From da142f3d373a6ddaca0119615a8db2175ddc4121 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 5 Dec 2025 15:26:55 -0800 Subject: [PATCH 001/487] KVM: Remove subtle "struct kvm_stats_desc" pseudo-overlay Remove KVM's internal pseudo-overlay of kvm_stats_desc, which subtly aliases the flexible name[] in the uAPI definition with a fixed-size array of the same name. The unusual embedded structure results in compiler warnings due to -Wflex-array-member-not-at-end, and also necessitates an extra level of dereferencing in KVM. To avoid the "overlay", define the uAPI structure to have a fixed-size name when building for the kernel. Opportunistically clean up the indentation for the stats macros, and replace spaces with tabs. No functional change intended. Reported-by: Gustavo A. R. Silva Closes: https://lore.kernel.org/all/aPfNKRpLfhmhYqfP@kspp Acked-by: Marc Zyngier Acked-by: Christian Borntraeger [..] Acked-by: Anup Patel Reviewed-by: Bibo Mao Acked-by: Gustavo A. R. Silva Link: https://patch.msgid.link/20251205232655.445294-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/arm64/kvm/guest.c | 4 +- arch/loongarch/kvm/vcpu.c | 2 +- arch/loongarch/kvm/vm.c | 2 +- arch/mips/kvm/mips.c | 4 +- arch/powerpc/kvm/book3s.c | 4 +- arch/powerpc/kvm/booke.c | 4 +- arch/riscv/kvm/vcpu.c | 2 +- arch/riscv/kvm/vm.c | 2 +- arch/s390/kvm/kvm-s390.c | 4 +- arch/x86/kvm/x86.c | 4 +- include/linux/kvm_host.h | 83 +++++++++++++++++---------------------- include/uapi/linux/kvm.h | 8 ++++ virt/kvm/binary_stats.c | 2 +- virt/kvm/kvm_main.c | 20 +++++----- 14 files changed, 70 insertions(+), 75 deletions(-) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 1c87699fd886..332c453b87cf 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -29,7 +29,7 @@ #include "trace.h" -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; @@ -42,7 +42,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, hvc_exit_stat), STATS_DESC_COUNTER(VCPU, wfe_exit_stat), diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 656b954c1134..b3547bd41d21 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -14,7 +14,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, int_exits), STATS_DESC_COUNTER(VCPU, idle_exits), diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c index 194ccbcdc3b3..7deff56e0e1a 100644 --- a/arch/loongarch/kvm/vm.c +++ b/arch/loongarch/kvm/vm.c @@ -10,7 +10,7 @@ #include #include -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, pages), STATS_DESC_ICOUNTER(VM, hugepages), diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b0fb92fda4d4..23e69baad453 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -38,7 +38,7 @@ #define VECTORSPACING 0x100 /* for EI/VI mode */ #endif -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; @@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, wait_exits), STATS_DESC_COUNTER(VCPU, cache_exits), diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d79c5d1098c0..2efbe05caed7 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -38,7 +38,7 @@ /* #define EXIT_DEBUG */ -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -53,7 +53,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 3401b96be475..f3ddb24ece74 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -36,7 +36,7 @@ unsigned long kvmppc_booke_handlers; -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index a55a95da54d0..fdd99ac1e714 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -24,7 +24,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, ecall_exit_stat), STATS_DESC_COUNTER(VCPU, wfi_exit_stat), diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 66d91ae6e9b2..715a06ae8c13 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -13,7 +13,7 @@ #include #include -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 56a50524b3ee..495141bf0398 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -64,7 +64,7 @@ #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ (KVM_MAX_VCPUS + LOCAL_IRQS)) -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, inject_io), STATS_DESC_COUNTER(VM, inject_float_mchk), @@ -90,7 +90,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, exit_userspace), STATS_DESC_COUNTER(VCPU, exit_null), diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ff8812f3a129..69e0a033e4ac 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -237,7 +237,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv); bool __read_mostly enable_device_posted_irqs = true; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_device_posted_irqs); -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, mmu_shadow_zapped), STATS_DESC_COUNTER(VM, mmu_pte_write), @@ -263,7 +263,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, pf_taken), STATS_DESC_COUNTER(VCPU, pf_fixed), diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d93f75b05ae2..7428d9949382 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1927,56 +1927,43 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - const struct _kvm_stats_desc *desc; + const struct kvm_stats_desc *desc; enum kvm_stat_kind kind; }; -struct _kvm_stats_desc { - struct kvm_stats_desc desc; - char name[KVM_STATS_NAME_SIZE]; -}; - -#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ - .flags = type | unit | base | \ - BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ - BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ - BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ - .exponent = exp, \ - .size = sz, \ +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = sz, \ .bucket_size = bsz -#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, stat) \ - }, \ - .name = #stat, \ - } +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat), \ + .name = #stat, \ +} +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat), \ + .name = #stat, \ +} +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, stat), \ + .name = #stat, \ +} +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, stat), \ + .name = #stat, \ +} /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) @@ -2053,7 +2040,7 @@ struct _kvm_stats_desc { STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, - const struct _kvm_stats_desc *desc, + const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); @@ -2098,9 +2085,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) extern const struct kvm_stats_header kvm_vm_stats_header; -extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; -extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; +extern const struct kvm_stats_desc kvm_vcpu_stats_desc[]; #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dddb781b0507..76bd54848b11 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -14,6 +14,10 @@ #include #include +#ifdef __KERNEL__ +#include +#endif + #define KVM_API_VERSION 12 /* @@ -1579,7 +1583,11 @@ struct kvm_stats_desc { __u16 size; __u32 offset; __u32 bucket_size; +#ifdef __KERNEL__ + char name[KVM_STATS_NAME_SIZE]; +#else char name[]; +#endif }; #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c index eefca6c69f51..76ce697c773b 100644 --- a/virt/kvm/binary_stats.c +++ b/virt/kvm/binary_stats.c @@ -50,7 +50,7 @@ * Return: the number of bytes that has been successfully read */ ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, - const struct _kvm_stats_desc *desc, + const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5b5b69c97665..cf65fd82d36d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -983,9 +983,9 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) kvm_free_memslot(kvm, memslot); } -static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) +static umode_t kvm_stats_debugfs_mode(const struct kvm_stats_desc *desc) { - switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { + switch (desc->flags & KVM_STATS_TYPE_MASK) { case KVM_STATS_TYPE_INSTANT: return 0444; case KVM_STATS_TYPE_CUMULATIVE: @@ -1020,7 +1020,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) struct dentry *dent; char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; - const struct _kvm_stats_desc *pdesc; + const struct kvm_stats_desc *pdesc; int i, ret = -ENOMEM; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; @@ -6186,11 +6186,11 @@ static int kvm_stat_data_get(void *data, u64 *val) switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_get_stat_per_vm(stat_data->kvm, - stat_data->desc->desc.offset, val); + stat_data->desc->offset, val); break; case KVM_STAT_VCPU: r = kvm_get_stat_per_vcpu(stat_data->kvm, - stat_data->desc->desc.offset, val); + stat_data->desc->offset, val); break; } @@ -6208,11 +6208,11 @@ static int kvm_stat_data_clear(void *data, u64 val) switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_clear_stat_per_vm(stat_data->kvm, - stat_data->desc->desc.offset); + stat_data->desc->offset); break; case KVM_STAT_VCPU: r = kvm_clear_stat_per_vcpu(stat_data->kvm, - stat_data->desc->desc.offset); + stat_data->desc->offset); break; } @@ -6360,7 +6360,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) static void kvm_init_debug(void) { const struct file_operations *fops; - const struct _kvm_stats_desc *pdesc; + const struct kvm_stats_desc *pdesc; int i; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); @@ -6373,7 +6373,7 @@ static void kvm_init_debug(void) fops = &vm_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, - (void *)(long)pdesc->desc.offset, fops); + (void *)(long)pdesc->offset, fops); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { @@ -6384,7 +6384,7 @@ static void kvm_init_debug(void) fops = &vcpu_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, - (void *)(long)pdesc->desc.offset, fops); + (void *)(long)pdesc->offset, fops); } } From c9f3a593137d862d424130343e77d4b5260a4f5a Mon Sep 17 00:00:00 2001 From: Jean-Baptiste Maneyrol Date: Fri, 30 Jan 2026 16:38:47 +0100 Subject: [PATCH 002/487] iio: imu: inv_icm42600: fix odr switch to the same value ODR switch is done in 2 steps when FIFO is on : change the ODR register value and acknowledge change when reading the FIFO ODR change flag. When we are switching to the same odr value, we end up waiting for a FIFO ODR flag that is never happening. Fix the issue by doing nothing and exiting properly when we are switching to the same ODR value. Fixes: ec74ae9fd37c ("iio: imu: inv_icm42600: add accurate timestamping") Signed-off-by: Jean-Baptiste Maneyrol Cc: stable@vger.kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c | 2 ++ drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c index 54760d8f92a2..0ab6eddf0543 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c @@ -651,6 +651,8 @@ static int inv_icm42600_accel_write_odr(struct iio_dev *indio_dev, return -EINVAL; conf.odr = inv_icm42600_accel_odr_conv[idx / 2]; + if (conf.odr == st->conf.accel.odr) + return 0; pm_runtime_get_sync(dev); mutex_lock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c index 7ef0a25ec74f..11339ddf1da3 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c @@ -358,6 +358,8 @@ static int inv_icm42600_gyro_write_odr(struct iio_dev *indio_dev, return -EINVAL; conf.odr = inv_icm42600_gyro_odr_conv[idx / 2]; + if (conf.odr == st->conf.gyro.odr) + return 0; pm_runtime_get_sync(dev); mutex_lock(&st->lock); From ffd32db8263d2d785a2c419486a450dc80693235 Mon Sep 17 00:00:00 2001 From: Jean-Baptiste Maneyrol Date: Fri, 30 Jan 2026 17:10:23 +0100 Subject: [PATCH 003/487] iio: imu: inv_icm42600: fix odr switch when turning buffer off ODR switch is done in 2 steps when FIFO is on : change the ODR register value and acknowledge change when reading the FIFO ODR change flag. When we are switching odr and turning buffer off just afterward, we are losing the FIFO ODR change flag and ODR switch is blocked. Fix the issue by force applying any waiting ODR change when turning buffer off. Fixes: ec74ae9fd37c ("iio: imu: inv_icm42600: add accurate timestamping") Signed-off-by: Jean-Baptiste Maneyrol Cc: stable@vger.kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index ada968be954d..68a395758031 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -371,6 +371,8 @@ static int inv_icm42600_buffer_predisable(struct iio_dev *indio_dev) static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) { struct inv_icm42600_state *st = iio_device_get_drvdata(indio_dev); + struct inv_icm42600_sensor_state *sensor_st = iio_priv(indio_dev); + struct inv_sensors_timestamp *ts = &sensor_st->ts; struct device *dev = regmap_get_device(st->map); unsigned int sensor; unsigned int *watermark; @@ -392,6 +394,8 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) mutex_lock(&st->lock); + inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); + ret = inv_icm42600_buffer_set_fifo_en(st, st->fifo.en & ~sensor); if (ret) goto out_unlock; From dd72e6c3cdea05cad24e99710939086f7a113fb5 Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Fri, 30 Jan 2026 13:30:20 +0200 Subject: [PATCH 004/487] iio: light: bh1780: fix PM runtime leak on error path Move pm_runtime_put_autosuspend() before the error check to ensure the PM runtime reference count is always decremented after pm_runtime_get_sync(), regardless of whether the read operation succeeds or fails. Fixes: 1f0477f18306 ("iio: light: new driver for the ROHM BH1780") Signed-off-by: Antoniu Miclaus Reviewed-by: Linus Walleij Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/light/bh1780.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/light/bh1780.c b/drivers/iio/light/bh1780.c index 5d3c6d5276ba..a740d1f992a8 100644 --- a/drivers/iio/light/bh1780.c +++ b/drivers/iio/light/bh1780.c @@ -109,9 +109,9 @@ static int bh1780_read_raw(struct iio_dev *indio_dev, case IIO_LIGHT: pm_runtime_get_sync(&bh1780->client->dev); value = bh1780_read_word(bh1780, BH1780_REG_DLOW); + pm_runtime_put_autosuspend(&bh1780->client->dev); if (value < 0) return value; - pm_runtime_put_autosuspend(&bh1780->client->dev); *val = value; return IIO_VAL_INT; From 6c8bf4b604a8a6346ca71f1c027fa01c2c2e04cb Mon Sep 17 00:00:00 2001 From: SeungJu Cheon Date: Sat, 24 Jan 2026 04:47:58 +0900 Subject: [PATCH 005/487] iio: frequency: adf4377: Fix duplicated soft reset mask The regmap_read_poll_timeout() uses ADF4377_0000_SOFT_RESET_R_MSK twice instead of checking both SOFT_RESET_MSK (bit 0) and SOFT_RESET_R_MSK (bit 7). This causes an incomplete reset status check. The code first sets both SOFT_RESET and SOFT_RESET_R bits to 1 via regmap_update_bits(), then polls for them to be cleared. Since we set both bits before polling, we should be waiting for both to clear. Fix by using both masks as done in regmap_update_bits() above. Fixes: eda549e2e524 ("iio: frequency: adf4377: add support for ADF4377") Signed-off-by: SeungJu Cheon Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/frequency/adf4377.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c index fa686f785fa4..8e2da218d48a 100644 --- a/drivers/iio/frequency/adf4377.c +++ b/drivers/iio/frequency/adf4377.c @@ -508,7 +508,7 @@ static int adf4377_soft_reset(struct adf4377_state *st) return ret; return regmap_read_poll_timeout(st->regmap, 0x0, read_val, - !(read_val & (ADF4377_0000_SOFT_RESET_R_MSK | + !(read_val & (ADF4377_0000_SOFT_RESET_MSK | ADF4377_0000_SOFT_RESET_R_MSK)), 200, 200 * 100); } From d23d763e00ace4e9c59f8d33e0713d401133ba88 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Wed, 31 Dec 2025 22:14:16 +0100 Subject: [PATCH 006/487] iio: imu: inv-mpu9150: fix irq ack preventing irq storms IRQ needs to be acked. for some odd reasons, reading from irq status does not reliable help, enable acking from any register to be on the safe side and read the irq status register. Comments in the code indicate a known unreliability with that register. The blamed commit was tested with mpu6050 in lg,p895 and lg,p880 according to Tested-bys. But with the MPU9150 in the Epson Moverio BT-200 this leads to irq storms without properly acking the irq. Fixes: 0a3b517c8089 ("iio: imu: inv_mpu6050: fix interrupt status read for old buggy chips") Signed-off-by: Andreas Kemnade Acked-by: Jean-Baptiste Maneyrol Signed-off-by: Jonathan Cameron --- drivers/iio/imu/inv_mpu6050/inv_mpu_core.c | 8 ++++++++ drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h | 2 ++ drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c | 5 ++++- 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index b2fa1f4957a5..5796896d54cd 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -1943,6 +1943,14 @@ int inv_mpu_core_probe(struct regmap *regmap, int irq, const char *name, irq_type); return -EINVAL; } + + /* + * Acking interrupts by status register does not work reliably + * but seem to work when this bit is set. + */ + if (st->chip_type == INV_MPU9150) + st->irq_mask |= INV_MPU6050_INT_RD_CLEAR; + device_set_wakeup_capable(dev, true); st->vdd_supply = devm_regulator_get(dev, "vdd"); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h index 211901f8b8eb..6239b1a803f7 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h @@ -390,6 +390,8 @@ struct inv_mpu6050_state { /* enable level triggering */ #define INV_MPU6050_LATCH_INT_EN 0x20 #define INV_MPU6050_BIT_BYPASS_EN 0x2 +/* allow acking interrupts by any register read */ +#define INV_MPU6050_INT_RD_CLEAR 0x10 /* Allowed timestamp period jitter in percent */ #define INV_MPU6050_TS_PERIOD_JITTER 4 diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 10a473342075..22c1ce66f99e 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -248,7 +248,6 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p) switch (st->chip_type) { case INV_MPU6000: case INV_MPU6050: - case INV_MPU9150: /* * WoM is not supported and interrupt status read seems to be broken for * some chips. Since data ready is the only interrupt, bypass interrupt @@ -257,6 +256,10 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p) wom_bits = 0; int_status = INV_MPU6050_BIT_RAW_DATA_RDY_INT; goto data_ready_interrupt; + case INV_MPU9150: + /* IRQ needs to be acked */ + wom_bits = 0; + break; case INV_MPU6500: case INV_MPU6515: case INV_MPU6880: From 85e4614524dca6c0a43874f475a17de2b9725648 Mon Sep 17 00:00:00 2001 From: Lukas Schmid Date: Mon, 2 Feb 2026 21:15:35 +0100 Subject: [PATCH 007/487] iio: potentiometer: mcp4131: fix double application of wiper shift The MCP4131 wiper address is shifted twice when preparing the SPI command in mcp4131_write_raw(). The address is already shifted when assigned to the local variable "address", but is then shifted again when written to data->buf[0]. This results in an incorrect command being sent to the device and breaks wiper writes to the second channel. Remove the second shift and use the pre-shifted address directly when composing the SPI transfer. Fixes: 22d199a53910 ("iio: potentiometer: add driver for Microchip MCP413X/414X/415X/416X/423X/424X/425X/426X") Signed-off-by: Lukas Schmid # Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/potentiometer/mcp4131.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/potentiometer/mcp4131.c b/drivers/iio/potentiometer/mcp4131.c index ad082827aad5..56c9111ef5e8 100644 --- a/drivers/iio/potentiometer/mcp4131.c +++ b/drivers/iio/potentiometer/mcp4131.c @@ -221,7 +221,7 @@ static int mcp4131_write_raw(struct iio_dev *indio_dev, mutex_lock(&data->lock); - data->buf[0] = address << MCP4131_WIPER_SHIFT; + data->buf[0] = address; data->buf[0] |= MCP4131_WRITE | (val >> 8); data->buf[1] = val & 0xFF; /* 8 bits here */ From 7ef74d961d1ad6ec72b50887ca119d7f98f07717 Mon Sep 17 00:00:00 2001 From: Jean-Baptiste Maneyrol Date: Thu, 5 Feb 2026 17:59:14 +0100 Subject: [PATCH 008/487] iio: imu: inv_icm45600: fix INT1 drive bit inverted Drive bit must be set for open-drain mode and be cleared for push-pull mode. Referring to datasheet DS-000576_ICM-45605.pdf section 17.23 INT1_CONFIG2. Fixes: 06674a72cf7a ("iio: imu: inv_icm45600: add buffer support in iio devices") Signed-off-by: Jean-Baptiste Maneyrol Reviewed-by: Andy Shevchenko Cc: stable@vger.kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/inv_icm45600/inv_icm45600.h | 2 +- drivers/iio/imu/inv_icm45600/inv_icm45600_core.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600.h b/drivers/iio/imu/inv_icm45600/inv_icm45600.h index c5b5446f6c3b..1c796d4b2a40 100644 --- a/drivers/iio/imu/inv_icm45600/inv_icm45600.h +++ b/drivers/iio/imu/inv_icm45600/inv_icm45600.h @@ -205,7 +205,7 @@ struct inv_icm45600_sensor_state { #define INV_ICM45600_SPI_SLEW_RATE_38NS 0 #define INV_ICM45600_REG_INT1_CONFIG2 0x0018 -#define INV_ICM45600_INT1_CONFIG2_PUSH_PULL BIT(2) +#define INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN BIT(2) #define INV_ICM45600_INT1_CONFIG2_LATCHED BIT(1) #define INV_ICM45600_INT1_CONFIG2_ACTIVE_HIGH BIT(0) #define INV_ICM45600_INT1_CONFIG2_ACTIVE_LOW 0x00 diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c index 25bd9757a594..e4638926a10c 100644 --- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c +++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c @@ -637,8 +637,8 @@ static int inv_icm45600_irq_init(struct inv_icm45600_state *st, int irq, break; } - if (!open_drain) - val |= INV_ICM45600_INT1_CONFIG2_PUSH_PULL; + if (open_drain) + val |= INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN; ret = regmap_write(st->map, INV_ICM45600_REG_INT1_CONFIG2, val); if (ret) From 5187e03b817c26c1c3bcb2645a612ea935c4be89 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 4 Feb 2026 15:00:33 +0100 Subject: [PATCH 009/487] iio: dac: ds4424: reject -128 RAW value The DS442x DAC uses sign-magnitude encoding, so -128 cannot be represented in hardware (7-bit magnitude). Previously, passing -128 resulted in a truncated value that programmed 0mA (magnitude 0) instead of the expected maximum negative current, effectively failing silently. Reject -128 to avoid producing the wrong current. Fixes: d632a2bd8ffc ("iio: dac: ds4422/ds4424 dac driver") Cc: stable@vger.kernel.org Signed-off-by: Oleksij Rempel Reviewed-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- drivers/iio/dac/ds4424.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/dac/ds4424.c b/drivers/iio/dac/ds4424.c index 6dda8918975a..c61868f2de31 100644 --- a/drivers/iio/dac/ds4424.c +++ b/drivers/iio/dac/ds4424.c @@ -140,7 +140,7 @@ static int ds4424_write_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: - if (val < S8_MIN || val > S8_MAX) + if (val <= S8_MIN || val > S8_MAX) return -EINVAL; if (val > 0) { From f55b9510cd9437da3a0efa08b089caeb47595ff1 Mon Sep 17 00:00:00 2001 From: Chris Spencer Date: Thu, 5 Feb 2026 14:55:45 +0000 Subject: [PATCH 010/487] iio: chemical: bme680: Fix measurement wait duration calculation This function refers to the Bosch BME680 API as the source of the calculation, but one of the constants does not match the Bosch implementation. This appears to be a simple transposition of two digits, resulting in a wait time that is too short. This can cause the following 'device measurement cycle incomplete' check to occasionally fail, returning EBUSY to user space. Adjust the constant to match the Bosch implementation and resolve the EBUSY errors. Fixes: 4241665e6ea0 ("iio: chemical: bme680: Fix sensor data read operation") Link: https://github.com/boschsensortec/BME68x_SensorAPI/blob/v4.4.8/bme68x.c#L521 Signed-off-by: Chris Spencer Acked-by: Vasileios Amoiridis Cc: stable@vger.kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/bme680_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c index 70f81c4a96ba..24e0b59e2fdf 100644 --- a/drivers/iio/chemical/bme680_core.c +++ b/drivers/iio/chemical/bme680_core.c @@ -613,7 +613,7 @@ static int bme680_wait_for_eoc(struct bme680_data *data) * + heater duration */ int wait_eoc_us = ((data->oversampling_temp + data->oversampling_press + - data->oversampling_humid) * 1936) + (477 * 4) + + data->oversampling_humid) * 1963) + (477 * 4) + (477 * 5) + 1000 + (data->heater_dur * 1000); fsleep(wait_eoc_us); From 585b90c0161ab77416fe3acdbdc55b978e33e16c Mon Sep 17 00:00:00 2001 From: Yasin Lee Date: Fri, 13 Feb 2026 23:14:43 +0800 Subject: [PATCH 011/487] iio: proximity: hx9023s: fix assignment order for __counted_by Initialize fw_size before copying firmware data into the flexible array member to match the __counted_by() annotation. This fixes the incorrect assignment order that triggers runtime safety checks. Fixes: e9ed97be4fcc ("iio: proximity: hx9023s: Added firmware file parsing functionality") Signed-off-by: Yasin Lee Reviewed-by: Andy Shevchenko Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/proximity/hx9023s.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c index 2918dfc0df54..ad839db6b326 100644 --- a/drivers/iio/proximity/hx9023s.c +++ b/drivers/iio/proximity/hx9023s.c @@ -1034,9 +1034,8 @@ static int hx9023s_send_cfg(const struct firmware *fw, struct hx9023s_data *data if (!bin) return -ENOMEM; - memcpy(bin->data, fw->data, fw->size); - bin->fw_size = fw->size; + memcpy(bin->data, fw->data, bin->fw_size); bin->fw_ver = bin->data[FW_VER_OFFSET]; bin->reg_count = get_unaligned_le16(bin->data + FW_REG_CNT_OFFSET); From a318cfc0853706f1d6ce682dba660bc455d674ef Mon Sep 17 00:00:00 2001 From: Yasin Lee Date: Fri, 13 Feb 2026 23:14:44 +0800 Subject: [PATCH 012/487] iio: proximity: hx9023s: Protect against division by zero in set_samp_freq Avoid division by zero when sampling frequency is unspecified. Fixes: 60df548277b7 ("iio: proximity: Add driver support for TYHX's HX9023S capacitive proximity sensor") Signed-off-by: Yasin Lee Reviewed-by: Andy Shevchenko Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/proximity/hx9023s.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c index ad839db6b326..17e00ee2b6f8 100644 --- a/drivers/iio/proximity/hx9023s.c +++ b/drivers/iio/proximity/hx9023s.c @@ -719,6 +719,9 @@ static int hx9023s_set_samp_freq(struct hx9023s_data *data, int val, int val2) struct device *dev = regmap_get_device(data->regmap); unsigned int i, period_ms; + if (!val && !val2) + return -EINVAL; + period_ms = div_u64(NANO, (val * MEGA + val2)); for (i = 0; i < ARRAY_SIZE(hx9023s_samp_freq_table); i++) { From 82ee91d6b15f06b6094eea2c26afe0032fe8e177 Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Tue, 10 Feb 2026 18:49:50 +0200 Subject: [PATCH 013/487] iio: magnetometer: tlv493d: remove erroneous shift in X-axis data TLV493D_BX2_MAG_X_AXIS_LSB is defined as GENMASK(7, 4). FIELD_GET() already right-shifts bits [7:4] to [3:0], so the additional >> 4 discards most of the X-axis low nibble. The Y and Z axes correctly omit this extra shift. Remove it. Fixes: 106511d280c7 ("iio: magnetometer: add support for Infineon TLV493D 3D Magentic sensor") Signed-off-by: Antoniu Miclaus Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/magnetometer/tlv493d.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/magnetometer/tlv493d.c b/drivers/iio/magnetometer/tlv493d.c index ec53fd40277b..e5e050af2b74 100644 --- a/drivers/iio/magnetometer/tlv493d.c +++ b/drivers/iio/magnetometer/tlv493d.c @@ -171,7 +171,7 @@ static s16 tlv493d_get_channel_data(u8 *b, enum tlv493d_channels ch) switch (ch) { case TLV493D_AXIS_X: val = FIELD_GET(TLV493D_BX_MAG_X_AXIS_MSB, b[TLV493D_RD_REG_BX]) << 4 | - FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]) >> 4; + FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]); break; case TLV493D_AXIS_Y: val = FIELD_GET(TLV493D_BY_MAG_Y_AXIS_MSB, b[TLV493D_RD_REG_BY]) << 4 | From 216345f98cae7fcc84f49728c67478ac00321c87 Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Thu, 12 Feb 2026 14:46:07 +0200 Subject: [PATCH 014/487] iio: chemical: sps30_i2c: fix buffer size in sps30_i2c_read_meas() sizeof(num) evaluates to sizeof(size_t) (8 bytes on 64-bit) instead of the intended __be32 element size (4 bytes). Use sizeof(*meas) to correctly match the buffer element type. Fixes: 8f3f13085278 ("iio: sps30: separate core and interface specific code") Signed-off-by: Antoniu Miclaus Acked-by: Tomasz Duszynski Reviewed-by: Andy Shevchenko Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/sps30_i2c.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/chemical/sps30_i2c.c b/drivers/iio/chemical/sps30_i2c.c index f692c089d17b..c92f04990c34 100644 --- a/drivers/iio/chemical/sps30_i2c.c +++ b/drivers/iio/chemical/sps30_i2c.c @@ -171,7 +171,7 @@ static int sps30_i2c_read_meas(struct sps30_state *state, __be32 *meas, size_t n if (!sps30_i2c_meas_ready(state)) return -ETIMEDOUT; - return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(num) * num); + return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(*meas) * num); } static int sps30_i2c_clean_fan(struct sps30_state *state) From c3914ce1963c4db25e186112c90fa5d2361e9e0a Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Thu, 12 Feb 2026 14:46:08 +0200 Subject: [PATCH 015/487] iio: chemical: sps30_serial: fix buffer size in sps30_serial_read_meas() sizeof(num) evaluates to sizeof(size_t) which is 8 bytes on 64-bit, but the buffer elements are only 4 bytes. The same function already uses sizeof(*meas) on line 312, making the mismatch evident. Use sizeof(*meas) consistently. Fixes: b2e171f5a5c6 ("iio: sps30: add support for serial interface") Signed-off-by: Antoniu Miclaus Acked-by: Tomasz Duszynski Reviewed-by: Andy Shevchenko Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/sps30_serial.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/chemical/sps30_serial.c b/drivers/iio/chemical/sps30_serial.c index 008bc88590f3..a5e6bc08d5fd 100644 --- a/drivers/iio/chemical/sps30_serial.c +++ b/drivers/iio/chemical/sps30_serial.c @@ -303,7 +303,7 @@ static int sps30_serial_read_meas(struct sps30_state *state, __be32 *meas, size_ if (msleep_interruptible(1000)) return -EINTR; - ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(num)); + ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(*meas)); if (ret < 0) return ret; /* if measurements aren't ready sensor returns empty frame */ From dd6183e42719cc54057579b8e6be5348cecfeda7 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Sat, 14 Feb 2026 12:46:37 -0600 Subject: [PATCH 016/487] iio: adc: ad7768-1: Fix ERR_PTR dereference in ad7768_fill_scale_tbl The function iio_get_current_scan_type() can return an error pointer, the return value scan_type is not checked for this and immediately dereferenced which can cause a kernel panic. Add check for IS_ERR() and propagate the error back. Fixes: ff085189cb17 ("iio: adc: ad7768-1: add support for ADAQ776x-1 ADC Family") Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202602051234.5gArzLyZ-lkp@intel.com/ Signed-off-by: Ethan Tidmore Reviewed-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad7768-1.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index fcd8aea7152e..e16dede687d3 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -531,7 +531,7 @@ static int ad7768_reg_access(struct iio_dev *indio_dev, return ret; } -static void ad7768_fill_scale_tbl(struct iio_dev *dev) +static int ad7768_fill_scale_tbl(struct iio_dev *dev) { struct ad7768_state *st = iio_priv(dev); const struct iio_scan_type *scan_type; @@ -541,6 +541,11 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev) u64 tmp2; scan_type = iio_get_current_scan_type(dev, &dev->channels[0]); + if (IS_ERR(scan_type)) { + dev_err(&st->spi->dev, "Failed to get scan type.\n"); + return PTR_ERR(scan_type); + } + if (scan_type->sign == 's') val2 = scan_type->realbits - 1; else @@ -565,6 +570,8 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev) st->scale_tbl[i][0] = tmp0; /* Integer part */ st->scale_tbl[i][1] = abs(tmp1); /* Fractional part */ } + + return 0; } static int ad7768_set_sinc3_dec_rate(struct ad7768_state *st, @@ -669,7 +676,9 @@ static int ad7768_configure_dig_fil(struct iio_dev *dev, } /* Update scale table: scale values vary according to the precision */ - ad7768_fill_scale_tbl(dev); + ret = ad7768_fill_scale_tbl(dev); + if (ret) + return ret; ad7768_fill_samp_freq_tbl(st); From 91f950b4cbb1aa9ea4eb3999f1463e8044b717fb Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Mon, 16 Feb 2026 11:57:55 +0200 Subject: [PATCH 017/487] iio: gyro: mpu3050-i2c: fix pm_runtime error handling The return value of pm_runtime_get_sync() is not checked, and the function always returns success. This allows I2C mux operations to proceed even when the device fails to resume. Use pm_runtime_resume_and_get() and propagate its return value to properly handle resume failures. Fixes: 3904b28efb2c ("iio: gyro: Add driver for the MPU-3050 gyroscope") Signed-off-by: Antoniu Miclaus Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/gyro/mpu3050-i2c.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/iio/gyro/mpu3050-i2c.c b/drivers/iio/gyro/mpu3050-i2c.c index 092878f2c886..6549b22e643d 100644 --- a/drivers/iio/gyro/mpu3050-i2c.c +++ b/drivers/iio/gyro/mpu3050-i2c.c @@ -19,8 +19,7 @@ static int mpu3050_i2c_bypass_select(struct i2c_mux_core *mux, u32 chan_id) struct mpu3050 *mpu3050 = i2c_mux_priv(mux); /* Just power up the device, that is all that is needed */ - pm_runtime_get_sync(mpu3050->dev); - return 0; + return pm_runtime_resume_and_get(mpu3050->dev); } static int mpu3050_i2c_bypass_deselect(struct i2c_mux_core *mux, u32 chan_id) From acc3949aab3e8094641a9c7c2768de1958c88378 Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Mon, 16 Feb 2026 11:57:56 +0200 Subject: [PATCH 018/487] iio: gyro: mpu3050-core: fix pm_runtime error handling The return value of pm_runtime_get_sync() is not checked, allowing the driver to access hardware that may fail to resume. The device usage count is also unconditionally incremented. Use pm_runtime_resume_and_get() which propagates errors and avoids incrementing the usage count on failure. In preenable, add pm_runtime_put_autosuspend() on set_8khz_samplerate() failure since postdisable does not run when preenable fails. Fixes: 3904b28efb2c ("iio: gyro: Add driver for the MPU-3050 gyroscope") Reviewed-by: Linus Walleij Signed-off-by: Antoniu Miclaus Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/gyro/mpu3050-core.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index ee2fcd20545d..317e7b217ec6 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -322,7 +322,9 @@ static int mpu3050_read_raw(struct iio_dev *indio_dev, } case IIO_CHAN_INFO_RAW: /* Resume device */ - pm_runtime_get_sync(mpu3050->dev); + ret = pm_runtime_resume_and_get(mpu3050->dev); + if (ret) + return ret; mutex_lock(&mpu3050->lock); ret = mpu3050_set_8khz_samplerate(mpu3050); @@ -647,14 +649,20 @@ static irqreturn_t mpu3050_trigger_handler(int irq, void *p) static int mpu3050_buffer_preenable(struct iio_dev *indio_dev) { struct mpu3050 *mpu3050 = iio_priv(indio_dev); + int ret; - pm_runtime_get_sync(mpu3050->dev); + ret = pm_runtime_resume_and_get(mpu3050->dev); + if (ret) + return ret; /* Unless we have OUR trigger active, run at full speed */ - if (!mpu3050->hw_irq_trigger) - return mpu3050_set_8khz_samplerate(mpu3050); + if (!mpu3050->hw_irq_trigger) { + ret = mpu3050_set_8khz_samplerate(mpu3050); + if (ret) + pm_runtime_put_autosuspend(mpu3050->dev); + } - return 0; + return ret; } static int mpu3050_buffer_postdisable(struct iio_dev *indio_dev) From 064234044056c93a3719d6893e6e5a26a94a61b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 16 Feb 2026 13:24:27 +0000 Subject: [PATCH 019/487] iio: buffer: Fix wait_queue not being removed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the edge case where the IIO device is unregistered while we're buffering, we were directly returning an error without removing the wait queue. Instead, set 'ret' and break out of the loop. Fixes: 9eeee3b0bf19 ("iio: Add output buffer support") Signed-off-by: Nuno Sá Reviewed-by: David Lechner Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-buffer.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index f15a180dc49e..46f36a6ed271 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -228,8 +228,10 @@ static ssize_t iio_buffer_write(struct file *filp, const char __user *buf, written = 0; add_wait_queue(&rb->pollq, &wait); do { - if (!indio_dev->info) - return -ENODEV; + if (!indio_dev->info) { + ret = -ENODEV; + break; + } if (!iio_buffer_space_available(rb)) { if (signal_pending(current)) { From 2617595538be8a2f270ad13fccb9f56007b292d7 Mon Sep 17 00:00:00 2001 From: Jean-Baptiste Maneyrol Date: Tue, 17 Feb 2026 11:44:50 +0100 Subject: [PATCH 020/487] iio: imu: inv_icm45600: fix regulator put warning when probe fails When the driver probe fails we encounter a regulator put warning because vddio regulator is not stopped before release. The issue comes from pm_runtime not already setup when core probe fails and the vddio regulator disable callback is called. Fix the issue by setting pm_runtime active early before vddio regulator resource cleanup. This requires to cut pm_runtime set_active and enable in 2 function calls. Fixes: 7ff021a3faca ("iio: imu: inv_icm45600: add new inv_icm45600 driver") Signed-off-by: Jean-Baptiste Maneyrol Cc: stable@vger.kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/inv_icm45600/inv_icm45600_core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c index e4638926a10c..d49053161a65 100644 --- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c +++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c @@ -744,6 +744,11 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi */ fsleep(5 * USEC_PER_MSEC); + /* set pm_runtime active early for disable vddio resource cleanup */ + ret = pm_runtime_set_active(dev); + if (ret) + return ret; + ret = inv_icm45600_enable_regulator_vddio(st); if (ret) return ret; @@ -776,7 +781,7 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi if (ret) return ret; - ret = devm_pm_runtime_set_active_enabled(dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; From 9990cd4f8827bd1ae3fb6eb7407630d8d463c430 Mon Sep 17 00:00:00 2001 From: Radu Sabau Date: Fri, 20 Feb 2026 16:16:41 +0200 Subject: [PATCH 021/487] iio: imu: adis: Fix NULL pointer dereference in adis_init The adis_init() function dereferences adis->ops to check if the individual function pointers (write, read, reset) are NULL, but does not first check if adis->ops itself is NULL. Drivers like adis16480, adis16490, adis16545 and others do not set custom ops and rely on adis_init() assigning the defaults. Since struct adis is zero-initialized by devm_iio_device_alloc(), adis->ops is NULL when adis_init() is called, causing a NULL pointer dereference: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 pc : adis_init+0xc0/0x118 Call trace: adis_init+0xc0/0x118 adis16480_probe+0xe0/0x670 Fix this by checking if adis->ops is NULL before dereferencing it, falling through to assign the default ops in that case. Fixes: 3b29bcee8f6f ("iio: imu: adis: Add custom ops struct") Signed-off-by: Radu Sabau Reviewed-by: Andy Shevchenko Reviewed-by: Antoniu Miclaus Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/imu/adis.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index d160147cce0b..a2bc1d14ed91 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -526,7 +526,7 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev, adis->spi = spi; adis->data = data; - if (!adis->ops->write && !adis->ops->read && !adis->ops->reset) + if (!adis->ops) adis->ops = &adis_default_ops; else if (!adis->ops->write || !adis->ops->read || !adis->ops->reset) return -EINVAL; From 8225489ddb900656cc21573b4e1b00c9181fd777 Mon Sep 17 00:00:00 2001 From: Artem Lytkin Date: Mon, 16 Feb 2026 20:20:38 +0000 Subject: [PATCH 022/487] staging: sm750fb: add missing pci_release_region on error and removal hw_sm750_map() calls pci_request_region() but never releases the region on error paths or in lynxfb_pci_remove(). This causes a resource leak that prevents the PCI region from being mapped again after driver removal or a failed probe. A TODO comment in the code acknowledges this missing cleanup. Restructure the error handling in hw_sm750_map() to properly release the PCI region on ioremap failures, and add pci_release_region() to lynxfb_pci_remove(). Signed-off-by: Artem Lytkin Cc: stable Link: https://patch.msgid.link/20260216202038.1828-1-iprintercanon@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/sm750fb/sm750.c | 1 + drivers/staging/sm750fb/sm750_hw.c | 22 +++++++++++----------- 2 files changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c index dec1f6b88a7d..62f6e0cdff4d 100644 --- a/drivers/staging/sm750fb/sm750.c +++ b/drivers/staging/sm750fb/sm750.c @@ -1123,6 +1123,7 @@ static void lynxfb_pci_remove(struct pci_dev *pdev) iounmap(sm750_dev->pvReg); iounmap(sm750_dev->pvMem); + pci_release_region(pdev, 1); kfree(g_settings); } diff --git a/drivers/staging/sm750fb/sm750_hw.c b/drivers/staging/sm750fb/sm750_hw.c index a29faee91c78..f60b152a647d 100644 --- a/drivers/staging/sm750fb/sm750_hw.c +++ b/drivers/staging/sm750fb/sm750_hw.c @@ -36,16 +36,11 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev) pr_info("mmio phyAddr = %lx\n", sm750_dev->vidreg_start); - /* - * reserve the vidreg space of smi adaptor - * if you do this, you need to add release region code - * in lynxfb_remove, or memory will not be mapped again - * successfully - */ + /* reserve the vidreg space of smi adaptor */ ret = pci_request_region(pdev, 1, "sm750fb"); if (ret) { pr_err("Can not request PCI regions.\n"); - goto exit; + return ret; } /* now map mmio and vidmem */ @@ -54,7 +49,7 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev) if (!sm750_dev->pvReg) { pr_err("mmio failed\n"); ret = -EFAULT; - goto exit; + goto err_release_region; } pr_info("mmio virtual addr = %p\n", sm750_dev->pvReg); @@ -79,13 +74,18 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev) sm750_dev->pvMem = ioremap_wc(sm750_dev->vidmem_start, sm750_dev->vidmem_size); if (!sm750_dev->pvMem) { - iounmap(sm750_dev->pvReg); pr_err("Map video memory failed\n"); ret = -EFAULT; - goto exit; + goto err_unmap_reg; } pr_info("video memory vaddr = %p\n", sm750_dev->pvMem); -exit: + + return 0; + +err_unmap_reg: + iounmap(sm750_dev->pvReg); +err_release_region: + pci_release_region(pdev, 1); return ret; } From f0109b9d3e1e455429279d602f6276e34689750a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 23 Feb 2026 14:31:35 +0100 Subject: [PATCH 023/487] staging: rtl8723bs: properly validate the data in rtw_get_ie_ex() Just like in commit 154828bf9559 ("staging: rtl8723bs: fix out-of-bounds read in rtw_get_ie() parser"), we don't trust the data in the frame so we should check the length better before acting on it Cc: stable Assisted-by: gkh_clanker_2000 Tested-by: Navaneeth K Reviewed-by: Navaneeth K Link: https://patch.msgid.link/2026022336-arrange-footwork-6e54@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_ieee80211.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 6cf217e21593..3e2b5e6b07f9 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -186,20 +186,25 @@ u8 *rtw_get_ie_ex(u8 *in_ie, uint in_len, u8 eid, u8 *oui, u8 oui_len, u8 *ie, u cnt = 0; - while (cnt < in_len) { + while (cnt + 2 <= in_len) { + u8 ie_len = in_ie[cnt + 1]; + + if (cnt + 2 + ie_len > in_len) + break; + if (eid == in_ie[cnt] - && (!oui || !memcmp(&in_ie[cnt+2], oui, oui_len))) { + && (!oui || (ie_len >= oui_len && !memcmp(&in_ie[cnt + 2], oui, oui_len)))) { target_ie = &in_ie[cnt]; if (ie) - memcpy(ie, &in_ie[cnt], in_ie[cnt+1]+2); + memcpy(ie, &in_ie[cnt], ie_len + 2); if (ielen) - *ielen = in_ie[cnt+1]+2; + *ielen = ie_len + 2; break; } - cnt += in_ie[cnt+1]+2; /* goto next */ + cnt += ie_len + 2; /* goto next */ } return target_ie; From 410666a298c34ebd57256fde6b24c96bd23059a2 Mon Sep 17 00:00:00 2001 From: Roberto Bergantinos Corpas Date: Thu, 19 Feb 2026 13:04:40 +0100 Subject: [PATCH 024/487] nfs: return EISDIR on nfs3_proc_create if d_alias is a dir If we found an alias through nfs3_do_create/nfs_add_or_obtain /d_splice_alias which happens to be a dir dentry, we don't return any error, and simply forget about this alias, but the original dentry we were adding and passed as parameter remains negative. This later causes an oops on nfs_atomic_open_v23/finish_open since we supply a negative dentry to do_dentry_open. This has been observed running lustre-racer, where dirs and files are created/removed concurrently with the same name and O_EXCL is not used to open files (frequent file redirection). While d_splice_alias typically returns a directory alias or NULL, we explicitly check d_is_dir() to ensure that we don't attempt to perform file operations (like finish_open) on a directory inode, which triggers the observed oops. Fixes: 7c6c5249f061 ("NFS: add atomic_open for NFSv3 to handle O_TRUNC correctly.") Reviewed-by: Olga Kornievskaia Reviewed-by: Scott Mayhew Signed-off-by: Roberto Bergantinos Corpas Signed-off-by: Anna Schumaker --- fs/nfs/nfs3proc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 3e2de45c95fe..be2aebf62056 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -392,8 +392,13 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, if (status != 0) goto out_release_acls; - if (d_alias) + if (d_alias) { + if (d_is_dir(d_alias)) { + status = -EISDIR; + goto out_dput; + } dentry = d_alias; + } /* When we created the file with exclusive semantics, make * sure we set the attributes afterwards. */ From 93cd0d664661f58f7e7bed7373714ab2ace41734 Mon Sep 17 00:00:00 2001 From: A1RM4X Date: Wed, 4 Feb 2026 14:26:48 -0500 Subject: [PATCH 025/487] USB: add QUIRK_NO_BOS for video capture several devices Several USB capture devices also need the USB_QUIRK_NO_BOS set for them to work properly, odds are they are all the same chip inside, just different vendor/product ids. This fixes up: - ASUS TUF 4K PRO - Avermedia Live Gamer Ultra 2.1 (GC553G2) - UGREEN 35871 to now run at full speed (10 Gbps/4K 60 fps mode.) Link: https://lore.kernel.org/r/CACy+XB-f-51xGpNQFCSm5pE_momTQLu=BaZggHYU1DiDmFX=ug@mail.gmail.com Cc: stable Signed-off-by: A1RM4X Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 9e7e49712739..e347236d83e8 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -376,6 +376,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* SanDisk Extreme 55AE */ { USB_DEVICE(0x0781, 0x55ae), .driver_info = USB_QUIRK_NO_LPM }, + /* Avermedia Live Gamer Ultra 2.1 (GC553G2) - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x07ca, 0x2553), .driver_info = USB_QUIRK_NO_BOS }, + /* Realforce 87U Keyboard */ { USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM }, @@ -436,6 +439,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* ASUS TUF 4K PRO - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x0b05, 0x1ab9), .driver_info = USB_QUIRK_NO_BOS }, + /* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/ { USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -564,6 +570,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM }, + /* UGREEN 35871 - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x2b89, 0x5871), .driver_info = USB_QUIRK_NO_BOS }, + /* APTIV AUTOMOTIVE HUB */ { USB_DEVICE(0x2c48, 0x0132), .driver_info = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT }, From b9fde507355342a2d64225d582dc8b98ff5ecb19 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 19 Feb 2026 02:38:34 +0000 Subject: [PATCH 026/487] usb: gadget: f_tcm: Fix NULL pointer dereferences in nexus handling The `tpg->tpg_nexus` pointer in the USB Target driver is dynamically managed and tied to userspace configuration via ConfigFS. It can be NULL if the USB host sends requests before the nexus is fully established or immediately after it is dropped. Currently, functions like `bot_submit_command()` and the data transfer paths retrieve `tv_nexus = tpg->tpg_nexus` and immediately dereference `tv_nexus->tvn_se_sess` without any validation. If a malicious or misconfigured USB host sends a BOT (Bulk-Only Transport) command during this race window, it triggers a NULL pointer dereference, leading to a kernel panic (local DoS). This exposes an inconsistent API usage within the module, as peer functions like `usbg_submit_command()` and `bot_send_bad_response()` correctly implement a NULL check for `tv_nexus` before proceeding. Fix this by bringing consistency to the nexus handling. Add the missing `if (!tv_nexus)` checks to the vulnerable BOT command and request processing paths, aborting the command gracefully with an error instead of crashing the system. Fixes: c52661d60f63 ("usb-gadget: Initial merge of target module for UASP + BOT") Cc: stable Signed-off-by: Jiasheng Jiang Reviewed-by: Thinh Nguyen Link: https://patch.msgid.link/20260219023834.17976-1-jiashengjiangcool@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_tcm.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index ec050d8f99f1..a7853dcbb14c 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1222,6 +1222,13 @@ static void usbg_submit_cmd(struct usbg_cmd *cmd) se_cmd = &cmd->se_cmd; tpg = cmd->fu->tpg; tv_nexus = tpg->tpg_nexus; + if (!tv_nexus) { + struct usb_gadget *gadget = fuas_to_gadget(cmd->fu); + + dev_err(&gadget->dev, "Missing nexus, ignoring command\n"); + return; + } + dir = get_cmd_dir(cmd->cmd_buf); if (dir < 0) goto out; @@ -1483,6 +1490,13 @@ static void bot_cmd_work(struct work_struct *work) se_cmd = &cmd->se_cmd; tpg = cmd->fu->tpg; tv_nexus = tpg->tpg_nexus; + if (!tv_nexus) { + struct usb_gadget *gadget = fuas_to_gadget(cmd->fu); + + dev_err(&gadget->dev, "Missing nexus, ignoring command\n"); + return; + } + dir = get_cmd_dir(cmd->cmd_buf); if (dir < 0) goto out; From fde0634ad9856b3943a2d1a8cc8de174a63ac840 Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Sat, 21 Feb 2026 22:48:15 +0800 Subject: [PATCH 027/487] usb: legacy: ncm: Fix NPE in gncm_bind Commit 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") deferred the allocation of the net_device. This change leads to a NULL pointer dereference in the legacy NCM driver as it attempts to access the net_device before it's fully instantiated. Store the provided qmult, host_addr, and dev_addr into the struct ncm_opts->net_opts during gncm_bind(). These values will be properly applied to the net_device when it is allocated and configured later in the binding process by the NCM function driver. Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable@kernel.org Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202602181727.fd76c561-lkp@intel.com Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260221-legacy-ncm-v2-1-dfb891d76507@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/ncm.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c index 0f1b45e3abd1..e8d565534053 100644 --- a/drivers/usb/gadget/legacy/ncm.c +++ b/drivers/usb/gadget/legacy/ncm.c @@ -15,8 +15,10 @@ /* #define DEBUG */ /* #define VERBOSE_DEBUG */ +#include #include #include +#include #include #include "u_ether.h" @@ -129,6 +131,7 @@ static int gncm_bind(struct usb_composite_dev *cdev) struct usb_gadget *gadget = cdev->gadget; struct f_ncm_opts *ncm_opts; int status; + u8 mac[ETH_ALEN]; f_ncm_inst = usb_get_function_instance("ncm"); if (IS_ERR(f_ncm_inst)) @@ -136,11 +139,15 @@ static int gncm_bind(struct usb_composite_dev *cdev) ncm_opts = container_of(f_ncm_inst, struct f_ncm_opts, func_inst); - gether_set_qmult(ncm_opts->net, qmult); - if (!gether_set_host_addr(ncm_opts->net, host_addr)) + ncm_opts->net_opts.qmult = qmult; + if (host_addr && mac_pton(host_addr, mac)) { + memcpy(&ncm_opts->net_opts.host_mac, mac, ETH_ALEN); pr_info("using host ethernet address: %s", host_addr); - if (!gether_set_dev_addr(ncm_opts->net, dev_addr)) + } + if (dev_addr && mac_pton(dev_addr, mac)) { + memcpy(&ncm_opts->net_opts.dev_mac, mac, ETH_ALEN); pr_info("using self ethernet address: %s", dev_addr); + } /* Allocate string descriptor numbers ... note that string * contents can be overridden by the composite_dev glue. From 0d6c8144ca4d93253de952a5ea0028c19ed7ab68 Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Sat, 21 Feb 2026 22:48:16 +0800 Subject: [PATCH 028/487] usb: gadget: f_ncm: Fix atomic context locking issue The ncm_set_alt function was holding a mutex to protect against races with configfs, which invokes the might-sleep function inside an atomic context. Remove the struct net_device pointer from the f_ncm_opts structure to eliminate the contention. The connection state is now managed by a new boolean flag to preserve the use-after-free fix from commit 6334b8e4553c ("usb: gadget: f_ncm: Fix UAF ncm object at re-bind after usb ep transport error"). BUG: sleeping function called from invalid context Call Trace: dump_stack_lvl+0x83/0xc0 dump_stack+0x14/0x16 __might_resched+0x389/0x4c0 __might_sleep+0x8e/0x100 ... __mutex_lock+0x6f/0x1740 ... ncm_set_alt+0x209/0xa40 set_config+0x6b6/0xb40 composite_setup+0x734/0x2b40 ... Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable@kernel.org Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260221-legacy-ncm-v2-2-dfb891d76507@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_ncm.c | 29 ++++++++----------- .../usb/gadget/function/u_ether_configfs.h | 11 +------ drivers/usb/gadget/function/u_ncm.h | 1 - 3 files changed, 13 insertions(+), 28 deletions(-) diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 14fc7dce6f39..4da19864d70b 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -58,6 +58,7 @@ struct f_ncm { u8 notify_state; atomic_t notify_count; bool is_open; + bool is_connected; const struct ndp_parser_opts *parser_opts; bool is_crc; @@ -864,7 +865,6 @@ static int ncm_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) { struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; /* Control interface has only altsetting 0 */ @@ -887,13 +887,12 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (alt > 1) goto fail; - scoped_guard(mutex, &opts->lock) - if (opts->net) { - DBG(cdev, "reset ncm\n"); - opts->net = NULL; - gether_disconnect(&ncm->port); - ncm_reset_values(ncm); - } + if (ncm->is_connected) { + DBG(cdev, "reset ncm\n"); + ncm->is_connected = false; + gether_disconnect(&ncm->port); + ncm_reset_values(ncm); + } /* * CDC Network only sends data in non-default altsettings. @@ -926,8 +925,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) net = gether_connect(&ncm->port); if (IS_ERR(net)) return PTR_ERR(net); - scoped_guard(mutex, &opts->lock) - opts->net = net; + ncm->is_connected = true; } spin_lock(&ncm->lock); @@ -1374,16 +1372,14 @@ static int ncm_unwrap_ntb(struct gether *port, static void ncm_disable(struct usb_function *f) { struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; DBG(cdev, "ncm deactivated\n"); - scoped_guard(mutex, &opts->lock) - if (opts->net) { - opts->net = NULL; - gether_disconnect(&ncm->port); - } + if (ncm->is_connected) { + ncm->is_connected = false; + gether_disconnect(&ncm->port); + } if (ncm->notify->enabled) { usb_ep_disable(ncm->notify); @@ -1687,7 +1683,6 @@ static struct usb_function_instance *ncm_alloc_inst(void) if (!opts) return ERR_PTR(-ENOMEM); - opts->net = NULL; opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id; gether_setup_opts_default(&opts->net_opts, "usb"); diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h index 217990a266b2..25d8fb05b598 100644 --- a/drivers/usb/gadget/function/u_ether_configfs.h +++ b/drivers/usb/gadget/function/u_ether_configfs.h @@ -327,18 +327,9 @@ out: \ char *page) \ { \ struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - const char *name; \ \ guard(mutex)(&opts->lock); \ - rtnl_lock(); \ - if (opts->net_opts.ifname_set) \ - name = opts->net_opts.name; \ - else if (opts->net) \ - name = netdev_name(opts->net); \ - else \ - name = "(inactive net_device)"; \ - rtnl_unlock(); \ - return sysfs_emit(page, "%s\n", name); \ + return sysfs_emit(page, "%s\n", opts->net_opts.name); \ } \ \ static ssize_t _f_##_opts_ifname_store(struct config_item *item, \ diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h index d99330fe31e8..6d7538855744 100644 --- a/drivers/usb/gadget/function/u_ncm.h +++ b/drivers/usb/gadget/function/u_ncm.h @@ -19,7 +19,6 @@ struct f_ncm_opts { struct usb_function_instance func_inst; - struct net_device *net; struct gether_opts net_opts; struct config_group *ncm_interf_group; From 7a875c09899ba0404844abfd8f0d54cdc481c151 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Mon, 9 Feb 2026 15:37:20 +0100 Subject: [PATCH 029/487] usb: yurex: fix race in probe The bbu member of the descriptor must be set to the value standing for uninitialized values before the URB whose completion handler sets bbu is submitted. Otherwise there is a window during which probing can overwrite already retrieved data. Cc: stable Signed-off-by: Oliver Neukum Link: https://patch.msgid.link/20260209143720.1507500-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/yurex.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 9189e4bb213a..7a482cdee1e9 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -272,6 +272,7 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_ dev->int_buffer, YUREX_BUF_SIZE, yurex_interrupt, dev, 1); dev->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + dev->bbu = -1; if (usb_submit_urb(dev->urb, GFP_KERNEL)) { retval = -EIO; dev_err(&interface->dev, "Could not submitting URB\n"); @@ -280,7 +281,6 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_ /* save our data pointer in this interface device */ usb_set_intfdata(interface, dev); - dev->bbu = -1; /* we can register the device now, as it is ready */ retval = usb_register_dev(interface, &yurex_class); From f9b888599418951b8229bbb28851ed4da50c58e9 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 28 Jan 2026 16:02:42 -0600 Subject: [PATCH 030/487] remoteproc: qcom_wcnss: Fix reserved region mapping failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit c70b9d5fdcd7 ("remoteproc: qcom: Use of_reserved_mem_region_* functions for "memory-region"") switched from devm_ioremap_wc() to devm_ioremap_resource_wc(). The difference is devm_ioremap_resource_wc() also requests the resource which fails. Testing of both fixed and dynamic reserved regions indicates that requesting the resource should work, so I'm not sure why it doesn't work in this case. Fix the issue by reverting back to devm_ioremap_wc(). Reported-by: Marek Szyprowski Reported-by: André Apitzsch Fixes: c70b9d5fdcd7 ("remoteproc: qcom: Use of_reserved_mem_region_* functions for "memory-region"") Signed-off-by: Rob Herring (Arm) Tested-by: Marek Szyprowski Tested-by: André Apitzsch # on BQ Aquaris M5 Link: https://lore.kernel.org/r/20260128220243.3018526-1-robh@kernel.org Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_wcnss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c index ee18bf2e8054..4add9037dbd5 100644 --- a/drivers/remoteproc/qcom_wcnss.c +++ b/drivers/remoteproc/qcom_wcnss.c @@ -537,7 +537,7 @@ static int wcnss_alloc_memory_region(struct qcom_wcnss *wcnss) wcnss->mem_phys = wcnss->mem_reloc = res.start; wcnss->mem_size = resource_size(&res); - wcnss->mem_region = devm_ioremap_resource_wc(wcnss->dev, &res); + wcnss->mem_region = devm_ioremap_wc(wcnss->dev, wcnss->mem_phys, wcnss->mem_size); if (IS_ERR(wcnss->mem_region)) { dev_err(wcnss->dev, "unable to map memory region: %pR\n", &res); return PTR_ERR(wcnss->mem_region); From a9dece60cc8246e5fc4c46d391272024bf1d309d Mon Sep 17 00:00:00 2001 From: Akhil P Oommen Date: Sat, 24 Jan 2026 06:32:56 +0530 Subject: [PATCH 031/487] drm/msm/adreno: Add GPU to MODULE_DEVICE_TABLE Since it is possible to independently probe Adreno GPU, add GPU match table to MODULE_DEVICE_TABLE to allow auto-loading of msm module. Signed-off-by: Akhil P Oommen Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/700656/ Link: https://lore.kernel.org/r/20260124-adreno-module-table-v1-1-9c2dbb2638b4@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/adreno/adreno_device.