diff options
410 files changed, 4117 insertions, 1967 deletions
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 5b58fc4e1268..4574352d6ff4 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -61,8 +61,8 @@ The ``ice`` driver reports the following versions - running - ICE OS Default Package - The name of the DDP package that is active in the device. The DDP - package is loaded by the driver during initialization. Each varation - of DDP package shall have a unique name. + package is loaded by the driver during initialization. Each + variation of the DDP package has a unique name. * - ``fw.app`` - running - 1.3.1.0 diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index dcc252634cf9..b6833c7bb474 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -28,3 +28,5 @@ KVM arm/index devices/index + + running-nested-guests diff --git a/Documentation/virt/kvm/running-nested-guests.rst b/Documentation/virt/kvm/running-nested-guests.rst new file mode 100644 index 000000000000..d0a1fc754c84 --- /dev/null +++ b/Documentation/virt/kvm/running-nested-guests.rst @@ -0,0 +1,276 @@ +============================== +Running nested guests with KVM +============================== + +A nested guest is the ability to run a guest inside another guest (it +can be KVM-based or a different hypervisor). The straightforward +example is a KVM guest that in turn runs on a KVM guest (the rest of +this document is built on this example):: + + .----------------. .----------------. + | | | | + | L2 | | L2 | + | (Nested Guest) | | (Nested Guest) | + | | | | + |----------------'--'----------------| + | | + | L1 (Guest Hypervisor) | + | KVM (/dev/kvm) | + | | + .------------------------------------------------------. + | L0 (Host Hypervisor) | + | KVM (/dev/kvm) | + |------------------------------------------------------| + | Hardware (with virtualization extensions) | + '------------------------------------------------------' + +Terminology: + +- L0 – level-0; the bare metal host, running KVM + +- L1 – level-1 guest; a VM running on L0; also called the "guest + hypervisor", as it itself is capable of running KVM. + +- L2 – level-2 guest; a VM running on L1, this is the "nested guest" + +.. note:: The above diagram is modelled after the x86 architecture; + s390x, ppc64 and other architectures are likely to have + a different design for nesting. + + For example, s390x always has an LPAR (LogicalPARtition) + hypervisor running on bare metal, adding another layer and + resulting in at least four levels in a nested setup — L0 (bare + metal, running the LPAR hypervisor), L1 (host hypervisor), L2 + (guest hypervisor), L3 (nested guest). + + This document will stick with the three-level terminology (L0, + L1, and L2) for all architectures; and will largely focus on + x86. + + +Use Cases +--------- + +There are several scenarios where nested KVM can be useful, to name a +few: + +- As a developer, you want to test your software on different operating + systems (OSes). Instead of renting multiple VMs from a Cloud + Provider, using nested KVM lets you rent a large enough "guest + hypervisor" (level-1 guest). This in turn allows you to create + multiple nested guests (level-2 guests), running different OSes, on + which you can develop and test your software. + +- Live migration of "guest hypervisors" and their nested guests, for + load balancing, disaster recovery, etc. + +- VM image creation tools (e.g. ``virt-install``, etc) often run + their own VM, and users expect these to work inside a VM. + +- Some OSes use virtualization internally for security (e.g. to let + applications run safely in isolation). + + +Enabling "nested" (x86) +----------------------- + +From Linux kernel v4.19 onwards, the ``nested`` KVM parameter is enabled +by default for Intel and AMD. (Though your Linux distribution might +override this default.) + +In case you are running a Linux kernel older than v4.19, to enable +nesting, set the ``nested`` KVM module parameter to ``Y`` or ``1``. To +persist this setting across reboots, you can add it in a config file, as +shown below: + +1. On the bare metal host (L0), list the kernel modules and ensure that + the KVM modules:: + + $ lsmod | grep -i kvm + kvm_intel 133627 0 + kvm 435079 1 kvm_intel + +2. Show information for ``kvm_intel`` module:: + + $ modinfo kvm_intel | grep -i nested + parm: nested:bool + +3. For the nested KVM configuration to persist across reboots, place the + below in ``/etc/modprobed/kvm_intel.conf`` (create the file if it + doesn't exist):: + + $ cat /etc/modprobe.d/kvm_intel.conf + options kvm-intel nested=y + +4. Unload and re-load the KVM Intel module:: + + $ sudo rmmod kvm-intel + $ sudo modprobe kvm-intel + +5. Verify if the ``nested`` parameter for KVM is enabled:: + + $ cat /sys/module/kvm_intel/parameters/nested + Y + +For AMD hosts, the process is the same as above, except that the module +name is ``kvm-amd``. + + +Additional nested-related kernel parameters (x86) +------------------------------------------------- + +If your hardware is sufficiently advanced (Intel Haswell processor or +higher, which has newer hardware virt extensions), the following +additional features will also be enabled by default: "Shadow VMCS +(Virtual Machine Control Structure)", APIC Virtualization on your bare +metal host (L0). Parameters for Intel hosts:: + + $ cat /sys/module/kvm_intel/parameters/enable_shadow_vmcs + Y + + $ cat /sys/module/kvm_intel/parameters/enable_apicv + Y + + $ cat /sys/module/kvm_intel/parameters/ept + Y + +.. note:: If you suspect your L2 (i.e. nested guest) is running slower, + ensure the above are enabled (particularly + ``enable_shadow_vmcs`` and ``ept``). + + +Starting a nested guest (x86) +----------------------------- + +Once your bare metal host (L0) is configured for nesting, you should be +able to start an L1 guest with:: + + $ qemu-kvm -cpu host [...] + +The above will pass through the host CPU's capabilities as-is to the +gues); or for better live migration compatibility, use a named CPU +model supported by QEMU. e.g.:: + + $ qemu-kvm -cpu Haswell-noTSX-IBRS,vmx=on + +then the guest hypervisor will subsequently be capable of running a +nested guest with accelerated KVM. + + +Enabling "nested" (s390x) +------------------------- + +1. On the host hypervisor (L0), enable the ``nested`` parameter on + s390x:: + + $ rmmod kvm + $ modprobe kvm nested=1 + +.. note:: On s390x, the kernel parameter ``hpage`` is mutually exclusive + with the ``nested`` paramter — i.e. to be able to enable + ``nested``, the ``hpage`` parameter *must* be disabled. + +2. The guest hypervisor (L1) must be provided with the ``sie`` CPU + feature — with QEMU, this can be done by using "host passthrough" + (via the command-line ``-cpu host``). + +3. Now the KVM module can be loaded in the L1 (guest hypervisor):: + + $ modprobe kvm + + +Live migration with nested KVM +------------------------------ + +Migrating an L1 guest, with a *live* nested guest in it, to another +bare metal host, works as of Linux kernel 5.3 and QEMU 4.2.0 for +Intel x86 systems, and even on older versions for s390x. + +On AMD systems, once an L1 guest has started an L2 guest, the L1 guest +should no longer be migrated or saved (refer to QEMU documentation on +"savevm"/"loadvm") until the L2 guest shuts down. Attempting to migrate +or save-and-load an L1 guest while an L2 guest is running will result in +undefined behavior. You might see a ``kernel BUG!`` entry in ``dmesg``, a +kernel 'oops', or an outright kernel panic. Such a migrated or loaded L1 +guest can no longer be considered stable or secure, and must be restarted. +Migrating an L1 guest merely configured to support nesting, while not +actually running L2 guests, is expected to function normally even on AMD +systems but may fail once guests are started. + +Migrating an L2 guest is always expected to succeed, so all the following +scenarios should work even on AMD systems: + +- Migrating a nested guest (L2) to another L1 guest on the *same* bare + metal host. + +- Migrating a nested guest (L2) to another L1 guest on a *different* + bare metal host. + +- Migrating a nested guest (L2) to a bare metal host. + +Reporting bugs from nested setups +----------------------------------- + +Debugging "nested" problems can involve sifting through log files across +L0, L1 and L2; this can result in tedious back-n-forth between the bug +reporter and the bug fixer. + +- Mention that you are in a "nested" setup. If you are running any kind + of "nesting" at all, say so. Unfortunately, this needs to be called + out because when reporting bugs, people tend to forget to even + *mention* that they're using nested virtualization. + +- Ensure you are actually running KVM on KVM. Sometimes people do not + have KVM enabled for their guest hypervisor (L1), which results in + them running with pure emulation or what QEMU calls it as "TCG", but + they think they're running nested KVM. Thus confusing "nested Virt" + (which could also mean, QEMU on KVM) with "nested KVM" (KVM on KVM). + +Information to collect (generic) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The following is not an exhaustive list, but a very good starting point: + + - Kernel, libvirt, and QEMU version from L0 + + - Kernel, libvirt and QEMU version from L1 + + - QEMU command-line of L1 -- when using libvirt, you'll find it here: + ``/var/log/libvirt/qemu/instance.log`` + + - QEMU command-line of L2 -- as above, when using libvirt, get the + complete libvirt-generated QEMU command-line + + - ``cat /sys/cpuinfo`` from L0 + + - ``cat /sys/cpuinfo`` from L1 + + - ``lscpu`` from L0 + + - ``lscpu`` from L1 + + - Full ``dmesg`` output from L0 + + - Full ``dmesg`` output from L1 + +x86-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Both the below commands, ``x86info`` and ``dmidecode``, should be +available on most Linux distributions with the same name: + + - Output of: ``x86info -a`` from L0 + + - Output of: ``x86info -a`` from L1 + + - Output of: ``dmidecode`` from L0 + + - Output of: ``dmidecode`` from L1 + +s390x-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Along with the earlier mentioned generic details, the below is +also recommended: + + - ``/proc/sysinfo`` from L1; this will also include the info from L0 diff --git a/MAINTAINERS b/MAINTAINERS index 2926327e4976..091ec22c1a23 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3936,11 +3936,9 @@ F: arch/powerpc/platforms/cell/ CEPH COMMON CODE (LIBCEPH) M: Ilya Dryomov <idryomov@gmail.com> M: Jeff Layton <jlayton@kernel.org> -M: Sage Weil <sage@redhat.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: include/linux/ceph/ F: include/linux/crush/ @@ -3948,12 +3946,10 @@ F: net/ceph/ CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH) M: Jeff Layton <jlayton@kernel.org> -M: Sage Weil <sage@redhat.com> M: Ilya Dryomov <idryomov@gmail.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/filesystems/ceph.rst F: fs/ceph/ @@ -5935,9 +5931,9 @@ F: lib/dynamic_debug.c DYNAMIC INTERRUPT MODERATION M: Tal Gilboa <talgi@mellanox.com> S: Maintained +F: Documentation/networking/net_dim.rst F: include/linux/dim.h F: lib/dim/ -F: Documentation/networking/net_dim.rst DZ DECSTATION DZ11 SERIAL DRIVER M: "Maciej W. Rozycki" <macro@linux-mips.org> @@ -7119,9 +7115,10 @@ F: include/uapi/asm-generic/ GENERIC PHY FRAMEWORK M: Kishon Vijay Abraham I <kishon@ti.com> +M: Vinod Koul <vkoul@kernel.org> L: linux-kernel@vger.kernel.org S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kishon/linux-phy.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git F: Documentation/devicetree/bindings/phy/ F: drivers/phy/ F: include/linux/phy/ @@ -7746,11 +7743,6 @@ L: platform-driver-x86@vger.kernel.org S: Orphan F: drivers/platform/x86/tc1100-wmi.c -HP100: Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series -M: Jaroslav Kysela <perex@perex.cz> -S: Obsolete -F: drivers/staging/hp/hp100.* - HPET: High Precision Event Timers driver M: Clemens Ladisch <clemens@ladisch.de> S: Maintained @@ -14102,12 +14094,10 @@ F: drivers/media/radio/radio-tea5777.c RADOS BLOCK DEVICE (RBD) M: Ilya Dryomov <idryomov@gmail.com> -M: Sage Weil <sage@redhat.com> R: Dongsheng Yang <dongsheng.yang@easystack.cn> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/ABI/testing/sysfs-bus-rbd F: drivers/block/rbd.c @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -729,10 +729,6 @@ else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os endif -ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED -KBUILD_CFLAGS += -Wno-maybe-uninitialized -endif - # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0) KBUILD_CFLAGS += $(call cc-option,-fno-allow-store-data-races) @@ -881,6 +877,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign # disable stringop warnings in gcc 8+ KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) +# We'll want to enable this eventually, but it's not going away for 5.7 at least +KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow) + +# Another good warning that we'll want to enable eventually +KBUILD_CFLAGS += $(call cc-disable-warning, restrict) + +# Enabled with W=2, disabled by default as noisy +KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c index 6fdb0ac62b3d..59da6c0b63b6 100644 --- a/arch/arm/crypto/chacha-glue.c +++ b/arch/arm/crypto/chacha-glue.c @@ -91,9 +91,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, return; } - kernel_neon_begin(); - chacha_doneon(state, dst, src, bytes, nrounds); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_neon_begin(); + chacha_doneon(state, dst, src, todo, nrounds); + kernel_neon_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c index ae5aefc44a4d..ffa8d73fe722 100644 --- a/arch/arm/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c index ceec04ec2f40..13cfef4ae22e 100644 --- a/arch/arm/crypto/poly1305-glue.c +++ b/arch/arm/crypto/poly1305-glue.c @@ -160,13 +160,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); if (static_branch_likely(&have_neon) && do_neon) { - kernel_neon_begin(); - poly1305_blocks_neon(&dctx->h, src, len, 1); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, len, SZ_4K); + + kernel_neon_begin(); + poly1305_blocks_neon(&dctx->h, src, todo, 1); + kernel_neon_end(); + + len -= todo; + src += todo; + } while (len); } else { poly1305_blocks_arm(&dctx->h, src, len, 1); + src += len; } - src += len; nbytes %= POLY1305_BLOCK_SIZE; } diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index e133da303a98..a9151884bc85 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -165,8 +165,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) preempt_enable(); #endif - if (!ret) - *oval = oldval; + /* + * Store unconditionally. If ret != 0 the extra store is the least + * of the worries but GCC cannot figure out that __futex_atomic_op() + * is either setting ret to -EFAULT or storing the old value in + * oldval which results in a uninitialized warning at the call site. + */ + *oval = oldval; return ret; } diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c index 37ca3e889848..af2bbca38e70 100644 --- a/arch/arm64/crypto/chacha-neon-glue.c +++ b/arch/arm64/crypto/chacha-neon-glue.c @@ -87,9 +87,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, !crypto_simd_usable()) return chacha_crypt_generic(state, dst, src, bytes, nrounds); - kernel_neon_begin(); - chacha_doneon(state, dst, src, bytes, nrounds); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_neon_begin(); + chacha_doneon(state, dst, src, todo, nrounds); + kernel_neon_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c index 895d3727c1fb..c5405e6a6db7 100644 --- a/arch/arm64/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index e97b092f56b8..f33ada70c4ed 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -143,13 +143,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); if (static_branch_likely(&have_neon) && crypto_simd_usable()) { - kernel_neon_begin(); - poly1305_blocks_neon(&dctx->h, src, len, 1); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, len, SZ_4K); + + kernel_neon_begin(); + poly1305_blocks_neon(&dctx->h, src, todo, 1); + kernel_neon_end(); + + len -= todo; + src += todo; + } while (len); } else { poly1305_blocks(&dctx->h, src, len, 1); + src += len; } - src += len; nbytes %= POLY1305_BLOCK_SIZE; } diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 8e9c924423b4..a0b144cfaea7 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -177,6 +177,7 @@ void machine_kexec(struct kimage *kimage) * the offline CPUs. Therefore, we must use the __* variant here. */ __flush_icache_range((uintptr_t)reboot_code_buffer, + (uintptr_t)reboot_code_buffer + arm64_relocate_new_kernel_size); /* Flush the kimage list and its buffers. */ diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 23ebe51410f0..50a279d3ddd7 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + + if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { + int i; + + for (i = 0; i < 16; i++) + *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + } out: return err; } diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index d22d0534dd60..90186cf6473e 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -18,6 +18,7 @@ #define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x) #define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x) +#define CPU_SP_EL0_OFFSET (CPU_XREG_OFFSET(30) + 8) .text .pushsection .hyp.text, "ax" @@ -47,6 +48,16 @@ ldp x29, lr, [\ctxt, #CPU_XREG_OFFSET(29)] .endm +.macro save_sp_el0 ctxt, tmp + mrs \tmp, sp_el0 + str \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] +.endm + +.macro restore_sp_el0 ctxt, tmp + ldr \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] + msr sp_el0, \tmp +.endm + /* * u64 __guest_enter(struct kvm_vcpu *vcpu, * struct kvm_cpu_context *host_ctxt); @@ -60,6 +71,9 @@ SYM_FUNC_START(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Save the host's sp_el0 + save_sp_el0 x1, x2 + // Now the host state is stored if we have a pending RAS SError it must // affect the host. If any asynchronous exception is pending we defer // the guest entry. The DSB isn't necessary before v8.2 as any SError @@ -83,6 +97,9 @@ alternative_else_nop_endif // when this feature is enabled for kernel code. ptrauth_switch_to_guest x29, x0, x1, x2 + // Restore the guest's sp_el0 + restore_sp_el0 x29, x0 + // Restore guest regs x0-x17 ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] @@ -130,6 +147,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // Store the guest regs x18-x29, lr save_callee_saved_regs x1 + // Store the guest's sp_el0 + save_sp_el0 x1, x2 + get_host_ctxt x2, x3 // Macro ptrauth_switch_to_guest format: @@ -139,6 +159,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // when this feature is enabled for kernel code. ptrauth_switch_to_host x1, x2, x3, x4, x5 + // Restore the hosts's sp_el0 + restore_sp_el0 x2, x3 + // Now restore the host regs restore_callee_saved_regs x2 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index c2a13ab3c471..9c5cfb04170e 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -198,7 +198,6 @@ SYM_CODE_END(__hyp_panic) .macro invalid_vector label, target = __hyp_panic .align 2 SYM_CODE_START(\label) -\label: b \target SYM_CODE_END(\label) .endm diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 75b1925763f1..6d2df9fe0b5d 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -15,8 +15,9 @@ /* * Non-VHE: Both host and guest must save everything. * - * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate, - * which are handled as part of the el2 return state) on every switch. + * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and + * pstate, which are handled as part of the el2 return state) on every + * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two @@ -26,12 +27,6 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - ctxt->gp_regs.regs.sp = read_sysreg(sp_el0); } static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) @@ -99,12 +94,6 @@ NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - write_sysreg(ctxt->gp_regs.regs.sp, sp_el0); } static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index bbeb6a5a6ba6..0be3355e3499 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); + if (!pmdp) + return NULL; WARN_ON(addr & (sz - 1)); /* diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index e15166b0a16d..ad2f172c26a6 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -521,6 +521,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 74f82cf4f781..a31e1a41913a 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -54,7 +54,7 @@ config RISCV select GENERIC_ARCH_TOPOLOGY if SMP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MMIOWB - select ARCH_HAS_DEBUG_VIRTUAL + select ARCH_HAS_DEBUG_VIRTUAL if MMU select HAVE_EBPF_JIT if MMU select EDAC_SUPPORT select ARCH_HAS_GIGANTIC_PAGE @@ -136,6 +136,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y config SYS_SUPPORTS_HUGETLBFS + depends on MMU def_bool y config STACKTRACE_SUPPORT diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 216286db81c9..d646332e44f1 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -11,14 +11,15 @@ config SOC_SIFIVE This enables support for SiFive SoC platform hardware. config SOC_VIRT - bool "QEMU Virt Machine" - select POWER_RESET_SYSCON - select POWER_RESET_SYSCON_POWEROFF - select GOLDFISH - select RTC_DRV_GOLDFISH - select SIFIVE_PLIC - help - This enables support for QEMU Virt Machine. + bool "QEMU Virt Machine" + select POWER_RESET + select POWER_RESET_SYSCON + select POWER_RESET_SYSCON_POWEROFF + select GOLDFISH + select RTC_DRV_GOLDFISH if RTC_CLASS + select SIFIVE_PLIC + help + This enables support for QEMU Virt Machine. config SOC_KENDRYTE bool "Kendryte K210 SoC" diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 8e18d2c64399..cec462e198ce 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -51,13 +51,10 @@ #define CAUSE_IRQ_FLAG (_AC(1, UL) << (__riscv_xlen - 1)) /* Interrupt causes (minus the high bit) */ -#define IRQ_U_SOFT 0 #define IRQ_S_SOFT 1 #define IRQ_M_SOFT 3 -#define IRQ_U_TIMER 4 #define IRQ_S_TIMER 5 #define IRQ_M_TIMER 7 -#define IRQ_U_EXT 8 #define IRQ_S_EXT 9 #define IRQ_M_EXT 11 diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 1bb0cd04aec3..5ce50468aff1 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -8,6 +8,7 @@ #ifndef _ASM_RISCV_HWCAP_H #define _ASM_RISCV_HWCAP_H +#include <linux/bits.h> #include <uapi/asm/hwcap.h> #ifndef __ASSEMBLY__ @@ -22,6 +23,27 @@ enum { }; extern unsigned long elf_hwcap; + +#define RISCV_ISA_EXT_a ('a' - 'a') +#define RISCV_ISA_EXT_c ('c' - 'a') +#define RISCV_ISA_EXT_d ('d' - 'a') +#define RISCV_ISA_EXT_f ('f' - 'a') +#define RISCV_ISA_EXT_h ('h' - 'a') +#define RISCV_ISA_EXT_i ('i' - 'a') +#define RISCV_ISA_EXT_m ('m' - 'a') +#define RISCV_ISA_EXT_s ('s' - 'a') +#define RISCV_ISA_EXT_u ('u' - 'a') + +#define RISCV_ISA_EXT_MAX 64 + +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); + +#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext) + +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit); +#define riscv_isa_extension_available(isa_bitmap, ext) \ + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) + #endif #endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index a2c809df2733..56053c9838b2 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -16,6 +16,8 @@ #ifndef CONFIG_MMU #define pgprot_noncached(x) (x) +#define pgprot_writecombine(x) (x) +#define pgprot_device(x) (x) #endif /* CONFIG_MMU */ /* Generic IO read/write. These perform native-endian accesses. */ diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h index bb4091ff4a21..0b2333e71fdc 100644 --- a/arch/riscv/include/asm/mmiowb.h +++ b/arch/riscv/include/asm/mmiowb.h @@ -9,6 +9,7 @@ */ #define mmiowb() __asm__ __volatile__ ("fence o,w" : : : "memory"); +#include <linux/smp.h> #include <asm-generic/mmiowb.h> #endif /* _ASM_RISCV_MMIOWB_H */ diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h index 0234048b12bc..062efd3a1d5d 100644 --- a/arch/riscv/include/asm/perf_event.h +++ b/arch/riscv/include/asm/perf_event.h @@ -12,19 +12,14 @@ #include <linux/ptrace.h> #include <linux/interrupt.h> +#ifdef CONFIG_RISCV_BASE_PMU #define RISCV_BASE_COUNTERS 2 /* * The RISCV_MAX_COUNTERS parameter should be specified. */ -#ifdef CONFIG_RISCV_BASE_PMU #define RISCV_MAX_COUNTERS 2 -#endif - -#ifndef RISCV_MAX_COUNTERS -#error "Please provide a valid RISCV_MAX_COUNTERS for the PMU." -#endif /* * These are the indexes of bits in counteren register *minus* 1, @@ -82,6 +77,7 @@ struct riscv_pmu { int irq; }; +#endif #ifdef CONFIG_PERF_EVENTS #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs #endif diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 9c188ad2e52d..35b60035b6b0 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -470,12 +470,15 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #else /* CONFIG_MMU */ +#define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL #define VMALLOC_START 0 #define TASK_SIZE 0xffffffffUL +static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {} + #endif /* !CONFIG_MMU */ #define kern_addr_valid(addr) (1) /* FIXME */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index c38df4771c09..4c5bae7ca01c 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -22,14 +22,6 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif -#ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_ro(void); -void set_kernel_text_rw(void); -#else -static inline void set_kernel_text_ro(void) { } -static inline void set_kernel_text_rw(void) { } -#endif - int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 86c83081044f..d8bbd3207100 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_RISCV_BASE_PMU) += perf_event.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o obj-$(CONFIG_RISCV_SBI) += sbi.o diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c index c4c33bf02369..0ec22354018c 100644 --- a/arch/riscv/kernel/cpu_ops.c +++ b/arch/riscv/kernel/cpu_ops.c @@ -15,8 +15,8 @@ const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; -void *__cpu_up_stack_pointer[NR_CPUS]; -void *__cpu_up_task_pointer[NR_CPUS]; +void *__cpu_up_stack_pointer[NR_CPUS] __section(.data); +void *__cpu_up_task_pointer[NR_CPUS] __section(.data); extern const struct cpu_operations cpu_ops_sbi; extern const struct cpu_operations cpu_ops_spinwait; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index a5ad00043104..ac202f44a670 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -6,6 +6,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/bitmap.h> #include <linux/of.h> #include <asm/processor.h> #include <asm/hwcap.h> @@ -13,15 +14,57 @@ #include <asm/switch_to.h> unsigned long elf_hwcap __read_mostly; + +/* Host ISA bitmap */ +static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; + #ifdef CONFIG_FPU bool has_fpu __read_mostly; #endif +/** + * riscv_isa_extension_base() - Get base extension word + * + * @isa_bitmap: ISA bitmap to use + * Return: base extension word as unsigned long value + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap) +{ + if (!isa_bitmap) + return riscv_isa[0]; + return isa_bitmap[0]; +} +EXPORT_SYMBOL_GPL(riscv_isa_extension_base); + +/** + * __riscv_isa_extension_available() - Check whether given extension + * is available or not + * + * @isa_bitmap: ISA bitmap to use + * @bit: bit position of the desired extension + * Return: true or false + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) +{ + const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa; + + if (bit >= RISCV_ISA_EXT_MAX) + return false; + + return test_bit(bit, bmap) ? true : false; +} +EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); + void riscv_fill_hwcap(void) { struct device_node *node; const char *isa; - size_t i; + char print_str[BITS_PER_LONG + 1]; + size_t i, j, isa_len; static unsigned long isa2hwcap[256] = {0}; isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; @@ -33,8 +76,11 @@ void riscv_fill_hwcap(void) elf_hwcap = 0; + bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); + for_each_of_cpu_node(node) { unsigned long this_hwcap = 0; + unsigned long this_isa = 0; if (riscv_of_processor_hartid(node) < 0) continue; @@ -44,8 +90,24 @@ void riscv_fill_hwcap(void) continue; } - for (i = 0; i < strlen(isa); ++i) + i = 0; + isa_len = strlen(isa); +#if IS_ENABLED(CONFIG_32BIT) + if (!strncmp(isa, "rv32", 4)) + i += 4; +#elif IS_ENABLED(CONFIG_64BIT) + if (!strncmp(isa, "rv64", 4)) + i += 4; +#endif + for (; i < isa_len; ++i) { this_hwcap |= isa2hwcap[(unsigned char)(isa[i])]; + /* + * TODO: X, Y and Z extension parsing for Host ISA + * bitmap will be added in-future. + */ + if ('a' <= isa[i] && isa[i] < 'x') + this_isa |= (1UL << (isa[i] - 'a')); + } /* * All "okay" hart should have same isa. Set HWCAP based on @@ -56,6 +118,11 @@ void riscv_fill_hwcap(void) elf_hwcap &= this_hwcap; else elf_hwcap = this_hwcap; + + if (riscv_isa[0]) + riscv_isa[0] &= this_isa; + else + riscv_isa[0] = this_isa; } /* We don't support systems with F but without D, so mask those out @@ -65,7 +132,17 @@ void riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - pr_info("elf_hwcap is 0x%lx\n", elf_hwcap); + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (riscv_isa[0] & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ISA extensions %s\n", print_str); + + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (elf_hwcap & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ELF capabilities %s\n", print_str); #ifdef CONFIG_FPU if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)) diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c index 91626d9ae5f2..c835f0362d94 100644 --- a/arch/riscv/kernel/perf_event.c +++ b/arch/riscv/kernel/perf_event.c @@ -147,7 +147,7 @@ static int riscv_map_hw_event(u64 config) return riscv_pmu->hw_events[config]; } -int riscv_map_cache_decode(u64 config, unsigned int *type, +static int riscv_map_cache_decode(u64 config, unsigned int *type, unsigned int *op, unsigned int *result) { return -ENOENT; @@ -342,7 +342,7 @@ static void riscv_pmu_del(struct perf_event *event, int flags) static DEFINE_MUTEX(pmc_reserve_mutex); -irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev) +static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev) { return IRQ_NONE; } @@ -361,7 +361,7 @@ static int reserve_pmc_hardware(void) return err; } -void release_pmc_hardware(void) +static void release_pmc_hardware(void) { mutex_lock(&pmc_reserve_mutex); if (riscv_pmu->irq >= 0) @@ -464,7 +464,7 @@ static const struct of_device_id riscv_pmu_of_ids[] = { { /* sentinel value */ } }; -int __init init_hw_perf_events(void) +static int __init init_hw_perf_events(void) { struct device_node *node = of_find_node_by_type(NULL, "pmu"); const struct of_device_id *of_id; diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index e0a6293093f1..a65a8fa0c22d 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -10,6 +10,7 @@ #include <linux/cpu.h> #include <linux/interrupt.h> +#include <linux/module.h> #include <linux/profile.h> #include <linux/smp.h> #include <linux/sched.h> @@ -63,6 +64,7 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out) for_each_cpu(cpu, in) cpumask_set_cpu(cpuid_to_hartid_map(cpu), out); } +EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask); bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 6c854875ac74..837b9b38f825 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -65,7 +65,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, #else /* !CONFIG_FRAME_POINTER */ -static void notrace walk_stackframe(struct task_struct *task, +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) { unsigned long sp, pc; diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index a4ee3a0e7d20..4c8b2a4a6a70 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -12,7 +12,7 @@ vdso-syms += getcpu vdso-syms += flush_icache # Files to link into the vdso -obj-vdso = $(patsubst %, %.o, $(vdso-syms)) +obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o # Build rules targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S new file mode 100644 index 000000000000..2a956c942211 --- /dev/null +++ b/arch/riscv/kernel/vdso/note.S @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/elfnote.h> +#include <linux/version.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b55be44ff9bd..27a334106708 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -150,7 +150,8 @@ void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = max_pfn; #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); @@ -501,22 +502,6 @@ static inline void setup_vm_final(void) #endif /* CONFIG_MMU */ #ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_rw(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_rw(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - void mark_rodata_ro(void) { unsigned long text_start = (unsigned long)_text; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5dcf9ff12828..d05bb040fd42 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -545,6 +545,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_AIS: case KVM_CAP_S390_AIS_MIGRATION: case KVM_CAP_S390_VCPU_RESETS: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_S390_HPAGE_1M: diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 69a824f9ef0b..893893642415 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu) * available for the guest are AQIC and TAPQ with the t bit set * since we do not set IC.3 (FIII) we currently will only intercept * the AQIC function code. + * Note: running nested under z/VM can result in intercepts for other + * function codes, e.g. PQAP(QCI). We do not support this and bail out. */ reg0 = vcpu->run->s.regs.gprs[0]; fc = (reg0 >> 24) & 0xff; - if (WARN_ON_ONCE(fc != 0x03)) + if (fc != 0x03) return -EOPNOTSUPP; /* PQAP instruction is allowed for guest kernel only */ diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 06ef2d4a4701..6737bcea1fa1 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -32,16 +32,16 @@ void blake2s_compress_arch(struct blake2s_state *state, const u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8); + BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { blake2s_compress_generic(state, block, nblocks, inc); return; } - for (;;) { + do { const size_t blocks = min_t(size_t, nblocks, - PAGE_SIZE / BLAKE2S_BLOCK_SIZE); + SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && @@ -52,10 +52,8 @@ void blake2s_compress_arch(struct blake2s_state *state, kernel_fpu_end(); nblocks -= blocks; - if (!nblocks) - break; block += blocks * BLAKE2S_BLOCK_SIZE; - } + } while (nblocks); } EXPORT_SYMBOL(blake2s_compress_arch); diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index b412c21ee06e..22250091cdbe 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -153,9 +153,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, bytes <= CHACHA_BLOCK_SIZE) return chacha_crypt_generic(state, dst, src, bytes, nrounds); - kernel_fpu_begin(); - chacha_dosimd(state, dst, src, bytes, nrounds); - kernel_fpu_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_fpu_begin(); + chacha_dosimd(state, dst, src, todo, nrounds); + kernel_fpu_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index f7567cbd35b6..80fcb85736e1 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2); diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index a661ede3b5cf..cc6b7c1a2705 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 6dfec19f7d57..dfe921efa9b2 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -91,8 +91,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, struct poly1305_arch_internal *state = ctx; /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || - PAGE_SIZE % POLY1305_BLOCK_SIZE); + BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || + SZ_4K % POLY1305_BLOCK_SIZE); if (!static_branch_likely(&poly1305_use_avx) || (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || @@ -102,8 +102,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, return; } - for (;;) { - const size_t bytes = min_t(size_t, len, PAGE_SIZE); + do { + const size_t bytes = min_t(size_t, len, SZ_4K); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) @@ -113,11 +113,10 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, else poly1305_blocks_avx(ctx, inp, bytes, padbit); kernel_fpu_end(); + len -= bytes; - if (!len) - break; inp += bytes; - } + } while (len); } static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 0789e13ece90..1c7f13bb6728 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 0e9504fabe52..3063aa9090f9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -258,6 +257,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -279,8 +279,7 @@ SYM_CODE_END(entry_SYSCALL_64) * %rdi: prev task * %rsi: next task */ -SYM_CODE_START(__switch_to_asm) - UNWIND_HINT_FUNC +SYM_FUNC_START(__switch_to_asm) /* * Save callee-saved registers * This must match the order in inactive_task_frame @@ -321,7 +320,7 @@ SYM_CODE_START(__switch_to_asm) popq %rbp jmp __switch_to -SYM_CODE_END(__switch_to_asm) +SYM_FUNC_END(__switch_to_asm) /* * A newly forked process directly context switches into this address. @@ -512,7 +511,7 @@ SYM_CODE_END(spurious_entries_start) * +----------------------------------------------------+ */ SYM_CODE_START(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -544,9 +543,9 @@ SYM_CODE_START(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -637,6 +636,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1739,7 +1739,7 @@ SYM_CODE_START(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 85be2f506272..84b9449be080 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -56,16 +56,23 @@ struct dyn_arch_ftrace { #ifndef __ASSEMBLY__ +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +extern void set_ftrace_ops_ro(void); +#else +static inline void set_ftrace_ops_ro(void) { } +#endif + #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { /* * Compare the symbol name with the system call name. Skip the - * "__x64_sys", "__ia32_sys" or simple "sys" prefix. + * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix. */ return !strcmp(sym + 3, name + 3) || (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) || - (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)); + (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) || + (!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3)); } #ifndef COMPILE_OFFSETS diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 42a2d0d3984a..0dea9f122bb9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 81b9c63dae1b..e53dda210cd7 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -546,7 +544,7 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -556,7 +554,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -568,7 +566,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -581,7 +579,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), @@ -603,18 +601,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -626,11 +625,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " "please update microcode to version: 0x%x (or later)\n", rev); + return false; } /* @@ -2092,7 +2092,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_debug("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 87b97897a881..460ae7f66818 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -183,7 +183,8 @@ recursion_check: */ if (visit_mask) { if (*visit_mask & (1UL << info->type)) { - printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); + if (task == current) + printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); goto unknown; } *visit_mask |= 1UL << info->type; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 37a0aeaf89e7..b0e641793be4 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -407,7 +407,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) set_vm_flush_reset_perms(trampoline); - set_memory_ro((unsigned long)trampoline, npages); + if (likely(system_state != SYSTEM_BOOTING)) + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -415,6 +416,32 @@ fail: return 0; } +void set_ftrace_ops_ro(void) +{ + struct ftrace_ops *ops; + unsigned long start_offset; + unsigned long end_offset; + unsigned long npages; + unsigned long size; + + do_for_each_ftrace_op(ops, ftrace_ops_list) { + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + continue; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + start_offset = (unsigned long)ftrace_regs_caller; + end_offset = (unsigned long)ftrace_regs_caller_end; + } else { + start_offset = (unsigned long)ftrace_caller; + end_offset = (unsigned long)ftrace_epilogue; + } + size = end_offset - start_offset; + size = size + RET_SIZE + sizeof(void *); + npages = DIV_ROUND_UP(size, PAGE_SIZE); + set_memory_ro((unsigned long)ops->trampoline, npages); + } while_for_each_ftrace_op(ops); +} + static unsigned long calc_trampoline_call_offset(bool save_regs) { unsigned long start_offset; diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index a224b5ab103f..54226110bc7f 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -344,6 +344,9 @@ bad_address: if (IS_ENABLED(CONFIG_X86_32)) goto the_end; + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index e9cc182aa97e..5b0bd8581fe6 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -8,19 +8,21 @@ #include <asm/orc_lookup.h> #define orc_warn(fmt, ...) \ - printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) + +#define orc_warn_current(args...) \ +({ \ + if (state->task == current) \ + orc_warn(args); \ +}) extern int __start_orc_unwind_ip[]; extern int __stop_orc_unwind_ip[]; extern struct orc_entry __start_orc_unwind[]; extern struct orc_entry __stop_orc_unwind[]; -static DEFINE_MUTEX(sort_mutex); -int *cur_orc_ip_table = __start_orc_unwind_ip; -struct orc_entry *cur_orc_table = __start_orc_unwind; - -unsigned int lookup_num_blocks; -bool orc_init; +static bool orc_init __ro_after_init; +static unsigned int lookup_num_blocks __ro_after_init; static inline unsigned long orc_ip(const int *ip) { @@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip) #ifdef CONFIG_MODULES +static DEFINE_MUTEX(sort_mutex); +static int *cur_orc_ip_table = __start_orc_unwind_ip; +static struct orc_entry *cur_orc_table = __start_orc_unwind; + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -381,9 +384,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -445,43 +477,39 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { + orc_warn_current("missing R10 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { + orc_warn_current("missing R13 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { + orc_warn_current("missing RDI value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { + orc_warn_current("missing DX value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: - orc_warn("unknown SP base reg %d for ip %pB\n", + orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->ip); goto err; } @@ -504,44 +532,48 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access registers at %pB\n", + (void *)orig_ip); goto err; } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; case ORC_TYPE_REGS_IRET: if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference iret registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access iret registers at %pB\n", + (void *)orig_ip); goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; break; default: - orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -564,8 +596,8 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%pB\n", - (void *)orig_ip); + orc_warn_current("stack going in the wrong direction? at %pB\n", + (void *)orig_ip); goto err; } @@ -585,6 +617,9 @@ EXPORT_SYMBOL_GPL(unwind_next_frame); void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { + if (!orc_init) + goto done; + memset(state, 0, sizeof(*state)); state->task = task; @@ -651,7 +686,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 750ff0b29404..d057376bd3d3 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, } /* - * AMD SVM AVIC accelerate EOI write and do not trap, - * in-kernel IOAPIC will not be able to receive the EOI. - * In this case, we do lazy update of the pending EOI when - * trying to set IOAPIC irq. + * AMD SVM AVIC accelerate EOI write iff the interrupt is edge + * triggered, in which case the in-kernel IOAPIC will not be able + * to receive the EOI. In this case, we do a lazy update of the + * pending EOI when trying to set IOAPIC irq. */ - if (kvm_apicv_activated(ioapic->kvm)) + if (edge && kvm_apicv_activated(ioapic->kvm)) ioapic_lazy_update_eoi(ioapic, irq); /* diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index cf912b4aaba8..89f7f3aebd31 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -345,7 +345,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f379bacbb26..38f6aeefeb55 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1752,6 +1752,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6; + kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = DB_VECTOR; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index fd78ffbde644..e44f33c82332 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) */ break; default: - BUG_ON(1); + BUG(); break; } diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 87f3f24fef37..51d1a82742fd 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c5835f9cb9ad..d786c7d27ce5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -926,19 +926,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); __reserved_bits; \ }) -static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) -{ - u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - - if (kvm_cpu_cap_has(X86_FEATURE_LA57)) - reserved_bits &= ~X86_CR4_LA57; - - if (kvm_cpu_cap_has(X86_FEATURE_UMIP)) - reserved_bits &= ~X86_CR4_UMIP; - - return reserved_bits; -} - static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) @@ -3385,6 +3372,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -9675,7 +9663,9 @@ int kvm_arch_hardware_setup(void *opaque) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; - cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has if (kvm_has_tsc_control) { /* @@ -9707,7 +9697,8 @@ int kvm_arch_check_processor_compat(void *opaque) WARN_ON(!irqs_disabled()); - if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; return ops->check_processor_compatibility(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3b289c2f75cd..8b5f73f5e207 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -54,6 +54,7 @@ #include <asm/init.h> #include <asm/uv/uv.h> #include <asm/setup.h> +#include <asm/ftrace.h> #include "mm_internal.h" @@ -1291,6 +1292,8 @@ void mark_rodata_ro(void) all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); + set_ftrace_ops_ro(); + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end); set_memory_rw(start, (end-start) >> PAGE_SHIFT); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 59eca6a94ce7..b8c55a2e402d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -43,7 +43,8 @@ struct cpa_data { unsigned long pfn; unsigned int flags; unsigned int force_split : 1, - force_static_prot : 1; + force_static_prot : 1, + force_flush_all : 1; struct page **pages; }; @@ -355,10 +356,10 @@ static void cpa_flush(struct cpa_data *data, int cache) return; } - if (cpa->numpages <= tlb_single_page_flush_ceiling) - on_each_cpu(__cpa_flush_tlb, cpa, 1); - else + if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) flush_tlb_all(); + else + on_each_cpu(__cpa_flush_tlb, cpa, 1); if (!cache) return; @@ -1598,6 +1599,8 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; + ret = __change_page_attr_set_clr(&alias_cpa, 0); if (ret) return ret; @@ -1618,6 +1621,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the * return value. diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 78ba57efd16b..3d411716d7ee 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -123,6 +123,7 @@ #include <linux/ioprio.h> #include <linux/sbitmap.h> #include <linux/delay.h> +#include <linux/backing-dev.h> #include "blk.h" #include "blk-mq.h" @@ -4976,8 +4977,9 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); switch (ioprio_class) { default: - dev_err(bfqq->bfqd->queue->backing_dev_info->dev, - "bfq: bad prio class %d\n", ioprio_class); + pr_err("bdi %s: bfq: bad prio class %d\n", + bdi_dev_name(bfqq->bfqd->queue->backing_dev_info), + ioprio_class); /* fall through */ case IOPRIO_CLASS_NONE: /* diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c5dc833212e1..930212c1a512 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -496,7 +496,7 @@ const char *blkg_dev_name(struct blkcg_gq *blkg) { /* some drivers (floppy) instantiate a queue w/o disk registered */ if (blkg->q->backing_dev_info->dev) - return dev_name(blkg->q->backing_dev_info->dev); + return bdi_dev_name(blkg->q->backing_dev_info); return NULL; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 3ab0c1c704b6..7c1fe605d0d6 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -466,7 +466,7 @@ struct ioc_gq { */ atomic64_t vtime; atomic64_t done_vtime; - atomic64_t abs_vdebt; + u64 abs_vdebt; u64 last_vtime; /* @@ -1142,7 +1142,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 margin_ns = (u64)(ioc->period_us * WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC; - u64 abs_vdebt, vdebt, vshortage, expires, oexpires; + u64 vdebt, vshortage, expires, oexpires; s64 vbudget; u32 hw_inuse; @@ -1152,18 +1152,15 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ - abs_vdebt = atomic64_read(&iocg->abs_vdebt); - vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse); + vdebt = abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); if (vdebt && vbudget > 0) { u64 delta = min_t(u64, vbudget, vdebt); u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse), - abs_vdebt); + iocg->abs_vdebt); atomic64_add(delta, &iocg->vtime); atomic64_add(delta, &iocg->done_vtime); - atomic64_sub(abs_delta, &iocg->abs_vdebt); - if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0)) - atomic64_set(&iocg->abs_vdebt, 0); + iocg->abs_vdebt -= abs_delta; } /* @@ -1219,12 +1216,18 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) u64 expires, oexpires; u32 hw_inuse; + lockdep_assert_held(&iocg->waitq.lock); + /* debt-adjust vtime */ current_hweight(iocg, NULL, &hw_inuse); - vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse); + vtime += abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); - /* clear or maintain depending on the overage */ - if (time_before_eq64(vtime, now->vnow)) { + /* + * Clear or maintain depending on the overage. Non-zero vdebt is what + * guarantees that @iocg is online and future iocg_kick_delay() will + * clear use_delay. Don't leave it on when there's no vdebt. + */ + if (!iocg->abs_vdebt || time_before_eq64(vtime, now->vnow)) { blkcg_clear_delay(blkg); return false; } @@ -1258,9 +1261,12 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer); struct ioc_now now; + unsigned long flags; + spin_lock_irqsave(&iocg->waitq.lock, flags); ioc_now(iocg->ioc, &now); iocg_kick_delay(iocg, &now, 0); + spin_unlock_irqrestore(&iocg->waitq.lock, flags); return HRTIMER_NORESTART; } @@ -1368,14 +1374,13 @@ static void ioc_timer_fn(struct timer_list *timer) * should have woken up in the last period and expire idle iocgs. */ list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg)) + if (!waitqueue_active(&iocg->waitq) && iocg->abs_vdebt && + !