigned int num_items, int min_factor); struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root); -struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root); +struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction_barrier( @@ -218,8 +217,6 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info, struct extent_io_tree *dirty_pages, int mark); -int btrfs_wait_extents(struct btrfs_fs_info *fs_info, - struct extent_io_tree *dirty_pages); int btrfs_wait_tree_log_extents(struct btrfs_root *root, int mark); int btrfs_transaction_blocked(struct btrfs_fs_info *info); int btrfs_transaction_in_commit(struct btrfs_fs_info *info); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 43e488f5d063..493d4d9e0f79 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -23,6 +23,7 @@ #include "disk-io.h" #include "compression.h" #include "volumes.h" +#include "misc.h" /* * Error message should follow the following format: @@ -124,6 +125,74 @@ static u64 file_extent_end(struct extent_buffer *leaf, return end; } +/* + * Customized report for dir_item, the only new important information is + * key->objectid, which represents inode number + */ +__printf(3, 4) +__cold +static void dir_item_err(const struct extent_buffer *eb, int slot, + const char *fmt, ...) +{ + const struct btrfs_fs_info *fs_info = eb->fs_info; + struct btrfs_key key; + struct va_format vaf; + va_list args; + + btrfs_item_key_to_cpu(eb, &key, slot); + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + btrfs_crit(fs_info, + "corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV", + btrfs_header_level(eb) == 0 ? "leaf" : "node", + btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot, + key.objectid, &vaf); + va_end(args); +} + +/* + * This functions checks prev_key->objectid, to ensure current key and prev_key + * share the same objectid as inode number. + * + * This is to detect missing INODE_ITEM in subvolume trees. + * + * Return true if everything is OK or we don't need to check. + * Return false if anything is wrong. + */ +static bool check_prev_ino(struct extent_buffer *leaf, + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) +{ + /* No prev key, skip check */ + if (slot == 0) + return true; + + /* Only these key->types needs to be checked */ + ASSERT(key->type == BTRFS_XATTR_ITEM_KEY || + key->type == BTRFS_INODE_REF_KEY || + key->type == BTRFS_DIR_INDEX_KEY || + key->type == BTRFS_DIR_ITEM_KEY || + key->type == BTRFS_EXTENT_DATA_KEY); + + /* + * Only subvolume trees along with their reloc trees need this check. + * Things like log tree doesn't follow this ino requirement. + */ + if (!is_fstree(btrfs_header_owner(leaf))) + return true; + + if (key->objectid == prev_key->objectid) + return true; + + /* Error found */ + dir_item_err(leaf, slot, + "invalid previous key objectid, have %llu expect %llu", + prev_key->objectid, key->objectid); + return false; +} static int check_extent_data_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot, struct btrfs_key *prev_key) @@ -141,13 +210,33 @@ static int check_extent_data_item(struct extent_buffer *leaf, return -EUCLEAN; } + /* + * Previous key must have the same key->objectid (ino). + * It can be XATTR_ITEM, INODE_ITEM or just another EXTENT_DATA. + * But if objectids mismatch, it means we have a missing + * INODE_ITEM. + */ + if (!check_prev_ino(leaf, key, slot, prev_key)) + return -EUCLEAN; + fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); - if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) { + /* + * Make sure the item contains at least inline header, so the file + * extent type is not some garbage. + */ + if (item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START) { + file_extent_err(leaf, slot, + "invalid item size, have %u expect [%lu, %u)", + item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START, + SZ_4K); + return -EUCLEAN; + } + if (btrfs_file_extent_type(leaf, fi) >= BTRFS_NR_FILE_EXTENT_TYPES) { file_extent_err(leaf, slot, "invalid type for file extent, have %u expect range [0, %u]", btrfs_file_extent_type(leaf, fi), - BTRFS_FILE_EXTENT_TYPES); + BTRFS_NR_FILE_EXTENT_TYPES - 1); return -EUCLEAN; } @@ -155,11 +244,11 @@ static int check_extent_data_item(struct extent_buffer *leaf, * Support for new compression/encryption must introduce incompat flag, * and must be caught in open_ctree(). */ - if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) { + if (btrfs_file_extent_compression(leaf, fi) >= BTRFS_NR_COMPRESS_TYPES) { file_extent_err(leaf, slot, "invalid compression for file extent, have %u expect range [0, %u]", btrfs_file_extent_compression(leaf, fi), - BTRFS_COMPRESS_TYPES); + BTRFS_NR_COMPRESS_TYPES - 1); return -EUCLEAN; } if (btrfs_file_extent_encryption(leaf, fi)) { @@ -270,42 +359,17 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, return 0; } -/* - * Customized reported for dir_item, only important new info is key->objectid, - * which represents inode number - */ -__printf(3, 4) -__cold -static void dir_item_err(const struct extent_buffer *eb, int slot, - const char *fmt, ...) -{ - const struct btrfs_fs_info *fs_info = eb->fs_info; - struct btrfs_key key; - struct va_format vaf; - va_list args; - - btrfs_item_key_to_cpu(eb, &key, slot); - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - btrfs_crit(fs_info, - "corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV", - btrfs_header_level(eb) == 0 ? "leaf" : "node", - btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot, - key.objectid, &vaf); - va_end(args); -} - static int check_dir_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, struct btrfs_key *prev_key, + int slot) { struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_dir_item *di; u32 item_size = btrfs_item_size_nr(leaf, slot); u32 cur = 0; + if (!check_prev_ino(leaf, key, slot, prev_key)) + return -EUCLEAN; di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); while (cur < item_size) { u32 name_len; @@ -459,23 +523,23 @@ static int check_block_group_item(struct extent_buffer *leaf, read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), sizeof(bgi)); - if (btrfs_block_group_chunk_objectid(&bgi) != + if (btrfs_stack_block_group_chunk_objectid(&bgi) != BTRFS_FIRST_CHUNK_TREE_OBJECTID) { block_group_err(leaf, slot, "invalid block group chunk objectid, have %llu expect %llu", - btrfs_block_group_chunk_objectid(&bgi), + btrfs_stack_block_group_chunk_objectid(&bgi), BTRFS_FIRST_CHUNK_TREE_OBJECTID); return -EUCLEAN; } - if (btrfs_block_group_used(&bgi) > key->offset) { + if (btrfs_stack_block_group_used(&bgi) > key->offset) { block_group_err(leaf, slot, "invalid block group used, have %llu expect [0, %llu)", - btrfs_block_group_used(&bgi), key->offset); + btrfs_stack_block_group_used(&bgi), key->offset); return -EUCLEAN; } - flags = btrfs_block_group_flags(&bgi); + flags = btrfs_stack_block_group_flags(&bgi); if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) { block_group_err(leaf, slot, "invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set", @@ -609,7 +673,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, return -EUCLEAN; } - if (!is_power_of_2(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && + if (!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) { chunk_err(leaf, chunk, logical, "invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set", @@ -686,9 +750,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot, static int check_dev_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { - struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_dev_item *ditem; - u64 max_devid = max(BTRFS_MAX_DEVS(fs_info), BTRFS_MAX_DEVS_SYS_CHUNK); if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) { dev_item_err(leaf, slot, @@ -696,12 +758,6 @@ static int check_dev_item(struct extent_buffer *leaf, key->objectid, BTRFS_DEV_ITEMS_OBJECTID); return -EUCLEAN; } - if (key->offset > max_devid) { - dev_item_err(leaf, slot, - "invalid devid: has=%llu expect=[0, %llu]", - key->offset, max_devid); - return -EUCLEAN; - } ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); if (btrfs_device_id(leaf, ditem) != key->offset) { dev_item_err(leaf, slot, @@ -793,11 +849,11 @@ static int check_inode_item(struct extent_buffer *leaf, } /* - * S_IFMT is not bit mapped so we can't completely rely on is_power_of_2, - * but is_power_of_2() can save us from checking FIFO/CHR/DIR/REG. - * Only needs to check BLK, LNK and SOCKS + * S_IFMT is not bit mapped so we can't completely rely on + * is_power_of_2/has_single_bit_set, but it can save us from checking + * FIFO/CHR/DIR/REG. Only needs to check BLK, LNK and SOCKS */ - if (!is_power_of_2(mode & S_IFMT)) { + if (!has_single_bit_set(mode & S_IFMT)) { if (!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode)) { inode_item_err(fs_info, leaf, slot, "invalid mode: has 0%o expect valid S_IF* bit(s)", @@ -1018,8 +1074,8 @@ static int check_extent_item(struct extent_buffer *leaf, btrfs_super_generation(fs_info->super_copy) + 1); return -EUCLEAN; } - if (!is_power_of_2(flags & (BTRFS_EXTENT_FLAG_DATA | - BTRFS_EXTENT_FLAG_TREE_BLOCK))) { + if (!has_single_bit_set(flags & (BTRFS_EXTENT_FLAG_DATA | + BTRFS_EXTENT_FLAG_TREE_BLOCK))) { extent_err(leaf, slot, "invalid extent flag, have 0x%llx expect 1 bit set in 0x%llx", flags, BTRFS_EXTENT_FLAG_DATA | @@ -1232,6 +1288,58 @@ static int check_extent_data_ref(struct extent_buffer *leaf, return 0; } +#define inode_ref_err(fs_info, eb, slot, fmt, args...) \ + inode_item_err(fs_info, eb, slot, fmt, ##args) +static int check_inode_ref(struct extent_buffer *leaf, + struct btrfs_key *key, struct btrfs_key *prev_key, + int slot) +{ + struct btrfs_inode_ref *iref; + unsigned long ptr; + unsigned long end; + + if (!check_prev_ino(leaf, key, slot, prev_key)) + return -EUCLEAN; + /* namelen can't be 0, so item_size == sizeof() is also invalid */ + if (btrfs_item_size_nr(leaf, slot) <= sizeof(*iref)) { + inode_ref_err(fs_info, leaf, slot, + "invalid item size, have %u expect (%zu, %u)", + btrfs_item_size_nr(leaf, slot), + sizeof(*iref), BTRFS_LEAF_DATA_SIZE(leaf->fs_info)); + return -EUCLEAN; + } + + ptr = btrfs_item_ptr_offset(leaf, slot); + end = ptr + btrfs_item_size_nr(leaf, slot); + while (ptr < end) { + u16 namelen; + + if (ptr + sizeof(iref) > end) { + inode_ref_err(fs_info, leaf, slot, + "inode ref overflow, ptr %lu end %lu inode_ref_size %zu", + ptr, end, sizeof(iref)); + return -EUCLEAN; + } + + iref = (struct btrfs_inode_ref *)ptr; + namelen = btrfs_inode_ref_name_len(leaf, iref); + if (ptr + sizeof(*iref) + namelen > end) { + inode_ref_err(fs_info, leaf, slot, + "inode ref overflow, ptr %lu end %lu namelen %u", + ptr, end, namelen); + return -EUCLEAN; + } + + /* + * NOTE: In theory we should record all found index numbers + * to find any duplicated indexes, but that will be too time + * consuming for inodes with too many hard links. + */ + ptr += sizeof(*iref) + namelen; + } + return 0; +} + /* * Common point to switch the item-specific validation. */ @@ -1252,7 +1360,10 @@ static int check_leaf_item(struct extent_buffer *leaf, case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY: case BTRFS_XATTR_ITEM_KEY: - ret = check_dir_item(leaf, key, slot); + ret = check_dir_item(leaf, key, prev_key, slot); + break; + case BTRFS_INODE_REF_KEY: + ret = check_inode_ref(leaf, key, prev_key, slot); break; case BTRFS_BLOCK_GROUP_ITEM_KEY: ret = check_block_group_item(leaf, key, slot); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 8a6cc600bf18..6f757361db53 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -559,7 +559,7 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root, key.objectid = objectid; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(root->fs_info->sb, &key, root, NULL); + inode = btrfs_iget(root->fs_info->sb, &key, root); if (IS_ERR(inode)) inode = NULL; return inode; @@ -945,54 +945,32 @@ static noinline int backref_in_log(struct btrfs_root *log, const char *name, int namelen) { struct btrfs_path *path; - struct btrfs_inode_ref *ref; - unsigned long ptr; - unsigned long ptr_end; - unsigned long name_ptr; - int found_name_len; - int item_size; int ret; - int match = 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(NULL, log, key, path, 0, 0); - if (ret != 0) + if (ret < 0) { goto out; - - ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); - - if (key->type == BTRFS_INODE_EXTREF_KEY) { - if (btrfs_find_name_in_ext_backref(path->nodes[0], - path->slots[0], - ref_objectid, - name, namelen)) - match = 1; - + } else if (ret == 1) { + ret = 0; goto out; } - item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]); - ptr_end = ptr + item_size; - while (ptr < ptr_end) { - ref = (struct btrfs_inode_ref *)ptr; - found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref); - if (found_name_len == namelen) { - name_ptr = (unsigned long)(ref + 1); - ret = memcmp_extent_buffer(path->nodes[0], name, - name_ptr, namelen); - if (ret == 0) { - match = 1; - goto out; - } - } - ptr = (unsigned long)(ref + 1) + found_name_len; - } + if (key->type == BTRFS_INODE_EXTREF_KEY) + ret = !!btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], + ref_objectid, + name, namelen); + else + ret = !!btrfs_find_name_in_backref(path->nodes[0], + path->slots[0], + name, namelen); out: btrfs_free_path(path); - return match; + return ret; } static inline int __add_inode_ref(struct btrfs_trans_handle *trans, @@ -1050,10 +1028,13 @@ again: (unsigned long)(victim_ref + 1), victim_name_len); - if (!backref_in_log(log_root, &search_key, - parent_objectid, - victim_name, - victim_name_len)) { + ret = backref_in_log(log_root, &search_key, + parent_objectid, victim_name, + victim_name_len); + if (ret < 0) { + kfree(victim_name); + return ret; + } else if (!ret) { inc_nlink(&inode->vfs_inode); btrfs_release_path(path); @@ -1115,10 +1096,12 @@ again: search_key.offset = btrfs_extref_hash(parent_objectid, victim_name, victim_name_len); - ret = 0; - if (!backref_in_log(log_root, &search_key, - parent_objectid, victim_name, - victim_name_len)) { + ret = backref_in_log(log_root, &search_key, + parent_objectid, victim_name, + victim_name_len); + if (ret < 0) { + return ret; + } else if (!ret) { ret = -ENOENT; victim_parent = read_one_inode(root, parent_objectid); @@ -1885,30 +1868,6 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, } /* - * Return true if an inode reference exists in the log for the given name, - * inode and parent inode. - */ -static bool name_in_log_ref(struct btrfs_root *log_root, - const char *name, const int name_len, - const u64 dirid, const u64 ino) -{ - struct btrfs_key search_key; - - search_key.objectid = ino; - search_key.type = BTRFS_INODE_REF_KEY; - search_key.offset = dirid; - if (backref_in_log(log_root, &search_key, dirid, name, name_len)) - return true; - - search_key.type = BTRFS_INODE_EXTREF_KEY; - search_key.offset = btrfs_extref_hash(dirid, name, name_len); - if (backref_in_log(log_root, &search_key, dirid, name, name_len)) - return true; - - return false; -} - -/* * take a single entry in a log directory item and replay it into * the subvolume. * @@ -2024,8 +1983,31 @@ out: return ret; insert: - if (name_in_log_ref(root->log_root, name, name_len, - key->objectid, log_key.objectid)) { + /* + * Check if the inode reference exists in the log for the given name, + * inode and parent inode + */ + found_key.objectid = log_key.objectid; + found_key.type = BTRFS_INODE_REF_KEY; + found_key.offset = key->objectid; + ret = backref_in_log(root->log_root, &found_key, 0, name, name_len); + if (ret < 0) { + goto out; + } else if (ret) { + /* The dentry will be added later. */ + ret = 0; + update_size = false; + goto out; + } + + found_key.objectid = log_key.objectid; + found_key.type = BTRFS_INODE_EXTREF_KEY; + found_key.offset = key->objectid; + ret = backref_in_log(root->log_root, &found_key, key->objectid, name, + name_len); + if (ret < 0) { + goto out; + } else if (ret) { /* The dentry will be added later. */ ret = 0; update_size = false; @@ -2869,7 +2851,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, level = btrfs_header_level(log->node); orig_level = level; path->nodes[level] = log->node; - extent_buffer_get(log->node); + atomic_inc(&log->node->refs); path->slots[level] = 0; while (1) { @@ -4983,7 +4965,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans, key.objectid = ino; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(fs_info->sb, &key, root, NULL); + inode = btrfs_iget(fs_info->sb, &key, root); /* * If the other inode that had a conflicting dir entry was * deleted in the current transaction, we need to log its parent @@ -4993,8 +4975,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans, ret = PTR_ERR(inode); if (ret == -ENOENT) { key.objectid = parent; - inode = btrfs_iget(fs_info->sb, &key, root, - NULL); + inode = btrfs_iget(fs_info->sb, &key, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); } else { @@ -5699,7 +5680,7 @@ process_leaf: continue; btrfs_release_path(path); - di_inode = btrfs_iget(fs_info->sb, &di_key, root, NULL); + di_inode = btrfs_iget(fs_info->sb, &di_key, root); if (IS_ERR(di_inode)) { ret = PTR_ERR(di_inode); goto next_dir_inode; @@ -5825,8 +5806,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, cur_offset = item_size; } - dir_inode = btrfs_iget(fs_info->sb, &inode_key, - root, NULL); + dir_inode = btrfs_iget(fs_info->sb, &inode_key, root); /* * If the parent inode was deleted, return an error to * fallback to a transaction commit. This is to prevent @@ -5900,7 +5880,7 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans, search_key.objectid = found_key.offset; search_key.type = BTRFS_INODE_ITEM_KEY; search_key.offset = 0; - inode = btrfs_iget(fs_info->sb, &search_key, root, NULL); + inode = btrfs_iget(fs_info->sb, &search_key, root); if (IS_ERR(inode)) return PTR_ERR(inode); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bdfe4493e43a..d8e5560db285 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -58,6 +58,30 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .bg_flag = BTRFS_BLOCK_GROUP_RAID1, .mindev_error = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET, }, + [BTRFS_RAID_RAID1C3] = { + .sub_stripes = 1, + .dev_stripes = 1, + .devs_max = 0, + .devs_min = 3, + .tolerated_failures = 2, + .devs_increment = 3, + .ncopies = 3, + .raid_name = "raid1c3", + .bg_flag = BTRFS_BLOCK_GROUP_RAID1C3, + .mindev_error = BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET, + }, + [BTRFS_RAID_RAID1C4] = { + .sub_stripes = 1, + .dev_stripes = 1, + .devs_max = 0, + .devs_min = 4, + .tolerated_failures = 3, + .devs_increment = 4, + .ncopies = 4, + .raid_name = "raid1c4", + .bg_flag = BTRFS_BLOCK_GROUP_RAID1C4, + .mindev_error = BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET, + }, [BTRFS_RAID_DUP] = { .sub_stripes = 1, .dev_stripes = 2, @@ -297,7 +321,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, DEFINE_MUTEX(uuid_mutex); static LIST_HEAD(fs_uuids); -struct list_head *btrfs_get_fs_uuids(void) +struct list_head * __attribute_const__ btrfs_get_fs_uuids(void) { return &fs_uuids; } @@ -397,8 +421,6 @@ static struct btrfs_device *__alloc_device(void) INIT_LIST_HEAD(&dev->dev_alloc_list); INIT_LIST_HEAD(&dev->post_commit_list); - spin_lock_init(&dev->io_lock); - atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); btrfs_device_data_ordered_init(dev); @@ -501,212 +523,6 @@ error: return ret; } -static void requeue_list(struct btrfs_pending_bios *pending_bios, - struct bio *head, struct bio *tail) -{ - - struct bio *old_head; - - old_head = pending_bios->head; - pending_bios->head = head; - if (pending_bios->tail) - tail->bi_next = old_head; - else - pending_bios->tail = tail; -} - -/* - * we try to collect pending bios for a device so we don't get a large - * number of procs sending bios down to the same device. This greatly - * improves the schedulers ability to collect and merge the bios. - * - * But, it also turns into a long list of bios to process and that is sure - * to eventually make the worker thread block. The solution here is to - * make some progress and then put this work struct back at the end of - * the list if the block device is congested. This way, multiple devices - * can make progress from a single worker thread. - */ -static noinline void run_scheduled_bios(struct btrfs_device *device) -{ - struct btrfs_fs_info *fs_info = device->fs_info; - struct bio *pending; - struct backing_dev_info *bdi; - struct btrfs_pending_bios *pending_bios; - struct bio *tail; - struct bio *cur; - int again = 0; - unsigned long num_run; - unsigned long batch_run = 0; - unsigned long last_waited = 0; - int force_reg = 0; - int sync_pending = 0; - struct blk_plug plug; - - /* - * this function runs all the bios we've collected for - * a particular device. We don't want to wander off to - * another device without first sending all of these down. - * So, setup a plug here and finish it off before we return - */ - blk_start_plug(&plug); - - bdi = device->bdev->bd_bdi; - -loop: - spin_lock(&device->io_lock); - -loop_lock: - num_run = 0; - - /* take all the bios off the list at once and process them - * later on (without the lock held). But, remember the - * tail and other pointers so the bios can be properly reinserted - * into the list if we hit congestion - */ - if (!force_reg && device->pending_sync_bios.head) { - pending_bios = &device->pending_sync_bios; - force_reg = 1; - } else { - pending_bios = &device->pending_bios; - force_reg = 0; - } - - pending = pending_bios->head; - tail = pending_bios->tail; - WARN_ON(pending && !tail); - - /* - * if pending was null this time around, no bios need processing - * at all and we can stop. Otherwise it'll loop back up again - * and do an additional check so no bios are missed. - * - * device->running_pending is used to synchronize with the - * schedule_bio code. - */ - if (device->pending_sync_bios.head == NULL && - device->pending_bios.head == NULL) { - again = 0; - device->running_pending = 0; - } else { - again = 1; - device->running_pending = 1; - } - - pending_bios->head = NULL; - pending_bios->tail = NULL; - - spin_unlock(&device->io_lock); - - while (pending) { - - rmb(); - /* we want to work on both lists, but do more bios on the - * sync list than the regular list - */ - if ((num_run > 32 && - pending_bios != &device->pending_sync_bios && - device->pending_sync_bios.head) || - (num_run > 64 && pending_bios == &device->pending_sync_bios && - device->pending_bios.head)) { - spin_lock(&device->io_lock); - requeue_list(pending_bios, pending, tail); - goto loop_lock; - } - - cur = pending; - pending = pending->bi_next; - cur->bi_next = NULL; - - BUG_ON(atomic_read(&cur->__bi_cnt) == 0); - - /* - * if we're doing the sync list, record that our - * plug has some sync requests on it - * - * If we're doing the regular list and there are - * sync requests sitting around, unplug before - * we add more - */ - if (pending_bios == &device->pending_sync_bios) { - sync_pending = 1; - } else if (sync_pending) { - blk_finish_plug(&plug); - blk_start_plug(&plug); - sync_pending = 0; - } - - btrfsic_submit_bio(cur); - num_run++; - batch_run++; - - cond_resched(); - - /* - * we made progress, there is more work to do and the bdi - * is now congested. Back off and let other work structs - * run instead - */ - if (pending && bdi_write_congested(bdi) && batch_run > 8 && - fs_info->fs_devices->open_devices > 1) { - struct io_context *ioc; - - ioc = current->io_context; - - /* - * the main goal here is that we don't want to - * block if we're going to be able to submit - * more requests without blocking. - * - * This code does two great things, it pokes into - * the elevator code from a filesystem _and_ - * it makes assumptions about how batching works. - */ - if (ioc && ioc->nr_batch_requests > 0 && - time_before(jiffies, ioc->last_waited + HZ/50UL) && - (last_waited == 0 || - ioc->last_waited == last_waited)) { - /* - * we want to go through our batch of - * requests and stop. So, we copy out - * the ioc->last_waited time and test - * against it before looping - */ - last_waited = ioc->last_waited; - cond_resched(); - continue; - } - spin_lock(&device->io_lock); - requeue_list(pending_bios, pending, tail); - device->running_pending = 1; - - spin_unlock(&device->io_lock); - btrfs_queue_work(fs_info->submit_workers, - &device->work); - goto done; - } - } - - cond_resched(); - if (again) - goto loop; - - spin_lock(&device->io_lock); - if (device->pending_bios.head || device->pending_sync_bios.head) - goto loop_lock; - spin_unlock(&device->io_lock); - -done: - blk_finish_plug(&plug); -} - -static void pending_bios_fn(struct btrfs_work *work) -{ - struct btrfs_device *device; - - device = container_of(work, struct btrfs_device, work); - run_scheduled_bios(device); -} - static bool device_path_matched(const char *path, struct btrfs_device *device) { int found; @@ -818,7 +634,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, } clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); - fs_devices->seeding = 1; + fs_devices->seeding = true; } else { if (bdev_read_only(bdev)) clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); @@ -828,7 +644,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, q = bdev_get_queue(bdev); if (!blk_queue_nonrot(q)) - fs_devices->rotating = 1; + fs_devices->rotating = true; device->bdev = bdev; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); @@ -1005,11 +821,15 @@ static noinline struct btrfs_device *device_list_add(const char *path, *new_device_added = true; if (disk_super->label[0]) - pr_info("BTRFS: device label %s devid %llu transid %llu %s\n", - disk_super->label, devid, found_transid, path); + pr_info( + "BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n", + disk_super->label, devid, found_transid, path, + current->comm, task_pid_nr(current)); else - pr_info("BTRFS: device fsid %pU devid %llu transid %llu %s\n", - disk_super->fsid, devid, found_transid, path); + pr_info( + "BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n", + disk_super->fsid, devid, found_transid, path, + current->comm, task_pid_nr(current)); } else if (!device->name || strcmp(device->name->str, path)) { /* @@ -1295,7 +1115,7 @@ static int close_fs_devices(struct btrfs_fs_devices *fs_devices) WARN_ON(fs_devices->open_devices); WARN_ON(fs_devices->rw_devices); fs_devices->opened = 0; - fs_devices->seeding = 0; + fs_devices->seeding = false; return 0; } @@ -2048,7 +1868,7 @@ static struct btrfs_device * btrfs_find_next_active_device( * where this function called, there should be always be another device (or * this_dev) which is active. */ -void btrfs_assign_next_active_device(struct btrfs_device *device, +void __cold btrfs_assign_next_active_device(struct btrfs_device *device, struct btrfs_device *this_dev) { struct btrfs_fs_info *fs_info = device->fs_info; @@ -2450,11 +2270,11 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info) list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list); mutex_unlock(&fs_info->chunk_mutex); - fs_devices->seeding = 0; + fs_devices->seeding = false; fs_devices->num_devices = 0; fs_devices->open_devices = 0; fs_devices->missing_devices = 0; - fs_devices->rotating = 0; + fs_devices->rotating = false; fs_devices->seed = seed_devices; generate_random_uuid(fs_devices->fsid); @@ -2649,7 +2469,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path atomic64_add(device->total_bytes, &fs_info->free_chunk_space); if (!blk_queue_nonrot(q)) - fs_devices->rotating = 1; + fs_devices->rotating = true; orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy); btrfs_set_super_total_bytes(fs_info->super_copy, @@ -3177,7 +2997,7 @@ error: static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; u64 bytes_used; u64 chunk_type; @@ -3186,27 +3006,28 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info, chunk_type = cache->flags; btrfs_put_block_group(cache); - if (chunk_type & BTRFS_BLOCK_GROUP_DATA) { - spin_lock(&fs_info->data_sinfo->lock); - bytes_used = fs_info->data_sinfo->bytes_used; - spin_unlock(&fs_info->data_sinfo->lock); + if (!(chunk_type & BTRFS_BLOCK_GROUP_DATA)) + return 0; + + spin_lock(&fs_info->data_sinfo->lock); + bytes_used = fs_info->data_sinfo->bytes_used; + spin_unlock(&fs_info->data_sinfo->lock); - if (!bytes_used) { - struct btrfs_trans_handle *trans; - int ret; + if (!bytes_used) { + struct btrfs_trans_handle *trans; + int ret; - trans = btrfs_join_transaction(fs_info->tree_root); - if (IS_ERR(trans)) - return PTR_ERR(trans); + trans = btrfs_join_transaction(fs_info->tree_root); + if (IS_ERR(trans)) + return PTR_ERR(trans); - ret = btrfs_force_chunk_alloc(trans, - BTRFS_BLOCK_GROUP_DATA); - btrfs_end_transaction(trans); - if (ret < 0) - return ret; - return 1; - } + ret = btrfs_force_chunk_alloc(trans, BTRFS_BLOCK_GROUP_DATA); + btrfs_end_transaction(trans); + if (ret < 0) + return ret; + return 1; } + return 0; } @@ -3385,28 +3206,28 @@ static int chunk_profiles_filter(u64 chunk_type, static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, struct btrfs_balance_args *bargs) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; u64 chunk_used; u64 user_thresh_min; u64 user_thresh_max; int ret = 1; cache = btrfs_lookup_block_group(fs_info, chunk_offset); - chunk_used = btrfs_block_group_used(&cache->item); + chunk_used = cache->used; if (bargs->usage_min == 0) user_thresh_min = 0; else - user_thresh_min = div_factor_fine(cache->key.offset, - bargs->usage_min); + user_thresh_min = div_factor_fine(cache->length, + bargs->usage_min); if (bargs->usage_max == 0) user_thresh_max = 1; else if (bargs->usage_max > 100) - user_thresh_max = cache->key.offset; + user_thresh_max = cache->length; else - user_thresh_max = div_factor_fine(cache->key.offset, - bargs->usage_max); + user_thresh_max = div_factor_fine(cache->length, + bargs->usage_max); if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max) ret = 0; @@ -3418,20 +3239,19 @@ static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_off static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, struct btrfs_balance_args *bargs) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group *cache; u64 chunk_used, user_thresh; int ret = 1; cache = btrfs_lookup_block_group(fs_info, chunk_offset); - chunk_used = btrfs_block_group_used(&cache->item); + chunk_used = cache->used; if (bargs->usage_min == 0) user_thresh = 1; else if (bargs->usage > 100) - user_thresh = cache->key.offset; + user_thresh = cache->length; else - user_thresh = div_factor_fine(cache->key.offset, - bargs->usage); + user_thresh = div_factor_fine(cache->length, bargs->usage); if (chunk_used < user_thresh) ret = 0; @@ -3844,12 +3664,7 @@ static int alloc_profile_is_valid(u64 flags, int extended) if (flags == 0) return !extended; /* "0" is valid for usual profiles */ - /* true if exactly one bit set */ - /* - * Don't use is_power_of_2(unsigned long) because it won't work - * for the single profile (1ULL << 48) on 32-bit CPUs. - */ - return flags != 0 && (flags & (flags - 1)) == 0; + return has_single_bit_set(flags); } static inline int balance_need_close(struct btrfs_fs_info *fs_info) @@ -4036,7 +3851,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, int ret; u64 num_devices; unsigned seq; - bool reducing_integrity; + bool reducing_redundancy; int i; if (btrfs_fs_closing(fs_info) || @@ -4119,9 +3934,9 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) && (fs_info->avail_metadata_alloc_bits & allowed) && !(bctl->meta.target & allowed))) - reducing_integrity = true; + reducing_redundancy = true; else - reducing_integrity = false; + reducing_redundancy = false; /* if we're not converting, the target field is uninitialized */ meta_target = (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) ? @@ -4130,13 +3945,13 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, bctl->data.target : fs_info->avail_data_alloc_bits; } while (read_seqretry(&fs_info->profiles_lock, seq)); - if (reducing_integrity) { + if (reducing_redundancy) { if (bctl->flags & BTRFS_BALANCE_FORCE) { btrfs_info(fs_info, - "balance: force reducing metadata integrity"); + "balance: force reducing metadata redundancy"); } else { btrfs_err(fs_info, - "balance: reduces metadata integrity, use --force if you want this"); + "balance: reduces metadata redundancy, use --force if you want this"); ret = -EINVAL; goto out; } @@ -4902,6 +4717,14 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type) btrfs_set_fs_incompat(info, RAID56); } +static void check_raid1c34_incompat_flag(struct btrfs_fs_info *info, u64 type) +{ + if (!(type & (BTRFS_BLOCK_GROUP_RAID1C3 | BTRFS_BLOCK_GROUP_RAID1C4))) + return; + + btrfs_set_fs_incompat(info, RAID1C34); +} + static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 start, u64 type) { @@ -4967,6 +4790,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, } else if (type & BTRFS_BLOCK_GROUP_SYSTEM) { max_stripe_size = SZ_32M; max_chunk_size = 2 * max_stripe_size; + devs_max = min_t(int, devs_max, BTRFS_MAX_DEVS_SYS_CHUNK); } else { btrfs_err(info, "invalid chunk type 0x%llx requested", type); @@ -5047,8 +4871,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, sort(devices_info, ndevs, sizeof(struct btrfs_device_info), btrfs_cmp_device_info, NULL); - /* round down to number of usable stripes */ - ndevs = round_down(ndevs, devs_increment); + /* + * Round down to number of usable stripes, devs_increment can be any + * number so we can't use round_down() + */ + ndevs -= ndevs % devs_increment; if (ndevs < devs_min) { ret = -ENOSPC; @@ -5164,6 +4991,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, free_extent_map(em); check_raid56_incompat_flag(info, type); + check_raid1c34_incompat_flag(info, type); kfree(devices_info); return 0; @@ -5582,12 +5410,13 @@ void btrfs_put_bbio(struct btrfs_bio *bbio) * replace. */ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info, - u64 logical, u64 length, + u64 logical, u64 *length_ret, struct btrfs_bio **bbio_ret) { struct extent_map *em; struct map_lookup *map; struct btrfs_bio *bbio; + u64 length = *length_ret; u64 offset; u64 stripe_nr; u64 stripe_nr_end; @@ -5620,7 +5449,8 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info, } offset = logical - em->start; - length = min_t(u64, em->len - offset, length); + length = min_t(u64, em->start + em->len - logical, length); + *length_ret = length; stripe_len = map->stripe_len; /* @@ -6035,7 +5865,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, if (op == BTRFS_MAP_DISCARD) return __btrfs_map_block_for_discard(fs_info, logical, - *length, bbio_ret); + length, bbio_ret); ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom); if (ret < 0) @@ -6415,52 +6245,8 @@ static void btrfs_end_bio(struct bio *bio) } } -/* - * see run_scheduled_bios for a description of why bios are collected for - * async submit. - * - * This will add one bio to the pending list for a device and make sure - * the work struct is scheduled. - */ -static noinline void btrfs_schedule_bio(struct btrfs_device *device, - struct bio *bio) -{ - struct btrfs_fs_info *fs_info = device->fs_info; - int should_queue = 1; - struct btrfs_pending_bios *pending_bios; - - /* don't bother with additional async steps for reads, right now */ - if (bio_op(bio) == REQ_OP_READ) { - btrfsic_submit_bio(bio); - return; - } - - WARN_ON(bio->bi_next); - bio->bi_next = NULL; - - spin_lock(&device->io_lock); - if (op_is_sync(bio->bi_opf)) - pending_bios = &device->pending_sync_bios; - else - pending_bios = &device->pending_bios; - - if (pending_bios->tail) - pending_bios->tail->bi_next = bio; - - pending_bios->tail = bio; - if (!pending_bios->head) - pending_bios->head = bio; - if (device->running_pending) - should_queue = 0; - - spin_unlock(&device->io_lock); - - if (should_queue) - btrfs_queue_work(fs_info->submit_workers, &device->work); -} - static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, - u64 physical, int dev_nr, int async) + u64 physical, int dev_nr) { struct btrfs_device *dev = bbio->stripes[dev_nr].dev; struct btrfs_fs_info *fs_info = bbio->fs_info; @@ -6478,10 +6264,7 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, btrfs_bio_counter_inc_noblocked(fs_info); - if (async) - btrfs_schedule_bio(dev, bio); - else - btrfsic_submit_bio(bio); + btrfsic_submit_bio(bio); } static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) @@ -6502,7 +6285,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) } blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, int async_submit) + int mirror_num) { struct btrfs_device *dev; struct bio *first_bio = bio; @@ -6571,7 +6354,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, bio = first_bio; submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical, - dev_nr, async_submit); + dev_nr); } btrfs_bio_counter_dec(fs_info); return BLK_STS_OK; @@ -6675,9 +6458,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, else generate_random_uuid(dev->uuid); - btrfs_init_work(&dev->work, btrfs_submit_helper, - pending_bios_fn, NULL, NULL); - return dev; } @@ -6874,7 +6654,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info, if (IS_ERR(fs_devices)) return fs_devices; - fs_devices->seeding = 1; + fs_devices->seeding = true; fs_devices->opened = 1; return fs_devices; } @@ -7063,48 +6843,49 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) sb_array_offset += len; cur_offset += len; - if (key.type == BTRFS_CHUNK_ITEM_KEY) { - chunk = (struct btrfs_chunk *)sb_array_offset; - /* - * At least one btrfs_chunk with one stripe must be - * present, exact stripe count check comes afterwards - */ - len = btrfs_chunk_item_size(1); - if (cur_offset + len > array_size) - goto out_short_read; - - num_stripes = btrfs_chunk_num_stripes(sb, chunk); - if (!num_stripes) { - btrfs_err(fs_info, - "invalid number of stripes %u in sys_array at offset %u", - num_stripes, cur_offset); - ret = -EIO; - break; - } + if (key.type != BTRFS_CHUNK_ITEM_KEY) { + btrfs_err(fs_info, + "unexpected item type %u in sys_array at offset %u", + (u32)key.type, cur_offset); + ret = -EIO; + break; + } - type = btrfs_chunk_type(sb, chunk); - if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) { - btrfs_err(fs_info, - "invalid chunk type %llu in sys_array at offset %u", - type, cur_offset); - ret = -EIO; - break; - } + chunk = (struct btrfs_chunk *)sb_array_offset; + /* + * At least one btrfs_chunk with one stripe must be present, + * exact stripe count check comes afterwards + */ + len = btrfs_chunk_item_size(1); + if (cur_offset + len > array_size) + goto out_short_read; - len = btrfs_chunk_item_size(num_stripes); - if (cur_offset + len > array_size) - goto out_short_read; + num_stripes = btrfs_chunk_num_stripes(sb, chunk); + if (!num_stripes) { + btrfs_err(fs_info, + "invalid number of stripes %u in sys_array at offset %u", + num_stripes, cur_offset); + ret = -EIO; + break; + } - ret = read_one_chunk(&key, sb, chunk); - if (ret) - break; - } else { + type = btrfs_chunk_type(sb, chunk); + if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) { btrfs_err(fs_info, - "unexpected item type %u in sys_array at offset %u", - (u32)key.type, cur_offset); + "invalid chunk type %llu in sys_array at offset %u", + type, cur_offset); ret = -EIO; break; } + + len = btrfs_chunk_item_size(num_stripes); + if (cur_offset + len > array_size) + goto out_short_read; + + ret = read_one_chunk(&key, sb, chunk); + if (ret) + break; + array_ptr += len; sb_array_offset += len; cur_offset += len; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index a7da1f3e3627..fc1b564b9cfe 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -18,10 +18,6 @@ extern struct mutex uuid_mutex; #define BTRFS_STRIPE_LEN SZ_64K struct buffer_head; -struct btrfs_pending_bios { - struct bio *head; - struct bio *tail; -}; struct btrfs_io_geometry { /* remaining bytes before crossing a stripe */ @@ -68,13 +64,6 @@ struct btrfs_device { u64 generation; - spinlock_t io_lock ____cacheline_aligned; - int running_pending; - /* regular prio bios */ - struct btrfs_pending_bios pending_bios; - /* sync bios */ - struct btrfs_pending_bios pending_sync_bios; - struct block_device *bdev; /* the mode sent to blkdev_get */ @@ -254,14 +243,14 @@ struct btrfs_fs_devices { struct list_head alloc_list; struct btrfs_fs_devices *seed; - int seeding; + bool seeding; int opened; /* set when we find or add a device that doesn't have the * nonrot flag set */ - int rotating; + bool rotating; struct btrfs_fs_info *fs_info; /* sysfs kobjects */ @@ -330,7 +319,6 @@ struct btrfs_bio { u64 map_type; /* get from map_lookup->type */ bio_end_io_t *end_io; struct bio *orig_bio; - unsigned long flags; void *private; atomic_t error; int max_errors; @@ -436,7 +424,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info); int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type); void btrfs_mapping_tree_free(struct extent_map_tree *tree); blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, int async_submit); + int mirror_num); int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fmode_t flags, void *holder); struct btrfs_device *btrfs_scan_one_device(const char *path, @@ -557,6 +545,10 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags) return BTRFS_RAID_RAID10; else if (flags & BTRFS_BLOCK_GROUP_RAID1) return BTRFS_RAID_RAID1; + else if (flags & BTRFS_BLOCK_GROUP_RAID1C3) + return BTRFS_RAID_RAID1C3; + else if (flags & BTRFS_BLOCK_GROUP_RAID1C4) + return BTRFS_RAID_RAID1C4; else if (flags & BTRFS_BLOCK_GROUP_DUP) return BTRFS_RAID_DUP; else if (flags & BTRFS_BLOCK_GROUP_RAID0) @@ -571,7 +563,7 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags) void btrfs_commit_device_sizes(struct btrfs_transaction *trans); -struct list_head *btrfs_get_fs_uuids(void); +struct list_head * __attribute_const__ btrfs_get_fs_uuids(void); void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info); void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info); bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index df1aace5df50..a6c90a003c12 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -29,19 +29,9 @@ struct workspace { static struct workspace_manager wsm; -static void zlib_init_workspace_manager(void) +struct list_head *zlib_get_workspace(unsigned int level) { - btrfs_init_workspace_manager(&wsm, &btrfs_zlib_compress); -} - -static void zlib_cleanup_workspace_manager(void) -{ - btrfs_cleanup_workspace_manager(&wsm); -} - -static struct list_head *zlib_get_workspace(unsigned int level) -{ - struct list_head *ws = btrfs_get_workspace(&wsm, level); + struct list_head *ws = btrfs_get_workspace(BTRFS_COMPRESS_ZLIB, level); struct workspace *workspace = list_entry(ws, struct workspace, list); workspace->level = level; @@ -49,12 +39,7 @@ static struct list_head *zlib_get_workspace(unsigned int level) return ws; } -static void zlib_put_workspace(struct list_head *ws) -{ - btrfs_put_workspace(&wsm, ws); -} - -static void zlib_free_workspace(struct list_head *ws) +void zlib_free_workspace(struct list_head *ws) { struct workspace *workspace = list_entry(ws, struct workspace, list); @@ -63,7 +48,7 @@ static void zlib_free_workspace(struct list_head *ws) kfree(workspace); } -static struct list_head *zlib_alloc_workspace(unsigned int level) +struct list_head *zlib_alloc_workspace(unsigned int level) { struct workspace *workspace; int workspacesize; @@ -88,13 +73,9 @@ fail: return ERR_PTR(-ENOMEM); } -static int zlib_compress_pages(struct list_head *ws, - struct address_space *mapping, - u64 start, - struct page **pages, - unsigned long *out_pages, - unsigned long *total_in, - unsigned long *total_out) +int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, + u64 start, struct page **pages, unsigned long *out_pages, + unsigned long *total_in, unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret; @@ -228,7 +209,7 @@ out: return ret; } -static int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) +int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0, ret2; @@ -319,10 +300,9 @@ done: return ret; } -static int zlib_decompress(struct list_head *ws, unsigned char *data_in, - struct page *dest_page, - unsigned long start_byte, - size_t srclen, size_t destlen) +int zlib_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, unsigned long start_byte, size_t srclen, + size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0; @@ -419,15 +399,7 @@ next: } const struct btrfs_compress_op btrfs_zlib_compress = { - .init_workspace_manager = zlib_init_workspace_manager, - .cleanup_workspace_manager = zlib_cleanup_workspace_manager, - .get_workspace = zlib_get_workspace, - .put_workspace = zlib_put_workspace, - .alloc_workspace = zlib_alloc_workspace, - .free_workspace = zlib_free_workspace, - .compress_pages = zlib_compress_pages, - .decompress_bio = zlib_decompress_bio, - .decompress = zlib_decompress, + .workspace_manager = &wsm, .max_level = 9, .default_level = BTRFS_ZLIB_DEFAULT_LEVEL, }; diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 764d47b107e5..9a4871636c6c 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -91,9 +91,8 @@ static inline struct workspace *list_to_workspace(struct list_head *list) return container_of(list, struct workspace, list); } -static void zstd_free_workspace(struct list_head *ws); -static struct list_head *zstd_alloc_workspace(unsigned int level); - +void zstd_free_workspace(struct list_head *ws); +struct list_head *zstd_alloc_workspace(unsigned int level); /* * zstd_reclaim_timer_fn - reclaim timer * @t: timer @@ -168,7 +167,7 @@ static void zstd_calc_ws_mem_sizes(void) } } -static void zstd_init_workspace_manager(void) +void zstd_init_workspace_manager(void) { struct list_head *ws; int i; @@ -194,7 +193,7 @@ static void zstd_init_workspace_manager(void) } } -static void zstd_cleanup_workspace_manager(void) +void zstd_cleanup_workspace_manager(void) { struct workspace *workspace; int i; @@ -261,7 +260,7 @@ static struct list_head *zstd_find_workspace(unsigned int level) * attempt to allocate a new workspace. If we fail to allocate one due to * memory pressure, go to sleep waiting for the max level workspace to free up. */ -static struct list_head *zstd_get_workspace(unsigned int level) +struct list_head *zstd_get_workspace(unsigned int level) { struct list_head *ws; unsigned int nofs_flag; @@ -302,7 +301,7 @@ again: * isn't set, it is also set here. Only the max level workspace tries and wakes * up waiting workspaces. */ -static void zstd_put_workspace(struct list_head *ws) +void zstd_put_workspace(struct list_head *ws) { struct workspace *workspace = list_to_workspace(ws); @@ -332,7 +331,7 @@ static void zstd_put_workspace(struct list_head *ws) cond_wake_up(&wsm.wait); } -static void zstd_free_workspace(struct list_head *ws) +void zstd_free_workspace(struct list_head *ws) { struct workspace *workspace = list_entry(ws, struct workspace, list); @@ -341,7 +340,7 @@ static void zstd_free_workspace(struct list_head *ws) kfree(workspace); } -static struct list_head *zstd_alloc_workspace(unsigned int level) +struct list_head *zstd_alloc_workspace(unsigned int level) { struct workspace *workspace; @@ -367,13 +366,9 @@ fail: return ERR_PTR(-ENOMEM); } -static int zstd_compress_pages(struct list_head *ws, - struct address_space *mapping, - u64 start, - struct page **pages, - unsigned long *out_pages, - unsigned long *total_in, - unsigned long *total_out) +int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, + u64 start, struct page **pages, unsigned long *out_pages, + unsigned long *total_in, unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); ZSTD_CStream *stream; @@ -548,7 +543,7 @@ out: return ret; } -static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) +int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) { struct workspace *workspace = list_entry(ws, struct workspace, list); struct page **pages_in = cb->compressed_pages; @@ -626,10 +621,9 @@ done: return ret; } -static int zstd_decompress(struct list_head *ws, unsigned char *data_in, - struct page *dest_page, - unsigned long start_byte, - size_t srclen, size_t destlen) +int zstd_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, unsigned long start_byte, size_t srclen, + size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); ZSTD_DStream *stream; @@ -712,15 +706,8 @@ finish: } const struct btrfs_compress_op btrfs_zstd_compress = { - .init_workspace_manager = zstd_init_workspace_manager, - .cleanup_workspace_manager = zstd_cleanup_workspace_manager, - .get_workspace = zstd_get_workspace, - .put_workspace = zstd_put_workspace, - .alloc_workspace = zstd_alloc_workspace, - .free_workspace = zstd_free_workspace, - .compress_pages = zstd_compress_pages, - .decompress_bio = zstd_decompress_bio, - .decompress = zstd_decompress, + /* ZSTD uses own workspace manager */ + .workspace_manager = NULL, .max_level = ZSTD_BTRFS_MAX_LEVEL, .default_level = ZSTD_BTRFS_DEFAULT_LEVEL, }; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index d3b9c9d5c1bd..f5a38910a82b 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1058,6 +1058,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode); + /* remove from inode's cap rbtree, and clear auth cap */ + rb_erase(&cap->ci_node, &ci->i_caps); + if (ci->i_auth_cap == cap) + ci->i_auth_cap = NULL; + /* remove from session list */ spin_lock(&session->s_cap_lock); if (session->s_cap_iterator == cap) { @@ -1091,11 +1096,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) spin_unlock(&session->s_cap_lock); - /* remove from inode list */ - rb_erase(&cap->ci_node, &ci->i_caps); - if (ci->i_auth_cap == cap) - ci->i_auth_cap = NULL; - if (removed) ceph_put_cap(mdsc, cap); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4ca0b8ff9a72..d17a789fd856 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1553,36 +1553,37 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) { int valid = 0; struct dentry *parent; - struct inode *dir; + struct inode *dir, *inode; if (flags & LOOKUP_RCU) { parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) return -ECHILD; + inode = d_inode_rcu(dentry); } else { parent = dget_parent(dentry); dir = d_inode(parent); + inode = d_inode(dentry); } dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry, - dentry, d_inode(dentry), ceph_dentry(dentry)->offset); + dentry, inode, ceph_dentry(dentry)->offset); /* always trust cached snapped dentries, snapdir dentry */ if (ceph_snap(dir) != CEPH_NOSNAP) { dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry, - dentry, d_inode(dentry)); + dentry, inode); valid = 1; - } else if (d_really_is_positive(dentry) && - ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) { + } else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) { valid = 1; } else { valid = dentry_lease_is_valid(dentry, flags); if (valid == -ECHILD) return valid; if (valid || dir_lease_is_valid(dir, dentry)) { - if (d_really_is_positive(dentry)) - valid = ceph_is_any_caps(d_inode(dentry)); + if (inode) + valid = ceph_is_any_caps(inode); else valid = 1; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d277f71abe0b..8de633964dc3 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -462,6 +462,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, err = ceph_security_init_secctx(dentry, mode, &as_ctx); if (err < 0) goto out_ctx; + } else if (!d_in_lookup(dentry)) { + /* If it's not being looked up, it's negative */ + return -ENOENT; } /* do the open */ @@ -750,6 +753,9 @@ static void ceph_aio_complete(struct inode *inode, if (!atomic_dec_and_test(&aio_req->pending_reqs)) return; + if (aio_req->iocb->ki_flags & IOCB_DIRECT) + inode_dio_end(inode); + ret = aio_req->error; if (!ret) ret = aio_req->total_len; @@ -1088,6 +1094,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, CEPH_CAP_FILE_RD); list_splice(&aio_req->osd_reqs, &osd_reqs); + inode_dio_begin(inode); while (!list_empty(&osd_reqs)) { req = list_first_entry(&osd_reqs, struct ceph_osd_request, @@ -1261,14 +1268,24 @@ again: dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode); + if (iocb->ki_flags & IOCB_DIRECT) + ceph_start_io_direct(inode); + else + ceph_start_io_read(inode); + if (fi->fmode & CEPH_FILE_MODE_LAZY) want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO; else want = CEPH_CAP_FILE_CACHE; ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1, &got, &pinned_page); - if (ret < 0) + if (ret < 0) { + if (iocb->ki_flags & IOCB_DIRECT) + ceph_end_io_direct(inode); + else + ceph_end_io_read(inode); return ret; + } if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 || (iocb->ki_flags & IOCB_DIRECT) || @@ -1280,16 +1297,12 @@ again: if (ci->i_inline_version == CEPH_INLINE_NONE) { if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) { - ceph_start_io_direct(inode); ret = ceph_direct_read_write(iocb, to, NULL, NULL); - ceph_end_io_direct(inode); if (ret >= 0 && ret < len) retry_op = CHECK_EOF; } else { - ceph_start_io_read(inode); ret = ceph_sync_read(iocb, to, &retry_op); - ceph_end_io_read(inode); } } else { retry_op = READ_INLINE; @@ -1300,11 +1313,10 @@ again: inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, ceph_cap_string(got)); ceph_add_rw_context(fi, &rw_ctx); - ceph_start_io_read(inode); ret = generic_file_read_iter(iocb, to); - ceph_end_io_read(inode); ceph_del_rw_context(fi, &rw_ctx); } + dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n", inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret); if (pinned_page) { @@ -1312,6 +1324,12 @@ again: pinned_page = NULL; } ceph_put_cap_refs(ci, got); + + if (iocb->ki_flags & IOCB_DIRECT) + ceph_end_io_direct(inode); + else + ceph_end_io_read(inode); + if (retry_op > HAVE_RETRIED && ret >= 0) { int statret; struct page *page = NULL; @@ -1956,10 +1974,18 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, if (ceph_test_mount_opt(src_fsc, NOCOPYFROM)) return -EOPNOTSUPP; + /* + * Striped file layouts require that we copy partial objects, but the + * OSD copy-from operation only supports full-object copies. Limit + * this to non-striped file layouts for now. + */ if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) || - (src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) || - (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) + (src_ci->i_layout.stripe_count != 1) || + (dst_ci->i_layout.stripe_count != 1) || + (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) { + dout("Invalid src/dst files layout\n"); return -EOPNOTSUPP; + } if (len < src_ci->i_layout.object_size) return -EOPNOTSUPP; /* no remote copy will be done */ diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9f135624ae47..c07407586ce8 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1434,6 +1434,7 @@ retry_lookup: dout(" final dn %p\n", dn); } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP || req->r_op == CEPH_MDS_OP_MKSNAP) && + test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) && !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) { struct inode *dir = req->r_parent; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index edfd643a8205..b47f43fc2d68 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -268,6 +268,7 @@ static int parse_fsopt_token(char *c, void *private) } break; case Opt_fscache_uniq: +#ifdef CONFIG_CEPH_FSCACHE kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = kstrndup(argstr[0].from, argstr[0].to-argstr[0].from, @@ -276,7 +277,10 @@ static int parse_fsopt_token(char *c, void *private) return -ENOMEM; fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; break; - /* misc */ +#else + pr_err("fscache support is disabled\n"); + return -EINVAL; +#endif case Opt_wsize: if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE) return -EINVAL; @@ -353,10 +357,15 @@ static int parse_fsopt_token(char *c, void *private) fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; case Opt_fscache: +#ifdef CONFIG_CEPH_FSCACHE fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = NULL; break; +#else + pr_err("fscache support is disabled\n"); + return -EINVAL; +#endif case Opt_nofscache: fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index ea735d59c36e..0abfde6d0b05 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -838,6 +838,7 @@ struct create_durable_handle_reconnect_v2 { struct create_context ccontext; __u8 Name[8]; struct durable_reconnect_context_v2 dcontext; + __u8 Pad[4]; } __packed; /* See MS-SMB2 2.2.13.2.5 */ diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index dc5dbf6a81d7..cb61467478ca 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -101,7 +101,7 @@ static int create_link(struct config_item *parent_item, } target_sd->s_links++; spin_unlock(&configfs_dirent_lock); - ret = configfs_get_target_path(item, item, body); + ret = configfs_get_target_path(parent_item, item, body); if (!ret) ret = configfs_create_link(target_sd, parent_item->ci_dentry, dentry, body); diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index d12ea28836a5..2f04024c3588 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -958,8 +958,8 @@ static int cramfs_get_tree(struct fs_context *fc) if (IS_ENABLED(CONFIG_CRAMFS_MTD)) { ret = get_tree_mtd(fc, cramfs_mtd_fill_super); - if (ret < 0) - return ret; + if (!ret) + return 0; } if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV)) ret = get_tree_bdev(fc, cramfs_blkdev_fill_super); diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 82da2510721f..1f4b8a277060 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -26,7 +26,7 @@ #include <linux/namei.h> #include "fscrypt_private.h" -static void __fscrypt_decrypt_bio(struct bio *bio, bool done) +void fscrypt_decrypt_bio(struct bio *bio) { struct bio_vec *bv; struct bvec_iter_all iter_all; @@ -37,37 +37,10 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done) bv->bv_offset); if (ret) SetPageError(page); - else if (done) - SetPageUptodate(page); - if (done) - unlock_page(page); } } - -void fscrypt_decrypt_bio(struct bio *bio) -{ - __fscrypt_decrypt_bio(bio, false); -} EXPORT_SYMBOL(fscrypt_decrypt_bio); -static void completion_pages(struct work_struct *work) -{ - struct fscrypt_ctx *ctx = container_of(work, struct fscrypt_ctx, work); - struct bio *bio = ctx->bio; - - __fscrypt_decrypt_bio(bio, true); - fscrypt_release_ctx(ctx); - bio_put(bio); -} - -void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio) -{ - INIT_WORK(&ctx->work, completion_pages); - ctx->bio = bio; - fscrypt_enqueue_decrypt_work(&ctx->work); -} -EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio); - int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 32a7ad0098cc..3719efa546c6 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -27,29 +27,20 @@ #include <linux/ratelimit.h> #include <linux/dcache.h> #include <linux/namei.h> -#include <crypto/aes.h> #include <crypto/skcipher.h> #include "fscrypt_private.h" static unsigned int num_prealloc_crypto_pages = 32; -static unsigned int num_prealloc_crypto_ctxs = 128; module_param(num_prealloc_crypto_pages, uint, 0444); MODULE_PARM_DESC(num_prealloc_crypto_pages, "Number of crypto pages to preallocate"); -module_param(num_prealloc_crypto_ctxs, uint, 0444); -MODULE_PARM_DESC(num_prealloc_crypto_ctxs, - "Number of crypto contexts to preallocate"); static mempool_t *fscrypt_bounce_page_pool = NULL; -static LIST_HEAD(fscrypt_free_ctxs); -static DEFINE_SPINLOCK(fscrypt_ctx_lock); - static struct workqueue_struct *fscrypt_read_workqueue; static DEFINE_MUTEX(fscrypt_init_mutex); -static struct kmem_cache *fscrypt_ctx_cachep; struct kmem_cache *fscrypt_info_cachep; void fscrypt_enqueue_decrypt_work(struct work_struct *work) @@ -58,62 +49,6 @@ void fscrypt_enqueue_decrypt_work(struct work_struct *work) } EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work); -/** - * fscrypt_release_ctx() - Release a decryption context - * @ctx: The decryption context to release. - * - * If the decryption context was allocated from the pre-allocated pool, return - * it to that pool. Else, free it. - */ -void fscrypt_release_ctx(struct fscrypt_ctx *ctx) -{ - unsigned long flags; - - if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) { - kmem_cache_free(fscrypt_ctx_cachep, ctx); - } else { - spin_lock_irqsave(&fscrypt_ctx_lock, flags); - list_add(&ctx->free_list, &fscrypt_free_ctxs); - spin_unlock_irqrestore(&fscrypt_ctx_lock, flags); - } -} -EXPORT_SYMBOL(fscrypt_release_ctx); - -/** - * fscrypt_get_ctx() - Get a decryption context - * @gfp_flags: The gfp flag for memory allocation - * - * Allocate and initialize a decryption context. - * - * Return: A new decryption context on success; an ERR_PTR() otherwise. - */ -struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) -{ - struct fscrypt_ctx *ctx; - unsigned long flags; - - /* - * First try getting a ctx from the free list so that we don't have to - * call into the slab allocator. - */ - spin_lock_irqsave(&fscrypt_ctx_lock, flags); - ctx = list_first_entry_or_null(&fscrypt_free_ctxs, - struct fscrypt_ctx, free_list); - if (ctx) - list_del(&ctx->free_list); - spin_unlock_irqrestore(&fscrypt_ctx_lock, flags); - if (!ctx) { - ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, gfp_flags); - if (!ctx) - return ERR_PTR(-ENOMEM); - ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL; - } else { - ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL; - } - return ctx; -} -EXPORT_SYMBOL(fscrypt_get_ctx); - struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags) { return mempool_alloc(fscrypt_bounce_page_pool, gfp_flags); @@ -138,14 +73,17 @@ EXPORT_SYMBOL(fscrypt_free_bounce_page); void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, const struct fscrypt_info *ci) { + u8 flags = fscrypt_policy_flags(&ci->ci_policy); + memset(iv, 0, ci->ci_mode->ivsize); - iv->lblk_num = cpu_to_le64(lblk_num); - if (fscrypt_is_direct_key_policy(&ci->ci_policy)) + if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { + WARN_ON_ONCE((u32)lblk_num != lblk_num); + lblk_num |= (u64)ci->ci_inode->i_ino << 32; + } else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); - - if (ci->ci_essiv_tfm != NULL) - crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw); + } + iv->lblk_num = cpu_to_le64(lblk_num); } /* Encrypt or decrypt a single filesystem block of file contents */ @@ -396,17 +334,6 @@ const struct dentry_operations fscrypt_d_ops = { .d_revalidate = fscrypt_d_revalidate, }; -static void fscrypt_destroy(void) -{ - struct fscrypt_ctx *pos, *n; - - list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list) - kmem_cache_free(fscrypt_ctx_cachep, pos); - INIT_LIST_HEAD(&fscrypt_free_ctxs); - mempool_destroy(fscrypt_bounce_page_pool); - fscrypt_bounce_page_pool = NULL; -} - /** * fscrypt_initialize() - allocate major buffers for fs encryption. * @cop_flags: fscrypt operations flags @@ -414,11 +341,11 @@ static void fscrypt_destroy(void) * We only call this when we start accessing encrypted files, since it * results in memory getting allocated that wouldn't otherwise be used. * - * Return: Zero on success, non-zero otherwise. + * Return: 0 on success; -errno on failure */ int fscrypt_initialize(unsigned int cop_flags) { - int i, res = -ENOMEM; + int err = 0; /* No need to allocate a bounce page pool if this FS won't use it. */ if (cop_flags & FS_CFLG_OWN_PAGES) @@ -426,29 +353,18 @@ int fscrypt_initialize(unsigned int cop_flags) mutex_lock(&fscrypt_init_mutex); if (fscrypt_bounce_page_pool) - goto already_initialized; - - for (i = 0; i < num_prealloc_crypto_ctxs; i++) { - struct fscrypt_ctx *ctx; - - ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS); - if (!ctx) - goto fail; - list_add(&ctx->free_list, &fscrypt_free_ctxs); - } + goto out_unlock; + err = -ENOMEM; fscrypt_bounce_page_pool = mempool_create_page_pool(num_prealloc_crypto_pages, 0); if (!fscrypt_bounce_page_pool) - goto fail; + goto out_unlock; -already_initialized: - mutex_unlock(&fscrypt_init_mutex); - return 0; -fail: - fscrypt_destroy(); + err = 0; +out_unlock: mutex_unlock(&fscrypt_init_mutex); - return res; + return err; } void fscrypt_msg(const struct inode *inode, const char *level, @@ -494,13 +410,9 @@ static int __init fscrypt_init(void) if (!fscrypt_read_workqueue) goto fail; - fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT); - if (!fscrypt_ctx_cachep) - goto fail_free_queue; - fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT); if (!fscrypt_info_cachep) - goto fail_free_ctx; + goto fail_free_queue; err = fscrypt_init_keyring(); if (err) @@ -510,8 +422,6 @@ static int __init fscrypt_init(void) fail_free_info: kmem_cache_destroy(fscrypt_info_cachep); -fail_free_ctx: - kmem_cache_destroy(fscrypt_ctx_cachep); fail_free_queue: destroy_workqueue(fscrypt_read_workqueue); fail: diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index e84efc01512e..130b50e5a011 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -163,11 +163,8 @@ struct fscrypt_info { /* The actual crypto transform used for encryption and decryption */ struct crypto_skcipher *ci_ctfm; - /* - * Cipher for ESSIV IV generation. Only set for CBC contents - * encryption, otherwise is NULL. - */ - struct crypto_cipher *ci_essiv_tfm; + /* True if the key should be freed when this fscrypt_info is freed */ + bool ci_owns_key; /* * Encryption mode used for this inode. It corresponds to either the @@ -209,8 +206,6 @@ typedef enum { FS_ENCRYPT, } fscrypt_direction_t; -#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 - static inline bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode) { @@ -289,7 +284,8 @@ extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, */ #define HKDF_CONTEXT_KEY_IDENTIFIER 1 #define HKDF_CONTEXT_PER_FILE_KEY 2 -#define HKDF_CONTEXT_PER_MODE_KEY 3 +#define HKDF_CONTEXT_DIRECT_KEY 3 +#define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 extern int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context, const u8 *info, unsigned int infolen, @@ -386,8 +382,14 @@ struct fscrypt_master_key { struct list_head mk_decrypted_inodes; spinlock_t mk_decrypted_inodes_lock; - /* Per-mode tfms for DIRECT_KEY policies, allocated on-demand */ - struct crypto_skcipher *mk_mode_keys[__FSCRYPT_MODE_MAX + 1]; + /* 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. + */ + struct crypto_skcipher *mk_iv_ino_lblk_64_tfms[__FSCRYPT_MODE_MAX + 1]; } __randomize_layout; @@ -443,8 +445,7 @@ struct fscrypt_mode { const char *cipher_str; int keysize; int ivsize; - bool logged_impl_name; - bool needs_essiv; + int logged_impl_name; }; static inline bool diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index c34fa7c61b43..040df1f5e1c8 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -43,8 +43,10 @@ static void free_master_key(struct fscrypt_master_key *mk) wipe_master_key_secret(&mk->mk_secret); - for (i = 0; i < ARRAY_SIZE(mk->mk_mode_keys); i++) - crypto_free_skcipher(mk->mk_mode_keys[i]); + 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]); + } key_put(mk->mk_users); kzfree(mk); diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index d71c2d6dd162..f577bb6613f9 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -8,15 +8,11 @@ * Heavily modified since then. */ -#include <crypto/aes.h> -#include <crypto/sha.h> #include <crypto/skcipher.h> #include <linux/key.h> #include "fscrypt_private.h" -static struct crypto_shash *essiv_hash_tfm; - static struct fscrypt_mode available_modes[] = { [FSCRYPT_MODE_AES_256_XTS] = { .friendly_name = "AES-256-XTS", @@ -31,11 +27,10 @@ static struct fscrypt_mode available_modes[] = { .ivsize = 16, }, [FSCRYPT_MODE_AES_128_CBC] = { - .friendly_name = "AES-128-CBC", - .cipher_str = "cbc(aes)", + .friendly_name = "AES-128-CBC-ESSIV", + .cipher_str = "essiv(cbc(aes),sha256)", .keysize = 16, .ivsize = 16, - .needs_essiv = true, }, [FSCRYPT_MODE_AES_128_CTS] = { .friendly_name = "AES-128-CTS-CBC", @@ -86,15 +81,13 @@ struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode, mode->cipher_str, PTR_ERR(tfm)); return tfm; } - if (unlikely(!mode->logged_impl_name)) { + if (!xchg(&mode->logged_impl_name, 1)) { /* * fscrypt performance can vary greatly depending on which * crypto algorithm implementation is used. Help people debug * performance problems by logging the ->cra_driver_name the - * first time a mode is used. Note that multiple threads can - * race here, but it doesn't really matter. + * first time a mode is used. */ - mode->logged_impl_name = true; pr_info("fscrypt: %s using implementation \"%s\"\n", mode->friendly_name, crypto_skcipher_alg(tfm)->base.cra_driver_name); @@ -111,131 +104,64 @@ err_free_tfm: return ERR_PTR(err); } -static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) -{ - struct crypto_shash *tfm = READ_ONCE(essiv_hash_tfm); - - /* init hash transform on demand */ - if (unlikely(!tfm)) { - struct crypto_shash *prev_tfm; - - tfm = crypto_alloc_shash("sha256", 0, 0); - if (IS_ERR(tfm)) { - if (PTR_ERR(tfm) == -ENOENT) { - fscrypt_warn(NULL, - "Missing crypto API support for SHA-256"); - return -ENOPKG; - } - fscrypt_err(NULL, - "Error allocating SHA-256 transform: %ld", - PTR_ERR(tfm)); - return PTR_ERR(tfm); - } - prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm); - if (prev_tfm) { - crypto_free_shash(tfm); - tfm = prev_tfm; - } - } - - { - SHASH_DESC_ON_STACK(desc, tfm); - desc->tfm = tfm; - - return crypto_shash_digest(desc, key, keysize, salt); - } -} - -static int init_essiv_generator(struct fscrypt_info *ci, const u8 *raw_key, - int keysize) -{ - int err; - struct crypto_cipher *essiv_tfm; - u8 salt[SHA256_DIGEST_SIZE]; - - if (WARN_ON(ci->ci_mode->ivsize != AES_BLOCK_SIZE)) - return -EINVAL; - - essiv_tfm = crypto_alloc_cipher("aes", 0, 0); - if (IS_ERR(essiv_tfm)) - return PTR_ERR(essiv_tfm); - - ci->ci_essiv_tfm = essiv_tfm; - - err = derive_essiv_salt(raw_key, keysize, salt); - if (err) - goto out; - - /* - * Using SHA256 to derive the salt/key will result in AES-256 being - * used for IV generation. File contents encryption will still use the - * configured keysize (AES-128) nevertheless. - */ - err = crypto_cipher_setkey(essiv_tfm, salt, sizeof(salt)); - if (err) - goto out; - -out: - memzero_explicit(salt, sizeof(salt)); - return err; -} - -/* Given the per-file key, set up the file's crypto transform object(s) */ +/* Given the per-file key, set up the file's crypto transform object */ int fscrypt_set_derived_key(struct fscrypt_info *ci, const u8 *derived_key) { - struct fscrypt_mode *mode = ci->ci_mode; - struct crypto_skcipher *ctfm; - int err; - - ctfm = fscrypt_allocate_skcipher(mode, derived_key, ci->ci_inode); - if (IS_ERR(ctfm)) - return PTR_ERR(ctfm); + struct crypto_skcipher *tfm; - ci->ci_ctfm = ctfm; + tfm = fscrypt_allocate_skcipher(ci->ci_mode, derived_key, ci->ci_inode); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); - if (mode->needs_essiv) { - err = init_essiv_generator(ci, derived_key, mode->keysize); - if (err) { - fscrypt_warn(ci->ci_inode, - "Error initializing ESSIV generator: %d", - err); - return err; - } - } + ci->ci_ctfm = tfm; + ci->ci_owns_key = true; return 0; } static int setup_per_mode_key(struct fscrypt_info *ci, - struct fscrypt_master_key *mk) + struct fscrypt_master_key *mk, + struct crypto_skcipher **tfms, + u8 hkdf_context, bool include_fs_uuid) { + const struct inode *inode = ci->ci_inode; + const struct super_block *sb = inode->i_sb; struct fscrypt_mode *mode = ci->ci_mode; u8 mode_num = mode - available_modes; struct crypto_skcipher *tfm, *prev_tfm; u8 mode_key[FSCRYPT_MAX_KEY_SIZE]; + u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; + unsigned int hkdf_infolen = 0; int err; - if (WARN_ON(mode_num >= ARRAY_SIZE(mk->mk_mode_keys))) + if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX)) return -EINVAL; /* pairs with cmpxchg() below */ - tfm = READ_ONCE(mk->mk_mode_keys[mode_num]); + tfm = READ_ONCE(tfms[mode_num]); if (likely(tfm != NULL)) goto done; BUILD_BUG_ON(sizeof(mode_num) != 1); + BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); + BUILD_BUG_ON(sizeof(hkdf_info) != 17); + hkdf_info[hkdf_infolen++] = mode_num; + if (include_fs_uuid) { + memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, + sizeof(sb->s_uuid)); + hkdf_infolen += sizeof(sb->s_uuid); + } err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, - HKDF_CONTEXT_PER_MODE_KEY, - &mode_num, sizeof(mode_num), + hkdf_context, hkdf_info, hkdf_infolen, mode_key, mode->keysize); if (err) return err; - tfm = fscrypt_allocate_skcipher(mode, mode_key, ci->ci_inode); + 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(&mk->mk_mode_keys[mode_num], NULL, tfm); + prev_tfm = cmpxchg(&tfms[mode_num], NULL, tfm); if (prev_tfm != NULL) { crypto_free_skcipher(tfm); tfm = prev_tfm; @@ -266,7 +192,19 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, ci->ci_mode->friendly_name); return -EINVAL; } - return setup_per_mode_key(ci, mk); + return setup_per_mode_key(ci, mk, mk->mk_direct_tfms, + HKDF_CONTEXT_DIRECT_KEY, false); + } else if (ci->ci_policy.v2.flags & + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { + /* + * 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. + */ + return setup_per_mode_key(ci, mk, mk->mk_iv_ino_lblk_64_tfms, + HKDF_CONTEXT_IV_INO_LBLK_64_KEY, + true); } err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, @@ -388,13 +326,10 @@ static void put_crypt_info(struct fscrypt_info *ci) if (!ci) return; - if (ci->ci_direct_key) { + if (ci->ci_direct_key) fscrypt_put_direct_key(ci->ci_direct_key); - } else if ((ci->ci_ctfm != NULL || ci->ci_essiv_tfm != NULL) && - !fscrypt_is_direct_key_policy(&ci->ci_policy)) { + else if (ci->ci_owns_key) crypto_free_skcipher(ci->ci_ctfm); - crypto_free_cipher(ci->ci_essiv_tfm); - } key = ci->ci_master_key; if (key) { @@ -415,6 +350,7 @@ static void put_crypt_info(struct fscrypt_info *ci) key_invalidate(key); key_put(key); } + memzero_explicit(ci, sizeof(*ci)); kmem_cache_free(fscrypt_info_cachep, ci); } diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c index ad1a36c370c3..5298ef22aa85 100644 --- a/fs/crypto/keysetup_v1.c +++ b/fs/crypto/keysetup_v1.c @@ -270,10 +270,6 @@ static int setup_v1_file_key_direct(struct fscrypt_info *ci, return -EINVAL; } - /* ESSIV implies 16-byte IVs which implies !DIRECT_KEY */ - if (WARN_ON(mode->needs_essiv)) - return -EINVAL; - dk = fscrypt_get_direct_key(ci, raw_master_key); if (IS_ERR(dk)) return PTR_ERR(dk); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 4072ba644595..96f528071bed 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -29,6 +29,40 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1, return !memcmp(policy1, policy2, fscrypt_policy_size(policy1)); } +static bool supported_iv_ino_lblk_64_policy( + const struct fscrypt_policy_v2 *policy, + const struct inode *inode) +{ + 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. + */ + 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); + 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) { + 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); + return false; + } + return true; +} + /** * fscrypt_supported_policy - check whether an encryption policy is supported * @@ -55,7 +89,8 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, return false; } - if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID) { + if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK | + FSCRYPT_POLICY_FLAG_DIRECT_KEY)) { fscrypt_warn(inode, "Unsupported encryption flags (0x%02x)", policy->flags); @@ -83,6 +118,10 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, return false; } + if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) && + !supported_iv_ino_lblk_64_policy(policy, inode)) + return false; + if (memchr_inv(policy->__reserved, 0, sizeof(policy->__reserved))) { fscrypt_warn(inode, diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 18426f4855f1..e23752d9a79f 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -128,13 +128,20 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, struct inode *inode) { struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); - struct inode *lower_dir_inode = ecryptfs_inode_to_lower(dir); struct dentry *lower_dir_dentry; + struct inode *lower_dir_inode; int rc; - dget(lower_dentry); - lower_dir_dentry = lock_parent(lower_dentry); - rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL); + lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent); + lower_dir_inode = d_inode(lower_dir_dentry); + inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT); + dget(lower_dentry); // don't even try to make the lower negative + if (lower_dentry->d_parent != lower_dir_dentry) + rc = -EINVAL; + else if (d_unhashed(lower_dentry)) + rc = -EINVAL; + else + rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL); if (rc) { printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc); goto out_unlock; @@ -142,10 +149,11 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, fsstack_copy_attr_times(dir, lower_dir_inode); set_nlink(inode, ecryptfs_inode_to_lower(inode)->i_nlink); inode->i_ctime = dir->i_ctime; - d_drop(dentry); out_unlock: - unlock_dir(lower_dir_dentry); dput(lower_dentry); + inode_unlock(lower_dir_inode); + if (!rc) + d_drop(dentry); return rc; } @@ -311,9 +319,9 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode) static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, struct dentry *lower_dentry) { - struct inode *inode, *lower_inode = d_inode(lower_dentry); + struct path *path = ecryptfs_dentry_to_lower_path(dentry->d_parent); + struct inode *inode, *lower_inode; struct ecryptfs_dentry_info *dentry_info; - struct vfsmount *lower_mnt; int rc = 0; dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL); @@ -322,16 +330,23 @@ static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, return ERR_PTR(-ENOMEM); } - lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent)); fsstack_copy_attr_atime(d_inode(dentry->d_parent), - d_inode(lower_dentry->d_parent)); + d_inode(path->dentry)); BUG_ON(!d_count(lower_dentry)); ecryptfs_set_dentry_private(dentry, dentry_info); - dentry_info->lower_path.mnt = lower_mnt; + dentry_info->lower_path.mnt = mntget(path->mnt); dentry_info->lower_path.dentry = lower_dentry; - if (d_really_is_negative(lower_dentry)) { + /* + * negative dentry can go positive under us here - its parent is not + * locked. That's OK and that could happen just as we return from + * ecryptfs_lookup() anyway. Just need to be careful and fetch + * ->d_inode only once - it's not stable here. + */ + lower_inode = READ_ONCE(lower_dentry->d_inode); + + if (!lower_inode) { /* We want to add because we couldn't find in lower */ d_add(dentry, NULL); return NULL; @@ -512,22 +527,30 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) { struct dentry *lower_dentry; struct dentry *lower_dir_dentry; + struct inode *lower_dir_inode; int rc; lower_dentry = ecryptfs_dentry_to_lower(dentry); - dget(dentry); - lower_dir_dentry = lock_parent(lower_dentry); - dget(lower_dentry); - rc = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry); - dput(lower_dentry); - if (!rc && d_really_is_positive(dentry)) + lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent); + lower_dir_inode = d_inode(lower_dir_dentry); + + inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT); + dget(lower_dentry); // don't even try to make the lower negative + if (lower_dentry->d_parent != lower_dir_dentry) + rc = -EINVAL; + else if (d_unhashed(lower_dentry)) + rc = -EINVAL; + else + rc = vfs_rmdir(lower_dir_inode, lower_dentry); + if (!rc) { clear_nlink(d_inode(dentry)); - fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry)); - set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink); - unlock_dir(lower_dir_dentry); + fsstack_copy_attr_times(dir, lower_dir_inode); + set_nlink(dir, lower_dir_inode->i_nlink); + } + dput(lower_dentry); + inode_unlock(lower_dir_inode); if (!rc) d_drop(dentry); - dput(dentry); return rc; } @@ -565,20 +588,22 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct dentry *lower_new_dentry; struct dentry *lower_old_dir_dentry; struct dentry *lower_new_dir_dentry; - struct dentry *trap = NULL; + struct dentry *trap; struct inode *target_inode; if (flags) return -EINVAL; + lower_old_dir_dentry = ecryptfs_dentry_to_lower(old_dentry->d_parent); + lower_new_dir_dentry = ecryptfs_dentry_to_lower(new_dentry->d_parent); + lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry); lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry); - dget(lower_old_dentry); - dget(lower_new_dentry); - lower_old_dir_dentry = dget_parent(lower_old_dentry); - lower_new_dir_dentry = dget_parent(lower_new_dentry); + target_inode = d_inode(new_dentry); + trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + dget(lower_new_dentry); rc = -EINVAL; if (lower_old_dentry->d_parent != lower_old_dir_dentry) goto out_lock; @@ -606,11 +631,8 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dir != old_dir) fsstack_copy_attr_all(old_dir, d_inode(lower_old_dir_dentry)); out_lock: - unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); - dput(lower_new_dir_dentry); - dput(lower_old_dir_dentry); dput(lower_new_dentry); - dput(lower_old_dentry); + unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); return rc; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 09bc68708d28..2dd55b172d57 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -519,26 +519,33 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, * inode is actually connected to the parent. */ err = exportfs_get_name(mnt, target_dir, nbuf, result); - if (!err) { - inode_lock(target_dir->d_inode); - nresult = lookup_one_len(nbuf, target_dir, - strlen(nbuf)); - inode_unlock(target_dir->d_inode); - if (!IS_ERR(nresult)) { - if (nresult->d_inode) { - dput(result); - result = nresult; - } else - dput(nresult); - } + if (err) { + dput(target_dir); + goto err_result; } + inode_lock(target_dir->d_inode); + nresult = lookup_one_len(nbuf, target_dir, strlen(nbuf)); + if (!IS_ERR(nresult)) { + if (unlikely(nresult->d_inode != result->d_inode)) { + dput(nresult); + nresult = ERR_PTR(-ESTALE); + } + } + inode_unlock(target_dir->d_inode); /* * At this point we are done with the parent, but it's pinned * by the child dentry anyway. */ dput(target_dir); + if (IS_ERR(nresult)) { + err = PTR_ERR(nresult); + goto err_result; + } + dput(result); + result = nresult; + /* * And finally make sure the dentry is actually acceptable * to NFSD. diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index cbb5ca830e57..ef42ab040905 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -106,3 +106,20 @@ config EXT4_DEBUG If you select Y here, then you will be able to turn on debugging with a command such as: echo 1 > /sys/module/ext4/parameters/mballoc_debug + +config EXT4_KUNIT_TESTS + bool "KUnit tests for ext4" + select EXT4_FS + depends on KUNIT + help + This builds the ext4 KUnit tests. + + KUnit tests run during boot and output the results to the debug log + in TAP format (http://testanything.org/). Only useful for kernel devs + running KUnit test harness and are not for inclusion into a production + build. + + 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. diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index b17ddc229ac5..840b91d040f1 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -13,4 +13,5 @@ ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \ ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o +ext4-$(CONFIG_EXT4_KUNIT_TESTS) += inode-test.o ext4-$(CONFIG_FS_VERITY) += verity.o diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 03db3e71676c..b3a2cc7c0252 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1678,6 +1678,7 @@ static inline bool ext4_verity_in_progress(struct inode *inode) #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200 +#define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 @@ -1779,6 +1780,7 @@ EXT4_FEATURE_COMPAT_FUNCS(xattr, EXT_ATTR) EXT4_FEATURE_COMPAT_FUNCS(resize_inode, RESIZE_INODE) EXT4_FEATURE_COMPAT_FUNCS(dir_index, DIR_INDEX) EXT4_FEATURE_COMPAT_FUNCS(sparse_super2, SPARSE_SUPER2) +EXT4_FEATURE_COMPAT_FUNCS(stable_inodes, STABLE_INODES) EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super, SPARSE_SUPER) EXT4_FEATURE_RO_COMPAT_FUNCS(large_file, LARGE_FILE) diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c new file mode 100644 index 000000000000..92a9da1774aa --- /dev/null +++ b/fs/ext4/inode-test.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test of ext4 inode that verify the seconds part of [a/c/m] + * timestamps in ext4 inode structs are decoded correctly. + */ + +#include <kunit/test.h> +#include <linux/kernel.h> +#include <linux/time64.h> + +#include "ext4.h" + +/* + * For constructing the nonnegative timestamp lower bound value. + * binary: 00000000 00000000 00000000 00000000 + */ +#define LOWER_MSB_0 0L +/* + * For constructing the nonnegative timestamp upper bound value. + * binary: 01111111 11111111 11111111 11111111 + * + */ +#define UPPER_MSB_0 0x7fffffffL +/* + * For constructing the negative timestamp lower bound value. + * binary: 10000000 00000000 00000000 00000000 + */ +#define LOWER_MSB_1 (-0x80000000L) +/* + * For constructing the negative timestamp upper bound value. + * binary: 11111111 11111111 11111111 11111111 + */ +#define UPPER_MSB_1 (-1L) +/* + * Upper bound for nanoseconds value supported by the encoding. + * binary: 00111111 11111111 11111111 11111111 + */ +#define MAX_NANOSECONDS ((1L << 30) - 1) + +#define CASE_NAME_FORMAT "%s: msb:%x lower_bound:%x extra_bits: %x" + +#define LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE\ + "1901-12-13 Lower bound of 32bit < 0 timestamp, no extra bits" +#define UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE\ + "1969-12-31 Upper bound of 32bit < 0 timestamp, no extra bits" +#define LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\ + "1970-01-01 Lower bound of 32bit >=0 timestamp, no extra bits" +#define UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\ + "2038-01-19 Upper bound of 32bit >=0 timestamp, no extra bits" +#define LOWER_BOUND_NEG_LO_1_CASE\ + "2038-01-19 Lower bound of 32bit <0 timestamp, lo extra sec bit on" +#define UPPER_BOUND_NEG_LO_1_CASE\ + "2106-02-07 Upper bound of 32bit <0 timestamp, lo extra sec bit on" +#define LOWER_BOUND_NONNEG_LO_1_CASE\ + "2106-02-07 Lower bound of 32bit >=0 timestamp, lo extra sec bit on" +#define UPPER_BOUND_NONNEG_LO_1_CASE\ + "2174-02-25 Upper bound of 32bit >=0 timestamp, lo extra sec bit on" +#define LOWER_BOUND_NEG_HI_1_CASE\ + "2174-02-25 Lower bound of 32bit <0 timestamp, hi extra sec bit on" +#define UPPER_BOUND_NEG_HI_1_CASE\ + "2242-03-16 Upper bound of 32bit <0 timestamp, hi extra sec bit on" +#define LOWER_BOUND_NONNEG_HI_1_CASE\ + "2242-03-16 Lower bound of 32bit >=0 timestamp, hi extra sec bit on" +#define UPPER_BOUND_NONNEG_HI_1_CASE\ + "2310-04-04 Upper bound of 32bit >=0 timestamp, hi extra sec bit on" +#define UPPER_BOUND_NONNEG_HI_1_NS_1_CASE\ + "2310-04-04 Upper bound of 32bit>=0 timestamp, hi extra sec bit 1. 1 ns" +#define LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE\ + "2378-04-22 Lower bound of 32bit>= timestamp. Extra sec bits 1. Max ns" +#define LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE\ + "2378-04-22 Lower bound of 32bit >=0 timestamp. All extra sec bits on" +#define UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE\ + "2446-05-10 Upper bound of 32bit >=0 timestamp. All extra sec bits on" + +struct timestamp_expectation { + const char *test_case_name; + struct timespec64 expected; + u32 extra_bits; + bool msb_set; + bool lower_bound; +}; + +static time64_t get_32bit_time(const struct timestamp_expectation * const test) +{ + if (test->msb_set) { + if (test->lower_bound) + return LOWER_MSB_1; + + return UPPER_MSB_1; + } + + if (test->lower_bound) + return LOWER_MSB_0; + return UPPER_MSB_0; +} + + +/* + * Test data is derived from the table in the Inode Timestamps section of + * Documentation/filesystems/ext4/inodes.rst. + */ +static void inode_test_xtimestamp_decoding(struct kunit *test) +{ + const struct timestamp_expectation test_data[] = { + { + .test_case_name = LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE, + .msb_set = true, + .lower_bound = true, + .extra_bits = 0, + .expected = {.tv_sec = -0x80000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE, + .msb_set = true, + .lower_bound = false, + .extra_bits = 0, + .expected = {.tv_sec = -1LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 0, + .expected = {0LL, 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 0, + .expected = {.tv_sec = 0x7fffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NEG_LO_1_CASE, + .msb_set = true, + .lower_bound = true, + .extra_bits = 1, + .expected = {.tv_sec = 0x80000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NEG_LO_1_CASE, + .msb_set = true, + .lower_bound = false, + .extra_bits = 1, + .expected = {.tv_sec = 0xffffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_LO_1_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 1, + .expected = {.tv_sec = 0x100000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_LO_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 1, + .expected = {.tv_sec = 0x17fffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NEG_HI_1_CASE, + .msb_set = true, + .lower_bound = true, + .extra_bits = 2, + .expected = {.tv_sec = 0x180000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NEG_HI_1_CASE, + .msb_set = true, + .lower_bound = false, + .extra_bits = 2, + .expected = {.tv_sec = 0x1ffffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_HI_1_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 2, + .expected = {.tv_sec = 0x200000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_HI_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 2, + .