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 554d746f115b..4edfe80c5be7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -302,6 +302,7 @@ static const struct of_device_id dt_match[] = { { .compatible = "qcom,kgsl-3d0" }, {} }; +MODULE_DEVICE_TABLE(of, dt_match); static int adreno_runtime_resume(struct device *dev) { From f7bf1319739291067b2bc4b22bd56336afad8f0a Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 27 Jan 2026 11:58:49 +0100 Subject: [PATCH 032/487] drm/msm/dpu: Fix LM size on a number of platforms The register space has grown with what seems to be DPU8. Bump up the .len to match. Fixes: e3b1f369db5a ("drm/msm/dpu: Add X1E80100 support") Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Fixes: efcd0107727c ("drm/msm/dpu: add support for SM8550") Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450") Fixes: 178575173472 ("drm/msm/dpu: add catalog entry for SAR2130P") Signed-off-by: Konrad Dybcio Reviewed-by: Abel Vesa Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/701063/ Link: https://lore.kernel.org/r/20260127-topic-lm_size_fix-v1-1-25f88d014dfd@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov --- .../gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 12 ++++++------ .../gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 12 ++++++------ .../gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h | 12 ++++++------ .../gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h | 12 ++++++------ .../gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h | 12 ++++++------ 5 files changed, 30 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 303d33dc7783..9f2bceca1789 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -133,7 +133,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { static const struct dpu_lm_cfg sc8280xp_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -141,7 +141,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -149,7 +149,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -157,7 +157,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -165,14 +165,14 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index b09a6af4c474..04b22167f93d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -134,7 +134,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = { static const struct dpu_lm_cfg sm8450_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -142,7 +142,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -150,7 +150,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -158,7 +158,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -166,14 +166,14 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 465b6460f875..4c7eb55d474c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = { static const struct dpu_lm_cfg sm8550_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h index 6caa7d40f368..dec83ea8167d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h @@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sar2130p_sspp[] = { static const struct dpu_lm_cfg sar2130p_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index 7243eebb85f3..52ff4baa668a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -130,7 +130,7 @@ static const struct dpu_sspp_cfg x1e80100_sspp[] = { static const struct dpu_lm_cfg x1e80100_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -138,7 +138,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -146,7 +146,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -154,7 +154,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -162,14 +162,14 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, From 6f6f3535192dd597c5326ea5456ae3bafc7d43b2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 6 Feb 2026 14:21:52 -0800 Subject: [PATCH 033/487] drm/msm: Adjust msm_iommu_pagetable_prealloc_allocate() allocation type In preparation for making the kmalloc family of allocators type aware, we need to make sure that the returned type from the allocation matches the type of the variable being assigned. (Before, the allocator would always return "void *", which can be implicitly cast to any pointer type.) The assigned type is "void **" but the returned type will be "void ***". These are the same allocation size (pointer size), but the types do not match. Adjust the allocation type to match the assignment. Signed-off-by: Kees Cook Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/703588/ Link: https://lore.kernel.org/r/20260206222151.work.016-kees@kernel.org Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/msm_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index d5dede4ff761..271baf4dc4e8 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -332,7 +332,7 @@ msm_iommu_pagetable_prealloc_allocate(struct msm_mmu *mmu, struct msm_mmu_preall struct kmem_cache *pt_cache = get_pt_cache(mmu); int ret; - p->pages = kvmalloc_array(p->count, sizeof(p->pages), GFP_KERNEL); + p->pages = kvmalloc_array(p->count, sizeof(*p->pages), GFP_KERNEL); if (!p->pages) return -ENOMEM; From b1dcc804f4662256a3e4bd8ac182a7a2c9464723 Mon Sep 17 00:00:00 2001 From: sunliming Date: Fri, 30 Jan 2026 13:36:15 +0800 Subject: [PATCH 034/487] drm/msm/dpu: Fix smatch warnings about variable dereferenced before check Fix below smatch warnings: drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c:161 dpu_hw_sspp_setup_pe_config_v13() warn: variable dereferenced before check 'ctx' (see line 159) Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202601252214.oEaY3UZM-lkp@intel.com/ Signed-off-by: sunliming Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/701853/ Link: https://lore.kernel.org/r/20260130053615.24886-1-sunliming@linux.dev Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c index e65f1fc026fd..f8f96ad971d7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c @@ -156,11 +156,13 @@ static void dpu_hw_sspp_setup_pe_config_v13(struct dpu_hw_sspp *ctx, u8 color; u32 lr_pe[4], tb_pe[4]; const u32 bytemask = 0xff; - u32 offset = ctx->cap->sblk->sspp_rec0_blk.base; + u32 offset; if (!ctx || !pe_ext) return; + offset = ctx->cap->sblk->sspp_rec0_blk.base; + c = &ctx->hw; /* program SW pixel extension override for all pipes*/ for (color = 0; color < DPU_MAX_PLANES; color++) { From 9f593419eb42c68f31829aed3c199591190bfe5d Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 14 Feb 2026 01:02:59 +0200 Subject: [PATCH 035/487] Revert "drm/msm/dpu: try reserving the DSPP-less LM first" This reverts commit 42f62cd79578 ("drm/msm/dpu: try reserving the DSPP-less LM first"). It seems on later DPUs using higher LMs require some additional setup or conflicts with the hardware defaults. Val (and other developers) reported blue screen on Hamoa (X1E80100) laptops. Revert the offending commit until we understand, what is the issue. Fixes: 42f62cd79578 ("drm/msm/dpu: try reserving the DSPP-less LM first") Reported-by: Val Packett Closes: https://lore.kernel.org/r/33424a9d-10a6-4479-bba6-12f8ce60da1a@packett.cool Signed-off-by: Dmitry Baryshkov Tested-by: Manivannan Sadhasivam # T14s Patchwork: https://patchwork.freedesktop.org/patch/704814/ Link: https://lore.kernel.org/r/20260214-revert-dspp-less-v1-1-be0d636a2a6e@oss.qualcomm.com --- drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c | 52 +++++++------------------- 1 file changed, 14 insertions(+), 38 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 451a4fcf3e65..7e77d88f8959 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -350,26 +350,28 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return true; } -static bool dpu_rm_find_lms(struct dpu_rm *rm, - struct dpu_global_state *global_state, - uint32_t crtc_id, bool skip_dspp, - struct msm_display_topology *topology, - int *lm_idx, int *pp_idx, int *dspp_idx) +static int _dpu_rm_reserve_lms(struct dpu_rm *rm, + struct dpu_global_state *global_state, + uint32_t crtc_id, + struct msm_display_topology *topology) { + int lm_idx[MAX_BLOCKS]; + int pp_idx[MAX_BLOCKS]; + int dspp_idx[MAX_BLOCKS] = {0}; int i, lm_count = 0; + if (!topology->num_lm) { + DPU_ERROR("zero LMs in topology\n"); + return -EINVAL; + } + /* Find a primary mixer */ for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) && lm_count < topology->num_lm; i++) { if (!rm->mixer_blks[i]) continue; - if (skip_dspp && to_dpu_hw_mixer(rm->mixer_blks[i])->cap->dspp) { - DPU_DEBUG("Skipping LM_%d, skipping LMs with DSPPs\n", i); - continue; - } - /* * Reset lm_count to an even index. This will drop the previous * primary mixer if failed to find its peer. @@ -408,38 +410,12 @@ static bool dpu_rm_find_lms(struct dpu_rm *rm, } } - return lm_count == topology->num_lm; -} - -static int _dpu_rm_reserve_lms(struct dpu_rm *rm, - struct dpu_global_state *global_state, - uint32_t crtc_id, - struct msm_display_topology *topology) - -{ - int lm_idx[MAX_BLOCKS]; - int pp_idx[MAX_BLOCKS]; - int dspp_idx[MAX_BLOCKS] = {0}; - int i; - bool found; - - if (!topology->num_lm) { - DPU_ERROR("zero LMs in topology\n"); - return -EINVAL; - } - - /* Try using non-DSPP LM blocks first */ - found = dpu_rm_find_lms(rm, global_state, crtc_id, !topology->num_dspp, - topology, lm_idx, pp_idx, dspp_idx); - if (!found && !topology->num_dspp) - found = dpu_rm_find_lms(rm, global_state, crtc_id, false, - topology, lm_idx, pp_idx, dspp_idx); - if (!found) { + if (lm_count != topology->num_lm) { DPU_DEBUG("unable to find appropriate mixers\n"); return -ENAVAIL; } - for (i = 0; i < topology->num_lm; i++) { + for (i = 0; i < lm_count; i++) { global_state->mixer_to_crtc_id[lm_idx[i]] = crtc_id; global_state->pingpong_to_crtc_id[pp_idx[i]] = crtc_id; global_state->dspp_to_crtc_id[dspp_idx[i]] = From 5886cc8f895bf578903eb681fca9123065e1012e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 23 Feb 2026 08:16:55 +0100 Subject: [PATCH 036/487] drm/msm/dpu: Don't use %pK through printk (again) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the past %pK was preferable to %p as it would not leak raw pointer values into the kernel log. Since commit ad67b74d2469 ("printk: hash addresses printed with %p") the regular %p has been improved to avoid this issue. Furthermore, restricted pointers ("%pK") were never meant to be used through printk(). They can still unintentionally leak raw pointers or acquire sleeping locks in atomic contexts. Switch to the regular pointer formatting which is safer and easier to reason about. This was previously fixed in this driver in commit 1ba9fbe40337 ("drm/msm: Don't use %pK through printk") but an additional usage was reintroduced in commit 39a750ff5fc9 ("drm/msm/dpu: Add DSPP GC driver to provide GAMMA_LUT DRM property") Signed-off-by: Thomas Weißschuh Fixes: 39a750ff5fc9 ("drm/msm/dpu: Add DSPP GC driver to provide GAMMA_LUT DRM property") Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/706229/ Link: https://lore.kernel.org/r/20260223-restricted-pointers-msm-v1-1-14c0b451e372@linutronix.de Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index 188ee0af2c90..23dcbe1ce1b8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -89,7 +89,7 @@ static void dpu_setup_dspp_gc(struct dpu_hw_dspp *ctx, base = ctx->cap->sblk->gc.base; if (!base) { - DRM_ERROR("invalid ctx %pK gc base\n", ctx); + DRM_ERROR("invalid ctx %p gc base\n", ctx); return; } From ac47870fd795549f03d57e0879fc730c79119f4b Mon Sep 17 00:00:00 2001 From: Pengyu Luo Date: Sat, 14 Feb 2026 18:51:28 +0800 Subject: [PATCH 037/487] drm/msm/dsi: fix hdisplay calculation when programming dsi registers Recently, the hdisplay calculation is working for 3:1 compressed ratio only. If we have a video panel with DSC BPP = 8, and BPC = 10, we still use the default bits_per_pclk = 24, then we get the wrong hdisplay. We can draw the conclusion by cross-comparing the calculation with the calculation in dsi_adjust_pclk_for_compression(). Since CMD mode does not use this, we can remove !(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) safely. Fixes: efcbd6f9cdeb ("drm/msm/dsi: Enable widebus for DSI") Signed-off-by: Pengyu Luo Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/704822/ Link: https://lore.kernel.org/r/20260214105145.105308-1-mitltlatltl@gmail.com Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/dsi/dsi_host.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index e0de545d4077..e8e83ee61eb0 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -993,7 +993,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) if (msm_host->dsc) { struct drm_dsc_config *dsc = msm_host->dsc; - u32 bytes_per_pclk; + u32 bits_per_pclk; /* update dsc params with timing params */ if (!dsc || !mode->hdisplay || !mode->vdisplay) { @@ -1015,7 +1015,9 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) /* * DPU sends 3 bytes per pclk cycle to DSI. If widebus is - * enabled, bus width is extended to 6 bytes. + * enabled, MDP always sends out 48-bit compressed data per + * pclk and on average, DSI consumes an amount of compressed + * data equivalent to the uncompressed pixel depth per pclk. * * Calculate the number of pclks needed to transmit one line of * the compressed data. @@ -1027,12 +1029,12 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) * unused anyway. */ h_total -= hdisplay; - if (wide_bus_enabled && !(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO)) - bytes_per_pclk = 6; + if (wide_bus_enabled) + bits_per_pclk = mipi_dsi_pixel_format_to_bpp(msm_host->format); else - bytes_per_pclk = 3; + bits_per_pclk = 24; - hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc), bytes_per_pclk); + hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc) * 8, bits_per_pclk); h_total += hdisplay; ha_end = ha_start + hdisplay; From a75281626fc8fa6dc6c9cc314ee423e8bc45203b Mon Sep 17 00:00:00 2001 From: Luka Gejak Date: Tue, 24 Feb 2026 14:26:47 +0100 Subject: [PATCH 038/487] staging: rtl8723bs: fix potential out-of-bounds read in rtw_restruct_wmm_ie The current code checks 'i + 5 < in_len' at the end of the if statement. However, it accesses 'in_ie[i + 5]' before that check, which can lead to an out-of-bounds read. Move the length check to the beginning of the conditional to ensure the index is within bounds before accessing the array. Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver") Cc: stable Signed-off-by: Luka Gejak Reviewed-by: Dan Carpenter Link: https://patch.msgid.link/20260224132647.11642-2-luka.gejak@linux.dev Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_mlme.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index 7df651708381..1ef48bf6581c 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -1988,7 +1988,10 @@ int rtw_restruct_wmm_ie(struct adapter *adapter, u8 *in_ie, u8 *out_ie, uint in_ while (i < in_len) { ielength = initial_out_len; - if (in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 && in_ie[i + 3] == 0x50 && in_ie[i + 4] == 0xF2 && in_ie[i + 5] == 0x02 && i + 5 < in_len) { /* WMM element ID and OUI */ + if (i + 5 < in_len && + in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 && + in_ie[i + 3] == 0x50 && in_ie[i + 4] == 0xF2 && + in_ie[i + 5] == 0x02) { for (j = i; j < i + 9; j++) { out_ie[ielength] = in_ie[j]; ielength++; From c45f7263100cece247dd3fa5fe277bd97fdb5687 Mon Sep 17 00:00:00 2001 From: Liwei Song Date: Thu, 12 Feb 2026 12:00:35 +0800 Subject: [PATCH 039/487] firmware: stratix10-rsu: Fix NULL pointer dereference when RSU is disabled When the Remote System Update (RSU) isn't enabled in the First Stage Boot Loader (FSBL), the driver encounters a NULL pointer dereference when excute svc_normal_to_secure_thread() thread, resulting in a kernel panic: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 Mem abort info: ... Data abort info: ... [0000000000000008] user address but active_mm is swapper Internal error: Oops: 0000000096000004 [#1] SMP Modules linked in: CPU: 0 UID: 0 PID: 79 Comm: svc_smc_hvc_thr Not tainted 6.19.0-rc8-yocto-standard+ #59 PREEMPT Hardware name: SoCFPGA Stratix 10 SoCDK (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : svc_normal_to_secure_thread+0x38c/0x990 lr : svc_normal_to_secure_thread+0x144/0x990 ... Call trace: svc_normal_to_secure_thread+0x38c/0x990 (P) kthread+0x150/0x210 ret_from_fork+0x10/0x20 Code: 97cfc113 f9400260 aa1403e1 f9400400 (f9400402) ---[ end trace 0000000000000000 ]--- The issue occurs because rsu_send_async_msg() fails when RSU is not enabled in firmware, causing the channel to be freed via stratix10_svc_free_channel(). However, the probe function continues execution and registers svc_normal_to_secure_thread(), which subsequently attempts to access the already-freed channel, triggering the NULL pointer dereference. Fix this by properly cleaning up the async client and returning early on failure, preventing the thread from being used with an invalid channel. Fixes: 15847537b623 ("firmware: stratix10-rsu: Migrate RSU driver to use stratix10 asynchronous framework.") Cc: stable@kernel.org Signed-off-by: Liwei Song Signed-off-by: Dinh Nguyen --- drivers/firmware/stratix10-rsu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c index 41da07c445a6..e1912108a0fe 100644 --- a/drivers/firmware/stratix10-rsu.c +++ b/drivers/firmware/stratix10-rsu.c @@ -768,7 +768,9 @@ static int stratix10_rsu_probe(struct platform_device *pdev) rsu_async_status_callback); if (ret) { dev_err(dev, "Error, getting RSU status %i\n", ret); + stratix10_svc_remove_async_client(priv->chan); stratix10_svc_free_channel(priv->chan); + return ret; } /* get DCMF version from firmware */ From 2d6d260e9a3576256fe9ef6d1f7930c9ec348723 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Mon, 9 Feb 2026 15:20:48 +0100 Subject: [PATCH 040/487] usb: mdc800: handle signal and read racing If a signal arrives after a read has partially completed, we need to return the number of bytes read. -EINTR is correct only if that number is zero. Signed-off-by: Oliver Neukum Cc: stable Link: https://patch.msgid.link/20260209142048.1503791-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/image/mdc800.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c index 8d8e79afa600..e76a502fa9da 100644 --- a/drivers/usb/image/mdc800.c +++ b/drivers/usb/image/mdc800.c @@ -707,7 +707,7 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l if (signal_pending (current)) { mutex_unlock(&mdc800->io_lock); - return -EINTR; + return len == left ? -EINTR : len-left; } sts=left > (mdc800->out_count-mdc800->out_ptr)?mdc800->out_count-mdc800->out_ptr:left; From 1be3b77de4eb89af8ae2fd6610546be778e25589 Mon Sep 17 00:00:00 2001 From: Ziyi Guo Date: Mon, 9 Feb 2026 15:19:37 +0000 Subject: [PATCH 041/487] usb: image: mdc800: kill download URB on timeout mdc800_device_read() submits download_urb and waits for completion. If the timeout fires and the device has not responded, the function returns without killing the URB, leaving it active. A subsequent read() resubmits the same URB while it is still in-flight, triggering the WARN in usb_submit_urb(): "URB submitted while active" Check the return value of wait_event_timeout() and kill the URB if it indicates timeout, ensuring the URB is complete before its status is inspected or the URB is resubmitted. Similar to - commit 372c93131998 ("USB: yurex: fix control-URB timeout handling") - commit b98d5000c505 ("media: rc: iguanair: handle timeouts") Signed-off-by: Ziyi Guo Cc: stable Link: https://patch.msgid.link/20260209151937.2247202-1-n7l8m4@u.northwestern.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/image/mdc800.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c index e76a502fa9da..ca287b770e8c 100644 --- a/drivers/usb/image/mdc800.c +++ b/drivers/usb/image/mdc800.c @@ -730,9 +730,11 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l mutex_unlock(&mdc800->io_lock); return len-left; } - wait_event_timeout(mdc800->download_wait, + retval = wait_event_timeout(mdc800->download_wait, mdc800->downloaded, msecs_to_jiffies(TO_DOWNLOAD_GET_READY)); + if (!retval) + usb_kill_urb(mdc800->download_urb); mdc800->downloaded = 0; if (mdc800->download_urb->status != 0) { From 4fc87c240b8f30e22b7ebaae29d57105589e1c0b Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Tue, 10 Feb 2026 23:28:20 +0000 Subject: [PATCH 042/487] rust_binder: fix oneway spam detection The spam detection logic in TreeRange was executed before the current request was inserted into the tree. So the new request was not being factored in the spam calculation. Fix this by moving the logic after the new range has been inserted. Also, the detection logic for ArrayRange was missing altogether which meant large spamming transactions could get away without being detected. Fix this by implementing an equivalent low_oneway_space() in ArrayRange. Note that I looked into centralizing this logic in RangeAllocator but iterating through 'state' and 'size' got a bit too complicated (for me) and I abandoned this effort. Cc: stable Cc: Alice Ryhl Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver") Signed-off-by: Carlos Llamas Reviewed-by: Alice Ryhl Link: https://patch.msgid.link/20260210232949.3770644-1-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder/range_alloc/array.rs | 35 +++++++++++++++++++-- drivers/android/binder/range_alloc/mod.rs | 4 +-- drivers/android/binder/range_alloc/tree.rs | 18 +++++------ 3 files changed, 44 insertions(+), 13 deletions(-) diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs index 07e1dec2ce63..ada1d1b4302e 100644 --- a/drivers/android/binder/range_alloc/array.rs +++ b/drivers/android/binder/range_alloc/array.rs @@ -118,7 +118,7 @@ pub(crate) fn reserve_new( size: usize, is_oneway: bool, pid: Pid, - ) -> Result { + ) -> Result<(usize, bool)> { // Compute new value of free_oneway_space, which is set only on success. let new_oneway_space = if is_oneway { match self.free_oneway_space.checked_sub(size) { @@ -146,7 +146,38 @@ pub(crate) fn reserve_new( .ok() .unwrap(); - Ok(insert_at_offset) + // Start detecting spammers once we have less than 20% + // of async space left (which is less than 10% of total + // buffer size). + // + // (This will short-circuit, so `low_oneway_space` is + // only called when necessary.) + let oneway_spam_detected = + is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid); + + Ok((insert_at_offset, oneway_spam_detected)) + } + + /// Find the amount and size of buffers allocated by the current caller. + /// + /// The idea is that once we cross the threshold, whoever is responsible + /// for the low async space is likely to try to send another async transaction, + /// and at some point we'll catch them in the act. This is more efficient + /// than keeping a map per pid. + fn low_oneway_space(&self, calling_pid: Pid) -> bool { + let mut total_alloc_size = 0; + let mut num_buffers = 0; + + // Warn if this pid has more than 50 transactions, or more than 50% of + // async space (which is 25% of total buffer size). Oneway spam is only + // detected when the threshold is exceeded. + for range in &self.ranges { + if range.state.is_oneway() && range.state.pid() == calling_pid { + total_alloc_size += range.size; + num_buffers += 1; + } + } + num_buffers > 50 || total_alloc_size > self.size / 4 } pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result { diff --git a/drivers/android/binder/range_alloc/mod.rs b/drivers/android/binder/range_alloc/mod.rs index 2301e2bc1a1f..1f4734468ff1 100644 --- a/drivers/android/binder/range_alloc/mod.rs +++ b/drivers/android/binder/range_alloc/mod.rs @@ -188,11 +188,11 @@ pub(crate) fn reserve_new(&mut self, mut args: ReserveNewArgs) -> Result { - let offset = + let (offset, oneway_spam_detected) = array.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid)?; Ok(ReserveNew::Success(ReserveNewSuccess { offset, - oneway_spam_detected: false, + oneway_spam_detected, _empty_array_alloc: args.empty_array_alloc, _new_tree_alloc: args.new_tree_alloc, _tree_alloc: args.tree_alloc, diff --git a/drivers/android/binder/range_alloc/tree.rs b/drivers/android/binder/range_alloc/tree.rs index 838fdd2b47ea..48796fcdb362 100644 --- a/drivers/android/binder/range_alloc/tree.rs +++ b/drivers/android/binder/range_alloc/tree.rs @@ -164,15 +164,6 @@ pub(crate) fn reserve_new( self.free_oneway_space }; - // Start detecting spammers once we have less than 20% - // of async space left (which is less than 10% of total - // buffer size). - // - // (This will short-circut, so `low_oneway_space` is - // only called when necessary.) - let oneway_spam_detected = - is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid); - let (found_size, found_off, tree_node, free_tree_node) = match self.find_best_match(size) { None => { pr_warn!("ENOSPC from range_alloc.reserve_new - size: {}", size); @@ -203,6 +194,15 @@ pub(crate) fn reserve_new( self.free_tree.insert(free_tree_node); } + // Start detecting spammers once we have less than 20% + // of async space left (which is less than 10% of total + // buffer size). + // + // (This will short-circuit, so `low_oneway_space` is + // only called when necessary.) + let oneway_spam_detected = + is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid); + Ok((found_off, oneway_spam_detected)) } From 8ef2c15aeae07647f530d30f6daaf79eb801bcd1 Mon Sep 17 00:00:00 2001 From: Alice Ryhl Date: Wed, 18 Feb 2026 11:53:26 +0000 Subject: [PATCH 043/487] rust_binder: check ownership before using vma When installing missing pages (or zapping them), Rust Binder will look up the vma in the mm by address, and then call vm_insert_page (or zap_page_range_single). However, if the vma is closed and replaced with a different vma at the same address, this can lead to Rust Binder installing pages into the wrong vma. By installing the page into a writable vma, it becomes possible to write to your own binder pages, which are normally read-only. Although you're not supposed to be able to write to those pages, the intent behind the design of Rust Binder is that even if you get that ability, it should not lead to anything bad. Unfortunately, due to another bug, that is not the case. To fix this, store a pointer in vm_private_data and check that the vma returned by vma_lookup() has the right vm_ops and vm_private_data before trying to use the vma. This should ensure that Rust Binder will refuse to interact with any other VMA. The plan is to introduce more vma abstractions to avoid this unsafe access to vm_ops and vm_private_data, but for now let's start with the simplest possible fix. C Binder performs the same check in a slightly different way: it provides a vm_ops->close that sets a boolean to true, then checks that boolean after calling vma_lookup(), but this is more fragile than the solution in this patch. (We probably still want to do both, but the vm_ops->close callback will be added later as part of the follow-up vma API changes.) It's still possible to remap the vma so that pages appear in the right vma, but at the wrong offset, but this is a separate issue and will be fixed when Rust Binder gets a vm_ops->close callback. Cc: stable Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver") Reported-by: Jann Horn Reviewed-by: Jann Horn Signed-off-by: Alice Ryhl Acked-by: Danilo Krummrich Acked-by: Liam R. Howlett Link: https://patch.msgid.link/20260218-binder-vma-check-v2-1-60f9d695a990@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder/page_range.rs | 83 +++++++++++++++++++++------- 1 file changed, 63 insertions(+), 20 deletions(-) diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs index fdd97112ef5c..67aae783e8b8 100644 --- a/drivers/android/binder/page_range.rs +++ b/drivers/android/binder/page_range.rs @@ -142,6 +142,30 @@ pub(crate) struct ShrinkablePageRange { _pin: PhantomPinned, } +// We do not define any ops. For now, used only to check identity of vmas. +static BINDER_VM_OPS: bindings::vm_operations_struct = pin_init::zeroed(); + +// To ensure that we do not accidentally install pages into or zap pages from the wrong vma, we +// check its vm_ops and private data before using it. +fn check_vma(vma: &virt::VmaRef, owner: *const ShrinkablePageRange) -> Option<&virt::VmaMixedMap> { + // SAFETY: Just reading the vm_ops pointer of any active vma is safe. + let vm_ops = unsafe { (*vma.as_ptr()).vm_ops }; + if !ptr::eq(vm_ops, &BINDER_VM_OPS) { + return None; + } + + // SAFETY: Reading the vm_private_data pointer of a binder-owned vma is safe. + let vm_private_data = unsafe { (*vma.as_ptr()).vm_private_data }; + // The ShrinkablePageRange is only dropped when the Process is dropped, which only happens once + // the file's ->release handler is invoked, which means the ShrinkablePageRange outlives any + // VMA associated with it, so there can't be any false positives due to pointer reuse here. + if !ptr::eq(vm_private_data, owner.cast()) { + return None; + } + + vma.as_mixedmap_vma() +} + struct Inner { /// Array of pages. /// @@ -308,6 +332,18 @@ pub(crate) fn register_with_vma(&self, vma: &virt::VmaNew) -> Result { inner.size = num_pages; inner.vma_addr = vma.start(); + // This pointer is only used for comparison - it's not dereferenced. + // + // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on + // `vm_private_data`. + unsafe { + (*vma.as_ptr()).vm_private_data = ptr::from_ref(self).cast_mut().cast::() + }; + + // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on + // `vm_ops`. + unsafe { (*vma.as_ptr()).vm_ops = &BINDER_VM_OPS }; + Ok(num_pages) } @@ -399,22 +435,24 @@ unsafe fn use_page_slow(&self, i: usize) -> Result<()> { // // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a // workqueue. - MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?) - .mmap_read_lock() - .vma_lookup(vma_addr) - .ok_or(ESRCH)? - .as_mixedmap_vma() - .ok_or(ESRCH)? - .vm_insert_page(user_page_addr, &new_page) - .inspect_err(|err| { - pr_warn!( - "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}", - user_page_addr, - vma_addr, - i, - err - ) - })?; + check_vma( + MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?) + .mmap_read_lock() + .vma_lookup(vma_addr) + .ok_or(ESRCH)?, + self, + ) + .ok_or(ESRCH)? + .vm_insert_page(user_page_addr, &new_page) + .inspect_err(|err| { + pr_warn!( + "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}", + user_page_addr, + vma_addr, + i, + err + ) + })?; let inner = self.lock.lock(); @@ -667,12 +705,15 @@ fn drop(self: Pin<&mut Self>) { let mmap_read; let mm_mutex; let vma_addr; + let range_ptr; { // CAST: The `list_head` field is first in `PageInfo`. let info = item as *mut PageInfo; // SAFETY: The `range` field of `PageInfo` is immutable. - let range = unsafe { &*((*info).range) }; + range_ptr = unsafe { (*info).range }; + // SAFETY: The `range` outlives its `PageInfo` values. + let range = unsafe { &*range_ptr }; mm = match range.mm.mmget_not_zero() { Some(mm) => MmWithUser::into_mmput_async(mm), @@ -717,9 +758,11 @@ fn drop(self: Pin<&mut Self>) { // SAFETY: The lru lock is locked when this method is called. unsafe { bindings::spin_unlock(&raw mut (*lru).lock) }; - if let Some(vma) = mmap_read.vma_lookup(vma_addr) { - let user_page_addr = vma_addr + (page_index << PAGE_SHIFT); - vma.zap_page_range_single(user_page_addr, PAGE_SIZE); + if let Some(unchecked_vma) = mmap_read.vma_lookup(vma_addr) { + if let Some(vma) = check_vma(unchecked_vma, range_ptr) { + let user_page_addr = vma_addr + (page_index << PAGE_SHIFT); + vma.zap_page_range_single(user_page_addr, PAGE_SIZE); + } } drop(mmap_read); From 4cb9e13fec0de7c942f5f927469beb8e48ddd20f Mon Sep 17 00:00:00 2001 From: Alice Ryhl Date: Wed, 18 Feb 2026 11:53:27 +0000 Subject: [PATCH 044/487] rust_binder: avoid reading the written value in offsets array When sending a transaction, its offsets array is first copied into the target proc's vma, and then the values are read back from there. This is normally fine because the vma is a read-only mapping, so the target process cannot change the value under us. However, if the target process somehow gains the ability to write to its own vma, it could change the offset before it's read back, causing the kernel to misinterpret what the sender meant. If the sender happens to send a payload with a specific shape, this could in the worst case lead to the receiver being able to privilege escalate into the sender. The intent is that gaining the ability to change the read-only vma of your own process should not be exploitable, so remove this TOCTOU read even though it's unexploitable without another Binder bug. Cc: stable Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver") Reported-by: Jann Horn Reviewed-by: Jann Horn Signed-off-by: Alice Ryhl Acked-by: Liam R. Howlett Link: https://patch.msgid.link/20260218-binder-vma-check-v2-2-60f9d695a990@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder/thread.rs | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs index 0b62d24b2118..c004214b1662 100644 --- a/drivers/android/binder/thread.rs +++ b/drivers/android/binder/thread.rs @@ -1015,12 +1015,9 @@ pub(crate) fn copy_transaction_data( // Copy offsets if there are any. if offsets_size > 0 { - { - let mut reader = - UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size) - .reader(); - alloc.copy_into(&mut reader, aligned_data_size, offsets_size)?; - } + let mut offsets_reader = + UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size) + .reader(); let offsets_start = aligned_data_size; let offsets_end = aligned_data_size + offsets_size; @@ -1041,11 +1038,9 @@ pub(crate) fn copy_transaction_data( .step_by(size_of::()) .enumerate() { - let offset: usize = view - .alloc - .read::(index_offset)? - .try_into() - .map_err(|_| EINVAL)?; + let offset = offsets_reader.read::()?; + view.alloc.write(index_offset, &offset)?; + let offset: usize = offset.try_into().map_err(|_| EINVAL)?; if offset < end_of_previous_object || !is_aligned(offset, size_of::()) { pr_warn!("Got transaction with invalid offset."); From 2e303f0febb65a434040774b793ba8356698802b Mon Sep 17 00:00:00 2001 From: Alice Ryhl Date: Tue, 24 Feb 2026 18:16:39 +0000 Subject: [PATCH 045/487] rust_binder: call set_notification_done() without proc lock Consider the following sequence of events on a death listener: 1. The remote process dies and sends a BR_DEAD_BINDER message. 2. The local process invokes the BC_CLEAR_DEATH_NOTIFICATION command. 3. The local process then invokes the BC_DEAD_BINDER_DONE. Then, the kernel will reply to the BC_DEAD_BINDER_DONE command with a BR_CLEAR_DEATH_NOTIFICATION_DONE reply using push_work_if_looper(). However, this can result in a deadlock if the current thread is not a looper. This is because dead_binder_done() still holds the proc lock during set_notification_done(), which called push_work_if_looper(). Normally, push_work_if_looper() takes the thread lock, which is fine to take under the proc lock. But if the current thread is not a looper, then it falls back to delivering the reply to the process work queue, which involves taking the proc lock. Since the proc lock is already held, this is a deadlock. Fix this by releasing the proc lock during set_notification_done(). It was not intentional that it was held during that function to begin with. I don't think this ever happens in Android because BC_DEAD_BINDER_DONE is only invoked in response to BR_DEAD_BINDER messages, and the kernel always delivers BR_DEAD_BINDER to a looper. So there's no scenario where Android userspace will call BC_DEAD_BINDER_DONE on a non-looper thread. Cc: stable Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver") Reported-by: syzbot+c8287e65a57a89e7fb72@syzkaller.appspotmail.com Tested-by: syzbot+c8287e65a57a89e7fb72@syzkaller.appspotmail.com Signed-off-by: Alice Ryhl Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Link: https://patch.msgid.link/20260224-binder-dead-binder-done-proc-lock-v1-1-bbe1b8a6e74a@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder/process.rs | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs index 41de5593197c..f06498129aa9 100644 --- a/drivers/android/binder/process.rs +++ b/drivers/android/binder/process.rs @@ -1295,7 +1295,8 @@ pub(crate) fn clear_death(&self, reader: &mut UserSliceReader, thread: &Thread) } pub(crate) fn dead_binder_done(&self, cookie: u64, thread: &Thread) { - if let Some(death) = self.inner.lock().pull_delivered_death(cookie) { + let death = self.inner.lock().pull_delivered_death(cookie); + if let Some(death) = death { death.set_notification_done(thread); } } From a0b9b0f1433c845bda708753db32befef78e0f1f Mon Sep 17 00:00:00 2001 From: Alice Ryhl Date: Wed, 18 Feb 2026 15:13:23 +0000 Subject: [PATCH 046/487] rust_binder: use lock_vma_under_rcu() in use_page_slow() There's no reason to lock the whole mm when we are doing operations on the vma if we can help it, so to reduce contention, use the lock_vma_under_rcu() abstraction. Signed-off-by: Alice Ryhl Reviewed-by: Jann Horn Reviewed-by: Liam R. Howlett Link: https://patch.msgid.link/20260218-binder-vma-rcu-v1-1-8bd45b2b1183@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder/page_range.rs | 37 ++++++++++++++-------------- 1 file changed, 19 insertions(+), 18 deletions(-) diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs index 67aae783e8b8..9dfc154e5dd4 100644 --- a/drivers/android/binder/page_range.rs +++ b/drivers/android/binder/page_range.rs @@ -435,24 +435,25 @@ unsafe fn use_page_slow(&self, i: usize) -> Result<()> { // // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a // workqueue. - check_vma( - MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?) - .mmap_read_lock() - .vma_lookup(vma_addr) - .ok_or(ESRCH)?, - self, - ) - .ok_or(ESRCH)? - .vm_insert_page(user_page_addr, &new_page) - .inspect_err(|err| { - pr_warn!( - "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}", - user_page_addr, - vma_addr, - i, - err - ) - })?; + let mm = MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?); + { + let vma_read; + let mmap_read; + let vma = if let Some(ret) = mm.lock_vma_under_rcu(vma_addr) { + vma_read = ret; + check_vma(&vma_read, self) + } else { + mmap_read = mm.mmap_read_lock(); + mmap_read + .vma_lookup(vma_addr) + .and_then(|vma| check_vma(vma, self)) + }; + + match vma { + Some(vma) => vma.vm_insert_page(user_page_addr, &new_page)?, + None => return Err(ESRCH), + } + } let inner = self.lock.lock(); From 663eb8763c251dbcd0536b14ec134e63e4173348 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 4 Feb 2026 17:41:58 +0100 Subject: [PATCH 047/487] i3c: simplify combined i3c/i2c dependencies All combined i2c/i3c drivers appear to suffer from the same link time problem when CONFIG_I3C is set to 'm': arm-linux-gnueabi-ld: drivers/iio/magnetometer/mmc5633.o: in function `mmc5633_i3c_driver_init': mmc5633.c:(.init.text+0x30): undefined reference to `i3c_driver_register_with_owner' This was previously fixed every time by marking individual drivers as 'depends on I2C; depends on I3C || !I3C', but this gets tedious and is somewhat confusing. Add a Kconfig symbol 'I3C_OR_I2C' to help replace those dependencies, and use this in all the existing drivers that had already fixed it as well as the new mmc5633 driver. Reviewed-by: Jonathan Cameron Signed-off-by: Arnd Bergmann Acked-by: Guenter Roeck Acked-by: Jonathan Cameron Link: https://patch.msgid.link/20260204164216.544409-1-arnd@kernel.org Signed-off-by: Alexandre Belloni --- drivers/hwmon/Kconfig | 6 ++---- drivers/i3c/Kconfig | 12 ++++++++++++ drivers/iio/magnetometer/Kconfig | 3 +-- drivers/misc/amd-sbi/Kconfig | 3 +-- 4 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 41c381764c2b..ecfba861f66d 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1493,8 +1493,7 @@ config SENSORS_LM73 config SENSORS_LM75 tristate "National Semiconductor LM75 and compatibles" - depends on I2C - depends on I3C || !I3C + depends on I3C_OR_I2C select REGMAP_I2C select REGMAP_I3C if I3C help @@ -2392,8 +2391,7 @@ config SENSORS_TMP103 config SENSORS_TMP108 tristate "Texas Instruments TMP108" - depends on I2C - depends on I3C || !I3C + depends on I3C_OR_I2C select REGMAP_I2C select REGMAP_I3C if I3C help diff --git a/drivers/i3c/Kconfig b/drivers/i3c/Kconfig index 30a441506f61..626c54b386d5 100644 --- a/drivers/i3c/Kconfig +++ b/drivers/i3c/Kconfig @@ -22,3 +22,15 @@ menuconfig I3C if I3C source "drivers/i3c/master/Kconfig" endif # I3C + +config I3C_OR_I2C + tristate + default m if I3C=m + default I2C + help + Device drivers using module_i3c_i2c_driver() can use either + i2c or i3c hosts, but cannot be built-in for the kernel when + CONFIG_I3C=m. + + Add 'depends on I2C_OR_I3C' in Kconfig for those drivers to + get the correct dependencies. diff --git a/drivers/iio/magnetometer/Kconfig b/drivers/iio/magnetometer/Kconfig index 9345fb6d5317..fb313e591e85 100644 --- a/drivers/iio/magnetometer/Kconfig +++ b/drivers/iio/magnetometer/Kconfig @@ -143,8 +143,7 @@ config MMC5633 tristate "MEMSIC MMC5633 3-axis magnetic sensor" select REGMAP_I2C select REGMAP_I3C if I3C - depends on I2C - depends on I3C || !I3C + depends on I3C_OR_I2C help Say yes here to build support for the MEMSIC MMC5633 3-axis magnetic sensor. diff --git a/drivers/misc/amd-sbi/Kconfig b/drivers/misc/amd-sbi/Kconfig index be022c71a90c..30e7fad7356c 100644 --- a/drivers/misc/amd-sbi/Kconfig +++ b/drivers/misc/amd-sbi/Kconfig @@ -1,10 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only config AMD_SBRMI_I2C tristate "AMD side band RMI support" - depends on I2C + depends on I3C_OR_I2C depends on ARM || ARM64 || COMPILE_TEST select REGMAP_I2C - depends on I3C || !I3C select REGMAP_I3C if I3C help Side band RMI over I2C/I3C support for AMD out of band management. From 7b6275c80a0c81c5f8943272292dfe67730ce849 Mon Sep 17 00:00:00 2001 From: Eric Badger Date: Mon, 23 Feb 2026 10:28:55 -0800 Subject: [PATCH 048/487] xprtrdma: Decrement re_receiving on the early exit paths In the event that rpcrdma_post_recvs() fails to create a work request (due to memory allocation failure, say) or otherwise exits early, we should decrement ep->re_receiving before returning. Otherwise we will hang in rpcrdma_xprt_drain() as re_receiving will never reach zero and the completion will never be triggered. On a system with high memory pressure, this can appear as the following hung task: INFO: task kworker/u385:17:8393 blocked for more than 122 seconds. Tainted: G S E 6.19.0 #3 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u385:17 state:D stack:0 pid:8393 tgid:8393 ppid:2 task_flags:0x4248060 flags:0x00080000 Workqueue: xprtiod xprt_autoclose [sunrpc] Call Trace: __schedule+0x48b/0x18b0 ? ib_post_send_mad+0x247/0xae0 [ib_core] schedule+0x27/0xf0 schedule_timeout+0x104/0x110 __wait_for_common+0x98/0x180 ? __pfx_schedule_timeout+0x10/0x10 wait_for_completion+0x24/0x40 rpcrdma_xprt_disconnect+0x444/0x460 [rpcrdma] xprt_rdma_close+0x12/0x40 [rpcrdma] xprt_autoclose+0x5f/0x120 [sunrpc] process_one_work+0x191/0x3e0 worker_thread+0x2e3/0x420 ? __pfx_worker_thread+0x10/0x10 kthread+0x10d/0x230 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x273/0x2b0 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 Fixes: 15788d1d1077 ("xprtrdma: Do not refresh Receive Queue while it is draining") Signed-off-by: Eric Badger Reviewed-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 15bbf953dfad..b51a162885bb 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1362,7 +1362,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) needed += RPCRDMA_MAX_RECV_BATCH; if (atomic_inc_return(&ep->re_receiving) > 1) - goto out; + goto out_dec; /* fast path: all needed reps can be found on the free list */ wr = NULL; @@ -1385,7 +1385,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) ++count; } if (!wr) - goto out; + goto out_dec; rc = ib_post_recv(ep->re_id->qp, wr, (const struct ib_recv_wr **)&bad_wr); @@ -1400,9 +1400,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) --count; } } + +out_dec: if (atomic_dec_return(&ep->re_receiving) > 0) complete(&ep->re_done); - out: trace_xprtrdma_post_recvs(r_xprt, count); ep->re_receive_count += count; From 4529e0015432977af3ecc3b9f940fc2a1ef1b265 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 18 Feb 2026 11:41:15 -0500 Subject: [PATCH 049/487] NFS: Fix NFS KConfig typos Two issues were noticed after the NFS v4.0 KConfig changes were merged upstream. First, the text of CONFIG_NFS_V4 should not encourage people to select it if they are unsure. Second, the new CONFIG_NFS_V4_0 option should default to "on" instead of "off" to avoid breaking people's setups if they are using NFS v4.0. Reported-by: Niklas Cassel Reported-by: Geert Uytterhoeven Fixes: 4e0269352534 ("NFS: Add a way to disable NFS v4.0 via KConfig") Fixes: 7537db24806f ("NFS: Merge CONFIG_NFS_V4_1 with CONFIG_NFS_V4") Signed-off-by: Anna Schumaker --- fs/nfs/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 12cb0ca738af..6bb30543eff0 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -87,7 +87,7 @@ config NFS_V4 space programs which can be found in the Linux nfs-utils package, available from http://linux-nfs.org/. - If unsure, say Y. + If unsure, say N. config NFS_SWAP bool "Provide swap over NFS support" @@ -100,6 +100,7 @@ config NFS_SWAP config NFS_V4_0 bool "NFS client support for NFSv4.0" depends on NFS_V4 + default y help This option enables support for minor version 0 of the NFSv4 protocol (RFC 3530) in the kernel's NFS client. From dff8e3c025862001956b8edb29c1287c9efcd902 Mon Sep 17 00:00:00 2001 From: Kaushlendra Kumar Date: Wed, 4 Feb 2026 10:51:40 +0530 Subject: [PATCH 050/487] cpupower: fix swapped power/energy unit labels Fix error where microWatts and microJoules units were interchanged. Signed-off-by: Kaushlendra Kumar Signed-off-by: Shuah Khan --- tools/power/cpupower/utils/powercap-info.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/power/cpupower/utils/powercap-info.c b/tools/power/cpupower/utils/powercap-info.c index 3ea4486f1a0e..e53033488218 100644 --- a/tools/power/cpupower/utils/powercap-info.c +++ b/tools/power/cpupower/utils/powercap-info.c @@ -38,11 +38,11 @@ static int powercap_print_one_zone(struct powercap_zone *zone) printf(" (%s)\n", mode ? "enabled" : "disabled"); if (zone->has_power_uw) - printf(_("%sPower can be monitored in micro Jules\n"), + printf(_("%sPower can be monitored in micro Watts\n"), pr_prefix); if (zone->has_energy_uj) - printf(_("%sPower can be monitored in micro Watts\n"), + printf(_("%sPower can be monitored in micro Jules\n"), pr_prefix); printf("\n"); From f8211e95dfda702ba81ea2e3e7a8c6c967f385fa Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 2 Mar 2026 09:02:39 -0800 Subject: [PATCH 051/487] Documentation: KVM: Formalizing taking vcpu->mutex *outside* of kvm->slots_lock Explicitly document the ordering of vcpu->mutex being taken *outside* of kvm->slots_lock. While somewhat unintuitive since vCPUs conceptually have narrower scope than VMs, the scope of the owning object (vCPU versus VM) doesn't automatically carry over to the lock. In this case, vcpu->mutex has far broader scope than kvm->slots_lock. As Paolo put it, it's a "don't worry about multiple ioctls at the same time" mutex that's intended to be taken at the outer edges of KVM. More importantly, arm64 and x86 have gained flows that take kvm->slots_lock inside of vcpu->mutex. x86's kvm_inhibit_apic_access_page() is particularly nasty, as slots_lock is taken quite deep within KVM_RUN, i.e. simply swapping the ordering isn't an option. Commit to the vcpu->mutex => kvm->slots_lock ordering, as vcpu->mutex really is intended to be a "top-level" lock, whereas kvm->slots_lock is "just" a helper lock. Opportunistically document that vcpu->mutex is also taken outside of slots_arch_lock, e.g. when allocating shadow roots on x86 (which is the entire reason slots_arch_lock exists, as shadow roots must be allocated while holding kvm->srcu) kvm_mmu_new_pgd() | -> kvm_mmu_reload() | -> kvm_mmu_load() | -> mmu_alloc_shadow_roots() | -> mmu_first_shadow_root_alloc() but also when manipulating memslots in vCPU context, e.g. when inhibiting the APIC-access page via the aforementioned kvm_inhibit_apic_access_page() kvm_inhibit_apic_access_page() | -> __x86_set_memory_region() | -> kvm_set_internal_memslot() | -> kvm_set_memory_region() | -> kvm_set_memslot() Cc: Oliver Upton Cc: Marc Zyngier Link: https://patch.msgid.link/20260302170239.596810-1-seanjc@google.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/locking.rst | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index ae8bce7fecbe..662231e958a0 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -17,6 +17,8 @@ The acquisition orders for mutexes are as follows: - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock +- vcpu->mutex is taken outside kvm->slots_lock and kvm->slots_arch_lock + - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring them together is quite rare. From b85cfdf46b2402a9e57d6b7d43e2c977f9554645 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Mon, 9 Feb 2026 18:00:14 +0000 Subject: [PATCH 052/487] btrfs: print-tree: add remap tree definitions Add the definitions for the remap tree to print-tree.c, so that we get more useful information if a tree is dumped to dmesg. Reviewed-by: Johannes Thumshirn Reviewed-by: Qu Wenruo Signed-off-by: Mark Harmstone Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/print-tree.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index f189bf09ce6a..b7dfe877cf8d 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -38,6 +38,7 @@ static const struct root_name_map root_map[] = { { BTRFS_BLOCK_GROUP_TREE_OBJECTID, "BLOCK_GROUP_TREE" }, { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }, { BTRFS_RAID_STRIPE_TREE_OBJECTID, "RAID_STRIPE_TREE" }, + { BTRFS_REMAP_TREE_OBJECTID, "REMAP_TREE" }, }; const char *btrfs_root_name(const struct btrfs_key *key, char *buf) @@ -415,6 +416,9 @@ static void key_type_string(const struct btrfs_key *key, char *buf, int buf_size [BTRFS_UUID_KEY_SUBVOL] = "UUID_KEY_SUBVOL", [BTRFS_UUID_KEY_RECEIVED_SUBVOL] = "UUID_KEY_RECEIVED_SUBVOL", [BTRFS_RAID_STRIPE_KEY] = "RAID_STRIPE", + [BTRFS_IDENTITY_REMAP_KEY] = "IDENTITY_REMAP", + [BTRFS_REMAP_KEY] = "REMAP", + [BTRFS_REMAP_BACKREF_KEY] = "REMAP_BACKREF", }; if (key->type == 0 && key->objectid == BTRFS_FREE_SPACE_OBJECTID) @@ -435,6 +439,7 @@ void btrfs_print_leaf(const struct extent_buffer *l) struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; struct btrfs_dev_extent *dev_extent; + struct btrfs_remap_item *remap; struct btrfs_key key; if (!l) @@ -569,6 +574,11 @@ void btrfs_print_leaf(const struct extent_buffer *l) print_raid_stripe_key(l, btrfs_item_size(l, i), btrfs_item_ptr(l, i, struct btrfs_stripe_extent)); break; + case BTRFS_REMAP_KEY: + case BTRFS_REMAP_BACKREF_KEY: + remap = btrfs_item_ptr(l, i, struct btrfs_remap_item); + pr_info("\t\taddress %llu\n", btrfs_remap_address(l, remap)); + break; } } } From b8883b61f2fc50dcf22938cbed40fec05020552f Mon Sep 17 00:00:00 2001 From: Sun YangKai Date: Mon, 9 Feb 2026 20:53:39 +0800 Subject: [PATCH 053/487] btrfs: hold space_info->lock when clearing periodic reclaim ready btrfs_set_periodic_reclaim_ready() requires space_info->lock to be held, as enforced by lockdep_assert_held(). However, btrfs_reclaim_sweep() was calling it after do_reclaim_sweep() returns, at which point space_info->lock is no longer held. Fix this by explicitly acquiring space_info->lock before clearing the periodic reclaim ready flag in btrfs_reclaim_sweep(). Reported-by: Chris Mason Link: https://lore.kernel.org/linux-btrfs/20260208182556.891815-1-clm@meta.com/ Fixes: 19eff93dc738 ("btrfs: fix periodic reclaim condition") Reviewed-by: Boris Burkov Signed-off-by: Sun YangKai Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/space-info.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index bb5aac7ee9d2..36bfd2385b2a 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -2194,8 +2194,11 @@ void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info) if (!btrfs_should_periodic_reclaim(space_info)) continue; for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++) { - if (do_reclaim_sweep(space_info, raid)) + if (do_reclaim_sweep(space_info, raid)) { + spin_lock(&space_info->lock); btrfs_set_periodic_reclaim_ready(space_info, false); + spin_unlock(&space_info->lock); + } } } } From 17da926ca8757cc0432ce3e13230759894a6b017 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 24 Feb 2026 13:51:13 +0100 Subject: [PATCH 054/487] btrfs: zoned: move btrfs_zoned_reserve_data_reloc_bg() after kthread start btrfs_zoned_reserve_data_reloc_bg() is called on each mount of a file system and allocates a new block-group, to assign it to be the dedicated relocation target, if no pre-existing usable block-group for this task is found. If for some reason the transaction is aborted, btrfs_end_transaction() will wake up the transaction kthread. But the transaction kthread is not yet initialized at the time btrfs_zoned_reserve_data_reloc_bg() is called, leading to the following NULL-pointer dereference: RSP: 0018:ffffc9000c617c98 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 000000000000073c RCX: 0000000000000002 RDX: 0000000000000001 RSI: 0000000000000003 RDI: 0000000000000001 RBP: 0000000000000207 R08: ffffffff8223c71d R09: 0000000000000635 R10: ffff888108588000 R11: 0000000000000003 R12: 0000000000000003 R13: 000000000000073c R14: 0000000000000000 R15: ffff888114dd6000 FS: 00007f2993745840(0000) GS:ffff8882b508d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000073c CR3: 0000000121a82006 CR4: 0000000000770eb0 PKRU: 55555554 Call Trace: try_to_wake_up (./include/linux/spinlock.h:557 kernel/sched/core.c:4106) __btrfs_end_transaction (fs/btrfs/transaction.c:1115 (discriminator 2)) btrfs_zoned_reserve_data_reloc_bg (fs/btrfs/zoned.c:2840) open_ctree (fs/btrfs/disk-io.c:3588) btrfs_get_tree.cold (fs/btrfs/super.c:982 fs/btrfs/super.c:1944 fs/btrfs/super.c:2087 fs/btrfs/super.c:2121) vfs_get_tree (fs/super.c:1752) __do_sys_fsconfig (fs/fsopen.c:231 fs/fsopen.c:295 fs/fsopen.c:473) do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131) RIP: 0033:0x7f299392740e Move the call to btrfs_zoned_reserve_data_reloc_bg() after the transaction_kthread has been initialized to fix this problem. Fixes: 694ce5e143d6 ("btrfs: zoned: reserve data_reloc block group on mount") Reviewed-by: Filipe Manana Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 49987334dd15..2aeb85e3ece9 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3594,7 +3594,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } } - btrfs_zoned_reserve_data_reloc_bg(fs_info); btrfs_free_zone_cache(fs_info); btrfs_check_active_zone_reservation(fs_info); @@ -3622,6 +3621,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_cleaner; } + /* + * Starts a transaction, must be called after the transaction kthread + * is initialized. + */ + btrfs_zoned_reserve_data_reloc_bg(fs_info); + ret = btrfs_read_qgroup_config(fs_info); if (ret) goto fail_trans_kthread; From 5131fa077f9bb386a1b901bf5b247041f0ec8f80 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Tue, 24 Feb 2026 14:25:35 -0800 Subject: [PATCH 055/487] btrfs: set BTRFS_ROOT_ORPHAN_CLEANUP during subvol create We have recently observed a number of subvolumes with broken dentries. ls-ing the parent dir looks like: drwxrwxrwt 1 root root 16 Jan 23 16:49 . drwxr-xr-x 1 root root 24 Jan 23 16:48 .. d????????? ? ? ? ? ? broken_subvol and similarly stat-ing the file fails. In this state, deleting the subvol fails with ENOENT, but attempting to create a new file or subvol over it errors out with EEXIST and even aborts the fs. Which leaves us a bit stuck. dmesg contains a single notable error message reading: "could not do orphan cleanup -2" 2 is ENOENT and the error comes from the failure handling path of btrfs_orphan_cleanup(), with the stack leading back up to btrfs_lookup(). btrfs_lookup btrfs_lookup_dentry btrfs_orphan_cleanup // prints that message and returns -ENOENT After some detailed inspection of the internal state, it became clear that: - there are no orphan items for the subvol - the subvol is otherwise healthy looking, it is not half-deleted or anything, there is no drop progress, etc. - the subvol was created a while ago and does the meaningful first btrfs_orphan_cleanup() call that sets BTRFS_ROOT_ORPHAN_CLEANUP much later. - after btrfs_orphan_cleanup() fails, btrfs_lookup_dentry() returns -ENOENT, which results in a negative dentry for the subvolume via d_splice_alias(NULL, dentry), leading to the observed behavior. The bug can be mitigated by dropping the dentry cache, at which point we can successfully delete the subvolume if we want. i.e., btrfs_lookup() btrfs_lookup_dentry() if (!sb_rdonly(inode->vfs_inode)->vfs_inode) btrfs_orphan_cleanup(sub_root) test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) btrfs_search_slot() // finds orphan item for inode N ... prints "could not do orphan cleanup -2" if (inode == ERR_PTR(-ENOENT)) inode = NULL; return d_splice_alias(NULL, dentry) // NEGATIVE DENTRY for valid subvolume btrfs_orphan_cleanup() does test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) on the root when it runs, so it cannot run more than once on a given root, so something else must run concurrently. However, the obvious routes to deleting an orphan when nlinks goes to 0 should not be able to run without first doing a lookup into the subvolume, which should run btrfs_orphan_cleanup() and set the bit. The final important observation is that create_subvol() calls d_instantiate_new() but does not set BTRFS_ROOT_ORPHAN_CLEANUP, so if the dentry cache gets dropped, the next lookup into the subvolume will make a real call into btrfs_orphan_cleanup() for the first time. This opens up the possibility of concurrently deleting the inode/orphan items but most typical evict() paths will be holding a reference on the parent dentry (child dentry holds parent->d_lockref.count via dget in d_alloc(), released in __dentry_kill()) and prevent the parent from being removed from the dentry cache. The one exception is delayed iputs. Ordered extent creation calls igrab() on the inode. If the file is unlinked and closed while those refs are held, iput() in __dentry_kill() decrements i_count but does not trigger eviction (i_count > 0). The child dentry is freed and the subvol dentry's d_lockref.count drops to 0, making it evictable while the inode is still alive. Since there are two races (the race between writeback and unlink and the race between lookup and delayed iputs), and there are too many moving parts, the following three diagrams show the complete picture. (Only the second and third are races) Phase 1: Create Subvol in dentry cache without BTRFS_ROOT_ORPHAN_CLEANUP set btrfs_mksubvol() lookup_one_len() __lookup_slow() d_alloc_parallel() __d_alloc() // d_lockref.count = 1 create_subvol(dentry) // doesn't touch the bit.. d_instantiate_new(dentry, inode) // dentry in cache with d_lockref.count == 1 Phase 2: Create a delayed iput for a file in the subvol but leave the subvol in state where its dentry can be evicted (d_lockref.count == 0) T1 (task) T2 (writeback) T3 (OE workqueue) write() // dirty pages btrfs_writepages() btrfs_run_delalloc_range() cow_file_range() btrfs_alloc_ordered_extent() igrab() // i_count: 1 -> 2 btrfs_unlink_inode() btrfs_orphan_add() close() __fput() dput() finish_dput() __dentry_kill() dentry_unlink_inode() iput() // 2 -> 1 --parent->d_lockref.count // 1 -> 0; evictable finish_ordered_fn() btrfs_finish_ordered_io() btrfs_put_ordered_extent() btrfs_add_delayed_iput() Phase 3: Once the delayed iput is pending and the subvol dentry is evictable, the shrinker can free it, causing the next lookup to go through btrfs_lookup() and call btrfs_orphan_cleanup() for the first time. If the cleaner kthread processes the delayed iput concurrently, the two race: T1 (shrinker) T2 (cleaner kthread) T3 (lookup) super_cache_scan() prune_dcache_sb() __dentry_kill() // subvol dentry freed btrfs_run_delayed_iputs() iput() // i_count -> 0 evict() // sets I_FREEING btrfs_evict_inode() // truncation loop btrfs_lookup() btrfs_lookup_dentry() btrfs_orphan_cleanup() // first call (bit never set) btrfs_iget() // blocks on I_FREEING btrfs_orphan_del() // inode freed // returns -ENOENT btrfs_del_orphan_item() // -ENOENT // "could not do orphan cleanup -2" d_splice_alias(NULL, dentry) // negative dentry for valid subvol The most straightforward fix is to ensure the invariant that a dentry for a subvolume can exist if and only if that subvolume has BTRFS_ROOT_ORPHAN_CLEANUP set on its root (and is known to have no orphans or ran btrfs_orphan_cleanup()). Reviewed-by: Filipe Manana Signed-off-by: Boris Burkov Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index dadf9bf30f08..1d22c5c05b50 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -672,6 +672,13 @@ static noinline int create_subvol(struct mnt_idmap *idmap, goto out; } + /* + * Subvolumes have orphans cleaned on first dentry lookup. A new + * subvolume cannot have any orphans, so we should set the bit before we + * add the subvolume dentry to the dentry cache, so that it is in the + * same state as a subvolume after first lookup. + */ + set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &new_root->state); d_instantiate_new(dentry, new_inode_args.inode); new_inode_args.inode = NULL; From b2840e33127ce0eea880504b7f133e780f567a9b Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 25 Feb 2026 11:59:58 -0800 Subject: [PATCH 056/487] btrfs: add missing RCU unlock in error path in try_release_subpage_extent_buffer() Call rcu_read_lock() before exiting the loop in try_release_subpage_extent_buffer() because there is a rcu_read_unlock() call past the loop. This has been detected by the Clang thread-safety analyzer. Fixes: ad580dfa388f ("btrfs: fix subpage deadlock in try_release_subpage_extent_buffer()") CC: stable@vger.kernel.org # 6.18+ Reviewed-by: Qu Wenruo Reviewed-by: Boris Burkov Signed-off-by: Bart Van Assche Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3df399dc8856..051309e90079 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4494,6 +4494,7 @@ static int try_release_subpage_extent_buffer(struct folio *folio) */ if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { spin_unlock(&eb->refs_lock); + rcu_read_lock(); break; } From ae1238b77feafa2f7f10bcd0432a99e098a98ec6 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Wed, 25 Feb 2026 10:36:06 +0000 Subject: [PATCH 057/487] btrfs: read key again after incrementing slot in move_existing_remaps() Fix move_existing_remaps() so that if we increment the slot because the key we encounter isn't a REMAP_BACKREF, we don't reuse the objectid and offset of the old item. Link: https://lore.kernel.org/linux-btrfs/20260125123908.2096548-1-clm@meta.com/ Reported-by: Chris Mason Fixes: bbea42dfb91f ("btrfs: move existing remaps before relocating block group") Reviewed-by: Johannes Thumshirn Signed-off-by: Mark Harmstone Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/relocation.