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); - if (waitqueue_active(&iocg->waitq) || - atomic64_read(&iocg->abs_vdebt)) { + if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, &now); iocg_kick_delay(iocg, &now, 0); @@ -1718,28 +1723,49 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && + if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); return; } /* - * We're over budget. If @bio has to be issued regardless, - * remember the abs_cost instead of advancing vtime. - * iocg_kick_waitq() will pay off the debt before waking more IOs. + * We activated above but w/o any synchronization. Deactivation is + * synchronized with waitq.lock and we won't get deactivated as long + * as we're waiting or has debt, so we're good if we're activated + * here. In the unlikely case that we aren't, just issue the IO. + */ + spin_lock_irq(&iocg->waitq.lock); + + if (unlikely(list_empty(&iocg->active_list))) { + spin_unlock_irq(&iocg->waitq.lock); + iocg_commit_bio(iocg, bio, cost); + return; + } + + /* + * We're over budget. If @bio has to be issued regardless, remember + * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay + * off the debt before waking more IOs. + * * This way, the debt is continuously paid off each period with the - * actual budget available to the cgroup. If we just wound vtime, - * we would incorrectly use the current hw_inuse for the entire - * amount which, for example, can lead to the cgroup staying - * blocked for a long time even with substantially raised hw_inuse. + * actual budget available to the cgroup. If we just wound vtime, we + * would incorrectly use the current hw_inuse for the entire amount + * which, for example, can lead to the cgroup staying blocked for a + * long time even with substantially raised hw_inuse. + * + * An iocg with vdebt should stay online so that the timer can keep + * deducting its vdebt and [de]activate use_delay mechanism + * accordingly. We don't want to race against the timer trying to + * clear them and leave @iocg inactive w/ dangling use_delay heavily + * penalizing the cgroup and its descendants. */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { - atomic64_add(abs_cost, &iocg->abs_vdebt); + iocg->abs_vdebt += abs_cost; if (iocg_kick_delay(iocg, &now, cost)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); + spin_unlock_irq(&iocg->waitq.lock); return; } @@ -1756,20 +1782,6 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ - spin_lock_irq(&iocg->waitq.lock); - - /* - * We activated above but w/o any synchronization. Deactivation is - * synchronized with waitq.lock and we won't get deactivated as - * long as we're waiting, so we're good if we're activated here. - * In the unlikely case that we are deactivated, just issue the IO. - */ - if (unlikely(list_empty(&iocg->active_list))) { - spin_unlock_irq(&iocg->waitq.lock); - iocg_commit_bio(iocg, bio, cost); - return; - } - init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; @@ -1801,6 +1813,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct ioc_now now; u32 hw_inuse; u64 abs_cost, cost; + unsigned long flags; /* bypass if disabled or for root cgroup */ if (!ioc->enabled || !iocg->level) @@ -1820,15 +1833,28 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, iocg->cursor = bio_end; /* - * Charge if there's enough vtime budget and the existing request - * has cost assigned. Otherwise, account it as debt. See debt - * handling in ioc_rqos_throttle() for details. + * Charge if there's enough vtime budget and the existing request has + * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && - time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) + time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); - else - atomic64_add(abs_cost, &iocg->abs_vdebt); + return; + } + + /* + * Otherwise, account it as debt if @iocg is online, which it should + * be for the vast majority of cases. See debt handling in + * ioc_rqos_throttle() for details. + */ + spin_lock_irqsave(&iocg->waitq.lock, flags); + if (likely(!list_empty(&iocg->active_list))) { + iocg->abs_vdebt += abs_cost; + iocg_kick_delay(iocg, &now, cost); + } else { + iocg_commit_bio(iocg, bio, cost); + } + spin_unlock_irqrestore(&iocg->waitq.lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) @@ -1998,7 +2024,6 @@ static void ioc_pd_init(struct blkg_policy_data *pd) iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); - atomic64_set(&iocg->abs_vdebt, 0); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); iocg->hweight_active = HWEIGHT_WHOLE; diff --git a/crypto/lrw.c b/crypto/lrw.c index 376d7ed3f1f8..3c734b81b3a2 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -287,7 +287,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_skcipher(ctx->child); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -400,12 +400,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/crypto/xts.c b/crypto/xts.c index dbdd8af629e6..6d8cea94b3cf 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -322,7 +322,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_cipher(ctx->tweak); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -434,12 +434,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index b4c0152e92aa..145ec0b6f20b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1994,23 +1994,31 @@ void acpi_ec_set_gpe_wake_mask(u8 action) acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); } -bool acpi_ec_other_gpes_active(void) -{ - return acpi_any_gpe_status_set(first_ec ? first_ec->gpe : U32_MAX); -} - bool acpi_ec_dispatch_gpe(void) { u32 ret; if (!first_ec) + return acpi_any_gpe_status_set(U32_MAX); + + /* + * Report wakeup if the status bit is set for any enabled GPE other + * than the EC one. + */ + if (acpi_any_gpe_status_set(first_ec->gpe)) + return true; + + if (ec_no_wakeup) return false; + /* + * Dispatch the EC GPE in-band, but do not report wakeup in any case + * to allow the caller to process events properly after that. + */ ret = acpi_dispatch_gpe(NULL, first_ec->gpe); - if (ret == ACPI_INTERRUPT_HANDLED) { + if (ret == ACPI_INTERRUPT_HANDLED) pm_pr_dbg("EC GPE dispatched\n"); - return true; - } + return false; } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index e387517d3354..43411a7457cd 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -202,7 +202,6 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); #ifdef CONFIG_PM_SLEEP void acpi_ec_flush_work(void); -bool acpi_ec_other_gpes_active(void); bool acpi_ec_dispatch_gpe(void); #endif diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 4edc8a3ce40f..3850704570c0 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -1013,21 +1013,11 @@ static bool acpi_s2idle_wake(void) if (acpi_check_wakeup_handlers()) return true; - /* - * If the status bit is set for any enabled GPE other than the - * EC one, the wakeup is regarded as a genuine one. - */ - if (acpi_ec_other_gpes_active()) + /* Check non-EC GPE wakeups and dispatch the EC GPE. */ + if (acpi_ec_dispatch_gpe()) return true; /* - * If the EC GPE status bit has not been set, the wakeup is - * regarded as a spurious one. - */ - if (!acpi_ec_dispatch_gpe()) - return false; - - /* * Cancel the wakeup and process all pending events in case * there are any wakeup ones in there. * diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index fe1523664816..8558b629880b 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -645,6 +645,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name) dev->dev.release = amba_device_release; dev->dev.bus = &amba_bustype; dev->dev.dma_mask = &dev->dev.coherent_dma_mask; + dev->dev.dma_parms = &dev->dma_parms; dev->res.name = dev_name(&dev->dev); } diff --git a/drivers/base/component.c b/drivers/base/component.c index e97704104784..dcfbe7251dc4 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -256,7 +256,8 @@ static int try_to_bring_up_master(struct master *master, ret = master->ops->bind(master->dev); if (ret < 0) { devres_release_group(master->dev, NULL); - dev_info(master->dev, "master bind failed: %d\n", ret); + if (ret != -EPROBE_DEFER) + dev_info(master->dev, "master bind failed: %d\n", ret); return ret; } @@ -611,8 +612,9 @@ static int component_bind(struct component *component, struct master *master, devres_release_group(component->dev, NULL); devres_release_group(master->dev, NULL); - dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", - dev_name(component->dev), component->ops, ret); + if (ret != -EPROBE_DEFER) + dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", + dev_name(component->dev), component->ops, ret); } return ret; diff --git a/drivers/base/core.c b/drivers/base/core.c index 139cdf7e7327..073045cb214e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2370,6 +2370,11 @@ u32 fw_devlink_get_flags(void) return fw_devlink_flags; } +static bool fw_devlink_is_permissive(void) +{ + return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY; +} + /** * device_add - add device to device hierarchy. * @dev: device. @@ -2524,7 +2529,7 @@ int device_add(struct device *dev) if (fw_devlink_flags && is_fwnode_dev && fwnode_has_op(dev->fwnode, add_links)) { fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev); - if (fw_ret == -ENODEV) + if (fw_ret == -ENODEV && !fw_devlink_is_permissive()) device_link_wait_for_mandatory_supplier(dev); else if (fw_ret) device_link_wait_for_optional_supplier(dev); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 06ec0e851fa1..94037be7f5d7 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -224,17 +224,9 @@ static int deferred_devs_show(struct seq_file *s, void *data) } DEFINE_SHOW_ATTRIBUTE(deferred_devs); -#ifdef CONFIG_MODULES -/* - * In the case of modules, set the default probe timeout to - * 30 seconds to give userland some time to load needed modules - */ -int driver_deferred_probe_timeout = 30; -#else -/* In the case of !modules, no probe timeout needed */ -int driver_deferred_probe_timeout = -1; -#endif +int driver_deferred_probe_timeout; EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); +static DECLARE_WAIT_QUEUE_HEAD(probe_timeout_waitqueue); static int __init deferred_probe_timeout_setup(char *str) { @@ -266,8 +258,8 @@ int driver_deferred_probe_check_state(struct device *dev) return -ENODEV; } - if (!driver_deferred_probe_timeout) { - dev_WARN(dev, "deferred probe timeout, ignoring dependency"); + if (!driver_deferred_probe_timeout && initcalls_done) { + dev_warn(dev, "deferred probe timeout, ignoring dependency"); return -ETIMEDOUT; } @@ -284,6 +276,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work) list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe) dev_info(private->device, "deferred probe pending"); + wake_up(&probe_timeout_waitqueue); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); @@ -658,6 +651,9 @@ int driver_probe_done(void) */ void wait_for_device_probe(void) { + /* wait for probe timeout */ + wait_event(probe_timeout_waitqueue, !driver_deferred_probe_timeout); + /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 5255550b7c34..b27d0f6c18c9 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -380,6 +380,8 @@ struct platform_object { */ static void setup_pdev_dma_masks(struct platform_device *pdev) { + pdev->dev.dma_parms = &pdev->dma_parms; + if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); if (!pdev->dev.dma_mask) { diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 93468b7c6701..9d21bf0f155e 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -33,6 +33,15 @@ struct virtio_blk_vq { } ____cacheline_aligned_in_smp; struct virtio_blk { + /* + * This mutex must be held by anything that may run after + * virtblk_remove() sets vblk->vdev to NULL. + * + * blk-mq, virtqueue processing, and sysfs attribute code paths are + * shut down before vblk->vdev is set to NULL and therefore do not need + * to hold this mutex. + */ + struct mutex vdev_mutex; struct virtio_device *vdev; /* The disk structure for the kernel. */ @@ -44,6 +53,13 @@ struct virtio_blk { /* Process context for config space updates */ struct work_struct config_work; + /* + * Tracks references from block_device_operations open/release and + * virtio_driver probe/remove so this object can be freed once no + * longer in use. + */ + refcount_t refs; + /* What host tells us, plus 2 for header & tailer. */ unsigned int sg_elems; @@ -295,10 +311,55 @@ out: return err; } +static void virtblk_get(struct virtio_blk *vblk) +{ + refcount_inc(&vblk->refs); +} + +static void virtblk_put(struct virtio_blk *vblk) +{ + if (refcount_dec_and_test(&vblk->refs)) { + ida_simple_remove(&vd_index_ida, vblk->index); + mutex_destroy(&vblk->vdev_mutex); + kfree(vblk); + } +} + +static int virtblk_open(struct block_device *bd, fmode_t mode) +{ + struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (vblk->vdev) + virtblk_get(vblk); + else + ret = -ENXIO; + + mutex_unlock(&vblk->vdev_mutex); + return ret; +} + +static void virtblk_release(struct gendisk *disk, fmode_t mode) +{ + struct virtio_blk *vblk = disk->private_data; + + virtblk_put(vblk); +} + /* We provide getgeo only to please some old bootloader/partitioning tools */ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) { struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (!vblk->vdev) { + ret = -ENXIO; + goto out; + } /* see if the host passed in geometry config */ if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) { @@ -314,11 +375,15 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) geo->sectors = 1 << 5; geo->cylinders = get_capacity(bd->bd_disk) >> 11; } - return 0; +out: + mutex_unlock(&vblk->vdev_mutex); + return ret; } static const struct block_device_operations virtblk_fops = { .owner = THIS_MODULE, + .open = virtblk_open, + .release = virtblk_release, .getgeo = virtblk_getgeo, }; @@ -655,6 +720,10 @@ static int virtblk_probe(struct virtio_device *vdev) goto out_free_index; } + /* This reference is dropped in virtblk_remove(). */ + refcount_set(&vblk->refs, 1); + mutex_init(&vblk->vdev_mutex); + vblk->vdev = vdev; vblk->sg_elems = sg_elems; @@ -820,8 +889,6 @@ out: static void virtblk_remove(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; - int index = vblk->index; - int refc; /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); @@ -831,18 +898,21 @@ static void virtblk_remove(struct virtio_device *vdev) blk_mq_free_tag_set(&vblk->tag_set); + mutex_lock(&vblk->vdev_mutex); + /* Stop all the virtqueues. */ vdev->config->reset(vdev); - refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref); + /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ + vblk->vdev = NULL; + put_disk(vblk->disk); vdev->config->del_vqs(vdev); kfree(vblk->vqs); - kfree(vblk); - /* Only free device id if we don't have any users */ - if (refc == 1) - ida_simple_remove(&vd_index_ida, index); + mutex_unlock(&vblk->vdev_mutex); + + virtblk_put(vblk); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c index b38359c480ea..eb2ab058a01d 100644 --- a/drivers/bus/mhi/core/init.c +++ b/drivers/bus/mhi/core/init.c @@ -812,10 +812,9 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl, if (!mhi_cntrl) return -EINVAL; - if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put) - return -EINVAL; - - if (!mhi_cntrl->status_cb || !mhi_cntrl->link_status) + if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put || + !mhi_cntrl->status_cb || !mhi_cntrl->read_reg || + !mhi_cntrl->write_reg) return -EINVAL; ret = parse_config(mhi_cntrl, config); diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 5deadfaa053a..095d95bc0e37 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -11,9 +11,6 @@ extern struct bus_type mhi_bus_type; -/* MHI MMIO register mapping */ -#define PCI_INVALID_READ(val) (val == U32_MAX) - #define MHIREGLEN (0x0) #define MHIREGLEN_MHIREGLEN_MASK (0xFFFFFFFF) #define MHIREGLEN_MHIREGLEN_SHIFT (0) diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index eb4256b81406..97e06cc586e4 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -18,16 +18,7 @@ int __must_check mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 *out) { - u32 tmp = readl(base + offset); - - /* If there is any unexpected value, query the link status */ - if (PCI_INVALID_READ(tmp) && - mhi_cntrl->link_status(mhi_cntrl)) - return -EIO; - - *out = tmp; - - return 0; + return mhi_cntrl->read_reg(mhi_cntrl, base + offset, out); } int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, @@ -49,7 +40,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 val) { - writel(val, base + offset); + mhi_cntrl->write_reg(mhi_cntrl, base + offset, val); } void mhi_write_reg_field(struct mhi_controller *mhi_cntrl, void __iomem *base, @@ -294,7 +285,7 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) !(mhi_chan->ee_mask & BIT(mhi_cntrl->ee))) continue; mhi_dev = mhi_alloc_device(mhi_cntrl); - if (!mhi_dev) + if (IS_ERR(mhi_dev)) return; mhi_dev->dev_type = MHI_DEVICE_XFER; @@ -336,7 +327,8 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) /* Channel name is same for both UL and DL */ mhi_dev->chan_name = mhi_chan->name; - dev_set_name(&mhi_dev->dev, "%04x_%s", mhi_chan->chan, + dev_set_name(&mhi_dev->dev, "%s_%s", + dev_name(mhi_cntrl->cntrl_dev), mhi_dev->chan_name); /* Init wakeup source if available */ diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c index 52690cb5c89c..dc83d65f7784 100644 --- a/drivers/bus/mhi/core/pm.c +++ b/drivers/bus/mhi/core/pm.c @@ -902,7 +902,11 @@ int mhi_sync_power_up(struct mhi_controller *mhi_cntrl) MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state), msecs_to_jiffies(mhi_cntrl->timeout_ms)); - return (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -EIO; + ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT; + if (ret) + mhi_power_down(mhi_cntrl, false); + + return ret; } EXPORT_SYMBOL(mhi_sync_power_up); diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c index e92b352fb0ad..43d9e2420110 100644 --- a/drivers/crypto/chelsio/chcr_ktls.c +++ b/drivers/crypto/chelsio/chcr_ktls.c @@ -673,41 +673,14 @@ int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) return 0; } -/* - * chcr_write_cpl_set_tcb_ulp: update tcb values. - * TCB is responsible to create tcp headers, so all the related values - * should be correctly updated. - * @tx_info - driver specific tls info. - * @q - tx queue on which packet is going out. - * @tid - TCB identifier. - * @pos - current index where should we start writing. - * @word - TCB word. - * @mask - TCB word related mask. - * @val - TCB word related value. - * @reply - set 1 if looking for TP response. - * return - next position to write. - */ -static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, - struct sge_eth_txq *q, u32 tid, - void *pos, u16 word, u64 mask, +static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, + u32 tid, void *pos, u16 word, u64 mask, u64 val, u32 reply) { struct cpl_set_tcb_field_core *cpl; struct ulptx_idata *idata; struct ulp_txpkt *txpkt; - void *save_pos = NULL; - u8 buf[48] = {0}; - int left; - left = (void *)q->q.stat - pos; - if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) { - if (!left) { - pos = q->q.desc; - } else { - save_pos = pos; - pos = buf; - } - } /* ULP_TXPKT */ txpkt = pos; txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0)); @@ -732,18 +705,54 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, idata = (struct ulptx_idata *)(cpl + 1); idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP)); idata->len = htonl(0); + pos = idata + 1; - if (save_pos) { - pos = chcr_copy_to_txd(buf, &q->q, save_pos, - CHCR_SET_TCB_FIELD_LEN); - } else { - /* check again if we are at the end of the queue */ - if (left == CHCR_SET_TCB_FIELD_LEN) + return pos; +} + + +/* + * chcr_write_cpl_set_tcb_ulp: update tcb values. + * TCB is responsible to create tcp headers, so all the related values + * should be correctly updated. + * @tx_info - driver specific tls info. + * @q - tx queue on which packet is going out. + * @tid - TCB identifier. + * @pos - current index where should we start writing. + * @word - TCB word. + * @mask - TCB word related mask. + * @val - TCB word related value. + * @reply - set 1 if looking for TP response. + * return - next position to write. + */ +static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, + struct sge_eth_txq *q, u32 tid, + void *pos, u16 word, u64 mask, + u64 val, u32 reply) +{ + int left = (void *)q->q.stat - pos; + + if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) { + if (!left) { pos = q->q.desc; - else - pos = idata + 1; + } else { + u8 buf[48] = {0}; + + __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, + mask, val, reply); + + return chcr_copy_to_txd(buf, &q->q, pos, + CHCR_SET_TCB_FIELD_LEN); + } } + pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, + mask, val, reply); + + /* check again if we are at the end of the queue */ + if (left == CHCR_SET_TCB_FIELD_LEN) + pos = q->q.desc; + return pos; } diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 31f9f0e369b9..55b031d2c989 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -16,7 +16,7 @@ int efi_tpm_final_log_size; EXPORT_SYMBOL(efi_tpm_final_log_size); -static int tpm2_calc_event_log_size(void *data, int count, void *size_info) +static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info) { struct tcg_pcr_event2_head *header; int event_size, size = 0; diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 5638b4e5355f..4269ea9a817e 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -531,7 +531,7 @@ static int pca953x_gpio_set_config(struct gpio_chip *gc, unsigned int offset, { struct pca953x_chip *chip = gpiochip_get_data(gc); - switch (config) { + switch (pinconf_to_config_param(config)) { case PIN_CONFIG_BIAS_PULL_UP: case PIN_CONFIG_BIAS_PULL_DOWN: return pca953x_gpio_set_pull_up_down(chip, offset, config); diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index acb99eff9939..86568154cdb3 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -368,6 +368,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d) struct tegra_gpio_info *tgi = bank->tgi; unsigned int gpio = d->hwirq; + tegra_gpio_irq_mask(d); gpiochip_unlock_as_irq(&tgi->gc, gpio); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 40f2d7f69be2..182136d98b97 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1158,8 +1158,19 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, struct gpioline_info *info) { struct gpio_chip *gc = desc->gdev->chip; + bool ok_for_pinctrl; unsigned long flags; + /* + * This function takes a mutex so we must check this before taking + * the spinlock. + * + * FIXME: find a non-racy way to retrieve this information. Maybe a + * lock common to both frameworks? + */ + ok_for_pinctrl = + pinctrl_gpio_can_use_line(gc->base + info->line_offset); + spin_lock_irqsave(&gpio_lock, flags); if (desc->name) { @@ -1186,7 +1197,7 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, test_bit(FLAG_USED_AS_IRQ, &desc->flags) || test_bit(FLAG_EXPORT, &desc->flags) || test_bit(FLAG_SYSFS, &desc->flags) || - !pinctrl_gpio_can_use_line(gc->base + info->line_offset)) + !ok_for_pinctrl) info->flags |= GPIOLINE_FLAG_KERNEL; if (test_bit(FLAG_IS_OUT, &desc->flags)) info->flags |= GPIOLINE_FLAG_IS_OUT; @@ -1227,6 +1238,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) void __user *ip = (void __user *)arg; struct gpio_desc *desc; __u32 offset; + int hwgpio; /* We fail any subsequent ioctl():s when the chip is gone */ if (!gc) @@ -1259,13 +1271,19 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (IS_ERR(desc)) return PTR_ERR(desc); + hwgpio = gpio_chip_hwgpio(desc); + + if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL && + test_bit(hwgpio, priv->watched_lines)) + return -EBUSY; + gpio_desc_to_lineinfo(desc, &lineinfo); if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) return -EFAULT; if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL) - set_bit(gpio_chip_hwgpio(desc), priv->watched_lines); + set_bit(hwgpio, priv->watched_lines); return 0; } else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) { @@ -1280,7 +1298,12 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (IS_ERR(desc)) return PTR_ERR(desc); - clear_bit(gpio_chip_hwgpio(desc), priv->watched_lines); + hwgpio = gpio_chip_hwgpio(desc); + + if (!test_bit(hwgpio, priv->watched_lines)) + return -EBUSY; + + clear_bit(hwgpio, priv->watched_lines); return 0; } return -EINVAL; @@ -5289,8 +5312,9 @@ static int __init gpiolib_dev_init(void) gpiolib_initialized = true; gpiochip_setup_devs(); - if (IS_ENABLED(CONFIG_OF_DYNAMIC)) - WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier)); +#if IS_ENABLED(CONFIG_OF_DYNAMIC) && IS_ENABLED(CONFIG_OF_GPIO) + WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier)); +#endif /* CONFIG_OF_DYNAMIC && CONFIG_OF_GPIO */ return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 2992a49ad4a5..8ac1581a6b53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -945,6 +945,7 @@ struct amdgpu_device { /* s3/s4 mask */ bool in_suspend; + bool in_hibernate; /* record last mm index being written through WREG32*/ unsigned long last_mm_index; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 9dff792c9290..6a5b91d23fd9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1343,7 +1343,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( } /* Free the BO*/ - amdgpu_bo_unref(&mem->bo); + drm_gem_object_put_unlocked(&mem->bo->tbo.base); mutex_destroy(&mem->lock); kfree(mem); @@ -1688,7 +1688,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd, | KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE | KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE; - (*mem)->bo = amdgpu_bo_ref(bo); + drm_gem_object_get(&bo->tbo.base); + (*mem)->bo = bo; (*mem)->va = va; (*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f84f9e35a73b..affde2de2a0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3372,15 +3372,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) } } - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - - amdgpu_amdkfd_suspend(adev, !fbcon); - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); + amdgpu_amdkfd_suspend(adev, !fbcon); + /* evict vram memory */ amdgpu_bo_evict_vram(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 466bfe541e45..a735d79a717b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1181,7 +1181,9 @@ static int amdgpu_pmops_freeze(struct device *dev) struct amdgpu_device *adev = drm_dev->dev_private; int r; + adev->in_hibernate = true; r = amdgpu_device_suspend(drm_dev, true); + adev->in_hibernate = false; if (r) return r; return amdgpu_asic_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 9ae7b61f696a..25ddb482466a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -133,8 +133,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev, u32 cpp; u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS | - AMDGPU_GEM_CREATE_VRAM_CLEARED | - AMDGPU_GEM_CREATE_CPU_GTT_USWC; + AMDGPU_GEM_CREATE_VRAM_CLEARED; info = drm_get_format_info(adev->ddev, mode_cmd); cpp = info->cpp[0]; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f92c158d89a1..0e0daf0021b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4273,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === CGCG /CGLS for GFX 3D Only === */ gfx_v10_0_update_3d_clock_gating(adev, enable); /* === MGCG + MGLS === */ - /* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */ + gfx_v10_0_update_medium_grain_clock_gating(adev, enable); } if (adev->cg_flags & @@ -4353,11 +4353,7 @@ static int gfx_v10_0_set_powergating_state(void *handle, switch (adev->asic_type) { case CHIP_NAVI10: case CHIP_NAVI14: - if (!enable) { - amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } else - amdgpu_gfx_off_ctrl(adev, true); + amdgpu_gfx_off_ctrl(adev, enable); break; default: break; @@ -4918,6 +4914,19 @@ static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, ref, mask); } +static void gfx_v10_0_ring_soft_recovery(struct amdgpu_ring *ring, + unsigned vmid) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t value = 0; + + value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03); + value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01); + value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1); + value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid); + WREG32_SOC15(GC, 0, mmSQ_CMD, value); +} + static void gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, uint32_t me, uint32_t pipe, @@ -5309,6 +5318,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { .emit_wreg = gfx_v10_0_ring_emit_wreg, .emit_reg_wait = gfx_v10_0_ring_emit_reg_wait, .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait, + .soft_recovery = gfx_v10_0_ring_soft_recovery, }; static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 0c390485bc10..d2d9dce68c2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1236,6 +1236,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 }, /* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */ { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, + /* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */ + { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, { 0, 0, 0, 0, 0 }, }; @@ -5025,10 +5027,9 @@ static int gfx_v9_0_set_powergating_state(void *handle, switch (adev->asic_type) { case CHIP_RAVEN: case CHIP_RENOIR: - if (!enable) { + if (!enable) amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } + if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) { gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true); gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true); @@ -5052,12 +5053,7 @@ static int gfx_v9_0_set_powergating_state(void *handle, amdgpu_gfx_off_ctrl(adev, true); break; case CHIP_VEGA12: - if (!enable) { - amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } else { - amdgpu_gfx_off_ctrl(adev, true); - } + amdgpu_gfx_off_ctrl(adev, enable); break; default: break; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 94c29b74c086..28e651b173ab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -441,7 +441,7 @@ static void dm_vupdate_high_irq(void *interrupt_params) /** * dm_crtc_high_irq() - Handles CRTC interrupt - * @interrupt_params: ignored + * @interrupt_params: used for determining the CRTC instance * * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK * event handler. @@ -455,70 +455,6 @@ static void dm_crtc_high_irq(void *interrupt_params) unsigned long flags; acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); - - if (acrtc) { - acrtc_state = to_dm_crtc_state(acrtc->base.state); - - DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n", - acrtc->crtc_id, - amdgpu_dm_vrr_active(acrtc_state)); - - /* Core vblank handling at start of front-porch is only possible - * in non-vrr mode, as only there vblank timestamping will give - * valid results while done in front-porch. Otherwise defer it - * to dm_vupdate_high_irq after end of front-porch. - */ - if (!amdgpu_dm_vrr_active(acrtc_state)) - drm_crtc_handle_vblank(&acrtc->base); - - /* Following stuff must happen at start of vblank, for crc - * computation and below-the-range btr support in vrr mode. - */ - amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); - - if (acrtc_state->stream && adev->family >= AMDGPU_FAMILY_AI && - acrtc_state->vrr_params.supported && - acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { - spin_lock_irqsave(&adev->ddev->event_lock, flags); - mod_freesync_handle_v_update( - adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); - - dc_stream_adjust_vmin_vmax( - adev->dm.dc, - acrtc_state->stream, - &acrtc_state->vrr_params.adjust); - spin_unlock_irqrestore(&adev->ddev->event_lock, flags); - } - } -} - -#if defined(CONFIG_DRM_AMD_DC_DCN) -/** - * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs - * @interrupt params - interrupt parameters - * - * Notify DRM's vblank event handler at VSTARTUP - * - * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which: - * * We are close enough to VUPDATE - the point of no return for hw - * * We are in the fixed portion of variable front porch when vrr is enabled - * * We are before VUPDATE, where double-buffered vrr registers are swapped - * - * It is therefore the correct place to signal vblank, send user flip events, - * and update VRR. - */ -static void dm_dcn_crtc_high_irq(void *interrupt_params) -{ - struct common_irq_params *irq_params = interrupt_params; - struct amdgpu_device *adev = irq_params->adev; - struct amdgpu_crtc *acrtc; - struct dm_crtc_state *acrtc_state; - unsigned long flags; - - acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); - if (!acrtc) return; @@ -528,22 +464,35 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) amdgpu_dm_vrr_active(acrtc_state), acrtc_state->active_planes); + /** + * Core vblank handling at start of front-porch is only possible + * in non-vrr mode, as only there vblank timestamping will give + * valid results while done in front-porch. Otherwise defer it + * to dm_vupdate_high_irq after end of front-porch. + */ + if (!amdgpu_dm_vrr_active(acrtc_state)) + drm_crtc_handle_vblank(&acrtc->base); + + /** + * Following stuff must happen at start of vblank, for crc + * computation and below-the-range btr support in vrr mode. + */ amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); - drm_crtc_handle_vblank(&acrtc->base); + + /* BTR updates need to happen before VUPDATE on Vega and above. */ + if (adev->family < AMDGPU_FAMILY_AI) + return; spin_lock_irqsave(&adev->ddev->event_lock, flags); - if (acrtc_state->vrr_params.supported && + if (acrtc_state->stream && acrtc_state->vrr_params.supported && acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { - mod_freesync_handle_v_update( - adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); + mod_freesync_handle_v_update(adev->dm.freesync_module, + acrtc_state->stream, + &acrtc_state->vrr_params); - dc_stream_adjust_vmin_vmax( - adev->dm.dc, - acrtc_state->stream, - &acrtc_state->vrr_params.adjust); + dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream, + &acrtc_state->vrr_params.adjust); } /* @@ -556,7 +505,8 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) * avoid race conditions between flip programming and completion, * which could cause too early flip completion events. */ - if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + if (adev->family >= AMDGPU_FAMILY_RV && + acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && acrtc_state->active_planes == 0) { if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); @@ -568,7 +518,6 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) spin_unlock_irqrestore(&adev->ddev->event_lock, flags); } -#endif static int dm_set_clockgating_state(void *handle, enum amd_clockgating_state state) @@ -2008,17 +1957,22 @@ void amdgpu_dm_update_connector_after_detect( dc_sink_retain(aconnector->dc_sink); if (sink->dc_edid.length == 0) { aconnector->edid = NULL; - drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux); + if (aconnector->dc_link->aux_mode) { + drm_dp_cec_unset_edid( + &aconnector->dm_dp_aux.aux); + } } else { aconnector->edid = - (struct edid *) sink->dc_edid.raw_edid; - + (struct edid *)sink->dc_edid.raw_edid; drm_connector_update_edid_property(connector, - aconnector->edid); - drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, - aconnector->edid); + aconnector->edid); + + if (aconnector->dc_link->aux_mode) + drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, + aconnector->edid); } + amdgpu_dm_update_freesync_caps(connector, aconnector->edid); update_connector_ext_caps(aconnector); } else { @@ -2440,8 +2394,36 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) c_irq_params->adev = adev; c_irq_params->irq_src = int_params.irq_source; + amdgpu_dm_irq_register_interrupt( + adev, &int_params, dm_crtc_high_irq, c_irq_params); + } + + /* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to + * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx + * to trigger at end of each vblank, regardless of state of the lock, + * matching DCE behaviour. + */ + for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT; + i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1; + i++) { + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq); + + if (r) { + DRM_ERROR("Failed to add vupdate irq id!\n"); + return r; + } + + int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT; + int_params.irq_source = + dc_interrupt_to_irq_source(dc, i, 0); + + c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1]; + + c_irq_params->adev = adev; + c_irq_params->irq_src = int_params.irq_source; + amdgpu_dm_irq_register_interrupt(adev, &int_params, - dm_dcn_crtc_high_irq, c_irq_params); + dm_vupdate_high_irq, c_irq_params); } /* Use GRPH_PFLIP interrupt */ @@ -4448,10 +4430,6 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable) struct amdgpu_device *adev = crtc->dev->dev_private; int rc; - /* Do not set vupdate for DCN hardware */ - if (adev->family > AMDGPU_FAMILY_AI) - return 0; - irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst; rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; @@ -7877,6 +7855,7 @@ static int dm_update_plane_state(struct dc *dc, struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state; struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state; + struct amdgpu_crtc *new_acrtc; bool needs_reset; int ret = 0; @@ -7886,9 +7865,30 @@ static int dm_update_plane_state(struct dc *dc, dm_new_plane_state = to_dm_plane_state(new_plane_state); dm_old_plane_state = to_dm_plane_state(old_plane_state); - /*TODO Implement atomic check for cursor plane */ - if (plane->type == DRM_PLANE_TYPE_CURSOR) + /*TODO Implement better atomic check for cursor plane */ + if (plane->type == DRM_PLANE_TYPE_CURSOR) { + if (!enable || !new_plane_crtc || + drm_atomic_plane_disabling(plane->state, new_plane_state)) + return 0; + + new_acrtc = to_amdgpu_crtc(new_plane_crtc); + + if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) || + (new_plane_state->crtc_h > new_acrtc->max_cursor_height)) { + DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n", + new_plane_state->crtc_w, new_plane_state->crtc_h); + return -EINVAL; + } + + if (new_plane_state->crtc_x <= -new_acrtc->max_cursor_width || + new_plane_state->crtc_y <= -new_acrtc->max_cursor_height) { + DRM_DEBUG_ATOMIC("Bad cursor position %d, %d\n", + new_plane_state->crtc_x, new_plane_state->crtc_y); + return -EINVAL; + } + return 0; + } needs_reset = should_reset_plane(state, plane, old_plane_state, new_plane_state); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 78e1c11d4ae5..dcf84a61de37 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -398,15 +398,15 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) struct mod_hdcp_display *display = &hdcp_work[link_index].display; struct mod_hdcp_link *link = &hdcp_work[link_index].link; - memset(display, 0, sizeof(*display)); - memset(link, 0, sizeof(*link)); - - display->index = aconnector->base.index; - if (config->dpms_off) { hdcp_remove_display(hdcp_work, link_index, aconnector); return; } + + memset(display, 0, sizeof(*display)); + memset(link, 0, sizeof(*link)); + + display->index = aconnector->base.index; display->state = MOD_HDCP_DISPLAY_ACTIVE; if (aconnector->dc_sink != NULL) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 8489f1e56892..47431ca6986d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -834,11 +834,10 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) { int i; - int count = 0; - struct pipe_ctx *pipe; PERF_TRACE(); for (i = 0; i < MAX_PIPES; i++) { - pipe = &context->res_ctx.pipe_ctx[i]; + int count = 0; + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; if (!pipe->plane_state) continue; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index c3535bd3965b..e4348e3b6389 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3068,25 +3068,32 @@ validate_out: return out; } - -bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, - bool fast_validate) +/* + * This must be noinline to ensure anything that deals with FP registers + * is contained within this call; previously our compiling with hard-float + * would result in fp instructions being emitted outside of the boundaries + * of the DC_FP_START/END macros, which makes sense as the compiler has no + * idea about what is wrapped and what is not + * + * This is largely just a workaround to avoid breakage introduced with 5.6, + * ideally all fp-using code should be moved into its own file, only that + * should be compiled with hard-float, and all code exported from there + * should be strictly wrapped with DC_FP_START/END + */ +static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, bool fast_validate) { bool voltage_supported = false; bool full_pstate_supported = false; bool dummy_pstate_supported = false; double p_state_latency_us; - DC_FP_START(); p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = dc->debug.disable_dram_clock_change_vactive_support; if (fast_validate) { - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true); - - DC_FP_END(); - return voltage_supported; + return dcn20_validate_bandwidth_internal(dc, context, true); } // Best case, we support full UCLK switch latency @@ -3115,7 +3122,15 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, restore_dml_state: context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; + return voltage_supported; +} +bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, + bool fast_validate) +{ + bool voltage_supported = false; + DC_FP_START(); + voltage_supported = dcn20_validate_bandwidth_fp(dc, context, fast_validate); DC_FP_END(); return voltage_supported; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index a38baa73d484..b8ec08e3b7a3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -1200,7 +1200,7 @@ static void dml_rq_dlg_get_dlg_params( min_hratio_fact_l = 1.0; min_hratio_fact_c = 1.0; - if (htaps_l <= 1) + if (hratio_l <= 1) min_hratio_fact_l = 2.0; else if (htaps_l <= 6) { if ((hratio_l * 2.0) > 4.0) @@ -1216,7 +1216,7 @@ static void dml_rq_dlg_get_dlg_params( hscale_pixel_rate_l = min_hratio_fact_l * dppclk_freq_in_mhz; - if (htaps_c <= 1) + if (hratio_c <= 1) min_hratio_fact_c = 2.0; else if (htaps_c <= 6) { if ((hratio_c * 2.0) > 4.0) @@ -1522,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params( disp_dlg_regs->refcyc_per_vm_group_vblank = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; disp_dlg_regs->refcyc_per_vm_group_flip = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; + disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); + disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); // Clamp to max for now if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23)) diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index c34eba19860a..6d7bca562eec 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -108,7 +108,7 @@ #define ASSERT(expr) ASSERT_CRITICAL(expr) #else -#define ASSERT(expr) WARN_ON(!(expr)) +#define ASSERT(expr) WARN_ON_ONCE(!