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_HI_1_NS_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 6, + .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 1L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 0xFFFFFFFF, + .expected = {.tv_sec = 0x300000000LL, + .tv_nsec = MAX_NANOSECONDS}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 3, + .expected = {.tv_sec = 0x300000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 3, + .expected = {.tv_sec = 0x37fffffffLL, .tv_nsec = 0L}, + } + }; + + struct timespec64 timestamp; + int i; + + for (i = 0; i < ARRAY_SIZE(test_data); ++i) { + timestamp.tv_sec = get_32bit_time(&test_data[i]); + ext4_decode_extra_time(×tamp, + cpu_to_le32(test_data[i].extra_bits)); + + KUNIT_EXPECT_EQ_MSG(test, + test_data[i].expected.tv_sec, + timestamp.tv_sec, + CASE_NAME_FORMAT, + test_data[i].test_case_name, + test_data[i].msb_set, + test_data[i].lower_bound, + test_data[i].extra_bits); + KUNIT_EXPECT_EQ_MSG(test, + test_data[i].expected.tv_nsec, + timestamp.tv_nsec, + CASE_NAME_FORMAT, + test_data[i].test_case_name, + test_data[i].msb_set, + test_data[i].lower_bound, + test_data[i].extra_bits); + } +} + +static struct kunit_case ext4_inode_test_cases[] = { + KUNIT_CASE(inode_test_xtimestamp_decoding), + {} +}; + +static struct kunit_suite ext4_inode_test_suite = { + .name = "ext4_inode_test", + .test_cases = ext4_inode_test_cases, +}; + +kunit_test_suite(ext4_inode_test_suite); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 516faa280ced..a7ca65177980 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5717,12 +5717,15 @@ int ext4_getattr(const struct path *path, struct kstat *stat, stat->attributes |= STATX_ATTR_IMMUTABLE; if (flags & EXT4_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; + if (flags & EXT4_VERITY_FL) + stat->attributes |= STATX_ATTR_VERITY; stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | - STATX_ATTR_NODUMP); + STATX_ATTR_NODUMP | + STATX_ATTR_VERITY); generic_fillattr(inode, stat); return 0; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dd654e53ba3d..b3cbf8622eab 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1345,6 +1345,18 @@ static bool ext4_dummy_context(struct inode *inode) return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb)); } +static bool ext4_has_stable_inodes(struct super_block *sb) +{ + return ext4_has_feature_stable_inodes(sb); +} + +static void ext4_get_ino_and_lblk_bits(struct super_block *sb, + int *ino_bits_ret, int *lblk_bits_ret) +{ + *ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count); + *lblk_bits_ret = 8 * sizeof(ext4_lblk_t); +} + static const struct fscrypt_operations ext4_cryptops = { .key_prefix = "ext4:", .get_context = ext4_get_context, @@ -1352,6 +1364,8 @@ static const struct fscrypt_operations ext4_cryptops = { .dummy_context = ext4_dummy_context, .empty_dir = ext4_empty_dir, .max_namelen = EXT4_NAME_LEN, + .has_stable_inodes = ext4_has_stable_inodes, + .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, }; #endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 29bc0a542759..6a2e5b7d8fc7 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -726,11 +726,14 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, stat->attributes |= STATX_ATTR_IMMUTABLE; if (flags & F2FS_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; + if (IS_VERITY(inode)) + stat->attributes |= STATX_ATTR_VERITY; stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | - STATX_ATTR_NODUMP); + STATX_ATTR_NODUMP | + STATX_ATTR_VERITY); generic_fillattr(inode, stat); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 808709581481..2c997f94a3b2 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1771,7 +1771,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, return -EIO; } trace_f2fs_issue_reset_zone(bdev, blkstart); - return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS); + return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, + sector, nr_sects, GFP_NOFS); } /* For conventional zones, use regular discard if supported */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1443cee15863..197ad6b314de 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2308,13 +2308,27 @@ static bool f2fs_dummy_context(struct inode *inode) return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode)); } +static bool f2fs_has_stable_inodes(struct super_block *sb) +{ + return true; +} + +static void f2fs_get_ino_and_lblk_bits(struct super_block *sb, + int *ino_bits_ret, int *lblk_bits_ret) +{ + *ino_bits_ret = 8 * sizeof(nid_t); + *lblk_bits_ret = 8 * sizeof(block_t); +} + 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, - .empty_dir = f2fs_empty_dir, - .max_namelen = F2FS_NAME_LEN, + .key_prefix = "f2fs:", + .get_context = f2fs_get_context, + .set_context = f2fs_set_context, + .dummy_context = f2fs_dummy_context, + .empty_dir = f2fs_empty_dir, + .max_namelen = F2FS_NAME_LEN, + .has_stable_inodes = f2fs_has_stable_inodes, + .get_ino_and_lblk_bits = f2fs_get_ino_and_lblk_bits, }; #endif @@ -2857,15 +2871,21 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) } #ifdef CONFIG_BLK_DEV_ZONED +static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct f2fs_dev_info *dev = data; + + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, dev->blkz_seq); + return 0; +} + static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) { struct block_device *bdev = FDEV(devi).bdev; sector_t nr_sectors = bdev->bd_part->nr_sects; - sector_t sector = 0; - struct blk_zone *zones; - unsigned int i, nr_zones; - unsigned int n = 0; - int err = -EIO; + int ret; if (!f2fs_sb_has_blkzoned(sbi)) return 0; @@ -2890,38 +2910,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (!FDEV(devi).blkz_seq) return -ENOMEM; -#define F2FS_REPORT_NR_ZONES 4096 - - zones = f2fs_kzalloc(sbi, - array_size(F2FS_REPORT_NR_ZONES, - sizeof(struct blk_zone)), - GFP_KERNEL); - if (!zones) - return -ENOMEM; - /* Get block zones type */ - while (zones && sector < nr_sectors) { - - nr_zones = F2FS_REPORT_NR_ZONES; - err = blkdev_report_zones(bdev, sector, zones, &nr_zones); - if (err) - break; - if (!nr_zones) { - err = -EIO; - break; - } - - for (i = 0; i < nr_zones; i++) { - if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(n, FDEV(devi).blkz_seq); - sector += zones[i].len; - n++; - } - } - - kvfree(zones); + ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb, + &FDEV(devi)); + if (ret < 0) + return ret; - return err; + return 0; } #endif diff --git a/fs/fcntl.c b/fs/fcntl.c index 3d40771e8e7c..41b6438bd2d9 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -261,7 +261,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) static bool rw_hint_valid(enum rw_hint hint) { switch (hint) { - case RWF_WRITE_LIFE_NOT_SET: + case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: diff --git a/fs/file.c b/fs/file.c index 3da91a112bab..b241ea7f1aa4 100644 --- a/fs/file.c +++ b/fs/file.c @@ -795,7 +795,7 @@ unsigned long __fdget_pos(unsigned int fd) unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file && !(file->f_mode & FMODE_STREAM)) { if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8461a6322039..335607b8c5c0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -576,10 +576,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, spin_unlock(&inode->i_lock); /* - * A dying wb indicates that the memcg-blkcg mapping has changed - * and a new wb is already serving the memcg. Switch immediately. + * A dying wb indicates that either the blkcg associated with the + * memcg changed or the associated memcg is dying. In the first + * case, a replacement wb should already be available and we should + * refresh the wb immediately. In the second case, trying to + * refresh will keep failing. */ - if (unlikely(wb_dying(wbc->wb))) + if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); diff --git a/fs/io-wq.c b/fs/io-wq.c new file mode 100644 index 000000000000..9174007ce107 --- /dev/null +++ b/fs/io-wq.c @@ -0,0 +1,1065 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic worker thread pool for io_uring + * + * Copyright (C) 2019 Jens Axboe + * + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/sched/signal.h> +#include <linux/mm.h> +#include <linux/mmu_context.h> +#include <linux/sched/mm.h> +#include <linux/percpu.h> +#include <linux/slab.h> +#include <linux/kthread.h> +#include <linux/rculist_nulls.h> + +#include "io-wq.h" + +#define WORKER_IDLE_TIMEOUT (5 * HZ) + +enum { + IO_WORKER_F_UP = 1, /* up and active */ + IO_WORKER_F_RUNNING = 2, /* account as running */ + IO_WORKER_F_FREE = 4, /* worker on free list */ + IO_WORKER_F_EXITING = 8, /* worker exiting */ + IO_WORKER_F_FIXED = 16, /* static idle worker */ + IO_WORKER_F_BOUND = 32, /* is doing bounded work */ +}; + +enum { + IO_WQ_BIT_EXIT = 0, /* wq exiting */ + IO_WQ_BIT_CANCEL = 1, /* cancel work on list */ +}; + +enum { + IO_WQE_FLAG_STALLED = 1, /* stalled on hash */ +}; + +/* + * One for each thread in a wqe pool + */ +struct io_worker { + refcount_t ref; + unsigned flags; + struct hlist_nulls_node nulls_node; + struct list_head all_list; + struct task_struct *task; + wait_queue_head_t wait; + struct io_wqe *wqe; + + struct io_wq_work *cur_work; + spinlock_t lock; + + struct rcu_head rcu; + struct mm_struct *mm; + struct files_struct *restore_files; +}; + +#if BITS_PER_LONG == 64 +#define IO_WQ_HASH_ORDER 6 +#else +#define IO_WQ_HASH_ORDER 5 +#endif + +struct io_wqe_acct { + unsigned nr_workers; + unsigned max_workers; + atomic_t nr_running; +}; + +enum { + IO_WQ_ACCT_BOUND, + IO_WQ_ACCT_UNBOUND, +}; + +/* + * Per-node worker thread pool + */ +struct io_wqe { + struct { + spinlock_t lock; + struct list_head work_list; + unsigned long hash_map; + unsigned flags; + } ____cacheline_aligned_in_smp; + + int node; + struct io_wqe_acct acct[2]; + + struct hlist_nulls_head free_list; + struct hlist_nulls_head busy_list; + struct list_head all_list; + + struct io_wq *wq; +}; + +/* + * Per io_wq state + */ +struct io_wq { + struct io_wqe **wqes; + unsigned long state; + unsigned nr_wqes; + + get_work_fn *get_work; + put_work_fn *put_work; + + struct task_struct *manager; + struct user_struct *user; + struct mm_struct *mm; + refcount_t refs; + struct completion done; +}; + +static bool io_worker_get(struct io_worker *worker) +{ + return refcount_inc_not_zero(&worker->ref); +} + +static void io_worker_release(struct io_worker *worker) +{ + if (refcount_dec_and_test(&worker->ref)) + wake_up_process(worker->task); +} + +/* + * Note: drops the wqe->lock if returning true! The caller must re-acquire + * the lock in that case. Some callers need to restart handling if this + * happens, so we can't just re-acquire the lock on behalf of the caller. + */ +static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) +{ + bool dropped_lock = false; + + if (current->files != worker->restore_files) { + __acquire(&wqe->lock); + spin_unlock_irq(&wqe->lock); + dropped_lock = true; + + task_lock(current); + current->files = worker->restore_files; + task_unlock(current); + } + + /* + * If we have an active mm, we need to drop the wq lock before unusing + * it. If we do, return true and let the caller retry the idle loop. + */ + if (worker->mm) { + if (!dropped_lock) { + __acquire(&wqe->lock); + spin_unlock_irq(&wqe->lock); + dropped_lock = true; + } + __set_current_state(TASK_RUNNING); + set_fs(KERNEL_DS); + unuse_mm(worker->mm); + mmput(worker->mm); + worker->mm = NULL; + } + + return dropped_lock; +} + +static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, + struct io_wq_work *work) +{ + if (work->flags & IO_WQ_WORK_UNBOUND) + return &wqe->acct[IO_WQ_ACCT_UNBOUND]; + + return &wqe->acct[IO_WQ_ACCT_BOUND]; +} + +static inline struct io_wqe_acct *io_wqe_get_acct(struct io_wqe *wqe, + struct io_worker *worker) +{ + if (worker->flags & IO_WORKER_F_BOUND) + return &wqe->acct[IO_WQ_ACCT_BOUND]; + + return &wqe->acct[IO_WQ_ACCT_UNBOUND]; +} + +static void io_worker_exit(struct io_worker *worker) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); + unsigned nr_workers; + + /* + * If we're not at zero, someone else is holding a brief reference + * to the worker. Wait for that to go away. + */ + set_current_state(TASK_INTERRUPTIBLE); + if (!refcount_dec_and_test(&worker->ref)) + schedule(); + __set_current_state(TASK_RUNNING); + + preempt_disable(); + current->flags &= ~PF_IO_WORKER; + if (worker->flags & IO_WORKER_F_RUNNING) + atomic_dec(&acct->nr_running); + if (!(worker->flags & IO_WORKER_F_BOUND)) + atomic_dec(&wqe->wq->user->processes); + worker->flags = 0; + preempt_enable(); + + spin_lock_irq(&wqe->lock); + hlist_nulls_del_rcu(&worker->nulls_node); + list_del_rcu(&worker->all_list); + if (__io_worker_unuse(wqe, worker)) { + __release(&wqe->lock); + spin_lock_irq(&wqe->lock); + } + acct->nr_workers--; + nr_workers = wqe->acct[IO_WQ_ACCT_BOUND].nr_workers + + wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers; + spin_unlock_irq(&wqe->lock); + + /* all workers gone, wq exit can proceed */ + if (!nr_workers && refcount_dec_and_test(&wqe->wq->refs)) + complete(&wqe->wq->done); + + kfree_rcu(worker, rcu); +} + +static inline bool io_wqe_run_queue(struct io_wqe *wqe) + __must_hold(wqe->lock) +{ + if (!list_empty(&wqe->work_list) && !(wqe->flags & IO_WQE_FLAG_STALLED)) + return true; + return false; +} + +/* + * Check head of free list for an available worker. If one isn't available, + * caller must wake up the wq manager to create one. + */ +static bool io_wqe_activate_free_worker(struct io_wqe *wqe) + __must_hold(RCU) +{ + struct hlist_nulls_node *n; + struct io_worker *worker; + + n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list)); + if (is_a_nulls(n)) + return false; + + worker = hlist_nulls_entry(n, struct io_worker, nulls_node); + if (io_worker_get(worker)) { + wake_up(&worker->wait); + io_worker_release(worker); + return true; + } + + return false; +} + +/* + * We need a worker. If we find a free one, we're good. If not, and we're + * below the max number of workers, wake up the manager to create one. + */ +static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) +{ + bool ret; + + /* + * Most likely an attempt to queue unbounded work on an io_wq that + * wasn't setup with any unbounded workers. + */ + WARN_ON_ONCE(!acct->max_workers); + + rcu_read_lock(); + ret = io_wqe_activate_free_worker(wqe); + rcu_read_unlock(); + + if (!ret && acct->nr_workers < acct->max_workers) + wake_up_process(wqe->wq->manager); +} + +static void io_wqe_inc_running(struct io_wqe *wqe, struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); + + atomic_inc(&acct->nr_running); +} + +static void io_wqe_dec_running(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); + + if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe)) + io_wqe_wake_worker(wqe, acct); +} + +static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) +{ + allow_kernel_signal(SIGINT); + + current->flags |= PF_IO_WORKER; + + worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + worker->restore_files = current->files; + io_wqe_inc_running(wqe, worker); +} + +/* + * Worker will start processing some work. Move it to the busy list, if + * it's currently on the freelist + */ +static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, + struct io_wq_work *work) + __must_hold(wqe->lock) +{ + bool worker_bound, work_bound; + + if (worker->flags & IO_WORKER_F_FREE) { + worker->flags &= ~IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->busy_list); + } + + /* + * If worker is moving from bound to unbound (or vice versa), then + * ensure we update the running accounting. + */ + worker_bound = (worker->flags & IO_WORKER_F_BOUND) != 0; + work_bound = (work->flags & IO_WQ_WORK_UNBOUND) == 0; + if (worker_bound != work_bound) { + io_wqe_dec_running(wqe, worker); + if (work_bound) { + worker->flags |= IO_WORKER_F_BOUND; + wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers--; + wqe->acct[IO_WQ_ACCT_BOUND].nr_workers++; + atomic_dec(&wqe->wq->user->processes); + } else { + worker->flags &= ~IO_WORKER_F_BOUND; + wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers++; + wqe->acct[IO_WQ_ACCT_BOUND].nr_workers--; + atomic_inc(&wqe->wq->user->processes); + } + io_wqe_inc_running(wqe, worker); + } +} + +/* + * No work, worker going to sleep. Move to freelist, and unuse mm if we + * have one attached. Dropping the mm may potentially sleep, so we drop + * the lock in that case and return success. Since the caller has to + * retry the loop in that case (we changed task state), we don't regrab + * the lock if we return success. + */ +static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + if (!(worker->flags & IO_WORKER_F_FREE)) { + worker->flags |= IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + } + + return __io_worker_unuse(wqe, worker); +} + +static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash) + __must_hold(wqe->lock) +{ + struct io_wq_work *work; + + list_for_each_entry(work, &wqe->work_list, list) { + /* not hashed, can run anytime */ + if (!(work->flags & IO_WQ_WORK_HASHED)) { + list_del(&work->list); + return work; + } + + /* hashed, can run if not already running */ + *hash = work->flags >> IO_WQ_HASH_SHIFT; + if (!(wqe->hash_map & BIT_ULL(*hash))) { + wqe->hash_map |= BIT_ULL(*hash); + list_del(&work->list); + return work; + } + } + + return NULL; +} + +static void io_worker_handle_work(struct io_worker *worker) + __releases(wqe->lock) +{ + struct io_wq_work *work, *old_work = NULL, *put_work = NULL; + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + do { + unsigned hash = -1U; + + /* + * If we got some work, mark us as busy. If we didn't, but + * the list isn't empty, it means we stalled on hashed work. + * Mark us stalled so we don't keep looking for work when we + * can't make progress, any work completion or insertion will + * clear the stalled flag. + */ + work = io_get_next_work(wqe, &hash); + if (work) + __io_worker_busy(wqe, worker, work); + else if (!list_empty(&wqe->work_list)) + wqe->flags |= IO_WQE_FLAG_STALLED; + + spin_unlock_irq(&wqe->lock); + if (put_work && wq->put_work) + wq->put_work(old_work); + if (!work) + break; +next: + /* flush any pending signals before assigning new work */ + if (signal_pending(current)) + flush_signals(current); + + spin_lock_irq(&worker->lock); + worker->cur_work = work; + spin_unlock_irq(&worker->lock); + + if ((work->flags & IO_WQ_WORK_NEEDS_FILES) && + current->files != work->files) { + task_lock(current); + current->files = work->files; + task_unlock(current); + } + if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm && + wq->mm && mmget_not_zero(wq->mm)) { + use_mm(wq->mm); + set_fs(USER_DS); + worker->mm = wq->mm; + } + if (test_bit(IO_WQ_BIT_CANCEL, &wq->state)) + work->flags |= IO_WQ_WORK_CANCEL; + if (worker->mm) + work->flags |= IO_WQ_WORK_HAS_MM; + + if (wq->get_work && !(work->flags & IO_WQ_WORK_INTERNAL)) { + put_work = work; + wq->get_work(work); + } + + old_work = work; + work->func(&work); + + spin_lock_irq(&worker->lock); + worker->cur_work = NULL; + spin_unlock_irq(&worker->lock); + + spin_lock_irq(&wqe->lock); + + if (hash != -1U) { + wqe->hash_map &= ~BIT_ULL(hash); + wqe->flags &= ~IO_WQE_FLAG_STALLED; + } + if (work && work != old_work) { + spin_unlock_irq(&wqe->lock); + + if (put_work && wq->put_work) { + wq->put_work(put_work); + put_work = NULL; + } + + /* dependent work not hashed */ + hash = -1U; + goto next; + } + } while (1); +} + +static int io_wqe_worker(void *data) +{ + struct io_worker *worker = data; + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + DEFINE_WAIT(wait); + + io_worker_start(wqe, worker); + + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + prepare_to_wait(&worker->wait, &wait, TASK_INTERRUPTIBLE); + + spin_lock_irq(&wqe->lock); + if (io_wqe_run_queue(wqe)) { + __set_current_state(TASK_RUNNING); + io_worker_handle_work(worker); + continue; + } + /* drops the lock on success, retry */ + if (__io_worker_idle(wqe, worker)) { + __release(&wqe->lock); + continue; + } + spin_unlock_irq(&wqe->lock); + if (signal_pending(current)) + flush_signals(current); + if (schedule_timeout(WORKER_IDLE_TIMEOUT)) + continue; + /* timed out, exit unless we're the fixed worker */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || + !(worker->flags & IO_WORKER_F_FIXED)) + break; + } + + finish_wait(&worker->wait, &wait); + + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + spin_lock_irq(&wqe->lock); + if (!list_empty(&wqe->work_list)) + io_worker_handle_work(worker); + else + spin_unlock_irq(&wqe->lock); + } + + io_worker_exit(worker); + return 0; +} + +/* + * Called when a worker is scheduled in. Mark us as currently running. + */ +void io_wq_worker_running(struct task_struct *tsk) +{ + struct io_worker *worker = kthread_data(tsk); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (worker->flags & IO_WORKER_F_RUNNING) + return; + worker->flags |= IO_WORKER_F_RUNNING; + io_wqe_inc_running(wqe, worker); +} + +/* + * Called when worker is going to sleep. If there are no workers currently + * running and we have work pending, wake up a free one or have the manager + * set one up. + */ +void io_wq_worker_sleeping(struct task_struct *tsk) +{ + struct io_worker *worker = kthread_data(tsk); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (!(worker->flags & IO_WORKER_F_RUNNING)) + return; + + worker->flags &= ~IO_WORKER_F_RUNNING; + + spin_lock_irq(&wqe->lock); + io_wqe_dec_running(wqe, worker); + spin_unlock_irq(&wqe->lock); +} + +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +{ + struct io_wqe_acct *acct =&wqe->acct[index]; + struct io_worker *worker; + + worker = kcalloc_node(1, sizeof(*worker), GFP_KERNEL, wqe->node); + if (!worker) + return; + + refcount_set(&worker->ref, 1); + worker->nulls_node.pprev = NULL; + init_waitqueue_head(&worker->wait); + worker->wqe = wqe; + spin_lock_init(&worker->lock); + + worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node, + "io_wqe_worker-%d/%d", index, wqe->node); + if (IS_ERR(worker->task)) { + kfree(worker); + return; + } + + spin_lock_irq(&wqe->lock); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + list_add_tail_rcu(&worker->all_list, &wqe->all_list); + worker->flags |= IO_WORKER_F_FREE; + if (index == IO_WQ_ACCT_BOUND) + worker->flags |= IO_WORKER_F_BOUND; + if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND)) + worker->flags |= IO_WORKER_F_FIXED; + acct->nr_workers++; + spin_unlock_irq(&wqe->lock); + + if (index == IO_WQ_ACCT_UNBOUND) + atomic_inc(&wq->user->processes); + + wake_up_process(worker->task); +} + +static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index) + __must_hold(wqe->lock) +{ + struct io_wqe_acct *acct = &wqe->acct[index]; + + /* always ensure we have one bounded worker */ + if (index == IO_WQ_ACCT_BOUND && !acct->nr_workers) + return true; + /* if we have available workers or no work, no need */ + if (!hlist_nulls_empty(&wqe->free_list) || !io_wqe_run_queue(wqe)) + return false; + return acct->nr_workers < acct->max_workers; +} + +/* + * Manager thread. Tasked with creating new workers, if we need them. + */ +static int io_wq_manager(void *data) +{ + struct io_wq *wq = data; + + while (!kthread_should_stop()) { + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + bool fork_worker[2] = { false, false }; + + spin_lock_irq(&wqe->lock); + if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND)) + fork_worker[IO_WQ_ACCT_BOUND] = true; + if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND)) + fork_worker[IO_WQ_ACCT_UNBOUND] = true; + spin_unlock_irq(&wqe->lock); + if (fork_worker[IO_WQ_ACCT_BOUND]) + create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND); + if (fork_worker[IO_WQ_ACCT_UNBOUND]) + create_io_worker(wq, wqe, IO_WQ_ACCT_UNBOUND); + } + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ); + } + + return 0; +} + +static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct, + struct io_wq_work *work) +{ + bool free_worker; + + if (!(work->flags & IO_WQ_WORK_UNBOUND)) + return true; + if (atomic_read(&acct->nr_running)) + return true; + + rcu_read_lock(); + free_worker = !hlist_nulls_empty(&wqe->free_list); + rcu_read_unlock(); + if (free_worker) + return true; + + if (atomic_read(&wqe->wq->user->processes) >= acct->max_workers && + !(capable(CAP_SYS_RESOURCE) || capable(CAP_SYS_ADMIN))) + return false; + + return true; +} + +static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned long flags; + + /* + * Do early check to see if we need a new unbound worker, and if we do, + * if we're allowed to do so. This isn't 100% accurate as there's a + * gap between this check and incrementing the value, but that's OK. + * It's close enough to not be an issue, fork() has the same delay. + */ + if (unlikely(!io_wq_can_queue(wqe, acct, work))) { + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + return; + } + + spin_lock_irqsave(&wqe->lock, flags); + list_add_tail(&work->list, &wqe->work_list); + wqe->flags &= ~IO_WQE_FLAG_STALLED; + spin_unlock_irqrestore(&wqe->lock, flags); + + if (!atomic_read(&acct->nr_running)) + io_wqe_wake_worker(wqe, acct); +} + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + + io_wqe_enqueue(wqe, work); +} + +/* + * Enqueue work, hashed by some key. Work items that hash to the same value + * will not be done in parallel. Used to limit concurrent writes, generally + * hashed by inode. + */ +void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + unsigned bit; + + + bit = hash_ptr(val, IO_WQ_HASH_ORDER); + work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); + io_wqe_enqueue(wqe, work); +} + +static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) +{ + send_sig(SIGINT, worker->task, 1); + return false; +} + +/* + * Iterate the passed in list and call the specific function for each + * worker that isn't exiting + */ +static bool io_wq_for_each_worker(struct io_wqe *wqe, + bool (*func)(struct io_worker *, void *), + void *data) +{ + struct io_worker *worker; + bool ret = false; + + list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { + if (io_worker_get(worker)) { + ret = func(worker, data); + io_worker_release(worker); + if (ret) + break; + } + } + + return ret; +} + +void io_wq_cancel_all(struct io_wq *wq) +{ + int i; + + set_bit(IO_WQ_BIT_CANCEL, &wq->state); + + /* + * Browse both lists, as there's a gap between handing work off + * to a worker and the worker putting itself on the busy_list + */ + rcu_read_lock(); + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL); + } + rcu_read_unlock(); +} + +struct io_cb_cancel_data { + struct io_wqe *wqe; + work_cancel_fn *cancel; + void *caller_data; +}; + +static bool io_work_cancel(struct io_worker *worker, void *cancel_data) +{ + struct io_cb_cancel_data *data = cancel_data; + unsigned long flags; + bool ret = false; + + /* + * Hold the lock to avoid ->cur_work going out of scope, caller + * may dereference the passed in work. + */ + spin_lock_irqsave(&worker->lock, flags); + if (worker->cur_work && + data->cancel(worker->cur_work, data->caller_data)) { + send_sig(SIGINT, worker->task, 1); + ret = true; + } + spin_unlock_irqrestore(&worker->lock, flags); + + return ret; +} + +static enum io_wq_cancel io_wqe_cancel_cb_work(struct io_wqe *wqe, + work_cancel_fn *cancel, + void *cancel_data) +{ + struct io_cb_cancel_data data = { + .wqe = wqe, + .cancel = cancel, + .caller_data = cancel_data, + }; + struct io_wq_work *work; + unsigned long flags; + bool found = false; + + spin_lock_irqsave(&wqe->lock, flags); + list_for_each_entry(work, &wqe->work_list, list) { + if (cancel(work, cancel_data)) { + list_del(&work->list); + found = true; + break; + } + } + spin_unlock_irqrestore(&wqe->lock, flags); + + if (found) { + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + return IO_WQ_CANCEL_OK; + } + + rcu_read_lock(); + found = io_wq_for_each_worker(wqe, io_work_cancel, &data); + rcu_read_unlock(); + return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND; +} + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data) +{ + enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + ret = io_wqe_cancel_cb_work(wqe, cancel, data); + if (ret != IO_WQ_CANCEL_NOTFOUND) + break; + } + + return ret; +} + +static bool io_wq_worker_cancel(struct io_worker *worker, void *data) +{ + struct io_wq_work *work = data; + unsigned long flags; + bool ret = false; + + if (worker->cur_work != work) + return false; + + spin_lock_irqsave(&worker->lock, flags); + if (worker->cur_work == work) { + send_sig(SIGINT, worker->task, 1); + ret = true; + } + spin_unlock_irqrestore(&worker->lock, flags); + + return ret; +} + +static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, + struct io_wq_work *cwork) +{ + struct io_wq_work *work; + unsigned long flags; + bool found = false; + + cwork->flags |= IO_WQ_WORK_CANCEL; + + /* + * First check pending list, if we're lucky we can just remove it + * from there. CANCEL_OK means that the work is returned as-new, + * no completion will be posted for it. + */ + spin_lock_irqsave(&wqe->lock, flags); + list_for_each_entry(work, &wqe->work_list, list) { + if (work == cwork) { + list_del(&work->list); + found = true; + break; + } + } + spin_unlock_irqrestore(&wqe->lock, flags); + + if (found) { + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + return IO_WQ_CANCEL_OK; + } + + /* + * Now check if a free (going busy) or busy worker has the work + * currently running. If we find it there, we'll return CANCEL_RUNNING + * as an indication that we attempte to signal cancellation. The + * completion will run normally in this case. + */ + rcu_read_lock(); + found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, cwork); + rcu_read_unlock(); + return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND; +} + +enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork) +{ + enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + ret = io_wqe_cancel_work(wqe, cwork); + if (ret != IO_WQ_CANCEL_NOTFOUND) + break; + } + + return ret; +} + +struct io_wq_flush_data { + struct io_wq_work work; + struct completion done; +}; + +static void io_wq_flush_func(struct io_wq_work **workptr) +{ + struct io_wq_work *work = *workptr; + struct io_wq_flush_data *data; + + data = container_of(work, struct io_wq_flush_data, work); + complete(&data->done); +} + +/* + * Doesn't wait for previously queued work to finish. When this completes, + * it just means that previously queued work was started. + */ +void io_wq_flush(struct io_wq *wq) +{ + struct io_wq_flush_data data; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + init_completion(&data.done); + INIT_IO_WORK(&data.work, io_wq_flush_func); + data.work.flags |= IO_WQ_WORK_INTERNAL; + io_wqe_enqueue(wqe, &data.work); + wait_for_completion(&data.done); + } +} + +struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm, + struct user_struct *user, get_work_fn *get_work, + put_work_fn *put_work) +{ + int ret = -ENOMEM, i, node; + struct io_wq *wq; + + wq = kcalloc(1, sizeof(*wq), GFP_KERNEL); + if (!wq) + return ERR_PTR(-ENOMEM); + + wq->nr_wqes = num_online_nodes(); + wq->wqes = kcalloc(wq->nr_wqes, sizeof(struct io_wqe *), GFP_KERNEL); + if (!wq->wqes) { + kfree(wq); + return ERR_PTR(-ENOMEM); + } + + wq->get_work = get_work; + wq->put_work = put_work; + + /* caller must already hold a reference to this */ + wq->user = user; + + i = 0; + refcount_set(&wq->refs, wq->nr_wqes); + for_each_online_node(node) { + struct io_wqe *wqe; + + wqe = kcalloc_node(1, sizeof(struct io_wqe), GFP_KERNEL, node); + if (!wqe) + break; + wq->wqes[i] = wqe; + wqe->node = node; + wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; + atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0); + if (user) { + wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers = + task_rlimit(current, RLIMIT_NPROC); + } + atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0); + wqe->node = node; + wqe->wq = wq; + spin_lock_init(&wqe->lock); + INIT_LIST_HEAD(&wqe->work_list); + INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); + INIT_HLIST_NULLS_HEAD(&wqe->busy_list, 1); + INIT_LIST_HEAD(&wqe->all_list); + + i++; + } + + init_completion(&wq->done); + + if (i != wq->nr_wqes) + goto err; + + /* caller must have already done mmgrab() on this mm */ + wq->mm = mm; + + wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager"); + if (!IS_ERR(wq->manager)) { + wake_up_process(wq->manager); + return wq; + } + + ret = PTR_ERR(wq->manager); + wq->manager = NULL; +err: + complete(&wq->done); + io_wq_destroy(wq); + return ERR_PTR(ret); +} + +static bool io_wq_worker_wake(struct io_worker *worker, void *data) +{ + wake_up_process(worker->task); + return false; +} + +void io_wq_destroy(struct io_wq *wq) +{ + int i; + + if (wq->manager) { + set_bit(IO_WQ_BIT_EXIT, &wq->state); + kthread_stop(wq->manager); + } + + rcu_read_lock(); + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + if (!wqe) + continue; + io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL); + } + rcu_read_unlock(); + + wait_for_completion(&wq->done); + + for (i = 0; i < wq->nr_wqes; i++) + kfree(wq->wqes[i]); + kfree(wq->wqes); + kfree(wq); +} diff --git a/fs/io-wq.h b/fs/io-wq.h new file mode 100644 index 000000000000..4b29f922f80c --- /dev/null +++ b/fs/io-wq.h @@ -0,0 +1,74 @@ +#ifndef INTERNAL_IO_WQ_H +#define INTERNAL_IO_WQ_H + +struct io_wq; + +enum { + IO_WQ_WORK_CANCEL = 1, + IO_WQ_WORK_HAS_MM = 2, + IO_WQ_WORK_HASHED = 4, + IO_WQ_WORK_NEEDS_USER = 8, + IO_WQ_WORK_NEEDS_FILES = 16, + IO_WQ_WORK_UNBOUND = 32, + IO_WQ_WORK_INTERNAL = 64, + + IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ +}; + +enum io_wq_cancel { + IO_WQ_CANCEL_OK, /* cancelled before started */ + IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */ + IO_WQ_CANCEL_NOTFOUND, /* work not found */ +}; + +struct io_wq_work { + struct list_head list; + void (*func)(struct io_wq_work **); + unsigned flags; + struct files_struct *files; +}; + +#define INIT_IO_WORK(work, _func) \ + do { \ + (work)->func = _func; \ + (work)->flags = 0; \ + (work)->files = NULL; \ + } while (0) \ + +typedef void (get_work_fn)(struct io_wq_work *); +typedef void (put_work_fn)(struct io_wq_work *); + +struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm, + struct user_struct *user, + get_work_fn *get_work, put_work_fn *put_work); +void io_wq_destroy(struct io_wq *wq); + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); +void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val); +void io_wq_flush(struct io_wq *wq); + +void io_wq_cancel_all(struct io_wq *wq); +enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork); + +typedef bool (work_cancel_fn)(struct io_wq_work *, void *); + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data); + +#if defined(CONFIG_IO_WQ) +extern void io_wq_worker_sleeping(struct task_struct *); +extern void io_wq_worker_running(struct task_struct *); +#else +static inline void io_wq_worker_sleeping(struct task_struct *tsk) +{ +} +static inline void io_wq_worker_running(struct task_struct *tsk) +{ +} +#endif + +static inline bool io_wq_current_is_worker(void) +{ + return in_task() && (current->flags & PF_IO_WORKER); +} +#endif diff --git a/fs/io_uring.c b/fs/io_uring.c index f9a38998f2fc..4c030a92de79 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -56,7 +56,6 @@ #include <linux/mmu_context.h> #include <linux/percpu.h> #include <linux/slab.h> -#include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/blkdev.h> #include <linux/bvec.h> @@ -71,12 +70,24 @@ #include <linux/sizes.h> #include <linux/hugetlb.h> +#define CREATE_TRACE_POINTS +#include <trace/events/io_uring.h> + #include <uapi/linux/io_uring.h> #include "internal.h" +#include "io-wq.h" #define IORING_MAX_ENTRIES 32768 -#define IORING_MAX_FIXED_FILES 1024 +#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) + +/* + * Shift of 9 is 512 entries, or exactly one page on 64-bit archs + */ +#define IORING_FILE_TABLE_SHIFT 9 +#define IORING_MAX_FILES_TABLE (1U << IORING_FILE_TABLE_SHIFT) +#define IORING_FILE_TABLE_MASK (IORING_MAX_FILES_TABLE - 1) +#define IORING_MAX_FIXED_FILES (64 * IORING_MAX_FILES_TABLE) struct io_uring { u32 head ____cacheline_aligned_in_smp; @@ -161,14 +172,8 @@ struct io_mapped_ubuf { unsigned int nr_bvecs; }; -struct async_list { - spinlock_t lock; - atomic_t cnt; - struct list_head list; - - struct file *file; - off_t io_start; - size_t io_len; +struct fixed_file_table { + struct file **files; }; struct io_ring_ctx { @@ -180,6 +185,7 @@ struct io_ring_ctx { unsigned int flags; bool compat; bool account_mem; + bool cq_overflow_flushed; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -198,38 +204,30 @@ struct io_ring_ctx { unsigned sq_mask; unsigned sq_thread_idle; unsigned cached_sq_dropped; + atomic_t cached_cq_overflow; struct io_uring_sqe *sq_sqes; struct list_head defer_list; struct list_head timeout_list; + struct list_head cq_overflow_list; + + wait_queue_head_t inflight_wait; } ____cacheline_aligned_in_smp; + struct io_rings *rings; + /* IO offload */ - struct workqueue_struct *sqo_wq[2]; + struct io_wq *io_wq; struct task_struct *sqo_thread; /* if using sq thread polling */ struct mm_struct *sqo_mm; wait_queue_head_t sqo_wait; - struct completion sqo_thread_started; - - struct { - unsigned cached_cq_tail; - atomic_t cached_cq_overflow; - unsigned cq_entries; - unsigned cq_mask; - struct wait_queue_head cq_wait; - struct fasync_struct *cq_fasync; - struct eventfd_ctx *cq_ev_fd; - atomic_t cq_timeouts; - } ____cacheline_aligned_in_smp; - - struct io_rings *rings; /* * If used, fixed file set. Writers must ensure that ->refs is dead, * readers must ensure that ->refs is alive as long as the file* is * used. Only updated through io_uring_register(2). */ - struct file **user_files; + struct fixed_file_table *file_table; unsigned nr_user_files; /* if used, fixed mapped user buffers */ @@ -238,7 +236,25 @@ struct io_ring_ctx { struct user_struct *user; - struct completion ctx_done; + /* 0 is for ctx quiesce/reinit/free, 1 is for sqo_thread started */ + struct completion *completions; + + /* if all else fails... */ + struct io_kiocb *fallback_req; + +#if defined(CONFIG_UNIX) + struct socket *ring_sock; +#endif + + struct { + unsigned cached_cq_tail; + unsigned cq_entries; + unsigned cq_mask; + atomic_t cq_timeouts; + struct wait_queue_head cq_wait; + struct fasync_struct *cq_fasync; + struct eventfd_ctx *cq_ev_fd; + } ____cacheline_aligned_in_smp; struct { struct mutex uring_lock; @@ -255,22 +271,20 @@ struct io_ring_ctx { * manipulate the list, hence no extra locking is needed there. */ struct list_head poll_list; - struct list_head cancel_list; - } ____cacheline_aligned_in_smp; + struct rb_root cancel_tree; - struct async_list pending_async[2]; - -#if defined(CONFIG_UNIX) - struct socket *ring_sock; -#endif + spinlock_t inflight_lock; + struct list_head inflight_list; + } ____cacheline_aligned_in_smp; }; struct sqe_submit { const struct io_uring_sqe *sqe; - unsigned short index; + struct file *ring_file; + int ring_fd; u32 sequence; bool has_user; - bool needs_lock; + bool in_async; bool needs_fixed_file; }; @@ -309,7 +323,10 @@ struct io_kiocb { struct sqe_submit submit; struct io_ring_ctx *ctx; - struct list_head list; + union { + struct list_head list; + struct rb_node rb_node; + }; struct list_head link_list; unsigned int flags; refcount_t refs; @@ -320,17 +337,22 @@ struct io_kiocb { #define REQ_F_IO_DRAIN 16 /* drain existing IO first */ #define REQ_F_IO_DRAINED 32 /* drain done */ #define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_LINK_DONE 128 /* linked sqes done */ +#define REQ_F_LINK_TIMEOUT 128 /* has linked timeout */ #define REQ_F_FAIL_LINK 256 /* fail rest of links */ #define REQ_F_SHADOW_DRAIN 512 /* link-drain shadow req */ #define REQ_F_TIMEOUT 1024 /* timeout request */ #define REQ_F_ISREG 2048 /* regular file */ #define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */ +#define REQ_F_TIMEOUT_NOSEQ 8192 /* no timeout sequence */ +#define REQ_F_INFLIGHT 16384 /* on inflight list */ +#define REQ_F_COMP_LOCKED 32768 /* completion under lock */ u64 user_data; u32 result; u32 sequence; - struct work_struct work; + struct list_head inflight_entry; + + struct io_wq_work work; }; #define IO_PLUG_THRESHOLD 2 @@ -356,10 +378,11 @@ struct io_submit_state { unsigned int ios_left; }; -static void io_sq_wq_submit_work(struct work_struct *work); -static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, - long res); +static void io_wq_submit_work(struct io_wq_work **workptr); +static void io_cqring_fill_event(struct io_kiocb *req, long res); static void __io_free_req(struct io_kiocb *req); +static void io_put_req(struct io_kiocb *req); +static void io_double_put_req(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -382,57 +405,67 @@ static void io_ring_ctx_ref_free(struct percpu_ref *ref) { struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); - complete(&ctx->ctx_done); + complete(&ctx->completions[0]); } static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; - int i; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; + ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL); + if (!ctx->fallback_req) + goto err; + + ctx->completions = kmalloc(2 * sizeof(struct completion), GFP_KERNEL); + if (!ctx->completions) + goto err; + if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { - kfree(ctx); - return NULL; - } + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) + goto err; ctx->flags = p->flags; init_waitqueue_head(&ctx->cq_wait); - init_completion(&ctx->ctx_done); - init_completion(&ctx->sqo_thread_started); + INIT_LIST_HEAD(&ctx->cq_overflow_list); + init_completion(&ctx->completions[0]); + init_completion(&ctx->completions[1]); mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->wait); - for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) { - spin_lock_init(&ctx->pending_async[i].lock); - INIT_LIST_HEAD(&ctx->pending_async[i].list); - atomic_set(&ctx->pending_async[i].cnt, 0); - } spin_lock_init(&ctx->completion_lock); INIT_LIST_HEAD(&ctx->poll_list); - INIT_LIST_HEAD(&ctx->cancel_list); + ctx->cancel_tree = RB_ROOT; INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); + init_waitqueue_head(&ctx->inflight_wait); + spin_lock_init(&ctx->inflight_lock); + INIT_LIST_HEAD(&ctx->inflight_list); return ctx; +err: + if (ctx->fallback_req) + kmem_cache_free(req_cachep, ctx->fallback_req); + kfree(ctx->completions); + kfree(ctx); + return NULL; } -static inline bool __io_sequence_defer(struct io_ring_ctx *ctx, - struct io_kiocb *req) +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); } -static inline bool io_sequence_defer(struct io_ring_ctx *ctx, - struct io_kiocb *req) +static inline bool req_need_defer(struct io_kiocb *req) { - if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) - return false; + if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN) + return __req_need_defer(req); - return __io_sequence_defer(ctx, req); + return false; } static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) @@ -440,7 +473,7 @@ static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) struct io_kiocb *req; req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list); - if (req && !io_sequence_defer(ctx, req)) { + if (req && !req_need_defer(req)) { list_del_init(&req->list); return req; } @@ -453,9 +486,13 @@ static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx) struct io_kiocb *req; req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list); - if (req && !__io_sequence_defer(ctx, req)) { - list_del_init(&req->list); - return req; + if (req) { + if (req->flags & REQ_F_TIMEOUT_NOSEQ) + return NULL; + if (!__req_need_defer(req)) { + list_del_init(&req->list); + return req; + } } return NULL; @@ -476,21 +513,59 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx) } } -static inline void io_queue_async_work(struct io_ring_ctx *ctx, - struct io_kiocb *req) +static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) +{ + u8 opcode = READ_ONCE(sqe->opcode); + + return !(opcode == IORING_OP_READ_FIXED || + opcode == IORING_OP_WRITE_FIXED); +} + +static inline bool io_prep_async_work(struct io_kiocb *req) { - int rw = 0; + bool do_hashed = false; if (req->submit.sqe) { switch (req->submit.sqe->opcode) { case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: - rw = !(req->rw.ki_flags & IOCB_DIRECT); + do_hashed = true; + /* fall-through */ + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_SENDMSG: + case IORING_OP_RECVMSG: + case IORING_OP_ACCEPT: + case IORING_OP_POLL_ADD: + /* + * We know REQ_F_ISREG is not set on some of these + * opcodes, but this enables us to keep the check in + * just one place. + */ + if (!(req->flags & REQ_F_ISREG)) + req->work.flags |= IO_WQ_WORK_UNBOUND; break; } + if (io_sqe_needs_user(req->submit.sqe)) + req->work.flags |= IO_WQ_WORK_NEEDS_USER; } - queue_work(ctx->sqo_wq[rw], &req->work); + return do_hashed; +} + +static inline void io_queue_async_work(struct io_kiocb *req) +{ + bool do_hashed = io_prep_async_work(req); + struct io_ring_ctx *ctx = req->ctx; + + trace_io_uring_queue_async_work(ctx, do_hashed, req, &req->work, + req->flags); + if (!do_hashed) { + io_wq_enqueue(ctx->io_wq, &req->work); + } else { + io_wq_enqueue_hashed(ctx->io_wq, &req->work, + file_inode(req->file)); + } } static void io_kill_timeout(struct io_kiocb *req) @@ -500,9 +575,9 @@ static void io_kill_timeout(struct io_kiocb *req) ret = hrtimer_try_to_cancel(&req->timeout.timer); if (ret != -1) { atomic_inc(&req->ctx->cq_timeouts); - list_del(&req->list); - io_cqring_fill_event(req->ctx, req->user_data, 0); - __io_free_req(req); + list_del_init(&req->list); + io_cqring_fill_event(req, 0); + io_put_req(req); } } @@ -532,7 +607,7 @@ static void io_commit_cqring(struct io_ring_ctx *ctx) continue; } req->flags |= REQ_F_IO_DRAINED; - io_queue_async_work(ctx, req); + io_queue_async_work(req); } } @@ -554,10 +629,73 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) return &rings->cqes[tail & ctx->cq_mask]; } -static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, - long res) +static void io_cqring_ev_posted(struct io_ring_ctx *ctx) +{ + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); + if (waitqueue_active(&ctx->sqo_wait)) + wake_up(&ctx->sqo_wait); + if (ctx->cq_ev_fd) + eventfd_signal(ctx->cq_ev_fd, 1); +} + +static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { + struct io_rings *rings = ctx->rings; struct io_uring_cqe *cqe; + struct io_kiocb *req; + unsigned long flags; + LIST_HEAD(list); + + if (!force) { + if (list_empty_careful(&ctx->cq_overflow_list)) + return; + if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) == + rings->cq_ring_entries)) + return; + } + + spin_lock_irqsave(&ctx->completion_lock, flags); + + /* if force is set, the ring is going away. always drop after that */ + if (force) + ctx->cq_overflow_flushed = true; + + while (!list_empty(&ctx->cq_overflow_list)) { + cqe = io_get_cqring(ctx); + if (!cqe && !force) + break; + + req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb, + list); + list_move(&req->list, &list); + if (cqe) { + WRITE_ONCE(cqe->user_data, req->user_data); + WRITE_ONCE(cqe->res, req->result); + WRITE_ONCE(cqe->flags, 0); + } else { + WRITE_ONCE(ctx->rings->cq_overflow, + atomic_inc_return(&ctx->cached_cq_overflow)); + } + } + + io_commit_cqring(ctx); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + io_cqring_ev_posted(ctx); + + while (!list_empty(&list)) { + req = list_first_entry(&list, struct io_kiocb, list); + list_del(&req->list); + io_put_req(req); + } +} + +static void io_cqring_fill_event(struct io_kiocb *req, long res) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_cqe *cqe; + + trace_io_uring_complete(ctx, req->user_data, res); /* * If we can't get a cq entry, userspace overflowed the @@ -565,39 +703,50 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, * the ring. */ cqe = io_get_cqring(ctx); - if (cqe) { - WRITE_ONCE(cqe->user_data, ki_user_data); + if (likely(cqe)) { + WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, 0); - } else { + } else if (ctx->cq_overflow_flushed) { WRITE_ONCE(ctx->rings->cq_overflow, atomic_inc_return(&ctx->cached_cq_overflow)); + } else { + refcount_inc(&req->refs); + req->result = res; + list_add_tail(&req->list, &ctx->cq_overflow_list); } } -static void io_cqring_ev_posted(struct io_ring_ctx *ctx) -{ - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); - if (waitqueue_active(&ctx->sqo_wait)) - wake_up(&ctx->sqo_wait); - if (ctx->cq_ev_fd) - eventfd_signal(ctx->cq_ev_fd, 1); -} - -static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data, - long res) +static void io_cqring_add_event(struct io_kiocb *req, long res) { + struct io_ring_ctx *ctx = req->ctx; unsigned long flags; spin_lock_irqsave(&ctx->completion_lock, flags); - io_cqring_fill_event(ctx, user_data, res); + io_cqring_fill_event(req, res); io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); } +static inline bool io_is_fallback_req(struct io_kiocb *req) +{ + return req == (struct io_kiocb *) + ((unsigned long) req->ctx->fallback_req & ~1UL); +} + +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)) + return req; + + return NULL; +} + static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, struct io_submit_state *state) { @@ -610,7 +759,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, if (!state) { req = kmem_cache_alloc(req_cachep, gfp); if (unlikely(!req)) - goto out; + goto fallback; } else if (!state->free_reqs) { size_t sz; int ret; @@ -625,7 +774,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, if (unlikely(ret <= 0)) { state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); if (!state->reqs[0]) - goto out; + goto fallback; ret = 1; } state->free_reqs = ret - 1; @@ -637,14 +786,19 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, state->cur_req++; } +got_it: req->file = NULL; req->ctx = ctx; req->flags = 0; /* one is dropped after submission, the other at completion */ refcount_set(&req->refs, 2); req->result = 0; + INIT_IO_WORK(&req->work, io_wq_submit_work); return req; -out: +fallback: + req = io_get_fallback_req(ctx); + if (req) + goto got_it; percpu_ref_put(&ctx->refs); return NULL; } @@ -660,15 +814,48 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr) static void __io_free_req(struct io_kiocb *req) { + struct io_ring_ctx *ctx = req->ctx; + if (req->file && !(req->flags & REQ_F_FIXED_FILE)) fput(req->file); - percpu_ref_put(&req->ctx->refs); - kmem_cache_free(req_cachep, req); + if (req->flags & REQ_F_INFLIGHT) { + unsigned long flags; + + spin_lock_irqsave(&ctx->inflight_lock, flags); + list_del(&req->inflight_entry); + if (waitqueue_active(&ctx->inflight_wait)) + wake_up(&ctx->inflight_wait); + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + } + percpu_ref_put(&ctx->refs); + if (likely(!io_is_fallback_req(req))) + kmem_cache_free(req_cachep, req); + else + clear_bit_unlock(0, (unsigned long *) ctx->fallback_req); +} + +static bool io_link_cancel_timeout(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + ret = hrtimer_try_to_cancel(&req->timeout.timer); + if (ret != -1) { + io_cqring_fill_event(req, -ECANCELED); + io_commit_cqring(ctx); + req->flags &= ~REQ_F_LINK; + io_put_req(req); + return true; + } + + return false; } -static void io_req_link_next(struct io_kiocb *req) +static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr) { + struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *nxt; + bool wake_ev = false; /* * The list should never be empty when we are called here. But could @@ -676,18 +863,35 @@ static void io_req_link_next(struct io_kiocb *req) * safe side. */ nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list); - if (nxt) { - list_del(&nxt->list); + while (nxt) { + list_del_init(&nxt->list); if (!list_empty(&req->link_list)) { INIT_LIST_HEAD(&nxt->link_list); list_splice(&req->link_list, &nxt->link_list); nxt->flags |= REQ_F_LINK; } - nxt->flags |= REQ_F_LINK_DONE; - INIT_WORK(&nxt->work, io_sq_wq_submit_work); - io_queue_async_work(req->ctx, nxt); + /* + * If we're in async work, we can continue processing the chain + * in this context instead of having to queue up new async work. + */ + if (req->flags & REQ_F_LINK_TIMEOUT) { + wake_ev = io_link_cancel_timeout(nxt); + + /* we dropped this link, get next */ + nxt = list_first_entry_or_null(&req->link_list, + struct io_kiocb, list); + } else if (nxtptr && io_wq_current_is_worker()) { + *nxtptr = nxt; + break; + } else { + io_queue_async_work(nxt); + break; + } } + + if (wake_ev) + io_cqring_ev_posted(ctx); } /* @@ -695,43 +899,118 @@ static void io_req_link_next(struct io_kiocb *req) */ static void io_fail_links(struct io_kiocb *req) { + struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link; + unsigned long flags; + + spin_lock_irqsave(&ctx->completion_lock, flags); while (!list_empty(&req->link_list)) { link = list_first_entry(&req->link_list, struct io_kiocb, list); - list_del(&link->list); + list_del_init(&link->list); + + trace_io_uring_fail_link(req, link); - io_cqring_add_event(req->ctx, link->user_data, -ECANCELED); - __io_free_req(link); + if ((req->flags & REQ_F_LINK_TIMEOUT) && + link->submit.sqe->opcode == IORING_OP_LINK_TIMEOUT) { + io_link_cancel_timeout(link); + } else { + io_cqring_fill_event(link, -ECANCELED); + io_double_put_req(link); + } } + + io_commit_cqring(ctx); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + io_cqring_ev_posted(ctx); } -static void io_free_req(struct io_kiocb *req) +static void io_free_req_find_next(struct io_kiocb *req, struct io_kiocb **nxt) { + if (likely(!(req->flags & REQ_F_LINK))) { + __io_free_req(req); + return; + } + /* * If LINK is set, we have dependent requests in this chain. If we * didn't fail this request, queue the first one up, moving any other * dependencies to the next request. In case of failure, fail the rest * of the chain. */ - if (req->flags & REQ_F_LINK) { - if (req->flags & REQ_F_FAIL_LINK) - io_fail_links(req); - else - io_req_link_next(req); + if (req->flags & REQ_F_FAIL_LINK) { + io_fail_links(req); + } else if ((req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_COMP_LOCKED)) == + REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + /* + * If this is a timeout link, we could be racing with the + * timeout timer. Grab the completion lock for this case to + * protect against that. + */ + spin_lock_irqsave(&ctx->completion_lock, flags); + io_req_link_next(req, nxt); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + } else { + io_req_link_next(req, nxt); } __io_free_req(req); } +static void io_free_req(struct io_kiocb *req) +{ + io_free_req_find_next(req, NULL); +} + +/* + * Drop reference to request, return next in chain (if there is one) if this + * was the last reference to this request. + */ +static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr) +{ + struct io_kiocb *nxt = NULL; + + if (refcount_dec_and_test(&req->refs)) + io_free_req_find_next(req, &nxt); + + if (nxt) { + if (nxtptr) + *nxtptr = nxt; + else + io_queue_async_work(nxt); + } +} + static void io_put_req(struct io_kiocb *req) { if (refcount_dec_and_test(&req->refs)) io_free_req(req); } -static unsigned io_cqring_events(struct io_rings *rings) +static void io_double_put_req(struct io_kiocb *req) { + /* drop both submit and complete references */ + if (refcount_sub_and_test(2, &req->refs)) + __io_free_req(req); +} + +static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush) +{ + struct io_rings *rings = ctx->rings; + + /* + * noflush == true is from the waitqueue handler, just ensure we wake + * up the task, and the next invocation will flush the entries. We + * cannot safely to it from here. + */ + if (noflush && !list_empty(&ctx->cq_overflow_list)) + return -1U; + + io_cqring_overflow_flush(ctx, false); + /* See comment at the top of this file */ smp_rmb(); return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head); @@ -760,7 +1039,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, list); list_del(&req->list); - io_cqring_fill_event(ctx, req->user_data, req->result); + io_cqring_fill_event(req, req->result); (*nr_events)++; if (refcount_dec_and_test(&req->refs)) { @@ -769,8 +1048,8 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, * completions for those, only batch free for fixed * file and non-linked commands. */ - if ((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) == - REQ_F_FIXED_FILE) { + if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) == + REQ_F_FIXED_FILE) && !io_is_fallback_req(req)) { reqs[to_free++] = req; if (to_free == ARRAY_SIZE(reqs)) io_free_req_many(ctx, reqs, &to_free); @@ -887,7 +1166,7 @@ static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ - if (io_cqring_events(ctx->rings)) + if (io_cqring_events(ctx, false)) break; /* @@ -947,7 +1226,7 @@ static void kiocb_end_write(struct io_kiocb *req) file_end_write(req->file); } -static void io_complete_rw(struct kiocb *kiocb, long res, long res2) +static void io_complete_rw_common(struct kiocb *kiocb, long res) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); @@ -956,10 +1235,28 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) if ((req->flags & REQ_F_LINK) && res != req->result) req->flags |= REQ_F_FAIL_LINK; - io_cqring_add_event(req->ctx, req->user_data, res); + io_cqring_add_event(req, res); +} + +static void io_complete_rw(struct kiocb *kiocb, long res, long res2) +{ + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + + io_complete_rw_common(kiocb, res); io_put_req(req); } +static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) +{ + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *nxt = NULL; + + io_complete_rw_common(kiocb, res); + io_put_req_find_next(req, &nxt); + + return nxt; +} + static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); @@ -1067,10 +1364,9 @@ static bool io_file_supports_async(struct file *file) return false; } -static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock) +static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) { - const struct io_uring_sqe *sqe = s->sqe; + const struct io_uring_sqe *sqe = req->submit.sqe; struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw; unsigned ioprio; @@ -1154,6 +1450,15 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } +static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt, + bool in_async) +{ + if (in_async && ret >= 0 && nxt && kiocb->ki_complete == io_complete_rw) + *nxt = __io_complete_rw(kiocb, ret); + else + io_rw_done(kiocb, ret); +} + static int io_import_fixed(struct io_ring_ctx *ctx, int rw, const struct io_uring_sqe *sqe, struct iov_iter *iter) @@ -1225,7 +1530,7 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, } } - return 0; + return len; } static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, @@ -1265,65 +1570,6 @@ static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter); } -static inline bool io_should_merge(struct async_list *al, struct kiocb *kiocb) -{ - if (al->file == kiocb->ki_filp) { - off_t start, end; - - /* - * Allow merging if we're anywhere in the range of the same - * page. Generally this happens for sub-page reads or writes, - * and it's beneficial to allow the first worker to bring the - * page in and the piggy backed work can then work on the - * cached page. - */ - start = al->io_start & PAGE_MASK; - end = (al->io_start + al->io_len + PAGE_SIZE - 1) & PAGE_MASK; - if (kiocb->ki_pos >= start && kiocb->ki_pos <= end) - return true; - } - - al->file = NULL; - return false; -} - -/* - * Make a note of the last file/offset/direction we punted to async - * context. We'll use this information to see if we can piggy back a - * sequential request onto the previous one, if it's still hasn't been - * completed by the async worker. - */ -static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) -{ - struct async_list *async_list = &req->ctx->pending_async[rw]; - struct kiocb *kiocb = &req->rw; - struct file *filp = kiocb->ki_filp; - - if (io_should_merge(async_list, kiocb)) { - unsigned long max_bytes; - - /* Use 8x RA size as a decent limiter for both reads/writes */ - max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3); - if (!max_bytes) - max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3); - - /* If max len are exceeded, reset the state */ - if (async_list->io_len + len <= max_bytes) { - req->flags |= REQ_F_SEQ_PREV; - async_list->io_len += len; - } else { - async_list->file = NULL; - } - } - - /* New file? Reset state. */ - if (async_list->file != filp) { - async_list->io_start = kiocb->ki_pos; - async_list->io_len = len; - async_list->file = filp; - } -} - /* * For files that don't have ->read_iter() and ->write_iter(), handle them * by looping over ->read() or ->write() manually. @@ -1369,7 +1615,7 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, return ret; } -static int io_read(struct io_kiocb *req, const struct sqe_submit *s, +static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; @@ -1379,7 +1625,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; ssize_t read_size, ret; - ret = io_prep_rw(req, s, force_nonblock); + ret = io_prep_rw(req, force_nonblock); if (ret) return ret; file = kiocb->ki_filp; @@ -1387,7 +1633,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; - ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, READ, &req->submit, &iovec, &iter); if (ret < 0) return ret; @@ -1418,23 +1664,16 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, ret2 > 0 && ret2 < read_size) ret2 = -EAGAIN; /* Catch -EAGAIN return for forced non-blocking submission */ - if (!force_nonblock || ret2 != -EAGAIN) { - io_rw_done(kiocb, ret2); - } else { - /* - * If ->needs_lock is true, we're already in async - * context. - */ - if (!s->needs_lock) - io_async_list_note(READ, req, iov_count); + if (!force_nonblock || ret2 != -EAGAIN) + kiocb_done(kiocb, ret2, nxt, req->submit.in_async); + else ret = -EAGAIN; - } } kfree(iovec); return ret; } -static int io_write(struct io_kiocb *req, const struct sqe_submit *s, +static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; @@ -1444,7 +1683,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; ssize_t ret; - ret = io_prep_rw(req, s, force_nonblock); + ret = io_prep_rw(req, force_nonblock); if (ret) return ret; @@ -1452,7 +1691,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_WRITE))) return -EBADF; - ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, WRITE, &req->submit, &iovec, &iter); if (ret < 0) return ret; @@ -1462,12 +1701,8 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, iov_count = iov_iter_count(&iter); ret = -EAGAIN; - if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) { - /* If ->needs_lock is true, we're already in async context. */ - if (!s->needs_lock) - io_async_list_note(WRITE, req, iov_count); + if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) goto out_free; - } ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); if (!ret) { @@ -1492,17 +1727,10 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, ret2 = call_write_iter(file, kiocb, &iter); else ret2 = loop_rw_iter(WRITE, file, kiocb, &iter); - if (!force_nonblock || ret2 != -EAGAIN) { - io_rw_done(kiocb, ret2); - } else { - /* - * If ->needs_lock is true, we're already in async - * context. - */ - if (!s->needs_lock) - io_async_list_note(WRITE, req, iov_count); + if (!force_nonblock || ret2 != -EAGAIN) + kiocb_done(kiocb, ret2, nxt, req->submit.in_async); + else ret = -EAGAIN; - } } out_free: kfree(iovec); @@ -1512,15 +1740,14 @@ out_free: /* * IORING_OP_NOP just posts a completion event, nothing else. */ -static int io_nop(struct io_kiocb *req, u64 user_data) +static int io_nop(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - long err = 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - io_cqring_add_event(ctx, user_data, err); + io_cqring_add_event(req, 0); io_put_req(req); return 0; } @@ -1541,7 +1768,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) } static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock) + struct io_kiocb **nxt, bool force_nonblock) { loff_t sqe_off = READ_ONCE(sqe->off); loff_t sqe_len = READ_ONCE(sqe->len); @@ -1567,8 +1794,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; - io_cqring_add_event(req->ctx, sqe->user_data, ret); - io_put_req(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); return 0; } @@ -1590,6 +1817,7 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_sync_file_range(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) { loff_t sqe_off; @@ -1613,14 +1841,14 @@ static int io_sync_file_range(struct io_kiocb *req, if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; - io_cqring_add_event(req->ctx, sqe->user_data, ret); - io_put_req(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); return 0; } #if defined(CONFIG_NET) static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock, + struct io_kiocb **nxt, bool force_nonblock, long (*fn)(struct socket *, struct user_msghdr __user *, unsigned int)) { @@ -1649,32 +1877,80 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, return ret; } - io_cqring_add_event(req->ctx, sqe->user_data, ret); - io_put_req(req); + io_cqring_add_event(req, ret); + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_put_req_find_next(req, nxt); return 0; } #endif static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock) + struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, force_nonblock, __sys_sendmsg_sock); + return io_send_recvmsg(req, sqe, nxt, force_nonblock, + __sys_sendmsg_sock); #else return -EOPNOTSUPP; #endif } static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock) + struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, force_nonblock, __sys_recvmsg_sock); + return io_send_recvmsg(req, sqe, nxt, force_nonblock, + __sys_recvmsg_sock); #else return -EOPNOTSUPP; #endif } +static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) +{ +#if defined(CONFIG_NET) + struct sockaddr __user *addr; + int __user *addr_len; + unsigned file_flags; + int flags, ret; + + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) + return -EINVAL; + + addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); + addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2); + flags = READ_ONCE(sqe->accept_flags); + file_flags = force_nonblock ? O_NONBLOCK : 0; + + ret = __sys_accept4_file(req->file, file_flags, addr, addr_len, flags); + if (ret == -EAGAIN && force_nonblock) { + req->work.flags |= IO_WQ_WORK_NEEDS_FILES; + return -EAGAIN; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static inline void io_poll_remove_req(struct io_kiocb *req) +{ + if (!RB_EMPTY_NODE(&req->rb_node)) { + rb_erase(&req->rb_node, &req->ctx->cancel_tree); + RB_CLEAR_NODE(&req->rb_node); + } +} + static void io_poll_remove_one(struct io_kiocb *req) { struct io_poll_iocb *poll = &req->poll; @@ -1683,25 +1959,47 @@ static void io_poll_remove_one(struct io_kiocb *req) WRITE_ONCE(poll->canceled, true); if (!list_empty(&poll->wait.entry)) { list_del_init(&poll->wait.entry); - io_queue_async_work(req->ctx, req); + io_queue_async_work(req); } spin_unlock(&poll->head->lock); - - list_del_init(&req->list); + io_poll_remove_req(req); } static void io_poll_remove_all(struct io_ring_ctx *ctx) { + struct rb_node *node; struct io_kiocb *req; spin_lock_irq(&ctx->completion_lock); - while (!list_empty(&ctx->cancel_list)) { - req = list_first_entry(&ctx->cancel_list, struct io_kiocb,list); + while ((node = rb_first(&ctx->cancel_tree)) != NULL) { + req = rb_entry(node, struct io_kiocb, rb_node); io_poll_remove_one(req); } spin_unlock_irq(&ctx->completion_lock); } +static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) +{ + struct rb_node *p, *parent = NULL; + struct io_kiocb *req; + + p = ctx->cancel_tree.rb_node; + while (p) { + parent = p; + req = rb_entry(parent, struct io_kiocb, rb_node); + if (sqe_addr < req->user_data) { + p = p->rb_left; + } else if (sqe_addr > req->user_data) { + p = p->rb_right; + } else { + io_poll_remove_one(req); + return 0; + } + } + + return -ENOENT; +} + /* * Find a running poll command that matches one specified in sqe->addr, * and remove it if found. @@ -1709,8 +2007,7 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx) static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *poll_req, *next; - int ret = -ENOENT; + int ret; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; @@ -1719,36 +2016,38 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; spin_lock_irq(&ctx->completion_lock); - list_for_each_entry_safe(poll_req, next, &ctx->cancel_list, list) { - if (READ_ONCE(sqe->addr) == poll_req->user_data) { - io_poll_remove_one(poll_req); - ret = 0; - break; - } - } + ret = io_poll_cancel(ctx, READ_ONCE(sqe->addr)); spin_unlock_irq(&ctx->completion_lock); - io_cqring_add_event(req->ctx, sqe->user_data, ret); + io_cqring_add_event(req, ret); + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; io_put_req(req); return 0; } -static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req, - __poll_t mask) +static void io_poll_complete(struct io_kiocb *req, __poll_t mask) { + struct io_ring_ctx *ctx = req->ctx; + req->poll.done = true; - io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask)); + io_cqring_fill_event(req, mangle_poll(mask)); io_commit_cqring(ctx); } -static void io_poll_complete_work(struct work_struct *work) +static void io_poll_complete_work(struct io_wq_work **workptr) { + struct io_wq_work *work = *workptr; struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_poll_iocb *poll = &req->poll; struct poll_table_struct pt = { ._key = poll->events }; struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *nxt = NULL; __poll_t mask = 0; + if (work->flags & IO_WQ_WORK_CANCEL) + WRITE_ONCE(poll->canceled, true); + if (!READ_ONCE(poll->canceled)) mask = vfs_poll(poll->file, &pt) & poll->events; @@ -1765,12 +2064,15 @@ static void io_poll_complete_work(struct work_struct *work) spin_unlock_irq(&ctx->completion_lock); return; } - list_del_init(&req->list); - io_poll_complete(ctx, req, mask); + io_poll_remove_req(req); + io_poll_complete(req, mask); spin_unlock_irq(&ctx->completion_lock); io_cqring_ev_posted(ctx); - io_put_req(req); + + io_put_req_find_next(req, &nxt); + if (nxt) + *workptr = &nxt->work; } static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, @@ -1789,15 +2091,22 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del_init(&poll->wait.entry); + /* + * Run completion inline if we can. We're using trylock here because + * we are violating the completion_lock -> poll wq lock ordering. + * If we have a link timeout we're going to need the completion_lock + * for finalizing the request, mark us as having grabbed that already. + */ if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) { - list_del(&req->list); - io_poll_complete(ctx, req, mask); + io_poll_remove_req(req); + io_poll_complete(req, mask); + req->flags |= REQ_F_COMP_LOCKED; + io_put_req(req); spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); - io_put_req(req); } else { - io_queue_async_work(ctx, req); + io_queue_async_work(req); } return 1; @@ -1824,7 +2133,27 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, add_wait_queue(head, &pt->req->poll.wait); } -static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static void io_poll_req_insert(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct rb_node **p = &ctx->cancel_tree.rb_node; + struct rb_node *parent = NULL; + struct io_kiocb *tmp; + + while (*p) { + parent = *p; + tmp = rb_entry(parent, struct io_kiocb, rb_node); + if (req->user_data < tmp->user_data) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&req->rb_node, parent, p); + rb_insert_color(&req->rb_node, &ctx->cancel_tree); +} + +static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt) { struct io_poll_iocb *poll = &req->poll; struct io_ring_ctx *ctx = req->ctx; @@ -1841,9 +2170,10 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EBADF; req->submit.sqe = NULL; - INIT_WORK(&req->work, io_poll_complete_work); + INIT_IO_WORK(&req->work, io_poll_complete_work); events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; + RB_CLEAR_NODE(&req->rb_node); poll->head = NULL; poll->done = false; @@ -1876,18 +2206,18 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) else if (cancel) WRITE_ONCE(poll->canceled, true); else if (!poll->done) /* actually waiting for an event */ - list_add_tail(&req->list, &ctx->cancel_list); + io_poll_req_insert(req); spin_unlock(&poll->head->lock); } if (mask) { /* no async, we'd stolen it */ ipt.error = 0; - io_poll_complete(ctx, req, mask); + io_poll_complete(req, mask); } spin_unlock_irq(&ctx->completion_lock); if (mask) { io_cqring_ev_posted(ctx); - io_put_req(req); + io_put_req_find_next(req, nxt); } return ipt.error; } @@ -1895,7 +2225,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) { struct io_ring_ctx *ctx; - struct io_kiocb *req, *prev; + struct io_kiocb *req; unsigned long flags; req = container_of(timer, struct io_kiocb, timeout.timer); @@ -1904,55 +2234,136 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) spin_lock_irqsave(&ctx->completion_lock, flags); /* - * Adjust the reqs sequence before the current one because it - * will consume a slot in the cq_ring and the the cq_tail pointer - * will be increased, otherwise other timeout reqs may return in - * advance without waiting for enough wait_nr. + * We could be racing with timeout deletion. If the list is empty, + * then timeout lookup already found it and will be handling it. */ - prev = req; - list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list) - prev->sequence++; - list_del(&req->list); + if (!list_empty(&req->list)) { + struct io_kiocb *prev; + + /* + * Adjust the reqs sequence before the current one because it + * will consume a slot in the cq_ring and the the cq_tail + * pointer will be increased, otherwise other timeout reqs may + * return in advance without waiting for enough wait_nr. + */ + prev = req; + list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list) + prev->sequence++; + list_del_init(&req->list); + } - io_cqring_fill_event(ctx, req->user_data, -ETIME); + io_cqring_fill_event(req, -ETIME); io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); - + if (req->flags & REQ_F_LINK) + req->flags |= REQ_F_FAIL_LINK; io_put_req(req); return HRTIMER_NORESTART; } +static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) +{ + struct io_kiocb *req; + int ret = -ENOENT; + + list_for_each_entry(req, &ctx->timeout_list, list) { + if (user_data == req->user_data) { + list_del_init(&req->list); + ret = 0; + break; + } + } + + if (ret == -ENOENT) + return ret; + + ret = hrtimer_try_to_cancel(&req->timeout.timer); + if (ret == -1) + return -EALREADY; + + io_cqring_fill_event(req, -ECANCELED); + io_put_req(req); + return 0; +} + +/* + * Remove or update an existing timeout command + */ +static int io_timeout_remove(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_ring_ctx *ctx = req->ctx; + unsigned flags; + int ret; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) + return -EINVAL; + flags = READ_ONCE(sqe->timeout_flags); + if (flags) + return -EINVAL; + + spin_lock_irq(&ctx->completion_lock); + ret = io_timeout_cancel(ctx, READ_ONCE(sqe->addr)); + + io_cqring_fill_event(req, ret); + io_commit_cqring(ctx); + spin_unlock_irq(&ctx->completion_lock); + io_cqring_ev_posted(ctx); + if (ret < 0 && req->flags & REQ_F_LINK) + req->flags |= REQ_F_FAIL_LINK; + io_put_req(req); + return 0; +} + static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) { unsigned count; struct io_ring_ctx *ctx = req->ctx; struct list_head *entry; + enum hrtimer_mode mode; struct timespec64 ts; unsigned span = 0; + unsigned flags; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags || - sqe->len != 1) + if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len != 1) + return -EINVAL; + flags = READ_ONCE(sqe->timeout_flags); + if (flags & ~IORING_TIMEOUT_ABS) return -EINVAL; if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; + if (flags & IORING_TIMEOUT_ABS) + mode = HRTIMER_MODE_ABS; + else + mode = HRTIMER_MODE_REL; + + hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, mode); + req->flags |= REQ_F_TIMEOUT; + /* * sqe->off holds how many events that need to occur for this - * timeout event to be satisfied. + * timeout event to be satisfied. If it isn't set, then this is + * a pure timeout request, sequence isn't used. */ count = READ_ONCE(sqe->off); - if (!count) - count = 1; + if (!count) { + req->flags |= REQ_F_TIMEOUT_NOSEQ; + spin_lock_irq(&ctx->completion_lock); + entry = ctx->timeout_list.prev; + goto add; + } req->sequence = ctx->cached_sq_head + count - 1; /* reuse it to store the count */ req->submit.sequence = count; - req->flags |= REQ_F_TIMEOUT; /* * Insertion sort, ensuring the first entry in the list is always @@ -1964,6 +2375,9 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) unsigned nxt_sq_head; long long tmp, tmp_nxt; + if (nxt->flags & REQ_F_TIMEOUT_NOSEQ) + continue; + /* * Since cached_sq_head + count - 1 can overflow, use type long * long to store it. @@ -1990,22 +2404,94 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) nxt->sequence++; } req->sequence -= span; +add: list_add(&req->list, entry); + req->timeout.timer.function = io_timeout_fn; + hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts), mode); spin_unlock_irq(&ctx->completion_lock); + return 0; +} - hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - req->timeout.timer.function = io_timeout_fn; - hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts), - HRTIMER_MODE_REL); +static bool io_cancel_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + return req->user_data == (unsigned long) data; +} + +static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr) +{ + enum io_wq_cancel cancel_ret; + int ret = 0; + + cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr); + switch (cancel_ret) { + case IO_WQ_CANCEL_OK: + ret = 0; + break; + case IO_WQ_CANCEL_RUNNING: + ret = -EALREADY; + break; + case IO_WQ_CANCEL_NOTFOUND: + ret = -ENOENT; + break; + } + + return ret; +} + +static void io_async_find_and_cancel(struct io_ring_ctx *ctx, + struct io_kiocb *req, __u64 sqe_addr, + struct io_kiocb **nxt) +{ + unsigned long flags; + int ret; + + ret = io_async_cancel_one(ctx, (void *) (unsigned long) sqe_addr); + if (ret != -ENOENT) { + spin_lock_irqsave(&ctx->completion_lock, flags); + goto done; + } + + spin_lock_irqsave(&ctx->completion_lock, flags); + ret = io_timeout_cancel(ctx, sqe_addr); + if (ret != -ENOENT) + goto done; + ret = io_poll_cancel(ctx, sqe_addr); +done: + io_cqring_fill_event(req, ret); + io_commit_cqring(ctx); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + io_cqring_ev_posted(ctx); + + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_put_req_find_next(req, nxt); +} + +static int io_async_cancel(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->flags || sqe->ioprio || sqe->off || sqe->len || + sqe->cancel_flags) + return -EINVAL; + + io_async_find_and_cancel(ctx, req, READ_ONCE(sqe->addr), NULL); return 0; } -static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_req_defer(struct io_kiocb *req) { + const struct io_uring_sqe *sqe = req->submit.sqe; struct io_uring_sqe *sqe_copy; + struct io_ring_ctx *ctx = req->ctx; - if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) + /* Still need defer if there is pending req in defer list. */ + if (!req_need_defer(req) && list_empty(&ctx->defer_list)) return 0; sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL); @@ -2013,7 +2499,7 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, return -EAGAIN; spin_lock_irq(&ctx->completion_lock); - if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) { + if (!req_need_defer(req) && list_empty(&ctx->defer_list)) { spin_unlock_irq(&ctx->completion_lock); kfree(sqe_copy); return 0; @@ -2022,64 +2508,70 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, memcpy(sqe_copy, sqe, sizeof(*sqe_copy)); req->submit.sqe = sqe_copy; - INIT_WORK(&req->work, io_sq_wq_submit_work); + trace_io_uring_defer(ctx, req, false); list_add_tail(&req->list, &ctx->defer_list); spin_unlock_irq(&ctx->completion_lock); return -EIOCBQUEUED; } -static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct sqe_submit *s, bool force_nonblock) +static int __io_submit_sqe(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { int ret, opcode; - - req->user_data = READ_ONCE(s->sqe->user_data); - - if (unlikely(s->index >= ctx->sq_entries)) - return -EINVAL; + struct sqe_submit *s = &req->submit; + struct io_ring_ctx *ctx = req->ctx; opcode = READ_ONCE(s->sqe->opcode); switch (opcode) { case IORING_OP_NOP: - ret = io_nop(req, req->user_data); + ret = io_nop(req); break; case IORING_OP_READV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_read(req, s, force_nonblock); + ret = io_read(req, nxt, force_nonblock); break; case IORING_OP_WRITEV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_write(req, s, force_nonblock); + ret = io_write(req, nxt, force_nonblock); break; case IORING_OP_READ_FIXED: - ret = io_read(req, s, force_nonblock); + ret = io_read(req, nxt, force_nonblock); break; case IORING_OP_WRITE_FIXED: - ret = io_write(req, s, force_nonblock); + ret = io_write(req, nxt, force_nonblock); break; case IORING_OP_FSYNC: - ret = io_fsync(req, s->sqe, force_nonblock); + ret = io_fsync(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_POLL_ADD: - ret = io_poll_add(req, s->sqe); + ret = io_poll_add(req, s->sqe, nxt); break; case IORING_OP_POLL_REMOVE: ret = io_poll_remove(req, s->sqe); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, s->sqe, force_nonblock); + ret = io_sync_file_range(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_SENDMSG: - ret = io_sendmsg(req, s->sqe, force_nonblock); + ret = io_sendmsg(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_RECVMSG: - ret = io_recvmsg(req, s->sqe, force_nonblock); + ret = io_recvmsg(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_TIMEOUT: ret = io_timeout(req, s->sqe); break; + case IORING_OP_TIMEOUT_REMOVE: + ret = io_timeout_remove(req, s->sqe); + break; + case IORING_OP_ACCEPT: + ret = io_accept(req, s->sqe, nxt, force_nonblock); + break; + case IORING_OP_ASYNC_CANCEL: + ret = io_async_cancel(req, s->sqe, nxt); + break; default: ret = -EINVAL; break; @@ -2093,187 +2585,65 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return -EAGAIN; /* workqueue context doesn't hold uring_lock, grab it now */ - if (s->needs_lock) + if (s->in_async) mutex_lock(&ctx->uring_lock); io_iopoll_req_issued(req); - if (s->needs_lock) + if (s->in_async) mutex_unlock(&ctx->uring_lock); } return 0; } -static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx, - const struct io_uring_sqe *sqe) -{ - switch (sqe->opcode) { - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - return &ctx->pending_async[READ]; - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: - return &ctx->pending_async[WRITE]; - default: - return NULL; - } -} - -static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) -{ - u8 opcode = READ_ONCE(sqe->opcode); - - return !(opcode == IORING_OP_READ_FIXED || - opcode == IORING_OP_WRITE_FIXED); -} - -static void io_sq_wq_submit_work(struct work_struct *work) +static void io_wq_submit_work(struct io_wq_work **workptr) { + struct io_wq_work *work = *workptr; struct io_kiocb *req = container_of(work, struct io_kiocb, work); - struct io_ring_ctx *ctx = req->ctx; - struct mm_struct *cur_mm = NULL; - struct async_list *async_list; - LIST_HEAD(req_list); - mm_segment_t old_fs; - int ret; + struct sqe_submit *s = &req->submit; + const struct io_uring_sqe *sqe = s->sqe; + struct io_kiocb *nxt = NULL; + int ret = 0; - async_list = io_async_list_from_sqe(ctx, req->submit.sqe); -restart: - do { - struct sqe_submit *s = &req->submit; - const struct io_uring_sqe *sqe = s->sqe; - unsigned int flags = req->flags; + /* Ensure we clear previously set non-block flag */ + req->rw.ki_flags &= ~IOCB_NOWAIT; - /* Ensure we clear previously set non-block flag */ - req->rw.ki_flags &= ~IOCB_NOWAIT; + if (work->flags & IO_WQ_WORK_CANCEL) + ret = -ECANCELED; - ret = 0; - if (io_sqe_needs_user(sqe) && !cur_mm) { - if (!mmget_not_zero(ctx->sqo_mm)) { - ret = -EFAULT; - } else { - cur_mm = ctx->sqo_mm; - use_mm(cur_mm); - old_fs = get_fs(); - set_fs(USER_DS); - } - } + if (!ret) { + s->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0; + s->in_async = true; + do { + ret = __io_submit_sqe(req, &nxt, false); + /* + * We can get EAGAIN for polled IO even though we're + * forcing a sync submission from here, since we can't + * wait for request slots on the block side. + */ + if (ret != -EAGAIN) + break; + cond_resched(); + } while (1); + } - if (!ret) { - s->has_user = cur_mm != NULL; - s->needs_lock = true; - do { - ret = __io_submit_sqe(ctx, req, s, false); - /* - * We can get EAGAIN for polled IO even though - * we're forcing a sync submission from here, - * since we can't wait for request slots on the - * block side. - */ - if (ret != -EAGAIN) - break; - cond_resched(); - } while (1); - } + /* drop submission reference */ + io_put_req(req); - /* drop submission reference */ + if (ret) { + if (req->flags & REQ_F_LINK) + req->flags |= REQ_F_FAIL_LINK; + io_cqring_add_event(req, ret); io_put_req(req); - - if (ret) { - io_cqring_add_event(ctx, sqe->user_data, ret); - io_put_req(req); - } - - /* async context always use a copy of the sqe */ - kfree(sqe); - - /* req from defer and link list needn't decrease async cnt */ - if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) - goto out; - - if (!async_list) - break; - if (!list_empty(&req_list)) { - req = list_first_entry(&req_list, struct io_kiocb, - list); - list_del(&req->list); - continue; - } - if (list_empty(&async_list->list)) - break; - - req = NULL; - spin_lock(&async_list->lock); - if (list_empty(&async_list->list)) { - spin_unlock(&async_list->lock); - break; - } - list_splice_init(&async_list->list, &req_list); - spin_unlock(&async_list->lock); - - req = list_first_entry(&req_list, struct io_kiocb, list); - list_del(&req->list); - } while (req); - - /* - * Rare case of racing with a submitter. If we find the count has - * dropped to zero AND we have pending work items, then restart - * the processing. This is a tiny race window. - */ - if (async_list) { - ret = atomic_dec_return(&async_list->cnt); - while (!ret && !list_empty(&async_list->list)) { - spin_lock(&async_list->lock); - atomic_inc(&async_list->cnt); - list_splice_init(&async_list->list, &req_list); - spin_unlock(&async_list->lock); - - if (!list_empty(&req_list)) { - req = list_first_entry(&req_list, - struct io_kiocb, list); - list_del(&req->list); - goto restart; - } - ret = atomic_dec_return(&async_list->cnt); - } } -out: - if (cur_mm) { - set_fs(old_fs); - unuse_mm(cur_mm); - mmput(cur_mm); - } -} - -/* - * See if we can piggy back onto previously submitted work, that is still - * running. We currently only allow this if the new request is sequential - * to the previous one we punted. - */ -static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) -{ - bool ret; + /* async context always use a copy of the sqe */ + kfree(sqe); - if (!list) - return false; - if (!