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index cdb53c0b26ec..fcfbe1b1dab4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4399,6 +4399,8 @@ static int move_existing_remaps(struct btrfs_fs_info *fs_info, leaf = path->nodes[0]; } + + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); } remap = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_remap_item); From 2d1ababdedd4ba38867c2500eb7f95af5ddeeef7 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 26 Feb 2026 11:05:43 +0000 Subject: [PATCH 058/487] btrfs: fix transaction abort on file creation due to name hash collision If we attempt to create several files with names that result in the same hash, we have to pack them in same dir item and that has a limit inherent to the leaf size. However if we reach that limit, we trigger a transaction abort and turns the filesystem into RO mode. This allows for a malicious user to disrupt a system, without the need to have administration privileges/capabilities. Reproducer: $ cat exploit-hash-collisions.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi # Use smallest node size to make the test faster and require fewer file # names that result in hash collision. mkfs.btrfs -f --nodesize 4K $DEV mount $DEV $MNT # List of names that result in the same crc32c hash for btrfs. declare -a names=( 'foobar' '%a8tYkxfGMLWRGr55QSeQc4PBNH9PCLIvR6jZnkDtUUru1t@RouaUe_L:@xGkbO3nCwvLNYeK9vhE628gss:T$yZjZ5l-Nbd6CbC$M=hqE-ujhJICXyIxBvYrIU9-TDC' 'AQci3EUB%shMsg-N%frgU:02ByLs=IPJU0OpgiWit5nexSyxZDncY6WB:=zKZuk5Zy0DD$Ua78%MelgBuMqaHGyKsJUFf9s=UW80PcJmKctb46KveLSiUtNmqrMiL9-Y0I_l5Fnam04CGIg=8@U:Z' 'CvVqJpJzueKcuA$wqwePfyu7VxuWNN3ho$p0zi2H8QFYK$7YlEqOhhb%:hHgjhIjW5vnqWHKNP4' 'ET:vk@rFU4tsvMB0$C_p=xQHaYZjvoF%-BTc%wkFW8yaDAPcCYoR%x$FH5O:' 'HwTon%v7SGSP4FE08jBwwiu5aot2CFKXHTeEAa@38fUcNGOWvE@Mz6WBeDH_VooaZ6AgsXPkVGwy9l@@ZbNXabUU9csiWrrOp0MWUdfi$EZ3w9GkIqtz7I_eOsByOkBOO' 'Ij%2VlFGXSuPvxJGf5UWy6O@1svxGha%b@=%wjkq:CIgE6u7eJOjmQY5qTtxE2Rjbis9@us' 'KBkjG5%9R8K9sOG8UTnAYjxLNAvBmvV5vz3IiZaPmKuLYO03-6asI9lJ_j4@6Xo$KZicaLWJ3Pv8XEwVeUPMwbHYWwbx0pYvNlGMO9F:ZhHAwyctnGy%_eujl%WPd4U2BI7qooOSr85J-C2V$LfY' 'NcRfDfuUQ2=zP8K3CCF5dFcpfiOm6mwenShsAb_F%n6GAGC7fT2JFFn:c35X-3aYwoq7jNX5$ZJ6hI3wnZs$7KgGi7wjulffhHNUxAT0fRRLF39vJ@NvaEMxsMO' 'Oj42AQAEzRoTxa5OuSKIr=A_lwGMy132v4g3Pdq1GvUG9874YseIFQ6QU' 'Ono7avN5GjC:_6dBJ_' 'WHmN2gnmaN-9dVDy4aWo:yNGFzz8qsJyJhWEWcud7$QzN2D9R0efIWWEdu5kwWr73NZm4=@CoCDxrrZnRITr-kGtU_cfW2:%2_am' 'WiFnuTEhAG9FEC6zopQmj-A-$LDQ0T3WULz%ox3UZAPybSV6v1Z$b4L_XBi4M4BMBtJZpz93r9xafpB77r:lbwvitWRyo$odnAUYlYMmU4RvgnNd--e=I5hiEjGLETTtaScWlQp8mYsBovZwM2k' 'XKyH=OsOAF3p%uziGF_ZVr$ivrvhVgD@1u%5RtrV-gl_vqAwHkK@x7YwlxX3qT6WKKQ%PR56NrUBU2dOAOAdzr2=5nJuKPM-T-$ZpQfCL7phxQbUcb:BZOTPaFExc-qK-gDRCDW2' 'd3uUR6OFEwZr%ns1XH_@tbxA@cCPmbBRLdyh7p6V45H$P2$F%w0RqrD3M0g8aGvWpoTFMiBdOTJXjD:JF7=h9a_43xBywYAP%r$SPZi%zDg%ql-KvkdUCtF9OLaQlxmd' 'ePTpbnit%hyNm@WELlpKzNZYOzOTf8EQ$sEfkMy1VOfIUu3coyvIr13-Y7Sv5v-Ivax2Go_GQRFMU1b3362nktT9WOJf3SpT%z8sZmM3gvYQBDgmKI%%RM-G7hyrhgYflOw%z::ZRcv5O:lDCFm' 'evqk743Y@dvZAiG5J05L_ROFV@$2%rVWJ2%3nxV72-W7$e$-SK3tuSHA2mBt$qloC5jwNx33GmQUjD%akhBPu=VJ5g$xhlZiaFtTrjeeM5x7dt4cHpX0cZkmfImndYzGmvwQG:$euFYmXn$_2rA9mKZ' 'gkgUtnihWXsZQTEkrMAWIxir09k3t7jk_IK25t1:cy1XWN0GGqC%FrySdcmU7M8MuPO_ppkLw3=Dfr0UuBAL4%GFk2$Ma10V1jDRGJje%Xx9EV2ERaWKtjpwiZwh0gCSJsj5UL7CR8RtW5opCVFKGGy8Cky' 'hNgsG_8lNRik3PvphqPm0yEH3P%%fYG:kQLY=6O-61Wa6nrV_WVGR6TLB09vHOv%g4VQRP8Gzx7VXUY1qvZyS' 'isA7JVzN12xCxVPJZ_qoLm-pTBuhjjHMvV7o=F:EaClfYNyFGlsfw-Kf%uxdqW-kwk1sPl2vhbjyHU1A6$hz' 'kiJ_fgcdZFDiOptjgH5PN9-PSyLO4fbk_:u5_2tz35lV_iXiJ6cx7pwjTtKy-XGaQ5IefmpJ4N_ZqGsqCsKuqOOBgf9LkUdffHet@Wu' 'lvwtxyhE9:%Q3UxeHiViUyNzJsy:fm38pg_b6s25JvdhOAT=1s0$pG25x=LZ2rlHTszj=gN6M4zHZYr_qrB49i=pA--@WqWLIuX7o1S_SfS@2FSiUZN' 'rC24cw3UBDZ=5qJBUMs9e$=S4Y94ni%Z8639vnrGp=0Hv4z3dNFL0fBLmQ40=EYIY:Z=SLc@QLMSt2zsss2ZXrP7j4=' 'uwGl2s-fFrf@GqS=DQqq2I0LJSsOmM%xzTjS:lzXguE3wChdMoHYtLRKPvfaPOZF2fER@j53evbKa7R%A7r4%YEkD=kicJe@SFiGtXHbKe4gCgPAYbnVn' 'UG37U6KKua2bgc:IHzRs7BnB6FD:2Mt5Cc5NdlsW%$1tyvnfz7S27FvNkroXwAW:mBZLA1@qa9WnDbHCDmQmfPMC9z-Eq6QT0jhhPpqyymaD:R02ghwYo%yx7SAaaq-:x33LYpei$5g8DMl3C' 'y2vjek0FE1PDJC0qpfnN:x8k2wCFZ9xiUF2ege=JnP98R%wxjKkdfEiLWvQzmnW' '8-HCSgH5B%K7P8_jaVtQhBXpBk:pE-$P7ts58U0J@iR9YZntMPl7j$s62yAJO@_9eanFPS54b=UTw$94C-t=HLxT8n6o9P=QnIxq-f1=Ne2dvhe6WbjEQtc' 'YPPh:IFt2mtR6XWSmjHptXL_hbSYu8bMw-JP8@PNyaFkdNFsk$M=xfL6LDKCDM-mSyGA_2MBwZ8Dr4=R1D%7-mCaaKGxb990jzaagRktDTyp' '9hD2ApKa_t_7x-a@GCG28kY:7$M@5udI1myQ$x5udtggvagmCQcq9QXWRC5hoB0o-_zHQUqZI5rMcz_kbMgvN5jr63LeYA4Cj-c6F5Ugmx6DgVf@2Jqm%MafecpgooqreJ53P-QTS' ) # Now create files with all those names in the same parent directory. # It should not fail since a 4K leaf has enough space for them. for name in "${names[@]}"; do touch $MNT/$name done # Now add one more file name that causes a crc32c hash collision. # This should fail, but it should not turn the filesystem into RO mode # (which could be exploited by malicious users) due to a transaction # abort. touch $MNT/'W6tIm-VK2@BGC@IBfcgg6j_p:pxp_QUqtWpGD5Ok_GmijKOJJt' # Check that we are able to create another file, with a name that does not cause # a crc32c hash collision. echo -n "hello world" > $MNT/baz # Unmount and mount again, verify file baz exists and with the right content. umount $MNT mount $DEV $MNT echo "File baz content: $(cat $MNT/baz)" umount $MNT When running the reproducer: $ ./exploit-hash-collisions.sh (...) touch: cannot touch '/mnt/sdi/W6tIm-VK2@BGC@IBfcgg6j_p:pxp_QUqtWpGD5Ok_GmijKOJJt': Value too large for defined data type ./exploit-hash-collisions.sh: line 57: /mnt/sdi/baz: Read-only file system cat: /mnt/sdi/baz: No such file or directory File baz content: And the transaction abort stack trace in dmesg/syslog: $ dmesg (...) [758240.509761] ------------[ cut here ]------------ [758240.510668] BTRFS: Transaction aborted (error -75) [758240.511577] WARNING: fs/btrfs/inode.c:6854 at btrfs_create_new_inode+0x805/0xb50 [btrfs], CPU#6: touch/888644 [758240.513513] Modules linked in: btrfs dm_zero (...) [758240.523221] CPU: 6 UID: 0 PID: 888644 Comm: touch Tainted: G W 6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full) [758240.524621] Tainted: [W]=WARN [758240.525037] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [758240.526331] RIP: 0010:btrfs_create_new_inode+0x80b/0xb50 [btrfs] [758240.527093] Code: 0f 82 cf (...) [758240.529211] RSP: 0018:ffffce64418fbb48 EFLAGS: 00010292 [758240.529935] RAX: 00000000ffffffd3 RBX: 0000000000000000 RCX: 00000000ffffffb5 [758240.531040] RDX: 0000000d04f33e06 RSI: 00000000ffffffb5 RDI: ffffffffc0919dd0 [758240.531920] RBP: ffffce64418fbc10 R08: 0000000000000000 R09: 00000000ffffffb5 [758240.532928] R10: 0000000000000000 R11: ffff8e52c0000000 R12: ffff8e53eee7d0f0 [758240.533818] R13: ffff8e57f70932a0 R14: ffff8e5417629568 R15: 0000000000000000 [758240.534664] FS: 00007f1959a2a740(0000) GS:ffff8e5b27cae000(0000) knlGS:0000000000000000 [758240.535821] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [758240.536644] CR2: 00007f1959b10ce0 CR3: 000000012a2cc005 CR4: 0000000000370ef0 [758240.537517] Call Trace: [758240.537828] [758240.538099] btrfs_create_common+0xbf/0x140 [btrfs] [758240.538760] path_openat+0x111a/0x15b0 [758240.539252] do_filp_open+0xc2/0x170 [758240.539699] ? preempt_count_add+0x47/0xa0 [758240.540200] ? __virt_addr_valid+0xe4/0x1a0 [758240.540800] ? __check_object_size+0x1b3/0x230 [758240.541661] ? alloc_fd+0x118/0x180 [758240.542315] do_sys_openat2+0x70/0xd0 [758240.543012] __x64_sys_openat+0x50/0xa0 [758240.543723] do_syscall_64+0x50/0xf20 [758240.544462] entry_SYSCALL_64_after_hwframe+0x76/0x7e [758240.545397] RIP: 0033:0x7f1959abc687 [758240.546019] Code: 48 89 fa (...) [758240.548522] RSP: 002b:00007ffe16ff8690 EFLAGS: 00000202 ORIG_RAX: 0000000000000101 [758240.566278] RAX: ffffffffffffffda RBX: 00007f1959a2a740 RCX: 00007f1959abc687 [758240.567068] RDX: 0000000000000941 RSI: 00007ffe16ffa333 RDI: ffffffffffffff9c [758240.567860] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 [758240.568707] R10: 00000000000001b6 R11: 0000000000000202 R12: 0000561eec7c4b90 [758240.569712] R13: 0000561eec7c311f R14: 00007ffe16ffa333 R15: 0000000000000000 [758240.570758] [758240.571040] ---[ end trace 0000000000000000 ]--- [758240.571681] BTRFS: error (device sdi state A) in btrfs_create_new_inode:6854: errno=-75 unknown [758240.572899] BTRFS info (device sdi state EA): forced readonly Fix this by checking for hash collision, and if the adding a new name is possible, early in btrfs_create_new_inode() before we do any tree updates, so that we don't need to abort the transaction if we cannot add the new name due to the leaf size limit. A test case for fstests will be sent soon. Fixes: caae78e03234 ("btrfs: move common inode creation code into btrfs_create_new_inode()") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Boris Burkov Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d28d55beaacd..b409efe1857e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6610,6 +6610,25 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, int ret; bool xa_reserved = false; + if (!args->orphan && !args->subvol) { + /* + * Before anything else, check if we can add the name to the + * parent directory. We want to avoid a dir item overflow in + * case we have an existing dir item due to existing name + * hash collisions. We do this check here before we call + * btrfs_add_link() down below so that we can avoid a + * transaction abort (which could be exploited by malicious + * users). + * + * For subvolumes we already do this in btrfs_mksubvol(). + */ + ret = btrfs_check_dir_item_collision(BTRFS_I(dir)->root, + btrfs_ino(BTRFS_I(dir)), + name); + if (ret < 0) + return ret; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; From e1b18b959025e6b5dbad668f391f65d34b39595a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Feb 2026 16:19:31 +0000 Subject: [PATCH 059/487] btrfs: fix transaction abort when snapshotting received subvolumes Currently a user can trigger a transaction abort by snapshotting a previously received snapshot a bunch of times until we reach a BTRFS_UUID_KEY_RECEIVED_SUBVOL item overflow (the maximum item size we can store in a leaf). This is very likely not common in practice, but if it happens, it turns the filesystem into RO mode. The snapshot, send and set_received_subvol and subvol_setflags (used by receive) don't require CAP_SYS_ADMIN, just inode_owner_or_capable(). A malicious user could use this to turn a filesystem into RO mode and disrupt a system. Reproducer script: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi # Use smallest node size to make the test faster. mkfs.btrfs -f --nodesize 4K $DEV mount $DEV $MNT # Create a subvolume and set it to RO so that it can be used for send. btrfs subvolume create $MNT/sv touch $MNT/sv/foo btrfs property set $MNT/sv ro true # Send and receive the subvolume into snaps/sv. mkdir $MNT/snaps btrfs send $MNT/sv | btrfs receive $MNT/snaps # Now snapshot the received subvolume, which has a received_uuid, a # lot of times to trigger the leaf overflow. total=500 for ((i = 1; i <= $total; i++)); do echo -ne "\rCreating snapshot $i/$total" btrfs subvolume snapshot -r $MNT/snaps/sv $MNT/snaps/sv_$i > /dev/null done echo umount $MNT When running the test: $ ./test.sh (...) Create subvolume '/mnt/sdi/sv' At subvol /mnt/sdi/sv At subvol sv Creating snapshot 496/500ERROR: Could not create subvolume: Value too large for defined data type Creating snapshot 497/500ERROR: Could not create subvolume: Read-only file system Creating snapshot 498/500ERROR: Could not create subvolume: Read-only file system Creating snapshot 499/500ERROR: Could not create subvolume: Read-only file system Creating snapshot 500/500ERROR: Could not create subvolume: Read-only file system And in dmesg/syslog: $ dmesg (...) [251067.627338] BTRFS warning (device sdi): insert uuid item failed -75 (0x4628b21c4ac8d898, 0x2598bee2b1515c91) type 252! [251067.629212] ------------[ cut here ]------------ [251067.630033] BTRFS: Transaction aborted (error -75) [251067.630871] WARNING: fs/btrfs/transaction.c:1907 at create_pending_snapshot.cold+0x52/0x465 [btrfs], CPU#10: btrfs/615235 [251067.632851] Modules linked in: btrfs dm_zero (...) [251067.644071] CPU: 10 UID: 0 PID: 615235 Comm: btrfs Tainted: G W 6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full) [251067.646165] Tainted: [W]=WARN [251067.646733] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [251067.648735] RIP: 0010:create_pending_snapshot.cold+0x55/0x465 [btrfs] [251067.649984] Code: f0 48 0f (...) [251067.653313] RSP: 0018:ffffce644908fae8 EFLAGS: 00010292 [251067.653987] RAX: 00000000ffffff01 RBX: ffff8e5639e63a80 RCX: 00000000ffffffd3 [251067.655042] RDX: ffff8e53faa76b00 RSI: 00000000ffffffb5 RDI: ffffffffc0919750 [251067.656077] RBP: ffffce644908fbd8 R08: 0000000000000000 R09: ffffce644908f820 [251067.657068] R10: ffff8e5adc1fffa8 R11: 0000000000000003 R12: ffff8e53c0431bd0 [251067.658050] R13: ffff8e5414593600 R14: ffff8e55efafd000 R15: 00000000ffffffb5 [251067.659019] FS: 00007f2a4944b3c0(0000) GS:ffff8e5b27dae000(0000) knlGS:0000000000000000 [251067.660115] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [251067.660943] CR2: 00007ffc5aa57898 CR3: 00000005813a2003 CR4: 0000000000370ef0 [251067.661972] Call Trace: [251067.662292] [251067.662653] create_pending_snapshots+0x97/0xc0 [btrfs] [251067.663413] btrfs_commit_transaction+0x26e/0xc00 [btrfs] [251067.664257] ? btrfs_qgroup_convert_reserved_meta+0x35/0x390 [btrfs] [251067.665238] ? _raw_spin_unlock+0x15/0x30 [251067.665837] ? record_root_in_trans+0xa2/0xd0 [btrfs] [251067.666531] btrfs_mksubvol+0x330/0x580 [btrfs] [251067.667145] btrfs_mksnapshot+0x74/0xa0 [btrfs] [251067.667827] __btrfs_ioctl_snap_create+0x194/0x1d0 [btrfs] [251067.668595] btrfs_ioctl_snap_create_v2+0x107/0x130 [btrfs] [251067.669479] btrfs_ioctl+0x1580/0x2690 [btrfs] [251067.670093] ? count_memcg_events+0x6d/0x180 [251067.670849] ? handle_mm_fault+0x1a0/0x2a0 [251067.671652] __x64_sys_ioctl+0x92/0xe0 [251067.672406] do_syscall_64+0x50/0xf20 [251067.673129] entry_SYSCALL_64_after_hwframe+0x76/0x7e [251067.674096] RIP: 0033:0x7f2a495648db [251067.674812] Code: 00 48 89 (...) [251067.678227] RSP: 002b:00007ffc5aa57840 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [251067.679691] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f2a495648db [251067.681145] RDX: 00007ffc5aa588b0 RSI: 0000000050009417 RDI: 0000000000000004 [251067.682511] RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000 [251067.683842] R10: 000000000000000a R11: 0000000000000246 R12: 00007ffc5aa59910 [251067.685176] R13: 00007ffc5aa588b0 R14: 0000000000000004 R15: 0000000000000006 [251067.686524] [251067.686972] ---[ end trace 0000000000000000 ]--- [251067.687890] BTRFS: error (device sdi state A) in create_pending_snapshot:1907: errno=-75 unknown [251067.689049] BTRFS info (device sdi state EA): forced readonly [251067.689054] BTRFS warning (device sdi state EA): Skipping commit of aborted transaction. [251067.690119] BTRFS: error (device sdi state EA) in cleanup_transaction:2043: errno=-75 unknown [251067.702028] BTRFS info (device sdi state EA): last unmount of filesystem 46dc3975-30a2-4a69-a18f-418b859cccda Fix this by ignoring -EOVERFLOW errors from btrfs_uuid_tree_add() in the snapshot creation code when attempting to add the BTRFS_UUID_KEY_RECEIVED_SUBVOL item. This is OK because it's not critical and we are still able to delete the snapshot, as snapshot/subvolume deletion ignores if a BTRFS_UUID_KEY_RECEIVED_SUBVOL is missing (see inode.c:btrfs_delete_subvolume()). As for send/receive, we can still do send/receive operations since it always peeks the first root ID in the existing BTRFS_UUID_KEY_RECEIVED_SUBVOL (it could peek any since all snapshots have the same content), and even if the key is missing, it falls back to searching by BTRFS_UUID_KEY_SUBVOL key. A test case for fstests will be sent soon. Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree") CC: stable@vger.kernel.org # 3.12+ Reviewed-by: Boris Burkov Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 463238ca8a4d..8d887ffcdba1 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1905,6 +1905,22 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_uuid_tree_add(trans, new_root_item->received_uuid, BTRFS_UUID_KEY_RECEIVED_SUBVOL, objectid); + /* + * We are creating of lot of snapshots of the same root that was + * received (has a received UUID) and reached a leaf's limit for + * an item. We can safely ignore this and avoid a transaction + * abort. A deletion of this snapshot will still work since we + * ignore if an item with a BTRFS_UUID_KEY_RECEIVED_SUBVOL key + * is missing (see btrfs_delete_subvolume()). Send/receive will + * work too since it peeks the first root id from the existing + * item (it could peek any), and in case it's missing it + * falls back to search by BTRFS_UUID_KEY_SUBVOL keys. + * Creation of a snapshot does not require CAP_SYS_ADMIN, so + * we don't want users triggering transaction aborts, either + * intentionally or not. + */ + if (ret == -EOVERFLOW) + ret = 0; if (unlikely(ret && ret != -EEXIST)) { btrfs_abort_transaction(trans, ret); goto fail; From 87f2c46003fce4d739138aab4af1942b1afdadac Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 26 Feb 2026 23:41:07 +0000 Subject: [PATCH 060/487] btrfs: fix transaction abort on set received ioctl due to item overflow If the set received ioctl fails due to an item overflow when attempting to add the BTRFS_UUID_KEY_RECEIVED_SUBVOL we have to abort the transaction since we did some metadata updates before. This means that if a user calls this ioctl with the same received UUID field for a lot of subvolumes, we will hit the overflow, trigger the transaction abort and turn the filesystem into RO mode. A malicious user could exploit this, and this ioctl does not even requires that a user has admin privileges (CAP_SYS_ADMIN), only that he/she owns the subvolume. Fix this by doing an early check for item overflow before starting a transaction. This is also race safe because we are holding the subvol_sem semaphore in exclusive (write) mode. A test case for fstests will follow soon. Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree") CC: stable@vger.kernel.org # 3.12+ Reviewed-by: Anand Jain Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 21 +++++++++++++++++++-- fs/btrfs/uuid-tree.c | 38 ++++++++++++++++++++++++++++++++++++++ fs/btrfs/uuid-tree.h | 2 ++ 3 files changed, 59 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1d22c5c05b50..56d17eedaf90 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3929,6 +3929,25 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, goto out; } + received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid, + BTRFS_UUID_SIZE); + + /* + * Before we attempt to add the new received uuid, check if we have room + * for it in case there's already an item. If the size of the existing + * item plus this root's ID (u64) exceeds the maximum item size, we can + * return here without the need to abort a transaction. If we don't do + * this check, the btrfs_uuid_tree_add() call below would fail with + * -EOVERFLOW and result in a transaction abort. Malicious users could + * exploit this to turn the fs into RO mode. + */ + if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) { + ret = btrfs_uuid_tree_check_overflow(fs_info, sa->uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL); + if (ret < 0) + goto out; + } + /* * 1 - root item * 2 - uuid items (received uuid + subvol uuid) @@ -3944,8 +3963,6 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, sa->rtime.sec = ct.tv_sec; sa->rtime.nsec = ct.tv_nsec; - received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid, - BTRFS_UUID_SIZE); if (received_uuid_changed && !btrfs_is_empty_uuid(root_item->received_uuid)) { ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid, diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index f24c14b9bb2f..43c17a1d3451 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -199,6 +199,44 @@ int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8 return 0; } +/* + * Check if we can add one root ID to a UUID key. + * If the key does not yet exists, we can, otherwise only if extended item does + * not exceeds the maximum item size permitted by the leaf size. + * + * Returns 0 on success, negative value on error. + */ +int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info, + const u8 *uuid, u8 type) +{ + BTRFS_PATH_AUTO_FREE(path); + int ret; + u32 item_size; + struct btrfs_key key; + + if (WARN_ON_ONCE(!fs_info->uuid_root)) + return -EINVAL; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + btrfs_uuid_to_key(uuid, type, &key); + ret = btrfs_search_slot(NULL, fs_info->uuid_root, &key, path, 0, 0); + if (ret < 0) + return ret; + if (ret > 0) + return 0; + + item_size = btrfs_item_size(path->nodes[0], path->slots[0]); + + if (sizeof(struct btrfs_item) + item_size + sizeof(u64) > + BTRFS_LEAF_DATA_SIZE(fs_info)) + return -EOVERFLOW; + + return 0; +} + static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type, u64 subid) { diff --git a/fs/btrfs/uuid-tree.h b/fs/btrfs/uuid-tree.h index c60ad20325cc..02b235a3653f 100644 --- a/fs/btrfs/uuid-tree.h +++ b/fs/btrfs/uuid-tree.h @@ -12,6 +12,8 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, const u8 *uuid, u8 typ u64 subid); int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8 type, u64 subid); +int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info, + const u8 *uuid, u8 type); int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info); int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info); int btrfs_uuid_scan_kthread(void *data); From 0f475ee0ebce5c9492b260027cd95270191675fa Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 27 Feb 2026 00:02:33 +0000 Subject: [PATCH 061/487] btrfs: abort transaction on failure to update root in the received subvol ioctl If we failed to update the root we don't abort the transaction, which is wrong since we already used the transaction to remove an item from the uuid tree. Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree") CC: stable@vger.kernel.org # 3.12+ Reviewed-by: Anand Jain Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 56d17eedaf90..5805ac2078f2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3984,7 +3984,8 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, ret = btrfs_update_root(trans, fs_info->tree_root, &root->root_key, &root->root_item); - if (ret < 0) { + if (unlikely(ret < 0)) { + btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; } From 8dd0e6807b54a2411ed7263018139c60d1406e39 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 27 Feb 2026 00:05:08 +0000 Subject: [PATCH 062/487] btrfs: remove unnecessary transaction abort in the received subvol ioctl If we fail to remove an item from the uuid tree, we don't need to abort the transaction since we have not done any change before. So remove that transaction abort. Reviewed-by: Anand Jain Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5805ac2078f2..7d86e9c8909e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3969,7 +3969,6 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, BTRFS_UUID_KEY_RECEIVED_SUBVOL, btrfs_root_id(root)); if (unlikely(ret && ret != -ENOENT)) { - btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; } From 0749cab6174dc035b1628fb6db03abf758cfda6f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 27 Feb 2026 12:09:47 +0000 Subject: [PATCH 063/487] btrfs: remove duplicated definition of btrfs_printk_in_rcu() It's defined twice in a row for the !CONFIG_PRINTK case, so remove one of the duplicates. Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/messages.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h index 943e53980945..c8e92efce405 100644 --- a/fs/btrfs/messages.h +++ b/fs/btrfs/messages.h @@ -28,9 +28,6 @@ void _btrfs_printk(const struct btrfs_fs_info *fs_info, unsigned int level, cons #else -#define btrfs_printk_in_rcu(fs_info, level, fmt, args...) \ - btrfs_no_printk(fs_info, fmt, ##args) - #define btrfs_printk_in_rcu(fs_info, level, fmt, args...) \ btrfs_no_printk(fs_info, fmt, ##args) From 50ad1a31bed898787e12b73cb5716fe7960cdde4 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sat, 21 Feb 2026 07:21:55 +0100 Subject: [PATCH 064/487] cpupower: Add support for setting EPP via systemd service Extend the systemd service so that it can be used for tuning the Energy Performance Preference (EPP) as well. Available options can be read from /sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_preferences. The desired one can then be set in cpupower-service.conf. Signed-off-by: Jan Kiszka Signed-off-by: Shuah Khan --- tools/power/cpupower/cpupower-service.conf | 5 +++++ tools/power/cpupower/cpupower.sh | 6 ++++++ 2 files changed, 11 insertions(+) diff --git a/tools/power/cpupower/cpupower-service.conf b/tools/power/cpupower/cpupower-service.conf index 02eabe8e3614..abbb46967565 100644 --- a/tools/power/cpupower/cpupower-service.conf +++ b/tools/power/cpupower/cpupower-service.conf @@ -30,3 +30,8 @@ # its policy for the relative importance of performance versus energy savings to # the processor. See man CPUPOWER-SET(1) for additional details #PERF_BIAS= + +# Set the Energy Performance Preference +# Available options can be read from +# /sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_preferences +#EPP= diff --git a/tools/power/cpupower/cpupower.sh b/tools/power/cpupower/cpupower.sh index a37dd4cfdb2b..6283e8bf275d 100644 --- a/tools/power/cpupower/cpupower.sh +++ b/tools/power/cpupower/cpupower.sh @@ -23,4 +23,10 @@ then cpupower set -b "$PERF_BIAS" > /dev/null || ESTATUS=1 fi +# apply Energy Performance Preference +if test -n "$EPP" +then + cpupower set -e "$EPP" > /dev/null || ESTATUS=1 +fi + exit $ESTATUS From 3817b1d34432d3d83a61576719570d04c341b7cd Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Mon, 9 Feb 2026 11:24:41 +0800 Subject: [PATCH 065/487] cpupower: Add intel_pstate turbo boost support for Intel platforms On modern Intel platforms, the intel_pstate driver is commonly used and it provides turbo boost control via /sys/devices/system/cpu/intel_pstate/no_turbo. However, cpupower doesn't handle this. it 1. shows turbo boost as "active" blindly for Intel platforms 2. controls turbo boost functionality via the generic /sys/devices/system/cpu/cpufreq/boost sysfs interface only. Enhance the cpupower tool to ensure the "--boost" command works seamlessly on Intel platforms with intel_pstate driver running. Without this patch, $ echo 1 | sudo tee /sys/devices/system/cpu/intel_pstate/no_turbo 1 $ sudo cpupower frequency-info --boost analyzing CPU 21: boost state support: Supported: yes Active: yes $ sudo cpupower set --boost 0 Error setting turbo-boost $ sudo cpupower set --boost 1 Error setting turbo-boost With this patch, $ cat /sys/devices/system/cpu/intel_pstate/no_turbo 0 $ sudo cpupower set --boost 0 $ sudo cpupower frequency-info --boost analyzing CPU 21: boost state support: Supported: yes Active: no $ cat /sys/devices/system/cpu/intel_pstate/no_turbo 1 $ sudo cpupower set --boost 1 $ sudo cpupower frequency-info --boost analyzing CPU 28: boost state support: Supported: yes Active: yes $ cat /sys/devices/system/cpu/intel_pstate/no_turbo 0 Signed-off-by: Zhang Rui Signed-off-by: Shuah Khan --- tools/power/cpupower/utils/cpupower-set.c | 6 ++- tools/power/cpupower/utils/helpers/helpers.h | 5 ++- tools/power/cpupower/utils/helpers/misc.c | 41 +++++++++++++++++++- 3 files changed, 48 insertions(+), 4 deletions(-) diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c index c2117e5650dd..550a942e72ce 100644 --- a/tools/power/cpupower/utils/cpupower-set.c +++ b/tools/power/cpupower/utils/cpupower-set.c @@ -124,7 +124,11 @@ int cmd_set(int argc, char **argv) } if (params.turbo_boost) { - ret = cpupower_set_turbo_boost(turbo_boost); + if (cpupower_cpu_info.vendor == X86_VENDOR_INTEL) + ret = cpupower_set_intel_turbo_boost(turbo_boost); + else + ret = cpupower_set_generic_turbo_boost(turbo_boost); + if (ret) fprintf(stderr, "Error setting turbo-boost\n"); } diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 82ea62bdf5a2..a3ad80b9c2c2 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -104,7 +104,7 @@ extern struct cpupower_cpu_info cpupower_cpu_info; /* cpuid and cpuinfo helpers **************************/ int cpufreq_has_generic_boost_support(bool *active); -int cpupower_set_turbo_boost(int turbo_boost); +int cpupower_set_generic_turbo_boost(int turbo_boost); /* X86 ONLY ****************************************/ #if defined(__i386__) || defined(__x86_64__) @@ -143,6 +143,7 @@ extern int decode_pstates(unsigned int cpu, int boost_states, int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, int *states); +int cpupower_set_intel_turbo_boost(int turbo_boost); /* AMD P-State stuff **************************/ bool cpupower_amd_pstate_enabled(void); @@ -189,6 +190,8 @@ static inline int cpupower_set_amd_pstate_mode(char *mode) static inline int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, int *states) { return -1; } +static inline int cpupower_set_intel_turbo_boost(int turbo_boost) +{ return -1; } static inline bool cpupower_amd_pstate_enabled(void) { return false; } diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index 166dc1e470ea..eebfc79a4889 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -19,6 +19,9 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, { int ret; unsigned long long val; + char linebuf[MAX_LINE_LEN]; + char path[SYSFS_PATH_MAX]; + char *endp; *support = *active = *states = 0; @@ -42,8 +45,42 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, } } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) { amd_pstate_boost_init(cpu, support, active); - } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) + } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) { *support = *active = 1; + + snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo"); + + if (!is_valid_path(path)) + return 0; + + if (cpupower_read_sysfs(path, linebuf, MAX_LINE_LEN) == 0) + return -1; + + val = strtol(linebuf, &endp, 0); + if (endp == linebuf || errno == ERANGE) + return -1; + + *active = !val; + } + return 0; +} + +int cpupower_set_intel_turbo_boost(int turbo_boost) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[2] = {}; + + snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo"); + + /* Fallback to generic solution when intel_pstate driver not running */ + if (!is_valid_path(path)) + return cpupower_set_generic_turbo_boost(turbo_boost); + + snprintf(linebuf, sizeof(linebuf), "%d", !turbo_boost); + + if (cpupower_write_sysfs(path, linebuf, 2) <= 0) + return -1; + return 0; } @@ -274,7 +311,7 @@ void print_speed(unsigned long speed, int no_rounding) } } -int cpupower_set_turbo_boost(int turbo_boost) +int cpupower_set_generic_turbo_boost(int turbo_boost) { char path[SYSFS_PATH_MAX]; char linebuf[2] = {}; From 20f644f42e3b8e729d3c3199d48e75c0b257de8f Mon Sep 17 00:00:00 2001 From: Akhil P Oommen Date: Wed, 25 Feb 2026 13:11:57 +0530 Subject: [PATCH 066/487] drm/msm/a6xx: Fix the bogus protect error on X2-85 Update the X2-85 gpu's register protect count configuration with the correct count_max value to avoid blocking the entire MMIO region from the UMD. Protect configurations are a bit complicated on A8xx. There are 2 set of protect registers with different counts: Global and Pipe-specific. The last-span-unbound feature is available only on the Pipe-specific protect registers. Due to this, we cannot use the BUILD_BUG sanity check for A8x protect configurations, so remove the A840 entry from there. Fixes: 01ff3bf27215 ("drm/msm/a8xx: Add support for Adreno X2-85 GPU") Signed-off-by: Akhil P Oommen Reviewed-by: Konrad Dybcio Patchwork: https://patchwork.freedesktop.org/patch/706944/ Message-ID: <20260225-glymur-protect-fix-v1-1-0deddedf9277@oss.qualcomm.com> Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/adreno/a6xx_catalog.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 550a53a7865e..38561f26837e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -1759,7 +1759,7 @@ static const u32 x285_protect_regs[] = { A6XX_PROTECT_NORDWR(0x27c06, 0x0000), }; -DECLARE_ADRENO_PROTECT(x285_protect, 64); +DECLARE_ADRENO_PROTECT(x285_protect, 15); static const struct adreno_reglist_pipe a840_nonctxt_regs[] = { { REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) }, @@ -1966,5 +1966,4 @@ static inline __always_unused void __build_asserts(void) BUILD_BUG_ON(a660_protect.count > a660_protect.count_max); BUILD_BUG_ON(a690_protect.count > a690_protect.count_max); BUILD_BUG_ON(a730_protect.count > a730_protect.count_max); - BUILD_BUG_ON(a840_protect.count > a840_protect.count_max); } From e4eb6e4dd6348dd00e19c2275e3fbaed304ca3bd Mon Sep 17 00:00:00 2001 From: Thomas Fourier Date: Thu, 26 Feb 2026 10:57:11 +0100 Subject: [PATCH 067/487] drm/msm: Fix dma_free_attrs() buffer size The gpummu->table buffer is alloc'd with size TABLE_SIZE + 32 in a2xx_gpummu_new() but freed with size TABLE_SIZE in a2xx_gpummu_destroy(). Change the free size to match the allocation. Fixes: c2052a4e5c99 ("drm/msm: implement a2xx mmu") Cc: Signed-off-by: Thomas Fourier Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/707340/ Message-ID: <20260226095714.12126-2-fourier.thomas@gmail.com> Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/adreno/a2xx_gpummu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c index 0407c9bc8c1b..4467b04527cd 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c @@ -78,7 +78,7 @@ static void a2xx_gpummu_destroy(struct msm_mmu *mmu) { struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu); - dma_free_attrs(mmu->dev, TABLE_SIZE, gpummu->table, gpummu->pt_base, + dma_free_attrs(mmu->dev, TABLE_SIZE + 32, gpummu->table, gpummu->pt_base, DMA_ATTR_FORCE_CONTIGUOUS); kfree(gpummu); From 3ac88a9948792b092a4b11323e2abd1ecbe0cc68 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Tue, 24 Feb 2026 11:25:34 +0900 Subject: [PATCH 068/487] rust: str: make NullTerminatedFormatter public If `CONFIG_BLOCK` is disabled, the following warnings are displayed during build: warning: struct `NullTerminatedFormatter` is never constructed --> ../rust/kernel/str.rs:667:19 | 667 | pub(crate) struct NullTerminatedFormatter<'a> { | ^^^^^^^^^^^^^^^^^^^^^^^ | = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default warning: associated function `new` is never used --> ../rust/kernel/str.rs:673:19 | 671 | impl<'a> NullTerminatedFormatter<'a> { | ------------------------------------ associated function in this implementation 672 | /// Create a new [`Self`] instance. 673 | pub(crate) fn new(buffer: &'a mut [u8]) -> Option> { Fix them by making `NullTerminatedFormatter` public, as it could be useful for drivers anyway. Fixes: cdde7a1951ff ("rust: str: introduce `NullTerminatedFormatter`") Signed-off-by: Alexandre Courbot Reviewed-by: Alice Ryhl Reviewed-by: Andreas Hindborg Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260224-nullterminatedformatter-v1-1-5bef7b9b3d4c@nvidia.com Signed-off-by: Miguel Ojeda --- rust/kernel/str.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index fa87779d2253..3f8918764640 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -664,13 +664,13 @@ fn write_str(&mut self, s: &str) -> fmt::Result { /// /// * The first byte of `buffer` is always zero. /// * The length of `buffer` is at least 1. -pub(crate) struct NullTerminatedFormatter<'a> { +pub struct NullTerminatedFormatter<'a> { buffer: &'a mut [u8], } impl<'a> NullTerminatedFormatter<'a> { /// Create a new [`Self`] instance. - pub(crate) fn new(buffer: &'a mut [u8]) -> Option> { + pub fn new(buffer: &'a mut [u8]) -> Option> { *(buffer.first_mut()?) = 0; // INVARIANT: From b9e7e3ea605f23d342c67fc5bded99bcaa32d93b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 6 Jan 2026 18:40:19 +0100 Subject: [PATCH 069/487] powerpc/e500: Always use 64 bits PTE Today there are two PTE formats for e500: - The 64 bits format, used - On 64 bits kernel - On 32 bits kernel with 64 bits physical addresses - On 32 bits kernel with support of huge pages - The 32 bits format, used in other cases Maintaining two PTE formats means unnecessary maintenance burden because every change needs to be implemented and tested for both formats. Remove the 32 bits PTE format. The memory usage increase due to larger PTEs is minimal (approx. 0,1% of memory). This also means that from now on huge pages are supported also with 32 bits physical addresses. Signed-off-by: Christophe Leroy Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/04a658209ea78dcc0f3dbde6b2c29cf1939adfe9.1767721208.git.chleroy@kernel.org --- arch/powerpc/include/asm/nohash/32/pgtable.h | 4 +- arch/powerpc/include/asm/nohash/32/pte-85xx.h | 59 ------------------- arch/powerpc/include/asm/pgtable-types.h | 2 +- arch/powerpc/kernel/head_85xx.S | 46 +-------------- arch/powerpc/platforms/Kconfig.cputype | 4 +- 5 files changed, 5 insertions(+), 110 deletions(-) delete mode 100644 arch/powerpc/include/asm/nohash/32/pte-85xx.h diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 2d71e4b7cd09..496ecc65ac25 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -120,10 +120,8 @@ #if defined(CONFIG_44x) #include -#elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT) -#include #elif defined(CONFIG_PPC_85xx) -#include +#include #elif defined(CONFIG_PPC_8xx) #include #endif diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h deleted file mode 100644 index 14d64b4f3f14..000000000000 --- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_32_PTE_85xx_H -#define _ASM_POWERPC_NOHASH_32_PTE_85xx_H -#ifdef __KERNEL__ - -/* PTE bit definitions for Freescale BookE SW loaded TLB MMU based - * processors - * - MMU Assist Register 3: - - 32 33 34 35 36 ... 50 51 52 53 54 55 56 57 58 59 60 61 62 63 - RPN...................... 0 0 U0 U1 U2 U3 UX SX UW SW UR SR - - - PRESENT *must* be in the bottom two bits because swap PTEs use - the top 30 bits. - -*/ - -/* Definitions for FSL Book-E Cores */ -#define _PAGE_READ 0x00001 /* H: Read permission (SR) */ -#define _PAGE_PRESENT 0x00002 /* S: PTE contains a translation */ -#define _PAGE_WRITE 0x00004 /* S: Write permission (SW) */ -#define _PAGE_DIRTY 0x00008 /* S: Page dirty */ -#define _PAGE_EXEC 0x00010 /* H: SX permission */ -#define _PAGE_ACCESSED 0x00020 /* S: Page referenced */ - -#define _PAGE_ENDIAN 0x00040 /* H: E bit */ -#define _PAGE_GUARDED 0x00080 /* H: G bit */ -#define _PAGE_COHERENT 0x00100 /* H: M bit */ -#define _PAGE_NO_CACHE 0x00200 /* H: I bit */ -#define _PAGE_WRITETHRU 0x00400 /* H: W bit */ -#define _PAGE_SPECIAL 0x00800 /* S: Special page */ - -#define _PMD_PRESENT 0 -#define _PMD_PRESENT_MASK (PAGE_MASK) -#define _PMD_BAD (~PAGE_MASK) -#define _PMD_USER 0 - -#define _PTE_NONE_MASK 0 - -#define PTE_WIMGE_SHIFT (6) - -/* - * We define 2 sets of base prot bits, one for basic pages (ie, - * cacheable kernel and user pages) and one for non cacheable - * pages. We always set _PAGE_COHERENT when SMP is enabled or - * the processor might need it for DMA coherency. - */ -#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) -#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC) -#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) -#else -#define _PAGE_BASE (_PAGE_BASE_NC) -#endif - -#include - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */ diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index f3086e39e7d2..e8dec885b6e4 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -49,7 +49,7 @@ static inline unsigned long pud_val(pud_t x) #endif /* CONFIG_PPC64 */ /* PGD level */ -#if defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT) +#if defined(CONFIG_PPC_85xx) typedef struct { unsigned long long pgd; } pgd_t; static inline unsigned long long pgd_val(pgd_t x) diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index f9a73fae6464..8867596d35ad 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -305,7 +305,6 @@ set_ivor: * r12 is pointer to the pte * r10 is the pshift from the PGD, if we're a hugepage */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_HUGETLB_PAGE #define FIND_PTE \ rlwinm r12, r13, 14, 18, 28; /* Compute pgdir/pmd offset */ \ @@ -329,15 +328,6 @@ set_ivor: rlwimi r12, r13, 23, 20, 28; /* Compute pte address */ \ lwz r11, 4(r12); /* Get pte entry */ #endif /* HUGEPAGE */ -#else /* !PTE_64BIT */ -#define FIND_PTE \ - rlwimi r11, r13, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \ - lwz r11, 0(r11); /* Get L1 entry */ \ - rlwinm. r12, r11, 0, 0, 19; /* Extract L2 (pte) base address */ \ - beq 2f; /* Bail if no table */ \ - rlwimi r12, r13, 22, 20, 29; /* Compute PTE address */ \ - lwz r11, 0(r12); /* Get Linux PTE */ -#endif /* * Interrupt vector entry code @@ -473,21 +463,15 @@ END_BTB_FLUSH_SECTION 4: FIND_PTE -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT|_PAGE_BAP_SR oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED -#endif andc. r13,r13,r11 /* Check permission */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP subf r13,r11,r12 /* create false data dep */ lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ -#endif #endif bne 2f /* Bail if permission/valid mismatch */ @@ -552,12 +536,8 @@ END_BTB_FLUSH_SECTION FIND_PTE /* Make up the required permissions for kernel code */ -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT | _PAGE_BAP_SX oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#endif b 4f /* Get the PGD for the current thread */ @@ -573,23 +553,17 @@ END_BTB_FLUSH_SECTION FIND_PTE /* Make up the required permissions for user code */ -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT | _PAGE_BAP_UX oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#endif 4: andc. r13,r13,r11 /* Check permission */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP subf r13,r11,r12 /* create false data dep */ lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ -#endif #endif bne 2f /* Bail if permission mismatch */ @@ -683,7 +657,7 @@ interrupt_end: * r10 - tsize encoding (if HUGETLB_PAGE) or available to use * r11 - TLB (info from Linux PTE) * r12 - available to use - * r13 - upper bits of PTE (if PTE_64BIT) or available to use + * r13 - upper bits of PTE * CR5 - results of addr >= PAGE_OFFSET * MAS0, MAS1 - loaded with proper value when we get here * MAS2, MAS3 - will need additional info from Linux PTE @@ -751,7 +725,6 @@ finish_tlb_load: * here we (properly should) assume have the appropriate value. */ finish_tlb_load_cont: -#ifdef CONFIG_PTE_64BIT rlwinm r12, r11, 32-2, 26, 31 /* Move in perm bits */ andi. r10, r11, _PAGE_DIRTY bne 1f @@ -764,26 +737,9 @@ BEGIN_MMU_FTR_SECTION srwi r10, r13, 12 /* grab RPN[12:31] */ mtspr SPRN_MAS7, r10 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) -#else - li r10, (_PAGE_EXEC | _PAGE_READ) - mr r13, r11 - rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */ - and r12, r11, r10 - mcrf cr0, cr5 /* Test for user page */ - slwi r10, r12, 1 - or r10, r10, r12 - rlwinm r10, r10, 0, ~_PAGE_EXEC /* Clear SX on user pages */ - isellt r12, r10, r12 - rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */ - mtspr SPRN_MAS3, r13 -#endif mfspr r12, SPRN_MAS2 -#ifdef CONFIG_PTE_64BIT rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ -#else - rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ -#endif #ifdef CONFIG_HUGETLB_PAGE beq 6, 3f /* don't mask if page isn't huge */ li r13, 1 diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index f399917c17bd..bac02c83bb3e 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -276,7 +276,7 @@ config PPC_BOOK3S config PPC_E500 select FSL_EMB_PERFMON bool - select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64 + select ARCH_SUPPORTS_HUGETLBFS select PPC_SMP_MUXED_IPI select PPC_DOORBELL select PPC_KUEP @@ -337,7 +337,7 @@ config BOOKE config PTE_64BIT bool depends on 44x || PPC_E500 || PPC_86xx - default y if PHYS_64BIT + default y if PPC_E500 || PHYS_64BIT config PHYS_64BIT bool 'Large physical address support' if PPC_E500 || PPC_86xx From 0ee95a1d458630272d0415d0ffa9424fcb606c90 Mon Sep 17 00:00:00 2001 From: "Christophe Leroy (CS GROUP)" Date: Tue, 3 Feb 2026 08:30:41 +0100 Subject: [PATCH 070/487] powerpc/uaccess: Fix inline assembly for clang build on PPC32 Test robot reports the following error with clang-16.0.6: In file included from kernel/rseq.c:75: include/linux/rseq_entry.h:141:3: error: invalid operand for instruction unsafe_get_user(offset, &ucs->post_commit_offset, efault); ^ include/linux/uaccess.h:608:2: note: expanded from macro 'unsafe_get_user' arch_unsafe_get_user(x, ptr, local_label); \ ^ arch/powerpc/include/asm/uaccess.h:518:2: note: expanded from macro 'arch_unsafe_get_user' __get_user_size_goto(__gu_val, __gu_addr, sizeof(*(p)), e); \ ^ arch/powerpc/include/asm/uaccess.h:284:2: note: expanded from macro '__get_user_size_goto' __get_user_size_allowed(x, ptr, size, __gus_retval); \ ^ arch/powerpc/include/asm/uaccess.h:275:10: note: expanded from macro '__get_user_size_allowed' case 8: __get_user_asm2(x, (u64 __user *)ptr, retval); break; \ ^ arch/powerpc/include/asm/uaccess.h:258:4: note: expanded from macro '__get_user_asm2' " li %1+1,0\n" \ ^ :7:5: note: instantiated into assembly here li 31+1,0 ^ 1 error generated. On PPC32, for 64 bits vars a pair of registers is used. Usually the lower register in the pair is the high part and the higher register is the low part. GCC uses r3/r4 ... r11/r12 ... r14/r15 ... r30/r31 In older kernel code inline assembly was using %1 and %1+1 to represent 64 bits values. However here it looks like clang uses r31 as high part, allthough r32 doesn't exist hence the error. Allthoug %1+1 should work, most places now use %L1 instead of %1+1, so let's do the same here. With that change, the build doesn't fail anymore and a disassembly shows clang uses r17/r18 and r31/r14 pair when GCC would have used r16/r17 and r30/r31: Disassembly of section .fixup: 00000000 <.fixup>: 0: 38 a0 ff f2 li r5,-14 4: 3a 20 00 00 li r17,0 8: 3a 40 00 00 li r18,0 c: 48 00 00 00 b c <.fixup+0xc> c: R_PPC_REL24 .text+0xbc 10: 38 a0 ff f2 li r5,-14 14: 3b e0 00 00 li r31,0 18: 39 c0 00 00 li r14,0 1c: 48 00 00 00 b 1c <.fixup+0x1c> 1c: R_PPC_REL24 .text+0x144 Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202602021825.otcItxGi-lkp@intel.com/ Fixes: c20beffeec3c ("powerpc/uaccess: Use flexible addressing with __put_user()/__get_user()") Signed-off-by: Christophe Leroy (CS GROUP) Acked-by: Nathan Chancellor Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/8ca3a657a650e497a96bfe7acde2f637dadab344.1770103646.git.chleroy@kernel.org --- arch/powerpc/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index ba1d878c3f40..570b3d91e2e4 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -255,7 +255,7 @@ __gus_failed: \ ".section .fixup,\"ax\"\n" \ "4: li %0,%3\n" \ " li %1,0\n" \ - " li %1+1,0\n" \ + " li %L1,0\n" \ " b 3b\n" \ ".previous\n" \ EX_TABLE(1b, 4b) \ From 0706178339974d4332a782ba851cb6694bd210fe Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 28 Jan 2026 08:02:20 -0600 Subject: [PATCH 071/487] powerpc: dts: fsl: Drop unused .dtsi files These files are not included by anything and therefore don't get built or tested. There's also no upstream driver for the interlaken-lac stuff. Signed-off-by: Rob Herring (Arm) Reviewed-by: Christophe Leroy (CS GROUP) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260128140222.1627203-1-robh@kernel.org --- .../boot/dts/fsl/interlaken-lac-portals.dtsi | 156 ------------------ arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi | 45 ----- .../boot/dts/fsl/pq3-mpic-message-B.dtsi | 43 ----- .../fsl/qoriq-fman3-0-10g-1-best-effort.dtsi | 80 --------- 4 files changed, 324 deletions(-) delete mode 100644 arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi delete mode 100644 arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi delete mode 100644 arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi delete mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi deleted file mode 100644 index 9cffccf4e07e..000000000000 --- a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi +++ /dev/null @@ -1,156 +0,0 @@ -/* T4240 Interlaken LAC Portal device tree stub with 24 portals. - * - * Copyright 2012 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#address-cells = <0x1>; -#size-cells = <0x1>; -compatible = "fsl,interlaken-lac-portals"; - -lportal0: lac-portal@0 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x0 0x1000>; -}; - -lportal1: lac-portal@1000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x1000 0x1000>; -}; - -lportal2: lac-portal@2000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x2000 0x1000>; -}; - -lportal3: lac-portal@3000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x3000 0x1000>; -}; - -lportal4: lac-portal@4000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x4000 0x1000>; -}; - -lportal5: lac-portal@5000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x5000 0x1000>; -}; - -lportal6: lac-portal@6000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x6000 0x1000>; -}; - -lportal7: lac-portal@7000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x7000 0x1000>; -}; - -lportal8: lac-portal@8000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x8000 0x1000>; -}; - -lportal9: lac-portal@9000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x9000 0x1000>; -}; - -lportal10: lac-portal@A000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xA000 0x1000>; -}; - -lportal11: lac-portal@B000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xB000 0x1000>; -}; - -lportal12: lac-portal@C000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xC000 0x1000>; -}; - -lportal13: lac-portal@D000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xD000 0x1000>; -}; - -lportal14: lac-portal@E000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xE000 0x1000>; -}; - -lportal15: lac-portal@F000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0xF000 0x1000>; -}; - -lportal16: lac-portal@10000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x10000 0x1000>; -}; - -lportal17: lac-portal@11000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x11000 0x1000>; -}; - -lportal18: lac-portal@1200 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x12000 0x1000>; -}; - -lportal19: lac-portal@13000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x13000 0x1000>; -}; - -lportal20: lac-portal@14000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x14000 0x1000>; -}; - -lportal21: lac-portal@15000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x15000 0x1000>; -}; - -lportal22: lac-portal@16000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x16000 0x1000>; -}; - -lportal23: lac-portal@17000 { - compatible = "fsl,interlaken-lac-portal-v1.0"; - reg = <0x17000 0x1000>; -}; diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi deleted file mode 100644 index e8208720ac0e..000000000000 --- a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi +++ /dev/null @@ -1,45 +0,0 @@ -/* - * T4 Interlaken Look-aside Controller (LAC) device tree stub - * - * Copyright 2012 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -lac: lac@229000 { - compatible = "fsl,interlaken-lac"; - reg = <0x229000 0x1000>; - interrupts = <16 2 1 18>; -}; - -lac-hv@228000 { - compatible = "fsl,interlaken-lac-hv"; - reg = <0x228000 0x1000>; - fsl,non-hv-node = <&lac>; -}; diff --git a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi b/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi deleted file mode 100644 index 1cf0b77b1efe..000000000000 --- a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi +++ /dev/null @@ -1,43 +0,0 @@ -/* - * PQ3 MPIC Message (Group B) device tree stub [ controller @ offset 0x42400 ] - * - * Copyright 2012 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -message@42400 { - compatible = "fsl,mpic-v3.1-msgr"; - reg = <0x42400 0x200>; - interrupts = < - 0xb4 2 0 0 - 0xb5 2 0 0 - 0xb6 2 0 0 - 0xb7 2 0 0>; -}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi deleted file mode 100644 index 71eb75e82c2e..000000000000 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi +++ /dev/null @@ -1,80 +0,0 @@ -/* - * QorIQ FMan v3 1g port #1 device tree stub [ controller @ offset 0x400000 ] - * - * Copyright 2012 - 2015 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -fman@400000 { - fman0_rx_0x09: port@89000 { - cell-index = <0x9>; - compatible = "fsl,fman-v3-port-rx"; - reg = <0x89000 0x1000>; - fsl,fman-10g-port; - fsl,fman-best-effort-port; - }; - - fman0_tx_0x29: port@a9000 { - cell-index = <0x29>; - compatible = "fsl,fman-v3-port-tx"; - reg = <0xa9000 0x1000>; - fsl,fman-10g-port; - fsl,fman-best-effort-port; - }; - - ethernet@e2000 { - cell-index = <1>; - compatible = "fsl,fman-memac"; - reg = <0xe2000 0x1000>; - fsl,fman-ports = <&fman0_rx_0x09 &fman0_tx_0x29>; - ptp-timer = <&ptp_timer0>; - pcsphy-handle = <&pcsphy1>, <&qsgmiia_pcs1>; - pcs-handle-names = "sgmii", "qsgmii"; - }; - - mdio@e1000 { - qsgmiia_pcs1: ethernet-pcs@1 { - compatible = "fsl,lynx-pcs"; - reg = <1>; - }; - }; - - mdio@e3000 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; - reg = <0xe3000 0x1000>; - fsl,erratum-a011043; /* must ignore read errors */ - - pcsphy1: ethernet-phy@0 { - reg = <0x0>; - }; - }; -}; From 6fc5d63c6ff5fe5e5beea3e7fe2ca3058351ae99 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 29 Oct 2025 12:40:46 -0500 Subject: [PATCH 072/487] powerpc/prom_init: Fixup missing #size-cells on PowerMac media-bay nodes Similar to other PowerMac mac-io devices, the media-bay node is missing the "#size-cells" property. Depends-on: commit 045b14ca5c36 ("of: WARN on deprecated #address-cells/#size-cells handling") Reported-by: Stan Johnson Signed-off-by: Rob Herring (Arm) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20251029174047.1620073-1-robh@kernel.org --- arch/powerpc/kernel/prom_init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 827c958677f8..f26e80cbc615 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2893,7 +2893,8 @@ static void __init fixup_device_tree_pmac(void) for (node = 0; prom_next_node(&node); ) { type[0] = '\0'; prom_getprop(node, "device_type", type, sizeof(type)); - if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s")) + if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s") && + prom_strcmp(type, "media-bay")) continue; if (prom_getproplen(node, "#size-cells") != PROM_ERROR) From 20197b967a6a29dab81495f25a988515bda84cfe Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Wed, 24 Dec 2025 20:42:57 +0530 Subject: [PATCH 073/487] powerpc/kexec/core: use big-endian types for crash variables Use explicit word-sized big-endian types for kexec and crash related variables. This makes the endianness unambiguous and avoids type mismatches that trigger sparse warnings. The change addresses sparse warnings like below (seen on both 32-bit and 64-bit builds): CHECK ../arch/powerpc/kexec/core.c sparse: expected unsigned int static [addressable] [toplevel] [usertype] crashk_base sparse: got restricted __be32 [usertype] sparse: warning: incorrect type in assignment (different base types) sparse: expected unsigned int static [addressable] [toplevel] [usertype] crashk_size sparse: got restricted __be32 [usertype] sparse: warning: incorrect type in assignment (different base types) sparse: expected unsigned long long static [addressable] [toplevel] mem_limit sparse: got restricted __be32 [usertype] sparse: warning: incorrect type in assignment (different base types) sparse: expected unsigned int static [addressable] [toplevel] [usertype] kernel_end sparse: got restricted __be32 [usertype] No functional change intended. Fixes: ea961a828fe7 ("powerpc: Fix endian issues in kexec and crash dump code") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202512221405.VHPKPjnp-lkp@intel.com/ Signed-off-by: Sourabh Jain Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20251224151257.28672-1-sourabhjain@linux.ibm.com --- arch/powerpc/kexec/core.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index 104c05520bf0..dc44f11be353 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -23,6 +23,7 @@ #include #define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG) +#define __be_word __PASTE(__be, BITS_PER_LONG) #ifdef CONFIG_CRASH_DUMP void machine_crash_shutdown(struct pt_regs *regs) @@ -146,25 +147,25 @@ int __init overlaps_crashkernel(unsigned long start, unsigned long size) } /* Values we need to export to the second kernel via the device tree. */ -static phys_addr_t crashk_base; -static phys_addr_t crashk_size; -static unsigned long long mem_limit; +static __be_word crashk_base; +static __be_word crashk_size; +static __be_word mem_limit; static struct property crashk_base_prop = { .name = "linux,crashkernel-base", - .length = sizeof(phys_addr_t), + .length = sizeof(__be_word), .value = &crashk_base }; static struct property crashk_size_prop = { .name = "linux,crashkernel-size", - .length = sizeof(phys_addr_t), + .length = sizeof(__be_word), .value = &crashk_size, }; static struct property memory_limit_prop = { .name = "linux,memory-limit", - .length = sizeof(unsigned long long), + .length = sizeof(__be_word), .value = &mem_limit, }; @@ -193,11 +194,11 @@ static void __init export_crashk_values(struct device_node *node) } #endif /* CONFIG_CRASH_RESERVE */ -static phys_addr_t kernel_end; +static __be_word kernel_end; static struct property kernel_end_prop = { .name = "linux,kernel-end", - .length = sizeof(phys_addr_t), + .length = sizeof(__be_word), .value = &kernel_end, }; From 04e707cb77c272cb0bb2e2e3c5c7f844d804a089 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Fri, 27 Feb 2026 22:48:01 +0530 Subject: [PATCH 074/487] powerpc/crash: adjust the elfcorehdr size With crash hotplug support enabled, additional memory is allocated to the elfcorehdr kexec segment to accommodate resources added during memory hotplug events. However, the kdump FDT is not updated with the same size, which can result in elfcorehdr corruption in the kdump kernel. Update elf_headers_sz (the kimage member representing the size of the elfcorehdr kexec segment) to reflect the total memory allocated for the elfcorehdr segment instead of the elfcorehdr buffer size at the time of kdump load. This allows of_kexec_alloc_and_setup_fdt() to reserve the full elfcorehdr memory in the kdump FDT and prevents elfcorehdr corruption. Fixes: 849599b702ef8 ("powerpc/crash: add crash memory hotplug support") Reviewed-by: Hari Bathini Signed-off-by: Sourabh Jain Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260227171801.2238847-1-sourabhjain@linux.ibm.com --- arch/powerpc/kexec/file_load_64.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index e7ef8b2a2554..5f6d50e4c3d4 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -450,6 +450,11 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) kbuf->buffer = headers; kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; kbuf->bufsz = headers_sz; + + /* + * Account for extra space required to accommodate additional memory + * ranges in elfcorehdr due to memory hotplug events. + */ kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem); kbuf->top_down = false; @@ -460,7 +465,14 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) } image->elf_load_addr = kbuf->mem; - image->elf_headers_sz = headers_sz; + + /* + * If CONFIG_CRASH_HOTPLUG is enabled, the elfcorehdr kexec segment + * memsz can be larger than bufsz. Always initialize elf_headers_sz + * with memsz. This ensures the correct size is reserved for elfcorehdr + * memory in the FDT prepared for kdump. + */ + image->elf_headers_sz = kbuf->memsz; image->elf_headers = headers; out: kfree(cmem); From 5c3daa5301693d2e5364483a3405649a0fdaed98 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Mon, 2 Mar 2026 22:31:44 +0800 Subject: [PATCH 075/487] power: sequencing: pcie-m2: Fix device node reference leak in probe In pwrseq_pcie_m2_probe(), ctx->of_node acquires an explicit reference to the device node using of_node_get(), but there is no corresponding of_node_put() in the driver's error handling paths or removal. Since the ctx is tied to the lifecycle of the platform device, there is no need to hold an additional reference to the device's own of_node. Fixes: 52e7b5bd62ba ("power: sequencing: Add the Power Sequencing driver for the PCIe M.2 connectors") Signed-off-by: Felix Gu Link: https://patch.msgid.link/20260302-m2-v1-1-a6533e18aa69@gmail.com Signed-off-by: Bartosz Golaszewski --- drivers/power/sequencing/pwrseq-pcie-m2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/sequencing/pwrseq-pcie-m2.c b/drivers/power/sequencing/pwrseq-pcie-m2.c index d31a7dd8b35c..dadb4aad9d5d 100644 --- a/drivers/power/sequencing/pwrseq-pcie-m2.c +++ b/drivers/power/sequencing/pwrseq-pcie-m2.c @@ -109,7 +109,7 @@ static int pwrseq_pcie_m2_probe(struct platform_device *pdev) if (!ctx) return -ENOMEM; - ctx->of_node = of_node_get(dev->of_node); + ctx->of_node = dev_of_node(dev); ctx->pdata = device_get_match_data(dev); if (!ctx->pdata) return dev_err_probe(dev, -ENODEV, From 6270b8ac2f41858952074b23c2d3d9aa2fe1bfa9 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 26 Feb 2026 07:46:46 +0900 Subject: [PATCH 076/487] xfs: remove scratch field from struct xfs_gc_bio The scratch field in struct xfs_gc_bio is unused. Remove it. Fixes: 102f444b57b3 ("xfs: rework zone GC buffer management") Signed-off-by: Damien Le Moal Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_zone_gc.