(expr)) #endif #define BREAK_TO_DEBUGGER() ASSERT(0) diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index e4e5a53b2b4e..8e2acb4df860 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -319,12 +319,12 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr *hwmgr, if (*level & profile_mode_mask) { hwmgr->saved_dpm_level = hwmgr->dpm_level; hwmgr->en_umd_pstate = true; - amdgpu_device_ip_set_clockgating_state(hwmgr->adev, - AMD_IP_BLOCK_TYPE_GFX, - AMD_CG_STATE_UNGATE); amdgpu_device_ip_set_powergating_state(hwmgr->adev, AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_UNGATE); + amdgpu_device_ip_set_clockgating_state(hwmgr->adev, + AMD_IP_BLOCK_TYPE_GFX, + AMD_CG_STATE_UNGATE); } } else { /* exit umd pstate, restore level, enable gfx cg*/ diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index e8b27fab6aa1..e77046931e4c 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -1476,7 +1476,7 @@ static int smu_disable_dpm(struct smu_context *smu) bool use_baco = !smu->is_apu && ((adev->in_gpu_reset && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || - (adev->in_runpm && amdgpu_asic_supports_baco(adev))); + ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev))); ret = smu_get_smc_version(smu, NULL, &smu_version); if (ret) { @@ -1744,12 +1744,12 @@ static int smu_enable_umd_pstate(void *handle, if (*level & profile_mode_mask) { smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level; smu_dpm_ctx->enable_umd_pstate = true; - amdgpu_device_ip_set_clockgating_state(smu->adev, - AMD_IP_BLOCK_TYPE_GFX, - AMD_CG_STATE_UNGATE); amdgpu_device_ip_set_powergating_state(smu->adev, AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_UNGATE); + amdgpu_device_ip_set_clockgating_state(smu->adev, + AMD_IP_BLOCK_TYPE_GFX, + AMD_CG_STATE_UNGATE); } } else { /* exit umd pstate, restore level, enable gfx cg*/ diff --git a/drivers/gpu/drm/drm_hdcp.c b/drivers/gpu/drm/drm_hdcp.c index 7f386adcf872..910108ccaae1 100644 --- a/drivers/gpu/drm/drm_hdcp.c +++ b/drivers/gpu/drm/drm_hdcp.c @@ -241,8 +241,12 @@ static int drm_hdcp_request_srm(struct drm_device *drm_dev, ret = request_firmware_direct(&fw, (const char *)fw_name, drm_dev->dev); - if (ret < 0) + if (ret < 0) { + *revoked_ksv_cnt = 0; + *revoked_ksv_list = NULL; + ret = 0; goto exit; + } if (fw->size && fw->data) ret = drm_hdcp_srm_update(fw->data, fw->size, revoked_ksv_list, @@ -287,6 +291,8 @@ int drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs, ret = drm_hdcp_request_srm(drm_dev, &revoked_ksv_list, &revoked_ksv_cnt); + if (ret) + return ret; /* revoked_ksv_cnt will be zero when above function failed */ for (i = 0; i < revoked_ksv_cnt; i++) diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 2e5d835a9eaa..c125ca9ab9b3 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -485,8 +485,7 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, if (!ret) goto err_llb; else if (ret > 1) { - DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); - + DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); } fbc->threshold = ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 0cc40e77bbd2..4f96c8788a2e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -368,7 +368,6 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_vma *vma; - GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); if (!atomic_read(&obj->bind_count)) return; @@ -400,12 +399,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma) { - struct drm_i915_gem_object *obj = vma->obj; - - assert_object_held(obj); - /* Bump the LRU to try and avoid premature eviction whilst flipping */ - i915_gem_object_bump_inactive_ggtt(obj); + i915_gem_object_bump_inactive_ggtt(vma->obj); i915_vma_unpin(vma); } diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 07cb83a0d017..ca0d4f4f3615 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -69,7 +69,13 @@ struct intel_context { #define CONTEXT_NOPREEMPT 7 u32 *lrc_reg_state; - u64 lrc_desc; + union { + struct { + u32 lrca; + u32 ccid; + }; + u64 desc; + } lrc; u32 tag; /* cookie passed to HW to track this context on submission */ /* Time on GPU as tracked by the hw. */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index b469de0dd9b6..a1aa0d3e8be1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -333,13 +333,4 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) return intel_engine_has_preemption(engine); } -static inline bool -intel_engine_has_timeslices(const struct intel_engine_cs *engine) -{ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) - return false; - - return intel_engine_has_semaphores(engine); -} - #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 3aa8a652c16d..883a9b7fe88d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1295,6 +1295,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7)) drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID)); + if (HAS_EXECLISTS(dev_priv)) { + drm_printf(m, "\tEL_STAT_HI: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_HI)); + drm_printf(m, "\tEL_STAT_LO: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_LO)); + } drm_printf(m, "\tRING_START: 0x%08x\n", ENGINE_READ(engine, RING_START)); drm_printf(m, "\tRING_HEAD: 0x%08x\n", diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 80cdde712842..0be674ae1cf6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -157,6 +157,20 @@ struct intel_engine_execlists { struct i915_priolist default_priolist; /** + * @ccid: identifier for contexts submitted to this engine + */ + u32 ccid; + + /** + * @yield: CCID at the time of the last semaphore-wait interrupt. + * + * Instead of leaving a semaphore busy-spinning on an engine, we would + * like to switch to another ready context, i.e. yielding the semaphore + * timeslice. + */ + u32 yield; + + /** * @error_interrupt: CS Master EIR * * The CS generates an interrupt when it detects an error. We capture @@ -295,8 +309,7 @@ struct intel_engine_cs { u32 context_size; u32 mmio_base; - unsigned int context_tag; -#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS) + unsigned long context_tag; struct rb_node uabi_node; @@ -483,10 +496,11 @@ struct intel_engine_cs { #define I915_ENGINE_SUPPORTS_STATS BIT(1) #define I915_ENGINE_HAS_PREEMPTION BIT(2) #define I915_ENGINE_HAS_SEMAPHORES BIT(3) -#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4) -#define I915_ENGINE_IS_VIRTUAL BIT(5) -#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6) -#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7) +#define I915_ENGINE_HAS_TIMESLICES BIT(4) +#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5) +#define I915_ENGINE_IS_VIRTUAL BIT(6) +#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8) unsigned int flags; /* @@ -585,6 +599,15 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine) } static inline bool +intel_engine_has_timeslices(const struct intel_engine_cs *engine) +{ + if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + return false; + + return engine->flags & I915_ENGINE_HAS_TIMESLICES; +} + +static inline bool intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine) { return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index f0e7fd95165a..0cc7dd54f4f9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir) } } + if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) { + WRITE_ONCE(engine->execlists.yield, + ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI)); + ENGINE_TRACE(engine, "semaphore yield: %08x\n", + engine->execlists.yield); + if (del_timer(&engine->execlists.timer)) + tasklet = true; + } + if (iir & GT_CONTEXT_SWITCH_INTERRUPT) tasklet = true; @@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; struct intel_uncore *uncore = gt->uncore; const u32 dmask = irqs << 16 | irqs; const u32 smask = irqs << 16; @@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; const u32 gt_interrupts[] = { irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT, irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 683014e7bc51..2dfaddb8811e 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -456,10 +456,10 @@ assert_priority_queue(const struct i915_request *prev, * engine info, SW context ID and SW counter need to form a unique number * (Context ID) per lrc. */ -static u64 +static u32 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) { - u64 desc; + u32 desc; desc = INTEL_LEGACY_32B_CONTEXT; if (i915_vm_is_4lvl(ce->vm)) @@ -470,21 +470,7 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) if (IS_GEN(engine->i915, 8)) desc |= GEN8_CTX_L3LLC_COHERENT; - desc |= i915_ggtt_offset(ce->state); /* bits 12-31 */ - /* - * The following 32bits are copied into the OA reports (dword 2). - * Consider updating oa_get_render_ctx_id in i915_perf.c when changing - * anything below. - */ - if (INTEL_GEN(engine->i915) >= 11) { - desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT; - /* bits 48-53 */ - - desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT; - /* bits 61-63 */ - } - - return desc; + return i915_ggtt_offset(ce->state) | desc; } static inline unsigned int dword_in_page(void *addr) @@ -1192,7 +1178,7 @@ static void reset_active(struct i915_request *rq, __execlists_update_reg_state(ce, engine, head); /* We've switched away, so this should be a no-op, but intent matters */ - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static u32 intel_context_get_runtime(const struct intel_context *ce) @@ -1251,18 +1237,23 @@ __execlists_schedule_in(struct i915_request *rq) if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) execlists_check_context(ce, engine); - ce->lrc_desc &= ~GENMASK_ULL(47, 37); if (ce->tag) { /* Use a fixed tag for OA and friends */ - ce->lrc_desc |= (u64)ce->tag << 32; + GEM_BUG_ON(ce->tag <= BITS_PER_LONG); + ce->lrc.ccid = ce->tag; } else { /* We don't need a strict matching tag, just different values */ - ce->lrc_desc |= - (u64)(++engine->context_tag % NUM_CONTEXT_TAG) << - GEN11_SW_CTX_ID_SHIFT; - BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID); + unsigned int tag = ffs(engine->context_tag); + + GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG); + clear_bit(tag - 1, &engine->context_tag); + ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32); + + BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID); } + ce->lrc.ccid |= engine->execlists.ccid; + __intel_gt_pm_get(engine->gt); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN); intel_engine_context_in(engine); @@ -1302,7 +1293,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce) static inline void __execlists_schedule_out(struct i915_request *rq, - struct intel_engine_cs * const engine) + struct intel_engine_cs * const engine, + unsigned int ccid) { struct intel_context * const ce = rq->context; @@ -1320,6 +1312,14 @@ __execlists_schedule_out(struct i915_request *rq, i915_request_completed(rq)) intel_engine_add_retire(engine, ce->timeline); + ccid >>= GEN11_SW_CTX_ID_SHIFT - 32; + ccid &= GEN12_MAX_CONTEXT_HW_ID; + if (ccid < BITS_PER_LONG) { + GEM_BUG_ON(ccid == 0); + GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag)); + set_bit(ccid - 1, &engine->context_tag); + } + intel_context_update_runtime(ce); intel_engine_context_out(engine); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT); @@ -1345,15 +1345,17 @@ execlists_schedule_out(struct i915_request *rq) { struct intel_context * const ce = rq->context; struct intel_engine_cs *cur, *old; + u32 ccid; trace_i915_request_out(rq); + ccid = rq->context->lrc.ccid; old = READ_ONCE(ce->inflight); do cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL; while (!try_cmpxchg(&ce->inflight, &old, cur)); if (!cur) - __execlists_schedule_out(rq, old); + __execlists_schedule_out(rq, old, ccid); i915_request_put(rq); } @@ -1361,7 +1363,7 @@ execlists_schedule_out(struct i915_request *rq) static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; u32 tail, prev; /* @@ -1400,7 +1402,7 @@ static u64 execlists_update_context(struct i915_request *rq) */ wmb(); - ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; + ce->lrc.desc &= ~CTX_DESC_FORCE_RESTORE; return desc; } @@ -1719,6 +1721,9 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Leave semaphores spinning on the other engines */ if (w->engine != rq->engine) continue; @@ -1754,7 +1759,8 @@ static void defer_active(struct intel_engine_cs *engine) } static bool -need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) +need_timeslice(const struct intel_engine_cs *engine, + const struct i915_request *rq) { int hint; @@ -1768,6 +1774,32 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) return hint >= effective_prio(rq); } +static bool +timeslice_yield(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + /* + * Once bitten, forever smitten! + * + * If the active context ever busy-waited on a semaphore, + * it will be treated as a hog until the end of its timeslice (i.e. + * until it is scheduled out and replaced by a new submission, + * possibly even its own lite-restore). The HW only sends an interrupt + * on the first miss, and we do know if that semaphore has been + * signaled, or even if it is now stuck on another semaphore. Play + * safe, yield if it might be stuck -- it will be given a fresh + * timeslice in the near future. + */ + return rq->context->lrc.ccid == READ_ONCE(el->yield); +} + +static bool +timeslice_expired(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + return timer_expired(&el->timer) || timeslice_yield(el, rq); +} + static int switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq) { @@ -1783,8 +1815,7 @@ timeslice(const struct intel_engine_cs *engine) return READ_ONCE(engine->props.timeslice_duration_ms); } -static unsigned long -active_timeslice(const struct intel_engine_cs *engine) +static unsigned long active_timeslice(const struct intel_engine_cs *engine) { const struct intel_engine_execlists *execlists = &engine->execlists; const struct i915_request *rq = *execlists->active; @@ -1946,13 +1977,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine) last = NULL; } else if (need_timeslice(engine, last) && - timer_expired(&engine->execlists.timer)) { + timeslice_expired(execlists, last)) { ENGINE_TRACE(engine, - "expired last=%llx:%lld, prio=%d, hint=%d\n", + "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n", last->fence.context, last->fence.seqno, last->sched.attr.priority, - execlists->queue_priority_hint); + execlists->queue_priority_hint, + yesno(timeslice_yield(execlists, last))); ring_set_paused(engine, 1); defer_active(engine); @@ -2213,6 +2245,7 @@ done: } clear_ports(port + 1, last_port - port); + WRITE_ONCE(execlists->yield, -1); execlists_submit_ports(engine); set_preempt_timeout(engine, *active); } else { @@ -3043,7 +3076,7 @@ __execlists_context_pin(struct intel_context *ce, if (IS_ERR(vaddr)) return PTR_ERR(vaddr); - ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; + ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; __execlists_update_reg_state(ce, engine, ce->ring->tail); @@ -3072,7 +3105,7 @@ static void execlists_context_reset(struct intel_context *ce) ce, ce->engine, ce->ring, true); __execlists_update_reg_state(ce, ce->engine, ce->ring->tail); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static const struct intel_context_ops execlists_context_ops = { @@ -3541,7 +3574,7 @@ static void enable_execlists(struct intel_engine_cs *engine) enable_error_interrupt(engine); - engine->context_tag = 0; + engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0); } static bool unexpected_starting_state(struct intel_engine_cs *engine) @@ -3753,7 +3786,7 @@ out_replay: head, ce->ring->tail); __execlists_reset_reg_state(ce, engine); __execlists_update_reg_state(ce, engine, head); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ unwind: /* Push back any incomplete requests for replay after the reset. */ @@ -4369,8 +4402,11 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine) engine->flags |= I915_ENGINE_SUPPORTS_STATS; if (!intel_vgpu_active(engine->i915)) { engine->flags |= I915_ENGINE_HAS_SEMAPHORES; - if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) + if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) { engine->flags |= I915_ENGINE_HAS_PREEMPTION; + if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + engine->flags |= I915_ENGINE_HAS_TIMESLICES; + } } if (INTEL_GEN(engine->i915) >= 12) @@ -4449,6 +4485,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine) engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift; engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift; engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift; + engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift; } static void rcs_submission_override(struct intel_engine_cs *engine) @@ -4516,6 +4553,11 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) else execlists->csb_size = GEN11_CSB_ENTRIES; + if (INTEL_GEN(engine->i915) >= 11) { + execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32); + execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32); + } + reset_csb_pointers(engine); /* Finally, take ownership and responsibility for cleanup! */ diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 6f06ba750a0a..f95ae15ce865 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -929,7 +929,7 @@ create_rewinder(struct intel_context *ce, goto err; } - cs = intel_ring_begin(rq, 10); + cs = intel_ring_begin(rq, 14); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err; @@ -941,8 +941,8 @@ create_rewinder(struct intel_context *ce, *cs++ = MI_SEMAPHORE_WAIT | MI_SEMAPHORE_GLOBAL_GTT | MI_SEMAPHORE_POLL | - MI_SEMAPHORE_SAD_NEQ_SDD; - *cs++ = 0; + MI_SEMAPHORE_SAD_GTE_SDD; + *cs++ = idx; *cs++ = offset; *cs++ = 0; @@ -951,6 +951,11 @@ create_rewinder(struct intel_context *ce, *cs++ = offset + idx * sizeof(u32); *cs++ = 0; + *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *cs++ = offset; + *cs++ = 0; + *cs++ = idx + 1; + intel_ring_advance(rq, cs); rq->sched.attr.priority = I915_PRIORITY_MASK; @@ -984,7 +989,7 @@ static int live_timeslice_rewind(void *arg) for_each_engine(engine, gt, id) { enum { A1, A2, B1 }; - enum { X = 1, Y, Z }; + enum { X = 1, Z, Y }; struct i915_request *rq[3] = {}; struct intel_context *ce; unsigned long heartbeat; @@ -1017,13 +1022,13 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[0] = create_rewinder(ce, NULL, slot, 1); + rq[0] = create_rewinder(ce, NULL, slot, X); if (IS_ERR(rq[0])) { intel_context_put(ce); goto err; } - rq[1] = create_rewinder(ce, NULL, slot, 2); + rq[1] = create_rewinder(ce, NULL, slot, Y); intel_context_put(ce); if (IS_ERR(rq[1])) goto err; @@ -1041,7 +1046,7 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[2] = create_rewinder(ce, rq[0], slot, 3); + rq[2] = create_rewinder(ce, rq[0], slot, Z); intel_context_put(ce); if (IS_ERR(rq[2])) goto err; @@ -1055,15 +1060,12 @@ static int live_timeslice_rewind(void *arg) GEM_BUG_ON(!timer_pending(&engine->execlists.timer)); /* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */ - GEM_BUG_ON(!i915_request_is_active(rq[A1])); - GEM_BUG_ON(!i915_request_is_active(rq[A2])); - GEM_BUG_ON(!i915_request_is_active(rq[B1])); - - /* Wait for the timeslice to kick in */ - del_timer(&engine->execlists.timer); - tasklet_hi_schedule(&engine->execlists.tasklet); - intel_engine_flush_submission(engine); - + if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */ + /* Wait for the timeslice to kick in */ + del_timer(&engine->execlists.timer); + tasklet_hi_schedule(&engine->execlists.tasklet); + intel_engine_flush_submission(engine); + } /* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */ GEM_BUG_ON(!i915_request_is_active(rq[A1])); GEM_BUG_ON(!i915_request_is_active(rq[B1])); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index fe7778c28d2d..aa6d56e25a10 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -217,7 +217,7 @@ static void guc_wq_item_append(struct intel_guc *guc, static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) { struct intel_engine_cs *engine = rq->engine; - u32 ctx_desc = lower_32_bits(rq->context->lrc_desc); + u32 ctx_desc = rq->context->lrc.ccid; u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64); guc_wq_item_append(guc, engine->guc_id, ctx_desc, diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index a83df2f84eb9..a1696e9ce4b6 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -208,14 +208,41 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) SKL_FUSE_PG_DIST_STATUS(SKL_PG0) | SKL_FUSE_PG_DIST_STATUS(SKL_PG1) | SKL_FUSE_PG_DIST_STATUS(SKL_PG2); - vgpu_vreg_t(vgpu, LCPLL1_CTL) |= - LCPLL_PLL_ENABLE | - LCPLL_PLL_LOCK; - vgpu_vreg_t(vgpu, LCPLL2_CTL) |= LCPLL_PLL_ENABLE; - + /* + * Only 1 PIPE enabled in current vGPU display and PIPE_A is + * tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A, + * TRANSCODER_A can be enabled. PORT_x depends on the input of + * setup_virtual_dp_monitor, we can bind DPLL0 to any PORT_x + * so we fixed to DPLL0 here. + * Setup DPLL0: DP link clk 1620 MHz, non SSC, DP Mode + */ + vgpu_vreg_t(vgpu, DPLL_CTRL1) = + DPLL_CTRL1_OVERRIDE(DPLL_ID_SKL_DPLL0); + vgpu_vreg_t(vgpu, DPLL_CTRL1) |= + DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, DPLL_ID_SKL_DPLL0); + vgpu_vreg_t(vgpu, LCPLL1_CTL) = + LCPLL_PLL_ENABLE | LCPLL_PLL_LOCK; + vgpu_vreg_t(vgpu, DPLL_STATUS) = DPLL_LOCK(DPLL_ID_SKL_DPLL0); + /* + * Golden M/N are calculated based on: + * 24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID), + * DP link clk 1620 MHz and non-constant_n. + * TODO: calculate DP link symbol clk and stream clk m/n. + */ + vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT; + vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e; + vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000; + vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e; + vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000; } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_B); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_B); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_B); vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | @@ -236,6 +263,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_C); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_C); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_C); vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | @@ -256,6 +289,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_D); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_D); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_D); vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index cb11c3184085..e92ed96c9b23 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -290,7 +290,7 @@ static void shadow_context_descriptor_update(struct intel_context *ce, struct intel_vgpu_workload *workload) { - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; /* * Update bits 0-11 of the context descriptor which includes flags @@ -300,7 +300,7 @@ shadow_context_descriptor_update(struct intel_context *ce, desc |= (u64)workload->ctx_desc.addressing_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; - ce->lrc_desc = desc; + ce->lrc.desc = desc; } static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload) @@ -379,7 +379,11 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) { struct i915_page_directory * const pd = i915_pd_entry(ppgtt->pd, i); - + /* skip now as current i915 ppgtt alloc won't allocate + top level pdp for non 4-level table, won't impact + shadow ppgtt. */ + if (!pd) + break; px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i]; } } diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 4518b9b35c3d..02ad1acd117c 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -128,6 +128,13 @@ search_again: active = NULL; INIT_LIST_HEAD(&eviction_list); list_for_each_entry_safe(vma, next, &vm->bound_list, vm_link) { + if (vma == active) { /* now seen this vma twice */ + if (flags & PIN_NONBLOCK) + break; + + active = ERR_PTR(-EAGAIN); + } + /* * We keep this list in a rough least-recently scanned order * of active elements (inactive elements are cheap to reap). @@ -143,21 +150,12 @@ search_again: * To notice when we complete one full cycle, we record the * first active element seen, before moving it to the tail. */ - if (i915_vma_is_active(vma)) { - if (vma == active) { - if (flags & PIN_NONBLOCK) - break; - - active = ERR_PTR(-EAGAIN); - } - - if (active != ERR_PTR(-EAGAIN)) { - if (!active) - active = vma; + if (active != ERR_PTR(-EAGAIN) && i915_vma_is_active(vma)) { + if (!active) + active = vma; - list_move_tail(&vma->vm_link, &vm->bound_list); - continue; - } + list_move_tail(&vma->vm_link, &vm->bound_list); + continue; } if (mark_free(&scan, vma, flags, &eviction_list)) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2a4cd0ba5464..5c8e51d2ba5b 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1207,8 +1207,6 @@ static void engine_record_registers(struct intel_engine_coredump *ee) static void record_request(const struct i915_request *request, struct i915_request_coredump *erq) { - const struct i915_gem_context *ctx; - erq->flags = request->fence.flags; erq->context = request->fence.context; erq->seqno = request->fence.seqno; @@ -1219,9 +1217,13 @@ static void record_request(const struct i915_request *request, erq->pid = 0; rcu_read_lock(); - ctx = rcu_dereference(request->context->gem_context); - if (ctx) - erq->pid = pid_nr(ctx->pid); + if (!intel_context_is_closed(request->context)) { + const struct i915_gem_context *ctx; + + ctx = rcu_dereference(request->context->gem_context); + if (ctx) + erq->pid = pid_nr(ctx->pid); + } rcu_read_unlock(); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index d91557d842dc..8a2b83807ffc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3361,7 +3361,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) u32 de_pipe_masked = gen8_de_pipe_fault_mask(dev_priv) | GEN8_PIPE_CDCLK_CRC_DONE; u32 de_pipe_enables; - u32 de_port_masked = GEN8_AUX_CHANNEL_A; + u32 de_port_masked = gen8_de_port_aux_mask(dev_priv); u32 de_port_enables; u32 de_misc_masked = GEN8_DE_EDP_PSR; enum pipe pipe; @@ -3369,18 +3369,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) <= 10) de_misc_masked |= GEN8_DE_MISC_GSE; - if (INTEL_GEN(dev_priv) >= 9) { - de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | - GEN9_AUX_CHANNEL_D; - if (IS_GEN9_LP(dev_priv)) - de_port_masked |= BXT_DE_PORT_GMBUS; - } - - if (INTEL_GEN(dev_priv) >= 11) - de_port_masked |= ICL_AUX_CHANNEL_E; - - if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11) - de_port_masked |= CNL_AUX_CHANNEL_F; + if (IS_GEN9_LP(dev_priv)) + de_port_masked |= BXT_DE_PORT_GMBUS; de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN; diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 66a46e41d5ef..cf2c01f17da8 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1310,8 +1310,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) * dropped by GuC. They won't be part of the context * ID in the OA reports, so squash those lower bits. */ - stream->specific_ctx_id = - lower_32_bits(ce->lrc_desc) >> 12; + stream->specific_ctx_id = ce->lrc.lrca >> 12; /* * GuC uses the top bit to signal proxy submission, so @@ -1328,11 +1327,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); /* * Pick an unused context id - * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts + * 0 - BITS_PER_LONG are used by other contexts * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context */ stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); - BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG); break; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e0c6021fdaf9..6e12000c4b6b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3094,6 +3094,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GT_BSD_CS_ERROR_INTERRUPT (1 << 15) #define GT_BSD_USER_INTERRUPT (1 << 12) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 (1 << 11) /* hsw+; rsvd on snb, ivb, vlv */ +#define GT_WAIT_SEMAPHORE_INTERRUPT REG_BIT(11) /* bdw+ */ #define GT_CONTEXT_SWITCH_INTERRUPT (1 << 8) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT (1 << 5) /* !snb */ #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT (1 << 4) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index c0df71d7d0ff..e2b78db685ea 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1017,11 +1017,15 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) GEM_BUG_ON(to == from); GEM_BUG_ON(to->timeline == from->timeline); - if (i915_request_completed(from)) + if (i915_request_completed(from)) { + i915_sw_fence_set_error_once(&to->submit, from->fence.error); return 0; + } if (to->engine->schedule) { - ret = i915_sched_node_add_dependency(&to->sched, &from->sched); + ret = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_EXTERNAL); if (ret < 0) return ret; } @@ -1183,7 +1187,9 @@ __i915_request_await_execution(struct i915_request *to, /* Couple the dependency tree for PI on this exposed to->fence */ if (to->engine->schedule) { - err = i915_sched_node_add_dependency(&to->sched, &from->sched); + err = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_WEAK); if (err < 0) return err; } diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 68b06a7ba667..f0a9e8958ca0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -456,7 +456,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, } int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal) + struct i915_sched_node *signal, + unsigned long flags) { struct i915_dependency *dep; @@ -465,8 +466,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node, return -ENOMEM; if (!__i915_sched_node_add_dependency(node, signal, dep, - I915_DEPENDENCY_EXTERNAL | - I915_DEPENDENCY_ALLOC)) + flags | I915_DEPENDENCY_ALLOC)) i915_dependency_free(dep); return 0; diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h index d1dc4efef77b..6f0bf00fc569 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.h +++ b/drivers/gpu/drm/i915/i915_scheduler.h @@ -34,7 +34,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, unsigned long flags); int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal); + struct i915_sched_node *signal, + unsigned long flags); void i915_sched_node_fini(struct i915_sched_node *node); diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h index d18e70550054..7186875088a0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler_types.h +++ b/drivers/gpu/drm/i915/i915_scheduler_types.h @@ -78,6 +78,7 @@ struct i915_dependency { unsigned long flags; #define I915_DEPENDENCY_ALLOC BIT(0) #define I915_DEPENDENCY_EXTERNAL BIT(1) +#define I915_DEPENDENCY_WEAK BIT(2) }; #endif /* _I915_SCHEDULER_TYPES_H_ */ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 82e3bc280622..2cd7a7e87c0a 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1228,18 +1228,6 @@ int __i915_vma_unbind(struct i915_vma *vma) lockdep_assert_held(&vma->vm->mutex); - /* - * First wait upon any activity as retiring the request may - * have side-effects such as unpinning or even unbinding this vma. - * - * XXX Actually waiting under the vm->mutex is a hinderance and - * should be pipelined wherever possible. In cases where that is - * unavoidable, we should lift the wait to before the mutex. - */ - ret = i915_vma_sync(vma); - if (ret) - return ret; - if (i915_vma_is_pinned(vma)) { vma_print_allocator(vma, "is pinned"); return -EAGAIN; @@ -1313,15 +1301,20 @@ int i915_vma_unbind(struct i915_vma *vma) if (!drm_mm_node_allocated(&vma->node)) return 0; - if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) - /* XXX not always required: nop_clear_range */ - wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); - /* Optimistic wait before taking the mutex */ err = i915_vma_sync(vma); if (err) goto out_rpm; + if (i915_vma_is_pinned(vma)) { + vma_print_allocator(vma, "is pinned"); + return -EAGAIN; + } + + if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) + /* XXX not always required: nop_clear_range */ + wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); + err = mutex_lock_interruptible(&vm->mutex); if (err) goto out_rpm; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8375054ba27d..a52986a9e7a6 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4992,7 +4992,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, * WaIncreaseLatencyIPCEnabled: kbl,cfl * Display WA #1141: kbl,cfl */ - if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) || + if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) && dev_priv->ipc_enabled) latency += 4; diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index 58b5f40a07dd..af89c7fc8f59 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -173,7 +173,7 @@ static int igt_vma_create(void *arg) } nc = 0; - for_each_prime_number(num_ctx, 2 * NUM_CONTEXT_TAG) { + for_each_prime_number(num_ctx, 2 * BITS_PER_LONG) { for (; nc < num_ctx; nc++) { ctx = mock_context(i915, "mock"); if (!ctx) diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c index 9dfe7cb530e1..1754c0547069 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm.c @@ -843,6 +843,7 @@ static const struct of_device_id ingenic_drm_of_match[] = { { .compatible = "ingenic,jz4770-lcd", .data = &jz4770_soc_info }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, ingenic_drm_of_match); static struct platform_driver ingenic_drm_driver = { .driver = { diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index b5f5eb7b4bb9..8c2e1b47e81a 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -412,9 +412,7 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev) if (priv->afbcd.ops) priv->afbcd.ops->init(priv); - drm_mode_config_helper_resume(priv->drm); - - return 0; + return drm_mode_config_helper_resume(priv->drm); } static int compare_of(struct device *dev, void *data) diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 059939789730..3eb89f1eb0e1 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -717,7 +717,7 @@ static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder) struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder); struct mipi_dsi_device *device = dsi->device; - union phy_configure_opts opts = { 0 }; + union phy_configure_opts opts = { }; struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy; u16 delay; int err; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index bd268028fb3d..583cd6e0ae27 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1039,6 +1039,7 @@ void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt, static bool host1x_drm_wants_iommu(struct host1x_device *dev) { + struct host1x *host1x = dev_get_drvdata(dev->dev.parent); struct iommu_domain *domain; /* @@ -1076,7 +1077,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) * sufficient and whether or not the host1x is attached to an IOMMU * doesn't matter. */ - if (!domain && dma_get_mask(dev->dev.parent) <= DMA_BIT_MASK(32)) + if (!domain && host1x_get_dma_mask(host1x) <= DMA_BIT_MASK(32)) return true; return domain != NULL; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index c1824bdf2418..7879ff58236f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -221,6 +221,7 @@ struct virtio_gpu_fpriv { /* virtio_ioctl.c */ #define DRM_VIRTIO_NUM_IOCTLS 10 extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file); /* virtio_kms.c */ int virtio_gpu_init(struct drm_device *dev); diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 0d6152c99a27..f0d5a8974677 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -39,6 +39,9 @@ int virtio_gpu_gem_create(struct drm_file *file, int ret; u32 handle; + if (vgdev->has_virgl_3d) + virtio_gpu_create_context(dev, file); + ret = virtio_gpu_object_create(vgdev, params, &obj, NULL); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 3f60bf2fe05a..512daff92038 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -34,8 +34,7 @@ #include "virtgpu_drv.h" -static void virtio_gpu_create_context(struct drm_device *dev, - struct drm_file *file) +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file) { struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_fpriv *vfpriv = file->driver_priv; diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 388bcc2889aa..d24344e91922 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -192,17 +192,55 @@ static void host1x_setup_sid_table(struct host1x *host) } } +static bool host1x_wants_iommu(struct host1x *host1x) +{ + /* + * If we support addressing a maximum of 32 bits of physical memory + * and if the host1x firewall is enabled, there's no need to enable + * IOMMU support. This can happen for example on Tegra20, Tegra30 + * and Tegra114. + * + * Tegra124 and later can address up to 34 bits of physical memory and + * many platforms come equipped with more than 2 GiB of system memory, + * which requires crossing the 4 GiB boundary. But there's a catch: on + * SoCs before Tegra186 (i.e. Tegra124 and Tegra210), the host1x can + * only address up to 32 bits of memory in GATHER opcodes, which means + * that command buffers need to either be in the first 2 GiB of system + * memory (which could quickly lead to memory exhaustion), or command + * buffers need to be treated differently from other buffers (which is + * not possible with the current ABI). + * + * A third option is to use the IOMMU in these cases to make sure all + * buffers will be mapped into a 32-bit IOVA space that host1x can + * address. This allows all of the system memory to be used and works + * within the limitations of the host1x on these SoCs. + * + * In summary, default to enable IOMMU on Tegra124 and later. For any + * of the earlier SoCs, only use the IOMMU for additional safety when + * the host1x firewall is disabled. + */ + if (host1x->info->dma_mask <= DMA_BIT_MASK(32)) { + if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + return false; + } + + return true; +} + static struct iommu_domain *host1x_iommu_attach(struct host1x *host) { struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev); int err; /* - * If the host1x firewall is enabled, there's no need to enable IOMMU - * support. Similarly, if host1x is already attached to an IOMMU (via - * the DMA API), don't try to attach again. + * We may not always want to enable IOMMU support (for example if the + * host1x firewall is already enabled and we don't support addressing + * more than 32 bits of physical memory), so check for that first. + * + * Similarly, if host1x is already attached to an IOMMU (via the DMA + * API), don't try to attach again. */ - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) || domain) + if (!host1x_wants_iommu(host) || domain) return domain; host->group = iommu_group_get(host->dev); @@ -502,6 +540,19 @@ static void __exit tegra_host1x_exit(void) } module_exit(tegra_host1x_exit); +/** + * host1x_get_dma_mask() - query the supported DMA mask for host1x + * @host1x: host1x instance + * + * Note that this returns the supported DMA mask for host1x, which can be + * different from the applicable DMA mask under certain circumstances. + */ +u64 host1x_get_dma_mask(struct host1x *host1x) +{ + return host1x->info->dma_mask; +} +EXPORT_SYMBOL(host1x_get_dma_mask); + MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>"); MODULE_AUTHOR("Terje Bergstrom <tbergstrom@nvidia.com>"); MODULE_DESCRIPTION("Host1x driver for Tegra products"); diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 7c89edbd6c5a..34f07371716d 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1155,6 +1155,7 @@ config HID_ALPS config HID_MCP2221 tristate "Microchip MCP2221 HID USB-to-I2C/SMbus host support" depends on USB_HID && I2C + depends on GPIOLIB ---help--- Provides I2C and SMBUS host adapter functionality over USB-HID through MCP2221 device. diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index fa704153cb00..b2ad319a74b9 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -802,6 +802,7 @@ static int alps_probe(struct hid_device *hdev, const struct hid_device_id *id) break; case HID_DEVICE_ID_ALPS_U1_DUAL: case HID_DEVICE_ID_ALPS_U1: + case HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY: data->dev_type = U1; break; default: diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index b18b13147a6f..1c71a1aa76b2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -79,10 +79,10 @@ #define HID_DEVICE_ID_ALPS_U1_DUAL_PTP 0x121F #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP 0x1220 #define HID_DEVICE_ID_ALPS_U1 0x1215 +#define HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY 0x121E #define HID_DEVICE_ID_ALPS_T4_BTNLESS 0x120C #define HID_DEVICE_ID_ALPS_1222 0x1222 - #define USB_VENDOR_ID_AMI 0x046b #define USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE 0xff10 @@ -385,6 +385,7 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7349 0x7349 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7 0x73f7 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 +#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002 0xc002 #define USB_VENDOR_ID_ELAN 0x04f3 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 @@ -759,6 +760,7 @@ #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2 0xc218 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2 0xc219 #define USB_DEVICE_ID_LOGITECH_G15_LCD 0xc222 +#define USB_DEVICE_ID_LOGITECH_G11 0xc225 #define USB_DEVICE_ID_LOGITECH_G15_V2_LCD 0xc227 #define USB_DEVICE_ID_LOGITECH_G510 0xc22d #define USB_DEVICE_ID_LOGITECH_G510_USB_AUDIO 0xc22e @@ -1097,6 +1099,9 @@ #define USB_DEVICE_ID_SYMBOL_SCANNER_2 0x1300 #define USB_DEVICE_ID_SYMBOL_SCANNER_3 0x1200 +#define I2C_VENDOR_ID_SYNAPTICS 0x06cb +#define I2C_PRODUCT_ID_SYNAPTICS_SYNA2393 0x7a13 + #define USB_VENDOR_ID_SYNAPTICS 0x06cb #define USB_DEVICE_ID_SYNAPTICS_TP 0x0001 #define USB_DEVICE_ID_SYNAPTICS_INT_TP 0x0002 @@ -1111,6 +1116,7 @@ #define USB_DEVICE_ID_SYNAPTICS_LTS2 0x1d10 #define USB_DEVICE_ID_SYNAPTICS_HD 0x0ac3 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD 0x1ac3 +#define USB_DEVICE_ID_SYNAPTICS_DELL_K12A 0x2819 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c index ad4b5412a9f4..ef0cbcd7540d 100644 --- a/drivers/hid/hid-lg-g15.c +++ b/drivers/hid/hid-lg-g15.c @@ -872,6 +872,10 @@ error_hw_stop: } static const struct hid_device_id lg_g15_devices[] = { + /* The G11 is a G15 without the LCD, treat it as a G15 */ + { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_G11), + .driver_data = LG_G15 }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G15_LCD), .driver_data = LG_G15 }, diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 362805ddf377..03c720b47306 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1922,6 +1922,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_EGALAX_SERIAL, MT_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) }, + { .driver_data = MT_CLS_EGALAX, + MT_USB_DEVICE(USB_VENDOR_ID_DWAV, + USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) }, /* Elitegroup panel */ { .driver_data = MT_CLS_SERIAL, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index ebec818344af..e4cb543de0cd 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -163,6 +163,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DELL_K12A), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPMAX, USB_DEVICE_ID_TOPMAX_COBRAPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8882), HID_QUIRK_NOGET }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 009000c5d55c..294c84e136d7 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -177,6 +177,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_BOGUS_IRQ }, { USB_VENDOR_ID_ALPS_JP, HID_ANY_ID, I2C_HID_QUIRK_RESET_ON_RESUME }, + { I2C_VENDOR_ID_SYNAPTICS, I2C_PRODUCT_ID_SYNAPTICS_SYNA2393, + I2C_HID_QUIRK_RESET_ON_RESUME }, { USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720, I2C_HID_QUIRK_BAD_INPUT_SIZE }, { 0, 0 } diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index c7bc9db5b192..17a638f15082 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -682,16 +682,21 @@ static int usbhid_open(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; int res; + mutex_lock(&usbhid->mutex); + set_bit(HID_OPENED, &usbhid->iofl); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return 0; + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { + res = 0; + goto Done; + } res = usb_autopm_get_interface(usbhid->intf); /* the device must be awake to reliably request remote wakeup */ if (res < 0) { clear_bit(HID_OPENED, &usbhid->iofl); - return -EIO; + res = -EIO; + goto Done; } usbhid->intf->needs_remote_wakeup = 1; @@ -725,6 +730,9 @@ static int usbhid_open(struct hid_device *hid) msleep(50); clear_bit(HID_RESUME_RUNNING, &usbhid->iofl); + + Done: + mutex_unlock(&usbhid->mutex); return res; } @@ -732,6 +740,8 @@ static void usbhid_close(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; + mutex_lock(&usbhid->mutex); + /* * Make sure we don't restart data acquisition due to * a resumption we no longer care about by avoiding racing @@ -743,12 +753,13 @@ static void usbhid_close(struct hid_device *hid) clear_bit(HID_IN_POLLING, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return; + if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { + hid_cancel_delayed_stuff(usbhid); + usb_kill_urb(usbhid->urbin); + usbhid->intf->needs_remote_wakeup = 0; + } - hid_cancel_delayed_stuff(usbhid); - usb_kill_urb(usbhid->urbin); - usbhid->intf->needs_remote_wakeup = 0; + mutex_unlock(&usbhid->mutex); } /* @@ -1057,6 +1068,8 @@ static int usbhid_start(struct hid_device *hid) unsigned int n, insize = 0; int ret; + mutex_lock(&usbhid->mutex); + clear_bit(HID_DISCONNECTED, &usbhid->iofl); usbhid->bufsize = HID_MIN_BUFFER_SIZE; @@ -1177,6 +1190,8 @@ static int usbhid_start(struct hid_device *hid) usbhid_set_leds(hid); device_set_wakeup_enable(&dev->dev, 1); } + + mutex_unlock(&usbhid->mutex); return 0; fail: @@ -1187,6 +1202,7 @@ fail: usbhid->urbout = NULL; usbhid->urbctrl = NULL; hid_free_buffers(dev, hid); + mutex_unlock(&usbhid->mutex); return ret; } @@ -1202,6 +1218,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->intf->needs_remote_wakeup = 0; } + mutex_lock(&usbhid->mutex); + clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); @@ -1222,6 +1240,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->urbout = NULL; hid_free_buffers(hid_to_usb_dev(hid), hid); + + mutex_unlock(&usbhid->mutex); } static int usbhid_power(struct hid_device *hid, int lvl) @@ -1382,6 +1402,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id * INIT_WORK(&usbhid->reset_work, hid_reset); timer_setup(&usbhid->io_retry, hid_retry_timeout, 0); spin_lock_init(&usbhid->lock); + mutex_init(&usbhid->mutex); ret = hid_add_device(hid); if (ret) { diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h index 8620408bd7af..75fe85d3d27a 100644 --- a/drivers/hid/usbhid/usbhid.h +++ b/drivers/hid/usbhid/usbhid.h @@ -80,6 +80,7 @@ struct usbhid_device { dma_addr_t outbuf_dma; /* Output buffer dma */ unsigned long last_out; /* record of last output for timeouts */ + struct mutex mutex; /* start/stop/open/close */ spinlock_t lock; /* fifo spinlock */ unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ struct timer_list io_retry; /* Retry timer */ diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 5ded94b7bf68..cd71e7133944 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -319,9 +319,11 @@ static void wacom_feature_mapping(struct hid_device *hdev, data[0] = field->report->id; ret = wacom_get_report(hdev, HID_FEATURE_REPORT, data, n, WAC_CMD_RETRIES); - if (ret == n) { + if (ret == n && features->type == HID_GENERIC) { ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, data, n, 0); + } else if (ret == 2 && features->type != HID_GENERIC) { + features->touch_max = data[1]; } else { features->touch_max = 16; hid_warn(hdev, "wacom_feature_mapping: " diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index d99a9d407671..1c96809b51c9 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1427,11 +1427,13 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) { struct input_dev *pad_input = wacom->pad_input; unsigned char *data = wacom->data; + int nbuttons = wacom->features.numbered_buttons; - int buttons = data[282] | ((data[281] & 0x40) << 2); + int expresskeys = data[282]; + int center = (data[281] & 0x40) >> 6; int ring = data[285] & 0x7F; bool ringstatus = data[285] & 0x80; - bool prox = buttons || ringstatus; + bool prox = expresskeys || center || ringstatus; /* Fix touchring data: userspace expects 0 at left and increasing clockwise */ ring = 71 - ring; @@ -1439,7 +1441,8 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) if (ring > 71) ring -= 72; - wacom_report_numbered_buttons(pad_input, 9, buttons); + wacom_report_numbered_buttons(pad_input, nbuttons, + expresskeys | (center << (nbuttons - 1))); input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0); @@ -2637,9 +2640,25 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev, case HID_DG_TIPSWITCH: hid_data->last_slot_field = equivalent_usage; break; + case HID_DG_CONTACTCOUNT: + hid_data->cc_report = report->id; + hid_data->cc_index = i; + hid_data->cc_value_index = j; + break; } } } + + if (hid_data->cc_report != 0 && + hid_data->cc_index >= 0) { + struct hid_field *field = report->field[hid_data->cc_index]; + int value = field->value[hid_data->cc_value_index]; + if (value) + hid_data->num_expected = value; + } + else { + hid_data->num_expected = wacom_wac->features.touch_max; + } } static void wacom_wac_finger_report(struct hid_device *hdev, @@ -2649,7 +2668,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, struct wacom_wac *wacom_wac = &wacom->wacom_wac; struct input_dev *input = wacom_wac->touch_input; unsigned touch_max = wacom_wac->features.touch_max; - struct hid_data *hid_data = &wacom_wac->hid_data; /* If more packets of data are expected, give us a chance to * process them rather than immediately syncing a partial @@ -2663,7 +2681,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, input_sync(input); wacom_wac->hid_data.num_received = 0; - hid_data->num_expected = 0; /* keep touch state for pen event */ wacom_wac->shared->touch_down = wacom_wac_finger_count_touches(wacom_wac); @@ -2738,73 +2755,12 @@ static void wacom_report_events(struct hid_device *hdev, } } -static void wacom_set_num_expected(struct hid_device *hdev, - struct hid_report *report, - int collection_index, - struct hid_field *field, - int field_index) -{ - struct wacom *wacom = hid_get_drvdata(hdev); - struct wacom_wac *wacom_wac = &wacom->wacom_wac; - struct hid_data *hid_data = &wacom_wac->hid_data; - unsigned int original_collection_level = - hdev->collection[collection_index].level; - bool end_collection = false; - int i; - - if (hid_data->num_expected) - return; - - // find the contact count value for this segment - for (i = field_index; i < report->maxfield && !end_collection; i++) { - struct hid_field *field = report->field[i]; - unsigned int field_level = - hdev->collection[field->usage[0].collection_index].level; - unsigned int j; - - if (field_level != original_collection_level) - continue; - - for (j = 0; j < field->maxusage; j++) { - struct hid_usage *usage = &field->usage[j]; - - if (usage->collection_index != collection_index) { - end_collection = true; - break; - } - if (wacom_equivalent_usage(usage->hid) == HID_DG_CONTACTCOUNT) { - hid_data->cc_report = report->id; - hid_data->cc_index = i; - hid_data->cc_value_index = j; - - if (hid_data->cc_report != 0 && - hid_data->cc_index >= 0) { - - struct hid_field *field = - report->field[hid_data->cc_index]; - int value = - field->value[hid_data->cc_value_index]; - - if (value) - hid_data->num_expected = value; - } - } - } - } - - if (hid_data->cc_report == 0 || hid_data->cc_index < 0) - hid_data->num_expected = wacom_wac->features.touch_max; -} - static int wacom_wac_collection(struct hid_device *hdev, struct hid_report *report, int collection_index, struct hid_field *field, int field_index) { struct wacom *wacom = hid_get_drvdata(hdev); - if (WACOM_FINGER_FIELD(field)) - wacom_set_num_expected(hdev, report, collection_index, field, - field_index); wacom_report_events(hdev, report, collection_index, field_index); /* diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c index 53b517dbe7e6..4af2fc309c28 100644 --- a/drivers/hwmon/da9052-hwmon.c +++ b/drivers/hwmon/da9052-hwmon.c @@ -244,9 +244,9 @@ static ssize_t da9052_tsi_show(struct device *dev, int channel = to_sensor_dev_attr(devattr)->index; int ret; - mutex_lock(&hwmon->hwmon_lock); + mutex_lock(&hwmon->da9052->auxadc_lock); ret = __da9052_read_tsi(dev, channel); - mutex_unlock(&hwmon->hwmon_lock); + mutex_unlock(&hwmon->da9052->auxadc_lock); if (ret < 0) return ret; diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 9179460c2d9d..0d4f3d97ffc6 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -346,7 +346,7 @@ static int drivetemp_identify_sata(struct drivetemp_data *st) st->have_temp_highest = temp_is_valid(buf[SCT_STATUS_TEMP_HIGHEST]); if (!have_sct_data_table) - goto skip_sct; + goto skip_sct_data; /* Request and read temperature history table */ memset(buf, '\0', sizeof(st->smartdata)); diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index 1f5743d68984..a7eb10d2a053 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -41,6 +41,7 @@ #define FANCTL_MAX 4 /* Counted from 1 */ #define TCPU_MAX 8 /* Counted from 1 */ #define TEMP_MAX 4 /* Counted from 1 */ +#define SMI_STS_MAX 10 /* Counted from 1 */ #define VT_ADC_CTRL0_REG 0x20 /* Bank 0 */ #define VT_ADC_CTRL1_REG 0x21 /* Bank 0 */ @@ -361,6 +362,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel, struct nct7904_data *data = dev_get_drvdata(dev); int ret, temp; unsigned int reg1, reg2, reg3; + s8 temps; switch (attr) { case hwmon_temp_input: @@ -466,7 +468,8 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel, if (ret < 0) return ret; - *val = ret * 1000; + temps = ret; + *val = temps * 1000; return 0; } @@ -1009,6 +1012,13 @@ static int nct7904_probe(struct i2c_client *client, data->fan_mode[i] = ret; } + /* Read all of SMI status register to clear alarms */ + for (i = 0; i < SMI_STS_MAX; i++) { + ret = nct7904_read_reg(data, BANK_0, SMI_STS1_REG + i); + if (ret < 0) + return ret; + } + hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data, &nct7904_chip_info, NULL); diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index a03c6d6833df..96fb9ff5ff2e 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -78,7 +78,7 @@ static struct qcom_icc_node *sdm845_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sdm845_osm_l3, }; -const static struct qcom_icc_desc sdm845_icc_osm_l3 = { +static const struct qcom_icc_desc sdm845_icc_osm_l3 = { .nodes = sdm845_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sdm845_osm_l3_nodes), }; @@ -91,7 +91,7 @@ static struct qcom_icc_node *sc7180_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sc7180_osm_l3, }; -const static struct qcom_icc_desc sc7180_icc_osm_l3 = { +static const struct qcom_icc_desc sc7180_icc_osm_l3 = { .nodes = sc7180_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sc7180_osm_l3_nodes), }; diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c index b013b80caa45..f6c7b969520d 100644 --- a/drivers/interconnect/qcom/sdm845.c +++ b/drivers/interconnect/qcom/sdm845.c @@ -192,7 +192,7 @@ static struct qcom_icc_node *aggre1_noc_nodes[] = { [SLAVE_ANOC_PCIE_A1NOC_SNOC] = &qns_pcie_a1noc_snoc, }; -const static struct qcom_icc_desc sdm845_aggre1_noc = { +static const struct qcom_icc_desc sdm845_aggre1_noc = { .nodes = aggre1_noc_nodes, .num_nodes = ARRAY_SIZE(aggre1_noc_nodes), .bcms = aggre1_noc_bcms, @@ -220,7 +220,7 @@ static struct qcom_icc_node *aggre2_noc_nodes[] = { [SLAVE_SERVICE_A2NOC] = &srvc_aggre2_noc, }; -const static struct qcom_icc_desc sdm845_aggre2_noc = { +static const struct qcom_icc_desc sdm845_aggre2_noc = { .nodes = aggre2_noc_nodes, .num_nodes = ARRAY_SIZE(aggre2_noc_nodes), .bcms = aggre2_noc_bcms, @@ -281,7 +281,7 @@ static struct qcom_icc_node *config_noc_nodes[] = { [SLAVE_SERVICE_CNOC] = &srvc_cnoc, }; -const static struct qcom_icc_desc sdm845_config_noc = { +static const struct qcom_icc_desc sdm845_config_noc = { .nodes = config_noc_nodes, .num_nodes = ARRAY_SIZE(config_noc_nodes), .bcms = config_noc_bcms, @@ -297,7 +297,7 @@ static struct qcom_icc_node *dc_noc_nodes[] = { [SLAVE_MEM_NOC_CFG] = &qhs_memnoc, }; -const static struct qcom_icc_desc sdm845_dc_noc = { +static const struct qcom_icc_desc sdm845_dc_noc = { .nodes = dc_noc_nodes, .num_nodes = ARRAY_SIZE(dc_noc_nodes), .bcms = dc_noc_bcms, @@ -315,7 +315,7 @@ static struct qcom_icc_node *gladiator_noc_nodes[] = { [SLAVE_SERVICE_GNOC] = &srvc_gnoc, }; -const