(req->flags & REQ_F_SEQ_PREV)) - return false; - if (!atomic_read(&list->cnt)) - return false; - - ret = true; - spin_lock(&list->lock); - list_add_tail(&req->list, &list->list); - /* - * Ensure we see a simultaneous modification from io_sq_wq_submit_work() - */ - smp_mb(); - if (!atomic_read(&list->cnt)) { - list_del_init(&req->list); - ret = false; + /* if a dependent link is ready, pass it back */ + if (!ret && nxt) { + io_prep_async_work(nxt); + *workptr = &nxt->work; } - spin_unlock(&list->lock); - return ret; } static bool io_op_needs_file(const struct io_uring_sqe *sqe) @@ -2283,15 +2653,29 @@ static bool io_op_needs_file(const struct io_uring_sqe *sqe) switch (op) { case IORING_OP_NOP: case IORING_OP_POLL_REMOVE: + case IORING_OP_TIMEOUT: + case IORING_OP_TIMEOUT_REMOVE: + case IORING_OP_ASYNC_CANCEL: + case IORING_OP_LINK_TIMEOUT: return false; default: return true; } } -static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, - struct io_submit_state *state, struct io_kiocb *req) +static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, + int index) { + struct fixed_file_table *table; + + table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT]; + return table->files[index & IORING_FILE_TABLE_MASK]; +} + +static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req) +{ + struct sqe_submit *s = &req->submit; + struct io_ring_ctx *ctx = req->ctx; unsigned flags; int fd; @@ -2311,14 +2695,18 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, return 0; if (flags & IOSQE_FIXED_FILE) { - if (unlikely(!ctx->user_files || + if (unlikely(!ctx->file_table || (unsigned) fd >= ctx->nr_user_files)) return -EBADF; - req->file = ctx->user_files[fd]; + fd = array_index_nospec(fd, ctx->nr_user_files); + req->file = io_file_from_index(ctx, fd); + if (!req->file) + return -EBADF; req->flags |= REQ_F_FIXED_FILE; } else { if (s->needs_fixed_file) return -EBADF; + trace_io_uring_file_get(ctx, fd); req->file = io_file_get(state, fd); if (unlikely(!req->file)) return -EBADF; @@ -2327,12 +2715,146 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, return 0; } -static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s) +static int io_grab_files(struct io_kiocb *req) +{ + int ret = -EBADF; + struct io_ring_ctx *ctx = req->ctx; + + rcu_read_lock(); + spin_lock_irq(&ctx->inflight_lock); + /* + * We use the f_ops->flush() handler to ensure that we can flush + * out work accessing these files if the fd is closed. Check if + * the fd has changed since we started down this path, and disallow + * this operation if it has. + */ + if (fcheck(req->submit.ring_fd) == req->submit.ring_file) { + list_add(&req->inflight_entry, &ctx->inflight_list); + req->flags |= REQ_F_INFLIGHT; + req->work.files = current->files; + ret = 0; + } + spin_unlock_irq(&ctx->inflight_lock); + rcu_read_unlock(); + + return ret; +} + +static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) +{ + struct io_kiocb *req = container_of(timer, struct io_kiocb, + timeout.timer); + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *prev = NULL; + unsigned long flags; + + spin_lock_irqsave(&ctx->completion_lock, flags); + + /* + * We don't expect the list to be empty, that will only happen if we + * race with the completion of the linked work. + */ + if (!list_empty(&req->list)) { + prev = list_entry(req->list.prev, struct io_kiocb, link_list); + if (refcount_inc_not_zero(&prev->refs)) + list_del_init(&req->list); + else + prev = NULL; + } + + spin_unlock_irqrestore(&ctx->completion_lock, flags); + + if (prev) { + io_async_find_and_cancel(ctx, req, prev->user_data, NULL); + io_put_req(prev); + } else { + io_cqring_add_event(req, -ETIME); + io_put_req(req); + } + return HRTIMER_NORESTART; +} + +static void io_queue_linked_timeout(struct io_kiocb *req, struct timespec64 *ts, + enum hrtimer_mode *mode) +{ + struct io_ring_ctx *ctx = req->ctx; + + /* + * If the list is now empty, then our linked request finished before + * we got a chance to setup the timer + */ + spin_lock_irq(&ctx->completion_lock); + if (!list_empty(&req->list)) { + req->timeout.timer.function = io_link_timeout_fn; + hrtimer_start(&req->timeout.timer, timespec64_to_ktime(*ts), + *mode); + } + spin_unlock_irq(&ctx->completion_lock); + + /* drop submission reference */ + io_put_req(req); +} + +static int io_validate_link_timeout(const struct io_uring_sqe *sqe, + struct timespec64 *ts) +{ + if (sqe->ioprio || sqe->buf_index || sqe->len != 1 || sqe->off) + return -EINVAL; + if (sqe->timeout_flags & ~IORING_TIMEOUT_ABS) + return -EINVAL; + if (get_timespec64(ts, u64_to_user_ptr(sqe->addr))) + return -EFAULT; + + return 0; +} + +static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req, + struct timespec64 *ts, + enum hrtimer_mode *mode) +{ + struct io_kiocb *nxt; + int ret; + + if (!(req->flags & REQ_F_LINK)) + return NULL; + + nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list); + if (!nxt || nxt->submit.sqe->opcode != IORING_OP_LINK_TIMEOUT) + return NULL; + + ret = io_validate_link_timeout(nxt->submit.sqe, ts); + if (ret) { + list_del_init(&nxt->list); + io_cqring_add_event(nxt, ret); + io_double_put_req(nxt); + return ERR_PTR(-ECANCELED); + } + + if (nxt->submit.sqe->timeout_flags & IORING_TIMEOUT_ABS) + *mode = HRTIMER_MODE_ABS; + else + *mode = HRTIMER_MODE_REL; + + req->flags |= REQ_F_LINK_TIMEOUT; + hrtimer_init(&nxt->timeout.timer, CLOCK_MONOTONIC, *mode); + return nxt; +} + +static int __io_queue_sqe(struct io_kiocb *req) { + enum hrtimer_mode mode; + struct io_kiocb *nxt; + struct timespec64 ts; int ret; - ret = __io_submit_sqe(ctx, req, s, true); + nxt = io_prep_linked_timeout(req, &ts, &mode); + if (IS_ERR(nxt)) { + ret = PTR_ERR(nxt); + nxt = NULL; + goto err; + } + + ret = __io_submit_sqe(req, NULL, true); /* * We async punt it if the file wasn't marked NOWAIT, or if the file @@ -2340,36 +2862,47 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, */ if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) || (req->flags & REQ_F_MUST_PUNT))) { + struct sqe_submit *s = &req->submit; struct io_uring_sqe *sqe_copy; sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL); if (sqe_copy) { - struct async_list *list; - s->sqe = sqe_copy; - memcpy(&req->submit, s, sizeof(*s)); - list = io_async_list_from_sqe(ctx, s->sqe); - if (!io_add_to_prev_work(list, req)) { - if (list) - atomic_inc(&list->cnt); - INIT_WORK(&req->work, io_sq_wq_submit_work); - io_queue_async_work(ctx, req); + if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) { + ret = io_grab_files(req); + if (ret) { + kfree(sqe_copy); + goto err; + } } /* * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ + io_queue_async_work(req); + + if (nxt) + io_queue_linked_timeout(nxt, &ts, &mode); + return 0; } } +err: /* drop submission reference */ io_put_req(req); + if (nxt) { + if (!ret) + io_queue_linked_timeout(nxt, &ts, &mode); + else + io_put_req(nxt); + } + /* and drop final reference, if we failed */ if (ret) { - io_cqring_add_event(ctx, req->user_data, ret); + io_cqring_add_event(req, ret); if (req->flags & REQ_F_LINK) req->flags |= REQ_F_FAIL_LINK; io_put_req(req); @@ -2378,31 +2911,30 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return ret; } -static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s) +static int io_queue_sqe(struct io_kiocb *req) { int ret; - ret = io_req_defer(ctx, req, s->sqe); + ret = io_req_defer(req); if (ret) { if (ret != -EIOCBQUEUED) { - io_free_req(req); - io_cqring_add_event(ctx, s->sqe->user_data, ret); + io_cqring_add_event(req, ret); + io_double_put_req(req); } return 0; } - return __io_queue_sqe(ctx, req, s); + return __io_queue_sqe(req); } -static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s, struct io_kiocb *shadow) +static int io_queue_link_head(struct io_kiocb *req, struct io_kiocb *shadow) { int ret; int need_submit = false; + struct io_ring_ctx *ctx = req->ctx; if (!shadow) - return io_queue_sqe(ctx, req, s); + return io_queue_sqe(req); /* * Mark the first IO in link list as DRAIN, let all the following @@ -2410,12 +2942,12 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, * list. */ req->flags |= REQ_F_IO_DRAIN; - ret = io_req_defer(ctx, req, s->sqe); + ret = io_req_defer(req); if (ret) { if (ret != -EIOCBQUEUED) { - io_free_req(req); + io_cqring_add_event(req, ret); + io_double_put_req(req); __io_free_req(shadow); - io_cqring_add_event(ctx, s->sqe->user_data, ret); return 0; } } else { @@ -2428,47 +2960,42 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, /* Insert shadow req to defer_list, blocking next IOs */ spin_lock_irq(&ctx->completion_lock); + trace_io_uring_defer(ctx, shadow, true); list_add_tail(&shadow->list, &ctx->defer_list); spin_unlock_irq(&ctx->completion_lock); if (need_submit) - return __io_queue_sqe(ctx, req, s); + return __io_queue_sqe(req); return 0; } #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK) -static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, - struct io_submit_state *state, struct io_kiocb **link) +static void io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state, + struct io_kiocb **link) { struct io_uring_sqe *sqe_copy; - struct io_kiocb *req; + struct sqe_submit *s = &req->submit; + struct io_ring_ctx *ctx = req->ctx; int ret; + req->user_data = s->sqe->user_data; + /* enforce forwards compatibility on users */ if (unlikely(s->sqe->flags & ~SQE_VALID_FLAGS)) { ret = -EINVAL; - goto err; + goto err_req; } - req = io_get_req(ctx, state); - if (unlikely(!req)) { - ret = -EAGAIN; - goto err; - } - - ret = io_req_set_file(ctx, s, state, req); + ret = io_req_set_file(state, req); if (unlikely(ret)) { err_req: - io_free_req(req); -err: - io_cqring_add_event(ctx, s->sqe->user_data, ret); + io_cqring_add_event(req, ret); + io_double_put_req(req); return; } - req->user_data = s->sqe->user_data; - /* * If we already have a head request, queue this one for async * submittal once the head completes. If we don't have a head but @@ -2486,16 +3013,19 @@ err: } s->sqe = sqe_copy; - memcpy(&req->submit, s, sizeof(*s)); + trace_io_uring_link(ctx, req, prev); list_add_tail(&req->list, &prev->link_list); } else if (s->sqe->flags & IOSQE_IO_LINK) { req->flags |= REQ_F_LINK; - memcpy(&req->submit, s, sizeof(*s)); INIT_LIST_HEAD(&req->link_list); *link = req; + } else if (READ_ONCE(s->sqe->opcode) == IORING_OP_LINK_TIMEOUT) { + /* Only valid as a linked SQE */ + ret = -EINVAL; + goto err_req; } else { - io_queue_sqe(ctx, req, s); + io_queue_sqe(req); } } @@ -2566,7 +3096,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) head = READ_ONCE(sq_array[head & ctx->sq_mask]); if (head < ctx->sq_entries) { - s->index = head; + s->ring_file = NULL; s->sqe = &ctx->sq_sqes[head]; s->sequence = ctx->cached_sq_head; ctx->cached_sq_head++; @@ -2581,13 +3111,19 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, - bool has_user, bool mm_fault) + struct file *ring_file, int ring_fd, + struct mm_struct **mm, bool async) { struct io_submit_state state, *statep = NULL; struct io_kiocb *link = NULL; struct io_kiocb *shadow_req = NULL; - bool prev_was_link = false; int i, submitted = 0; + bool mm_fault = false; + + if (!list_empty(&ctx->cq_overflow_list)) { + io_cqring_overflow_flush(ctx, false); + return -EBUSY; + } if (nr > IO_PLUG_THRESHOLD) { io_submit_state_start(&state, ctx, nr); @@ -2595,23 +3131,31 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, } for (i = 0; i < nr; i++) { - struct sqe_submit s; + struct io_kiocb *req; + unsigned int sqe_flags; - if (!io_get_sqring(ctx, &s)) + req = io_get_req(ctx, statep); + if (unlikely(!req)) { + if (!submitted) + submitted = -EAGAIN; + break; + } + if (!io_get_sqring(ctx, &req->submit)) { + __io_free_req(req); break; + } - /* - * If previous wasn't linked and we have a linked command, - * that's the end of the chain. Submit the previous link. - */ - if (!prev_was_link && link) { - io_queue_link_head(ctx, link, &link->submit, shadow_req); - link = NULL; - shadow_req = NULL; + if (io_sqe_needs_user(req->submit.sqe) && !*mm) { + mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm); + if (!mm_fault) { + use_mm(ctx->sqo_mm); + *mm = ctx->sqo_mm; + } } - prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0; - if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) { + sqe_flags = req->submit.sqe->flags; + + if (link && (sqe_flags & IOSQE_IO_DRAIN)) { if (!shadow_req) { shadow_req = io_get_req(ctx, NULL); if (unlikely(!shadow_req)) @@ -2619,27 +3163,39 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN); refcount_dec(&shadow_req->refs); } - shadow_req->sequence = s.sequence; + shadow_req->sequence = req->submit.sequence; } out: - if (unlikely(mm_fault)) { - io_cqring_add_event(ctx, s.sqe->user_data, - -EFAULT); - } else { - s.has_user = has_user; - s.needs_lock = true; - s.needs_fixed_file = true; - io_submit_sqe(ctx, &s, statep, &link); - submitted++; + req->submit.ring_file = ring_file; + req->submit.ring_fd = ring_fd; + req->submit.has_user = *mm != NULL; + req->submit.in_async = async; + req->submit.needs_fixed_file = async; + trace_io_uring_submit_sqe(ctx, req->submit.sqe->user_data, + true, async); + io_submit_sqe(req, statep, &link); + submitted++; + + /* + * If previous wasn't linked and we have a linked command, + * that's the end of the chain. Submit the previous link. + */ + if (!(sqe_flags & IOSQE_IO_LINK) && link) { + io_queue_link_head(link, shadow_req); + link = NULL; + shadow_req = NULL; } } if (link) - io_queue_link_head(ctx, link, &link->submit, shadow_req); + io_queue_link_head(link, shadow_req); if (statep) io_submit_state_end(&state); + /* Commit SQ ring head once we've consumed and submitted all SQEs */ + io_commit_sqring(ctx); + return submitted; } @@ -2651,15 +3207,15 @@ static int io_sq_thread(void *data) DEFINE_WAIT(wait); unsigned inflight; unsigned long timeout; + int ret; - complete(&ctx->sqo_thread_started); + complete(&ctx->completions[1]); old_fs = get_fs(); set_fs(USER_DS); - timeout = inflight = 0; + ret = timeout = inflight = 0; while (!kthread_should_park()) { - bool mm_fault = false; unsigned int to_submit; if (inflight) { @@ -2694,13 +3250,21 @@ static int io_sq_thread(void *data) } to_submit = io_sqring_entries(ctx); - if (!to_submit) { + + /* + * If submit got -EBUSY, flag us as needing the application + * to enter the kernel to reap and flush events. + */ + if (!to_submit || ret == -EBUSY) { /* * We're polling. If we're within the defined idle * period, then let us spin without work before going - * to sleep. + * to sleep. The exception is if we got EBUSY doing + * more IO, we should wait for the application to + * reap events and wake us up. */ - if (inflight || !time_after(jiffies, timeout)) { + if (inflight || + (!time_after(jiffies, timeout) && ret != -EBUSY)) { cond_resched(); continue; } @@ -2726,7 +3290,7 @@ static int io_sq_thread(void *data) smp_mb(); to_submit = io_sqring_entries(ctx); - if (!to_submit) { + if (!to_submit || ret == -EBUSY) { if (kthread_should_park()) { finish_wait(&ctx->sqo_wait, &wait); break; @@ -2744,21 +3308,10 @@ static int io_sq_thread(void *data) ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; } - /* Unless all new commands are FIXED regions, grab mm */ - if (!cur_mm) { - mm_fault = !mmget_not_zero(ctx->sqo_mm); - if (!mm_fault) { - use_mm(ctx->sqo_mm); - cur_mm = ctx->sqo_mm; - } - } - to_submit = min(to_submit, ctx->sq_entries); - inflight += io_submit_sqes(ctx, to_submit, cur_mm != NULL, - mm_fault); - - /* Commit SQ ring head once we've consumed all SQEs */ - io_commit_sqring(ctx); + ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true); + if (ret > 0) + inflight += ret; } set_fs(old_fs); @@ -2772,65 +3325,6 @@ static int io_sq_thread(void *data) return 0; } -static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) -{ - struct io_submit_state state, *statep = NULL; - struct io_kiocb *link = NULL; - struct io_kiocb *shadow_req = NULL; - bool prev_was_link = false; - int i, submit = 0; - - if (to_submit > IO_PLUG_THRESHOLD) { - io_submit_state_start(&state, ctx, to_submit); - statep = &state; - } - - for (i = 0; i < to_submit; i++) { - struct sqe_submit s; - - if (!io_get_sqring(ctx, &s)) - break; - - /* - * If previous wasn't linked and we have a linked command, - * that's the end of the chain. Submit the previous link. - */ - if (!prev_was_link && link) { - io_queue_link_head(ctx, link, &link->submit, shadow_req); - link = NULL; - shadow_req = NULL; - } - prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0; - - if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) { - if (!shadow_req) { - shadow_req = io_get_req(ctx, NULL); - if (unlikely(!shadow_req)) - goto out; - shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN); - refcount_dec(&shadow_req->refs); - } - shadow_req->sequence = s.sequence; - } - -out: - s.has_user = true; - s.needs_lock = false; - s.needs_fixed_file = false; - submit++; - io_submit_sqe(ctx, &s, statep, &link); - } - - if (link) - io_queue_link_head(ctx, link, &link->submit, shadow_req); - if (statep) - io_submit_state_end(statep); - - io_commit_sqring(ctx); - - return submit; -} - struct io_wait_queue { struct wait_queue_entry wq; struct io_ring_ctx *ctx; @@ -2838,7 +3332,7 @@ struct io_wait_queue { unsigned nr_timeouts; }; -static inline bool io_should_wake(struct io_wait_queue *iowq) +static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) { struct io_ring_ctx *ctx = iowq->ctx; @@ -2847,7 +3341,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq) * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ - return io_cqring_events(ctx->rings) >= iowq->to_wait || + return io_cqring_events(ctx, noflush) >= iowq->to_wait || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } @@ -2857,7 +3351,8 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq); - if (!io_should_wake(iowq)) + /* use noflush == true, as we can't safely rely on locking context */ + if (!io_should_wake(iowq, true)) return -1; return autoremove_wake_function(curr, mode, wake_flags, key); @@ -2880,9 +3375,9 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, .to_wait = min_events, }; struct io_rings *rings = ctx->rings; - int ret; + int ret = 0; - if (io_cqring_events(rings) >= min_events) + if (io_cqring_events(ctx, false) >= min_events) return 0; if (sig) { @@ -2898,24 +3393,22 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } - ret = 0; iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); + trace_io_uring_cqring_wait(ctx, min_events); do { prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, TASK_INTERRUPTIBLE); - if (io_should_wake(&iowq)) + if (io_should_wake(&iowq, false)) break; schedule(); if (signal_pending(current)) { - ret = -ERESTARTSYS; + ret = -EINTR; break; } } while (1); finish_wait(&ctx->wait, &iowq.wq); - restore_saved_sigmask_unless(ret == -ERESTARTSYS); - if (ret == -ERESTARTSYS) - ret = -EINTR; + restore_saved_sigmask_unless(ret == -EINTR); return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } @@ -2933,19 +3426,29 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) #else int i; - for (i = 0; i < ctx->nr_user_files; i++) - fput(ctx->user_files[i]); + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file; + + file = io_file_from_index(ctx, i); + if (file) + fput(file); + } #endif } static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { - if (!ctx->user_files) + unsigned nr_tables, i; + + if (!ctx->file_table) return -ENXIO; __io_sqe_files_unregister(ctx); - kfree(ctx->user_files); - ctx->user_files = NULL; + nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); + for (i = 0; i < nr_tables; i++) + kfree(ctx->file_table[i].files); + kfree(ctx->file_table); + ctx->file_table = NULL; ctx->nr_user_files = 0; return 0; } @@ -2953,7 +3456,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) static void io_sq_thread_stop(struct io_ring_ctx *ctx) { if (ctx->sqo_thread) { - wait_for_completion(&ctx->sqo_thread_started); + wait_for_completion(&ctx->completions[1]); /* * The park is a bit of a work-around, without it we get * warning spews on shutdown with SQPOLL set and affinity @@ -2967,15 +3470,11 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx) static void io_finish_async(struct io_ring_ctx *ctx) { - int i; - io_sq_thread_stop(ctx); - for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) { - if (ctx->sqo_wq[i]) { - destroy_workqueue(ctx->sqo_wq[i]); - ctx->sqo_wq[i] = NULL; - } + if (ctx->io_wq) { + io_wq_destroy(ctx->io_wq); + ctx->io_wq = NULL; } } @@ -2983,11 +3482,9 @@ static void io_finish_async(struct io_ring_ctx *ctx) static void io_destruct_skb(struct sk_buff *skb) { struct io_ring_ctx *ctx = skb->sk->sk_user_data; - int i; - for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) - if (ctx->sqo_wq[i]) - flush_workqueue(ctx->sqo_wq[i]); + if (ctx->io_wq) + io_wq_flush(ctx->io_wq); unix_destruct_scm(skb); } @@ -3002,7 +3499,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) struct sock *sk = ctx->ring_sock->sk; struct scm_fp_list *fpl; struct sk_buff *skb; - int i; + int i, nr_files; if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { unsigned long inflight = ctx->user->unix_inflight + nr; @@ -3022,21 +3519,33 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) } skb->sk = sk; - skb->destructor = io_destruct_skb; + nr_files = 0; fpl->user = get_uid(ctx->user); for (i = 0; i < nr; i++) { - fpl->fp[i] = get_file(ctx->user_files[i + offset]); - unix_inflight(fpl->user, fpl->fp[i]); + struct file *file = io_file_from_index(ctx, i + offset); + + if (!file) + continue; + fpl->fp[nr_files] = get_file(file); + unix_inflight(fpl->user, fpl->fp[nr_files]); + nr_files++; } - fpl->max = fpl->count = nr; - UNIXCB(skb).fp = fpl; - refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_queue_head(&sk->sk_receive_queue, skb); + if (nr_files) { + fpl->max = SCM_MAX_FD; + fpl->count = nr_files; + UNIXCB(skb).fp = fpl; + skb->destructor = io_destruct_skb; + refcount_add(skb->truesize, &sk->sk_wmem_alloc); + skb_queue_head(&sk->sk_receive_queue, skb); - for (i = 0; i < nr; i++) - fput(fpl->fp[i]); + for (i = 0; i < nr_files; i++) + fput(fpl->fp[i]); + } else { + kfree_skb(skb); + kfree(fpl); + } return 0; } @@ -3067,7 +3576,10 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) return 0; while (total < ctx->nr_user_files) { - fput(ctx->user_files[total]); + struct file *file = io_file_from_index(ctx, total); + + if (file) + fput(file); total++; } @@ -3080,33 +3592,79 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) } #endif +static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables, + unsigned nr_files) +{ + int i; + + for (i = 0; i < nr_tables; i++) { + struct fixed_file_table *table = &ctx->file_table[i]; + unsigned this_files; + + this_files = min(nr_files, IORING_MAX_FILES_TABLE); + table->files = kcalloc(this_files, sizeof(struct file *), + GFP_KERNEL); + if (!table->files) + break; + nr_files -= this_files; + } + + if (i == nr_tables) + return 0; + + for (i = 0; i < nr_tables; i++) { + struct fixed_file_table *table = &ctx->file_table[i]; + kfree(table->files); + } + return 1; +} + static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { __s32 __user *fds = (__s32 __user *) arg; + unsigned nr_tables; int fd, ret = 0; unsigned i; - if (ctx->user_files) + if (ctx->file_table) return -EBUSY; if (!nr_args) return -EINVAL; if (nr_args > IORING_MAX_FIXED_FILES) return -EMFILE; - ctx->user_files = kcalloc(nr_args, sizeof(struct file *), GFP_KERNEL); - if (!ctx->user_files) + nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE); + ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table), + GFP_KERNEL); + if (!ctx->file_table) + return -ENOMEM; + + if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) { + kfree(ctx->file_table); + ctx->file_table = NULL; return -ENOMEM; + } + + for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { + struct fixed_file_table *table; + unsigned index; - for (i = 0; i < nr_args; i++) { ret = -EFAULT; if (copy_from_user(&fd, &fds[i], sizeof(fd))) break; + /* allow sparse sets */ + if (fd == -1) { + ret = 0; + continue; + } - ctx->user_files[i] = fget(fd); + table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT]; + index = i & IORING_FILE_TABLE_MASK; + table->files[index] = fget(fd); ret = -EBADF; - if (!ctx->user_files[i]) + if (!table->files[index]) break; /* * Don't allow io_uring instances to be registered. If UNIX @@ -3115,20 +3673,26 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, * handle it just fine, but there's still no point in allowing * a ring fd as it doesn't support regular read/write anyway. */ - if (ctx->user_files[i]->f_op == &io_uring_fops) { - fput(ctx->user_files[i]); + if (table->files[index]->f_op == &io_uring_fops) { + fput(table->files[index]); break; } - ctx->nr_user_files++; ret = 0; } if (ret) { - for (i = 0; i < ctx->nr_user_files; i++) - fput(ctx->user_files[i]); + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file; + + file = io_file_from_index(ctx, i); + if (file) + fput(file); + } + for (i = 0; i < nr_tables; i++) + kfree(ctx->file_table[i].files); - kfree(ctx->user_files); - ctx->user_files = NULL; + kfree(ctx->file_table); + ctx->file_table = NULL; ctx->nr_user_files = 0; return ret; } @@ -3140,9 +3704,201 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return ret; } +static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index) +{ +#if defined(CONFIG_UNIX) + struct file *file = io_file_from_index(ctx, index); + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff_head list, *head = &sock->sk_receive_queue; + struct sk_buff *skb; + int i; + + __skb_queue_head_init(&list); + + /* + * Find the skb that holds this file in its SCM_RIGHTS. When found, + * remove this entry and rearrange the file array. + */ + skb = skb_dequeue(head); + while (skb) { + struct scm_fp_list *fp; + + fp = UNIXCB(skb).fp; + for (i = 0; i < fp->count; i++) { + int left; + + if (fp->fp[i] != file) + continue; + + unix_notinflight(fp->user, fp->fp[i]); + left = fp->count - 1 - i; + if (left) { + memmove(&fp->fp[i], &fp->fp[i + 1], + left * sizeof(struct file *)); + } + fp->count--; + if (!fp->count) { + kfree_skb(skb); + skb = NULL; + } else { + __skb_queue_tail(&list, skb); + } + fput(file); + file = NULL; + break; + } + + if (!file) + break; + + __skb_queue_tail(&list, skb); + + skb = skb_dequeue(head); + } + + if (skb_peek(&list)) { + spin_lock_irq(&head->lock); + while ((skb = __skb_dequeue(&list)) != NULL) + __skb_queue_tail(head, skb); + spin_unlock_irq(&head->lock); + } +#else + fput(io_file_from_index(ctx, index)); +#endif +} + +static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, + int index) +{ +#if defined(CONFIG_UNIX) + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff_head *head = &sock->sk_receive_queue; + struct sk_buff *skb; + + /* + * See if we can merge this file into an existing skb SCM_RIGHTS + * file set. If there's no room, fall back to allocating a new skb + * and filling it in. + */ + spin_lock_irq(&head->lock); + skb = skb_peek(head); + if (skb) { + struct scm_fp_list *fpl = UNIXCB(skb).fp; + + if (fpl->count < SCM_MAX_FD) { + __skb_unlink(skb, head); + spin_unlock_irq(&head->lock); + fpl->fp[fpl->count] = get_file(file); + unix_inflight(fpl->user, fpl->fp[fpl->count]); + fpl->count++; + spin_lock_irq(&head->lock); + __skb_queue_head(head, skb); + } else { + skb = NULL; + } + } + spin_unlock_irq(&head->lock); + + if (skb) { + fput(file); + return 0; + } + + return __io_sqe_files_scm(ctx, 1, index); +#else + return 0; +#endif +} + +static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_files_update up; + __s32 __user *fds; + int fd, i, err; + __u32 done; + + if (!ctx->file_table) + return -ENXIO; + if (!nr_args) + return -EINVAL; + if (copy_from_user(&up, arg, sizeof(up))) + return -EFAULT; + if (check_add_overflow(up.offset, nr_args, &done)) + return -EOVERFLOW; + if (done > ctx->nr_user_files) + return -EINVAL; + + done = 0; + fds = (__s32 __user *) up.fds; + while (nr_args) { + struct fixed_file_table *table; + unsigned index; + + err = 0; + if (copy_from_user(&fd, &fds[done], sizeof(fd))) { + err = -EFAULT; + break; + } + i = array_index_nospec(up.offset, ctx->nr_user_files); + table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT]; + index = i & IORING_FILE_TABLE_MASK; + if (table->files[index]) { + io_sqe_file_unregister(ctx, i); + table->files[index] = NULL; + } + if (fd != -1) { + struct file *file; + + file = fget(fd); + if (!file) { + err = -EBADF; + break; + } + /* + * Don't allow io_uring instances to be registered. If + * UNIX isn't enabled, then this causes a reference + * cycle and this instance can never get freed. If UNIX + * is enabled we'll handle it just fine, but there's + * still no point in allowing a ring fd as it doesn't + * support regular read/write anyway. + */ + if (file->f_op == &io_uring_fops) { + fput(file); + err = -EBADF; + break; + } + table->files[index] = file; + err = io_sqe_file_register(ctx, file, i); + if (err) + break; + } + nr_args--; + done++; + up.offset++; + } + + return done ? done : err; +} + +static void io_put_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + io_put_req(req); +} + +static void io_get_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + refcount_inc(&req->refs); +} + static int io_sq_offload_start(struct io_ring_ctx *ctx, struct io_uring_params *p) { + unsigned concurrency; int ret; init_waitqueue_head(&ctx->sqo_wait); @@ -3186,26 +3942,13 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, goto err; } - /* Do QD, or 2 * CPUS, whatever is smallest */ - ctx->sqo_wq[0] = alloc_workqueue("io_ring-wq", - WQ_UNBOUND | WQ_FREEZABLE, - min(ctx->sq_entries - 1, 2 * num_online_cpus())); - if (!ctx->sqo_wq[0]) { - ret = -ENOMEM; - goto err; - } - - /* - * This is for buffered writes, where we want to limit the parallelism - * due to file locking in file systems. As "normal" buffered writes - * should parellelize on writeout quite nicely, limit us to having 2 - * pending. This avoids massive contention on the inode when doing - * buffered async writes. - */ - ctx->sqo_wq[1] = alloc_workqueue("io_ring-write-wq", - WQ_UNBOUND | WQ_FREEZABLE, 2); - if (!ctx->sqo_wq[1]) { - ret = -ENOMEM; + /* Do QD, or 4 * CPUS, whatever is smallest */ + concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); + ctx->io_wq = io_wq_create(concurrency, ctx->sqo_mm, ctx->user, + io_get_work, io_put_work); + if (IS_ERR(ctx->io_wq)) { + ret = PTR_ERR(ctx->io_wq); + ctx->io_wq = NULL; goto err; } @@ -3551,6 +4294,8 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_unaccount_mem(ctx->user, ring_pages(ctx->sq_entries, ctx->cq_entries)); free_uid(ctx->user); + kfree(ctx->completions); + kmem_cache_free(req_cachep, ctx->fallback_req); kfree(ctx); } @@ -3589,8 +4334,15 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_kill_timeouts(ctx); io_poll_remove_all(ctx); + + if (ctx->io_wq) + io_wq_cancel_all(ctx->io_wq); + io_iopoll_reap_events(ctx); - wait_for_completion(&ctx->ctx_done); + /* if we failed setting up the ctx, we might not have any rings */ + if (ctx->rings) + io_cqring_overflow_flush(ctx, true); + wait_for_completion(&ctx->completions[0]); io_ring_ctx_free(ctx); } @@ -3603,6 +4355,53 @@ static int io_uring_release(struct inode *inode, struct file *file) return 0; } +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; + + spin_lock_irq(&ctx->inflight_lock); + list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { + if (req->work.files != files) + continue; + /* req is being completed, ignore */ + if (!refcount_inc_not_zero(&req->refs)) + continue; + cancel_req = req; + break; + } + if (cancel_req) + prepare_to_wait(&ctx->inflight_wait, &wait, + TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&ctx->inflight_lock); + + /* We need to keep going until we don't find a matching req */ + if (!cancel_req) + break; + + io_wq_cancel_work(ctx->io_wq, &cancel_req->work); + io_put_req(cancel_req); + schedule(); + } + finish_wait(&ctx->inflight_wait, &wait); +} + +static int io_uring_flush(struct file *file, void *data) +{ + struct io_ring_ctx *ctx = file->private_data; + + io_uring_cancel_files(ctx, data); + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) { + io_cqring_overflow_flush(ctx, true); + io_wq_cancel_all(ctx->io_wq); + } + return 0; +} + static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) { loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT; @@ -3664,14 +4463,20 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, */ ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { + if (!list_empty_careful(&ctx->cq_overflow_list)) + io_cqring_overflow_flush(ctx, false); if (flags & IORING_ENTER_SQ_WAKEUP) wake_up(&ctx->sqo_wait); submitted = to_submit; } else if (to_submit) { - to_submit = min(to_submit, ctx->sq_entries); + struct mm_struct *cur_mm; + to_submit = min(to_submit, ctx->sq_entries); mutex_lock(&ctx->uring_lock); - submitted = io_ring_submit(ctx, to_submit); + /* 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); mutex_unlock(&ctx->uring_lock); } if (flags & IORING_ENTER_GETEVENTS) { @@ -3694,6 +4499,7 @@ out_fput: static const struct file_operations io_uring_fops = { .release = io_uring_release, + .flush = io_uring_flush, .mmap = io_uring_mmap, .poll = io_uring_poll, .fasync = io_uring_fasync, @@ -3793,10 +4599,23 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) * Use twice as many entries for the CQ ring. It's possible for the * application to drive a higher depth than the size of the SQ ring, * since the sqes are only used at submission time. This allows for - * some flexibility in overcommitting a bit. + * some flexibility in overcommitting a bit. If the application has + * set IORING_SETUP_CQSIZE, it will have passed in the desired number + * of CQ ring entries manually. */ p->sq_entries = roundup_pow_of_two(entries); - p->cq_entries = 2 * p->sq_entries; + if (p->flags & IORING_SETUP_CQSIZE) { + /* + * If IORING_SETUP_CQSIZE is set, we do the same roundup + * to a power-of-two, if it isn't already. We do NOT impose + * any cq vs sq ring sizing. + */ + if (p->cq_entries < p->sq_entries || p->cq_entries > IORING_MAX_CQ_ENTRIES) + return -EINVAL; + p->cq_entries = roundup_pow_of_two(p->cq_entries); + } else { + p->cq_entries = 2 * p->sq_entries; + } user = get_uid(current_user()); account_mem = !capable(CAP_IPC_LOCK); @@ -3855,7 +4674,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret < 0) goto err; - p->features = IORING_FEAT_SINGLE_MMAP; + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP; + trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: io_ring_ctx_wait_and_kill(ctx); @@ -3881,7 +4701,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) } if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | - IORING_SETUP_SQ_AFF)) + IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE)) return -EINVAL; ret = io_uring_create(entries, &p); @@ -3925,7 +4745,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, * no new references will come in after we've killed the percpu ref. */ mutex_unlock(&ctx->uring_lock); - wait_for_completion(&ctx->ctx_done); + wait_for_completion(&ctx->completions[0]); mutex_lock(&ctx->uring_lock); switch (opcode) { @@ -3947,6 +4767,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_sqe_files_unregister(ctx); break; + case IORING_REGISTER_FILES_UPDATE: + ret = io_sqe_files_update(ctx, arg, nr_args); + break; case IORING_REGISTER_EVENTFD: ret = -EINVAL; if (nr_args != 1) @@ -3965,7 +4788,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, } /* bring the ctx back to life */ - reinit_completion(&ctx->ctx_done); + reinit_completion(&ctx->completions[0]); percpu_ref_reinit(&ctx->refs); return ret; } @@ -3990,6 +4813,8 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, mutex_lock(&ctx->uring_lock); ret = __io_uring_register(ctx, opcode, arg, nr_args); mutex_unlock(&ctx->uring_lock); + trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, + ctx->cq_ev_fd != NULL, ret); out_fput: fdput(f); return ret; diff --git a/fs/namespace.c b/fs/namespace.c index fe0e9e1410fe..2adfe7b166a3 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2478,8 +2478,10 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount * time64_to_tm(sb->s_time_max, 0, &tm); - pr_warn("Mounted %s file system at %s supports timestamps until %04ld (0x%llx)\n", - sb->s_type->name, mntpath, + pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n", + sb->s_type->name, + is_mounted(mnt) ? "remounted" : "mounted", + mntpath, tm.tm_year+1900, (unsigned long long)sb->s_time_max); free_page((unsigned long)buf); @@ -2764,14 +2766,11 @@ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, if (IS_ERR(mnt)) return PTR_ERR(mnt); - error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags); - if (error < 0) { - mntput(mnt); - return error; - } - mnt_warn_timestamp_expiry(mountpoint, mnt); + error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags); + if (error < 0) + mntput(mnt); return error; } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index d8507972ee13..90c830e3758e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1490,6 +1490,18 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc, return loc->xl_ops->xlo_check_space(loc, xi); } +static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash) +{ + loc->xl_ops->xlo_add_entry(loc, name_hash); + loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash); + /* + * We can't leave the new entry's xe_name_offset at zero or + * add_namevalue() will go nuts. We set it to the size of our + * storage so that it can never be less than any other entry. + */ + loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size); +} + static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc, struct ocfs2_xattr_info *xi) { @@ -2121,31 +2133,29 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc, if (rc) goto out; - if (!loc->xl_entry) { - rc = -EINVAL; - goto out; - } - - if (ocfs2_xa_can_reuse_entry(loc, xi)) { - orig_value_size = loc->xl_entry->xe_value_size; - rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); - if (rc) - goto out; - goto alloc_value; - } + if (loc->xl_entry) { + if (ocfs2_xa_can_reuse_entry(loc, xi)) { + orig_value_size = loc->xl_entry->xe_value_size; + rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); + if (rc) + goto out; + goto alloc_value; + } - if (!ocfs2_xattr_is_local(loc->xl_entry)) { - orig_clusters = ocfs2_xa_value_clusters(loc); - rc = ocfs2_xa_value_truncate(loc, 0, ctxt); - if (rc) { - mlog_errno(rc); - ocfs2_xa_cleanup_value_truncate(loc, - "overwriting", - orig_clusters); - goto out; + if (!ocfs2_xattr_is_local(loc->xl_entry)) { + orig_clusters = ocfs2_xa_value_clusters(loc); + rc = ocfs2_xa_value_truncate(loc, 0, ctxt); + if (rc) { + mlog_errno(rc); + ocfs2_xa_cleanup_value_truncate(loc, + "overwriting", + orig_clusters); + goto out; + } } - } - ocfs2_xa_wipe_namevalue(loc); + ocfs2_xa_wipe_namevalue(loc); + } else + ocfs2_xa_add_entry(loc, name_hash); /* * If we get here, we have a blank entry. Fill it. We grow our diff --git a/fs/open.c b/fs/open.c index b62f5c0923a8..5c68282ea79e 100644 --- a/fs/open.c +++ b/fs/open.c @@ -771,10 +771,6 @@ static int do_dentry_open(struct file *f, f->f_mode |= FMODE_WRITER; } - /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) - f->f_mode |= FMODE_ATOMIC_POS; - f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; @@ -1256,7 +1252,7 @@ EXPORT_SYMBOL(nonseekable_open); */ int stream_open(struct inode *inode, struct file *filp) { - filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); filp->f_mode |= FMODE_STREAM; return 0; } diff --git a/fs/pipe.c b/fs/pipe.c index 8a2ab2f974bd..a9149199e0e7 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -793,6 +793,8 @@ int create_pipe_files(struct file **res, int flags) } res[0]->private_data = inode->i_pipe; res[1] = f; + stream_open(inode, res[0]); + stream_open(inode, res[1]); return 0; } @@ -931,9 +933,9 @@ static int fifo_open(struct inode *inode, struct file *filp) __pipe_lock(pipe); /* We can only do regular read/write on fifos */ - filp->f_mode &= (FMODE_READ | FMODE_WRITE); + stream_open(inode, filp); - switch (filp->f_mode) { + switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY diff --git a/include/Kbuild b/include/Kbuild index ffba79483cc5..95508049ee51 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -65,7 +65,6 @@ header-test- += keys/asymmetric-subtype.h header-test- += keys/asymmetric-type.h header-test- += keys/big_key-type.h header-test- += keys/request_key_auth-type.h -header-test- += keys/trusted.h header-test- += kvm/arm_arch_timer.h header-test- += kvm/arm_pmu.h header-test-$(CONFIG_ARM) += kvm/arm_psci.h @@ -1028,6 +1027,7 @@ header-test- += trace/events/fsi_master_gpio.h header-test- += trace/events/huge_memory.h header-test- += trace/events/ib_mad.h header-test- += trace/events/ib_umad.h +header-test- += trace/events/io_uring.h header-test- += trace/events/iscsi.h header-test- += trace/events/jbd2.h header-test- += trace/events/kvm.h diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h index e94b19782c92..ce4103208619 100644 --- a/include/asm-generic/vdso/vsyscall.h +++ b/include/asm-generic/vdso/vsyscall.h @@ -25,13 +25,6 @@ static __always_inline int __arch_get_clock_mode(struct timekeeper *tk) } #endif /* __arch_get_clock_mode */ -#ifndef __arch_use_vsyscall -static __always_inline int __arch_use_vsyscall(struct vdso_data *vdata) -{ - return 1; -} -#endif /* __arch_use_vsyscall */ - #ifndef __arch_update_vsyscall static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index dae64600ccbf..a9c4e4721434 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -110,17 +110,17 @@ #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD -#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY -#define MCOUNT_REC() . = ALIGN(8); \ - __start_mcount_loc = .; \ - KEEP(*(__patchable_function_entries)) \ - __stop_mcount_loc = .; -#else +/* + * The ftrace call sites are logged to a section whose name depends on the + * compiler option used. A given kernel image will only use one, AKA + * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header + * dependencies for FTRACE_CALLSITE_SECTION's definition. + */ #define MCOUNT_REC() . = ALIGN(8); \ __start_mcount_loc = .; \ KEEP(*(__mcount_loc)) \ + KEEP(*(__patchable_function_entries)) \ __stop_mcount_loc = .; -#endif #else #define MCOUNT_REC() #endif diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h index 987ff16b9420..e9ad4863d915 100644 --- a/include/drm/drm_cache.h +++ b/include/drm/drm_cache.h @@ -45,7 +45,7 @@ static inline bool drm_arch_can_wc_memory(void) { #if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE) return false; -#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3) +#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON64) return false; #elif defined(CONFIG_ARM) || defined(CONFIG_ARM64) /* diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 01f514521687..7865e6b5d36c 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -44,7 +44,20 @@ struct drm_gem_shmem_object { */ unsigned int pages_use_count; + /** + * @madv: State for madvise + * + * 0 is active/inuse. + * A negative value is the object is purged. + * Positive values are driver specific and not used by the helpers. + */ int madv; + + /** + * @madv_list: List entry for madvise tracking + * + * Typically used by drivers to track purgeable objects + */ struct list_head madv_list; /** diff --git a/include/drm/drm_self_refresh_helper.h b/include/drm/drm_self_refresh_helper.h index 5b79d253fb46..520235c20708 100644 --- a/include/drm/drm_self_refresh_helper.h +++ b/include/drm/drm_self_refresh_helper.h @@ -13,7 +13,8 @@ struct drm_crtc; void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state); void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, - unsigned int commit_time_ms); + unsigned int commit_time_ms, + unsigned int new_self_refresh_mask); int drm_self_refresh_helper_init(struct drm_crtc *crtc); void drm_self_refresh_helper_cleanup(struct drm_crtc *crtc); diff --git a/include/keys/trusted.h b/include/keys/trusted_tpm.h index 0071298b9b28..a56d8e1298f2 100644 --- a/include/keys/trusted.h +++ b/include/keys/trusted_tpm.h @@ -1,14 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __TRUSTED_KEY_H -#define __TRUSTED_KEY_H +#ifndef __TRUSTED_TPM_H +#define __TRUSTED_TPM_H + +#include <keys/trusted-type.h> +#include <linux/tpm_command.h> /* implementation specific TPM constants */ #define MAX_BUF_SIZE 1024 #define TPM_GETRANDOM_SIZE 14 -#define TPM_OSAP_SIZE 36 -#define TPM_OIAP_SIZE 10 -#define TPM_SEAL_SIZE 87 -#define TPM_UNSEAL_SIZE 104 #define TPM_SIZE_OFFSET 2 #define TPM_RETURN_OFFSET 6 #define TPM_DATA_OFFSET 10 @@ -17,13 +16,6 @@ #define LOAD32N(buffer, offset) (*(uint32_t *)&buffer[offset]) #define LOAD16(buffer, offset) (ntohs(*(uint16_t *)&buffer[offset])) -struct tpm_buf { - int len; - unsigned char data[MAX_BUF_SIZE]; -}; - -#define INIT_BUF(tb) (tb->len = 0) - struct osapsess { uint32_t handle; unsigned char secret[SHA1_DIGEST_SIZE]; @@ -48,6 +40,13 @@ int TSS_checkhmac1(unsigned char *buffer, int trusted_tpm_send(unsigned char *cmd, size_t buflen); int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce); +int tpm2_seal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options); +int tpm2_unseal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options); + #define TPM_DEBUG 0 #if TPM_DEBUG @@ -109,28 +108,4 @@ static inline void dump_tpm_buf(unsigned char *buf) { } #endif - -static inline void store8(struct tpm_buf *buf, const unsigned char value) -{ - buf->data[buf->len++] = value; -} - -static inline void store16(struct tpm_buf *buf, const uint16_t value) -{ - *(uint16_t *) & buf->data[buf->len] = htons(value); - buf->len += sizeof value; -} - -static inline void store32(struct tpm_buf *buf, const uint32_t value) -{ - *(uint32_t *) & buf->data[buf->len] = htonl(value); - buf->len += sizeof value; -} - -static inline void storebytes(struct tpm_buf *buf, const unsigned char *in, - const int len) -{ - memcpy(buf->data + buf->len, in, len); - buf->len += len; -} #endif diff --git a/include/kunit/assert.h b/include/kunit/assert.h new file mode 100644 index 000000000000..db6a0fca09b4 --- /dev/null +++ b/include/kunit/assert.h @@ -0,0 +1,356 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Assertion and expectation serialization API. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#ifndef _KUNIT_ASSERT_H +#define _KUNIT_ASSERT_H + +#include <kunit/string-stream.h> +#include <linux/err.h> + +struct kunit; + +/** + * enum kunit_assert_type - Type of expectation/assertion. + * @KUNIT_ASSERTION: Used to denote that a kunit_assert represents an assertion. + * @KUNIT_EXPECTATION: Denotes that a kunit_assert represents an expectation. + * + * Used in conjunction with a &struct kunit_assert to denote whether it + * represents an expectation or an assertion. + */ +enum kunit_assert_type { + KUNIT_ASSERTION, + KUNIT_EXPECTATION, +}; + +/** + * struct kunit_assert - Data for printing a failed assertion or expectation. + * @test: the test case this expectation/assertion is associated with. + * @type: the type (either an expectation or an assertion) of this kunit_assert. + * @line: the source code line number that the expectation/assertion is at. + * @file: the file path of the source file that the expectation/assertion is in. + * @message: an optional message to provide additional context. + * @format: a function which formats the data in this kunit_assert to a string. + * + * Represents a failed expectation/assertion. Contains all the data necessary to + * format a string to a user reporting the failure. + */ +struct kunit_assert { + struct kunit *test; + enum kunit_assert_type type; + int line; + const char *file; + struct va_format message; + void (*format)(const struct kunit_assert *assert, + struct string_stream *stream); +}; + +/** + * KUNIT_INIT_VA_FMT_NULL - Default initializer for struct va_format. + * + * Used inside a struct initialization block to initialize struct va_format to + * default values where fmt and va are null. + */ +#define KUNIT_INIT_VA_FMT_NULL { .fmt = NULL, .va = NULL } + +/** + * KUNIT_INIT_ASSERT_STRUCT() - Initializer for a &struct kunit_assert. + * @kunit: The test case that this expectation/assertion is associated with. + * @assert_type: The type (assertion or expectation) of this kunit_assert. + * @fmt: The formatting function which builds a string out of this kunit_assert. + * + * The base initializer for a &struct kunit_assert. + */ +#define KUNIT_INIT_ASSERT_STRUCT(kunit, assert_type, fmt) { \ + .test = kunit, \ + .type = assert_type, \ + .file = __FILE__, \ + .line = __LINE__, \ + .message = KUNIT_INIT_VA_FMT_NULL, \ + .format = fmt \ +} + +void kunit_base_assert_format(const struct kunit_assert *assert, + struct string_stream *stream); + +void kunit_assert_print_msg(const struct kunit_assert *assert, + struct string_stream *stream); + +/** + * struct kunit_fail_assert - Represents a plain fail expectation/assertion. + * @assert: The parent of this type. + * + * Represents a simple KUNIT_FAIL/KUNIT_ASSERT_FAILURE that always fails. + */ +struct kunit_fail_assert { + struct kunit_assert assert; +}; + +void kunit_fail_assert_format(const struct kunit_assert *assert, + struct string_stream *stream); + +/** + * KUNIT_INIT_FAIL_ASSERT_STRUCT() - Initializer for &struct kunit_fail_assert. + * @test: The test case that this expectation/assertion is associated with. + * @type: The type (assertion or expectation) of this kunit_assert. + * + * Initializes a &struct kunit_fail_assert. Intended to be used in + * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. + */ +#define KUNIT_INIT_FAIL_ASSERT_STRUCT(test, type) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ + type, \ + kunit_fail_assert_format) \ +} + +/** + * struct kunit_unary_assert - Represents a KUNIT_{EXPECT|ASSERT}_{TRUE|FALSE} + * @assert: The parent of this type. + * @condition: A string representation of a conditional expression. + * @expected_true: True if of type KUNIT_{EXPECT|ASSERT}_TRUE, false otherwise. + * + * Represents a simple expectation or assertion that simply asserts something is + * true or false. In other words, represents the expectations: + * KUNIT_{EXPECT|ASSERT}_{TRUE|FALSE} + */ +struct kunit_unary_assert { + struct kunit_assert assert; + const char *condition; + bool expected_true; +}; + +void kunit_unary_assert_format(const struct kunit_assert *assert, + struct string_stream *stream); + +/** + * KUNIT_INIT_UNARY_ASSERT_STRUCT() - Initializes &struct kunit_unary_assert. + * @test: The test case that this expectation/assertion is associated with. + * @type: The type (assertion or expectation) of this kunit_assert. + * @cond: A string representation of the expression asserted true or false. + * @expect_true: True if of type KUNIT_{EXPECT|ASSERT}_TRUE, false otherwise. + * + * Initializes a &struct kunit_unary_assert. Intended to be used in + * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. + */ +#define KUNIT_INIT_UNARY_ASSERT_STRUCT(test, type, cond, expect_true) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ + type, \ + kunit_unary_assert_format), \ + .condition = cond, \ + .expected_true = expect_true \ +} + +/** + * struct kunit_ptr_not_err_assert - An expectation/assertion that a pointer is + * not NULL and not a -errno. + * @assert: The parent of this type. + * @text: A string representation of the expression passed to the expectation. + * @value: The actual evaluated pointer value of the expression. + * + * Represents an expectation/assertion that a pointer is not null and is does + * not contain a -errno. (See IS_ERR_OR_NULL().) + */ +struct kunit_ptr_not_err_assert { + struct kunit_assert assert; + const char *text; + const void *value; +}; + +void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, + struct string_stream *stream); + +/** + * KUNIT_INIT_PTR_NOT_ERR_ASSERT_STRUCT() - Initializes a + * &struct kunit_ptr_not_err_assert. + * @test: The test case that this expectation/assertion is associated with. + * @type: The type (assertion or expectation) of this kunit_assert. + * @txt: A string representation of the expression passed to the expectation. + * @val: The actual evaluated pointer value of the expression. + * + * Initializes a &struct kunit_ptr_not_err_assert. Intended to be used in + * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. + */ +#define KUNIT_INIT_PTR_NOT_ERR_STRUCT(test, type, txt, val) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ + type, \ + kunit_ptr_not_err_assert_format), \ + .text = txt, \ + .value = val \ +} + +/** + * struct kunit_binary_assert - An expectation/assertion that compares two + * non-pointer values (for example, KUNIT_EXPECT_EQ(test, 1 + 1, 2)). + * @assert: The parent of this type. + * @operation: A string representation of the comparison operator (e.g. "=="). + * @left_text: A string representation of the expression in the left slot. + * @left_value: The actual evaluated value of the expression in the left slot. + * @right_text: A string representation of the expression in the right slot. + * @right_value: The actual evaluated value of the expression in the right slot. + * + * Represents an expectation/assertion that compares two non-pointer values. For + * example, to expect that 1 + 1 == 2, you can use the expectation + * KUNIT_EXPECT_EQ(test, 1 + 1, 2); + */ +struct kunit_binary_assert { + struct kunit_assert assert; + const char *operation; + const char *left_text; + long long left_value; + const char *right_text; + long long right_value; +}; + +void kunit_binary_assert_format(const struct kunit_assert *assert, + struct string_stream *stream); + +/** + * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a + * &struct kunit_binary_assert. + * @test: The test case that this expectation/assertion is associated with. + * @type: The type (assertion or expectation) of this kunit_assert. + * @op_str: A string representation of the comparison operator (e.g. "=="). + * @left_str: A string representation of the expression in the left slot. + * @left_val: The actual evaluated value of the expression in the left slot. + * @right_str: A string representation of the expression in the right slot. + * @right_val: The actual evaluated value of the expression in the right slot. + * + * Initializes a &struct kunit_binary_assert. Intended to be used in + * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. + */ +#define KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \ + type, \ + op_str, \ + left_str, \ + left_val, \ + right_str, \ + right_val) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ + type, \ + kunit_binary_assert_format), \ + .operation = op_str, \ + .left_text = left_str, \ + .left_value = left_val, \ + .right_text = right_str, \ + .right_value = right_val \ +} + +/** + * struct kunit_binary_ptr_assert - An expectation/assertion that compares two + * pointer values (for example, KUNIT_EXPECT_PTR_EQ(test, foo, bar)). + * @assert: The parent of this type. + * @operation: A string representation of the comparison operator (e.g. "=="). + * @left_text: A string representation of the expression in the left slot. + * @left_value: The actual evaluated value of the expression in the left slot. + * @right_text: A string representation of the expression in the right slot. + * @right_value: The actual evaluated value of the expression in the right slot. + * + * Represents an expectation/assertion that compares two pointer values. For + * example, to expect that foo and bar point to the same thing, you can use the + * expectation KUNIT_EXPECT_PTR_EQ(test, foo, bar); + */ +struct kunit_binary_ptr_assert { + struct kunit_assert assert; + const char *operation; + const char *left_text; + const void *left_value; + const char *right_text; + const void *right_value; +}; + +void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, + struct string_stream *stream); + +/** + * KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT() - Initializes a + * &struct kunit_binary_ptr_assert. + * @test: The test case that this expectation/assertion is associated with. + * @type: The type (assertion or expectation) of this kunit_assert. + * @op_str: A string representation of the comparison operator (e.g. "=="). + * @left_str: A string representation of the expression in the left slot. + * @left_val: The actual evaluated value of the expression in the left slot. + * @right_str: A string representation of the expression in the right slot. + * @right_val: The actual evaluated value of the expression in the right slot. + * + * Initializes a &struct kunit_binary_ptr_assert. Intended to be used in + * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. + */ +#define KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT(test, \ + type, \ + op_str, \ + left_str, \ + left_val, \ + right_str, \ + right_val) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ + type, \ + kunit_binary_ptr_assert_format), \ + .operation = op_str, \ + .left_text = left_str, \ + .left_value = left_val, \ + .right_text = right_str, \ + .right_value = right_val \ +} + +/** + * struct kunit_binary_str_assert - An expectation/assertion that compares two + * string values (for example, KUNIT_EXPECT_STREQ(test, foo, "bar")). + * @assert: The parent of this type. + * @operation: A string representation of the comparison operator (e.g. "=="). + * @left_text: A string representation of the expression in the left slot. + * @left_value: The actual evaluated value of the expression in the left slot. + * @right_text: A string representation of the expression in the right slot. + * @right_value: The actual evaluated value of the expression in the right slot. + * + * Represents an expectation/assertion that compares two string values. For + * example, to expect that the string in foo is equal to "bar", you can use the + * expectation KUNIT_EXPECT_STREQ(test, foo, "bar"); + */ +struct kunit_binary_str_assert { + struct kunit_assert assert; + const char *operation; + const char *left_text; + const char *left_value; + const char *right_text; + const char *right_value; +}; + +void kunit_binary_str_assert_format(const struct kunit_assert *assert, + struct string_stream *stream); + +/** + * KUNIT_INIT_BINARY_STR_ASSERT_STRUCT() - Initializes a + * &struct kunit_binary_str_assert. + * @test: The test case that this expectation/assertion is associated with. + * @type: The type (assertion or expectation) of this kunit_assert. + * @op_str: A string representation of the comparison operator (e.g. "=="). + * @left_str: A string representation of the expression in the left slot. + * @left_val: The actual evaluated value of the expression in the left slot. + * @right_str: A string representation of the expression in the right slot. + * @right_val: The actual evaluated value of the expression in the right slot. + * + * Initializes a &struct kunit_binary_str_assert. Intended to be used in + * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. + */ +#define KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \ + type, \ + op_str, \ + left_str, \ + left_val, \ + right_str, \ + right_val) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ + type, \ + kunit_binary_str_assert_format), \ + .operation = op_str, \ + .left_text = left_str, \ + .left_value = left_val, \ + .right_text = right_str, \ + .right_value = right_val \ +} + +#endif /* _KUNIT_ASSERT_H */ diff --git a/include/kunit/string-stream.h b/include/kunit/string-stream.h new file mode 100644 index 000000000000..fe98a00b75a9 --- /dev/null +++ b/include/kunit/string-stream.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * C++ stream style string builder used in KUnit for building messages. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#ifndef _KUNIT_STRING_STREAM_H +#define _KUNIT_STRING_STREAM_H + +#include <linux/spinlock.h> +#include <linux/types.h> +#include <stdarg.h> + +struct string_stream_fragment { + struct kunit *test; + struct list_head node; + char *fragment; +}; + +struct string_stream { + size_t length; + struct list_head fragments; + /* length and fragments are protected by this lock */ + spinlock_t lock; + struct kunit *test; + gfp_t gfp; +}; + +struct kunit; + +struct string_stream *alloc_string_stream(struct kunit *test, gfp_t gfp); + +int __printf(2, 3) string_stream_add(struct string_stream *stream, + const char *fmt, ...); + +int string_stream_vadd(struct string_stream *stream, + const char *fmt, + va_list args); + +char *string_stream_get_string(struct string_stream *stream); + +int string_stream_append(struct string_stream *stream, + struct string_stream *other); + +bool string_stream_is_empty(struct string_stream *stream); + +int string_stream_destroy(struct string_stream *stream); + +#endif /* _KUNIT_STRING_STREAM_H */ diff --git a/include/kunit/test.h b/include/kunit/test.h new file mode 100644 index 000000000000..dba48304b3bd --- /dev/null +++ b/include/kunit/test.h @@ -0,0 +1,1490 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Base unit test (KUnit) API. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#ifndef _KUNIT_TEST_H +#define _KUNIT_TEST_H + +#include <kunit/assert.h> +#include <kunit/try-catch.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/types.h> + +struct kunit_resource; + +typedef int (*kunit_resource_init_t)(struct kunit_resource *, void *); +typedef void (*kunit_resource_free_t)(struct kunit_resource *); + +/** + * struct kunit_resource - represents a *test managed resource* + * @allocation: for the user to store arbitrary data. + * @free: a user supplied function to free the resource. Populated by + * kunit_alloc_resource(). + * + * Represents a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. + * + * Example: + * + * .. code-block:: c + * + * struct kunit_kmalloc_params { + * size_t size; + * gfp_t gfp; + * }; + * + * static int kunit_kmalloc_init(struct kunit_resource *res, void *context) + * { + * struct kunit_kmalloc_params *params = context; + * res->allocation = kmalloc(params->size, params->gfp); + * + * if (!res->allocation) + * return -ENOMEM; + * + * return 0; + * } + * + * static void kunit_kmalloc_free(struct kunit_resource *res) + * { + * kfree(res->allocation); + * } + * + * void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp) + * { + * struct kunit_kmalloc_params params; + * struct kunit_resource *res; + * + * params.size = size; + * params.gfp = gfp; + * + * res = kunit_alloc_resource(test, kunit_kmalloc_init, + * kunit_kmalloc_free, ¶ms); + * if (res) + * return res->allocation; + * + * return NULL; + * } + */ +struct kunit_resource { + void *allocation; + kunit_resource_free_t free; + + /* private: internal use only. */ + struct list_head node; +}; + +struct kunit; + +/** + * struct kunit_case - represents an individual test case. + * + * @run_case: the function representing the actual test case. + * @name: the name of the test case. + * + * A test case is a function with the signature, + * ``void (*)(struct kunit *)`` + * that makes expectations and assertions (see KUNIT_EXPECT_TRUE() and + * KUNIT_ASSERT_TRUE()) about code under test. Each test case is associated + * with a &struct kunit_suite and will be run after the suite's init + * function and followed by the suite's exit function. + * + * A test case should be static and should only be created with the + * KUNIT_CASE() macro; additionally, every array of test cases should be + * terminated with an empty test case. + * + * Example: + * + * .. code-block:: c + * + * void add_test_basic(struct kunit *test) + * { + * KUNIT_EXPECT_EQ(test, 1, add(1, 0)); + * KUNIT_EXPECT_EQ(test, 2, add(1, 1)); + * KUNIT_EXPECT_EQ(test, 0, add(-1, 1)); + * KUNIT_EXPECT_EQ(test, INT_MAX, add(0, INT_MAX)); + * KUNIT_EXPECT_EQ(test, -1, add(INT_MAX, INT_MIN)); + * } + * + * static struct kunit_case example_test_cases[] = { + * KUNIT_CASE(add_test_basic), + * {} + * }; + * + */ +struct kunit_case { + void (*run_case)(struct kunit *test); + const char *name; + + /* private: internal use only. */ + bool success; +}; + +/** + * KUNIT_CASE - A helper for creating a &struct kunit_case + * + * @test_name: a reference to a test case function. + * + * Takes a symbol for a function representing a test case and creates a + * &struct kunit_case object from it. See the documentation for + * &struct kunit_case for an example on how to use it. + */ +#define KUNIT_CASE(test_name) { .run_case = test_name, .name = #test_name } + +/** + * struct kunit_suite - describes a related collection of &struct kunit_case + * + * @name: the name of the test. Purely informational. + * @init: called before every test case. + * @exit: called after every test case. + * @test_cases: a null terminated array of test cases. + * + * A kunit_suite is a collection of related &struct kunit_case s, such that + * @init is called before every test case and @exit is called after every + * test case, similar to the notion of a *test fixture* or a *test class* + * in other unit testing frameworks like JUnit or Googletest. + * + * Every &struct kunit_case must be associated with a kunit_suite for KUnit + * to run it. + */ +struct kunit_suite { + const char name[256]; + int (*init)(struct kunit *test); + void (*exit)(struct kunit *test); + struct kunit_case *test_cases; +}; + +/** + * struct kunit - represents a running instance of a test. + * + * @priv: for user to store arbitrary data. Commonly used to pass data + * created in the init function (see &struct kunit_suite). + * + * Used to store information about the current context under which the test + * is running. Most of this data is private and should only be accessed + * indirectly via public functions; the one exception is @priv which can be + * used by the test writer to store arbitrary data. + */ +struct kunit { + void *priv; + + /* private: internal use only. */ + const char *name; /* Read only after initialization! */ + struct kunit_try_catch try_catch; + /* + * success starts as true, and may only be set to false during a + * test case; thus, it is safe to update this across multiple + * threads using WRITE_ONCE; however, as a consequence, it may only + * be read after the test case finishes once all threads associated + * with the test case have terminated. + */ + bool success; /* Read only after test_case finishes! */ + spinlock_t lock; /* Guards all mutable test state. */ + /* + * Because resources is a list that may be updated multiple times (with + * new resources) from any thread associated with a test case, we must + * protect it with some type of lock. + */ + struct list_head resources; /* Protected by lock. */ +}; + +void kunit_init_test(struct kunit *test, const char *name); + +int kunit_run_tests(struct kunit_suite *suite); + +/** + * kunit_test_suite() - used to register a &struct kunit_suite with KUnit. + * + * @suite: a statically allocated &struct kunit_suite. + * + * Registers @suite with the test framework. See &struct kunit_suite for + * more information. + * + * NOTE: Currently KUnit tests are all run as late_initcalls; this means + * that they cannot test anything where tests must run at a different init + * phase. One significant restriction resulting from this is that KUnit + * cannot reliably test anything that is initialize in the late_init phase; + * another is that KUnit is useless to test things that need to be run in + * an earlier init phase. + * + * TODO(brendanhiggins@google.com): Don't run all KUnit tests as + * late_initcalls. I have some future work planned to dispatch all KUnit + * tests from the same place, and at the very least to do so after + * everything else is definitely initialized. + */ +#define kunit_test_suite(suite) \ + static int kunit_suite_init##suite(void) \ + { \ + return kunit_run_tests(&suite); \ + } \ + late_initcall(kunit_suite_init##suite) + +/* + * Like kunit_alloc_resource() below, but returns the struct kunit_resource + * object that contains the allocation. This is mostly for testing purposes. + */ +struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + gfp_t internal_gfp, + void *context); + +/** + * kunit_alloc_resource() - Allocates a *test managed resource*. + * @test: The test context object. + * @init: a user supplied function to initialize the resource. + * @free: a user supplied function to free the resource. + * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL + * @context: for the user to pass in arbitrary data to the init function. + * + * Allocates a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. See &struct kunit_resource for an + * example. + * + * NOTE: KUnit needs to allocate memory for each kunit_resource object. You must + * specify an @internal_gfp that is compatible with the use context of your + * resource. + */ +static inline void *kunit_alloc_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + gfp_t internal_gfp, + void *context) +{ + struct kunit_resource *res; + + res = kunit_alloc_and_get_resource(test, init, free, internal_gfp, + context); + + if (res) + return res->allocation; + + return NULL; +} + +typedef bool (*kunit_resource_match_t)(struct kunit *test, + const void *res, + void *match_data); + +/** + * kunit_resource_instance_match() - Match a resource with the same instance. + * @test: Test case to which the resource belongs. + * @res: The data stored in kunit_resource->allocation. + * @match_data: The resource pointer to match against. + * + * An instance of kunit_resource_match_t that matches a resource whose + * allocation matches @match_data. + */ +static inline bool kunit_resource_instance_match(struct kunit *test, + const void *res, + void *match_data) +{ + return res == match_data; +} + +/** + * kunit_resource_destroy() - Find a kunit_resource and destroy it. + * @test: Test case to which the resource belongs. + * @match: Match function. Returns whether a given resource matches @match_data. + * @free: Must match free on the kunit_resource to free. + * @match_data: Data passed into @match. + * + * Free the latest kunit_resource of @test for which @free matches the + * kunit_resource_free_t associated with the resource and for which @match + * returns true. + * + * RETURNS: + * 0 if kunit_resource is found and freed, -ENOENT if not found. + */ +int kunit_resource_destroy(struct kunit *test, + kunit_resource_match_t match, + kunit_resource_free_t free, + void *match_data); + +/** + * kunit_kmalloc() - Like kmalloc() except the allocation is *test managed*. + * @test: The test context object. + * @size: The size in bytes of the desired memory. + * @gfp: flags passed to underlying kmalloc(). + * + * Just like `kmalloc(...)`, except the allocation is managed by the test case + * and is automatically cleaned up after the test case concludes. See &struct + * kunit_resource for more information. + */ +void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp); + +/** + * kunit_kfree() - Like kfree except for allocations managed by KUnit. + * @test: The test case to which the resource belongs. + * @ptr: The memory allocation to free. + */ +void kunit_kfree(struct kunit *test, const void *ptr); + +/** + * kunit_kzalloc() - Just like kunit_kmalloc(), but zeroes the allocation. + * @test: The test context object. + * @size: The size in bytes of the desired memory. + * @gfp: flags passed to underlying kmalloc(). + * + * See kzalloc() and kunit_kmalloc() for more information. + */ +static inline void *kunit_kzalloc(struct kunit *test, size_t size, gfp_t gfp) +{ + return kunit_kmalloc(test, size, gfp | __GFP_ZERO); +} + +void kunit_cleanup(struct kunit *test); + +#define kunit_printk(lvl, test, fmt, ...) \ + printk(lvl "\t# %s: " fmt, (test)->name, ##__VA_ARGS__) + +/** + * kunit_info() - Prints an INFO level message associated with @test. + * + * @test: The test context object. + * @fmt: A printk() style format string. + * + * Prints an info level message associated with the test suite being run. + * Takes a variable number of format parameters just like printk(). + */ +#define kunit_info(test, fmt, ...) \ + kunit_printk(KERN_INFO, test, fmt, ##__VA_ARGS__) + +/** + * kunit_warn() - Prints a WARN level message associated with @test. + * + * @test: The test context object. + * @fmt: A printk() style format string. + * + * Prints a warning level message. + */ +#define kunit_warn(test, fmt, ...) \ + kunit_printk(KERN_WARNING, test, fmt, ##__VA_ARGS__) + +/** + * kunit_err() - Prints an ERROR level message associated with @test. + * + * @test: The test context object. + * @fmt: A printk() style format string. + * + * Prints an error level message. + */ +#define kunit_err(test, fmt, ...) \ + kunit_printk(KERN_ERR, test, fmt, ##__VA_ARGS__) + +/** + * KUNIT_SUCCEED() - A no-op expectation. Only exists for code clarity. + * @test: The test context object. + * + * The opposite of KUNIT_FAIL(), it is an expectation that cannot fail. In other + * words, it does nothing and only exists for code clarity. See + * KUNIT_EXPECT_TRUE() for more information. + */ +#define KUNIT_SUCCEED(test) do {} while (0) + +void kunit_do_assertion(struct kunit *test, + struct kunit_assert *assert, + bool pass, + const char *fmt, ...); + +#define KUNIT_ASSERTION(test, pass, assert_class, INITIALIZER, fmt, ...) do { \ + struct assert_class __assertion = INITIALIZER; \ + kunit_do_assertion(test, \ + &__assertion.assert, \ + pass, \ + fmt, \ + ##__VA_ARGS__); \ +} while (0) + + +#define KUNIT_FAIL_ASSERTION(test, assert_type, fmt, ...) \ + KUNIT_ASSERTION(test, \ + false, \ + kunit_fail_assert, \ + KUNIT_INIT_FAIL_ASSERT_STRUCT(test, assert_type), \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_FAIL() - Always causes a test to fail when evaluated. + * @test: The test context object. + * @fmt: an informational message to be printed when the assertion is made. + * @...: string format arguments. + * + * The opposite of KUNIT_SUCCEED(), it is an expectation that always fails. In + * other words, it always results in a failed expectation, and consequently + * always causes the test case to fail when evaluated. See KUNIT_EXPECT_TRUE() + * for more information. + */ +#define KUNIT_FAIL(test, fmt, ...) \ + KUNIT_FAIL_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_UNARY_ASSERTION(test, \ + assert_type, \ + condition, \ + expected_true, \ + fmt, \ + ...) \ + KUNIT_ASSERTION(test, \ + !!(condition) == !!expected_true, \ + kunit_unary_assert, \ + KUNIT_INIT_UNARY_ASSERT_STRUCT(test, \ + assert_type, \ + #condition, \ + expected_true), \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_TRUE_MSG_ASSERTION(test, assert_type, condition, fmt, ...) \ + KUNIT_UNARY_ASSERTION(test, \ + assert_type, \ + condition, \ + true, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_TRUE_ASSERTION(test, assert_type, condition) \ + KUNIT_TRUE_MSG_ASSERTION(test, assert_type, condition, NULL) + +#define KUNIT_FALSE_MSG_ASSERTION(test, assert_type, condition, fmt, ...) \ + KUNIT_UNARY_ASSERTION(test, \ + assert_type, \ + condition, \ + false, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_FALSE_ASSERTION(test, assert_type, condition) \ + KUNIT_FALSE_MSG_ASSERTION(test, assert_type, condition, NULL) + +/* + * A factory macro for defining the assertions and expectations for the basic + * comparisons defined for the built in types. + * + * Unfortunately, there is no common type that all types can be promoted to for + * which all the binary operators behave the same way as for the actual types + * (for example, there is no type that long long and unsigned long long can + * both be cast to where the comparison result is preserved for all values). So + * the best we can do is do the comparison in the original types and then coerce + * everything to long long for printing; this way, the comparison behaves + * correctly and the printed out value usually makes sense without + * interpretation, but can always be interpreted to figure out the actual + * value. + */ +#define KUNIT_BASE_BINARY_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, \ + op, \ + right, \ + fmt, \ + ...) \ +do { \ + typeof(left) __left = (left); \ + typeof(right) __right = (right); \ + ((void)__typecheck(__left, __right)); \ + \ + KUNIT_ASSERTION(test, \ + __left op __right, \ + assert_class, \ + ASSERT_CLASS_INIT(test, \ + assert_type, \ + #op, \ + #left, \ + __left, \ + #right, \ + __right), \ + fmt, \ + ##__VA_ARGS__); \ +} while (0) + +#define KUNIT_BASE_EQ_MSG_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_BINARY_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BASE_NE_MSG_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_BINARY_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BASE_LT_MSG_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_BINARY_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, <, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BASE_LE_MSG_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_BINARY_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, <=, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BASE_GT_MSG_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_BINARY_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, >, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BASE_GE_MSG_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_BINARY_ASSERTION(test, \ + assert_class, \ + ASSERT_CLASS_INIT, \ + assert_type, \ + left, >=, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_EQ_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ + KUNIT_BASE_EQ_MSG_ASSERTION(test, \ + kunit_binary_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_EQ_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_EQ_MSG_ASSERTION(test, \ + kunit_binary_ptr_assert, \ + KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_PTR_EQ_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_NE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ + KUNIT_BASE_NE_MSG_ASSERTION(test, \ + kunit_binary_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_NE_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_NE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_NE_MSG_ASSERTION(test, \ + kunit_binary_ptr_assert, \ + KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_PTR_NE_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_LT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ + KUNIT_BASE_LT_MSG_ASSERTION(test, \ + kunit_binary_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_LT_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_LT_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_PTR_LT_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_LT_MSG_ASSERTION(test, \ + kunit_binary_ptr_assert, \ + KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_PTR_LT_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_PTR_LT_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_LE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ + KUNIT_BASE_LE_MSG_ASSERTION(test, \ + kunit_binary_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_LE_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_LE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_PTR_LE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_LE_MSG_ASSERTION(test, \ + kunit_binary_ptr_assert, \ + KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_PTR_LE_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_PTR_LE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_GT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ + KUNIT_BASE_GT_MSG_ASSERTION(test, \ + kunit_binary_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_GT_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_GT_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_PTR_GT_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_GT_MSG_ASSERTION(test, \ + kunit_binary_ptr_assert, \ + KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_PTR_GT_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_PTR_GT_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_GE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ + KUNIT_BASE_GE_MSG_ASSERTION(test, \ + kunit_binary_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_GE_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_GE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_PTR_GE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_GE_MSG_ASSERTION(test, \ + kunit_binary_ptr_assert, \ + KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_PTR_GE_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_PTR_GE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_STR_ASSERTION(test, \ + assert_type, \ + left, \ + op, \ + right, \ + fmt, \ + ...) \ +do { \ + typeof(left) __left = (left); \ + typeof(right) __right = (right); \ + \ + KUNIT_ASSERTION(test, \ + strcmp(__left, __right) op 0, \ + kunit_binary_str_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \ + assert_type, \ + #op, \ + #left, \ + __left, \ + #right, \ + __right), \ + fmt, \ + ##__VA_ARGS__); \ +} while (0) + +#define KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BINARY_STR_ASSERTION(test, \ + assert_type, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_STR_EQ_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + fmt, \ + ...) \ + KUNIT_BINARY_STR_ASSERTION(test, \ + assert_type, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_BINARY_STR_NE_ASSERTION(test, assert_type, left, right) \ + KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ + assert_type, \ + left, \ + right, \ + NULL) + +#define KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ + assert_type, \ + ptr, \ + fmt, \ + ...) \ +do { \ + typeof(ptr) __ptr = (ptr); \ + \ + KUNIT_ASSERTION(test, \ + !IS_ERR_OR_NULL(__ptr), \ + kunit_ptr_not_err_assert, \ + KUNIT_INIT_PTR_NOT_ERR_STRUCT(test, \ + assert_type, \ + #ptr, \ + __ptr), \ + fmt, \ + ##__VA_ARGS__); \ +} while (0) + +#define KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, assert_type, ptr) \ + KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ + assert_type, \ + ptr, \ + NULL) + +/** + * KUNIT_EXPECT_TRUE() - Causes a test failure when the expression is not true. + * @test: The test context object. + * @condition: an arbitrary boolean expression. The test fails when this does + * not evaluate to true. + * + * This and expectations of the form `KUNIT_EXPECT_*` will cause the test case + * to fail when the specified condition is not met; however, it will not prevent + * the test case from continuing to run; this is otherwise known as an + * *expectation failure*. + */ +#define KUNIT_EXPECT_TRUE(test, condition) \ + KUNIT_TRUE_ASSERTION(test, KUNIT_EXPECTATION, condition) + +#define KUNIT_EXPECT_TRUE_MSG(test, condition, fmt, ...) \ + KUNIT_TRUE_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + condition, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_FALSE() - Makes a test failure when the expression is not false. + * @test: The test context object. + * @condition: an arbitrary boolean expression. The test fails when this does + * not evaluate to false. + * + * Sets an expectation that @condition evaluates to false. See + * KUNIT_EXPECT_TRUE() for more information. + */ +#define KUNIT_EXPECT_FALSE(test, condition) \ + KUNIT_FALSE_ASSERTION(test, KUNIT_EXPECTATION, condition) + +#define KUNIT_EXPECT_FALSE_MSG(test, condition, fmt, ...) \ + KUNIT_FALSE_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + condition, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_EQ() - Sets an expectation that @left and @right are equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an expectation that the values that @left and @right evaluate to are + * equal. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, (@left) == (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_EQ(test, left, right) \ + KUNIT_BINARY_EQ_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_EQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_PTR_EQ() - Expects that pointers @left and @right are equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a pointer. + * @right: an arbitrary expression that evaluates to a pointer. + * + * Sets an expectation that the values that @left and @right evaluate to are + * equal. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, (@left) == (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_PTR_EQ(test, left, right) \ + KUNIT_BINARY_PTR_EQ_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right) + +#define KUNIT_EXPECT_PTR_EQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_NE() - An expectation that @left and @right are not equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an expectation that the values that @left and @right evaluate to are not + * equal. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, (@left) != (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_NE(test, left, right) \ + KUNIT_BINARY_NE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_NE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_NE_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_PTR_NE() - Expects that pointers @left and @right are not equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a pointer. + * @right: an arbitrary expression that evaluates to a pointer. + * + * Sets an expectation that the values that @left and @right evaluate to are not + * equal. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, (@left) != (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_PTR_NE(test, left, right) \ + KUNIT_BINARY_PTR_NE_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right) + +#define KUNIT_EXPECT_PTR_NE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_LT() - An expectation that @left is less than @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an expectation that the value that @left evaluates to is less than the + * value that @right evaluates to. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, (@left) < (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_LT(test, left, right) \ + KUNIT_BINARY_LT_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_LT_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_LT_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_LE() - Expects that @left is less than or equal to @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an expectation that the value that @left evaluates to is less than or + * equal to the value that @right evaluates to. Semantically this is equivalent + * to KUNIT_EXPECT_TRUE(@test, (@left) <= (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_LE(test, left, right) \ + KUNIT_BINARY_LE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_LE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_LE_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_GT() - An expectation that @left is greater than @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an expectation that the value that @left evaluates to is greater than + * the value that @right evaluates to. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, (@left) > (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_GT(test, left, right) \ + KUNIT_BINARY_GT_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_GT_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_GT_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_GE() - Expects that @left is greater than or equal to @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an expectation that the value that @left evaluates to is greater than + * the value that @right evaluates to. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, (@left) >= (@right)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_GE(test, left, right) \ + KUNIT_BINARY_GE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_GE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_GE_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_STREQ() - Expects that strings @left and @right are equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a null terminated string. + * @right: an arbitrary expression that evaluates to a null terminated string. + * + * Sets an expectation that the values that @left and @right evaluate to are + * equal. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, !strcmp((@left), (@right))). See KUNIT_EXPECT_TRUE() + * for more information. + */ +#define KUNIT_EXPECT_STREQ(test, left, right) \ + KUNIT_BINARY_STR_EQ_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_STREQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_STRNEQ() - Expects that strings @left and @right are not equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a null terminated string. + * @right: an arbitrary expression that evaluates to a null terminated string. + * + * Sets an expectation that the values that @left and @right evaluate to are + * not equal. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, strcmp((@left), (@right))). See KUNIT_EXPECT_TRUE() + * for more information. + */ +#define KUNIT_EXPECT_STRNEQ(test, left, right) \ + KUNIT_BINARY_STR_NE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + +#define KUNIT_EXPECT_STRNEQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_NOT_ERR_OR_NULL() - Expects that @ptr is not null and not err. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an expectation that the value that @ptr evaluates to is not null and not + * an errno stored in a pointer. This is semantically equivalent to + * KUNIT_EXPECT_TRUE(@test, !IS_ERR_OR_NULL(@ptr)). See KUNIT_EXPECT_TRUE() for + * more information. + */ +#define KUNIT_EXPECT_NOT_ERR_OR_NULL(test, ptr) \ + KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, KUNIT_EXPECTATION, ptr) + +#define KUNIT_EXPECT_NOT_ERR_OR_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + ptr, \ + fmt, \ + ##__VA_ARGS__) + +#define KUNIT_ASSERT_FAILURE(test, fmt, ...) \ + KUNIT_FAIL_ASSERTION(test, KUNIT_ASSERTION, fmt, ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_TRUE() - Sets an assertion that @condition is true. + * @test: The test context object. + * @condition: an arbitrary boolean expression. The test fails and aborts when + * this does not evaluate to true. + * + * This and assertions of the form `KUNIT_ASSERT_*` will cause the test case to + * fail *and immediately abort* when the specified condition is not met. Unlike + * an expectation failure, it will prevent the test case from continuing to run; + * this is otherwise known as an *assertion failure*. + */ +#define KUNIT_ASSERT_TRUE(test, condition) \ + KUNIT_TRUE_ASSERTION(test, KUNIT_ASSERTION, condition) + +#define KUNIT_ASSERT_TRUE_MSG(test, condition, fmt, ...) \ + KUNIT_TRUE_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + condition, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_FALSE() - Sets an assertion that @condition is false. + * @test: The test context object. + * @condition: an arbitrary boolean expression. + * + * Sets an assertion that the value that @condition evaluates to is false. This + * is the same as KUNIT_EXPECT_FALSE(), except it causes an assertion failure + * (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_FALSE(test, condition) \ + KUNIT_FALSE_ASSERTION(test, KUNIT_ASSERTION, condition) + +#define KUNIT_ASSERT_FALSE_MSG(test, condition, fmt, ...) \ + KUNIT_FALSE_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + condition, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_EQ() - Sets an assertion that @left and @right are equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an assertion that the values that @left and @right evaluate to are + * equal. This is the same as KUNIT_EXPECT_EQ(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_EQ(test, left, right) \ + KUNIT_BINARY_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_EQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_PTR_EQ() - Asserts that pointers @left and @right are equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a pointer. + * @right: an arbitrary expression that evaluates to a pointer. + * + * Sets an assertion that the values that @left and @right evaluate to are + * equal. This is the same as KUNIT_EXPECT_EQ(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_PTR_EQ(test, left, right) \ + KUNIT_BINARY_PTR_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_PTR_EQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_NE() - An assertion that @left and @right are not equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an assertion that the values that @left and @right evaluate to are not + * equal. This is the same as KUNIT_EXPECT_NE(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_NE(test, left, right) \ + KUNIT_BINARY_NE_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_NE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_NE_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_PTR_NE() - Asserts that pointers @left and @right are not equal. + * KUNIT_ASSERT_PTR_EQ() - Asserts that pointers @left and @right are equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a pointer. + * @right: an arbitrary expression that evaluates to a pointer. + * + * Sets an assertion that the values that @left and @right evaluate to are not + * equal. This is the same as KUNIT_EXPECT_NE(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_PTR_NE(test, left, right) \ + KUNIT_BINARY_PTR_NE_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_PTR_NE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) +/** + * KUNIT_ASSERT_LT() - An assertion that @left is less than @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an assertion that the value that @left evaluates to is less than the + * value that @right evaluates to. This is the same as KUNIT_EXPECT_LT(), except + * it causes an assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion + * is not met. + */ +#define KUNIT_ASSERT_LT(test, left, right) \ + KUNIT_BINARY_LT_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_LT_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_LT_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) +/** + * KUNIT_ASSERT_LE() - An assertion that @left is less than or equal to @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an assertion that the value that @left evaluates to is less than or + * equal to the value that @right evaluates to. This is the same as + * KUNIT_EXPECT_LE(), except it causes an assertion failure (see + * KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_LE(test, left, right) \ + KUNIT_BINARY_LE_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_LE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_LE_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_GT() - An assertion that @left is greater than @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an assertion that the value that @left evaluates to is greater than the + * value that @right evaluates to. This is the same as KUNIT_EXPECT_GT(), except + * it causes an assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion + * is not met. + */ +#define KUNIT_ASSERT_GT(test, left, right) \ + KUNIT_BINARY_GT_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_GT_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_GT_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_GE() - Assertion that @left is greater than or equal to @right. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a primitive C type. + * @right: an arbitrary expression that evaluates to a primitive C type. + * + * Sets an assertion that the value that @left evaluates to is greater than the + * value that @right evaluates to. This is the same as KUNIT_EXPECT_GE(), except + * it causes an assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion + * is not met. + */ +#define KUNIT_ASSERT_GE(test, left, right) \ + KUNIT_BINARY_GE_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_GE_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_GE_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_STREQ() - An assertion that strings @left and @right are equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a null terminated string. + * @right: an arbitrary expression that evaluates to a null terminated string. + * + * Sets an assertion that the values that @left and @right evaluate to are + * equal. This is the same as KUNIT_EXPECT_STREQ(), except it causes an + * assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_STREQ(test, left, right) \ + KUNIT_BINARY_STR_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_STREQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_STRNEQ() - Expects that strings @left and @right are not equal. + * @test: The test context object. + * @left: an arbitrary expression that evaluates to a null terminated string. + * @right: an arbitrary expression that evaluates to a null terminated string. + * + * Sets an expectation that the values that @left and @right evaluate to are + * not equal. This is semantically equivalent to + * KUNIT_ASSERT_TRUE(@test, strcmp((@left), (@right))). See KUNIT_ASSERT_TRUE() + * for more information. + */ +#define KUNIT_ASSERT_STRNEQ(test, left, right) \ + KUNIT_BINARY_STR_NE_ASSERTION(test, KUNIT_ASSERTION, left, right) + +#define KUNIT_ASSERT_STRNEQ_MSG(test, left, right, fmt, ...) \ + KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, \ + right, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_NOT_ERR_OR_NULL() - Assertion that @ptr is not null and not err. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an assertion that the value that @ptr evaluates to is not null and not + * an errno stored in a pointer. This is the same as + * KUNIT_EXPECT_NOT_ERR_OR_NULL(), except it causes an assertion failure (see + * KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr) \ + KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, KUNIT_ASSERTION, ptr) + +#define KUNIT_ASSERT_NOT_ERR_OR_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ + KUNIT_ASSERTION, \ + ptr, \ + fmt, \ + ##__VA_ARGS__) + +#endif /* _KUNIT_TEST_H */ diff --git a/include/kunit/try-catch.h b/include/kunit/try-catch.h new file mode 100644 index 000000000000..404f336cbdc8 --- /dev/null +++ b/include/kunit/try-catch.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * An API to allow a function, that may fail, to be executed, and recover in a + * controlled manner. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#ifndef _KUNIT_TRY_CATCH_H +#define _KUNIT_TRY_CATCH_H + +#include <linux/types.h> + +typedef void (*kunit_try_catch_func_t)(void *); + +struct completion; +struct kunit; + +/** + * struct kunit_try_catch - provides a generic way to run code which might fail. + * @test: The test case that is currently being executed. + * @try_completion: Completion that the control thread waits on while test runs. + * @try_result: Contains any errno obtained while running test case. + * @try: The function, the test case, to attempt to run. + * @catch: The function called if @try bails out. + * @context: used to pass user data to the try and catch functions. + * + * kunit_try_catch provides a generic, architecture independent way to execute + * an arbitrary function of type kunit_try_catch_func_t which may bail out by + * calling kunit_try_catch_throw(). If kunit_try_catch_throw() is called, @try + * is stopped at the site of invocation and @catch is called. + * + * struct kunit_try_catch provides a generic interface for the functionality + * needed to implement kunit->abort() which in turn is needed for implementing + * assertions. Assertions allow stating a precondition for a test simplifying + * how test cases are written and presented. + * + * Assertions are like expectations, except they abort (call + * kunit_try_catch_throw()) when the specified condition is not met. This is + * useful when you look at a test case as a logical statement about some piece + * of code, where assertions are the premises for the test case, and the + * conclusion is a set of predicates, rather expectations, that must all be + * true. If your premises are violated, it does not makes sense to continue. + */ +struct kunit_try_catch { + /* private: internal use only. */ + struct kunit *test; + struct completion *try_completion; + int try_result; + kunit_try_catch_func_t try; + kunit_try_catch_func_t catch; + void *context; +}; + +void kunit_try_catch_init(struct kunit_try_catch *try_catch, + struct kunit *test, + kunit_try_catch_func_t try, + kunit_try_catch_func_t catch); + +void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context); + +void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch); + +static inline int kunit_try_catch_get_result(struct kunit_try_catch *try_catch) +{ + return try_catch->try_result; +} + +/* + * Exposed for testing only. + */ +void kunit_generic_try_catch_init(struct kunit_try_catch *try_catch); + +#endif /* _KUNIT_TRY_CATCH_H */ diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 080012a6f025..df01a8579034 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -80,6 +80,22 @@ #include <linux/linkage.h> #include <linux/types.h> + +enum arm_smccc_conduit { + SMCCC_CONDUIT_NONE, + SMCCC_CONDUIT_SMC, + SMCCC_CONDUIT_HVC, +}; + +/** + * arm_smccc_1_1_get_conduit() + * + * Returns the conduit to be used for SMCCCv1.1 or later. + * + * When SMCCCv1.1 is not present, returns SMCCC_CONDUIT_NONE. + */ +enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 3305ea7f9dc7..0a241c5c911d 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -5,12 +5,6 @@ #include <uapi/linux/arm_sdei.h> -enum sdei_conduit_types { - CONDUIT_INVALID = 0, - CONDUIT_SMC, - CONDUIT_HVC, -}; - #include <acpi/ghes.h> #ifdef CONFIG_ARM_SDE_INTERFACE diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index bed9e43f9426..19394c77ed99 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -15,7 +15,9 @@ */ #include <linux/cgroup.h> +#include <linux/percpu.h> #include <linux/percpu_counter.h> +#include <linux/u64_stats_sync.h> #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> @@ -31,15 +33,12 @@ #ifdef CONFIG_BLK_CGROUP -enum blkg_rwstat_type { - BLKG_RWSTAT_READ, - BLKG_RWSTAT_WRITE, - BLKG_RWSTAT_SYNC, - BLKG_RWSTAT_ASYNC, - BLKG_RWSTAT_DISCARD, +enum blkg_iostat_type { + BLKG_IOSTAT_READ, + BLKG_IOSTAT_WRITE, + BLKG_IOSTAT_DISCARD, - BLKG_RWSTAT_NR, - BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, + BLKG_IOSTAT_NR, }; struct blkcg_gq; @@ -61,17 +60,15 @@ struct blkcg { #endif }; -/* - * blkg_[rw]stat->aux_cnt is excluded for local stats but included for - * recursive. Used to carry stats of dead children. - */ -struct blkg_rwstat { - struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; - atomic64_t aux_cnt[BLKG_RWSTAT_NR]; +struct blkg_iostat { + u64 bytes[BLKG_IOSTAT_NR]; + u64 ios[BLKG_IOSTAT_NR]; }; -struct blkg_rwstat_sample { - u64 cnt[BLKG_RWSTAT_NR]; +struct blkg_iostat_set { + struct u64_stats_sync sync; + struct blkg_iostat cur; + struct blkg_iostat last; }; /* @@ -127,8 +124,8 @@ struct blkcg_gq { /* is this blkg online? protected by both blkcg and q locks */ bool online; - struct blkg_rwstat stat_bytes; - struct blkg_rwstat stat_ios; + struct blkg_iostat_set __percpu *iostat_cpu; + struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; @@ -202,13 +199,6 @@ int blkcg_activate_policy(struct request_queue *q, void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol); -static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, - unsigned int idx) -{ - return atomic64_read(&rwstat->aux_cnt[idx]) + - percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); -} - const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, @@ -216,17 +206,6 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); -u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - const struct blkg_rwstat_sample *rwstat); -u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - int off); -int blkg_print_stat_bytes(struct seq_file *sf, void *v); -int blkg_print_stat_ios(struct seq_file *sf, void *v); -int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v); -int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v); - -void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, - int off, struct blkg_rwstat_sample *sum); struct blkg_conf_ctx { struct gendisk *disk; @@ -578,128 +557,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) -{ - int i, ret; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) { - ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); - if (ret) { - while (--i >= 0) - percpu_counter_destroy(&rwstat->cpu_cnt[i]); - return ret; - } - atomic64_set(&rwstat->aux_cnt[i], 0); - } - return 0; -} - -static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - percpu_counter_destroy(&rwstat->cpu_cnt[i]); -} - -/** - * blkg_rwstat_add - add a value to a blkg_rwstat - * @rwstat: target blkg_rwstat - * @op: REQ_OP and flags - * @val: value to add - * - * Add @val to @rwstat. The counters are chosen according to @rw. The - * caller is responsible for synchronizing calls to this function. - */ -static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, - unsigned int op, uint64_t val) -{ - struct percpu_counter *cnt; - - if (op_is_discard(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; - else if (op_is_write(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; - - percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); - - if (op_is_sync(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - - percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); -} - -/** - * blkg_rwstat_read - read the current values of a blkg_rwstat - * @rwstat: blkg_rwstat to read - * - * Read the current snapshot of @rwstat and return it in the aux counts. - */ -static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, - struct blkg_rwstat_sample *result) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - result->cnt[i] = - percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); -} - -/** - * blkg_rwstat_total - read the total count of a blkg_rwstat - * @rwstat: blkg_rwstat to read - * - * Return the total count of @rwstat regardless of the IO direction. This - * function can be called without synchronization and takes care of u64 - * atomicity. - */ -static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) -{ - struct blkg_rwstat_sample tmp = { }; - - blkg_rwstat_read(rwstat, &tmp); - return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; -} - -/** - * blkg_rwstat_reset - reset a blkg_rwstat - * @rwstat: blkg_rwstat to reset - */ -static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) { - percpu_counter_set(&rwstat->cpu_cnt[i], 0); - atomic64_set(&rwstat->aux_cnt[i], 0); - } -} - -/** - * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count - * @to: the destination blkg_rwstat - * @from: the source - * - * Add @from's count including the aux one to @to's aux count. - */ -static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, - struct blkg_rwstat *from) -{ - u64 sum[BLKG_RWSTAT_NR]; - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]), - &to->aux_cnt[i]); -} - #ifdef CONFIG_BLK_DEV_THROTTLING extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio); @@ -745,15 +602,33 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + struct blkg_iostat_set *bis; + int rwd, cpu; + + if (op_is_discard(bio->bi_opf)) + rwd = BLKG_IOSTAT_DISCARD; + else if (op_is_write(bio->bi_opf)) + rwd = BLKG_IOSTAT_WRITE; + else + rwd = BLKG_IOSTAT_READ; + + cpu = get_cpu(); + bis = per_cpu_ptr(blkg->iostat_cpu, cpu); + u64_stats_update_begin(&bis->sync); + /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the * size of the bio. */ if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, - bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); + bis->cur.bytes[rwd] += bio->bi_iter.bi_size; + bis->cur.ios[rwd]++; + + u64_stats_update_end(&bis->sync); + if (cgroup_subsys_on_dfl(io_cgrp_subsys)) + cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); + put_cpu(); } blkcg_bio_issue_init(bio); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 0bf056de5cc3..11cfd6470b1a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -10,103 +10,239 @@ struct blk_mq_tags; struct blk_flush_queue; /** - * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device + * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware + * block device */ struct blk_mq_hw_ctx { struct { + /** @lock: Protects the dispatch list. */ spinlock_t lock; + /** + * @dispatch: Used for requests that are ready to be + * dispatched to the hardware but for some reason (e.g. lack of + * resources) could not be sent to the hardware. As soon as the + * driver can send new requests, requests at this list will + * be sent first for a fairer dispatch. + */ struct list_head dispatch; - unsigned long state; /* BLK_MQ_S_* flags */ + /** + * @state: BLK_MQ_S_* flags. Defines the state of the hw + * queue (active, scheduled to restart, stopped). + */ + unsigned long state; } ____cacheline_aligned_in_smp; + /** + * @run_work: Used for scheduling a hardware queue run at a later time. + */ struct delayed_work run_work; + /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; + /** + * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU + * selection from @cpumask. + */ int next_cpu; + /** + * @next_cpu_batch: Counter of how many works left in the batch before + * changing to the next CPU. + */ int next_cpu_batch; - unsigned long flags; /* BLK_MQ_F_* flags */ + /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ + unsigned long flags; + /** + * @sched_data: Pointer owned by the IO scheduler attached to a request + * queue. It's up to the IO scheduler how to use this pointer. + */ void *sched_data; + /** + * @queue: Pointer to the request queue that owns this hardware context. + */ struct request_queue *queue; + /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; + /** + * @driver_data: Pointer to data owned by the block driver that created + * this hctx + */ void *driver_data; + /** + * @ctx_map: Bitmap for each software queue. If bit is on, there is a + * pending request in that software queue. + */ struct sbitmap ctx_map; + /** + * @dispatch_from: Software queue to be used when no scheduler was + * selected. + */ struct blk_mq_ctx *dispatch_from; + /** + * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to + * decide if the hw_queue is busy using Exponential Weighted Moving + * Average algorithm. + */ unsigned int dispatch_busy; + /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; + /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; + /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; + /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; + /** + * @dispatch_wait: Waitqueue to put requests when there is no tag + * available at the moment, to wait for another try in the future. + */ wait_queue_entry_t dispatch_wait; + + /** + * @wait_index: Index of next available dispatch_wait queue to insert + * requests. + */ atomic_t wait_index; + /** + * @tags: Tags owned by the block driver. A tag at this set is only + * assigned when a request is dispatched from a hardware queue. + */ struct blk_mq_tags *tags; + /** + * @sched_tags: Tags owned by I/O scheduler. If there is an I/O + * scheduler associated with a request queue, a tag is assigned when + * that request is allocated. Else, this member is not used. + */ struct blk_mq_tags *sched_tags; + /** @queued: Number of queued requests. */ unsigned long queued; + /** @run: Number of dispatched requests. */ unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 + /** @dispatched: Number of dispatch requests by queue. */ unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; + /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; + /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; + /** + * @nr_active: Number of active requests. Only used when a tag set is + * shared across request queues. + */ atomic_t nr_active; + /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; + /** @kobj: Kernel object for sysfs. */ struct kobject kobj; + /** @poll_considered: Count times blk_poll() was called. */ unsigned long poll_considered; + /** @poll_invoked: Count how many requests blk_poll() polled. */ unsigned long poll_invoked; + /** @poll_success: Count how many polled requests were completed. */ unsigned long poll_success; #ifdef CONFIG_BLK_DEBUG_FS + /** + * @debugfs_dir: debugfs directory for this hardware queue. Named + * as cpu<cpu_number>. + */ struct dentry *debugfs_dir; + /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif + /** @hctx_list: List of all hardware queues. */ struct list_head hctx_list; - /* Must be the last member - see also blk_mq_hw_ctx_size(). */ + /** + * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is + * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also + * blk_mq_hw_ctx_size(). + */ struct srcu_struct srcu[0]; }; +/** + * struct blk_mq_queue_map - Map software queues to hardware queues + * @mq_map: CPU ID to hardware queue index map. This is an array + * with nr_cpu_ids elements. Each element has a value in the range + * [@queue_offset, @queue_offset + @nr_queues). + * @nr_queues: Number of hardware queues to map CPU IDs onto. + * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe + * driver to map each hardware queue type (enum hctx_type) onto a distinct + * set of hardware queues. + */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; +/** + * enum hctx_type - Type of hardware queue + * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. + * @HCTX_TYPE_READ: Just for READ I/O. + * @HCTX_TYPE_POLL: Polled I/O of any kind. + * @HCTX_MAX_TYPES: Number of types of hctx. + */ enum hctx_type { - HCTX_TYPE_DEFAULT, /* all I/O not otherwise accounted for */ - HCTX_TYPE_READ, /* just for READ I/O */ - HCTX_TYPE_POLL, /* polled I/O of any kind */ + HCTX_TYPE_DEFAULT, + HCTX_TYPE_READ, + HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; +/** + * struct blk_mq_tag_set - tag set that can be shared between request queues + * @map: One or more ctx -> hctx mappings. One map exists for each + * hardware queue type (enum hctx_type) that the driver wishes + * to support. There are no restrictions on maps being of the + * same size, and it's perfectly legal to share maps between + * types. + * @nr_maps: Number of elements in the @map array. A number in the range + * [1, HCTX_MAX_TYPES]. + * @ops: Pointers to functions that implement block driver behavior. + * @nr_hw_queues: Number of hardware queues supported by the block driver that + * owns this data structure. + * @queue_depth: Number of tags per hardware queue, reserved tags included. + * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag + * allocations. + * @cmd_size: Number of additional bytes to allocate per request. The block + * driver owns these additional bytes. + * @numa_node: NUMA node the storage adapter has been connected to. + * @timeout: Request processing timeout in jiffies. + * @flags: Zero or more BLK_MQ_F_* flags. + * @driver_data: Pointer to data owned by the block driver that created this + * tag set. + * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues + * elements. + * @tag_list_lock: Serializes tag_list accesses. + * @tag_list: List of the request queues that use this tag set. See also + * request_queue.tag_set_list. + */ struct blk_mq_tag_set { - /* - * map[] holds ctx -> hctx mappings, one map exists for each type - * that the driver wishes to support. There are no restrictions - * on maps being of the same size, and it's perfectly legal to - * share maps between types. - */ struct blk_mq_queue_map map[HCTX_MAX_TYPES]; - unsigned int nr_maps; /* nr entries in map[] */ + unsigned int nr_maps; const struct blk_mq_ops *ops; - unsigned int nr_hw_queues; /* nr hw queues across maps */ - unsigned int queue_depth; /* max hw supported */ + unsigned int nr_hw_queues; + unsigned int queue_depth; unsigned int reserved_tags; - unsigned int cmd_size; /* per-request extra data */ + unsigned int cmd_size; int numa_node; unsigned int timeout; - unsigned int flags; /* BLK_MQ_F_* */ + unsigned int flags; void *driver_data; struct blk_mq_tags **tags; @@ -115,6 +251,12 @@ struct blk_mq_tag_set { struct list_head tag_list; }; +/** + * struct blk_mq_queue_data - Data about a request inserted in a queue + * + * @rq: Request pointer. + * @last: If it is the last request in the queue. + */ struct blk_mq_queue_data { struct request *rq; bool last; @@ -142,81 +284,101 @@ typedef bool (busy_fn)(struct request_queue *); typedef void (complete_fn)(struct request *); typedef void (cleanup_rq_fn)(struct request *); - +/** + * struct blk_mq_ops - Callback functions that implements block driver + * behaviour. + */ struct blk_mq_ops { - /* - * Queue request + /** + * @queue_rq: Queue a new request from block IO. */ queue_rq_fn *queue_rq; - /* - * If a driver uses bd->last to judge when to submit requests to - * hardware, it must define this function. In case of errors that - * make us stop issuing further requests, this hook serves the + /** + * @commit_rqs: If a driver uses bd->last to judge when to submit + * requests to hardware, it must define this function. In case of errors + * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ commit_rqs_fn *commit_rqs; - /* - * Reserve budget before queue request, once .queue_rq is + /** + * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ get_budget_fn *get_budget; + /** + * @put_budget: Release the reserved budget. + */ put_budget_fn *put_budget; - /* - * Called on request timeout + /** + * @timeout: Called on request timeout. */ timeout_fn *timeout; - /* - * Called to poll for completion of a specific tag. + /** + * @poll: Called to poll for completion of a specific tag. */ poll_fn *poll; + /** + * @complete: Mark the request as complete. + */ complete_fn *complete; - /* - * Called when the block layer side of a hardware queue has been - * set up, allowing the driver to allocate/init matching structures. - * Ditto for exit/teardown. + /** + * @init_hctx: Called when the block layer side of a hardware queue has + * been set up, allowing the driver to allocate/init matching + * structures. */ init_hctx_fn *init_hctx; + /** + * @exit_hctx: Ditto for exit/teardown. + */ exit_hctx_fn *exit_hctx; - /* - * Called for every command allocated by the block layer to allow - * the driver to set up driver specific data. + /** + * @init_request: Called for every command allocated by the block layer + * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. - * - * Ditto for exit/teardown. */ init_request_fn *init_request; + /** + * @exit_request: Ditto for exit/teardown. + */ exit_request_fn *exit_request; - /* Called from inside blk_get_request() */ + + /** + * @initialize_rq_fn: Called from inside blk_get_request(). + */ void (*initialize_rq_fn)(struct request *rq); - /* - * Called before freeing one request which isn't completed yet, - * and usually for freeing the driver private data + /** + * @cleanup_rq: Called before freeing one request which isn't completed + * yet, and usually for freeing the driver private data. */ cleanup_rq_fn *cleanup_rq; - /* - * If set, returns whether or not this queue currently is busy + /** + * @busy: If set, returns whether or not this queue currently is busy. */ busy_fn *busy; + /** + * @map_queues: This allows drivers specify their own queue mapping by + * overriding the setup-time function that builds the mq_map. + */ map_queues_fn *map_queues; #ifdef CONFIG_BLK_DEBUG_FS - /* - * Used by the debugfs implementation to show driver-specific + /** + * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); @@ -262,7 +424,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_free_request(struct request *rq); -bool blk_mq_can_queue(struct blk_mq_hw_ctx *); bool blk_mq_queue_inflight(struct request_queue *q); @@ -301,9 +462,25 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } +/** + * blk_mq_rq_state() - read the current MQ_RQ_* state of a request + * @rq: target request. + */ +static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) +{ + return READ_ONCE(rq->state); +} + +static inline int blk_mq_request_started(struct request *rq) +{ + return blk_mq_rq_state(rq) != MQ_RQ_IDLE; +} + +static inline int blk_mq_request_completed(struct request *rq) +{ + return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; +} -int blk_mq_request_started(struct request *rq); -int blk_mq_request_completed(struct request *rq); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); @@ -324,7 +501,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); @@ -343,14 +520,29 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); -/* +/** + * blk_mq_rq_from_pdu - cast a PDU to a request + * @pdu: the PDU (Protocol Data Unit) to be casted + * + * Return: request + * * Driver command data is immediately after the request. So subtract request - * size to get back to the original request, add request size to get the PDU. + * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } + +/** + * blk_mq_rq_to_pdu - cast a request to a PDU + * @rq: the request to be casted + * + * Return: pointer to the PDU + * + * Driver command data is immediately after the request. So add request to get + * the PDU. + */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d688b96d1d63..70254ae11769 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -153,10 +153,10 @@ struct bio { unsigned short bi_write_hint; blk_status_t bi_status; u8 bi_partno; + atomic_t __bi_remaining; struct bvec_iter bi_iter; - atomic_t __bi_remaining; bio_end_io_t *bi_end_io; void *bi_private; @@ -290,6 +290,12 @@ enum req_opf { REQ_OP_ZONE_RESET_ALL = 8, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, + /* Open a zone */ + REQ_OP_ZONE_OPEN = 10, + /* Close a zone */ + REQ_OP_ZONE_CLOSE = 11, + /* Transition a zone to full */ + REQ_OP_ZONE_FINISH = 12, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, @@ -371,6 +377,7 @@ enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, + STAT_FLUSH, NR_STAT_GROUPS }; @@ -417,6 +424,25 @@ static inline bool op_is_discard(unsigned int op) return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } +/* + * Check if a bio or request operation is a zone management operation, with + * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case + * due to its different handling in the block layer and device response in + * case of command failure. + */ +static inline bool op_is_zone_mgmt(enum req_opf op) +{ + switch (op & REQ_OP_MASK) { + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return true; + default: + return false; + } +} + static inline int op_stat_group(unsigned int op) { if (op_is_discard(op)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3ea78b0c91c..397bb9bc230b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -349,25 +349,25 @@ struct queue_limits { enum blk_zoned_model zoned; }; +typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, + void *data); + #ifdef CONFIG_BLK_DEV_ZONED -/* - * Maximum number of zones to report with a single report zones command. - */ -#define BLK_ZONED_REPORT_MAX_ZONES 8192U +#define BLK_ALL_ZONES ((unsigned int)-1) +int blkdev_report_zones(struct block_device *bdev, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); extern unsigned int blkdev_nr_zones(struct block_device *bdev); -extern int blkdev_report_zones(struct block_device *bdev, - sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones); -extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, - sector_t nr_sectors, gfp_t gfp_mask); +extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, + sector_t sectors, sector_t nr_sectors, + gfp_t gfp_mask); extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); -extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); +extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ @@ -388,9 +388,9 @@ static inline int blkdev_report_zones_ioctl(struct block_device *bdev, return -ENOTTY; } -static inline int blkdev_reset_zones_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) +static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) { return -ENOTTY; } @@ -411,7 +411,6 @@ struct request_queue { /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; - unsigned int nr_queues; unsigned int queue_depth; @@ -1709,7 +1708,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); + unsigned int nr_zones, report_zones_cb cb, void *data); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5b9d22338606..3bf3835d0e86 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -656,11 +656,11 @@ void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size); +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size); void bpf_map_charge_finish(struct bpf_map_memory *mem); void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src); -void *bpf_map_area_alloc(size_t size, int numa_node); +void *bpf_map_area_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 8339071ab08b..e20a0cd09ba5 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -65,5 +65,6 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); +void can_sock_destruct(struct sock *sk); #endif /* !_CAN_CORE_H */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d0633ebdaa9c..bc6c879bd110 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -59,6 +59,11 @@ extern ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_tsx_async_abort(struct device *dev, + struct device_attribute *attr, + char *buf); +extern ssize_t cpu_show_itlb_multihit(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -213,28 +218,7 @@ static inline int cpuhp_smt_enable(void) { return 0; } static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; } #endif -/* - * These are used for a global "mitigations=" cmdline option for toggling - * optional CPU mitigations. - */ -enum cpu_mitigations { - CPU_MITIGATIONS_OFF, - CPU_MITIGATIONS_AUTO, - CPU_MITIGATIONS_AUTO_NOSMT, -}; - -extern enum cpu_mitigations cpu_mitigations; - -/* mitigations=off */ -static inline bool cpu_mitigations_off(void) -{ - return cpu_mitigations == CPU_MITIGATIONS_OFF; -} - -/* mitigations=auto,nosmt */ -static inline bool cpu_mitigations_auto_nosmt(void) -{ - return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; -} +extern bool cpu_mitigations_off(void); +extern bool cpu_mitigations_auto_nosmt(void); #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 399ad8632356..475668c69dbc 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -17,6 +17,7 @@ struct dm_dev; struct dm_target; struct dm_table; +struct dm_report_zones_args; struct mapped_device; struct bio_vec; @@ -93,9 +94,9 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); -typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, - struct blk_zone *zones, - unsigned int *nr_zones); +typedef int (*dm_report_zones_fn) (struct dm_target *ti, + struct dm_report_zones_args *args, + unsigned int nr_zones); /* * These iteration functions are typically used to check (and combine) @@ -422,10 +423,23 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_remap_zone_report(struct dm_target *ti, sector_t start, - struct blk_zone *zones, unsigned int *nr_zones); union map_info *dm_get_rq_mapinfo(struct request *rq); +#ifdef CONFIG_BLK_DEV_ZONED +struct dm_report_zones_args { + struct dm_target *tgt; + sector_t next_sector; + + void *orig_data; + report_zones_cb orig_cb; + unsigned int zone_idx; + + /* must be filled by ->report_zones before calling dm_report_zones_cb */ + sector_t start; +}; +int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data); +#endif /* CONFIG_BLK_DEV_ZONED */ + /* * Device mapper functions to parse and create devices specified by the * parameter "dm-mod.create=" @@ -594,9 +608,6 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); */ #define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz)) -#define dm_array_too_big(fixed, obj, num) \ - ((num) > (UINT_MAX - (fixed)) / (obj)) - /* * Sector offset taken relative to the start of the target instead of * relative to the start of the device. diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index adf993a3bd58..d03af3605460 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,6 +5,8 @@ #include <linux/dma-mapping.h> #include <linux/mem_encrypt.h> +extern unsigned int zone_dma_bits; + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include <asm/dma-direct.h> #else diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..dde6dc4492a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -148,8 +148,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) -/* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ @@ -2632,8 +2630,6 @@ extern void bd_finish_claiming(struct block_device *bdev, extern void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); -extern int __blkdev_reread_part(struct block_device *bdev); -extern int blkdev_reread_part(struct block_device *bdev); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); @@ -2703,8 +2699,6 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK -extern void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev, bool verbose); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); extern int __invalidate_device(struct block_device *, bool); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index f622f7460ed8..1a7bffe78ed5 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -20,7 +20,6 @@ #define FS_CRYPTO_BLOCK_SIZE 16 -struct fscrypt_ctx; struct fscrypt_info; struct fscrypt_str { @@ -62,18 +61,9 @@ struct fscrypt_operations { bool (*dummy_context)(struct inode *); bool (*empty_dir)(struct inode *); unsigned int max_namelen; -}; - -/* Decryption work */ -struct fscrypt_ctx { - union { - struct { - struct bio *bio; - struct work_struct work; - }; - struct list_head free_list; /* Free list */ - }; - u8 flags; /* Flags */ + bool (*has_stable_inodes)(struct super_block *sb); + void (*get_ino_and_lblk_bits)(struct super_block *sb, + int *ino_bits_ret, int *lblk_bits_ret); }; static inline bool fscrypt_has_encryption_key(const struct inode *inode) @@ -102,8 +92,6 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) /* crypto.c */ extern void fscrypt_enqueue_decrypt_work(struct work_struct *); -extern struct fscrypt_ctx *fscrypt_get_ctx(gfp_t); -extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, unsigned int len, @@ -244,8 +232,6 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, /* bio.c */ extern void fscrypt_decrypt_bio(struct bio *); -extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio); extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, unsigned int); @@ -295,16 +281,6 @@ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { } -static inline struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx) -{ - return; -} - static inline struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, unsigned int len, unsigned int offs, @@ -484,11 +460,6 @@ static inline void fscrypt_decrypt_bio(struct bio *bio) { } -static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio) -{ -} - static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8a8cb3c401b2..9141f2263286 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -499,7 +499,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } /** * ftrace_make_nop - convert code into nop * @mod: module structure if called by module load initialization - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should be calling * * This is a very sensitive operation and great care needs @@ -520,9 +520,38 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } extern int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr); + +/** + * ftrace_init_nop - initialize a nop call site + * @mod: module structure if called by module load initialization + * @rec: the call site record (e.g. mcount/fentry) + * + * This is a very sensitive operation and great care needs + * to be taken by the arch. The operation should carefully + * read the location, check to see if what is read is indeed + * what we expect it to be, and then on success of the compare, + * it should write to the location. + * + * The code segment at @rec->ip should contain the contents created by + * the compiler + * + * Return must be: + * 0 on success + * -EFAULT on error reading the location + * -EINVAL on a failed compare of the contents + * -EPERM on error writing to the location + * Any other value will be considered a failure. + */ +#ifndef ftrace_init_nop +static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + return ftrace_make_nop(mod, rec, MCOUNT_ADDR); +} +#endif + /** * ftrace_make_call - convert a nop call site into a call to addr - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should call * * This is a very sensitive operation and great care needs @@ -545,7 +574,7 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS /** * ftrace_modify_call - convert from one addr to another (no nop) - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @old_addr: the address expected to be currently called to * @addr: the address to change to * @@ -709,6 +738,11 @@ static inline unsigned long get_lock_parent_ip(void) #ifdef CONFIG_FTRACE_MCOUNT_RECORD extern void ftrace_init(void); +#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY +#define FTRACE_CALLSITE_SECTION "__patchable_function_entries" +#else +#define FTRACE_CALLSITE_SECTION "__mcount_loc" +#endif #else static inline void ftrace_init(void) { } #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8b5330dd5ac0..8bb63027e4d6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -621,9 +621,10 @@ extern void blk_invalidate_devt(dev_t devt); extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); +int bdev_disk_changed(struct block_device *bdev, bool invalidate); +int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); +int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev); extern int disk_expand_part_tbl(struct gendisk *disk, int target); -extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); -extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev); extern struct hd_struct * __must_check add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, diff --git a/include/linux/idr.h b/include/linux/idr.h index 4ec8986e5dfb..ac6e946b6767 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -185,7 +185,7 @@ static inline void idr_preload_end(void) * is convenient for a "not found" value. */ #define idr_for_each_entry(idr, entry, id) \ - for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) + for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U) /** * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ed11ef594378..6d8bf4bdf240 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -336,7 +336,8 @@ enum { #define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) #define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16) #define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) -#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) +#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ + ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_IOTLB_SIZE 1 #define QI_DEV_IOTLB_MAX_INVS 32 @@ -360,7 +361,8 @@ enum { #define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) -#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) +#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ + ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_EIOTLB_MAX_INVS 32 /* Page group response descriptor QW0 */ diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 5cc10cf7cb3e..a0bde9e12efa 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -487,6 +487,8 @@ #define ICC_CTLR_EL1_EOImode_MASK (1 << ICC_CTLR_EL1_EOImode_SHIFT) #define ICC_CTLR_EL1_CBPR_SHIFT 0 #define ICC_CTLR_EL1_CBPR_MASK (1 << ICC_CTLR_EL1_CBPR_SHIFT) +#define ICC_CTLR_EL1_PMHE_SHIFT 6 +#define ICC_CTLR_EL1_PMHE_MASK (1 << ICC_CTLR_EL1_PMHE_SHIFT) #define ICC_CTLR_EL1_PRI_BITS_SHIFT 8 #define ICC_CTLR_EL1_PRI_BITS_MASK (0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT) #define ICC_CTLR_EL1_ID_BITS_SHIFT 11 diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 719fc3e15ea4..d41c521a39da 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -966,6 +966,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); +bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -1382,4 +1383,10 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ +typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data); + +int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, + uintptr_t data, const char *name, + struct task_struct **thread_ptr); + #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index 207e7ee764ce..d3bbfddf616a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -484,6 +484,7 @@ enum hsm_task_states { }; enum ata_completion_errors { + AC_ERR_OK = 0, /* no error */ AC_ERR_DEV = (1 << 0), /* device reported error */ AC_ERR_HSM = (1 << 1), /* host state machine violation */ AC_ERR_TIMEOUT = (1 << 2), /* timeout */ @@ -891,9 +892,9 @@ struct ata_port_operations { /* * Command execution */ - int (*qc_defer)(struct ata_queued_cmd *qc); - int (*check_atapi_dma)(struct ata_queued_cmd *qc); - void (*qc_prep)(struct ata_queued_cmd *qc); + int (*qc_defer)(struct ata_queued_cmd *qc); + int (*check_atapi_dma)(struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc); unsigned int (*qc_issue)(struct ata_queued_cmd *qc); bool (*qc_fill_rtf)(struct ata_queued_cmd *qc); @@ -1161,7 +1162,7 @@ extern int ata_xfer_mode2shift(unsigned long xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -extern void ata_noop_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); @@ -1893,9 +1894,9 @@ extern const struct ata_port_operations ata_bmdma_port_ops; .sg_tablesize = LIBATA_MAX_PRD, \ .dma_boundary = ATA_DMA_BOUNDARY -extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); -extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance); diff --git a/include/linux/memory.h b/include/linux/memory.h index 0ebb105eb261..4c75dae8dd29 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -119,6 +119,7 @@ extern struct memory_block *find_memory_block(struct mem_section *); typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); +extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT) #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bda20282746b..b0a36d1580b6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -359,33 +359,40 @@ struct per_cpu_nodestat { #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { -#ifdef CONFIG_ZONE_DMA /* - * ZONE_DMA is used when there are devices that are not able - * to do DMA to all of addressable memory (ZONE_NORMAL). Then we - * carve out the portion of memory that is needed for these devices. - * The range is arch specific. + * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able + * to DMA to all of the addressable memory (ZONE_NORMAL). + * On architectures where this area covers the whole 32 bit address + * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller + * DMA addressing constraints. This distinction is important as a 32bit + * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit + * platforms may need both zones as they support peripherals with + * different DMA addressing limitations. + * + * Some examples: + * + * - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the + * rest of the lower 4G. + * + * - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on + * the specific device. + * + * - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the + * lower 4G. * - * Some examples + * - powerpc only uses ZONE_DMA, the size, up to 2G, may vary + * depending on the specific device. * - * Architecture Limit - * --------------------------- - * parisc, ia64, sparc <4G - * s390, powerpc <2G - * arm Various - * alpha Unlimited or 0-16MB. + * - s390 uses ZONE_DMA fixed to the lower 2G. * - * i386, x86_64 and multiple other arches - * <16M. + * - ia64 and riscv only use ZONE_DMA32. + * + * - parisc uses neither. */ +#ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 - /* - * x86_64 needs two ZONE_DMAs because it supports devices that are - * only able to do DMA to the lower 16M but also 32 bit devices that - * can only do DMA areas below 4G. - */ ZONE_DMA32, #endif /* diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index fc0b4b19c900..5a4623fc586b 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -22,6 +22,7 @@ #define SNOR_MFR_INTEL CFI_MFR_INTEL #define SNOR_MFR_ST CFI_MFR_ST /* ST Micro */ #define SNOR_MFR_MICRON CFI_MFR_MICRON /* Micron */ +#define SNOR_MFR_ISSI CFI_MFR_PMC #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST @@ -133,7 +134,7 @@ #define SR_E_ERR BIT(5) #define SR_P_ERR BIT(6) -#define SR_QUAD_EN_MX BIT(6) /* Macronix Quad I/O */ +#define SR1_QUAD_EN_BIT6 BIT(6) /* Enhanced Volatile Configuration Register bits */ #define EVCR_QUAD_EN_MICRON BIT(7) /* Micron Quad I/O */ @@ -144,10 +145,8 @@ #define FSR_P_ERR BIT(4) /* Program operation status */ #define FSR_PT_ERR BIT(1) /* Protection error bit */ -/* Configuration Register bits. */ -#define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ - /* Status Register 2 bits. */ +#define SR2_QUAD_EN_BIT1 BIT(1) #define SR2_QUAD_EN_BIT7 BIT(7) /* Supported SPI protocols */ @@ -243,6 +242,9 @@ enum spi_nor_option_flags { SNOR_F_4B_OPCODES = BIT(6), SNOR_F_HAS_4BAIT = BIT(7), SNOR_F_HAS_LOCK = BIT(8), + SNOR_F_HAS_16BIT_SR = BIT(9), + SNOR_F_NO_READ_CR = BIT(10), + }; /** @@ -466,6 +468,34 @@ enum spi_nor_pp_command_index { struct spi_nor; /** + * struct spi_nor_controller_ops - SPI NOR controller driver specific + * operations. + * @prepare: [OPTIONAL] do some preparations for the + * read/write/erase/lock/unlock operations. + * @unprepare: [OPTIONAL] do some post work after the + * read/write/erase/lock/unlock operations. + * @read_reg: read out the register. + * @write_reg: write data to the register. + * @read: read data from the SPI NOR. + * @write: write data to the SPI NOR. + * @erase: erase a sector of the SPI NOR at the offset @offs; if + * not provided by the driver, spi-nor will send the erase + * opcode via write_reg(). + */ +struct spi_nor_controller_ops { + int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); + void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); + int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len); + int (*write_reg)(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len); + + ssize_t (*read)(struct spi_nor *nor, loff_t from, size_t len, u8 *buf); + ssize_t (*write)(struct spi_nor *nor, loff_t to, size_t len, + const u8 *buf); + int (*erase)(struct spi_nor *nor, loff_t offs); +}; + +/** * struct spi_nor_locking_ops - SPI NOR locking methods * @lock: lock a region of the SPI NOR. * @unlock: unlock a region of the SPI NOR. @@ -549,19 +579,7 @@ struct flash_info; * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations * @reg_proto the SPI protocol for read_reg/write_reg/erase operations - * @prepare: [OPTIONAL] do some preparations for the - * read/write/erase/lock/unlock operations - * @unprepare: [OPTIONAL] do some post work after the - * read/write/erase/lock/unlock operations - * @read_reg: [DRIVER-SPECIFIC] read out the register - * @write_reg: [DRIVER-SPECIFIC] write data to the register - * @read: [DRIVER-SPECIFIC] read data from the SPI NOR - * @write: [DRIVER-SPECIFIC] write data to the SPI NOR - * @erase: [DRIVER-SPECIFIC] erase a sector of the SPI NOR - * at the offset @offs; if not provided by the driver, - * spi-nor will send the erase opcode via write_reg() - * @clear_sr_bp: [FLASH-SPECIFIC] clears the Block Protection Bits from - * the SPI NOR Status Register. + * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. * The structure includes legacy flash parameters and * settings that can be overwritten by the spi_nor_fixups @@ -588,18 +606,8 @@ struct spi_nor { bool sst_write_second; u32 flags; - int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); - void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); - int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - - ssize_t (*read)(struct spi_nor *nor, loff_t from, - size_t len, u_char *read_buf); - ssize_t (*write)(struct spi_nor *nor, loff_t to, - size_t len, const u_char *write_buf); - int (*erase)(struct spi_nor *nor, loff_t offs); + const struct spi_nor_controller_ops *controller_ops; - int (*clear_sr_bp)(struct spi_nor *nor); struct spi_nor_flash_parameter params; void *priv; diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index 067c9fea64fe..e8c30b39bb27 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -4,33 +4,60 @@ */ /* - * This file contains definitions relative to FC-NVME r1.14 (16-020vB). - * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. + * This file contains definitions relative to FC-NVME-2 r1.06 + * (T11-2019-00210-v001). */ #ifndef _NVME_FC_H #define _NVME_FC_H 1 +#include <uapi/scsi/fc/fc_fs.h> -#define NVME_CMD_SCSI_ID 0xFD +#define NVME_CMD_FORMAT_ID 0xFD #define NVME_CMD_FC_ID FC_TYPE_NVME /* FC-NVME Cmd IU Flags */ -#define FCNVME_CMD_FLAGS_DIRMASK 0x03 -#define FCNVME_CMD_FLAGS_WRITE 0x01 -#define FCNVME_CMD_FLAGS_READ 0x02 +enum { + FCNVME_CMD_FLAGS_DIRMASK = 0x03, + FCNVME_CMD_FLAGS_WRITE = (1 << 0), + FCNVME_CMD_FLAGS_READ = (1 << 1), + + FCNVME_CMD_FLAGS_PICWP = (1 << 2), +}; + +enum { + FCNVME_CMD_CAT_MASK = 0x0F, + FCNVME_CMD_CAT_ADMINQ = 0x01, + FCNVME_CMD_CAT_CSSMASK = 0x07, + FCNVME_CMD_CAT_CSSFLAG = 0x08, +}; + +static inline __u8 fccmnd_set_cat_admin(__u8 rsv_cat) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_ADMINQ; +} + +static inline __u8 fccmnd_set_cat_css(__u8 rsv_cat, __u8 css) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_CSSFLAG | + (css & FCNVME_CMD_CAT_CSSMASK); +} struct nvme_fc_cmd_iu { - __u8 scsi_id; + __u8 format_id; __u8 fc_id; __be16 iu_len; - __u8 rsvd4[3]; + __u8 rsvd4[2]; + __u8 rsv_cat; __u8 flags; __be64 connection_id; __be32 csn; __be32 data_len; struct nvme_command sqe; - __be32 rsvd88[2]; + __u8 dps; + __u8 lbads; + __be16 ms; + __be32 rsvd92; }; #define NVME_FC_SIZEOF_ZEROS_RSP 12 @@ -38,11 +65,12 @@ struct nvme_fc_cmd_iu { enum { FCNVME_SC_SUCCESS = 0, FCNVME_SC_INVALID_FIELD = 1, - FCNVME_SC_INVALID_CONNID = 2, + /* reserved 2 */ + FCNVME_SC_ILL_CONN_PARAMS = 3, }; struct nvme_fc_ersp_iu { - __u8 status_code; + __u8 ersp_result; __u8 rsvd1; __be16 iu_len; __be32 rsn; @@ -53,14 +81,44 @@ struct nvme_fc_ersp_iu { }; -/* FC-NVME Link Services */ +#define FCNVME_NVME_SR_OPCODE 0x01 + +struct nvme_fc_nvme_sr_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 retry_rctl; + __be32 rsvd4; +}; + + +enum { + FCNVME_SRSTAT_ACC = 0x0, + FCNVME_SRSTAT_INV_FCID = 0x1, + /* reserved 0x2 */ + FCNVME_SRSTAT_LOGICAL_ERR = 0x3, + FCNVME_SRSTAT_INV_QUALIF = 0x4, + FCNVME_SRSTAT_UNABL2PERFORM = 0x9, +}; + +struct nvme_fc_nvme_sr_rsp_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 status; + __be32 rsvd4; +}; + + +/* FC-NVME Link Services - LS cmd values (w0 bits 31:24) */ enum { FCNVME_LS_RSVD = 0, FCNVME_LS_RJT = 1, FCNVME_LS_ACC = 2, - FCNVME_LS_CREATE_ASSOCIATION = 3, - FCNVME_LS_CREATE_CONNECTION = 4, - FCNVME_LS_DISCONNECT = 5, + FCNVME_LS_CREATE_ASSOCIATION = 3, /* Create Association */ + FCNVME_LS_CREATE_CONNECTION = 4, /* Create I/O Connection */ + FCNVME_LS_DISCONNECT_ASSOC = 5, /* Disconnect Association */ + FCNVME_LS_DISCONNECT_CONN = 6, /* Disconnect Connection */ }; /* FC-NVME Link Service Descriptors */ @@ -117,14 +175,17 @@ enum fcnvme_ls_rjt_reason { FCNVME_RJT_RC_UNSUP = 0x0b, /* command not supported */ - FCNVME_RJT_RC_INPROG = 0x0e, - /* command already in progress */ - FCNVME_RJT_RC_INV_ASSOC = 0x40, - /* Invalid Association ID*/ + /* Invalid Association ID */ FCNVME_RJT_RC_INV_CONN = 0x41, - /* Invalid Connection ID*/ + /* Invalid Connection ID */ + + FCNVME_RJT_RC_INV_PARAM = 0x42, + /* Invalid Parameters */ + + FCNVME_RJT_RC_INSUF_RES = 0x43, + /* Insufficient Resources */ FCNVME_RJT_RC_VENDOR = 0xff, /* vendor specific error */ @@ -138,14 +199,32 @@ enum fcnvme_ls_rjt_explan { FCNVME_RJT_EXP_OXID_RXID = 0x17, /* invalid OX_ID-RX_ID combination */ - FCNVME_RJT_EXP_INSUF_RES = 0x29, - /* insufficient resources */ - FCNVME_RJT_EXP_UNAB_DATA = 0x2a, /* unable to supply requested data */ FCNVME_RJT_EXP_INV_LEN = 0x2d, /* Invalid payload length */ + + FCNVME_RJT_EXP_INV_ERSP_RAT = 0x40, + /* Invalid NVMe_ERSP Ratio */ + + FCNVME_RJT_EXP_INV_CTLR_ID = 0x41, + /* Invalid Controller ID */ + + FCNVME_RJT_EXP_INV_QUEUE_ID = 0x42, + /* Invalid Queue ID */ + + FCNVME_RJT_EXP_INV_SQSIZE = 0x43, + /* Invalid Submission Queue Size */ + + FCNVME_RJT_EXP_INV_HOSTID = 0x44, + /* Invalid HOST ID */ + + FCNVME_RJT_EXP_INV_HOSTNQN = 0x45, + /* Invalid HOSTNQN */ + + FCNVME_RJT_EXP_INV_SUBNQN = 0x46, + /* Invalid SUBNQN */ }; /* FCNVME_LSDESC_RJT */ @@ -209,21 +288,11 @@ struct fcnvme_lsdesc_cr_conn_cmd { __be32 rsvd52; }; -/* Disconnect Scope Values */ -enum { - FCNVME_DISCONN_ASSOCIATION = 0, - FCNVME_DISCONN_CONNECTION = 1, -}; - /* FCNVME_LSDESC_DISCONN_CMD */ struct fcnvme_lsdesc_disconn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ __be32 desc_len; - u8 rsvd8[3]; - /* note: scope is really a 1 bit field */ - u8 scope; /* FCNVME_DISCONN_xxx */ - __be32 rsvd12; - __be64 id; + __be32 rsvd8[4]; }; /* FCNVME_LSDESC_CONN_ID */ @@ -242,9 +311,14 @@ struct fcnvme_lsdesc_assoc_id { /* r_ctl values */ enum { - FCNVME_RS_RCTL_DATA = 1, - FCNVME_RS_RCTL_XFER_RDY = 5, - FCNVME_RS_RCTL_RSP = 8, + FCNVME_RS_RCTL_CMND = 0x6, + FCNVME_RS_RCTL_DATA = 0x1, + FCNVME_RS_RCTL_CONF = 0x3, + FCNVME_RS_RCTL_SR = 0x9, + FCNVME_RS_RCTL_XFER_RDY = 0x5, + FCNVME_RS_RCTL_RSP = 0x7, + FCNVME_RS_RCTL_ERSP = 0x8, + FCNVME_RS_RCTL_SR_RSP = 0xA, }; @@ -264,7 +338,10 @@ struct fcnvme_ls_acc_hdr { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_rqst rqst; - /* Followed by cmd-specific ACC descriptors, see next definitions */ + /* + * Followed by cmd-specific ACCEPT descriptors, see xxx_acc + * definitions below + */ }; /* FCNVME_LS_CREATE_ASSOCIATION */ @@ -302,25 +379,39 @@ struct fcnvme_ls_cr_conn_acc { struct fcnvme_lsdesc_conn_id connectid; }; -/* FCNVME_LS_DISCONNECT */ -struct fcnvme_ls_disconnect_rqst { +/* FCNVME_LS_DISCONNECT_ASSOC */ +struct fcnvme_ls_disconnect_assoc_rqst { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_assoc_id associd; struct fcnvme_lsdesc_disconn_cmd discon_cmd; }; -struct fcnvme_ls_disconnect_acc { +struct fcnvme_ls_disconnect_assoc_acc { + struct fcnvme_ls_acc_hdr hdr; +}; + + +/* FCNVME_LS_DISCONNECT_CONN */ +struct fcnvme_ls_disconnect_conn_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_disconn_cmd connectid; +}; + +struct fcnvme_ls_disconnect_conn_acc { struct fcnvme_ls_acc_hdr hdr; }; /* - * Yet to be defined in FC-NVME: + * Default R_A_TOV is pulled in from fc_fs.h but needs conversion + * from ms to seconds for our use. */ -#define NVME_FC_CONNECT_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_LS_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_TGTOP_TIMEOUT_SEC 2 /* 2 seconds */ +#define FC_TWO_TIMES_R_A_TOV (2 * (FC_DEF_R_A_TOV / 1000)) +#define NVME_FC_LS_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV +#define NVME_FC_TGTOP_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV /* * TRADDR string must be of form "nn-<16hexdigits>:pn-<16hexdigits>" @@ -328,6 +419,7 @@ struct fcnvme_ls_disconnect_acc { * infront of the <16hexdigits>. Without is considered the "min" string * and with is considered the "max" string. The hexdigits may be upper * or lower case. + * Note: FC-NVME-2 standard requires a "0x" prefix. */ #define NVME_FC_TRADDR_NNLEN 3 /* "?n-" */ #define NVME_FC_TRADDR_OXNNLEN 5 /* "?n-0x" */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f61d6906e59d..3d5189f46cb1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,8 +107,22 @@ enum { NVME_REG_AQA = 0x0024, /* Admin Queue Attributes */ NVME_REG_ASQ = 0x0028, /* Admin SQ Base Address */ NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ - NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ + NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_BPINFO = 0x0040, /* Boot Partition Information */ + NVME_REG_BPRSEL = 0x0044, /* Boot Partition Read Select */ + NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer + * Location + */ + NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ + NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ + NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ + NVME_REG_PMREBS = 0x0e0c, /* Persistent Memory Region Elasticity + * Buffer Size + */ + NVME_REG_PMRSWTP = 0x0e10, /* Persistent Memory Region Sustained + * Write Throughput + */ NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; @@ -295,6 +309,14 @@ enum { NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, + NVME_CTRL_CTRATT_128_ID = 1 << 0, + NVME_CTRL_CTRATT_NON_OP_PSP = 1 << 1, + NVME_CTRL_CTRATT_NVM_SETS = 1 << 2, + NVME_CTRL_CTRATT_READ_RECV_LVLS = 1 << 3, + NVME_CTRL_CTRATT_ENDURANCE_GROUPS = 1 << 4, + NVME_CTRL_CTRATT_PREDICTABLE_LAT = 1 << 5, + NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY = 1 << 7, + NVME_CTRL_CTRATT_UUID_LIST = 1 << 9, }; struct nvme_lbaf { @@ -352,6 +374,9 @@ enum { NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, NVME_ID_CNS_CTRL_LIST = 0x13, + NVME_ID_CNS_SCNDRY_CTRL_LIST = 0x15, + NVME_ID_CNS_NS_GRANULARITY = 0x16, + NVME_ID_CNS_UUID_LIST = 0x17, }; enum { @@ -409,7 +434,8 @@ struct nvme_smart_log { __u8 avail_spare; __u8 spare_thresh; __u8 percent_used; - __u8 rsvd6[26]; + __u8 endu_grp_crit_warn_sumry; + __u8 rsvd7[25]; __u8 data_units_read[16]; __u8 data_units_written[16]; __u8 host_reads[16]; @@ -423,7 +449,11 @@ struct nvme_smart_log { __le32 warning_temp_time; __le32 critical_comp_time; __le16 temp_sensor[8]; - __u8 rsvd216[296]; + __le32 thm_temp1_trans_count; + __le32 thm_temp2_trans_count; + __le32 thm_temp1_total_time; + __le32 thm_temp2_total_time; + __u8 rsvd232[280]; }; struct nvme_fw_slot_info_log { @@ -440,6 +470,7 @@ enum { NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, + NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, }; struct nvme_effects_log { @@ -563,6 +594,7 @@ enum nvme_opcode { nvme_cmd_compare = 0x05, nvme_cmd_write_zeroes = 0x08, nvme_cmd_dsm = 0x09, + nvme_cmd_verify = 0x0c, nvme_cmd_resv_register = 0x0d, nvme_cmd_resv_report = 0x0e, nvme_cmd_resv_acquire = 0x11, @@ -772,6 +804,12 @@ struct nvme_write_zeroes_cmd { /* Features */ +enum { + NVME_TEMP_THRESH_MASK = 0xffff, + NVME_TEMP_THRESH_SELECT_SHIFT = 16, + NVME_TEMP_THRESH_TYPE_UNDER = 0x100000, +}; + struct nvme_feat_auto_pst { __le64 entries[32]; }; @@ -806,10 +844,14 @@ enum nvme_admin_opcode { nvme_admin_ns_mgmt = 0x0d, nvme_admin_activate_fw = 0x10, nvme_admin_download_fw = 0x11, + nvme_admin_dev_self_test = 0x14, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, nvme_admin_directive_send = 0x19, nvme_admin_directive_recv = 0x1a, + nvme_admin_virtual_mgmt = 0x1c, + nvme_admin_nvme_mi_send = 0x1d, + nvme_admin_nvme_mi_recv = 0x1e, nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, @@ -873,6 +915,7 @@ enum { NVME_FEAT_PLM_CONFIG = 0x13, NVME_FEAT_PLM_WINDOW = 0x14, NVME_FEAT_HOST_BEHAVIOR = 0x16, + NVME_FEAT_SANITIZE = 0x17, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, @@ -883,6 +926,10 @@ enum { NVME_LOG_FW_SLOT = 0x03, NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, + NVME_LOG_DEVICE_SELF_TEST = 0x06, + NVME_LOG_TELEMETRY_HOST = 0x07, + NVME_LOG_TELEMETRY_CTRL = 0x08, + NVME_LOG_ENDURANCE_GROUP = 0x09, NVME_LOG_ANA = 0x0c, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, @@ -1290,7 +1337,11 @@ enum { NVME_SC_SGL_INVALID_OFFSET = 0x16, NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_SANITIZE_FAILED = 0x1C, + NVME_SC_SANITIZE_IN_PROGRESS = 0x1D, + NVME_SC_NS_WRITE_PROTECTED = 0x20, + NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, @@ -1328,6 +1379,8 @@ enum { NVME_SC_NS_NOT_ATTACHED = 0x11a, NVME_SC_THIN_PROV_NOT_SUPP = 0x11b, NVME_SC_CTRL_LIST_INVALID = 0x11c, + NVME_SC_BP_WRITE_PROHIBITED = 0x11e, + NVME_SC_PMR_SAN_PROHIBITED = 0x123, /* * I/O Command Set Specific - NVM commands: @@ -1368,6 +1421,7 @@ enum { NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, NVME_SC_HOST_PATH_ERROR = 0x370, + NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, NVME_SC_DNR = 0x4000, diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 8f8be5b00060..02dc4aa992b2 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -89,6 +89,9 @@ void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, int nvmem_register_notifier(struct notifier_block *nb); int nvmem_unregister_notifier(struct notifier_block *nb); +struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -204,6 +207,12 @@ static inline int nvmem_unregister_notifier(struct notifier_block *nb) return -EOPNOTSUPP; } +static inline struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h index ebb4f332588b..7f53a5c6f35e 100644 --- a/include/linux/platform_data/intel-spi.h +++ b/include/linux/platform_data/intel-spi.h @@ -13,6 +13,7 @@ enum intel_spi_type { INTEL_SPI_BYT = 1, INTEL_SPI_LPT, INTEL_SPI_BXT, + INTEL_SPI_CNL, }; /** diff --git a/include/linux/psci.h b/include/linux/psci.h index e2bacc6fd2f2..ebe0a881d13d 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -7,6 +7,7 @@ #ifndef __LINUX_PSCI_H #define __LINUX_PSCI_H +#include <linux/arm-smccc.h> #include <linux/init.h> #include <linux/types.h> @@ -18,12 +19,6 @@ bool psci_tos_resident_on(int cpu); int psci_cpu_suspend_enter(u32 state); bool psci_power_state_is_valid(u32 state); -enum psci_conduit { - PSCI_CONDUIT_NONE, - PSCI_CONDUIT_SMC, - PSCI_CONDUIT_HVC, -}; - enum smccc_version { SMCCC_VERSION_1_0, SMCCC_VERSION_1_1, @@ -38,7 +33,7 @@ struct psci_operations { int (*affinity_info)(unsigned long target_affinity, unsigned long lowest_affinity_level); int (*migrate_info_type)(void); - enum psci_conduit conduit; + enum arm_smccc_conduit conduit; enum smccc_version smccc_version; }; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index b5116013f27e..63e62372443a 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -316,24 +316,6 @@ radix_tree_iter_lookup(const struct radix_tree_root *root, } /** - * radix_tree_iter_find - find a present entry - * @root: radix tree root - * @iter: iterator state - * @index: start location - * - * This function returns the slot containing the entry with the lowest index - * which is at least @index. If @index is larger than any present entry, this - * function returns NULL. The @iter is updated to describe the entry found. - */ -static inline void __rcu ** -radix_tree_iter_find(const struct radix_tree_root *root, - struct radix_tree_iter *iter, unsigned long index) -{ - radix_tree_iter_init(iter, index); - return radix_tree_next_chunk(root, iter, 0); -} - -/** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index 9326d671b6e6..eaae6b4e9f24 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -7,7 +7,7 @@ struct reset_controller_dev; /** - * struct reset_control_ops + * struct reset_control_ops - reset controller driver callbacks * * @reset: for self-deasserting resets, does all necessary * things to reset the device @@ -33,7 +33,7 @@ struct of_phandle_args; * @provider: name of the reset controller device controlling this reset line * @index: ID of the reset controller in the reset controller device * @dev_id: name of the device associated with this reset line - * @con_id name of the reset line (can be NULL) + * @con_id: name of the reset line (can be NULL) */ struct reset_control_lookup { struct list_head list; diff --git a/include/linux/reset.h b/include/linux/reset.h index e7793fc0fa93..eb597e8aa430 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -143,7 +143,7 @@ static inline int device_reset_optional(struct device *dev) * If this function is called more than once for the same reset_control it will * return -EBUSY. * - * See reset_control_get_shared for details on shared references to + * See reset_control_get_shared() for details on shared references to * reset-controls. * * Use of id names is optional. diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index a986ac12a848..e40d019c3d9d 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -216,15 +216,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, */ bool sbitmap_any_bit_set(const struct sbitmap *sb); -/** - * sbitmap_any_bit_clear() - Check for an unset bit in a &struct - * sbitmap. - * @sb: Bitmap to check. - * - * Return: true if any bit in the bitmap is clear, false otherwise. - */ -bool sbitmap_any_bit_clear(const struct sbitmap *sb); - #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..6666e25606b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ extern struct pid *cad_pid; #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ +#define PF_IO_WORKER 0x20000000 /* Task is an IO worker */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 53c28d750a45..1ac0d712a9c3 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -42,6 +42,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_PSID_REVERT_TPR: case IOC_OPAL_MBR_DONE: case IOC_OPAL_WRITE_SHADOW_MBR: + case IOC_OPAL_GENERIC_TABLE_RW: return true; } return false; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 64a395c7f689..8688f7adfda7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4169,12 +4169,18 @@ static inline void skb_ext_reset(struct sk_buff *skb) skb->active_extensions = 0; } } + +static inline bool skb_has_extensions(struct sk_buff *skb) +{ + return unlikely(skb->active_extensions); +} #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} +static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e4b3fb4bb77c..ce7055259877 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -139,6 +139,11 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) } } +static inline u32 sk_msg_iter_dist(u32 start, u32 end) +{ + return end >= start ? end - start : end + (MAX_MSG_FRAGS - start); +} + #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ @@ -198,9 +203,7 @@ static inline u32 sk_msg_elem_used(const struct sk_msg *msg) if (sk_msg_full(msg)) return MAX_MSG_FRAGS; - return msg->sg.end >= msg->sg.start ? - msg->sg.end - msg->sg.start : - msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); + return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) diff --git a/include/linux/socket.h b/include/linux/socket.h index 4049d9755cf1..09c32a21555b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -392,6 +392,9 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); +extern int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); diff --git a/include/linux/stat.h b/include/linux/stat.h index 765573dc17d6..528c4baad091 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -33,7 +33,8 @@ struct kstat { STATX_ATTR_IMMUTABLE | \ STATX_ATTR_APPEND | \ STATX_ATTR_NODUMP | \ - STATX_ATTR_ENCRYPTED \ + STATX_ATTR_ENCRYPTED | \ + STATX_ATTR_VERITY \ )/* Attrs corresponding to FS_*_FL flags */ u64 ino; dev_t dev; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 53c0ea9ec9df..0d6e949ba315 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -21,6 +21,7 @@ #include <linux/acpi.h> #include <linux/cdev.h> #include <linux/fs.h> +#include <linux/highmem.h> #include <crypto/hash_info.h> #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ @@ -67,6 +68,8 @@ struct tpm_class_ops { u8 (*status) (struct tpm_chip *chip); void (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); + void (*update_durations)(struct tpm_chip *chip, + unsigned long *duration_cap); int (*go_idle)(struct tpm_chip *chip); int (*cmd_ready)(struct tpm_chip *chip); int (*request_locality)(struct tpm_chip *chip, int loc); @@ -161,6 +164,235 @@ struct tpm_chip { int locality; }; +#define TPM_HEADER_SIZE 10 + +enum tpm2_const { + TPM2_PLATFORM_PCR = 24, + TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), +}; + +enum tpm2_timeouts { + TPM2_TIMEOUT_A = 750, + TPM2_TIMEOUT_B = 2000, + TPM2_TIMEOUT_C = 200, + TPM2_TIMEOUT_D = 30, + TPM2_DURATION_SHORT = 20, + TPM2_DURATION_MEDIUM = 750, + TPM2_DURATION_LONG = 2000, + TPM2_DURATION_LONG_LONG = 300000, + TPM2_DURATION_DEFAULT = 120000, +}; + +enum tpm2_structures { + TPM2_ST_NO_SESSIONS = 0x8001, + TPM2_ST_SESSIONS = 0x8002, +}; + +/* Indicates from what layer of the software stack the error comes from */ +#define TSS2_RC_LAYER_SHIFT 16 +#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) + +enum tpm2_return_codes { + TPM2_RC_SUCCESS = 0x0000, + TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ + TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ + TPM2_RC_FAILURE = 0x0101, + TPM2_RC_DISABLED = 0x0120, + TPM2_RC_COMMAND_CODE = 0x0143, + TPM2_RC_TESTING = 0x090A, /* RC_WARN */ + TPM2_RC_REFERENCE_H0 = 0x0910, + TPM2_RC_RETRY = 0x0922, +}; + +enum tpm2_command_codes { + TPM2_CC_FIRST = 0x011F, + TPM2_CC_HIERARCHY_CONTROL = 0x0121, + TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, + TPM2_CC_CREATE_PRIMARY = 0x0131, + TPM2_CC_SEQUENCE_COMPLETE = 0x013E, + TPM2_CC_SELF_TEST = 0x0143, + TPM2_CC_STARTUP = 0x0144, + TPM2_CC_SHUTDOWN = 0x0145, + TPM2_CC_NV_READ = 0x014E, + TPM2_CC_CREATE = 0x0153, + TPM2_CC_LOAD = 0x0157, + TPM2_CC_SEQUENCE_UPDATE = 0x015C, + TPM2_CC_UNSEAL = 0x015E, + TPM2_CC_CONTEXT_LOAD = 0x0161, + TPM2_CC_CONTEXT_SAVE = 0x0162, + TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_VERIFY_SIGNATURE = 0x0177, + TPM2_CC_GET_CAPABILITY = 0x017A, + TPM2_CC_GET_RANDOM = 0x017B, + TPM2_CC_PCR_READ = 0x017E, + TPM2_CC_PCR_EXTEND = 0x0182, + TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, + TPM2_CC_HASH_SEQUENCE_START = 0x0186, + TPM2_CC_CREATE_LOADED = 0x0191, + TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ +}; + +enum tpm2_permanent_handles { + TPM2_RS_PW = 0x40000009, +}; + +enum tpm2_capabilities { + TPM2_CAP_HANDLES = 1, + TPM2_CAP_COMMANDS = 2, + TPM2_CAP_PCRS = 5, + TPM2_CAP_TPM_PROPERTIES = 6, +}; + +enum tpm2_properties { + TPM_PT_TOTAL_COMMANDS = 0x0129, +}; + +enum tpm2_startup_types { + TPM2_SU_CLEAR = 0x0000, + TPM2_SU_STATE = 0x0001, +}; + +enum tpm2_cc_attrs { + TPM2_CC_ATTR_CHANDLES = 25, + TPM2_CC_ATTR_RHANDLE = 28, +}; + +#define TPM_VID_INTEL 0x8086 +#define TPM_VID_WINBOND 0x1050 +#define TPM_VID_STM 0x104A + +enum tpm_chip_flags { + TPM_CHIP_FLAG_TPM2 = BIT(1), + TPM_CHIP_FLAG_IRQ = BIT(2), + TPM_CHIP_FLAG_VIRTUAL = BIT(3), + TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), + TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), + TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), +}; + +#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) + +struct tpm_header { + __be16 tag; + __be32 length; + union { + __be32 ordinal; + __be32 return_code; + }; +} __packed; + +/* A string buffer type for constructing TPM commands. This is based on the + * ideas of string buffer code in security/keys/trusted.h but is heap based + * in order to keep the stack usage minimal. + */ + +enum tpm_buf_flags { + TPM_BUF_OVERFLOW = BIT(0), +}; + +struct tpm_buf { + unsigned int flags; + u8 *data; +}; + +enum tpm2_object_attributes { + TPM2_OA_USER_WITH_AUTH = BIT(6), +}; + +enum tpm2_session_attributes { + TPM2_SA_CONTINUE_SESSION = BIT(0), +}; + +struct tpm2_hash { + unsigned int crypto_id; + unsigned int tpm_id; +}; + +static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + head->tag = cpu_to_be16(tag); + head->length = cpu_to_be32(sizeof(*head)); + head->ordinal = cpu_to_be32(ordinal); +} + +static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + buf->data = (u8 *)__get_free_page(GFP_KERNEL); + if (!buf->data) + return -ENOMEM; + + buf->flags = 0; + tpm_buf_reset(buf, tag, ordinal); + return 0; +} + +static inline void tpm_buf_destroy(struct tpm_buf *buf) +{ + free_page((unsigned long)buf->data); +} + +static inline u32 tpm_buf_length(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be32_to_cpu(head->length); +} + +static inline u16 tpm_buf_tag(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be16_to_cpu(head->tag); +} + +static inline void tpm_buf_append(struct tpm_buf *buf, + const unsigned char *new_data, + unsigned int new_len) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + u32 len = tpm_buf_length(buf); + + /* Return silently if overflow has already happened. */ + if (buf->flags & TPM_BUF_OVERFLOW) + return; + + if ((len + new_len) > PAGE_SIZE) { + WARN(1, "tpm_buf: overflow\n"); + buf->flags |= TPM_BUF_OVERFLOW; + return; + } + + memcpy(&buf->data[len], new_data, new_len); + head->length = cpu_to_be32(len + new_len); +} + +static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) +{ + tpm_buf_append(buf, &value, 1); +} + +static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) +{ + __be16 value2 = cpu_to_be16(value); + + tpm_buf_append(buf, (u8 *) &value2, 2); +} + +static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) +{ + __be32 value2 = cpu_to_be32(value); + + tpm_buf_append(buf, (u8 *) &value2, 4); +} + +static inline u32 tpm2_rc_value(u32 rc) +{ + return (rc & BIT(7)) ? rc & 0xff : rc; +} + #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); @@ -170,12 +402,6 @@ extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); -extern int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); -extern int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); extern struct tpm_chip *tpm_default_chip(void); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) @@ -204,18 +430,6 @@ static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) return -ENODEV; } -static inline int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} -static inline int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} static inline struct tpm_chip *tpm_default_chip(void) { return NULL; diff --git a/include/net/bonding.h b/include/net/bonding.h index 1afc125014da..3d56b026bb9e 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -159,7 +159,6 @@ struct slave { unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 link_new_state; /* one of BOND_LINK_XXXX */ - s8 new_link; u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ @@ -549,7 +548,7 @@ static inline void bond_propose_link_state(struct slave *slave, int state) static inline void bond_commit_link_state(struct slave *slave, bool notify) { - if (slave->link == slave->link_new_state) + if (slave->link_new_state == BOND_LINK_NOCHANGE) return; slave->link = slave->link_new_state; diff --git a/include/net/devlink.h b/include/net/devlink.h index 23e4b65ec9df..2116c88663a1 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -38,7 +38,8 @@ struct devlink { struct device *dev; possible_net_t _net; struct mutex lock; - bool reload_failed; + u8 reload_failed:1, + reload_enabled:1; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -774,6 +775,8 @@ struct ib_device; struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); +void devlink_reload_enable(struct devlink *devlink); +void devlink_reload_disable(struct devlink *devlink); void devlink_free(struct devlink *devlink); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 107c0d700ed6..38a9a3d1222b 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -313,7 +313,7 @@ static int fq_init(struct fq *fq, int flows_cnt) fq->limit = 8192; fq->memory_limit = 16 << 20; /* 16 MBytes */ - fq->flows = kcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); + fq->flows = kvcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); if (!fq->flows) return -ENOMEM; @@ -331,7 +331,7 @@ static void fq_reset(struct fq *fq, for (i = 0; i < fq->flows_cnt; i++) fq_flow_reset(fq, &fq->flows[i], free_func); - kfree(fq->flows); + kvfree(fq->flows); fq->flows = NULL; } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 50a67bd6a434..b8452cc0e059 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -439,8 +439,8 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { unsigned long now = jiffies; - if (neigh->used != now) - neigh->used = now; + if (READ_ONCE(neigh->used) != now) + WRITE_ONCE(neigh->used, now); if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE))) return __neigh_event_send(neigh, skb); return 0; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 001d294edf57..2d0275f13bbf 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -820,7 +820,8 @@ struct nft_expr_ops { */ struct nft_expr { const struct nft_expr_ops *ops; - unsigned char data[]; + unsigned char data[] + __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_expr_priv(const struct nft_expr *expr) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 637548d54b3e..d80acda231ae 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -15,6 +15,7 @@ #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/atomic.h> +#include <linux/hashtable.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> #include <net/flow_offload.h> @@ -362,6 +363,7 @@ struct tcf_proto { bool deleting; refcount_t refcnt; struct rcu_head rcu; + struct hlist_node destroy_ht_node; }; struct qdisc_skb_cb { @@ -414,6 +416,8 @@ struct tcf_block { struct list_head filter_chain_list; } chain0; struct rcu_head rcu; + DECLARE_HASHTABLE(proto_destroy_ht, 7); + struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */ }; #ifdef CONFIG_PROVE_LOCKING diff --git a/include/net/sock.h b/include/net/sock.h index 8f9adcfac41b..718e62fbe869 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2342,7 +2342,7 @@ static inline ktime_t sock_read_timestamp(struct sock *sk) return kt; #else - return sk->sk_stamp; + return READ_ONCE(sk->sk_stamp); #endif } @@ -2353,7 +2353,7 @@ static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else - sk->sk_stamp = kt; + WRITE_ONCE(sk->sk_stamp, kt); #endif } diff --git a/include/net/tls.h b/include/net/tls.h index c664e6dba0d1..f4ad831eaa02 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -40,6 +40,7 @@ #include <linux/socket.h> #include <linux/tcp.h> #include <linux/skmsg.