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index 7efeecd2d85f..309f70098524 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -96,7 +96,6 @@ struct xfs_gc_bio { */ xfs_fsblock_t old_startblock; xfs_daddr_t new_daddr; - struct xfs_zone_scratch *scratch; /* Are we writing to a sequential write required zone? */ bool is_seq; @@ -779,7 +778,6 @@ xfs_zone_gc_split_write( ihold(VFS_I(chunk->ip)); split_chunk->ip = chunk->ip; split_chunk->is_seq = chunk->is_seq; - split_chunk->scratch = chunk->scratch; split_chunk->offset = chunk->offset; split_chunk->len = split_len; split_chunk->old_startblock = chunk->old_startblock; From 0ca1a8331c0fa5e57844e003a5d667a15b1e002c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 2 Mar 2026 09:31:58 -0800 Subject: [PATCH 077/487] xfs: fix race between healthmon unmount and read_iter xfs/1879 on one of my test VMs got stuck due to the xfs_io healthmon subcommand sleeping in wait_event_interruptible at: xfs_healthmon_read_iter+0x558/0x5f8 [xfs] vfs_read+0x248/0x320 ksys_read+0x78/0x120 Looking at xfs_healthmon_read_iter, in !O_NONBLOCK mode it will sleep until the mount cookie == DETACHED_MOUNT_COOKIE, there are events waiting to be formatted, or there are formatted events in the read buffer that could be copied to userspace. Poking into the running kernel, I see that there are zero events in the list, the read buffer is empty, and the mount cookie is indeed in DETACHED state. IOWs, xfs_healthmon_has_eventdata should have returned true, but instead we're asleep waiting for a wakeup. I think what happened here is that xfs_healthmon_read_iter and xfs_healthmon_unmount were racing with each other, and _read_iter lost the race. _unmount queued an unmount event, which woke up _read_iter. It found, formatted, and copied the event out to userspace. That cleared out the pending event list and emptied the read buffer. xfs_io then called read() again, so _has_eventdata decided that we should sleep on the empty event queue. Next, _unmount called xfs_healthmon_detach, which set the mount cookie to DETACHED. Unfortunately, it didn't call wake_up_all on the hm, so the wait_event_interruptible in the _read_iter thread remains asleep. That's why the test stalled. Fix this by moving the wake_up_all call to xfs_healthmon_detach. Fixes: b3a289a2a9397b ("xfs: create event queuing, formatting, and discovery infrastructure") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_healthmon.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 4a06d6632f65..26c325d34bd1 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -141,6 +141,16 @@ xfs_healthmon_detach( hm->mount_cookie = DETACHED_MOUNT_COOKIE; spin_unlock(&xfs_healthmon_lock); + /* + * Wake up any readers that might remain. This can happen if unmount + * races with the healthmon fd owner entering ->read_iter, having + * already emptied the event queue. + * + * In the ->release case there shouldn't be any readers because the + * only users of the waiter are read and poll. + */ + wake_up_all(&hm->wait); + trace_xfs_healthmon_detach(hm); xfs_healthmon_put(hm); } @@ -1027,13 +1037,6 @@ xfs_healthmon_release( * process can create another health monitor file. */ xfs_healthmon_detach(hm); - - /* - * Wake up any readers that might be left. There shouldn't be any - * because the only users of the waiter are read and poll. - */ - wake_up_all(&hm->wait); - xfs_healthmon_put(hm); return 0; } From cfdf6456c0aca337ff05cb1eb6e6f453e1d9dea1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 27 Feb 2026 09:08:14 -0300 Subject: [PATCH 078/487] tools headers: Sync uapi/linux/prctl.h with the kernel source To pick up the changes in these csets: 5ca243f6e3c30b97 ("prctl: add arch-agnostic prctl()s for indirect branch tracking") 28621ec2d46c6adf ("rseq: Add prctl() to enable time slice extensions") That don't introduced these new prctls: $ tools/perf/trace/beauty/prctl_option.sh > before.txt $ cp include/uapi/linux/prctl.h tools/perf/trace/beauty/include/uapi/linux/prctl.h $ tools/perf/trace/beauty/prctl_option.sh > after.txt $ diff -u before.txt after.txt --- before.txt 2026-02-27 09:07:16.435611457 -0300 +++ after.txt 2026-02-27 09:07:28.189816531 -0300 @@ -73,6 +73,10 @@ [76] = "LOCK_SHADOW_STACK_STATUS", [77] = "TIMER_CREATE_RESTORE_IDS", [78] = "FUTEX_HASH", + [79] = "RSEQ_SLICE_EXTENSION", + [80] = "GET_INDIR_BR_LP_STATUS", + [81] = "SET_INDIR_BR_LP_STATUS", + [82] = "LOCK_INDIR_BR_LP_STATUS", }; static const char *prctl_set_mm_options[] = { [1] = "START_CODE", $ That now will be used to decode the syscall option and also to compose filters, for instance: [root@five ~]# perf trace -e syscalls:sys_enter_prctl --filter option==SET_NAME 0.000 Isolated Servi/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23f13b7aee) 0.032 DOM Worker/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23deb25670) 7.920 :3474328/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fbb10) 7.935 StreamT~s #374/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fb970) 8.400 Isolated Servi/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24bab10) 8.418 StreamT~s #374/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24ba970) ^C[root@five ~]# This addresses these perf build warnings: Warning: Kernel ABI header differences: diff -u tools/perf/trace/beauty/include/uapi/linux/prctl.h include/uapi/linux/prctl.h Please see tools/include/uapi/README for further details. Cc: Deepak Gupta Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Arnaldo Carvalho de Melo --- .../trace/beauty/include/uapi/linux/prctl.h | 37 +++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 51c4e8c82b1e..55b0446fff9d 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -386,4 +386,41 @@ struct prctl_mm_map { # define PR_FUTEX_HASH_SET_SLOTS 1 # define PR_FUTEX_HASH_GET_SLOTS 2 +/* RSEQ time slice extensions */ +#define PR_RSEQ_SLICE_EXTENSION 79 +# define PR_RSEQ_SLICE_EXTENSION_GET 1 +# define PR_RSEQ_SLICE_EXTENSION_SET 2 +/* + * Bits for RSEQ_SLICE_EXTENSION_GET/SET + * PR_RSEQ_SLICE_EXT_ENABLE: Enable + */ +# define PR_RSEQ_SLICE_EXT_ENABLE 0x01 + +/* + * Get the current indirect branch tracking configuration for the current + * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS. + */ +#define PR_GET_INDIR_BR_LP_STATUS 80 + +/* + * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will + * enable cpu feature for user thread, to track all indirect branches and ensure + * they land on arch defined landing pad instruction. + * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction. + * arch64 - If enabled, an indirect branch must land on a BTI instruction. + * riscv - If enabled, an indirect branch must land on an lpad instruction. + * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect + * branches will no more be tracked by cpu to land on arch defined landing pad + * instruction. + */ +#define PR_SET_INDIR_BR_LP_STATUS 81 +# define PR_INDIR_BR_LP_ENABLE (1UL << 0) + +/* + * Prevent further changes to the specified indirect branch tracking + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_INDIR_BR_LP_STATUS 82 + #endif /* _LINUX_PRCTL_H */ From f079ff37324accb91c6247b59e249ebc22bf55f5 Mon Sep 17 00:00:00 2001 From: Changqing Li Date: Mon, 28 Jul 2025 17:31:53 +0800 Subject: [PATCH 079/487] tools build: Make in-target rule robust against too long argument error The command length of in-target scales with the depth of the directory times the number of objects in the Makefile. When there are many objects, and O=[absolute_path] is set, and the absolute_path is relatively long. It is possible that this line "$(call if_changed,$(host)ld_multi)" will report error: "make[4]: /bin/sh: Argument list too long" For example, build perf tools with O=/long/output/path Like built-in.a and *.mod rules in scripts/Makefile.build, add $(objpredix)/ by the shell command instead of by Make's builtin function. Reviewed-by: Ian Rogers Signed-off-by: Changqing Li Cc: Charlie Jenkins Cc: James Clark Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.build | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 60e65870eae1..ad69efdd4e85 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -70,11 +70,13 @@ quiet_cmd_gen = GEN $@ # If there's nothing to link, create empty $@ object. quiet_cmd_ld_multi = LD $@ cmd_ld_multi = $(if $(strip $(obj-y)),\ - $(LD) -r -o $@ $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@) + printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \ + xargs $(LD) -r -o $@,rm -f $@; $(AR) rcs $@) quiet_cmd_host_ld_multi = HOSTLD $@ cmd_host_ld_multi = $(if $(strip $(obj-y)),\ - $(HOSTLD) -r -o $@ $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@) + printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \ + xargs $(HOSTLD) -r -o $@,rm -f $@; $(HOSTAR) rcs $@) rust_common_cmd = \ $(RUSTC) $(rust_flags) \ From b6712d91f8f5a289f642c208083a8f5c27b8ab90 Mon Sep 17 00:00:00 2001 From: Markus Mayer Date: Tue, 3 Mar 2026 13:15:01 -0800 Subject: [PATCH 080/487] perf build: Prevent "argument list too long" error Due to a recent change, building perf may result in a build error when it is trying to "prune orphans". The file list passed to "rm" may exceed what the shell can handle. The build will then abort with an error like this: TEST [...]/arm64/build/linux-custom/tools/perf/pmu-events/metric_test.log make[5]: /bin/sh: Argument list too long make[5]: *** [pmu-events/Build:217: prune_orphans] Error 127 make[5]: *** Waiting for unfinished jobs.... make[4]: *** [Makefile.perf:773: [...]/tools/perf/pmu-events/pmu-events-in.o] Error 2 make[4]: *** Waiting for unfinished jobs.... make[3]: *** [Makefile.perf:289: sub-make] Error 2 Processing the arguments via "xargs", instead of passing the list of files directly to "rm" via the shell, prevents this issue. Fixes: 36a1b0061a584430 ("perf build: Reduce pmu-events related copying and mkdirs") Reviewed-by: Ian Rogers Signed-off-by: Markus Mayer Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/Build | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 63c65788d442..dc5f94862a3b 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -214,7 +214,8 @@ ifneq ($(strip $(ORPHAN_FILES)),) quiet_cmd_rm = RM $^ prune_orphans: $(ORPHAN_FILES) - $(Q)$(call echo-cmd,rm)rm -f $^ + # The list of files can be long. Use xargs to prevent issues. + $(Q)$(call echo-cmd,rm)echo "$^" | xargs rm -f JEVENTS_DEPS += prune_orphans endif From 30f998c992c9d32a5c2774ec1b624339483db19d Mon Sep 17 00:00:00 2001 From: Dmitrii Dolgov <9erthalion6@gmail.com> Date: Thu, 26 Feb 2026 17:59:59 +0100 Subject: [PATCH 081/487] tools build: Fix rust cross compilation Currently no target is specified to compile rust code when needed, which breaks cross compilation. E.g. for arm64: LD /tmp/build/tests/workloads/perf-test-in.o aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62) aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62) [...repeated...] aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62) aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62) aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a: error adding symbols: file in wrong format make[5]: *** [/perf/tools/build/Makefile.build:162: /tmp/build/tests/workloads/perf-test-in.o] Error 1 make[4]: *** [/perf/tools/build/Makefile.build:156: workloads] Error 2 make[3]: *** [/perf/tools/build/Makefile.build:156: tests] Error 2 make[2]: *** [Makefile.perf:785: /tmp/build/perf-test-in.o] Error 2 make[2]: *** Waiting for unfinished jobs.... make[1]: *** [Makefile.perf:289: sub-make] Error 2 make: *** [Makefile:76: all] Error 2 Detect required target and pass it via rust_flags to the compiler. Note that CROSS_COMPILE might be different from what rust compiler expects, since it may omit the target vendor value, e.g. "aarch64-linux-gnu" instead of "aarch64-unknown-linux-gnu". Thus explicitly map supported CROSS_COMPILE values to corresponding Rust versions, as suggested by Miguel Ojeda. Tested using arm64 cross-compilation example from [1]. Fixes: 2e05bb52a12d3cdb ("perf test workload: Add code_with_type test workload") Reviewed-by: Ian Rogers Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Levi Zim Cc: Miguel Ojeda Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nicolas Schier Link: https://perfwiki.github.io/main/arm64-cross-compilation-dockerfile/ [1] Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Build.include | 9 +++++++++ tools/perf/Makefile.config | 18 ++++++++++++++++++ tools/perf/Makefile.perf | 2 +- 3 files changed, 28 insertions(+), 1 deletion(-) diff --git a/tools/build/Build.include b/tools/build/Build.include index e45b2eb0d24a..cd0baa7a168d 100644 --- a/tools/build/Build.include +++ b/tools/build/Build.include @@ -98,6 +98,15 @@ c_flags_2 = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(c_flags_1)) c_flags = $(filter-out $(CFLAGS_REMOVE_$(obj)), $(c_flags_2)) cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj)) +### +# Rust flags to be used on rule definition, includes: +# - global $(RUST_FLAGS) +# - per target Rust flags +# - per object Rust flags +rust_flags_1 = $(RUST_FLAGS) $(RUST_FLAGS_$(basetarget).o) $(RUST_FLAGS_$(obj)) +rust_flags_2 = $(filter-out $(RUST_FLAGS_REMOVE_$(basetarget).o), $(rust_flags_1)) +rust_flags = $(filter-out $(RUST_FLAGS_REMOVE_$(obj)), $(rust_flags_2)) + ### ## HOSTCC C flags diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index a8dc72cfe48e..15fbba9f4ca8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1163,6 +1163,24 @@ ifndef NO_RUST CFLAGS += -DHAVE_RUST_SUPPORT $(call detected,CONFIG_RUST_SUPPORT) endif + + ifneq ($(CROSS_COMPILE),) + RUST_TARGET_FLAGS_arm := arm-unknown-linux-gnueabi + RUST_TARGET_FLAGS_arm64 := aarch64-unknown-linux-gnu + RUST_TARGET_FLAGS_m68k := m68k-unknown-linux-gnu + RUST_TARGET_FLAGS_mips := mipsel-unknown-linux-gnu + RUST_TARGET_FLAGS_powerpc := powerpc64le-unknown-linux-gnu + RUST_TARGET_FLAGS_riscv := riscv64gc-unknown-linux-gnu + RUST_TARGET_FLAGS_s390 := s390x-unknown-linux-gnu + RUST_TARGET_FLAGS_x86 := x86_64-unknown-linux-gnu + RUST_TARGET_FLAGS_x86_64 := x86_64-unknown-linux-gnu + + ifeq ($(RUST_TARGET_FLAGS_$(ARCH)),) + $(error Unknown rust cross compilation architecture $(ARCH)) + endif + + RUST_FLAGS += --target=$(RUST_TARGET_FLAGS_$(ARCH)) + endif endif # Among the variables below, these: diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 11b63bafdb23..f7b936deeaa2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -274,7 +274,7 @@ ifeq ($(PYLINT),1) PYLINT := $(shell which pylint 2> /dev/null) endif -export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS V BISON FLEX AWK +export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS RUST_FLAGS V BISON FLEX AWK export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK MYPY PYLINT include $(srctree)/tools/build/Makefile.include From 6036165ab1851ee28cedea592ee0393b77bfd0c0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 11:41:12 -0300 Subject: [PATCH 082/487] perf beauty: Sync linux/mount.h copy with the kernel sources To pick the changes from: 9b8a0ba68246a61d ("mount: add OPEN_TREE_NAMESPACE") 0e5032237ee55301 ("statmount: accept fd as a parameter") That doesn't change anything in tools this time as nothing that is harvested by the beauty scripts got changed: $ ls -1 tools/perf/trace/beauty/*mount*sh tools/perf/trace/beauty/fsmount.sh tools/perf/trace/beauty/mount_flags.sh tools/perf/trace/beauty/move_mount_flags.sh $ This addresses this perf build warning. Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/mount.h include/uapi/linux/mount.h Please see tools/include/uapi/README for further details. Cc: Christian Brauner Cc: Bhavik Sachdev Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/uapi/linux/mount.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index 5d3f8c9e3a62..d9d86598d100 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -61,7 +61,8 @@ /* * open_tree() flags. */ -#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */ +#define OPEN_TREE_CLONE (1 << 0) /* Clone the target tree and attach the clone */ +#define OPEN_TREE_NAMESPACE (1 << 1) /* Clone the target tree into a new mount namespace */ #define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */ /* @@ -197,7 +198,10 @@ struct statmount { */ struct mnt_id_req { __u32 size; - __u32 mnt_ns_fd; + union { + __u32 mnt_ns_fd; + __u32 mnt_fd; + }; __u64 mnt_id; __u64 param; __u64 mnt_ns_id; @@ -232,4 +236,9 @@ struct mnt_id_req { #define LSMT_ROOT 0xffffffffffffffff /* root mount */ #define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ +/* + * @flag bits for statmount(2) + */ +#define STATMOUNT_BY_FD 0x00000001U /* want mountinfo for given fd */ + #endif /* _UAPI_LINUX_MOUNT_H */ From e367679f167e46372cafca9cd903d60f84aa5e72 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 11:46:01 -0300 Subject: [PATCH 083/487] perf beauty: Sync UAPI linux/fs.h with kernel sources To pick up changes from: 0e6b7eae1fded85f ("fs: add FS_XFLAG_VERITY for fs-verity files") These are used to beautify fs syscall arguments, albeit the changes in this update are not affecting those beautifiers. This addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h Please see tools/include/uapi/README. Cc: Andrey Albershteyn Cc: Christian Brauner Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/uapi/linux/fs.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 66ca526cf786..70b2b661f42c 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -253,6 +253,7 @@ struct file_attr { #define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ #define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ #define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ +#define FS_XFLAG_VERITY 0x00020000 /* fs-verity enabled */ #define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ /* the read-only stuff doesn't really belong here, but any other place is From 3abbb7cae8d8bffae3516d885cde9f13c6ceb833 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 11:49:24 -0300 Subject: [PATCH 084/487] perf beauty: Update the arch/x86/include/asm/irq_vectors.h copy with the kernel sources To pick up the change in: a1fab3e69d9d0e9b ("x86/irq: Fix comment on IRQ vector layout") That just adds one comment, so no changes in perf tooling, just silences this build warning: diff -u tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h arch/x86/include/asm/irq_vectors.h Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h index 6e1d5b955aae..85253fc8e384 100644 --- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h +++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h @@ -77,6 +77,7 @@ */ #define IRQ_WORK_VECTOR 0xf6 +/* IRQ vector for PMIs when running a guest with a mediated PMU. */ #define PERF_GUEST_MEDIATED_PMI_VECTOR 0xf5 #define DEFERRED_ERROR_VECTOR 0xf4 From ecd5a2fd4c7495a1a923c754c47cdd500f5b30df Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 11:49:24 -0300 Subject: [PATCH 085/487] perf beauty: Update the linux/perf_event.h copy with the kernel sources Update it as one comment got realigned, probably in a merge, so no changes in perf tooling, just silences this build warning: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 76e9d0664d0c..fd10aa8d697f 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1396,7 +1396,7 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ #define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ -#define PERF_MEM_LVLNUM_L0 0x0007 /* L0 */ +#define PERF_MEM_LVLNUM_L0 0x0007 /* L0 */ #define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ From 916a9f385d81a65f7209614742208b8a923434bd Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 11:49:24 -0300 Subject: [PATCH 086/487] tools headers: Update the linux/gfp_types.h copy with the kernel sources To pick up the changes in: f3ec502b6755a3bf ("mm/slab: mark alloc tags empty for sheaves allocated with __GFP_NO_OBJ_EXT") 241b3a09639c317b ("mm: clarify GFP_ATOMIC/GFP_NOWAIT doc-comment") That just adds some comments, so no changes in perf tooling, just silences this build warning: Warning: Kernel ABI header differences: diff -u tools/include/linux/gfp_types.h include/linux/gfp_types.h Please see tools/include/uapi/README. Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/gfp_types.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h index 3de43b12209e..6c75df30a281 100644 --- a/tools/include/linux/gfp_types.h +++ b/tools/include/linux/gfp_types.h @@ -139,6 +139,8 @@ enum { * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. * * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension. + * mark_obj_codetag_empty() should be called upon freeing for objects allocated + * with this flag to indicate that their NULL tags are expected and normal. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) @@ -309,8 +311,10 @@ enum { * * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower * watermark is applied to allow access to "atomic reserves". - * The current implementation doesn't support NMI and few other strict - * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. + * The current implementation doesn't support NMI, nor contexts that disable + * preemption under PREEMPT_RT. This includes raw_spin_lock() and plain + * preempt_disable() - see "Memory allocation" in + * Documentation/core-api/real-time/differences.rst for more info. * * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. @@ -321,6 +325,7 @@ enum { * %GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. It is very * likely to fail to allocate memory, even for very small allocations. + * The same restrictions on calling contexts apply as for %GFP_ATOMIC. * * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. From 9cd284105bb77b063b61523f62096e853b8b890b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 12:32:19 -0300 Subject: [PATCH 087/487] tools headers UAPI: Sync linux/kvm.h with the kernel sources To pick the changes in: f7ab71f178d56447 ("KVM: s390: Add explicit padding to struct kvm_s390_keyop") 0ee4ddc1647b8b3b ("KVM: s390: Storage key manipulation IOCTL") fa9893fadbc245e1 ("KVM: Introduce KVM_EXIT_SNP_REQ_CERTS for SNP certificate-fetching") f174a9ffcd48d78a ("KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots") That just rebuilds perf, as these patches add just one new KVM ioctl, but for S390, that is not being considered by tools/perf/trace/beauty/kvm_ioctl.sh so far. This addresses this perf build warning: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Please see tools/include/uapi/README for further details. Cc: Arnd Bergmann Cc: Claudio Imbrenda Cc: Marc Zyngier Cc: Michael Roth Cc: Sean Christopherson Cc: Will Deacon Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/kvm.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index dddb781b0507..65500f5db379 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -135,6 +135,12 @@ struct kvm_xen_exit { } u; }; +struct kvm_exit_snp_req_certs { + __u64 gpa; + __u64 npages; + __u64 ret; +}; + #define KVM_S390_GET_SKEYS_NONE 1 #define KVM_S390_SKEYS_MAX 1048576 @@ -180,6 +186,8 @@ struct kvm_xen_exit { #define KVM_EXIT_MEMORY_FAULT 39 #define KVM_EXIT_TDX 40 #define KVM_EXIT_ARM_SEA 41 +#define KVM_EXIT_ARM_LDST64B 42 +#define KVM_EXIT_SNP_REQ_CERTS 43 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -402,7 +410,7 @@ struct kvm_run { } eoi; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; - /* KVM_EXIT_ARM_NISV */ + /* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */ struct { __u64 esr_iss; __u64 fault_ipa; @@ -482,6 +490,8 @@ struct kvm_run { __u64 gva; __u64 gpa; } arm_sea; + /* KVM_EXIT_SNP_REQ_CERTS */ + struct kvm_exit_snp_req_certs snp_req_certs; /* Fix the size of the union. */ char padding[256]; }; @@ -974,6 +984,7 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD_FLAGS 244 #define KVM_CAP_ARM_SEA_TO_USER 245 #define KVM_CAP_S390_USER_OPEREXEC 246 +#define KVM_CAP_S390_KEYOP 247 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1219,6 +1230,16 @@ struct kvm_vfio_spapr_tce { __s32 tablefd; }; +#define KVM_S390_KEYOP_ISKE 0x01 +#define KVM_S390_KEYOP_RRBE 0x02 +#define KVM_S390_KEYOP_SSKE 0x03 +struct kvm_s390_keyop { + __u64 guest_addr; + __u8 key; + __u8 operation; + __u8 pad[6]; +}; + /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. @@ -1238,6 +1259,7 @@ struct kvm_vfio_spapr_tce { #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) +#define KVM_S390_KEYOP _IOWR(KVMIO, 0x53, struct kvm_s390_keyop) /* Device model IOC */ #define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) From 4ebe2b8cda7e91a30c1cf1d297605682540d4ad9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 12:47:03 -0300 Subject: [PATCH 088/487] tools headers x86 cpufeatures: Sync with the kernel sources To pick the changes from: f24ef0093dd8cf60 ("KVM: x86: Advertise MOVRS CPUID to userspace") f49ecf5e110ab0ed ("x86/cpufeature: Replace X86_FEATURE_SYSENTER32 with X86_FEATURE_SYSFAST32") db5e82496492b489 ("KVM: SVM: Virtualize and advertise support for ERAPS") This causes these perf files to be rebuilt and brings some X86_FEATURE that may be used by: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header differences: diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Please see tools/include/uapi/README for further details. Cc: Amit Shah Cc: Dave Hansen Cc: H. Peter Anvin Cc: Sean Christopherson Cc: Zhao Liu Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index c3b53beb1300..dbe104df339b 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -84,7 +84,7 @@ #define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */ #define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* syscall in IA32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* sysenter in IA32 userspace */ +#define X86_FEATURE_SYSFAST32 ( 3*32+15) /* sysenter/syscall in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* "rep_good" REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */ #define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */ @@ -326,6 +326,7 @@ #define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */ #define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */ +#define X86_FEATURE_MOVRS (12*32+31) /* MOVRS instructions */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */ @@ -472,6 +473,7 @@ #define X86_FEATURE_GP_ON_USER_CPUID (20*32+17) /* User CPUID faulting */ #define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */ +#define X86_FEATURE_ERAPS (20*32+24) /* Enhanced Return Address Predictor Security */ #define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ From 1b3f004bac8e2c9e340ac237bd5b36b686ae63e8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 12:54:08 -0300 Subject: [PATCH 089/487] tools headers UAPI: Sync x86's asm/kvm.h with the kernel sources To pick the changes in: 6517dfbcc918f970 ("KVM: x86: Add x2APIC "features" to control EOI broadcast suppression") 20c3c4108d58f87c ("KVM: SEV: Add KVM_SEV_SNP_ENABLE_REQ_CERTS command") This silences these perf build warning: Warning: Kernel ABI header differences: diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h Please see tools/include/uapi/README for further details. Cc: Sean Christopherson Cc: Khushit Shah Cc: Michael Roth Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/kvm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7ceff6583652..846a63215ce1 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -503,6 +503,7 @@ struct kvm_sync_regs { #define KVM_X86_GRP_SEV 1 # define KVM_X86_SEV_VMSA_FEATURES 0 # define KVM_X86_SNP_POLICY_BITS 1 +# define KVM_X86_SEV_SNP_REQ_CERTS 2 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -743,6 +744,7 @@ enum sev_cmd_id { KVM_SEV_SNP_LAUNCH_START = 100, KVM_SEV_SNP_LAUNCH_UPDATE, KVM_SEV_SNP_LAUNCH_FINISH, + KVM_SEV_SNP_ENABLE_REQ_CERTS, KVM_SEV_NR_MAX, }; @@ -914,8 +916,10 @@ struct kvm_sev_snp_launch_finish { __u64 pad1[4]; }; -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) +#define KVM_X2APIC_API_USE_32BIT_IDS _BITULL(0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK _BITULL(1) +#define KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST _BITULL(2) +#define KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST _BITULL(3) struct kvm_hyperv_eventfd { __u32 conn_id; From 7a8464555d2e5f038758bb19e72ab4710b79e9cd Mon Sep 17 00:00:00 2001 From: zhidao su Date: Wed, 4 Mar 2026 13:37:30 +0800 Subject: [PATCH 090/487] sched_ext: Use WRITE_ONCE() for the write side of dsq->seq update bpf_iter_scx_dsq_new() reads dsq->seq via READ_ONCE() without holding any lock, making dsq->seq a lock-free concurrently accessed variable. However, dispatch_enqueue(), the sole writer of dsq->seq, uses a plain increment without the matching WRITE_ONCE() on the write side: dsq->seq++; ^^^^^^^^^^^ plain write -- KCSAN data race The KCSAN documentation requires that if one accessor uses READ_ONCE() or WRITE_ONCE() on a variable to annotate lock-free access, all other accesses must also use the appropriate accessor. A plain write leaves the pair incomplete and will trigger KCSAN warnings. Fix by using WRITE_ONCE() for the write side of the update: WRITE_ONCE(dsq->seq, dsq->seq + 1); This is consistent with bpf_iter_scx_dsq_new() and makes the concurrent access annotation complete and KCSAN-clean. Signed-off-by: zhidao su Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 1594987d637b..c56de568ed94 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1103,7 +1103,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq, } /* seq records the order tasks are queued, used by BPF DSQ iterator */ - dsq->seq++; + WRITE_ONCE(dsq->seq, dsq->seq + 1); p->scx.dsq_seq = dsq->seq; dsq_mod_nr(dsq, 1); From 50d7b4332f27762d24641970fc34bb68a2621926 Mon Sep 17 00:00:00 2001 From: "Pratyush Yadav (Google)" Date: Mon, 23 Feb 2026 18:39:28 +0100 Subject: [PATCH 091/487] mm: memfd_luo: always make all folios uptodate Patch series "mm: memfd_luo: fixes for folio flag preservation". This series contains a couple fixes for flag preservation for memfd live update. The first patch fixes memfd preservation when fallocate() was used to pre-allocate some pages. For these memfds, all the writes to fallocated pages touched after preserve were lost. The second patch fixes dirty flag tracking. If the dirty flag is not tracked correctly, the next kernel might incorrectly reclaim some folios under memory pressure, losing user data. This is a theoretical bug that I observed when reading the code, and haven't been able to reproduce it. This patch (of 2): When a folio is added to a shmem file via fallocate, it is not zeroed on allocation. This is done as a performance optimization since it is possible the folio will never end up being used at all. When the folio is used, shmem checks for the uptodate flag, and if absent, zeroes the folio (and sets the flag) before returning to user. With LUO, the flags of each folio are saved at preserve time. It is possible to have a memfd with some folios fallocated but not uptodate. For those, the uptodate flag doesn't get saved. The folios might later end up being used and become uptodate. They would get passed to the next kernel via KHO correctly since they did get preserved. But they won't have the MEMFD_LUO_FOLIO_UPTODATE flag. This means that when the memfd is retrieved, the folios will be added to the shmem file without the uptodate flag. They will be zeroed before first use, losing the data in those folios. Since we take a big performance hit in allocating, zeroing, and pinning all folios at prepare time anyway, take some more and zero all non-uptodate ones too. Later when there is a stronger need to make prepare faster, this can be optimized. To avoid racing with another uptodate operation, take the folio lock. Link: https://lkml.kernel.org/r/20260223173931.2221759-2-pratyush@kernel.org Fixes: b3749f174d68 ("mm: memfd_luo: allow preserving memfd") Signed-off-by: Pratyush Yadav (Google) Reviewed-by: Mike Rapoport (Microsoft) Cc: Pasha Tatashin Cc: Signed-off-by: Andrew Morton --- mm/memfd_luo.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c index e485b828d173..1c9510289312 100644 --- a/mm/memfd_luo.c +++ b/mm/memfd_luo.c @@ -152,10 +152,31 @@ static int memfd_luo_preserve_folios(struct file *file, if (err) goto err_unpreserve; + folio_lock(folio); + if (folio_test_dirty(folio)) flags |= MEMFD_LUO_FOLIO_DIRTY; - if (folio_test_uptodate(folio)) - flags |= MEMFD_LUO_FOLIO_UPTODATE; + + /* + * If the folio is not uptodate, it was fallocated but never + * used. Saving this flag at prepare() doesn't work since it + * might change later when someone uses the folio. + * + * Since we have taken the performance penalty of allocating, + * zeroing, and pinning all the folios in the holes, take a bit + * more and zero all non-uptodate folios too. + * + * NOTE: For someone looking to improve preserve performance, + * this is a good place to look. + */ + if (!folio_test_uptodate(folio)) { + folio_zero_range(folio, 0, folio_size(folio)); + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + flags |= MEMFD_LUO_FOLIO_UPTODATE; + + folio_unlock(folio); pfolio->pfn = folio_pfn(folio); pfolio->flags = flags; From 7e04bf1f33151a30e06a65b74b5f2c19fc2be128 Mon Sep 17 00:00:00 2001 From: "Pratyush Yadav (Google)" Date: Mon, 23 Feb 2026 18:39:29 +0100 Subject: [PATCH 092/487] mm: memfd_luo: always dirty all folios A dirty folio is one which has been written to. A clean folio is its opposite. Since a clean folio has no user data, it can be freed under memory pressure. memfd preservation with LUO saves the flag at preserve(). This is problematic. The folio might get dirtied later. Saving it at freeze() also doesn't work, since the dirty bit from PTE is normally synced at unmap and there might still be mappings of the file at freeze(). To see why this is a problem, say a folio is clean at preserve, but gets dirtied later. The serialized state of the folio will mark it as clean. After retrieve, the next kernel will see the folio as clean and might try to reclaim it under memory pressure. This will result in losing user data. Mark all folios of the file as dirty, and always set the MEMFD_LUO_FOLIO_DIRTY flag. This comes with the side effect of making all clean folios un-reclaimable. This is a cost that has to be paid for participants of live update. It is not expected to be a common use case to preserve a lot of clean folios anyway. Since the value of pfolio->flags is a constant now, drop the flags variable and set it directly. Link: https://lkml.kernel.org/r/20260223173931.2221759-3-pratyush@kernel.org Fixes: b3749f174d68 ("mm: memfd_luo: allow preserving memfd") Signed-off-by: Pratyush Yadav (Google) Reviewed-by: Mike Rapoport (Microsoft) Cc: Pasha Tatashin Cc: Signed-off-by: Andrew Morton --- mm/memfd_luo.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c index 1c9510289312..b8edb9f981d7 100644 --- a/mm/memfd_luo.c +++ b/mm/memfd_luo.c @@ -146,7 +146,6 @@ static int memfd_luo_preserve_folios(struct file *file, for (i = 0; i < nr_folios; i++) { struct memfd_luo_folio_ser *pfolio = &folios_ser[i]; struct folio *folio = folios[i]; - unsigned int flags = 0; err = kho_preserve_folio(folio); if (err) @@ -154,8 +153,26 @@ static int memfd_luo_preserve_folios(struct file *file, folio_lock(folio); - if (folio_test_dirty(folio)) - flags |= MEMFD_LUO_FOLIO_DIRTY; + /* + * A dirty folio is one which has been written to. A clean folio + * is its opposite. Since a clean folio does not carry user + * data, it can be freed by page reclaim under memory pressure. + * + * Saving the dirty flag at prepare() time doesn't work since it + * can change later. Saving it at freeze() also won't work + * because the dirty bit is normally synced at unmap and there + * might still be a mapping of the file at freeze(). + * + * To see why this is a problem, say a folio is clean at + * preserve, but gets dirtied later. The pfolio flags will mark + * it as clean. After retrieve, the next kernel might try to + * reclaim this folio under memory pressure, losing user data. + * + * Unconditionally mark it dirty to avoid this problem. This + * comes at the cost of making clean folios un-reclaimable after + * live update. + */ + folio_mark_dirty(folio); /* * If the folio is not uptodate, it was fallocated but never @@ -174,12 +191,11 @@ static int memfd_luo_preserve_folios(struct file *file, flush_dcache_folio(folio); folio_mark_uptodate(folio); } - flags |= MEMFD_LUO_FOLIO_UPTODATE; folio_unlock(folio); pfolio->pfn = folio_pfn(folio); - pfolio->flags = flags; + pfolio->flags = MEMFD_LUO_FOLIO_DIRTY | MEMFD_LUO_FOLIO_UPTODATE; pfolio->index = folio->index; } From d210fdcac9c0d1380eab448aebc93f602c1cd4e6 Mon Sep 17 00:00:00 2001 From: Raul Pazemecxas De Andrade Date: Mon, 23 Feb 2026 17:10:59 -0800 Subject: [PATCH 093/487] mm/damon/core: clear walk_control on inactive context in damos_walk() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit damos_walk() sets ctx->walk_control to the caller-provided control structure before checking whether the context is running. If the context is inactive (damon_is_running() returns false), the function returns -EINVAL without clearing ctx->walk_control. This leaves a dangling pointer to a stack-allocated structure that will be freed when the caller returns. This is structurally identical to the bug fixed in commit f9132fbc2e83 ("mm/damon/core: remove call_control in inactive contexts") for damon_call(), which had the same pattern of linking a control object and returning an error without unlinking it. The dangling walk_control pointer can cause: 1. Use-after-free if the context is later started and kdamond    dereferences ctx->walk_control (e.g., in damos_walk_cancel()    which writes to control->canceled and calls complete()) 2. Permanent -EBUSY from subsequent damos_walk() calls, since the    stale pointer is non-NULL Nonetheless, the real user impact is quite restrictive. The use-after-free is impossible because there is no damos_walk() callers who starts the context later. The permanent -EBUSY can actually confuse users, as DAMON is not running. But the symptom is kept only while the context is turned off. Turning it on again will make DAMON internally uses a newly generated damon_ctx object that doesn't have the invalid damos_walk_control pointer, so everything will work fine again. Fix this by clearing ctx->walk_control under walk_control_lock before returning -EINVAL, mirroring the fix pattern from f9132fbc2e83. Link: https://lkml.kernel.org/r/20260224011102.56033-1-sj@kernel.org Fixes: bf0eaba0ff9c ("mm/damon/core: implement damos_walk()") Reported-by: Raul Pazemecxas De Andrade Closes: https://lore.kernel.org/CPUPR80MB8171025468965E583EF2490F956CA@CPUPR80MB8171.lamprd80.prod.outlook.com Signed-off-by: Raul Pazemecxas De Andrade Signed-off-by: SeongJae Park Reviewed-by: SeongJae Park Cc: [6.14+] Signed-off-by: Andrew Morton --- mm/damon/core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index adfc52fee9dc..c1d1091d307e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1562,8 +1562,13 @@ int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control) } ctx->walk_control = control; mutex_unlock(&ctx->walk_control_lock); - if (!damon_is_running(ctx)) + if (!damon_is_running(ctx)) { + mutex_lock(&ctx->walk_control_lock); + if (ctx->walk_control == control) + ctx->walk_control = NULL; + mutex_unlock(&ctx->walk_control_lock); return -EINVAL; + } wait_for_completion(&control->completion); if (control->canceled) return -ECANCELED; From f4355d6bb39fc8e53d772fa0654c8441b214e349 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Tue, 24 Feb 2026 22:12:31 -0500 Subject: [PATCH 094/487] mm/cma: move put_page_testzero() out of VM_WARN_ON in cma_release() When CONFIG_DEBUG_VM is not set, VM_WARN_ON is a NOP. Putting any statement with side effect inside it is incorrect. Collect all !put_page_testzero() results and check the sum using WARN instead after the loop. It restores the same check in free_contig_range() before commit e0c1326779cc ("mm: page_alloc: add alloc_contig_frozen_{range,pages}()"), the commit prior to the Fixes one. Link: https://lkml.kernel.org/r/20260225031231.2352011-1-ziy@nvidia.com Fixes: 9bda131c6093 ("mm: cma: add cma_alloc_frozen{_compound}()") Signed-off-by: Zi Yan Reported-by: Ron Economos Closes: https://lore.kernel.org/all/1b17c38f-30d3-4bb4-a7e1-e74b19ada885@w6rz.net/ Suggested-by: Kefeng Wang Reviewed-by: Vishal Moola (Oracle) Debugged-by: David Hildenbrand (Arm) Acked-by: David Hildenbrand (Arm) Tested-by: Ron Economos Reviewed-by: Kefeng Wang Reviewed-by: Anshuman Khandual Reviewed-by: SeongJae Park Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/cma.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/cma.c b/mm/cma.c index 94b5da468a7d..15cc0ae76c8e 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -1013,6 +1013,7 @@ bool cma_release(struct cma *cma, const struct page *pages, unsigned long count) { struct cma_memrange *cmr; + unsigned long ret = 0; unsigned long i, pfn; cmr = find_cma_memrange(cma, pages, count); @@ -1021,7 +1022,9 @@ bool cma_release(struct cma *cma, const struct page *pages, pfn = page_to_pfn(pages); for (i = 0; i < count; i++, pfn++) - VM_WARN_ON(!put_page_testzero(pfn_to_page(pfn))); + ret += !put_page_testzero(pfn_to_page(pfn)); + + WARN(ret, "%lu pages are still in use!\n", ret); __cma_release_frozen(cma, cmr, pages, count); From 2d28ed588f8d7d0d41b0a4fad7f0d05e4bbf1797 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 24 Feb 2026 16:24:34 -0800 Subject: [PATCH 095/487] Revert "ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor()" This change swapped out mod_node_page_state for lruvec_stat_add_folio. But, these two APIs are not interchangeable: the lruvec version also increments memcg stats, in addition to "global" pgdat stats. So after this change, the "pagetables" memcg stat in memory.stat always yields "0", which is a userspace visible regression. I tried to look for a refactor where we add a variant of lruvec_stat_mod_folio which takes a pgdat and a memcg instead of a folio, to try to adhere to the spirit of the original patch. But at the end of the day this just means we have to call folio_memcg(ptdesc_folio(ptdesc)) anyway, which doesn't really accomplish much. This regression is visible in master as well as 6.18 stable, so CC stable too. Link: https://lkml.kernel.org/r/20260225002434.2953895-1-axelrasmussen@google.com Fixes: f0c92726e89f ("ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor()") Signed-off-by: Axel Rasmussen Acked-by: Shakeel Butt Acked-by: Johannes Weiner Reviewed-by: Vishal Moola (Oracle) Cc: David Hildenbrand Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Roman Gushchin Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 5be3d8a8f806..abb4963c1f06 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3514,26 +3514,21 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc) -{ - return compound_nr(ptdesc_page(ptdesc)); -} - static inline void __pagetable_ctor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); - __SetPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc)); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); ptlock_free(ptdesc); - __ClearPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc)); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor_free(struct ptdesc *ptdesc) From 5548dd7fa84510f7bbce67c35cc3b388c86aeddf Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 26 Feb 2026 01:31:11 +0200 Subject: [PATCH 096/487] tools/testing: fix testing/vma and testing/radix-tree build Build of VMA and radix-tree tests is unhappy after the conversion of kzalloc() to kzalloc_obj() in lib/idr.c: cc -I../shared -I. -I../../include -I../../arch/x86/include -I../../../lib -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined -DNUM_VMA_FLAG_BITS=128 -DNUM_MM_FLAG_BITS=128 -c -o idr.o idr.c idr.c: In function `ida_alloc_range': idr.c:420:34: error: implicit declaration of function `kzalloc_obj'; did you mean `kzalloc_node'? [-Wimplicit-function-declaration] 420 | bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT); | ^~~~~~~~~~~ | kzalloc_node idr.c:420:32: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion] 420 | bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT); | ^ idr.c:447:40: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion] 447 | bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT); | ^ idr.c:468:15: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion] 468 | alloc = kzalloc_obj(*bitmap, gfp); | ^ make: *** [: idr.o] Error 1 Import necessary macros from include/linux to tools/include/linux to fix the compilation. Link: https://lkml.kernel.org/r/20260225233111.2760752-1-rppt@kernel.org Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types") Signed-off-by: Mike Rapoport (Microsoft) Tested-by: SeongJae Park Reviewed-by: Lorenzo Stoakes Cc: David Hildenbrand Cc: Kees Cook Cc: Liam Howlett Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- tools/include/linux/gfp.h | 4 ++++ tools/include/linux/overflow.h | 19 +++++++++++++++++++ tools/include/linux/slab.h | 9 +++++++++ 3 files changed, 32 insertions(+) diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h index 6a10ff5f5be9..9e957b57b694 100644 --- a/tools/include/linux/gfp.h +++ b/tools/include/linux/gfp.h @@ -5,6 +5,10 @@ #include #include +/* Helper macro to avoid gfp flags if they are the default one */ +#define __default_gfp(a,...) a +#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL) + static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h index dcb0c1bf6866..3427d7880326 100644 --- a/tools/include/linux/overflow.h +++ b/tools/include/linux/overflow.h @@ -68,6 +68,25 @@ __builtin_mul_overflow(__a, __b, __d); \ }) +/** + * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX + * @factor1: first factor + * @factor2: second factor + * + * Returns: calculate @factor1 * @factor2, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. The + * lvalue must be size_t to avoid implicit type conversion. + */ +static inline size_t __must_check size_mul(size_t factor1, size_t factor2) +{ + size_t bytes; + + if (check_mul_overflow(factor1, factor2, &bytes)) + return SIZE_MAX; + + return bytes; +} + /** * array_size() - Calculate size of 2-dimensional array. * diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h index 94937a699402..6d8e9413d5a4 100644 --- a/tools/include/linux/slab.h +++ b/tools/include/linux/slab.h @@ -202,4 +202,13 @@ static inline unsigned int kmem_cache_sheaf_size(struct slab_sheaf *sheaf) return sheaf->size; } +#define __alloc_objs(KMALLOC, GFP, TYPE, COUNT) \ +({ \ + const size_t __obj_size = size_mul(sizeof(TYPE), COUNT); \ + (TYPE *)KMALLOC(__obj_size, GFP); \ +}) + +#define kzalloc_obj(P, ...) \ + __alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), 1) + #endif /* _TOOLS_SLAB_H */ From ba4c3698e6963eacd8e7c86c13343631bfeabe55 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 26 Feb 2026 11:54:21 +0900 Subject: [PATCH 097/487] zram: rename writeback_compressed device attr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename writeback_compressed attr to compressed_writeback to avoid possible confusion and have more natural naming. writeback_compressed may look like an alternative version of writeback while in fact writeback_compressed only sets a writeback property. Make this distinction more clear with a new compressed_writeback name. This updates a feature which is new in 7.0-rcX. Link: https://lkml.kernel.org/r/20260226025429.1042083-1-senozhatsky@chromium.org Fixes: 4c1d61389e8e ("zram: introduce writeback_compressed device attribute") Signed-off-by: Sergey Senozhatsky Suggested-by: Minchan Kim Acked-by: Minchan Kim Cc: Brian Geffon Cc: Richard Chang Cc: Suren Baghdasaryan Cc: "Christoph Böhmwalder" Cc: Jens Axboe Cc: Jonathan Corbet Cc: Lars Ellenberg Cc: Philipp Reisner Cc: Shuah Khan Signed-off-by: Andrew Morton --- Documentation/ABI/testing/sysfs-block-zram | 4 ++-- Documentation/admin-guide/blockdev/zram.rst | 6 +++--- drivers/block/zram/zram_drv.c | 24 ++++++++++----------- drivers/block/zram/zram_drv.h | 2 +- 4 files changed, 18 insertions(+), 18 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index e538d4850d61..64c03010e951 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -151,11 +151,11 @@ Description: The algorithm_params file is write-only and is used to setup compression algorithm parameters. -What: /sys/block/zram/writeback_compressed +What: /sys/block/zram/compressed_writeback Date: Decemeber 2025 Contact: Richard Chang Description: - The writeback_compressed device atrribute toggles compressed + The compressed_writeback device atrribute toggles compressed writeback feature. What: /sys/block/zram/writeback_batch_size diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst index 94bb7f2245ee..451fa00d3004 100644 --- a/Documentation/admin-guide/blockdev/zram.rst +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -216,7 +216,7 @@ writeback_limit WO specifies the maximum amount of write IO zram writeback_limit_enable RW show and set writeback_limit feature writeback_batch_size RW show and set maximum number of in-flight writeback operations -writeback_compressed RW show and set compressed writeback feature +compressed_writeback RW show and set compressed writeback feature comp_algorithm RW show and change the compression algorithm algorithm_params WO setup compression algorithm parameters compact WO trigger memory compaction @@ -439,11 +439,11 @@ budget in next setting is user's job. By default zram stores written back pages in decompressed (raw) form, which means that writeback operation involves decompression of the page before writing it to the backing device. This behavior can be changed by enabling -`writeback_compressed` feature, which causes zram to write compressed pages +`compressed_writeback` feature, which causes zram to write compressed pages to the backing device, thus avoiding decompression overhead. To enable this feature, execute:: - $ echo yes > /sys/block/zramX/writeback_compressed + $ echo yes > /sys/block/zramX/compressed_writeback Note that this feature should be configured before the `zramX` device is initialized. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index bca33403fc8b..a324ede6206d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -549,7 +549,7 @@ static ssize_t bd_stat_show(struct device *dev, struct device_attribute *attr, return ret; } -static ssize_t writeback_compressed_store(struct device *dev, +static ssize_t compressed_writeback_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -564,12 +564,12 @@ static ssize_t writeback_compressed_store(struct device *dev, return -EBUSY; } - zram->wb_compressed = val; + zram->compressed_wb = val; return len; } -static ssize_t writeback_compressed_show(struct device *dev, +static ssize_t compressed_writeback_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -577,7 +577,7 @@ static ssize_t writeback_compressed_show(struct device *dev, struct zram *zram = dev_to_zram(dev); guard(rwsem_read)(&zram->dev_lock); - val = zram->wb_compressed; + val = zram->compressed_wb; return sysfs_emit(buf, "%d\n", val); } @@ -946,7 +946,7 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req) goto out; } - if (zram->wb_compressed) { + if (zram->compressed_wb) { /* * ZRAM_WB slots get freed, we need to preserve data required * for read decompression. @@ -960,7 +960,7 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req) set_slot_flag(zram, index, ZRAM_WB); set_slot_handle(zram, index, req->blk_idx); - if (zram->wb_compressed) { + if (zram->compressed_wb) { if (huge) set_slot_flag(zram, index, ZRAM_HUGE); set_slot_size(zram, index, size); @@ -1100,7 +1100,7 @@ static int zram_writeback_slots(struct zram *zram, */ if (!test_slot_flag(zram, index, ZRAM_PP_SLOT)) goto next; - if (zram->wb_compressed) + if (zram->compressed_wb) err = read_from_zspool_raw(zram, req->page, index); else err = read_from_zspool(zram, req->page, index); @@ -1429,7 +1429,7 @@ static void zram_async_read_endio(struct bio *bio) * * Keep the existing behavior for now. */ - if (zram->wb_compressed == false) { + if (zram->compressed_wb == false) { /* No decompression needed, complete the parent IO */ bio_endio(req->parent); bio_put(bio); @@ -1508,7 +1508,7 @@ static int read_from_bdev_sync(struct zram *zram, struct page *page, u32 index, flush_work(&req.work); destroy_work_on_stack(&req.work); - if (req.error || zram->wb_compressed == false) + if (req.error || zram->compressed_wb == false) return req.error; return decompress_bdev_page(zram, page, index); @@ -3007,7 +3007,7 @@ static DEVICE_ATTR_WO(writeback); static DEVICE_ATTR_RW(writeback_limit); static DEVICE_ATTR_RW(writeback_limit_enable); static DEVICE_ATTR_RW(writeback_batch_size); -static DEVICE_ATTR_RW(writeback_compressed); +static DEVICE_ATTR_RW(compressed_writeback); #endif #ifdef CONFIG_ZRAM_MULTI_COMP static DEVICE_ATTR_RW(recomp_algorithm); @@ -3031,7 +3031,7 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_writeback_limit.attr, &dev_attr_writeback_limit_enable.attr, &dev_attr_writeback_batch_size.attr, - &dev_attr_writeback_compressed.attr, + &dev_attr_compressed_writeback.attr, #endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, @@ -3091,7 +3091,7 @@ static int zram_add(void) init_rwsem(&zram->dev_lock); #ifdef CONFIG_ZRAM_WRITEBACK zram->wb_batch_size = 32; - zram->wb_compressed = false; + zram->compressed_wb = false; #endif /* gendisk structure */ diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 515a72d9c06f..f0de8f8218f5 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -133,7 +133,7 @@ struct zram { #ifdef CONFIG_ZRAM_WRITEBACK struct file *backing_dev; bool wb_limit_enable; - bool wb_compressed; + bool compressed_wb; u32 wb_batch_size; u64 bd_wb_limit; struct block_device *bdev; From a1e59fc6ee4ed8988ea4aeb9224e75d03175be9c Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Thu, 26 Feb 2026 17:56:30 +0530 Subject: [PATCH 098/487] mm/hugetlb.c: use __pa() instead of virt_to_phys() in early bootmem alloc code Architecture like powerpc, checks for pfn_valid() in their virt_to_phys() implementation (when CONFIG_DEBUG_VIRTUAL is enabled) [1]. Commit d49004c5f0c1 "arch, mm: consolidate initialization of nodes, zones and memory map" changed the order of initialization between hugetlb_bootmem_alloc() and free_area_init(). This means, pfn_valid() can now return false in alloc_bootmem() path, since sparse_init() is not yet done. Since, alloc_bootmem() uses memblock_alloc(.., MEMBLOCK_ALLOC_ACCESSIBLE), this means these allocations are always going to happen below high_memory, where __pa() should return valid physical addresses. Hence this patch converts the two callers of virt_to_phys() in alloc_bootmem() path to __pa() to avoid this bootup warning: ------------[ cut here ]------------ WARNING: arch/powerpc/include/asm/io.h:879 at virt_to_phys+0x44/0x1b8, CPU#0: swapper/0 Modules linked in: <...> NIP [c000000000601584] virt_to_phys+0x44/0x1b8 LR [c000000004075de4] alloc_bootmem+0x144/0x1a8 Call Trace: [c000000004d1fb50] [c000000004075dd4] alloc_bootmem+0x134/0x1a8 [c000000004d1fba0] [c000000004075fac] __alloc_bootmem_huge_page+0x164/0x230 [c000000004d1fbe0] [c000000004030bc4] alloc_bootmem_huge_page+0x44/0x138 [c000000004d1fc10] [c000000004076e48] hugetlb_hstate_alloc_pages+0x350/0x5ac [c000000004d1fd30] [c0000000040782f0] hugetlb_bootmem_alloc+0x15c/0x19c [c000000004d1fd70] [c00000000406d7b4] mm_core_init_early+0x7c/0xdf4 [c000000004d1ff30] [c000000004011d84] start_kernel+0xac/0xc58 [c000000004d1ffe0] [c00000000000e99c] start_here_common+0x1c/0x20 [1]: https://lore.kernel.org/linuxppc-dev/87tsv5h544.ritesh.list@gmail.com/ Link: https://lkml.kernel.org/r/b4a7d2c6c4c1dd81dddc904fc21f01303290a4b8.1772107852.git.riteshh@linux.ibm.com Fixes: d49004c5f0c1 ("arch, mm: consolidate initialization of nodes, zones and memory map") Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Mike Rapoport (Microsoft) Cc: David Hildenbrand Cc: Muchun Song Cc: Oscar Salvador Signed-off-by: Andrew Morton --- mm/hugetlb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0beb6e22bc26..327eaa4074d3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3101,7 +3101,7 @@ static __init void *alloc_bootmem(struct hstate *h, int nid, bool node_exact) * extract the actual node first. */ if (m) - listnode = early_pfn_to_nid(PHYS_PFN(virt_to_phys(m))); + listnode = early_pfn_to_nid(PHYS_PFN(__pa(m))); } if (m) { @@ -3160,7 +3160,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) * The head struct page is used to get folio information by the HugeTLB * subsystem like zone id and node id. */ - memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), + memblock_reserved_mark_noinit(__pa((void *)m + PAGE_SIZE), huge_page_size(h) - PAGE_SIZE); return 1; From dccd5ee2625d50239510bcd73ed78559005e00a3 Mon Sep 17 00:00:00 2001 From: Hao Li Date: Thu, 26 Feb 2026 19:51:37 +0800 Subject: [PATCH 099/487] memcg: fix slab accounting in refill_obj_stock() trylock path In the trylock path of refill_obj_stock(), mod_objcg_mlstate() should use the real alloc/free bytes (i.e., nr_acct) for accounting, rather than nr_bytes. The user-visible impact is that the NR_SLAB_RECLAIMABLE_B and NR_SLAB_UNRECLAIMABLE_B stats can end up being incorrect. For example, if a user allocates a 6144-byte object, then before this fix efill_obj_stock() calls mod_objcg_mlstate(..., nr_bytes=2048), even though it should account for 6144 bytes (i.e., nr_acct). When the user later frees the same object with kfree(), refill_obj_stock() calls mod_objcg_mlstate(..., nr_bytes=6144). This ends up adding 6144 to the stats, but it should be applying -6144 (i.e., nr_acct) since the object is being freed. Link: https://lkml.kernel.org/r/20260226115145.62903-1-hao.li@linux.dev Fixes: 200577f69f29 ("memcg: objcg stock trylock without irq disabling") Signed-off-by: Hao Li Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a52da3a5e4fd..772bac21d155 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3086,7 +3086,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, if (!local_trylock(&obj_stock.lock)) { if (pgdat) - mod_objcg_mlstate(objcg, pgdat, idx, nr_bytes); + mod_objcg_mlstate(objcg, pgdat, idx, nr_acct); nr_pages = nr_bytes >> PAGE_SHIFT; nr_bytes = nr_bytes & (PAGE_SIZE - 1); atomic_add(nr_bytes, &objcg->nr_charged_bytes); From 06de173b138513087896f9cf090f30b35846518d Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Sun, 1 Mar 2026 10:09:02 +0800 Subject: [PATCH 100/487] MAINTAINERS: add RELAY entry RELAYFS was originally developed by Tom Zanussi and Karim Yaghmour in 2005[1]. Jens Axboe converted it from filesystem into a generic API in 2006[2] and made it widely known through the notable I/O tracing tool blktrace. In the decade, there remain a few users scatterred across different subsystems, like recently added wifi commit[3] that is an example to show how to communicate between users and kernel. Last year I've already done some maintenance and added/corrected some diagnostic counters. At Tencent, we internally maintain RELAY as one of most crucial components of network observibility platform which was shared a bit at LPC 2025[4][5] and hopefully will be published in the paper this year. RELAY has proven highly efficient due to its inherent design essence. This design becomes the indispensable way to build a 7x24 platform monitoring various hot paths even without any selectively sampling (yes, sampling is commonly used to avoid the overall performance degradation). One of the recommended usages is to use its zerocopy function relay_reserve() to transfer data in a raw format that can be recognized and parsed by the corresponding application to userspace without introducing heavy locks and complicated logic that appears in other types of approaches, like printk. More details can be discovered by reading through the Documentation :) Credits are given to the all the contributors and reviewers for RELAY/RELAYFS in the past and future! Many thanks! [1]: commit e82894f84dbb ("[PATCH] relayfs") [2]: commit b86ff981a825 ("[PATCH] relay: migrate from relayfs to a generic relay API") [3]: commit c1bf6959dd81 ("wifi: ath11k: Register relayfs entries for CFR dump") [4]: https://lpc.events/event/19/contributions/2055/ [5]: https://lpc.events/event/19/contributions/2010/ Link: https://lkml.kernel.org/r/20260301020902.56476-1-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Acked-by: Andrew Morton Acked-by: Jens Axboe Cc: Andriy Shevchenko Cc: Tom Zanussi Signed-off-by: Andrew Morton --- MAINTAINERS | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e4572a36afd2..0ecf11bab619 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22284,6 +22284,16 @@ L: linux-wireless@vger.kernel.org S: Orphan F: drivers/net/wireless/rsi/ +RELAY +M: Andrew Morton +M: Jens Axboe +M: Jason Xing +L: linux-kernel@vger.kernel.org +S: Maintained +F: Documentation/filesystems/relay.rst +F: include/linux/relay.h +F: kernel/relay.c + REGISTER MAP ABSTRACTION M: Mark Brown L: linux-kernel@vger.kernel.org From 431b04f0084d244569e81ca4216a40644b23b0c5 Mon Sep 17 00:00:00 2001 From: "Vlastimil Babka (SUSE)" Date: Mon, 2 Mar 2026 11:13:46 +0100 Subject: [PATCH 101/487] MAINTAINERS: add co-maintainer and reviewer for SLAB ALLOCATOR Promote Harry Yoo from reviewer to maintainer. Harry's been involved in slab development for multiple years now and doing a great job. Add Hao Li as a new reviewer. Hao has been doing very useful reviews for a while now, so make it official and ensure the Cc's. Link: https://lkml.kernel.org/r/20260302101345.36713-2-vbabka@kernel.org Signed-off-by: Vlastimil Babka (SUSE) Acked-by: Lorenzo Stoakes Acked-by: Harry Yoo Acked-by: Hao Li Acked-by: SeongJae Park Cc: Christoph Lameter Cc: David Rientjes Cc: Roman Gushchin Signed-off-by: Andrew Morton --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 0ecf11bab619..e510fbc6f882 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -24361,11 +24361,12 @@ F: drivers/nvmem/layouts/sl28vpd.c SLAB ALLOCATOR M: Vlastimil Babka +M: Harry Yoo M: Andrew Morton +R: Hao Li R: Christoph Lameter R: David Rientjes R: Roman Gushchin -R: Harry Yoo L: linux-mm@kvack.