static struct qcom_icc_desc sdm845_gladiator_noc = { +static const struct qcom_icc_desc sdm845_gladiator_noc = { .nodes = gladiator_noc_nodes, .num_nodes = ARRAY_SIZE(gladiator_noc_nodes), .bcms = gladiator_noc_bcms, @@ -350,7 +350,7 @@ static struct qcom_icc_node *mem_noc_nodes[] = { [SLAVE_EBI1] = &ebi, }; -const static struct qcom_icc_desc sdm845_mem_noc = { +static const struct qcom_icc_desc sdm845_mem_noc = { .nodes = mem_noc_nodes, .num_nodes = ARRAY_SIZE(mem_noc_nodes), .bcms = mem_noc_bcms, @@ -384,7 +384,7 @@ static struct qcom_icc_node *mmss_noc_nodes[] = { [SLAVE_CAMNOC_UNCOMP] = &qns_camnoc_uncomp, }; -const static struct qcom_icc_desc sdm845_mmss_noc = { +static const struct qcom_icc_desc sdm845_mmss_noc = { .nodes = mmss_noc_nodes, .num_nodes = ARRAY_SIZE(mmss_noc_nodes), .bcms = mmss_noc_bcms, @@ -430,7 +430,7 @@ static struct qcom_icc_node *system_noc_nodes[] = { [SLAVE_TCU] = &xs_sys_tcu_cfg, }; -const static struct qcom_icc_desc sdm845_system_noc = { +static const struct qcom_icc_desc sdm845_system_noc = { .nodes = system_noc_nodes, .num_nodes = ARRAY_SIZE(system_noc_nodes), .bcms = system_noc_bcms, diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 20cce366e951..1dc3718560d0 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -101,6 +101,8 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); static void detach_device(struct device *dev); +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable); /**************************************************************************** * @@ -151,6 +153,26 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom) return container_of(dom, struct protection_domain, domain); } +static void amd_iommu_domain_get_pgtable(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + u64 pt_root = atomic64_read(&domain->pt_root); + + pgtable->root = (u64 *)(pt_root & PAGE_MASK); + pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */ +} + +static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode) +{ + u64 pt_root; + + /* lowest 3 bits encode pgtable mode */ + pt_root = mode & 7; + pt_root |= (u64)root; + + return pt_root; +} + static struct iommu_dev_data *alloc_dev_data(u16 devid) { struct iommu_dev_data *dev_data; @@ -1397,13 +1419,18 @@ static struct page *free_sub_pt(unsigned long root, int mode, static void free_pagetable(struct protection_domain *domain) { - unsigned long root = (unsigned long)domain->pt_root; + struct domain_pgtable pgtable; struct page *freelist = NULL; + unsigned long root; - BUG_ON(domain->mode < PAGE_MODE_NONE || - domain->mode > PAGE_MODE_6_LEVEL); + amd_iommu_domain_get_pgtable(domain, &pgtable); + atomic64_set(&domain->pt_root, 0); - freelist = free_sub_pt(root, domain->mode, freelist); + BUG_ON(pgtable.mode < PAGE_MODE_NONE || + pgtable.mode > PAGE_MODE_6_LEVEL); + + root = (unsigned long)pgtable.root; + freelist = free_sub_pt(root, pgtable.mode, freelist); free_page_list(freelist); } @@ -1417,24 +1444,39 @@ static bool increase_address_space(struct protection_domain *domain, unsigned long address, gfp_t gfp) { + struct domain_pgtable pgtable; unsigned long flags; - bool ret = false; - u64 *pte; + bool ret = true; + u64 *pte, root; spin_lock_irqsave(&domain->lock, flags); - if (address <= PM_LEVEL_SIZE(domain->mode) || - WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address <= PM_LEVEL_SIZE(pgtable.mode)) + goto out; + + ret = false; + if (WARN_ON_ONCE(pgtable.mode == PAGE_MODE_6_LEVEL)) goto out; pte = (void *)get_zeroed_page(gfp); if (!pte) goto out; - *pte = PM_LEVEL_PDE(domain->mode, - iommu_virt_to_phys(domain->pt_root)); - domain->pt_root = pte; - domain->mode += 1; + *pte = PM_LEVEL_PDE(pgtable.mode, iommu_virt_to_phys(pgtable.root)); + + pgtable.root = pte; + pgtable.mode += 1; + update_and_flush_device_table(domain, &pgtable); + domain_flush_complete(domain); + + /* + * Device Table needs to be updated and flushed before the new root can + * be published. + */ + root = amd_iommu_domain_encode_pgtable(pte, pgtable.mode); + atomic64_set(&domain->pt_root, root); ret = true; @@ -1451,16 +1493,29 @@ static u64 *alloc_pte(struct protection_domain *domain, gfp_t gfp, bool *updated) { + struct domain_pgtable pgtable; int level, end_lvl; u64 *pte, *page; BUG_ON(!is_power_of_2(page_size)); - while (address > PM_LEVEL_SIZE(domain->mode)) - *updated = increase_address_space(domain, address, gfp) || *updated; + amd_iommu_domain_get_pgtable(domain, &pgtable); + + while (address > PM_LEVEL_SIZE(pgtable.mode)) { + /* + * Return an error if there is no memory to update the + * page-table. + */ + if (!increase_address_space(domain, address, gfp)) + return NULL; + + /* Read new values to check if update was successful */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + } + - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -1536,16 +1591,19 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address, unsigned long *page_size) { + struct domain_pgtable pgtable; int level; u64 *pte; *page_size = 0; - if (address > PM_LEVEL_SIZE(domain->mode)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address > PM_LEVEL_SIZE(pgtable.mode)) return NULL; - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -1660,7 +1718,13 @@ out: unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - update_domain(dom); + /* + * Flush domain TLB(s) and wait for completion. Any Device-Table + * Updates and flushing already happened in + * increase_address_space(). + */ + domain_flush_tlb_pde(dom); + domain_flush_complete(dom); spin_unlock_irqrestore(&dom->lock, flags); } @@ -1806,6 +1870,7 @@ static void dma_ops_domain_free(struct protection_domain *domain) static struct protection_domain *dma_ops_domain_alloc(void) { struct protection_domain *domain; + u64 *pt_root, root; domain = kzalloc(sizeof(struct protection_domain), GFP_KERNEL); if (!domain) @@ -1814,12 +1879,14 @@ static struct protection_domain *dma_ops_domain_alloc(void) if (protection_domain_init(domain)) goto free_domain; - domain->mode = PAGE_MODE_3_LEVEL; - domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - domain->flags = PD_DMA_OPS_MASK; - if (!domain->pt_root) + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) goto free_domain; + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&domain->pt_root, root); + domain->flags = PD_DMA_OPS_MASK; + if (iommu_get_dma_cookie(&domain->domain) == -ENOMEM) goto free_domain; @@ -1841,16 +1908,17 @@ static bool dma_ops_domain(struct protection_domain *domain) } static void set_dte_entry(u16 devid, struct protection_domain *domain, + struct domain_pgtable *pgtable, bool ats, bool ppr) { u64 pte_root = 0; u64 flags = 0; u32 old_domid; - if (domain->mode != PAGE_MODE_NONE) - pte_root = iommu_virt_to_phys(domain->pt_root); + if (pgtable->mode != PAGE_MODE_NONE) + pte_root = iommu_virt_to_phys(pgtable->root); - pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK) + pte_root |= (pgtable->mode & DEV_ENTRY_MODE_MASK) << DEV_ENTRY_MODE_SHIFT; pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V | DTE_FLAG_TV; @@ -1923,6 +1991,7 @@ static void clear_dte_entry(u16 devid) static void do_attach(struct iommu_dev_data *dev_data, struct protection_domain *domain) { + struct domain_pgtable pgtable; struct amd_iommu *iommu; bool ats; @@ -1938,7 +2007,9 @@ static void do_attach(struct iommu_dev_data *dev_data, domain->dev_cnt += 1; /* Update device table */ - set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2); + amd_iommu_domain_get_pgtable(domain, &pgtable); + set_dte_entry(dev_data->devid, domain, &pgtable, + ats, dev_data->iommu_v2); clone_aliases(dev_data->pdev); device_flush_dte(dev_data); @@ -2249,23 +2320,36 @@ static int amd_iommu_domain_get_attr(struct iommu_domain *domain, * *****************************************************************************/ -static void update_device_table(struct protection_domain *domain) +static void update_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) { struct iommu_dev_data *dev_data; list_for_each_entry(dev_data, &domain->dev_list, list) { - set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled, - dev_data->iommu_v2); + set_dte_entry(dev_data->devid, domain, pgtable, + dev_data->ats.enabled, dev_data->iommu_v2); clone_aliases(dev_data->pdev); } } +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + update_device_table(domain, pgtable); + domain_flush_devices(domain); +} + static void update_domain(struct protection_domain *domain) { - update_device_table(domain); + struct domain_pgtable pgtable; - domain_flush_devices(domain); + /* Update device table */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + update_and_flush_device_table(domain, &pgtable); + + /* Flush domain TLB(s) and wait for completion */ domain_flush_tlb_pde(domain); + domain_flush_complete(domain); } int __init amd_iommu_init_api(void) @@ -2375,6 +2459,7 @@ out_err: static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { struct protection_domain *pdomain; + u64 *pt_root, root; switch (type) { case IOMMU_DOMAIN_UNMANAGED: @@ -2382,13 +2467,15 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_3_LEVEL; - pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - if (!pdomain->pt_root) { + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) { protection_domain_free(pdomain); return NULL; } + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&pdomain->pt_root, root); + pdomain->domain.geometry.aperture_start = 0; pdomain->domain.geometry.aperture_end = ~0ULL; pdomain->domain.geometry.force_aperture = true; @@ -2406,7 +2493,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_NONE; + atomic64_set(&pdomain->pt_root, PAGE_MODE_NONE); break; default: return NULL; @@ -2418,6 +2505,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) static void amd_iommu_domain_free(struct iommu_domain *dom) { struct protection_domain *domain; + struct domain_pgtable pgtable; domain = to_pdomain(dom); @@ -2435,7 +2523,9 @@ static void amd_iommu_domain_free(struct iommu_domain *dom) dma_ops_domain_free(domain); break; default: - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (pgtable.mode != PAGE_MODE_NONE) free_pagetable(domain); if (domain->flags & PD_IOMMUV2_MASK) @@ -2518,10 +2608,12 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, gfp_t gfp) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; int prot = 0; int ret; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return -EINVAL; if (iommu_prot & IOMMU_READ) @@ -2541,8 +2633,10 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, struct iommu_iotlb_gather *gather) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return 0; return iommu_unmap_page(domain, iova, page_size); @@ -2553,9 +2647,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, { struct protection_domain *domain = to_pdomain(dom); unsigned long offset_mask, pte_pgsize; + struct domain_pgtable pgtable; u64 *pte, __pte; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return iova; pte = fetch_pte(domain, iova, &pte_pgsize); @@ -2708,16 +2804,26 @@ EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier); void amd_iommu_domain_direct_map(struct iommu_domain *dom) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; unsigned long flags; + u64 pt_root; spin_lock_irqsave(&domain->lock, flags); + /* First save pgtable configuration*/ + amd_iommu_domain_get_pgtable(domain, &pgtable); + /* Update data structure */ - domain->mode = PAGE_MODE_NONE; + pt_root = amd_iommu_domain_encode_pgtable(NULL, PAGE_MODE_NONE); + atomic64_set(&domain->pt_root, pt_root); /* Make changes visible to IOMMUs */ update_domain(domain); + /* Restore old pgtable in domain->ptroot to free page-table */ + pt_root = amd_iommu_domain_encode_pgtable(pgtable.root, pgtable.mode); + atomic64_set(&domain->pt_root, pt_root); + /* Page-table is not visible to IOMMU anymore, so free it */ free_pagetable(domain); @@ -2908,9 +3014,11 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc) static int __set_gcr3(struct protection_domain *domain, int pasid, unsigned long cr3) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, true); @@ -2924,9 +3032,11 @@ static int __set_gcr3(struct protection_domain *domain, int pasid, static int __clear_gcr3(struct protection_domain *domain, int pasid) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, false); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index ca8c4522045b..7a8fdec138bd 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -468,8 +468,7 @@ struct protection_domain { iommu core code */ spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ - int mode; /* paging mode (0-6 levels) */ - u64 *pt_root; /* page table root pointer */ + atomic64_t pt_root; /* pgtable root and pgtable mode */ int glx; /* Number of levels for GCR3 table */ u64 *gcr3_tbl; /* Guest CR3 table */ unsigned long flags; /* flags to find out type of domain */ @@ -477,6 +476,12 @@ struct protection_domain { unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ }; +/* For decocded pt_root */ +struct domain_pgtable { + int mode; + u64 *root; +}; + /* * Structure where we save information about one hardware AMD IOMMU in the * system. diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index d5cac4f46ca5..4e1d11af23c8 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -453,7 +453,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev, if (!region) return -ENOMEM; - list_add(&vdev->resv_regions, ®ion->list); + list_add(®ion->list, &vdev->resv_regions); return 0; } diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 668418d7ea77..f620442addf5 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1465,6 +1465,13 @@ static const struct mei_cfg mei_me_pch12_cfg = { MEI_CFG_DMA_128, }; +/* LBG with quirk for SPS Firmware exclusion */ +static const struct mei_cfg mei_me_pch12_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_FW_SPS, +}; + /* Tiger Lake and newer devices */ static const struct mei_cfg mei_me_pch15_cfg = { MEI_CFG_PCH8_HFS, @@ -1487,6 +1494,7 @@ static const struct mei_cfg *const mei_cfg_list[] = { [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, [MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg, + [MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg, [MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg, }; diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index 4a8d4dcd5a91..b6b94e211464 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -80,6 +80,9 @@ struct mei_me_hw { * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH12_CFG: Platform Controller Hub Gen12 and newer + * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 and newer + * servers platforms with quirk for + * SPS firmware exclusion. * @MEI_ME_PCH15_CFG: Platform Controller Hub Gen15 and newer * @MEI_ME_NUM_CFG: Upper Sentinel. */ @@ -93,6 +96,7 @@ enum mei_cfg_idx { MEI_ME_PCH8_CFG, MEI_ME_PCH8_SPS_CFG, MEI_ME_PCH12_CFG, + MEI_ME_PCH12_SPS_CFG, MEI_ME_PCH15_CFG, MEI_ME_NUM_CFG, }; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 0c390fe421ad..a1ed375fed37 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -70,7 +70,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8499b56a15a8..c5367e2c8487 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1370,6 +1370,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req) struct mmc_request *mrq = &mqrq->brq.mrq; struct request_queue *q = req->q; struct mmc_host *host = mq->card->host; + enum mmc_issue_type issue_type = mmc_issue_type(mq, req); unsigned long flags; bool put_card; int err; @@ -1399,7 +1400,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req) spin_lock_irqsave(&mq->lock, flags); - mq->in_flight[mmc_issue_type(mq, req)] -= 1; + mq->in_flight[issue_type] -= 1; put_card = (mmc_tot_in_flight(mq) == 0); diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 25bee3daf9e2..4b1eb89b401d 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -107,11 +107,10 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req) case MMC_ISSUE_DCMD: if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) { if (recovery_needed) - __mmc_cqe_recovery_notifier(mq); + mmc_cqe_recovery_notifier(mrq); return BLK_EH_RESET_TIMER; } - /* No timeout (XXX: huh? comment doesn't make much sense) */ - blk_mq_complete_request(req); + /* The request has gone already */ return BLK_EH_DONE; default: /* Timeout is handled by mmc core */ @@ -127,18 +126,13 @@ static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req, struct mmc_card *card = mq->card; struct mmc_host *host = card->host; unsigned long flags; - int ret; + bool ignore_tout; spin_lock_irqsave(&mq->lock, flags); - - if (mq->recovery_needed || !mq->use_cqe || host->hsq_enabled) - ret = BLK_EH_RESET_TIMER; - else - ret = mmc_cqe_timed_out(req); - + ignore_tout = mq->recovery_needed || !mq->use_cqe || host->hsq_enabled; spin_unlock_irqrestore(&mq->lock, flags); - return ret; + return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req); } static void mmc_mq_recovery_handler(struct work_struct *work) diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c index 1aee485d56d4..026ca9194ce5 100644 --- a/drivers/mmc/host/alcor.c +++ b/drivers/mmc/host/alcor.c @@ -1104,7 +1104,7 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to get irq for data line\n"); - return ret; + goto free_host; } mutex_init(&host->cmd_mutex); @@ -1116,6 +1116,10 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, host); mmc_add_host(mmc); return 0; + +free_host: + mmc_free_host(mmc); + return ret; } static int alcor_pci_sdmmc_drv_remove(struct platform_device *pdev) diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index faba53cf139b..d8b76cb8698a 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -605,10 +605,12 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev, } static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = { - .chip = &sdhci_acpi_chip_amd, - .caps = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE, - .quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | SDHCI_QUIRK_32BIT_DMA_SIZE | - SDHCI_QUIRK_32BIT_ADMA_SIZE, + .chip = &sdhci_acpi_chip_amd, + .caps = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE, + .quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | + SDHCI_QUIRK_32BIT_DMA_SIZE | + SDHCI_QUIRK_32BIT_ADMA_SIZE, + .quirks2 = SDHCI_QUIRK2_BROKEN_64_BIT_DMA, .probe_slot = sdhci_acpi_emmc_amd_probe_slot, }; diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index ce15a05f23d4..fd76aa672e02 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -26,6 +26,9 @@ #define SDHCI_GLI_9750_DRIVING_2 GENMASK(27, 26) #define GLI_9750_DRIVING_1_VALUE 0xFFF #define GLI_9750_DRIVING_2_VALUE 0x3 +#define SDHCI_GLI_9750_SEL_1 BIT(29) +#define SDHCI_GLI_9750_SEL_2 BIT(31) +#define SDHCI_GLI_9750_ALL_RST (BIT(24)|BIT(25)|BIT(28)|BIT(30)) #define SDHCI_GLI_9750_PLL 0x864 #define SDHCI_GLI_9750_PLL_TX2_INV BIT(23) @@ -122,6 +125,8 @@ static void gli_set_9750(struct sdhci_host *host) GLI_9750_DRIVING_1_VALUE); driving_value |= FIELD_PREP(SDHCI_GLI_9750_DRIVING_2, GLI_9750_DRIVING_2_VALUE); + driving_value &= ~(SDHCI_GLI_9750_SEL_1|SDHCI_GLI_9750_SEL_2|SDHCI_GLI_9750_ALL_RST); + driving_value |= SDHCI_GLI_9750_SEL_2; sdhci_writel(host, driving_value, SDHCI_GLI_9750_DRIVING); sw_ctrl_value &= ~SDHCI_GLI_9750_SW_CTRL_4; @@ -334,6 +339,18 @@ static u32 sdhci_gl9750_readl(struct sdhci_host *host, int reg) return value; } +#ifdef CONFIG_PM_SLEEP +static int sdhci_pci_gli_resume(struct sdhci_pci_chip *chip) +{ + struct sdhci_pci_slot *slot = chip->slots[0]; + + pci_free_irq_vectors(slot->chip->pdev); + gli_pcie_enable_msi(slot); + + return sdhci_pci_resume_host(chip); +} +#endif + static const struct sdhci_ops sdhci_gl9755_ops = { .set_clock = sdhci_set_clock, .enable_dma = sdhci_pci_enable_dma, @@ -348,6 +365,9 @@ const struct sdhci_pci_fixes sdhci_gl9755 = { .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50, .probe_slot = gli_probe_slot_gl9755, .ops = &sdhci_gl9755_ops, +#ifdef CONFIG_PM_SLEEP + .resume = sdhci_pci_gli_resume, +#endif }; static const struct sdhci_ops sdhci_gl9750_ops = { @@ -366,4 +386,7 @@ const struct sdhci_pci_fixes sdhci_gl9750 = { .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50, .probe_slot = gli_probe_slot_gl9750, .ops = &sdhci_gl9750_ops, +#ifdef CONFIG_PM_SLEEP + .resume = sdhci_pci_gli_resume, +#endif }; diff --git a/drivers/most/core.c b/drivers/most/core.c index 06426fc5c990..f781c46cd4af 100644 --- a/drivers/most/core.c +++ b/drivers/most/core.c @@ -1483,7 +1483,7 @@ static void __exit most_exit(void) ida_destroy(&mdev_id); } -module_init(most_init); +subsys_initcall(most_init); module_exit(most_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Christian Gromm <christian.gromm@microchip.com>"); diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 6435020d690d..51185e4d7d15 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -24,8 +24,8 @@ config NET_DSA_MV88E6XXX_PTP bool "PTP support for Marvell 88E6xxx" default n depends on NET_DSA_MV88E6XXX_GLOBAL2 + depends on PTP_1588_CLOCK imply NETWORK_PHY_TIMESTAMPING - imply PTP_1588_CLOCK help Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch chips that support it. diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index dd8a5666a584..2b4a723c8306 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3962,7 +3962,6 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390_phylink_validate, }; @@ -4021,7 +4020,6 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390x_phylink_validate, }; @@ -4079,7 +4077,6 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, .phylink_validate = mv88e6390_phylink_validate, @@ -4235,7 +4232,6 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index d0a3764ff0cf..e2c6bf0e430e 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -400,6 +400,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) ocelot->stats_layout = felix->info->stats_layout; ocelot->num_stats = felix->info->num_stats; ocelot->shared_queue_sz = felix->info->shared_queue_sz; + ocelot->num_mact_rows = felix->info->num_mact_rows; ocelot->vcap_is2_keys = felix->info->vcap_is2_keys; ocelot->vcap_is2_actions= felix->info->vcap_is2_actions; ocelot->vcap = felix->info->vcap; diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 82d46f260041..9af106513e53 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -15,6 +15,7 @@ struct felix_info { const u32 *const *map; const struct ocelot_ops *ops; int shared_queue_sz; + int num_mact_rows; const struct ocelot_stat_layout *stats_layout; unsigned int num_stats; int num_ports; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index b4078f3c5c38..8bf395f12b47 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1220,6 +1220,7 @@ struct felix_info felix_info_vsc9959 = { .vcap_is2_actions = vsc9959_vcap_is2_actions, .vcap = vsc9959_vcap_props, .shared_queue_sz = 128 * 1024, + .num_mact_rows = 2048, .num_ports = 6, .switch_pci_bar = 4, .imdio_pci_bar = 0, diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index 0fe1ae173aa1..68c3086af9af 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -20,6 +20,7 @@ tristate "NXP SJA1105 Ethernet switch family support" config NET_DSA_SJA1105_PTP bool "Support for the PTP clock on the NXP SJA1105 Ethernet switch" depends on NET_DSA_SJA1105 + depends on PTP_1588_CLOCK help This enables support for timestamping and PTP clock manipulations in the SJA1105 DSA driver. diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index a22f8e3fc06b..bc0e47c1dbb9 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -16,14 +16,15 @@ /* PTPSYNCTS has no interrupt or update mechanism, because the intended * hardware use case is for the timestamp to be collected synchronously, - * immediately after the CAS_MASTER SJA1105 switch has triggered a CASSYNC - * pulse on the PTP_CLK pin. When used as a generic extts source, it needs - * polling and a comparison with the old value. The polling interval is just - * the Nyquist rate of a canonical PPS input (e.g. from a GPS module). - * Anything of higher frequency than 1 Hz will be lost, since there is no - * timestamp FIFO. + * immediately after the CAS_MASTER SJA1105 switch has performed a CASSYNC + * one-shot toggle (no return to level) on the PTP_CLK pin. When used as a + * generic extts source, the PTPSYNCTS register needs polling and a comparison + * with the old value. The polling interval is configured as the Nyquist rate + * of a signal with 50% duty cycle and 1Hz frequency, which is sadly all that + * this hardware can do (but may be enough for some setups). Anything of higher + * frequency than 1 Hz will be lost, since there is no timestamp FIFO. */ -#define SJA1105_EXTTS_INTERVAL (HZ / 2) +#define SJA1105_EXTTS_INTERVAL (HZ / 4) /* This range is actually +/- SJA1105_MAX_ADJ_PPB * divided by 1000 (ppb -> ppm) and with a 16-bit @@ -754,7 +755,16 @@ static int sja1105_extts_enable(struct sja1105_private *priv, return -EOPNOTSUPP; /* Reject requests with unsupported flags */ - if (extts->flags) + if (extts->flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* We can only enable time stamping on both edges, sadly. */ + if ((extts->flags & PTP_STRICT_FLAGS) && + (extts->flags & PTP_ENABLE_FEATURE) && + (extts->flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) return -EOPNOTSUPP; rc = sja1105_change_ptp_clk_pin_func(priv, PTP_PF_EXTTS); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 97dfd0c67e84..9e1860d81908 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -69,7 +69,7 @@ * 16kB. */ #if PAGE_SIZE > SZ_16K -#define ENA_PAGE_SIZE SZ_16K +#define ENA_PAGE_SIZE (_AC(SZ_16K, UL)) #else #define ENA_PAGE_SIZE PAGE_SIZE #endif diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 2edf137a7030..8a70ffe1d326 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -57,7 +57,7 @@ static const struct aq_board_revision_s hw_atl_boards[] = { { AQ_DEVICE_ID_D108, AQ_HWREV_2, &hw_atl_ops_b0, &hw_atl_b0_caps_aqc108, }, { AQ_DEVICE_ID_D109, AQ_HWREV_2, &hw_atl_ops_b0, &hw_atl_b0_caps_aqc109, }, - { AQ_DEVICE_ID_AQC100, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, }, + { AQ_DEVICE_ID_AQC100, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc100, }, { AQ_DEVICE_ID_AQC107, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, }, { AQ_DEVICE_ID_AQC108, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc108, }, { AQ_DEVICE_ID_AQC109, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc109, }, diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index a5d1a6cb9ce3..6795b6d95f54 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -172,6 +172,7 @@ static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct bgmac *bgmac; + struct resource *regs; const u8 *mac_addr; bgmac = bgmac_alloc(&pdev->dev); @@ -206,16 +207,21 @@ static int bgmac_probe(struct platform_device *pdev) if (IS_ERR(bgmac->plat.base)) return PTR_ERR(bgmac->plat.base); - bgmac->plat.idm_base = - devm_platform_ioremap_resource_byname(pdev, "idm_base"); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); + if (regs) { + bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; + } - bgmac->plat.nicpm_base = - devm_platform_ioremap_resource_byname(pdev, "nicpm_base"); - if (IS_ERR(bgmac->plat.nicpm_base)) - return PTR_ERR(bgmac->plat.nicpm_base); + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); + if (regs) { + bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, + regs); + if (IS_ERR(bgmac->plat.nicpm_base)) + return PTR_ERR(bgmac->plat.nicpm_base); + } bgmac->read = platform_bgmac_read; bgmac->write = platform_bgmac_write; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fead64f1ad90..d1a83716d934 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6642,7 +6642,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp, int rc; if (!mem_size) - return 0; + return -EINVAL; ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE); if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) { @@ -9780,6 +9780,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, netdev_features_t features) { struct bnxt *bp = netdev_priv(dev); + netdev_features_t vlan_features; if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp)) features &= ~NETIF_F_NTUPLE; @@ -9796,12 +9797,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, /* Both CTAG and STAG VLAN accelaration on the RX side have to be * turned on or off together. */ - if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) != - (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) { + vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX); + if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX)) { if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) features &= ~(NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); - else + else if (vlan_features) features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; } @@ -12212,12 +12215,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) bnxt_ulp_start(bp, err); } - if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev)) - dev_close(netdev); + if (result != PCI_ERS_RESULT_RECOVERED) { + if (netif_running(netdev)) + dev_close(netdev); + pci_disable_device(pdev); + } rtnl_unlock(); - return PCI_ERS_RESULT_RECOVERED; + return result; } /** diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index f2caa2756f5b..f6a3250ef1c5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1066,7 +1066,6 @@ struct bnxt_vf_info { #define BNXT_VF_LINK_FORCED 0x4 #define BNXT_VF_LINK_UP 0x8 #define BNXT_VF_TRUST 0x10 - u32 func_flags; /* func cfg flags */ u32 min_tx_rate; u32 max_tx_rate; void *hwrm_cmd_req_addr; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 95f893f2a74d..d5c8bd49383a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -43,7 +43,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) #define BNXT_NVM_CFG_VER_BITS 24 #define BNXT_NVM_CFG_VER_BYTES 4 -#define BNXT_MSIX_VEC_MAX 1280 +#define BNXT_MSIX_VEC_MAX 512 #define BNXT_MSIX_VEC_MIN_MAX 128 enum bnxt_nvm_dir_type { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 6ea3df6da18c..cea2f9958a1d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -85,11 +85,10 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) if (old_setting == setting) return 0; - func_flags = vf->func_flags; if (setting) - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; else - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; /*TODO: if the driver supports VLAN filter on guest VLAN, * the spoof check should also include vlan anti-spoofing */ @@ -98,7 +97,6 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) req.flags = cpu_to_le32(func_flags); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { - vf->func_flags = func_flags; if (setting) vf->flags |= BNXT_VF_SPOOFCHK; else @@ -228,7 +226,6 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac) memcpy(vf->mac_addr, mac, ETH_ALEN); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); memcpy(req.dflt_mac_addr, mac, ETH_ALEN); return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -266,7 +263,6 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.dflt_vlan = cpu_to_le16(vlan_tag); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -305,7 +301,6 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate, return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW); req.max_bw = cpu_to_le32(max_tx_rate); req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW); @@ -477,7 +472,6 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id) vf = &bp->pf.vf[vf_id]; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); if (is_valid_ether_addr(vf->mac_addr)) { req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig index 53b50c24d9c9..2c4c12b03502 100644 --- a/drivers/net/ethernet/cadence/Kconfig +++ b/drivers/net/ethernet/cadence/Kconfig @@ -35,8 +35,8 @@ config MACB config MACB_USE_HWSTAMP bool "Use IEEE 1588 hwstamp" depends on MACB + depends on PTP_1588_CLOCK default y - imply PTP_1588_CLOCK ---help--- Enable IEEE 1588 Precision Time Protocol (PTP) support for MACB. diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index a0e8c5bbabc0..36290a8e2a84 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -334,8 +334,10 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum) int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -386,8 +388,10 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum, int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -3816,8 +3820,10 @@ static int at91ether_open(struct net_device *dev) int ret; ret = pm_runtime_get_sync(&lp->pdev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(&lp->pdev->dev); return ret; + } /* Clear internal statistics */ ctl = macb_readl(lp, NCR); @@ -4172,15 +4178,9 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk, static int fu540_c000_init(struct platform_device *pdev) { - struct resource *res; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!res) - return -ENODEV; - - mgmt->reg = ioremap(res->start, resource_size(res)); - if (!mgmt->reg) - return -ENOMEM; + mgmt->reg = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(mgmt->reg)) + return PTR_ERR(mgmt->reg); return macb_init(pdev); } diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 6a700d34019e..4520e7ee00fe 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -54,7 +54,7 @@ config THUNDER_NIC_RGX config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" depends on 64BIT && PCI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK ---help--- This driver adds support for the Precision Time Protocol Clocks and Timestamping coprocessor (PTP) found on Cavium processors. diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index f5dd34db4b54..6516c45864b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2207,6 +2207,9 @@ static void ethofld_hard_xmit(struct net_device *dev, if (unlikely(skip_eotx_wr)) { start = (u64 *)wr; eosw_txq->state = next_state; + eosw_txq->cred -= wrlen16; + eosw_txq->ncompl++; + eosw_txq->last_compl = 0; goto write_wr_headers; } @@ -2365,6 +2368,34 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev) return cxgb4_eth_xmit(skb, dev); } +static void eosw_txq_flush_pending_skbs(struct sge_eosw_txq *eosw_txq) +{ + int pktcount = eosw_txq->pidx - eosw_txq->last_pidx; + int pidx = eosw_txq->pidx; + struct sk_buff *skb; + + if (!pktcount) + return; + + if (pktcount < 0) + pktcount += eosw_txq->ndesc; + + while (pktcount--) { + pidx--; + if (pidx < 0) + pidx += eosw_txq->ndesc; + + skb = eosw_txq->desc[pidx].skb; + if (skb) { + dev_consume_skb_any(skb); + eosw_txq->desc[pidx].skb = NULL; + eosw_txq->inuse--; + } + } + + eosw_txq->pidx = eosw_txq->last_pidx + 1; +} + /** * cxgb4_ethofld_send_flowc - Send ETHOFLD flowc request to bind eotid to tc. * @dev - netdevice @@ -2440,9 +2471,11 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc) FW_FLOWC_MNEM_EOSTATE_CLOSING : FW_FLOWC_MNEM_EOSTATE_ESTABLISHED); - eosw_txq->cred -= len16; - eosw_txq->ncompl++; - eosw_txq->last_compl = 0; + /* Free up any pending skbs to ensure there's room for + * termination FLOWC. + */ + if (tc == FW_SCHED_CLS_NONE) + eosw_txq_flush_pending_skbs(eosw_txq); ret = eosw_txq_enqueue(eosw_txq, skb); if (ret) { @@ -2695,6 +2728,7 @@ static void ofldtxq_stop(struct sge_uld_txq *q, struct fw_wr_hdr *wr) * is ever running at a time ... */ static void service_ofldq(struct sge_uld_txq *q) + __must_hold(&q->sendq.lock) { u64 *pos, *before, *end; int credits; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c index ebc635f8a4cc..15f37c5b8dc1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c @@ -74,8 +74,8 @@ err_pci_mem_reg: pci_disable_device(pdev); err_pci_enable: err_mdiobus_alloc: - iounmap(port_regs); err_hw_alloc: + iounmap(port_regs); err_ioremap: return err; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4bd33245bad6..3de549c6c693 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2189,7 +2189,8 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_hard_reset(adapter, rwi, reset_state); rtnl_unlock(); } - } else { + } else if (!(rwi->reset_reason == VNIC_RESET_FATAL && + adapter->from_passive_init)) { rc = do_reset(adapter, rwi, reset_state); } kfree(rwi); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 8972cdd559e8..7352244c5e68 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1428,6 +1428,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port, struct mvpp2_ethtool_fs *efs; int ret; + if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW) + return -EINVAL; + efs = port->rfs_rules[info->fs.location]; if (!efs) return -EINVAL; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 1fa60e985b43..2b5dad2ec650 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4329,6 +4329,8 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir, if (!mvpp22_rss_is_supported()) return -EOPNOTSUPP; + if (rss_context >= MVPP22_N_RSS_TABLES) + return -EINVAL; if (hfunc) *hfunc = ETH_RSS_HASH_CRC32; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5716c3d2bb86..c72c4e1ea383 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2550,6 +2550,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev) if (!err || err == -ENOSPC) { priv->def_counter[port] = idx; + err = 0; } else if (err == -ENOENT) { err = 0; continue; @@ -2600,7 +2601,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage) MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (!err) *idx = get_param_l(&out_param); - + if (WARN_ON(err == -ENOSPC)) + err = -EINVAL; return err; } return __mlx4_counter_alloc(dev, idx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 34cba97f7bf4..cede5bdfd598 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -888,7 +888,6 @@ static void cmd_work_handler(struct work_struct *work) } cmd->ent_arr[ent->idx] = ent; - set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -910,6 +909,7 @@ static void cmd_work_handler(struct work_struct *work) if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); /* Skip sending command to fw if internal error */ if (pci_channel_offline(dev->pdev) || @@ -922,6 +922,10 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + /* no doorbell, no need to keep the entry */ + free_ent(cmd, ent->idx); + if (ent->callback) + free_cmd(ent); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 55457f268495..f372e94948fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1773,19 +1773,14 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv) { - int err = mlx5e_init_rep_rx(priv); - - if (err) - return err; - mlx5e_create_q_counters(priv); - return 0; + return mlx5e_init_rep_rx(priv); } static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv) { - mlx5e_destroy_q_counters(priv); mlx5e_cleanup_rep_rx(priv); + mlx5e_destroy_q_counters(priv); } static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b2e38e0cde97..5d9def18ae3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1550,9 +1550,9 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw) MLX5_FLOW_NAMESPACE_KERNEL, 1, modact); if (IS_ERR(mod_hdr)) { + err = PTR_ERR(mod_hdr); esw_warn(dev, "Failed to create restore mod header, err: %d\n", err); - err = PTR_ERR(mod_hdr); goto err_mod_hdr; } @@ -2219,10 +2219,12 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev); memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb)); + mutex_init(&esw->fdb_table.offloads.vports.lock); + hash_init(esw->fdb_table.offloads.vports.table); err = esw_create_uplink_offloads_acl_tables(esw); if (err) - return err; + goto create_acl_err; err = esw_create_offloads_table(esw, total_vports); if (err) @@ -2240,9 +2242,6 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) if (err) goto create_fg_err; - mutex_init(&esw->fdb_table.offloads.vports.lock); - hash_init(esw->fdb_table.offloads.vports.table); - return 0; create_fg_err: @@ -2253,18 +2252,19 @@ create_restore_err: esw_destroy_offloads_table(esw); create_offloads_err: esw_destroy_uplink_offloads_acl_tables(esw); - +create_acl_err: + mutex_destroy(&esw->fdb_table.offloads.vports.lock); return err; } static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) { - mutex_destroy(&esw->fdb_table.offloads.vports.lock); esw_destroy_vport_rx_group(esw); esw_destroy_offloads_fdb_tables(esw); esw_destroy_restore_table(esw); esw_destroy_offloads_table(esw); esw_destroy_uplink_offloads_acl_tables(esw); + mutex_destroy(&esw->fdb_table.offloads.vports.lock); } static void @@ -2377,9 +2377,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) err_vports: esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); err_uplink: - esw_set_passing_vport_metadata(esw, false); -err_steering_init: esw_offloads_steering_cleanup(esw); +err_steering_init: + esw_set_passing_vport_metadata(esw, false); err_vport_metadata: mlx5_rdma_disable_roce(esw->dev); mutex_destroy(&esw->offloads.termtbl_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index c0ab9cf74929..18719acb7e54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -695,6 +695,12 @@ static void dr_cq_event(struct mlx5_core_cq *mcq, pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn); } +static void dr_cq_complete(struct mlx5_core_cq *mcq, + struct mlx5_eqe *eqe) +{ + pr_err("CQ completion CQ: #%u\n", mcq->cqn); +} + static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_uars_page *uar, size_t ncqe) @@ -756,6 +762,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); cq->mcq.event = dr_cq_event; + cq->mcq.comp = dr_cq_complete; err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); kvfree(in); @@ -767,7 +774,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cq->mcq.set_ci_db = cq->wq_ctrl.db.db; cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; *cq->mcq.set_ci_db = 0; - *cq->mcq.arm_db = 0; + + /* set no-zero value, in order to avoid the HW to run db-recovery on + * CQ that used in polling mode. + */ + *cq->mcq.arm_db = cpu_to_be32(2 << 28); + cq->mcq.vector = 0; cq->mcq.irqn = irqn; cq->mcq.uar = uar; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 430da69003d8..a6e30e020b5c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, unsigned int priority, struct mlxsw_afk_element_usage *elusage) { + struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2; struct mlxsw_sp_acl_tcam_vregion *vregion; - struct mlxsw_sp_acl_tcam_vchunk *vchunk; + struct list_head *pos; int err; if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO) @@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, } mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion); - list_add_tail(&vchunk->list, &vregion->vchunk_list); + + /* Position the vchunk inside the list according to priority */ + list_for_each(pos, &vregion->vchunk_list) { + vchunk2 = list_entry(pos, typeof(*vchunk2), list); + if (vchunk2->priority > priority) + break; + } + list_add_tail(&vchunk->list, pos); mutex_unlock(&vregion->lock); return vchunk; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 51117a5a6bbf..890b078851c9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -36,7 +36,8 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack); if (err) return err; - } else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED) { + } else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED && + act->hw_stats != FLOW_ACTION_HW_STATS_DONT_CARE) { NL_SET_ERR_MSG_MOD(extack, "Unsupported action HW stats type"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index e1651756bf9d..f70bb81e1ed6 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -564,7 +564,7 @@ static int moxart_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); unregister_netdev(ndev); - free_irq(ndev->irq, ndev); + devm_free_irq(&pdev->dev, ndev->irq, ndev); moxart_mac_free_memory(ndev); free_netdev(ndev); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index a8c48a4a708f..02350c3d9d01 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1031,10 +1031,8 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port, { int i, j; - /* Loop through all the mac tables entries. There are 1024 rows of 4 - * entries. - */ - for (i = 0; i < 1024; i++) { + /* Loop through all the mac tables entries. */ + for (i = 0; i < ocelot->num_mact_rows; i++) { for (j = 0; j < 4; j++) { struct ocelot_mact_entry entry; bool is_static; @@ -1453,8 +1451,15 @@ static void ocelot_port_attr_stp_state_set(struct ocelot *ocelot, int port, void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs) { - ocelot_write(ocelot, ANA_AUTOAGE_AGE_PERIOD(msecs / 2), - ANA_AUTOAGE); + unsigned int age_period = ANA_AUTOAGE_AGE_PERIOD(msecs / 2000); + + /* Setting AGE_PERIOD to zero effectively disables automatic aging, + * which is clearly not what our intention is. So avoid that. + */ + if (!age_period) + age_period = 1; + + ocelot_rmw(ocelot, age_period, ANA_AUTOAGE_AGE_PERIOD_M, ANA_AUTOAGE); } EXPORT_SYMBOL(ocelot_set_ageing_time); diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index b88b5899b227..7d4fd1b6adda 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -431,6 +431,7 @@ int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops) ocelot->stats_layout = ocelot_stats_layout; ocelot->num_stats = ARRAY_SIZE(ocelot_stats_layout); ocelot->shared_queue_sz = 224 * 1024; + ocelot->num_mact_rows = 1024; ocelot->ops = ops; ret = ocelot_regfields_init(ocelot, ocelot_regfields); diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c index bfa0c0d39600..8b018ed37b1b 100644 --- a/drivers/net/ethernet/natsemi/jazzsonic.c +++ b/drivers/net/ethernet/natsemi/jazzsonic.c @@ -208,11 +208,13 @@ static int jazz_sonic_probe(struct platform_device *pdev) err = register_netdev(dev); if (err) - goto out1; + goto undo_probe1; return 0; -out1: +undo_probe1: + dma_free_coherent(lp->device, SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode), + lp->descriptors, lp->descriptors_laddr); release_mem_region(dev->base_addr, SONIC_MEM_SIZE); out: free_netdev(dev); diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index 9183b3e85d21..354efffac0f9 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn, if (!nfp_nsp_has_hwinfo_lookup(nsp)) { nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n"); eth_hw_addr_random(nn->dp.netdev); + nfp_nsp_close(nsp); return; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 5f8fc58d42b3..11621ccc1faf 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -170,8 +170,7 @@ void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) debugfs_create_x64("base_pa", 0400, cq_dentry, &cq->base_pa); debugfs_create_u32("num_descs", 0400, cq_dentry, &cq->num_descs); debugfs_create_u32("desc_size", 0400, cq_dentry, &cq->desc_size); - debugfs_create_u8("done_color", 0400, cq_dentry, - (u8 *)&cq->done_color); + debugfs_create_bool("done_color", 0400, cq_dentry, &cq->done_color); debugfs_create_file("tail", 0400, cq_dentry, cq, &cq_tail_fops); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5acf4f46c268..d5293bfded29 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2101,6 +2101,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) ionic_txrx_free(lif); } ionic_lifs_deinit(ionic); + ionic_reset(ionic); ionic_qcqs_free(lif); dev_info(ionic->dev, "FW Down: LIFs stopped\n"); @@ -2116,6 +2117,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) dev_info(ionic->dev, "FW Up: restarting LIFs\n"); + ionic_init_devinfo(ionic); err = ionic_qcqs_alloc(lif); if (err) goto err_out; @@ -2549,8 +2551,6 @@ int ionic_lifs_register(struct ionic *ionic) dev_err(ionic->dev, "Cannot register net device, aborting\n"); return err; } - - ionic_link_status_check_request(ionic->master_lif); ionic->master_lif->registered = true; return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 494c859b4ade..67ba67ed0cb9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -624,7 +624,7 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg, total_offset += offset; } - total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000; + total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000ULL; total_ctr += total_offset; ctr_low = do_div(total_ctr, 1000000000); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 565da6498c84..a999d6b33a64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4060,7 +4060,7 @@ static int stmmac_set_features(struct net_device *netdev, /** * stmmac_interrupt - main ISR * @irq: interrupt number. - * @dev_id: to pass the net device pointer. + * @dev_id: to pass the net device pointer (must be valid). * Description: this is the main driver interrupt service routine. * It can call: * o DMA service routine (to manage incoming frame reception and transmission @@ -4084,11 +4084,6 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if (priv->irq_wake) pm_wakeup_event(priv->device, 0); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -4991,7 +4986,7 @@ int stmmac_dvr_probe(struct device *device, priv->plat->bsp_priv); if (ret < 0) - return ret; + goto error_serdes_powerup; } #ifdef CONFIG_DEBUG_FS @@ -5000,6 +4995,8 @@ int stmmac_dvr_probe(struct device *device, return ret; +error_serdes_powerup: + unregister_netdev(ndev); error_netdev_register: phylink_destroy(priv->phylink); error_phy_setup: diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 89cec778cf2d..8e348780efb6 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -90,9 +90,8 @@ config TI_CPTS config TI_CPTS_MOD tristate depends on TI_CPTS + depends on PTP_1588_CLOCK default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y || TI_CPSW_SWITCHDEV=y - select NET_PTP_CLASSIFY - imply PTP_1588_CLOCK default m config TI_K3_AM65_CPSW_NUSS diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2bf56733ba94..2517ffba8178 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1719,7 +1719,8 @@ static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common) ret = devm_request_irq(dev, tx_chn->irq, am65_cpsw_nuss_tx_irq, - 0, tx_chn->tx_chn_name, tx_chn); + IRQF_TRIGGER_HIGH, + tx_chn->tx_chn_name, tx_chn); if (ret) { dev_err(dev, "failure requesting tx%u irq %u, %d\n", tx_chn->id, tx_chn->irq, ret); @@ -1744,7 +1745,7 @@ static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common) ret = devm_request_irq(dev, common->rx_chns.irq, am65_cpsw_nuss_rx_irq, - 0, dev_name(dev), common); + IRQF_TRIGGER_HIGH, dev_name(dev), common); if (ret) { dev_err(dev, "failure requesting rx irq %u, %d\n", common->rx_chns.irq, ret); diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index b50c3ec3495b..6bcda20ed7e7 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -643,7 +643,7 @@ static int tc_mii_probe(struct net_device *dev) linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask); linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask); } - linkmode_and(phydev->supported, phydev->supported, mask); + linkmode_andnot(phydev->supported, phydev->supported, mask); linkmode_copy(phydev->advertising, phydev->supported); lp->link = 0; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 672cd2caf2fb..21640a035d7d 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1169,11 +1169,11 @@ out_unlock: static struct genl_family gtp_genl_family; static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, - u32 type, struct pdp_ctx *pctx) + int flags, u32 type, struct pdp_ctx *pctx) { void *genlh; - genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, 0, + genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, flags, type); if (genlh == NULL) goto nlmsg_failure; @@ -1227,8 +1227,8 @@ static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) goto err_unlock; } - err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, - info->snd_seq, info->nlhdr->nlmsg_type, pctx); + err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, info->snd_seq, + 0, info->nlhdr->nlmsg_type, pctx); if (err < 0) goto err_unlock_free; @@ -1271,6 +1271,7 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, gtp_genl_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb->nlh->nlmsg_type, pctx)) { cb->args[0] = i; cb->args[1] = j; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d8e86bdbfba1..ebcfbae05690 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -707,7 +707,8 @@ no_memory: goto drop; } -static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb, + struct net_device *ndev) { return netvsc_xmit(skb, ndev, false); } diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 845478a19a4f..b671bea0aa7c 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -1041,6 +1041,7 @@ static void gsi_isr_gp_int1(struct gsi *gsi) complete(&gsi->completion); } + /* Inter-EE interrupt handler */ static void gsi_isr_glob_ee(struct gsi *gsi) { @@ -1493,6 +1494,12 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id, struct completion *completion = &gsi->completion; u32 val; + /* First zero the result code field */ + val = ioread32(gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET); + val &= ~GENERIC_EE_RESULT_FMASK; + iowrite32(val, gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET); + + /* Now issue the command */ val = u32_encode_bits(opcode, GENERIC_OPCODE_FMASK); val |= u32_encode_bits(channel_id, GENERIC_CHID_FMASK); val |= u32_encode_bits(GSI_EE_MODEM, GENERIC_EE_FMASK); @@ -1798,9 +1805,9 @@ static int gsi_channel_init_one(struct gsi *gsi, /* Worst case we need an event for every outstanding TRE */ if (data->channel.tre_count > data->channel.event_count) { - dev_warn(gsi->dev, "channel %u limited to %u TREs\n", - data->channel_id, data->channel.tre_count); tre_count = data->channel.event_count; + dev_warn(gsi->dev, "channel %u limited to %u TREs\n", + data->channel_id, tre_count); } else { tre_count = data->channel.tre_count; } diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h index 7613b9cc7cf6..acc9e744c67d 100644 --- a/drivers/net/ipa/gsi_reg.h +++ b/drivers/net/ipa/gsi_reg.h @@ -410,6 +410,8 @@ #define INTER_EE_RESULT_FMASK GENMASK(2, 0) #define GENERIC_EE_RESULT_FMASK GENMASK(7, 5) #define GENERIC_EE_SUCCESS_FVAL 1 +#define GENERIC_EE_INCORRECT_DIRECTION_FVAL 3 +#define GENERIC_EE_INCORRECT_CHANNEL_FVAL 5 #define GENERIC_EE_NO_RESOURCES_FVAL 7 #define USB_MAX_PACKET_FMASK GENMASK(15, 15) /* 0: HS; 1: SS */ #define MHI_BASE_CHANNEL_FMASK GENMASK(31, 24) diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 6de03be28784..a21534f1462f 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1283,7 +1283,7 @@ static int ipa_endpoint_stop_rx_dma(struct ipa *ipa) */ int ipa_endpoint_stop(struct ipa_endpoint *endpoint) { - u32 retries = endpoint->toward_ipa ? 