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> @@ -269,6 +270,10 @@ struct tls_context { bool in_tcp_sendpages; bool pending_open_record_frags; + + struct mutex tx_lock; /* protects partially_sent_* fields and + * per-type TX fields + */ unsigned long flags; /* cache cold stuff */ @@ -351,6 +356,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int tls_sw_sendpage_locked(struct sock *sk, struct page *page, + int offset, size_t size, int flags); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 75ae1899452b..620bf1b38fba 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -19,7 +19,7 @@ struct btrfs_delayed_ref_node; struct btrfs_delayed_tree_ref; struct btrfs_delayed_data_ref; struct btrfs_delayed_ref_head; -struct btrfs_block_group_cache; +struct btrfs_block_group; struct btrfs_free_cluster; struct map_lookup; struct extent_buffer; @@ -170,7 +170,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, TP_STRUCT__entry_btrfs( __field( u64, ino ) - __field( blkcnt_t, blocks ) + __field( u64, blocks ) __field( u64, disk_i_size ) __field( u64, generation ) __field( u64, last_trans ) @@ -194,7 +194,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, show_root_type(__entry->root_objectid), __entry->generation, __entry->ino, - (unsigned long long)__entry->blocks, + __entry->blocks, __entry->disk_i_size, __entry->last_trans, __entry->logged_trans) @@ -292,7 +292,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, TRACE_EVENT(btrfs_handle_em_exist, - TP_PROTO(struct btrfs_fs_info *fs_info, + TP_PROTO(const struct btrfs_fs_info *fs_info, const struct extent_map *existing, const struct extent_map *map, u64 start, u64 len), @@ -330,8 +330,8 @@ TRACE_EVENT(btrfs_handle_em_exist, /* file extent item */ DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular, - TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l, - struct btrfs_file_extent_item *fi, u64 start), + TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, + const struct btrfs_file_extent_item *fi, u64 start), TP_ARGS(bi, l, fi, start), @@ -385,8 +385,8 @@ DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular, DECLARE_EVENT_CLASS( btrfs__file_extent_item_inline, - TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l, - struct btrfs_file_extent_item *fi, int slot, u64 start), + TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, + const struct btrfs_file_extent_item *fi, int slot, u64 start), TP_ARGS(bi, l, fi, slot, start), @@ -426,8 +426,8 @@ DECLARE_EVENT_CLASS( DEFINE_EVENT( btrfs__file_extent_item_regular, btrfs_get_extent_show_fi_regular, - TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l, - struct btrfs_file_extent_item *fi, u64 start), + TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, + const struct btrfs_file_extent_item *fi, u64 start), TP_ARGS(bi, l, fi, start) ); @@ -435,8 +435,8 @@ DEFINE_EVENT( DEFINE_EVENT( btrfs__file_extent_item_regular, btrfs_truncate_show_fi_regular, - TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l, - struct btrfs_file_extent_item *fi, u64 start), + TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, + const struct btrfs_file_extent_item *fi, u64 start), TP_ARGS(bi, l, fi, start) ); @@ -444,8 +444,8 @@ DEFINE_EVENT( DEFINE_EVENT( btrfs__file_extent_item_inline, btrfs_get_extent_show_fi_inline, - TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l, - struct btrfs_file_extent_item *fi, int slot, u64 start), + TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, + const struct btrfs_file_extent_item *fi, int slot, u64 start), TP_ARGS(bi, l, fi, slot, start) ); @@ -453,8 +453,8 @@ DEFINE_EVENT( DEFINE_EVENT( btrfs__file_extent_item_inline, btrfs_truncate_show_fi_inline, - TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l, - struct btrfs_file_extent_item *fi, int slot, u64 start), + TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, + const struct btrfs_file_extent_item *fi, int slot, u64 start), TP_ARGS(bi, l, fi, slot, start) ); @@ -574,7 +574,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, __field( char, for_kupdate ) __field( char, for_reclaim ) __field( char, range_cyclic ) - __field( pgoff_t, writeback_index ) + __field( unsigned long, writeback_index ) __field( u64, root_objectid ) ), @@ -603,7 +603,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, __entry->range_start, __entry->range_end, __entry->for_kupdate, __entry->for_reclaim, __entry->range_cyclic, - (unsigned long)__entry->writeback_index) + __entry->writeback_index) ); DEFINE_EVENT(btrfs__writepage, __extent_writepage, @@ -622,7 +622,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, TP_STRUCT__entry_btrfs( __field( u64, ino ) - __field( pgoff_t, index ) + __field( unsigned long, index ) __field( u64, start ) __field( u64, end ) __field( int, uptodate ) @@ -642,7 +642,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu start=%llu " "end=%llu uptodate=%d", show_root_type(__entry->root_objectid), - __entry->ino, (unsigned long)__entry->index, + __entry->ino, __entry->index, __entry->start, __entry->end, __entry->uptodate) ); @@ -699,7 +699,7 @@ TRACE_EVENT(btrfs_sync_fs, TRACE_EVENT(btrfs_add_block_group, TP_PROTO(const struct btrfs_fs_info *fs_info, - const struct btrfs_block_group_cache *block_group, int create), + const struct btrfs_block_group *block_group, int create), TP_ARGS(fs_info, block_group, create), @@ -713,11 +713,10 @@ TRACE_EVENT(btrfs_add_block_group, ), TP_fast_assign_btrfs(fs_info, - __entry->offset = block_group->key.objectid; - __entry->size = block_group->key.offset; + __entry->offset = block_group->start; + __entry->size = block_group->length; __entry->flags = block_group->flags; - __entry->bytes_used = - btrfs_block_group_used(&block_group->item); + __entry->bytes_used = block_group->used; __entry->bytes_super = block_group->bytes_super; __entry->create = create; ), @@ -1018,7 +1017,7 @@ TRACE_EVENT(btrfs_cow_block, TRACE_EVENT(btrfs_space_reservation, - TP_PROTO(const struct btrfs_fs_info *fs_info, char *type, u64 val, + TP_PROTO(const struct btrfs_fs_info *fs_info, const char *type, u64 val, u64 bytes, int reserve), TP_ARGS(fs_info, type, val, bytes, reserve), @@ -1051,7 +1050,7 @@ TRACE_EVENT(btrfs_space_reservation, TRACE_EVENT(btrfs_trigger_flush, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 bytes, - int flush, char *reason), + int flush, const char *reason), TP_ARGS(fs_info, flags, bytes, flush, reason), @@ -1185,7 +1184,7 @@ TRACE_EVENT(find_free_extent, DECLARE_EVENT_CLASS(btrfs__reserve_extent, - TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start, + TP_PROTO(const struct btrfs_block_group *block_group, u64 start, u64 len), TP_ARGS(block_group, start, len), @@ -1198,7 +1197,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, ), TP_fast_assign_btrfs(block_group->fs_info, - __entry->bg_objectid = block_group->key.objectid; + __entry->bg_objectid = block_group->start; __entry->flags = block_group->flags; __entry->start = start; __entry->len = len; @@ -1215,7 +1214,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent, - TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start, + TP_PROTO(const struct btrfs_block_group *block_group, u64 start, u64 len), TP_ARGS(block_group, start, len) @@ -1223,7 +1222,7 @@ DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent, DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent_cluster, - TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start, + TP_PROTO(const struct btrfs_block_group *block_group, u64 start, u64 len), TP_ARGS(block_group, start, len) @@ -1231,7 +1230,7 @@ DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent_cluster, TRACE_EVENT(btrfs_find_cluster, - TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start, + TP_PROTO(const struct btrfs_block_group *block_group, u64 start, u64 bytes, u64 empty_size, u64 min_bytes), TP_ARGS(block_group, start, bytes, empty_size, min_bytes), @@ -1246,7 +1245,7 @@ TRACE_EVENT(btrfs_find_cluster, ), TP_fast_assign_btrfs(block_group->fs_info, - __entry->bg_objectid = block_group->key.objectid; + __entry->bg_objectid = block_group->start; __entry->flags = block_group->flags; __entry->start = start; __entry->bytes = bytes; @@ -1264,7 +1263,7 @@ TRACE_EVENT(btrfs_find_cluster, TRACE_EVENT(btrfs_failed_cluster_setup, - TP_PROTO(const struct btrfs_block_group_cache *block_group), + TP_PROTO(const struct btrfs_block_group *block_group), TP_ARGS(block_group), @@ -1273,7 +1272,7 @@ TRACE_EVENT(btrfs_failed_cluster_setup, ), TP_fast_assign_btrfs(block_group->fs_info, - __entry->bg_objectid = block_group->key.objectid; + __entry->bg_objectid = block_group->start; ), TP_printk_btrfs("block_group=%llu", __entry->bg_objectid) @@ -1281,7 +1280,7 @@ TRACE_EVENT(btrfs_failed_cluster_setup, TRACE_EVENT(btrfs_setup_cluster, - TP_PROTO(const struct btrfs_block_group_cache *block_group, + TP_PROTO(const struct btrfs_block_group *block_group, const struct btrfs_free_cluster *cluster, u64 size, int bitmap), @@ -1297,7 +1296,7 @@ TRACE_EVENT(btrfs_setup_cluster, ), TP_fast_assign_btrfs(block_group->fs_info, - __entry->bg_objectid = block_group->key.objectid; + __entry->bg_objectid = block_group->start; __entry->flags = block_group->flags; __entry->start = cluster->window_start; __entry->max_size = cluster->max_size; @@ -1325,17 +1324,17 @@ TRACE_EVENT(alloc_extent_state, TP_STRUCT__entry( __field(const struct extent_state *, state) __field(gfp_t, mask) - __field(unsigned long, ip) + __field(const void*, ip) ), TP_fast_assign( __entry->state = state, __entry->mask = mask, - __entry->ip = IP + __entry->ip = (const void *)IP ), TP_printk("state=%p mask=%s caller=%pS", __entry->state, - show_gfp_flags(__entry->mask), (const void *)__entry->ip) + show_gfp_flags(__entry->mask), __entry->ip) ); TRACE_EVENT(free_extent_state, @@ -1346,16 +1345,15 @@ TRACE_EVENT(free_extent_state, TP_STRUCT__entry( __field(const struct extent_state *, state) - __field(unsigned long, ip) + __field(const void*, ip) ), TP_fast_assign( __entry->state = state, - __entry->ip = IP + __entry->ip = (const void *)IP ), - TP_printk("state=%p caller=%pS", __entry->state, - (const void *)__entry->ip) + TP_printk("state=%p caller=%pS", __entry->state, __entry->ip) ); DECLARE_EVENT_CLASS(btrfs__work, @@ -1389,9 +1387,9 @@ DECLARE_EVENT_CLASS(btrfs__work, ); /* - * For situiations when the work is freed, we pass fs_info and a tag that that - * matches address of the work structure so it can be paired with the - * scheduling event. + * For situations when the work is freed, we pass fs_info and a tag that matches + * the address of the work structure so it can be paired with the scheduling + * event. DO NOT add anything here that dereferences wtag. */ DECLARE_EVENT_CLASS(btrfs__work__done, @@ -1567,8 +1565,7 @@ DECLARE_EVENT_CLASS(btrfs_qgroup_extent, ), TP_printk_btrfs("bytenr=%llu num_bytes=%llu", - (unsigned long long)__entry->bytenr, - (unsigned long long)__entry->num_bytes) + __entry->bytenr, __entry->num_bytes) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents, @@ -1644,7 +1641,7 @@ TRACE_EVENT(btrfs_qgroup_account_extent, TRACE_EVENT(qgroup_update_counters, TP_PROTO(const struct btrfs_fs_info *fs_info, - struct btrfs_qgroup *qgroup, + const struct btrfs_qgroup *qgroup, u64 cur_old_count, u64 cur_new_count), TP_ARGS(fs_info, qgroup, cur_old_count, cur_new_count), @@ -1825,7 +1822,7 @@ DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_insert, ); TRACE_EVENT(btrfs_inode_mod_outstanding_extents, - TP_PROTO(struct btrfs_root *root, u64 ino, int mod), + TP_PROTO(const struct btrfs_root *root, u64 ino, int mod), TP_ARGS(root, ino, mod), @@ -1847,7 +1844,7 @@ TRACE_EVENT(btrfs_inode_mod_outstanding_extents, ); DECLARE_EVENT_CLASS(btrfs__block_group, - TP_PROTO(const struct btrfs_block_group_cache *bg_cache), + TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache), @@ -1859,9 +1856,9 @@ DECLARE_EVENT_CLASS(btrfs__block_group, ), TP_fast_assign_btrfs(bg_cache->fs_info, - __entry->bytenr = bg_cache->key.objectid, - __entry->len = bg_cache->key.offset, - __entry->used = btrfs_block_group_used(&bg_cache->item); + __entry->bytenr = bg_cache->start, + __entry->len = bg_cache->length, + __entry->used = bg_cache->used; __entry->flags = bg_cache->flags; ), @@ -1871,19 +1868,19 @@ DECLARE_EVENT_CLASS(btrfs__block_group, ); DEFINE_EVENT(btrfs__block_group, btrfs_remove_block_group, - TP_PROTO(const struct btrfs_block_group_cache *bg_cache), + TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); DEFINE_EVENT(btrfs__block_group, btrfs_add_unused_block_group, - TP_PROTO(const struct btrfs_block_group_cache *bg_cache), + TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); DEFINE_EVENT(btrfs__block_group, btrfs_skip_unused_block_group, - TP_PROTO(const struct btrfs_block_group_cache *bg_cache), + TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); @@ -1906,7 +1903,7 @@ TRACE_EVENT(btrfs_set_extent_bit, TP_fast_assign_btrfs(tree->fs_info, __entry->owner = tree->owner; if (tree->private_data) { - struct inode *inode = tree->private_data; + const struct inode *inode = tree->private_data; __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->rootid = @@ -1945,7 +1942,7 @@ TRACE_EVENT(btrfs_clear_extent_bit, TP_fast_assign_btrfs(tree->fs_info, __entry->owner = tree->owner; if (tree->private_data) { - struct inode *inode = tree->private_data; + const struct inode *inode = tree->private_data; __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->rootid = @@ -1985,7 +1982,7 @@ TRACE_EVENT(btrfs_convert_extent_bit, TP_fast_assign_btrfs(tree->fs_info, __entry->owner = tree->owner; if (tree->private_data) { - struct inode *inode = tree->private_data; + const struct inode *inode = tree->private_data; __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->rootid = @@ -2094,8 +2091,8 @@ DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_read_lock_atomic); DECLARE_EVENT_CLASS(btrfs__space_info_update, - TP_PROTO(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *sinfo, u64 old, s64 diff), + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, u64 old, s64 diff), TP_ARGS(fs_info, sinfo, old, diff), @@ -2117,16 +2114,16 @@ DECLARE_EVENT_CLASS(btrfs__space_info_update, DEFINE_EVENT(btrfs__space_info_update, update_bytes_may_use, - TP_PROTO(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *sinfo, u64 old, s64 diff), + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, u64 old, s64 diff), TP_ARGS(fs_info, sinfo, old, diff) ); DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned, - TP_PROTO(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *sinfo, u64 old, s64 diff), + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, u64 old, s64 diff), TP_ARGS(fs_info, sinfo, old, diff) ); diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h new file mode 100644 index 000000000000..72a4d0174b02 --- /dev/null +++ b/include/trace/events/io_uring.h @@ -0,0 +1,358 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM io_uring + +#if !defined(_TRACE_IO_URING_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IO_URING_H + +#include <linux/tracepoint.h> + +struct io_wq_work; + +/** + * io_uring_create - called after a new io_uring context was prepared + * + * @fd: corresponding file descriptor + * @ctx: pointer to a ring context structure + * @sq_entries: actual SQ size + * @cq_entries: actual CQ size + * @flags: SQ ring flags, provided to io_uring_setup(2) + * + * Allows to trace io_uring creation and provide pointer to a context, that can + * be used later to find correlated events. + */ +TRACE_EVENT(io_uring_create, + + TP_PROTO(int fd, void *ctx, u32 sq_entries, u32 cq_entries, u32 flags), + + TP_ARGS(fd, ctx, sq_entries, cq_entries, flags), + + TP_STRUCT__entry ( + __field( int, fd ) + __field( void *, ctx ) + __field( u32, sq_entries ) + __field( u32, cq_entries ) + __field( u32, flags ) + ), + + TP_fast_assign( + __entry->fd = fd; + __entry->ctx = ctx; + __entry->sq_entries = sq_entries; + __entry->cq_entries = cq_entries; + __entry->flags = flags; + ), + + TP_printk("ring %p, fd %d sq size %d, cq size %d, flags %d", + __entry->ctx, __entry->fd, __entry->sq_entries, + __entry->cq_entries, __entry->flags) +); + +/** + * io_uring_register - called after a buffer/file/eventfd was succesfully + * registered for a ring + * + * @ctx: pointer to a ring context structure + * @opcode: describes which operation to perform + * @nr_user_files: number of registered files + * @nr_user_bufs: number of registered buffers + * @cq_ev_fd: whether eventfs registered or not + * @ret: return code + * + * Allows to trace fixed files/buffers/eventfds, that could be registered to + * avoid an overhead of getting references to them for every operation. This + * event, together with io_uring_file_get, can provide a full picture of how + * much overhead one can reduce via fixing. + */ +TRACE_EVENT(io_uring_register, + + TP_PROTO(void *ctx, unsigned opcode, unsigned nr_files, + unsigned nr_bufs, bool eventfd, long ret), + + TP_ARGS(ctx, opcode, nr_files, nr_bufs, eventfd, ret), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned, opcode ) + __field( unsigned, nr_files ) + __field( unsigned, nr_bufs ) + __field( bool, eventfd ) + __field( long, ret ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->opcode = opcode; + __entry->nr_files = nr_files; + __entry->nr_bufs = nr_bufs; + __entry->eventfd = eventfd; + __entry->ret = ret; + ), + + TP_printk("ring %p, opcode %d, nr_user_files %d, nr_user_bufs %d, " + "eventfd %d, ret %ld", + __entry->ctx, __entry->opcode, __entry->nr_files, + __entry->nr_bufs, __entry->eventfd, __entry->ret) +); + +/** + * io_uring_file_get - called before getting references to an SQE file + * + * @ctx: pointer to a ring context structure + * @fd: SQE file descriptor + * + * Allows to trace out how often an SQE file reference is obtained, which can + * help figuring out if it makes sense to use fixed files, or check that fixed + * files are used correctly. + */ +TRACE_EVENT(io_uring_file_get, + + TP_PROTO(void *ctx, int fd), + + TP_ARGS(ctx, fd), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( int, fd ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->fd = fd; + ), + + TP_printk("ring %p, fd %d", __entry->ctx, __entry->fd) +); + +/** + * io_uring_queue_async_work - called before submitting a new async work + * + * @ctx: pointer to a ring context structure + * @hashed: type of workqueue, hashed or normal + * @req: pointer to a submitted request + * @work: pointer to a submitted io_wq_work + * + * Allows to trace asynchronous work submission. + */ +TRACE_EVENT(io_uring_queue_async_work, + + TP_PROTO(void *ctx, int rw, void * req, struct io_wq_work *work, + unsigned int flags), + + TP_ARGS(ctx, rw, req, work, flags), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( int, rw ) + __field( void *, req ) + __field( struct io_wq_work *, work ) + __field( unsigned int, flags ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->rw = rw; + __entry->req = req; + __entry->work = work; + __entry->flags = flags; + ), + + TP_printk("ring %p, request %p, flags %d, %s queue, work %p", + __entry->ctx, __entry->req, __entry->flags, + __entry->rw ? "hashed" : "normal", __entry->work) +); + +/** + * io_uring_defer_list - called before the io_uring work added into defer_list + * + * @ctx: pointer to a ring context structure + * @req: pointer to a deferred request + * @shadow: whether request is shadow or not + * + * Allows to track deferred requests, to get an insight about what requests are + * not started immediately. + */ +TRACE_EVENT(io_uring_defer, + + TP_PROTO(void *ctx, void *req, bool shadow), + + TP_ARGS(ctx, req, shadow), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( void *, req ) + __field( bool, shadow ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->req = req; + __entry->shadow = shadow; + ), + + TP_printk("ring %p, request %p%s", __entry->ctx, __entry->req, + __entry->shadow ? ", shadow": "") +); + +/** + * io_uring_link - called before the io_uring request added into link_list of + * another request + * + * @ctx: pointer to a ring context structure + * @req: pointer to a linked request + * @target_req: pointer to a previous request, that would contain @req + * + * Allows to track linked requests, to understand dependencies between requests + * and how does it influence their execution flow. + */ +TRACE_EVENT(io_uring_link, + + TP_PROTO(void *ctx, void *req, void *target_req), + + TP_ARGS(ctx, req, target_req), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( void *, req ) + __field( void *, target_req ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->req = req; + __entry->target_req = target_req; + ), + + TP_printk("ring %p, request %p linked after %p", + __entry->ctx, __entry->req, __entry->target_req) +); + +/** + * io_uring_cqring_wait - called before start waiting for an available CQE + * + * @ctx: pointer to a ring context structure + * @min_events: minimal number of events to wait for + * + * Allows to track waiting for CQE, so that we can e.g. troubleshoot + * situations, when an application wants to wait for an event, that never + * comes. + */ +TRACE_EVENT(io_uring_cqring_wait, + + TP_PROTO(void *ctx, int min_events), + + TP_ARGS(ctx, min_events), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( int, min_events ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->min_events = min_events; + ), + + TP_printk("ring %p, min_events %d", __entry->ctx, __entry->min_events) +); + +/** + * io_uring_fail_link - called before failing a linked request + * + * @req: request, which links were cancelled + * @link: cancelled link + * + * Allows to track linked requests cancellation, to see not only that some work + * was cancelled, but also which request was the reason. + */ +TRACE_EVENT(io_uring_fail_link, + + TP_PROTO(void *req, void *link), + + TP_ARGS(req, link), + + TP_STRUCT__entry ( + __field( void *, req ) + __field( void *, link ) + ), + + TP_fast_assign( + __entry->req = req; + __entry->link = link; + ), + + TP_printk("request %p, link %p", __entry->req, __entry->link) +); + +/** + * io_uring_complete - called when completing an SQE + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: result of the request + * + */ +TRACE_EVENT(io_uring_complete, + + TP_PROTO(void *ctx, u64 user_data, long res), + + TP_ARGS(ctx, user_data, res), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( u64, user_data ) + __field( long, res ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + ), + + TP_printk("ring %p, user_data 0x%llx, result %ld", + __entry->ctx, (unsigned long long)__entry->user_data, + __entry->res) +); + + +/** + * io_uring_submit_sqe - called before submitting one SQE + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @force_nonblock: whether a context blocking or not + * @sq_thread: true if sq_thread has submitted this SQE + * + * Allows to track SQE submitting, to understand what was the source of it, SQ + * thread or io_uring_enter call. + */ +TRACE_EVENT(io_uring_submit_sqe, + + TP_PROTO(void *ctx, u64 user_data, bool force_nonblock, bool sq_thread), + + TP_ARGS(ctx, user_data, force_nonblock, sq_thread), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( u64, user_data ) + __field( bool, force_nonblock ) + __field( bool, sq_thread ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->force_nonblock = force_nonblock; + __entry->sq_thread = sq_thread; + ), + + TP_printk("ring %p, user data 0x%llx, non block %d, sq_thread %d", + __entry->ctx, (unsigned long long) __entry->user_data, + __entry->force_nonblock, __entry->sq_thread) +); + +#endif /* _TRACE_IO_URING_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 2bc9960a31aa..cf97f6339acb 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -86,7 +86,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s\n", + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->state)) diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index b048694070e2..37342a13c9cb 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -33,7 +33,8 @@ TRACE_EVENT(wbt_stat, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->rmean = stat[0].mean; __entry->rmin = stat[0].min; __entry->rmax = stat[0].max; @@ -67,7 +68,8 @@ TRACE_EVENT(wbt_lat, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->lat = div_u64(lat, 1000); ), @@ -103,7 +105,8 @@ TRACE_EVENT(wbt_step, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->msg = msg; __entry->step = step; __entry->window = div_u64(window, 1000); @@ -138,7 +141,8 @@ TRACE_EVENT(wbt_timer, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->status = status; __entry->step = step; __entry->inflight = inflight; diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 498eec813494..0cdef67135f0 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -120,9 +120,11 @@ struct blk_zone_report { }; /** - * struct blk_zone_range - BLKRESETZONE ioctl request - * @sector: starting sector of the first zone to issue reset write pointer - * @nr_sectors: Total number of sectors of 1 or more zones to reset + * struct blk_zone_range - BLKRESETZONE/BLKOPENZONE/ + * BLKCLOSEZONE/BLKFINISHZONE ioctl + * requests + * @sector: Starting sector of the first zone to operate on. + * @nr_sectors: Total number of sectors of all zones to operate on. */ struct blk_zone_range { __u64 sector; @@ -139,10 +141,19 @@ struct blk_zone_range { * sector range. The sector range must be zone aligned. * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors. * @BLKGETNRZONES: Get the total number of zones of the device. + * @BLKOPENZONE: Open the zones in the specified sector range. + * The 512 B sector range must be zone aligned. + * @BLKCLOSEZONE: Close the zones in the specified sector range. + * The 512 B sector range must be zone aligned. + * @BLKFINISHZONE: Mark the zones as full in the specified sector range. + * The 512 B sector range must be zone aligned. */ #define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) #define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) #define BLKGETZONESZ _IOR(0x12, 132, __u32) #define BLKGETNRZONES _IOR(0x12, 133, __u32) +#define BLKOPENZONE _IOW(0x12, 134, struct blk_zone_range) +#define BLKCLOSEZONE _IOW(0x12, 135, struct blk_zone_range) +#define BLKFINISHZONE _IOW(0x12, 136, struct blk_zone_range) #endif /* _UAPI_BLKZONED_H */ diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 3ee0678c0a83..7a8bc8b920f5 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -270,6 +270,7 @@ struct btrfs_ioctl_fs_info_args { #define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8) #define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9) #define BTRFS_FEATURE_INCOMPAT_METADATA_UUID (1ULL << 10) +#define BTRFS_FEATURE_INCOMPAT_RAID1C34 (1ULL << 11) struct btrfs_ioctl_feature_flags { __u64 compat_flags; @@ -831,7 +832,9 @@ enum btrfs_err_code { BTRFS_ERROR_DEV_TGT_REPLACE, BTRFS_ERROR_DEV_MISSING_NOT_FOUND, BTRFS_ERROR_DEV_ONLY_WRITABLE, - BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS + BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS, + BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET, + BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET, }; #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index b65c7ee75bc7..8e322e2c7e78 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -302,6 +302,9 @@ /* csum types */ enum btrfs_csum_type { BTRFS_CSUM_TYPE_CRC32 = 0, + BTRFS_CSUM_TYPE_XXHASH = 1, + BTRFS_CSUM_TYPE_SHA256 = 2, + BTRFS_CSUM_TYPE_BLAKE2 = 3, }; /* @@ -737,10 +740,12 @@ struct btrfs_balance_item { __le64 unused[4]; } __attribute__ ((__packed__)); -#define BTRFS_FILE_EXTENT_INLINE 0 -#define BTRFS_FILE_EXTENT_REG 1 -#define BTRFS_FILE_EXTENT_PREALLOC 2 -#define BTRFS_FILE_EXTENT_TYPES 2 +enum { + BTRFS_FILE_EXTENT_INLINE = 0, + BTRFS_FILE_EXTENT_REG = 1, + BTRFS_FILE_EXTENT_PREALLOC = 2, + BTRFS_NR_FILE_EXTENT_TYPES = 3, +}; struct btrfs_file_extent_item { /* @@ -836,6 +841,8 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6) #define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7) #define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8) +#define BTRFS_BLOCK_GROUP_RAID1C3 (1ULL << 9) +#define BTRFS_BLOCK_GROUP_RAID1C4 (1ULL << 10) #define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ BTRFS_SPACE_INFO_GLOBAL_RSV) @@ -847,6 +854,8 @@ enum btrfs_raid_types { BTRFS_RAID_SINGLE, BTRFS_RAID_RAID5, BTRFS_RAID_RAID6, + BTRFS_RAID_RAID1C3, + BTRFS_RAID_RAID1C4, BTRFS_NR_RAID_TYPES }; @@ -856,6 +865,8 @@ enum btrfs_raid_types { #define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ BTRFS_BLOCK_GROUP_RAID1 | \ + BTRFS_BLOCK_GROUP_RAID1C3 | \ + BTRFS_BLOCK_GROUP_RAID1C4 | \ BTRFS_BLOCK_GROUP_RAID5 | \ BTRFS_BLOCK_GROUP_RAID6 | \ BTRFS_BLOCK_GROUP_DUP | \ @@ -863,7 +874,9 @@ enum btrfs_raid_types { #define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \ BTRFS_BLOCK_GROUP_RAID6) -#define BTRFS_BLOCK_GROUP_RAID1_MASK (BTRFS_BLOCK_GROUP_RAID1) +#define BTRFS_BLOCK_GROUP_RAID1_MASK (BTRFS_BLOCK_GROUP_RAID1 | \ + BTRFS_BLOCK_GROUP_RAID1C3 | \ + BTRFS_BLOCK_GROUP_RAID1C4) /* * We need a bit for restriper to be able to tell when chunks of type diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index 1e988fdeba34..6a6d2c7655ff 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can.h * diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index 0fb328d93148..dd2b925b09ac 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/bcm.h * diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h index bfc4b5d22a5e..34633283de64 100644 --- a/include/uapi/linux/can/error.h +++ b/include/uapi/linux/can/error.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/error.h * diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h index 3aea5388c8e4..c2190bbe21d8 100644 --- a/include/uapi/linux/can/gw.h +++ b/include/uapi/linux/can/gw.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/gw.h * diff --git a/include/uapi/linux/can/j1939.h b/include/uapi/linux/can/j1939.h index c32325342d30..df6e821075c1 100644 --- a/include/uapi/linux/can/j1939.h +++ b/include/uapi/linux/can/j1939.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * j1939.h * diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 1bc70d3a4d39..6f598b73839e 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * linux/can/netlink.h * diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h index be3b36e7ff61..6a11d308eb5c 100644 --- a/include/uapi/linux/can/raw.h +++ b/include/uapi/linux/can/raw.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/raw.h * diff --git a/include/uapi/linux/can/vxcan.h b/include/uapi/linux/can/vxcan.h index 066812d118a2..4fa9d8777a07 100644 --- a/include/uapi/linux/can/vxcan.h +++ b/include/uapi/linux/can/vxcan.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ #ifndef _UAPI_CAN_VXCAN_H #define _UAPI_CAN_VXCAN_H diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 580b7a2e40e1..a8a2174db030 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -421,6 +421,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_FAILED, /* u8 0 or 1 */ + DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, /* u64 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 1d338357df8a..1f97b33c840e 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -58,7 +58,7 @@ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be * used to clear any hints previously set. */ -#define RWF_WRITE_LIFE_NOT_SET 0 +#define RWH_WRITE_LIFE_NOT_SET 0 #define RWH_WRITE_LIFE_NONE 1 #define RWH_WRITE_LIFE_SHORT 2 #define RWH_WRITE_LIFE_MEDIUM 3 @@ -66,6 +66,13 @@ #define RWH_WRITE_LIFE_EXTREME 5 /* + * The originally introduced spelling is remained from the first + * versions of the patch set that introduced the feature, see commit + * v4.13-rc1~212^2~51. + */ +#define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET + +/* * Types of directory notifications that may be requested. */ #define DN_ACCESS 0x00000001 /* File accessed */ diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 39ccfe9311c3..1beb174ad950 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -17,7 +17,8 @@ #define FSCRYPT_POLICY_FLAGS_PAD_32 0x03 #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 -#define FSCRYPT_POLICY_FLAGS_VALID 0x07 +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 +#define FSCRYPT_POLICY_FLAGS_VALID 0x0F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ea57526a5b89..2a1569211d87 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -19,7 +19,10 @@ struct io_uring_sqe { __u8 flags; /* IOSQE_ flags */ __u16 ioprio; /* ioprio for the request */ __s32 fd; /* file descriptor to do IO on */ - __u64 off; /* offset into file */ + union { + __u64 off; /* offset into file */ + __u64 addr2; + }; __u64 addr; /* pointer to buffer or iovecs */ __u32 len; /* buffer size or number of iovecs */ union { @@ -29,6 +32,8 @@ struct io_uring_sqe { __u32 sync_range_flags; __u32 msg_flags; __u32 timeout_flags; + __u32 accept_flags; + __u32 cancel_flags; }; __u64 user_data; /* data to be passed back at completion time */ union { @@ -50,6 +55,7 @@ struct io_uring_sqe { #define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */ #define IORING_SETUP_SQPOLL (1U << 1) /* SQ poll thread */ #define IORING_SETUP_SQ_AFF (1U << 2) /* sq_thread_cpu is valid */ +#define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */ #define IORING_OP_NOP 0 #define IORING_OP_READV 1 @@ -63,6 +69,10 @@ struct io_uring_sqe { #define IORING_OP_SENDMSG 9 #define IORING_OP_RECVMSG 10 #define IORING_OP_TIMEOUT 11 +#define IORING_OP_TIMEOUT_REMOVE 12 +#define IORING_OP_ACCEPT 13 +#define IORING_OP_ASYNC_CANCEL 14 +#define IORING_OP_LINK_TIMEOUT 15 /* * sqe->fsync_flags @@ -70,6 +80,11 @@ struct io_uring_sqe { #define IORING_FSYNC_DATASYNC (1U << 0) /* + * sqe->timeout_flags + */ +#define IORING_TIMEOUT_ABS (1U << 0) + +/* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { @@ -140,6 +155,7 @@ struct io_uring_params { * io_uring_params->features flags */ #define IORING_FEAT_SINGLE_MMAP (1U << 0) +#define IORING_FEAT_NODROP (1U << 1) /* * io_uring_register(2) opcodes and arguments @@ -150,5 +166,11 @@ struct io_uring_params { #define IORING_UNREGISTER_FILES 3 #define IORING_REGISTER_EVENTFD 4 #define IORING_UNREGISTER_EVENTFD 5 +#define IORING_REGISTER_FILES_UPDATE 6 + +struct io_uring_files_update { + __u32 offset; + __s32 *fds; +}; #endif diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index e168dc59e9a0..d99b5a772698 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -63,6 +63,7 @@ struct nvme_passthru_cmd64 { __u32 cdw14; __u32 cdw15; __u32 timeout_ms; + __u32 rsvd2; __u64 result; }; diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 59e89a1bc3bb..9dc9d0079e98 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -31,13 +31,16 @@ #define PTP_ENABLE_FEATURE (1<<0) #define PTP_RISING_EDGE (1<<1) #define PTP_FALLING_EDGE (1<<2) +#define PTP_STRICT_FLAGS (1<<3) +#define PTP_EXTTS_EDGES (PTP_RISING_EDGE | PTP_FALLING_EDGE) /* * flag fields valid for the new PTP_EXTTS_REQUEST2 ioctl. */ #define PTP_EXTTS_VALID_FLAGS (PTP_ENABLE_FEATURE | \ PTP_RISING_EDGE | \ - PTP_FALLING_EDGE) + PTP_FALLING_EDGE | \ + PTP_STRICT_FLAGS) /* * flag fields valid for the original PTP_EXTTS_REQUEST ioctl. diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index c6d035fa1b6c..6f5af1a84213 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -113,6 +113,25 @@ struct opal_shadow_mbr { __u64 size; }; +/* Opal table operations */ +enum opal_table_ops { + OPAL_READ_TABLE, + OPAL_WRITE_TABLE, +}; + +#define OPAL_UID_LENGTH 8 +struct opal_read_write_table { + struct opal_key key; + const __u64 data; + const __u8 table_uid[OPAL_UID_LENGTH]; + __u64 offset; + __u64 size; +#define OPAL_TABLE_READ (1 << OPAL_READ_TABLE) +#define OPAL_TABLE_WRITE (1 << OPAL_WRITE_TABLE) + __u64 flags; + __u64 priv; +}; + #define IOC_OPAL_SAVE _IOW('p', 220, struct opal_lock_unlock) #define IOC_OPAL_LOCK_UNLOCK _IOW('p', 221, struct opal_lock_unlock) #define IOC_OPAL_TAKE_OWNERSHIP _IOW('p', 222, struct opal_key) @@ -128,5 +147,6 @@ struct opal_shadow_mbr { #define IOC_OPAL_PSID_REVERT_TPR _IOW('p', 232, struct opal_key) #define IOC_OPAL_MBR_DONE _IOW('p', 233, struct opal_mbr_done) #define IOC_OPAL_WRITE_SHADOW_MBR _IOW('p', 234, struct opal_shadow_mbr) +#define IOC_OPAL_GENERIC_TABLE_RW _IOW('p', 235, struct opal_read_write_table) #endif /* _UAPI_SED_OPAL_H */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 7b35e98d3c58..ad80a5c885d5 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -167,8 +167,8 @@ struct statx { #define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */ #define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ - #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..4d8d145c41d2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1548,6 +1548,7 @@ config AIO config IO_URING bool "Enable IO uring support" if EXPERT select ANON_INODES + select IO_WQ default y help This option enables support for the io_uring interface, enabling diff --git a/init/initramfs.c b/init/initramfs.c index c47dad0884f7..8ec1be4d7d51 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -10,6 +10,7 @@ #include <linux/syscalls.h> #include <linux/utime.h> #include <linux/file.h> +#include <linux/memblock.h> static ssize_t __init xwrite(int fd, const char *p, size_t count) { @@ -529,6 +530,13 @@ extern unsigned long __initramfs_size; void __weak free_initrd_mem(unsigned long start, unsigned long end) { +#ifdef CONFIG_ARCH_KEEP_MEMBLOCK + unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); + unsigned long aligned_end = ALIGN(end, PAGE_SIZE); + + memblock_free(__pa(aligned_start), aligned_end - aligned_start); +#endif + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, "initrd"); } diff --git a/kernel/Makefile b/kernel/Makefile index daad787fb795..f0902a7bd1b3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -115,6 +115,8 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o + obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o KASAN_SANITIZE_stackleak.o := n KCOV_INSTRUMENT_stackleak.o := n diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 1f31c2f1e6fc..4508d5e0cf69 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -351,12 +351,12 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent) struct dentry *d = kern_path_locked(watch->path, parent); if (IS_ERR(d)) return PTR_ERR(d); - inode_unlock(d_backing_inode(parent->dentry)); if (d_is_positive(d)) { /* update watch filter fields */ watch->dev = d->d_sb->s_dev; watch->ino = d_backing_inode(d)->i_ino; } + inode_unlock(d_backing_inode(parent->dentry)); dput(d); return 0; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ddd8addcdb5c..a3eaf08e7dd3 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1311,12 +1311,12 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type, return false; switch (off) { - case offsetof(struct bpf_sysctl, write): + case bpf_ctx_range(struct bpf_sysctl, write): if (type != BPF_READ) return false; bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); - case offsetof(struct bpf_sysctl, file_pos): + case bpf_ctx_range(struct bpf_sysctl, file_pos): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index ba635209ae9a..5b9da0954a27 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -678,8 +678,10 @@ bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv) down_write(&bpf_devs_lock); if (!offdevs_inited) { err = rhashtable_init(&offdevs, &offdevs_params); - if (err) + if (err) { + up_write(&bpf_devs_lock); return ERR_PTR(err); + } offdevs_inited = true; } up_write(&bpf_devs_lock); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0937719b87e2..ace1cfaa24b6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -126,7 +126,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -void *bpf_map_area_alloc(size_t size, int numa_node) +void *bpf_map_area_alloc(u64 size, int numa_node) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, @@ -141,6 +141,9 @@ void *bpf_map_area_alloc(size_t size, int numa_node) const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; + if (size >= SIZE_MAX) + return NULL; + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, numa_node); @@ -197,7 +200,7 @@ static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) atomic_long_sub(pages, &user->locked_vm); } -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size) +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) { u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; struct user_struct *user; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 080561bb8a4b..ef4242e5d4bc 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2119,11 +2119,12 @@ int cgroup_do_get_tree(struct fs_context *fc) nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); - fc->root = nsdentry; if (IS_ERR(nsdentry)) { - ret = PTR_ERR(nsdentry); deactivate_locked_super(sb); + ret = PTR_ERR(nsdentry); + nsdentry = NULL; } + fc->root = nsdentry; } if (!ctx->kfc.new_sb_created) diff --git a/kernel/cpu.c b/kernel/cpu.c index fc28e17940e0..e2cad3ee2ead 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2373,7 +2373,18 @@ void __init boot_cpu_hotplug_init(void) this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } -enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; +/* + * These are used for a global "mitigations=" cmdline option for toggling + * optional CPU mitigations. + */ +enum cpu_mitigations { + CPU_MITIGATIONS_OFF, + CPU_MITIGATIONS_AUTO, + CPU_MITIGATIONS_AUTO_NOSMT, +}; + +static enum cpu_mitigations cpu_mitigations __ro_after_init = + CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { @@ -2390,3 +2401,17 @@ static int __init mitigations_parse_cmdline(char *arg) return 0; } early_param("mitigations", mitigations_parse_cmdline); + +/* mitigations=off */ +bool cpu_mitigations_off(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_OFF; +} +EXPORT_SYMBOL_GPL(cpu_mitigations_off); + +/* mitigations=auto,nosmt */ +bool cpu_mitigations_auto_nosmt(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; +} +EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 8402b29c280f..0b67c04e531b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -16,12 +16,11 @@ #include <linux/swiotlb.h> /* - * Most architectures use ZONE_DMA for the first 16 Megabytes, but - * some use it for entirely different regions: + * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it + * it for entirely different regions. In that case the arch code needs to + * override the variable below for dma-direct to work properly. */ -#ifndef ARCH_ZONE_DMA_BITS -#define ARCH_ZONE_DMA_BITS 24 -#endif +unsigned int zone_dma_bits __ro_after_init = 24; static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) { @@ -69,7 +68,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding * zones. */ - if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + if (*phys_mask <= DMA_BIT_MASK(zone_dma_bits)) return GFP_DMA; if (*phys_mask <= DMA_BIT_MASK(32)) return GFP_DMA32; @@ -395,7 +394,7 @@ int dma_direct_supported(struct device *dev, u64 mask) u64 min_mask; if (IS_ENABLED(CONFIG_ZONE_DMA)) - min_mask = DMA_BIT_MASK(ARCH_ZONE_DMA_BITS); + min_mask = DMA_BIT_MASK(zone_dma_bits); else min_mask = DMA_BIT_MASK(32); diff --git a/kernel/events/core.c b/kernel/events/core.c index aec8dba2bea4..00a014670ed0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1031,7 +1031,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, { } -void +static inline void perf_cgroup_switch(struct task_struct *task, struct task_struct *next) { } @@ -10535,6 +10535,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, goto err_ns; } + /* + * Disallow uncore-cgroup events, they don't make sense as the cgroup will + * be different on other CPUs in the uncore mask. + */ + if (pmu->task_ctx_nr == perf_invalid_context && cgroup_fd != -1) { + err = -EINVAL; + goto err_pmu; + } + if (event->attr.aux_output && !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) { err = -EOPNOTSUPP; @@ -11323,8 +11332,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, int err; /* - * Get the target context (task or percpu): + * Grouping is not supported for kernel events, neither is 'AUX', + * make sure the caller's intentions are adjusted. */ + if (attr->aux_output) + return ERR_PTR(-EINVAL); event = perf_event_alloc(attr, cpu, task, NULL, NULL, overflow_handler, context, -1); @@ -11336,6 +11348,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, /* Mark owner so we could distinguish it from user events. */ event->owner = TASK_TOMBSTONE; + /* + * Get the target context (task or percpu): + */ ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); @@ -11787,7 +11802,7 @@ inherit_event(struct perf_event *parent_event, GFP_KERNEL); if (!child_ctx->task_ctx_data) { free_event(child_event); - return NULL; + return ERR_PTR(-ENOMEM); } } @@ -11890,7 +11905,7 @@ static int inherit_group(struct perf_event *parent_event, if (IS_ERR(child_ctr)) return PTR_ERR(child_ctr); - if (sub->aux_event == parent_event && + if (sub->aux_event == parent_event && child_ctr && !perf_get_aux_event(child_ctr, leader)) return -EINVAL; } diff --git a/kernel/fork.c b/kernel/fork.c index 55af6931c6ec..13b38794efb5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1708,11 +1708,11 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) /* * Poll support for process exit notification. */ -static unsigned int pidfd_poll(struct file *file, struct poll_table_struct *pts) +static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct task_struct *task; struct pid *pid = file->private_data; - int poll_flags = 0; + __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); @@ -1724,7 +1724,7 @@ static unsigned int pidfd_poll(struct file *file, struct poll_table_struct *pts) * group, then poll(2) should block, similar to the wait(2) family. */ if (!task || (task->exit_state && thread_group_empty(task))) - poll_flags = POLLIN | POLLRDNORM; + poll_flags = EPOLLIN | EPOLLRDNORM; rcu_read_unlock(); return poll_flags; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 132672b74e4b..dd822fd8a7d5 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops); * @type: Type of irqchip_fwnode. See linux/irqdomain.h * @name: Optional user provided domain name * @id: Optional user provided id if name != NULL - * @data: Optional user-provided data + * @pa: Optional user-provided physical address * * Allocate a struct irqchip_fwid, and return a poiner to the embedded * fwnode_handle (or NULL on failure). diff --git a/kernel/module.c b/kernel/module.c index ff2d7359a418..acf7962936c4 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3222,7 +3222,7 @@ static int find_module_sections(struct module *mod, struct load_info *info) #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* sechdrs[0].sh_size is always zero */ - mod->ftrace_callsites = section_objs(info, "__mcount_loc", + mod->ftrace_callsites = section_objs(info, FTRACE_CALLSITE_SECTION, sizeof(*mod->ftrace_callsites), &mod->num_ftrace_callsites); #endif diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 04e83fdfbe80..a45cba7df0ae 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -814,6 +814,8 @@ EXPORT_SYMBOL_GPL(freq_qos_update_request); */ int freq_qos_remove_request(struct freq_qos_request *req) { + int ret; + if (!req) return -EINVAL; @@ -821,7 +823,11 @@ int freq_qos_remove_request(struct freq_qos_request *req) "%s() called for unknown object\n", __func__)) return -EINVAL; - return freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); + ret = freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); + req->qos = NULL; + req->type = 0; + + return ret; } EXPORT_SYMBOL_GPL(freq_qos_remove_request); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index dd05a378631a..80b60ca7767f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -16,6 +16,7 @@ #include <asm/tlb.h> #include "../workqueue_internal.h" +#include "../../fs/io-wq.h" #include "../smpboot.h" #include "pelt.h" @@ -1065,7 +1066,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) * affecting a valid clamp bucket, the next time it's enqueued, * it will already see the updated clamp bucket value. */ - if (!p->uclamp[clamp_id].active) { + if (p->uclamp[clamp_id].active) { uclamp_rq_dec_id(rq, p, clamp_id); uclamp_rq_inc_id(rq, p, clamp_id); } @@ -1073,6 +1074,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) task_rq_unlock(rq, p, &rf); } +#ifdef CONFIG_UCLAMP_TASK_GROUP static inline void uclamp_update_active_tasks(struct cgroup_subsys_state *css, unsigned int clamps) @@ -1091,7 +1093,6 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css, css_task_iter_end(&it); } -#ifdef CONFIG_UCLAMP_TASK_GROUP static void cpu_util_update_eff(struct cgroup_subsys_state *css); static void uclamp_update_root_tg(void) { @@ -3929,13 +3930,22 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } restart: +#ifdef CONFIG_SMP /* - * Ensure that we put DL/RT tasks before the pick loop, such that they - * can PULL higher prio tasks when we lower the RQ 'priority'. + * We must do the balancing pass before put_next_task(), such + * that when we release the rq->lock the task is in the same + * state as before we took rq->lock. + * + * We can terminate the balance pass as soon as we know there is + * a runnable task of @class priority or higher. */ - prev->sched_class->put_prev_task(rq, prev, rf); - if (!rq->nr_running) - newidle_balance(rq, rf); + for_class_range(class, prev->sched_class, &idle_sched_class) { + if (class->balance(rq, prev, rf)) + break; + } +#endif + + put_prev_task(rq, prev); for_each_class(class) { p = class->pick_next_task(rq, NULL, NULL); @@ -4103,9 +4113,12 @@ static inline void sched_submit_work(struct task_struct *tsk) * we disable preemption to avoid it calling schedule() again * in the possible wakeup of a kworker. */ - if (tsk->flags & PF_WQ_WORKER) { + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { preempt_disable(); - wq_worker_sleeping(tsk); + if (tsk->flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + else + io_wq_worker_sleeping(tsk); preempt_enable_no_resched(); } @@ -4122,8 +4135,12 @@ static inline void sched_submit_work(struct task_struct *tsk) static void sched_update_worker(struct task_struct *tsk) { - if (tsk->flags & PF_WQ_WORKER) - wq_worker_running(tsk); + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); + else + io_wq_worker_running(tsk); + } } asmlinkage __visible void __sched schedule(void) @@ -6010,10 +6027,11 @@ void init_idle(struct task_struct *idle, int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; + __sched_fork(0, idle); + raw_spin_lock_irqsave(&idle->pi_lock, flags); raw_spin_lock(&rq->lock); - __sched_fork(0, idle); idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); idle->flags |= PF_IDLE; @@ -6201,7 +6219,7 @@ static struct task_struct *__pick_migrate_task(struct rq *rq) for_each_class(class) { next = class->pick_next_task(rq, NULL, NULL); if (next) { - next->sched_class->put_prev_task(rq, next, NULL); + next->sched_class->put_prev_task(rq, next); return next; } } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 2dc48720f189..a8a08030a8f7 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1691,6 +1691,22 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) resched_curr(rq); } +static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +{ + if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_dl_task(rq); + rq_repin_lock(rq, rf); + } + + return sched_stop_runnable(rq) || sched_dl_runnable(rq); +} #endif /* CONFIG_SMP */ /* @@ -1758,45 +1774,28 @@ static struct task_struct * pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct sched_dl_entity *dl_se; + struct dl_rq *dl_rq = &rq->dl; struct task_struct *p; - struct dl_rq *dl_rq; WARN_ON_ONCE(prev || rf); - dl_rq = &rq->dl; - - if (unlikely(!dl_rq->dl_nr_running)) + if (!sched_dl_runnable(rq)) return NULL; dl_se = pick_next_dl_entity(rq, dl_rq); BUG_ON(!dl_se); - p = dl_task_of(dl_se); - set_next_task_dl(rq, p); - return p; } -static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); - - if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we've - * not yet started the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_dl_task(rq); - rq_repin_lock(rq, rf); - } } /* @@ -2442,6 +2441,7 @@ const struct sched_class dl_sched_class = { .set_next_task = set_next_task_dl, #ifdef CONFIG_SMP + .balance = balance_dl, .select_task_rq = select_task_rq_dl, .migrate_task_rq = migrate_task_rq_dl, .set_cpus_allowed = set_cpus_allowed_dl, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 682a754ea3e1..69a81a5709ff 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6570,6 +6570,15 @@ static void task_dead_fair(struct task_struct *p) { remove_entity_load_avg(&p->se); } + +static int +balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + if (rq->nr_running) + return 1; + + return newidle_balance(rq, rf) != 0; +} #endif /* CONFIG_SMP */ static unsigned long wakeup_gran(struct sched_entity *se) @@ -6746,7 +6755,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf int new_tasks; again: - if (!cfs_rq->nr_running) + if (!sched_fair_runnable(rq)) goto idle; #ifdef CONFIG_FAIR_GROUP_SCHED @@ -6884,7 +6893,7 @@ idle: /* * Account for a descheduled task: */ -static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) { struct sched_entity *se = &prev->se; struct cfs_rq *cfs_rq; @@ -7539,6 +7548,19 @@ static void update_blocked_averages(int cpu) update_rq_clock(rq); /* + * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure + * that RT, DL and IRQ signals have been updated before updating CFS. + */ + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); + update_irq_load_avg(rq, 0); + + /* Don't need periodic decay once load/util_avg are null */ + if (others_have_blocked(rq)) + done = false; + + /* * Iterates the task_group tree in a bottom up fashion, see * list_add_leaf_cfs_rq() for details. */ @@ -7565,14 +7587,6 @@ static void update_blocked_averages(int cpu) done = false; } - curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); - update_irq_load_avg(rq, 0); - /* Don't need periodic decay once load/util_avg are null */ - if (others_have_blocked(rq)) - done = false; - update_blocked_load_status(rq, !done); rq_unlock_irqrestore(rq, &rf); } @@ -7633,12 +7647,18 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); + /* + * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure + * that RT, DL and IRQ signals have been updated before updating CFS. + */ curr_class = rq->curr->sched_class; update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); + + update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); + update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq)); rq_unlock_irqrestore(rq, &rf); } @@ -10414,11 +10434,11 @@ const struct sched_class fair_sched_class = { .check_preempt_curr = check_preempt_wakeup, .pick_next_task = pick_next_task_fair, - .put_prev_task = put_prev_task_fair, .set_next_task = set_next_task_fair, #ifdef CONFIG_SMP + .balance = balance_fair, .select_task_rq = select_task_rq_fair, .migrate_task_rq = migrate_task_rq_fair, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8dad5aa600ea..f65ef1e2f204 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -365,6 +365,12 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } + +static int +balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + return WARN_ON_ONCE(1); +} #endif /* @@ -375,7 +381,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl resched_curr(rq); } -static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { } @@ -460,6 +466,7 @@ const struct sched_class idle_sched_class = { .set_next_task = set_next_task_idle, #ifdef CONFIG_SMP + .balance = balance_idle, .select_task_rq = select_task_rq_idle, .set_cpus_allowed = set_cpus_allowed_common, #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index ebaa4e619684..9b8adc01be3d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1469,6 +1469,22 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) resched_curr(rq); } +static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +{ + if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_rt_task(rq); + rq_repin_lock(rq, rf); + } + + return sched_stop_runnable(rq) || sched_dl_runnable(rq) || sched_rt_runnable(rq); +} #endif /* CONFIG_SMP */ /* @@ -1552,21 +1568,18 @@ static struct task_struct * pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *p; - struct rt_rq *rt_rq = &rq->rt; WARN_ON_ONCE(prev || rf); - if (!rt_rq->rt_queued) + if (!sched_rt_runnable(rq)) return NULL; p = _pick_next_task_rt(rq); - set_next_task_rt(rq, p); - return p; } -static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); @@ -1578,18 +1591,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_fla */ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); - - if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we've - * not yet started the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_rt_task(rq); - rq_repin_lock(rq, rf); - } } #ifdef CONFIG_SMP @@ -2366,8 +2367,8 @@ const struct sched_class rt_sched_class = { .set_next_task = set_next_task_rt, #ifdef CONFIG_SMP + .balance = balance_rt, .select_task_rq = select_task_rq_rt, - .set_cpus_allowed = set_cpus_allowed_common, .rq_online = rq_online_rt, .rq_offline = rq_offline_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0db2c1b3361e..c8870c5bd7df 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1727,10 +1727,11 @@ struct sched_class { struct task_struct * (*pick_next_task)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); - void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf); + void (*put_prev_task)(struct rq *rq, struct task_struct *p); void (*set_next_task)(struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP + int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); void (*migrate_task_rq)(struct task_struct *p, int new_cpu); @@ -1773,7 +1774,7 @@ struct sched_class { static inline void put_prev_task(struct rq *rq, struct task_struct *prev) { WARN_ON_ONCE(rq->curr != prev); - prev->sched_class->put_prev_task(rq, prev, NULL); + prev->sched_class->put_prev_task(rq, prev); } static inline void set_next_task(struct rq *rq, struct task_struct *next) @@ -1787,8 +1788,12 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next) #else #define sched_class_highest (&dl_sched_class) #endif + +#define for_class_range(class, _from, _to) \ + for (class = (_from); class != (_to); class = class->next) + #define for_each_class(class) \ - for (class = sched_class_highest; class; class = class->next) + for_class_range(class, sched_class_highest, NULL) extern const struct sched_class stop_sched_class; extern const struct sched_class dl_sched_class; @@ -1796,6 +1801,25 @@ extern const struct sched_class rt_sched_class; extern const struct sched_class fair_sched_class; extern const struct sched_class idle_sched_class; +static inline bool sched_stop_runnable(struct rq *rq) +{ + return rq->stop && task_on_rq_queued(rq->stop); +} + +static inline bool sched_dl_runnable(struct rq *rq) +{ + return rq->dl.dl_nr_running > 0; +} + +static inline bool sched_rt_runnable(struct rq *rq) +{ + return rq->rt.rt_queued > 0; +} + +static inline bool sched_fair_runnable(struct rq *rq) +{ + return rq->cfs.nr_running > 0; +} #ifdef CONFIG_SMP diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 7e1cee4e65b2..c0640739e05e 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -15,6 +15,12 @@ select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } + +static int +balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + return sched_stop_runnable(rq); +} #endif /* CONFIG_SMP */ static void @@ -31,16 +37,13 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop) static struct task_struct * pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { - struct task_struct *stop = rq->stop; - WARN_ON_ONCE(prev || rf); - if (!stop || !task_on_rq_queued(stop)) + if (!sched_stop_runnable(rq)) return NULL; - set_next_task_stop(rq, stop); - - return stop; + set_next_task_stop(rq, rq->stop); + return rq->stop; } static void @@ -60,7 +63,7 @@ static void yield_task_stop(struct rq *rq) BUG(); /* the stop task should never yield, its pointless. */ } -static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) { struct task_struct *curr = rq->curr; u64 delta_exec; @@ -129,6 +132,7 @@ const struct sched_class stop_sched_class = { .set_next_task = set_next_task_stop, #ifdef CONFIG_SMP + .balance = balance_stop, .select_task_rq = select_task_rq_stop, .set_cpus_allowed = set_cpus_allowed_common, #endif diff --git a/kernel/signal.c b/kernel/signal.c index c4da1ef56fdf..bcd46f547db3 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2205,8 +2205,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t */ preempt_disable(); read_unlock(&tasklist_lock); - preempt_enable_no_resched(); cgroup_enter_frozen(); + preempt_enable_no_resched(); freezable_schedule(); cgroup_leave_frozen(true); } else { diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 6d1f68b7e528..c9ea7eb2cb1a 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -141,7 +141,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store, struct stacktrace_cookie c = { .store = store, .size = size, - .skip = skipnr + 1, + /* skip this function if they are tracing us */ + .skip = skipnr + !!(current == tsk), }; if (!try_get_task_stack(tsk)) @@ -298,7 +299,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *task, struct stack_trace trace = { .entries = store, .max_entries = size, - .skip = skipnr + 1, + /* skip this function if they are tracing us */ + .skip = skipnr + !!(current == task), }; save_stack_trace_tsk(task, &trace); diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c new file mode 100644 index 000000000000..2a63241a8453 --- /dev/null +++ b/kernel/sysctl-test.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test of proc sysctl. + */ + +#include <kunit/test.h> +#include <linux/sysctl.h> + +#define KUNIT_PROC_READ 0 +#define KUNIT_PROC_WRITE 1 + +static int i_zero; +static int i_one_hundred = 100; + +/* + * Test that proc_dointvec will not try to use a NULL .data field even when the + * length is non-zero. + */ +static void sysctl_test_api_dointvec_null_tbl_data(struct kunit *test) +{ + struct ctl_table null_data_table = { + .procname = "foo", + /* + * Here we are testing that proc_dointvec behaves correctly when + * we give it a NULL .data field. Normally this would point to a + * piece of memory where the value would be stored. + */ + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + /* + * proc_dointvec expects a buffer in user space, so we allocate one. We + * also need to cast it to __user so sparse doesn't get mad. + */ + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + size_t len; + loff_t pos; + + /* + * We don't care what the starting length is since proc_dointvec should + * not try to read because .data is NULL. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table, + KUNIT_PROC_READ, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + /* + * See above. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table, + KUNIT_PROC_WRITE, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Similar to the previous test, we create a struct ctrl_table that has a .data + * field that proc_dointvec cannot do anything with; however, this time it is + * because we tell proc_dointvec that the size is 0. + */ +static void sysctl_test_api_dointvec_table_maxlen_unset(struct kunit *test) +{ + int data = 0; + struct ctl_table data_maxlen_unset_table = { + .procname = "foo", + .data = &data, + /* + * So .data is no longer NULL, but we tell proc_dointvec its + * length is 0, so it still shouldn't try to use it. + */ + .maxlen = 0, + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + size_t len; + loff_t pos; + + /* + * As before, we don't care what buffer length is because proc_dointvec + * cannot do anything because its internal .data buffer has zero length. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table, + KUNIT_PROC_READ, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + /* + * See previous comment. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table, + KUNIT_PROC_WRITE, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Here we provide a valid struct ctl_table, but we try to read and write from + * it using a buffer of zero length, so it should still fail in a similar way as + * before. + */ +static void sysctl_test_api_dointvec_table_len_is_zero(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + /* + * However, now our read/write buffer has zero length. + */ + size_t len = 0; + loff_t pos; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Test that proc_dointvec refuses to read when the file position is non-zero. + */ +static void sysctl_test_api_dointvec_table_read_but_position_set( + struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + /* + * We don't care about our buffer length because we start off with a + * non-zero file position. + */ + size_t len = 1234; + /* + * proc_dointvec should refuse to read into the buffer since the file + * pos is non-zero. + */ + loff_t pos = 1; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Test that we can read a two digit number in a sufficiently size buffer. + * Nothing fancy. + */ +static void sysctl_test_dointvec_read_happy_single_positive(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t len = 4; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + /* Store 13 in the data field. */ + *((int *)table.data) = 13; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, (size_t)3, len); + buffer[len] = '\0'; + /* And we read 13 back out. */ + KUNIT_EXPECT_STREQ(test, "13\n", buffer); +} + +/* + * Same as previous test, just now with negative numbers. + */ +static void sysctl_test_dointvec_read_happy_single_negative(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t len = 5; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + *((int *)table.data) = -16; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, (size_t)4, len); + buffer[len] = '\0'; + KUNIT_EXPECT_STREQ(test, "-16\n", (char *)buffer); +} + +/* + * Test that a simple positive write works. + */ +static void sysctl_test_dointvec_write_happy_single_positive(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + char input[] = "9"; + size_t len = sizeof(input) - 1; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + + memcpy(buffer, input, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos); + KUNIT_EXPECT_EQ(test, 9, *((int *)table.data)); +} + +/* + * Same as previous test, but now with negative numbers. + */ +static void sysctl_test_dointvec_write_happy_single_negative(struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + char input[] = "-9"; + size_t len = sizeof(input) - 1; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + + memcpy(buffer, input, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos); + KUNIT_EXPECT_EQ(test, -9, *((int *)table.data)); +} + +/* + * Test that writing a value smaller than the minimum possible value is not + * allowed. + */ +static void sysctl_test_api_dointvec_write_single_less_int_min( + struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t max_len = 32, len = max_len; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, max_len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + unsigned long abs_of_less_than_min = (unsigned long)INT_MAX + - (INT_MAX + INT_MIN) + 1; + + /* + * We use this rigmarole to create a string that contains a value one + * less than the minimum accepted value. + */ + KUNIT_ASSERT_LT(test, + (size_t)snprintf(buffer, max_len, "-%lu", + abs_of_less_than_min), + max_len); + + KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, max_len, len); + KUNIT_EXPECT_EQ(test, 0, *((int *)table.data)); +} + +/* + * Test that writing the maximum possible value works. + */ +static void sysctl_test_api_dointvec_write_single_greater_int_max( + struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t max_len = 32, len = max_len; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, max_len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + unsigned long greater_than_max = (unsigned long)INT_MAX + 1; + + KUNIT_ASSERT_GT(test, greater_than_max, (unsigned long)INT_MAX); + KUNIT_ASSERT_LT(test, (size_t)snprintf(buffer, max_len, "%lu", + greater_than_max), + max_len); + KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, max_len, len); + KUNIT_EXPECT_EQ(test, 0, *((int *)table.data)); +} + +static struct kunit_case sysctl_test_cases[] = { + KUNIT_CASE(sysctl_test_api_dointvec_null_tbl_data), + KUNIT_CASE(sysctl_test_api_dointvec_table_maxlen_unset), + KUNIT_CASE(sysctl_test_api_dointvec_table_len_is_zero), + KUNIT_CASE(sysctl_test_api_dointvec_table_read_but_position_set), + KUNIT_CASE(sysctl_test_dointvec_read_happy_single_positive), + KUNIT_CASE(sysctl_test_dointvec_read_happy_single_negative), + KUNIT_CASE(sysctl_test_dointvec_write_happy_single_positive), + KUNIT_CASE(sysctl_test_dointvec_write_happy_single_negative), + KUNIT_CASE(sysctl_test_api_dointvec_write_single_less_int_min), + KUNIT_CASE(sysctl_test_api_dointvec_write_single_greater_int_max), + {} +}; + +static struct kunit_suite sysctl_test_suite = { + .name = "sysctl_test", + .test_cases = sysctl_test_cases, +}; + +kunit_test_suite(sysctl_test_suite); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 65eb796610dc..069ca78fb0bf 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -771,7 +771,7 @@ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, /* fill PPS status fields */ pps_fill_timex(txc); - txc->time.tv_sec = (time_t)ts->tv_sec; + txc->time.tv_sec = ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(time_status & STA_NANO)) txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC; diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 4bc37ac3bb05..5ee0f7709410 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -110,8 +110,7 @@ void update_vsyscall(struct timekeeper *tk) nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); - if (__arch_use_vsyscall(vdata)) - update_vdso_data(vdata, tk); + update_vdso_data(vdata, tk); __arch_update_vsyscall(vdata, tk); @@ -124,10 +123,8 @@ void update_vsyscall_tz(void) { struct vdso_data *vdata = __arch_get_k_vdso_data(); - if (__arch_use_vsyscall(vdata)) { - vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest; - vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime; - } + vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest; + vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime; __arch_sync_vdso_data(vdata); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f296d89be757..5259d4dea675 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2494,14 +2494,14 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter) } static int -ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) +ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec) { int ret; if (unlikely(ftrace_disabled)) return 0; - ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ret = ftrace_init_nop(mod, rec); if (ret) { ftrace_bug_type = FTRACE_BUG_INIT; ftrace_bug(ret, rec); @@ -2943,7 +2943,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) * to the NOP instructions. */ if (!__is_defined(CC_USING_NOP_MCOUNT) && - !ftrace_code_disable(mod, p)) + !ftrace_nop_initialize(mod, p)) break; update_cnt++; diff --git a/lib/Kconfig b/lib/Kconfig index 183f92a297ca..3321d04dfa5a 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -447,7 +447,6 @@ config ASSOCIATIVE_ARRAY config HAS_IOMEM bool depends on !NO_IOMEM - select GENERIC_IO default y config HAS_IOPORT_MAP diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 93d97f9b0157..6c1be6181e38 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1664,6 +1664,8 @@ config PROVIDE_OHCI1394_DMA_INIT See Documentation/debugging-via-ohci1394.txt for more information. +source "lib/kunit/Kconfig" + menuconfig RUNTIME_TESTING_MENU bool "Runtime Testing" def_bool y @@ -1948,6 +1950,35 @@ config TEST_SYSCTL If unsure, say N. +config SYSCTL_KUNIT_TEST + bool "KUnit test for sysctl" + depends on KUNIT + help + This builds the proc sysctl unit test, which runs on boot. + Tests the API contract and implementation correctness of sysctl. + 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 LIST_KUNIT_TEST + bool "KUnit Test for Kernel Linked-list structures" + depends on KUNIT + help + This builds the linked list KUnit test suite. + It tests that the API and basic functionality of the list_head type + and associated macros. + + KUnit tests run during boot and output the results to the debug log + in TAP format (http://testanything.org/). Only useful for kernel devs + running the KUnit test harness, and not intended for inclusion into a + production build. + + 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/Makefile b/lib/Makefile index c5892807e06f..890e581d00c4 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -92,6 +92,8 @@ obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/ +obj-$(CONFIG_KUNIT) += kunit/ + ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG CFLAGS_kobject_uevent.o += -DDEBUG @@ -290,3 +292,6 @@ obj-$(CONFIG_GENERIC_LIB_MULDI3) += muldi3.o obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o obj-$(CONFIG_OBJAGG) += objagg.o + +# KUnit tests +obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o diff --git a/lib/idr.c b/lib/idr.c index 66a374892482..c2cf2c52bbde 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -215,7 +215,7 @@ int idr_for_each(const struct idr *idr, EXPORT_SYMBOL(idr_for_each); /** - * idr_get_next() - Find next populated entry. + * idr_get_next_ul() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * @@ -224,7 +224,7 @@ EXPORT_SYMBOL(idr_for_each); * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ -void *idr_get_next(struct idr *idr, int *nextid) +void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; @@ -245,18 +245,14 @@ void *idr_get_next(struct idr *idr, int *nextid) } if (!slot) return NULL; - id = iter.index + base; - - if (WARN_ON_ONCE(id > INT_MAX)) - return NULL; - *nextid = id; + *nextid = iter.index + base; return entry; } -EXPORT_SYMBOL(idr_get_next); +EXPORT_SYMBOL(idr_get_next_ul); /** - * idr_get_next_ul() - Find next populated entry. + * idr_get_next() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * @@ -265,22 +261,17 @@ EXPORT_SYMBOL(idr_get_next); * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ -void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) +void *idr_get_next(struct idr *idr, int *nextid) { - struct radix_tree_iter iter; - void __rcu **slot; - unsigned long base = idr->idr_base; unsigned long id = *nextid; + void *entry = idr_get_next_ul(idr, &id); - id = (id < base) ? 0 : id - base; - slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); - if (!slot) + if (WARN_ON_ONCE(id > INT_MAX)) return NULL; - - *nextid = iter.index + base; - return rcu_dereference_raw(*slot); + *nextid = id; + return entry; } -EXPORT_SYMBOL(idr_get_next_ul); +EXPORT_SYMBOL(idr_get_next); /** * idr_replace() - replace pointer for given ID. diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig new file mode 100644 index 000000000000..af37016bfdd4 --- /dev/null +++ b/lib/kunit/Kconfig @@ -0,0 +1,36 @@ +# +# KUnit base configuration +# + +menuconfig KUNIT + bool "KUnit - Enable support for unit tests" + help + Enables support for kernel unit tests (KUnit), a lightweight unit + testing and mocking framework for the Linux kernel. These tests are + able to be run locally on a developer's workstation without a VM or + special hardware when using UML. Can also be used on most other + architectures. For more information, please see + Documentation/dev-tools/kunit/. + +if KUNIT + +config KUNIT_TEST + bool "KUnit test for KUnit" + help + Enables the unit tests for the KUnit test framework. These tests test + the KUnit test framework itself; the tests are both written using + KUnit and test KUnit. This option should only be enabled for testing + purposes by developers interested in testing that KUnit works as + expected. + +config KUNIT_EXAMPLE_TEST + bool "Example test for KUnit" + help + Enables an example unit test that illustrates some of the basic + features of KUnit. This test only exists to help new users understand + what KUnit is and how it is used. Please refer to the example test + itself, lib/kunit/example-test.c, for more information. This option + is intended for curious hackers who would like to understand how to + use KUnit for kernel development. + +endif # KUNIT diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile new file mode 100644 index 000000000000..769d9402b5d3 --- /dev/null +++ b/lib/kunit/Makefile @@ -0,0 +1,9 @@ +obj-$(CONFIG_KUNIT) += test.o \ + string-stream.o \ + assert.o \ + try-catch.o + +obj-$(CONFIG_KUNIT_TEST) += test-test.o \ + string-stream-test.o + +obj-$(CONFIG_KUNIT_EXAMPLE_TEST) += example-test.o diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c new file mode 100644 index 000000000000..86013d4cf891 --- /dev/null +++ b/lib/kunit/assert.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Assertion and expectation serialization API. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ +#include <kunit/assert.h> + +void kunit_base_assert_format(const struct kunit_assert *assert, + struct string_stream *stream) +{ + const char *expect_or_assert = NULL; + + switch (assert->type) { + case KUNIT_EXPECTATION: + expect_or_assert = "EXPECTATION"; + break; + case KUNIT_ASSERTION: + expect_or_assert = "ASSERTION"; + break; + } + + string_stream_add(stream, "%s FAILED at %s:%d\n", + expect_or_assert, assert->file, assert->line); +} + +void kunit_assert_print_msg(const struct kunit_assert *assert, + struct string_stream *stream) +{ + if (assert->message.fmt) + string_stream_add(stream, "\n%pV", &assert->message); +} + +void kunit_fail_assert_format(const struct kunit_assert *assert, + struct string_stream *stream) +{ + kunit_base_assert_format(assert, stream); + string_stream_add(stream, "%pV", &assert->message); +} + +void kunit_unary_assert_format(const struct kunit_assert *assert, + struct string_stream *stream) +{ + struct kunit_unary_assert *unary_assert = container_of( + assert, struct kunit_unary_assert, assert); + + kunit_base_assert_format(assert, stream); + if (unary_assert->expected_true) + string_stream_add(stream, + "\tExpected %s to be true, but is false\n", + unary_assert->condition); + else + string_stream_add(stream, + "\tExpected %s to be false, but is true\n", + unary_assert->condition); + kunit_assert_print_msg(assert, stream); +} + +void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, + struct string_stream *stream) +{ + struct kunit_ptr_not_err_assert *ptr_assert = container_of( + assert, struct kunit_ptr_not_err_assert, assert); + + kunit_base_assert_format(assert, stream); + if (!ptr_assert->value) { + string_stream_add(stream, + "\tExpected %s is not null, but is\n", + ptr_assert->text); + } else if (IS_ERR(ptr_assert->value)) { + string_stream_add(stream, + "\tExpected %s is not error, but is: %ld\n", + ptr_assert->text, + PTR_ERR(ptr_assert->value)); + } + kunit_assert_print_msg(assert, stream); +} + +void kunit_binary_assert_format(const struct kunit_assert *assert, + struct string_stream *stream) +{ + struct kunit_binary_assert *binary_assert = container_of( + assert, struct kunit_binary_assert, assert); + + kunit_base_assert_format(assert, stream); + string_stream_add(stream, + "\tExpected %s %s %s, but\n", + binary_assert->left_text, + binary_assert->operation, + binary_assert->right_text); + string_stream_add(stream, "\t\t%s == %lld\n", + binary_assert->left_text, + binary_assert->left_value); + string_stream_add(stream, "\t\t%s == %lld", + binary_assert->right_text, + binary_assert->right_value); + kunit_assert_print_msg(assert, stream); +} + +void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, + struct string_stream *stream) +{ + struct kunit_binary_ptr_assert *binary_assert = container_of( + assert, struct kunit_binary_ptr_assert, assert); + + kunit_base_assert_format(assert, stream); + string_stream_add(stream, + "\tExpected %s %s %s, but\n", + binary_assert->left_text, + binary_assert->operation, + binary_assert->right_text); + string_stream_add(stream, "\t\t%s == %pK\n", + binary_assert->left_text, + binary_assert->left_value); + string_stream_add(stream, "\t\t%s == %pK", + binary_assert->right_text, + binary_assert->right_value); + kunit_assert_print_msg(assert, stream); +} + +void kunit_binary_str_assert_format(const struct kunit_assert *assert, + struct string_stream *stream) +{ + struct kunit_binary_str_assert *binary_assert = container_of( + assert, struct kunit_binary_str_assert, assert); + + kunit_base_assert_format(assert, stream); + string_stream_add(stream, + "\tExpected %s %s %s, but\n", + binary_assert->left_text, + binary_assert->operation, + binary_assert->right_text); + string_stream_add(stream, "\t\t%s == %s\n", + binary_assert->left_text, + binary_assert->left_value); + string_stream_add(stream, "\t\t%s == %s", + binary_assert->right_text, + binary_assert->right_value); + kunit_assert_print_msg(assert, stream); +} diff --git a/lib/kunit/example-test.c b/lib/kunit/example-test.c new file mode 100644 index 000000000000..f64a829aa441 --- /dev/null +++ b/lib/kunit/example-test.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Example KUnit test to show how to use KUnit. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#include <kunit/test.h> + +/* + * This is the most fundamental element of KUnit, the test case. A test case + * makes a set EXPECTATIONs and ASSERTIONs about the behavior of some code; if + * any expectations or assertions are not met, the test fails; otherwise, the + * test passes. + * + * In KUnit, a test case is just a function with the signature + * `void (*)(struct kunit *)`. `struct kunit` is a context object that stores + * information about the current test. + */ +static void example_simple_test(struct kunit *test) +{ + /* + * This is an EXPECTATION; it is how KUnit tests things. When you want + * to test a piece of code, you set some expectations about what the + * code should do. KUnit then runs the test and verifies that the code's + * behavior matched what was expected. + */ + KUNIT_EXPECT_EQ(test, 1 + 1, 2); +} + +/* + * This is run once before each test case, see the comment on + * example_test_suite for more information. + */ +static int example_test_init(struct kunit *test) +{ + kunit_info(test, "initializing\n"); + + return 0; +} + +/* + * Here we make a list of all the test cases we want to add to the test suite + * below. + */ +static struct kunit_case example_test_cases[] = { + /* + * This is a helper to create a test case object from a test case + * function; its exact function is not important to understand how to + * use KUnit, just know that this is how you associate test cases with a + * test suite. + */ + KUNIT_CASE(example_simple_test), + {} +}; + +/* + * This defines a suite or grouping of tests. + * + * Test cases are defined as belonging to the suite by adding them to + * `kunit_cases`. + * + * Often it is desirable to run some function which will set up things which + * will be used by every test; this is accomplished with an `init` function + * which runs before each test case is invoked. Similarly, an `exit` function + * may be specified which runs after every test case and can be used to for + * cleanup. For clarity, running tests in a test suite would behave as follows: + * + * suite.init(test); + * suite.test_case[0](test); + * suite.exit(test); + * suite.init(test); + * suite.test_case[1](test); + * suite.exit(test); + * ...; + */ +static struct kunit_suite example_test_suite = { + .name = "example", + .init = example_test_init, + .test_cases = example_test_cases, +}; + +/* + * This registers the above test suite telling KUnit that this is a suite of + * tests that need to be run. + */ +kunit_test_suite(example_test_suite); diff --git a/lib/kunit/string-stream-test.c b/lib/kunit/string-stream-test.c new file mode 100644 index 000000000000..76cc05eb00ed --- /dev/null +++ b/lib/kunit/string-stream-test.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test for struct string_stream. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#include <kunit/string-stream.h> +#include <kunit/test.h> +#include <linux/slab.h> + +static void string_stream_test_empty_on_creation(struct kunit *test) +{ + struct string_stream *stream = alloc_string_stream(test, GFP_KERNEL); + + KUNIT_EXPECT_TRUE(test, string_stream_is_empty(stream)); +} + +static void string_stream_test_not_empty_after_add(struct kunit *test) +{ + struct string_stream *stream = alloc_string_stream(test, GFP_KERNEL); + + string_stream_add(stream, "Foo"); + + KUNIT_EXPECT_FALSE(test, string_stream_is_empty(stream)); +} + +static void string_stream_test_get_string(struct kunit *test) +{ + struct string_stream *stream = alloc_string_stream(test, GFP_KERNEL); + char *output; + + string_stream_add(stream, "Foo"); + string_stream_add(stream, " %s", "bar"); + + output = string_stream_get_string(stream); + KUNIT_ASSERT_STREQ(test, output, "Foo bar"); +} + +static struct kunit_case string_stream_test_cases[] = { + KUNIT_CASE(string_stream_test_empty_on_creation), + KUNIT_CASE(string_stream_test_not_empty_after_add), + KUNIT_CASE(string_stream_test_get_string), + {} +}; + +static struct kunit_suite string_stream_test_suite = { + .name = "string-stream-test", + .test_cases = string_stream_test_cases +}; +kunit_test_suite(string_stream_test_suite); diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c new file mode 100644 index 000000000000..e6d17aacca30 --- /dev/null +++ b/lib/kunit/string-stream.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * C++ stream style string builder used in KUnit for building messages. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#include <kunit/string-stream.h> +#include <kunit/test.h> +#include <linux/list.h> +#include <linux/slab.h> + +struct string_stream_fragment_alloc_context { + struct kunit *test; + int len; + gfp_t gfp; +}; + +static int string_stream_fragment_init(struct kunit_resource *res, + void *context) +{ + struct string_stream_fragment_alloc_context *ctx = context; + struct string_stream_fragment *frag; + + frag = kunit_kzalloc(ctx->test, sizeof(*frag), ctx->gfp); + if (!frag) + return -ENOMEM; + + frag->test = ctx->test; + frag->fragment = kunit_kmalloc(ctx->test, ctx->len, ctx->gfp); + if (!frag->fragment) + return -ENOMEM; + + res->allocation = frag; + + return 0; +} + +static void string_stream_fragment_free(struct kunit_resource *res) +{ + struct string_stream_fragment *frag = res->allocation; + + list_del(&frag->node); + kunit_kfree(frag->test, frag->fragment); + kunit_kfree(frag->test, frag); +} + +static struct string_stream_fragment *alloc_string_stream_fragment( + struct kunit *test, int len, gfp_t gfp) +{ + struct string_stream_fragment_alloc_context context = { + .test = test, + .len = len, + .gfp = gfp + }; + + return kunit_alloc_resource(test, + string_stream_fragment_init, + string_stream_fragment_free, + gfp, + &context); +} + +static int string_stream_fragment_destroy(struct string_stream_fragment *frag) +{ + return kunit_resource_destroy(frag->test, + kunit_resource_instance_match, + string_stream_fragment_free, + frag); +} + +int string_stream_vadd(struct string_stream *stream, + const char *fmt, + va_list args) +{ + struct string_stream_fragment *frag_container; + int len; + va_list args_for_counting; + + /* Make a copy because `vsnprintf` could change it */ + va_copy(args_for_counting, args); + + /* Need space for null byte. */ + len = vsnprintf(NULL, 0, fmt, args_for_counting) + 1; + + va_end(args_for_counting); + + frag_container = alloc_string_stream_fragment(stream->test, + len, + stream->gfp); + if (!frag_container) + return -ENOMEM; + + len = vsnprintf(frag_container->fragment, len, fmt, args); + spin_lock(&stream->lock); + stream->length += len; + list_add_tail(&frag_container->node, &stream->fragments); + spin_unlock(&stream->lock); + + return 0; +} + +int string_stream_add(struct string_stream *stream, const char *fmt, ...) +{ + va_list args; + int result; + + va_start(args, fmt); + result = string_stream_vadd(stream, fmt, args); + va_end(args); + + return result; +} + +static void string_stream_clear(struct string_stream *stream) +{ + struct string_stream_fragment *frag_container, *frag_container_safe; + + spin_lock(&stream->lock); + list_for_each_entry_safe(frag_container, + frag_container_safe, + &stream->fragments, + node) { + string_stream_fragment_destroy(frag_container); + } + stream->length = 0; + spin_unlock(&stream->lock); +} + +char *string_stream_get_string(struct string_stream *stream) +{ + struct string_stream_fragment *frag_container; + size_t buf_len = stream->length + 1; /* +1 for null byte. */ + char *buf; + + buf = kunit_kzalloc(stream->test, buf_len, stream->gfp); + if (!buf) + return NULL; + + spin_lock(&stream->lock); + list_for_each_entry(frag_container, &stream->fragments, node) + strlcat(buf, frag_container->fragment, buf_len); + spin_unlock(&stream->lock); + + return buf; +} + +int string_stream_append(struct string_stream *stream, + struct string_stream *other) +{ + const char *other_content; + + other_content = string_stream_get_string(other); + + if (!other_content) + return -ENOMEM; + + return string_stream_add(stream, other_content); +} + +bool string_stream_is_empty(struct string_stream *stream) +{ + return list_empty(&stream->fragments); +} + +struct string_stream_alloc_context { + struct kunit *test; + gfp_t gfp; +}; + +static int string_stream_init(struct kunit_resource *res, void *context) +{ + struct string_stream *stream; + struct string_stream_alloc_context *ctx = context; + + stream = kunit_kzalloc(ctx->test, sizeof(*stream), ctx->gfp); + if (!stream) + return -ENOMEM; + + res->allocation = stream; + stream->gfp = ctx->gfp; + stream->test = ctx->test; + INIT_LIST_HEAD(&stream->fragments); + spin_lock_init(&stream->lock); + + return 0; +} + +static void string_stream_free(struct kunit_resource *res) +{ + struct string_stream *stream = res->allocation; + + string_stream_clear(stream); +} + +struct string_stream *alloc_string_stream(struct kunit *test, gfp_t gfp) +{ + struct string_stream_alloc_context context = { + .test = test, + .gfp = gfp + }; + + return kunit_alloc_resource(test, + string_stream_init, + string_stream_free, + gfp, + &context); +} + +int string_stream_destroy(struct string_stream *stream) +{ + return kunit_resource_destroy(stream->test, + kunit_resource_instance_match, + string_stream_free, + stream); +} diff --git a/lib/kunit/test-test.c b/lib/kunit/test-test.c new file mode 100644 index 000000000000..5ebe059d16e2 --- /dev/null +++ b/lib/kunit/test-test.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test for core test infrastructure. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ +#include <kunit/test.h> + +struct kunit_try_catch_test_context { + struct kunit_try_catch *try_catch; + bool function_called; +}; + +static void kunit_test_successful_try(void *data) +{ + struct kunit *test = data; + struct kunit_try_catch_test_context *ctx = test->priv; + + ctx->function_called = true; +} + +static void kunit_test_no_catch(void *data) +{ + struct kunit *test = data; + + KUNIT_FAIL(test, "Catch should not be called\n"); +} + +static void kunit_test_try_catch_successful_try_no_catch(struct kunit *test) +{ + struct kunit_try_catch_test_context *ctx = test->priv; + struct kunit_try_catch *try_catch = ctx->try_catch; + + kunit_try_catch_init(try_catch, + test, + kunit_test_successful_try, + kunit_test_no_catch); + kunit_try_catch_run(try_catch, test); + + KUNIT_EXPECT_TRUE(test, ctx->function_called); +} + +static void kunit_test_unsuccessful_try(void *data) +{ + struct kunit *test = data; + struct kunit_try_catch_test_context *ctx = test->priv; + struct kunit_try_catch *try_catch = ctx->try_catch; + + kunit_try_catch_throw(try_catch); + KUNIT_FAIL(test, "This line should never be reached\n"); +} + +static void kunit_test_catch(void *data) +{ + struct kunit *test = data; + struct kunit_try_catch_test_context *ctx = test->priv; + + ctx->function_called = true; +} + +static void kunit_test_try_catch_unsuccessful_try_does_catch(struct kunit *test) +{ + struct kunit_try_catch_test_context *ctx = test->priv; + struct kunit_try_catch *try_catch = ctx->try_catch; + + kunit_try_catch_init(try_catch, + test, + kunit_test_unsuccessful_try, + kunit_test_catch); + kunit_try_catch_run(try_catch, test); + + KUNIT_EXPECT_TRUE(test, ctx->function_called); +} + +static int kunit_try_catch_test_init(struct kunit *test) +{ + struct kunit_try_catch_test_context *ctx; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + test->priv = ctx; + + ctx->try_catch = kunit_kmalloc(test, + sizeof(*ctx->try_catch), + GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx->try_catch); + + return 0; +} + +static struct kunit_case kunit_try_catch_test_cases[] = { + KUNIT_CASE(kunit_test_try_catch_successful_try_no_catch), + KUNIT_CASE(kunit_test_try_catch_unsuccessful_try_does_catch), + {} +}; + +static struct kunit_suite kunit_try_catch_test_suite = { + .name = "kunit-try-catch-test", + .init = kunit_try_catch_test_init, + .test_cases = kunit_try_catch_test_cases, +}; +kunit_test_suite(kunit_try_catch_test_suite); + +/* + * Context for testing test managed resources + * is_resource_initialized is used to test arbitrary resources + */ +struct kunit_test_resource_context { + struct kunit test; + bool is_resource_initialized; + int allocate_order[2]; + int free_order[2]; +}; + +static int fake_resource_init(struct kunit_resource *res, void *context) +{ + struct kunit_test_resource_context *ctx = context; + + res->allocation = &ctx->is_resource_initialized; + ctx->is_resource_initialized = true; + return 0; +} + +static void fake_resource_free(struct kunit_resource *res) +{ + bool *is_resource_initialized = res->allocation; + + *is_resource_initialized = false; +} + +static void kunit_resource_test_init_resources(struct kunit *test) +{ + struct kunit_test_resource_context *ctx = test->priv; + + kunit_init_test(&ctx->test, "testing_test_init_test"); + + KUNIT_EXPECT_TRUE(test, list_empty(&ctx->test.resources)); +} + +static void kunit_resource_test_alloc_resource(struct kunit *test) +{ + struct kunit_test_resource_context *ctx = test->priv; + struct kunit_resource *res; + kunit_resource_free_t free = fake_resource_free; + + res = kunit_alloc_and_get_resource(&ctx->test, + fake_resource_init, + fake_resource_free, + GFP_KERNEL, + ctx); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, res); + KUNIT_EXPECT_PTR_EQ(test, + &ctx->is_resource_initialized, + (bool *) res->allocation); + KUNIT_EXPECT_TRUE(test, list_is_last(&res->node, &ctx->test.resources)); + KUNIT_EXPECT_PTR_EQ(test, free, res->free); +} + +static void kunit_resource_test_destroy_resource(struct kunit *test) +{ + struct kunit_test_resource_context *ctx = test->priv; + struct kunit_resource *res = kunit_alloc_and_get_resource( + &ctx->test, + fake_resource_init, + fake_resource_free, + GFP_KERNEL, + ctx); + + KUNIT_ASSERT_FALSE(test, + kunit_resource_destroy(&ctx->test, + kunit_resource_instance_match, + res->free, + res->allocation)); + + KUNIT_EXPECT_FALSE(test, ctx->is_resource_initialized); + KUNIT_EXPECT_TRUE(test, list_empty(&ctx->test.resources)); +} + +static void kunit_resource_test_cleanup_resources(struct kunit *test) +{ + int i; + struct kunit_test_resource_context *ctx = test->priv; + struct kunit_resource *resources[5]; + + for (i = 0; i < ARRAY_SIZE(resources); i++) { + resources[i] = kunit_alloc_and_get_resource(&ctx->test, + fake_resource_init, + fake_resource_free, + GFP_KERNEL, + ctx); + } + + kunit_cleanup(&ctx->test); + + KUNIT_EXPECT_TRUE(test, list_empty(&ctx->test.resources)); +} + +static void kunit_resource_test_mark_order(int order_array[], + size_t order_size, + int key) +{ + int i; + + for (i = 0; i < order_size && order_array[i]; i++) + ; + + order_array[i] = key; +} + +#define KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, order_field, key) \ + kunit_resource_test_mark_order(ctx->order_field, \ + ARRAY_SIZE(ctx->order_field), \ + key) + +static int fake_resource_2_init(struct kunit_resource *res, void *context) +{ + struct kunit_test_resource_context *ctx = context; + + KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, allocate_order, 2); + + res->allocation = ctx; + + return 0; +} + +static void fake_resource_2_free(struct kunit_resource *res) +{ + struct kunit_test_resource_context *ctx = res->allocation; + + KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, free_order, 2); +} + +static int fake_resource_1_init(struct kunit_resource *res, void *context) +{ + struct kunit_test_resource_context *ctx = context; + + kunit_alloc_and_get_resource(&ctx->test, + fake_resource_2_init, + fake_resource_2_free, + GFP_KERNEL, + ctx); + + KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, allocate_order, 1); + + res->allocation = ctx; + + return 0; +} + +static void fake_resource_1_free(struct kunit_resource *res) +{ + struct kunit_test_resource_context *ctx = res->allocation; + + KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, free_order, 1); +} + +/* + * TODO(brendanhiggins@google.com): replace the arrays that keep track of the + * order of allocation and freeing with strict mocks using the IN_SEQUENCE macro + * to assert allocation and freeing order when the feature becomes available. + */ +static void kunit_resource_test_proper_free_ordering(struct kunit *test) +{ + struct kunit_test_resource_context *ctx = test->priv; + + /* fake_resource_1 allocates a fake_resource_2 in its init. */ + kunit_alloc_and_get_resource(&ctx->test, + fake_resource_1_init, + fake_resource_1_free, + GFP_KERNEL, + ctx); + + /* + * Since fake_resource_2_init calls KUNIT_RESOURCE_TEST_MARK_ORDER + * before returning to fake_resource_1_init, it should be the first to + * put its key in the allocate_order array. + */ + KUNIT_EXPECT_EQ(test, ctx->allocate_order[0], 2); + KUNIT_EXPECT_EQ(test, ctx->allocate_order[1], 1); + + kunit_cleanup(&ctx->test); + + /* + * Because fake_resource_2 finishes allocation before fake_resource_1, + * fake_resource_1 should be freed first since it could depend on + * fake_resource_2. + */ + KUNIT_EXPECT_EQ(test, ctx->free_order[0], 1); + KUNIT_EXPECT_EQ(test, ctx->free_order[1], 2); +} + +static int kunit_resource_test_init(struct kunit *test) +{ + struct kunit_test_resource_context *ctx = + kzalloc(sizeof(*ctx), GFP_KERNEL); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + + test->priv = ctx; + + kunit_init_test(&ctx->test, "test_test_context"); + + return 0; +} + +static void kunit_resource_test_exit(struct kunit *test) +{ + struct kunit_test_resource_context *ctx = test->priv; + + kunit_cleanup(&ctx->test); + kfree(ctx); +} + +static struct kunit_case kunit_resource_test_cases[] = { + KUNIT_CASE(kunit_resource_test_init_resources), + KUNIT_CASE(kunit_resource_test_alloc_resource), + KUNIT_CASE(kunit_resource_test_destroy_resource), + KUNIT_CASE(kunit_resource_test_cleanup_resources), + KUNIT_CASE(kunit_resource_test_proper_free_ordering), + {} +}; + +static struct kunit_suite kunit_resource_test_suite = { + .name = "kunit-resource-test", + .init = kunit_resource_test_init, + .exit = kunit_resource_test_exit, + .test_cases = kunit_resource_test_cases, +}; +kunit_test_suite(kunit_resource_test_suite); diff --git a/lib/kunit/test.c b/lib/kunit/test.c new file mode 100644 index 000000000000..c83c0fa59cbd --- /dev/null +++ b/lib/kunit/test.c @@ -0,0 +1,478 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Base unit test (KUnit) API. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#include <kunit/test.h> +#include <kunit/try-catch.h> +#include <linux/kernel.h> +#include <linux/sched/debug.h> + +static void kunit_set_failure(struct kunit *test) +{ + WRITE_ONCE(test->success, false); +} + +static void kunit_print_tap_version(void) +{ + static bool kunit_has_printed_tap_version; + + if (!kunit_has_printed_tap_version) { + pr_info("TAP version 14\n"); + kunit_has_printed_tap_version = true; + } +} + +static size_t kunit_test_cases_len(struct kunit_case *test_cases) +{ + struct kunit_case *test_case; + size_t len = 0; + + for (test_case = test_cases; test_case->run_case; test_case++) + len++; + + return len; +} + +static void kunit_print_subtest_start(struct kunit_suite *suite) +{ + kunit_print_tap_version(); + pr_info("\t# Subtest: %s\n", suite->name); + pr_info("\t1..%zd\n", kunit_test_cases_len(suite->test_cases)); +} + +static void kunit_print_ok_not_ok(bool should_indent, + bool is_ok, + size_t test_number, + const char *description) +{ + const char *indent, *ok_not_ok; + + if (should_indent) + indent = "\t"; + else + indent = ""; + + if (is_ok) + ok_not_ok = "ok"; + else + ok_not_ok = "not ok"; + + pr_info("%s%s %zd - %s\n", indent, ok_not_ok, test_number, description); +} + +static bool kunit_suite_has_succeeded(struct kunit_suite *suite) +{ + const struct kunit_case *test_case; + + for (test_case = suite->test_cases; test_case->run_case; test_case++) + if (!test_case->success) + return false; + + return true; +} + +static void kunit_print_subtest_end(struct kunit_suite *suite) +{ + static size_t kunit_suite_counter = 1; + + kunit_print_ok_not_ok(false, + kunit_suite_has_succeeded(suite), + kunit_suite_counter++, + suite->name); +} + +static void kunit_print_test_case_ok_not_ok(struct kunit_case *test_case, + size_t test_number) +{ + kunit_print_ok_not_ok(true, + test_case->success, + test_number, + test_case->name); +} + +static void kunit_print_string_stream(struct kunit *test, + struct string_stream *stream) +{ + struct string_stream_fragment *fragment; + char *buf; + + buf = string_stream_get_string(stream); + if (!buf) { + kunit_err(test, + "Could not allocate buffer, dumping stream:\n"); + list_for_each_entry(fragment, &stream->fragments, node) { + kunit_err(test, "%s", fragment->fragment); + } + kunit_err(test, "\n"); + } else { + kunit_err(test, "%s", buf); + kunit_kfree(test, buf); + } +} + +static void kunit_fail(struct kunit *test, struct kunit_assert *assert) +{ + struct string_stream *stream; + + kunit_set_failure(test); + + stream = alloc_string_stream(test, GFP_KERNEL); + if (!stream) { + WARN(true, + "Could not allocate stream to print failed assertion in %s:%d\n", + assert->file, + assert->line); + return; + } + + assert->format(assert, stream); + + kunit_print_string_stream(test, stream); + + WARN_ON(string_stream_destroy(stream)); +} + +static void __noreturn kunit_abort(struct kunit *test) +{ + kunit_try_catch_throw(&test->try_catch); /* Does not return. */ + + /* + * Throw could not abort from test. + * + * XXX: we should never reach this line! As kunit_try_catch_throw is + * marked __noreturn. + */ + WARN_ONCE(true, "Throw could not abort from test!\n"); +} + +void kunit_do_assertion(struct kunit *test, + struct kunit_assert *assert, + bool pass, + const char *fmt, ...) +{ + va_list args; + + if (pass) + return; + + va_start(args, fmt); + + assert->message.fmt = fmt; + assert->message.va = &args; + + kunit_fail(test, assert); + + va_end(args); + + if (assert->type == KUNIT_ASSERTION) + kunit_abort(test); +} + +void kunit_init_test(struct kunit *test, const char *name) +{ + spin_lock_init(&test->lock); + INIT_LIST_HEAD(&test->resources); + test->name = name; + test->success = true; +} + +/* + * Initializes and runs test case. Does not clean up or do post validations. + */ +static void kunit_run_case_internal(struct kunit *test, + struct kunit_suite *suite, + struct kunit_case *test_case) +{ + if (suite->init) { + int ret; + + ret = suite->init(test); + if (ret) { + kunit_err(test, "failed to initialize: %d\n", ret); + kunit_set_failure(test); + return; + } + } + + test_case->run_case(test); +} + +static void kunit_case_internal_cleanup(struct kunit *test) +{ + kunit_cleanup(test); +} + +/* + * Performs post validations and cleanup after a test case was run. + * XXX: Should ONLY BE CALLED AFTER kunit_run_case_internal! + */ +static void kunit_run_case_cleanup(struct kunit *test, + struct kunit_suite *suite) +{ + if (suite->exit) + suite->exit(test); + + kunit_case_internal_cleanup(test); +} + +struct kunit_try_catch_context { + struct kunit *test; + struct kunit_suite *suite; + struct kunit_case *test_case; +}; + +static void kunit_try_run_case(void *data) +{ + struct kunit_try_catch_context *ctx = data; + struct kunit *test = ctx->test; + struct kunit_suite *suite = ctx->suite; + struct kunit_case *test_case = ctx->test_case; + + /* + * kunit_run_case_internal may encounter a fatal error; if it does, + * abort will be called, this thread will exit, and finally the parent + * thread will resume control and handle any necessary clean up. + */ + kunit_run_case_internal(test, suite, test_case); + /* This line may never be reached. */ + kunit_run_case_cleanup(test, suite); +} + +static void kunit_catch_run_case(void *data) +{ + struct kunit_try_catch_context *ctx = data; + struct kunit *test = ctx->test; + struct kunit_suite *suite = ctx->suite; + int try_exit_code = kunit_try_catch_get_result(&test->try_catch); + + if (try_exit_code) { + kunit_set_failure(test); + /* + * Test case could not finish, we have no idea what state it is + * in, so don't do clean up. + */ + if (try_exit_code == -ETIMEDOUT) { + kunit_err(test, "test case timed out\n"); + /* + * Unknown internal error occurred preventing test case from + * running, so there is nothing to clean up. + */ + } else { + kunit_err(test, "internal error occurred preventing test case from running: %d\n", + try_exit_code); + } + return; + } + + /* + * Test case was run, but aborted. It is the test case's business as to + * whether it failed or not, we just need to clean up. + */ + kunit_run_case_cleanup(test, suite); +} + +/* + * Performs all logic to run a test case. It also catches most errors that + * occur in a test case and reports them as failures. + */ +static void kunit_run_case_catch_errors(struct kunit_suite *suite, + struct kunit_case *test_case) +{ + struct kunit_try_catch_context context; + struct kunit_try_catch *try_catch; + struct kunit test; + + kunit_init_test(&test, test_case->name); + try_catch = &test.try_catch; + + kunit_try_catch_init(try_catch, + &test, + kunit_try_run_case, + kunit_catch_run_case); + context.test = &test; + context.suite = suite; + context.test_case = test_case; + kunit_try_catch_run(try_catch, &context); + + test_case->success = test.success; +} + +int kunit_run_tests(struct kunit_suite *suite) +{ + struct kunit_case *test_case; + size_t test_case_count = 1; + + kunit_print_subtest_start(suite); + + for (test_case = suite->test_cases; test_case->run_case; test_case++) { + kunit_run_case_catch_errors(suite, test_case); + kunit_print_test_case_ok_not_ok(test_case, test_case_count++); + } + + kunit_print_subtest_end(suite); + + return 0; +} + +struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + gfp_t internal_gfp, + void *context) +{ + struct kunit_resource *res; + int ret; + + res = kzalloc(sizeof(*res), internal_gfp); + if (!res) + return NULL; + + ret = init(res, context); + if (ret) + return NULL; + + res->free = free; + spin_lock(&test->lock); + list_add_tail(&res->node, &test->resources); + spin_unlock(&test->lock); + + return res; +} + +static void kunit_resource_free(struct kunit *test, struct kunit_resource *res) +{ + res->free(res); + kfree(res); +} + +static struct kunit_resource *kunit_resource_find(struct kunit *test, + kunit_resource_match_t match, + kunit_resource_free_t free, + void *match_data) +{ + struct kunit_resource *resource; + + lockdep_assert_held(&test->lock); + + list_for_each_entry_reverse(resource, &test->resources, node) { + if (resource->free != free) + continue; + if (match(test, resource->allocation, match_data)) + return resource; + } + + return NULL; +} + +static struct kunit_resource *kunit_resource_remove( + struct kunit *test, + kunit_resource_match_t match, + kunit_resource_free_t free, + void *match_data) +{ + struct kunit_resource *resource; + + spin_lock(&test->lock); + resource = kunit_resource_find(test, match, free, match_data); + if (resource) + list_del(&resource->node); + spin_unlock(&test->lock); + + return resource; +} + +int kunit_resource_destroy(struct kunit *test, + kunit_resource_match_t match, + kunit_resource_free_t free, + void *match_data) +{ + struct kunit_resource *resource; + + resource = kunit_resource_remove(test, match, free, match_data); + + if (!resource) + return -ENOENT; + + kunit_resource_free(test, resource); + return 0; +} + +struct kunit_kmalloc_params { + size_t size; + gfp_t gfp; +}; + +static int kunit_kmalloc_init(struct kunit_resource *res, void *context) +{ + struct kunit_kmalloc_params *params = context; + + res->allocation = kmalloc(params->size, params->gfp); + if (!res->allocation) + return -ENOMEM; + + return 0; +} + +static void kunit_kmalloc_free(struct kunit_resource *res) +{ + kfree(res->allocation); +} + +void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp) +{ + struct kunit_kmalloc_params params = { + .size = size, + .gfp = gfp + }; + + return kunit_alloc_resource(test, + kunit_kmalloc_init, + kunit_kmalloc_free, + gfp, + ¶ms); +} + +void kunit_kfree(struct kunit *test, const void *ptr) +{ + int rc; + + rc = kunit_resource_destroy(test, + kunit_resource_instance_match, + kunit_kmalloc_free, + (void *)ptr); + + WARN_ON(rc); +} + +void kunit_cleanup(struct kunit *test) +{ + struct kunit_resource *resource; + + /* + * test->resources is a stack - each allocation must be freed in the + * reverse order from which it was added since one resource may depend + * on another for its entire lifetime. + * Also, we cannot use the normal list_for_each constructs, even the + * safe ones because *arbitrary* nodes may be deleted when + * kunit_resource_free is called; the list_for_each_safe variants only + * protect against the current node being deleted, not the next. + */ + while (true) { + spin_lock(&test->lock); + if (list_empty(&test->resources)) { + spin_unlock(&test->lock); + break; + } + resource = list_last_entry(&test->resources, + struct kunit_resource, + node); + list_del(&resource->node); + spin_unlock(&test->lock); + + kunit_resource_free(test, resource); + } +} diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c new file mode 100644 index 000000000000..55686839eb61 --- /dev/null +++ b/lib/kunit/try-catch.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * An API to allow a function, that may fail, to be executed, and recover in a + * controlled manner. + * + * Copyright (C) 2019, Google LLC. + * Author: Brendan Higgins <brendanhiggins@google.com> + */ + +#include <kunit/test.h> +#include <kunit/try-catch.h> +#include <linux/completion.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/sched/sysctl.h> + +void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch) +{ + try_catch->try_result = -EFAULT; + complete_and_exit(try_catch->try_completion, -EFAULT); +} + +static int kunit_generic_run_threadfn_adapter(void *data) +{ + struct kunit_try_catch *try_catch = data; + + try_catch->try(try_catch->context); + + complete_and_exit(try_catch->try_completion, 0); +} + +static unsigned long kunit_test_timeout(void) +{ + unsigned long timeout_msecs; + + /* + * TODO(brendanhiggins@google.com): We should probably have some type of + * variable timeout here. The only question is what that timeout value + * should be. + * + * The intention has always been, at some point, to be able to label + * tests with some type of size bucket (unit/small, integration/medium, + * large/system/end-to-end, etc), where each size bucket would get a + * default timeout value kind of like what Bazel does: + * https://docs.bazel.build/versions/master/be/common-definitions.html#test.size + * There is still some debate to be had on exactly how we do this. (For + * one, we probably want to have some sort of test runner level + * timeout.) + * + * For more background on this topic, see: + * https://mike-bland.com/2011/11/01/small-medium-large.html + */ + if (sysctl_hung_task_timeout_secs) { + /* + * If sysctl_hung_task is active, just set the timeout to some + * value less than that. + * + * In regards to the above TODO, if we decide on variable + * timeouts, this logic will likely need to change. + */ + timeout_msecs = (sysctl_hung_task_timeout_secs - 1) * + MSEC_PER_SEC; + } else { + timeout_msecs = 300 * MSEC_PER_SEC; /* 5 min */ + } + + return timeout_msecs; +} + +void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) +{ + DECLARE_COMPLETION_ONSTACK(try_completion); + struct kunit *test = try_catch->test; + struct task_struct *task_struct; + int exit_code, time_remaining; + + try_catch->context = context; + try_catch->try_completion = &try_completion; + try_catch->try_result = 0; + task_struct = kthread_run(kunit_generic_run_threadfn_adapter, + try_catch, + "kunit_try_catch_thread"); + if (IS_ERR(task_struct)) { + try_catch->catch(try_catch->context); + return; + } + + time_remaining = wait_for_completion_timeout(&try_completion, + kunit_test_timeout()); + if (time_remaining == 0) { + kunit_err(test, "try timed out\n"); + try_catch->try_result = -ETIMEDOUT; + } + + exit_code = try_catch->try_result; + + if (!exit_code) + return; + + if (exit_code == -EFAULT) + try_catch->try_result = 0; + else if (exit_code == -EINTR) + kunit_err(test, "wake_up_process() was never called\n"); + else if (exit_code) + kunit_err(test, "Unknown error: %d\n", exit_code); + + try_catch->catch(try_catch->context); +} + +void kunit_try_catch_init(struct kunit_try_catch *try_catch, + struct kunit *test, + kunit_try_catch_func_t try, + kunit_try_catch_func_t catch) +{ + try_catch->test = test; + try_catch->try = try; + try_catch->catch = catch; +} diff --git a/lib/list-test.c b/lib/list-test.c new file mode 100644 index 000000000000..363c600491c3 --- /dev/null +++ b/lib/list-test.c @@ -0,0 +1,746 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test for the Kernel Linked-list structures. + * + * Copyright (C) 2019, Google LLC. + * Author: David Gow <davidgow@google.com> + */ +#include <kunit/test.h> + +#include <linux/list.h> + +struct list_test_struct { + int data; + struct list_head list; +}; + +static void list_test_list_init(struct kunit *test) +{ + /* Test the different ways of initialising a list. */ + struct list_head list1 = LIST_HEAD_INIT(list1); + struct list_head list2; + LIST_HEAD(list3); + struct list_head *list4; + struct list_head *list5; + + INIT_LIST_HEAD(&list2); + + list4 = kzalloc(sizeof(*list4), GFP_KERNEL | __GFP_NOFAIL); + INIT_LIST_HEAD(list4); + + list5 = kmalloc(sizeof(*list5), GFP_KERNEL | __GFP_NOFAIL); + memset(list5, 0xFF, sizeof(*list5)); + INIT_LIST_HEAD(list5); + + /* list_empty_careful() checks both next and prev. */ + KUNIT_EXPECT_TRUE(test, list_empty_careful(&list1)); + KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2)); + KUNIT_EXPECT_TRUE(test, list_empty_careful(&list3)); + KUNIT_EXPECT_TRUE(test, list_empty_careful(list4)); + KUNIT_EXPECT_TRUE(test, list_empty_careful(list5)); + + kfree(list4); + kfree(list5); +} + +static void list_test_list_add(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add(&a, &list); + list_add(&b, &list); + + /* should be [list] -> b -> a */ + KUNIT_EXPECT_PTR_EQ(test, list.next, &b); + KUNIT_EXPECT_PTR_EQ(test, b.prev, &list); + KUNIT_EXPECT_PTR_EQ(test, b.next, &a); +} + +static void list_test_list_add_tail(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + + /* should be [list] -> a -> b */ + KUNIT_EXPECT_PTR_EQ(test, list.next, &a); + KUNIT_EXPECT_PTR_EQ(test, a.prev, &list); + KUNIT_EXPECT_PTR_EQ(test, a.next, &b); +} + +static void list_test_list_del(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + + /* before: [list] -> a -> b */ + list_del(&a); + + /* now: [list] -> b */ + KUNIT_EXPECT_PTR_EQ(test, list.next, &b); + KUNIT_EXPECT_PTR_EQ(test, b.prev, &list); +} + +static void list_test_list_replace(struct kunit *test) +{ + struct list_head a_old, a_new, b; + LIST_HEAD(list); + + list_add_tail(&a_old, &list); + list_add_tail(&b, &list); + + /* before: [list] -> a_old -> b */ + list_replace(&a_old, &a_new); + + /* now: [list] -> a_new -> b */ + KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new); + KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new); +} + +static void list_test_list_replace_init(struct kunit *test) +{ + struct list_head a_old, a_new, b; + LIST_HEAD(list); + + list_add_tail(&a_old, &list); + list_add_tail(&b, &list); + + /* before: [list] -> a_old -> b */ + list_replace_init(&a_old, &a_new); + + /* now: [list] -> a_new -> b */ + KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new); + KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new); + + /* check a_old is empty (initialized) */ + KUNIT_EXPECT_TRUE(test, list_empty_careful(&a_old)); +} + +static void list_test_list_swap(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + + /* before: [list] -> a -> b */ + list_swap(&a, &b); + + /* after: [list] -> b -> a */ + KUNIT_EXPECT_PTR_EQ(test, &b, list.next); + KUNIT_EXPECT_PTR_EQ(test, &a, list.prev); + + KUNIT_EXPECT_PTR_EQ(test, &a, b.next); + KUNIT_EXPECT_PTR_EQ(test, &list, b.prev); + + KUNIT_EXPECT_PTR_EQ(test, &list, a.next); + KUNIT_EXPECT_PTR_EQ(test, &b, a.prev); +} + +static void list_test_list_del_init(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + + /* before: [list] -> a -> b */ + list_del_init(&a); + /* after: [list] -> b, a initialised */ + + KUNIT_EXPECT_PTR_EQ(test, list.next, &b); + KUNIT_EXPECT_PTR_EQ(test, b.prev, &list); + KUNIT_EXPECT_TRUE(test, list_empty_careful(&a)); +} + +static void list_test_list_move(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list1); + LIST_HEAD(list2); + + list_add_tail(&a, &list1); + list_add_tail(&b, &list2); + + /* before: [list1] -> a, [list2] -> b */ + list_move(&a, &list2); + /* after: [list1] empty, [list2] -> a -> b */ + + KUNIT_EXPECT_TRUE(test, list_empty(&list1)); + + KUNIT_EXPECT_PTR_EQ(test, &a, list2.next); + KUNIT_EXPECT_PTR_EQ(test, &b, a.next); +} + +static void list_test_list_move_tail(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list1); + LIST_HEAD(list2); + + list_add_tail(&a, &list1); + list_add_tail(&b, &list2); + + /* before: [list1] -> a, [list2] -> b */ + list_move_tail(&a, &list2); + /* after: [list1] empty, [list2] -> b -> a */ + + KUNIT_EXPECT_TRUE(test, list_empty(&list1)); + + KUNIT_EXPECT_PTR_EQ(test, &b, list2.next); + KUNIT_EXPECT_PTR_EQ(test, &a, b.next); +} + +static void list_test_list_bulk_move_tail(struct kunit *test) +{ + struct list_head a, b, c, d, x, y; + struct list_head *list1_values[] = { &x, &b, &c, &y }; + struct list_head *list2_values[] = { &a, &d }; + struct list_head *ptr; + LIST_HEAD(list1); + LIST_HEAD(list2); + int i = 0; + + list_add_tail(&x, &list1); + list_add_tail(&y, &list1); + + list_add_tail(&a, &list2); + list_add_tail(&b, &list2); + list_add_tail(&c, &list2); + list_add_tail(&d, &list2); + + /* before: [list1] -> x -> y, [list2] -> a -> b -> c -> d */ + list_bulk_move_tail(&y, &b, &c); + /* after: [list1] -> x -> b -> c -> y, [list2] -> a -> d */ + + list_for_each(ptr, &list1) { + KUNIT_EXPECT_PTR_EQ(test, ptr, list1_values[i]); + i++; + } + KUNIT_EXPECT_EQ(test, i, 4); + i = 0; + list_for_each(ptr, &list2) { + KUNIT_EXPECT_PTR_EQ(test, ptr, list2_values[i]); + i++; + } + KUNIT_EXPECT_EQ(test, i, 2); +} + +static void list_test_list_is_first(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + + KUNIT_EXPECT_TRUE(test, list_is_first(&a, &list)); + KUNIT_EXPECT_FALSE(test, list_is_first(&b, &list)); +} + +static void list_test_list_is_last(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + + KUNIT_EXPECT_FALSE(test, list_is_last(&a, &list)); + KUNIT_EXPECT_TRUE(test, list_is_last(&b, &list)); +} + +static void list_test_list_empty(struct kunit *test) +{ + struct list_head a; + LIST_HEAD(list1); + LIST_HEAD(list2); + + list_add_tail(&a, &list1); + + KUNIT_EXPECT_FALSE(test, list_empty(&list1)); + KUNIT_EXPECT_TRUE(test, list_empty(&list2)); +} + +static void list_test_list_empty_careful(struct kunit *test) +{ + /* This test doesn't check correctness under concurrent access */ + struct list_head a; + LIST_HEAD(list1); + LIST_HEAD(list2); + + list_add_tail(&a, &list1); + + KUNIT_EXPECT_FALSE(test, list_empty_careful(&list1)); + KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2)); +} + +static void list_test_list_rotate_left(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + + /* before: [list] -> a -> b */ + list_rotate_left(&list); + /* after: [list] -> b -> a */ + + KUNIT_EXPECT_PTR_EQ(test, list.next, &b); + KUNIT_EXPECT_PTR_EQ(test, b.prev, &list); + KUNIT_EXPECT_PTR_EQ(test, b.next, &a); +} + +static void list_test_list_rotate_to_front(struct kunit *test) +{ + struct list_head a, b, c, d; + struct list_head *list_values[] = { &c, &d, &a, &b }; + struct list_head *ptr; + LIST_HEAD(list); + int i = 0; + + list_add_tail(&a, &list); + list_add_tail(&b, &list); + list_add_tail(&c, &list); + list_add_tail(&d, &list); + + /* before: [list] -> a -> b -> c -> d */ + list_rotate_to_front(&c, &list); + /* after: [list] -> c -> d -> a -> b */ + + list_for_each(ptr, &list) { + KUNIT_EXPECT_PTR_EQ(test, ptr, list_values[i]); + i++; + } + KUNIT_EXPECT_EQ(test, i, 4); +} + +static void list_test_list_is_singular(struct kunit *test) +{ + struct list_head a, b; + LIST_HEAD(list); + + /* [list] empty */ + KUNIT_EXPECT_FALSE(test, list_is_singular(&list)); + + list_add_tail(&a, &list); + + /* [list] -> a */ + KUNIT_EXPECT_TRUE(test, list_is_singular(&list)); + + list_add_tail(&b, &list); + + /* [list] -> a -> b */ + KUNIT_EXPECT_FALSE(test, list_is_singular(&list)); +} + +static void list_test_list_cut_position(struct kunit *test) +{ + struct list_head entries[3], *cur; + LIST_HEAD(list1); + LIST_HEAD(list2); + int i = 0; + + list_add_tail(&entries[0], &list1); + list_add_tail(&entries[1], &list1); + list_add_tail(&entries[2], &list1); + + /* before: [list1] -> entries[0] -> entries[1] -> entries[2] */ + list_cut_position(&list2, &list1, &entries[1]); + /* after: [list2] -> entries[0] -> entries[1], [list1] -> entries[2] */ + + list_for_each(cur, &list2) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 2); + + list_for_each(cur, &list1) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } +} + +static void list_test_list_cut_before(struct kunit *test) +{ + struct list_head entries[3], *cur; + LIST_HEAD(list1); + LIST_HEAD(list2); + int i = 0; + + list_add_tail(&entries[0], &list1); + list_add_tail(&entries[1], &list1); + list_add_tail(&entries[2], &list1); + + /* before: [list1] -> entries[0] -> entries[1] -> entries[2] */ + list_cut_before(&list2, &list1, &entries[1]); + /* after: [list2] -> entries[0], [list1] -> entries[1] -> entries[2] */ + + list_for_each(cur, &list2) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 1); + + list_for_each(cur, &list1) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } +} + +static void list_test_list_splice(struct kunit *test) +{ + struct list_head entries[5], *cur; + LIST_HEAD(list1); + LIST_HEAD(list2); + int i = 0; + + list_add_tail(&entries[0], &list1); + list_add_tail(&entries[1], &list1); + list_add_tail(&entries[2], &list2); + list_add_tail(&entries[3], &list2); + list_add_tail(&entries[4], &list1); + + /* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */ + list_splice(&list2, &entries[1]); + /* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] uninit */ + + list_for_each(cur, &list1) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 5); +} + +static void list_test_list_splice_tail(struct kunit *test) +{ + struct list_head entries[5], *cur; + LIST_HEAD(list1); + LIST_HEAD(list2); + int i = 0; + + list_add_tail(&entries[0], &list1); + list_add_tail(&entries[1], &list1); + list_add_tail(&entries[2], &list2); + list_add_tail(&entries[3], &list2); + list_add_tail(&entries[4], &list1); + + /* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */ + list_splice_tail(&list2, &entries[4]); + /* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] uninit */ + + list_for_each(cur, &list1) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 5); +} + +static void list_test_list_splice_init(struct kunit *test) +{ + struct list_head entries[5], *cur; + LIST_HEAD(list1); + LIST_HEAD(list2); + int i = 0; + + list_add_tail(&entries[0], &list1); + list_add_tail(&entries[1], &list1); + list_add_tail(&entries[2], &list2); + list_add_tail(&entries[3], &list2); + list_add_tail(&entries[4], &list1); + + /* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */ + list_splice_init(&list2, &entries[1]); + /* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] empty */ + + list_for_each(cur, &list1) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 5); + + KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2)); +} + +static void list_test_list_splice_tail_init(struct kunit *test) +{ + struct list_head entries[5], *cur; + LIST_HEAD(list1); + LIST_HEAD(list2); + int i = 0; + + list_add_tail(&entries[0], &list1); + list_add_tail(&entries[1], &list1); + list_add_tail(&entries[2], &list2); + list_add_tail(&entries[3], &list2); + list_add_tail(&entries[4], &list1); + + /* before: [list1]->e[0]->e[1]->e[4], [list2]->e[2]->e[3] */ + list_splice_tail_init(&list2, &entries[4]); + /* after: [list1]->e[0]->e[1]->e[2]->e[3]->e[4], [list2] empty */ + + list_for_each(cur, &list1) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 5); + + KUNIT_EXPECT_TRUE(test, list_empty_careful(&list2)); +} + +static void list_test_list_entry(struct kunit *test) +{ + struct list_test_struct test_struct; + + KUNIT_EXPECT_PTR_EQ(test, &test_struct, list_entry(&(test_struct.list), + struct list_test_struct, list)); +} + +static void list_test_list_first_entry(struct kunit *test) +{ + struct list_test_struct test_struct1, test_struct2; + LIST_HEAD(list); + + list_add_tail(&test_struct1.list, &list); + list_add_tail(&test_struct2.list, &list); + + + KUNIT_EXPECT_PTR_EQ(test, &test_struct1, list_first_entry(&list, + struct list_test_struct, list)); +} + +static void list_test_list_last_entry(struct kunit *test) +{ + struct list_test_struct test_struct1, test_struct2; + LIST_HEAD(list); + + list_add_tail(&test_struct1.list, &list); + list_add_tail(&test_struct2.list, &list); + + + KUNIT_EXPECT_PTR_EQ(test, &test_struct2, list_last_entry(&list, + struct list_test_struct, list)); +} + +static void list_test_list_first_entry_or_null(struct kunit *test) +{ + struct list_test_struct test_struct1, test_struct2; + LIST_HEAD(list); + + KUNIT_EXPECT_FALSE(test, list_first_entry_or_null(&list, + struct list_test_struct, list)); + + list_add_tail(&test_struct1.list, &list); + list_add_tail(&test_struct2.list, &list); + + KUNIT_EXPECT_PTR_EQ(test, &test_struct1, + list_first_entry_or_null(&list, + struct list_test_struct, list)); +} + +static void list_test_list_next_entry(struct kunit *test) +{ + struct list_test_struct test_struct1, test_struct2; + LIST_HEAD(list); + + list_add_tail(&test_struct1.list, &list); + list_add_tail(&test_struct2.list, &list); + + + KUNIT_EXPECT_PTR_EQ(test, &test_struct2, list_next_entry(&test_struct1, + list)); +} + +static void list_test_list_prev_entry(struct kunit *test) +{ + struct list_test_struct test_struct1, test_struct2; + LIST_HEAD(list); + + list_add_tail(&test_struct1.list, &list); + list_add_tail(&test_struct2.list, &list); + + + KUNIT_EXPECT_PTR_EQ(test, &test_struct1, list_prev_entry(&test_struct2, + list)); +} + +static void list_test_list_for_each(struct kunit *test) +{ + struct list_head entries[3], *cur; + LIST_HEAD(list); + int i = 0; + + list_add_tail(&entries[0], &list); + list_add_tail(&entries[1], &list); + list_add_tail(&entries[2], &list); + + list_for_each(cur, &list) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 3); +} + +static void list_test_list_for_each_prev(struct kunit *test) +{ + struct list_head entries[3], *cur; + LIST_HEAD(list); + int i = 2; + + list_add_tail(&entries[0], &list); + list_add_tail(&entries[1], &list); + list_add_tail(&entries[2], &list); + + list_for_each_prev(cur, &list) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + i--; + } + + KUNIT_EXPECT_EQ(test, i, -1); +} + +static void list_test_list_for_each_safe(struct kunit *test) +{ + struct list_head entries[3], *cur, *n; + LIST_HEAD(list); + int i = 0; + + + list_add_tail(&entries[0], &list); + list_add_tail(&entries[1], &list); + list_add_tail(&entries[2], &list); + + list_for_each_safe(cur, n, &list) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + list_del(&entries[i]); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 3); + KUNIT_EXPECT_TRUE(test, list_empty(&list)); +} + +static void list_test_list_for_each_prev_safe(struct kunit *test) +{ + struct list_head entries[3], *cur, *n; + LIST_HEAD(list); + int i = 2; + + list_add_tail(&entries[0], &list); + list_add_tail(&entries[1], &list); + list_add_tail(&entries[2], &list); + + list_for_each_prev_safe(cur, n, &list) { + KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); + list_del(&entries[i]); + i--; + } + + KUNIT_EXPECT_EQ(test, i, -1); + KUNIT_EXPECT_TRUE(test, list_empty(&list)); +} + +static void list_test_list_for_each_entry(struct kunit *test) +{ + struct list_test_struct entries[5], *cur; + static LIST_HEAD(list); + int i = 0; + + for (i = 0; i < 5; ++i) { + entries[i].data = i; + list_add_tail(&entries[i].list, &list); + } + + i = 0; + + list_for_each_entry(cur, &list, list) { + KUNIT_EXPECT_EQ(test, cur->data, i); + i++; + } + + KUNIT_EXPECT_EQ(test, i, 5); +} + +static void list_test_list_for_each_entry_reverse(struct kunit *test) +{ + struct list_test_struct entries[5], *cur; + static LIST_HEAD(list); + int i = 0; + + for (i = 0; i < 5; ++i) { + entries[i].data = i; + list_add_tail(&entries[i].list, &list); + } + + i = 4; + + list_for_each_entry_reverse(cur, &list, list) { + KUNIT_EXPECT_EQ(test, cur->data, i); + i--; + } + + KUNIT_EXPECT_EQ(test, i, -1); +} + +static struct kunit_case list_test_cases[] = { + KUNIT_CASE(list_test_list_init), + KUNIT_CASE(list_test_list_add), + KUNIT_CASE(list_test_list_add_tail), + KUNIT_CASE(list_test_list_del), + KUNIT_CASE(list_test_list_replace), + KUNIT_CASE(list_test_list_replace_init), + KUNIT_CASE(list_test_list_swap), + KUNIT_CASE(list_test_list_del_init), + KUNIT_CASE(list_test_list_move), + KUNIT_CASE(list_test_list_move_tail), + KUNIT_CASE(list_test_list_bulk_move_tail), + KUNIT_CASE(list_test_list_is_first), + KUNIT_CASE(list_test_list_is_last), + KUNIT_CASE(list_test_list_empty), + KUNIT_CASE(list_test_list_empty_careful), + KUNIT_CASE(list_test_list_rotate_left), + KUNIT_CASE(list_test_list_rotate_to_front), + KUNIT_CASE(list_test_list_is_singular), + KUNIT_CASE(list_test_list_cut_position), + KUNIT_CASE(list_test_list_cut_before), + KUNIT_CASE(list_test_list_splice), + KUNIT_CASE(list_test_list_splice_tail), + KUNIT_CASE(list_test_list_splice_init), + KUNIT_CASE(list_test_list_splice_tail_init), + KUNIT_CASE(list_test_list_entry), + KUNIT_CASE(list_test_list_first_entry), + KUNIT_CASE(list_test_list_last_entry), + KUNIT_CASE(list_test_list_first_entry_or_null), + KUNIT_CASE(list_test_list_next_entry), + KUNIT_CASE(list_test_list_prev_entry), + KUNIT_CASE(list_test_list_for_each), + KUNIT_CASE(list_test_list_for_each_prev), + KUNIT_CASE(list_test_list_for_each_safe), + KUNIT_CASE(list_test_list_for_each_prev_safe), + KUNIT_CASE(list_test_list_for_each_entry), + KUNIT_CASE(list_test_list_for_each_entry_reverse), + {}, +}; + +static struct kunit_suite list_test_module = { + .name = "list-kunit-test", + .test_cases = list_test_cases, +}; + +kunit_test_suite(list_test_module); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 18c1dfbb1765..c8fa1d274530 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1529,7 +1529,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root, offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); - if (start > max) + if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 969e5400a615..33feec8989f1 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -236,23 +236,6 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb) } EXPORT_SYMBOL_GPL(sbitmap_any_bit_set); -bool sbitmap_any_bit_clear(const struct sbitmap *sb) -{ - unsigned int i; - - for (i = 0; i < sb->map_nr; i++) { - const struct sbitmap_word *word = &sb->map[i]; - unsigned long mask = word->word & ~word->cleared; - unsigned long ret; - - ret = find_first_zero_bit(&mask, word->depth); - if (ret < word->depth) - return true; - } - return false; -} -EXPORT_SYMBOL_GPL(sbitmap_any_bit_clear); - static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set) { unsigned int i, weight = 0; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 9d631a7b6a70..7df4f7f395bf 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1110,6 +1110,28 @@ static noinline void check_find_entry(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_move_tiny(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + XA_BUG_ON(xa, !xa_empty(xa)); + rcu_read_lock(); + XA_BUG_ON(xa, xas_next(&xas) != NULL); + XA_BUG_ON(xa, xas_next(&xas) != NULL); + rcu_read_unlock(); + xa_store_index(xa, 0, GFP_KERNEL); + rcu_read_lock(); + xas_set(&xas, 0); + XA_BUG_ON(xa, xas_next(&xas) != xa_mk_index(0)); + XA_BUG_ON(xa, xas_next(&xas) != NULL); + xas_set(&xas, 0); + XA_BUG_ON(xa, xas_prev(&xas) != xa_mk_index(0)); + XA_BUG_ON(xa, xas_prev(&xas) != NULL); + rcu_read_unlock(); + xa_erase_index(xa, 0); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_move_small(struct xarray *xa, unsigned long idx) { XA_STATE(xas, xa, 0); @@ -1217,6 +1239,8 @@ static noinline void check_move(struct xarray *xa) xa_destroy(xa); + check_move_tiny(xa); + for (i = 0; i < 16; i++) check_move_small(xa, 1UL << i); diff --git a/lib/xarray.c b/lib/xarray.c index 446b956c9188..1237c213f52b 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -994,6 +994,8 @@ void *__xas_prev(struct xa_state *xas) if (!xas_frozen(xas->xa_node)) xas->xa_index--; + if (!xas->xa_node) + return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); @@ -1031,6 +1033,8 @@ void *__xas_next(struct xa_state *xas) if (!xas_frozen(xas->xa_node)) xas->xa_index++; + if (!xas->xa_node) + return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index 08c3c8049998..156f26fdc4c9 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -1146,6 +1146,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) if (DEC_IS_DYNALLOC(s->dict.mode)) { if (s->dict.allocated < s->dict.size) { + s->dict.allocated = s->dict.size; vfree(s->dict.buf); s->dict.buf = vmalloc(s->dict.size); if (s->dict.buf == NULL) { diff --git a/mm/debug.c b/mm/debug.c index 8345bb6e4769..0461df1207cb 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -67,28 +67,31 @@ void __dump_page(struct page *page, const char *reason) */ mapcount = PageSlab(page) ? 0 : page_mapcount(page); - pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx", - page, page_ref_count(page), mapcount, - page->mapping, page_to_pgoff(page)); if (PageCompound(page)) - pr_cont(" compound_mapcount: %d", compound_mapcount(page)); - pr_cont("\n"); - if (PageAnon(page)) - pr_warn("anon "); - else if (PageKsm(page)) - pr_warn("ksm "); + pr_warn("page:%px refcount:%d mapcount:%d mapping:%px " + "index:%#lx compound_mapcount: %d\n", + page, page_ref_count(page), mapcount, + page->mapping, page_to_pgoff(page), + compound_mapcount(page)); + else + pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx\n", + page, page_ref_count(page), mapcount, + page->mapping, page_to_pgoff(page)); + if (PageKsm(page)) + pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags); + else if (PageAnon(page)) + pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags); else if (mapping) { - pr_warn("%ps ", mapping->a_ops); if (mapping->host && mapping->host->i_dentry.first) { struct dentry *dentry; dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias); - pr_warn("name:\"%pd\" ", dentry); - } + pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry); + } else + pr_warn("%ps\n", mapping->a_ops); + pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags); } BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); - pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags); - hex_only: print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index f1930fa0b445..2ac38bdc18a1 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -196,7 +196,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); - if (!css_tryget_online(&h_cg->css)) { + if (!css_tryget(&h_cg->css)) { rcu_read_unlock(); goto again; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index f05d27b7183d..a8a57bebb5fa 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1602,17 +1602,6 @@ static void collapse_file(struct mm_struct *mm, result = SCAN_FAIL; goto xa_unlocked; } - } else if (!PageUptodate(page)) { - xas_unlock_irq(&xas); - wait_on_page_locked(page); - if (!trylock_page(page)) { - result = SCAN_PAGE_LOCK; - goto xa_unlocked; - } - get_page(page); - } else if (PageDirty(page)) { - result = SCAN_FAIL; - goto xa_locked; } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); @@ -1627,7 +1616,12 @@ static void collapse_file(struct mm_struct *mm, * without racing with truncate. */ VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageUptodate(page), page); + + /* make sure the page is up to date */ + if (unlikely(!PageUptodate(page))) { + result = SCAN_FAIL; + goto out_unlock; + } /* * If file was truncated then extended, or hole-punched, before @@ -1643,6 +1637,16 @@ static void collapse_file(struct mm_struct *mm, goto out_unlock; } + if (!is_shmem && PageDirty(page)) { + /* + * khugepaged only works on read-only fd, so this + * page is dirty because it hasn't been flushed + * since first write. + */ + result = SCAN_FAIL; + goto out_unlock; + } + if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; @@ -885,13 +885,13 @@ static int remove_stable_node(struct stable_node *stable_node) return 0; } - if (WARN_ON_ONCE(page_mapped(page))) { - /* - * This should not happen: but if it does, just refuse to let - * merge_across_nodes be switched - there is no need to panic. - */ - err = -EBUSY; - } else { + /* + * Page could be still mapped if this races with __mmput() running in + * between ksm_exit() and exit_mmap(). Just refuse to let + * merge_across_nodes/max_page_sharing be switched. + */ + err = -EBUSY; + if (!page_mapped(page)) { /* * The stable node did not yet appear stale to get_ksm_page(), * since that allows for an unmapped ksm page to be recognized diff --git a/mm/madvise.c b/mm/madvise.c index 2be9f3fdb05e..94c343b4c968 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -363,8 +363,12 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, ClearPageReferenced(page); test_and_clear_page_young(page); if (pageout) { - if (!isolate_lru_page(page)) - list_add(&page->lru, &page_list); + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } } else deactivate_page(page); huge_unlock: @@ -441,8 +445,12 @@ regular_page: ClearPageReferenced(page); test_and_clear_page_young(page); if (pageout) { - if (!isolate_lru_page(page)) - list_add(&page->lru, &page_list); + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } } else deactivate_page(page); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 37592dd7ae32..46ad252e6d6a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -960,7 +960,7 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (unlikely(!memcg)) memcg = root_mem_cgroup; } - } while (!css_tryget_online(&memcg->css)); + } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; } diff --git a/mm/memory.c b/mm/memory.c index b1ca51a079f2..b6a5d6a08438 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -118,6 +118,18 @@ int randomize_va_space __read_mostly = 2; #endif +#ifndef arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + /* + * Those arches which don't have hw access flag feature need to + * implement their own helper. By default, "true" means pagefault + * will be hit on old pte. + */ + return true; +} +#endif + static int __init disable_randmaps(char *s) { randomize_va_space = 0; @@ -2145,32 +2157,82 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, return same; } -static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) +static inline bool cow_user_page(struct page *dst, struct page *src, + struct vm_fault *vmf) { + bool ret; + void *kaddr; + void __user *uaddr; + bool force_mkyoung; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = vmf->address; + debug_dma_assert_idle(src); + if (likely(src)) { + copy_user_highpage(dst, src, addr, vma); + return true; + } + /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ - if (unlikely(!src)) { - void *kaddr = kmap_atomic(dst); - void __user *uaddr = (void __user *)(va & PAGE_MASK); + kaddr = kmap_atomic(dst); + uaddr = (void __user *)(addr & PAGE_MASK); + + /* + * On architectures with software "accessed" bits, we would + * take a double page fault, so mark it accessed here. + */ + force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte); + if (force_mkyoung) { + pte_t entry; + + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* + * Other thread has already handled the fault + * and we don't need to do anything. If it's + * not the case, the fault will be triggered + * again on the same address. + */ + ret = false; + goto pte_unlock; + } + entry = pte_mkyoung(vmf->orig_pte); + if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) + update_mmu_cache(vma, addr, vmf->pte); + } + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* - * This really shouldn't fail, because the page is there - * in the page tables. But it might just be unreadable, - * in which case we just give up and fill the result with - * zeroes. + * Give a warn in case there can be some obscure + * use-case */ - if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) - clear_page(kaddr); - kunmap_atomic(kaddr); - flush_dcache_page(dst); - } else - copy_user_highpage(dst, src, va, vma); + WARN_ON_ONCE(1); + clear_page(kaddr); + } + + ret = true; + +pte_unlock: + if (force_mkyoung) + pte_unmap_unlock(vmf->pte, vmf->ptl); + kunmap_atomic(kaddr); + flush_dcache_page(dst); + + return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) @@ -2327,7 +2389,19 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) vmf->address); if (!new_page) goto oom; - cow_user_page(new_page, old_page, vmf->address, vma); + + if (!cow_user_page(new_page, old_page, vmf)) { + /* + * COW failed, if the fault was solved by other, + * it's fine. If not, userspace would re-fault on + * the same address and we will handle the fault + * from the second attempt. + */ + put_page(new_page); + if (old_page) + put_page(old_page); + return 0; + } } if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 07e5c67f48a8..f307bd82d750 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -331,7 +331,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long end_pfn) { for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(start_pfn))) + if (unlikely(!pfn_to_online_page(start_pfn))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) @@ -356,7 +356,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) @@ -415,7 +415,7 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, */ pfn = zone_start_pfn; for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (page_zone(pfn_to_page(pfn)) != zone) @@ -471,6 +471,16 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; +#ifdef CONFIG_ZONE_DEVICE + /* + * Zone shrinking code cannot properly deal with ZONE_DEVICE. So + * we will not try to shrink the zones - which is okay as + * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. + */ + if (zone_idx(zone) == ZONE_DEVICE) + return; +#endif + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); @@ -1646,6 +1656,18 @@ static int check_cpu_on_node(pg_data_t *pgdat) return 0; } +static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg) +{ + int nid = *(int *)arg; + + /* + * If a memory block belongs to multiple nodes, the stored nid is not + * reliable. However, such blocks are always online (e.g., cannot get + * offlined) and, therefore, are still spanned by the node. + */ + return mem->nid == nid ? -EEXIST : 0; +} + /** * try_offline_node * @nid: the node ID @@ -1658,25 +1680,24 @@ static int check_cpu_on_node(pg_data_t *pgdat) void try_offline_node(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - unsigned long start_pfn = pgdat->node_start_pfn; - unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; - unsigned long pfn; - - for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - unsigned long section_nr = pfn_to_section_nr(pfn); - - if (!present_section_nr(section_nr)) - continue; + int rc; - if (pfn_to_nid(pfn) != nid) - continue; + /* + * If the node still spans pages (especially ZONE_DEVICE), don't + * offline it. A node spans memory after move_pfn_range_to_zone(), + * e.g., after the memory block was onlined. + */ + if (pgdat->node_spanned_pages) + return; - /* - * some memory sections of this node are not removed, and we - * can't offline node now. - */ + /* + * Especially offline memory blocks might not be spanned by the + * node. They will get spanned by the node once they get onlined. + * However, they link to the node in sysfs and can get onlined later. + */ + rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb); + if (rc) return; - } if (check_cpu_on_node(pgdat)) return; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4ae967bcf954..e08c94170ae4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -672,7 +672,9 @@ static const struct mm_walk_ops queue_pages_walk_ops = { * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 0 - queue pages successfully or no misplaced page. - * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified. + * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or + * memory range specified by nodemask and maxnode points outside + * your accessible address space (-EFAULT) */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, @@ -1286,7 +1288,7 @@ static long do_mbind(unsigned long start, unsigned long len, flags | MPOL_MF_INVERT, &pagelist); if (ret < 0) { - err = -EIO; + err = ret; goto up_out; } @@ -1305,10 +1307,12 @@ static long do_mbind(unsigned long start, unsigned long len, if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; - } else - putback_movable_pages(&pagelist); - + } else { up_out: + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); + } + up_write(&mm->mmap_sem); mpol_out: mpol_put(new); diff --git a/mm/page_io.c b/mm/page_io.c index 24ee600f9131..60a66a58b9bf 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -73,6 +73,7 @@ static void swap_slot_free_notify(struct page *page) { struct swap_info_struct *sis; struct gendisk *disk; + swp_entry_t entry; /* * There is no guarantee that the page is in swap cache - the software @@ -104,11 +105,10 @@ static void swap_slot_free_notify(struct page *page) * we again wish to reclaim it. */ disk = sis->bdev->bd_disk; - if (disk->fops->swap_slot_free_notify) { - swp_entry_t entry; + entry.val = page_private(page); + if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) { unsigned long offset; - entry.val = page_private(page); offset = swp_offset(entry); SetPageDirty(page); diff --git a/mm/slub.c b/mm/slub.c index b25c807a111f..e72e802fc569 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1433,12 +1433,15 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; - if (slab_want_init_on_free(s)) { - void *p = NULL; + /* Head and tail of the reconstructed freelist */ + *head = NULL; + *tail = NULL; - do { - object = next; - next = get_freepointer(s, object); + do { + object = next; + next = get_freepointer(s, object); + + if (slab_want_init_on_free(s)) { /* * Clear the object and the metadata, but don't touch * the redzone. @@ -1448,29 +1451,8 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, : 0; memset((char *)object + s->inuse, 0, s->size - s->inuse - rsize); - set_freepointer(s, object, p); - p = object; - } while (object != old_tail); - } - -/* - * Compiler cannot detect this function can be removed if slab_free_hook() - * evaluates to nothing. Thus, catch all relevant config debug options here. - */ -#if defined(CONFIG_LOCKDEP) || \ - defined(CONFIG_DEBUG_KMEMLEAK) || \ - defined(CONFIG_DEBUG_OBJECTS_FREE) || \ - defined(CONFIG_KASAN) - next = *head; - - /* Head and tail of the reconstructed freelist */ - *head = NULL; - *tail = NULL; - - do { - object = next; - next = get_freepointer(s, object); + } /* If object's reuse doesn't have to be delayed */ if (!slab_free_hook(s, object)) { /* Move object to the new freelist */ @@ -1485,9 +1467,6 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, *tail = NULL; return *head != NULL; -#else - return true; -#endif } static void *setup_object(struct kmem_cache *s, struct page *page, diff --git a/net/atm/clip.c b/net/atm/clip.c index a7972da7235d..294cb9efe3d3 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -89,7 +89,7 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc) struct clip_vcc **walk; if (!entry) { - pr_crit("!clip_vcc->entry (clip_vcc %p)\n", clip_vcc); + pr_err("!clip_vcc->entry (clip_vcc %p)\n", clip_vcc); return; } netif_tx_lock_bh(entry->neigh->dev); /* block clip_start_xmit() */ @@ -109,10 +109,10 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc) error = neigh_update(entry->neigh, NULL, NUD_NONE, NEIGH_UPDATE_F_ADMIN, 0); if (error) - pr_crit("neigh_update failed with %d\n", error); + pr_err("neigh_update failed with %d\n", error); goto out; } - pr_crit("ATMARP: failed (entry %p, vcc 0x%p)\n", entry, clip_vcc); + pr_err("ATMARP: failed (entry %p, vcc 0x%p)\n", entry, clip_vcc); out: netif_tx_unlock_bh(entry->neigh->dev); } diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index ed91ea31978a..12a4f4d93681 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -20,7 +20,6 @@ static unsigned int ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - struct net_device *dev; if (skb_ensure_writable(skb, ETH_ALEN)) return EBT_DROP; @@ -33,10 +32,22 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) else skb->pkt_type = PACKET_MULTICAST; } else { - if (xt_hooknum(par) != NF_BR_BROUTING) - dev = br_port_get_rcu(xt_in(par))->br->dev; - else + const struct net_device *dev; + + switch (xt_hooknum(par)) { + case NF_BR_BROUTING: dev = xt_in(par); + break; + case NF_BR_PRE_ROUTING: + dev = br_port_get_rcu(xt_in(par))->br->dev; + break; + default: + dev = NULL; + break; + } + + if (!dev) /* NF_BR_LOCAL_OUT */ + return info->target; if (ether_addr_equal(info->mac, dev->dev_addr)) skb->pkt_type = PACKET_HOST; diff --git a/net/can/af_can.c b/net/can/af_can.c index 5518a7d9eed9..128d37a4c2e0 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -86,11 +86,12 @@ static atomic_t skbcounter = ATOMIC_INIT(0); /* af_can socket functions */ -static void can_sock_destruct(struct sock *sk) +void can_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_error_queue); } +EXPORT_SYMBOL(can_sock_destruct); static const struct can_proto *can_get_proto(int protocol) { diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index def2f813ffce..137054bff9ec 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -51,6 +51,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) if (!skb) return; + j1939_priv_get(priv); can_skb_set_owner(skb, iskb->sk); /* get a pointer to the header of the skb @@ -104,6 +105,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) j1939_simple_recv(priv, skb); j1939_sk_recv(priv, skb); done: + j1939_priv_put(priv); kfree_skb(skb); } @@ -150,6 +152,10 @@ static void __j1939_priv_release(struct kref *kref) netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv); + WARN_ON_ONCE(!list_empty(&priv->active_session_list)); + WARN_ON_ONCE(!list_empty(&priv->ecus)); + WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); + dev_put(ndev); kfree(priv); } @@ -207,6 +213,9 @@ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { struct can_ml_priv *can_ml_priv = ndev->ml_priv; + if (!can_ml_priv) + return NULL; + return can_ml_priv->j1939_priv; } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 37c1040bcb9c..de09b0a65791 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -78,7 +78,6 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) { jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - jsk->priv = priv; spin_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); @@ -91,7 +90,6 @@ static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) list_del_init(&jsk->list); spin_unlock_bh(&priv->j1939_socks_lock); - jsk->priv = NULL; j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; } @@ -349,6 +347,34 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) spin_unlock_bh(&priv->j1939_socks_lock); } +static void j1939_sk_sock_destruct(struct sock *sk) +{ + struct j1939_sock *jsk = j1939_sk(sk); + + /* This function will be call by the generic networking code, when then + * the socket is ultimately closed (sk->sk_destruct). + * + * The race between + * - processing a received CAN frame + * (can_receive -> j1939_can_recv) + * and accessing j1939_priv + * ... and ... + * - closing a socket + * (j1939_can_rx_unregister -> can_rx_unregister) + * and calling the final j1939_priv_put() + * + * is avoided by calling the final j1939_priv_put() from this + * RCU deferred cleanup call. + */ + if (jsk->priv) { + j1939_priv_put(jsk->priv); + jsk->priv = NULL; + } + + /* call generic CAN sock destruct */ + can_sock_destruct(sk); +} + static int j1939_sk_init(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); @@ -371,6 +397,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + sk->sk_destruct = j1939_sk_sock_destruct; return 0; } @@ -443,6 +470,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) } jsk->ifindex = addr->can_ifindex; + + /* the corresponding j1939_priv_put() is called via + * sk->sk_destruct, which points to j1939_sk_sock_destruct() + */ + j1939_priv_get(priv); + jsk->priv = priv; } /* set default transmit pgn */ @@ -560,8 +593,8 @@ static int j1939_sk_release(struct socket *sock) if (!sk) return 0; - jsk = j1939_sk(sk); lock_sock(sk); + jsk = j1939_sk(sk); if (jsk->state & J1939_SOCK_BOUND) { struct j1939_priv *priv = jsk->priv; @@ -580,6 +613,7 @@ static int j1939_sk_release(struct socket *sock) j1939_netdev_stop(priv); } + kfree(jsk->filters); sock_orphan(sk); sock->sk = NULL; @@ -909,8 +943,10 @@ void j1939_sk_errqueue(struct j1939_session *session, memset(serr, 0, sizeof(*serr)); switch (type) { case J1939_ERRQUEUE_ACK: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) { + kfree_skb(skb); return; + } serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; @@ -918,8 +954,10 @@ void j1939_sk_errqueue(struct j1939_session *session, state = "ACK"; break; case J1939_ERRQUEUE_SCHED: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) { + kfree_skb(skb); return; + } serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; @@ -1054,51 +1092,72 @@ static int j1939_sk_sendmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct j1939_sock *jsk = j1939_sk(sk); - struct j1939_priv *priv = jsk->priv; + struct j1939_priv *priv; int ifindex; int ret; + lock_sock(sock->sk); /* various socket state tests */ - if (!(jsk->state & J1939_SOCK_BOUND)) - return -EBADFD; + if (!(jsk->state & J1939_SOCK_BOUND)) { + ret = -EBADFD; + goto sendmsg_done; + } + priv = jsk->priv; ifindex = jsk->ifindex; - if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) + if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) { /* no source address assigned yet */ - return -EBADFD; + ret = -EBADFD; + goto sendmsg_done; + } /* deal with provided destination address info */ if (msg->msg_name) { struct sockaddr_can *addr = msg->msg_name; - if (msg->msg_namelen < J1939_MIN_NAMELEN) - return -EINVAL; + if (msg->msg_namelen < J1939_MIN_NAMELEN) { + ret = -EINVAL; + goto sendmsg_done; + } - if (addr->can_family != AF_CAN) - return -EINVAL; + if (addr->can_family != AF_CAN) { + ret = -EINVAL; + goto sendmsg_done; + } - if (addr->can_ifindex && addr->can_ifindex != ifindex) - return -EBADFD; + if (addr->can_ifindex && addr->can_ifindex != ifindex) { + ret = -EBADFD; + goto sendmsg_done; + } if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) && - !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) - return -EINVAL; + !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) { + ret = -EINVAL; + goto sendmsg_done; + } if (!addr->can_addr.j1939.name && addr->can_addr.j1939.addr == J1939_NO_ADDR && - !sock_flag(sk, SOCK_BROADCAST)) + !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ - return -EACCES; + ret = -EACCES; + goto sendmsg_done; + } } else { if (!jsk->addr.dst_name && jsk->addr.da == J1939_NO_ADDR && - !sock_flag(sk, SOCK_BROADCAST)) + !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ - return -EACCES; + ret = -EACCES; + goto sendmsg_done; + } } ret = j1939_sk_send_loop(priv, sk, msg, size); +sendmsg_done: + release_sock(sock->sk); + return ret; } diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fe000ea757ea..9f99af5b0b11 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -255,6 +255,7 @@ static void __j1939_session_drop(struct j1939_session *session) return; j1939_sock_pending_del(session->sk); + sock_put(session->sk); } static void j1939_session_destroy(struct j1939_session *session) @@ -266,6 +267,9 @@ static void j1939_session_destroy(struct j1939_session *session) netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + WARN_ON_ONCE(!list_empty(&session->sk_session_queue_entry)); + WARN_ON_ONCE(!list_empty(&session->active_session_list_entry)); + skb_queue_purge(&session->skb_queue); __j1939_session_drop(session); j1939_priv_put(session->priv); @@ -1042,12 +1046,13 @@ j1939_session_deactivate_activate_next(struct j1939_session *session) j1939_sk_queue_activate_next(session); } -static void j1939_session_cancel(struct j1939_session *session, +static void __j1939_session_cancel(struct j1939_session *session, enum j1939_xtp_abort err) { struct j1939_priv *priv = session->priv; WARN_ON_ONCE(!err); + lockdep_assert_held(&session->priv->active_session_list_lock); session->err = j1939_xtp_abort_to_errno(priv, err); /* do not send aborts on incoming broadcasts */ @@ -1062,6 +1067,20 @@ static void j1939_session_cancel(struct j1939_session *session, j1939_sk_send_loop_abort(session->sk, session->err); } +static void j1939_session_cancel(struct j1939_session *session, + enum j1939_xtp_abort err) +{ + j1939_session_list_lock(session->priv); + + if (session->state >= J1939_SESSION_ACTIVE && + session->state < J1939_SESSION_WAITING_ABORT) { + j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); + __j1939_session_cancel(session, err); + } + + j1939_session_list_unlock(session->priv); +} + static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) { struct j1939_session *session = @@ -1108,8 +1127,6 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) netdev_alert(priv->ndev, "%s: 0x%p: tx aborted with unknown reason: %i\n", __func__, session, ret); if (session->skcb.addr.type != J1939_SIMPLE) { - j1939_tp_set_rxtimeout(session, - J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_OTHER); } else { session->err = ret; @@ -1169,7 +1186,7 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer) hrtimer_start(&session->rxtimer, ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS), HRTIMER_MODE_REL_SOFT); - j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); + __j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); } j1939_session_list_unlock(session->priv); } @@ -1273,9 +1290,27 @@ j1939_xtp_rx_abort(struct j1939_priv *priv, struct sk_buff *skb, static void j1939_xtp_rx_eoma_one(struct j1939_session *session, struct sk_buff *skb) { + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + const u8 *dat; + int len; + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) return; + dat = skb->data; + + if (skcb->addr.type == J1939_ETP) + len = j1939_etp_ctl_to_size(dat); + else + len = j1939_tp_ctl_to_size(dat); + + if (session->total_message_size != len) { + netdev_warn_once(session->priv->ndev, + "%s: 0x%p: Incorrect size. Expected: %i; got: %i.\n", + __func__, session, session->total_message_size, + len); + } + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); session->pkt.tx_acked = session->pkt.total; @@ -1357,7 +1392,6 @@ j1939_xtp_rx_cts_one(struct j1939_session *session, struct sk_buff *skb) out_session_cancel: j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, err); } @@ -1432,7 +1466,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, skcb = j1939_skb_to_cb(skb); memcpy(skcb, rel_skcb, sizeof(*skcb)); - session = j1939_session_new(priv, skb, skb->len); + session = j1939_session_new(priv, skb, size); if (!session) { kfree_skb(skb); return NULL; @@ -1554,7 +1588,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, /* RTS on active session */ j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); } @@ -1565,7 +1598,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, session->last_cmd); j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); return -EBUSY; @@ -1767,7 +1799,6 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, out_session_cancel: j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); j1939_session_put(session); } @@ -1848,6 +1879,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv, return ERR_PTR(-ENOMEM); /* skb is recounted in j1939_session_new() */ + sock_hold(skb->sk); session->sk = skb->sk; session->transmission = true; session->pkt.total = (size + 6) / 7; @@ -2010,7 +2042,11 @@ int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk) &priv->active_session_list, active_session_list_entry) { if (!sk || sk == session->sk) { - j1939_session_timers_cancel(session); + if (hrtimer_try_to_cancel(&session->txtimer) == 1) + j1939_session_put(session); + if (hrtimer_try_to_cancel(&session->rxtimer) == 1) + j1939_session_put(session); + session->err = ESHUTDOWN; j1939_session_deactivate_locked(session); } diff --git a/net/core/devlink.c b/net/core/devlink.c index f80151eeaf51..93905dc7c179 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2699,7 +2699,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) struct devlink *devlink = info->user_ptr[0]; int err; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink) || !devlink->reload_enabled) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -4618,6 +4618,7 @@ struct devlink_health_reporter { bool auto_recover; u8 health_state; u64 dump_ts; + u64 dump_real_ts; u64 error_count; u64 recovery_count; u64 last_recovery_ts; @@ -4790,6 +4791,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, goto dump_err; reporter->dump_ts = jiffies; + reporter->dump_real_ts = ktime_get_real_ns(); return 0; @@ -4952,6 +4954,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg, jiffies_to_msecs(reporter->dump_ts), DEVLINK_ATTR_PAD)) goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, + reporter->dump_real_ts, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; nla_nest_end(msg, reporter_attr); genlmsg_end(msg, hdr); @@ -6196,6 +6202,8 @@ EXPORT_SYMBOL_GPL(devlink_register); void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); + WARN_ON(devlink_reload_supported(devlink) && + devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); mutex_unlock(&devlink_mutex); @@ -6203,6 +6211,41 @@ void devlink_unregister(struct devlink *devlink) EXPORT_SYMBOL_GPL(devlink_unregister); /** + * devlink_reload_enable - Enable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at end of device initialization + * process when reload operation is supported. + */ +void devlink_reload_enable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink->reload_enabled = true; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_enable); + +/** + * devlink_reload_disable - Disable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at the beginning of device cleanup + * process when reload operation is supported. + */ +void devlink_reload_disable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + /* Mutex is taken which ensures that no reload operation is in + * progress while setting up forbidded flag. + */ + devlink->reload_enabled = false; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_disable); + +/** * devlink_free - Free devlink instance resources * * @devlink: devlink diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 865ba6ca16eb..ae3bcb1540ec 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -923,21 +923,23 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) - return error; + goto err; dev_hold(queue->dev); if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); - if (error) { - kobject_put(kobj); - return error; - } + if (error) + goto err; } kobject_uevent(kobj, KOBJ_ADD); return error; + +err: + kobject_put(kobj); + return error; } #endif /* CONFIG_SYSFS */ @@ -1461,21 +1463,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) - return error; + goto err; dev_hold(queue->dev); #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); - if (error) { - kobject_put(kobj); - return error; - } + if (error) + goto err; #endif kobject_uevent(kobj, KOBJ_ADD); - return 0; + +err: + kobject_put(kobj); + return error; } #endif /* CONFIG_SYSFS */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c81cd80114d9..e4ec575c1fba 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2195,6 +2195,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_MAC]) { struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); + if (ivm->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_mac) err = ops->ndo_set_vf_mac(dev, ivm->vf, @@ -2206,6 +2208,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_VLAN]) { struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + if (ivv->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, @@ -2238,6 +2242,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (len == 0) return -EINVAL; + if (ivvl[0]->vf >= INT_MAX) + return -EINVAL; err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) @@ -2248,6 +2254,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); struct ifla_vf_info ivf; + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_get_vf_config) err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf); @@ -2266,6 +2274,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_RATE]) { struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_rate) err = ops->ndo_set_vf_rate(dev, ivt->vf, @@ -2278,6 +2288,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_SPOOFCHK]) { struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + if (ivs->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_spoofchk) err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, @@ -2289,6 +2301,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_LINK_STATE]) { struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]); + if (ivl->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_link_state) err = ops->ndo_set_vf_link_state(dev, ivl->vf, @@ -2302,6 +2316,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]); + if (ivrssq_en->vf >= INT_MAX) + return -EINVAL; if (ops->ndo_set_vf_rss_query_en) err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf, ivrssq_en->setting); @@ -2312,6 +2328,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_TRUST]) { struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_trust) err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting); @@ -2322,15 +2340,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_IB_NODE_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; - return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID); } if (tb[IFLA_VF_IB_PORT_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index cf390e0aa73d..ad31e4e53d0a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -270,18 +270,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len) msg->sg.data[i].length -= trim; sk_mem_uncharge(sk, trim); + /* Adjust copybreak if it falls into the trimmed part of last buf */ + if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length) + msg->sg.copybreak = msg->sg.data[i].length; out: - /* If we trim data before curr pointer update copybreak and current - * so that any future copy operations start at new copy location. + sk_msg_iter_var_next(i); + msg->sg.end = i; + + /* If we trim data a full sg elem before curr pointer update + * copybreak and current so that any future copy operations + * start at new copy location. * However trimed data that has not yet been used in a copy op * does not require an update. */ - if (msg->sg.curr >= i) { + if (!msg->sg.size) { + msg->sg.curr = msg->sg.start; + msg->sg.copybreak = 0; + } else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >= + sk_msg_iter_dist(msg->sg.start, msg->sg.end)) { + sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } - sk_msg_iter_var_next(i); - msg->sg.end = i; } EXPORT_SYMBOL_GPL(sk_msg_trim); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 0d8f782c25cc..d19557c6d04b 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -416,7 +416,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = jiffies; + newinet->inet_id = prandom_u32(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 9c1cc2482b68..9e5a883a9f0c 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -106,7 +106,7 @@ static int dsa_8021q_restore_pvid(struct dsa_switch *ds, int port) slave = ds->ports[port].slave; err = br_vlan_get_pvid(slave, &pvid); - if (err < 0) + if (!pvid || err < 0) /* There is no pvid on the bridge for this port, which is * perfectly valid. Nothing to restore, bye-bye! */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0913a090b2bf..f1888c683426 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1814,8 +1814,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); - int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 716d5472c022..58007439cffd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2289,7 +2289,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_unlock(); return -ENODEV; } - skb2 = skb_clone(skb, GFP_ATOMIC); + + skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { read_unlock(&mrt_lock); rcu_read_unlock(); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 59ded25acd04..0902cb32bbad 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1037,7 +1037,7 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_fib_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, #endif { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1d58ce829dca..447defbfccdd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1297,6 +1297,27 @@ out: #define UDP_SKB_IS_STATELESS 0x80000000 +/* all head states (dst, sk, nf conntrack) except skb extensions are + * cleared by udp_rcv(). + * + * We need to preserve secpath, if present, to eventually process + * IP_CMSG_PASSSEC at recvmsg() time. + * + * Other extensions can be cleared. + */ +static bool udp_try_make_stateless(struct sk_buff *skb) +{ + if (!skb_has_extensions(skb)) + return true; + + if (!secpath_exists(skb)) { + skb_ext_reset(skb); + return true; + } + + return false; +} + static void udp_set_dev_scratch(struct sk_buff *skb) { struct udp_dev_scratch *scratch = udp_skb_scratch(skb); @@ -1308,11 +1329,7 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif - /* all head states execept sp (dst, sk, nf) are always cleared by - * udp_rcv() and we need to preserve secpath, if present, to eventually - * process IP_CMSG_PASSSEC at recvmsg() time - */ - if (likely(!skb_sec_path(skb))) + if (udp_try_make_stateless(skb)) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 264c292e7dcc..79fc012dd2ca 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -363,8 +363,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; case IPV6_TRANSPARENT: - if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) && - !ns_capable(net->user_ns, CAP_NET_RAW)) { + if (valbool && !ns_capable(net->user_ns, CAP_NET_RAW) && + !ns_capable(net->user_ns, CAP_NET_ADMIN)) { retv = -EPERM; break; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a63ff85fe141..3f83ea851ebf 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -621,6 +621,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; + unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; @@ -633,12 +634,13 @@ static void rt6_probe(struct fib6_nh *fib6_nh) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - if (fib6_nh->fib_nh_gw_family) + if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock_bh(); + last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { @@ -654,13 +656,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh) __neigh_set_probe_once(neigh); } write_unlock(&neigh->lock); - } else if (time_after(jiffies, fib6_nh->last_probe + + } else if (time_after(jiffies, last_probe + idev->cnf.rtr_probe_interval)) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } - if (work) { - fib6_nh->last_probe = jiffies; + if (!work || cmpxchg(&fib6_nh->last_probe, + last_probe, jiffies) != last_probe) { + kfree(work); + } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; dev_hold(dev); @@ -3383,6 +3387,9 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, int err; fib6_nh->fib_nh_family = AF_INET6; +#ifdef CONFIG_IPV6_ROUTER_PREF + fib6_nh->last_probe = jiffies; +#endif err = -ENODEV; if (cfg->fc_ifindex) { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 9d4f75e0d33a..e70567446f28 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -81,6 +81,11 @@ static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb) if (!pskb_may_pull(skb, srhoff + len)) return NULL; + /* note that pskb_may_pull may change pointers in header; + * for this reason it is necessary to reload them when needed. + */ + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + if (!seg6_validate_srh(srh, len)) return NULL; @@ -336,6 +341,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (!ipv6_addr_any(&slwt->nh6)) nhaddr = &slwt->nh6; + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + seg6_lookup_nexthop(skb, nhaddr, 0); return dst_input(skb); @@ -365,6 +372,8 @@ static int input_action_end_dx4(struct sk_buff *skb, skb_dst_drop(skb); + skb_set_transport_header(skb, sizeof(struct iphdr)); + err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev); if (err) goto drop; @@ -385,6 +394,8 @@ static int input_action_end_dt6(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + seg6_lookup_nexthop(skb, NULL, slwt->table); return dst_input(skb); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index aba094b4ccfc..2d05c4cfaf6d 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1292,8 +1292,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_remove_interfaces(local); fail_rate: rtnl_unlock(); - ieee80211_led_exit(local); fail_flows: + ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: wiphy_unregister(local->hw.wiphy); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index bd11fef2139f..8d3a2389b055 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2457,7 +2457,8 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta) { struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta); - if (time_after(stats->last_rx, sta->status_stats.last_ack)) + if (!sta->status_stats.last_ack || + time_after(stats->last_rx, sta->status_stats.last_ack)) return stats->last_rx; return sta->status_stats.last_ack; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e64d5f9a89dd..d73d1828216a 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -296,7 +296,8 @@ ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4))) return -IPSET_ERR_PROTOCOL; @@ -314,7 +315,8 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6))) return -IPSET_ERR_PROTOCOL; @@ -934,7 +936,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Without holding any locks, create private part. */ if (attr[IPSET_ATTR_DATA] && - nla_parse_nested_deprecated(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy, NULL)) { + nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], + set->type->create_policy, NULL)) { ret = -IPSET_ERR_PROTOCOL; goto put_out; } @@ -1281,6 +1284,14 @@ dump_attrs(struct nlmsghdr *nlh) } } +static const struct nla_policy +ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_FLAGS] = { .type = NLA_U32 }, +}; + static int dump_init(struct netlink_callback *cb, struct ip_set_net *inst) { @@ -1292,9 +1303,9 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst) ip_set_id_t index; int ret; - ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, attr, - nlh->nlmsg_len - min_len, - ip_set_setname_policy, NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, + nlh->nlmsg_len - min_len, + ip_set_dump_policy, NULL); if (ret) return ret; @@ -1543,9 +1554,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, memcpy(&errmsg->msg, nlh, nlh->nlmsg_len); cmdattr = (void *)&errmsg->msg + min_len; - ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, cmdattr, - nlh->nlmsg_len - min_len, - ip_set_adt_policy, NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr, + nlh->nlmsg_len - min_len, ip_set_adt_policy, + NULL); if (ret) { nlmsg_free(skb2); @@ -1596,7 +1607,9 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, use_lineno = !!attr[IPSET_ATTR_LINENO]; if (attr[IPSET_ATTR_DATA]) { - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, + attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, adt, flags, use_lineno); @@ -1606,7 +1619,8 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) { if (nla_type(nla) != IPSET_ATTR_DATA || !flag_nested(nla) || - nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL)) + nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, adt, flags, use_lineno); @@ -1655,7 +1669,8 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, if (!set) return -ENOENT; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; rcu_read_lock_bh(); @@ -1961,7 +1976,7 @@ static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { [IPSET_CMD_LIST] = { .call = ip_set_dump, .attr_count = IPSET_ATTR_CMD_MAX, - .policy = ip_set_setname_policy, + .policy = ip_set_dump_policy, }, [IPSET_CMD_SAVE] = { .call = ip_set_dump, @@ -2069,8 +2084,9 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } req_version->version = IPSET_PROTOCOL; - ret = copy_to_user(user, req_version, - sizeof(struct ip_set_req_version)); + if (copy_to_user(user, req_version, + sizeof(struct ip_set_req_version))) + ret = -EFAULT; goto done; } case IP_SET_OP_GET_BYNAME: { @@ -2129,7 +2145,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } /* end of switch(op) */ copy: - ret = copy_to_user(user, data, copylen); + if (copy_to_user(user, data, copylen)) + ret = -EFAULT; done: vfree(data); diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index 24d8f4df4230..4ce563eb927d 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -209,7 +209,7 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb, (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c259cbc3ef45..3d932de0ad29 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -368,6 +368,7 @@ static struct ip_set_type hash_net_type __read_mostly = { [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index a3ae69bfee66..4398322fad59 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -476,6 +476,7 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d481f9baca2f..712a428509ad 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1922,6 +1922,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + flags |= chain->flags & NFT_BASE_CHAIN; return nf_tables_updchain(&ctx, genmask, policy, flags); } @@ -5143,9 +5144,6 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, struct nft_trans *trans; int err; - if (!obj->ops->update) - return -EOPNOTSUPP; - trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) @@ -6499,7 +6497,8 @@ static void nft_obj_commit_update(struct nft_trans *trans) obj = nft_trans_obj(trans); newobj = nft_trans_obj_newobj(trans); - obj->ops->update(obj, newobj); + if (obj->ops->update) + obj->ops->update(obj, newobj); kfree(newobj); } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index ad783f4840ef..e25dab8128db 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -334,7 +334,8 @@ int nft_flow_rule_offload_commit(struct net *net) switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) || + nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 974300178fa9..02afa752dd2e 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -134,12 +134,13 @@ static int nft_bitwise_offload(struct nft_offload_ctx *ctx, const struct nft_expr *expr) { const struct nft_bitwise *priv = nft_expr_priv(expr); + struct nft_offload_reg *reg = &ctx->regs[priv->dreg]; if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) || - priv->sreg != priv->dreg) + priv->sreg != priv->dreg || priv->len != reg->len) return -EOPNOTSUPP; - memcpy(&ctx->regs[priv->dreg].mask, &priv->mask, sizeof(priv->mask)); + memcpy(®->mask, &priv->mask, sizeof(priv->mask)); return 0; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index bd173b1824c6..0744b2bb46da 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -116,7 +116,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, u8 *mask = (u8 *)&flow->match.mask; u8 *key = (u8 *)&flow->match.key; - if (priv->op != NFT_CMP_EQ) + if (priv->op != NFT_CMP_EQ || reg->len != priv->len) return -EOPNOTSUPP; memcpy(key + reg->offset, &priv->data, priv->len); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 17e6ca62f1be..afde0d763039 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1099,7 +1099,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } @@ -1159,7 +1158,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 233f1368162b..18c6fac6ead9 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -450,6 +450,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) struct ib_qp_init_attr attr; struct ib_cq_init_attr cq_attr = {}; struct rds_ib_device *rds_ibdev; + unsigned long max_wrs; int ret, fr_queue_space; /* @@ -469,10 +470,15 @@ static int rds_ib_setup_qp(struct rds_connection *conn) /* add the conn now so that connection establishment has the dev */ rds_ib_add_conn(rds_ibdev, conn); - if (rds_ibdev->max_wrs < ic->i_send_ring.w_nr + 1) - rds_ib_ring_resize(&ic->i_send_ring, rds_ibdev->max_wrs - 1); - if (rds_ibdev->max_wrs < ic->i_recv_ring.w_nr + 1) - rds_ib_ring_resize(&ic->i_recv_ring, rds_ibdev->max_wrs - 1); + max_wrs = rds_ibdev->max_wrs < rds_ib_sysctl_max_send_wr + 1 ? + rds_ibdev->max_wrs - 1 : rds_ib_sysctl_max_send_wr; + if (ic->i_send_ring.w_nr != max_wrs) + rds_ib_ring_resize(&ic->i_send_ring, max_wrs); + + max_wrs = rds_ibdev->max_wrs < rds_ib_sysctl_max_recv_wr + 1 ? + rds_ibdev->max_wrs - 1 : rds_ib_sysctl_max_recv_wr; + if (ic->i_recv_ring.w_nr != max_wrs) + rds_ib_ring_resize(&ic->i_recv_ring, max_wrs); /* Protection domain and memory range */ ic->i_pd = rds_ibdev->pd; @@ -1099,8 +1105,9 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp) ic->i_flowctl = 0; atomic_set(&ic->i_credits, 0); - rds_ib_ring_init(&ic->i_send_ring, rds_ib_sysctl_max_send_wr); - rds_ib_ring_init(&ic->i_recv_ring, rds_ib_sysctl_max_recv_wr); + /* Re-init rings, but retain sizes. */ + rds_ib_ring_init(&ic->i_send_ring, ic->i_send_ring.w_nr); + rds_ib_ring_init(&ic->i_recv_ring, ic->i_recv_ring.w_nr); if (ic->i_ibinc) { rds_inc_put(&ic->i_ibinc->ii_inc); @@ -1147,8 +1154,8 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) * rds_ib_conn_shutdown() waits for these to be emptied so they * must be initialized before it can be called. */ - rds_ib_ring_init(&ic->i_send_ring, rds_ib_sysctl_max_send_wr); - rds_ib_ring_init(&ic->i_recv_ring, rds_ib_sysctl_max_recv_wr); + rds_ib_ring_init(&ic->i_send_ring, 0); + rds_ib_ring_init(&ic->i_recv_ring, 0); ic->conn = conn; conn->c_transport_data = ic; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index cdfaa79382a2..b5bc631b96b7 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -43,7 +43,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, int err = -EINVAL; int rem; - if (!nla || !n) + if (!nla) return NULL; keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL); @@ -170,6 +170,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(pattr); + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); + return -EINVAL; + } ksize = parm->nkeys * sizeof(struct tc_pedit_key); if (nla_len(pattr) < sizeof(*parm) + ksize) { NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); @@ -183,12 +187,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - if (!parm->nkeys) { - tcf_idr_cleanup(tn, index); - NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); - ret = -EINVAL; - goto out_free; - } ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 2f83a79f76aa..d55669e14741 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -135,6 +135,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; + if (opts_len > IP_TUNNEL_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -EINVAL; + } if (dst) { dst_len -= opt_len; dst += opt_len; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8717c0b26c90..20d60b8fcb70 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -47,6 +48,62 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +static u32 destroy_obj_hashfn(const struct tcf_proto *tp) +{ + return jhash_3words(tp->chain->index, tp->prio, + (__force __u32)tp->protocol, 0); +} + +static void tcf_proto_signal_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node, + destroy_obj_hashfn(tp)); + mutex_unlock(&block->proto_destroy_lock); +} + +static bool tcf_proto_cmp(const struct tcf_proto *tp1, + const struct tcf_proto *tp2) +{ + return tp1->chain->index == tp2->chain->index && + tp1->prio == tp2->prio && + tp1->protocol == tp2->protocol; +} + +static bool tcf_proto_exists_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + u32 hash = destroy_obj_hashfn(tp); + struct tcf_proto *iter; + bool found = false; + + rcu_read_lock(); + hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter, + destroy_ht_node, hash) { + if (tcf_proto_cmp(tp, iter)) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; +} + +static void +tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + if (hash_hashed(&tp->destroy_ht_node)) + hash_del_rcu(&tp->destroy_ht_node); + mutex_unlock(&block->proto_destroy_lock); +} + /* Find classifier type by string name */ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) @@ -234,9 +291,11 @@ static void tcf_proto_get(struct tcf_proto *tp) static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) + bool sig_destroy, struct netlink_ext_ack *extack) { tp->ops->destroy(tp, rtnl_held, extack); + if (sig_destroy) + tcf_proto_signal_destroyed(tp->chain, tp); tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); @@ -246,7 +305,7 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { if (refcount_dec_and_test(&tp->refcnt)) - tcf_proto_destroy(tp, rtnl_held, extack); + tcf_proto_destroy(tp, rtnl_held, true, extack); } static int walker_check_empty(struct tcf_proto *tp, void *fh, @@ -370,6 +429,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain) static void tcf_block_destroy(struct tcf_block *block) { mutex_destroy(&block->lock); + mutex_destroy(&block->proto_destroy_lock); kfree_rcu(block, rcu); } @@ -545,6 +605,12 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_dereference(chain->filter_chain, chain); + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_signal_destroying(chain, tp); + tp = tp_next; + } + tp = tcf_chain_dereference(chain->filter_chain, chain); RCU_INIT_POINTER(chain->filter_chain, NULL); tcf_chain0_head_change(chain, NULL); chain->flushing = true; @@ -844,6 +910,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + mutex_init(&block->proto_destroy_lock); init_rwsem(&block->cb_lock); flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); @@ -1621,6 +1688,12 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_lock(&chain->filter_chain_lock); + if (tcf_proto_exists_destroying(chain, tp_new)) { + mutex_unlock(&chain->filter_chain_lock); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + return ERR_PTR(-EAGAIN); + } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); if (!tp) @@ -1628,10 +1701,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_unlock(&chain->filter_chain_lock); if (tp) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = tp; } else if (err) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = ERR_PTR(err); } @@ -1669,6 +1742,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, return; } + tcf_proto_signal_destroying(chain, tp); next = tcf_chain_dereference(chain_info.next, chain); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); @@ -2188,6 +2262,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -EINVAL; goto errout_locked; } else if (t->tcm_handle == 0) { + tcf_proto_signal_destroying(chain, tp); tcf_chain_tp_remove(chain, &chain_info, tp); mutex_unlock(&chain->filter_chain_lock); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 2121187229cd..c609373c8661 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -922,7 +922,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, } /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { + for (i = 0; i <= TC_BITMASK; i++) { if (qopt->prio_tc_map[i] >= qopt->num_tc) { NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); return -EINVAL; @@ -1224,8 +1224,6 @@ static int taprio_enable_offload(struct net_device *dev, goto done; } - taprio_offload_config_changed(q); - done: taprio_offload_free(offload); @@ -1349,6 +1347,26 @@ out: return err; } +static int taprio_mqprio_cmp(const struct net_device *dev, + const struct tc_mqprio_qopt *mqprio) +{ + int i; + + if (!mqprio || mqprio->num_tc != dev->num_tc) + return -1; + + for (i = 0; i < mqprio->num_tc; i++) + if (dev->tc_to_txq[i].count != mqprio->count[i] || + dev->tc_to_txq[i].offset != mqprio->offset[i]) + return -1; + + for (i = 0; i <= TC_BITMASK; i++) + if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i]) + return -1; + + return 0; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1400,6 +1418,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, admin = rcu_dereference(q->admin_sched); rcu_read_unlock(); + /* no changes - no new mqprio settings */ + if (!taprio_mqprio_cmp(dev, mqprio)) + mqprio = NULL; + if (mqprio && (oper || admin)) { NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported"); err = -ENOTSUPP; @@ -1457,7 +1479,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, mqprio->offset[i]); /* Always use supplied priority mappings */ - for (i = 0; i < TC_BITMASK + 1; i++) + for (i = 0; i <= TC_BITMASK; i++) netdev_set_prio_tc_map(dev, i, mqprio->prio_tc_map[i]); } @@ -1505,6 +1527,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, call_rcu(&admin->rcu, taprio_free_sched_cb); spin_unlock_irqrestore(&q->current_entry_lock, flags); + + if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) + taprio_offload_config_changed(q); } new_admin = NULL; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 47946f489fd4..737b49909a7a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -796,6 +796,7 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = EPIPE; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); + sock_put(&smc->sk); /* passive closing */ goto out; } @@ -1731,7 +1732,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 2920b006f65c..571e6d84da3b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -376,8 +376,6 @@ static int smc_pnet_fill_entry(struct net *net, return 0; error: - if (pnetelem->ndev) - dev_put(pnetelem->ndev); return rc; } diff --git a/net/socket.c b/net/socket.c index 6a9ab7a8b1d2..17bc1eee198a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -404,6 +404,7 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) sock->file = file; file->private_data = sock; + stream_open(SOCK_INODE(sock), file); return file; } EXPORT_SYMBOL(sock_alloc_file); @@ -1690,24 +1691,13 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -/* - * For accept, we attempt to create a new socket, set up the link - * with the client, wake up the client, then return the new - * connected fd. We collect the address of the connector in kernel - * space and move it to user at the very end. This is unclean because - * we open the socket then return an error. - * - * 1003.1g adds the ability to recvmsg() to query connection pending - * status to recvmsg. We need to add that support in a way thats - * clean when we restructure accept also. - */ - -int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags) +int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd, fput_needed; + int err, len, newfd; struct sockaddr_storage address; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) @@ -1716,14 +1706,14 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - sock = sockfd_lookup_light(fd, &err, &fput_needed); + sock = sock_from_file(file, &err); if (!sock) goto out; err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out_put; + goto out; newsock->type = sock->type; newsock->ops = sock->ops; @@ -1738,20 +1728,21 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); - goto out_put; + goto out; } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) { err = PTR_ERR(newfile); put_unused_fd(newfd); - goto out_put; + goto out; } err = security_socket_accept(sock, newsock); if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); + err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags, + false); if (err < 0) goto out_fd; @@ -1772,15 +1763,42 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, fd_install(newfd, newfile); err = newfd; - -out_put: - fput_light(sock->file, fput_needed); out: return err; out_fd: fput(newfile); put_unused_fd(newfd); - goto out_put; + goto out; + +} + +/* + * For accept, we attempt to create a new socket, set up the link + * with the client, wake up the client, then return the new + * connected fd. We collect the address of the connector in kernel + * space and move it to user at the very end. This is unclean because + * we open the socket then return an error. + * + * 1003.1g adds the ability to recvmsg() to query connection pending + * status to recvmsg. We need to add that support in a way thats + * clean when we restructure accept also. + */ + +int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) +{ + int ret = -EBADF; + struct fd f; + + f = fdget(fd); + if (f.file) { + ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, + upeer_addrlen, flags); + if (f.flags) + fput(f.file); + } + + return ret; } SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, diff --git a/net/tipc/core.c b/net/tipc/core.c index 23cb379a93d6..8f35060a24e1 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -34,8 +34,6 @@ * POSSIBILITY OF SUCH DAMAGE. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include "core.h" #include "name_table.h" #include "subscr.h" diff --git a/net/tipc/core.h b/net/tipc/core.h index 60d829581068..3042f654e0af 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -60,6 +60,12 @@ #include <linux/rhashtable.h> #include <net/genetlink.h> +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + struct tipc_node; struct tipc_bearer; struct tipc_bc_base; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index f959487c5cd1..683d00837693 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -523,8 +523,10 @@ last_record: int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; + struct tls_context *tls_ctx = tls_get_ctx(sk); int rc; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (unlikely(msg->msg_controllen)) { @@ -538,12 +540,14 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; char *kaddr = kmap(page); struct kvec iov; @@ -552,6 +556,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, if (flags & MSG_SENDPAGE_NOTLAST) flags |= MSG_MORE; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (flags & MSG_OOB) { @@ -568,6 +573,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } @@ -623,9 +629,11 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) void tls_device_write_space(struct sock *sk, struct tls_context *ctx) { - if (!sk->sk_write_pending && tls_is_partially_sent_record(ctx)) { + if (tls_is_partially_sent_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; + WARN_ON_ONCE(sk->sk_write_pending); + sk->sk_allocation = GFP_ATOMIC; tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL | diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index ac88877dcade..f874cc0da45d 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -267,6 +267,7 @@ void tls_ctx_free(struct sock *sk, struct tls_context *ctx) memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + mutex_destroy(&ctx->tx_lock); if (sk) kfree_rcu(ctx, rcu); @@ -612,6 +613,7 @@ static struct tls_context *create_ctx(struct sock *sk) if (!ctx) return NULL; + mutex_init(&ctx->tx_lock); rcu_assign_pointer(icsk->icsk_ulp_data, ctx); ctx->sk_proto = sk->sk_prot; return ctx; @@ -906,6 +908,7 @@ static int __init tls_register(void) { tls_sw_proto_ops = inet_stream_ops; tls_sw_proto_ops.splice_read = tls_sw_splice_read; + tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked, tls_device_init(); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index c2b5e0d2ba1a..319735d5c084 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -897,15 +897,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) return -ENOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto send_end; - } - if (unlikely(msg->msg_controllen)) { ret = tls_proccess_cmsg(sk, msg, &record_type); if (ret) { @@ -1091,6 +1085,7 @@ send_end: ret = sk_stream_error(sk, msg->msg_flags, ret); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return copied ? copied : ret; } @@ -1114,13 +1109,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto sendpage_end; - } - /* Call the sk_stream functions to manage the sndbuf mem. */ while (size > 0) { size_t copy, required_size; @@ -1216,18 +1204,32 @@ sendpage_end: return copied ? copied : ret; } +int tls_sw_sendpage_locked(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY | + MSG_NO_SHARED_FRAGS)) + return -ENOTSUPP; + + return tls_sw_do_sendpage(sk, page, offset, size, flags); +} + int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); int ret; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) return -ENOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); ret = tls_sw_do_sendpage(sk, page, offset, size, flags); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return ret; } @@ -2170,9 +2172,11 @@ static void tx_work_handler(struct work_struct *work) if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) return; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); } void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) @@ -2180,12 +2184,9 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx); /* Schedule the transmission if tx list is ready */ - if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) { - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, - &tx_ctx->tx_bitmask)) - schedule_delayed_work(&tx_ctx->tx_work.work, 0); - } + if (is_tx_ready(tx_ctx) && + !test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) + schedule_delayed_work(&tx_ctx->tx_work.work, 0); } void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 481f7f8a1655..fb2060dffb0a 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -947,9 +947,11 @@ virtio_transport_recv_connected(struct sock *sk, if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) vsk->peer_shutdown |= SEND_SHUTDOWN; if (vsk->peer_shutdown == SHUTDOWN_MASK && - vsock_stream_has_data(vsk) <= 0) { - sock_set_flag(sk, SOCK_DONE); - sk->sk_state = TCP_CLOSING; + vsock_stream_has_data(vsk) <= 0 && + !sock_flag(sk, SOCK_DONE)) { + (void)virtio_transport_reset(vsk, NULL); + + virtio_transport_do_close(vsk, true); } if (le32_to_cpu(pkt->hdr.flags)) sk->sk_state_change(sk); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 9b599ed66d97..2c86a2fc3915 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -480,6 +480,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); + + if (encap_type == -1) + dev_put(skb->dev); goto drop; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index c6f3c4a1bd99..f3423562d933 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -495,6 +495,8 @@ static void ___xfrm_state_destroy(struct xfrm_state *x) x->type->destructor(x); xfrm_put_type(x->type); } + if (x->xfrag.page) + put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 1d9be26b4edd..42b571cde177 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -176,6 +176,7 @@ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf +KBUILD_HOSTCFLAGS += -DHAVE_ATTR_TEST=0 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable diff --git a/scripts/nsdeps b/scripts/nsdeps index dda6fbac016e..04cea0921673 100644 --- a/scripts/nsdeps +++ b/scripts/nsdeps @@ -31,12 +31,12 @@ generate_deps() { local mod_file=`echo $@ | sed -e 's/\.ko/\.mod/'` local ns_deps_file=`echo $@ | sed -e 's/\.ko/\.ns_deps/'` if [ ! -f "$ns_deps_file" ]; then return; fi - local mod_source_files=`cat $mod_file | sed -n 1p \ + local mod_source_files="`cat $mod_file | sed -n 1p \ | sed -e 's/\.o/\.c/g' \ - | sed "s|[^ ]* *|${srctree}/&|g"` + | sed "s|[^ ]* *|${srctree}/&|g"`" for ns in `cat $ns_deps_file`; do echo "Adding namespace $ns to module $mod_name (if needed)." - generate_deps_for_ns $ns $mod_source_files + generate_deps_for_ns $ns "$mod_source_files" # sort the imports for source_file in $mod_source_files; do sed '/MODULE_IMPORT_NS/Q' $source_file > ${source_file}.tmp diff --git a/scripts/tools-support-relr.sh b/scripts/tools-support-relr.sh index 97a2c844a95e..45e8aa360b45 100755 --- a/scripts/tools-support-relr.sh +++ b/scripts/tools-support-relr.sh @@ -4,13 +4,13 @@ tmp_file=$(mktemp) trap "rm -f $tmp_file.o $tmp_file $tmp_file.bin" EXIT -cat << "END" | "$CC" -c -x c - -o $tmp_file.o >/dev/null 2>&1 +cat << "END" | $CC -c -x c - -o $tmp_file.o >/dev/null 2>&1 void *p = &p; END -"$LD" $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr -o $tmp_file +$LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr -o $tmp_file # Despite printing an error message, GNU nm still exits with exit code 0 if it # sees a relr section. So we need to check that nothing is printed to stderr. -test -z "$("$NM" $tmp_file 2>&1 >/dev/null)" +test -z "$($NM $tmp_file 2>&1 >/dev/null)" -"$OBJCOPY" -O binary $tmp_file $tmp_file.bin +$OBJCOPY -O binary $tmp_file $tmp_file.bin diff --git a/security/keys/Makefile b/security/keys/Makefile index 9cef54064f60..074f27538f55 100644 --- a/security/keys/Makefile +++ b/security/keys/Makefile @@ -28,5 +28,5 @@ obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += keyctl_pkey.o # Key types # obj-$(CONFIG_BIG_KEYS) += big_key.o -obj-$(CONFIG_TRUSTED_KEYS) += trusted.o +obj-$(CONFIG_TRUSTED_KEYS) += trusted-keys/ obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/ diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile new file mode 100644 index 000000000000..7b73cebbb378 --- /dev/null +++ b/security/keys/trusted-keys/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for trusted keys +# + +obj-$(CONFIG_TRUSTED_KEYS) += trusted.o +trusted-y += trusted_tpm1.o +trusted-y += trusted_tpm2.o diff --git a/security/keys/trusted.c b/security/keys/trusted-keys/trusted_tpm1.c index 1fbd77816610..d2c5ec1e040b 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -27,7 +27,7 @@ #include <linux/tpm.h> #include <linux/tpm_command.h> -#include <keys/trusted.h> +#include <keys/trusted_tpm.h> static const char hmac_alg[] = "hmac(sha1)"; static const char hash_alg[] = "sha1"; @@ -406,13 +406,10 @@ static int osap(struct tpm_buf *tb, struct osapsess *s, if (ret != TPM_NONCE_SIZE) return ret; - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_COMMAND); - store32(tb, TPM_OSAP_SIZE); - store32(tb, TPM_ORD_OSAP); - store16(tb, type); - store32(tb, handle); - storebytes(tb, ononce, TPM_NONCE_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OSAP); + tpm_buf_append_u16(tb, type); + tpm_buf_append_u32(tb, handle); + tpm_buf_append(tb, ononce, TPM_NONCE_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) @@ -437,10 +434,7 @@ int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) if (!chip) return -ENODEV; - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_COMMAND); - store32(tb, TPM_OIAP_SIZE); - store32(tb, TPM_ORD_OIAP); + tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OIAP); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) return ret; @@ -535,20 +529,17 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype, goto out; /* build and send the TPM request packet */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_SEAL_SIZE + pcrinfosize + datalen); - store32(tb, TPM_ORD_SEAL); - store32(tb, keyhandle); - storebytes(tb, td->encauth, SHA1_DIGEST_SIZE); - store32(tb, pcrinfosize); - storebytes(tb, pcrinfo, pcrinfosize); - store32(tb, datalen); - storebytes(tb, data, datalen); - store32(tb, sess.handle); - storebytes(tb, td->nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, td->pubauth, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SEAL); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append(tb, td->encauth, SHA1_DIGEST_SIZE); + tpm_buf_append_u32(tb, pcrinfosize); + tpm_buf_append(tb, pcrinfo, pcrinfosize); + tpm_buf_append_u32(tb, datalen); + tpm_buf_append(tb, data, datalen); + tpm_buf_append_u32(tb, sess.handle); + tpm_buf_append(tb, td->nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, td->pubauth, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) @@ -594,7 +585,6 @@ static int tpm_unseal(struct tpm_buf *tb, uint32_t authhandle2 = 0; unsigned char cont = 0; uint32_t ordinal; - uint32_t keyhndl; int ret; /* sessions for unsealing key and data */ @@ -610,7 +600,6 @@ static int tpm_unseal(struct tpm_buf *tb, } ordinal = htonl(TPM_ORD_UNSEAL); - keyhndl = htonl(SRKHANDLE); ret = tpm_get_random(chip, nonceodd, TPM_NONCE_SIZE); if (ret != TPM_NONCE_SIZE) { pr_info("trusted_key: tpm_get_random failed (%d)\n", ret); @@ -628,20 +617,17 @@ static int tpm_unseal(struct tpm_buf *tb, return ret; /* build and send TPM request packet */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH2_COMMAND); - store32(tb, TPM_UNSEAL_SIZE + bloblen); - store32(tb, TPM_ORD_UNSEAL); - store32(tb, keyhandle); - storebytes(tb, blob, bloblen); - store32(tb, authhandle1); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata1, SHA1_DIGEST_SIZE); - store32(tb, authhandle2); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata2, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH2_COMMAND, TPM_ORD_UNSEAL); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append(tb, blob, bloblen); + tpm_buf_append_u32(tb, authhandle1); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata1, SHA1_DIGEST_SIZE); + tpm_buf_append_u32(tb, authhandle2); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata2, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -670,23 +656,23 @@ static int tpm_unseal(struct tpm_buf *tb, static int key_seal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf *tb; + struct tpm_buf tb; int ret; - tb = kzalloc(sizeof *tb, GFP_KERNEL); - if (!tb) - return -ENOMEM; + ret = tpm_buf_init(&tb, 0, 0); + if (ret) + return ret; /* include migratable flag at end of sealed key */ p->key[p->key_len] = p->migratable; - ret = tpm_seal(tb, o->keytype, o->keyhandle, o->keyauth, + ret = tpm_seal(&tb, o->keytype, o->keyhandle, o->keyauth, p->key, p->key_len + 1, p->blob, &p->blob_len, o->blobauth, o->pcrinfo, o->pcrinfo_len); if (ret < 0) pr_info("trusted_key: srkseal failed (%d)\n", ret); - kzfree(tb); + tpm_buf_destroy(&tb); return ret; } @@ -696,14 +682,14 @@ static int key_seal(struct trusted_key_payload *p, static int key_unseal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf *tb; + struct tpm_buf tb; int ret; - tb = kzalloc(sizeof *tb, GFP_KERNEL); - if (!tb) - return -ENOMEM; + ret = tpm_buf_init(&tb, 0, 0); + if (ret) + return ret; - ret = tpm_unseal(tb, o->keyhandle, o->keyauth, p->blob, p->blob_len, + ret = tpm_unseal(&tb, o->keyhandle, o->keyauth, p->blob, p->blob_len, o->blobauth, p->key, &p->key_len); if (ret < 0) pr_info("trusted_key: srkunseal failed (%d)\n", ret); @@ -711,7 +697,7 @@ static int key_unseal(struct trusted_key_payload *p, /* pull migratable flag out of sealed key */ p->migratable = p->key[--p->key_len]; - kzfree(tb); + tpm_buf_destroy(&tb); return ret; } @@ -1016,7 +1002,7 @@ static int trusted_instantiate(struct key *key, switch (key_cmd) { case Opt_load: if (tpm2) - ret = tpm_unseal_trusted(chip, payload, options); + ret = tpm2_unseal_trusted(chip, payload, options); else ret = key_unseal(payload, options); dump_payload(payload); @@ -1032,7 +1018,7 @@ static int trusted_instantiate(struct key *key, goto out; } if (tpm2) - ret = tpm_seal_trusted(chip, payload, options); + ret = tpm2_seal_trusted(chip, payload, options); else ret = key_seal(payload, options); if (ret < 0) diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c new file mode 100644 index 000000000000..a9810ac2776f --- /dev/null +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2004 IBM Corporation + * Copyright (C) 2014 Intel Corporation + */ + +#include <linux/string.h> +#include <linux/err.h> +#include <linux/tpm.h> +#include <linux/tpm_command.h> + +#include <keys/trusted-type.h> +#include <keys/trusted_tpm.h> + +static struct tpm2_hash tpm2_hash_map[] = { + {HASH_ALGO_SHA1, TPM_ALG_SHA1}, + {HASH_ALGO_SHA256, TPM_ALG_SHA256}, + {HASH_ALGO_SHA384, TPM_ALG_SHA384}, + {HASH_ALGO_SHA512, TPM_ALG_SHA512}, + {HASH_ALGO_SM3_256, TPM_ALG_SM3_256}, +}; + +/** + * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. + * + * @buf: an allocated tpm_buf instance + * @session_handle: session handle + * @nonce: the session nonce, may be NULL if not used + * @nonce_len: the session nonce length, may be 0 if not used + * @attributes: the session attributes + * @hmac: the session HMAC or password, may be NULL if not used + * @hmac_len: the session HMAC or password length, maybe 0 if not used + */ +static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle, + const u8 *nonce, u16 nonce_len, + u8 attributes, + const u8 *hmac, u16 hmac_len) +{ + tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len); + tpm_buf_append_u32(buf, session_handle); + tpm_buf_append_u16(buf, nonce_len); + + if (nonce && nonce_len) + tpm_buf_append(buf, nonce, nonce_len); + + tpm_buf_append_u8(buf, attributes); + tpm_buf_append_u16(buf, hmac_len); + + if (hmac && hmac_len) + tpm_buf_append(buf, hmac, hmac_len); +} + +/** + * tpm2_seal_trusted() - seal the payload of a trusted key + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * + * Return: < 0 on error and 0 on success. + */ +int tpm2_seal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + unsigned int blob_len; + struct tpm_buf buf; + u32 hash; + int i; + int rc; + + for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) { + if (options->hash == tpm2_hash_map[i].crypto_id) { + hash = tpm2_hash_map[i].tpm_id; + break; + } + } + + if (i == ARRAY_SIZE(tpm2_hash_map)) + return -EINVAL; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, options->keyhandle); + tpm2_buf_append_auth(&buf, TPM2_RS_PW, + NULL /* nonce */, 0, + 0 /* session_attributes */, + options->keyauth /* hmac */, + TPM_DIGEST_SIZE); + + /* sensitive */ + tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); + + tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); + tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); + tpm_buf_append_u16(&buf, payload->key_len + 1); + tpm_buf_append(&buf, payload->key, payload->key_len); + tpm_buf_append_u8(&buf, payload->migratable); + + /* public */ + tpm_buf_append_u16(&buf, 14 + options->policydigest_len); + tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH); + tpm_buf_append_u16(&buf, hash); + + /* policy */ + if (options->policydigest_len) { + tpm_buf_append_u32(&buf, 0); + tpm_buf_append_u16(&buf, options->policydigest_len); + tpm_buf_append(&buf, options->policydigest, + options->policydigest_len); + } else { + tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH); + tpm_buf_append_u16(&buf, 0); + } + + /* public parameters */ + tpm_buf_append_u16(&buf, TPM_ALG_NULL); + tpm_buf_append_u16(&buf, 0); + + /* outside info */ + tpm_buf_append_u16(&buf, 0); + + /* creation PCR */ + tpm_buf_append_u32(&buf, 0); + + if (buf.flags & TPM_BUF_OVERFLOW) { + rc = -E2BIG; + goto out; + } + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (rc) + goto out; + + blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]); + if (blob_len > MAX_BLOB_SIZE) { + rc = -E2BIG; + goto out; + } + if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) { + rc = -EFAULT; + goto out; + } + + memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len); + payload->blob_len = blob_len; + +out: + tpm_buf_destroy(&buf); + + if (rc > 0) { + if (tpm2_rc_value(rc) == TPM2_RC_HASH) + rc = -EINVAL; + else + rc = -EPERM; + } + + return rc; +} + +/** + * tpm2_load_cmd() - execute a TPM2_Load command + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * @blob_handle: returned blob handle + * + * Return: 0 on success. + * -E2BIG on wrong payload size. + * -EPERM on tpm error status. + * < 0 error from tpm_send. + */ +static int tpm2_load_cmd(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options, + u32 *blob_handle) +{ + struct tpm_buf buf; + unsigned int private_len; + unsigned int public_len; + unsigned int blob_len; + int rc; + + private_len = be16_to_cpup((__be16 *) &payload->blob[0]); + if (private_len > (payload->blob_len - 2)) + return -E2BIG; + + public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]); + blob_len = private_len + public_len + 4; + if (blob_len > payload->blob_len) + return -E2BIG; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, options->keyhandle); + tpm2_buf_append_auth(&buf, TPM2_RS_PW, + NULL /* nonce */, 0, + 0 /* session_attributes */, + options->keyauth /* hmac */, + TPM_DIGEST_SIZE); + + tpm_buf_append(&buf, payload->blob, blob_len); + + if (buf.flags & TPM_BUF_OVERFLOW) { + rc = -E2BIG; + goto out; + } + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (!rc) + *blob_handle = be32_to_cpup( + (__be32 *) &buf.data[TPM_HEADER_SIZE]); + +out: + tpm_buf_destroy(&buf); + + if (rc > 0) + rc = -EPERM; + + return rc; +} + +/** + * tpm2_unseal_cmd() - execute a TPM2_Unload command + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * @blob_handle: blob handle + * + * Return: 0 on success + * -EPERM on tpm error status + * < 0 error from tpm_send + */ +static int tpm2_unseal_cmd(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options, + u32 blob_handle) +{ + struct tpm_buf buf; + u16 data_len; + u8 *data; + int rc; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, blob_handle); + tpm2_buf_append_auth(&buf, + options->policyhandle ? + options->policyhandle : TPM2_RS_PW, + NULL /* nonce */, 0, + TPM2_SA_CONTINUE_SESSION, + options->blobauth /* hmac */, + TPM_DIGEST_SIZE); + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (rc > 0) + rc = -EPERM; + + if (!rc) { + data_len = be16_to_cpup( + (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); + if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { + rc = -EFAULT; + goto out; + } + + if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) { + rc = -EFAULT; + goto out; + } + data = &buf.data[TPM_HEADER_SIZE + 6]; + + memcpy(payload->key, data, data_len - 1); + payload->key_len = data_len - 1; + payload->migratable = data[data_len - 1]; + } + +out: + tpm_buf_destroy(&buf); + return rc; +} + +/** + * tpm2_unseal_trusted() - unseal the payload of a trusted key + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * + * Return: Same as with tpm_send. + */ +int tpm2_unseal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + u32 blob_handle; + int rc; + + rc = tpm2_load_cmd(chip, payload, options, &blob_handle); + if (rc) + return rc; + + rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); + + return rc; +} diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 41905afada63..f34ce564d92c 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -528,7 +528,7 @@ static int snd_compress_check_input(struct snd_compr_params *params) { /* first let's check the buffer parameter's */ if (params->buffer.fragment_size == 0 || - params->buffer.fragments > INT_MAX / params->buffer.fragment_size || + params->buffer.fragments > U32_MAX / params->buffer.fragment_size || params->buffer.fragments == 0) return -EINVAL; diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index d80041ea4e01..2236b5e0c1f2 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1782,11 +1782,14 @@ void snd_pcm_period_elapsed(struct snd_pcm_substream *substream) struct snd_pcm_runtime *runtime; unsigned long flags; - if (PCM_RUNTIME_CHECK(substream)) + if (snd_BUG_ON(!substream)) return; - runtime = substream->runtime; snd_pcm_stream_lock_irqsave(substream, flags); + if (PCM_RUNTIME_CHECK(substream)) + goto _unlock; + runtime = substream->runtime; + if (!snd_pcm_running(substream) || snd_pcm_update_hw_ptr0(substream, 1) < 0) goto _end; @@ -1797,6 +1800,7 @@ void snd_pcm_period_elapsed(struct snd_pcm_substream *substream) #endif _end: kill_fasync(&runtime->fasync, SIGIO, POLL_IN); + _unlock: snd_pcm_stream_unlock_irqrestore(substream, flags); } EXPORT_SYMBOL(snd_pcm_period_elapsed); diff --git a/sound/core/timer.c b/sound/core/timer.c index 6b724d2ee2de..59ae21b0bb93 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -284,11 +284,11 @@ int snd_timer_open(struct snd_timer_instance **ti, goto unlock; } if (!list_empty(&timer->open_list_head)) { - timeri = list_entry(timer->open_list_head.next, + struct snd_timer_instance *t = + list_entry(timer->open_list_head.next, struct snd_timer_instance, open_list); - if (timeri->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { + if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { err = -EBUSY; - timeri = NULL; goto unlock; } } diff --git a/sound/firewire/bebob/bebob_focusrite.c b/sound/firewire/bebob/bebob_focusrite.c index 32b864bee25f..06d6a37cd853 100644 --- a/sound/firewire/bebob/bebob_focusrite.c +++ b/sound/firewire/bebob/bebob_focusrite.c @@ -27,6 +27,8 @@ #define SAFFIRE_CLOCK_SOURCE_SPDIF 1 /* clock sources as returned from register of Saffire Pro 10 and 26 */ +#define SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK 0x000000ff +#define SAFFIREPRO_CLOCK_SOURCE_DETECT_MASK 0x0000ff00 #define SAFFIREPRO_CLOCK_SOURCE_INTERNAL 0 #define SAFFIREPRO_CLOCK_SOURCE_SKIP 1 /* never used on hardware */ #define SAFFIREPRO_CLOCK_SOURCE_SPDIF 2 @@ -189,6 +191,7 @@ saffirepro_both_clk_src_get(struct snd_bebob *bebob, unsigned int *id) map = saffirepro_clk_maps[1]; /* In a case that this driver cannot handle the value of register. */ + value &= SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK; if (value >= SAFFIREPRO_CLOCK_SOURCE_COUNT || map[value] < 0) { err = -EIO; goto end; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index cf53fbd872ee..c52419376c74 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2396,6 +2396,9 @@ static const struct pci_device_id azx_ids[] = { /* CometLake-H */ { PCI_DEVICE(0x8086, 0x06C8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* CometLake-S */ + { PCI_DEVICE(0x8086, 0xa3f0), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Icelake */ { PCI_DEVICE(0x8086, 0x34c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 6d1fb7c11f17..b7a1abb3e231 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -7604,7 +7604,7 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work_sync(&spec->unsol_hp_work); + cancel_delayed_work(&spec->unsol_hp_work); schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index b72553710ffb..78bd2e3722c7 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -46,10 +46,12 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); ((codec)->core.vendor_id == 0x80862800)) #define is_cannonlake(codec) ((codec)->core.vendor_id == 0x8086280c) #define is_icelake(codec) ((codec)->core.vendor_id == 0x8086280f) +#define is_tigerlake(codec) ((codec)->core.vendor_id == 0x80862812) #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \ || is_skylake(codec) || is_broxton(codec) \ || is_kabylake(codec) || is_geminilake(codec) \ - || is_cannonlake(codec) || is_icelake(codec)) + || is_cannonlake(codec) || is_icelake(codec) \ + || is_tigerlake(codec)) #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882) #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883) #define is_valleyview_plus(codec) (is_valleyview(codec) || is_cherryview(codec)) @@ -2851,6 +2853,18 @@ static int patch_i915_icl_hdmi(struct hda_codec *codec) return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map)); } +static int patch_i915_tgl_hdmi(struct hda_codec *codec) +{ + /* + * pin to port mapping table where the value indicate the pin number and + * the index indicate the port number with 1 base. + */ + static const int map[] = {0x4, 0x6, 0x8, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf}; + + return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map)); +} + + /* Intel Baytrail and Braswell; with eld notifier */ static int patch_i915_byt_hdmi(struct hda_codec *codec) { @@ -4153,6 +4167,7 @@ HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), +HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index 91242b6f8ea7..4570f662fb48 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -410,8 +410,8 @@ static void hdac_hda_codec_remove(struct snd_soc_component *component) return; } - snd_hdac_ext_bus_link_put(hdev->bus, hlink); pm_runtime_disable(&hdev->dev); + snd_hdac_ext_bus_link_put(hdev->bus, hlink); } static const struct snd_soc_dapm_route hdac_hda_dapm_routes[] = { diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index b5fd8f08726e..f8b5b960e597 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -274,7 +274,7 @@ struct hdmi_codec_priv { uint8_t eld[MAX_ELD_BYTES]; struct snd_pcm_chmap *chmap_info; unsigned int chmap_idx; - struct mutex lock; + unsigned long busy; struct snd_soc_jack *jack; unsigned int jack_status; }; @@ -390,8 +390,8 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream, struct hdmi_codec_priv *hcp = snd_soc_dai_get_drvdata(dai); int ret = 0; - ret = mutex_trylock(&hcp->lock); - if (!ret) { + ret = test_and_set_bit(0, &hcp->busy); + if (ret) { dev_err(dai->dev, "Only one simultaneous stream supported!\n"); return -EINVAL; } @@ -419,7 +419,7 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream, err: /* Release the exclusive lock on error */ - mutex_unlock(&hcp->lock); + clear_bit(0, &hcp->busy); return ret; } @@ -431,7 +431,7 @@ static void hdmi_codec_shutdown(struct snd_pcm_substream *substream, hcp->chmap_idx = HDMI_CODEC_CHMAP_IDX_UNKNOWN; hcp->hcd.ops->audio_shutdown(dai->dev->parent, hcp->hcd.data); - mutex_unlock(&hcp->lock); + clear_bit(0, &hcp->busy); } static int hdmi_codec_hw_params(struct snd_pcm_substream *substream, @@ -811,8 +811,6 @@ static int hdmi_codec_probe(struct platform_device *pdev) return -ENOMEM; hcp->hcd = *hcd; - mutex_init(&hcp->lock); - daidrv = devm_kcalloc(dev, dai_count, sizeof(*daidrv), GFP_KERNEL); if (!daidrv) return -ENOMEM; diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c index eb709d528259..cae1def8902d 100644 --- a/sound/soc/codecs/max98373.c +++ b/sound/soc/codecs/max98373.c @@ -960,11 +960,11 @@ static int max98373_i2c_probe(struct i2c_client *i2c, /* Power on device */ if (gpio_is_valid(max98373->reset_gpio)) { - ret = gpio_request(max98373->reset_gpio, "MAX98373_RESET"); + ret = devm_gpio_request(&i2c->dev, max98373->reset_gpio, + "MAX98373_RESET"); if (ret) { dev_err(&i2c->dev, "%s: Failed to request gpio %d\n", __func__, max98373->reset_gpio); - gpio_free(max98373->reset_gpio); return -EINVAL; } gpio_direction_output(max98373->reset_gpio, 0); diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c index 667e9f73aba3..e3d311fb510e 100644 --- a/sound/soc/codecs/msm8916-wcd-analog.c +++ b/sound/soc/codecs/msm8916-wcd-analog.c @@ -306,7 +306,7 @@ struct pm8916_wcd_analog_priv { }; static const char *const adc2_mux_text[] = { "ZERO", "INP2", "INP3" }; -static const char *const rdac2_mux_text[] = { "ZERO", "RX2", "RX1" }; +static const char *const rdac2_mux_text[] = { "RX1", "RX2" }; static const char *const hph_text[] = { "ZERO", "Switch", }; static const struct soc_enum hph_enum = SOC_ENUM_SINGLE_VIRT( @@ -321,7 +321,7 @@ static const struct soc_enum adc2_enum = SOC_ENUM_SINGLE_VIRT( /* RDAC2 MUX */ static const struct soc_enum rdac2_mux_enum = SOC_ENUM_SINGLE( - CDC_D_CDC_CONN_HPHR_DAC_CTL, 0, 3, rdac2_mux_text); + CDC_D_CDC_CONN_HPHR_DAC_CTL, 0, 2, rdac2_mux_text); static const struct snd_kcontrol_new spkr_switch[] = { SOC_DAPM_SINGLE("Switch", CDC_A_SPKR_DAC_CTL, 7, 1, 0) diff --git a/sound/soc/kirkwood/kirkwood-i2s.c b/sound/soc/kirkwood/kirkwood-i2s.c index 61226fefe1c4..2a4ffe945177 100644 --- a/sound/soc/kirkwood/kirkwood-i2s.c +++ b/sound/soc/kirkwood/kirkwood-i2s.c @@ -555,10 +555,6 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev) return PTR_ERR(priv->clk); } - err = clk_prepare_enable(priv->clk); - if (err < 0) - return err; - priv->extclk = devm_clk_get(&pdev->dev, "extclk"); if (IS_ERR(priv->extclk)) { if (PTR_ERR(priv->extclk) == -EPROBE_DEFER) @@ -574,6 +570,10 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev) } } + err = clk_prepare_enable(priv->clk); + if (err < 0) + return err; + /* Some sensible defaults - this reflects the powerup values */ priv->ctl_play = KIRKWOOD_PLAYCTL_SIZE_24; priv->ctl_rec = KIRKWOOD_RECCTL_SIZE_24; @@ -587,7 +587,7 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev) priv->ctl_rec |= KIRKWOOD_RECCTL_BURST_128; } - err = devm_snd_soc_register_component(&pdev->dev, &kirkwood_soc_component, + err = snd_soc_register_component(&pdev->dev, &kirkwood_soc_component, soc_dai, 2); if (err) { dev_err(&pdev->dev, "snd_soc_register_component failed\n"); @@ -610,6 +610,7 @@ static int kirkwood_i2s_dev_remove(struct platform_device *pdev) { struct kirkwood_dma_data *priv = dev_get_drvdata(&pdev->dev); + snd_soc_unregister_component(&pdev->dev); if (!IS_ERR(priv->extclk)) clk_disable_unprepare(priv->extclk); clk_disable_unprepare(priv->clk); diff --git a/sound/soc/rockchip/rockchip_max98090.c b/sound/soc/rockchip/rockchip_max98090.c index 0097df1fae66..e80b09143b63 100644 --- a/sound/soc/rockchip/rockchip_max98090.c +++ b/sound/soc/rockchip/rockchip_max98090.c @@ -66,10 +66,13 @@ static int rk_jack_event(struct notifier_block *nb, unsigned long event, struct snd_soc_jack *jack = (struct snd_soc_jack *)data; struct snd_soc_dapm_context *dapm = &jack->card->dapm; - if (event & SND_JACK_MICROPHONE) + if (event & SND_JACK_MICROPHONE) { snd_soc_dapm_force_enable_pin(dapm, "MICBIAS"); - else + snd_soc_dapm_force_enable_pin(dapm, "SHDN"); + } else { snd_soc_dapm_disable_pin(dapm, "MICBIAS"); + snd_soc_dapm_disable_pin(dapm, "SHDN"); + } snd_soc_dapm_sync(dapm); diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index 0324a5c39619..28f65eba2bb4 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -508,10 +508,10 @@ static struct rsnd_mod_ops rsnd_dmapp_ops = { #define RDMA_SSI_I_N(addr, i) (addr ##_reg - 0x00300000 + (0x40 * i) + 0x8) #define RDMA_SSI_O_N(addr, i) (addr ##_reg - 0x00300000 + (0x40 * i) + 0xc) -#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400)) +#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4))) #define RDMA_SSIU_O_N(addr, i, j) RDMA_SSIU_I_N(addr, i, j) -#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400)) +#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4))) #define RDMA_SSIU_O_P(addr, i, j) RDMA_SSIU_I_P(addr, i, j) #define RDMA_SRC_I_N(addr, i) (addr ##_reg - 0x00500000 + (0x400 * i)) diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index 54cd431faab7..5529e8eeca46 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -152,8 +152,10 @@ static ssize_t sof_dfsentry_write(struct file *file, const char __user *buffer, */ dentry = file->f_path.dentry; if (strcmp(dentry->d_name.name, "ipc_flood_count") && - strcmp(dentry->d_name.name, "ipc_flood_duration_ms")) - return -EINVAL; + strcmp(dentry->d_name.name, "ipc_flood_duration_ms")) { + ret = -EINVAL; + goto out; + } if (!strcmp(dentry->d_name.name, "ipc_flood_duration_ms")) flood_duration_test = true; diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index 2c7447188402..0c11fceb28a7 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -190,7 +190,7 @@ hda_dsp_stream_get(struct snd_sof_dev *sdev, int direction) * Workaround to address a known issue with host DMA that results * in xruns during pause/release in capture scenarios. */ - if (!IS_ENABLED(SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1)) + if (!IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1)) if (stream && direction == SNDRV_PCM_STREAM_CAPTURE) snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, HDA_VS_INTEL_EM2, @@ -228,7 +228,7 @@ int hda_dsp_stream_put(struct snd_sof_dev *sdev, int direction, int stream_tag) spin_unlock_irq(&bus->reg_lock); /* Enable DMI L1 entry if there are no capture streams open */ - if (!IS_ENABLED(SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1)) + if (!IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1)) if (!active_capture_stream) snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, HDA_VS_INTEL_EM2, diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c index b2f359d2f7e5..086eeeab8679 100644 --- a/sound/soc/sof/ipc.c +++ b/sound/soc/sof/ipc.c @@ -572,8 +572,10 @@ static int sof_set_get_large_ctrl_data(struct snd_sof_dev *sdev, else err = sof_get_ctrl_copy_params(cdata->type, partdata, cdata, sparams); - if (err < 0) + if (err < 0) { + kfree(partdata); return err; + } msg_bytes = sparams->msg_bytes; pl_size = sparams->pl_size; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 0aabb3190ddc..4452594c2e17 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -543,15 +543,16 @@ static int sof_control_load_bytes(struct snd_soc_component *scomp, struct soc_bytes_ext *sbe = (struct soc_bytes_ext *)kc->private_value; int max_size = sbe->max; - if (le32_to_cpu(control->priv.size) > max_size) { + /* init the get/put bytes data */ + scontrol->size = sizeof(struct sof_ipc_ctrl_data) + + le32_to_cpu(control->priv.size); + + if (scontrol->size > max_size) { dev_err(sdev->dev, "err: bytes data size %d exceeds max %d.\n", - control->priv.size, max_size); + scontrol->size, max_size); return -EINVAL; } - /* init the get/put bytes data */ - scontrol->size = sizeof(struct sof_ipc_ctrl_data) + - le32_to_cpu(control->priv.size); scontrol->control_data = kzalloc(max_size, GFP_KERNEL); cdata = scontrol->control_data; if (!scontrol->control_data) diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index a4060813bc74..48e629ac2d88 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -1218,6 +1218,16 @@ static int stm32_sai_pcm_process_spdif(struct snd_pcm_substream *substream, return 0; } +/* No support of mmap in S/PDIF mode */ +static const struct snd_pcm_hardware stm32_sai_pcm_hw_spdif = { + .info = SNDRV_PCM_INFO_INTERLEAVED, + .buffer_bytes_max = 8 * PAGE_SIZE, + .period_bytes_min = 1024, + .period_bytes_max = PAGE_SIZE, + .periods_min = 2, + .periods_max = 8, +}; + static const struct snd_pcm_hardware stm32_sai_pcm_hw = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP, .buffer_bytes_max = 8 * PAGE_SIZE, @@ -1270,7 +1280,7 @@ static const struct snd_dmaengine_pcm_config stm32_sai_pcm_config = { }; static const struct snd_dmaengine_pcm_config stm32_sai_pcm_config_spdif = { - .pcm_hardware = &stm32_sai_pcm_hw, + .pcm_hardware = &stm32_sai_pcm_hw_spdif, .prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config, .process = stm32_sai_pcm_process_spdif, }; diff --git a/sound/soc/ti/sdma-pcm.c b/sound/soc/ti/sdma-pcm.c index a236350beb10..2b0bc234e1b6 100644 --- a/sound/soc/ti/sdma-pcm.c +++ b/sound/soc/ti/sdma-pcm.c @@ -62,7 +62,7 @@ int sdma_pcm_platform_register(struct device *dev, config->chan_names[0] = txdmachan; config->chan_names[1] = rxdmachan; - return devm_snd_dmaengine_pcm_register(dev, config, 0); + return devm_snd_dmaengine_pcm_register(dev, config, flags); } EXPORT_SYMBOL_GPL(sdma_pcm_platform_register); diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index a2ab8e8d3a93..4a9a2f6ef5a4 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -388,6 +388,9 @@ static void snd_complete_urb(struct urb *urb) } prepare_outbound_urb(ep, ctx); + /* can be stopped during prepare callback */ + if (unlikely(!test_bit(EP_FLAG_RUNNING, &ep->flags))) + goto exit_clear; } else { retire_inbound_urb(ep, ctx); /* can be stopped during retire callback */ diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 3fd1d1749edf..45eee5cc312e 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1229,7 +1229,8 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, if (cval->min + cval->res < cval->max) { int last_valid_res = cval->res; int saved, test, check; - get_cur_mix_raw(cval, minchn, &saved); + if (get_cur_mix_raw(cval, minchn, &saved) < 0) + goto no_res_check; for (;;) { test = saved; if (test < cval->max) @@ -1249,6 +1250,7 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, snd_usb_set_cur_mix_value(cval, minchn, 0, saved); } +no_res_check: cval->initialized = 1; } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 0bbe1201a6ac..349e1e52996d 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -248,8 +248,8 @@ static int create_yamaha_midi_quirk(struct snd_usb_audio *chip, NULL, USB_MS_MIDI_OUT_JACK); if (!injd && !outjd) return -ENODEV; - if (!(injd && snd_usb_validate_midi_desc(injd)) || - !(outjd && snd_usb_validate_midi_desc(outjd))) + if ((injd && !snd_usb_validate_midi_desc(injd)) || + (outjd && !snd_usb_validate_midi_desc(outjd))) return -ENODEV; if (injd && (injd->bLength < 5 || (injd->bJackType != USB_MS_EMBEDDED && diff --git a/sound/usb/validate.c b/sound/usb/validate.c index a5e584b60dcd..389e8657434a 100644 --- a/sound/usb/validate.c +++ b/sound/usb/validate.c @@ -81,9 +81,9 @@ static bool validate_processing_unit(const void *p, switch (v->protocol) { case UAC_VERSION_1: default: - /* bNrChannels, wChannelConfig, iChannelNames, bControlSize */ - len += 1 + 2 + 1 + 1; - if (d->bLength < len) /* bControlSize */ + /* bNrChannels, wChannelConfig, iChannelNames */ + len += 1 + 2 + 1; + if (d->bLength < len + 1) /* bControlSize */ return false; m = hdr[len]; len += 1 + m + 1; /* bControlSize, bmControls, iProcessing */ diff --git a/tools/gpio/Build b/tools/gpio/Build index 620c1937d957..4141f35837db 100644 --- a/tools/gpio/Build +++ b/tools/gpio/Build @@ -1,3 +1,4 @@ +gpio-utils-y += gpio-utils.o lsgpio-y += lsgpio.o gpio-utils.o gpio-hammer-y += gpio-hammer.o gpio-utils.o gpio-event-mon-y += gpio-event-mon.o gpio-utils.o diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index 1178d302757e..6080de58861f 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -35,11 +35,15 @@ $(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h prepare: $(OUTPUT)include/linux/gpio.h +GPIO_UTILS_IN := $(output)gpio-utils-in.o +$(GPIO_UTILS_IN): prepare FORCE + $(Q)$(MAKE) $(build)=gpio-utils + # # lsgpio # LSGPIO_IN := $(OUTPUT)lsgpio-in.o -$(LSGPIO_IN): prepare FORCE +$(LSGPIO_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=lsgpio $(OUTPUT)lsgpio: $(LSGPIO_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ @@ -48,7 +52,7 @@ $(OUTPUT)lsgpio: $(LSGPIO_IN) # gpio-hammer # GPIO_HAMMER_IN := $(OUTPUT)gpio-hammer-in.o -$(GPIO_HAMMER_IN): prepare FORCE +$(GPIO_HAMMER_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=gpio-hammer $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ @@ -57,7 +61,7 @@ $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN) # gpio-event-mon # GPIO_EVENT_MON_IN := $(OUTPUT)gpio-event-mon-in.o -$(GPIO_EVENT_MON_IN): prepare FORCE +$(GPIO_EVENT_MON_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=gpio-event-mon $(OUTPUT)gpio-event-mon: $(GPIO_EVENT_MON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 1d338357df8a..1f97b33c840e 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -58,7 +58,7 @@ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be * used to clear any hints previously set. */ -#define RWF_WRITE_LIFE_NOT_SET 0 +#define RWH_WRITE_LIFE_NOT_SET 0 #define RWH_WRITE_LIFE_NONE 1 #define RWH_WRITE_LIFE_SHORT 2 #define RWH_WRITE_LIFE_MEDIUM 3 @@ -66,6 +66,13 @@ #define RWH_WRITE_LIFE_EXTREME 5 /* + * The originally introduced spelling is remained from the first + * versions of the patch set that introduced the feature, see commit + * v4.13-rc1~212^2~51. + */ +#define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET + +/* * Types of directory notifications that may be requested. */ #define DN_ACCESS 0x00000001 /* File accessed */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 044c9a3cb247..543c068096b1 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -144,6 +144,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "usercopy_abort", "machine_real_restart", "rewind_stack_do_exit", + "kunit_try_catch_throw", }; if (!func) diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index 63e4349a772a..15e458e150bd 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -15,7 +15,9 @@ void test_attr__init(void); void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, int fd, int group_fd, unsigned long flags); -#define HAVE_ATTR_TEST +#ifndef HAVE_ATTR_TEST +#define HAVE_ATTR_TEST 1 +#endif static inline int sys_perf_event_open(struct perf_event_attr *attr, @@ -27,7 +29,7 @@ sys_perf_event_open(struct perf_event_attr *attr, fd = syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); -#ifdef HAVE_ATTR_TEST +#if HAVE_ATTR_TEST if (unlikely(test_attr__enabled)) test_attr__open(attr, pid, cpu, fd, group_fd, flags); #endif diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 679a1d75090c..7b6eaf5e0bda 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1625,7 +1625,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) +static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 15961854ba67..741f040648b5 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -539,10 +539,11 @@ static int perl_stop_script(void) static int perl_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.pl", outfile); @@ -603,8 +604,11 @@ sub print_backtrace\n\ }\n\n\ "); + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); - while ((event = trace_find_next_event(pevent, event))) { + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 5d341efc3237..93c03b39cd9c 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1687,10 +1687,11 @@ static int python_stop_script(void) static int python_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.py", outfile); @@ -1735,7 +1736,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint(\"in trace_end\")\n\n"); - while ((event = trace_find_next_event(pevent, event))) { + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); + + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 5d6bfc70b210..9634f0ae57be 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -173,37 +173,6 @@ int parse_event_file(struct tep_handle *pevent, return tep_parse_event(pevent, buf, size, sys); } -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event) -{ - static int idx; - int events_count; - struct tep_event *all_events; - - all_events = tep_get_first_event(pevent); - events_count = tep_get_events_count(pevent); - if (!pevent || !all_events || events_count < 1) - return NULL; - - if (!event) { - idx = 0; - return all_events; - } - - if (idx < events_count && event == (all_events + idx)) { - idx++; - if (idx == events_count) - return NULL; - return (all_events + idx); - } - - for (idx = 1; idx < events_count; idx++) { - if (event == (all_events + (idx - 1))) - return (all_events + idx); - } - return NULL; -} - struct flag { const char *name; unsigned long long value; diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 2e158387b3d7..72fdf2a3577c 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -47,8 +47,6 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event); unsigned long long read_size(struct tep_event *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); diff --git a/tools/testing/kunit/.gitignore b/tools/testing/kunit/.gitignore new file mode 100644 index 000000000000..c791ff59a37a --- /dev/null +++ b/tools/testing/kunit/.gitignore @@ -0,0 +1,3 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod]
\ No newline at end of file diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config new file mode 100644 index 000000000000..9235b7d42d38 --- /dev/null +++ b/tools/testing/kunit/configs/all_tests.config @@ -0,0 +1,3 @@ +CONFIG_KUNIT=y +CONFIG_KUNIT_TEST=y +CONFIG_KUNIT_EXAMPLE_TEST=y diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py new file mode 100755 index 000000000000..efe06d621983 --- /dev/null +++ b/tools/testing/kunit/kunit.py @@ -0,0 +1,138 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 +# +# A thin wrapper on top of the KUnit Kernel +# +# Copyright (C) 2019, Google LLC. +# Author: Felix Guo <felixguoxiuping@gmail.com> +# Author: Brendan Higgins <brendanhiggins@google.com> + +import argparse +import sys +import os +import time +import shutil + +from collections import namedtuple +from enum import Enum, auto + +import kunit_config +import kunit_kernel +import kunit_parser + +KunitResult = namedtuple('KunitResult', ['status','result']) + +KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', 'build_dir', 'defconfig']) + +class KunitStatus(Enum): + SUCCESS = auto() + CONFIG_FAILURE = auto() + BUILD_FAILURE = auto() + TEST_FAILURE = auto() + +def create_default_kunitconfig(): + if not os.path.exists(kunit_kernel.KUNITCONFIG_PATH): + shutil.copyfile('arch/um/configs/kunit_defconfig', + kunit_kernel.KUNITCONFIG_PATH) + +def run_tests(linux: kunit_kernel.LinuxSourceTree, + request: KunitRequest) -> KunitResult: + if request.defconfig: + create_default_kunitconfig() + + config_start = time.time() + success = linux.build_reconfig(request.build_dir) + config_end = time.time() + if not success: + return KunitResult(KunitStatus.CONFIG_FAILURE, 'could not configure kernel') + + kunit_parser.print_with_timestamp('Building KUnit Kernel ...') + + build_start = time.time() + success = linux.build_um_kernel(request.jobs, request.build_dir) + build_end = time.time() + if not success: + return KunitResult(KunitStatus.BUILD_FAILURE, 'could not build kernel') + + kunit_parser.print_with_timestamp('Starting KUnit Kernel ...') + test_start = time.time() + + test_result = kunit_parser.TestResult(kunit_parser.TestStatus.SUCCESS, + [], + 'Tests not Parsed.') + if request.raw_output: + kunit_parser.raw_output( + linux.run_kernel(timeout=request.timeout, + build_dir=request.build_dir)) + else: + kunit_output = linux.run_kernel(timeout=request.timeout, + build_dir=request.build_dir) + test_result = kunit_parser.parse_run_tests(kunit_output) + test_end = time.time() + + kunit_parser.print_with_timestamp(( + 'Elapsed time: %.3fs total, %.3fs configuring, %.3fs ' + + 'building, %.3fs running\n') % ( + test_end - config_start, + config_end - config_start, + build_end - build_start, + test_end - test_start)) + + if test_result.status != kunit_parser.TestStatus.SUCCESS: + return KunitResult(KunitStatus.TEST_FAILURE, test_result) + else: + return KunitResult(KunitStatus.SUCCESS, test_result) + +def main(argv, linux=None): + parser = argparse.ArgumentParser( + description='Helps writing and running KUnit tests.') + subparser = parser.add_subparsers(dest='subcommand') + + run_parser = subparser.add_parser('run', help='Runs KUnit tests.') + run_parser.add_argument('--raw_output', help='don\'t format output from kernel', + action='store_true') + + run_parser.add_argument('--timeout', + help='maximum number of seconds to allow for all tests ' + 'to run. This does not include time taken to build the ' + 'tests.', + type=int, + default=300, + metavar='timeout') + + run_parser.add_argument('--jobs', + help='As in the make command, "Specifies the number of ' + 'jobs (commands) to run simultaneously."', + type=int, default=8, metavar='jobs') + + run_parser.add_argument('--build_dir', + help='As in the make command, it specifies the build ' + 'directory.', + type=str, default=None, metavar='build_dir') + + run_parser.add_argument('--defconfig', + help='Uses a default kunitconfig.', + action='store_true') + + cli_args = parser.parse_args(argv) + + if cli_args.subcommand == 'run': + if cli_args.defconfig: + create_default_kunitconfig() + + if not linux: + linux = kunit_kernel.LinuxSourceTree() + + request = KunitRequest(cli_args.raw_output, + cli_args.timeout, + cli_args.jobs, + cli_args.build_dir, + cli_args.defconfig) + result = run_tests(linux, request) + if result.status != KunitStatus.SUCCESS: + sys.exit(1) + else: + parser.print_help() + +if __name__ == '__main__': + main(sys.argv[1:]) diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py new file mode 100644 index 000000000000..ebf3942b23f5 --- /dev/null +++ b/tools/testing/kunit/kunit_config.py @@ -0,0 +1,66 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Builds a .config from a kunitconfig. +# +# Copyright (C) 2019, Google LLC. +# Author: Felix Guo <felixguoxiuping@gmail.com> +# Author: Brendan Higgins <brendanhiggins@google.com> + +import collections +import re + +CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_\w+ is not set$' +CONFIG_PATTERN = r'^CONFIG_\w+=\S+$' + +KconfigEntryBase = collections.namedtuple('KconfigEntry', ['raw_entry']) + + +class KconfigEntry(KconfigEntryBase): + + def __str__(self) -> str: + return self.raw_entry + + +class KconfigParseError(Exception): + """Error parsing Kconfig defconfig or .config.""" + + +class Kconfig(object): + """Represents defconfig or .config specified using the Kconfig language.""" + + def __init__(self): + self._entries = [] + + def entries(self): + return set(self._entries) + + def add_entry(self, entry: KconfigEntry) -> None: + self._entries.append(entry) + + def is_subset_of(self, other: 'Kconfig') -> bool: + return self.entries().issubset(other.entries()) + + def write_to_file(self, path: str) -> None: + with open(path, 'w') as f: + for entry in self.entries(): + f.write(str(entry) + '\n') + + def parse_from_string(self, blob: str) -> None: + """Parses a string containing KconfigEntrys and populates this Kconfig.""" + self._entries = [] + is_not_set_matcher = re.compile(CONFIG_IS_NOT_SET_PATTERN) + config_matcher = re.compile(CONFIG_PATTERN) + for line in blob.split('\n'): + line = line.strip() + if not line: + continue + elif config_matcher.match(line) or is_not_set_matcher.match(line): + self._entries.append(KconfigEntry(line)) + elif line[0] == '#': + continue + else: + raise KconfigParseError('Failed to parse: ' + line) + + def read_from_file(self, path: str) -> None: + with open(path, 'r') as f: + self.parse_from_string(f.read()) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py new file mode 100644 index 000000000000..bf3876835331 --- /dev/null +++ b/tools/testing/kunit/kunit_kernel.py @@ -0,0 +1,149 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Runs UML kernel, collects output, and handles errors. +# +# Copyright (C) 2019, Google LLC. +# Author: Felix Guo <felixguoxiuping@gmail.com> +# Author: Brendan Higgins <brendanhiggins@google.com> + + +import logging +import subprocess +import os + +import kunit_config + +KCONFIG_PATH = '.config' +KUNITCONFIG_PATH = 'kunitconfig' + +class ConfigError(Exception): + """Represents an error trying to configure the Linux kernel.""" + + +class BuildError(Exception): + """Represents an error trying to build the Linux kernel.""" + + +class LinuxSourceTreeOperations(object): + """An abstraction over command line operations performed on a source tree.""" + + def make_mrproper(self): + try: + subprocess.check_output(['make', 'mrproper']) + except OSError as e: + raise ConfigError('Could not call make command: ' + e) + except subprocess.CalledProcessError as e: + raise ConfigError(e.output) + + def make_olddefconfig(self, build_dir): + command = ['make', 'ARCH=um', 'olddefconfig'] + if build_dir: + command += ['O=' + build_dir] + try: + subprocess.check_output(command) + except OSError as e: + raise ConfigError('Could not call make command: ' + e) + except subprocess.CalledProcessError as e: + raise ConfigError(e.output) + + def make(self, jobs, build_dir): + command = ['make', 'ARCH=um', '--jobs=' + str(jobs)] + if build_dir: + command += ['O=' + build_dir] + try: + subprocess.check_output(command) + except OSError as e: + raise BuildError('Could not call execute make: ' + e) + except subprocess.CalledProcessError as e: + raise BuildError(e.output) + + def linux_bin(self, params, timeout, build_dir): + """Runs the Linux UML binary. Must be named 'linux'.""" + linux_bin = './linux' + if build_dir: + linux_bin = os.path.join(build_dir, 'linux') + process = subprocess.Popen( + [linux_bin] + params, + stdin=subprocess.PIPE, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE) + process.wait(timeout=timeout) + return process + + +def get_kconfig_path(build_dir): + kconfig_path = KCONFIG_PATH + if build_dir: + kconfig_path = os.path.join(build_dir, KCONFIG_PATH) + return kconfig_path + +class LinuxSourceTree(object): + """Represents a Linux kernel source tree with KUnit tests.""" + + def __init__(self): + self._kconfig = kunit_config.Kconfig() + self._kconfig.read_from_file(KUNITCONFIG_PATH) + self._ops = LinuxSourceTreeOperations() + + def clean(self): + try: + self._ops.make_mrproper() + except ConfigError as e: + logging.error(e) + return False + return True + + def build_config(self, build_dir): + kconfig_path = get_kconfig_path(build_dir) + if build_dir and not os.path.exists(build_dir): + os.mkdir(build_dir) + self._kconfig.write_to_file(kconfig_path) + try: + self._ops.make_olddefconfig(build_dir) + except ConfigError as e: + logging.error(e) + return False + validated_kconfig = kunit_config.Kconfig() + validated_kconfig.read_from_file(kconfig_path) + if not self._kconfig.is_subset_of(validated_kconfig): + logging.error('Provided Kconfig is not contained in validated .config!') + return False + return True + + def build_reconfig(self, build_dir): + """Creates a new .config if it is not a subset of the kunitconfig.""" + kconfig_path = get_kconfig_path(build_dir) + if os.path.exists(kconfig_path): + existing_kconfig = kunit_config.Kconfig() + existing_kconfig.read_from_file(kconfig_path) + if not self._kconfig.is_subset_of(existing_kconfig): + print('Regenerating .config ...') + os.remove(kconfig_path) + return self.build_config(build_dir) + else: + return True + else: + print('Generating .config ...') + return self.build_config(build_dir) + + def build_um_kernel(self, jobs, build_dir): + try: + self._ops.make_olddefconfig(build_dir) + self._ops.make(jobs, build_dir) + except (ConfigError, BuildError) as e: + logging.error(e) + return False + used_kconfig = kunit_config.Kconfig() + used_kconfig.read_from_file(get_kconfig_path(build_dir)) + if not self._kconfig.is_subset_of(used_kconfig): + logging.error('Provided Kconfig is not contained in final config!') + return False + return True + + def run_kernel(self, args=[], timeout=None, build_dir=None): + args.extend(['mem=256M']) + process = self._ops.linux_bin(args, timeout, build_dir) + with open('test.log', 'w') as f: + for line in process.stdout: + f.write(line.rstrip().decode('ascii') + '\n') + yield line.rstrip().decode('ascii') diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py new file mode 100644 index 000000000000..4ffbae0f6732 --- /dev/null +++ b/tools/testing/kunit/kunit_parser.py @@ -0,0 +1,310 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Parses test results from a kernel dmesg log. +# +# Copyright (C) 2019, Google LLC. +# Author: Felix Guo <felixguoxiuping@gmail.com> +# Author: Brendan Higgins <brendanhiggins@google.com> + +import re + +from collections import namedtuple +from datetime import datetime +from enum import Enum, auto +from functools import reduce +from typing import List + +TestResult = namedtuple('TestResult', ['status','suites','log']) + +class TestSuite(object): + def __init__(self): + self.status = None + self.name = None + self.cases = [] + + def __str__(self): + return 'TestSuite(' + self.status + ',' + self.name + ',' + str(self.cases) + ')' + + def __repr__(self): + return str(self) + +class TestCase(object): + def __init__(self): + self.status = None + self.name = '' + self.log = [] + + def __str__(self): + return 'TestCase(' + self.status + ',' + self.name + ',' + str(self.log) + ')' + + def __repr__(self): + return str(self) + +class TestStatus(Enum): + SUCCESS = auto() + FAILURE = auto() + TEST_CRASHED = auto() + NO_TESTS = auto() + +kunit_start_re = re.compile(r'^TAP version [0-9]+$') +kunit_end_re = re.compile('List of all partitions:') + +def isolate_kunit_output(kernel_output): + started = False + for line in kernel_output: + if kunit_start_re.match(line): + started = True + yield line + elif kunit_end_re.match(line): + break + elif started: + yield line + +def raw_output(kernel_output): + for line in kernel_output: + print(line) + +DIVIDER = '=' * 60 + +RESET = '\033[0;0m' + +def red(text): + return '\033[1;31m' + text + RESET + +def yellow(text): + return '\033[1;33m' + text + RESET + +def green(text): + return '\033[1;32m' + text + RESET + +def print_with_timestamp(message): + print('[%s] %s' % (datetime.now().strftime('%H:%M:%S'), message)) + +def format_suite_divider(message): + return '======== ' + message + ' ========' + +def print_suite_divider(message): + print_with_timestamp(DIVIDER) + print_with_timestamp(format_suite_divider(message)) + +def print_log(log): + for m in log: + print_with_timestamp(m) + +TAP_ENTRIES = re.compile(r'^(TAP|\t?ok|\t?not ok|\t?[0-9]+\.\.[0-9]+|\t?#).*$') + +def consume_non_diagnositic(lines: List[str]) -> None: + while lines and not TAP_ENTRIES.match(lines[0]): + lines.pop(0) + +def save_non_diagnositic(lines: List[str], test_case: TestCase) -> None: + while lines and not TAP_ENTRIES.match(lines[0]): + test_case.log.append(lines[0]) + lines.pop(0) + +OkNotOkResult = namedtuple('OkNotOkResult', ['is_ok','description', 'text']) + +OK_NOT_OK_SUBTEST = re.compile(r'^\t(ok|not ok) [0-9]+ - (.*)$') + +OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) [0-9]+ - (.*)$') + +def parse_ok_not_ok_test_case(lines: List[str], + test_case: TestCase, + expecting_test_case: bool) -> bool: + save_non_diagnositic(lines, test_case) + if not lines: + if expecting_test_case: + test_case.status = TestStatus.TEST_CRASHED + return True + else: + return False + line = lines[0] + match = OK_NOT_OK_SUBTEST.match(line) + if match: + test_case.log.append(lines.pop(0)) + test_case.name = match.group(2) + if test_case.status == TestStatus.TEST_CRASHED: + return True + if match.group(1) == 'ok': + test_case.status = TestStatus.SUCCESS + else: + test_case.status = TestStatus.FAILURE + return True + else: + return False + +SUBTEST_DIAGNOSTIC = re.compile(r'^\t# .*?: (.*)$') +DIAGNOSTIC_CRASH_MESSAGE = 'kunit test case crashed!' + +def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: + save_non_diagnositic(lines, test_case) + if not lines: + return False + line = lines[0] + match = SUBTEST_DIAGNOSTIC.match(line) + if match: + test_case.log.append(lines.pop(0)) + if match.group(1) == DIAGNOSTIC_CRASH_MESSAGE: + test_case.status = TestStatus.TEST_CRASHED + return True + else: + return False + +def parse_test_case(lines: List[str], expecting_test_case: bool) -> TestCase: + test_case = TestCase() + save_non_diagnositic(lines, test_case) + while parse_diagnostic(lines, test_case): + pass + if parse_ok_not_ok_test_case(lines, test_case, expecting_test_case): + return test_case + else: + return None + +SUBTEST_HEADER = re.compile(r'^\t# Subtest: (.*)$') + +def parse_subtest_header(lines: List[str]) -> str: + consume_non_diagnositic(lines) + if not lines: + return None + match = SUBTEST_HEADER.match(lines[0]) + if match: + lines.pop(0) + return match.group(1) + else: + return None + +SUBTEST_PLAN = re.compile(r'\t[0-9]+\.\.([0-9]+)') + +def parse_subtest_plan(lines: List[str]) -> int: + consume_non_diagnositic(lines) + match = SUBTEST_PLAN.match(lines[0]) + if match: + lines.pop(0) + return int(match.group(1)) + else: + return None + +def max_status(left: TestStatus, right: TestStatus) -> TestStatus: + if left == TestStatus.TEST_CRASHED or right == TestStatus.TEST_CRASHED: + return TestStatus.TEST_CRASHED + elif left == TestStatus.FAILURE or right == TestStatus.FAILURE: + return TestStatus.FAILURE + elif left != TestStatus.SUCCESS: + return left + elif right != TestStatus.SUCCESS: + return right + else: + return TestStatus.SUCCESS + +def parse_ok_not_ok_test_suite(lines: List[str], test_suite: TestSuite) -> bool: + consume_non_diagnositic(lines) + if not lines: + test_suite.status = TestStatus.TEST_CRASHED + return False + line = lines[0] + match = OK_NOT_OK_MODULE.match(line) + if match: + lines.pop(0) + if match.group(1) == 'ok': + test_suite.status = TestStatus.SUCCESS + else: + test_suite.status = TestStatus.FAILURE + return True + else: + return False + +def bubble_up_errors(to_status, status_container_list) -> TestStatus: + status_list = map(to_status, status_container_list) + return reduce(max_status, status_list, TestStatus.SUCCESS) + +def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: + max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases) + return max_status(max_test_case_status, test_suite.status) + +def parse_test_suite(lines: List[str]) -> TestSuite: + if not lines: + return None + consume_non_diagnositic(lines) + test_suite = TestSuite() + test_suite.status = TestStatus.SUCCESS + name = parse_subtest_header(lines) + if not name: + return None + test_suite.name = name + expected_test_case_num = parse_subtest_plan(lines) + if not expected_test_case_num: + return None + test_case = parse_test_case(lines, expected_test_case_num > 0) + expected_test_case_num -= 1 + while test_case: + test_suite.cases.append(test_case) + test_case = parse_test_case(lines, expected_test_case_num > 0) + expected_test_case_num -= 1 + if parse_ok_not_ok_test_suite(lines, test_suite): + test_suite.status = bubble_up_test_case_errors(test_suite) + return test_suite + elif not lines: + print_with_timestamp(red('[ERROR] ') + 'ran out of lines before end token') + return test_suite + else: + print('failed to parse end of suite' + lines[0]) + return None + +TAP_HEADER = re.compile(r'^TAP version 14$') + +def parse_tap_header(lines: List[str]) -> bool: + consume_non_diagnositic(lines) + if TAP_HEADER.match(lines[0]): + lines.pop(0) + return True + else: + return False + +def bubble_up_suite_errors(test_suite_list: List[TestSuite]) -> TestStatus: + return bubble_up_errors(lambda x: x.status, test_suite_list) + +def parse_test_result(lines: List[str]) -> TestResult: + if not lines: + return TestResult(TestStatus.NO_TESTS, [], lines) + consume_non_diagnositic(lines) + if not parse_tap_header(lines): + return None + test_suites = [] + test_suite = parse_test_suite(lines) + while test_suite: + test_suites.append(test_suite) + test_suite = parse_test_suite(lines) + return TestResult(bubble_up_suite_errors(test_suites), test_suites, lines) + +def parse_run_tests(kernel_output) -> TestResult: + total_tests = 0 + failed_tests = 0 + crashed_tests = 0 + test_result = parse_test_result(list(isolate_kunit_output(kernel_output))) + for test_suite in test_result.suites: + if test_suite.status == TestStatus.SUCCESS: + print_suite_divider(green('[PASSED] ') + test_suite.name) + elif test_suite.status == TestStatus.TEST_CRASHED: + print_suite_divider(red('[CRASHED] ' + test_suite.name)) + else: + print_suite_divider(red('[FAILED] ') + test_suite.name) + for test_case in test_suite.cases: + total_tests += 1 + if test_case.status == TestStatus.SUCCESS: + print_with_timestamp(green('[PASSED] ') + test_case.name) + elif test_case.status == TestStatus.TEST_CRASHED: + crashed_tests += 1 + print_with_timestamp(red('[CRASHED] ' + test_case.name)) + print_log(map(yellow, test_case.log)) + print_with_timestamp('') + else: + failed_tests += 1 + print_with_timestamp(red('[FAILED] ') + test_case.name) + print_log(map(yellow, test_case.log)) + print_with_timestamp('') + print_with_timestamp(DIVIDER) + fmt = green if test_result.status == TestStatus.SUCCESS else red + print_with_timestamp( + fmt('Testing complete. %d tests run. %d failed. %d crashed.' % + (total_tests, failed_tests, crashed_tests))) + return test_result diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py new file mode 100755 index 000000000000..4a12baa0cd4e --- /dev/null +++ b/tools/testing/kunit/kunit_tool_test.py @@ -0,0 +1,206 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 +# +# A collection of tests for tools/testing/kunit/kunit.py +# +# Copyright (C) 2019, Google LLC. +# Author: Brendan Higgins <brendanhiggins@google.com> + +import unittest +from unittest import mock + +import tempfile, shutil # Handling test_tmpdir + +import os + +import kunit_config +import kunit_parser +import kunit_kernel +import kunit + +test_tmpdir = '' + +def setUpModule(): + global test_tmpdir + test_tmpdir = tempfile.mkdtemp() + +def tearDownModule(): + shutil.rmtree(test_tmpdir) + +def get_absolute_path(path): + return os.path.join(os.path.dirname(__file__), path) + +class KconfigTest(unittest.TestCase): + + def test_is_subset_of(self): + kconfig0 = kunit_config.Kconfig() + self.assertTrue(kconfig0.is_subset_of(kconfig0)) + + kconfig1 = kunit_config.Kconfig() + kconfig1.add_entry(kunit_config.KconfigEntry('CONFIG_TEST=y')) + self.assertTrue(kconfig1.is_subset_of(kconfig1)) + self.assertTrue(kconfig0.is_subset_of(kconfig1)) + self.assertFalse(kconfig1.is_subset_of(kconfig0)) + + def test_read_from_file(self): + kconfig = kunit_config.Kconfig() + kconfig_path = get_absolute_path( + 'test_data/test_read_from_file.kconfig') + + kconfig.read_from_file(kconfig_path) + + expected_kconfig = kunit_config.Kconfig() + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_UML=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_MMU=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_TEST=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_EXAMPLE_TEST=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('# CONFIG_MK8 is not set')) + + self.assertEqual(kconfig.entries(), expected_kconfig.entries()) + + def test_write_to_file(self): + kconfig_path = os.path.join(test_tmpdir, '.config') + + expected_kconfig = kunit_config.Kconfig() + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_UML=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_MMU=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_TEST=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('CONFIG_EXAMPLE_TEST=y')) + expected_kconfig.add_entry( + kunit_config.KconfigEntry('# CONFIG_MK8 is not set')) + + expected_kconfig.write_to_file(kconfig_path) + + actual_kconfig = kunit_config.Kconfig() + actual_kconfig.read_from_file(kconfig_path) + + self.assertEqual(actual_kconfig.entries(), + expected_kconfig.entries()) + +class KUnitParserTest(unittest.TestCase): + + def assertContains(self, needle, haystack): + for line in haystack: + if needle in line: + return + raise AssertionError('"' + + str(needle) + '" not found in "' + str(haystack) + '"!') + + def test_output_isolated_correctly(self): + log_path = get_absolute_path( + 'test_data/test_output_isolated_correctly.log') + file = open(log_path) + result = kunit_parser.isolate_kunit_output(file.readlines()) + self.assertContains('TAP version 14\n', result) + self.assertContains(' # Subtest: example', result) + self.assertContains(' 1..2', result) + self.assertContains(' ok 1 - example_simple_test', result) + self.assertContains(' ok 2 - example_mock_test', result) + self.assertContains('ok 1 - example', result) + file.close() + + def test_parse_successful_test_log(self): + all_passed_log = get_absolute_path( + 'test_data/test_is_test_passed-all_passed.log') + file = open(all_passed_log) + result = kunit_parser.parse_run_tests(file.readlines()) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + file.close() + + def test_parse_failed_test_log(self): + failed_log = get_absolute_path( + 'test_data/test_is_test_passed-failure.log') + file = open(failed_log) + result = kunit_parser.parse_run_tests(file.readlines()) + self.assertEqual( + kunit_parser.TestStatus.FAILURE, + result.status) + file.close() + + def test_no_tests(self): + empty_log = get_absolute_path( + 'test_data/test_is_test_passed-no_tests_run.log') + file = open(empty_log) + result = kunit_parser.parse_run_tests( + kunit_parser.isolate_kunit_output(file.readlines())) + self.assertEqual(0, len(result.suites)) + self.assertEqual( + kunit_parser.TestStatus.NO_TESTS, + result.status) + file.close() + + def test_crashed_test(self): + crashed_log = get_absolute_path( + 'test_data/test_is_test_passed-crash.log') + file = open(crashed_log) + result = kunit_parser.parse_run_tests(file.readlines()) + self.assertEqual( + kunit_parser.TestStatus.TEST_CRASHED, + result.status) + file.close() + +class StrContains(str): + def __eq__(self, other): + return self in other + +class KUnitMainTest(unittest.TestCase): + def setUp(self): + path = get_absolute_path('test_data/test_is_test_passed-all_passed.log') + file = open(path) + all_passed_log = file.readlines() + self.print_patch = mock.patch('builtins.print') + self.print_mock = self.print_patch.start() + self.linux_source_mock = mock.Mock() + self.linux_source_mock.build_reconfig = mock.Mock(return_value=True) + self.linux_source_mock.build_um_kernel = mock.Mock(return_value=True) + self.linux_source_mock.run_kernel = mock.Mock(return_value=all_passed_log) + + def tearDown(self): + self.print_patch.stop() + pass + + def test_run_passes_args_pass(self): + kunit.main(['run'], self.linux_source_mock) + assert self.linux_source_mock.build_reconfig.call_count == 1 + assert self.linux_source_mock.run_kernel.call_count == 1 + self.print_mock.assert_any_call(StrContains('Testing complete.')) + + def test_run_passes_args_fail(self): + self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) + with self.assertRaises(SystemExit) as e: + kunit.main(['run'], self.linux_source_mock) + assert type(e.exception) == SystemExit + assert e.exception.code == 1 + assert self.linux_source_mock.build_reconfig.call_count == 1 + assert self.linux_source_mock.run_kernel.call_count == 1 + self.print_mock.assert_any_call(StrContains(' 0 tests run')) + + def test_run_raw_output(self): + self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) + kunit.main(['run', '--raw_output'], self.linux_source_mock) + assert self.linux_source_mock.build_reconfig.call_count == 1 + assert self.linux_source_mock.run_kernel.call_count == 1 + for kall in self.print_mock.call_args_list: + assert kall != mock.call(StrContains('Testing complete.')) + assert kall != mock.call(StrContains(' 0 tests run')) + + def test_run_timeout(self): + timeout = 3453 + kunit.main(['run', '--timeout', str(timeout)], self.linux_source_mock) + assert self.linux_source_mock.build_reconfig.call_count == 1 + self.linux_source_mock.run_kernel.assert_called_once_with(timeout=timeout) + self.print_mock.assert_any_call(StrContains('Testing complete.')) + +if __name__ == '__main__': + unittest.main() diff --git a/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log b/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log new file mode 100644 index 000000000000..62ebc0288355 --- /dev/null +++ b/tools/testing/kunit/test_data/test_is_test_passed-all_passed.log @@ -0,0 +1,32 @@ +TAP version 14 + # Subtest: sysctl_test + 1..8 + # sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed + ok 1 - sysctl_test_dointvec_null_tbl_data + # sysctl_test_dointvec_table_maxlen_unset: sysctl_test_dointvec_table_maxlen_unset passed + ok 2 - sysctl_test_dointvec_table_maxlen_unset + # sysctl_test_dointvec_table_len_is_zero: sysctl_test_dointvec_table_len_is_zero passed + ok 3 - sysctl_test_dointvec_table_len_is_zero + # sysctl_test_dointvec_table_read_but_position_set: sysctl_test_dointvec_table_read_but_position_set passed + ok 4 - sysctl_test_dointvec_table_read_but_position_set + # sysctl_test_dointvec_happy_single_positive: sysctl_test_dointvec_happy_single_positive passed + ok 5 - sysctl_test_dointvec_happy_single_positive + # sysctl_test_dointvec_happy_single_negative: sysctl_test_dointvec_happy_single_negative passed + ok 6 - sysctl_test_dointvec_happy_single_negative + # sysctl_test_dointvec_single_less_int_min: sysctl_test_dointvec_single_less_int_min passed + ok 7 - sysctl_test_dointvec_single_less_int_min + # sysctl_test_dointvec_single_greater_int_max: sysctl_test_dointvec_single_greater_int_max passed + ok 8 - sysctl_test_dointvec_single_greater_int_max +kunit sysctl_test: all tests passed +ok 1 - sysctl_test + # Subtest: example + 1..2 +init_suite + # example_simple_test: initializing + # example_simple_test: example_simple_test passed + ok 1 - example_simple_test + # example_mock_test: initializing + # example_mock_test: example_mock_test passed + ok 2 - example_mock_test +kunit example: all tests passed +ok 2 - example diff --git a/tools/testing/kunit/test_data/test_is_test_passed-crash.log b/tools/testing/kunit/test_data/test_is_test_passed-crash.log new file mode 100644 index 000000000000..0b249870c8be --- /dev/null +++ b/tools/testing/kunit/test_data/test_is_test_passed-crash.log @@ -0,0 +1,69 @@ +printk: console [tty0] enabled +printk: console [mc-1] enabled +TAP version 14 + # Subtest: sysctl_test + 1..8 + # sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed + ok 1 - sysctl_test_dointvec_null_tbl_data + # sysctl_test_dointvec_table_maxlen_unset: sysctl_test_dointvec_table_maxlen_unset passed + ok 2 - sysctl_test_dointvec_table_maxlen_unset + # sysctl_test_dointvec_table_len_is_zero: sysctl_test_dointvec_table_len_is_zero passed + ok 3 - sysctl_test_dointvec_table_len_is_zero + # sysctl_test_dointvec_table_read_but_position_set: sysctl_test_dointvec_table_read_but_position_set passed + ok 4 - sysctl_test_dointvec_table_read_but_position_set + # sysctl_test_dointvec_happy_single_positive: sysctl_test_dointvec_happy_single_positive passed + ok 5 - sysctl_test_dointvec_happy_single_positive + # sysctl_test_dointvec_happy_single_negative: sysctl_test_dointvec_happy_single_negative passed + ok 6 - sysctl_test_dointvec_happy_single_negative + # sysctl_test_dointvec_single_less_int_min: sysctl_test_dointvec_single_less_int_min passed + ok 7 - sysctl_test_dointvec_single_less_int_min + # sysctl_test_dointvec_single_greater_int_max: sysctl_test_dointvec_single_greater_int_max passed + ok 8 - sysctl_test_dointvec_single_greater_int_max +kunit sysctl_test: all tests passed +ok 1 - sysctl_test + # Subtest: example + 1..2 +init_suite + # example_simple_test: initializing +Stack: + 6016f7db 6f81bd30 6f81bdd0 60021450 + 6024b0e8 60021440 60018bbe 16f81bdc0 + 00000001 6f81bd30 6f81bd20 6f81bdd0 +Call Trace: + [<6016f7db>] ? kunit_try_run_case+0xab/0xf0 + [<60021450>] ? set_signals+0x0/0x60 + [<60021440>] ? get_signals+0x0/0x10 + [<60018bbe>] ? kunit_um_run_try_catch+0x5e/0xc0 + [<60021450>] ? set_signals+0x0/0x60 + [<60021440>] ? get_signals+0x0/0x10 + [<60018bb3>] ? kunit_um_run_try_catch+0x53/0xc0 + [<6016f321>] ? kunit_run_case_catch_errors+0x121/0x1a0 + [<60018b60>] ? kunit_um_run_try_catch+0x0/0xc0 + [<600189e0>] ? kunit_um_throw+0x0/0x180 + [<6016f730>] ? kunit_try_run_case+0x0/0xf0 + [<6016f600>] ? kunit_catch_run_case+0x0/0x130 + [<6016edd0>] ? kunit_vprintk+0x0/0x30 + [<6016ece0>] ? kunit_fail+0x0/0x40 + [<6016eca0>] ? kunit_abort+0x0/0x40 + [<6016ed20>] ? kunit_printk_emit+0x0/0xb0 + [<6016f200>] ? kunit_run_case_catch_errors+0x0/0x1a0 + [<6016f46e>] ? kunit_run_tests+0xce/0x260 + [<6005b390>] ? unregister_console+0x0/0x190 + [<60175b70>] ? suite_kunit_initexample_test_suite+0x0/0x20 + [<60001cbb>] ? do_one_initcall+0x0/0x197 + [<60001d47>] ? do_one_initcall+0x8c/0x197 + [<6005cd20>] ? irq_to_desc+0x0/0x30 + [<60002005>] ? kernel_init_freeable+0x1b3/0x272 + [<6005c5ec>] ? printk+0x0/0x9b + [<601c0086>] ? kernel_init+0x26/0x160 + [<60014442>] ? new_thread_handler+0x82/0xc0 + + # example_simple_test: kunit test case crashed! + # example_simple_test: example_simple_test failed + not ok 1 - example_simple_test + # example_mock_test: initializing + # example_mock_test: example_mock_test passed + ok 2 - example_mock_test +kunit example: one or more tests failed +not ok 2 - example +List of all partitions: diff --git a/tools/testing/kunit/test_data/test_is_test_passed-failure.log b/tools/testing/kunit/test_data/test_is_test_passed-failure.log new file mode 100644 index 000000000000..9e89d32d5667 --- /dev/null +++ b/tools/testing/kunit/test_data/test_is_test_passed-failure.log @@ -0,0 +1,36 @@ +TAP version 14 + # Subtest: sysctl_test + 1..8 + # sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed + ok 1 - sysctl_test_dointvec_null_tbl_data + # sysctl_test_dointvec_table_maxlen_unset: sysctl_test_dointvec_table_maxlen_unset passed + ok 2 - sysctl_test_dointvec_table_maxlen_unset + # sysctl_test_dointvec_table_len_is_zero: sysctl_test_dointvec_table_len_is_zero passed + ok 3 - sysctl_test_dointvec_table_len_is_zero + # sysctl_test_dointvec_table_read_but_position_set: sysctl_test_dointvec_table_read_but_position_set passed + ok 4 - sysctl_test_dointvec_table_read_but_position_set + # sysctl_test_dointvec_happy_single_positive: sysctl_test_dointvec_happy_single_positive passed + ok 5 - sysctl_test_dointvec_happy_single_positive + # sysctl_test_dointvec_happy_single_negative: sysctl_test_dointvec_happy_single_negative passed + ok 6 - sysctl_test_dointvec_happy_single_negative + # sysctl_test_dointvec_single_less_int_min: sysctl_test_dointvec_single_less_int_min passed + ok 7 - sysctl_test_dointvec_single_less_int_min + # sysctl_test_dointvec_single_greater_int_max: sysctl_test_dointvec_single_greater_int_max passed + ok 8 - sysctl_test_dointvec_single_greater_int_max +kunit sysctl_test: all tests passed +ok 1 - sysctl_test + # Subtest: example + 1..2 +init_suite + # example_simple_test: initializing + # example_simple_test: EXPECTATION FAILED at lib/kunit/example-test.c:30 + Expected 1 + 1 == 3, but + 1 + 1 == 2 + 3 == 3 + # example_simple_test: example_simple_test failed + not ok 1 - example_simple_test + # example_mock_test: initializing + # example_mock_test: example_mock_test passed + ok 2 - example_mock_test +kunit example: one or more tests failed +not ok 2 - example diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log new file mode 100644 index 000000000000..ba69f5c94b75 --- /dev/null +++ b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log @@ -0,0 +1,75 @@ +Core dump limits : + soft - 0 + hard - NONE +Checking environment variables for a tempdir...none found +Checking if /dev/shm is on tmpfs...OK +Checking PROT_EXEC mmap in /dev/shm...OK +Adding 24743936 bytes to physical memory to account for exec-shield gap +Linux version 4.12.0-rc3-00010-g7319eb35f493-dirty (brendanhiggins@mactruck.svl.corp.google.com) (gcc version 7.3.0 (Debian 7.3.0-5) ) #29 Thu Mar 15 14:57:19 PDT 2018 +Built 1 zonelists in Zone order, mobility grouping on. Total pages: 14038 +Kernel command line: root=98:0 +PID hash table entries: 256 (order: -1, 2048 bytes) +Dentry cache hash table entries: 8192 (order: 4, 65536 bytes) +Inode-cache hash table entries: 4096 (order: 3, 32768 bytes) +Memory: 27868K/56932K available (1681K kernel code, 480K rwdata, 400K rodata, 89K init, 205K bss, 29064K reserved, 0K cma-reserved) +SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=1, Nodes=1 +NR_IRQS:15 +clocksource: timer: mask: 0xffffffffffffffff max_cycles: 0x1cd42e205, max_idle_ns: 881590404426 ns +Calibrating delay loop... 7384.26 BogoMIPS (lpj=36921344) +pid_max: default: 32768 minimum: 301 +Mount-cache hash table entries: 512 (order: 0, 4096 bytes) +Mountpoint-cache hash table entries: 512 (order: 0, 4096 bytes) +Checking that host ptys support output SIGIO...Yes +Checking that host ptys support SIGIO on close...No, enabling workaround +Using 2.6 host AIO +clocksource: jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 19112604462750000 ns +futex hash table entries: 256 (order: 0, 6144 bytes) +clocksource: Switched to clocksource timer +console [stderr0] disabled +mconsole (version 2) initialized on /usr/local/google/home/brendanhiggins/.uml/6Ijecl/mconsole +Checking host MADV_REMOVE support...OK +workingset: timestamp_bits=62 max_order=13 bucket_order=0 +Block layer SCSI generic (bsg) driver version 0.4 loaded (major 254) +io scheduler noop registered +io scheduler deadline registered +io scheduler cfq registered (default) +io scheduler mq-deadline registered +io scheduler kyber registered +Initialized stdio console driver +Using a channel type which is configured out of UML +setup_one_line failed for device 1 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 2 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 3 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 4 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 5 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 6 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 7 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 8 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 9 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 10 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 11 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 12 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 13 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 14 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 15 : Configuration failed +Console initialized on /dev/tty0 +console [tty0] enabled +console [mc-1] enabled +List of all partitions: +No filesystem could mount root, tried: + +Kernel panic - not syncing: VFS: Unable to mount root fs on unknown-block(98,0) diff --git a/tools/testing/kunit/test_data/test_output_isolated_correctly.log b/tools/testing/kunit/test_data/test_output_isolated_correctly.log new file mode 100644 index 000000000000..94a6b3aeaa92 --- /dev/null +++ b/tools/testing/kunit/test_data/test_output_isolated_correctly.log @@ -0,0 +1,106 @@ +Linux version 5.1.0-rc7-00061-g04652f1cb4aa0 (brendanhiggins@mactruck.svl.corp.google.com) (gcc version 7.3.0 (Debian 7.3.0-18)) #163 Wed May 8 16:18:20 PDT 2019 +Built 1 zonelists, mobility grouping on. Total pages: 69906 +Kernel command line: mem=256M root=98:0 +Dentry cache hash table entries: 65536 (order: 7, 524288 bytes) +Inode-cache hash table entries: 32768 (order: 6, 262144 bytes) +Memory: 254468K/283500K available (1734K kernel code, 489K rwdata, 396K rodata, 85K init, 216K bss, 29032K reserved, 0K cma-reserved) +SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=1, Nodes=1 +NR_IRQS: 15 +clocksource: timer: mask: 0xffffffffffffffff max_cycles: 0x1cd42e205, max_idle_ns: 881590404426 ns +------------[ cut here ]------------ +WARNING: CPU: 0 PID: 0 at kernel/time/clockevents.c:458 clockevents_register_device+0x143/0x160 +posix-timer cpumask == cpu_all_mask, using cpu_possible_mask instead +CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc7-00061-g04652f1cb4aa0 #163 +Stack: + 6005cc00 60233e18 60233e60 60233e18 + 60233e60 00000009 00000000 6002a1b4 + 1ca00000000 60071c23 60233e78 100000000000062 +Call Trace: + [<600214c5>] ? os_is_signal_stack+0x15/0x30 + [<6005c5ec>] ? printk+0x0/0x9b + [<6001597e>] ? show_stack+0xbe/0x1c0 + [<6005cc00>] ? __printk_safe_exit+0x0/0x40 + [<6002a1b4>] ? __warn+0x144/0x170 + [<60071c23>] ? clockevents_register_device+0x143/0x160 + [<60021440>] ? get_signals+0x0/0x10 + [<6005c5ec>] ? printk+0x0/0x9b + [<6002a27b>] ? warn_slowpath_fmt+0x9b/0xb0 + [<6005c5ec>] ? printk+0x0/0x9b + [<6002a1e0>] ? warn_slowpath_fmt+0x0/0xb0 + [<6005c5ec>] ? printk+0x0/0x9b + [<60021440>] ? get_signals+0x0/0x10 + [<600213f0>] ? block_signals+0x0/0x20 + [<60071c23>] ? clockevents_register_device+0x143/0x160 + [<60021440>] ? get_signals+0x0/0x10 + [<600213f0>] ? block_signals+0x0/0x20 + [<6005c5ec>] ? printk+0x0/0x9b + [<60001bc8>] ? start_kernel+0x477/0x56a + [<600036f1>] ? start_kernel_proc+0x46/0x4d + [<60014442>] ? new_thread_handler+0x82/0xc0 + +random: get_random_bytes called from print_oops_end_marker+0x4c/0x60 with crng_init=0 +---[ end trace c83434852b3702d3 ]--- +Calibrating delay loop... 6958.28 BogoMIPS (lpj=34791424) +pid_max: default: 32768 minimum: 301 +Mount-cache hash table entries: 1024 (order: 1, 8192 bytes) +Mountpoint-cache hash table entries: 1024 (order: 1, 8192 bytes) +*** VALIDATE proc *** +Checking that host ptys support output SIGIO...Yes +Checking that host ptys support SIGIO on close...No, enabling workaround +clocksource: jiffies: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 19112604462750000 ns +futex hash table entries: 256 (order: 0, 6144 bytes) +clocksource: Switched to clocksource timer +printk: console [stderr0] disabled +mconsole (version 2) initialized on /usr/local/google/home/brendanhiggins/.uml/VZ2qMm/mconsole +Checking host MADV_REMOVE support...OK +workingset: timestamp_bits=62 max_order=16 bucket_order=0 +Block layer SCSI generic (bsg) driver version 0.4 loaded (major 254) +io scheduler mq-deadline registered +io scheduler kyber registered +Initialized stdio console driver +Using a channel type which is configured out of UML +setup_one_line failed for device 1 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 2 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 3 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 4 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 5 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 6 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 7 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 8 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 9 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 10 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 11 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 12 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 13 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 14 : Configuration failed +Using a channel type which is configured out of UML +setup_one_line failed for device 15 : Configuration failed +Console initialized on /dev/tty0 +printk: console [tty0] enabled +printk: console [mc-1] enabled +TAP version 14 + # Subtest: example + 1..2 +init_suite + # example_simple_test: initializing + # example_simple_test: example_simple_test passed + ok 1 - example_simple_test + # example_mock_test: initializing + # example_mock_test: example_mock_test passed + ok 2 - example_mock_test +kunit example: all tests passed +ok 1 - example +List of all partitions: diff --git a/tools/testing/kunit/test_data/test_read_from_file.kconfig b/tools/testing/kunit/test_data/test_read_from_file.kconfig new file mode 100644 index 000000000000..d2a4928ac773 --- /dev/null +++ b/tools/testing/kunit/test_data/test_read_from_file.kconfig @@ -0,0 +1,17 @@ +# +# Automatically generated file; DO NOT EDIT. +# User Mode Linux/x86 4.12.0-rc3 Kernel Configuration +# +CONFIG_UML=y +CONFIG_MMU=y + +# +# UML-specific options +# + +# +# Host processor type and features +# +# CONFIG_MK8 is not set +CONFIG_TEST=y +CONFIG_EXAMPLE_TEST=y diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 4cdbae6f4e61..0b6b81ba4421 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 TARGETS = android +TARGETS += arm64 TARGETS += bpf TARGETS += breakpoints TARGETS += capabilities @@ -86,10 +87,10 @@ override LDFLAGS = endif ifneq ($(O),) - BUILD := $(O) + BUILD := $(abs_objtree) else ifneq ($(KBUILD_OUTPUT),) - BUILD := $(KBUILD_OUTPUT)/kselftest + BUILD := $(abs_objtree)/kselftest else BUILD := $(shell pwd) DEFAULT_INSTALL_HDR_PATH := 1 @@ -102,6 +103,7 @@ include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) export KSFT_KHDR_INSTALL_DONE := 1 export BUILD +#$(info abd_objtree = $(abs_objtree) BUILD = $(BUILD)) # build and run gpio when output directory is the src dir. # gpio has dependency on tools/gpio and builds tools/gpio @@ -190,6 +192,7 @@ install: all ifdef INSTALL_PATH @# Ask all targets to install their files mkdir -p $(INSTALL_PATH)/kselftest + install -m 744 kselftest/module.sh $(INSTALL_PATH)/kselftest/ install -m 744 kselftest/runner.sh $(INSTALL_PATH)/kselftest/ install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/ @for TARGET in $(TARGETS); do \ @@ -213,7 +216,7 @@ ifdef INSTALL_PATH @# included in the generated runlist. for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - [ ! -d $$INSTALL_PATH/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \ + [ ! -d $(INSTALL_PATH)/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \ echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \ echo "cd $$TARGET" >> $(ALL_SCRIPT); \ echo -n "run_many" >> $(ALL_SCRIPT); \ diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index f9f79fb272f0..93b567d23c8b 100644 --- a/tools/testing/selftests/arm64/Makefile +++ b/tools/testing/selftests/arm64/Makefile @@ -1,12 +1,66 @@ # SPDX-License-Identifier: GPL-2.0 -# ARCH can be overridden by the user for cross compiling +# When ARCH not overridden for crosscompiling, lookup machine ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),aarch64 arm64)) -CFLAGS += -I../../../../usr/include/ -TEST_GEN_PROGS := tags_test -TEST_PROGS := run_tags_test.sh +ARM64_SUBTARGETS ?= tags signal +else +ARM64_SUBTARGETS := endif -include ../lib.mk +CFLAGS := -Wall -O2 -g + +# A proper top_srcdir is needed by KSFT(lib.mk) +top_srcdir = $(realpath ../../../../) + +# Additional include paths needed by kselftest.h and local headers +CFLAGS += -I$(top_srcdir)/tools/testing/selftests/ + +# Guessing where the Kernel headers could have been installed +# depending on ENV config +ifeq ($(KBUILD_OUTPUT),) +khdr_dir = $(top_srcdir)/usr/include +else +# the KSFT preferred location when KBUILD_OUTPUT is set +khdr_dir = $(KBUILD_OUTPUT)/kselftest/usr/include +endif + +CFLAGS += -I$(khdr_dir) + +export CFLAGS +export top_srcdir + +all: + @for DIR in $(ARM64_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + mkdir -p $$BUILD_TARGET; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +install: all + @for DIR in $(ARM64_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +run_tests: all + @for DIR in $(ARM64_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +# Avoid any output on non arm64 on emit_tests +emit_tests: all + @for DIR in $(ARM64_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +clean: + @for DIR in $(ARM64_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +.PHONY: all clean install run_tests emit_tests diff --git a/tools/testing/selftests/arm64/README b/tools/testing/selftests/arm64/README new file mode 100644 index 000000000000..a1badd882102 --- /dev/null +++ b/tools/testing/selftests/arm64/README @@ -0,0 +1,25 @@ +KSelfTest ARM64 +=============== + +- These tests are arm64 specific and so not built or run but just skipped + completely when env-variable ARCH is found to be different than 'arm64' + and `uname -m` reports other than 'aarch64'. + +- Holding true the above, ARM64 KSFT tests can be run within the KSelfTest + framework using standard Linux top-level-makefile targets: + + $ make TARGETS=arm64 kselftest-clean + $ make TARGETS=arm64 kselftest + + or + + $ make -C tools/testing/selftests TARGETS=arm64 \ + INSTALL_PATH=<your-installation-path> install + + or, alternatively, only specific arm64/ subtargets can be picked: + + $ make -C tools/testing/selftests TARGETS=arm64 ARM64_SUBTARGETS="tags signal" \ + INSTALL_PATH=<your-installation-path> install + + Further details on building and running KFST can be found in: + Documentation/dev-tools/kselftest.rst diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore new file mode 100644 index 000000000000..3c5b4e8ff894 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -0,0 +1,3 @@ +mangle_* +fake_sigreturn_* +!*.[ch] diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile new file mode 100644 index 000000000000..b497cfea4643 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/Makefile @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2019 ARM Limited + +# Additional include paths needed by kselftest.h and local headers +CFLAGS += -D_GNU_SOURCE -std=gnu99 -I. + +SRCS := $(filter-out testcases/testcases.c,$(wildcard testcases/*.c)) +PROGS := $(patsubst %.c,%,$(SRCS)) + +# Generated binaries to be installed by top KSFT script +TEST_GEN_PROGS := $(notdir $(PROGS)) + +# Get Kernel headers installed and use them. +KSFT_KHDR_INSTALL := 1 + +# Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list +# to account for any OUTPUT target-dirs optionally provided by +# the toplevel makefile +include ../../lib.mk + +$(TEST_GEN_PROGS): $(PROGS) + cp $(PROGS) $(OUTPUT)/ + +clean: + $(CLEAN) + rm -f $(PROGS) + +# Common test-unit targets to build common-layout test-cases executables +# Needs secondary expansion to properly include the testcase c-file in pre-reqs +.SECONDEXPANSION: +$(PROGS): test_signals.c test_signals_utils.c testcases/testcases.c signals.S $$@.c test_signals.h test_signals_utils.h testcases/testcases.h + $(CC) $(CFLAGS) $^ -o $@ diff --git a/tools/testing/selftests/arm64/signal/README b/tools/testing/selftests/arm64/signal/README new file mode 100644 index 000000000000..967a531b245c --- /dev/null +++ b/tools/testing/selftests/arm64/signal/README @@ -0,0 +1,59 @@ +KSelfTest arm64/signal/ +======================= + +Signals Tests ++++++++++++++ + +- Tests are built around a common main compilation unit: such shared main + enforces a standard sequence of operations needed to perform a single + signal-test (setup/trigger/run/result/cleanup) + +- The above mentioned ops are configurable on a test-by-test basis: each test + is described (and configured) using the descriptor signals.h::struct tdescr + +- Each signal testcase is compiled into its own executable: a separate + executable is used for each test since many tests complete successfully + by receiving some kind of fatal signal from the Kernel, so it's safer + to run each test unit in its own standalone process, so as to start each + test from a clean slate. + +- New tests can be simply defined in testcases/ dir providing a proper struct + tdescr overriding all the defaults we wish to change (as of now providing a + custom run method is mandatory though) + +- Signals' test-cases hereafter defined belong currently to two + principal families: + + - 'mangle_' tests: a real signal (SIGUSR1) is raised and used as a trigger + and then the test case code modifies the signal frame from inside the + signal handler itself. + + - 'fake_sigreturn_' tests: a brand new custom artificial sigframe structure + is placed on the stack and a sigreturn syscall is called to simulate a + real signal return. This kind of tests does not use a trigger usually and + they are just fired using some simple included assembly trampoline code. + + - Most of these tests are successfully passing if the process gets killed by + some fatal signal: usually SIGSEGV or SIGBUS. Since while writing this + kind of tests it is extremely easy in fact to end-up injecting other + unrelated SEGV bugs in the testcases, it becomes extremely tricky to + be really sure that the tests are really addressing what they are meant + to address and they are not instead falling apart due to unplanned bugs + in the test code. + In order to alleviate the misery of the life of such test-developer, a few + helpers are provided: + + - a couple of ASSERT_BAD/GOOD_CONTEXT() macros to easily parse a ucontext_t + and verify if it is indeed GOOD or BAD (depending on what we were + expecting), using the same logic/perspective as in the arm64 Kernel signals + routines. + + - a sanity mechanism to be used in 'fake_sigreturn_'-alike tests: enabled by + default it takes care to verify that the test-execution had at least + successfully progressed up to the stage of triggering the fake sigreturn + call. + + In both cases test results are expected in terms of: + - some fatal signal sent by the Kernel to the test process + or + - analyzing some final regs state diff --git a/tools/testing/selftests/arm64/signal/signals.S b/tools/testing/selftests/arm64/signal/signals.S new file mode 100644 index 000000000000..9f8c1aefc3b9 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/signals.S @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 ARM Limited */ + +#include <asm/unistd.h> + +.section .rodata, "a" +call_fmt: + .asciz "Calling sigreturn with fake sigframe sized:%zd at SP @%08lX\n" + +.text + +.globl fake_sigreturn + +/* fake_sigreturn x0:&sigframe, x1:sigframe_size, x2:misalign_bytes */ +fake_sigreturn: + stp x29, x30, [sp, #-16]! + mov x29, sp + + mov x20, x0 + mov x21, x1 + mov x22, x2 + + /* create space on the stack for fake sigframe 16 bytes-aligned */ + add x0, x21, x22 + add x0, x0, #15 + bic x0, x0, #15 /* round_up(sigframe_size + misalign_bytes, 16) */ + sub sp, sp, x0 + add x23, sp, x22 /* new sigframe base with misaligment if any */ + + ldr x0, =call_fmt + mov x1, x21 + mov x2, x23 + bl printf + + /* memcpy the provided content, while still keeping SP aligned */ + mov x0, x23 + mov x1, x20 + mov x2, x21 + bl memcpy + + /* + * Here saving a last minute SP to current->token acts as a marker: + * if we got here, we are successfully faking a sigreturn; in other + * words we are sure no bad fatal signal has been raised till now + * for unrelated reasons, so we should consider the possibly observed + * fatal signal like SEGV coming from Kernel restore_sigframe() and + * triggered as expected from our test-case. + * For simplicity this assumes that current field 'token' is laid out + * as first in struct tdescr + */ + ldr x0, current + str x23, [x0] + /* finally move SP to misaligned address...if any requested */ + mov sp, x23 + + mov x8, #__NR_rt_sigreturn + svc #0 + + /* + * Above sigreturn should not return...looping here leads to a timeout + * and ensure proper and clean test failure, instead of jumping around + * on a potentially corrupted stack. + */ + b . diff --git a/tools/testing/selftests/arm64/signal/test_signals.c b/tools/testing/selftests/arm64/signal/test_signals.c new file mode 100644 index 000000000000..416b1ff43199 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/test_signals.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Generic test wrapper for arm64 signal tests. + * + * Each test provides its own tde struct tdescr descriptor to link with + * this wrapper. Framework provides common helpers. + */ +#include <kselftest.h> + +#include "test_signals.h" +#include "test_signals_utils.h" + +struct tdescr *current; + +int main(int argc, char *argv[]) +{ + current = &tde; + + ksft_print_msg("%s :: %s\n", current->name, current->descr); + if (test_setup(current) && test_init(current)) { + test_run(current); + test_cleanup(current); + } + test_result(current); + + return current->result; +} diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h new file mode 100644 index 000000000000..f96baf1cef1a --- /dev/null +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 ARM Limited */ + +#ifndef __TEST_SIGNALS_H__ +#define __TEST_SIGNALS_H__ + +#include <signal.h> +#include <stdbool.h> +#include <ucontext.h> + +/* + * Using ARCH specific and sanitized Kernel headers installed by KSFT + * framework since we asked for it by setting flag KSFT_KHDR_INSTALL + * in our Makefile. + */ +#include <asm/ptrace.h> +#include <asm/hwcap.h> + +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) + +#define get_regval(regname, out) \ +{ \ + asm volatile("mrs %0, " __stringify(regname) \ + : "=r" (out) \ + : \ + : "memory"); \ +} + +/* + * Feature flags used in tdescr.feats_required to specify + * any feature by the test + */ +enum { + FSSBS_BIT, + FMAX_END +}; + +#define FEAT_SSBS (1UL << FSSBS_BIT) + +/* + * A descriptor used to describe and configure a test case. + * Fields with a non-trivial meaning are described inline in the following. + */ +struct tdescr { + /* KEEP THIS FIELD FIRST for easier lookup from assembly */ + void *token; + /* when disabled token based sanity checking is skipped in handler */ + bool sanity_disabled; + /* just a name for the test-case; manadatory field */ + char *name; + char *descr; + unsigned long feats_required; + /* bitmask of effectively supported feats: populated at run-time */ + unsigned long feats_supported; + bool initialized; + unsigned int minsigstksz; + /* signum used as a test trigger. Zero if no trigger-signal is used */ + int sig_trig; + /* + * signum considered as a successful test completion. + * Zero when no signal is expected on success + */ + int sig_ok; + /* signum expected on unsupported CPU features. */ + int sig_unsupp; + /* a timeout in second for test completion */ + unsigned int timeout; + bool triggered; + bool pass; + unsigned int result; + /* optional sa_flags for the installed handler */ + int sa_flags; + ucontext_t saved_uc; + /* used by get_current_ctx() */ + size_t live_sz; + ucontext_t *live_uc; + volatile sig_atomic_t live_uc_valid; + /* optional test private data */ + void *priv; + + /* a custom setup: called alternatively to default_setup */ + int (*setup)(struct tdescr *td); + /* a custom init: called by default test init after test_setup */ + bool (*init)(struct tdescr *td); + /* a custom cleanup function called before test exits */ + void (*cleanup)(struct tdescr *td); + /* an optional function to be used as a trigger for starting test */ + int (*trigger)(struct tdescr *td); + /* + * the actual test-core: invoked differently depending on the + * presence of the trigger function above; this is mandatory + */ + int (*run)(struct tdescr *td, siginfo_t *si, ucontext_t *uc); + /* an optional function for custom results' processing */ + void (*check_result)(struct tdescr *td); +}; + +extern struct tdescr tde; +#endif diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c new file mode 100644 index 000000000000..2de6e5ed5e25 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019 ARM Limited */ + +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <unistd.h> +#include <assert.h> +#include <sys/auxv.h> +#include <linux/auxvec.h> +#include <ucontext.h> + +#include <asm/unistd.h> + +#include <kselftest.h> + +#include "test_signals.h" +#include "test_signals_utils.h" +#include "testcases/testcases.h" + + +extern struct tdescr *current; + +static int sig_copyctx = SIGTRAP; + +static char const *const feats_names[FMAX_END] = { + " SSBS ", +}; + +#define MAX_FEATS_SZ 128 +static char feats_string[MAX_FEATS_SZ]; + +static inline char *feats_to_string(unsigned long feats) +{ + size_t flen = MAX_FEATS_SZ - 1; + + for (int i = 0; i < FMAX_END; i++) { + if (feats & (1UL << i)) { + size_t tlen = strlen(feats_names[i]); + + assert(flen > tlen); + flen -= tlen; + strncat(feats_string, feats_names[i], flen); + } + } + + return feats_string; +} + +static void unblock_signal(int signum) +{ + sigset_t sset; + + sigemptyset(&sset); + sigaddset(&sset, signum); + sigprocmask(SIG_UNBLOCK, &sset, NULL); +} + +static void default_result(struct tdescr *td, bool force_exit) +{ + if (td->result == KSFT_SKIP) { + fprintf(stderr, "==>> completed. SKIP.\n"); + } else if (td->pass) { + fprintf(stderr, "==>> completed. PASS(1)\n"); + td->result = KSFT_PASS; + } else { + fprintf(stdout, "==>> completed. FAIL(0)\n"); + td->result = KSFT_FAIL; + } + + if (force_exit) + exit(td->result); +} + +/* + * The following handle_signal_* helpers are used by main default_handler + * and are meant to return true when signal is handled successfully: + * when false is returned instead, it means that the signal was somehow + * unexpected in that context and it was NOT handled; default_handler will + * take care of such unexpected situations. + */ + +static bool handle_signal_unsupported(struct tdescr *td, + siginfo_t *si, void *uc) +{ + if (feats_ok(td)) + return false; + + /* Mangling PC to avoid loops on original SIGILL */ + ((ucontext_t *)uc)->uc_mcontext.pc += 4; + + if (!td->initialized) { + fprintf(stderr, + "Got SIG_UNSUPP @test_init. Ignore.\n"); + } else { + fprintf(stderr, + "-- RX SIG_UNSUPP on unsupported feat...OK\n"); + td->pass = 1; + default_result(current, 1); + } + + return true; +} + +static bool handle_signal_trigger(struct tdescr *td, + siginfo_t *si, void *uc) +{ + td->triggered = 1; + /* ->run was asserted NON-NULL in test_setup() already */ + td->run(td, si, uc); + + return true; +} + +static bool handle_signal_ok(struct tdescr *td, + siginfo_t *si, void *uc) +{ + /* + * it's a bug in the test code when this assert fail: + * if sig_trig was defined, it must have been used before getting here. + */ + assert(!td->sig_trig || td->triggered); + fprintf(stderr, + "SIG_OK -- SP:0x%llX si_addr@:%p si_code:%d token@:%p offset:%ld\n", + ((ucontext_t *)uc)->uc_mcontext.sp, + si->si_addr, si->si_code, td->token, td->token - si->si_addr); + /* + * fake_sigreturn tests, which have sanity_enabled=1, set, at the very + * last time, the token field to the SP address used to place the fake + * sigframe: so token==0 means we never made it to the end, + * segfaulting well-before, and the test is possibly broken. + */ + if (!td->sanity_disabled && !td->token) { + fprintf(stdout, + "current->token ZEROED...test is probably broken!\n"); + abort(); + } + /* + * Trying to narrow down the SEGV to the ones generated by Kernel itself + * via arm64_notify_segfault(). This is a best-effort check anyway, and + * the si_code check may need to change if this aspect of the kernel + * ABI changes. + */ + if (td->sig_ok == SIGSEGV && si->si_code != SEGV_ACCERR) { + fprintf(stdout, + "si_code != SEGV_ACCERR...test is probably broken!\n"); + abort(); + } + td->pass = 1; + /* + * Some tests can lead to SEGV loops: in such a case we want to + * terminate immediately exiting straight away; some others are not + * supposed to outlive the signal handler code, due to the content of + * the fake sigframe which caused the signal itself. + */ + default_result(current, 1); + + return true; +} + +static bool handle_signal_copyctx(struct tdescr *td, + siginfo_t *si, void *uc) +{ + /* Mangling PC to avoid loops on original BRK instr */ + ((ucontext_t *)uc)->uc_mcontext.pc += 4; + memcpy(td->live_uc, uc, td->live_sz); + ASSERT_GOOD_CONTEXT(td->live_uc); + td->live_uc_valid = 1; + fprintf(stderr, + "GOOD CONTEXT grabbed from sig_copyctx handler\n"); + + return true; +} + +static void default_handler(int signum, siginfo_t *si, void *uc) +{ + if (current->sig_unsupp && signum == current->sig_unsupp && + handle_signal_unsupported(current, si, uc)) { + fprintf(stderr, "Handled SIG_UNSUPP\n"); + } else if (current->sig_trig && signum == current->sig_trig && + handle_signal_trigger(current, si, uc)) { + fprintf(stderr, "Handled SIG_TRIG\n"); + } else if (current->sig_ok && signum == current->sig_ok && + handle_signal_ok(current, si, uc)) { + fprintf(stderr, "Handled SIG_OK\n"); + } else if (signum == sig_copyctx && current->live_uc && + handle_signal_copyctx(current, si, uc)) { + fprintf(stderr, "Handled SIG_COPYCTX\n"); + } else { + if (signum == SIGALRM && current->timeout) { + fprintf(stderr, "-- Timeout !\n"); + } else { + fprintf(stderr, + "-- RX UNEXPECTED SIGNAL: %d\n", signum); + } + default_result(current, 1); + } +} + +static int default_setup(struct tdescr *td) +{ + struct sigaction sa; + + sa.sa_sigaction = default_handler; + sa.sa_flags = SA_SIGINFO | SA_RESTART; + sa.sa_flags |= td->sa_flags; + sigemptyset(&sa.sa_mask); + /* uncatchable signals naturally skipped ... */ + for (int sig = 1; sig < 32; sig++) + sigaction(sig, &sa, NULL); + /* + * RT Signals default disposition is Term but they cannot be + * generated by the Kernel in response to our tests; so just catch + * them all and report them as UNEXPECTED signals. + */ + for (int sig = SIGRTMIN; sig <= SIGRTMAX; sig++) + sigaction(sig, &sa, NULL); + + /* just in case...unblock explicitly all we need */ + if (td->sig_trig) + unblock_signal(td->sig_trig); + if (td->sig_ok) + unblock_signal(td->sig_ok); + if (td->sig_unsupp) + unblock_signal(td->sig_unsupp); + + if (td->timeout) { + unblock_signal(SIGALRM); + alarm(td->timeout); + } + fprintf(stderr, "Registered handlers for all signals.\n"); + + return 1; +} + +static inline int default_trigger(struct tdescr *td) +{ + return !raise(td->sig_trig); +} + +int test_init(struct tdescr *td) +{ + if (td->sig_trig == sig_copyctx) { + fprintf(stdout, + "Signal %d is RESERVED, cannot be used as a trigger. Aborting\n", + sig_copyctx); + return 0; + } + /* just in case */ + unblock_signal(sig_copyctx); + + td->minsigstksz = getauxval(AT_MINSIGSTKSZ); + if (!td->minsigstksz) + td->minsigstksz = MINSIGSTKSZ; + fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz); + + if (td->feats_required) { + td->feats_supported = 0; + /* + * Checking for CPU required features using both the + * auxval and the arm64 MRS Emulation to read sysregs. + */ + if (getauxval(AT_HWCAP) & HWCAP_SSBS) + td->feats_supported |= FEAT_SSBS; + if (feats_ok(td)) + fprintf(stderr, + "Required Features: [%s] supported\n", + feats_to_string(td->feats_required & + td->feats_supported)); + else + fprintf(stderr, + "Required Features: [%s] NOT supported\n", + feats_to_string(td->feats_required & + ~td->feats_supported)); + } + + /* Perform test specific additional initialization */ + if (td->init && !td->init(td)) { + fprintf(stderr, "FAILED Testcase initialization.\n"); + return 0; + } + td->initialized = 1; + fprintf(stderr, "Testcase initialized.\n"); + + return 1; +} + +int test_setup(struct tdescr *td) +{ + /* assert core invariants symptom of a rotten testcase */ + assert(current); + assert(td); + assert(td->name); + assert(td->run); + + /* Default result is FAIL if test setup fails */ + td->result = KSFT_FAIL; + if (td->setup) + return td->setup(td); + else + return default_setup(td); +} + +int test_run(struct tdescr *td) +{ + if (td->sig_trig) { + if (td->trigger) + return td->trigger(td); + else + return default_trigger(td); + } else { + return td->run(td, NULL, NULL); + } +} + +void test_result(struct tdescr *td) +{ + if (td->initialized && td->result != KSFT_SKIP && td->check_result) + td->check_result(td); + default_result(td, 0); +} + +void test_cleanup(struct tdescr *td) +{ + if (td->cleanup) + td->cleanup(td); +} diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h new file mode 100644 index 000000000000..6772b5c8d274 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 ARM Limited */ + +#ifndef __TEST_SIGNALS_UTILS_H__ +#define __TEST_SIGNALS_UTILS_H__ + +#include <assert.h> +#include <stdio.h> +#include <string.h> + +#include "test_signals.h" + +int test_init(struct tdescr *td); +int test_setup(struct tdescr *td); +void test_cleanup(struct tdescr *td); +int test_run(struct tdescr *td); +void test_result(struct tdescr *td); + +static inline bool feats_ok(struct tdescr *td) +{ + return (td->feats_required & td->feats_supported) == td->feats_required; +} + +/* + * Obtaining a valid and full-blown ucontext_t from userspace is tricky: + * libc getcontext does() not save all the regs and messes with some of + * them (pstate value in particular is not reliable). + * + * Here we use a service signal to grab the ucontext_t from inside a + * dedicated signal handler, since there, it is populated by Kernel + * itself in setup_sigframe(). The grabbed context is then stored and + * made available in td->live_uc. + * + * As service-signal is used a SIGTRAP induced by a 'brk' instruction, + * because here we have to avoid syscalls to trigger the signal since + * they would cause any SVE sigframe content (if any) to be removed. + * + * Anyway this function really serves a dual purpose: + * + * 1. grab a valid sigcontext into td->live_uc for result analysis: in + * such case it returns 1. + * + * 2. detect if, somehow, a previously grabbed live_uc context has been + * used actively with a sigreturn: in such a case the execution would have + * magically resumed in the middle of this function itself (seen_already==1): + * in such a case return 0, since in fact we have not just simply grabbed + * the context. + * + * This latter case is useful to detect when a fake_sigreturn test-case has + * unexpectedly survived without hitting a SEGV. + * + * Note that the case of runtime dynamically sized sigframes (like in SVE + * context) is still NOT addressed: sigframe size is supposed to be fixed + * at sizeof(ucontext_t). + */ +static __always_inline bool get_current_context(struct tdescr *td, + ucontext_t *dest_uc) +{ + static volatile bool seen_already; + + assert(td && dest_uc); + /* it's a genuine invocation..reinit */ + seen_already = 0; + td->live_uc_valid = 0; + td->live_sz = sizeof(*dest_uc); + memset(dest_uc, 0x00, td->live_sz); + td->live_uc = dest_uc; + /* + * Grab ucontext_t triggering a SIGTRAP. + * + * Note that: + * - live_uc_valid is declared volatile sig_atomic_t in + * struct tdescr since it will be changed inside the + * sig_copyctx handler + * - the additional 'memory' clobber is there to avoid possible + * compiler's assumption on live_uc_valid and the content + * pointed by dest_uc, which are all changed inside the signal + * handler + * - BRK causes a debug exception which is handled by the Kernel + * and finally causes the SIGTRAP signal to be delivered to this + * test thread. Since such delivery happens on the ret_to_user() + * /do_notify_resume() debug exception return-path, we are sure + * that the registered SIGTRAP handler has been run to completion + * before the execution path is restored here: as a consequence + * we can be sure that the volatile sig_atomic_t live_uc_valid + * carries a meaningful result. Being in a single thread context + * we'll also be sure that any access to memory modified by the + * handler (namely ucontext_t) will be visible once returned. + * - note that since we are using a breakpoint instruction here + * to cause a SIGTRAP, the ucontext_t grabbed from the signal + * handler would naturally contain a PC pointing exactly to this + * BRK line, which means that, on return from the signal handler, + * or if we place the ucontext_t on the stack to fake a sigreturn, + * we'll end up in an infinite loop of BRK-SIGTRAP-handler. + * For this reason we take care to artificially move forward the + * PC to the next instruction while inside the signal handler. + */ + asm volatile ("brk #666" + : "+m" (*dest_uc) + : + : "memory"); + + /* + * If we get here with seen_already==1 it implies the td->live_uc + * context has been used to get back here....this probably means + * a test has failed to cause a SEGV...anyway live_uc does not + * point to a just acquired copy of ucontext_t...so return 0 + */ + if (seen_already) { + fprintf(stdout, + "Unexpected successful sigreturn detected: live_uc is stale !\n"); + return 0; + } + seen_already = 1; + + return td->live_uc_valid; +} + +int fake_sigreturn(void *sigframe, size_t sz, int misalign_bytes); +#endif diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c new file mode 100644 index 000000000000..8dc600a7d4fd --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_magic.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Place a fake sigframe on the stack including a BAD Unknown magic + * record: on sigreturn Kernel must spot this attempt and the test + * case is expected to be terminated via SEGV. + */ + +#include <signal.h> +#include <ucontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; + +static int fake_sigreturn_bad_magic_run(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head; + + /* just to fill the ucontext_t with something real */ + if (!get_current_context(td, &sf.uc)) + return 1; + + /* need at least 2*HDR_SZ space: KSFT_BAD_MAGIC + terminator. */ + head = get_starting_head(shead, HDR_SZ * 2, GET_SF_RESV_SIZE(sf), NULL); + if (!head) + return 0; + + /* + * use a well known NON existent bad magic...something + * we should pretty sure won't be ever defined in Kernel + */ + head->magic = KSFT_BAD_MAGIC; + head->size = HDR_SZ; + write_terminator_record(GET_RESV_NEXT_HEAD(head)); + + ASSERT_BAD_CONTEXT(&sf.uc); + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_BAD_MAGIC", + .descr = "Trigger a sigreturn with a sigframe with a bad magic", + .sig_ok = SIGSEGV, + .timeout = 3, + .run = fake_sigreturn_bad_magic_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c new file mode 100644 index 000000000000..b3c362100666 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Place a fake sigframe on the stack including a bad record overflowing + * the __reserved space: on sigreturn Kernel must spot this attempt and + * the test case is expected to be terminated via SEGV. + */ + +#include <signal.h> +#include <ucontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; + +#define MIN_SZ_ALIGN 16 + +static int fake_sigreturn_bad_size_run(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, need_sz, offset; + struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head; + + /* just to fill the ucontext_t with something real */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + /* at least HDR_SZ + bad sized esr_context needed */ + need_sz = sizeof(struct esr_context) + HDR_SZ; + head = get_starting_head(shead, need_sz, resv_sz, &offset); + if (!head) + return 0; + + /* + * Use an esr_context to build a fake header with a + * size greater then the free __reserved area minus HDR_SZ; + * using ESR_MAGIC here since it is not checked for size nor + * is limited to one instance. + * + * At first inject an additional normal esr_context + */ + head->magic = ESR_MAGIC; + head->size = sizeof(struct esr_context); + /* and terminate properly */ + write_terminator_record(GET_RESV_NEXT_HEAD(head)); + ASSERT_GOOD_CONTEXT(&sf.uc); + + /* + * now mess with fake esr_context size: leaving less space than + * needed while keeping size value 16-aligned + * + * It must trigger a SEGV from Kernel on: + * + * resv_sz - offset < sizeof(*head) + */ + /* at first set the maximum good 16-aligned size */ + head->size = (resv_sz - offset - need_sz + MIN_SZ_ALIGN) & ~0xfUL; + /* plus a bit more of 16-aligned sized stuff */ + head->size += MIN_SZ_ALIGN; + /* and terminate properly */ + write_terminator_record(GET_RESV_NEXT_HEAD(head)); + ASSERT_BAD_CONTEXT(&sf.uc); + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_BAD_SIZE", + .descr = "Triggers a sigreturn with a overrun __reserved area", + .sig_ok = SIGSEGV, + .timeout = 3, + .run = fake_sigreturn_bad_size_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c new file mode 100644 index 000000000000..a44b88bfc81a --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_bad_size_for_magic0.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Place a fake sigframe on the stack including a badly sized terminator + * record: on sigreturn Kernel must spot this attempt and the test case + * is expected to be terminated via SEGV. + */ + +#include <signal.h> +#include <ucontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; + +static int fake_sigreturn_bad_size_for_magic0_run(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head; + + /* just to fill the ucontext_t with something real */ + if (!get_current_context(td, &sf.uc)) + return 1; + + /* at least HDR_SZ for the badly sized terminator. */ + head = get_starting_head(shead, HDR_SZ, GET_SF_RESV_SIZE(sf), NULL); + if (!head) + return 0; + + head->magic = 0; + head->size = HDR_SZ; + ASSERT_BAD_CONTEXT(&sf.uc); + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_BAD_SIZE_FOR_TERMINATOR", + .descr = "Trigger a sigreturn using non-zero size terminator", + .sig_ok = SIGSEGV, + .timeout = 3, + .run = fake_sigreturn_bad_size_for_magic0_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c new file mode 100644 index 000000000000..afe8915f0998 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_duplicated_fpsimd.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Place a fake sigframe on the stack including an additional FPSIMD + * record: on sigreturn Kernel must spot this attempt and the test + * case is expected to be terminated via SEGV. + */ + +#include <signal.h> +#include <ucontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; + +static int fake_sigreturn_duplicated_fpsimd_run(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + struct _aarch64_ctx *shead = GET_SF_RESV_HEAD(sf), *head; + + /* just to fill the ucontext_t with something real */ + if (!get_current_context(td, &sf.uc)) + return 1; + + head = get_starting_head(shead, sizeof(struct fpsimd_context) + HDR_SZ, + GET_SF_RESV_SIZE(sf), NULL); + if (!head) + return 0; + + /* Add a spurious fpsimd_context */ + head->magic = FPSIMD_MAGIC; + head->size = sizeof(struct fpsimd_context); + /* and terminate */ + write_terminator_record(GET_RESV_NEXT_HEAD(head)); + + ASSERT_BAD_CONTEXT(&sf.uc); + fake_sigreturn(&sf, sizeof(sf), 0); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_DUPLICATED_FPSIMD", + .descr = "Triggers a sigreturn including two fpsimd_context", + .sig_ok = SIGSEGV, + .timeout = 3, + .run = fake_sigreturn_duplicated_fpsimd_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c new file mode 100644 index 000000000000..1e089e66f9f3 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_misaligned_sp.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Place a fake sigframe on the stack at a misaligned SP: on sigreturn + * Kernel must spot this attempt and the test case is expected to be + * terminated via SEGV. + */ + +#include <signal.h> +#include <ucontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; + +static int fake_sigreturn_misaligned_run(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + /* just to fill the ucontext_t with something real */ + if (!get_current_context(td, &sf.uc)) + return 1; + + /* Forcing sigframe on misaligned SP (16 + 3) */ + fake_sigreturn(&sf, sizeof(sf), 3); + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_MISALIGNED_SP", + .descr = "Triggers a sigreturn with a misaligned sigframe", + .sig_ok = SIGSEGV, + .timeout = 3, + .run = fake_sigreturn_misaligned_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c new file mode 100644 index 000000000000..08ecd8073a1a --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_missing_fpsimd.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Place a fake sigframe on the stack missing the mandatory FPSIMD + * record: on sigreturn Kernel must spot this attempt and the test + * case is expected to be terminated via SEGV. + */ + +#include <stdio.h> +#include <signal.h> +#include <ucontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +struct fake_sigframe sf; + +static int fake_sigreturn_missing_fpsimd_run(struct tdescr *td, + siginfo_t *si, ucontext_t *uc) +{ + size_t resv_sz, offset; + struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); + + /* just to fill the ucontext_t with something real */ + if (!get_current_context(td, &sf.uc)) + return 1; + + resv_sz = GET_SF_RESV_SIZE(sf); + head = get_header(head, FPSIMD_MAGIC, resv_sz, &offset); + if (head && resv_sz - offset >= HDR_SZ) { + fprintf(stderr, "Mangling template header. Spare space:%zd\n", + resv_sz - offset); + /* Just overwrite fpsmid_context */ + write_terminator_record(head); + + ASSERT_BAD_CONTEXT(&sf.uc); + fake_sigreturn(&sf, sizeof(sf), 0); + } + + return 1; +} + +struct tdescr tde = { + .name = "FAKE_SIGRETURN_MISSING_FPSIMD", + .descr = "Triggers a sigreturn with a missing fpsimd_context", + .sig_ok = SIGSEGV, + .timeout = 3, + .run = fake_sigreturn_missing_fpsimd_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_compat_toggle.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_compat_toggle.c new file mode 100644 index 000000000000..2cb118b0ba05 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_compat_toggle.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, toggling + * the execution state bit: this attempt must be spotted by Kernel and + * the test case is expected to be terminated via SEGV. + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +static int mangle_invalid_pstate_run(struct tdescr *td, siginfo_t *si, + ucontext_t *uc) +{ + ASSERT_GOOD_CONTEXT(uc); + + /* This config should trigger a SIGSEGV by Kernel */ + uc->uc_mcontext.pstate ^= PSR_MODE32_BIT; + + return 1; +} + +struct tdescr tde = { + .sanity_disabled = true, + .name = "MANGLE_PSTATE_INVALID_STATE_TOGGLE", + .descr = "Mangling uc_mcontext with INVALID STATE_TOGGLE", + .sig_trig = SIGUSR1, + .sig_ok = SIGSEGV, + .run = mangle_invalid_pstate_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_daif_bits.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_daif_bits.c new file mode 100644 index 000000000000..434b82597007 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_daif_bits.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, mangling the + * DAIF bits in an illegal manner: this attempt must be spotted by Kernel + * and the test case is expected to be terminated via SEGV. + * + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +static int mangle_invalid_pstate_run(struct tdescr *td, siginfo_t *si, + ucontext_t *uc) +{ + ASSERT_GOOD_CONTEXT(uc); + + /* + * This config should trigger a SIGSEGV by Kernel when it checks + * the sigframe consistency in valid_user_regs() routine. + */ + uc->uc_mcontext.pstate |= PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT; + + return 1; +} + +struct tdescr tde = { + .sanity_disabled = true, + .name = "MANGLE_PSTATE_INVALID_DAIF_BITS", + .descr = "Mangling uc_mcontext with INVALID DAIF_BITS", + .sig_trig = SIGUSR1, + .sig_ok = SIGSEGV, + .run = mangle_invalid_pstate_run, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1h.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1h.c new file mode 100644 index 000000000000..95f821abdf46 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1h.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, toggling + * the mode bit to escalate exception level: this attempt must be spotted + * by Kernel and the test case is expected to be termninated via SEGV. + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +#include "mangle_pstate_invalid_mode_template.h" + +DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(1h); diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1t.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1t.c new file mode 100644 index 000000000000..cc222d8a618a --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el1t.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, toggling + * the mode bit to escalate exception level: this attempt must be spotted + * by Kernel and the test case is expected to be termninated via SEGV. + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +#include "mangle_pstate_invalid_mode_template.h" + +DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(1t); diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2h.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2h.c new file mode 100644 index 000000000000..2188add7d28c --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2h.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, toggling + * the mode bit to escalate exception level: this attempt must be spotted + * by Kernel and the test case is expected to be termninated via SEGV. + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +#include "mangle_pstate_invalid_mode_template.h" + +DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(2h); diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2t.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2t.c new file mode 100644 index 000000000000..df32dd5a479c --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el2t.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, toggling + * the mode bit to escalate exception level: this attempt must be spotted + * by Kernel and the test case is expected to be termninated via SEGV. + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +#include "mangle_pstate_invalid_mode_template.h" + +DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(2t); diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3h.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3h.c new file mode 100644 index 000000000000..9e6829b7e5db --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3h.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, toggling + * the mode bit to escalate exception level: this attempt must be spotted + * by Kernel and the test case is expected to be termninated via SEGV. + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +#include "mangle_pstate_invalid_mode_template.h" + +DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(3h); diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3t.c b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3t.c new file mode 100644 index 000000000000..5685a4f10d06 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_el3t.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 ARM Limited + * + * Try to mangle the ucontext from inside a signal handler, toggling + * the mode bit to escalate exception level: this attempt must be spotted + * by Kernel and the test case is expected to be termninated via SEGV. + */ + +#include "test_signals_utils.h" +#include "testcases.h" + +#include "mangle_pstate_invalid_mode_template.h" + +DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(3t); diff --git a/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_template.h b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_template.h new file mode 100644 index 000000000000..f5bf1804d858 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/mangle_pstate_invalid_mode_template.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 ARM Limited + * + * Utility macro to ease definition of testcases toggling mode EL + */ + +#define DEFINE_TESTCASE_MANGLE_PSTATE_INVALID_MODE(_mode) \ + \ +static int mangle_invalid_pstate_run(struct tdescr *td, siginfo_t *si, \ + ucontext_t *uc) \ +{ \ + ASSERT_GOOD_CONTEXT(uc); \ + \ + uc->uc_mcontext.pstate &= ~PSR_MODE_MASK; \ + uc->uc_mcontext.pstate |= PSR_MODE_EL ## _mode; \ + \ + return 1; \ +} \ + \ +struct tdescr tde = { \ + .sanity_disabled = true, \ + .name = "MANGLE_PSTATE_INVALID_MODE_EL"#_mode, \ + .descr = "Mangling uc_mcontext INVALID MODE EL"#_mode, \ + .sig_trig = SIGUSR1, \ + .sig_ok = SIGSEGV, \ + .run = mangle_invalid_pstate_run, \ +} diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c new file mode 100644 index 000000000000..61ebcdf63831 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019 ARM Limited */ +#include "testcases.h" + +struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic, + size_t resv_sz, size_t *offset) +{ + size_t offs = 0; + struct _aarch64_ctx *found = NULL; + + if (!head || resv_sz < HDR_SZ) + return found; + + while (offs <= resv_sz - HDR_SZ && + head->magic != magic && head->magic) { + offs += head->size; + head = GET_RESV_NEXT_HEAD(head); + } + if (head->magic == magic) { + found = head; + if (offset) + *offset = offs; + } + + return found; +} + +bool validate_extra_context(struct extra_context *extra, char **err) +{ + struct _aarch64_ctx *term; + + if (!extra || !err) + return false; + + fprintf(stderr, "Validating EXTRA...\n"); + term = GET_RESV_NEXT_HEAD(extra); + if (!term || term->magic || term->size) { + *err = "Missing terminator after EXTRA context"; + return false; + } + if (extra->datap & 0x0fUL) + *err = "Extra DATAP misaligned"; + else if (extra->size & 0x0fUL) + *err = "Extra SIZE misaligned"; + else if (extra->datap != (uint64_t)term + sizeof(*term)) + *err = "Extra DATAP misplaced (not contiguous)"; + if (*err) + return false; + + return true; +} + +bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) +{ + bool terminated = false; + size_t offs = 0; + int flags = 0; + struct extra_context *extra = NULL; + struct _aarch64_ctx *head = + (struct _aarch64_ctx *)uc->uc_mcontext.__reserved; + + if (!err) + return false; + /* Walk till the end terminator verifying __reserved contents */ + while (head && !terminated && offs < resv_sz) { + if ((uint64_t)head & 0x0fUL) { + *err = "Misaligned HEAD"; + return false; + } + + switch (head->magic) { + case 0: + if (head->size) + *err = "Bad size for terminator"; + else + terminated = true; + break; + case FPSIMD_MAGIC: + if (flags & FPSIMD_CTX) + *err = "Multiple FPSIMD_MAGIC"; + else if (head->size != + sizeof(struct fpsimd_context)) + *err = "Bad size for fpsimd_context"; + flags |= FPSIMD_CTX; + break; + case ESR_MAGIC: + if (head->size != sizeof(struct esr_context)) + *err = "Bad size for esr_context"; + break; + case SVE_MAGIC: + if (flags & SVE_CTX) + *err = "Multiple SVE_MAGIC"; + else if (head->size != + sizeof(struct sve_context)) + *err = "Bad size for sve_context"; + flags |= SVE_CTX; + break; + case EXTRA_MAGIC: + if (flags & EXTRA_CTX) + *err = "Multiple EXTRA_MAGIC"; + else if (head->size != + sizeof(struct extra_context)) + *err = "Bad size for extra_context"; + flags |= EXTRA_CTX; + extra = (struct extra_context *)head; + break; + case KSFT_BAD_MAGIC: + /* + * This is a BAD magic header defined + * artificially by a testcase and surely + * unknown to the Kernel parse_user_sigframe(). + * It MUST cause a Kernel induced SEGV + */ + *err = "BAD MAGIC !"; + break; + default: + /* + * A still unknown Magic: potentially freshly added + * to the Kernel code and still unknown to the + * tests. + */ + fprintf(stdout, + "SKIP Unknown MAGIC: 0x%X - Is KSFT arm64/signal up to date ?\n", + head->magic); + break; + } + + if (*err) + return false; + + offs += head->size; + if (resv_sz < offs + sizeof(*head)) { + *err = "HEAD Overrun"; + return false; + } + + if (flags & EXTRA_CTX) + if (!validate_extra_context(extra, err)) + return false; + + head = GET_RESV_NEXT_HEAD(head); + } + + if (terminated && !(flags & FPSIMD_CTX)) { + *err = "Missing FPSIMD"; + return false; + } + + return true; +} + +/* + * This function walks through the records inside the provided reserved area + * trying to find enough space to fit @need_sz bytes: if not enough space is + * available and an extra_context record is present, it throws away the + * extra_context record. + * + * It returns a pointer to a new header where it is possible to start storing + * our need_sz bytes. + * + * @shead: points to the start of reserved area + * @need_sz: needed bytes + * @resv_sz: reserved area size in bytes + * @offset: if not null, this will be filled with the offset of the return + * head pointer from @shead + * + * @return: pointer to a new head where to start storing need_sz bytes, or + * NULL if space could not be made available. + */ +struct _aarch64_ctx *get_starting_head(struct _aarch64_ctx *shead, + size_t need_sz, size_t resv_sz, + size_t *offset) +{ + size_t offs = 0; + struct _aarch64_ctx *head; + + head = get_terminator(shead, resv_sz, &offs); + /* not found a terminator...no need to update offset if any */ + if (!head) + return head; + if (resv_sz - offs < need_sz) { + fprintf(stderr, "Low on space:%zd. Discarding extra_context.\n", + resv_sz - offs); + head = get_header(shead, EXTRA_MAGIC, resv_sz, &offs); + if (!head || resv_sz - offs < need_sz) { + fprintf(stderr, + "Failed to reclaim space on sigframe.\n"); + return NULL; + } + } + + fprintf(stderr, "Available space:%zd\n", resv_sz - offs); + if (offset) + *offset = offs; + return head; +} diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h new file mode 100644 index 000000000000..ad884c135314 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 ARM Limited */ +#ifndef __TESTCASES_H__ +#define __TESTCASES_H__ + +#include <stddef.h> +#include <stdio.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdlib.h> +#include <ucontext.h> +#include <signal.h> + +/* Architecture specific sigframe definitions */ +#include <asm/sigcontext.h> + +#define FPSIMD_CTX (1 << 0) +#define SVE_CTX (1 << 1) +#define EXTRA_CTX (1 << 2) + +#define KSFT_BAD_MAGIC 0xdeadbeef + +#define HDR_SZ \ + sizeof(struct _aarch64_ctx) + +#define GET_SF_RESV_HEAD(sf) \ + (struct _aarch64_ctx *)(&(sf).uc.uc_mcontext.__reserved) + +#define GET_SF_RESV_SIZE(sf) \ + sizeof((sf).uc.uc_mcontext.__reserved) + +#define GET_UCP_RESV_SIZE(ucp) \ + sizeof((ucp)->uc_mcontext.__reserved) + +#define ASSERT_BAD_CONTEXT(uc) do { \ + char *err = NULL; \ + if (!validate_reserved((uc), GET_UCP_RESV_SIZE((uc)), &err)) { \ + if (err) \ + fprintf(stderr, \ + "Using badly built context - ERR: %s\n",\ + err); \ + } else { \ + abort(); \ + } \ +} while (0) + +#define ASSERT_GOOD_CONTEXT(uc) do { \ + char *err = NULL; \ + if (!validate_reserved((uc), GET_UCP_RESV_SIZE((uc)), &err)) { \ + if (err) \ + fprintf(stderr, \ + "Detected BAD context - ERR: %s\n", err);\ + abort(); \ + } else { \ + fprintf(stderr, "uc context validated.\n"); \ + } \ +} while (0) + +/* + * A simple record-walker for __reserved area: it walks through assuming + * only to find a proper struct __aarch64_ctx header descriptor. + * + * Instead it makes no assumptions on the content and ordering of the + * records, any needed bounds checking must be enforced by the caller + * if wanted: this way can be used by caller on any maliciously built bad + * contexts. + * + * head->size accounts both for payload and header _aarch64_ctx size ! + */ +#define GET_RESV_NEXT_HEAD(h) \ + (struct _aarch64_ctx *)((char *)(h) + (h)->size) + +struct fake_sigframe { + siginfo_t info; + ucontext_t uc; +}; + + +bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err); + +bool validate_extra_context(struct extra_context *extra, char **err); + +struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic, + size_t resv_sz, size_t *offset); + +static inline struct _aarch64_ctx *get_terminator(struct _aarch64_ctx *head, + size_t resv_sz, + size_t *offset) +{ + return get_header(head, 0, resv_sz, offset); +} + +static inline void write_terminator_record(struct _aarch64_ctx *tail) +{ + if (tail) { + tail->magic = 0; + tail->size = 0; + } +} + +struct _aarch64_ctx *get_starting_head(struct _aarch64_ctx *shead, + size_t need_sz, size_t resv_sz, + size_t *offset); +#endif diff --git a/tools/testing/selftests/arm64/.gitignore b/tools/testing/selftests/arm64/tags/.gitignore index e8fae8d61ed6..e8fae8d61ed6 100644 --- a/tools/testing/selftests/arm64/.gitignore +++ b/tools/testing/selftests/arm64/tags/.gitignore diff --git a/tools/testing/selftests/arm64/tags/Makefile b/tools/testing/selftests/arm64/tags/Makefile new file mode 100644 index 000000000000..41cb75070511 --- /dev/null +++ b/tools/testing/selftests/arm64/tags/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += -I../../../../../usr/include/ +TEST_GEN_PROGS := tags_test +TEST_PROGS := run_tags_test.sh + +include ../../lib.mk diff --git a/tools/testing/selftests/arm64/run_tags_test.sh b/tools/testing/selftests/arm64/tags/run_tags_test.sh index 745f11379930..745f11379930 100755 --- a/tools/testing/selftests/arm64/run_tags_test.sh +++ b/tools/testing/selftests/arm64/tags/run_tags_test.sh diff --git a/tools/testing/selftests/arm64/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c index 5701163460ef..5701163460ef 100644 --- a/tools/testing/selftests/arm64/tags_test.c +++ b/tools/testing/selftests/arm64/tags/tags_test.c diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index a320e3844b17..7c6e5b173f33 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -161,9 +161,14 @@ static struct sysctl_test tests[] = { .descr = "ctx:file_pos sysctl:read read ok narrow", .insns = { /* If (file_pos == X) */ +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, file_pos)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2), +#else + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sysctl, file_pos) + 3), +#endif + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 4, 2), /* return ALLOW; */ BPF_MOV64_IMM(BPF_REG_0, 1), @@ -176,6 +181,7 @@ static struct sysctl_test tests[] = { .attach_type = BPF_CGROUP_SYSCTL, .sysctl = "kernel/ostype", .open_flags = O_RDONLY, + .seek = 4, .result = SUCCESS, }, { diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c index 58ed5eeab709..ad41ea69001b 100644 --- a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c +++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c @@ -109,7 +109,7 @@ static bool set_watchpoint(pid_t pid, int size, int wp) return false; } -static bool arun_test(int wr_size, int wp_size, int wr, int wp) +static bool run_test(int wr_size, int wp_size, int wr, int wp) { int status; siginfo_t siginfo; diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index ae6146ec5afd..4632f51af7ab 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -112,14 +112,16 @@ sanitization_single_dev_mcast_group_test() RET=0 ip link add dev br0 type bridge mcast_snooping 0 + ip link add name dummy1 up type dummy ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ ttl 20 tos inherit local 198.51.100.1 dstport 4789 \ - dev $swp2 group 239.0.0.1 + dev dummy1 group 239.0.0.1 sanitization_single_dev_test_fail ip link del dev vxlan0 + ip link del dev dummy1 ip link del dev br0 log_test "vxlan device with a multicast group" @@ -181,13 +183,15 @@ sanitization_single_dev_local_interface_test() RET=0 ip link add dev br0 type bridge mcast_snooping 0 + ip link add name dummy1 up type dummy ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev $swp2 + ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev dummy1 sanitization_single_dev_test_fail ip link del dev vxlan0 + ip link del dev dummy1 ip link del dev br0 log_test "vxlan device with local interface" diff --git a/tools/testing/selftests/gen_kselftest_tar.sh b/tools/testing/selftests/gen_kselftest_tar.sh index a27e2eec3586..8b2b6088540d 100755 --- a/tools/testing/selftests/gen_kselftest_tar.sh +++ b/tools/testing/selftests/gen_kselftest_tar.sh @@ -38,16 +38,21 @@ main() esac fi - install_dir=./kselftest + # Create working directory. + dest=`pwd` + install_work="$dest"/kselftest_install + install_name=kselftest + install_dir="$install_work"/"$install_name" + mkdir -p "$install_dir" -# Run install using INSTALL_KSFT_PATH override to generate install -# directory -./kselftest_install.sh -tar $copts kselftest${ext} $install_dir -echo "Kselftest archive kselftest${ext} created!" + # Run install using INSTALL_KSFT_PATH override to generate install + # directory + ./kselftest_install.sh "$install_dir" + (cd "$install_work"; tar $copts "$dest"/kselftest${ext} $install_name) + echo "Kselftest archive kselftest${ext} created!" -# clean up install directory -rm -rf kselftest + # clean up top-level install work directory + rm -rf "$install_work" } main "$@" diff --git a/tools/testing/selftests/kselftest_module.sh b/tools/testing/selftests/kselftest/module.sh index 18e1c7992d30..18e1c7992d30 100755 --- a/tools/testing/selftests/kselftest_module.sh +++ b/tools/testing/selftests/kselftest/module.sh diff --git a/tools/testing/selftests/kselftest_install.sh b/tools/testing/selftests/kselftest_install.sh index e2e1911d62d5..407af7da7037 100755 --- a/tools/testing/selftests/kselftest_install.sh +++ b/tools/testing/selftests/kselftest_install.sh @@ -6,30 +6,30 @@ # Author: Shuah Khan <shuahkh@osg.samsung.com> # Copyright (C) 2015 Samsung Electronics Co., Ltd. -install_loc=`pwd` - main() { - if [ $(basename $install_loc) != "selftests" ]; then + base_dir=`pwd` + install_dir="$base_dir"/kselftest_install + + # Make sure we're in the selftests top-level directory. + if [ $(basename "$base_dir") != "selftests" ]; then echo "$0: Please run it in selftests directory ..." exit 1; fi + + # Only allow installation into an existing location. if [ "$#" -eq 0 ]; then - echo "$0: Installing in default location - $install_loc ..." + echo "$0: Installing in default location - $install_dir ..." elif [ ! -d "$1" ]; then echo "$0: $1 doesn't exist!!" exit 1; else - install_loc=$1 - echo "$0: Installing in specified location - $install_loc ..." + install_dir="$1" + echo "$0: Installing in specified location - $install_dir ..." fi - install_dir=$install_loc/kselftest_install - -# Create install directory - mkdir -p $install_dir -# Build tests - KSFT_INSTALL_PATH=$install_dir make install + # Build tests + KSFT_INSTALL_PATH="$install_dir" make install } main "$@" diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index 4911fc77d0f6..d1cf9f6e0e6b 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -55,7 +55,7 @@ static void test_dump_stack(void) #pragma GCC diagnostic pop } -static pid_t gettid(void) +static pid_t _gettid(void) { return syscall(SYS_gettid); } @@ -72,7 +72,7 @@ test_assert(bool exp, const char *exp_str, fprintf(stderr, "==== Test Assertion Failure ====\n" " %s:%u: %s\n" " pid=%d tid=%d - %s\n", - file, line, exp_str, getpid(), gettid(), + file, line, exp_str, getpid(), _gettid(), strerror(errno)); test_dump_stack(); if (fmt) { diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh index 5511dddc5c2d..00a416fbc0ef 100755 --- a/tools/testing/selftests/lib/bitmap.sh +++ b/tools/testing/selftests/lib/bitmap.sh @@ -1,3 +1,3 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -$(dirname $0)/../kselftest_module.sh "bitmap" test_bitmap +$(dirname $0)/../kselftest/module.sh "bitmap" test_bitmap diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh index 43b28f24e453..370b79a9cb2e 100755 --- a/tools/testing/selftests/lib/prime_numbers.sh +++ b/tools/testing/selftests/lib/prime_numbers.sh @@ -1,4 +1,4 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # Checks fast/slow prime_number generation for inconsistencies -$(dirname $0)/../kselftest_module.sh "prime numbers" prime_numbers selftest=65536 +$(dirname $0)/../kselftest/module.sh "prime numbers" prime_numbers selftest=65536 diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh index 2ffa61da0296..05f4544e87f9 100755 --- a/tools/testing/selftests/lib/printf.sh +++ b/tools/testing/selftests/lib/printf.sh @@ -1,4 +1,4 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # Tests the printf infrastructure using test_printf kernel module. -$(dirname $0)/../kselftest_module.sh "printf" test_printf +$(dirname $0)/../kselftest/module.sh "printf" test_printf diff --git a/tools/testing/selftests/lib/strscpy.sh b/tools/testing/selftests/lib/strscpy.sh index 71f2be6afba6..be60ef6e1a7f 100755 --- a/tools/testing/selftests/lib/strscpy.sh +++ b/tools/testing/selftests/lib/strscpy.sh @@ -1,3 +1,3 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0+ -$(dirname $0)/../kselftest_module.sh "strscpy*" test_strscpy +$(dirname $0)/../kselftest/module.sh "strscpy*" test_strscpy diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 53f598f06647..34df4c8882af 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -105,8 +105,8 @@ static void do_recv_one(int fdr, struct timed_send *ts) tstop = (gettime_ns() - glob_tstart) / 1000; texpect = ts->delay_us >= 0 ? ts->delay_us : 0; - fprintf(stderr, "payload:%c delay:%ld expected:%ld (us)\n", - rbuf[0], tstop, texpect); + fprintf(stderr, "payload:%c delay:%lld expected:%lld (us)\n", + rbuf[0], (long long)tstop, (long long)texpect); if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 31ced79f4f25..33035d1b3f6d 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -71,7 +71,7 @@ #define MSG_ZEROCOPY 0x4000000 #endif -#define FILE_SZ (1UL << 35) +#define FILE_SZ (1ULL << 35) static int cfg_family = AF_INET6; static socklen_t cfg_alen = sizeof(struct sockaddr_in6); static int cfg_port = 8787; @@ -155,7 +155,7 @@ void *child_thread(void *arg) socklen_t zc_len = sizeof(zc); int res; - zc.address = (__u64)addr; + zc.address = (__u64)((unsigned long)addr); zc.length = chunk_size; zc.recv_skip_hint = 0; res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, @@ -302,7 +302,7 @@ int main(int argc, char *argv[]) { struct sockaddr_storage listenaddr, addr; unsigned int max_pacing_rate = 0; - unsigned long total = 0; + size_t total = 0; char *host = NULL; int fd, c, on = 1; char *buffer; @@ -417,7 +417,7 @@ int main(int argc, char *argv[]) zflg = 0; } while (total < FILE_SZ) { - long wr = FILE_SZ - total; + ssize_t wr = FILE_SZ - total; if (wr > chunk_size) wr = chunk_size; diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 4c285b6e1db8..1c8f194d6556 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -898,6 +898,114 @@ TEST_F(tls, nonblocking) } } +static void +test_mutliproc(struct __test_metadata *_metadata, struct _test_data_tls *self, + bool sendpg, unsigned int n_readers, unsigned int n_writers) +{ + const unsigned int n_children = n_readers + n_writers; + const size_t data = 6 * 1000 * 1000; + const size_t file_sz = data / 100; + size_t read_bias, write_bias; + int i, fd, child_id; + char buf[file_sz]; + pid_t pid; + + /* Only allow multiples for simplicity */ + ASSERT_EQ(!(n_readers % n_writers) || !(n_writers % n_readers), true); + read_bias = n_writers / n_readers ?: 1; + write_bias = n_readers / n_writers ?: 1; + + /* prep a file to send */ + fd = open("/tmp/", O_TMPFILE | O_RDWR, 0600); + ASSERT_GE(fd, 0); + + memset(buf, 0xac, file_sz); + ASSERT_EQ(write(fd, buf, file_sz), file_sz); + + /* spawn children */ + for (child_id = 0; child_id < n_children; child_id++) { + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) + break; + } + + /* parent waits for all children */ + if (pid) { + for (i = 0; i < n_children; i++) { + int status; + + wait(&status); + EXPECT_EQ(status, 0); + } + + return; + } + + /* Split threads for reading and writing */ + if (child_id < n_readers) { + size_t left = data * read_bias; + char rb[8001]; + + while (left) { + int res; + + res = recv(self->cfd, rb, + left > sizeof(rb) ? sizeof(rb) : left, 0); + + EXPECT_GE(res, 0); + left -= res; + } + } else { + size_t left = data * write_bias; + + while (left) { + int res; + + ASSERT_EQ(lseek(fd, 0, SEEK_SET), 0); + if (sendpg) + res = sendfile(self->fd, fd, NULL, + left > file_sz ? file_sz : left); + else + res = send(self->fd, buf, + left > file_sz ? file_sz : left, 0); + + EXPECT_GE(res, 0); + left -= res; + } + } +} + +TEST_F(tls, mutliproc_even) +{ + test_mutliproc(_metadata, self, false, 6, 6); +} + +TEST_F(tls, mutliproc_readers) +{ + test_mutliproc(_metadata, self, false, 4, 12); +} + +TEST_F(tls, mutliproc_writers) +{ + test_mutliproc(_metadata, self, false, 10, 2); +} + +TEST_F(tls, mutliproc_sendpage_even) +{ + test_mutliproc(_metadata, self, true, 6, 6); +} + +TEST_F(tls, mutliproc_sendpage_readers) +{ + test_mutliproc(_metadata, self, true, 4, 12); +} + +TEST_F(tls, mutliproc_sendpage_writers) +{ + test_mutliproc(_metadata, self, true, 10, 2); +} + TEST_F(tls, control_msg) { if (self->notls) diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 614b31aad168..c66da6ffd6d8 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -440,7 +440,8 @@ static bool __send_one(int fd, struct msghdr *msg, int flags) if (ret == -1) error(1, errno, "sendmsg"); if (ret != msg->msg_iov->iov_len) - error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len); + error(1, 0, "sendto: %d != %llu", ret, + (unsigned long long)msg->msg_iov->iov_len); if (msg->msg_flags) error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags); diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index ada99496634a..17512a43885e 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -405,7 +405,8 @@ static int send_udp_segment(int fd, char *data) if (ret == -1) error(1, errno, "sendmsg"); if (ret != iov.iov_len) - error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len); + error(1, 0, "sendmsg: %u != %llu\n", ret, + (unsigned long long)iov.iov_len); return 1; } diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c index 47b7473dedef..e6aa00a183bc 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-002.c +++ b/tools/testing/selftests/proc/proc-self-map-files-002.c @@ -47,7 +47,11 @@ static void fail(const char *fmt, unsigned long a, unsigned long b) int main(void) { const int PAGE_SIZE = sysconf(_SC_PAGESIZE); - const unsigned long va_max = 1UL << 32; + /* + * va_max must be enough bigger than vm.mmap_min_addr, which is + * 64KB/32KB by default. (depends on CONFIG_LSM_MMAP_MIN_ADDR) + */ + const unsigned long va_max = 1UL << 20; unsigned long va; void *p; int fd; diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index bd4a7247b44f..c0dd10257df5 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -44,6 +44,46 @@ static int clock_adjtime(clockid_t id, struct timex *tx) } #endif +static void show_flag_test(int rq_index, unsigned int flags, int err) +{ + printf("PTP_EXTTS_REQUEST%c flags 0x%08x : (%d) %s\n", + rq_index ? '1' + rq_index : ' ', + flags, err, strerror(errno)); + /* sigh, uClibc ... */ + errno = 0; +} + +static void do_flag_test(int fd, unsigned int index) +{ + struct ptp_extts_request extts_request; + unsigned long request[2] = { + PTP_EXTTS_REQUEST, + PTP_EXTTS_REQUEST2, + }; + unsigned int enable_flags[5] = { + PTP_ENABLE_FEATURE, + PTP_ENABLE_FEATURE | PTP_RISING_EDGE, + PTP_ENABLE_FEATURE | PTP_FALLING_EDGE, + PTP_ENABLE_FEATURE | PTP_RISING_EDGE | PTP_FALLING_EDGE, + PTP_ENABLE_FEATURE | (PTP_EXTTS_VALID_FLAGS + 1), + }; + int err, i, j; + + memset(&extts_request, 0, sizeof(extts_request)); + extts_request.index = index; + + for (i = 0; i < 2; i++) { + for (j = 0; j < 5; j++) { + extts_request.flags = enable_flags[j]; + err = ioctl(fd, request[i], &extts_request); + show_flag_test(i, extts_request.flags, err); + + extts_request.flags = 0; + err = ioctl(fd, request[i], &extts_request); + } + } +} + static clockid_t get_clockid(int fd) { #define CLOCKFD 3 @@ -96,7 +136,8 @@ static void usage(char *progname) " -s set the ptp clock time from the system time\n" " -S set the system time from the ptp clock time\n" " -t val shift the ptp clock time by 'val' seconds\n" - " -T val set the ptp clock time to 'val' seconds\n", + " -T val set the ptp clock time to 'val' seconds\n" + " -z test combinations of rising/falling external time stamp flags\n", progname); } @@ -122,6 +163,7 @@ int main(int argc, char *argv[]) int adjtime = 0; int capabilities = 0; int extts = 0; + int flagtest = 0; int gettime = 0; int index = 0; int list_pins = 0; @@ -138,7 +180,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:v"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:z"))) { switch (c) { case 'c': capabilities = 1; @@ -191,6 +233,9 @@ int main(int argc, char *argv[]) settime = 3; seconds = atoi(optarg); break; + case 'z': + flagtest = 1; + break; case 'h': usage(progname); return 0; @@ -322,6 +367,10 @@ int main(int argc, char *argv[]) } } + if (flagtest) { + do_flag_test(fd, index); + } + if (list_pins) { int n_pins = 0; if (ioctl(fd, PTP_CLOCK_GETCAPS, &caps)) { diff --git a/tools/testing/selftests/sync/sync.c b/tools/testing/selftests/sync/sync.c index f3d599f249b9..7741c0518d18 100644 --- a/tools/testing/selftests/sync/sync.c +++ b/tools/testing/selftests/sync/sync.c @@ -109,7 +109,7 @@ static struct sync_file_info *sync_file_info(int fd) return NULL; } - info->sync_fence_info = (uint64_t)fence_info; + info->sync_fence_info = (uint64_t)(unsigned long)fence_info; err = ioctl(fd, SYNC_IOC_FILE_INFO, info); if (err < 0) { @@ -124,7 +124,7 @@ static struct sync_file_info *sync_file_info(int fd) static void sync_file_info_free(struct sync_file_info *info) { - free((void *)info->sync_fence_info); + free((void *)(unsigned long)info->sync_fence_info); free(info); } @@ -152,7 +152,7 @@ int sync_fence_count_with_status(int fd, int status) if (!info) return -1; - fence_info = (struct sync_fence_info *)info->sync_fence_info; + fence_info = (struct sync_fence_info *)(unsigned long)info->sync_fence_info; for (i = 0 ; i < info->num_fences ; i++) { if (fence_info[i].status == status) count++; diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9534dc2bc929..7f9a8a8c31da 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,5 +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/') CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) LDLIBS = -lrt @@ -16,8 +18,11 @@ TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd + +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range +endif TEST_PROGS := run_vmtests diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index 951c507a27f7..a692ea828317 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -58,6 +58,14 @@ else exit 1 fi +#filter 64bit architectures +ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64" +if [ -z $ARCH ]; then + ARCH=`uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/'` +fi +VADDR64=0 +echo "$ARCH64STR" | grep $ARCH && VADDR64=1 + mkdir $mnt mount -t hugetlbfs none $mnt @@ -189,6 +197,7 @@ else echo "[PASS]" fi +if [ $VADDR64 -ne 0 ]; then echo "-----------------------------" echo "running virtual_address_range" echo "-----------------------------" @@ -210,6 +219,7 @@ if [ $? -ne 0 ]; then else echo "[PASS]" fi +fi # VADDR64 echo "------------------------------------" echo "running vmalloc stability smoke test" diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d6f0696d98ef..13efc291b1c7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -50,6 +50,7 @@ #include <linux/bsearch.h> #include <linux/io.h> #include <linux/lockdep.h> +#include <linux/kthread.h> #include <asm/processor.h> #include <asm/ioctl.h> @@ -121,9 +122,22 @@ static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #define KVM_COMPAT(c) .compat_ioctl = (c) #else +/* + * For architectures that don't implement a compat infrastructure, + * adopt a double line of defense: + * - Prevent a compat task from opening /dev/kvm + * - If the open has been done by a 64bit task, and the KVM fd + * passed to a compat task, let the ioctls fail. + */ static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { return -EINVAL; } -#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl + +static int kvm_no_compat_open(struct inode *inode, struct file *file) +{ + return is_compat_task() ? -ENODEV : 0; +} +#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ + .open = kvm_no_compat_open #endif static int hardware_enable_all(void); static void hardware_disable_all(void); @@ -149,10 +163,30 @@ __weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, return 0; } +bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) +{ + /* + * The metadata used by is_zone_device_page() to determine whether or + * not a page is ZONE_DEVICE is guaranteed to be valid if and only if + * the device has been pinned, e.g. by get_user_pages(). WARN if the + * page_count() is zero to help detect bad usage of this helper. + */ + if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn)))) + return false; + + return is_zone_device_page(pfn_to_page(pfn)); +} + bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { + /* + * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting + * perspective they are "normal" pages, albeit with slightly different + * usage rules. + */ if (pfn_valid(pfn)) - return PageReserved(pfn_to_page(pfn)); + return PageReserved(pfn_to_page(pfn)) && + !kvm_is_zone_device_pfn(pfn); return true; } @@ -625,6 +659,23 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) return 0; } +/* + * Called after the VM is otherwise initialized, but just before adding it to + * the vm_list. + */ +int __weak kvm_arch_post_init_vm(struct kvm *kvm) +{ + return 0; +} + +/* + * Called just after removing the VM from the vm_list, but before doing any + * other destruction. + */ +void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ +} + static struct kvm *kvm_create_vm(unsigned long type) { struct kvm *kvm = kvm_arch_alloc_vm(); @@ -645,6 +696,12 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + if (init_srcu_struct(&kvm->srcu)) + goto out_err_no_srcu; + if (init_srcu_struct(&kvm->irq_srcu)) + goto out_err_no_irq_srcu; + + refcount_set(&kvm->users_count, 1); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_memslots *slots = kvm_alloc_memslots(); @@ -662,7 +719,6 @@ static struct kvm *kvm_create_vm(unsigned long type) goto out_err_no_arch_destroy_vm; } - refcount_set(&kvm->users_count, 1); r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; @@ -675,13 +731,12 @@ static struct kvm *kvm_create_vm(unsigned long type) INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif - if (init_srcu_struct(&kvm->srcu)) - goto out_err_no_srcu; - if (init_srcu_struct(&kvm->irq_srcu)) - goto out_err_no_irq_srcu; - r = kvm_init_mmu_notifier(kvm); if (r) + goto out_err_no_mmu_notifier; + + r = kvm_arch_post_init_vm(kvm); + if (r) goto out_err; mutex_lock(&kvm_lock); @@ -693,19 +748,24 @@ static struct kvm *kvm_create_vm(unsigned long type) return kvm; out_err: - cleanup_srcu_struct(&kvm->irq_srcu); -out_err_no_irq_srcu: - cleanup_srcu_struct(&kvm->srcu); -out_err_no_srcu: +#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) + if (kvm->mmu_notifier.ops) + mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); +#endif +out_err_no_mmu_notifier: hardware_disable_all(); out_err_no_disable: kvm_arch_destroy_vm(kvm); - WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); out_err_no_arch_destroy_vm: + WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); + cleanup_srcu_struct(&kvm->irq_srcu); +out_err_no_irq_srcu: + cleanup_srcu_struct(&kvm->srcu); +out_err_no_srcu: kvm_arch_free_vm(kvm); mmdrop(current->mm); return ERR_PTR(r); @@ -737,6 +797,8 @@ static void kvm_destroy_vm(struct kvm *kvm) mutex_lock(&kvm_lock); list_del(&kvm->vm_list); mutex_unlock(&kvm_lock); + kvm_arch_pre_destroy_vm(kvm); + kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { struct kvm_io_bus *bus = kvm_get_bus(kvm, i); @@ -1857,7 +1919,7 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); void kvm_set_pfn_dirty(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn)) { + if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) { struct page *page = pfn_to_page(pfn); SetPageDirty(page); @@ -1867,7 +1929,7 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); void kvm_set_pfn_accessed(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn)) + if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) mark_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); @@ -4371,3 +4433,86 @@ void kvm_exit(void) kvm_vfio_ops_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); + +struct kvm_vm_worker_thread_context { + struct kvm *kvm; + struct task_struct *parent; + struct completion init_done; + kvm_vm_thread_fn_t thread_fn; + uintptr_t data; + int err; +}; + +static int kvm_vm_worker_thread(void *context) +{ + /* + * The init_context is allocated on the stack of the parent thread, so + * we have to locally copy anything that is needed beyond initialization + */ + struct kvm_vm_worker_thread_context *init_context = context; + struct kvm *kvm = init_context->kvm; + kvm_vm_thread_fn_t thread_fn = init_context->thread_fn; + uintptr_t data = init_context->data; + int err; + + err = kthread_park(current); + /* kthread_park(current) is never supposed to return an error */ + WARN_ON(err != 0); + if (err) + goto init_complete; + + err = cgroup_attach_task_all(init_context->parent, current); + if (err) { + kvm_err("%s: cgroup_attach_task_all failed with err %d\n", + __func__, err); + goto init_complete; + } + + set_user_nice(current, task_nice(init_context->parent)); + +init_complete: + init_context->err = err; + complete(&init_context->init_done); + init_context = NULL; + + if (err) + return err; + + /* Wait to be woken up by the spawner before proceeding. */ + kthread_parkme(); + + if (!kthread_should_stop()) + err = thread_fn(kvm, data); + + return err; +} + +int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, + uintptr_t data, const char *name, + struct task_struct **thread_ptr) +{ + struct kvm_vm_worker_thread_context init_context = {}; + struct task_struct *thread; + + *thread_ptr = NULL; + init_context.kvm = kvm; + init_context.parent = current; + init_context.thread_fn = thread_fn; + init_context.data = data; + init_completion(&init_context.init_done); + + thread = kthread_run(kvm_vm_worker_thread, &init_context, + "%s-%d", name, task_pid_nr(current)); + if (IS_ERR(thread)) + return PTR_ERR(thread); + + /* kthread_run is never supposed to return NULL */ + WARN_ON(thread == NULL); + + wait_for_completion(&init_context.init_done); + + if (!init_context.err) + *thread_ptr = thread; + + return init_context.err; +} |