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git From 577a1f495fd78d8fb61b67ac3d3b595b01f6fcb0 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Mon, 2 Mar 2026 15:31:59 -0500 Subject: [PATCH 102/487] mm/huge_memory: fix a folio_split() race condition with folio_try_get() During a pagecache folio split, the values in the related xarray should not be changed from the original folio at xarray split time until all after-split folios are well formed and stored in the xarray. Current use of xas_try_split() in __split_unmapped_folio() lets some after-split folios show up at wrong indices in the xarray. When these misplaced after-split folios are unfrozen, before correct folios are stored via __xa_store(), and grabbed by folio_try_get(), they are returned to userspace at wrong file indices, causing data corruption. More detailed explanation is at the bottom. The reproducer is at: https://github.com/dfinity/thp-madv-remove-test It 1. creates a memfd, 2. forks, 3. in the child process, maps the file with large folios (via shmem code path) and reads the mapped file continuously with 16 threads, 4. in the parent process, uses madvise(MADV_REMOVE) to punch poles in the large folio. Data corruption can be observed without the fix. Basically, data from a wrong page->index is returned. Fix it by using the original folio in xas_try_split() calls, so that folio_try_get() can get the right after-split folios after the original folio is unfrozen. Uniform split, split_huge_page*(), is not affected, since it uses xas_split_alloc() and xas_split() only once and stores the original folio in the xarray. Change xas_split() used in uniform split branch to use the original folio to avoid confusion. Fixes below points to the commit introduces the code, but folio_split() is used in a later commit 7460b470a131f ("mm/truncate: use folio_split() in truncate operation"). More details: For example, a folio f is split non-uniformly into f, f2, f3, f4 like below: +----------------+---------+----+----+ | f | f2 | f3 | f4 | +----------------+---------+----+----+ but the xarray would look like below after __split_unmapped_folio() is done: +----------------+---------+----+----+ | f | f2 | f3 | f3 | +----------------+---------+----+----+ After __split_unmapped_folio(), the code changes the xarray and unfreezes after-split folios: 1. unfreezes f2, __xa_store(f2) 2. unfreezes f3, __xa_store(f3) 3. unfreezes f4, __xa_store(f4), which overwrites the second f3 to f4. 4. unfreezes f. Meanwhile, a parallel filemap_get_entry() can read the second f3 from the xarray and use folio_try_get() on it at step 2 when f3 is unfrozen. Then, f3 is wrongly returned to user. After the fix, the xarray looks like below after __split_unmapped_folio(): +----------------+---------+----+----+ | f | f | f | f | +----------------+---------+----+----+ so that the race window no longer exists. [ziy@nvidia.com: move comment, per David] Link: https://lkml.kernel.org/r/5C9FA053-A4C6-4615-BE05-74E47A6462B3@nvidia.com Link: https://lkml.kernel.org/r/20260302203159.3208341-1-ziy@nvidia.com Fixes: 00527733d0dc ("mm/huge_memory: add two new (not yet used) functions for folio_split()") Signed-off-by: Zi Yan Reported-by: Bas van Dijk Closes: https://lore.kernel.org/all/CAKNNEtw5_kZomhkugedKMPOG-sxs5Q5OLumWJdiWXv+C9Yct0w@mail.gmail.com/ Tested-by: Lance Yang Reviewed-by: Lorenzo Stoakes Reviewed-by: Wei Yang Reviewed-by: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Hugh Dickins Cc: Liam Howlett Cc: Matthew Wilcox (Oracle) Cc: Nico Pache Cc: Ryan Roberts Cc: Signed-off-by: Andrew Morton --- mm/huge_memory.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8e2746ea74ad..912c248a3f7e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3631,6 +3631,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order, const bool is_anon = folio_test_anon(folio); int old_order = folio_order(folio); int start_order = split_type == SPLIT_TYPE_UNIFORM ? new_order : old_order - 1; + struct folio *old_folio = folio; int split_order; /* @@ -3651,12 +3652,16 @@ static int __split_unmapped_folio(struct folio *folio, int new_order, * uniform split has xas_split_alloc() called before * irq is disabled to allocate enough memory, whereas * non-uniform split can handle ENOMEM. + * Use the to-be-split folio, so that a parallel + * folio_try_get() waits on it until xarray is updated + * with after-split folios and the original one is + * unfrozen. */ - if (split_type == SPLIT_TYPE_UNIFORM) - xas_split(xas, folio, old_order); - else { + if (split_type == SPLIT_TYPE_UNIFORM) { + xas_split(xas, old_folio, old_order); + } else { xas_set_order(xas, folio->index, split_order); - xas_try_split(xas, folio, old_order); + xas_try_split(xas, old_folio, old_order); if (xas_error(xas)) return xas_error(xas); } From 7392f8e4ea632622b2cd2086675ba022db238b3a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 1 Mar 2026 16:52:29 -0800 Subject: [PATCH 103/487] uaccess: correct kernel-doc parameter format Use the correct kernel-doc function parameter format to avoid kernel-doc warnings: Warning: include/linux/uaccess.h:814 function parameter 'uptr' not described in 'scoped_user_rw_access_size' Warning: include/linux/uaccess.h:826 function parameter 'uptr' not described in 'scoped_user_rw_access' Link: https://lkml.kernel.org/r/20260302005229.3471955-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1f3804245c06..001cfef21b61 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -806,7 +806,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access_size - Start a scoped user read/write access with given size - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @size: Size of the access starting from @uptr * @elbl: Error label to goto when the access region is rejected * @@ -817,7 +817,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access - Start a scoped user read/write access - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @elbl: Error label to goto when the access region is rejected * * The size of the access starting from @uptr is determined via sizeof(*@uptr)). From 599b4e290c8766b19378d85d4310c6ec8f90ade4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 1 Mar 2026 16:52:22 -0800 Subject: [PATCH 104/487] mm/mmu_notifier: clean up mmu_notifier.h kernel-doc Eliminate kernel-doc warnings in mmu_notifier.h: - add a missing struct short description - use the correct format for function parameters - add missing function return comment sections Warning: include/linux/mmu_notifier.h:236 missing initial short description on line: * struct mmu_interval_notifier_ops Warning: include/linux/mmu_notifier.h:325 function parameter 'interval_sub' not described in 'mmu_interval_set_seq' Warning: include/linux/mmu_notifier.h:325 function parameter 'cur_seq' not described in 'mmu_interval_set_seq' Warning: include/linux/mmu_notifier.h:346 function parameter 'interval_sub' not described in 'mmu_interval_read_retry' Warning: include/linux/mmu_notifier.h:346 function parameter 'seq' not described in 'mmu_interval_read_retry' Warning: include/linux/mmu_notifier.h:346 No description found for return value of 'mmu_interval_read_retry' Warning: include/linux/mmu_notifier.h:370 function parameter 'interval_sub' not described in 'mmu_interval_check_retry' Warning: include/linux/mmu_notifier.h:370 function parameter 'seq' not described in 'mmu_interval_check_retry' Warning: include/linux/mmu_notifier.h:370 No description found for return value of 'mmu_interval_check_retry' Link: https://lkml.kernel.org/r/20260302005222.3470783-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Reviewed-by: Jason Gunthorpe Cc: David Hildenbrand Cc: "Liam R. Howlett" Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Randy Dunlap Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mmu_notifier.h | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 07a2bbaf86e9..8450e18a87c2 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -234,7 +234,7 @@ struct mmu_notifier { }; /** - * struct mmu_interval_notifier_ops + * struct mmu_interval_notifier_ops - callback for range notification * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. @@ -309,8 +309,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence - * @interval_sub - The subscription passed to invalidate - * @cur_seq - The cur_seq passed to the invalidate() callback + * @interval_sub: The subscription passed to invalidate + * @cur_seq: The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call @@ -329,8 +329,8 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_read_retry - End a read side critical section against a VA range - * interval_sub: The subscription - * seq: The return of the paired mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). @@ -338,7 +338,7 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * - * Returns true if an invalidation collided with this critical section, and + * Returns: true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool @@ -350,20 +350,21 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_check_retry - Test if a collision has occurred - * interval_sub: The subscription - * seq: The return of the matching mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() - * and mmu_interval_read_retry(). A return of true indicates an invalidation - * has collided with this critical region and a future - * mmu_interval_read_retry() will return true. - * - * False is not reliable and only suggests a collision may not have - * occurred. It can be called many times and does not have to hold the user - * provided lock. + * and mmu_interval_read_retry(). * * This call can be used as part of loops and other expensive operations to * expedite a retry. + * It can be called many times and does not have to hold the user + * provided lock. + * + * Returns: true indicates an invalidation has collided with this critical + * region and a future mmu_interval_read_retry() will return true. + * False is not reliable and only suggests a collision may not have + * occurred. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, From b12bbe35c7c1e431f2fa01fe9291daa52fb7ab43 Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (Oracle)" Date: Tue, 3 Mar 2026 19:50:25 +0000 Subject: [PATCH 105/487] MAINTAINERS, mailmap: update email address for Lorenzo Stoakes I want to experiment with a new email setup, and using the @kernel.org address is the easiest way to have flexibility on this. Link: https://lkml.kernel.org/r/20260303195025.1170895-1-ljs@kernel.org Signed-off-by: Lorenzo Stoakes (Oracle) Signed-off-by: Andrew Morton --- .mailmap | 3 ++- MAINTAINERS | 20 ++++++++++---------- 2 files changed, 12 insertions(+), 11 deletions(-) diff --git a/.mailmap b/.mailmap index c124a1306d26..fd062abdb133 100644 --- a/.mailmap +++ b/.mailmap @@ -491,7 +491,8 @@ Lior David Loic Poulain Loic Poulain Lorenzo Pieralisi -Lorenzo Stoakes +Lorenzo Stoakes +Lorenzo Stoakes Luca Ceresoli Luca Weiss Lucas De Marchi diff --git a/MAINTAINERS b/MAINTAINERS index e510fbc6f882..a3b4e75ad1ce 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16654,7 +16654,7 @@ F: mm/balloon.c MEMORY MANAGEMENT - CORE M: Andrew Morton M: David Hildenbrand -R: Lorenzo Stoakes +R: Lorenzo Stoakes R: Liam R. Howlett R: Vlastimil Babka R: Mike Rapoport @@ -16784,7 +16784,7 @@ F: mm/workingset.c MEMORY MANAGEMENT - MISC M: Andrew Morton M: David Hildenbrand -R: Lorenzo Stoakes +R: Lorenzo Stoakes R: Liam R. Howlett R: Vlastimil Babka R: Mike Rapoport @@ -16875,7 +16875,7 @@ R: David Hildenbrand R: Michal Hocko R: Qi Zheng R: Shakeel Butt -R: Lorenzo Stoakes +R: Lorenzo Stoakes L: linux-mm@kvack.org S: Maintained F: mm/vmscan.c @@ -16884,7 +16884,7 @@ F: mm/workingset.c MEMORY MANAGEMENT - RMAP (REVERSE MAPPING) M: Andrew Morton M: David Hildenbrand -M: Lorenzo Stoakes +M: Lorenzo Stoakes R: Rik van Riel R: Liam R. Howlett R: Vlastimil Babka @@ -16929,7 +16929,7 @@ F: mm/swapfile.c MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) M: Andrew Morton M: David Hildenbrand -M: Lorenzo Stoakes +M: Lorenzo Stoakes R: Zi Yan R: Baolin Wang R: Liam R. Howlett @@ -16969,7 +16969,7 @@ F: tools/testing/selftests/mm/uffd-*.[ch] MEMORY MANAGEMENT - RUST M: Alice Ryhl -R: Lorenzo Stoakes +R: Lorenzo Stoakes R: Liam R. Howlett L: linux-mm@kvack.org L: rust-for-linux@vger.kernel.org @@ -16985,7 +16985,7 @@ F: rust/kernel/page.rs MEMORY MAPPING M: Andrew Morton M: Liam R. Howlett -M: Lorenzo Stoakes +M: Lorenzo Stoakes R: Vlastimil Babka R: Jann Horn R: Pedro Falcato @@ -17015,7 +17015,7 @@ MEMORY MAPPING - LOCKING M: Andrew Morton M: Suren Baghdasaryan M: Liam R. Howlett -M: Lorenzo Stoakes +M: Lorenzo Stoakes R: Vlastimil Babka R: Shakeel Butt L: linux-mm@kvack.org @@ -17030,7 +17030,7 @@ F: mm/mmap_lock.c MEMORY MAPPING - MADVISE (MEMORY ADVICE) M: Andrew Morton M: Liam R. Howlett -M: Lorenzo Stoakes +M: Lorenzo Stoakes M: David Hildenbrand R: Vlastimil Babka R: Jann Horn @@ -23183,7 +23183,7 @@ K: \b(?i:rust)\b RUST [ALLOC] M: Danilo Krummrich -R: Lorenzo Stoakes +R: Lorenzo Stoakes R: Vlastimil Babka R: Liam R. Howlett R: Uladzislau Rezki From da994db94e60f9a9411108ddf4d1836147ad4c9c Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 20 Feb 2026 15:11:48 -0600 Subject: [PATCH 106/487] remoteproc: sysmon: Correct subsys_name_len type in QMI request The QMI message encoder has up until recently read a single byte (as elem_size == 1), but with the introduction of big endian support it's become apparent that this field is expected to be a full u32 - regardless of the size of the length in the encoded message (which is what elem_size specifies). The result is that the encoder now reads past the length byte and rejects the unreasonably large length formed when including the following 3 bytes from the subsys_name array. Fix this by changing to the expected type. Fixes: 1fb82ee806d1 ("remoteproc: qcom: Introduce sysmon") Signed-off-by: Bjorn Andersson Reviewed-by: Chris Lew Link: https://lore.kernel.org/r/20260220-qmi-encode-invalid-length-v2-1-5674be35ab29@oss.qualcomm.com Signed-off-by: Bjorn Andersson --- drivers/remoteproc/qcom_sysmon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c index cf10e8ecfb8f..3ceec1fd6d99 100644 --- a/drivers/remoteproc/qcom_sysmon.c +++ b/drivers/remoteproc/qcom_sysmon.c @@ -203,7 +203,7 @@ static const struct qmi_elem_info ssctl_shutdown_resp_ei[] = { }; struct ssctl_subsys_event_req { - u8 subsys_name_len; + u32 subsys_name_len; char subsys_name[SSCTL_SUBSYS_NAME_LENGTH]; u32 event; u8 evt_driven_valid; From 6944e6d8a6d4c1e654de1da112da8fef1b30e623 Mon Sep 17 00:00:00 2001 From: Cheng-Yang Chou Date: Thu, 5 Mar 2026 03:57:57 +0800 Subject: [PATCH 107/487] sched_ext/selftests: Fix format specifier and buffer length in file_write_long() Use %ld (not %lu) for signed long, and pass the actual string length returned by sprintf() to write_text() instead of sizeof(buf). Signed-off-by: Cheng-Yang Chou Signed-off-by: Tejun Heo --- tools/testing/selftests/sched_ext/util.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c index e47769c91918..2111329ed289 100644 --- a/tools/testing/selftests/sched_ext/util.c +++ b/tools/testing/selftests/sched_ext/util.c @@ -60,11 +60,11 @@ int file_write_long(const char *path, long val) char buf[64]; int ret; - ret = sprintf(buf, "%lu", val); + ret = sprintf(buf, "%ld", val); if (ret < 0) return ret; - if (write_text(path, buf, sizeof(buf)) <= 0) + if (write_text(path, buf, ret) <= 0) return -1; return 0; From 281cb17787d4284a7790b9cbd80fded826ca7739 Mon Sep 17 00:00:00 2001 From: hongao Date: Wed, 4 Mar 2026 19:29:14 +0800 Subject: [PATCH 108/487] xfs: Remove redundant NULL check after __GFP_NOFAIL kzalloc() is called with __GFP_NOFAIL, so a NULL return is not expected. Drop the redundant !map check in xfs_dabuf_map(). Also switch the nirecs-sized allocation to kcalloc(). Signed-off-by: hongao Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_da_btree.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 766631f0562e..09d4c17b3e7b 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2716,12 +2716,8 @@ xfs_dabuf_map( * larger one that needs to be free by the caller. */ if (nirecs > 1) { - map = kzalloc(nirecs * sizeof(struct xfs_buf_map), - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - if (!map) { - error = -ENOMEM; - goto out_free_irecs; - } + map = kcalloc(nirecs, sizeof(struct xfs_buf_map), + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); *mapp = map; } From ac6769c8f948dff33265c50e524aebf9aa6f1be0 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 28 Feb 2026 16:45:59 +0000 Subject: [PATCH 109/487] KVM: arm64: Eagerly init vgic dist/redist on vgic creation If vgic_allocate_private_irqs_locked() fails for any odd reason, we exit kvm_vgic_create() early, leaving dist->rd_regions uninitialised. kvm_vgic_dist_destroy() then comes along and walks into the weeds trying to free the RDs. Got to love this stuff. Solve it by moving all the static initialisation early, and make sure that if we fail halfway, we're in a reasonable shape to perform the rest of the teardown. While at it, reset the vgic model on failure, just in case... Reported-by: syzbot+f6a46b038fc243ac0175@syzkaller.appspotmail.com Tested-by: syzbot+f6a46b038fc243ac0175@syzkaller.appspotmail.com Fixes: b3aa9283c0c50 ("KVM: arm64: vgic: Hoist SGI/PPI alloc from vgic_init() to kvm_create_vgic()") Link: https://lore.kernel.org/r/69a2d58c.050a0220.3a55be.003b.GAE@google.com Link: https://patch.msgid.link/20260228164559.936268-1-maz@kernel.org Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org --- arch/arm64/kvm/vgic/vgic-init.c | 34 ++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 9b3091ad868c..e9b8b5fc480c 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -143,23 +143,6 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST; - - kvm_for_each_vcpu(i, vcpu, kvm) { - ret = vgic_allocate_private_irqs_locked(vcpu, type); - if (ret) - break; - } - - if (ret) { - kvm_for_each_vcpu(i, vcpu, kvm) { - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - kfree(vgic_cpu->private_irqs); - vgic_cpu->private_irqs = NULL; - } - - goto out_unlock; - } - kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; @@ -176,6 +159,23 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); + kvm_for_each_vcpu(i, vcpu, kvm) { + ret = vgic_allocate_private_irqs_locked(vcpu, type); + if (ret) + break; + } + + if (ret) { + kvm_for_each_vcpu(i, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + kfree(vgic_cpu->private_irqs); + vgic_cpu->private_irqs = NULL; + } + + kvm->arch.vgic.vgic_model = 0; + goto out_unlock; + } + if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->arch.vgic.nassgicap = system_supports_direct_sgis(); From 8531d5a83d8eb8affb5c0249b466c28d94192603 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 5 Mar 2026 13:27:51 +0000 Subject: [PATCH 110/487] KVM: arm64: pkvm: Fallback to level-3 mapping on host stage-2 fault If, for any odd reason, we cannot converge to mapping size that is completely contained in a memblock region, we fail to install a S2 mapping and go back to the faulting instruction. Rince, repeat. This happens when faulting in regions that are smaller than a page or that do not have PAGE_SIZE-aligned boundaries (as witnessed on an O6 board that refuses to boot in protected mode). In this situation, fallback to using a PAGE_SIZE mapping anyway -- it isn't like we can go any lower. Fixes: e728e705802fe ("KVM: arm64: Adjust range correctly during host stage-2 faults") Link: https://lore.kernel.org/r/86wlzr77cn.wl-maz@kernel.org Cc: stable@vger.kernel.org Cc: Quentin Perret Reviewed-by: Quentin Perret Link: https://patch.msgid.link/20260305132751.2928138-1-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 38f66a56a766..d815265bd374 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -518,7 +518,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) granule = kvm_granule_size(level); cur.start = ALIGN_DOWN(addr, granule); cur.end = cur.start + granule; - if (!range_included(&cur, range)) + if (!range_included(&cur, range) && level < KVM_PGTABLE_LAST_LEVEL) continue; *range = cur; return 0; From 4c2264ecdf39ddbdb62e37b156015aacf05d0dcb Mon Sep 17 00:00:00 2001 From: "Zenghui Yu (Huawei)" Date: Thu, 26 Feb 2026 01:35:13 +0800 Subject: [PATCH 111/487] KVM: arm64: nv: Check S2 limits based on implemented PA size check_base_s2_limits() checks the validity of SL0 and inputsize against ia_size (inputsize again!) but the pseudocode from DDI0487 G.a AArch64.TranslationTableWalk() says that we should check against the implemented PA size. We would otherwise fail to walk S2 with a valid configuration. E.g., granule size = 4KB, inputsize = 40 bits, initial lookup level = 0 (no concatenation) on a system with 48 bits PA range supported is allowed by architecture. Fix it by obtaining PA size by kvm_get_pa_bits(). Note that kvm_get_pa_bits() returns the fixed limit now and should eventually reflect the per VM PARange (one day!). Given that the configured PARange should not be greater that kvm_ipa_limit, it at least fixes the problem described above. While at it, inject a level 0 translation fault to guest if check_base_s2_limits() fails, as per the pseudocode. Fixes: 61e30b9eef7f ("KVM: arm64: nv: Implement nested Stage-2 page table walk logic") Signed-off-by: Zenghui Yu (Huawei) Link: https://patch.msgid.link/20260225173515.20490-2-zenghui.yu@linux.dev Signed-off-by: Marc Zyngier --- arch/arm64/kvm/nested.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 12c9f6e8dfda..9da28814b646 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -152,31 +152,31 @@ static int get_ia_size(struct s2_walk_info *wi) return 64 - wi->t0sz; } -static int check_base_s2_limits(struct s2_walk_info *wi, +static int check_base_s2_limits(struct kvm_vcpu *vcpu, struct s2_walk_info *wi, int level, int input_size, int stride) { - int start_size, ia_size; + int start_size, pa_max; - ia_size = get_ia_size(wi); + pa_max = kvm_get_pa_bits(vcpu->kvm); /* Check translation limits */ switch (BIT(wi->pgshift)) { case SZ_64K: - if (level == 0 || (level == 1 && ia_size <= 42)) + if (level == 0 || (level == 1 && pa_max <= 42)) return -EFAULT; break; case SZ_16K: - if (level == 0 || (level == 1 && ia_size <= 40)) + if (level == 0 || (level == 1 && pa_max <= 40)) return -EFAULT; break; case SZ_4K: - if (level < 0 || (level == 0 && ia_size <= 42)) + if (level < 0 || (level == 0 && pa_max <= 42)) return -EFAULT; break; } /* Check input size limits */ - if (input_size > ia_size) + if (input_size > pa_max) return -EFAULT; /* Check number of entries in starting level table */ @@ -269,9 +269,11 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, if (input_size > 48 || input_size < 25) return -EFAULT; - ret = check_base_s2_limits(wi, level, input_size, stride); - if (WARN_ON(ret)) + ret = check_base_s2_limits(vcpu, wi, level, input_size, stride); + if (WARN_ON(ret)) { + out->esr = compute_fsc(0, ESR_ELx_FSC_FAULT); return ret; + } base_lower_bound = 3 + input_size - ((3 - level) * stride + wi->pgshift); From 99a339377f3c1bdf6edd5614d36893ab1806f9e6 Mon Sep 17 00:00:00 2001 From: "Zenghui Yu (Huawei)" Date: Thu, 26 Feb 2026 01:35:14 +0800 Subject: [PATCH 112/487] KVM: arm64: nv: Report addrsz fault at level 0 with a bad VTTBR.BADDR As per R_BFHQH, " When an Address size fault is generated, the reported fault code indicates one of the following: If the fault was generated due to the TTBR_ELx used in the translation having nonzero address bits above the OA size, then a fault at level 0. " Fix the reported Address size fault level as being 0 if the base address is wrongly programmed by L1. Fixes: 61e30b9eef7f ("KVM: arm64: nv: Implement nested Stage-2 page table walk logic") Signed-off-by: Zenghui Yu (Huawei) Link: https://patch.msgid.link/20260225173515.20490-3-zenghui.yu@linux.dev Signed-off-by: Marc Zyngier --- arch/arm64/kvm/nested.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 9da28814b646..91e4f3cb580a 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -280,7 +280,8 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound); if (check_output_size(wi, base_addr)) { - out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); + /* R_BFHQH */ + out->esr = compute_fsc(0, ESR_ELx_FSC_ADDRSZ); return 1; } From eb54fa1025f8b520f0e83a807d76e35e4587c5ff Mon Sep 17 00:00:00 2001 From: "Zenghui Yu (Huawei)" Date: Thu, 26 Feb 2026 01:35:15 +0800 Subject: [PATCH 113/487] KVM: arm64: nv: Inject a SEA if failed to read the descriptor Failure to read the descriptor (because it is outside of a memslot) should result in a SEA being injected in the guest. Suggested-by: Marc Zyngier Link: https://lore.kernel.org/r/86ms1m9lp3.wl-maz@kernel.org Signed-off-by: Zenghui Yu (Huawei) Link: https://patch.msgid.link/20260225173515.20490-4-zenghui.yu@linux.dev Signed-off-by: Marc Zyngier --- arch/arm64/kvm/nested.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 91e4f3cb580a..2c43097248b2 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -296,8 +296,10 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, paddr = base_addr | index; ret = read_guest_s2_desc(vcpu, paddr, &desc, wi); - if (ret < 0) + if (ret < 0) { + out->esr = ESR_ELx_FSC_SEA_TTW(level); return ret; + } new_desc = desc; From 0927780c90ce551869fb692279d66387a4b66af5 Mon Sep 17 00:00:00 2001 From: zhidao su Date: Thu, 5 Mar 2026 14:18:56 +0800 Subject: [PATCH 114/487] sched_ext: Use READ_ONCE() for lock-free reads of module param variables bypass_lb_cpu() reads scx_bypass_lb_intv_us and scx_slice_bypass_us without holding any lock, in timer callback context where module parameter writes via sysfs can happen concurrently: min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV; ^^^^^^^^^^^^^^^^^^^^ plain read -- KCSAN data race if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us)) ^^^^^^^^^^^^^^^^^ plain read -- KCSAN data race scx_bypass_lb_intv_us already uses READ_ONCE() in scx_bypass_lb_timerfn() and scx_bypass() for its other lock-free read sites, leaving bypass_lb_cpu() inconsistent. scx_slice_bypass_us has the same lock-free access pattern in the same function. Fix both plain reads by using READ_ONCE() to complete the concurrent access annotation and make the code KCSAN-clean. Signed-off-by: zhidao su Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index c56de568ed94..10866bfb88bf 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3908,8 +3908,8 @@ static u32 bypass_lb_cpu(struct scx_sched *sch, struct rq *rq, * consider offloading iff the total queued duration is over the * threshold. */ - min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV; - if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us)) + min_delta_us = READ_ONCE(scx_bypass_lb_intv_us) / SCX_BYPASS_LB_MIN_DELTA_DIV; + if (delta < DIV_ROUND_UP(min_delta_us, READ_ONCE(scx_slice_bypass_us))) return 0; raw_spin_rq_lock_irq(rq); From 70f54f61a3d52af13b72248a63e98eddf4c990ac Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Thu, 5 Mar 2026 07:29:00 +0100 Subject: [PATCH 115/487] sched_ext: Document task ownership state machine The task ownership state machine in sched_ext is quite hard to follow from the code alone. The interaction of ownership states, memory ordering rules and cross-CPU "lock dancing" makes the overall model subtle. Extend the documentation next to scx_ops_state to provide a more structured and self-contained description of the state transitions and their synchronization rules. The new reference should make the code easier to reason about and maintain and can help future contributors understand the overall task-ownership workflow. Signed-off-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext_internal.h | 114 +++++++++++++++++++++++++++++++----- 1 file changed, 98 insertions(+), 16 deletions(-) diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 11ebb744d893..00b450597f3e 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -1035,26 +1035,108 @@ static const char *scx_enable_state_str[] = { }; /* - * sched_ext_entity->ops_state + * Task Ownership State Machine (sched_ext_entity->ops_state) * - * Used to track the task ownership between the SCX core and the BPF scheduler. - * State transitions look as follows: + * The sched_ext core uses this state machine to track task ownership + * between the SCX core and the BPF scheduler. This allows the BPF + * scheduler to dispatch tasks without strict ordering requirements, while + * the SCX core safely rejects invalid dispatches. * - * NONE -> QUEUEING -> QUEUED -> DISPATCHING - * ^ | | - * | v v - * \-------------------------------/ + * State Transitions * - * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call - * sites for explanations on the conditions being waited upon and why they are - * safe. Transitions out of them into NONE or QUEUED must store_release and the - * waiters should load_acquire. + * .------------> NONE (owned by SCX core) + * | | ^ + * | enqueue | | direct dispatch + * | v | + * | QUEUEING -------' + * | | + * | enqueue | + * | completes | + * | v + * | QUEUED (owned by BPF scheduler) + * | | + * | dispatch | + * | | + * | v + * | DISPATCHING + * | | + * | dispatch | + * | completes | + * `---------------' * - * Tracking scx_ops_state enables sched_ext core to reliably determine whether - * any given task can be dispatched by the BPF scheduler at all times and thus - * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler - * to try to dispatch any task anytime regardless of its state as the SCX core - * can safely reject invalid dispatches. + * State Descriptions + * + * - %SCX_OPSS_NONE: + * Task is owned by the SCX core. It's either on a run queue, running, + * or being manipulated by the core scheduler. The BPF scheduler has no + * claim on this task. + * + * - %SCX_OPSS_QUEUEING: + * Transitional state while transferring a task from the SCX core to + * the BPF scheduler. The task's rq lock is held during this state. + * Since QUEUEING is both entered and exited under the rq lock, dequeue + * can never observe this state (it would be a BUG). When finishing a + * dispatch, if the task is still in %SCX_OPSS_QUEUEING the completion + * path busy-waits for it to leave this state (via wait_ops_state()) + * before retrying. + * + * - %SCX_OPSS_QUEUED: + * Task is owned by the BPF scheduler. It's on a DSQ (dispatch queue) + * and the BPF scheduler is responsible for dispatching it. A QSEQ + * (queue sequence number) is embedded in this state to detect + * dispatch/dequeue races: if a task is dequeued and re-enqueued, the + * QSEQ changes and any in-flight dispatch operations targeting the old + * QSEQ are safely ignored. + * + * - %SCX_OPSS_DISPATCHING: + * Transitional state while transferring a task from the BPF scheduler + * back to the SCX core. This state indicates the BPF scheduler has + * selected the task for execution. When dequeue needs to take the task + * off a DSQ and it is still in %SCX_OPSS_DISPATCHING, the dequeue path + * busy-waits for it to leave this state (via wait_ops_state()) before + * proceeding. Exits to %SCX_OPSS_NONE when dispatch completes. + * + * Memory Ordering + * + * Transitions out of %SCX_OPSS_QUEUEING and %SCX_OPSS_DISPATCHING into + * %SCX_OPSS_NONE or %SCX_OPSS_QUEUED must use atomic_long_set_release() + * and waiters must use atomic_long_read_acquire(). This ensures proper + * synchronization between concurrent operations. + * + * Cross-CPU Task Migration + * + * When moving a task in the %SCX_OPSS_DISPATCHING state, we can't simply + * grab the target CPU's rq lock because a concurrent dequeue might be + * waiting on %SCX_OPSS_DISPATCHING while holding the source rq lock + * (deadlock). + * + * The sched_ext core uses a "lock dancing" protocol coordinated by + * p->scx.holding_cpu. When moving a task to a different rq: + * + * 1. Verify task can be moved (CPU affinity, migration_disabled, etc.) + * 2. Set p->scx.holding_cpu to the current CPU + * 3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING + * is set, so clearing DISPATCHING first prevents the circular wait + * (safe to lock the rq we need) + * 4. Unlock the current CPU's rq + * 5. Lock src_rq (where the task currently lives) + * 6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the + * race (dequeue clears holding_cpu to -1 when it takes the task), in + * this case migration is aborted + * 7. If src_rq == dst_rq: clear holding_cpu and enqueue directly + * into dst_rq's local DSQ (no lock swap needed) + * 8. Otherwise: call move_remote_task_to_local_dsq(), which releases + * src_rq, locks dst_rq, and performs the deactivate/activate + * migration cycle (dst_rq is held on return) + * 9. Unlock dst_rq and re-lock the current CPU's rq to restore + * the lock state expected by the caller + * + * If any verification fails, abort the migration. + * + * This state tracking allows the BPF scheduler to try to dispatch any task + * at any time regardless of its state. The SCX core can safely + * reject/ignore invalid dispatches, simplifying the BPF scheduler + * implementation. */ enum scx_ops_state { SCX_OPSS_NONE, /* owned by the SCX core */ From e07fc9e2da91f6d9eeafa2961be9dc09d65ed633 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Wed, 4 Mar 2026 16:22:21 +0000 Subject: [PATCH 116/487] KVM: arm64: Fix page leak in user_mem_abort() on atomic fault When a guest performs an atomic/exclusive operation on memory lacking the required attributes, user_mem_abort() injects a data abort and returns early. However, it fails to release the reference to the host page acquired via __kvm_faultin_pfn(). A malicious guest could repeatedly trigger this fault, leaking host page references and eventually causing host memory exhaustion (OOM). Fix this by consolidating the early error returns to a new out_put_page label that correctly calls kvm_release_page_unused(). Fixes: 2937aeec9dc5 ("KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory") Signed-off-by: Fuad Tabba Reviewed-by: Yuan Yao Link: https://patch.msgid.link/20260304162222.836152-2-tabba@google.com Signed-off-by: Marc Zyngier --- arch/arm64/kvm/mmu.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index ec2eee857208..e1d6a4f591a9 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1837,10 +1837,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (exec_fault && s2_force_noncacheable) ret = -ENOEXEC; - if (ret) { - kvm_release_page_unused(page); - return ret; - } + if (ret) + goto out_put_page; /* * Guest performs atomic/exclusive operations on memory with unsupported @@ -1850,7 +1848,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, */ if (esr_fsc_is_excl_atomic_fault(kvm_vcpu_get_esr(vcpu))) { kvm_inject_dabt_excl_atomic(vcpu, kvm_vcpu_get_hfar(vcpu)); - return 1; + ret = 1; + goto out_put_page; } if (nested) @@ -1936,6 +1935,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, mark_page_dirty_in_slot(kvm, memslot, gfn); return ret != -EAGAIN ? ret : 0; + +out_put_page: + kvm_release_page_unused(page); + return ret; } /* Resolve the access fault by making the page young again. */ From 35c3f72a2d55dbf52f28f4ecae51c76be1acf545 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Fri, 6 Feb 2026 03:30:33 +0000 Subject: [PATCH 117/487] remoteproc: mediatek: Unprepare SCP clock during system suspend Prior to commit d935187cfb27 ("remoteproc: mediatek: Break lock dependency to prepare_lock"), `scp->clk` was prepared and enabled only when it needs to communicate with the SCP. The commit d935187cfb27 moved the prepare operation to remoteproc's prepare(), keeping the clock prepared as long as the SCP is running. The power consumption due to the prolonged clock preparation can be negligible when the system is running, as SCP is designed to be a very power efficient processor. However, the clock remains prepared even when the system enters system suspend. This prevents the underlying clock controller (and potentially the parent PLLs) from shutting down, which increases power consumption and may block the system from entering deep sleep states. Add suspend and resume callbacks. Unprepare the clock in suspend() if it was active and re-prepare it in resume() to ensure the clock is properly disabled during system suspend, while maintaining the "always prepared" semantics while the system is active. The driver doesn't implement .attach() callback, hence it only checks for RPROC_RUNNING. Fixes: d935187cfb27 ("remoteproc: mediatek: Break lock dependency to prepare_lock") Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20260206033034.3031781-1-tzungbi@kernel.org Signed-off-by: Mathieu Poirier --- drivers/remoteproc/mtk_scp.c | 39 ++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c index 4651311aeb07..bb6f6a16d895 100644 --- a/drivers/remoteproc/mtk_scp.c +++ b/drivers/remoteproc/mtk_scp.c @@ -1592,12 +1592,51 @@ static const struct of_device_id mtk_scp_of_match[] = { }; MODULE_DEVICE_TABLE(of, mtk_scp_of_match); +static int __maybe_unused scp_suspend(struct device *dev) +{ + struct mtk_scp *scp = dev_get_drvdata(dev); + struct rproc *rproc = scp->rproc; + + /* + * Only unprepare if the SCP is running and holding the clock. + * + * Note: `scp_ops` doesn't implement .attach() callback, hence + * `rproc->state` can never be RPROC_ATTACHED. Otherwise, it + * should also be checked here. + */ + if (rproc->state == RPROC_RUNNING) + clk_unprepare(scp->clk); + return 0; +} + +static int __maybe_unused scp_resume(struct device *dev) +{ + struct mtk_scp *scp = dev_get_drvdata(dev); + struct rproc *rproc = scp->rproc; + + /* + * Only prepare if the SCP was running and holding the clock. + * + * Note: `scp_ops` doesn't implement .attach() callback, hence + * `rproc->state` can never be RPROC_ATTACHED. Otherwise, it + * should also be checked here. + */ + if (rproc->state == RPROC_RUNNING) + return clk_prepare(scp->clk); + return 0; +} + +static const struct dev_pm_ops scp_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(scp_suspend, scp_resume) +}; + static struct platform_driver mtk_scp_driver = { .probe = scp_probe, .remove = scp_remove, .driver = { .name = "mtk-scp", .of_match_table = mtk_scp_of_match, + .pm = &scp_pm_ops, }, }; From 97e4567d39941248579da34b7fbb568e6659511e Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sun, 8 Feb 2026 19:30:35 +0800 Subject: [PATCH 118/487] remoteproc: imx_rproc: Fix unreachable platform prepare_ops Smatch reports unreachable code in imx_rproc_prepare(), where an early return inside the reserved-memory parsing loop prevents platform prepare_ops from being executed. When of_reserved_mem_region_to_resource() fails, imx_rproc_prepare() returns immediately, so the platform-specific prepare callback is never called. As a result, prepare_ops such as imx_rproc_sm_lmm_prepare() on i.MX95 have no chance to run. This is problematic when Linux controls the M7 Logical Machine and is responsible for preparing resources such as TCM. Without running the platform prepare callback, loading the M7 ELF into TCM may fail if the bootloader did not power up and initialize TCM. Fix this by breaking out of the reserved-memory loop instead of returning, allowing the platform prepare_ops to be executed as intended. Fixes: edd2a9956055 ("remoteproc: imx_rproc: Introduce prepare ops for imx_rproc_dcfg") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-remoteproc/aYYXAa2Fj36XG4yQ@p14s/T/#t Signed-off-by: Peng Fan Reviewed-by: Daniel Baluta Link: https://lore.kernel.org/r/20260208-imx-rproc-fix-v1-1-ad74555eb9a4@nxp.com Signed-off-by: Mathieu Poirier --- drivers/remoteproc/imx_rproc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index f5f916d67905..8c8ddbf995a4 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -617,7 +617,7 @@ static int imx_rproc_prepare(struct rproc *rproc) err = of_reserved_mem_region_to_resource(np, i++, &res); if (err) - return 0; + break; /* * Ignore the first memory region which will be used vdev buffer. From f42f9091be9e5ff57567a3945cfcdd498f475348 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:37 -0800 Subject: [PATCH 119/487] workqueue: Use POOL_BH instead of WQ_BH when checking pool flags pr_cont_worker_id() checks pool->flags against WQ_BH, which is a workqueue-level flag (defined in workqueue.h). Pool flags use a separate namespace with POOL_* constants (defined in workqueue.c). The correct constant is POOL_BH. Both WQ_BH and POOL_BH are defined as (1 << 0) so this has no behavioral impact, but it is semantically wrong and inconsistent with every other pool-level BH check in the file. Fixes: 4cb1ef64609f ("workqueue: Implement BH workqueues to eventually replace tasklets") Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index aeaec79bc09c..1e5b6cb0fbda 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6274,7 +6274,7 @@ static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; - if (pool->flags & WQ_BH) + if (pool->flags & POOL_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else From 6037160e52d72028da68546fd270a7dcac130d85 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:38 -0800 Subject: [PATCH 120/487] workqueue: Rename pool->watchdog_ts to pool->last_progress_ts The watchdog_ts name doesn't convey what the timestamp actually tracks. This field tracks the last time a workqueue got progress. Rename it to last_progress_ts to make it clear that it records when the pool last made forward progress (started processing new work items). No functional change. Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1e5b6cb0fbda..687d5c55c617 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -190,7 +190,7 @@ struct worker_pool { int id; /* I: pool ID */ unsigned int flags; /* L: flags */ - unsigned long watchdog_ts; /* L: watchdog timestamp */ + unsigned long last_progress_ts; /* L: last forward progress timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* @@ -1697,7 +1697,7 @@ static void __pwq_activate_work(struct pool_workqueue *pwq, WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) - pwq->pool->watchdog_ts = jiffies; + pwq->pool->last_progress_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } @@ -2348,7 +2348,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) - pool->watchdog_ts = jiffies; + pool->last_progress_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); @@ -3352,7 +3352,7 @@ static void process_scheduled_works(struct worker *worker) while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { - worker->pool->watchdog_ts = jiffies; + worker->pool->last_progress_ts = jiffies; first = false; } process_one_work(worker, work); @@ -4850,7 +4850,7 @@ static int init_worker_pool(struct worker_pool *pool) pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; - pool->watchdog_ts = jiffies; + pool->last_progress_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); @@ -6462,7 +6462,7 @@ static void show_one_worker_pool(struct worker_pool *pool) /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) - hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; + hung = jiffies_to_msecs(jiffies - pool->last_progress_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that @@ -7691,7 +7691,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); - pool_ts = READ_ONCE(pool->watchdog_ts); + pool_ts = READ_ONCE(pool->last_progress_ts); if (time_after(pool_ts, touched)) ts = pool_ts; From e8e14ac7cfe437b896838e7f7d07c573965b4e4e Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:39 -0800 Subject: [PATCH 121/487] workqueue: Show in-flight work item duration in stall diagnostics When diagnosing workqueue stalls, knowing how long each in-flight work item has been executing is valuable. Add a current_start timestamp (jiffies) to struct worker, set it when a work item begins execution in process_one_work(), and print the elapsed wall-clock time in show_pwq(). Unlike current_at (which tracks CPU runtime and resets on wakeup for CPU-intensive detection), current_start is never reset because the diagnostic cares about total wall-clock time including sleeps. Before: in-flight: 165:stall_work_fn [wq_stall] After: in-flight: 165:stall_work_fn [wq_stall] for 100s Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 3 +++ kernel/workqueue_internal.h | 1 + 2 files changed, 4 insertions(+) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 687d5c55c617..56d8af13843f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3204,6 +3204,7 @@ __acquires(&pool->lock) worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; + worker->current_start = jiffies; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); @@ -6359,6 +6360,8 @@ static void show_pwq(struct pool_workqueue *pwq) pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); + pr_cont(" for %us", + jiffies_to_msecs(jiffies - worker->current_start) / 1000); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index f6275944ada7..8def1ddc5a1b 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -32,6 +32,7 @@ struct worker { work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ + unsigned long current_start; /* K: start time of current work item */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ From 8823eaef45da7f156a1396f40d53b985c511edef Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:40 -0800 Subject: [PATCH 122/487] workqueue: Show all busy workers in stall diagnostics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit show_cpu_pool_hog() only prints workers whose task is currently running on the CPU (task_is_running()). This misses workers that are busy processing a work item but are sleeping or blocked — for example, a worker that clears PF_WQ_WORKER and enters wait_event_idle(). Such a worker still occupies a pool slot and prevents progress, yet produces an empty backtrace section in the watchdog output. This is happening on real arm64 systems, where toggle_allocation_gate() IPIs every single CPU in the machine (which lacks NMI), causing workqueue stalls that show empty backtraces because toggle_allocation_gate() is sleeping in wait_event_idle(). Remove the task_is_running() filter so every in-flight worker in the pool's busy_hash is dumped. The busy_hash is protected by pool->lock, which is already held. Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 56d8af13843f..09b9ad78d566 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -7583,9 +7583,9 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds /* * Show workers that might prevent the processing of pending work items. - * The only candidates are CPU-bound workers in the running state. - * Pending work items should be handled by another idle worker - * in all other situations. + * A busy worker that is not running on the CPU (e.g. sleeping in + * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as + * effectively as a CPU-bound one, so dump every in-flight worker. */ static void show_cpu_pool_hog(struct worker_pool *pool) { @@ -7596,19 +7596,17 @@ static void show_cpu_pool_hog(struct worker_pool *pool) raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { - if (task_is_running(worker->task)) { - /* - * Defer printing to avoid deadlocks in console - * drivers that queue work while holding locks - * also taken in their write paths. - */ - printk_deferred_enter(); + /* + * Defer printing to avoid deadlocks in console + * drivers that queue work while holding locks + * also taken in their write paths. + */ + printk_deferred_enter(); - pr_info("pool %d:\n", pool->id); - sched_show_task(worker->task); + pr_info("pool %d:\n", pool->id); + sched_show_task(worker->task); - printk_deferred_exit(); - } + printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); @@ -7619,7 +7617,7 @@ static void show_cpu_pools_hogs(void) struct worker_pool *pool; int pi; - pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); + pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n"); rcu_read_lock(); From 9e83d5104a70d8545bad61a77e166190d9447e1d Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:41 -0800 Subject: [PATCH 123/487] workqueue: Add stall detector sample module Add a sample module under samples/workqueue/stall_detector/ that reproduces a workqueue stall caused by PF_WQ_WORKER misuse. The module queues two work items on the same per-CPU pool, then clears PF_WQ_WORKER and sleeps in wait_event_idle(), hiding from the concurrency manager and stalling the second work item indefinitely. This is useful for testing the workqueue watchdog stall diagnostics. Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- samples/workqueue/stall_detector/Makefile | 1 + samples/workqueue/stall_detector/wq_stall.c | 98 +++++++++++++++++++++ 2 files changed, 99 insertions(+) create mode 100644 samples/workqueue/stall_detector/Makefile create mode 100644 samples/workqueue/stall_detector/wq_stall.c diff --git a/samples/workqueue/stall_detector/Makefile b/samples/workqueue/stall_detector/Makefile new file mode 100644 index 000000000000..8849e85e95bb --- /dev/null +++ b/samples/workqueue/stall_detector/Makefile @@ -0,0 +1 @@ +obj-m += wq_stall.o diff --git a/samples/workqueue/stall_detector/wq_stall.c b/samples/workqueue/stall_detector/wq_stall.c new file mode 100644 index 000000000000..6f4a497b1881 --- /dev/null +++ b/samples/workqueue/stall_detector/wq_stall.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * wq_stall - Test module for the workqueue stall detector. + * + * Deliberately creates a workqueue stall so the watchdog fires and + * prints diagnostic output. Useful for verifying that the stall + * detector correctly identifies stuck workers and produces useful + * backtraces. + * + * The stall is triggered by clearing PF_WQ_WORKER before sleeping, + * which hides the worker from the concurrency manager. A second + * work item queued on the same pool then sits in the worklist with + * no worker available to process it. + * + * After ~30s the workqueue watchdog fires: + * BUG: workqueue lockup - pool cpus=N ... + * + * Build: + * make -C M=samples/workqueue/stall_detector modules + * + * Copyright (c) 2026 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2026 Breno Leitao + */ + +#include +#include +#include +#include +#include + +static DECLARE_WAIT_QUEUE_HEAD(stall_wq_head); +static atomic_t wake_condition = ATOMIC_INIT(0); +static struct work_struct stall_work1; +static struct work_struct stall_work2; + +static void stall_work2_fn(struct work_struct *work) +{ + pr_info("wq_stall: second work item finally ran\n"); +} + +static void stall_work1_fn(struct work_struct *work) +{ + pr_info("wq_stall: first work item running on cpu %d\n", + raw_smp_processor_id()); + + /* + * Queue second item while we're still counted as running + * (pool->nr_running > 0). Since schedule_work() on a per-CPU + * workqueue targets raw_smp_processor_id(), item 2 lands on the + * same pool. __queue_work -> kick_pool -> need_more_worker() + * sees nr_running > 0 and does NOT wake a new worker. + */ + schedule_work(&stall_work2); + + /* + * Hide from the workqueue concurrency manager. Without + * PF_WQ_WORKER, schedule() won't call wq_worker_sleeping(), + * so nr_running is never decremented and no replacement + * worker is created. Item 2 stays stuck in pool->worklist. + */ + current->flags &= ~PF_WQ_WORKER; + + pr_info("wq_stall: entering wait_event_idle (PF_WQ_WORKER cleared)\n"); + pr_info("wq_stall: expect 'BUG: workqueue lockup' in ~30-60s\n"); + wait_event_idle(stall_wq_head, atomic_read(&wake_condition) != 0); + + /* Restore so process_one_work() cleanup works correctly */ + current->flags |= PF_WQ_WORKER; + pr_info("wq_stall: woke up, PF_WQ_WORKER restored\n"); +} + +static int __init wq_stall_init(void) +{ + pr_info("wq_stall: loading\n"); + + INIT_WORK(&stall_work1, stall_work1_fn); + INIT_WORK(&stall_work2, stall_work2_fn); + schedule_work(&stall_work1); + + return 0; +} + +static void __exit wq_stall_exit(void) +{ + pr_info("wq_stall: unloading\n"); + atomic_set(&wake_condition, 1); + wake_up(&stall_wq_head); + flush_work(&stall_work1); + flush_work(&stall_work2); + pr_info("wq_stall: all work flushed, module unloaded\n"); +} + +module_init(wq_stall_init); +module_exit(wq_stall_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Reproduce workqueue stall caused by PF_WQ_WORKER misuse"); +MODULE_AUTHOR("Breno Leitao "); From 1e972ec76e10cf9cdacf1db2fbf69f7216903a86 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 4 Mar 2026 17:22:20 -0300 Subject: [PATCH 124/487] tools arch x86: Sync msr-index.h to pick MSR_{OMR_[0-3],CORE_PERF_GLOBAL_STATUS_SET} To pick up the changes in: 4e955c08d6dc76fb ("perf/x86/intel: Support the 4 new OMR MSRs introduced in DMR and NVL") 736a2dcfdae72483 ("x86/CPU/AMD: Simplify the spectral chicken fix") 56bb2736975068cc ("KVM: x86/pmu: Load/put mediated PMU context when entering/exiting guest") Addressing this tools/perf build warning: Warning: Kernel ABI header differences: diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h That makes the beautification scripts to pick some new entries: $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before.txt $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after.txt $ diff -u before.txt after.txt --- before.txt 2026-03-04 17:21:39.165956041 -0300 +++ after.txt 2026-03-04 17:21:52.479191640 -0300 @@ -130,6 +130,11 @@ [0x0000038e] = "CORE_PERF_GLOBAL_STATUS", [0x0000038f] = "CORE_PERF_GLOBAL_CTRL", [0x00000390] = "CORE_PERF_GLOBAL_OVF_CTRL", + [0x00000391] = "CORE_PERF_GLOBAL_STATUS_SET", + [0x000003e0] = "OMR_0", + [0x000003e1] = "OMR_1", + [0x000003e2] = "OMR_2", + [0x000003e3] = "OMR_3", [0x000003f1] = "IA32_PEBS_ENABLE", [0x000003f2] = "PEBS_DATA_CFG", [0x000003f4] = "IA32_PEBS_BASE", $ Now one can use those strings in 'perf trace' to do filtering, e.g.: # perf trace -e msr:*_msr/max-stack=32/ --filter="msr==CORE_PERF_GLOBAL_STATUS_SET" Cc: Borislav Petkov (AMD) Cc: Dapeng Mi Cc: Peter Zijlstra Cc: Sean Christopherson Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 43adc38d31d5..da5275d8eda6 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -263,6 +263,11 @@ #define MSR_SNOOP_RSP_0 0x00001328 #define MSR_SNOOP_RSP_1 0x00001329 +#define MSR_OMR_0 0x000003e0 +#define MSR_OMR_1 0x000003e1 +#define MSR_OMR_2 0x000003e2 +#define MSR_OMR_3 0x000003e3 + #define MSR_LBR_SELECT 0x000001c8 #define MSR_LBR_TOS 0x000001c9 @@ -1219,6 +1224,7 @@ #define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e #define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f #define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 +#define MSR_CORE_PERF_GLOBAL_STATUS_SET 0x00000391 #define MSR_PERF_METRICS 0x00000329 From b3ce769203a99d6f3c6d6269ec09232a8c5da422 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 4 Mar 2026 11:06:12 -0800 Subject: [PATCH 125/487] perf disasm: Fix off-by-one bug in outside check If a branch target points to one past the end of a function, the branch should be treated as a branch to another function. This can happen e.g. with a tail call to a function that is laid out immediately after the caller. Fixes: 751b1783da784299 ("perf annotate: Mark jumps to outher functions with the call arrow") Reviewed-by: Ian Rogers Signed-off-by: Peter Collingbourne Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Bill Wendling Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Justin Stitt Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Link: https://linux-review.googlesource.com/id/Ide471112e82d68177e0faf08ca411d9fcf0a7bdf Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/disasm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index ddcc488f2e5f..9e0420e14be1 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -384,7 +384,7 @@ static int jump__parse(const struct arch *arch, struct ins_operands *ops, struct start = map__unmap_ip(map, sym->start); end = map__unmap_ip(map, sym->end); - ops->target.outside = target.addr < start || target.addr > end; + ops->target.outside = target.addr < start || target.addr >= end; /* * FIXME: things like this in _cpp_lex_token (gcc's cc1 program): From c9d77f0a0c78eacdf6bbac07c494205a2c3053b4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 5 Mar 2026 17:16:07 -0300 Subject: [PATCH 126/487] tools headers: Update the syscall tables and unistd.h, to support the new 'rseq_slice_yield' syscall Picking up the changes from these csets: 2153b2e8917b73e9 ("sparc: Add architecture support for clone3") 99d2592023e5d0a3 ("rseq: Implement sys_rseq_slice_yield()") 4ac286c4a8d904c8 ("s390/syscalls: Switch to generic system call table generation") This makes 'perf trace' support it, now its possible, for instance, to do: # perf trace -e rseq_slice_yield --max-stack=16 Here is an example with the 'sendmmsg' syscall: root@x1:~# perf trace -e sendmmsg --max-stack 16 --max-events=1 0.000 ( 0.062 ms): dbus-broker/1012 sendmmsg(fd: 150, mmsg: 0x7ffef57cca50, vlen: 1, flags: DONTWAIT|NOSIGNAL) = 1 syscall_exit_to_user_mode_prepare ([kernel.kallsyms]) syscall_exit_to_user_mode_prepare ([kernel.kallsyms]) syscall_exit_to_user_mode ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64 ([kernel.kallsyms]) [0x117ce7] (/usr/lib64/libc.so.6 (deleted)) root@x1:~# To do a system wide tracing of the new 'rseq_slice_yield' syscall with a backtrace of at most 16 entries. This addresses these perf tools build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h diff -u tools/scripts/syscall.tbl scripts/syscall.tbl diff -u tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl diff -u tools/perf/arch/arm/entry/syscalls/syscall.tbl arch/arm/tools/syscall.tbl diff -u tools/perf/arch/sh/entry/syscalls/syscall.tbl arch/sh/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/sparc/entry/syscalls/syscall.tbl arch/sparc/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/xtensa/entry/syscalls/syscall.tbl arch/xtensa/kernel/syscalls/syscall.tbl Cc: Andreas Larsson Cc: Heiko Carstens Cc: Ludwig Rydberg Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm-generic/unistd.h | 5 +- .../perf/arch/arm/entry/syscalls/syscall.tbl | 1 + .../arch/mips/entry/syscalls/syscall_n64.tbl | 1 + .../arch/powerpc/entry/syscalls/syscall.tbl | 1 + .../perf/arch/s390/entry/syscalls/syscall.tbl | 859 ++++++++---------- tools/perf/arch/sh/entry/syscalls/syscall.tbl | 1 + .../arch/sparc/entry/syscalls/syscall.tbl | 3 +- .../arch/x86/entry/syscalls/syscall_32.tbl | 1 + .../arch/x86/entry/syscalls/syscall_64.tbl | 1 + .../arch/xtensa/entry/syscalls/syscall.tbl | 1 + tools/scripts/syscall.tbl | 1 + 11 files changed, 406 insertions(+), 469 deletions(-) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 942370b3f5d2..a627acc8fb5f 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -860,8 +860,11 @@ __SYSCALL(__NR_file_setattr, sys_file_setattr) #define __NR_listns 470 __SYSCALL(__NR_listns, sys_listns) +#define __NR_rseq_slice_yield 471 +__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield) + #undef __NR_syscalls -#define __NR_syscalls 471 +#define __NR_syscalls 472 /* * 32 bit systems traditionally used different diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl index fd09afae72a2..94351e22bfcf 100644 --- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl @@ -485,3 +485,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 9b92bddf06b5..630aab9e5425 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -385,3 +385,4 @@ 468 n64 file_getattr sys_file_getattr 469 n64 file_setattr sys_file_setattr 470 n64 listns sys_listns +471 n64 rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index ec4458cdb97b..4fcc7c58a105 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -561,3 +561,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 