0 : IPA_ENDPOINT_STOP_RX_RETRIES; + u32 retries = IPA_ENDPOINT_STOP_RX_RETRIES; int ret; do { @@ -1291,12 +1291,9 @@ int ipa_endpoint_stop(struct ipa_endpoint *endpoint) struct gsi *gsi = &ipa->gsi; ret = gsi_channel_stop(gsi, endpoint->channel_id); - if (ret != -EAGAIN) + if (ret != -EAGAIN || endpoint->toward_ipa) break; - if (endpoint->toward_ipa) - continue; - /* For IPA v3.5.1, send a DMA read task and check again */ if (ipa->version == IPA_VERSION_3_5_1) { ret = ipa_endpoint_stop_rx_dma(ipa); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 758baf7cb8a1..d0d31cb99180 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1305,7 +1305,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) struct crypto_aead *tfm; int ret; - tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + /* Pick a sync gcm(aes) cipher to ensure order is preserved. */ + tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) return tfm; @@ -2640,11 +2641,12 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) if (ret) goto rollback; - rtnl_unlock(); /* Force features update, since they are different for SW MACSec and * HW offloading cases. */ netdev_update_features(dev); + + rtnl_unlock(); return 0; rollback: diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 415c27310982..ecbd5e0d685c 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1120,7 +1120,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus) goto out; } dp83640_clock_init(clock, bus); - list_add_tail(&phyter_clocks, &clock->list); + list_add_tail(&clock->list, &phyter_clocks); out: mutex_unlock(&phyter_clocks_lock); diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index fe9aa3ad52a7..1dd19d0cb269 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -137,19 +137,18 @@ static int dp83822_set_wol(struct phy_device *phydev, value &= ~DP83822_WOL_SECURE_ON; } - value |= (DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | - DP83822_WOL_CLR_INDICATION); - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); + /* Clear any pending WoL interrupt */ + phy_read(phydev, MII_DP83822_MISR2); + + value |= DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | + DP83822_WOL_CLR_INDICATION; + + return phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, value); } else { - value = phy_read_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_WOL_CFG); - value &= ~DP83822_WOL_EN; - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, DP83822_WOL_EN); } - - return 0; } static void dp83822_get_wol(struct phy_device *phydev, @@ -258,12 +257,11 @@ static int dp83822_config_intr(struct phy_device *phydev) static int dp83822_config_init(struct phy_device *phydev) { - int value; - - value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN; + int value = DP83822_WOL_EN | DP83822_WOL_MAGIC_EN | + DP83822_WOL_SECURE_ON; - return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, value); } static int dp83822_phy_reset(struct phy_device *phydev) diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index 06f08832ebcd..d73725312c7c 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -139,16 +139,19 @@ static int dp83811_set_wol(struct phy_device *phydev, value &= ~DP83811_WOL_SECURE_ON; } - value |= (DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL | - DP83811_WOL_CLR_INDICATION); - phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - value); + /* Clear any pending WoL interrupt */ + phy_read(phydev, MII_DP83811_INT_STAT1); + + value |= DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL | + DP83811_WOL_CLR_INDICATION; + + return phy_write_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG, value); } else { - phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - DP83811_WOL_EN); + return phy_clear_bits_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG, DP83811_WOL_EN); } - return 0; } static void dp83811_get_wol(struct phy_device *phydev, @@ -292,8 +295,8 @@ static int dp83811_config_init(struct phy_device *phydev) value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN; - return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + value); } static int dp83811_phy_reset(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index ff12492771ab..1f1a01c98e44 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -66,6 +66,9 @@ enum { MV_PCS_CSSR1_SPD2_2500 = 0x0004, MV_PCS_CSSR1_SPD2_10000 = 0x0000, + /* Temperature read register (88E2110 only) */ + MV_PCS_TEMP = 0x8042, + /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is * restarted, but status registers appear readable from either. @@ -77,6 +80,7 @@ enum { MV_V2_PORT_CTRL = 0xf001, MV_V2_PORT_CTRL_SWRST = BIT(15), MV_V2_PORT_CTRL_PWRDOWN = BIT(11), + /* Temperature control/read registers (88X3310 only) */ MV_V2_TEMP_CTRL = 0xf08a, MV_V2_TEMP_CTRL_MASK = 0xc000, MV_V2_TEMP_CTRL_SAMPLE = 0x0000, @@ -104,6 +108,24 @@ static umode_t mv3310_hwmon_is_visible(const void *data, return 0; } +static int mv3310_hwmon_read_temp_reg(struct phy_device *phydev) +{ + return phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP); +} + +static int mv2110_hwmon_read_temp_reg(struct phy_device *phydev) +{ + return phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_TEMP); +} + +static int mv10g_hwmon_read_temp_reg(struct phy_device *phydev) +{ + if (phydev->drv->phy_id == MARVELL_PHY_ID_88X3310) + return mv3310_hwmon_read_temp_reg(phydev); + else /* MARVELL_PHY_ID_88E2110 */ + return mv2110_hwmon_read_temp_reg(phydev); +} + static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *value) { @@ -116,7 +138,7 @@ static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type, } if (type == hwmon_temp && attr == hwmon_temp_input) { - temp = phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP); + temp = mv10g_hwmon_read_temp_reg(phydev); if (temp < 0) return temp; @@ -169,6 +191,9 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable) u16 val; int ret; + if (phydev->drv->phy_id != MARVELL_PHY_ID_88X3310) + return 0; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP, MV_V2_TEMP_UNKNOWN); if (ret < 0) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6c738a271257..4bb8552a00d3 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1359,6 +1359,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81cc, 8)}, /* Dell Wireless 5816e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 5c964fcb994e..71b8e80b58e1 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, if (multicore) { queue->worker = wg_packet_percpu_multicore_worker_alloc( function, queue); - if (!queue->worker) + if (!queue->worker) { + ptr_ring_cleanup(&queue->ring, NULL); return -ENOMEM; + } } else { INIT_WORK(&queue->work, function); } diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index da3b782ab7d3..3bb5b9ae7cd1 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -226,21 +226,20 @@ void wg_packet_handshake_receive_worker(struct work_struct *work) static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; - bool send = false; + bool send; if (peer->sent_lastminute_handshake) return; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); - if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && - keypair->i_am_the_initiator && - unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, - REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT))) - send = true; + send = keypair && READ_ONCE(keypair->sending.is_valid) && + keypair->i_am_the_initiator && + wg_birthdate_has_expired(keypair->sending.birthdate, + REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT); rcu_read_unlock_bh(); - if (send) { + if (unlikely(send)) { peer->sent_lastminute_handshake = true; wg_packet_send_queued_handshake_initiation(peer, false); } @@ -393,13 +392,11 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, len = ntohs(ip_hdr(skb)->tot_len); if (unlikely(len < sizeof(struct iphdr))) goto dishonest_packet_size; - if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) - IP_ECN_set_ce(ip_hdr(skb)); + INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos); } else if (skb->protocol == htons(ETH_P_IPV6)) { len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); - if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) - IP6_ECN_set_ce(skb, ipv6_hdr(skb)); + INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb))); } else { goto dishonest_packet_type; } @@ -518,6 +515,8 @@ void wg_packet_decrypt_worker(struct work_struct *work) &PACKET_CB(skb)->keypair->receiving)) ? PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; wg_queue_enqueue_per_peer_napi(skb, state); + if (need_resched()) + cond_resched(); } } diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c index bcd6462e4540..007cd4457c5f 100644 --- a/drivers/net/wireguard/selftest/ratelimiter.c +++ b/drivers/net/wireguard/selftest/ratelimiter.c @@ -120,9 +120,9 @@ bool __init wg_ratelimiter_selftest(void) enum { TRIALS_BEFORE_GIVING_UP = 5000 }; bool success = false; int test = 0, trials; - struct sk_buff *skb4, *skb6; + struct sk_buff *skb4, *skb6 = NULL; struct iphdr *hdr4; - struct ipv6hdr *hdr6; + struct ipv6hdr *hdr6 = NULL; if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN)) return true; diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 7348c10cbae3..6687db699803 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -124,20 +124,17 @@ void wg_packet_send_handshake_cookie(struct wg_device *wg, static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; - bool send = false; + bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); - if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && - (unlikely(atomic64_read(&keypair->sending.counter.counter) > - REKEY_AFTER_MESSAGES) || - (keypair->i_am_the_initiator && - unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, - REKEY_AFTER_TIME))))) - send = true; + send = keypair && READ_ONCE(keypair->sending.is_valid) && + (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES || + (keypair->i_am_the_initiator && + wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); - if (send) + if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } @@ -281,6 +278,8 @@ void wg_packet_tx_worker(struct work_struct *work) wg_noise_keypair_put(keypair, false); wg_peer_put(peer); + if (need_resched()) + cond_resched(); } } @@ -304,7 +303,8 @@ void wg_packet_encrypt_worker(struct work_struct *work) } wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, state); - + if (need_resched()) + cond_resched(); } } diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index b0d6541582d3..f9018027fc13 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; - } else if (unlikely(rt->dst.dev == skb->dev)) { - ip_rt_put(rt); - ret = -ELOOP; - net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", - wg->dev->name, &endpoint->addr); - goto err; } if (cache) dst_cache_set_ip4(cache, &rt->dst, fl.saddr); @@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, struct sk_buff *skb, net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; - } else if (unlikely(dst->dev == skb->dev)) { - dst_release(dst); - ret = -ELOOP; - net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", - wg->dev->name, &endpoint->addr); - goto err; } if (cache) dst_cache_set_ip6(cache, dst, &fl.saddr); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f2adea96b04c..f3c037f5a9ba 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1110,7 +1110,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, * Don't treat an error as fatal, as we potentially already * have a NGUID or EUI-64. */ - if (status > 0) + if (status > 0 && !(status & NVME_SC_DNR)) status = 0; goto free_data; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4e79e412b276..e13c370de830 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -973,9 +973,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) { - if (++nvmeq->cq_head == nvmeq->q_depth) { + u16 tmp = nvmeq->cq_head + 1; + + if (tmp == nvmeq->q_depth) { nvmeq->cq_head = 0; nvmeq->cq_phase ^= 1; + } else { + nvmeq->cq_head = tmp; } } diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index 3708d43b7508..393011a05b48 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -816,6 +816,13 @@ static const struct of_device_id qusb2_phy_of_match_table[] = { .compatible = "qcom,msm8998-qusb2-phy", .data = &msm8998_phy_cfg, }, { + /* + * Deprecated. Only here to support legacy device + * trees that didn't include "qcom,qusb2-v2-phy" + */ + .compatible = "qcom,sdm845-qusb2-phy", + .data = &qusb2_v2_phy_cfg, + }, { .compatible = "qcom,qusb2-v2-phy", .data = &qusb2_v2_phy_cfg, }, diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c index d998e65c89c8..a52a9bf13b75 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c @@ -160,18 +160,11 @@ static int qcom_snps_hsphy_power_on(struct phy *phy) ret = regulator_bulk_enable(VREG_NUM, priv->vregs); if (ret) return ret; - ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); - if (ret) - goto err_disable_regulator; + qcom_snps_hsphy_disable_hv_interrupts(priv); qcom_snps_hsphy_exit_retention(priv); return 0; - -err_disable_regulator: - regulator_bulk_disable(VREG_NUM, priv->vregs); - - return ret; } static int qcom_snps_hsphy_power_off(struct phy *phy) @@ -180,7 +173,6 @@ static int qcom_snps_hsphy_power_off(struct phy *phy) qcom_snps_hsphy_enter_retention(priv); qcom_snps_hsphy_enable_hv_interrupts(priv); - clk_bulk_disable_unprepare(priv->num_clks, priv->clks); regulator_bulk_disable(VREG_NUM, priv->vregs); return 0; @@ -266,21 +258,39 @@ static int qcom_snps_hsphy_init(struct phy *phy) struct hsphy_priv *priv = phy_get_drvdata(phy); int ret; - ret = qcom_snps_hsphy_reset(priv); + ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); if (ret) return ret; + ret = qcom_snps_hsphy_reset(priv); + if (ret) + goto disable_clocks; + qcom_snps_hsphy_init_sequence(priv); ret = qcom_snps_hsphy_por_reset(priv); if (ret) - return ret; + goto disable_clocks; + + return 0; + +disable_clocks: + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); + return ret; +} + +static int qcom_snps_hsphy_exit(struct phy *phy) +{ + struct hsphy_priv *priv = phy_get_drvdata(phy); + + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); return 0; } static const struct phy_ops qcom_snps_hsphy_ops = { .init = qcom_snps_hsphy_init, + .exit = qcom_snps_hsphy_exit, .power_on = qcom_snps_hsphy_power_on, .power_off = qcom_snps_hsphy_power_off, .set_mode = qcom_snps_hsphy_set_mode, diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c index b7f2c00db5e1..9c4af76a9956 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub.c +++ b/drivers/platform/chrome/cros_ec_sensorhub.c @@ -52,28 +52,15 @@ static int cros_ec_sensorhub_register(struct device *dev, int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 }; struct cros_ec_command *msg = sensorhub->msg; struct cros_ec_dev *ec = sensorhub->ec; - int ret, i, sensor_num; + int ret, i; char *name; - sensor_num = cros_ec_get_sensor_count(ec); - if (sensor_num < 0) { - dev_err(dev, - "Unable to retrieve sensor information (err:%d)\n", - sensor_num); - return sensor_num; - } - - sensorhub->sensor_num = sensor_num; - if (sensor_num == 0) { - dev_err(dev, "Zero sensors reported.\n"); - return -EINVAL; - } msg->version = 1; msg->insize = sizeof(struct ec_response_motion_sense); msg->outsize = sizeof(struct ec_params_motion_sense); - for (i = 0; i < sensor_num; i++) { + for (i = 0; i < sensorhub->sensor_num; i++) { sensorhub->params->cmd = MOTIONSENSE_CMD_INFO; sensorhub->params->info.sensor_num = i; @@ -140,8 +127,7 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) struct cros_ec_dev *ec = dev_get_drvdata(dev->parent); struct cros_ec_sensorhub *data; struct cros_ec_command *msg; - int ret; - int i; + int ret, i, sensor_num; msg = devm_kzalloc(dev, sizeof(struct cros_ec_command) + max((u16)sizeof(struct ec_params_motion_sense), @@ -166,10 +152,52 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) dev_set_drvdata(dev, data); /* Check whether this EC is a sensor hub. */ - if (cros_ec_check_features(data->ec, EC_FEATURE_MOTION_SENSE)) { + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE)) { + sensor_num = cros_ec_get_sensor_count(ec); + if (sensor_num < 0) { + dev_err(dev, + "Unable to retrieve sensor information (err:%d)\n", + sensor_num); + return sensor_num; + } + if (sensor_num == 0) { + dev_err(dev, "Zero sensors reported.\n"); + return -EINVAL; + } + data->sensor_num = sensor_num; + + /* + * Prepare the ring handler before enumering the + * sensors. + */ + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + ret = cros_ec_sensorhub_ring_allocate(data); + if (ret) + return ret; + } + + /* Enumerate the sensors.*/ ret = cros_ec_sensorhub_register(dev, data); if (ret) return ret; + + /* + * When the EC does not have a FIFO, the sensors will query + * their data themselves via sysfs or a software trigger. + */ + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + ret = cros_ec_sensorhub_ring_add(data); + if (ret) + return ret; + /* + * The msg and its data is not under the control of the + * ring handler. + */ + return devm_add_action_or_reset(dev, + cros_ec_sensorhub_ring_remove, + data); + } + } else { /* * If the device has sensors but does not claim to @@ -184,22 +212,6 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) } } - /* - * If the EC does not have a FIFO, the sensors will query their data - * themselves via sysfs or a software trigger. - */ - if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { - ret = cros_ec_sensorhub_ring_add(data); - if (ret) - return ret; - /* - * The msg and its data is not under the control of the ring - * handler. - */ - return devm_add_action_or_reset(dev, - cros_ec_sensorhub_ring_remove, - data); - } return 0; } diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index c48e5b38a441..24e48d96ed76 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -957,17 +957,15 @@ static int cros_ec_sensorhub_event(struct notifier_block *nb, } /** - * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC - * supports it. + * cros_ec_sensorhub_ring_allocate() - Prepare the FIFO functionality if the EC + * supports it. * * @sensorhub : Sensor Hub object. * * Return: 0 on success. */ -int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) +int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub) { - struct cros_ec_dev *ec = sensorhub->ec; - int ret; int fifo_info_length = sizeof(struct ec_response_motion_sense_fifo_info) + sizeof(u16) * sensorhub->sensor_num; @@ -978,6 +976,49 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) if (!sensorhub->fifo_info) return -ENOMEM; + /* + * Allocate the callback area based on the number of sensors. + * Add one for the sensor ring. + */ + sensorhub->push_data = devm_kcalloc(sensorhub->dev, + sensorhub->sensor_num, + sizeof(*sensorhub->push_data), + GFP_KERNEL); + if (!sensorhub->push_data) + return -ENOMEM; + + sensorhub->tight_timestamps = cros_ec_check_features( + sensorhub->ec, + EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS); + + if (sensorhub->tight_timestamps) { + sensorhub->batch_state = devm_kcalloc(sensorhub->dev, + sensorhub->sensor_num, + sizeof(*sensorhub->batch_state), + GFP_KERNEL); + if (!sensorhub->batch_state) + return -ENOMEM; + } + + return 0; +} + +/** + * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC + * supports it. + * + * @sensorhub : Sensor Hub object. + * + * Return: 0 on success. + */ +int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) +{ + struct cros_ec_dev *ec = sensorhub->ec; + int ret; + int fifo_info_length = + sizeof(struct ec_response_motion_sense_fifo_info) + + sizeof(u16) * sensorhub->sensor_num; + /* Retrieve FIFO information */ sensorhub->msg->version = 2; sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INFO; @@ -998,31 +1039,9 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) if (!sensorhub->ring) return -ENOMEM; - /* - * Allocate the callback area based on the number of sensors. - */ - sensorhub->push_data = devm_kcalloc( - sensorhub->dev, sensorhub->sensor_num, - sizeof(*sensorhub->push_data), - GFP_KERNEL); - if (!sensorhub->push_data) - return -ENOMEM; - sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS] = cros_ec_get_time_ns(); - sensorhub->tight_timestamps = cros_ec_check_features( - ec, EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS); - - if (sensorhub->tight_timestamps) { - sensorhub->batch_state = devm_kcalloc(sensorhub->dev, - sensorhub->sensor_num, - sizeof(*sensorhub->batch_state), - GFP_KERNEL); - if (!sensorhub->batch_state) - return -ENOMEM; - } - /* Register the notifier that will act as a top half interrupt. */ sensorhub->notifier.notifier_call = cros_ec_sensorhub_event; ret = blocking_notifier_chain_register(&ec->ec_dev->event_notifier, diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 6f12747a359a..c4404d9c1de4 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -515,9 +515,33 @@ static struct asus_wmi_driver asus_nb_wmi_driver = { .detect_quirks = asus_nb_wmi_quirks, }; +static const struct dmi_system_id asus_nb_wmi_blacklist[] __initconst = { + { + /* + * asus-nb-wm adds no functionality. The T100TA has a detachable + * USB kbd, so no hotkeys and it has no WMI rfkill; and loading + * asus-nb-wm causes the camera LED to turn and _stay_ on. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), + }, + }, + { + /* The Asus T200TA has the same issue as the T100TA */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T200TA"), + }, + }, + {} /* Terminating entry */ +}; static int __init asus_nb_wmi_init(void) { + if (dmi_check_system(asus_nb_wmi_blacklist)) + return -ENODEV; + return asus_wmi_register_driver(&asus_nb_wmi_driver); } diff --git a/drivers/platform/x86/intel-uncore-frequency.c b/drivers/platform/x86/intel-uncore-frequency.c index b96d172eb2c1..12d5ab7e1f5d 100644 --- a/drivers/platform/x86/intel-uncore-frequency.c +++ b/drivers/platform/x86/intel-uncore-frequency.c @@ -53,7 +53,7 @@ static int uncore_max_entries __read_mostly; /* Storage for uncore data for all instances */ static struct uncore_data *uncore_instances; /* Root of the all uncore sysfs kobjs */ -struct kobject *uncore_root_kobj; +static struct kobject *uncore_root_kobj; /* Stores the CPU mask of the target CPUs to use during uncore read/write */ static cpumask_t uncore_cpu_mask; /* CPU online callback register instance */ diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index d2a5d4c36715..7c8bdab078cf 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -255,7 +255,7 @@ static const struct pmc_bit_map *ext_cnp_pfear_map[] = { }; static const struct pmc_bit_map icl_pfear_map[] = { - /* Ice Lake generation onwards only */ + /* Ice Lake and Jasper Lake generation onwards only */ {"RES_65", BIT(0)}, {"RES_66", BIT(1)}, {"RES_67", BIT(2)}, @@ -274,7 +274,7 @@ static const struct pmc_bit_map *ext_icl_pfear_map[] = { }; static const struct pmc_bit_map tgl_pfear_map[] = { - /* Tiger Lake, Elkhart Lake and Jasper Lake generation onwards only */ + /* Tiger Lake and Elkhart Lake generation onwards only */ {"PSF9", BIT(0)}, {"RES_66", BIT(1)}, {"RES_67", BIT(2)}, @@ -692,7 +692,6 @@ static void pmc_core_lpm_display(struct pmc_dev *pmcdev, struct device *dev, kfree(lpm_regs); } -#if IS_ENABLED(CONFIG_DEBUG_FS) static bool slps0_dbg_latch; static inline u8 pmc_core_reg_read_byte(struct pmc_dev *pmcdev, int offset) @@ -1133,15 +1132,6 @@ static void pmc_core_dbgfs_register(struct pmc_dev *pmcdev) &pmc_core_substate_l_sts_regs_fops); } } -#else -static inline void pmc_core_dbgfs_register(struct pmc_dev *pmcdev) -{ -} - -static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev) -{ -} -#endif /* CONFIG_DEBUG_FS */ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &spt_reg_map), @@ -1156,7 +1146,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_reg_map), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_reg_map), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &tgl_reg_map), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &tgl_reg_map), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &icl_reg_map), {} }; @@ -1260,13 +1250,11 @@ static int pmc_core_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP - static bool warn_on_s0ix_failures; module_param(warn_on_s0ix_failures, bool, 0644); MODULE_PARM_DESC(warn_on_s0ix_failures, "Check and warn for S0ix failures"); -static int pmc_core_suspend(struct device *dev) +static __maybe_unused int pmc_core_suspend(struct device *dev) { struct pmc_dev *pmcdev = dev_get_drvdata(dev); @@ -1318,7 +1306,7 @@ static inline bool pmc_core_is_s0ix_failed(struct pmc_dev *pmcdev) return false; } -static int pmc_core_resume(struct device *dev) +static __maybe_unused int pmc_core_resume(struct device *dev) { struct pmc_dev *pmcdev = dev_get_drvdata(dev); const struct pmc_bit_map **maps = pmcdev->map->lpm_sts; @@ -1348,8 +1336,6 @@ static int pmc_core_resume(struct device *dev) return 0; } -#endif - static const struct dev_pm_ops pmc_core_pm_ops = { SET_LATE_SYSTEM_SLEEP_PM_OPS(pmc_core_suspend, pmc_core_resume) }; diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h index 0d50b2402abe..5eae55d80226 100644 --- a/drivers/platform/x86/intel_pmc_core.h +++ b/drivers/platform/x86/intel_pmc_core.h @@ -282,9 +282,7 @@ struct pmc_dev { u32 base_addr; void __iomem *regbase; const struct pmc_reg_map *map; -#if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbgfs_dir; -#endif /* CONFIG_DEBUG_FS */ int pmc_xram_read_bit; struct mutex lock; /* generic mutex lock for PMC Core */ diff --git a/drivers/platform/x86/surface3_power.c b/drivers/platform/x86/surface3_power.c index 946ac2dc08ae..cc4f9cba6856 100644 --- a/drivers/platform/x86/surface3_power.c +++ b/drivers/platform/x86/surface3_power.c @@ -522,8 +522,8 @@ static int mshw0011_probe(struct i2c_client *client) strlcpy(board_info.type, "MSHW0011-bat0", I2C_NAME_SIZE); bat0 = i2c_acpi_new_device(dev, 1, &board_info); - if (!bat0) - return -ENOMEM; + if (IS_ERR(bat0)) + return PTR_ERR(bat0); data->bat0 = bat0; i2c_set_clientdata(bat0, data); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 8eaadbaf8ffa..0f704484ae1d 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -9548,7 +9548,7 @@ static ssize_t tpacpi_battery_store(int what, if (!battery_info.batteries[battery].start_support) return -ENODEV; /* valid values are [0, 99] */ - if (value < 0 || value > 99) + if (value > 99) return -EINVAL; if (value > battery_info.batteries[battery].charge_stop) return -EINVAL; diff --git a/drivers/platform/x86/xiaomi-wmi.c b/drivers/platform/x86/xiaomi-wmi.c index 601cbb282f54..54a2546bb93b 100644 --- a/drivers/platform/x86/xiaomi-wmi.c +++ b/drivers/platform/x86/xiaomi-wmi.c @@ -23,7 +23,7 @@ struct xiaomi_wmi { unsigned int key_code; }; -int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) +static int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) { struct xiaomi_wmi *data; @@ -48,7 +48,7 @@ int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) return input_register_device(data->input_dev); } -void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy) +static void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy) { struct xiaomi_wmi *data; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index c340505150b6..7486f6e4e613 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5754,10 +5754,6 @@ static DECLARE_DELAYED_WORK(regulator_init_complete_work, static int __init regulator_init_complete(void) { - int delay = driver_deferred_probe_timeout; - - if (delay < 0) - delay = 0; /* * Since DT doesn't provide an idiomatic mechanism for * enabling full constraints and since it's much more natural @@ -5768,17 +5764,18 @@ static int __init regulator_init_complete(void) has_full_constraints = true; /* - * If driver_deferred_probe_timeout is set, we punt - * completion for that many seconds since systems like - * distros will load many drivers from userspace so consumers - * might not always be ready yet, this is particularly an - * issue with laptops where this might bounce the display off - * then on. Ideally we'd get a notification from userspace - * when this happens but we don't so just wait a bit and hope - * we waited long enough. It'd be better if we'd only do - * this on systems that need it. + * We punt completion for an arbitrary amount of time since + * systems like distros will load many drivers from userspace + * so consumers might not always be ready yet, this is + * particularly an issue with laptops where this might bounce + * the display off then on. Ideally we'd get a notification + * from userspace when this happens but we don't so just wait + * a bit and hope we waited long enough. It'd be better if + * we'd only do this on systems that need it, and a kernel + * command line option might be useful. */ - schedule_delayed_work(®ulator_init_complete_work, delay * HZ); + schedule_delayed_work(®ulator_init_complete_work, + msecs_to_jiffies(30000)); return 0; } diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index f7689461c242..569966bdc513 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -6717,17 +6717,17 @@ int qeth_stop(struct net_device *dev) unsigned int i; /* Quiesce the NAPI instances: */ - qeth_for_each_output_queue(card, queue, i) { + qeth_for_each_output_queue(card, queue, i) napi_disable(&queue->napi); - del_timer_sync(&queue->timer); - } /* Stop .ndo_start_xmit, might still access queue->napi. */ netif_tx_disable(dev); - /* Queues may get re-allocated, so remove the NAPIs here. */ - qeth_for_each_output_queue(card, queue, i) + qeth_for_each_output_queue(card, queue, i) { + del_timer_sync(&queue->timer); + /* Queues may get re-allocated, so remove the NAPIs. */ netif_napi_del(&queue->napi); + } } else { netif_tx_disable(dev); } diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 7da9e060b270..635f6f9cffc4 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -3640,6 +3640,11 @@ static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *tgt) struct ibmvfc_host *vhost = tgt->vhost; struct ibmvfc_event *evt; + if (!vhost->logged_in) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT); + return; + } + if (vhost->discovery_threads >= disc_threads) return; diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 7f66a7783209..59f0f1030c54 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -2320,16 +2320,12 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) static int ibmvscsi_remove(struct vio_dev *vdev) { struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev); - unsigned long flags; srp_remove_host(hostdata->host); scsi_remove_host(hostdata->host); purge_requests(hostdata, DID_ERROR); - - spin_lock_irqsave(hostdata->host->host_lock, flags); release_event_pool(&hostdata->pool, hostdata); - spin_unlock_irqrestore(hostdata->host->host_lock, flags); ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, max_events); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 97cabd7e0014..33255968f03a 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -3031,11 +3031,11 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags)) msleep(1000); - qla_nvme_delete(vha); qla24xx_disable_vp(vha); qla2x00_wait_for_sess_deletion(vha); + qla_nvme_delete(vha); vha->flags.delete_progress = 1; qlt_remove_target(ha, vha); diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 4ed90437e8c4..d6c991bd1bde 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3153,7 +3153,7 @@ qla24xx_abort_command(srb_t *sp) ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c, "Entered %s.\n", __func__); - if (vha->flags.qpairs_available && sp->qpair) + if (sp->qpair) req = sp->qpair->req; else return QLA_FUNCTION_FAILED; diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index 8e0575fcb4c8..67325fbaf760 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -925,6 +925,10 @@ do_map_region(const struct gasket_dev *gasket_dev, struct vm_area_struct *vma, gasket_get_bar_index(gasket_dev, (vma->vm_pgoff << PAGE_SHIFT) + driver_desc->legacy_mmap_address_offset); + + if (bar_index < 0) + return DO_MAP_REGION_INVALID; + phys_base = gasket_dev->bar_data[bar_index].phys_base + phys_offset; while (mapped_bytes < map_length) { /* diff --git a/drivers/staging/ks7010/TODO b/drivers/staging/ks7010/TODO index 87a6dac4890d..ab6f39175d99 100644 --- a/drivers/staging/ks7010/TODO +++ b/drivers/staging/ks7010/TODO @@ -30,5 +30,4 @@ Now the TODOs: Please send any patches to: Greg Kroah-Hartman <gregkh@linuxfoundation.org> -Wolfram Sang <wsa@the-dreams.de> Linux Driver Project Developer List <driverdev-devel@linuxdriverproject.org> diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 3d084cec136f..50c7534ba31e 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -182,6 +182,9 @@ static int usb4_switch_op(struct tb_switch *sw, u16 opcode, u8 *status) return ret; ret = tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_26, 1); + if (ret) + return ret; + if (val & ROUTER_CS_26_ONS) return -EOPNOTSUPP; diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index ed0aa5c0d9b7..5674da2b76f0 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -843,10 +843,8 @@ static int bcm_uart_probe(struct platform_device *pdev) if (IS_ERR(clk) && pdev->dev.of_node) clk = of_clk_get(pdev->dev.of_node, 0); - if (IS_ERR(clk)) { - clk_put(clk); + if (IS_ERR(clk)) return -ENODEV; - } port->iotype = UPIO_MEM; port->irq = res_irq->start; diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index ac137b6a1dc1..35e9e8faf8de 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1459,6 +1459,7 @@ static int cdns_uart_probe(struct platform_device *pdev) cdns_uart_uart_driver.nr = CDNS_UART_NR_PORTS; #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE cdns_uart_uart_driver.cons = &cdns_uart_console; + cdns_uart_console.index = id; #endif rc = uart_register_driver(&cdns_uart_uart_driver); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index e5ffed795e4c..48a8199f7845 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -365,9 +365,14 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows) return uniscr; } +static void vc_uniscr_free(struct uni_screen *uniscr) +{ + vfree(uniscr); +} + static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr) { - vfree(vc->vc_uni_screen); + vc_uniscr_free(vc->vc_uni_screen); vc->vc_uni_screen = new_uniscr; } @@ -1230,7 +1235,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, err = resize_screen(vc, new_cols, new_rows, user); if (err) { kfree(newscreen); - kfree(new_uniscr); + vc_uniscr_free(new_uniscr); return err; } diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index af648ba6544d..46105457e1ca 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -114,7 +114,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_ULPI_TX_PKT_EN_CLR_FIX, 0); - if (!IS_ERR(ci->platdata->vbus_extcon.edev)) { + if (!IS_ERR(ci->platdata->vbus_extcon.edev) || ci->role_switch) { hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_SESS_VLD_CTRL_EN, HS_PHY_SESS_VLD_CTRL_EN); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6833c918abce..b9db9812d6c5 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -217,6 +217,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) { struct usb_memory *usbm = NULL; struct usb_dev_state *ps = file->private_data; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); size_t size = vma->vm_end - vma->vm_start; void *mem; unsigned long flags; @@ -250,9 +251,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) usbm->vma_use_count = 1; INIT_LIST_HEAD(&usbm->memlist); - if (remap_pfn_range(vma, vma->vm_start, - virt_to_phys(usbm->mem) >> PAGE_SHIFT, - size, vma->vm_page_prot) < 0) { + if (dma_mmap_coherent(hcd->self.sysdev, vma, mem, dma_handle, size)) { dec_usb_memory_use_count(usbm, &usbm->vma_use_count); return -EAGAIN; } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index a48678a0c83a..6197938dcc2d 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1144,11 +1144,11 @@ void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr, if (usb_endpoint_out(epaddr)) { ep = dev->ep_out[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_out[epnum] = NULL; } else { ep = dev->ep_in[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_in[epnum] = NULL; } if (ep) { diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c index ffd984142171..d63072fee099 100644 --- a/drivers/usb/serial/garmin_gps.c +++ b/drivers/usb/serial/garmin_gps.c @@ -1138,8 +1138,8 @@ static void garmin_read_process(struct garmin_data *garmin_data_p, send it directly to the tty port */ if (garmin_data_p->flags & FLAGS_QUEUING) { pkt_add(garmin_data_p, data, data_length); - } else if (bulk_data || - getLayerId(data) == GARMIN_LAYERID_APPL) { + } else if (bulk_data || (data_length >= sizeof(u32) && + getLayerId(data) == GARMIN_LAYERID_APPL)) { spin_lock_irqsave(&garmin_data_p->lock, flags); garmin_data_p->flags |= APP_RESP_SEEN; diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 613f91add03d..ce0401d3137f 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -173,6 +173,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cc)}, /* Dell Wireless 5816e */ {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 1b23741036ee..37157ed9a881 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -28,6 +28,13 @@ * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org> */ +/* Reported-by: Julian Groß <julian.g@posteo.de> */ +UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, + "LaCie", + "2Big Quadra USB3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others? diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index f5c5e0aef66f..67c5139cfa0d 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -157,6 +157,10 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state) req.mode_data |= (state->mode - TYPEC_STATE_MODAL) << PMC_USB_ALTMODE_DP_MODE_SHIFT; + if (data->status & DP_STATUS_HPD_STATE) + req.mode_data |= PMC_USB_DP_HPD_LVL << + PMC_USB_ALTMODE_DP_MODE_SHIFT; + return pmc_usb_command(port, (void *)&req, sizeof(req)); } @@ -298,11 +302,11 @@ static int pmc_usb_register_port(struct pmc_usb *pmc, int index, struct typec_mux_desc mux_desc = { }; int ret; - ret = fwnode_property_read_u8(fwnode, "usb2-port", &port->usb2_port); + ret = fwnode_property_read_u8(fwnode, "usb2-port-number", &port->usb2_port); if (ret) return ret; - ret = fwnode_property_read_u8(fwnode, "usb3-port", &port->usb3_port); + ret = fwnode_property_read_u8(fwnode, "usb3-port-number", &port->usb3_port); if (ret) return ret; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index e36aaf9ba7bd..fb4e944c4d0d 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -181,14 +181,14 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); - added = true; - - /* Deliver to monitoring devices all correctly transmitted - * packets. + /* Deliver to monitoring devices all packets that we + * will transmit. */ virtio_transport_deliver_tap_pkt(pkt); + vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); + added = true; + pkt->off += payload_len; total_len += payload_len; @@ -196,6 +196,12 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, * to send it with the next available buffer. */ if (pkt->off < pkt->len) { + /* We are queueing the same virtio_vsock_pkt to handle + * the remaining bytes, and we want to deliver it + * to monitoring devices in the next iteration. + */ + pkt->tap_delivered = false; + spin_lock_bh(&vsock->send_pkt_list_lock); list_add(&pkt->list, &vsock->send_pkt_list); spin_unlock_bh(&vsock->send_pkt_list_lock); @@ -543,6 +549,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock) mutex_unlock(&vq->mutex); } + /* Some packets may have been queued before the device was started, + * let's kick the send worker to send them. + */ + vhost_work_queue(&vsock->dev, &vsock->send_pkt_work); + mutex_unlock(&vsock->dev.mutex); return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 185db76300b3..5f3aa4d607de 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2749,7 +2749,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, ret = try_get_cap_refs(inode, need, want, 0, flags, got); /* three special error codes */ - if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN) + if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE) ret = 0; return ret; } @@ -3746,6 +3746,7 @@ retry: WARN_ON(1); tsession = NULL; target = -1; + mutex_lock(&session->s_mutex); } goto retry; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 481ac97b4d25..dcaed75de9e6 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -271,7 +271,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) &congestion_kb_fops); snprintf(name, sizeof(name), "../../bdi/%s", - dev_name(fsc->sb->s_bdi->dev)); + bdi_dev_name(fsc->sb->s_bdi)); fsc->debugfs_bdi = debugfs_create_symlink("bdi", fsc->client->debugfs_dir, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 486f91f9685b..7c63abf5bea9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3251,8 +3251,7 @@ static void handle_session(struct ceph_mds_session *session, void *end = p + msg->front.iov_len; struct ceph_mds_session_head *h; u32 op; - u64 seq; - unsigned long features = 0; + u64 seq, features = 0; int wake = 0; bool blacklisted = false; @@ -3271,9 +3270,8 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_need(&p, end, len, bad); - memcpy(&features, p, min_t(size_t, len, sizeof(features))); - p += len; + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); } mutex_lock(&mdsc->mutex); diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index de56dee60540..19507e2fdb57 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, } if (IS_ERR(in)) { - pr_warn("Can't lookup inode %llx (err: %ld)\n", - realm->ino, PTR_ERR(in)); + dout("Can't lookup inode %llx (err: %ld)\n", + realm->ino, PTR_ERR(in)); qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ } else { qri->timeout = 0; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index cf7b7e1d5bd7..cb733652ecca 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1519,6 +1519,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) spin_lock(&configfs_dirent_lock); configfs_detach_rollback(dentry); spin_unlock(&configfs_dirent_lock); + config_item_put(parent_item); return -EINTR; } frag->frag_dead = true; diff --git a/fs/coredump.c b/fs/coredump.c index 408418e6aa13..478a0d810136 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -788,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (displaced) put_files_struct(displaced); if (!dump_interrupted()) { + /* + * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would + * have this set to NULL. + */ + if (!cprm.file) { + pr_info("Core dump to |%s disabled\n", cn.corename); + goto close_fail; + } file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); file_end_write(cprm.file); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8c596641a72b..12eebcdea9c8 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1171,6 +1171,10 @@ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; + /* Fast preliminary check */ + if (epi->next != EP_UNACTIVE_PTR) + return false; + /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; @@ -1237,16 +1241,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (epi->next == EP_UNACTIVE_PTR && - chain_epi_lockless(epi)) + if (chain_epi_lockless(epi)) + ep_pm_stay_awake_rcu(epi); + } else if (!ep_is_linked(epi)) { + /* In the usual case, add event to ready list. */ + if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); - goto out_unlock; - } - - /* If this file is already in the ready list we exit soon */ - if (!ep_is_linked(epi) && - list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) { - ep_pm_stay_awake_rcu(epi); } /* @@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; u64 slack = 0; - bool waiter = false; wait_queue_entry_t wait; ktime_t expires, *to = NULL; @@ -1867,55 +1866,75 @@ fetch_events: */ ep_reset_busy_poll_napi_id(ep); - /* - * We don't have any available event to return to the caller. We need - * to sleep here, and we will be woken by ep_poll_callback() when events - * become available. - */ - if (!waiter) { - waiter = true; - init_waitqueue_entry(&wait, current); + do { + /* + * Internally init_wait() uses autoremove_wake_function(), + * thus wait entry is removed from the wait queue on each + * wakeup. Why it is important? In case of several waiters + * each new wakeup will hit the next waiter, giving it the + * chance to harvest new event. Otherwise wakeup can be + * lost. This is also good performance-wise, because on + * normal wakeup path no need to call __remove_wait_queue() + * explicitly, thus ep->lock is not taken, which halts the + * event delivery. + */ + init_wait(&wait); write_lock_irq(&ep->lock); - __add_wait_queue_exclusive(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - - for (;;) { /* - * We don't want to sleep if the ep_poll_callback() sends us - * a wakeup in between. That's why we set the task state - * to TASK_INTERRUPTIBLE before doing the checks. + * Barrierless variant, waitqueue_active() is called under + * the same lock on wakeup ep_poll_callback() side, so it + * is safe to avoid an explicit barrier. */ - set_current_state(TASK_INTERRUPTIBLE); + __set_current_state(TASK_INTERRUPTIBLE); + /* - * Always short-circuit for fatal signals to allow - * threads to make a timely exit without the chance of - * finding more events available and fetching - * repeatedly. + * Do the final check under the lock. ep_scan_ready_list() + * plays with two lists (->rdllist and ->ovflist) and there + * is always a race when both lists are empty for short + * period of time although events are pending, so lock is + * important. */ - if (fatal_signal_pending(current)) { - res = -EINTR; - break; + eavail = ep_events_available(ep); + if (!eavail) { + if (signal_pending(current)) + res = -EINTR; + else + __add_wait_queue_exclusive(&ep->wq, &wait); } + write_unlock_irq(&ep->lock); - eavail = ep_events_available(ep); - if (eavail) + if (eavail || res) break; - if (signal_pending(current)) { - res = -EINTR; - break; - } if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) { timed_out = 1; break; } - } + + /* We were woken up, thus go and try to harvest some events */ + eavail = 1; + + } while (0); __set_current_state(TASK_RUNNING); + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + send_events: + if (fatal_signal_pending(current)) { + /* + * Always short-circuit for fatal signals to allow + * threads to make a timely exit without the chance of + * finding more events available and fetching + * repeatedly. + */ + res = -EINTR; + } /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of @@ -1925,12 +1944,6 @@ send_events: !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; - if (waiter) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - return res; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 936a8ec6b48e..6306eaae378b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -528,10 +528,12 @@ lower_metapath: /* Advance in metadata tree. */ (mp->mp_list[hgt])++; - if (mp->mp_list[hgt] >= sdp->sd_inptrs) { - if (!hgt) + if (hgt) { + if (mp->mp_list[hgt] >= sdp->sd_inptrs) + goto lower_metapath; + } else { + if (mp->mp_list[hgt] >= sdp->sd_diptrs) break; - goto lower_metapath; } fill_up_metapath: @@ -876,10 +878,9 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, ret = -ENOENT; goto unlock; } else { - /* report a hole */ iomap->offset = pos; iomap->length = length; - goto do_alloc; + goto hole_found; } } iomap->length = size; @@ -933,8 +934,6 @@ unlock: return ret; do_alloc: - iomap->addr = IOMAP_NULL_ADDR; - iomap->type = IOMAP_HOLE; if (flags & IOMAP_REPORT) { if (pos >= size) ret = -ENOENT; @@ -956,6 +955,9 @@ do_alloc: if (pos < size && height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); } +hole_found: + iomap->addr = IOMAP_NULL_ADDR; + iomap->type = IOMAP_HOLE; goto out; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 29f9b6684b74..bf70e3b14938 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -613,7 +613,7 @@ __acquires(&gl->gl_lockref.lock) fs_err(sdp, "Error %d syncing glock \n", ret); gfs2_dump_glock(NULL, gl, true); } - return; + goto skip_inval; } } if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) { @@ -633,6 +633,7 @@ __acquires(&gl->gl_lockref.lock) clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); } +skip_inval: gfs2_glock_hold(gl); /* * Check for an error encountered since we called go_sync and go_inval. @@ -722,9 +723,6 @@ __acquires(&gl->gl_lockref.lock) goto out_unlock; if (nonblock) goto out_sched; - smp_mb(); - if (atomic_read(&gl->gl_revokes) != 0) - goto out_sched; set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE); gl->gl_target = gl->gl_demote_state; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 70b2d3a1e866..5acd3ce30759 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -622,7 +622,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = finish_no_open(file, NULL); } gfs2_glock_dq_uninit(ghs); - return error; + goto fail; } else if (error != -ENOENT) { goto fail_gunlock; } @@ -764,9 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = finish_open(file, dentry, gfs2_open_common); } gfs2_glock_dq_uninit(ghs); + gfs2_qa_put(ip); gfs2_glock_dq_uninit(ghs + 1); clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); gfs2_glock_put(io_gl); + gfs2_qa_put(dip); return error; fail_gunlock3: @@ -776,7 +778,6 @@ fail_gunlock2: clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); gfs2_glock_put(io_gl); fail_free_inode: - gfs2_qa_put(ip); if (ip->i_gl) { glock_clear_object(ip->i_gl, ip); gfs2_glock_put(ip->i_gl); @@ -1005,7 +1006,7 @@ out_gunlock: out_child: gfs2_glock_dq(ghs); out_parent: - gfs2_qa_put(ip); + gfs2_qa_put(dip); gfs2_holder_uninit(ghs); gfs2_holder_uninit(ghs + 1); return error; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 3a75843ae580..0644e58c6191 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -669,13 +669,13 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct buffer_head *bh = bd->bd_bh; struct gfs2_glock *gl = bd->bd_gl; + sdp->sd_log_num_revoke++; + if (atomic_inc_return(&gl->gl_revokes) == 1) + gfs2_glock_hold(gl); bh->b_private = NULL; bd->bd_blkno = bh->b_blocknr; gfs2_remove_from_ail(bd); /* drops ref on bh */ bd->bd_bh = NULL; - sdp->sd_log_num_revoke++; - if (atomic_inc_return(&gl->gl_revokes) == 1) - gfs2_glock_hold(gl); set_bit(GLF_LFLUSH, &gl->gl_flags); list_add(&bd->bd_list, &sdp->sd_log_revokes); } @@ -1131,6 +1131,10 @@ int gfs2_logd(void *data) while (!kthread_should_stop()) { + if (gfs2_withdrawn(sdp)) { + msleep_interruptible(HZ); + continue; + } /* Check for errors writing to the journal */ if (sdp->sd_log_error) { gfs2_lm(sdp, @@ -1139,6 +1143,7 @@ int gfs2_logd(void *data) "prevent further damage.\n", sdp->sd_fsname, sdp->sd_log_error); gfs2_withdraw(sdp); + continue; } did_flush = false; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 5ea96757afc4..48b54ec1c793 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -263,7 +263,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno, struct super_block *sb = sdp->sd_vfs; struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); - bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9); + bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift; bio_set_dev(bio, sb->s_bdev); bio->bi_end_io = end_io; bio->bi_private = sdp; @@ -509,7 +509,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, unsigned int bsize = sdp->sd_sb.sb_bsize, off; unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; unsigned int shift = PAGE_SHIFT - bsize_shift; - unsigned int readahead_blocks = BIO_MAX_PAGES << shift; + unsigned int max_bio_size = 2 * 1024 * 1024; struct gfs2_journal_extent *je; int sz, ret = 0; struct bio *bio = NULL; @@ -537,12 +537,17 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, off = 0; } - if (!bio || (bio_chained && !off)) { + if (!bio || (bio_chained && !off) || + bio->bi_iter.bi_size >= max_bio_size) { /* start new bio */ } else { - sz = bio_add_page(bio, page, bsize, off); - if (sz == bsize) - goto block_added; + sector_t sector = dblock << sdp->sd_fsb2bb_shift; + + if (bio_end_sector(bio) == sector) { + sz = bio_add_page(bio, page, bsize, off); + if (sz == bsize) + goto block_added; + } if (off) { unsigned int blocks = (PAGE_SIZE - off) >> bsize_shift; @@ -568,7 +573,7 @@ block_added: off += bsize; if (off == PAGE_SIZE) page = NULL; - if (blocks_submitted < blocks_read + readahead_blocks) { + if (blocks_submitted < 2 * max_bio_size >> bsize_shift) { /* Keep at least one bio in flight */ continue; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 4b72abcf83b2..9856cc2e0795 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -252,7 +252,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, int num = 0; if (unlikely(gfs2_withdrawn(sdp)) && - (!sdp->sd_jdesc || (blkno != sdp->sd_jdesc->jd_no_addr))) { + (!sdp->sd_jdesc || gl != sdp->sd_jinode_gl)) { *bhp = NULL; return -EIO; } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index cc0c4b5800be..8259fef3f986 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1051,8 +1051,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) u32 x; int error = 0; - if (capable(CAP_SYS_RESOURCE) || - sdp->sd_args.ar_quota != GFS2_QUOTA_ON) + if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; error = gfs2_quota_hold(ip, uid, gid); @@ -1125,7 +1124,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) int found; if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags)) - goto out; + return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { struct gfs2_quota_data *qd; @@ -1162,7 +1161,6 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) qd_unlock(qda[x]); } -out: gfs2_quota_unhold(ip); } @@ -1210,9 +1208,6 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, if (!test_bit(GIF_QD_LOCKED, &ip->i_flags)) return 0; - if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) - return 0; - for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; @@ -1270,7 +1265,9 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, if (ip->i_diskflags & GFS2_DIF_SYSTEM) return; - BUG_ON(ip->i_qadata->qa_ref <= 0); + if (gfs2_assert_withdraw(sdp, ip->i_qadata && + ip->i_qadata->qa_ref > 0)) + return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 7f9ca8ef40fc..21ada332d555 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -44,7 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, int ret; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ - if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + if (capable(CAP_SYS_RESOURCE) || + sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (ret) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 37fc41632aa2..956fced0a8ec 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1404,7 +1404,6 @@ out: if (ip->i_qadata) gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0); gfs2_rs_delete(ip, NULL); - gfs2_qa_put(ip); gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 9b64d40ab379..aa087a5675af 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -119,6 +119,12 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) if (!sb_rdonly(sdp->sd_vfs)) ret = gfs2_make_fs_ro(sdp); + if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */ + if (!ret) + ret = -EIO; + clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags); + goto skip_recovery; + } /* * Drop the glock for our journal so another node can recover it. */ @@ -159,10 +165,6 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) wait_on_bit(&gl->gl_flags, GLF_FREEING, TASK_UNINTERRUPTIBLE); } - if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */ - clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags); - goto skip_recovery; - } /* * Dequeue the "live" glock, but keep a reference so it's never freed. */ diff --git a/fs/io_uring.c b/fs/io_uring.c index 0b91b0631173..979d9f977409 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -680,8 +680,6 @@ struct io_op_def { unsigned needs_mm : 1; /* needs req->file assigned */ unsigned needs_file : 1; - /* needs req->file assigned IFF fd is >= 0 */ - unsigned fd_non_neg : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -784,8 +782,6 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1, }, [IORING_OP_OPENAT] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -799,8 +795,6 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_STATX] = { .needs_mm = 1, - .needs_file = 1, - .fd_non_neg = 1, .needs_fs = 1, .file_table = 1, }, @@ -837,8 +831,6 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, }, [IORING_OP_OPENAT2] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -5368,15 +5360,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr) io_steal_work(req, workptr); } -static int io_req_needs_file(struct io_kiocb *req, int fd) -{ - if (!io_op_defs[req->opcode].needs_file) - return 0; - if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg) - return 0; - return 1; -} - static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { @@ -5414,14 +5397,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, } static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, - int fd, unsigned int flags) + int fd) { bool fixed; - if (!io_req_needs_file(req, fd)) - return 0; - - fixed = (flags & IOSQE_FIXED_FILE); + fixed = (req->flags & REQ_F_FIXED_FILE) != 0; if (unlikely(!fixed && req->needs_fixed_file)) return -EBADF; @@ -5798,7 +5778,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, struct io_submit_state *state, bool async) { unsigned int sqe_flags; - int id, fd; + int id; /* * All io need record the previous position, if LINK vs DARIN, @@ -5850,8 +5830,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, IOSQE_ASYNC | IOSQE_FIXED_FILE | IOSQE_BUFFER_SELECT | IOSQE_IO_LINK); - fd = READ_ONCE(sqe->fd); - return io_req_set_file(state, req, fd, sqe_flags); + if (!io_op_defs[req->opcode].needs_file) + return 0; + + return io_req_set_file(state, req, READ_ONCE(sqe->fd)); } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, @@ -7360,11 +7342,9 @@ static int io_uring_release(struct inode *inode, struct file *file) static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { - struct io_kiocb *req; - DEFINE_WAIT(wait); - while (!list_empty_careful(&ctx->inflight_list)) { - struct io_kiocb *cancel_req = NULL; + struct io_kiocb *cancel_req = NULL, *req; + DEFINE_WAIT(wait); spin_lock_irq(&ctx->inflight_lock); list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { @@ -7404,6 +7384,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, */ if (refcount_sub_and_test(2, &cancel_req->refs)) { io_put_req(cancel_req); + finish_wait(&ctx->inflight_wait, &wait); continue; } } @@ -7411,8 +7392,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_wq_cancel_work(ctx->io_wq, &cancel_req->work); io_put_req(cancel_req); schedule(); + finish_wait(&ctx->inflight_wait, &wait); } - finish_wait(&ctx->inflight_wait, &wait); } static int io_uring_flush(struct file *file, void *data) @@ -7761,7 +7742,8 @@ err: return ret; } -static int io_uring_create(unsigned entries, struct io_uring_params *p) +static int io_uring_create(unsigned entries, struct io_uring_params *p, + struct io_uring_params __user *params) { struct user_struct *user = NULL; struct io_ring_ctx *ctx; @@ -7853,6 +7835,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | + IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | + IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; + + if (copy_to_user(params, p, sizeof(*p))) { + ret = -EFAULT; + goto err; + } /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup @@ -7861,9 +7851,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret < 0) goto err; - p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | - IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | - IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: @@ -7879,7 +7866,6 @@ err: static long io_uring_setup(u32 entries, struct io_uring_params __user *params) { struct io_uring_params p; - long ret; int i; if (copy_from_user(&p, params, sizeof(p))) @@ -7894,14 +7880,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ)) return -EINVAL; - ret = io_uring_create(entries, &p); - if (ret < 0) - return ret; - - if (copy_to_user(params, &p, sizeof(p))) - return -EFAULT; - - return ret; + return io_uring_create(entries, &p, params); } SYSCALL_DEFINE2(io_uring_setup, u32, entries, diff --git a/fs/splice.c b/fs/splice.c index 4735defc46ee..fd0a1e7e5959 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in, loff_t offset; long ret; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + ipipe = get_pipe_info(in); opipe = get_pipe_info(out); @@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in, if (off_in || off_out) return -ESPIPE; - if (!(in->f_mode & FMODE_READ)) - return -EBADF; - - if (!(out->f_mode & FMODE_WRITE)) - return -EBADF; - /* Splicing to self would be fun, but... */ if (ipipe == opipe) return -EINVAL; @@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in, offset = out->f_pos; } - if (unlikely(!(out->f_mode & FMODE_WRITE))) - return -EBADF; - if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; @@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, error = -EBADF; in = fdget(fd_in); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - out = fdget(fd_out); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_splice(in.file, off_in, - out.file, off_out, - len, flags); - fdput(out); - } + out = fdget(fd_out); + if (out.file) { + error = do_splice(in.file, off_in, out.file, off_out, + len, flags); + fdput(out); } fdput(in); } @@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len, struct pipe_inode_info *opipe = get_pipe_info(out); int ret = -EINVAL; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + /* * Duplicate the contents of ipipe to opipe without actually * copying the data. @@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len, SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { - struct fd in; + struct fd in, out; int error; if (unlikely(flags & ~SPLICE_F_ALL)) @@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) error = -EBADF; in = fdget(fdin); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - struct fd out = fdget(fdout); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_tee(in.file, out.file, - len, flags); - fdput(out); - } + out = fdget(fdout); + if (out.file) { + error = do_tee(in.file, out.file, len, flags); + fdput(out); } fdput(in); } diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 675e26989376..8fe03b4a0d2b 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -164,7 +164,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) goto fail_free; } - err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id); + err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id); if (err) goto fail_free; diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index 99134d4f35eb..320f8112a0f8 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -48,7 +48,7 @@ struct videomode; * @MODE_HSYNC: hsync out of range * @MODE_VSYNC: vsync out of range * @MODE_H_ILLEGAL: mode has illegal horizontal timings - * @MODE_V_ILLEGAL: mode has illegal horizontal timings + * @MODE_V_ILLEGAL: mode has illegal vertical timings * @MODE_BAD_WIDTH: requires an unsupported linepitch * @MODE_NOMODE: no mode with a matching name * @MODE_NO_INTERLACE: interlaced mode not supported diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 26f0ecf401ea..0bbfd647f5c6 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -65,6 +65,7 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; + struct device_dma_parameters dma_parms; unsigned int periphid; unsigned int cid; struct amba_cs_uci_id uci; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ee577a83cfe6..7367150f962a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -219,6 +219,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f88197c1ffc2..c9ad5c3b7b4b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -505,13 +505,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << WB_async_congested)); } -extern const char *bdi_unknown_name; - -static inline const char *bdi_dev_name(struct backing_dev_info *bdi) -{ - if (!bdi || !bdi->dev) - return bdi_unknown_name; - return dev_name(bdi->dev); -} +const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..45cc10cdf6dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -983,7 +983,7 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[0]; + unsigned char f_handle[]; }; static inline struct file *get_file(struct file *f) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index db95244a62d4..ab4bd15cbcdb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -210,6 +210,29 @@ struct ftrace_ops { #endif }; +extern struct ftrace_ops __rcu *ftrace_ops_list; +extern struct ftrace_ops ftrace_list_end; + +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw_check() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw_check() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw_check(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + /* * Type of the current tracing. */ diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 62d216ff1097..c230b4e70d75 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -17,9 +17,12 @@ enum host1x_class { HOST1X_CLASS_GR3D = 0x60, }; +struct host1x; struct host1x_client; struct iommu_group; +u64 host1x_get_dma_mask(struct host1x *host1x); + /** * struct host1x_client_ops - host1x client operations * @init: host1x client initialization code diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..1bdd027766d4 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -55,7 +55,7 @@ LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) -LSM_HOOK(int, 0, fs_context_parse_param, struct fs_context *fc, +LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d275c72c4f8e..977edd3b7bd8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -783,6 +783,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && diff --git a/include/linux/mhi.h b/include/linux/mhi.h index ad1996001965..3d7c3c26eeb9 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -53,9 +53,9 @@ enum mhi_callback { * @MHI_CHAIN: Linked transfer */ enum mhi_flags { - MHI_EOB, - MHI_EOT, - MHI_CHAIN, + MHI_EOB = BIT(0), + MHI_EOT = BIT(1), + MHI_CHAIN = BIT(2), }; /** @@ -335,14 +335,15 @@ struct mhi_controller_config { * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) - * @link_status: CB function to query link status of the device (required) * @wake_get: CB function to assert device wake (optional) * @wake_put: CB function to de-assert device wake (optional) * @wake_toggle: CB function to assert and de-assert device wake (optional) * @runtime_get: CB function to controller runtime resume (required) - * @runtimet_put: CB function to decrement pm usage (required) + * @runtime_put: CB function to decrement pm usage (required) * @map_single: CB function to create TRE buffer * @unmap_single: CB function to destroy TRE buffer + * @read_reg: Read a MHI register via the physical link (required) + * @write_reg: Write a MHI register via the physical link (required) * @buffer_len: Bounce buffer length * @bounce_buf: Use of bounce buffer * @fbc_download: MHI host needs to do complete image transfer (optional) @@ -417,7 +418,6 @@ struct mhi_controller { void (*status_cb)(struct mhi_controller *mhi_cntrl, enum mhi_callback cb); - int (*link_status)(struct mhi_controller *mhi_cntrl); void (*wake_get)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_put)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_toggle)(struct mhi_controller *mhi_cntrl); @@ -427,6 +427,10 @@ struct mhi_controller { struct mhi_buf_info *buf); void (*unmap_single)(struct mhi_controller *mhi_cntrl, struct mhi_buf_info *buf); + int (*read_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 *out); + void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 val); size_t buffer_len; bool bounce_buf; diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h index c588be843f61..0ecce6aa69d5 100644 --- a/include/linux/platform_data/cros_ec_sensorhub.h +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -185,6 +185,7 @@ int cros_ec_sensorhub_register_push_data(struct cros_ec_sensorhub *sensorhub, void cros_ec_sensorhub_unregister_push_data(struct cros_ec_sensorhub *sensorhub, u8 sensor_num); +int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub); int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub); void cros_ec_sensorhub_ring_remove(void *arg); int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index bdc35753ef7c..77a2aada106d 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -25,6 +25,7 @@ struct platform_device { bool id_auto; struct device dev; u64 platform_dma_mask; + struct device_dma_parameters dma_parms; u32 num_resources; struct resource *resource; diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 48c1b1674cbf..bc07e51f20d1 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -21,6 +21,7 @@ struct gss_ctx { struct gss_api_mech *mech_type; void *internal_ctx_id; + unsigned int slack, align; }; #define GSS_C_NO_BUFFER ((struct xdr_netobj) 0) @@ -66,6 +67,7 @@ u32 gss_wrap( u32 gss_unwrap( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *inbuf); u32 gss_delete_sec_context( struct gss_ctx **ctx_id); @@ -126,6 +128,7 @@ struct gss_api_ops { u32 (*gss_unwrap)( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf); void (*gss_delete_sec_context)( void *internal_ctx_id); diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index c1d77dd8ed41..e8f8ffe7448b 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -83,7 +83,7 @@ struct gss_krb5_enctype { u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages); /* v2 encryption function */ - u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, + u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *headskip, u32 *tailskip); /* v2 decryption function */ }; @@ -255,7 +255,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset, struct xdr_buf *outbuf, struct page **pages); u32 -gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, +gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len, struct xdr_buf *buf); @@ -312,7 +312,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct page **pages); u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *plainoffset, u32 *plainlen); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 01bb41908c93..22c207b2425f 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -184,6 +184,7 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); +extern void xdr_buf_trim(struct xdr_buf *, unsigned int); extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 421c99c12291..4f8159e90ce1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -78,47 +78,6 @@ struct tcp_sack_block { #define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */ #define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/ -#if IS_ENABLED(CONFIG_MPTCP) -struct mptcp_options_received { - u64 sndr_key; - u64 rcvr_key; - u64 data_ack; - u64 data_seq; - u32 subflow_seq; - u16 data_len; - u16 mp_capable : 1, - mp_join : 1, - dss : 1, - add_addr : 1, - rm_addr : 1, - family : 4, - echo : 1, - backup : 1; - u32 token; - u32 nonce; - u64 thmac; - u8 hmac[20]; - u8 join_id; - u8 use_map:1, - dsn64:1, - data_fin:1, - use_ack:1, - ack64:1, - mpc_map:1, - __unused:2; - u8 addr_id; - u8 rm_id; - union { - struct in_addr addr; -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - struct in6_addr addr6; -#endif - }; - u64 ahmac; - u16 port; -}; -#endif - struct tcp_options_received { /* PAWS/RTTM data */ int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ @@ -136,9 +95,6 @@ struct tcp_options_received { u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ -#if IS_ENABLED(CONFIG_MPTCP) - struct mptcp_options_received mptcp; -#endif }; static inline void tcp_clear_options(struct tcp_options_received *rx_opt) @@ -148,13 +104,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) #if IS_ENABLED(CONFIG_SMC) rx_opt->smc_ok = 0; #endif -#if IS_ENABLED(CONFIG_MPTCP) - rx_opt->mptcp.mp_capable = 0; - rx_opt->mptcp.mp_join = 0; - rx_opt->mptcp.add_addr = 0; - rx_opt->mptcp.rm_addr = 0; - rx_opt->mptcp.dss = 0; -#endif } /* This is the max number of SACKS that we'll generate and process. It's safe diff --git a/include/linux/tty.h b/include/linux/tty.h index bd5fe0e907e8..a99e9b8e4e31 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -66,7 +66,7 @@ struct tty_buffer { int read; int flags; /* Data points here */ - unsigned long data[0]; + unsigned long data[]; }; /* Values for .flags field of tty_buffer */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 0d1fe9297ac6..6f6ade63b04c 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,6 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h> static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, @@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, bool little_endian) { unsigned int gso_type = 0; + unsigned int thlen = 0; + unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; + ip_proto = IPPROTO_UDP; + thlen = sizeof(struct udphdr); break; default: return -EINVAL; @@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + + if (skb_transport_offset(skb) + thlen > skb_headlen(skb)) + return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { + struct flow_keys_basic keys; + if (!skb->protocol) virtio_net_hdr_set_proto(skb, hdr); retry: - skb_probe_transport_header(skb); - if (!skb_transport_header_was_set(skb)) { + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, + 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { @@ -75,6 +91,12 @@ retry: } return -EINVAL; } + + if (keys.control.thoff + thlen > skb_headlen(skb) || + keys.basic.ip_proto != ip_proto) + return -EINVAL; + + skb_set_transport_header(skb, keys.control.thoff); } } diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 71c81e0dc8f2..dc636b727179 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,6 +48,7 @@ struct virtio_vsock_pkt { u32 len; u32 off; bool reply; + bool tap_delivered; }; struct virtio_vsock_pkt_info { diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 3619c6acf60f..efc8350b42fb 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -166,15 +166,18 @@ enum flow_action_mangle_base { enum flow_action_hw_stats_bit { FLOW_ACTION_HW_STATS_IMMEDIATE_BIT, FLOW_ACTION_HW_STATS_DELAYED_BIT, + FLOW_ACTION_HW_STATS_DISABLED_BIT, }; enum flow_action_hw_stats { - FLOW_ACTION_HW_STATS_DISABLED = 0, + FLOW_ACTION_HW_STATS_DONT_CARE = 0, FLOW_ACTION_HW_STATS_IMMEDIATE = BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT), FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT), FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE | FLOW_ACTION_HW_STATS_DELAYED, + FLOW_ACTION_HW_STATS_DISABLED = + BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT), }; typedef void (*action_destr)(void *priv); @@ -325,7 +328,11 @@ __flow_action_hw_stats_check(const struct flow_action *action, return true; if (!flow_action_mixed_hw_stats_check(action, extack)) return false; + action_entry = flow_action_first_entry_get(action); + if (action_entry->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE) + return true; + if (!check_allow_bit && action_entry->hw_stats != FLOW_ACTION_HW_STATS_ANY) { NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\""); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index c8e2bebd8d93..0f0d1efe06dd 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph) return 1; } +static inline int IP_ECN_set_ect1(struct iphdr *iph) +{ + u32 check = (__force u32)iph->check; + + if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + check += (__force u16)htons(0x100); + + iph->check = (__force __sum16)(check + (check>=0xFFFF)); + iph->tos ^= INET_ECN_MASK; + return 1; +} + static inline void IP_ECN_clear(struct iphdr *iph) { iph->tos &= ~INET_ECN_MASK; @@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) return 1; } +static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph) +{ + __be32 from, to; + + if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + from = *(__be32 *)iph; + to = from ^ htonl(INET_ECN_MASK << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); + return 1; +} + static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) { dscp &= ~INET_ECN_MASK; @@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +static inline int INET_ECN_set_ect1(struct sk_buff *skb) +{ + switch (skb->protocol) { + case cpu_to_be16(ETH_P_IP): + if (skb_network_header(skb) + sizeof(struct iphdr) <= + skb_tail_pointer(skb)) + return IP_ECN_set_ect1(ip_hdr(skb)); + break; + + case cpu_to_be16(ETH_P_IPV6): + if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= + skb_tail_pointer(skb)) + return IP6_ECN_set_ect1(skb, ipv6_hdr(skb)); + break; + } + + return 0; +} + /* * RFC 6040 4.2 * To decapsulate the inner header at the tunnel egress, a compliant @@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb, int rc; rc = __INET_ECN_decapsulate(outer, inner, &set_ce); - if (!rc && set_ce) - INET_ECN_set_ce(skb); + if (!rc) { + if (set_ce) + INET_ECN_set_ce(skb); + else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1) + INET_ECN_set_ect1(skb); + } return rc; } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 80262d2980f5..1d98828c6649 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -203,6 +203,7 @@ struct fib6_info { struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; + int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; @@ -291,6 +292,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt) struct fib6_info *from; u32 cookie = 0; + if (rt->sernum) + return rt->sernum; + rcu_read_lock(); from = rcu_dereference(rt->from); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0e7c5471010b..3bce2019e4da 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -68,11 +68,8 @@ static inline bool rsk_is_mptcp(const struct request_sock *req) return tcp_rsk(req)->is_mptcp; } -void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, - int opsize, struct tcp_options_received *opt_rx); bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts); -void mptcp_rcv_synsent(struct sock *sk); bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, struct mptcp_out_options *opts); bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index ab96fb59131c..8e001e049497 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -437,6 +437,13 @@ static inline int rt_genid_ipv4(const struct net *net) return atomic_read(&net->ipv4.rt_genid); } +#if IS_ENABLED(CONFIG_IPV6) +static inline int rt_genid_ipv6(const struct net *net) +{ + return atomic_read(&net->ipv6.fib6_sernum); +} +#endif + static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 25d2ec4c8f00..8428aa614265 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -407,6 +407,7 @@ struct tcf_block { struct mutex lock; struct list_head chain_list; u32 index; /* block index for shared blocks */ + u32 classid; /* which class this block belongs to */ refcount_t refcnt; struct net *net; struct Qdisc *q; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6d6a3947c8b7..efc8b613d486 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -502,6 +502,7 @@ struct ocelot { unsigned int num_stats; int shared_queue_sz; + int num_mact_rows; struct net_device *hw_bridge_dev; u16 bridge_mask; diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index a36b7227a15a..334842daa904 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -61,6 +61,7 @@ struct snd_rawmidi_runtime { size_t avail_min; /* min avail for wakeup */ size_t avail; /* max used buffer for wakeup */ size_t xruns; /* over/underruns counter */ + int buffer_ref; /* buffer reference count */ /* misc */ spinlock_t lock; wait_queue_head_t sleep; diff --git a/include/trace/events/gpu_mem.h b/include/trace/events/gpu_mem.h index 1897822a9150..26d871f96e94 100644 --- a/include/trace/events/gpu_mem.h +++ b/include/trace/events/gpu_mem.h @@ -24,7 +24,7 @@ * * @pid: Put 0 for global total, while positive pid for process total. * - * @size: Virtual size of the allocation in bytes. + * @size: Size of the allocation in bytes. * */ TRACE_EVENT(gpu_mem_total, diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index 784814160197..9c66e59d859c 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -33,7 +33,7 @@ TRACE_EVENT(wbt_stat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->rmean = stat[0].mean; __entry->rmin = stat[0].min; @@ -68,7 +68,7 @@ TRACE_EVENT(wbt_lat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->lat = div_u64(lat, 1000); ), @@ -105,7 +105,7 @@ TRACE_EVENT(wbt_step, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->msg = msg; __entry->step = step; @@ -141,7 +141,7 @@ TRACE_EVENT(wbt_timer, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->status = status; __entry->step = step; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bbf1b65be10..f9b7fdd951e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -73,7 +73,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[]; /* Arbitrary size */ + __u8 data[0]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index e83954c69fff..f880d2831160 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[]; + char name[0]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[]; + char name[0]; }; struct dlm_purge_params { diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 7a900b2377b6..8c0bc24d5d95 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -34,7 +34,7 @@ struct fiemap { __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ __u32 fm_extent_count; /* size of fm_extents array (in) */ __u32 fm_reserved; - struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */ + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ }; #define FIEMAP_MAX_OFFSET (~0ULL) diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index b122cfac7128..683878036d76 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -60,7 +60,7 @@ struct arc_rfc1201 { __u8 proto; /* protocol ID field - varies */ __u8 split_flag; /* for use with split packets */ __be16 sequence; /* sequence number */ - __u8 payload[]; /* space remaining in packet (504 bytes)*/ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 @@ -69,7 +69,7 @@ struct arc_rfc1201 { */ struct arc_rfc1051 { __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[]; /* 507 bytes */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 @@ -80,7 +80,7 @@ struct arc_rfc1051 { struct arc_eth_encap { __u8 proto; /* Always ARC_P_ETHER */ struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[]; /* 493 bytes */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 98e29e7f54ac..00c08120f3ba 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -57,7 +57,7 @@ struct mmc_ioc_cmd { */ struct mmc_ioc_multi_cmd { __u64 num_of_cmds; - struct mmc_ioc_cmd cmds[]; + struct mmc_ioc_cmd cmds[0]; }; #define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 67e31f329190..66048cc5d7b3 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -29,12 +29,12 @@ struct net_dm_config_entry { struct net_dm_config_msg { __u32 entries; - struct net_dm_config_entry options[]; + struct net_dm_config_entry options[0]; }; struct net_dm_alert_msg { __u32 entries; - struct net_dm_drop_point points[]; + struct net_dm_drop_point points[0]; }; struct net_dm_user_msg { diff --git a/include/uapi/linux/netfilter_bridge/ebt_among.h b/include/uapi/linux/netfilter_bridge/ebt_among.h index 73b26a280c4f..9acf757bc1f7 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_among.h +++ b/include/uapi/linux/netfilter_bridge/ebt_among.h @@ -40,7 +40,7 @@ struct ebt_mac_wormhash_tuple { struct ebt_mac_wormhash { int table[257]; int poolsize; - struct ebt_mac_wormhash_tuple pool[]; + struct ebt_mac_wormhash_tuple pool[0]; }; #define ebt_mac_wormhash_size(x) ((x) ? sizeof(struct ebt_mac_wormhash) \ diff --git a/include/uapi/scsi/scsi_bsg_fc.h b/include/uapi/scsi/scsi_bsg_fc.h index 7f5930801f72..3ae65e93235c 100644 --- a/include/uapi/scsi/scsi_bsg_fc.h +++ b/include/uapi/scsi/scsi_bsg_fc.h @@ -209,7 +209,7 @@ struct fc_bsg_host_vendor { __u64 vendor_id; /* start of vendor command area */ - __u32 vendor_cmd[]; + __u32 vendor_cmd[0]; }; /* Response: diff --git a/init/Kconfig b/init/Kconfig index 9e22ee8fbd75..9278a603d399 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -39,22 +39,6 @@ config TOOLS_SUPPORT_RELR config CC_HAS_ASM_INLINE def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null) -config CC_HAS_WARN_MAYBE_UNINITIALIZED - def_bool $(cc-option,-Wmaybe-uninitialized) - help - GCC >= 4.7 supports this option. - -config CC_DISABLE_WARN_MAYBE_UNINITIALIZED - bool - depends on CC_HAS_WARN_MAYBE_UNINITIALIZED - default CC_IS_GCC && GCC_VERSION < 40900 # unreliable for GCC < 4.9 - help - GCC's -Wmaybe-uninitialized is not reliable by definition. - Lots of false positive warnings are produced in some cases. - - If this option is enabled, -Wno-maybe-uninitialzed is passed - to the compiler to suppress maybe-uninitialized warnings. - config CONSTRUCTORS bool depends on !UML @@ -1257,14 +1241,12 @@ config CC_OPTIMIZE_FOR_PERFORMANCE config CC_OPTIMIZE_FOR_PERFORMANCE_O3 bool "Optimize more for performance (-O3)" depends on ARC - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-O3" to your compiler to optimize the kernel yet more for performance. config CC_OPTIMIZE_FOR_SIZE bool "Optimize for size (-Os)" - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-Os" to your compiler resulting in a smaller kernel. diff --git a/init/initramfs.c b/init/initramfs.c index 8ec1be4d7d51..7a38012e1af7 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -542,7 +542,7 @@ void __weak free_initrd_mem(unsigned long start, unsigned long end) } #ifdef CONFIG_KEXEC_CORE -static bool kexec_free_initrd(void) +static bool __init kexec_free_initrd(void) { unsigned long crashk_start = (unsigned long)__va(crashk_res.start); unsigned long crashk_end = (unsigned long)__va(crashk_res.end); diff --git a/init/main.c b/init/main.c index a48617f2e5e5..5803ecb411ab 100644 --- a/init/main.c +++ b/init/main.c @@ -257,6 +257,47 @@ static int __init loglevel(char *str) early_param("loglevel", loglevel); +#ifdef CONFIG_BLK_DEV_INITRD +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + u32 size, csum; + char *data; + u32 *hdr; + + if (!initrd_end) + return NULL; + + data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; + if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + return NULL; + + hdr = (u32 *)(data - 8); + size = hdr[0]; + csum = hdr[1]; + + data = ((void *)hdr) - size; + if ((unsigned long)data < initrd_start) { + pr_err("bootconfig size %d is greater than initrd size %ld\n", + size, initrd_end - initrd_start); + return NULL; + } + + /* Remove bootconfig from initramfs/initrd */ + initrd_end = (unsigned long)data; + if (_size) + *_size = size; + if (_csum) + *_csum = csum; + + return data; +} +#else +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + return NULL; +} +#endif + #ifdef CONFIG_BOOT_CONFIG char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; @@ -357,9 +398,11 @@ static void __init setup_boot_config(const char *cmdline) int pos; u32 size, csum; char *data, *copy; - u32 *hdr; int ret; + /* Cut out the bootconfig data even if we have no bootconfig option */ + data = get_boot_config_from_initrd(&size, &csum); + strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL, bootconfig_params); @@ -367,16 +410,10 @@ static void __init setup_boot_config(const char *cmdline) if (!bootconfig_found) return; - if (!initrd_end) - goto not_found; - - data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; - if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) - goto not_found; - - hdr = (u32 *)(data - 8); - size = hdr[0]; - csum = hdr[1]; + if (!data) { + pr_err("'bootconfig' found on command line, but no bootconfig found\n"); + return; + } if (size >= XBC_DATA_MAX) { pr_err("bootconfig size %d greater than max size %d\n", @@ -384,10 +421,6 @@ static void __init setup_boot_config(const char *cmdline) return; } - data = ((void *)hdr) - size; - if ((unsigned long)data < initrd_start) - goto not_found; - if (boot_config_checksum((unsigned char *)data, size) != csum) { pr_err("bootconfig checksum failed\n"); return; @@ -417,11 +450,15 @@ static void __init setup_boot_config(const char *cmdline) extra_init_args = xbc_make_cmdline("init"); } return; -not_found: - pr_err("'bootconfig' found on command line, but no bootconfig found\n"); } + #else -#define setup_boot_config(cmdline) do { } while (0) + +static void __init setup_boot_config(const char *cmdline) +{ + /* Remove bootconfig data from initrd */ + get_boot_config_from_initrd(NULL, NULL); +} static int __init warn_bootconfig(char *str) { diff --git a/ipc/mqueue.c b/ipc/mqueue.c index dc8307bf2d74..beff0cfcd1e8 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -142,6 +142,7 @@ struct mqueue_inode_info { struct sigevent notify; struct pid *notify_owner; + u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct user_struct *user; /* user who created, for accounting */ struct sock *notify_sock; @@ -773,28 +774,44 @@ static void __do_notify(struct mqueue_inode_info *info) * synchronously. */ if (info->notify_owner && info->attr.mq_curmsgs == 1) { - struct kernel_siginfo sig_i; switch (info->notify.sigev_notify) { case SIGEV_NONE: break; - case SIGEV_SIGNAL: - /* sends signal */ + case SIGEV_SIGNAL: { + struct kernel_siginfo sig_i; + struct task_struct *task; + + /* do_mq_notify() accepts sigev_signo == 0, why?? */ + if (!info->notify.sigev_signo) + break; clear_siginfo(&sig_i); sig_i.si_signo = info->notify.sigev_signo; sig_i.si_errno = 0; sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; - /* map current pid/uid into info->owner's namespaces */ rcu_read_lock(); + /* map current pid/uid into info->owner's namespaces */ sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); - sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid()); + sig_i.si_uid = from_kuid_munged(info->notify_user_ns, + current_uid()); + /* + * We can't use kill_pid_info(), this signal should + * bypass check_kill_permission(). It is from kernel + * but si_fromuser() can't know this. + * We do check the self_exec_id, to avoid sending + * signals to programs that don't expect them. + */ + task = pid_task(info->notify_owner, PIDTYPE_TGID); + if (task && task->self_exec_id == + info->notify_self_exec_id) { + do_send_sig_info(info->notify.sigev_signo, + &sig_i, task, PIDTYPE_TGID); + } rcu_read_unlock(); - - kill_pid_info(info->notify.sigev_signo, - &sig_i, info->notify_owner); break; + } case SIGEV_THREAD: set_cookie(info->notify_cookie, NOTIFY_WOKENUP); netlink_sendskb(info->notify_sock, info->notify_cookie); @@ -1383,6 +1400,7 @@ retry: info->notify.sigev_signo = notification->sigev_signo; info->notify.sigev_value = notification->sigev_value; info->notify.sigev_notify = SIGEV_SIGNAL; + info->notify_self_exec_id = current->self_exec_id; break; } diff --git a/ipc/util.c b/ipc/util.c index 7acccfded7cb..cfa0045e748d 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -764,21 +764,21 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, total++; } - *new_pos = pos + 1; + ipc = NULL; if (total >= ids->in_use) - return NULL; + goto out; for (; pos < ipc_mni; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { rcu_read_lock(); ipc_lock_object(ipc); - return ipc; + break; } } - - /* Out of range - return NULL to terminate iteration */ - return NULL; +out: + *new_pos = pos + 1; + return ipc; } static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) diff --git a/kernel/fork.c b/kernel/fork.c index 8c700f881d92..48ed22774efa 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2486,11 +2486,11 @@ long do_fork(unsigned long clone_flags, int __user *child_tidptr) { struct kernel_clone_args args = { - .flags = (clone_flags & ~CSIGNAL), + .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, - .exit_signal = (clone_flags & CSIGNAL), + .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = stack_start, .stack_size = stack_size, }; @@ -2508,8 +2508,9 @@ long do_fork(unsigned long clone_flags, pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { - .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), - .exit_signal = (flags & CSIGNAL), + .flags = ((lower_32_bits(flags) | CLONE_VM | + CLONE_UNTRACED) & ~CSIGNAL), + .exit_signal = (lower_32_bits(flags) & CSIGNAL), .stack = (unsigned long)fn, .stack_size = (unsigned long)arg, }; @@ -2570,11 +2571,11 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #endif { struct kernel_clone_args args = { - .flags = (clone_flags & ~CSIGNAL), + .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, - .exit_signal = (clone_flags & CSIGNAL), + .