nospu rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 5863787ab036..09a7ef04d979 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -3,473 +3,398 @@ # System call table for s390 # # Format: +# # -# -# -# where can be common, 64, or 32 +# is always common. -1 common exit sys_exit sys_exit -2 common fork sys_fork sys_fork -3 common read sys_read compat_sys_s390_read -4 common write sys_write compat_sys_s390_write -5 common open sys_open compat_sys_open -6 common close sys_close sys_close -7 common restart_syscall sys_restart_syscall sys_restart_syscall -8 common creat sys_creat sys_creat -9 common link sys_link sys_link -10 common unlink sys_unlink sys_unlink -11 common execve sys_execve compat_sys_execve -12 common chdir sys_chdir sys_chdir -13 32 time - sys_time32 -14 common mknod sys_mknod sys_mknod -15 common chmod sys_chmod sys_chmod -16 32 lchown - sys_lchown16 -19 common lseek sys_lseek compat_sys_lseek -20 common getpid sys_getpid sys_getpid -21 common mount sys_mount sys_mount -22 common umount sys_oldumount sys_oldumount -23 32 setuid - sys_setuid16 -24 32 getuid - sys_getuid16 -25 32 stime - sys_stime32 -26 common ptrace sys_ptrace compat_sys_ptrace -27 common alarm sys_alarm sys_alarm -29 common pause sys_pause sys_pause -30 common utime sys_utime sys_utime32 -33 common access sys_access sys_access -34 common nice sys_nice sys_nice -36 common sync sys_sync sys_sync -37 common kill sys_kill sys_kill -38 common rename sys_rename sys_rename -39 common mkdir sys_mkdir sys_mkdir -40 common rmdir sys_rmdir sys_rmdir -41 common dup sys_dup sys_dup -42 common pipe sys_pipe sys_pipe -43 common times sys_times compat_sys_times -45 common brk sys_brk sys_brk -46 32 setgid - sys_setgid16 -47 32 getgid - sys_getgid16 -48 common signal sys_signal sys_signal -49 32 geteuid - sys_geteuid16 -50 32 getegid - sys_getegid16 -51 common acct sys_acct sys_acct -52 common umount2 sys_umount sys_umount -54 common ioctl sys_ioctl compat_sys_ioctl -55 common fcntl sys_fcntl compat_sys_fcntl -57 common setpgid sys_setpgid sys_setpgid -60 common umask sys_umask sys_umask -61 common chroot sys_chroot sys_chroot -62 common ustat sys_ustat compat_sys_ustat -63 common dup2 sys_dup2 sys_dup2 -64 common getppid sys_getppid sys_getppid -65 common getpgrp sys_getpgrp sys_getpgrp -66 common setsid sys_setsid sys_setsid -67 common sigaction sys_sigaction compat_sys_sigaction -70 32 setreuid - sys_setreuid16 -71 32 setregid - sys_setregid16 -72 common sigsuspend sys_sigsuspend sys_sigsuspend -73 common sigpending sys_sigpending compat_sys_sigpending -74 common sethostname sys_sethostname sys_sethostname -75 common setrlimit sys_setrlimit compat_sys_setrlimit -76 32 getrlimit - compat_sys_old_getrlimit -77 common getrusage sys_getrusage compat_sys_getrusage -78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday -79 common settimeofday sys_settimeofday compat_sys_settimeofday -80 32 getgroups - sys_getgroups16 -81 32 setgroups - sys_setgroups16 -83 common symlink sys_symlink sys_symlink -85 common readlink sys_readlink sys_readlink -86 common uselib sys_uselib sys_uselib -87 common swapon sys_swapon sys_swapon -88 common reboot sys_reboot sys_reboot -89 common readdir - compat_sys_old_readdir -90 common mmap sys_old_mmap compat_sys_s390_old_mmap -91 common munmap sys_munmap sys_munmap -92 common truncate sys_truncate compat_sys_truncate -93 common ftruncate sys_ftruncate compat_sys_ftruncate -94 common fchmod sys_fchmod sys_fchmod -95 32 fchown - sys_fchown16 -96 common getpriority sys_getpriority sys_getpriority -97 common setpriority sys_setpriority sys_setpriority -99 common statfs sys_statfs compat_sys_statfs -100 common fstatfs sys_fstatfs compat_sys_fstatfs -101 32 ioperm - - -102 common socketcall sys_socketcall compat_sys_socketcall -103 common syslog sys_syslog sys_syslog -104 common setitimer sys_setitimer compat_sys_setitimer -105 common getitimer sys_getitimer compat_sys_getitimer -106 common stat sys_newstat compat_sys_newstat -107 common lstat sys_newlstat compat_sys_newlstat -108 common fstat sys_newfstat compat_sys_newfstat -110 common lookup_dcookie - - -111 common vhangup sys_vhangup sys_vhangup -112 common idle - - -114 common wait4 sys_wait4 compat_sys_wait4 -115 common swapoff sys_swapoff sys_swapoff -116 common sysinfo sys_sysinfo compat_sys_sysinfo -117 common ipc sys_s390_ipc compat_sys_s390_ipc -118 common fsync sys_fsync sys_fsync -119 common sigreturn sys_sigreturn compat_sys_sigreturn -120 common clone sys_clone sys_clone -121 common setdomainname sys_setdomainname sys_setdomainname -122 common uname sys_newuname sys_newuname -124 common adjtimex sys_adjtimex sys_adjtimex_time32 -125 common mprotect sys_mprotect sys_mprotect -126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask -127 common create_module - - -128 common init_module sys_init_module sys_init_module -129 common delete_module sys_delete_module sys_delete_module -130 common get_kernel_syms - - -131 common quotactl sys_quotactl sys_quotactl -132 common getpgid sys_getpgid sys_getpgid -133 common fchdir sys_fchdir sys_fchdir -134 common bdflush sys_ni_syscall sys_ni_syscall -135 common sysfs sys_sysfs sys_sysfs -136 common personality sys_s390_personality sys_s390_personality -137 common afs_syscall - - -138 32 setfsuid - sys_setfsuid16 -139 32 setfsgid - sys_setfsgid16 -140 32 _llseek - sys_llseek -141 common getdents sys_getdents compat_sys_getdents -142 32 _newselect - compat_sys_select -142 64 select sys_select - -143 common flock sys_flock sys_flock -144 common msync sys_msync sys_msync -145 common readv sys_readv sys_readv -146 common writev sys_writev sys_writev -147 common getsid sys_getsid sys_getsid -148 common fdatasync sys_fdatasync sys_fdatasync -149 common _sysctl - - -150 common mlock sys_mlock sys_mlock -151 common munlock sys_munlock sys_munlock -152 common mlockall sys_mlockall sys_mlockall -153 common munlockall sys_munlockall sys_munlockall -154 common sched_setparam sys_sched_setparam sys_sched_setparam -155 common sched_getparam sys_sched_getparam sys_sched_getparam -156 common sched_setscheduler sys_sched_setscheduler sys_sched_setscheduler -157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler -158 common sched_yield sys_sched_yield sys_sched_yield -159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max -160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 -162 common nanosleep sys_nanosleep sys_nanosleep_time32 -163 common mremap sys_mremap sys_mremap -164 32 setresuid - sys_setresuid16 -165 32 getresuid - sys_getresuid16 -167 common query_module - - -168 common poll sys_poll sys_poll -169 common nfsservctl - - -170 32 setresgid - sys_setresgid16 -171 32 getresgid - sys_getresgid16 -172 common prctl sys_prctl sys_prctl -173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn -174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction -175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask -176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 -178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo -179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -180 common pread64 sys_pread64 compat_sys_s390_pread64 -181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 -182 32 chown - sys_chown16 -183 common getcwd sys_getcwd sys_getcwd -184 common capget sys_capget sys_capget -185 common capset sys_capset sys_capset -186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack -187 common sendfile sys_sendfile64 compat_sys_sendfile -188 common getpmsg - - -189 common putpmsg - - -190 common vfork sys_vfork sys_vfork -191 32 ugetrlimit - compat_sys_getrlimit -191 64 getrlimit sys_getrlimit - -192 32 mmap2 - compat_sys_s390_mmap2 -193 32 truncate64 - compat_sys_s390_truncate64 -194 32 ftruncate64 - compat_sys_s390_ftruncate64 -195 32 stat64 - compat_sys_s390_stat64 -196 32 lstat64 - compat_sys_s390_lstat64 -197 32 fstat64 - compat_sys_s390_fstat64 -198 32 lchown32 - sys_lchown -198 64 lchown sys_lchown - -199 32 getuid32 - sys_getuid -199 64 getuid sys_getuid - -200 32 getgid32 - sys_getgid -200 64 getgid sys_getgid - -201 32 geteuid32 - sys_geteuid -201 64 geteuid sys_geteuid - -202 32 getegid32 - sys_getegid -202 64 getegid sys_getegid - -203 32 setreuid32 - sys_setreuid -203 64 setreuid sys_setreuid - -204 32 setregid32 - sys_setregid -204 64 setregid sys_setregid - -205 32 getgroups32 - sys_getgroups -205 64 getgroups sys_getgroups - -206 32 setgroups32 - sys_setgroups -206 64 setgroups sys_setgroups - -207 32 fchown32 - sys_fchown -207 64 fchown sys_fchown - -208 32 setresuid32 - sys_setresuid -208 64 setresuid sys_setresuid - -209 32 getresuid32 - sys_getresuid -209 64 getresuid sys_getresuid - -210 32 setresgid32 - sys_setresgid -210 64 setresgid sys_setresgid - -211 32 getresgid32 - sys_getresgid -211 64 getresgid sys_getresgid - -212 32 chown32 - sys_chown -212 64 chown sys_chown - -213 32 setuid32 - sys_setuid -213 64 setuid sys_setuid - -214 32 setgid32 - sys_setgid -214 64 setgid sys_setgid - -215 32 setfsuid32 - sys_setfsuid -215 64 setfsuid sys_setfsuid - -216 32 setfsgid32 - sys_setfsgid -216 64 setfsgid sys_setfsgid - -217 common pivot_root sys_pivot_root sys_pivot_root -218 common mincore sys_mincore sys_mincore -219 common madvise sys_madvise sys_madvise -220 common getdents64 sys_getdents64 sys_getdents64 -221 32 fcntl64 - compat_sys_fcntl64 -222 common readahead sys_readahead compat_sys_s390_readahead -223 32 sendfile64 - compat_sys_sendfile64 -224 common setxattr sys_setxattr sys_setxattr -225 common lsetxattr sys_lsetxattr sys_lsetxattr -226 common fsetxattr sys_fsetxattr sys_fsetxattr -227 common getxattr sys_getxattr sys_getxattr -228 common lgetxattr sys_lgetxattr sys_lgetxattr -229 common fgetxattr sys_fgetxattr sys_fgetxattr -230 common listxattr sys_listxattr sys_listxattr -231 common llistxattr sys_llistxattr sys_llistxattr -232 common flistxattr sys_flistxattr sys_flistxattr -233 common removexattr sys_removexattr sys_removexattr -234 common lremovexattr sys_lremovexattr sys_lremovexattr -235 common fremovexattr sys_fremovexattr sys_fremovexattr -236 common gettid sys_gettid sys_gettid -237 common tkill sys_tkill sys_tkill -238 common futex sys_futex sys_futex_time32 -239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity -240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity -241 common tgkill sys_tgkill sys_tgkill -243 common io_setup sys_io_setup compat_sys_io_setup -244 common io_destroy sys_io_destroy sys_io_destroy -245 common io_getevents sys_io_getevents sys_io_getevents_time32 -246 common io_submit sys_io_submit compat_sys_io_submit -247 common io_cancel sys_io_cancel sys_io_cancel -248 common exit_group sys_exit_group sys_exit_group -249 common epoll_create sys_epoll_create sys_epoll_create -250 common epoll_ctl sys_epoll_ctl sys_epoll_ctl -251 common epoll_wait sys_epoll_wait sys_epoll_wait -252 common set_tid_address sys_set_tid_address sys_set_tid_address -253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 -254 common timer_create sys_timer_create compat_sys_timer_create -255 common timer_settime sys_timer_settime sys_timer_settime32 -256 common timer_gettime sys_timer_gettime sys_timer_gettime32 -257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun -258 common timer_delete sys_timer_delete sys_timer_delete -259 common clock_settime sys_clock_settime sys_clock_settime32 -260 common clock_gettime sys_clock_gettime sys_clock_gettime32 -261 common clock_getres sys_clock_getres sys_clock_getres_time32 -262 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 -264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 -265 common statfs64 sys_statfs64 compat_sys_statfs64 -266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages -268 common mbind sys_mbind sys_mbind -269 common get_mempolicy sys_get_mempolicy sys_get_mempolicy -270 common set_mempolicy sys_set_mempolicy sys_set_mempolicy -271 common mq_open sys_mq_open compat_sys_mq_open -272 common mq_unlink sys_mq_unlink sys_mq_unlink -273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 -274 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 -275 common mq_notify sys_mq_notify compat_sys_mq_notify -276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr -277 common kexec_load sys_kexec_load compat_sys_kexec_load -278 common add_key sys_add_key sys_add_key -279 common request_key sys_request_key sys_request_key -280 common keyctl sys_keyctl compat_sys_keyctl -281 common waitid sys_waitid compat_sys_waitid -282 common ioprio_set sys_ioprio_set sys_ioprio_set -283 common ioprio_get sys_ioprio_get sys_ioprio_get -284 common inotify_init sys_inotify_init sys_inotify_init -285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch -286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch -287 common migrate_pages sys_migrate_pages sys_migrate_pages -288 common openat sys_openat compat_sys_openat -289 common mkdirat sys_mkdirat sys_mkdirat -290 common mknodat sys_mknodat sys_mknodat -291 common fchownat sys_fchownat sys_fchownat -292 common futimesat sys_futimesat sys_futimesat_time32 -293 32 fstatat64 - compat_sys_s390_fstatat64 -293 64 newfstatat sys_newfstatat - -294 common unlinkat sys_unlinkat sys_unlinkat -295 common renameat sys_renameat sys_renameat -296 common linkat sys_linkat sys_linkat -297 common symlinkat sys_symlinkat sys_symlinkat -298 common readlinkat sys_readlinkat sys_readlinkat -299 common fchmodat sys_fchmodat sys_fchmodat -300 common faccessat sys_faccessat sys_faccessat -301 common pselect6 sys_pselect6 compat_sys_pselect6_time32 -302 common ppoll sys_ppoll compat_sys_ppoll_time32 -303 common unshare sys_unshare sys_unshare -304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list -305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list -306 common splice sys_splice sys_splice -307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range -308 common tee sys_tee sys_tee -309 common vmsplice sys_vmsplice sys_vmsplice -310 common move_pages sys_move_pages sys_move_pages -311 common getcpu sys_getcpu sys_getcpu -312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -313 common utimes sys_utimes sys_utimes_time32 -314 common fallocate sys_fallocate compat_sys_s390_fallocate -315 common utimensat sys_utimensat sys_utimensat_time32 -316 common signalfd sys_signalfd compat_sys_signalfd -317 common timerfd - - -318 common eventfd sys_eventfd sys_eventfd -319 common timerfd_create sys_timerfd_create sys_timerfd_create -320 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 -321 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 -322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 -323 common eventfd2 sys_eventfd2 sys_eventfd2 -324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 -325 common pipe2 sys_pipe2 sys_pipe2 -326 common dup3 sys_dup3 sys_dup3 -327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 -328 common preadv sys_preadv compat_sys_preadv -329 common pwritev sys_pwritev compat_sys_pwritev -330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo -331 common perf_event_open sys_perf_event_open sys_perf_event_open -332 common fanotify_init sys_fanotify_init sys_fanotify_init -333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark -334 common prlimit64 sys_prlimit64 sys_prlimit64 -335 common name_to_handle_at sys_name_to_handle_at sys_name_to_handle_at -336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -337 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 -338 common syncfs sys_syncfs sys_syncfs -339 common setns sys_setns sys_setns -340 common process_vm_readv sys_process_vm_readv sys_process_vm_readv -341 common process_vm_writev sys_process_vm_writev sys_process_vm_writev -342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr -343 common kcmp sys_kcmp sys_kcmp -344 common finit_module sys_finit_module sys_finit_module -345 common sched_setattr sys_sched_setattr sys_sched_setattr -346 common sched_getattr sys_sched_getattr sys_sched_getattr -347 common renameat2 sys_renameat2 sys_renameat2 -348 common seccomp sys_seccomp sys_seccomp -349 common getrandom sys_getrandom sys_getrandom -350 common memfd_create sys_memfd_create sys_memfd_create -351 common bpf sys_bpf sys_bpf -352 common s390_pci_mmio_write sys_s390_pci_mmio_write sys_s390_pci_mmio_write -353 common s390_pci_mmio_read sys_s390_pci_mmio_read sys_s390_pci_mmio_read -354 common execveat sys_execveat compat_sys_execveat -355 common userfaultfd sys_userfaultfd sys_userfaultfd -356 common membarrier sys_membarrier sys_membarrier -357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 -358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg -359 common socket sys_socket sys_socket -360 common socketpair sys_socketpair sys_socketpair -361 common bind sys_bind sys_bind -362 common connect sys_connect sys_connect -363 common listen sys_listen sys_listen -364 common accept4 sys_accept4 sys_accept4 -365 common getsockopt sys_getsockopt sys_getsockopt -366 common setsockopt sys_setsockopt sys_setsockopt -367 common getsockname sys_getsockname sys_getsockname -368 common getpeername sys_getpeername sys_getpeername -369 common sendto sys_sendto sys_sendto -370 common sendmsg sys_sendmsg compat_sys_sendmsg -371 common recvfrom sys_recvfrom compat_sys_recvfrom -372 common recvmsg sys_recvmsg compat_sys_recvmsg -373 common shutdown sys_shutdown sys_shutdown -374 common mlock2 sys_mlock2 sys_mlock2 -375 common copy_file_range sys_copy_file_range sys_copy_file_range -376 common preadv2 sys_preadv2 compat_sys_preadv2 -377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 -378 common s390_guarded_storage sys_s390_guarded_storage sys_s390_guarded_storage -379 common statx sys_statx sys_statx -380 common s390_sthyi sys_s390_sthyi sys_s390_sthyi -381 common kexec_file_load sys_kexec_file_load sys_kexec_file_load -382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents -383 common rseq sys_rseq sys_rseq -384 common pkey_mprotect sys_pkey_mprotect sys_pkey_mprotect -385 common pkey_alloc sys_pkey_alloc sys_pkey_alloc -386 common pkey_free sys_pkey_free sys_pkey_free +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open +6 common close sys_close +7 common restart_syscall sys_restart_syscall +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve +12 common chdir sys_chdir +14 common mknod sys_mknod +15 common chmod sys_chmod +19 common lseek sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 common umount sys_oldumount +26 common ptrace sys_ptrace +27 common alarm sys_alarm +29 common pause sys_pause +30 common utime sys_utime +33 common access sys_access +34 common nice sys_nice +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times +45 common brk sys_brk +48 common signal sys_signal +51 common acct sys_acct +52 common umount2 sys_umount +54 common ioctl sys_ioctl +55 common fcntl sys_fcntl +57 common setpgid sys_setpgid +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit +77 common getrusage sys_getrusage +78 common gettimeofday sys_gettimeofday +79 common settimeofday sys_settimeofday +83 common symlink sys_symlink +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +89 common readdir sys_ni_syscall +90 common mmap sys_old_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate +93 common ftruncate sys_ftruncate +94 common fchmod sys_fchmod +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +99 common statfs sys_statfs +100 common fstatfs sys_fstatfs +102 common socketcall sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer +105 common getitimer sys_getitimer +106 common stat sys_newstat +107 common lstat sys_newlstat +108 common fstat sys_newfstat +110 common lookup_dcookie sys_ni_syscall +111 common vhangup sys_vhangup +112 common idle sys_ni_syscall +114 common wait4 sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo +117 common ipc sys_s390_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +124 common adjtimex sys_adjtimex +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask +127 common create_module sys_ni_syscall +128 common init_module sys_init_module +129 common delete_module sys_delete_module +130 common get_kernel_syms sys_ni_syscall +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_s390_personality +137 common afs_syscall sys_ni_syscall +141 common getdents sys_getdents +142 common select sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval +162 common nanosleep sys_nanosleep +163 common mremap sys_mremap +167 common query_module sys_ni_syscall +168 common poll sys_poll +169 common nfsservctl sys_ni_syscall +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend +180 common pread64 sys_pread64 +181 common pwrite64 sys_pwrite64 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack +187 common sendfile sys_sendfile64 +188 common getpmsg sys_ni_syscall +189 common putpmsg sys_ni_syscall +190 common vfork sys_vfork +191 common getrlimit sys_getrlimit +198 common lchown sys_lchown +199 common getuid sys_getuid +200 common getgid sys_getgid +201 common geteuid sys_geteuid +202 common getegid sys_getegid +203 common setreuid sys_setreuid +204 common setregid sys_setregid +205 common getgroups sys_getgroups +206 common setgroups sys_setgroups +207 common fchown sys_fchown +208 common setresuid sys_setresuid +209 common getresuid sys_getresuid +210 common setresgid sys_setresgid +211 common getresgid sys_getresgid +212 common chown sys_chown +213 common setuid sys_setuid +214 common setgid sys_setgid +215 common setfsuid sys_setfsuid +216 common setfsgid sys_setfsgid +217 common pivot_root sys_pivot_root +218 common mincore sys_mincore +219 common madvise sys_madvise +220 common getdents64 sys_getdents64 +222 common readahead sys_readahead +224 common setxattr sys_setxattr +225 common lsetxattr sys_lsetxattr +226 common fsetxattr sys_fsetxattr +227 common getxattr sys_getxattr +228 common lgetxattr sys_lgetxattr +229 common fgetxattr sys_fgetxattr +230 common listxattr sys_listxattr +231 common llistxattr sys_llistxattr +232 common flistxattr sys_flistxattr +233 common removexattr sys_removexattr +234 common lremovexattr sys_lremovexattr +235 common fremovexattr sys_fremovexattr +236 common gettid sys_gettid +237 common tkill sys_tkill +238 common futex sys_futex +239 common sched_setaffinity sys_sched_setaffinity +240 common sched_getaffinity sys_sched_getaffinity +241 common tgkill sys_tgkill +243 common io_setup sys_io_setup +244 common io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents +246 common io_submit sys_io_submit +247 common io_cancel sys_io_cancel +248 common exit_group sys_exit_group +249 common epoll_create sys_epoll_create +250 common epoll_ctl sys_epoll_ctl +251 common epoll_wait sys_epoll_wait +252 common set_tid_address sys_set_tid_address +253 common fadvise64 sys_fadvise64_64 +254 common timer_create sys_timer_create +255 common timer_settime sys_timer_settime +256 common timer_gettime sys_timer_gettime +257 common timer_getoverrun sys_timer_getoverrun +258 common timer_delete sys_timer_delete +259 common clock_settime sys_clock_settime +260 common clock_gettime sys_clock_gettime +261 common clock_getres sys_clock_getres +262 common clock_nanosleep sys_clock_nanosleep +265 common statfs64 sys_statfs64 +266 common fstatfs64 sys_fstatfs64 +267 common remap_file_pages sys_remap_file_pages +268 common mbind sys_mbind +269 common get_mempolicy sys_get_mempolicy +270 common set_mempolicy sys_set_mempolicy +271 common mq_open sys_mq_open +272 common mq_unlink sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend +274 common mq_timedreceive sys_mq_timedreceive +275 common mq_notify sys_mq_notify +276 common mq_getsetattr sys_mq_getsetattr +277 common kexec_load sys_kexec_load +278 common add_key sys_add_key +279 common request_key sys_request_key +280 common keyctl sys_keyctl +281 common waitid sys_waitid +282 common ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get +284 common inotify_init sys_inotify_init +285 common inotify_add_watch sys_inotify_add_watch +286 common inotify_rm_watch sys_inotify_rm_watch +287 common migrate_pages sys_migrate_pages +288 common openat sys_openat +289 common mkdirat sys_mkdirat +290 common mknodat sys_mknodat +291 common fchownat sys_fchownat +292 common futimesat sys_futimesat +293 common newfstatat sys_newfstatat +294 common unlinkat sys_unlinkat +295 common renameat sys_renameat +296 common linkat sys_linkat +297 common symlinkat sys_symlinkat +298 common readlinkat sys_readlinkat +299 common fchmodat sys_fchmodat +300 common faccessat sys_faccessat +301 common pselect6 sys_pselect6 +302 common ppoll sys_ppoll +303 common unshare sys_unshare +304 common set_robust_list sys_set_robust_list +305 common get_robust_list sys_get_robust_list +306 common splice sys_splice +307 common sync_file_range sys_sync_file_range +308 common tee sys_tee +309 common vmsplice sys_vmsplice +310 common move_pages sys_move_pages +311 common getcpu sys_getcpu +312 common epoll_pwait sys_epoll_pwait +313 common utimes sys_utimes +314 common fallocate sys_fallocate +315 common utimensat sys_utimensat +316 common signalfd sys_signalfd +317 common timerfd sys_ni_syscall +318 common eventfd sys_eventfd +319 common timerfd_create sys_timerfd_create +320 common timerfd_settime sys_timerfd_settime +321 common timerfd_gettime sys_timerfd_gettime +322 common signalfd4 sys_signalfd4 +323 common eventfd2 sys_eventfd2 +324 common inotify_init1 sys_inotify_init1 +325 common pipe2 sys_pipe2 +326 common dup3 sys_dup3 +327 common epoll_create1 sys_epoll_create1 +328 common preadv sys_preadv +329 common pwritev sys_pwritev +330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +331 common perf_event_open sys_perf_event_open +332 common fanotify_init sys_fanotify_init +333 common fanotify_mark sys_fanotify_mark +334 common prlimit64 sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at +336 common open_by_handle_at sys_open_by_handle_at +337 common clock_adjtime sys_clock_adjtime +338 common syncfs sys_syncfs +339 common setns sys_setns +340 common process_vm_readv sys_process_vm_readv +341 common process_vm_writev sys_process_vm_writev +342 common s390_runtime_instr sys_s390_runtime_instr +343 common kcmp sys_kcmp +344 common finit_module sys_finit_module +345 common sched_setattr sys_sched_setattr +346 common sched_getattr sys_sched_getattr +347 common renameat2 sys_renameat2 +348 common seccomp sys_seccomp +349 common getrandom sys_getrandom +350 common memfd_create sys_memfd_create +351 common bpf sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read +354 common execveat sys_execveat +355 common userfaultfd sys_userfaultfd +356 common membarrier sys_membarrier +357 common recvmmsg sys_recvmmsg +358 common sendmmsg sys_sendmmsg +359 common socket sys_socket +360 common socketpair sys_socketpair +361 common bind sys_bind +362 common connect sys_connect +363 common listen sys_listen +364 common accept4 sys_accept4 +365 common getsockopt sys_getsockopt +366 common setsockopt sys_setsockopt +367 common getsockname sys_getsockname +368 common getpeername sys_getpeername +369 common sendto sys_sendto +370 common sendmsg sys_sendmsg +371 common recvfrom sys_recvfrom +372 common recvmsg sys_recvmsg +373 common shutdown sys_shutdown +374 common mlock2 sys_mlock2 +375 common copy_file_range sys_copy_file_range +376 common preadv2 sys_preadv2 +377 common pwritev2 sys_pwritev2 +378 common s390_guarded_storage sys_s390_guarded_storage +379 common statx sys_statx +380 common s390_sthyi sys_s390_sthyi +381 common kexec_file_load sys_kexec_file_load +382 common io_pgetevents sys_io_pgetevents +383 common rseq sys_rseq +384 common pkey_mprotect sys_pkey_mprotect +385 common pkey_alloc sys_pkey_alloc +386 common pkey_free sys_pkey_free # room for arch specific syscalls -392 64 semtimedop sys_semtimedop - -393 common semget sys_semget sys_semget -394 common semctl sys_semctl compat_sys_semctl -395 common shmget sys_shmget sys_shmget -396 common shmctl sys_shmctl compat_sys_shmctl -397 common shmat sys_shmat compat_sys_shmat -398 common shmdt sys_shmdt sys_shmdt -399 common msgget sys_msgget sys_msgget -400 common msgsnd sys_msgsnd compat_sys_msgsnd -401 common msgrcv sys_msgrcv compat_sys_msgrcv -402 common msgctl sys_msgctl compat_sys_msgctl -403 32 clock_gettime64 - sys_clock_gettime -404 32 clock_settime64 - sys_clock_settime -405 32 clock_adjtime64 - sys_clock_adjtime -406 32 clock_getres_time64 - sys_clock_getres -407 32 clock_nanosleep_time64 - sys_clock_nanosleep -408 32 timer_gettime64 - sys_timer_gettime -409 32 timer_settime64 - sys_timer_settime -410 32 timerfd_gettime64 - sys_timerfd_gettime -411 32 timerfd_settime64 - sys_timerfd_settime -412 32 utimensat_time64 - sys_utimensat -413 32 pselect6_time64 - compat_sys_pselect6_time64 -414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 -417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 -418 32 mq_timedsend_time64 - sys_mq_timedsend -419 32 mq_timedreceive_time64 - sys_mq_timedreceive -420 32 semtimedop_time64 - sys_semtimedop -421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 -422 32 futex_time64 - sys_futex -423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval -424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal -425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup -426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter -427 common io_uring_register sys_io_uring_register sys_io_uring_register -428 common open_tree sys_open_tree sys_open_tree -429 common move_mount sys_move_mount sys_move_mount -430 common fsopen sys_fsopen sys_fsopen -431 common fsconfig sys_fsconfig sys_fsconfig -432 common fsmount sys_fsmount sys_fsmount -433 common fspick sys_fspick sys_fspick -434 common pidfd_open sys_pidfd_open sys_pidfd_open -435 common clone3 sys_clone3 sys_clone3 -436 common close_range sys_close_range sys_close_range -437 common openat2 sys_openat2 sys_openat2 -438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd -439 common faccessat2 sys_faccessat2 sys_faccessat2 -440 common process_madvise sys_process_madvise sys_process_madvise -441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 -442 common mount_setattr sys_mount_setattr sys_mount_setattr -443 common quotactl_fd sys_quotactl_fd sys_quotactl_fd -444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset -445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule -446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -447 common memfd_secret sys_memfd_secret sys_memfd_secret -448 common process_mrelease sys_process_mrelease sys_process_mrelease -449 common futex_waitv sys_futex_waitv sys_futex_waitv -450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node -451 common cachestat sys_cachestat sys_cachestat -452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 -453 common map_shadow_stack sys_map_shadow_stack sys_map_shadow_stack -454 common futex_wake sys_futex_wake sys_futex_wake -455 common futex_wait sys_futex_wait sys_futex_wait -456 common futex_requeue sys_futex_requeue sys_futex_requeue -457 common statmount sys_statmount sys_statmount -458 common listmount sys_listmount sys_listmount -459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr -460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr -461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules -462 common mseal sys_mseal sys_mseal -463 common setxattrat sys_setxattrat sys_setxattrat -464 common getxattrat sys_getxattrat sys_getxattrat -465 common listxattrat sys_listxattrat sys_listxattrat -466 common removexattrat sys_removexattrat sys_removexattrat -467 common open_tree_attr sys_open_tree_attr sys_open_tree_attr -468 common file_getattr sys_file_getattr sys_file_getattr -469 common file_setattr sys_file_setattr sys_file_setattr -470 common listns sys_listns sys_listns +392 common semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl +397 common shmat sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd +401 common msgrcv sys_msgrcv +402 common msgctl sys_msgctl +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +447 common memfd_secret sys_memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl index 969c11325ade..70b315cbe710 100644 --- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl @@ -474,3 +474,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl index 39aa26b6a50b..7e71bf7fcd14 100644 --- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl @@ -480,7 +480,7 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 common clone3 __sys_clone3 436 common close_range sys_close_range 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd @@ -516,3 +516,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl index e979a3eac7a3..f832ebd2d79b 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl @@ -476,3 +476,4 @@ 468 i386 file_getattr sys_file_getattr 469 i386 file_setattr sys_file_setattr 470 i386 listns sys_listns +471 i386 rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 8a4ac4841be6..524155d655da 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -395,6 +395,7 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl index 438a3b170402..a9bca4e484de 100644 --- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl @@ -441,3 +441,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl index e74868be513c..7a42b32b6577 100644 --- a/tools/scripts/syscall.tbl +++ b/tools/scripts/syscall.tbl @@ -411,3 +411,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield From 0693907ffaca001036009bc82dc334fb8e11540f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 5 Mar 2026 17:28:44 -0300 Subject: [PATCH 127/487] tools headers UAPI: Update tools' copy of linux/coresight-pmu.h To get the comment changes in this commit: 171efc70097a9f5f ("x86/ibs: Fix typo in dc_l2tlb_miss comment") This silences this perf build warning: Warning: Kernel ABI header differences: diff -u tools/arch/x86/include/asm/amd/ibs.h arch/x86/include/asm/amd/ibs.h Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/amd/ibs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/arch/x86/include/asm/amd/ibs.h b/tools/arch/x86/include/asm/amd/ibs.h index cbce54fec7b9..41e8abd72c8b 100644 --- a/tools/arch/x86/include/asm/amd/ibs.h +++ b/tools/arch/x86/include/asm/amd/ibs.h @@ -110,7 +110,7 @@ union ibs_op_data3 { __u64 ld_op:1, /* 0: load op */ st_op:1, /* 1: store op */ dc_l1tlb_miss:1, /* 2: data cache L1TLB miss */ - dc_l2tlb_miss:1, /* 3: data cache L2TLB hit in 2M page */ + dc_l2tlb_miss:1, /* 3: data cache L2TLB miss in 2M page */ dc_l1tlb_hit_2m:1, /* 4: data cache L1TLB hit in 2M page */ dc_l1tlb_hit_1g:1, /* 5: data cache L1TLB hit in 1G page */ dc_l2tlb_hit_2m:1, /* 6: data cache L2TLB hit in 2M page */ From 7e459c41264fdd87b096ede8da796a302d569722 Mon Sep 17 00:00:00 2001 From: Akhil P Oommen Date: Thu, 5 Mar 2026 23:51:16 +0530 Subject: [PATCH 128/487] drm/msm/a8xx: Fix ubwc config related to swizzling To disable l2/l3 swizzling in A8x, set the respective bits in both GRAS_NC_MODE_CNTL and RB_CCU_NC_MODE_CNTL registers. This is required for Glymur where it is recommended to keep l2/l3 swizzling disabled. Fixes: 288a93200892 ("drm/msm/adreno: Introduce A8x GPU Support") Signed-off-by: Akhil P Oommen Message-ID: <20260305-a8xx-ubwc-fix-v1-1-d99b6da4c5a9@oss.qualcomm.com> Reviewed-by: Dmitry Baryshkov Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/adreno/a8xx_gpu.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c index 5a320f5bde41..b1887e0cf698 100644 --- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c @@ -310,11 +310,21 @@ static void a8xx_set_ubwc_config(struct msm_gpu *gpu) hbb = cfg->highest_bank_bit - 13; hbb_hi = hbb >> 2; hbb_lo = hbb & 3; - a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); - a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); + + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, + hbb << 5 | + level3_swizzling_dis << 4 | + level2_swizzling_dis << 3); + + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, + hbb << 5 | + level3_swizzling_dis << 4 | + level2_swizzling_dis << 3); a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CCU_NC_MODE_CNTL, yuvnotcomptofc << 6 | + level3_swizzling_dis << 5 | + level2_swizzling_dis << 4 | hbb_hi << 3 | hbb_lo << 1); From 4ce71cea574658f5c5c7412b1a3cc54efe4f9b50 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Thu, 5 Mar 2026 18:17:07 +0800 Subject: [PATCH 129/487] drm/msm/dpu: Correct the SA8775P intr_underrun/intr_underrun index The intr_underrun and intr_vsync indices have been swapped, just simply corrects them. Cc: stable@vger.kernel.org Fixes: b139c80d181c ("drm/msm/dpu: Add SA8775P support") Signed-off-by: Abhinav Kumar Signed-off-by: Yongxing Mou Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/709209/ Link: https://lore.kernel.org/r/20260305-mdss_catalog-v5-2-06678ac39ac7@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h index 0f7b4a224e4c..42cf3bd5a12a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h @@ -366,8 +366,8 @@ static const struct dpu_intf_cfg sa8775p_intf[] = { .type = INTF_NONE, .controller_id = MSM_DP_CONTROLLER_0, /* pair with intf_0 for DP MST */ .prog_fetch_lines_worst_case = 24, - .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), - .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), }, { .name = "intf_7", .id = INTF_7, .base = 0x3b000, .len = 0x280, From 7403e87c138475a74e5176176778f391d847f42d Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Tue, 3 Mar 2026 11:03:11 +0200 Subject: [PATCH 130/487] dt-bindings: display: msm: Fix reg ranges and clocks on Glymur The Glymur platform has four DisplayPort controllers. The hardware supports four streams (MST) per controller. However, on Glymur the first three controllers only have two streams wired to the display subsystem, while the fourth controller operates in single-stream mode. Add a dedicated clause for the Glymur compatible to require the register ranges for all four stream blocks, while allowing either one pixel clock (for the single-stream controller) or two pixel clocks (for the remaining controllers). Update the Glymur MDSS schema example by adding the missing p2, p3, mst2link and mst3link register blocks. Without these, the bindings validation fails. Also replace the made-up register addresses with the actual addresses from the first controller to match the SoC devicetree description. Cc: stable@vger.kernel.org # v6.19 Fixes: 8f63bf908213 ("dt-bindings: display: msm: Document the Glymur DiplayPort controller") Fixes: 1aee577bbc60 ("dt-bindings: display: msm: Document the Glymur Mobile Display SubSystem") Signed-off-by: Abel Vesa Reviewed-by: Krzysztof Kozlowski Patchwork: https://patchwork.freedesktop.org/patch/708518/ Link: https://lore.kernel.org/r/20260303-glymur-fix-dp-bindings-reg-clocks-v4-1-1ebd9c7c2cee@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov --- .../bindings/display/msm/dp-controller.yaml | 21 ++++++++++++++++++- .../display/msm/qcom,glymur-mdss.yaml | 16 ++++++++------ 2 files changed, 30 insertions(+), 7 deletions(-) diff --git a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml index ebda78db87a6..02ddfaab5f56 100644 --- a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml +++ b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml @@ -253,7 +253,6 @@ allOf: enum: # these platforms support 2 streams MST on some interfaces, # others are SST only - - qcom,glymur-dp - qcom,sc8280xp-dp - qcom,x1e80100-dp then: @@ -310,6 +309,26 @@ allOf: minItems: 6 maxItems: 8 + - if: + properties: + compatible: + contains: + enum: + # these platforms support 2 streams MST on some interfaces, + # others are SST only, but all controllers have 4 ports + - qcom,glymur-dp + then: + properties: + reg: + minItems: 9 + maxItems: 9 + clocks: + minItems: 5 + maxItems: 6 + clocks-names: + minItems: 5 + maxItems: 6 + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml index 2329ed96e6cb..64dde43373ac 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml @@ -176,13 +176,17 @@ examples: }; }; - displayport-controller@ae90000 { + displayport-controller@af54000 { compatible = "qcom,glymur-dp"; - reg = <0xae90000 0x200>, - <0xae90200 0x200>, - <0xae90400 0x600>, - <0xae91000 0x400>, - <0xae91400 0x400>; + reg = <0xaf54000 0x200>, + <0xaf54200 0x200>, + <0xaf55000 0xc00>, + <0xaf56000 0x400>, + <0xaf57000 0x400>, + <0xaf58000 0x400>, + <0xaf59000 0x400>, + <0xaf5a000 0x600>, + <0xaf5b000 0x600>; interrupt-parent = <&mdss>; interrupts = <12>; From fd941c787cbb402e8ebd84336f2a0026d5d0724d Mon Sep 17 00:00:00 2001 From: Pengyu Luo Date: Thu, 26 Feb 2026 20:29:57 +0800 Subject: [PATCH 131/487] drm/msm/dsi/phy: fix hardware revision The hardware revision for TSMC 3nm-based Qualcomm SOCs should be 7.2, this can be confirmed from REG_DSI_7nm_PHY_CMN_REVISION_ID0, the value is 0x27, which means hardware revision is 7.2 No functional change. Fixes: 1337d7ebfb6d ("drm/msm/dsi/phy: Add support for SM8750") Suggested-by: Dmitry Baryshkov Signed-off-by: Pengyu Luo Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/707414/ Link: https://lore.kernel.org/r/20260226122958.22555-2-mitltlatltl@gmail.com Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 8cb0db3a9880..01182442dfd6 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -51,8 +51,8 @@ #define DSI_PHY_7NM_QUIRK_V4_3 BIT(3) /* Hardware is V5.2 */ #define DSI_PHY_7NM_QUIRK_V5_2 BIT(4) -/* Hardware is V7.0 */ -#define DSI_PHY_7NM_QUIRK_V7_0 BIT(5) +/* Hardware is V7.2 */ +#define DSI_PHY_7NM_QUIRK_V7_2 BIT(5) struct dsi_pll_config { bool enable_ssc; @@ -143,7 +143,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_PRE_V4_1) { config->pll_clock_inverters = 0x28; - } else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + } else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { if (pll_freq < 163000000ULL) config->pll_clock_inverters = 0xa0; else if (pll_freq < 175000000ULL) @@ -284,7 +284,7 @@ static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll) } if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { if (pll->vco_current_rate < 1557000000ULL) vco_config_1 = 0x08; else @@ -699,7 +699,7 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy) case MSM_DSI_PHY_MASTER: pll_7nm->slave = pll_7nm_list[(pll_7nm->phy->id + 1) % DSI_MAX]; /* v7.0: Enable ATB_EN0 and alternate clock output to external phy */ - if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0) + if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2) writel(0x07, base + REG_DSI_7nm_PHY_CMN_CTRL_5); break; case MSM_DSI_PHY_SLAVE: @@ -987,7 +987,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, /* Request for REFGEN READY */ if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) || (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { writel(0x1, phy->base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10); udelay(500); } @@ -1021,7 +1021,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, lane_ctrl0 = 0x1f; } - if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { if (phy->cphy_mode) { /* TODO: different for second phy */ vreg_ctrl_0 = 0x57; @@ -1097,7 +1097,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, /* program CMN_CTRL_4 for minor_ver 2 chipsets*/ if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0) || + (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2) || (readl(base + REG_DSI_7nm_PHY_CMN_REVISION_ID0) & (0xf0)) == 0x20) writel(0x04, base + REG_DSI_7nm_PHY_CMN_CTRL_4); @@ -1213,7 +1213,7 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) /* Turn off REFGEN Vote */ if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) || (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { writel(0x0, base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10); wmb(); /* Delay to ensure HW removes vote before PHY shut down */ @@ -1502,7 +1502,7 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_8750_cfgs = { #endif .io_start = { 0xae95000, 0xae97000 }, .num_dsi_phy = 2, - .quirks = DSI_PHY_7NM_QUIRK_V7_0, + .quirks = DSI_PHY_7NM_QUIRK_V7_2, }; const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = { @@ -1525,5 +1525,5 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = { #endif .io_start = { 0x9ac1000, 0x9ac4000 }, .num_dsi_phy = 2, - .quirks = DSI_PHY_7NM_QUIRK_V7_0, + .quirks = DSI_PHY_7NM_QUIRK_V7_2, }; From 4355b13d46f696d687f42b982efed7570e03e532 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 25 Feb 2026 18:34:20 +0100 Subject: [PATCH 132/487] dt-bindings: display/msm: qcom,sm8750-mdss: Fix model typo Fix obvious model typo (SM8650->SM8750) in the description. Signed-off-by: Krzysztof Kozlowski Fixes: 6b93840116df ("dt-bindings: display/msm: qcom,sm8750-mdss: Add SM8750") Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/707192/ Link: https://lore.kernel.org/r/20260225173419.125565-2-krzysztof.kozlowski@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov --- .../devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml index d55fda9a523e..a38c2261ef1a 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml @@ -10,7 +10,7 @@ maintainers: - Krzysztof Kozlowski description: - SM8650 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like + SM8750 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like DPU display controller, DSI and DP interfaces etc. $ref: /schemas/display/msm/mdss-common.yaml# From e174dd14bf0beac811a5201e370ab26ce8c67f23 Mon Sep 17 00:00:00 2001 From: Gary Guo Date: Tue, 24 Feb 2026 15:29:56 +0800 Subject: [PATCH 133/487] rust: kbuild: emit dep-info into $(depfile) directly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit 295d8398c67e ("kbuild: specify output names separately for each emission type from rustc"), the preferred pattern is to ask rustc to emit dependency information into $(depfile) directly, and after commit 2185242faddd ("kbuild: remove sed commands after rustc rules"), the post-processing to remove comments is no longer necessary as fixdep can handle comments directly. Thus, emit dep-info into $(depfile) directly and remove the mv and sed invocation. This fixes the issue where a non-ignored .d file is emitted during compilation and removed shortly afterwards. [ Like Gary mentioned in Zulip, this likely happened due to rebasing the builds part of the old `syn` work I had. - Miguel ] Reported-by: Onur Özkan Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/288089-General/topic/syn.20artifact.20being.20tracked.20by.20git/with/575467879 Fixes: 7dbe46c0b11d ("rust: kbuild: add proc macro library support") Signed-off-by: Gary Guo Tested-by: Onur Özkan Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260224072957.214979-1-gary@garyguo.net [ Reworded for a couple of typos. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/Makefile | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/rust/Makefile b/rust/Makefile index 629b3bdd2b20..1500993d7ecc 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -526,11 +526,9 @@ quiet_cmd_rustc_procmacrolibrary = $(RUSTC_OR_CLIPPY_QUIET) PL $@ cmd_rustc_procmacrolibrary = \ $(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \ $(filter-out $(skip_flags),$(rust_common_flags) $(rustc_target_flags)) \ - --emit=dep-info,link --crate-type rlib -O \ + --emit=dep-info=$(depfile) --emit=link=$@ --crate-type rlib -O \ --out-dir $(objtree)/$(obj) -L$(objtree)/$(obj) \ - --crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $<; \ - mv $(objtree)/$(obj)/$(patsubst lib%.rlib,%,$(notdir $@)).d $(depfile); \ - sed -i '/^\#/d' $(depfile) + --crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $< $(obj)/libproc_macro2.rlib: private skip_clippy = 1 $(obj)/libproc_macro2.rlib: private rustc_target_flags = $(proc_macro2-flags) From dda135077ecc9f15c407f094dcfe7800376be867 Mon Sep 17 00:00:00 2001 From: Gary Guo Date: Thu, 26 Feb 2026 15:21:11 +0000 Subject: [PATCH 134/487] rust: build: remap path to avoid absolute path When building with an out directory (O=), absolute paths can end up in the file name in `#[track_caller]` or the panic message. This is not desirable as this leaks the exact path being used to build the kernel and means that the same location can appear in two forms (relative or absolute). This is reported by Asahi [1] and is being workaround in [2] previously to force everything to be absolute path. Using absolute path for everything solves the inconsistency, however it does not address the reproducibility issue. So, fix this by remap all absolute paths to srctree to relative path instead. This is previously attempted in commit dbdffaf50ff9 ("kbuild, rust: use -fremap-path-prefix to make paths relative") but that was reverted as remapping debug info causes some tool (e.g. objdump) to be unable to find sources. Therefore, use `--remap-path-scope` to only remap macros but leave debuginfo untouched. `--remap-path-scope` is only stable in Rust 1.95, so use `rustc-option` to detect its presence. This feature has been available as `-Zremap-path-scope` for all versions that we support; however due to bugs in the Rust compiler, it does not work reliably until 1.94. I opted to not enable it for 1.94 as it's just a single version that we missed. This change can be validated by building a kernel with O=, strip debug info on vmlinux, and then check if the absolute path exists in `strings vmlinux`, e.g. `strings vmlinux |grep \/home`. Reported-by: Janne Grunau Reported-by: Asahi Lina Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/288089-General/topic/Per-call-site.20data.20and.20lock.20class.20keys/near/572466559 [1] Link: https://github.com/AsahiLinux/linux/commit/54ab88878869036c9d6620101bfe17a81e88c2f9 [2] Signed-off-by: Gary Guo Acked-by: Nicolas Schier # kbuild Link: https://patch.msgid.link/20260226152112.3222886-1-gary@kernel.org [ Reworded for few typos. - Miguel ] Signed-off-by: Miguel Ojeda --- Makefile | 3 +++ rust/Makefile | 5 +++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 2446085983f7..73a39592f112 100644 --- a/Makefile +++ b/Makefile @@ -1113,6 +1113,9 @@ KBUILD_CFLAGS += -fno-builtin-wcslen # change __FILE__ to the relative path to the source directory ifdef building_out_of_srctree KBUILD_CPPFLAGS += -fmacro-prefix-map=$(srcroot)/= +ifeq ($(call rustc-option-yn, --remap-path-scope=macro),y) +KBUILD_RUSTFLAGS += --remap-path-prefix=$(srcroot)/= --remap-path-scope=macro +endif endif # include additional Makefiles when needed diff --git a/rust/Makefile b/rust/Makefile index 1500993d7ecc..9801af2e1e02 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -148,7 +148,8 @@ doctests_modifiers_workaround := $(rustdoc_modifiers_workaround)$(if $(call rust quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $< cmd_rustdoc = \ OBJTREE=$(abspath $(objtree)) \ - $(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=%,$(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \ + $(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=% --remap-path-scope=%, \ + $(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \ $(rustc_target_flags) -L$(objtree)/$(obj) \ -Zunstable-options --generate-link-to-definition \ --output $(rustdoc_output) \ @@ -334,7 +335,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< rm -rf $(objtree)/$(obj)/test/doctests/kernel; \ mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \ OBJTREE=$(abspath $(objtree)) \ - $(RUSTDOC) --test $(filter-out --remap-path-prefix=%,$(rust_flags)) \ + $(RUSTDOC) --test $(filter-out --remap-path-prefix=% --remap-path-scope=%,$(rust_flags)) \ -L$(objtree)/$(obj) --extern ffi --extern pin_init \ --extern kernel --extern build_error --extern macros \ --extern bindings --extern uapi \ From a075082a15e7f5c4889d0cbb51a4041c332cb00c Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Mon, 2 Mar 2026 15:04:14 +0100 Subject: [PATCH 135/487] rust: pin-init: internal: init: remove `#[disable_initialized_field_access]` Gary noticed [1] that the initializer macros as well as the `[Pin]Init` traits cannot support unaligned fields, since they use operations that require aligned pointers. This means that any code using structs with unaligned fields in pin-init is unsound. By default, the `init!` macro generates references to initialized fields, which makes the compiler check that those fields are aligned. However, we added the `#[disable_initialized_field_access]` attribute to avoid this behavior in commit ceca298c53f9 ("rust: pin-init: internal: init: add escape hatch for referencing initialized fields"). Thus remove the `#[disable_initialized_field_access]` attribute from `init!`, which is the only safe way to create an initializer handling unaligned fields. If support for in-place initializing structs with unaligned fields is required in the future, we could figure out a solution. This is tracked in [2]. Reported-by: Gary Guo Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/561532-pin-init/topic/initialized.20field.20accessor.20detection/with/576210658 [1] Link: https://github.com/Rust-for-Linux/pin-init/issues/112 [2] Fixes: ceca298c53f9 ("rust: pin-init: internal: init: add escape hatch for referencing initialized fields") Signed-off-by: Benno Lossin Acked-by: Janne Grunau Reviewed-by: Gary Guo Reviewed-by: Alice Ryhl Link: https://patch.msgid.link/20260302140424.4097655-1-lossin@kernel.org [ Adjusted tags and reworded as discussed. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/pin-init/internal/src/init.rs | 39 ++++++------------------------ 1 file changed, 8 insertions(+), 31 deletions(-) diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs index 42936f915a07..da53adc44ecf 100644 --- a/rust/pin-init/internal/src/init.rs +++ b/rust/pin-init/internal/src/init.rs @@ -62,7 +62,6 @@ fn ident(&self) -> Option<&Ident> { enum InitializerAttribute { DefaultError(DefaultErrorAttribute), - DisableInitializedFieldAccess, } struct DefaultErrorAttribute { @@ -86,6 +85,7 @@ pub(crate) fn expand( let error = error.map_or_else( || { if let Some(default_error) = attrs.iter().fold(None, |acc, attr| { + #[expect(irrefutable_let_patterns)] if let InitializerAttribute::DefaultError(DefaultErrorAttribute { ty }) = attr { Some(ty.clone()) } else { @@ -145,15 +145,7 @@ fn assert_zeroable(_: *mut T) }; // `mixed_site` ensures that the data is not accessible to the user-controlled code. let data = Ident::new("__data", Span::mixed_site()); - let init_fields = init_fields( - &fields, - pinned, - !attrs - .iter() - .any(|attr| matches!(attr, InitializerAttribute::DisableInitializedFieldAccess)), - &data, - &slot, - ); + let init_fields = init_fields(&fields, pinned, &data, &slot); let field_check = make_field_check(&fields, init_kind, &path); Ok(quote! {{ // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return @@ -236,7 +228,6 @@ fn get_init_kind(rest: Option<(Token![..], Expr)>, dcx: &mut DiagCtxt) -> InitKi fn init_fields( fields: &Punctuated, pinned: bool, - generate_initialized_accessors: bool, data: &Ident, slot: &Ident, ) -> TokenStream { @@ -272,13 +263,6 @@ fn init_fields( unsafe { &mut (*#slot).#ident } } }; - let accessor = generate_initialized_accessors.then(|| { - quote! { - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; - } - }); quote! { #(#attrs)* { @@ -286,7 +270,9 @@ fn init_fields( // SAFETY: TODO unsafe { #write(::core::ptr::addr_of_mut!((*#slot).#ident), #value_ident) }; } - #accessor + #(#cfgs)* + #[allow(unused_variables)] + let #ident = #accessor; } } InitializerKind::Init { ident, value, .. } => { @@ -326,20 +312,15 @@ fn init_fields( }, ) }; - let accessor = generate_initialized_accessors.then(|| { - quote! { - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; - } - }); quote! { #(#attrs)* { let #init = #value; #value_init } - #accessor + #(#cfgs)* + #[allow(unused_variables)] + let #ident = #accessor; } } InitializerKind::Code { block: value, .. } => quote! { @@ -466,10 +447,6 @@ fn parse(input: syn::parse::ParseStream<'_>) -> syn::Result { if a.path().is_ident("default_error") { a.parse_args::() .map(InitializerAttribute::DefaultError) - } else if a.path().is_ident("disable_initialized_field_access") { - a.meta - .require_path_only() - .map(|_| InitializerAttribute::DisableInitializedFieldAccess) } else { Err(syn::Error::new_spanned(a, "unknown initializer attribute")) } From 580cc37b1de4fcd9997c48d7080e744533f09f36 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Mon, 2 Mar 2026 15:04:15 +0100 Subject: [PATCH 136/487] rust: pin-init: internal: init: document load-bearing fact of field accessors The functions `[Pin]Init::__[pinned_]init` and `ptr::write` called from the `init!` macro require the passed pointer to be aligned. This fact is ensured by the creation of field accessors to previously initialized fields. Since we missed this very important fact from the beginning [1], document it in the code. Link: https://rust-for-linux.zulipchat.com/#narrow/channel/561532-pin-init/topic/initialized.20field.20accessor.20detection/with/576210658 [1] Fixes: 90e53c5e70a6 ("rust: add pin-init API core") Cc: # 6.6.y, 6.12.y: 42415d163e5d: rust: pin-init: add references to previously initialized fields Cc: # 6.6.y, 6.12.y, 6.18.y, 6.19.y Signed-off-by: Benno Lossin Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260302140424.4097655-2-lossin@kernel.org [ Updated Cc: stable@ tags as discussed. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/pin-init/internal/src/init.rs | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs index da53adc44ecf..738f62c8105c 100644 --- a/rust/pin-init/internal/src/init.rs +++ b/rust/pin-init/internal/src/init.rs @@ -251,6 +251,10 @@ fn init_fields( }); // Again span for better diagnostics let write = quote_spanned!(ident.span()=> ::core::ptr::write); + // NOTE: the field accessor ensures that the initialized field is properly aligned. + // Unaligned fields will cause the compiler to emit E0793. We do not support + // unaligned fields since `Init::__init` requires an aligned pointer; the call to + // `ptr::write` below has the same requirement. let accessor = if pinned { let project_ident = format_ident!("__project_{ident}"); quote! { @@ -278,6 +282,10 @@ fn init_fields( InitializerKind::Init { ident, value, .. } => { // Again span for better diagnostics let init = format_ident!("init", span = value.span()); + // NOTE: the field accessor ensures that the initialized field is properly aligned. + // Unaligned fields will cause the compiler to emit E0793. We do not support + // unaligned fields since `Init::__init` requires an aligned pointer; the call to + // `ptr::write` below has the same requirement. let (value_init, accessor) = if pinned { let project_ident = format_ident!("__project_{ident}"); ( From f76a93241d71fbba8425e3967097b498c29264ed Mon Sep 17 00:00:00 2001 From: Mieczyslaw Nalewaj Date: Tue, 3 Mar 2026 17:25:12 -0300 Subject: [PATCH 137/487] net: dsa: realtek: rtl8365mb: remove ifOutDiscards from rx_packets rx_packets should report the number of frames successfully received: unicast + multicast + broadcast. Subtracting ifOutDiscards (a TX counter) is incorrect and can undercount RX packets. RX drops are already reported via rx_dropped (e.g. etherStatsDropEvents), so there is no need to adjust rx_packets. This patch removes the subtraction of ifOutDiscards from rx_packets in rtl8365mb_stats_update(). Link: https://lore.kernel.org/netdev/878777925.105015.1763423928520@mail.yahoo.com/ Fixes: 4af2950c50c8 ("net: dsa: realtek-smi: add rtl8365mb subdriver for RTL8365MB-VC") Signed-off-by: Mieczyslaw Nalewaj Signed-off-by: Luiz Angelo Daros de Luca Reviewed-by: Simon Horman Acked-by: Linus Walleij Link: https://patch.msgid.link/20260303-realtek_namiltd_fix2-v1-1-bfa433d3401e@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/realtek/rtl8365mb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index f938a3f701cc..31fa94dac627 100644 --- a/drivers/net/dsa/realtek/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -1480,8 +1480,7 @@ static void rtl8365mb_stats_update(struct realtek_priv *priv, int port) stats->rx_packets = cnt[RTL8365MB_MIB_ifInUcastPkts] + cnt[RTL8365MB_MIB_ifInMulticastPkts] + - cnt[RTL8365MB_MIB_ifInBroadcastPkts] - - cnt[RTL8365MB_MIB_ifOutDiscards]; + cnt[RTL8365MB_MIB_ifInBroadcastPkts]; stats->tx_packets = cnt[RTL8365MB_MIB_ifOutUcastPkts] + cnt[RTL8365MB_MIB_ifOutMulticastPkts] + From 8565617a8599dd17b96b7bf7e1eb19809ac6ae5e Mon Sep 17 00:00:00 2001 From: Lukas Gerlach Date: Fri, 16 Jan 2026 10:57:31 +0100 Subject: [PATCH 138/487] KVM: riscv: Fix Spectre-v1 in APLIC interrupt handling Guests can control IRQ indices via MMIO. Sanitize them with array_index_nospec() to prevent speculative out-of-bounds access to the aplic->irqs[] array. Similar to arm64 commit 41b87599c743 ("KVM: arm/arm64: vgic: fix possible spectre-v1 in vgic_get_irq()") and x86 commit 8c86405f606c ("KVM: x86: Protect ioapic_read_indirect() from Spectre-v1/L1TF attacks"). Fixes: 74967aa208e2 ("RISC-V: KVM: Add in-kernel emulation of AIA APLIC") Signed-off-by: Lukas Gerlach Reviewed-by: Nutty Liu Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260116095731.24555-1-lukas.gerlach@cispa.de Signed-off-by: Anup Patel --- arch/riscv/kvm/aia_aplic.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c index d1e50bf5c351..3464f3351df7 100644 --- a/arch/riscv/kvm/aia_aplic.c +++ b/arch/riscv/kvm/aia_aplic.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -45,7 +46,7 @@ static u32 aplic_read_sourcecfg(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return 0; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = irqd->sourcecfg; @@ -61,7 +62,7 @@ static void aplic_write_sourcecfg(struct aplic *aplic, u32 irq, u32 val) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; if (val & APLIC_SOURCECFG_D) val = 0; @@ -81,7 +82,7 @@ static u32 aplic_read_target(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return 0; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = irqd->target; @@ -97,7 +98,7 @@ static void aplic_write_target(struct aplic *aplic, u32 irq, u32 val) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; val &= APLIC_TARGET_EIID_MASK | (APLIC_TARGET_HART_IDX_MASK << APLIC_TARGET_HART_IDX_SHIFT) | @@ -116,7 +117,7 @@ static bool aplic_read_pending(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = (irqd->state & APLIC_IRQ_STATE_PENDING) ? true : false; @@ -132,7 +133,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -170,7 +171,7 @@ static bool aplic_read_enabled(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = (irqd->state & APLIC_IRQ_STATE_ENABLED) ? true : false; @@ -186,7 +187,7 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); if (enabled) @@ -205,7 +206,7 @@ static bool aplic_read_input(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -254,7 +255,7 @@ static void aplic_update_irq_range(struct kvm *kvm, u32 first, u32 last) for (irq = first; irq <= last; irq++) { if (!irq || aplic->nr_irqs <= irq) continue; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -283,7 +284,7 @@ int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level) if (!aplic || !source || (aplic->nr_irqs <= source)) return -ENODEV; - irqd = &aplic->irqs[source]; + irqd = &aplic->irqs[array_index_nospec(source, aplic->nr_irqs)]; ie = (aplic->domaincfg & APLIC_DOMAINCFG_IE) ? true : false; raw_spin_lock_irqsave(&irqd->lock, flags); From dec9ed9944349643874d482238ca2437d4f47b61 Mon Sep 17 00:00:00 2001 From: Jiakai Xu Date: Mon, 2 Feb 2026 04:00:59 +0000 Subject: [PATCH 139/487] RISC-V: KVM: Fix use-after-free in kvm_riscv_gstage_get_leaf() While fuzzing KVM on RISC-V, a use-after-free was observed in kvm_riscv_gstage_get_leaf(), where ptep_get() dereferences a freed gstage page table page during gfn unmap. The crash manifests as: use-after-free in ptep_get include/linux/pgtable.h:340 [inline] use-after-free in kvm_riscv_gstage_get_leaf arch/riscv/kvm/gstage.c:89 Call Trace: ptep_get include/linux/pgtable.h:340 [inline] kvm_riscv_gstage_get_leaf+0x2ea/0x358 arch/riscv/kvm/gstage.c:89 kvm_riscv_gstage_unmap_range+0xf0/0x308 arch/riscv/kvm/gstage.c:265 kvm_unmap_gfn_range+0x168/0x1fc arch/riscv/kvm/mmu.c:256 kvm_mmu_unmap_gfn_range virt/kvm/kvm_main.c:724 [inline] page last free pid 808 tgid 808 stack trace: kvm_riscv_mmu_free_pgd+0x1b6/0x26a arch/riscv/kvm/mmu.c:457 kvm_arch_flush_shadow_all+0x1a/0x24 arch/riscv/kvm/mmu.c:134 kvm_flush_shadow_all virt/kvm/kvm_main.c:344 [inline] The UAF is caused by gstage page table walks running concurrently with gstage pgd teardown. In particular, kvm_unmap_gfn_range() can traverse gstage page tables while kvm_arch_flush_shadow_all() frees the pgd, leading to use-after-free of page table pages. Fix the issue by serializing gstage unmap and pgd teardown with kvm->mmu_lock. Holding mmu_lock ensures that gstage page tables remain valid for the duration of unmap operations and prevents concurrent frees. This matches existing RISC-V KVM usage of mmu_lock to protect gstage map/unmap operations, e.g. kvm_riscv_mmu_iounmap. Fixes: dd82e35638d67f ("RISC-V: KVM: Factor-out g-stage page table management") Signed-off-by: Jiakai Xu Signed-off-by: Jiakai Xu Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260202040059.1801167-1-xujiakai2025@iscas.ac.cn Signed-off-by: Anup Patel --- arch/riscv/kvm/mmu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 0b75eb2a1820..87c8f41482c5 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -245,6 +245,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { struct kvm_gstage gstage; + bool mmu_locked; if (!kvm->arch.pgd) return false; @@ -253,9 +254,12 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) gstage.flags = 0; gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); gstage.pgd = kvm->arch.pgd; + mmu_locked = spin_trylock(&kvm->mmu_lock); kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); + if (mmu_locked) + spin_unlock(&kvm->mmu_lock); return false; } From c28eb189e481f5dac993d1907710716a9b561890 Mon Sep 17 00:00:00 2001 From: Jiakai Xu Date: Thu, 26 Feb 2026 08:51:19 +0000 Subject: [PATCH 140/487] RISC-V: KVM: Fix null pointer dereference in kvm_riscv_vcpu_aia_rmw_topei() kvm_riscv_vcpu_aia_rmw_topei() assumes that the per-vCPU IMSIC state has been initialized once AIA is reported as available and initialized at the VM level. This assumption does not always hold. Under fuzzed ioctl sequences, a guest may access the IMSIC TOPEI CSR before the vCPU IMSIC state is set up. In this case, vcpu->arch.aia_context.imsic_state is still NULL, and the TOPEI RMW path dereferences it unconditionally, leading to a host kernel crash. The crash manifests as: Unable to handle kernel paging request at virtual address dfffffff0000000e ... kvm_riscv_vcpu_aia_imsic_rmw arch/riscv/kvm/aia_imsic.c:909 kvm_riscv_vcpu_aia_rmw_topei arch/riscv/kvm/aia.c:231 csr_insn arch/riscv/kvm/vcpu_insn.c:208 system_opcode_insn arch/riscv/kvm/vcpu_insn.c:281 kvm_riscv_vcpu_virtual_insn arch/riscv/kvm/vcpu_insn.c:355 kvm_riscv_vcpu_exit arch/riscv/kvm/vcpu_exit.c:230 kvm_arch_vcpu_ioctl_run arch/riscv/kvm/vcpu.c:1008 ... Fix this by explicitly checking whether the vCPU IMSIC state has been initialized before handling TOPEI CSR accesses. If not, forward the CSR emulation to user space. Fixes: db8b7e97d6137 ("RISC-V: KVM: Add in-kernel virtualization of AIA IMSIC") Signed-off-by: Jiakai Xu Signed-off-by: Jiakai Xu Reviewed-by: Nutty Liu Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260226085119.643295-1-xujiakai2025@iscas.ac.cn Signed-off-by: Anup Patel --- arch/riscv/kvm/aia_imsic.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 06752fa24798..8786f52cf65a 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -908,6 +908,10 @@ int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel, int r, rc = KVM_INSN_CONTINUE_NEXT_SEPC; struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + /* If IMSIC vCPU state not initialized then forward to user space */ + if (!imsic) + return KVM_INSN_EXIT_TO_USER_SPACE; + if (isel == KVM_RISCV_AIA_IMSIC_TOPEI) { /* Read pending and enabled interrupt with highest priority */ topei = imsic_mrif_topei(imsic->swfile, imsic->nr_eix, From 5c1bb07871119eae6434c640e5e645a74d54a222 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Fri, 27 Feb 2026 13:46:16 +0000 Subject: [PATCH 141/487] RISC-V: KVM: fix off-by-one array access in SBI PMU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The indexed array only has RISCV_KVM_MAX_COUNTERS elements. The out-of-bound access could have been performed by a guest, but it could only access another guest accessible data. Fixes: 8f0153ecd3bf ("RISC-V: KVM: Add skeleton support for perf") Signed-off-by: Radim Krčmář Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260227134617.23378-1-radim.krcmar@oss.qualcomm.com Signed-off-by: Anup Patel --- arch/riscv/kvm/vcpu_pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 4d8d5e9aa53d..aec6b293968b 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -520,7 +520,7 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, { struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); - if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) { + if (cidx >= RISCV_KVM_MAX_COUNTERS || cidx == 1) { retdata->err_val = SBI_ERR_INVALID_PARAM; return 0; } From 721ead7757125d66ec9b4ad98939a13d25e0b473 Mon Sep 17 00:00:00 2001 From: Jiakai Xu Date: Mon, 2 Mar 2026 13:27:03 +0000 Subject: [PATCH 142/487] RISC-V: KVM: Fix use-after-free in kvm_riscv_aia_aplic_has_attr() Fuzzer reports a KASAN use-after-free bug triggered by a race between KVM_HAS_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls on the AIA device. The root cause is that aia_has_attr() invokes kvm_riscv_aia_aplic_has_attr() without holding dev->kvm->lock, while a concurrent aia_set_attr() may call aia_init() under that lock. When aia_init() fails after kvm_riscv_aia_aplic_init() has succeeded, it calls kvm_riscv_aia_aplic_cleanup() in its fail_cleanup_imsics path, which frees both aplic_state and aplic_state->irqs. The concurrent has_attr path can then dereference the freed aplic->irqs in aplic_read_pending(): irqd = &aplic->irqs[irq]; /* UAF here */ KASAN report: BUG: KASAN: slab-use-after-free in aplic_read_pending arch/riscv/kvm/aia_aplic.c:119 [inline] BUG: KASAN: slab-use-after-free in aplic_read_pending_word arch/riscv/kvm/aia_aplic.c:351 [inline] BUG: KASAN: slab-use-after-free in aplic_mmio_read_offset arch/riscv/kvm/aia_aplic.c:406 Read of size 8 at addr ff600000ba965d58 by task 9498 Call Trace: aplic_read_pending arch/riscv/kvm/aia_aplic.c:119 [inline] aplic_read_pending_word arch/riscv/kvm/aia_aplic.c:351 [inline] aplic_mmio_read_offset arch/riscv/kvm/aia_aplic.c:406 kvm_riscv_aia_aplic_has_attr arch/riscv/kvm/aia_aplic.c:566 aia_has_attr arch/riscv/kvm/aia_device.c:469 allocated by task 9473: kvm_riscv_aia_aplic_init arch/riscv/kvm/aia_aplic.c:583 aia_init arch/riscv/kvm/aia_device.c:248 [inline] aia_set_attr arch/riscv/kvm/aia_device.c:334 freed by task 9473: kvm_riscv_aia_aplic_cleanup arch/riscv/kvm/aia_aplic.c:644 aia_init arch/riscv/kvm/aia_device.c:292 [inline] aia_set_attr arch/riscv/kvm/aia_device.c:334 Fix this race by acquiring dev->kvm->lock in aia_has_attr() before calling kvm_riscv_aia_aplic_has_attr(), consistent with the locking pattern used in aia_get_attr() and aia_set_attr(). Fixes: 289a007b98b06d ("RISC-V: KVM: Expose APLIC registers as attributes of AIA irqchip") Signed-off-by: Jiakai Xu Signed-off-by: Jiakai Xu Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260302132703.1721415-1-xujiakai2025@iscas.ac.cn Signed-off-by: Anup Patel --- arch/riscv/kvm/aia_device.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index b195a93add1c..fb901947aefe 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -437,7 +437,7 @@ static int aia_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { - int nr_vcpus; + int nr_vcpus, r = -ENXIO; switch (attr->group) { case KVM_DEV_RISCV_AIA_GRP_CONFIG: @@ -466,12 +466,15 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) } break; case KVM_DEV_RISCV_AIA_GRP_APLIC: - return kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr); + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; case KVM_DEV_RISCV_AIA_GRP_IMSIC: return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); } - return -ENXIO; + return r; } struct kvm_device_ops kvm_riscv_aia_device_ops = { From 7120a9d9e0232ad3c661a100973c57328f462b80 Mon Sep 17 00:00:00 2001 From: Jiakai Xu Date: Wed, 4 Mar 2026 08:08:04 +0000 Subject: [PATCH 143/487] RISC-V: KVM: Fix potential UAF in kvm_riscv_aia_imsic_has_attr() The KVM_DEV_RISCV_AIA_GRP_APLIC branch of aia_has_attr() was identified to have a race condition with concurrent KVM_SET_DEVICE_ATTR ioctls, leading to a use-after-free bug. Upon analyzing the code, it was discovered that the KVM_DEV_RISCV_AIA_GRP_IMSIC branch of aia_has_attr() suffers from the same lack of synchronization. It invokes kvm_riscv_aia_imsic_has_attr() without holding dev->kvm->lock. While aia_has_attr() is running, a concurrent aia_set_attr() could call aia_init() under the dev->kvm->lock. If aia_init() fails, it may trigger kvm_riscv_vcpu_aia_imsic_cleanup(), which frees imsic_state. Without proper locking, kvm_riscv_aia_imsic_has_attr() could attempt to access imsic_state while it is being deallocated. Although this specific path has not yet been reported by a fuzzer, it is logically identical to the APLIC issue. Fix this by acquiring the dev->kvm->lock before calling kvm_riscv_aia_imsic_has_attr(), ensuring consistency with the locking pattern used for other AIA attribute groups. Fixes: 5463091a51cf ("RISC-V: KVM: Expose IMSIC registers as attributes of AIA irqchip") Signed-off-by: Jiakai Xu Signed-off-by: Jiakai Xu Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260304080804.2281721-1-xujiakai2025@iscas.ac.cn Signed-off-by: Anup Patel --- arch/riscv/kvm/aia_device.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index fb901947aefe..9a45c85239fe 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -471,7 +471,10 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) mutex_unlock(&dev->kvm->lock); break; case KVM_DEV_RISCV_AIA_GRP_IMSIC: - return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; } return r; From b342166cbcf96a8c846db96529e75dc2d2420d58 Mon Sep 17 00:00:00 2001 From: Wang Yechao Date: Thu, 26 Feb 2026 19:12:31 +0800 Subject: [PATCH 144/487] RISC-V: KVM: Skip THP support check during dirty logging When dirty logging is enabled, guest stage mappings are forced to PAGE_SIZE granularity. Changing the mapping page size at this point is incorrect. Fixes: ed7ae7a34bea ("RISC-V: KVM: Transparent huge page support") Signed-off-by: Wang Yechao Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260226191231140_X1Juus7s2kgVlc0ZyW_K@zte.com.cn Signed-off-by: Anup Patel --- arch/riscv/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 87c8f41482c5..088d33ba90ed 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -539,7 +539,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, goto out_unlock; /* Check if we are backed by a THP and thus use block mapping if possible */ - if (vma_pagesize == PAGE_SIZE) + if (!logging && (vma_pagesize == PAGE_SIZE)) vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &hfn, &gpa); if (writable) { From f9e26fc325411a34555ad07ddf0a19ff72ea06d4 Mon Sep 17 00:00:00 2001 From: Lukas Gerlach Date: Tue, 3 Mar 2026 15:19:41 +0100 Subject: [PATCH 145/487] KVM: riscv: Fix Spectre-v1 in ONE_REG register access MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit User-controlled register indices from the ONE_REG ioctl are used to index into arrays of register values. Sanitize them with array_index_nospec() to prevent speculative out-of-bounds access. Reviewed-by: Radim Krčmář Signed-off-by: Lukas Gerlach Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-1-192caab8e0dc@cispa.de Signed-off-by: Anup Patel --- arch/riscv/kvm/vcpu_onereg.c | 36 ++++++++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 8 deletions(-) diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index e7ab6cb00646..a4c8703a96a9 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -127,6 +128,7 @@ static int kvm_riscv_vcpu_isa_check_host(unsigned long kvm_ext, unsigned long *g kvm_ext >= ARRAY_SIZE(kvm_isa_ext_arr)) return -ENOENT; + kvm_ext = array_index_nospec(kvm_ext, ARRAY_SIZE(kvm_isa_ext_arr)); *guest_ext = kvm_isa_ext_arr[kvm_ext]; switch (*guest_ext) { case RISCV_ISA_EXT_SMNPM: @@ -443,13 +445,16 @@ static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu, unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); unsigned long reg_val; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc)) reg_val = cntx->sepc; else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num && @@ -476,13 +481,16 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu, unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); unsigned long reg_val; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; @@ -507,10 +515,13 @@ static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { kvm_riscv_vcpu_flush_interrupts(vcpu); *out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK; @@ -526,10 +537,13 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, unsigned long reg_val) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { reg_val &= VSIP_VALID_MASK; reg_val <<= VSIP_TO_HVIP_SHIFT; @@ -548,11 +562,14 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu, unsigned long reg_val) { struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) / - sizeof(unsigned long)) + if (reg_num >= regs_max) return -EINVAL; + reg_num = array_index_nospec(reg_num, regs_max); + ((unsigned long *)csr)[reg_num] = reg_val; return 0; } @@ -562,11 +579,14 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) / - sizeof(unsigned long)) + if (reg_num >= regs_max) return -EINVAL; + reg_num = array_index_nospec(reg_num, regs_max); + *out_val = ((unsigned long *)csr)[reg_num]; return 0; } From ec87a82ca8740891bce9e93e79ea2cd6c2d70ac8 Mon Sep 17 00:00:00 2001 From: Lukas Gerlach Date: Tue, 3 Mar 2026 15:19:42 +0100 Subject: [PATCH 146/487] KVM: riscv: Fix Spectre-v1 in AIA CSR access MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit User-controlled indices are used to access AIA CSR registers. Sanitize them with array_index_nospec() to prevent speculative out-of-bounds access. Similar to x86 commit 8c86405f606c ("KVM: x86: Protect ioapic_read_indirect() from Spectre-v1/L1TF attacks") and arm64 commit 41b87599c743 ("KVM: arm/arm64: vgic: fix possible spectre-v1 in vgic_get_irq()"). Reviewed-by: Radim Krčmář Signed-off-by: Lukas Gerlach Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-2-192caab8e0dc@cispa.de Signed-off-by: Anup Patel --- arch/riscv/kvm/aia.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index cac3c2b51d72..38de97d2f5b8 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -182,10 +183,13 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + *out_val = 0; if (kvm_riscv_aia_available()) *out_val = ((unsigned long *)csr)[reg_num]; @@ -198,10 +202,13 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, unsigned long val) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (kvm_riscv_aia_available()) { ((unsigned long *)csr)[reg_num] = val; From 8f0c15c4b14f27dd9bd35971adb9c908241f2f63 Mon Sep 17 00:00:00 2001 From: Lukas Gerlach Date: Tue, 3 Mar 2026 15:19:43 +0100 Subject: [PATCH 147/487] KVM: riscv: Fix Spectre-v1 in floating-point register access MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit User-controlled indices are used to index into floating-point registers. Sanitize them with array_index_nospec() to prevent speculative out-of-bounds access. Reviewed-by: Radim Krčmář Signed-off-by: Lukas Gerlach Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-3-192caab8e0dc@cispa.de Signed-off-by: Anup Patel --- arch/riscv/kvm/vcpu_fp.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 030904d82b58..bd5a9e7e7165 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -93,9 +94,11 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) reg_val = &cntx->fp.f.fcsr; else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); reg_val = &cntx->fp.f.f[reg_num]; - else + } else return -ENOENT; } else if ((rtype == KVM_REG_RISCV_FP_D) && riscv_isa_extension_available(vcpu->arch.isa, d)) { @@ -107,6 +110,8 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { if (KVM_REG_SIZE(reg->id) != sizeof(u64)) return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); reg_val = &cntx->fp.d.f[reg_num]; } else return -ENOENT; @@ -138,9 +143,11 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) reg_val = &cntx->fp.f.fcsr; else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); reg_val = &cntx->fp.f.f[reg_num]; - else + } else return -ENOENT; } else if ((rtype == KVM_REG_RISCV_FP_D) && riscv_isa_extension_available(vcpu->arch.isa, d)) { @@ -152,6 +159,8 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { if (KVM_REG_SIZE(reg->id) != sizeof(u64)) return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); reg_val = &cntx->fp.d.f[reg_num]; } else return -ENOENT; From 2dda6a9e09ee4f3c30ea72ba949a6ea781205e3a Mon Sep 17 00:00:00 2001 From: Lukas Gerlach Date: Tue, 3 Mar 2026 15:19:44 +0100 Subject: [PATCH 148/487] KVM: riscv: Fix Spectre-v1 in PMU counter access MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Guest-controlled counter indices received via SBI ecalls are used to index into the PMC array. Sanitize them with array_index_nospec() to prevent speculative out-of-bounds access. Similar to x86 commit 13c5183a4e64 ("KVM: x86: Protect MSR-based index computations in pmu.h from Spectre-v1/L1TF attacks"). Fixes: 8f0153ecd3bf ("RISC-V: KVM: Add skeleton support for perf") Reviewed-by: Radim Krčmář Signed-off-by: Lukas Gerlach Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-4-192caab8e0dc@cispa.de Signed-off-by: Anup Patel --- arch/riscv/kvm/vcpu_pmu.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index aec6b293968b..e873430e596b 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -87,7 +88,8 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code) { - return hw_event_perf_map[sbi_event_code]; + return hw_event_perf_map[array_index_nospec(sbi_event_code, + SBI_PMU_HW_GENERAL_MAX)]; } static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code) @@ -218,6 +220,7 @@ static int pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, return -EINVAL; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[cidx]; if (pmc->cinfo.type != SBI_PMU_CTR_TYPE_FW) @@ -244,6 +247,7 @@ static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, return -EINVAL; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[cidx]; if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { @@ -525,6 +529,7 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, return 0; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); retdata->out_val = kvpmu->pmc[cidx].cinfo.value; return 0; @@ -559,7 +564,8 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, } /* Start the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { - pmc_index = i + ctr_base; + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) continue; /* The guest started the counter again. Reset the overflow status */ @@ -630,7 +636,8 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, /* Stop the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { - pmc_index = i + ctr_base; + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) continue; pmc = &kvpmu->pmc[pmc_index]; @@ -761,6 +768,7 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba } } + ctr_idx = array_index_nospec(ctr_idx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[ctr_idx]; pmc->idx = ctr_idx; From 45700a743af3b7402cb7238860a25c62f0498ab4 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Tue, 20 Jan 2026 13:29:47 +0530 Subject: [PATCH 149/487] RISC-V: KVM: Fix error code returned for Smstateen ONE_REG Return -ENOENT for Smstateen ONE_REG when: 1) Smstateen is not enabled for a VCPU 2) ONE_REG id is out of range This will make Smstateen ONE_REG error codes consistent with other ONE_REG interfaces of KVM RISC-V. Fixes: c04913f2b54e ("RISCV: KVM: Add sstateen0 to ONE_REG") Signed-off-by: Anup Patel Link: https://lore.kernel.org/r/20260120080013.2153519-2-anup.patel@oss.qualcomm.com Signed-off-by: Anup Patel --- arch/riscv/kvm/vcpu_onereg.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index a4c8703a96a9..45ecc0082e90 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -565,8 +565,10 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu, unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / sizeof(unsigned long); + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; if (reg_num >= regs_max) - return -EINVAL; + return -ENOENT; reg_num = array_index_nospec(reg_num, regs_max); @@ -582,8 +584,10 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu, unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / sizeof(unsigned long); + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; if (reg_num >= regs_max) - return -EINVAL; + return -ENOENT; reg_num = array_index_nospec(reg_num, regs_max); @@ -615,10 +619,7 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu, rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, ®_val); break; case KVM_REG_RISCV_CSR_SMSTATEEN: - rc = -EINVAL; - if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) - rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, - ®_val); + rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, ®_val); break; default: rc = -ENOENT; @@ -660,10 +661,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu, rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val); break; case KVM_REG_RISCV_CSR_SMSTATEEN: - rc = -EINVAL; - if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) - rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, - reg_val); + rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, reg_val); break; default: rc = -ENOENT; From 24433b2b5c74a9fee7baa3a97a1947446868901d Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Tue, 20 Jan 2026 13:29:48 +0530 Subject: [PATCH 150/487] RISC-V: KVM: Fix error code returned for Ssaia ONE_REG Return -ENOENT for Ssaia ONE_REG when Ssaia is not enabled for a VCPU. This will make Ssaia ONE_REG error codes consistent with other ONE_REG interfaces of KVM RISC-V. Fixes: 2a88f38cd58d ("RISC-V: KVM: return ENOENT in *_one_reg() when reg is unknown") Signed-off-by: Anup Patel Link: https://lore.kernel.org/r/20260120080013.2153519-3-anup.patel@oss.qualcomm.com Signed-off-by: Anup Patel --- arch/riscv/kvm/aia.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index 38de97d2f5b8..5ec503288555 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -185,6 +185,8 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) + return -ENOENT; if (reg_num >= regs_max) return -ENOENT; @@ -204,6 +206,8 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) + return -ENOENT; if (reg_num >= regs_max) return -ENOENT; From c61ec3e8cc5d46fa269434a9ec16ca36d362e0dd Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Tue, 20 Jan 2026 13:29:49 +0530 Subject: [PATCH 151/487] RISC-V: KVM: Check host Ssaia extension when creating AIA irqchip The KVM user-space may create KVM AIA irqchip before checking VCPU Ssaia extension availability so KVM AIA irqchip must fail when host does not have Ssaia extension. Fixes: 89d01306e34d ("RISC-V: KVM: Implement device interface for AIA irqchip") Signed-off-by: Anup Patel Link: https://lore.kernel.org/r/20260120080013.2153519-4-anup.patel@oss.qualcomm.com Signed-off-by: Anup Patel --- arch/riscv/kvm/aia_device.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index 9a45c85239fe..49c71d3cdb00 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -11,6 +11,7 @@ #include #include #include +#include static int aia_create(struct kvm_device *dev, u32 type) { @@ -22,6 +23,9 @@ static int aia_create(struct kvm_device *dev, u32 type) if (irqchip_in_kernel(kvm)) return -EEXIST; + if (!riscv_isa_extension_available(NULL, SSAIA)) + return -ENODEV; + ret = -EBUSY; if (kvm_trylock_all_vcpus(kvm)) return ret; From 54fcd2f95f8d216183965a370ec69e1aab14f5da Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Wed, 4 Mar 2026 19:54:27 +0100 Subject: [PATCH 152/487] xfs: fix returned valued from xfs_defer_can_append xfs_defer_can_append returns a bool, it shouldn't be returning a NULL. Found by code inspection. Fixes: 4dffb2cbb483 ("xfs: allow pausing of pending deferred work items") Cc: # v6.8 Signed-off-by: Carlos Maiolino Reviewed-by: Darrick J. Wong Acked-by: Souptick Joarder Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_defer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 472c261163ed..c6909716b041 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -809,7 +809,7 @@ xfs_defer_can_append( /* Paused items cannot absorb more work */ if (dfp->dfp_flags & XFS_DEFER_PAUSED) - return NULL; + return false; /* Already full? */ if (ops->max_items && dfp->dfp_count >= ops->max_items) From 244acf1976b889b80b234982a70e9550c6f0bab7 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Wed, 4 Mar 2026 16:22:22 +0000 Subject: [PATCH 153/487] KVM: arm64: Fix vma_shift staleness on nested hwpoison path When user_mem_abort() handles a nested stage-2 fault, it truncates vma_pagesize to respect the guest's mapping size. However, the local variable vma_shift is never updated to match this new size. If the underlying host page turns out to be hardware poisoned, kvm_send_hwpoison_signal() is called with the original, larger vma_shift instead of the actual mapping size. This signals incorrect poison boundaries to userspace and breaks hugepage memory poison containment for nested VMs. Update vma_shift to match the truncated vma_pagesize when operating on behalf of a nested hypervisor. Fixes: fd276e71d1e7 ("KVM: arm64: nv: Handle shadow stage 2 page faults") Signed-off-by: Fuad Tabba Link: https://patch.msgid.link/20260304162222.836152-3-tabba@google.com [maz: simplified vma_shift assignment from the original patch] Signed-off-by: Marc Zyngier --- arch/arm64/kvm/mmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index e1d6a4f591a9..17d64a1e11e5 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1751,6 +1751,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, force_pte = (max_map_size == PAGE_SIZE); vma_pagesize = min_t(long, vma_pagesize, max_map_size); + vma_shift = __ffs(vma_pagesize); } /* From 3599c714c08c324f0fcfa392bfb857c92c575400 Mon Sep 17 00:00:00 2001 From: "Zenghui Yu (Huawei)" Date: Fri, 6 Mar 2026 15:44:22 +0800 Subject: [PATCH 154/487] KVM: arm64: Remove the redundant ISB in __kvm_at_s1e2() We already have an ISB in __kvm_at() to make the address translation result visible to subsequent reads of PAR_EL1. Remove the redundant one right after it. Signed-off-by: Zenghui Yu (Huawei) Link: https://patch.msgid.link/20260306074422.47694-1-zenghui.yu@linux.dev Signed-off-by: Marc Zyngier --- arch/arm64/kvm/at.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 6588ea251ed7..c5c5644b1878 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -1504,8 +1504,6 @@ int __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) fail = true; } - isb(); - if (!fail) par = read_sysreg_par(); From 25966fc097691e5c925ad080f64a2f19c5fd940a Mon Sep 17 00:00:00 2001 From: Mehul Rao Date: Thu, 5 Mar 2026 14:31:46 -0500 Subject: [PATCH 155/487] ublk: fix NULL pointer dereference in ublk_ctrl_set_size() ublk_ctrl_set_size() unconditionally dereferences ub->ub_disk via set_capacity_and_notify() without checking if it is NULL. ub->ub_disk is NULL before UBLK_CMD_START_DEV completes (it is only assigned in ublk_ctrl_start_dev()) and after UBLK_CMD_STOP_DEV runs (ublk_detach_disk() sets it to NULL). Since the UBLK_CMD_UPDATE_SIZE handler performs no state validation, a user can trigger a NULL pointer dereference by sending UPDATE_SIZE to a device that has been added but not yet started, or one that has been stopped. Fix this by checking ub->ub_disk under ub->mutex before dereferencing it, and returning -ENODEV if the disk is not available. Fixes: 98b995660bff ("ublk: Add UBLK_U_CMD_UPDATE_SIZE") Cc: stable@vger.kernel.org Signed-off-by: Mehul Rao Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c13cda58a7c6..03edabdf8977 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -5003,15 +5003,22 @@ static int ublk_ctrl_get_features(const struct ublksrv_ctrl_cmd *header) return 0; } -static void ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) +static int ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) { struct ublk_param_basic *p = &ub->params.basic; u64 new_size = header->data[0]; + int ret = 0; mutex_lock(&ub->mutex); + if (!ub->ub_disk) { + ret = -ENODEV; + goto out; + } p->dev_sectors = new_size; set_capacity_and_notify(ub->ub_disk, p->dev_sectors); +out: mutex_unlock(&ub->mutex); + return ret; } struct count_busy { @@ -5331,8 +5338,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ret = ublk_ctrl_end_recovery(ub, &header); break; case UBLK_CMD_UPDATE_SIZE: - ublk_ctrl_set_size(ub, &header); - ret = 0; + ret = ublk_ctrl_set_size(ub, &header); break; case UBLK_CMD_QUIESCE_DEV: ret = ublk_ctrl_quiesce_dev(ub, &header); From f9fb44b0ecefc1f218db56661ed66d4e8d67317d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 10 Feb 2026 13:50:09 -0800 Subject: [PATCH 156/487] objtool/klp: Fix detection of corrupt static branch/call entries Patching a function which references a static key living in a kernel module is unsupported due to ordering issues inherent to late module patching: 1) Load a livepatch module which has a __jump_table entry which needs a klp reloc to reference static key K which lives in module M. 2) The __jump_table klp reloc does *not* get resolved because module M is not yet loaded. 3) jump_label_add_module() corrupts memory (or causes a panic) when dereferencing the uninitialized pointer to key K. validate_special_section_klp_reloc() intends to prevent that from ever happening by catching it at build time. However, it incorrectly assumes the special section entry's reloc symbol references have already been converted from section symbols to object symbols, causing the validation to miss corruption in extracted static branch/call table entries. Make sure the references have been properly converted before doing the validation. Fixes: dd590d4d57eb ("objtool/klp: Introduce klp diff subcommand for diffing object files") Reported-by: Song Liu Reviewed-and-tested-by: Song Liu Link: https://patch.msgid.link/124ad747b751df0df1725eff89de8332e3fb26d6.1770759954.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/klp-diff.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c index 9f1f4011eb9c..d94632e80955 100644 --- a/tools/objtool/klp-diff.c +++ b/tools/objtool/klp-diff.c @@ -1364,6 +1364,9 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym const char *sym_modname; struct export *export; + if (convert_reloc_sym(e->patched, reloc)) + continue; + /* Static branch/call keys are always STT_OBJECT */ if (reloc->sym->type != STT_OBJECT) { From e476bb277cf91b7ac3ea803ec78a4f0791bddec3 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 10 Feb 2026 13:50:10 -0800 Subject: [PATCH 157/487] objtool/klp: Disable unsupported pr_debug() usage Instead of erroring out on unsupported pr_debug() (e.g., when patching a module), issue a warning and make it inert, similar to how unsupported tracepoints are currently handled. Reviewed-and-tested-by: Song Liu Link: https://patch.msgid.link/3a7db3a5b7d4abf9b2534803a74e2e7231322738.1770759954.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/klp-diff.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c index d94632e80955..9ff65b01882b 100644 --- a/tools/objtool/klp-diff.c +++ b/tools/objtool/klp-diff.c @@ -1334,18 +1334,18 @@ static bool should_keep_special_sym(struct elf *elf, struct symbol *sym) * be applied after static branch/call init, resulting in code corruption. * * Validate a special section entry to avoid that. Note that an inert - * tracepoint is harmless enough, in that case just skip the entry and print a - * warning. Otherwise, return an error. + * tracepoint or pr_debug() is harmless enough, in that case just skip the + * entry and print a warning. Otherwise, return an error. * - * This is only a temporary limitation which will be fixed when livepatch adds - * support for submodules: fully self-contained modules which are embedded in - * the top-level livepatch module's data and which can be loaded on demand when - * their corresponding to-be-patched module gets loaded. Then klp relocs can - * be retired. + * TODO: This is only a temporary limitation which will be fixed when livepatch + * adds support for submodules: fully self-contained modules which are embedded + * in the top-level livepatch module's data and which can be loaded on demand + * when their corresponding to-be-patched module gets loaded. Then klp relocs + * can be retired. * * Return: * -1: error: validation failed - * 1: warning: tracepoint skipped + * 1: warning: disabled tracepoint or pr_debug() * 0: success */ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym) @@ -1403,6 +1403,13 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym continue; } + if (strstr(reloc->sym->name, "__UNIQUE_ID_ddebug_")) { + WARN("%s: disabling unsupported pr_debug()", + code_sym->name); + ret = 1; + continue; + } + ERROR("%s+0x%lx: unsupported static branch key %s. Use static_key_enabled() instead", code_sym->name, code_offset, reloc->sym->name); return -1; From 11c2adcd1fa2a9380a507db1e57c8542bfc81827 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 10 Feb 2026 13:50:11 -0800 Subject: [PATCH 158/487] objtool/klp: Avoid NULL pointer dereference when printing code symbol name Fix a hypothetical NULL pointer defereference of the 'code_sym' variable. In theory this should never happen. Reviewed-and-tested-by: Song Liu Link: https://patch.msgid.link/64116517bc93851a98fe366ea0a4d807f4c70aab.1770759954.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/klp-diff.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c index 9ff65b01882b..a3198a63c2f0 100644 --- a/tools/objtool/klp-diff.c +++ b/tools/objtool/klp-diff.c @@ -1352,7 +1352,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym { bool static_branch = !strcmp(sym->sec->name, "__jump_table"); bool static_call = !strcmp(sym->sec->name, ".static_call_sites"); - struct symbol *code_sym = NULL; + const char *code_sym = NULL; unsigned long code_offset = 0; struct reloc *reloc; int ret = 0; @@ -1372,7 +1372,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym /* Save code location which can be printed below */ if (reloc->sym->type == STT_FUNC && !code_sym) { - code_sym = reloc->sym; + code_sym = reloc->sym->name; code_offset = reloc_addend(reloc); } @@ -1395,23 +1395,26 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym if (!strcmp(sym_modname, "vmlinux")) continue; + if (!code_sym) + code_sym = ""; + if (static_branch) { if (strstarts(reloc->sym->name, "__tracepoint_")) { WARN("%s: disabling unsupported tracepoint %s", - code_sym->name, reloc->sym->name + 13); + code_sym, reloc->sym->name + 13); ret = 1; continue; } if (strstr(reloc->sym->name, "__UNIQUE_ID_ddebug_")) { WARN("%s: disabling unsupported pr_debug()", - code_sym->name); + code_sym); ret = 1; continue; } ERROR("%s+0x%lx: unsupported static branch key %s. Use static_key_enabled() instead", - code_sym->name, code_offset, reloc->sym->name); + code_sym, code_offset, reloc->sym->name); return -1; } @@ -1422,7 +1425,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym } ERROR("%s()+0x%lx: unsupported static call key %s. Use KLP_STATIC_CALL() instead", - code_sym->name, code_offset, reloc->sym->name); + code_sym, code_offset, reloc->sym->name); return -1; } From 32234049107d012703d50547e815f198f147968b Mon Sep 17 00:00:00 2001 From: HONG Yifan Date: Tue, 3 Mar 2026 01:03:39 +0000 Subject: [PATCH 159/487] objtool: Use HOSTCFLAGS for HAVE_XXHASH test Previously, HAVE_XXHASH is tested by invoking HOSTCC without HOSTCFLAGS. Consider the following scenario: - The host machine has libxxhash installed - We build the kernel with HOSTCFLAGS containing a --sysroot that does not have xxhash.h (for hermetic builds) In this case, HAVE_XXHASH is set to y, but when it builds objtool with HOSTCFLAGS, because the --sysroot does not contain xxhash.h, the following error is raised: <...>/common/tools/objtool/include/objtool/checksum_types.h:12:10: fatal error: 'xxhash.h' file not found 12 | #include | ^~~~~~~~~~ To resolve the error, we test HAVE_XXHASH by invoking HOSTCC with HOSTCFLAGS. Signed-off-by: HONG Yifan Reviewed-by: Carlos Llamas Link: https://patch.msgid.link/20260303010340.306164-1-elsk@google.com Signed-off-by: Josh Poimboeuf --- tools/objtool/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 6964175abdfd..b8b8529f8ea9 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -13,7 +13,7 @@ endif ifeq ($(ARCH_HAS_KLP),y) HAVE_XXHASH = $(shell printf "$(pound)include \nXXH3_state_t *state;int main() {}" | \ - $(HOSTCC) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n) + $(HOSTCC) $(HOSTCFLAGS) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n) ifeq ($(HAVE_XXHASH),y) BUILD_KLP := y LIBXXHASH_CFLAGS := $(shell $(HOSTPKG_CONFIG) libxxhash --cflags 2>/dev/null) \ From 356e4b2f5b80f757965f3f4d0219c81fca91b6f2 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 4 Mar 2026 19:31:20 -0800 Subject: [PATCH 160/487] objtool: Fix data alignment in elf_add_data() Any data added to a section needs to be aligned in accordance with the section's sh_addralign value. Particularly strings added to a .str1.8 section. Otherwise you may get some funky strings. Fixes: dd590d4d57eb ("objtool/klp: Introduce klp diff subcommand for diffing object files") Link: https://patch.msgid.link/d962fc0ca24fa0825cca8dad71932dccdd9312a9.1772681234.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/elf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 2c02c7b49265..3da90686350d 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -1375,7 +1375,7 @@ void *elf_add_data(struct elf *elf, struct section *sec, const void *data, size_ memcpy(sec->data->d_buf, data, size); sec->data->d_size = size; - sec->data->d_align = 1; + sec->data->d_align = sec->sh.sh_addralign; offset = ALIGN(sec->sh.sh_size, sec->sh.sh_addralign); sec->sh.sh_size = offset + size; From 1fd1dc41724319406b0aff221a352a400b0ddfc5 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 4 Mar 2026 19:31:21 -0800 Subject: [PATCH 161/487] objtool: Fix ERROR_INSN() error message Confusingly, ERROR_INSN() shows "warning:" instead of "error:". Fix that. Link: https://patch.msgid.link/c4fe793bb3d23fac2c636b2511059af1158410e2.1772681234.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/include/objtool/warn.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index 2b27b54096b8..fa8b7d292e83 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -107,7 +107,7 @@ static inline char *offstr(struct section *sec, unsigned long offset) #define ERROR_ELF(format, ...) __WARN_ELF(ERROR_STR, format, ##__VA_ARGS__) #define ERROR_GLIBC(format, ...) __WARN_GLIBC(ERROR_STR, format, ##__VA_ARGS__) #define ERROR_FUNC(sec, offset, format, ...) __WARN_FUNC(ERROR_STR, sec, offset, format, ##__VA_ARGS__) -#define ERROR_INSN(insn, format, ...) WARN_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__) +#define ERROR_INSN(insn, format, ...) ERROR_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__) extern bool debug; extern int indent; From 8ce8d0524c136f60a1bddb0951db2999342d7217 Mon Sep 17 00:00:00 2001 From: Christian Loehle Date: Fri, 6 Mar 2026 10:30:51 +0000 Subject: [PATCH 162/487] sched_ext: Documentation: Mention scheduling class precedence Mention the scheduling class precedence of fair and sched_ext to clear up how sched_ext partial mode works. Signed-off-by: Christian Loehle Acked-by: Andrea Righi Signed-off-by: Tejun Heo --- Documentation/scheduler/sched-ext.rst | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 9e2882d937b4..100d45963781 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -58,7 +58,8 @@ in ``ops->flags``, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE``, and However, when the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and -``SCHED_IDLE`` policies are scheduled by the fair-class scheduler. +``SCHED_IDLE`` policies are scheduled by the fair-class scheduler which has +higher sched_class precedence than ``SCHED_EXT``. Terminating the sched_ext scheduler program, triggering `SysRq-S`, or detection of any internal error including stalled runnable tasks aborts the From 98c790b100764102d877e9339471b8c4c9233f2c Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 6 Mar 2026 02:46:42 -0800 Subject: [PATCH 163/487] workqueue: Rename show_cpu_pool{s,}_hog{s,}() to reflect broadened scope MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit show_cpu_pool_hog() and show_cpu_pools_hogs() no longer only dump CPU hogs — since commit 8823eaef45da ("workqueue: Show all busy workers in stall diagnostics"), they dump every in-flight worker in the pool's busy_hash. Rename them to show_cpu_pool_busy_workers() and show_cpu_pools_busy_workers() to accurately describe what they do. Also fix the pr_info() message to say "stalled worker pools" instead of "stalled CPU-bound worker pools", since sleeping/blocked workers are now included. No functional change. Suggested-by: Tejun Heo Signed-off-by: Breno Leitao Signed-off-by: Tejun Heo --- kernel/workqueue.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 09b9ad78d566..b77119d71641 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -7587,7 +7587,7 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as * effectively as a CPU-bound one, so dump every in-flight worker. */ -static void show_cpu_pool_hog(struct worker_pool *pool) +static void show_cpu_pool_busy_workers(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; @@ -7612,18 +7612,18 @@ static void show_cpu_pool_hog(struct worker_pool *pool) raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } -static void show_cpu_pools_hogs(void) +static void show_cpu_pools_busy_workers(void) { struct worker_pool *pool; int pi; - pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n"); + pr_info("Showing backtraces of busy workers in stalled worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) - show_cpu_pool_hog(pool); + show_cpu_pool_busy_workers(pool); } @@ -7720,7 +7720,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) show_all_workqueues(); if (cpu_pool_stall) - show_cpu_pools_hogs(); + show_cpu_pools_busy_workers(); if (lockup_detected) panic_on_wq_watchdog(max_stall_time); From 1dde502587657045b267f179d7a1ecc7b8a1a265 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 6 Mar 2026 04:50:55 +0000 Subject: [PATCH 164/487] sched_ext: Use READ_ONCE() for scx_slice_bypass_us in scx_bypass() Commit 0927780c90ce ("sched_ext: Use READ_ONCE() for lock-free reads of module param variables") annotated the plain reads of scx_slice_bypass_us and scx_bypass_lb_intv_us in bypass_lb_cpu(), but missed a third site in scx_bypass(): WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC); scx_slice_bypass_us is a module parameter writable via sysfs in process context through set_slice_us() -> param_set_uint_minmax(), which performs a plain store without holding bypass_lock. scx_bypass() reads the variable under bypass_lock, but since the writer does not take that lock, the two accesses are concurrent. WRITE_ONCE() only applies volatile semantics to the store of scx_slice_dfl -- the val expression containing scx_slice_bypass_us is evaluated as a plain read, providing no protection against concurrent writes. Wrap the read with READ_ONCE() to complete the annotation started by commit 0927780c90ce and make the access KCSAN-clean, consistent with the existing READ_ONCE(scx_slice_bypass_us) in bypass_lb_cpu(). Signed-off-by: David Carlier Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 10866bfb88bf..f323df7be180 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4137,7 +4137,7 @@ static void scx_bypass(bool bypass) WARN_ON_ONCE(scx_bypass_depth <= 0); if (scx_bypass_depth != 1) goto unlock; - WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC); + WRITE_ONCE(scx_slice_dfl, READ_ONCE(scx_slice_bypass_us) * NSEC_PER_USEC); bypass_timestamp = ktime_get_ns(); if (sch) scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1); From ca174c705db52db3cc842e754fd25a5f50eb702d Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 5 Mar 2026 14:53:29 -0500 Subject: [PATCH 165/487] cgroup/cpuset: Call rebuild_sched_domains() directly in hotplug Besides deferring the call to housekeeping_update(), commit 6df415aa46ec ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue") also defers the rebuild_sched_domains() call to the workqueue. So a new offline CPU may still be in a sched domain or new online CPU not showing up in the sched domains for a short transition period. That could be a problem in some corner cases and can be the cause of a reported test failure[1]. Fix it by calling rebuild_sched_domains_cpuslocked() directly in hotplug as before. If isolated partition invalidation or recreation is being done, the housekeeping_update() call to update the housekeeping cpumasks will still be deferred to a workqueue. In commit 3bfe47967191 ("cgroup/cpuset: Move housekeeping_update()/rebuild_sched_domains() together"), housekeeping_update() is called before rebuild_sched_domains() because it needs to access the HK_TYPE_DOMAIN housekeeping cpumask. That is now changed to use the static HK_TYPE_DOMAIN_BOOT cpumask as HK_TYPE_DOMAIN cpumask is now changeable at run time. As a result, we can move the rebuild_sched_domains() call before housekeeping_update() with the slight advantage that it will be done in the same cpus_read_lock critical section without the possibility of interference by a concurrent cpu hot add/remove operation. As it doesn't make sense to acquire cpuset_mutex/cpuset_top_mutex after calling housekeeping_update() and immediately release them again, move the cpuset_full_unlock() operation inside update_hk_sched_domains() and rename it to cpuset_update_sd_hk_unlock() to signify that it will release the full set of locks. [1] https://lore.kernel.org/lkml/1a89aceb-48db-4edd-a730-b445e41221fe@nvidia.com Fixes: 6df415aa46ec ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue") Tested-by: Jon Hunter Reviewed-by: Chen Ridong Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 59 ++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 28 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e200de7c60b6..d21868455341 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -879,7 +879,7 @@ static int generate_sched_domains(cpumask_var_t **domains, /* * Cgroup v2 doesn't support domain attributes, just set all of them * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a - * subset of HK_TYPE_DOMAIN housekeeping CPUs. + * subset of HK_TYPE_DOMAIN_BOOT housekeeping CPUs. */ for (i = 0; i < ndoms; i++) { /* @@ -888,7 +888,7 @@ static int generate_sched_domains(cpumask_var_t **domains, */ if (!csa || csa[i] == &top_cpuset) cpumask_and(doms[i], top_cpuset.effective_cpus, - housekeeping_cpumask(HK_TYPE_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)); else cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) @@ -1329,17 +1329,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) } /* - * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains + * cpuset_update_sd_hk_unlock - Rebuild sched domains, update HK & unlock * - * Update housekeeping cpumasks and rebuild sched domains if necessary. - * This should be called at the end of cpuset or hotplug actions. + * Update housekeeping cpumasks and rebuild sched domains if necessary and + * then do a cpuset_full_unlock(). + * This should be called at the end of cpuset operation. */ -static void update_hk_sched_domains(void) +static void cpuset_update_sd_hk_unlock(void) + __releases(&cpuset_mutex) + __releases(&cpuset_top_mutex) { + /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ + if (force_sd_rebuild) + rebuild_sched_domains_locked(); + if (update_housekeeping) { - /* Updating HK cpumasks implies rebuild sched domains */ update_housekeeping = false; - force_sd_rebuild = true; cpumask_copy(isolated_hk_cpus, isolated_cpus); /* @@ -1350,22 +1355,19 @@ static void update_hk_sched_domains(void) mutex_unlock(&cpuset_mutex); cpus_read_unlock(); WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); - cpus_read_lock(); - mutex_lock(&cpuset_mutex); + mutex_unlock(&cpuset_top_mutex); + } else { + cpuset_full_unlock(); } - /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ - if (force_sd_rebuild) - rebuild_sched_domains_locked(); } /* - * Work function to invoke update_hk_sched_domains() + * Work function to invoke cpuset_update_sd_hk_unlock() */ static void hk_sd_workfn(struct work_struct *work) { cpuset_full_lock(); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); } /** @@ -3230,8 +3232,7 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); return retval ?: nbytes; @@ -3338,8 +3339,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, cpuset_full_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); return retval ?: nbytes; } @@ -3513,8 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css) /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) @@ -3923,11 +3922,13 @@ static void cpuset_handle_hotplug(void) rcu_read_unlock(); } - /* - * Queue a work to call housekeeping_update() & rebuild_sched_domains() - * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping - * cpumask can correctly reflect what is in isolated_cpus. + * rebuild_sched_domains() will always be called directly if needed + * to make sure that newly added or removed CPU will be reflected in + * the sched domains. However, if isolated partition invalidation + * or recreation is being done (update_housekeeping set), a work item + * will be queued to call housekeeping_update() to update the + * corresponding housekeeping cpumasks after some slight delay. * * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that * is still pending. Before the pending bit is cleared, the work data @@ -3936,8 +3937,10 @@ static void cpuset_handle_hotplug(void) * previously queued work. Since hk_sd_workfn() doesn't use the work * item at all, this is not a problem. */ - if (update_housekeeping || force_sd_rebuild) - queue_work(system_unbound_wq, &hk_sd_work); + if (force_sd_rebuild) + rebuild_sched_domains_cpuslocked(); + if (update_housekeeping) + queue_work(system_dfl_wq, &hk_sd_work); free_tmpmasks(ptmp); } From e4eb11b34d6c84f398d8f08d7cb4d6c38e739dd2 Mon Sep 17 00:00:00 2001 From: Pengyu Luo Date: Sat, 7 Mar 2026 00:32:38 +0800 Subject: [PATCH 166/487] drm/msm/dsi: fix pclk rate calculation for bonded dsi Recently, we round up new_hdisplay once at most, for bonded dsi, we may need twice, since they are independent links, we should round up each half separately. This also aligns with the hdisplay we program later in dsi_timing_setup() Example: full_hdisplay = 1904, dsc_bpp = 8, bpc = 8 new_full_hdisplay = DIV_ROUND_UP(1904 * 8, 8 * 3) = 635 if we use half display new_half_hdisplay = DIV_ROUND_UP(952 * 8, 8 * 3) = 318 new_full_display = 636 Fixes: 7c9e4a554d4a ("drm/msm/dsi: Reduce pclk rate for compression") Signed-off-by: Pengyu Luo Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/709716/ Link: https://lore.kernel.org/r/20260306163255.215456-1-mitltlatltl@gmail.com Signed-off-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/dsi/dsi_host.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index e8e83ee61eb0..db6da99375a1 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -584,13 +584,30 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host) * FIXME: Reconsider this if/when CMD mode handling is rewritten to use * transfer time and data overhead as a starting point of the calculations. */ -static unsigned long dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode, - const struct drm_dsc_config *dsc) +static unsigned long +dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode, + const struct drm_dsc_config *dsc, + bool is_bonded_dsi) { - int new_hdisplay = DIV_ROUND_UP(mode->hdisplay * drm_dsc_get_bpp_int(dsc), - dsc->bits_per_component * 3); + int hdisplay, new_hdisplay, new_htotal; - int new_htotal = mode->htotal - mode->hdisplay + new_hdisplay; + /* + * For bonded DSI, split hdisplay across two links and round up each + * half separately, passing the full hdisplay would only round up once. + * This also aligns with the hdisplay we program later in + * dsi_timing_setup() + */ + hdisplay = mode->hdisplay; + if (is_bonded_dsi) + hdisplay /= 2; + + new_hdisplay = DIV_ROUND_UP(hdisplay * drm_dsc_get_bpp_int(dsc), + dsc->bits_per_component * 3); + + if (is_bonded_dsi) + new_hdisplay *= 2; + + new_htotal = mode->htotal - mode->hdisplay + new_hdisplay; return mult_frac(mode->clock * 1000u, new_htotal, mode->htotal); } @@ -603,7 +620,7 @@ static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode, pclk_rate = mode->clock * 1000u; if (dsc) - pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc); + pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc, is_bonded_dsi); /* * For bonded DSI mode, the current DRM mode has the complete width of the From 0e16181704e37330069c24cea143f15b7b298da3 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Thu, 5 Mar 2026 09:28:05 -0800 Subject: [PATCH 167/487] MAINTAINERS: Remove bouncing T7XX reviewer This reviewer's email no longer works. Remove it from MAINTAINERS. Cc: Chandrashekar Devegowda Cc: Liu Haijun Cc: Ricardo Martinez Cc: Sergey Ryazanov Cc: Johannes Berg Cc: Andrew Lunn Signed-off-by: Dave Hansen Reviewed-by: Loic Poulain Link: https://patch.msgid.link/20260305172806.3118806-1-dave.hansen@linux.intel.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7b277d5bf3d1..4f8e772808c7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16358,7 +16358,6 @@ F: net/dsa/tag_mtk.c MEDIATEK T7XX 5G WWAN MODEM DRIVER M: Chandrashekar Devegowda -R: Chiranjeevi Rapolu R: Liu Haijun R: Ricardo Martinez L: netdev@vger.kernel.org From cb47c882c31334aadc13ace80781728ed22a05ee Mon Sep 17 00:00:00 2001 From: Yang Wang Date: Tue, 3 Mar 2026 21:10:11 -0500 Subject: [PATCH 168/487] drm/amd/pm: add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v13 add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v13.0.0/13.0.7 Fixes: cfffd980bf21 ("drm/amd/pm: add zero RPM OD setting support for SMU13") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5018 Signed-off-by: Yang Wang Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 576a10797b607ee9e4068218daf367b481564120) --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 3 ++- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index b32c053950c9..a8d63d4d1f6e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2222,7 +2222,8 @@ static int smu_v13_0_0_restore_user_od_settings(struct smu_context *smu) user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) | BIT(PP_OD_FEATURE_UCLK_BIT) | BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) | - BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + BIT(PP_OD_FEATURE_FAN_CURVE_BIT) | + BIT(PP_OD_FEATURE_ZERO_FAN_BIT); res = smu_v13_0_0_upload_overdrive_table(smu, user_od_table); user_od_table->OverDriveTable.FeatureCtrlMask = 0; if (res == 0) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index f08cfa510a8a..5500a0f12f0e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2224,7 +2224,8 @@ static int smu_v13_0_7_restore_user_od_settings(struct smu_context *smu) user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) | BIT(PP_OD_FEATURE_UCLK_BIT) | BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) | - BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + BIT(PP_OD_FEATURE_FAN_CURVE_BIT) | + BIT(PP_OD_FEATURE_ZERO_FAN_BIT); res = smu_v13_0_7_upload_overdrive_table(smu, user_od_table); user_od_table->OverDriveTable.FeatureCtrlMask = 0; if (res == 0) From 9d4837a26149355ffe3a1f80de80531eafdd3353 Mon Sep 17 00:00:00 2001 From: Yang Wang Date: Tue, 3 Mar 2026 21:14:10 -0500 Subject: [PATCH 169/487] drm/amd/pm: add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v14 add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v14.0.2/14.0.3 Fixes: 9710b84e2a6a ("drm/amd/pm: add overdrive support on smu v14.0.2/3") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5018 Signed-off-by: Yang Wang Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 1b5cf07d80bb16d1593579ccdb23f08ea4262c14) --- drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 9994d4369da8..73762d9b5969 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -2311,7 +2311,8 @@ static int smu_v14_0_2_restore_user_od_settings(struct smu_context *smu) user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) | BIT(PP_OD_FEATURE_UCLK_BIT) | BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) | - BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + BIT(PP_OD_FEATURE_FAN_CURVE_BIT) | + BIT(PP_OD_FEATURE_ZERO_FAN_BIT); res = smu_v14_0_2_upload_overdrive_table(smu, user_od_table); user_od_table->OverDriveTable.FeatureCtrlMask = 0; if (res == 0) From 062ea905fff7756b2e87143ffccaece5cdb44267 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 4 Mar 2026 14:07:40 -0600 Subject: [PATCH 170/487] drm/amd: Fix NULL pointer dereference in device cleanup When GPU initialization fails due to an unsupported HW block IP blocks may have a NULL version pointer. During cleanup in amdgpu_device_fini_hw, the code calls amdgpu_device_set_pg_state and amdgpu_device_set_cg_state which iterate over all IP blocks and access adev->ip_blocks[i].version without NULL checks, leading to a kernel NULL pointer dereference. Add NULL checks for adev->ip_blocks[i].version in both amdgpu_device_set_cg_state and amdgpu_device_set_pg_state to prevent dereferencing NULL pointers during GPU teardown when initialization has failed. Fixes: 39fc2bc4da00 ("drm/amdgpu: Protect GPU register accesses in powergated state in some paths") Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit b7ac77468cda92eecae560b05f62f997a12fe2f2) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3e19b51a2763..10b10bac8b18 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3247,6 +3247,8 @@ int amdgpu_device_set_cg_state(struct amdgpu_device *adev, i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + if (!adev->ip_blocks[i].version) + continue; /* skip CG for GFX, SDMA on S0ix */ if (adev->in_s0ix && (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || @@ -3286,6 +3288,8 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + if (!adev->ip_blocks[i].version) + continue; /* skip PG for GFX, SDMA on S0ix */ if (adev->in_s0ix && (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || From 52289ce48ef1f8a81cd39df1574098356e3c9d4c Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Thu, 5 Mar 2026 13:16:36 +0200 Subject: [PATCH 171/487] drm/amdgpu: Fix kernel-doc comments for some LUT properties The following members of struct amdgpu_mode_info do not have valid references in the related kernel-doc sections: - plane_shaper_lut_property - plane_shaper_lut_size_property, - plane_lut3d_size_property Correct all affected comment blocks. Fixes: f545d82479b4 ("drm/amd/display: add plane shaper LUT and TF driver-specific properties") Fixes: 671994e3bf33 ("drm/amd/display: add plane 3D LUT driver-specific properties") Reviewed-by: Melissa Wen Signed-off-by: Cristian Ciocaltea Signed-off-by: Alex Deucher (cherry picked from commit ec5708d6e547f7efe2f009073bfa98dbc4c5c2ac) --- drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index dc8d2f52c7d6..e244c12ceb23 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -368,15 +368,15 @@ struct amdgpu_mode_info { struct drm_property *plane_ctm_property; /** - * @shaper_lut_property: Plane property to set pre-blending shaper LUT - * that converts color content before 3D LUT. If - * plane_shaper_tf_property != Identity TF, AMD color module will + * @plane_shaper_lut_property: Plane property to set pre-blending + * shaper LUT that converts color content before 3D LUT. + * If plane_shaper_tf_property != Identity TF, AMD color module will * combine the user LUT values with pre-defined TF into the LUT * parameters to be programmed. */ struct drm_property *plane_shaper_lut_property; /** - * @shaper_lut_size_property: Plane property for the size of + * @plane_shaper_lut_size_property: Plane property for the size of * pre-blending shaper LUT as supported by the driver (read-only). */ struct drm_property *plane_shaper_lut_size_property; @@ -400,10 +400,10 @@ struct amdgpu_mode_info { */ struct drm_property *plane_lut3d_property; /** - * @plane_degamma_lut_size_property: Plane property to define the max - * size of 3D LUT as supported by the driver (read-only). The max size - * is the max size of one dimension and, therefore, the max number of - * entries for 3D LUT array is the 3D LUT size cubed; + * @plane_lut3d_size_property: Plane property to define the max size + * of 3D LUT as supported by the driver (read-only). The max size is + * the max size of one dimension and, therefore, the max number of + * entries for 3D LUT array is the 3D LUT size cubed. */ struct drm_property *plane_lut3d_size_property; /** From a6571045cf06c4aa749b4801382ae96650e2f0e1 Mon Sep 17 00:00:00 2001 From: Yang Wang Date: Wed, 4 Mar 2026 18:45:45 -0500 Subject: [PATCH 172/487] drm/amdgpu: fix gpu idle power consumption issue for gfx v12 Older versions of the MES firmware may cause abnormal GPU power consumption. When performing inference tasks on the GPU (e.g., with Ollama using ROCm), the GPU may show abnormal power consumption in idle state and incorrect GPU load information. This issue has been fixed in firmware version 0x8b and newer. Closes: https://github.com/ROCm/ROCm/issues/5706 Signed-off-by: Yang Wang Acked-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 4e22a5fe6ea6e0b057e7f246df4ac3ff8bfbc46a) --- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 5bfa5d1d0b36..023c7345ea54 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -731,6 +731,9 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) int i; struct amdgpu_device *adev = mes->adev; union MESAPI_SET_HW_RESOURCES mes_set_hw_res_pkt; + uint32_t mes_rev = (pipe == AMDGPU_MES_SCHED_PIPE) ? + (mes->sched_version & AMDGPU_MES_VERSION_MASK) : + (mes->kiq_version & AMDGPU_MES_VERSION_MASK); memset(&mes_set_hw_res_pkt, 0, sizeof(mes_set_hw_res_pkt)); @@ -785,7 +788,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) * handling support, other queue will not use the oversubscribe timer. * handling mode - 0: disabled; 1: basic version; 2: basic+ version */ - mes_set_hw_res_pkt.oversubscription_timer = 50; + mes_set_hw_res_pkt.oversubscription_timer = mes_rev < 0x8b ? 