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; diff --git a/kernel/kcov.c b/kernel/kcov.c index f50354202dbe..8accc9722a81 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -740,8 +740,8 @@ static const struct file_operations kcov_fops = { * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an * arbitrary 4-byte non-zero number as the instance id). This common handle * then gets saved into the task_struct of the process that issued the - * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn - * kernel threads, the common handle must be retrived via kcov_common_handle() + * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn + * kernel threads, the common handle must be retrieved via kcov_common_handle() * and passed to the spawned threads via custom annotations. Those kernel * threads must in turn be annotated with kcov_remote_start(common_handle) and * kcov_remote_stop(). All of the threads that are spawned by the same process diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 402eef84c859..743647005f64 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -466,7 +466,6 @@ config PROFILE_ANNOTATED_BRANCHES config PROFILE_ALL_BRANCHES bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help This tracer profiles all branch conditions. Every if () taken in the kernel is recorded whether it hit or miss. diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h index 0456e0a3dab1..382775edf690 100644 --- a/kernel/trace/ftrace_internal.h +++ b/kernel/trace/ftrace_internal.h @@ -4,28 +4,6 @@ #ifdef CONFIG_FUNCTION_TRACER -/* - * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw_check() is that elements removed from this list - * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw_check() calls are needed to handle - * concurrent insertions into the ftrace_global_list. - * - * Silly Alpha and silly pointer-speculation compiler optimizations! - */ -#define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw_check(list); \ - do - -/* - * Optimized for just a single item in the list (as that is the normal case). - */ -#define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw_check((op)->next)) && \ - unlikely((op) != &ftrace_list_end)) - -extern struct ftrace_ops __rcu *ftrace_ops_list; -extern struct ftrace_ops ftrace_list_end; extern struct mutex ftrace_lock; extern struct ftrace_ops global_ops; diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index 31c0fad4cb9e..312d1a0ca3b6 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -16,6 +16,7 @@ #include <linux/printk.h> #include <linux/string.h> #include <linux/sysfs.h> +#include <linux/completion.h> static ulong delay = 100; static char test_mode[12] = "irq"; @@ -28,6 +29,8 @@ MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)"); MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)"); MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)"); +static struct completion done; + #define MIN(x, y) ((x) < (y) ? (x) : (y)) static void busy_wait(ulong time) @@ -113,22 +116,47 @@ static int preemptirq_delay_run(void *data) for (i = 0; i < s; i++) (testfuncs[i])(i); + + complete(&done); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + + __set_current_state(TASK_RUNNING); + return 0; } -static struct task_struct *preemptirq_start_test(void) +static int preemptirq_run_test(void) { + struct task_struct *task; char task_name[50]; + init_completion(&done); + snprintf(task_name, sizeof(task_name), "%s_test", test_mode); - return kthread_run(preemptirq_delay_run, NULL, task_name); + task = kthread_run(preemptirq_delay_run, NULL, task_name); + if (IS_ERR(task)) + return PTR_ERR(task); + if (task) { + wait_for_completion(&done); + kthread_stop(task); + } + return 0; } static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - preemptirq_start_test(); + ssize_t ret; + + ret = preemptirq_run_test(); + if (ret) + return ret; return count; } @@ -148,11 +176,9 @@ static struct kobject *preemptirq_delay_kobj; static int __init preemptirq_delay_init(void) { - struct task_struct *test_task; int retval; - test_task = preemptirq_start_test(); - retval = PTR_ERR_OR_ZERO(test_task); + retval = preemptirq_run_test(); if (retval != 0) return retval; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6f0b42ceeb00..b8e1ca48be50 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -193,7 +193,7 @@ rb_event_length(struct ring_buffer_event *event) case RINGBUF_TYPE_DATA: return rb_event_data_length(event); default: - BUG(); + WARN_ON_ONCE(1); } /* not hit */ return 0; @@ -249,7 +249,7 @@ rb_event_data(struct ring_buffer_event *event) { if (extended_time(event)) event = skip_time_extend(event); - BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); + WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); /* If length is in len field, then array[0] has the data */ if (event->type_len) return (void *)&event->array[0]; @@ -3727,7 +3727,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, return; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return; } @@ -3757,7 +3757,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter, return; default: - BUG(); + RB_WARN_ON(iter->cpu_buffer, 1); } return; } @@ -4020,7 +4020,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, return event; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return NULL; @@ -4034,7 +4034,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int nr_loops = 0; - bool failed = false; if (ts) *ts = 0; @@ -4056,19 +4055,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return NULL; /* - * We repeat when a time extend is encountered or we hit - * the end of the page. Since the time extend is always attached - * to a data event, we should never loop more than three times. - * Once for going to next page, once on time extend, and - * finally once to get the event. - * We should never hit the following condition more than thrice, - * unless the buffer is very small, and there's a writer - * that is causing the reader to fail getting an event. + * As the writer can mess with what the iterator is trying + * to read, just give up if we fail to get an event after + * three tries. The iterator is not as reliable when reading + * the ring buffer with an active write as the consumer is. + * Do not warn if the three failures is reached. */ - if (++nr_loops > 3) { - RB_WARN_ON(cpu_buffer, !failed); + if (++nr_loops > 3) return NULL; - } if (rb_per_cpu_empty(cpu_buffer)) return NULL; @@ -4079,10 +4073,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } event = rb_iter_head_event(iter); - if (!event) { - failed = true; + if (!event) goto again; - } switch (event->type_len) { case RINGBUF_TYPE_PADDING: @@ -4117,7 +4109,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return event; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return NULL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8d2b98812625..29615f15a820 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) +static void tracing_snapshot_instance_cond(struct trace_array *tr, + void *cond_data) { struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -8525,6 +8526,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) */ allocate_snapshot = false; #endif + + /* + * Because of some magic with the way alloc_percpu() works on + * x86_64, we need to synchronize the pgd of all the tables, + * otherwise the trace events that happen in x86_64 page fault + * handlers can't cope with accessing the chance that a + * alloc_percpu()'d memory might be touched in the page fault trace + * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() + * calls in tracing, because something might get triggered within a + * page fault trace event! + */ + vmalloc_sync_mappings(); + return 0; } diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 06d7feb5255f..9de29bb45a27 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -95,24 +95,20 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) struct xbc_node *anode; char buf[MAX_BUF_LEN]; const char *val; - int ret; + int ret = 0; - kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); + xbc_node_for_each_array_value(node, "probes", anode, val) { + kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); - ret = kprobe_event_gen_cmd_start(&cmd, event, NULL); - if (ret) - return ret; + ret = kprobe_event_gen_cmd_start(&cmd, event, val); + if (ret) + break; - xbc_node_for_each_array_value(node, "probes", anode, val) { - ret = kprobe_event_add_field(&cmd, val); + ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - return ret; + pr_err("Failed to add probe: %s\n", buf); } - ret = kprobe_event_gen_cmd_end(&cmd); - if (ret) - pr_err("Failed to add probe: %s\n", buf); - return ret; } #else diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d0568af4a0ef..35989383ae11 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr) static bool within_notrace_func(struct trace_kprobe *tk) { - unsigned long addr = addr = trace_kprobe_address(tk); + unsigned long addr = trace_kprobe_address(tk); char symname[KSYM_NAME_LEN], *p; if (!__within_notrace_func(addr)) @@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init); * complete command or only the first part of it; in the latter case, * kprobe_event_add_fields() can be used to add more fields following this. * + * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This + * returns -EINVAL if @loc == NULL. + * * Return: 0 if successful, error otherwise. */ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, @@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, if (cmd->type != DYNEVENT_TYPE_KPROBE) return -EINVAL; + if (!loc) + return -EINVAL; + if (kretprobe) snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name); else diff --git a/kernel/umh.c b/kernel/umh.c index 7f255b5a8845..11bf5eea474c 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -544,6 +544,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob); * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). + * + * Note: successful return value does not guarantee the helper was called at + * all. You can't rely on sub_info->{init,cleanup} being called even for + * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers + * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 48469c95d78e..929211039bac 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -60,18 +60,15 @@ config UBSAN_SANITIZE_ALL Enabling this option will get kernel image size increased significantly. -config UBSAN_NO_ALIGNMENT - bool "Disable checking of pointers alignment" - default y if HAVE_EFFICIENT_UNALIGNED_ACCESS +config UBSAN_ALIGNMENT + bool "Enable checks for pointers alignment" + default !HAVE_EFFICIENT_UNALIGNED_ACCESS + depends on !X86 || !COMPILE_TEST help - This option disables the check of unaligned memory accesses. - This option should be used when building allmodconfig. - Disabling this option on architectures that support unaligned + This option enables the check of unaligned memory accesses. + Enabling this option on architectures that support unaligned accesses may produce a lot of false positives. -config UBSAN_ALIGNMENT - def_bool !UBSAN_NO_ALIGNMENT - config TEST_UBSAN tristate "Module for testing for undefined behavior detection" depends on m diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c81b4f3a7268..efc5b83acd2d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -21,7 +21,7 @@ struct backing_dev_info noop_backing_dev_info = { EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; -const char *bdi_unknown_name = "(unknown)"; +static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU @@ -938,7 +938,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); + vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); + dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); @@ -1043,6 +1044,14 @@ void bdi_put(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_put); +const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return bdi->dev_name; +} +EXPORT_SYMBOL_GPL(bdi_dev_name); + static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) @@ -1218,6 +1218,10 @@ retry: if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; + if ((fault_flags & FAULT_FLAG_KILLABLE) && + fatal_signal_pending(current)) + return -EINTR; + ret = handle_mm_fault(vma, address, fault_flags); major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { @@ -1230,11 +1234,9 @@ retry: if (ret & VM_FAULT_RETRY) { down_read(&mm->mmap_sem); - if (!(fault_flags & FAULT_FLAG_TRIED)) { - *unlocked = true; - fault_flags |= FAULT_FLAG_TRIED; - goto retry; - } + *unlocked = true; + fault_flags |= FAULT_FLAG_TRIED; + goto retry; } if (tsk) { diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 08b43de2383b..434d503a6525 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -1,23 +1,28 @@ # SPDX-License-Identifier: GPL-2.0 KASAN_SANITIZE := n -UBSAN_SANITIZE_common.o := n -UBSAN_SANITIZE_generic.o := n -UBSAN_SANITIZE_generic_report.o := n -UBSAN_SANITIZE_tags.o := n +UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Disable ftrace to avoid recursion. CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_quarantine.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_tags_report.o = $(CC_FLAGS_FTRACE) # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 - CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_init.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_quarantine.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_tags_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) obj-$(CONFIG_KASAN) := common.o init.o report.o obj-$(CONFIG_KASAN_GENERIC) += generic.o generic_report.o quarantine.o diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index e8f37199d885..cfade6413528 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -212,8 +212,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); void __asan_register_globals(struct kasan_global *globals, size_t size); void __asan_unregister_globals(struct kasan_global *globals, size_t size); -void __asan_loadN(unsigned long addr, size_t size); -void __asan_storeN(unsigned long addr, size_t size); void __asan_handle_no_return(void); void __asan_alloca_poison(unsigned long addr, size_t size); void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom); @@ -228,6 +226,8 @@ void __asan_load8(unsigned long addr); void __asan_store8(unsigned long addr); void __asan_load16(unsigned long addr); void __asan_store16(unsigned long addr); +void __asan_loadN(unsigned long addr, size_t size); +void __asan_storeN(unsigned long addr, size_t size); void __asan_load1_noabort(unsigned long addr); void __asan_store1_noabort(unsigned long addr); @@ -239,6 +239,21 @@ void __asan_load8_noabort(unsigned long addr); void __asan_store8_noabort(unsigned long addr); void __asan_load16_noabort(unsigned long addr); void __asan_store16_noabort(unsigned long addr); +void __asan_loadN_noabort(unsigned long addr, size_t size); +void __asan_storeN_noabort(unsigned long addr, size_t size); + +void __asan_report_load1_noabort(unsigned long addr); +void __asan_report_store1_noabort(unsigned long addr); +void __asan_report_load2_noabort(unsigned long addr); +void __asan_report_store2_noabort(unsigned long addr); +void __asan_report_load4_noabort(unsigned long addr); +void __asan_report_store4_noabort(unsigned long addr); +void __asan_report_load8_noabort(unsigned long addr); +void __asan_report_store8_noabort(unsigned long addr); +void __asan_report_load16_noabort(unsigned long addr); +void __asan_report_store16_noabort(unsigned long addr); +void __asan_report_load_n_noabort(unsigned long addr, size_t size); +void __asan_report_store_n_noabort(unsigned long addr, size_t size); void __asan_set_shadow_00(const void *addr, size_t size); void __asan_set_shadow_f1(const void *addr, size_t size); @@ -247,4 +262,19 @@ void __asan_set_shadow_f3(const void *addr, size_t size); void __asan_set_shadow_f5(const void *addr, size_t size); void __asan_set_shadow_f8(const void *addr, size_t size); +void __hwasan_load1_noabort(unsigned long addr); +void __hwasan_store1_noabort(unsigned long addr); +void __hwasan_load2_noabort(unsigned long addr); +void __hwasan_store2_noabort(unsigned long addr); +void __hwasan_load4_noabort(unsigned long addr); +void __hwasan_store4_noabort(unsigned long addr); +void __hwasan_load8_noabort(unsigned long addr); +void __hwasan_store8_noabort(unsigned long addr); +void __hwasan_load16_noabort(unsigned long addr); +void __hwasan_store16_noabort(unsigned long addr); +void __hwasan_loadN_noabort(unsigned long addr, size_t size); +void __hwasan_storeN_noabort(unsigned long addr, size_t size); + +void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size); + #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5beea03dd58a..a3b97f103966 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4990,19 +4990,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void) unsigned int size; int node; int __maybe_unused i; + long error = -ENOMEM; size = sizeof(struct mem_cgroup); size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); memcg = kzalloc(size, GFP_KERNEL); if (!memcg) - return NULL; + return ERR_PTR(error); memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, GFP_KERNEL); - if (memcg->id.id < 0) + if (memcg->id.id < 0) { + error = memcg->id.id; goto fail; + } memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu); if (!memcg->vmstats_local) @@ -5046,7 +5049,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(error); } static struct cgroup_subsys_state * __ref @@ -5057,8 +5060,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) long error = -ENOMEM; memcg = mem_cgroup_alloc(); - if (!memcg) - return ERR_PTR(error); + if (IS_ERR(memcg)) + return ERR_CAST(memcg); WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; @@ -5108,7 +5111,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) fail: mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); } static int mem_cgroup_css_online(struct cgroup_subsys_state *css) diff --git a/mm/mremap.c b/mm/mremap.c index c881abeba0bf..6aa6ea605068 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -794,7 +794,7 @@ out: if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); userfaultfd_unmap_complete(mm, &uf_unmap_early); - mremap_userfaultfd_complete(&uf, addr, new_addr, old_len); + mremap_userfaultfd_complete(&uf, addr, ret, old_len); userfaultfd_unmap_complete(mm, &uf_unmap); return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 69827d4fa052..13cc653122b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1607,6 +1607,7 @@ void set_zone_contiguous(struct zone *zone) if (!__pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone)) return; + cond_resched(); } /* We confirm that there is no hole */ @@ -2400,6 +2401,14 @@ static inline void boost_watermark(struct zone *zone) if (!watermark_boost_factor) return; + /* + * Don't bother in zones that are unlikely to produce results. + * On small machines, including kdump capture kernels running + * in a small area, boosting the watermark can cause an out of + * memory situation immediately. + */ + if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) + return; max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); diff --git a/mm/percpu.c b/mm/percpu.c index d7e3bc649f4e..7da7d7737dab 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -80,6 +80,7 @@ #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <asm/cacheflush.h> #include <asm/sections.h> @@ -1557,10 +1558,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { - /* whitelisted flags that can be passed to the backing allocators */ - gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; - bool do_warn = !(gfp & __GFP_NOWARN); + gfp_t pcpu_gfp; + bool is_atomic; + bool do_warn; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; @@ -1569,6 +1569,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, void __percpu *ptr; size_t bits, bit_align; + gfp = current_gfp_context(gfp); + /* whitelisted flags that can be passed to the backing allocators */ + pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; + do_warn = !(gfp & __GFP_NOWARN); + /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. diff --git a/mm/slub.c b/mm/slub.c index 9bf44955c4f1..b762450fc9f0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -551,15 +551,32 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { struct track *p; - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; + p = object + get_info_end(s); return p + alloc; } @@ -686,10 +703,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); - if (s->offset) - off = s->offset + sizeof(void *); - else - off = s->inuse; + off = get_info_end(s); if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); @@ -782,7 +796,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object address * Bytes of the object to be managed. * If the freepointer may overlay the object then the free - * pointer is the first word of the object. + * pointer is at the middle of the object. * * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) @@ -816,11 +830,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) { - unsigned long off = s->inuse; /* The end of info */ - - if (s->offset) - /* Freepointer is placed after the object. */ - off += sizeof(void *); + unsigned long off = get_info_end(s); /* The end of info */ if (s->flags & SLAB_STORE_USER) /* We also have user information there */ @@ -907,7 +917,7 @@ static int check_object(struct kmem_cache *s, struct page *page, check_pad_bytes(s, page, p); } - if (!s->offset && val == SLUB_RED_ACTIVE) + if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) /* * Object and freepointer overlap. Cannot check * freepointer while object is allocated. @@ -3587,6 +3597,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * * This is the case if we do RCU, have a constructor or * destructor or are poisoning the objects. + * + * The assumption that s->offset >= s->inuse means free + * pointer is outside of the object is used in the + * freeptr_outside_object() function. If that is no + * longer true, the function needs to be modified. */ s->offset = size; size += sizeof(void *); diff --git a/mm/vmscan.c b/mm/vmscan.c index b06868fc4926..a37c87b5aee2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1625,7 +1625,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session - * @mode: One of the LRU isolation modes * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. diff --git a/net/atm/common.c b/net/atm/common.c index 0ce530af534d..8575f5d52087 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -177,18 +177,18 @@ static void vcc_destroy_socket(struct sock *sk) set_bit(ATM_VF_CLOSE, &vcc->flags); clear_bit(ATM_VF_READY, &vcc->flags); - if (vcc->dev) { - if (vcc->dev->ops->close) - vcc->dev->ops->close(vcc); - if (vcc->push) - vcc->push(vcc, NULL); /* atmarpd has no push */ - module_put(vcc->owner); - - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { - atm_return(vcc, skb->truesize); - kfree_skb(skb); - } + if (vcc->dev && vcc->dev->ops->close) + vcc->dev->ops->close(vcc); + if (vcc->push) + vcc->push(vcc, NULL); /* atmarpd has no push */ + module_put(vcc->owner); + + while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + atm_return(vcc, skb->truesize); + kfree_skb(skb); + } + if (vcc->dev && vcc->dev->ops->owner) { module_put(vcc->dev->ops->owner); atm_dev_put(vcc->dev); } diff --git a/net/atm/lec.c b/net/atm/lec.c index 25fa3a7b72bd..ca37f5a71f5e 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1264,6 +1264,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) entry->vcc = NULL; } if (entry->recv_vcc) { + struct atm_vcc *vcc = entry->recv_vcc; + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + + kfree(vpriv); + vcc->user_back = NULL; + entry->recv_vcc->push = entry->old_recv_push; vcc_release_async(entry->recv_vcc, -EPIPE); entry->recv_vcc = NULL; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 969466218999..80b87b1f4e3a 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -893,7 +893,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig); if (!orig_node) - return; + goto out; neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming, ethhdr->h_source); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 8f0717c3f7b5..b0469d15da0e 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1009,15 +1009,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, */ static u8 batadv_nc_random_weight_tq(u8 tq) { - u8 rand_val, rand_tq; - - get_random_bytes(&rand_val, sizeof(rand_val)); - /* randomize the estimated packet loss (max TQ - estimated TQ) */ - rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq); - - /* normalize the randomized packet loss */ - rand_tq /= BATADV_TQ_MAX_VALUE; + u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq); /* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index c45962d8527b..0f962dcd239e 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1150,7 +1150,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, ret = batadv_parse_throughput(net_dev, buff, "throughput_override", &tp_override); if (!ret) - return count; + goto out; old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override); if (old_tp_override == tp_override) @@ -1190,6 +1190,7 @@ static ssize_t batadv_show_throughput_override(struct kobject *kobj, tp_override = atomic_read(&hard_iface->bat_v.throughput_override); + batadv_hardif_put(hard_iface); return sprintf(buff, "%u.%u MBit\n", tp_override / 10, tp_override % 10); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 43dab4066f91..a0f5dbee8f9c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -612,6 +612,7 @@ int br_process_vlan_info(struct net_bridge *br, v - 1, rtm_cmd); v_change_start = 0; } + cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) diff --git a/net/core/devlink.c b/net/core/devlink.c index 80f97722f31f..899edcee7dab 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4283,6 +4283,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); dump = false; + + if (start_offset == end_offset) { + err = 0; + goto nla_put_failure; + } } err = devlink_nl_region_read_snapshot_fill(skb, devlink, @@ -5363,6 +5368,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter, { enum devlink_health_reporter_state prev_health_state; struct devlink *devlink = reporter->devlink; + unsigned long recover_ts_threshold; /* write a log message of the current error */ WARN_ON(!msg); @@ -5373,10 +5379,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); /* abort if the previous error wasn't recovered */ + recover_ts_threshold = reporter->last_recovery_ts + + msecs_to_jiffies(reporter->graceful_period); if (reporter->auto_recover && (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || - jiffies - reporter->last_recovery_ts < - msecs_to_jiffies(reporter->graceful_period))) { + (reporter->last_recovery_ts && reporter->recovery_count && + time_is_after_jiffies(recover_ts_threshold)))) { trace_devlink_health_recover_aborted(devlink, reporter->ops->name, reporter->health_state, diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 8e33cec9fc4e..2ee7bc4c9e03 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -213,6 +213,7 @@ static void sched_send_work(struct timer_list *t) static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; + struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; @@ -231,11 +232,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location) nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); + point = msg->points; for (i = 0; i < msg->entries; i++) { - if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { - msg->points[i].count++; + if (!memcmp(&location, &point->pc, sizeof(void *))) { + point->count++; goto out; } + point++; } if (msg->entries == dm_hit_limit) goto out; @@ -244,8 +247,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location) */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); - memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); - msg->points[msg->entries].count = 1; + memcpy(point->pc, &location, sizeof(void *)); + point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 39d37d0ef575..116139233d57 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1956,6 +1956,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } + if (protocol) + neigh->protocol = protocol; + if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; @@ -1969,9 +1972,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (protocol) - neigh->protocol = protocol; - neigh_release(neigh); out: diff --git a/net/core/sock.c b/net/core/sock.c index 90509c37d291..b714162213ae 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2364,7 +2364,6 @@ static void sk_leave_memory_pressure(struct sock *sk) } } -/* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9a271a58a41d..d90665b465b8 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -459,7 +459,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) list_for_each_entry(dp, &dst->ports, list) { err = dsa_port_setup(dp); if (err) - goto teardown; + continue; } return 0; diff --git a/net/dsa/master.c b/net/dsa/master.c index b5c535af63a3..a621367c6e8c 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -289,7 +289,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; - dev->netdev_ops = cpu_dp->orig_ndo_ops; + if (cpu_dp->orig_ndo_ops) + dev->netdev_ops = cpu_dp->orig_ndo_ops; cpu_dp->orig_ndo_ops = NULL; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d1068803cd11..62f4ee3da172 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -856,20 +856,18 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, struct dsa_port *to_dp; int err; - act = &cls->rule->action.entries[0]; - if (!ds->ops->port_mirror_add) return -EOPNOTSUPP; - if (!act->dev) - return -EINVAL; - if (!flow_action_basic_hw_stats_check(&cls->rule->action, cls->common.extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; + if (!act->dev) + return -EINVAL; + if (!dsa_slave_dev_check(act->dev)) return -EOPNOTSUPP; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index f4b9f7a3ce51..25b6ffba26cd 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -18,7 +18,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; - u16 protocol; + __be16 protocol; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bf4ced9273e8..b996dc1069c5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3926,10 +3926,6 @@ void tcp_parse_options(const struct net *net, */ break; #endif - case TCPOPT_MPTCP: - mptcp_parse_option(skb, ptr, opsize, opt_rx); - break; - case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -5990,9 +5986,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); - if (sk_is_mptcp(sk)) - mptcp_rcv_synsent(sk); - /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 310cbddaa533..8d418038fe32 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1385,9 +1385,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; + + if (f6i->nh) + pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); + return pcpu_rt; } +static bool rt6_is_valid(const struct rt6_info *rt6) +{ + return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); +} + /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { @@ -1395,6 +1404,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); + if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { + struct rt6_info *prev, **p; + + p = this_cpu_ptr(res->nh->rt6i_pcpu); + prev = xchg(p, NULL); + if (prev) { + dst_dev_put(&prev->dst); + dst_release(&prev->dst); + } + + pcpu_rt = NULL; + } + return pcpu_rt; } @@ -2593,6 +2615,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = container_of(dst, struct rt6_info, dst); + if (rt->sernum) + return rt6_is_valid(rt) ? dst : NULL; + rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 4c7e0a27fa9c..37b434293bda 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -27,8 +27,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) { - int trailing; unsigned int tlv_offset; + int max_last_entry; + int trailing; if (srh->type != IPV6_SRCRT_TYPE_4) return false; @@ -36,7 +37,12 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) if (((srh->hdrlen + 1) << 3) != len) return false; - if (srh->segments_left > srh->first_segment) + max_last_entry = (srh->hdrlen / 2) - 1; + + if (srh->first_segment > max_last_entry) + return false; + + if (srh->segments_left > srh->first_segment + 1) return false; tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4a7c467b99db..45497af23906 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -16,10 +16,10 @@ static bool mptcp_cap_flag_sha256(u8 flags) return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256; } -void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, - int opsize, struct tcp_options_received *opt_rx) +static void mptcp_parse_option(const struct sk_buff *skb, + const unsigned char *ptr, int opsize, + struct mptcp_options_received *mp_opt) { - struct mptcp_options_received *mp_opt = &opt_rx->mptcp; u8 subtype = *ptr >> 4; int expected_opsize; u8 version; @@ -283,12 +283,20 @@ void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, } void mptcp_get_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx) + struct mptcp_options_received *mp_opt) { - const unsigned char *ptr; const struct tcphdr *th = tcp_hdr(skb); - int length = (th->doff * 4) - sizeof(struct tcphdr); + const unsigned char *ptr; + int length; + + /* initialize option status */ + mp_opt->mp_capable = 0; + mp_opt->mp_join = 0; + mp_opt->add_addr = 0; + mp_opt->rm_addr = 0; + mp_opt->dss = 0; + length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); while (length > 0) { @@ -308,7 +316,7 @@ void mptcp_get_options(const struct sk_buff *skb, if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_MPTCP) - mptcp_parse_option(skb, ptr, opsize, opt_rx); + mptcp_parse_option(skb, ptr, opsize, mp_opt); ptr += opsize - 2; length -= opsize; } @@ -344,28 +352,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, return false; } -void mptcp_rcv_synsent(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct tcp_sock *tp = tcp_sk(sk); - - if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) { - subflow->mp_capable = 1; - subflow->can_ack = 1; - subflow->remote_key = tp->rx_opt.mptcp.sndr_key; - pr_debug("subflow=%p, remote_key=%llu", subflow, - subflow->remote_key); - } else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) { - subflow->mp_join = 1; - subflow->thmac = tp->rx_opt.mptcp.thmac; - subflow->remote_nonce = tp->rx_opt.mptcp.nonce; - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, - subflow->thmac, subflow->remote_nonce); - } else if (subflow->request_mptcp) { - tcp_sk(sk)->is_mptcp = 0; - } -} - /* MP_JOIN client subflow must wait for 4th ack before sending any data: * TCP can't schedule delack timer before the subflow is fully established. * MPTCP uses the delack timer to do 3rd ack retransmissions @@ -709,7 +695,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) return subflow->mp_capable; - if (mp_opt->use_ack) { + if (mp_opt->dss && mp_opt->use_ack) { /* subflows are fully established as soon as we get any * additional ack. */ @@ -717,8 +703,6 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, goto fully_established; } - WARN_ON_ONCE(subflow->can_ack); - /* If the first established packet does not contain MP_CAPABLE + data * then fallback to TCP */ @@ -728,6 +712,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, return false; } + if (unlikely(!READ_ONCE(msk->pm.server_side))) + pr_warn_once("bogus mpc option on established client sk"); subflow->fully_established = 1; subflow->remote_key = mp_opt->sndr_key; subflow->can_ack = 1; @@ -819,41 +805,41 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - struct mptcp_options_received *mp_opt; + struct mptcp_options_received mp_opt; struct mptcp_ext *mpext; - mp_opt = &opt_rx->mptcp; - if (!check_fully_established(msk, sk, subflow, skb, mp_opt)) + mptcp_get_options(skb, &mp_opt); + if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return; - if (mp_opt->add_addr && add_addr_hmac_valid(msk, mp_opt)) { + if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) { struct mptcp_addr_info addr; - addr.port = htons(mp_opt->port); - addr.id = mp_opt->addr_id; - if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) { + addr.port = htons(mp_opt.port); + addr.id = mp_opt.addr_id; + if (mp_opt.family == MPTCP_ADDR_IPVERSION_4) { addr.family = AF_INET; - addr.addr = mp_opt->addr; + addr.addr = mp_opt.addr; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) - else if (mp_opt->family == MPTCP_ADDR_IPVERSION_6) { + else if (mp_opt.family == MPTCP_ADDR_IPVERSION_6) { addr.family = AF_INET6; - addr.addr6 = mp_opt->addr6; + addr.addr6 = mp_opt.addr6; } #endif - if (!mp_opt->echo) + if (!mp_opt.echo) mptcp_pm_add_addr_received(msk, &addr); - mp_opt->add_addr = 0; + mp_opt.add_addr = 0; } - if (!mp_opt->dss) + if (!mp_opt.dss) return; /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck */ - if (mp_opt->use_ack) - update_una(msk, mp_opt); + if (mp_opt.use_ack) + update_una(msk, &mp_opt); mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) @@ -861,8 +847,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, memset(mpext, 0, sizeof(*mpext)); - if (mp_opt->use_map) { - if (mp_opt->mpc_map) { + if (mp_opt.use_map) { + if (mp_opt.mpc_map) { /* this is an MP_CAPABLE carrying MPTCP data * we know this map the first chunk of data */ @@ -872,13 +858,14 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, mpext->subflow_seq = 1; mpext->dsn64 = 1; mpext->mpc_map = 1; + mpext->data_fin = 0; } else { - mpext->data_seq = mp_opt->data_seq; - mpext->subflow_seq = mp_opt->subflow_seq; - mpext->dsn64 = mp_opt->dsn64; - mpext->data_fin = mp_opt->data_fin; + mpext->data_seq = mp_opt.data_seq; + mpext->subflow_seq = mp_opt.subflow_seq; + mpext->dsn64 = mp_opt.dsn64; + mpext->data_fin = mp_opt.data_fin; } - mpext->data_len = mp_opt->data_len; + mpext->data_len = mp_opt.data_len; mpext->use_map = 1; } } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b22a63ba2348..e1f23016ed3f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1316,11 +1316,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) static int mptcp_disconnect(struct sock *sk, int flags) { - lock_sock(sk); - __mptcp_clear_xmit(sk); - release_sock(sk); - mptcp_cancel_work(sk); - return tcp_disconnect(sk, flags); + /* Should never be called. + * inet_stream_connect() calls ->disconnect, but that + * refers to the subflow socket, not the mptcp one. + */ + WARN_ON_ONCE(1); + return 0; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1333,7 +1334,7 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) #endif struct sock *mptcp_sk_clone(const struct sock *sk, - const struct tcp_options_received *opt_rx, + const struct mptcp_options_received *mp_opt, struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); @@ -1372,9 +1373,9 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->write_seq = subflow_req->idsn + 1; atomic64_set(&msk->snd_una, msk->write_seq); - if (opt_rx->mptcp.mp_capable) { + if (mp_opt->mp_capable) { msk->can_ack = true; - msk->remote_key = opt_rx->mptcp.sndr_key; + msk->remote_key = mp_opt->sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); ack_seq++; msk->ack_seq = ack_seq; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a2b3048037d0..e4ca6320ce76 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -91,6 +91,45 @@ #define MPTCP_WORK_RTX 2 #define MPTCP_WORK_EOF 3 +struct mptcp_options_received { + u64 sndr_key; + u64 rcvr_key; + u64 data_ack; + u64 data_seq; + u32 subflow_seq; + u16 data_len; + u16 mp_capable : 1, + mp_join : 1, + dss : 1, + add_addr : 1, + rm_addr : 1, + family : 4, + echo : 1, + backup : 1; + u32 token; + u32 nonce; + u64 thmac; + u8 hmac[20]; + u8 join_id; + u8 use_map:1, + dsn64:1, + data_fin:1, + use_ack:1, + ack64:1, + mpc_map:1, + __unused:2; + u8 addr_id; + u8 rm_id; + union { + struct in_addr addr; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + struct in6_addr addr6; +#endif + }; + u64 ahmac; + u16 port; +}; + static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) { return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) | @@ -331,10 +370,10 @@ int mptcp_proto_v6_init(void); #endif struct sock *mptcp_sk_clone(const struct sock *sk, - const struct tcp_options_received *opt_rx, + const struct mptcp_options_received *mp_opt, struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx); + struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index fabd06f2ff45..67a4e35d4838 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -124,12 +124,11 @@ static void subflow_init_req(struct request_sock *req, { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - struct tcp_options_received rx_opt; + struct mptcp_options_received mp_opt; pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); - memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp)); - mptcp_get_options(skb, &rx_opt); + mptcp_get_options(skb, &mp_opt); subflow_req->mp_capable = 0; subflow_req->mp_join = 0; @@ -142,16 +141,16 @@ static void subflow_init_req(struct request_sock *req, return; #endif - if (rx_opt.mptcp.mp_capable) { + if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); - if (rx_opt.mptcp.mp_join) + if (mp_opt.mp_join) return; - } else if (rx_opt.mptcp.mp_join) { + } else if (mp_opt.mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); } - if (rx_opt.mptcp.mp_capable && listener->request_mptcp) { + if (mp_opt.mp_capable && listener->request_mptcp) { int err; err = mptcp_token_new_request(req); @@ -159,13 +158,13 @@ static void subflow_init_req(struct request_sock *req, subflow_req->mp_capable = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; - } else if (rx_opt.mptcp.mp_join && listener->request_mptcp) { + } else if (mp_opt.mp_join && listener->request_mptcp) { subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; subflow_req->mp_join = 1; - subflow_req->backup = rx_opt.mptcp.backup; - subflow_req->remote_id = rx_opt.mptcp.join_id; - subflow_req->token = rx_opt.mptcp.token; - subflow_req->remote_nonce = rx_opt.mptcp.nonce; + subflow_req->backup = mp_opt.backup; + subflow_req->remote_id = mp_opt.join_id; + subflow_req->token = mp_opt.token; + subflow_req->remote_nonce = mp_opt.nonce; pr_debug("token=%u, remote_nonce=%u", subflow_req->token, subflow_req->remote_nonce); if (!subflow_token_join_request(req, skb)) { @@ -221,23 +220,47 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow) static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_options_received mp_opt; struct sock *parent = subflow->conn; + struct tcp_sock *tp = tcp_sk(sk); subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - if (inet_sk_state_load(parent) != TCP_ESTABLISHED) { + if (inet_sk_state_load(parent) == TCP_SYN_SENT) { inet_sk_state_store(parent, TCP_ESTABLISHED); parent->sk_state_change(parent); } - if (subflow->conn_finished || !tcp_sk(sk)->is_mptcp) + /* be sure no special action on any packet other than syn-ack */ + if (subflow->conn_finished) + return; + + subflow->conn_finished = 1; + + mptcp_get_options(skb, &mp_opt); + if (subflow->request_mptcp && mp_opt.mp_capable) { + subflow->mp_capable = 1; + subflow->can_ack = 1; + subflow->remote_key = mp_opt.sndr_key; + pr_debug("subflow=%p, remote_key=%llu", subflow, + subflow->remote_key); + } else if (subflow->request_join && mp_opt.mp_join) { + subflow->mp_join = 1; + subflow->thmac = mp_opt.thmac; + subflow->remote_nonce = mp_opt.nonce; + pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, + subflow->thmac, subflow->remote_nonce); + } else if (subflow->request_mptcp) { + tp->is_mptcp = 0; + } + + if (!tp->is_mptcp) return; if (subflow->mp_capable) { pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk), subflow->remote_key); mptcp_finish_connect(sk); - subflow->conn_finished = 1; if (skb) { pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq); @@ -264,7 +287,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (!mptcp_finish_join(sk)) goto do_reset; - subflow->conn_finished = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); } else { do_reset: @@ -322,7 +344,7 @@ drop: /* validate hmac received in third ACK */ static bool subflow_hmac_valid(const struct request_sock *req, - const struct tcp_options_received *rx_opt) + const struct mptcp_options_received *mp_opt) { const struct mptcp_subflow_request_sock *subflow_req; u8 hmac[MPTCPOPT_HMAC_LEN]; @@ -339,7 +361,7 @@ static bool subflow_hmac_valid(const struct request_sock *req, subflow_req->local_nonce, hmac); ret = true; - if (crypto_memneq(hmac, rx_opt->mptcp.hmac, sizeof(hmac))) + if (crypto_memneq(hmac, mp_opt->hmac, sizeof(hmac))) ret = false; sock_put((struct sock *)msk); @@ -395,7 +417,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk); struct mptcp_subflow_request_sock *subflow_req; - struct tcp_options_received opt_rx; + struct mptcp_options_received mp_opt; bool fallback_is_fatal = false; struct sock *new_msk = NULL; bool fallback = false; @@ -403,7 +425,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); - opt_rx.mptcp.mp_capable = 0; + /* we need later a valid 'mp_capable' value even when options are not + * parsed + */ + mp_opt.mp_capable = 0; if (tcp_rsk(req)->is_mptcp == 0) goto create_child; @@ -418,22 +443,21 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, goto create_msk; } - mptcp_get_options(skb, &opt_rx); - if (!opt_rx.mptcp.mp_capable) { + mptcp_get_options(skb, &mp_opt); + if (!mp_opt.mp_capable) { fallback = true; goto create_child; } create_msk: - new_msk = mptcp_sk_clone(listener->conn, &opt_rx, req); + new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req); if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { fallback_is_fatal = true; - opt_rx.mptcp.mp_join = 0; - mptcp_get_options(skb, &opt_rx); - if (!opt_rx.mptcp.mp_join || - !subflow_hmac_valid(req, &opt_rx)) { + mptcp_get_options(skb, &mp_opt); + if (!mp_opt.mp_join || + !subflow_hmac_valid(req, &mp_opt)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); return NULL; } @@ -473,9 +497,9 @@ create_child: /* with OoO packets we can reach here without ingress * mpc option */ - ctx->remote_key = opt_rx.mptcp.sndr_key; - ctx->fully_established = opt_rx.mptcp.mp_capable; - ctx->can_ack = opt_rx.mptcp.mp_capable; + ctx->remote_key = mp_opt.sndr_key; + ctx->fully_established = mp_opt.mp_capable; + ctx->can_ack = mp_opt.mp_capable; } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -499,7 +523,7 @@ out: /* check for expected invariant - should never trigger, just help * catching eariler subtle bugs */ - WARN_ON_ONCE(*own_req && child && tcp_sk(child)->is_mptcp && + WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp && (!mptcp_subflow_ctx(child) || !mptcp_subflow_ctx(child)->conn)); return child; diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 3d816a1e5442..59151dc07fdc 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -68,15 +68,13 @@ static bool udp_manip_pkt(struct sk_buff *skb, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; - bool do_csum; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); - do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL; + __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); - __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum); return true; } diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 9f5dea0064ea..916a3c7f9eaf 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -165,12 +165,12 @@ static bool nf_osf_match_one(const struct sk_buff *skb, static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx, const struct sk_buff *skb, const struct iphdr *ip, - unsigned char *opts) + unsigned char *opts, + struct tcphdr *_tcph) { const struct tcphdr *tcp; - struct tcphdr _tcph; - tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph); if (!tcp) return NULL; @@ -205,10 +205,11 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, int fmatch = FMATCH_WRONG; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; @@ -265,10 +266,11 @@ bool nf_osf_find(const struct sk_buff *skb, const struct nf_osf_finger *kf; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 55bd1429678f..0a7ecc292bd3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2070,6 +2070,7 @@ replay: err = PTR_ERR(block); goto errout; } + block->classid = parent; chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { @@ -2612,12 +2613,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; parent = tcm->tcm_parent; - if (!parent) { + if (!parent) q = dev->qdisc; - parent = q->handle; - } else { + else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } if (!q) goto out; cops = q->ops->cl_ops; @@ -2633,6 +2632,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl, NULL); if (!block) goto out; + parent = block->classid; if (tcf_block_shared(block)) q = NULL; } @@ -3523,6 +3523,16 @@ static void tcf_sample_get_group(struct flow_action_entry *entry, #endif } +static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) +{ + if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY)) + return FLOW_ACTION_HW_STATS_DONT_CARE; + else if (!hw_stats) + return FLOW_ACTION_HW_STATS_DISABLED; + + return hw_stats; +} + int tc_setup_flow_action(struct flow_action *flow_action, const struct tcf_exts *exts) { @@ -3546,7 +3556,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, if (err) goto err_out_locked; - entry->hw_stats = act->hw_stats; + entry->hw_stats = tc_act_hw_stats(act->hw_stats); if (is_tcf_gact_ok(act)) { entry->id = FLOW_ACTION_ACCEPT; @@ -3614,7 +3624,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mangle.mask = tcf_pedit_mask(act, k); entry->mangle.val = tcf_pedit_val(act, k); entry->mangle.offset = tcf_pedit_offset(act, k); - entry->hw_stats = act->hw_stats; + entry->hw_stats = tc_act_hw_stats(act->hw_stats); entry = &flow_action->entries[++j]; } } else if (is_tcf_csum(act)) { diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index a36974e9c601..1bcf8fbfd40e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch) sch->q.qlen = 0; sch->qstats.backlog = 0; - memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + if (q->tab) + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 968519ff36e9..436160be9c18 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -416,7 +416,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index c787d4d46017..5a6def5e4e6d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; + + /* slot->allot is a short, make sure quantum is not too big. */ + if (ctl->quantum) { + unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum); + + if (scaled <= 0 || scaled > SHRT_MAX) + return -EINVAL; + } + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog)) return -EINVAL; diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 0fb10abf7579..7a5e4c454715 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, { struct tc_skbprio_qopt *ctl = nla_data(opt); + if (opt->nla_len != nla_attr_size(sizeof(*ctl))) + return -EINVAL; + sch->limit = ctl->limit; return 0; } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 25fbd8d9de74..ac5cac0dd24b 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -2032,7 +2032,6 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf; struct kvec *head = rqstp->rq_rcv_buf.head; struct rpc_auth *auth = cred->cr_auth; - unsigned int savedlen = rcv_buf->len; u32 offset, opaque_len, maj_stat; __be32 *p; @@ -2043,9 +2042,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, offset = (u8 *)(p) - (u8 *)head->iov_base; if (offset + opaque_len > rcv_buf->len) goto unwrap_failed; - rcv_buf->len = offset + opaque_len; - maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, rcv_buf); + maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, + offset + opaque_len, rcv_buf); if (maj_stat == GSS_S_CONTEXT_EXPIRED) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); if (maj_stat != GSS_S_COMPLETE) @@ -2059,10 +2058,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, */ xdr_init_decode(xdr, rcv_buf, p, rqstp); - auth->au_rslack = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); - auth->au_ralign = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); + auth->au_rslack = auth->au_verfsize + 2 + ctx->gc_gss_ctx->slack; + auth->au_ralign = auth->au_verfsize + 2 + ctx->gc_gss_ctx->align; + return 0; unwrap_failed: trace_rpcgss_unwrap_failed(task); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 6f2d30d7b766..e7180da1fc6a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -851,8 +851,8 @@ out_err: } u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, - u32 *headskip, u32 *tailskip) +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, + struct xdr_buf *buf, u32 *headskip, u32 *tailskip) { struct xdr_buf subbuf; u32 ret = 0; @@ -881,7 +881,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, /* create a segment skipping the header and leaving out the checksum */ xdr_buf_subsegment(buf, &subbuf, offset + GSS_KRB5_TOK_HDR_LEN, - (buf->len - offset - GSS_KRB5_TOK_HDR_LEN - + (len - offset - GSS_KRB5_TOK_HDR_LEN - kctx->gk5e->cksumlength)); nblocks = (subbuf.len + blocksize - 1) / blocksize; @@ -926,7 +926,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, goto out_err; /* Get the packet's hmac value */ - ret = read_bytes_from_xdr_buf(buf, buf->len - kctx->gk5e->cksumlength, + ret = read_bytes_from_xdr_buf(buf, len - kctx->gk5e->cksumlength, pkt_hmac, kctx->gk5e->cksumlength); if (ret) goto out_err; diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 6c1920eed771..cf0fd170ac18 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -261,7 +261,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, } static u32 -gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { int signalg; int sealalg; @@ -279,12 +281,13 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) u32 conflen = kctx->gk5e->conflen; int crypt_offset; u8 *cksumkey; + unsigned int saved_len = buf->len; dprintk("RPC: gss_unwrap_kerberos\n"); ptr = (u8 *)buf->head[0].iov_base + offset; if (g_verify_token_header(&kctx->mech_used, &bodysize, &ptr, - buf->len - offset)) + len - offset)) return GSS_S_DEFECTIVE_TOKEN; if ((ptr[0] != ((KG_TOK_WRAP_MSG >> 8) & 0xff)) || @@ -324,6 +327,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) (!kctx->initiate && direction != 0)) return GSS_S_BAD_SIG; + buf->len = len; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { struct crypto_sync_skcipher *cipher; int err; @@ -376,11 +380,15 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start; memmove(orig_start, data_start, data_len); buf->head[0].iov_len -= (data_start - orig_start); - buf->len -= (data_start - orig_start); + buf->len = len - (data_start - orig_start); if (gss_krb5_remove_padding(buf, blocksize)) return GSS_S_DEFECTIVE_TOKEN; + /* slack must include room for krb5 padding */ + *slack = XDR_QUADLEN(saved_len - buf->len); + /* The GSS blob always precedes the RPC message payload */ + *align = *slack; return GSS_S_COMPLETE; } @@ -486,7 +494,9 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, } static u32 -gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { time64_t now; u8 *ptr; @@ -532,7 +542,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) if (rrc != 0) rotate_left(offset + 16, buf, rrc); - err = (*kctx->gk5e->decrypt_v2)(kctx, offset, buf, + err = (*kctx->gk5e->decrypt_v2)(kctx, offset, len, buf, &headskip, &tailskip); if (err) return GSS_S_FAILURE; @@ -542,7 +552,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * it against the original */ err = read_bytes_from_xdr_buf(buf, - buf->len - GSS_KRB5_TOK_HDR_LEN - tailskip, + len - GSS_KRB5_TOK_HDR_LEN - tailskip, decrypted_hdr, GSS_KRB5_TOK_HDR_LEN); if (err) { dprintk("%s: error %u getting decrypted_hdr\n", __func__, err); @@ -568,18 +578,19 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * Note that buf->head[0].iov_len may indicate the available * head buffer space rather than that actually occupied. */ - movelen = min_t(unsigned int, buf->head[0].iov_len, buf->len); + movelen = min_t(unsigned int, buf->head[0].iov_len, len); movelen -= offset + GSS_KRB5_TOK_HDR_LEN + headskip; - if (offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > - buf->head[0].iov_len) - return GSS_S_FAILURE; + BUG_ON(offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > + buf->head[0].iov_len); memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen); buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; - buf->len -= GSS_KRB5_TOK_HDR_LEN + headskip; + buf->len = len - GSS_KRB5_TOK_HDR_LEN + headskip; /* Trim off the trailing "extra count" and checksum blob */ - buf->len -= ec + GSS_KRB5_TOK_HDR_LEN + tailskip; + xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip); + *align = XDR_QUADLEN(GSS_KRB5_TOK_HDR_LEN + headskip); + *slack = *align + XDR_QUADLEN(ec + GSS_KRB5_TOK_HDR_LEN + tailskip); return GSS_S_COMPLETE; } @@ -603,7 +614,8 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset, } u32 -gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, + int len, struct xdr_buf *buf) { struct krb5_ctx *kctx = gctx->internal_ctx_id; @@ -613,9 +625,11 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: case ENCTYPE_ARCFOUR_HMAC: - return gss_unwrap_kerberos_v1(kctx, offset, buf); + return gss_unwrap_kerberos_v1(kctx, offset, len, buf, + &gctx->slack, &gctx->align); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_unwrap_kerberos_v2(kctx, offset, buf); + return gss_unwrap_kerberos_v2(kctx, offset, len, buf, + &gctx->slack, &gctx->align); } } diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index db550bfc2642..69316ab1b9fa 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -411,10 +411,11 @@ gss_wrap(struct gss_ctx *ctx_id, u32 gss_unwrap(struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf) { return ctx_id->mech_type->gm_ops - ->gss_unwrap(ctx_id, offset, buf); + ->gss_unwrap(ctx_id, offset, len, buf); } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 54ae5be62f6a..50d93c49ef1a 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -906,7 +906,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g if (svc_getnl(&buf->head[0]) != seq) goto out; /* trim off the mic and padding at the end before returning */ - buf->len -= 4 + round_up_to_quad(mic.len); + xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4); stat = 0; out: kfree(mic.data); @@ -934,7 +934,7 @@ static int unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) { u32 priv_len, maj_stat; - int pad, saved_len, remaining_len, offset; + int pad, remaining_len, offset; clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); @@ -954,12 +954,8 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs buf->len -= pad; fix_priv_head(buf, pad); - /* Maybe it would be better to give gss_unwrap a length parameter: */ - saved_len = buf->len; - buf->len = priv_len; - maj_stat = gss_unwrap(ctx, 0, buf); + maj_stat = gss_unwrap(ctx, 0, priv_len, buf); pad = priv_len - buf->len; - buf->len = saved_len; buf->len -= pad; /* The upper layers assume the buffer is aligned on 4-byte boundaries. * In the krb5p case, at least, the data ends up offset, so we need to diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 15b58c5144f9..6f7d82fb1eb0 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1150,6 +1150,47 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, } EXPORT_SYMBOL_GPL(xdr_buf_subsegment); +/** + * xdr_buf_trim - lop at most "len" bytes off the end of "buf" + * @buf: buf to be trimmed + * @len: number of bytes to reduce "buf" by + * + * Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note + * that it's possible that we'll trim less than that amount if the xdr_buf is + * too small, or if (for instance) it's all in the head and the parser has + * already read too far into it. + */ +void xdr_buf_trim(struct xdr_buf *buf, unsigned int len) +{ + size_t cur; + unsigned int trim = len; + + if (buf->tail[0].iov_len) { + cur = min_t(size_t, buf->tail[0].iov_len, trim); + buf->tail[0].iov_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->page_len) { + cur = min_t(unsigned int, buf->page_len, trim); + buf->page_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->head[0].iov_len) { + cur = min_t(size_t, buf->head[0].iov_len, trim); + buf->head[0].iov_len -= cur; + trim -= cur; + } +fix_len: + buf->len -= (len - trim); +} +EXPORT_SYMBOL_GPL(xdr_buf_trim); + static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len) { unsigned int this_len; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 3a12fc18239b..73dbed0c4b6b 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -402,10 +402,11 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) read_lock_bh(&sk->sk_callback_lock); ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); + if (!ret) + return 0; } - if (ret < 0) - tipc_conn_close(con); + tipc_conn_close(con); return ret; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index c98e602a1a2d..e23f94a5549b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -800,6 +800,8 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); } + if (psock) + sk_psock_put(sk, psock); return err; } more_data: @@ -2081,8 +2083,9 @@ static void tls_data_ready(struct sock *sk) strp_data_ready(&ctx->strp); psock = sk_psock_get(sk); - if (psock && !list_empty(&psock->ingress_msg)) { - ctx->saved_data_ready(sk); + if (psock) { + if (!list_empty(&psock->ingress_msg)) + ctx->saved_data_ready(sk); sk_psock_put(sk, psock); } } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 709038a4783e..69efc891885f 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -157,7 +157,11 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) { + if (pkt->tap_delivered) + return; + vsock_deliver_tap(virtio_transport_build_skb, pkt); + pkt->tap_delivered = true; } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 8aa415a38814..0285aaa1e93c 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause, sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } + if (x25->neighbour) { + read_lock_bh(&x25_list_lock); + x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } } /* diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h index 80b4a70315b6..13a35f7cbe66 100644 --- a/samples/trace_events/trace-events-sample.h +++ b/samples/trace_events/trace-events-sample.h @@ -416,7 +416,7 @@ TRACE_EVENT_FN(foo_bar_with_fn, * Note, TRACE_EVENT() itself is simply defined as: * * #define TRACE_EVENT(name, proto, args, tstruct, assign, printk) \ - * DEFINE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ + * DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ * DEFINE_EVENT(name, name, proto, args) * * The DEFINE_EVENT() also can be declared with conditions and reg functions: diff --git a/scripts/decodecode b/scripts/decodecode index ba8b8d5834e6..fbdb325cdf4f 100755 --- a/scripts/decodecode +++ b/scripts/decodecode @@ -126,7 +126,7 @@ faultlinenum=$(( $(wc -l $T.oo | cut -d" " -f1) - \ faultline=`cat $T.dis | head -1 | cut -d":" -f2-` faultline=`echo "$faultline" | sed -e 's/\[/\\\[/g; s/\]/\\\]/g'` -cat $T.oo | sed -e "${faultlinenum}s/^\(.*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" +cat $T.oo | sed -e "${faultlinenum}s/^\([^:]*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" echo cat $T.aa cleanup diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index f22858b2c3d6..80f354289eeb 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -4,6 +4,7 @@ GCC_PLUGINS_DIR := $(shell $(CC) -print-file-name=plugin) HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat +HOST_EXTRACXXFLAGS += -Wno-format-diag $(obj)/randomize_layout_plugin.o: $(objtree)/$(obj)/randomize_layout_seed.h quiet_cmd_create_randomize_layout_seed = GENSEED $@ diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 17f06079a712..9ad76b7f3f10 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -35,7 +35,9 @@ #include "ggc.h" #include "timevar.h" +#if BUILDING_GCC_VERSION < 10000 #include "params.h" +#endif #if BUILDING_GCC_VERSION <= 4009 #include "pointer-set.h" @@ -847,6 +849,7 @@ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree l return gimple_build_assign(lhs, subcode, op1, op2 PASS_MEM_STAT); } +#if BUILDING_GCC_VERSION < 10000 template <> template <> inline bool is_a_helper<const ggoto *>::test(const_gimple gs) @@ -860,6 +863,7 @@ inline bool is_a_helper<const greturn *>::test(const_gimple gs) { return gs->code == GIMPLE_RETURN; } +#endif static inline gasm *as_a_gasm(gimple stmt) { diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index dbd37460c573..cc75eeba0be1 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -51,7 +51,6 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) gimple stmt; gcall *stackleak_track_stack; cgraph_node_ptr node; - int frequency; basic_block bb; /* Insert call to void stackleak_track_stack(void) */ @@ -68,9 +67,9 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) bb = gimple_bb(stackleak_track_stack); node = cgraph_get_create_node(track_function_decl); gcc_assert(node); - frequency = compute_call_stmt_bb_frequency(current_function_decl, bb); cgraph_create_edge(cgraph_get_node(current_function_decl), node, - stackleak_track_stack, bb->count, frequency); + stackleak_track_stack, bb->count, + compute_call_stmt_bb_frequency(current_function_decl, bb)); } static bool is_alloca(gimple stmt) diff --git a/scripts/gdb/linux/rbtree.py b/scripts/gdb/linux/rbtree.py index 39db889b874c..c4b991607917 100644 --- a/scripts/gdb/linux/rbtree.py +++ b/scripts/gdb/linux/rbtree.py @@ -12,7 +12,7 @@ rb_node_type = utils.CachedType("struct rb_node") def rb_first(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) @@ -28,7 +28,7 @@ def rb_first(root): def rb_last(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 3e8dea6e0a95..6dc3078649fa 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -34,7 +34,7 @@ struct sym_entry { unsigned int len; unsigned int start_pos; unsigned int percpu_absolute; - unsigned char sym[0]; + unsigned char sym[]; }; struct addr_range { diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 20dd08e1f675..2a688b711a9a 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -120,6 +120,17 @@ static void snd_rawmidi_input_event_work(struct work_struct *work) runtime->event(runtime->substream); } +/* buffer refcount management: call with runtime->lock held */ +static inline void snd_rawmidi_buffer_ref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref++; +} + +static inline void snd_rawmidi_buffer_unref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref--; +} + static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) { struct snd_rawmidi_runtime *runtime; @@ -669,6 +680,11 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime, if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock); + if (runtime->buffer_ref) { + spin_unlock_irq(&runtime->lock); + kvfree(newbuf); + return -EBUSY; + } oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; @@ -1019,8 +1035,10 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, long result = 0, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; unsigned long appl_ptr; + int err = 0; spin_lock_irqsave(&runtime->lock, flags); + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -1039,16 +1057,19 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); if (copy_to_user(userbuf + result, - runtime->buffer + appl_ptr, count1)) { - return result > 0 ? result : -EFAULT; - } + runtime->buffer + appl_ptr, count1)) + err = -EFAULT; spin_lock_irqsave(&runtime->lock, flags); + if (err) + goto out; } result += count1; count -= count1; } + out: + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); - return result; + return result > 0 ? result : err; } long snd_rawmidi_kernel_read(struct snd_rawmidi_substream *substream, @@ -1342,6 +1363,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, return -EAGAIN; } } + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail > 0) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -1373,6 +1395,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, } __end: count1 = runtime->avail < runtime->buffer_size; + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); if (count1) snd_rawmidi_output_trigger(substream, 1); diff --git a/sound/firewire/amdtp-stream-trace.h b/sound/firewire/amdtp-stream-trace.h index 16c7f6605511..26e7cb555d3c 100644 --- a/sound/firewire/amdtp-stream-trace.h +++ b/sound/firewire/amdtp-stream-trace.h @@ -66,8 +66,7 @@ TRACE_EVENT(amdtp_packet, __entry->irq, __entry->index, __print_array(__get_dynamic_array(cip_header), - __get_dynamic_array_len(cip_header), - sizeof(u8))) + __get_dynamic_array_len(cip_header), 1)) ); #endif diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c16f63957c5a..dc2302171a71 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5856,6 +5856,15 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, } } +static void alc225_fixup_s3_pop_noise(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + codec->power_save_node = 1; +} + /* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */ static void alc274_fixup_bind_dacs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -5960,6 +5969,7 @@ enum { ALC269_FIXUP_HP_LINE1_MIC1_LED, ALC269_FIXUP_INV_DMIC, ALC269_FIXUP_LENOVO_DOCK, + ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, ALC269_FIXUP_NO_SHUTUP, ALC286_FIXUP_SONY_MIC_NO_PRESENCE, ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT, @@ -6045,6 +6055,7 @@ enum { ALC233_FIXUP_ACER_HEADSET_MIC, ALC294_FIXUP_LENOVO_MIC_LOCATION, ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, + ALC225_FIXUP_S3_POP_NOISE, ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, @@ -6080,9 +6091,12 @@ enum { ALC294_FIXUP_ASUS_DUAL_SPK, ALC285_FIXUP_THINKPAD_HEADSET_JACK, ALC294_FIXUP_ASUS_HPE, + ALC294_FIXUP_ASUS_COEF_1B, ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED, + ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, + ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6280,6 +6294,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT }, + [ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_limit_int_mic_boost, + .chained = true, + .chain_id = ALC269_FIXUP_LENOVO_DOCK, + }, [ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_pincfg_no_hp_to_lineout, @@ -6932,6 +6952,12 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, + .chain_id = ALC225_FIXUP_S3_POP_NOISE + }, + [ALC225_FIXUP_S3_POP_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc225_fixup_s3_pop_noise, + .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, [ALC700_FIXUP_INTEL_REFERENCE] = { @@ -7204,6 +7230,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC }, + [ALC294_FIXUP_ASUS_COEF_1B] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Set bit 10 to correct noisy output after reboot from + * Windows 10 (due to pop noise reduction?) + */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x1b }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x4e4b }, + { } + }, + }, [ALC285_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_gpio_led, @@ -7216,6 +7253,22 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_mute_led, }, + [ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x1a, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc5 }, + { } + }, + }, + [ALC295_FIXUP_ASUS_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7383,8 +7436,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), + SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -7410,6 +7465,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), + SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), @@ -7426,7 +7483,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21ca, "Thinkpad L412", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21e9, "Thinkpad Edge 15", ALC269_FIXUP_SKU_IGNORE), - SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK), + SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST), SND_PCI_QUIRK(0x17aa, 0x21fa, "Thinkpad X230", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x21f3, "Thinkpad T430", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x21fb, "Thinkpad T430s", ALC269_FIXUP_LENOVO_DOCK), @@ -7565,6 +7622,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC269_FIXUP_HEADSET_MODE, .name = "headset-mode"}, {.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"}, {.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"}, + {.id = ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, .name = "lenovo-dock-limit-boost"}, {.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"}, {.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"}, {.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"}, @@ -7993,6 +8051,18 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x17, 0x90170110}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60120}, + {0x17, 0x90170110}, + {0x21, 0x04211030}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x03211020}), SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x04211020}), @@ -8209,8 +8279,6 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; break; case 0x10ec0225: - codec->power_save_node = 1; - /* fall through */ case 0x10ec0295: case 0x10ec0299: spec->codec_variant = ALC269_TYPE_ALC225; diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 0260c750e156..bfdc6ad52785 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -549,6 +549,11 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = trx40_mobo_map, .connector_map = trx40_mobo_connector_map, }, + { /* Asrock TRX40 Creator */ + .id = USB_ID(0x26ce, 0x0a01), + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, + }, { 0 } /* terminator */ }; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index a1df4c5b4f8c..6313c30f5c85 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3563,6 +3563,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), ALC1220_VB_DESKTOP(0x0414, 0xa002), /* Gigabyte TRX40 Aorus Pro WiFi */ ALC1220_VB_DESKTOP(0x0db0, 0x0d64), /* MSI TRX40 Creator */ ALC1220_VB_DESKTOP(0x0db0, 0x543d), /* MSI TRX40 */ +ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ #undef ALC1220_VB_DESKTOP #undef USB_DEVICE_VENDOR_SPEC diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 848a4cc25bed..d8a765be5dfe 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1636,13 +1636,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here, - * otherwise requests like get/set frequency return as failed despite - * actually succeeding. + /* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny + * delay here, otherwise requests like get/set frequency return as + * failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || chip->usb_id == USB_ID(0x046d, 0x0a46) || - chip->usb_id == USB_ID(0x0b0e, 0x0349)) && + chip->usb_id == USB_ID(0x0b0e, 0x0349) || + chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) usleep_range(1000, 2000); } diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 16b9a420e6fd..0efaf45f7367 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -314,6 +314,7 @@ int apply_xbc(const char *path, const char *xbc_path) ret = delete_xbc(path); if (ret < 0) { pr_err("Failed to delete previous boot config: %d\n", ret); + free(data); return ret; } @@ -321,24 +322,27 @@ int apply_xbc(const char *path, const char *xbc_path) fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { pr_err("Failed to open %s: %d\n", path, fd); + free(data); return fd; } /* TODO: Ensure the @path is initramfs/initrd image */ ret = write(fd, data, size + 8); if (ret < 0) { pr_err("Failed to apply a boot config: %d\n", ret); - return ret; + goto out; } /* Write a magic word of the bootconfig */ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); if (ret < 0) { pr_err("Failed to apply a boot config magic: %d\n", ret); - return ret; + goto out; } + ret = 0; +out: close(fd); free(data); - return 0; + return ret; } int usage(void) diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 7427a5ee761b..9d8e9613008a 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -159,7 +159,12 @@ class IocgStat: else: self.inflight_pct = 0 - self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + # vdebt used to be an atomic64_t and is now u64, support both + try: + self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + except: + self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 + self.use_delay = blkg.use_delay.counter.value_() self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4b170fd08a28..3c6da70e6084 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -72,6 +72,17 @@ static struct instruction *next_insn_same_func(struct objtool_file *file, return find_insn(file, func->cfunc->sec, func->cfunc->offset); } +static struct instruction *prev_insn_same_sym(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *prev = list_prev_entry(insn, list); + + if (&prev->list != &file->insn_list && prev->func == insn->func) + return prev; + + return NULL; +} + #define func_for_each_insn(file, func, insn) \ for (insn = find_insn(file, func->sec, func->offset); \ insn; \ @@ -1050,8 +1061,8 @@ static struct rela *find_jump_table(struct objtool_file *file, * it. */ for (; - &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func; - insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { + insn && insn->func && insn->func->pfunc == func; + insn = insn->first_jump_src ?: prev_insn_same_sym(file, insn)) { if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC) break; @@ -1449,7 +1460,7 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s struct cfi_reg *cfa = &state->cfa; struct stack_op *op = &insn->stack_op; - if (cfa->base != CFI_SP) + if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT) return 0; /* push */ diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 0b79c2353a21..12e01ac190ec 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -87,9 +87,10 @@ struct elf { #define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) #define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) -#define for_offset_range(_offset, _start, _end) \ - for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ - _offset <= ((_end) & OFFSET_STRIDE_MASK); \ +#define for_offset_range(_offset, _start, _end) \ + for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ + _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ + _offset <= ((_end) & OFFSET_STRIDE_MASK); \ _offset += OFFSET_STRIDE) static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index cd5e1f602ac9..909da9cdda97 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -351,6 +351,7 @@ static int test_alloc_errors(char *heap_name) } printf("Expected error checking passed\n"); + ret = 0; out: if (dmabuf_fd >= 0) close(dmabuf_fd); diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 11eee0b60040..d979ff14775a 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include <poll.h> #include <unistd.h> +#include <assert.h> #include <signal.h> #include <pthread.h> #include <sys/epoll.h> @@ -3136,4 +3137,149 @@ TEST(epoll59) close(ctx.sfd[0]); } +enum { + EPOLL60_EVENTS_NR = 10, +}; + +struct epoll60_ctx { + volatile int stopped; + int ready; + int waiters; + int epfd; + int evfd[EPOLL60_EVENTS_NR]; +}; + +static void *epoll60_wait_thread(void *ctx_) +{ + struct epoll60_ctx *ctx = ctx_; + struct epoll_event e; + sigset_t sigmask; + uint64_t v; + int ret; + + /* Block SIGUSR1 */ + sigemptyset(&sigmask); + sigaddset(&sigmask, SIGUSR1); + sigprocmask(SIG_SETMASK, &sigmask, NULL); + + /* Prepare empty mask for epoll_pwait() */ + sigemptyset(&sigmask); + + while (!ctx->stopped) { + /* Mark we are ready */ + __atomic_fetch_add(&ctx->ready, 1, __ATOMIC_ACQUIRE); + + /* Start when all are ready */ + while (__atomic_load_n(&ctx->ready, __ATOMIC_ACQUIRE) && + !ctx->stopped); + + /* Account this waiter */ + __atomic_fetch_add(&ctx->waiters, 1, __ATOMIC_ACQUIRE); + + ret = epoll_pwait(ctx->epfd, &e, 1, 2000, &sigmask); + if (ret != 1) { + /* We expect only signal delivery on stop */ + assert(ret < 0 && errno == EINTR && "Lost wakeup!\n"); + assert(ctx->stopped); + break; + } + + ret = read(e.data.fd, &v, sizeof(v)); + /* Since we are on ET mode, thus each thread gets its own fd. */ + assert(ret == sizeof(v)); + + __atomic_fetch_sub(&ctx->waiters, 1, __ATOMIC_RELEASE); + } + + return NULL; +} + +static inline unsigned long long msecs(void) +{ + struct timespec ts; + unsigned long long msecs; + + clock_gettime(CLOCK_REALTIME, &ts); + msecs = ts.tv_sec * 1000ull; + msecs += ts.tv_nsec / 1000000ull; + + return msecs; +} + +static inline int count_waiters(struct epoll60_ctx *ctx) +{ + return __atomic_load_n(&ctx->waiters, __ATOMIC_ACQUIRE); +} + +TEST(epoll60) +{ + struct epoll60_ctx ctx = { 0 }; + pthread_t waiters[ARRAY_SIZE(ctx.evfd)]; + struct epoll_event e; + int i, n, ret; + + signal(SIGUSR1, signal_handler); + + ctx.epfd = epoll_create1(0); + ASSERT_GE(ctx.epfd, 0); + + /* Create event fds */ + for (i = 0; i < ARRAY_SIZE(ctx.evfd); i++) { + ctx.evfd[i] = eventfd(0, EFD_NONBLOCK); + ASSERT_GE(ctx.evfd[i], 0); + + e.events = EPOLLIN | EPOLLET; + e.data.fd = ctx.evfd[i]; + ASSERT_EQ(epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd[i], &e), 0); + } + + /* Create waiter threads */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ASSERT_EQ(pthread_create(&waiters[i], NULL, + epoll60_wait_thread, &ctx), 0); + + for (i = 0; i < 300; i++) { + uint64_t v = 1, ms; + + /* Wait for all to be ready */ + while (__atomic_load_n(&ctx.ready, __ATOMIC_ACQUIRE) != + ARRAY_SIZE(ctx.evfd)) + ; + + /* Steady, go */ + __atomic_fetch_sub(&ctx.ready, ARRAY_SIZE(ctx.evfd), + __ATOMIC_ACQUIRE); + + /* Wait all have gone to kernel */ + while (count_waiters(&ctx) != ARRAY_SIZE(ctx.evfd)) + ; + + /* 1ms should be enough to schedule away */ + usleep(1000); + + /* Quickly signal all handles at once */ + for (n = 0; n < ARRAY_SIZE(ctx.evfd); n++) { + ret = write(ctx.evfd[n], &v, sizeof(v)); + ASSERT_EQ(ret, sizeof(v)); + } + + /* Busy loop for 1s and wait for all waiters to wake up */ + ms = msecs(); + while (count_waiters(&ctx) && msecs() < ms + 1000) + ; + + ASSERT_EQ(count_waiters(&ctx), 0); + } + ctx.stopped = 1; + /* Stop waiters */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ret = pthread_kill(waiters[i], SIGUSR1); + for (i = 0; i < ARRAY_SIZE(waiters); i++) + pthread_join(waiters[i], NULL); + + for (i = 0; i < ARRAY_SIZE(waiters); i++) + close(ctx.evfd[i]); + close(ctx.epfd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 063ecb290a5a..a4605b5ee66d 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -17,6 +17,7 @@ echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" echo " --fail-unsupported Treat UNSUPPORTED as a failure" +echo " --fail-unresolved Treat UNRESOLVED as a failure" echo " -d|--debug Debug mode (trace all shell commands)" echo " -l|--logdir <dir> Save logs on the <dir>" echo " If <dir> is -, all logs output in console only" @@ -29,8 +30,25 @@ err_ret=1 # kselftest skip code is 4 err_skip=4 +# cgroup RT scheduling prevents chrt commands from succeeding, which +# induces failures in test wakeup tests. Disable for the duration of +# the tests. + +readonly sched_rt_runtime=/proc/sys/kernel/sched_rt_runtime_us + +sched_rt_runtime_orig=$(cat $sched_rt_runtime) + +setup() { + echo -1 > $sched_rt_runtime +} + +cleanup() { + echo $sched_rt_runtime_orig > $sched_rt_runtime +} + errexit() { # message echo "Error: $1" 1>&2 + cleanup exit $err_ret } @@ -39,6 +57,8 @@ if [ `id -u` -ne 0 ]; then errexit "this must be run by root user" fi +setup + # Utilities absdir() { # file_path (cd `dirname $1`; pwd) @@ -93,6 +113,10 @@ parse_opts() { # opts UNSUPPORTED_RESULT=1 shift 1 ;; + --fail-unresolved) + UNRESOLVED_RESULT=1 + shift 1 + ;; --logdir|-l) LOG_DIR=$2 shift 2 @@ -157,6 +181,7 @@ KEEP_LOG=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 +UNRESOLVED_RESULT=0 STOP_FAILURE=0 # Parse command-line options parse_opts $* @@ -235,6 +260,7 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 + testcase() { # testfile CASENO=$((CASENO+1)) desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:` @@ -260,7 +286,7 @@ eval_result() { # sigval $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" - return 1 # this is a kind of bug.. something happened. + return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" @@ -273,7 +299,7 @@ eval_result() { # sigval return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) - prlog " [${color_red}XFAIL${color_reset}]" + prlog " [${color_green}XFAIL${color_reset}]" XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; @@ -406,5 +432,7 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +cleanup + # if no error, return 0 exit $TOTAL_RESULT diff --git a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc index cbd174334a48..2b82c80edf69 100644 --- a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc +++ b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc @@ -17,7 +17,14 @@ unsup() { #msg exit_unsupported } -modprobe $MOD || unsup "$MOD module not available" +unres() { #msg + reset_tracer + rmmod $MOD || true + echo $1 + exit_unresolved +} + +modprobe $MOD || unres "$MOD module not available" rmmod $MOD grep -q "preemptoff" available_tracers || unsup "preemptoff tracer not enabled" diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 712a2ddd2a27..b728c0a0f9b2 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -5,8 +5,34 @@ all: top_srcdir = ../../../.. KSFT_KHDR_INSTALL := 1 + +# For cross-builds to work, UNAME_M has to map to ARCH and arch specific +# directories and targets in this Makefile. "uname -m" doesn't map to +# arch specific sub-directory names. +# +# UNAME_M variable to used to run the compiles pointing to the right arch +# directories and build the right targets for these supported architectures. +# +# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable. +# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable. +# +# x86_64 targets are named to include x86_64 as a suffix and directories +# for includes are in x86_64 sub-directory. s390x and aarch64 follow the +# same convention. "uname -m" doesn't result in the correct mapping for +# s390x and aarch64. +# +# No change necessary for x86_64 UNAME_M := $(shell uname -m) +# Set UNAME_M for arm64 compile/install to work +ifeq ($(ARCH),arm64) + UNAME_M := aarch64 +endif +# Set UNAME_M s390x compile/install to work +ifeq ($(ARCH),s390) + UNAME_M := s390x +endif + LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c @@ -53,7 +79,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ @@ -84,6 +110,7 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ +x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h index d8f4d6bfe05d..a034438b6266 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -219,8 +219,8 @@ struct hv_enlightened_vmcs { #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) -struct hv_enlightened_vmcs *current_evmcs; -struct hv_vp_assist_page *current_vp_assist; +extern struct hv_enlightened_vmcs *current_evmcs; +extern struct hv_vp_assist_page *current_vp_assist; int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id); diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 6f17f69394be..4ae104f6ce69 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -17,6 +17,9 @@ bool enable_evmcs; +struct hv_enlightened_vmcs *current_evmcs; +struct hv_vp_assist_page *current_vp_assist; + struct eptPageTableEntry { uint64_t readable:1; uint64_t writable:1; diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index dadf819148a4..ee64ff8df8f4 100755 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -25,13 +25,13 @@ fi # Figure out which test to run from our script name. test=$(basename $0 .sh) # Look up details about the test from master list of LKDTM tests. -line=$(egrep '^#?'"$test"'\b' tests.txt) +line=$(grep -E '^#?'"$test"'\b' tests.txt) if [ -z "$line" ]; then echo "Skipped: missing test '$test' in tests.txt" exit $KSELFTEST_SKIP_TEST fi # Check that the test is known to LKDTM. -if ! egrep -q '^'"$test"'$' "$TRIGGER" ; then +if ! grep -E -q '^'"$test"'$' "$TRIGGER" ; then echo "Skipped: test '$test' missing in $TRIGGER!" exit $KSELFTEST_SKIP_TEST fi @@ -59,30 +59,32 @@ if [ -z "$expect" ]; then expect="call trace:" fi -# Clear out dmesg for output reporting -dmesg -c >/dev/null - # Prepare log for report checking -LOG=$(mktemp --tmpdir -t lkdtm-XXXXXX) +LOG=$(mktemp --tmpdir -t lkdtm-log-XXXXXX) +DMESG=$(mktemp --tmpdir -t lkdtm-dmesg-XXXXXX) cleanup() { - rm -f "$LOG" + rm -f "$LOG" "$DMESG" } trap cleanup EXIT +# Save existing dmesg so we can detect new content below +dmesg > "$DMESG" + # Most shells yell about signals and we're expecting the "cat" process # to usually be killed by the kernel. So we have to run it in a sub-shell # and silence errors. ($SHELL -c 'cat <(echo '"$test"') >'"$TRIGGER" 2>/dev/null) || true # Record and dump the results -dmesg -c >"$LOG" +dmesg | diff --changed-group-format='%>' --unchanged-group-format='' "$DMESG" - > "$LOG" || true + cat "$LOG" # Check for expected output -if egrep -qi "$expect" "$LOG" ; then +if grep -E -qi "$expect" "$LOG" ; then echo "$test: saw '$expect': ok" exit 0 else - if egrep -qi XFAIL: "$LOG" ; then + if grep -E -qi XFAIL: "$LOG" ; then echo "$test: saw 'XFAIL': [SKIP]" exit $KSELFTEST_SKIP_TEST else diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 35505b31e5cc..4555f88252ba 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -165,9 +165,10 @@ void *child_thread(void *arg) socklen_t zc_len = sizeof(zc); int res; + memset(&zc, 0, sizeof(zc)); zc.address = (__u64)((unsigned long)addr); zc.length = chunk_size; - zc.recv_skip_hint = 0; + res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, &zc, &zc_len); if (res == -1) @@ -281,12 +282,14 @@ static void setup_sockaddr(int domain, const char *str_addr, static void do_accept(int fdlisten) { pthread_attr_t attr; + int rcvlowat; pthread_attr_init(&attr); pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); + rcvlowat = chunk_size; if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT, - &chunk_size, sizeof(chunk_size)) == -1) { + &rcvlowat, sizeof(rcvlowat)) == -1) { perror("setsockopt SO_RCVLOWAT"); } diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/nsfs/pidns.c index e0d86e1668c0..e3c772c6a7c7 100644 --- a/tools/testing/selftests/nsfs/pidns.c +++ b/tools/testing/selftests/nsfs/pidns.c @@ -27,7 +27,7 @@ #define __stack_aligned__ __attribute__((aligned(16))) struct cr_clone_arg { char stack[128] __stack_aligned__; - char stack_ptr[0]; + char stack_ptr[]; }; static int child(void *args) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 936e1ca9410e..17a1f53ceba0 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -48,8 +48,11 @@ cleanup() { exec 2>/dev/null printf "$orig_message_cost" > /proc/sys/net/core/message_cost ip0 link del dev wg0 + ip0 link del dev wg1 ip1 link del dev wg0 + ip1 link del dev wg1 ip2 link del dev wg0 + ip2 link del dev wg1 local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" [[ -n $to_kill ]] && kill $to_kill pp ip netns del $netns1 @@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2 key1="$(pp wg genkey)" key2="$(pp wg genkey)" key3="$(pp wg genkey)" +key4="$(pp wg genkey)" pub1="$(pp wg pubkey <<<"$key1")" pub2="$(pp wg pubkey <<<"$key2")" pub3="$(pp wg pubkey <<<"$key3")" +pub4="$(pp wg pubkey <<<"$key4")" psk="$(pp wg genpsk)" [[ -n $key1 && -n $key2 && -n $psk ]] configure_peers() { ip1 addr add 192.168.241.1/24 dev wg0 - ip1 addr add fd00::1/24 dev wg0 + ip1 addr add fd00::1/112 dev wg0 ip2 addr add 192.168.241.2/24 dev wg0 - ip2 addr add fd00::2/24 dev wg0 + ip2 addr add fd00::2/112 dev wg0 n1 wg set wg0 \ private-key <(echo "$key1") \ @@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2 n1 wg set wg0 private-key <(echo "$key3") n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove n1 ping -W 1 -c 1 192.168.241.2 +n2 wg set wg0 peer "$pub3" remove + +# Test that we can route wg through wg +ip1 addr flush dev wg0 +ip2 addr flush dev wg0 +ip1 addr add fd00::5:1/112 dev wg0 +ip2 addr add fd00::5:2/112 dev wg0 +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2 +n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998 +ip1 link add wg1 type wireguard +ip2 link add wg1 type wireguard +ip1 addr add 192.168.241.1/24 dev wg1 +ip1 addr add fd00::1/112 dev wg1 +ip2 addr add 192.168.241.2/24 dev wg1 +ip2 addr add fd00::2/112 dev wg1 +ip1 link set mtu 1340 up dev wg1 +ip2 link set mtu 1340 up dev wg1 +n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5 +n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5 +tests +# Try to set up a routing loop between the two namespaces +ip1 link set netns $netns0 dev wg1 +ip0 addr add 192.168.241.1/24 dev wg1 +ip0 link set up dev wg1 +n0 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7 +ip2 link del wg0 +ip2 link del wg1 +! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel +ip0 link del wg1 ip1 link del wg0 -ip2 link del wg0 # Test using NAT. We now change the topology to this: # ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ @@ -282,6 +316,20 @@ pp sleep 3 n2 ping -W 1 -c 1 192.168.241.1 n1 wg set wg0 peer "$pub2" persistent-keepalive 0 +# Test that onion routing works, even when it loops +n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 +ip1 addr add 192.168.242.1/24 dev wg0 +ip2 link add wg1 type wireguard +ip2 addr add 192.168.242.2/24 dev wg1 +n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32 +ip2 link set wg1 up +n1 ping -W 1 -c 1 192.168.242.2 +ip2 link del wg1 +n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5 +! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel +n1 wg set wg0 peer "$pub3" remove +ip1 addr del 192.168.242.1/24 dev wg0 + # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. ip1 -6 addr add fc00::9/96 dev vethc ip1 -6 route add default via fc00::1 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config index 990c510a9cfa..f52f1e2bc7f6 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" CONFIG_SECTION_MISMATCH_WARN_ONLY=y CONFIG_FRAME_WARN=1280 +CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index 5909e7ef2a5c..9803dbb54181 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -25,7 +25,6 @@ CONFIG_KASAN=y CONFIG_KASAN_INLINE=y CONFIG_UBSAN=y CONFIG_UBSAN_SANITIZE_ALL=y -CONFIG_UBSAN_NO_ALIGNMENT=y CONFIG_UBSAN_NULL=y CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c index d31f267961e7..25c0e47d57cb 100644 --- a/virt/kvm/arm/hyp/aarch32.c +++ b/virt/kvm/arm/hyp/aarch32.c @@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) */ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { + u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; + pc += 2; else - *vcpu_pc(vcpu) += 4; + pc += 4; + + *vcpu_pc(vcpu) = pc; + kvm_adjust_itstate(vcpu); } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 14a162e295a9..ae364716ee40 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -186,6 +186,33 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET); } +static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) +{ + int i; + + /* + * Zero the input registers' upper 32 bits. They will be fully + * zeroed on exit, so we're fine changing them in place. + */ + for (i = 1; i < 4; i++) + vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i))); +} + +static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) +{ + switch(fn) { + case PSCI_0_2_FN64_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_ON: + case PSCI_0_2_FN64_AFFINITY_INFO: + /* Disallow these functions for 32bit guests */ + if (vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; + break; + } + + return 0; +} + static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; @@ -193,6 +220,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) unsigned long val; int ret = 1; + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) + goto out; + switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* @@ -210,12 +241,16 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) val = PSCI_RET_SUCCESS; break; case PSCI_0_2_FN_CPU_ON: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_CPU_ON: mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); mutex_unlock(&kvm->lock); break; case PSCI_0_2_FN_AFFINITY_INFO: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; @@ -256,6 +291,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } +out: smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } @@ -273,6 +309,10 @@ static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu) break; case PSCI_1_0_FN_PSCI_FEATURES: feature = smccc_get_arg1(vcpu); + val = kvm_psci_check_allowed_function(vcpu, feature); + if (val) + break; + switch(feature) { case PSCI_0_2_FN_PSCI_VERSION: case PSCI_0_2_FN_CPU_SUSPEND: diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index a963b9d766b7..32e32d67a127 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -294,8 +294,15 @@ int vgic_init(struct kvm *kvm) } } - if (vgic_has_its(kvm)) { + if (vgic_has_its(kvm)) vgic_lpi_translation_cache_init(kvm); + + /* + * If we have GICv4.1 enabled, unconditionnaly request enable the + * v4 support so that we get HW-accelerated vSGIs. Otherwise, only + * enable it if we present a virtual ITS to the guest. + */ + if (vgic_supports_direct_msis(kvm)) { ret = vgic_v4_init(kvm); if (ret) goto out; @@ -348,6 +355,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + /* + * Retire all pending LPIs on this vcpu anyway as we're + * going to destroy it. + */ + vgic_flush_pending_lpis(vcpu); + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); } @@ -359,10 +372,10 @@ static void __kvm_vgic_destroy(struct kvm *kvm) vgic_debug_destroy(kvm); - kvm_vgic_dist_destroy(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) kvm_vgic_vcpu_destroy(vcpu); + + kvm_vgic_dist_destroy(kvm); } void kvm_vgic_destroy(struct kvm *kvm) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index d53d34a33e35..c012a52b19f5 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -96,14 +96,21 @@ out_unlock: * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. + * + * Should any of these fail, behave as if we couldn't create the LPI + * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } return irq; } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index 5945f062d749..a016f07adc28 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -409,24 +409,28 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = { NULL, vgic_mmio_uaccess_write_v2_group, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, - vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_spending, + NULL, vgic_uaccess_write_spending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, - vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + NULL, vgic_uaccess_write_cpending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index e72dcc454247..89a14ec8b33b 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -50,7 +50,8 @@ bool vgic_has_its(struct kvm *kvm) bool vgic_supports_direct_msis(struct kvm *kvm) { - return kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm); + return (kvm_vgic_global_state.has_gicv4_1 || + (kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm))); } /* @@ -538,10 +539,12 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -553,11 +556,11 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, @@ -609,11 +612,13 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, vgic_mmio_read_group, vgic_mmio_write_group, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ISENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_senable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_cenable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -625,12 +630,12 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, vgic_mmio_read_priority, vgic_mmio_write_priority, 32, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 2199302597fa..b2d73fc0d1ef 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -184,6 +184,48 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, } } +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = false; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -219,17 +261,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) -{ - if (is_uaccess) - return; - - irq->pending_latch = true; - vgic_irq_set_phys_active(irq, true); -} - static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && @@ -240,7 +271,6 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -270,22 +300,48 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, continue; } + irq->pending_latch = true; if (irq->hw) - vgic_hw_irq_spending(vcpu, irq, is_uaccess); - else - irq->pending_latch = true; + vgic_irq_set_phys_active(irq, true); + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) { - if (is_uaccess) - return; + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + /* + * GICv2 SGIs are terribly broken. We can't restore + * the source of the interrupt, so just pick the vcpu + * itself as the source... + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source |= BIT(vcpu->vcpu_id); + + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) +{ irq->pending_latch = false; /* @@ -308,7 +364,6 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -339,7 +394,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } if (irq->hw) - vgic_hw_irq_cpending(vcpu, irq, is_uaccess); + vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; @@ -348,8 +403,68 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } } -unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + /* + * More fun with GICv2 SGIs! If we're clearing one of them + * from userspace, which source vcpu to clear? Let's not + * even think of it, and blow the whole set. + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source = 0; + + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* + * If we are fiddling with an IRQ's active state, we have to make sure the IRQ + * is not queued on some running VCPU's LRs, because then the change to the + * active state can be overwritten when the VCPU's state is synced coming back + * from the guest. + * + * For shared interrupts as well as GICv3 private interrupts, we have to + * stop all the VCPUs because interrupts can be migrated while we don't hold + * the IRQ locks and we don't want to be chasing moving targets. + * + * For GICv2 private interrupts we don't have to do anything because + * userspace accesses to the VGIC state already require all VCPUs to be + * stopped, and only the VCPU itself can modify its private interrupts + * active state, which guarantees that the VCPU is not running. + */ +static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_halt_guest(vcpu->kvm); +} + +/* See vgic_access_active_prepare */ +static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_resume_guest(vcpu->kvm); +} + +static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; @@ -359,6 +474,10 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + /* + * Even for HW interrupts, don't evaluate the HW state as + * all the guest is interested in is the virtual state. + */ if (irq->active) value |= (1U << i); @@ -368,6 +487,29 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, return value; } +unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 val; + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + val = __vgic_mmio_read_active(vcpu, addr, len); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); + + return val; +} + +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __vgic_mmio_read_active(vcpu, addr, len); +} + /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) @@ -426,36 +568,6 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } -/* - * If we are fiddling with an IRQ's active state, we have to make sure the IRQ - * is not queued on some running VCPU's LRs, because then the change to the - * active state can be overwritten when the VCPU's state is synced coming back - * from the guest. - * - * For shared interrupts, we have to stop all the VCPUs because interrupts can - * be migrated while we don't hold the IRQ locks and we don't want to be - * chasing moving targets. - * - * For private interrupts we don't have to do anything because userspace - * accesses to the VGIC state already require all VCPUs to be stopped, and - * only the VCPU itself can modify its private interrupts active state, which - * guarantees that the VCPU is not running. - */ -static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_halt_guest(vcpu->kvm); -} - -/* See vgic_change_active_prepare */ -static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_resume_guest(vcpu->kvm); -} - static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) @@ -477,11 +589,11 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } @@ -514,11 +626,11 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h index 5af2aefad435..fefcca2b14dc 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.h +++ b/virt/kvm/arm/vgic/vgic-mmio.h @@ -138,6 +138,14 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); @@ -149,9 +157,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); |