0 : 50; mes_set_hw_res_pkt.unmapped_doorbell_handling = 1; if (amdgpu_mes_log_enable) { From 72ecb1dae72775fa9fea0159d8445d620a0a2295 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 5 Mar 2026 09:06:11 -0600 Subject: [PATCH 173/487] drm/amd: Fix a few more NULL pointer dereference in device cleanup I found a few more paths that cleanup fails due to a NULL version pointer on unsupported hardware. Add NULL checks as applicable. Fixes: 39fc2bc4da00 ("drm/amdgpu: Protect GPU register accesses in powergated state in some paths") Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit f5a05f8414fc10f307eb965f303580c7778f8dd2) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 10b10bac8b18..761ee5ebb4f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3497,6 +3497,8 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev) int i, r; for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_blocks[i].version) + continue; if (!adev->ip_blocks[i].version->funcs->early_fini) continue; @@ -3574,6 +3576,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) if (!adev->ip_blocks[i].status.sw) continue; + if (!adev->ip_blocks[i].version) + continue; if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { amdgpu_ucode_free_bo(adev); amdgpu_free_static_csa(&adev->virt.csa_obj); @@ -3600,6 +3604,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.late_initialized) continue; + if (!adev->ip_blocks[i].version) + continue; if (adev->ip_blocks[i].version->funcs->late_fini) adev->ip_blocks[i].version->funcs->late_fini(&adev->ip_blocks[i]); adev->ip_blocks[i].status.late_initialized = false; From 2a0596d516870951ce0e8edf510e48c87cb80761 Mon Sep 17 00:00:00 2001 From: Cheng-Yang Chou Date: Sat, 7 Mar 2026 02:21:01 +0800 Subject: [PATCH 174/487] sched_ext: Documentation: Update sched-ext.rst - Remove CONFIG_PAHOLE_HAS_BTF_TAG from required config list - Document ext_idle.c as the built-in idle CPU selection policy - Add descriptions for example schedulers in tools/sched_ext/ Signed-off-by: Cheng-Yang Chou Signed-off-by: Tejun Heo --- Documentation/scheduler/sched-ext.rst | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 100d45963781..d74c2c2b9ef3 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -43,7 +43,6 @@ options should be enabled to use sched_ext: CONFIG_DEBUG_INFO_BTF=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT_DEFAULT_ON=y - CONFIG_PAHOLE_HAS_BTF_TAG=y sched_ext is used only when the BPF scheduler is loaded and running. @@ -346,6 +345,8 @@ Where to Look The functions prefixed with ``scx_bpf_`` can be called from the BPF scheduler. +* ``kernel/sched/ext_idle.c`` contains the built-in idle CPU selection policy. + * ``tools/sched_ext/`` hosts example BPF scheduler implementations. * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a @@ -354,13 +355,35 @@ Where to Look * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``. + * ``scx_central[.bpf].c``: A central FIFO scheduler where all scheduling + decisions are made on one CPU, demonstrating ``LOCAL_ON`` dispatching, + tickless operation, and kthread preemption. + + * ``scx_cpu0[.bpf].c``: A scheduler that queues all tasks to a shared DSQ + and only dispatches them on CPU0 in FIFO order. Useful for testing bypass + behavior. + + * ``scx_flatcg[.bpf].c``: A flattened cgroup hierarchy scheduler + implementing hierarchical weight-based cgroup CPU control by compounding + each cgroup's share at every level into a single flat scheduling layer. + + * ``scx_pair[.bpf].c``: A core-scheduling example that always makes + sibling CPU pairs execute tasks from the same CPU cgroup. + + * ``scx_sdt[.bpf].c``: A variation of ``scx_simple`` demonstrating BPF + arena memory management for per-task data. + + * ``scx_userland[.bpf].c``: A minimal scheduler demonstrating user space + scheduling. Tasks with CPU affinity are direct-dispatched in FIFO order; + all others are scheduled in user space by a simple vruntime scheduler. + ABI Instability =============== The APIs provided by sched_ext to BPF schedulers programs have no stability guarantees. This includes the ops table callbacks and constants defined in ``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in -``kernel/sched/ext.c``. +``kernel/sched/ext.c`` and ``kernel/sched/ext_idle.c``. While we will attempt to provide a relatively stable API surface when possible, they are subject to change without warning between kernel From a72f73c4dd9b209c53cf8b03b6e97fcefad4262c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 6 Mar 2026 20:22:35 +0100 Subject: [PATCH 175/487] cgroup: Don't expose dead tasks in cgroup Once a task exits it has its state set to TASK_DEAD and then it is removed from the cgroup it belonged to. The last step happens on the task gets out of its last schedule() invocation and is delayed on PREEMPT_RT due to locking constraints. As a result it is possible to receive a pid via waitpid() of a task which is still listed in cgroup.procs for the cgroup it belonged to. This is something that systemd does not expect and as a result it waits for its exit until a time out occurs. This can also be reproduced on !PREEMPT_RT kernel with a significant delay in do_exit() after exit_notify(). Hide the task from the output which have PF_EXITING set which is done before the parent is notified. Keeping zombies with live threads shouldn't break anything (suggested by Tejun). Reported-by: Bert Karwatzki Closes: https://lore.kernel.org/all/20260219164648.3014-1-spasswolf@web.de/ Tested-by: Bert Karwatzki Fixes: 9311e6c29b34 ("cgroup: Fix sleeping from invalid context warning on PREEMPT_RT") Cc: stable@vger.kernel.org # v6.19+ Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index be1d71dda317..01fc2a93f3ef 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5109,6 +5109,12 @@ static void css_task_iter_advance(struct css_task_iter *it) return; task = list_entry(it->task_pos, struct task_struct, cg_list); + /* + * Hide tasks that are exiting but not yet removed. Keep zombie + * leaders with live threads visible. + */ + if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) + goto repeat; if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ From 224a0d284c3caf1951302d1744a714784febed71 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 5 Mar 2026 11:45:49 +0100 Subject: [PATCH 176/487] net: mctp: fix device leak on probe failure Driver core holds a reference to the USB interface and its parent USB device while the interface is bound to a driver and there is no need to take additional references unless the structures are needed after disconnect. This driver takes a reference to the USB device during probe but does not to release it on probe failures. Drop the redundant device reference to fix the leak, reduce cargo culting, make it easier to spot drivers where an extra reference is needed, and reduce the risk of further memory leaks. Fixes: 0791c0327a6e ("net: mctp: Add MCTP USB transport driver") Cc: stable@vger.kernel.org # 6.15 Signed-off-by: Johan Hovold Acked-by: Jeremy Kerr Link: https://patch.msgid.link/20260305104549.16110-1-johan@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/mctp/mctp-usb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c index ef860cfc629f..3b5dff144177 100644 --- a/drivers/net/mctp/mctp-usb.c +++ b/drivers/net/mctp/mctp-usb.c @@ -329,7 +329,7 @@ static int mctp_usb_probe(struct usb_interface *intf, SET_NETDEV_DEV(netdev, &intf->dev); dev = netdev_priv(netdev); dev->netdev = netdev; - dev->usbdev = usb_get_dev(interface_to_usbdev(intf)); + dev->usbdev = interface_to_usbdev(intf); dev->intf = intf; usb_set_intfdata(intf, dev); @@ -365,7 +365,6 @@ static void mctp_usb_disconnect(struct usb_interface *intf) mctp_unregister_netdev(dev->netdev); usb_free_urb(dev->tx_urb); usb_free_urb(dev->rx_urb); - usb_put_dev(dev->usbdev); free_netdev(dev->netdev); } From 45fc134bcfadde456639c1b1e206e6918d69a553 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 4 Mar 2026 15:13:53 +0800 Subject: [PATCH 177/487] bonding: do not set usable_slaves for broadcast mode After commit e0caeb24f538 ("net: bonding: update the slave array for broadcast mode"), broadcast mode will also set all_slaves and usable_slaves during bond_enslave(). But if we also set updelay, during enslave, the slave init state will be BOND_LINK_BACK. And later bond_update_slave_arr() will alloc usable_slaves but add nothing. This will cause bond_miimon_inspect() to have ignore_updelay always true. So the updelay will be always ignored. e.g. [ 6.498368] bond0: (slave veth2): link status definitely down, disabling slave [ 7.536371] bond0: (slave veth2): link status up, enabling it in 0 ms [ 7.536402] bond0: (slave veth2): link status definitely up, 10000 Mbps full duplex To fix it, we can either always call bond_update_slave_arr() on every place when link changes. Or, let's just not set usable_slaves for broadcast mode. Fixes: e0caeb24f538 ("net: bonding: update the slave array for broadcast mode") Reported-by: Liang Li Signed-off-by: Hangbin Liu Link: https://patch.msgid.link/20260304-b4-bond_updelay-v1-1-f72eb2e454d0@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 14ed91391fcc..93a32a368d31 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5069,13 +5069,18 @@ static void bond_set_slave_arr(struct bonding *bond, { struct bond_up_slave *usable, *all; - usable = rtnl_dereference(bond->usable_slaves); - rcu_assign_pointer(bond->usable_slaves, usable_slaves); - kfree_rcu(usable, rcu); - all = rtnl_dereference(bond->all_slaves); rcu_assign_pointer(bond->all_slaves, all_slaves); kfree_rcu(all, rcu); + + if (BOND_MODE(bond) == BOND_MODE_BROADCAST) { + kfree_rcu(usable_slaves, rcu); + return; + } + + usable = rtnl_dereference(bond->usable_slaves); + rcu_assign_pointer(bond->usable_slaves, usable_slaves); + kfree_rcu(usable, rcu); } static void bond_reset_slave_arr(struct bonding *bond) From 3348be7978f450ede0c308a4e8416ac716cf1015 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 4 Mar 2026 15:13:54 +0800 Subject: [PATCH 178/487] bonding: handle BOND_LINK_FAIL, BOND_LINK_BACK as valid link states Before the fixed commit, we check slave->new_link during commit state, which values are only BOND_LINK_{NOCHANGE, UP, DOWN}. After the commit, we start using slave->link_new_state, which state also could be BOND_LINK_{FAIL, BACK}. For example, when we set updelay/downdelay, after a failover, the slave->link_new_state could be set to BOND_LINK_{FAIL, BACK} in bond_miimon_inspect(). And later in bond_miimon_commit(), it will treat it as invalid and print an error, which would cause confusion for users. [ 106.440254] bond0: (slave veth2): link status down for interface, disabling it in 200 ms [ 106.440265] bond0: (slave veth2): invalid new link 1 on slave [ 106.648276] bond0: (slave veth2): link status definitely down, disabling slave [ 107.480271] bond0: (slave veth2): link status up, enabling it in 200 ms [ 107.480288] bond0: (slave veth2): invalid new link 3 on slave [ 107.688302] bond0: (slave veth2): link status definitely up, 10000 Mbps full duplex Let's handle BOND_LINK_{FAIL, BACK} as valid link states. Fixes: 1899bb325149 ("bonding: fix state transition issue in link monitoring") Signed-off-by: Hangbin Liu Link: https://patch.msgid.link/20260304-b4-bond_updelay-v1-2-f72eb2e454d0@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 93a32a368d31..444519078da3 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2801,8 +2801,14 @@ static void bond_miimon_commit(struct bonding *bond) continue; + case BOND_LINK_FAIL: + case BOND_LINK_BACK: + slave_dbg(bond->dev, slave->dev, "link_new_state %d on slave\n", + slave->link_new_state); + continue; + default: - slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", + slave_err(bond->dev, slave->dev, "invalid link_new_state %d on slave\n", slave->link_new_state); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); From 55f854dd5bdd8e19b936a00ef1f8d776ac32c7b0 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Wed, 4 Mar 2026 14:43:38 +0100 Subject: [PATCH 179/487] qmi_wwan: allow max_mtu above hard_mtu to control rx_urb_size Commit c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu") capped net->max_mtu to the device's hard_mtu in usbnet_probe(). While this correctly prevents oversized packets on standard USB network devices, it breaks the qmi_wwan driver. qmi_wwan relies on userspace (e.g. ModemManager) setting a large MTU on the wwan0 interface to configure rx_urb_size via usbnet_change_mtu(). QMI modems negotiate USB transfer sizes of 16,383 or 32,767 bytes, and the USB receive buffers must be sized accordingly. With max_mtu capped to hard_mtu (~1500 bytes), userspace can no longer raise the MTU, the receive buffers remain small, and download speeds drop from >300 Mbps to ~0.8 Mbps. Introduce a FLAG_NOMAXMTU driver flag that allows individual usbnet drivers to opt out of the max_mtu cap. Set this flag in qmi_wwan's driver_info structures to restore the previous behavior for QMI devices, while keeping the safety fix in place for all other usbnet drivers. Fixes: c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/lkml/CAPh3n803k8JcBPV5qEzUB-oKzWkAs-D5CU7z=Vd_nLRCr5ZqQg@mail.gmail.com/ Reported-by: Koen Vandeputte Tested-by: Daniele Palmas Signed-off-by: Laurent Vivier Link: https://patch.msgid.link/20260304134338.1785002-1-lvivier@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/qmi_wwan.c | 4 ++-- drivers/net/usb/usbnet.c | 7 ++++--- include/linux/usb/usbnet.h | 1 + 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3a4985b582cb..05acac10cd2b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -928,7 +928,7 @@ static int qmi_wwan_resume(struct usb_interface *intf) static const struct driver_info qmi_wwan_info = { .description = "WWAN/QMI device", - .flags = FLAG_WWAN | FLAG_SEND_ZLP, + .flags = FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP, .bind = qmi_wwan_bind, .unbind = qmi_wwan_unbind, .manage_power = qmi_wwan_manage_power, @@ -937,7 +937,7 @@ static const struct driver_info qmi_wwan_info = { static const struct driver_info qmi_wwan_info_quirk_dtr = { .description = "WWAN/QMI device", - .flags = FLAG_WWAN | FLAG_SEND_ZLP, + .flags = FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP, .bind = qmi_wwan_bind, .unbind = qmi_wwan_unbind, .manage_power = qmi_wwan_manage_power, diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index ed86ba87ca4e..b72ba0803392 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1829,11 +1829,12 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) if ((dev->driver_info->flags & FLAG_NOARP) != 0) net->flags |= IFF_NOARP; - if (net->max_mtu > (dev->hard_mtu - net->hard_header_len)) + if ((dev->driver_info->flags & FLAG_NOMAXMTU) == 0 && + net->max_mtu > (dev->hard_mtu - net->hard_header_len)) net->max_mtu = dev->hard_mtu - net->hard_header_len; - if (net->mtu > net->max_mtu) - net->mtu = net->max_mtu; + if (net->mtu > (dev->hard_mtu - net->hard_header_len)) + net->mtu = dev->hard_mtu - net->hard_header_len; } else if (!info->in || !info->out) status = usbnet_get_endpoints(dev, udev); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index b0e84896e6ac..bbf799ccf3b3 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -132,6 +132,7 @@ struct driver_info { #define FLAG_MULTI_PACKET 0x2000 #define FLAG_RX_ASSEMBLE 0x4000 /* rx packets may span >1 frames */ #define FLAG_NOARP 0x8000 /* device can't do ARP */ +#define FLAG_NOMAXMTU 0x10000 /* allow max_mtu above hard_mtu */ /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); From aed763abf0e905b4b8d747d1ba9e172961572f57 Mon Sep 17 00:00:00 2001 From: Cosmin Ratiu Date: Thu, 5 Mar 2026 10:10:19 +0200 Subject: [PATCH 180/487] net/mlx5: Fix deadlock between devlink lock and esw->wq esw->work_queue executes esw_functions_changed_event_handler -> esw_vfs_changed_event_handler and acquires the devlink lock. .eswitch_mode_set (acquires devlink lock in devlink_nl_pre_doit) -> mlx5_devlink_eswitch_mode_set -> mlx5_eswitch_disable_locked -> mlx5_eswitch_event_handler_unregister -> flush_workqueue deadlocks when esw_vfs_changed_event_handler executes. Fix that by no longer flushing the work to avoid the deadlock, and using a generation counter to keep track of work relevance. This avoids an old handler manipulating an esw that has undergone one or more mode changes: - the counter is incremented in mlx5_eswitch_event_handler_unregister. - the counter is read and passed to the ephemeral mlx5_host_work struct. - the work handler takes the devlink lock and bails out if the current generation is different than the one it was scheduled to operate on. - mlx5_eswitch_cleanup does the final draining before destroying the wq. No longer flushing the workqueue has the side effect of maybe no longer cancelling pending vport_change_handler work items, but that's ok since those are disabled elsewhere: - mlx5_eswitch_disable_locked disables the vport eq notifier. - mlx5_esw_vport_disable disarms the HW EQ notification and marks vport->enabled under state_lock to false to prevent pending vport handler from doing anything. - mlx5_eswitch_cleanup destroys the workqueue and makes sure all events are disabled/finished. Fixes: f1bc646c9a06 ("net/mlx5: Use devl_ API in mlx5_esw_offloads_devlink_port_register") Signed-off-by: Cosmin Ratiu Reviewed-by: Moshe Shemesh Reviewed-by: Dragos Tatulea Reviewed-by: Simon Horman Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260305081019.1811100-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 7 ++++--- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 ++ .../mellanox/mlx5/core/eswitch_offloads.c | 18 +++++++++++++----- 3 files changed, 19 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d3af87a94a18..123c96716a54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1072,10 +1072,11 @@ static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw) static void mlx5_eswitch_event_handler_unregister(struct mlx5_eswitch *esw) { - if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) + if (esw->mode == MLX5_ESWITCH_OFFLOADS && + mlx5_eswitch_is_funcs_handler(esw->dev)) { mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb); - - flush_workqueue(esw->work_queue); + atomic_inc(&esw->esw_funcs.generation); + } } static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 6841caef02d1..c2563bee74df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -335,10 +335,12 @@ struct esw_mc_addr { /* SRIOV only */ struct mlx5_host_work { struct work_struct work; struct mlx5_eswitch *esw; + int work_gen; }; struct mlx5_esw_functions { struct mlx5_nb nb; + atomic_t generation; bool host_funcs_disabled; u16 num_vfs; u16 num_ec_vfs; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1366f6e489bd..8c5e48d001be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3582,22 +3582,28 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) } static void -esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out) +esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, int work_gen, + const u32 *out) { struct devlink *devlink; bool host_pf_disabled; u16 new_num_vfs; + devlink = priv_to_devlink(esw->dev); + devl_lock(devlink); + + /* Stale work from one or more mode changes ago. Bail out. */ + if (work_gen != atomic_read(&esw->esw_funcs.generation)) + goto unlock; + new_num_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_num_of_vfs); host_pf_disabled = MLX5_GET(query_esw_functions_out, out, host_params_context.host_pf_disabled); if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled) - return; + goto unlock; - devlink = priv_to_devlink(esw->dev); - devl_lock(devlink); /* Number of VFs can only change from "0 to x" or "x to 0". */ if (esw->esw_funcs.num_vfs > 0) { mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs); @@ -3612,6 +3618,7 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out) } } esw->esw_funcs.num_vfs = new_num_vfs; +unlock: devl_unlock(devlink); } @@ -3628,7 +3635,7 @@ static void esw_functions_changed_event_handler(struct work_struct *work) if (IS_ERR(out)) goto out; - esw_vfs_changed_event_handler(esw, out); + esw_vfs_changed_event_handler(esw, host_work->work_gen, out); kvfree(out); out: kfree(host_work); @@ -3648,6 +3655,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs); host_work->esw = esw; + host_work->work_gen = atomic_read(&esw_funcs->generation); INIT_WORK(&host_work->work, esw_functions_changed_event_handler); queue_work(esw->work_queue, &host_work->work); From 24b2795f9683e092dc22a68f487e7aaaf2ddafea Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 5 Mar 2026 16:26:30 +0200 Subject: [PATCH 181/487] net/mlx5: Fix crash when moving to switchdev mode When moving to switchdev mode when the device doesn't support IPsec, we try to clean up the IPsec resources anyway which causes the crash below, fix that by correctly checking for IPsec support before trying to clean up its resources. [27642.515799] WARNING: arch/x86/mm/fault.c:1276 at do_user_addr_fault+0x18a/0x680, CPU#4: devlink/6490 [27642.517159] Modules linked in: xt_conntrack xt_MASQUERADE ip6table_nat ip6table_filter ip6_tables iptable_nat nf_nat xt_addrtype rpcsec_gss_krb5 auth_rpcgss oid_registry overlay mlx5_fwctl nfnetlink zram zsmalloc mlx5_ib fuse rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_core ib_core [27642.521358] CPU: 4 UID: 0 PID: 6490 Comm: devlink Not tainted 6.19.0-rc5_for_upstream_min_debug_2026_01_14_16_47 #1 NONE [27642.522923] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 [27642.524528] RIP: 0010:do_user_addr_fault+0x18a/0x680 [27642.525362] Code: ff 0f 84 75 03 00 00 48 89 ee 4c 89 e7 e8 5e b9 22 00 49 89 c0 48 85 c0 0f 84 a8 02 00 00 f7 c3 60 80 00 00 74 22 31 c9 eb ae <0f> 0b 48 83 c4 10 48 89 ea 48 89 de 4c 89 f7 5b 5d 41 5c 41 5d 41 [27642.528166] RSP: 0018:ffff88810770f6b8 EFLAGS: 00010046 [27642.529038] RAX: 0000000000000000 RBX: 0000000000000002 RCX: ffff88810b980f00 [27642.530158] RDX: 00000000000000a0 RSI: 0000000000000002 RDI: ffff88810770f728 [27642.531270] RBP: 00000000000000a0 R08: 0000000000000000 R09: 0000000000000000 [27642.532383] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888103f3c4c0 [27642.533499] R13: 0000000000000000 R14: ffff88810770f728 R15: 0000000000000000 [27642.534614] FS: 00007f197c741740(0000) GS:ffff88856a94c000(0000) knlGS:0000000000000000 [27642.535915] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [27642.536858] CR2: 00000000000000a0 CR3: 000000011334c003 CR4: 0000000000172eb0 [27642.537982] Call Trace: [27642.538466] [27642.538907] exc_page_fault+0x76/0x140 [27642.539583] asm_exc_page_fault+0x22/0x30 [27642.540282] RIP: 0010:_raw_spin_lock_irqsave+0x10/0x30 [27642.541134] Code: 07 85 c0 75 11 ba ff 00 00 00 f0 0f b1 17 75 06 b8 01 00 00 00 c3 31 c0 c3 90 0f 1f 44 00 00 53 9c 5b fa 31 c0 ba 01 00 00 00 0f b1 17 75 05 48 89 d8 5b c3 89 c6 e8 7e 02 00 00 48 89 d8 5b [27642.543936] RSP: 0018:ffff88810770f7d8 EFLAGS: 00010046 [27642.544803] RAX: 0000000000000000 RBX: 0000000000000202 RCX: ffff888113ad96d8 [27642.545916] RDX: 0000000000000001 RSI: ffff88810770f818 RDI: 00000000000000a0 [27642.547027] RBP: 0000000000000098 R08: 0000000000000400 R09: ffff88810b980f00 [27642.548140] R10: 0000000000000001 R11: ffff888101845a80 R12: 00000000000000a8 [27642.549263] R13: ffffffffa02a9060 R14: 00000000000000a0 R15: ffff8881130d8a40 [27642.550379] complete_all+0x20/0x90 [27642.551010] mlx5e_ipsec_disable_events+0xb6/0xf0 [mlx5_core] [27642.552022] mlx5e_nic_disable+0x12d/0x220 [mlx5_core] [27642.552929] mlx5e_detach_netdev+0x66/0xf0 [mlx5_core] [27642.553822] mlx5e_netdev_change_profile+0x5b/0x120 [mlx5_core] [27642.554821] mlx5e_vport_rep_load+0x419/0x590 [mlx5_core] [27642.555757] ? xa_load+0x53/0x90 [27642.556361] __esw_offloads_load_rep+0x54/0x70 [mlx5_core] [27642.557328] mlx5_esw_offloads_rep_load+0x45/0xd0 [mlx5_core] [27642.558320] esw_offloads_enable+0xb4b/0xc90 [mlx5_core] [27642.559247] mlx5_eswitch_enable_locked+0x34e/0x4f0 [mlx5_core] [27642.560257] ? mlx5_rescan_drivers_locked+0x222/0x2d0 [mlx5_core] [27642.561284] mlx5_devlink_eswitch_mode_set+0x5ac/0x9c0 [mlx5_core] [27642.562334] ? devlink_rate_set_ops_supported+0x21/0x3a0 [27642.563220] devlink_nl_eswitch_set_doit+0x67/0xe0 [27642.564026] genl_family_rcv_msg_doit+0xe0/0x130 [27642.564816] genl_rcv_msg+0x183/0x290 [27642.565466] ? __devlink_nl_pre_doit.isra.0+0x160/0x160 [27642.566329] ? devlink_nl_eswitch_get_doit+0x290/0x290 [27642.567181] ? devlink_nl_pre_doit_parent_dev_optional+0x20/0x20 [27642.568147] ? genl_family_rcv_msg_dumpit+0xf0/0xf0 [27642.568966] netlink_rcv_skb+0x4b/0xf0 [27642.569629] genl_rcv+0x24/0x40 [27642.570215] netlink_unicast+0x255/0x380 [27642.570901] ? __alloc_skb+0xfa/0x1e0 [27642.571560] netlink_sendmsg+0x1f3/0x420 [27642.572249] __sock_sendmsg+0x38/0x60 [27642.572911] __sys_sendto+0x119/0x180 [27642.573561] ? __sys_recvmsg+0x5c/0xb0 [27642.574227] __x64_sys_sendto+0x20/0x30 [27642.574904] do_syscall_64+0x55/0xc10 [27642.575554] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [27642.576391] RIP: 0033:0x7f197c85e807 [27642.577050] Code: c7 c0 ff ff ff ff eb be 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 80 3d 45 08 0d 00 00 41 89 ca 74 10 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 69 c3 55 48 89 e5 53 48 83 ec 38 44 89 4d d0 [27642.579846] RSP: 002b:00007ffebd4e2248 EFLAGS: 00000202 ORIG_RAX: 000000000000002c [27642.581082] RAX: ffffffffffffffda RBX: 000055cfcd9cd2a0 RCX: 00007f197c85e807 [27642.582200] RDX: 0000000000000038 RSI: 000055cfcd9cd490 RDI: 0000000000000003 [27642.583320] RBP: 00007ffebd4e2290 R08: 00007f197c942200 R09: 000000000000000c [27642.584437] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000 [27642.585555] R13: 000055cfcd9cd490 R14: 00007ffebd4e45d1 R15: 000055cfcd9cd2a0 [27642.586671] [27642.587121] ---[ end trace 0000000000000000 ]--- [27642.587910] BUG: kernel NULL pointer dereference, address: 00000000000000a0 Fixes: 664f76be38a1 ("net/mlx5: Fix IPsec cleanup over MPV device") Signed-off-by: Patrisious Haddad Reviewed-by: Leon Romanovsky Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260305142634.1813208-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 197a1c6930c0..329608c59313 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -2912,7 +2912,7 @@ void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv) goto out; peer_priv = mlx5_devcom_get_next_peer_data(priv->devcom, &tmp); - if (peer_priv) + if (peer_priv && peer_priv->ipsec) complete_all(&peer_priv->ipsec->comp); mlx5_devcom_for_each_peer_end(priv->devcom); From 76324e4041c0efb4808702b05426d7a0a7d8df5b Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Thu, 5 Mar 2026 16:26:31 +0200 Subject: [PATCH 182/487] net/mlx5: Fix peer miss rules host disabled checks The check on mlx5_esw_host_functions_enabled(esw->dev) for adding VF peer miss rules is incorrect. These rules match traffic from peer's VFs, so the local device's host function status is irrelevant. Remove this check to ensure peer VF traffic is properly handled regardless of local host configuration. Also fix the PF peer miss rule deletion to be symmetric with the add path, so only attempt to delete the rule if it was actually created. Fixes: 520369ef43a8 ("net/mlx5: Support disabling host PFs") Signed-off-by: Carolina Jubran Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260305142634.1813208-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../mellanox/mlx5/core/eswitch_offloads.c | 27 +++++++++---------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 8c5e48d001be..7a9ee36b8dca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1241,21 +1241,17 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, flows[peer_vport->index] = flow; } - if (mlx5_esw_host_functions_enabled(esw->dev)) { - mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, - mlx5_core_max_vfs(peer_dev)) { - esw_set_peer_miss_rule_source_port(esw, peer_esw, - spec, - peer_vport->vport); - - flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), - spec, &flow_act, &dest, 1); - if (IS_ERR(flow)) { - err = PTR_ERR(flow); - goto add_vf_flow_err; - } - flows[peer_vport->index] = flow; + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { + esw_set_peer_miss_rule_source_port(esw, peer_esw, spec, + peer_vport->vport); + flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), + spec, &flow_act, &dest, 1); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto add_vf_flow_err; } + flows[peer_vport->index] = flow; } if (mlx5_core_ec_sriov_enabled(peer_dev)) { @@ -1347,7 +1343,8 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw, mlx5_del_flow_rules(flows[peer_vport->index]); } - if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + if (mlx5_core_is_ecpf_esw_manager(peer_dev) && + mlx5_esw_host_functions_enabled(peer_dev)) { peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); mlx5_del_flow_rules(flows[peer_vport->index]); } From 1633111d69053512d099658d4a05fc736fab36b0 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 5 Mar 2026 16:26:32 +0200 Subject: [PATCH 183/487] net/mlx5e: Fix DMA FIFO desync on error CQE SQ recovery In case of a TX error CQE, a recovery flow is triggered, mlx5e_reset_txqsq_cc_pc() resets dma_fifo_cc to 0 but not dma_fifo_pc, desyncing the DMA FIFO producer and consumer. After recovery, the producer pushes new DMA entries at the old dma_fifo_pc, while the consumer reads from position 0. This causes us to unmap stale DMA addresses from before the recovery. The DMA FIFO is a purely software construct with no HW counterpart. At the point of reset, all WQEs have been flushed so dma_fifo_cc is already equal to dma_fifo_pc. There is no need to reset either counter, similar to how skb_fifo pc/cc are untouched. Remove the 'dma_fifo_cc = 0' reset. This fixes the following WARNING: WARNING: CPU: 0 PID: 0 at drivers/iommu/dma-iommu.c:1240 iommu_dma_unmap_page+0x79/0x90 Modules linked in: mlx5_vdpa vringh vdpa bonding mlx5_ib mlx5_vfio_pci ipip mlx5_fwctl tunnel4 mlx5_core ib_ipoib geneve ip6_gre ip_gre gre nf_tables ip6_tunnel rdma_ucm ib_uverbs ib_umad vfio_pci vfio_pci_core act_mirred act_skbedit act_vlan vhost_net vhost tap ip6table_mangle ip6table_nat ip6table_filter ip6_tables iptable_mangle cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress vhost_iotlb iptable_raw tunnel6 vfio_iommu_type1 vfio openvswitch nsh rpcsec_gss_krb5 auth_rpcgss oid_registry xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter overlay zram zsmalloc rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core fuse [last unloaded: nf_tables] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.13.0-rc5_for_upstream_min_debug_2024_12_30_21_33 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:iommu_dma_unmap_page+0x79/0x90 Code: 2b 4d 3b 21 72 26 4d 3b 61 08 73 20 49 89 d8 44 89 f9 5b 4c 89 f2 4c 89 e6 48 89 ef 5d 41 5c 41 5d 41 5e 41 5f e9 c7 ae 9e ff <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 66 2e 0f 1f 84 00 00 00 00 Call Trace: ? __warn+0x7d/0x110 ? iommu_dma_unmap_page+0x79/0x90 ? report_bug+0x16d/0x180 ? handle_bug+0x4f/0x90 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? iommu_dma_unmap_page+0x79/0x90 ? iommu_dma_unmap_page+0x2e/0x90 dma_unmap_page_attrs+0x10d/0x1b0 mlx5e_tx_wi_dma_unmap+0xbe/0x120 [mlx5_core] mlx5e_poll_tx_cq+0x16d/0x690 [mlx5_core] mlx5e_napi_poll+0x8b/0xac0 [mlx5_core] __napi_poll+0x24/0x190 net_rx_action+0x32a/0x3b0 ? mlx5_eq_comp_int+0x7e/0x270 [mlx5_core] ? notifier_call_chain+0x35/0xa0 handle_softirqs+0xc9/0x270 irq_exit_rcu+0x71/0xd0 common_interrupt+0x7f/0xa0 asm_common_interrupt+0x22/0x40 Fixes: db75373c91b0 ("net/mlx5e: Recover Send Queue (SQ) from error state") Signed-off-by: Gal Pressman Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260305142634.1813208-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 60ba840e00fa..afdeb1b3d425 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -47,7 +47,6 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", sq->sqn, sq->cc, sq->pc); sq->cc = 0; - sq->dma_fifo_cc = 0; sq->pc = 0; } From db25c42c2e1f9c0d136420fff5e5700f7e771a6f Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 5 Mar 2026 16:26:33 +0200 Subject: [PATCH 184/487] net/mlx5e: RX, Fix XDP multi-buf frag counting for striding RQ XDP multi-buf programs can modify the layout of the XDP buffer when the program calls bpf_xdp_pull_data() or bpf_xdp_adjust_tail(). The referenced commit in the fixes tag corrected the assumption in the mlx5 driver that the XDP buffer layout doesn't change during a program execution. However, this fix introduced another issue: the dropped fragments still need to be counted on the driver side to avoid page fragment reference counting issues. The issue was discovered by the drivers/net/xdp.py selftest, more specifically the test_xdp_native_tx_mb: - The mlx5 driver allocates a page_pool page and initializes it with a frag counter of 64 (pp_ref_count=64) and the internal frag counter to 0. - The test sends one packet with no payload. - On RX (mlx5e_skb_from_cqe_mpwrq_nonlinear()), mlx5 configures the XDP buffer with the packet data starting in the first fragment which is the page mentioned above. - The XDP program runs and calls bpf_xdp_pull_data() which moves the header into the linear part of the XDP buffer. As the packet doesn't contain more data, the program drops the tail fragment since it no longer contains any payload (pp_ref_count=63). - mlx5 device skips counting this fragment. Internal frag counter remains 0. - mlx5 releases all 64 fragments of the page but page pp_ref_count is 63 => negative reference counting error. Resulting splat during the test: WARNING: CPU: 0 PID: 188225 at ./include/net/page_pool/helpers.h:297 mlx5e_page_release_fragmented.isra.0+0xbd/0xe0 [mlx5_core] Modules linked in: [...] CPU: 0 UID: 0 PID: 188225 Comm: ip Not tainted 6.18.0-rc7_for_upstream_min_debug_2025_12_08_11_44 #1 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5e_page_release_fragmented.isra.0+0xbd/0xe0 [mlx5_core] [...] Call Trace: mlx5e_free_rx_mpwqe+0x20a/0x250 [mlx5_core] mlx5e_dealloc_rx_mpwqe+0x37/0xb0 [mlx5_core] mlx5e_free_rx_descs+0x11a/0x170 [mlx5_core] mlx5e_close_rq+0x78/0xa0 [mlx5_core] mlx5e_close_queues+0x46/0x2a0 [mlx5_core] mlx5e_close_channel+0x24/0x90 [mlx5_core] mlx5e_close_channels+0x5d/0xf0 [mlx5_core] mlx5e_safe_switch_params+0x2ec/0x380 [mlx5_core] mlx5e_change_mtu+0x11d/0x490 [mlx5_core] mlx5e_change_nic_mtu+0x19/0x30 [mlx5_core] netif_set_mtu_ext+0xfc/0x240 do_setlink.isra.0+0x226/0x1100 rtnl_newlink+0x7a9/0xba0 rtnetlink_rcv_msg+0x220/0x3c0 netlink_rcv_skb+0x4b/0xf0 netlink_unicast+0x255/0x380 netlink_sendmsg+0x1f3/0x420 __sock_sendmsg+0x38/0x60 ____sys_sendmsg+0x1e8/0x240 ___sys_sendmsg+0x7c/0xb0 [...] __sys_sendmsg+0x5f/0xb0 do_syscall_64+0x55/0xc70 The problem applies for XDP_PASS as well which is handled in a different code path in the driver. This patch fixes the issue by doing page frag counting on all the original XDP buffer fragments for all relevant XDP actions (XDP_TX , XDP_REDIRECT and XDP_PASS). This is basically reverting to the original counting before the commit in the fixes tag. As frag_page is still pointing to the original tail, the nr_frags parameter to xdp_update_skb_frags_info() needs to be calculated in a different way to reflect the new nr_frags. Fixes: 87bcef158ac1 ("net/mlx5e: RX, Fix generating skb from non-linear xdp_buff for striding RQ") Signed-off-by: Dragos Tatulea Cc: Amery Hung Reviewed-by: Nimrod Oren Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260305142634.1813208-5-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index efcfcddab376..40e53a612989 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1957,14 +1957,13 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w if (prog) { u8 nr_frags_free, old_nr_frags = sinfo->nr_frags; + u8 new_nr_frags; u32 len; if (mlx5e_xdp_handle(rq, prog, mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { struct mlx5e_frag_page *pfp; - frag_page -= old_nr_frags - sinfo->nr_frags; - for (pfp = head_page; pfp < frag_page; pfp++) pfp->frags++; @@ -1975,13 +1974,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w return NULL; /* page/packet was consumed by XDP */ } - nr_frags_free = old_nr_frags - sinfo->nr_frags; - if (unlikely(nr_frags_free)) { - frag_page -= nr_frags_free; + new_nr_frags = sinfo->nr_frags; + nr_frags_free = old_nr_frags - new_nr_frags; + if (unlikely(nr_frags_free)) truesize -= (nr_frags_free - 1) * PAGE_SIZE + ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz)); - } len = mxbuf->xdp.data_end - mxbuf->xdp.data; @@ -2003,7 +2001,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w struct mlx5e_frag_page *pagep; /* sinfo->nr_frags is reset by build_skb, calculate again. */ - xdp_update_skb_frags_info(skb, frag_page - head_page, + xdp_update_skb_frags_info(skb, new_nr_frags, sinfo->xdp_frags_size, truesize, xdp_buff_get_skb_flags(&mxbuf->xdp)); From a6413e6f6c9d9bb9833324cb3753582f7bc0f2fa Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 5 Mar 2026 16:26:34 +0200 Subject: [PATCH 185/487] net/mlx5e: RX, Fix XDP multi-buf frag counting for legacy RQ XDP multi-buf programs can modify the layout of the XDP buffer when the program calls bpf_xdp_pull_data() or bpf_xdp_adjust_tail(). The referenced commit in the fixes tag corrected the assumption in the mlx5 driver that the XDP buffer layout doesn't change during a program execution. However, this fix introduced another issue: the dropped fragments still need to be counted on the driver side to avoid page fragment reference counting issues. Such issue can be observed with the test_xdp_native_adjst_tail_shrnk_data selftest when using a payload of 3600 and shrinking by 256 bytes (an upcoming selftest patch): the last fragment gets released by the XDP code but doesn't get tracked by the driver. This results in a negative pp_ref_count during page release and the following splat: WARNING: include/net/page_pool/helpers.h:297 at mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core], CPU#12: ip/3137 Modules linked in: [...] CPU: 12 UID: 0 PID: 3137 Comm: ip Not tainted 6.19.0-rc3+ #12 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core] [...] Call Trace: mlx5e_dealloc_rx_wqe+0xcb/0x1a0 [mlx5_core] mlx5e_free_rx_descs+0x7f/0x110 [mlx5_core] mlx5e_close_rq+0x50/0x60 [mlx5_core] mlx5e_close_queues+0x36/0x2c0 [mlx5_core] mlx5e_close_channel+0x1c/0x50 [mlx5_core] mlx5e_close_channels+0x45/0x80 [mlx5_core] mlx5e_safe_switch_params+0x1a5/0x230 [mlx5_core] mlx5e_change_mtu+0xf3/0x2f0 [mlx5_core] netif_set_mtu_ext+0xf1/0x230 do_setlink.isra.0+0x219/0x1180 rtnl_newlink+0x79f/0xb60 rtnetlink_rcv_msg+0x213/0x3a0 netlink_rcv_skb+0x48/0xf0 netlink_unicast+0x24a/0x350 netlink_sendmsg+0x1ee/0x410 __sock_sendmsg+0x38/0x60 ____sys_sendmsg+0x232/0x280 ___sys_sendmsg+0x78/0xb0 __sys_sendmsg+0x5f/0xb0 [...] do_syscall_64+0x57/0xc50 This patch fixes the issue by doing page frag counting on all the original XDP buffer fragments for all relevant XDP actions (XDP_TX , XDP_REDIRECT and XDP_PASS). This is basically reverting to the original counting before the commit in the fixes tag. As frag_page is still pointing to the original tail, the nr_frags parameter to xdp_update_skb_frags_info() needs to be calculated in a different way to reflect the new nr_frags. Fixes: afd5ba577c10 ("net/mlx5e: RX, Fix generating skb from non-linear xdp_buff for legacy RQ") Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Reviewed-by: Amery Hung Link: https://patch.msgid.link/20260305142634.1813208-6-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 40e53a612989..268e20884757 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1589,6 +1589,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi struct skb_shared_info *sinfo; u32 frag_consumed_bytes; struct bpf_prog *prog; + u8 nr_frags_free = 0; struct sk_buff *skb; dma_addr_t addr; u32 truesize; @@ -1631,15 +1632,13 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi prog = rcu_dereference(rq->xdp_prog); if (prog) { - u8 nr_frags_free, old_nr_frags = sinfo->nr_frags; + u8 old_nr_frags = sinfo->nr_frags; if (mlx5e_xdp_handle(rq, prog, mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { struct mlx5e_wqe_frag_info *pwi; - wi -= old_nr_frags - sinfo->nr_frags; - for (pwi = head_wi; pwi < wi; pwi++) pwi->frag_page->frags++; } @@ -1647,10 +1646,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi } nr_frags_free = old_nr_frags - sinfo->nr_frags; - if (unlikely(nr_frags_free)) { - wi -= nr_frags_free; + if (unlikely(nr_frags_free)) truesize -= nr_frags_free * frag_info->frag_stride; - } } skb = mlx5e_build_linear_skb( @@ -1666,7 +1663,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi if (xdp_buff_has_frags(&mxbuf->xdp)) { /* sinfo->nr_frags is reset by build_skb, calculate again. */ - xdp_update_skb_frags_info(skb, wi - head_wi - 1, + xdp_update_skb_frags_info(skb, wi - head_wi - nr_frags_free - 1, sinfo->xdp_frags_size, truesize, xdp_buff_get_skb_flags(&mxbuf->xdp)); From 5c3398a54266541610c8d0a7082e654e9ff3e259 Mon Sep 17 00:00:00 2001 From: Jian Zhang Date: Thu, 5 Mar 2026 14:06:55 +0800 Subject: [PATCH 186/487] net: ncsi: fix skb leak in error paths Early return paths in NCSI RX and AEN handlers fail to release the received skb, resulting in a memory leak. Specifically, ncsi_aen_handler() returns on invalid AEN packets without consuming the skb. Similarly, ncsi_rcv_rsp() exits early when failing to resolve the NCSI device, response handler, or request, leaving the skb unfreed. CC: stable@vger.kernel.org Fixes: 7a82ecf4cfb8 ("net/ncsi: NCSI AEN packet handler") Fixes: 138635cc27c9 ("net/ncsi: NCSI response packet handler") Signed-off-by: Jian Zhang Link: https://patch.msgid.link/20260305060656.3357250-1-zhangjian.3032@bytedance.com Signed-off-by: Jakub Kicinski --- net/ncsi/ncsi-aen.c | 3 ++- net/ncsi/ncsi-rsp.c | 16 ++++++++++++---- 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 62fb1031763d..040a31557201 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -224,7 +224,8 @@ int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb) if (!nah) { netdev_warn(ndp->ndev.dev, "Invalid AEN (0x%x) received\n", h->type); - return -ENOENT; + ret = -ENOENT; + goto out; } ret = ncsi_validate_aen_pkt(h, nah->payload); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 271ec6c3929e..fbd84bc8026a 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -1176,8 +1176,10 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, /* Find the NCSI device */ nd = ncsi_find_dev(orig_dev); ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; - if (!ndp) - return -ENODEV; + if (!ndp) { + ret = -ENODEV; + goto err_free_skb; + } /* Check if it is AEN packet */ hdr = (struct ncsi_pkt_hdr *)skb_network_header(skb); @@ -1199,7 +1201,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, if (!nrh) { netdev_err(nd->dev, "Received unrecognized packet (0x%x)\n", hdr->type); - return -ENOENT; + ret = -ENOENT; + goto err_free_skb; } /* Associate with the request */ @@ -1207,7 +1210,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, nr = &ndp->requests[hdr->id]; if (!nr->used) { spin_unlock_irqrestore(&ndp->lock, flags); - return -ENODEV; + ret = -ENODEV; + goto err_free_skb; } nr->rsp = skb; @@ -1261,4 +1265,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, out: ncsi_free_request(nr); return ret; + +err_free_skb: + kfree_skb(skb); + return ret; } From 0cc0c2e661af418bbf7074179ea5cfffc0a5c466 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Wed, 4 Mar 2026 12:42:18 +0800 Subject: [PATCH 187/487] net/sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit through slave devices, but does not update skb->dev to the slave device beforehand. When a gretap tunnel is a TEQL slave, the transmit path reaches iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0 master) and later calls iptunnel_xmit_stats(dev, pkt_len). This function does: get_cpu_ptr(dev->tstats) Since teql_master_setup() does not set dev->pcpu_stat_type to NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL) computes NULL + __per_cpu_offset[cpu], resulting in a page fault. BUG: unable to handle page fault for address: ffff8880e6659018 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 68bc067 P4D 68bc067 PUD 0 Oops: Oops: 0002 [#1] SMP KASAN PTI RIP: 0010:iptunnel_xmit (./include/net/ip_tunnels.h:664 net/ipv4/ip_tunnel_core.c:89) Call Trace: ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) __gre_xmit (net/ipv4/ip_gre.c:478) gre_tap_xmit (net/ipv4/ip_gre.c:779) teql_master_xmit (net/sched/sch_teql.c:319) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) neigh_direct_output (net/core/neighbour.c:1660) ip_finish_output2 (net/ipv4/ip_output.c:237) __ip_finish_output.part.0 (net/ipv4/ip_output.c:315) ip_mc_output (net/ipv4/ip_output.c:369) ip_send_skb (net/ipv4/ip_output.c:1508) udp_send_skb (net/ipv4/udp.c:1195) udp_sendmsg (net/ipv4/udp.c:1485) inet_sendmsg (net/ipv4/af_inet.c:859) __sys_sendto (net/socket.c:2206) Fix this by setting skb->dev = slave before calling netdev_start_xmit(), so that tunnel xmit functions see the correct slave device with properly allocated tstats. Fixes: 039f50629b7f ("ip_tunnel: Move stats update to iptunnel_xmit()") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Link: https://patch.msgid.link/20260304044216.3517851-3-bestswngs@gmail.com Signed-off-by: Jakub Kicinski --- net/sched/sch_teql.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 6e4bdaa876ed..783300d8b019 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -315,6 +315,7 @@ static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) if (__netif_tx_trylock(slave_txq)) { unsigned int length = qdisc_pkt_len(skb); + skb->dev = slave; if (!netif_xmit_frozen_or_stopped(slave_txq) && netdev_start_xmit(skb, slave, slave_txq, false) == NETDEV_TX_OK) { From 976703cae7375898b445fc40d14faf849e916a4b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 Mar 2026 00:08:59 +0200 Subject: [PATCH 188/487] net: dsa: sja1105: reorder sja1105_reload_cbs() and phylink_replay_link_end() Move phylink_replay_link_end() as the last locked operation under sja1105_static_config_reload(). The purpose is to be able to goto this step from the error path of intermediate steps (we must call phylink_replay_link_end()). sja1105_reload_cbs() notably does not depend on port states or link speeds. See commit 954ad9bf13c4 ("net: dsa: sja1105: fix bandwidth discrepancy between tc-cbs software and offload") which has discussed this issue specifically. Signed-off-by: Vladimir Oltean Link: https://patch.msgid.link/20260304220900.3865120-2-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/sja1105/sja1105_main.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 94d17b06da40..bf720d96bad8 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2339,13 +2339,11 @@ int sja1105_static_config_reload(struct sja1105_private *priv, goto out; } + rc = sja1105_reload_cbs(priv); + dsa_switch_for_each_available_port(dp, ds) if (dp->pl) phylink_replay_link_end(dp->pl); - - rc = sja1105_reload_cbs(priv); - if (rc < 0) - goto out; out: mutex_unlock(&priv->mgmt_lock); mutex_unlock(&priv->fdb_lock); From ce2da643f00af3111f1fffe2adea8506592ef6e5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 Mar 2026 00:09:00 +0200 Subject: [PATCH 189/487] net: dsa: sja1105: ensure phylink_replay_link_end() will not be missed Most errors that can occur in sja1105_static_config_reload() are fatal (example: fail to communicate with hardware), but not all are. For example, sja1105_static_config_upload() -> kcalloc() may fail, and if that happens, we have called phylink_replay_link_begin() but never phylink_replay_link_end(). Under that circumstance, all port phylink instances are left in a state where the resolver is stopped with the PHYLINK_DISABLE_REPLAY bit set. We have effectively disabled link management with no way to recover from this condition. Avoid that situation by ensuring phylink_replay_link_begin() is always paired with phylink_replay_link_end(), regardless of whether we faced any errors during switch reset, configuration reload and general state reload. Fixes: 0b2edc531e0b ("net: dsa: sja1105: let phylink help with the replay of link callbacks") Signed-off-by: Vladimir Oltean Link: https://patch.msgid.link/20260304220900.3865120-3-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/sja1105/sja1105_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index bf720d96bad8..c72c2bfdcffb 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2341,10 +2341,11 @@ int sja1105_static_config_reload(struct sja1105_private *priv, rc = sja1105_reload_cbs(priv); +out: dsa_switch_for_each_available_port(dp, ds) if (dp->pl) phylink_replay_link_end(dp->pl); -out: + mutex_unlock(&priv->mgmt_lock); mutex_unlock(&priv->fdb_lock); From 4245a79003adf30e67f8e9060915bd05cb31d142 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 5 Mar 2026 12:31:01 +0000 Subject: [PATCH 190/487] rxrpc, afs: Fix missing error pointer check after rxrpc_kernel_lookup_peer() rxrpc_kernel_lookup_peer() can also return error pointers in addition to NULL, so just checking for NULL is not sufficient. Fix this by: (1) Changing rxrpc_kernel_lookup_peer() to return -ENOMEM rather than NULL on allocation failure. (2) Making the callers in afs use IS_ERR() and PTR_ERR() to pass on the error code returned. Fixes: 72904d7b9bfb ("rxrpc, afs: Allow afs to pin rxrpc_peer objects") Signed-off-by: Miaoqian Lin Co-developed-by: David Howells Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/368272.1772713861@warthog.procyon.org.uk Signed-off-by: Jakub Kicinski --- fs/afs/addr_list.c | 8 ++++---- net/rxrpc/af_rxrpc.c | 8 +++++--- 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index a936f9ea5610..63bf096b721a 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -298,8 +298,8 @@ int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *alist, srx.transport.sin.sin_addr.s_addr = xdr; peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL); - if (!peer) - return -ENOMEM; + if (IS_ERR(peer)) + return PTR_ERR(peer); for (i = 0; i < alist->nr_ipv4; i++) { if (peer == alist->addrs[i].peer) { @@ -342,8 +342,8 @@ int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist, memcpy(&srx.transport.sin6.sin6_addr, xdr, 16); peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL); - if (!peer) - return -ENOMEM; + if (IS_ERR(peer)) + return PTR_ERR(peer); for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) { if (peer == alist->addrs[i].peer) { diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 0c2c68c4b07e..0f90272ac254 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -267,12 +267,13 @@ static int rxrpc_listen(struct socket *sock, int backlog) * Lookup or create a remote transport endpoint record for the specified * address. * - * Return: The peer record found with a reference, %NULL if no record is found - * or a negative error code if the address is invalid or unsupported. + * Return: The peer record found with a reference or a negative error code if + * the address is invalid or unsupported. */ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, struct sockaddr_rxrpc *srx, gfp_t gfp) { + struct rxrpc_peer *peer; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; @@ -280,7 +281,8 @@ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, if (ret < 0) return ERR_PTR(ret); - return rxrpc_lookup_peer(rx->local, srx, gfp); + peer = rxrpc_lookup_peer(rx->local, srx, gfp); + return peer ?: ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(rxrpc_kernel_lookup_peer); From 3aa1417803c1833cbd5bacb7e6a6489a196f2519 Mon Sep 17 00:00:00 2001 From: Vivian Wang Date: Thu, 5 Mar 2026 14:39:38 +0800 Subject: [PATCH 191/487] net: spacemit: Fix error handling in emac_alloc_rx_desc_buffers() Even if we get a dma_mapping_error() while mapping an RX buffer, we should still update rx_ring->head to ensure that the buffers we were able to allocate and map are used. Fix this by breaking out to the existing code after the loop, analogous to the existing handling for skb allocation failure. Fixes: bfec6d7f2001 ("net: spacemit: Add K1 Ethernet MAC") Signed-off-by: Vivian Wang Link: https://patch.msgid.link/20260305-k1-ethernet-more-fixes-v2-1-e4e434d65055@iscas.ac.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/spacemit/k1_emac.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index 338a2637b1da..5a5cb61be08c 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -565,7 +565,9 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv) DMA_FROM_DEVICE); if (dma_mapping_error(&priv->pdev->dev, rx_buf->dma_addr)) { dev_err_ratelimited(&ndev->dev, "Mapping skb failed\n"); - goto err_free_skb; + dev_kfree_skb_any(skb); + rx_buf->skb = NULL; + break; } rx_desc_addr = &((struct emac_desc *)rx_ring->desc_addr)[i]; @@ -590,10 +592,6 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv) rx_ring->head = i; return; - -err_free_skb: - dev_kfree_skb_any(skb); - rx_buf->skb = NULL; } /* Returns number of packets received */ From 86292155bea578ebab0ca3b65d4d87ecd8a0e9ea Mon Sep 17 00:00:00 2001 From: Vivian Wang Date: Thu, 5 Mar 2026 14:39:39 +0800 Subject: [PATCH 192/487] net: spacemit: Fix error handling in emac_tx_mem_map() The DMA mappings were leaked on mapping error. Free them with the existing emac_free_tx_buf() function. Fixes: bfec6d7f2001 ("net: spacemit: Add K1 Ethernet MAC") Signed-off-by: Vivian Wang Link: https://patch.msgid.link/20260305-k1-ethernet-more-fixes-v2-2-e4e434d65055@iscas.ac.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/spacemit/k1_emac.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index 5a5cb61be08c..15d43e4a748b 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -733,7 +733,7 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb) struct emac_desc tx_desc, *tx_desc_addr; struct device *dev = &priv->pdev->dev; struct emac_tx_desc_buffer *tx_buf; - u32 head, old_head, frag_num, f; + u32 head, old_head, frag_num, f, i; bool buf_idx; frag_num = skb_shinfo(skb)->nr_frags; @@ -801,6 +801,15 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb) err_free_skb: dev_dstats_tx_dropped(priv->ndev); + + i = old_head; + while (i != head) { + emac_free_tx_buf(priv, i); + + if (++i == tx_ring->total_cnt) + i = 0; + } + dev_kfree_skb_any(skb); } From 73cdf24e81e4eba52a40a6b10c6cf285d0ac23fd Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 27 Jan 2026 14:19:24 +0530 Subject: [PATCH 193/487] powerpc64: make clang cross-build friendly ARCH_USING_PATCHABLE_FUNCTION_ENTRY depends on toolchain support for -fpatchable-function-entry option. The current script that checks for this support only handles GCC. Rename the script and extend it to detect support for -fpatchable-function-entry with Clang as well, allowing clean cross-compilation with Clang toolchains. Signed-off-by: Hari Bathini Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260127084926.34497-2-hbathini@linux.ibm.com --- arch/powerpc/Kconfig | 4 ++-- ...e-function-entry.sh => check-fpatchable-function-entry.sh} | 0 2 files changed, 2 insertions(+), 2 deletions(-) rename arch/powerpc/tools/{gcc-check-fpatchable-function-entry.sh => check-fpatchable-function-entry.sh} (100%) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ad7a2fe63a2a..10240cb80904 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -573,8 +573,8 @@ config ARCH_USING_PATCHABLE_FUNCTION_ENTRY depends on FUNCTION_TRACER && (PPC32 || PPC64_ELF_ABI_V2) depends on $(cc-option,-fpatchable-function-entry=2) def_bool y if PPC32 - def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN - def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN + def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) $(CLANG_FLAGS) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN + def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN config PPC_FTRACE_OUT_OF_LINE def_bool PPC64 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/check-fpatchable-function-entry.sh similarity index 100% rename from arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh rename to arch/powerpc/tools/check-fpatchable-function-entry.sh From 875612a7745013a43c67493cb0583ee3f7476344 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 27 Jan 2026 14:19:25 +0530 Subject: [PATCH 194/487] powerpc64/ftrace: fix OOL stub count with clang The total number of out-of-line (OOL) stubs required for function tracing is determined using the following command: $(OBJDUMP) -r -j __patchable_function_entries vmlinux.o While this works correctly with GNU objdump, llvm-objdump does not list the expected relocation records for this section. Fix this by using the -d option and counting R_PPC64_ADDR64 relocation entries. This works as desired with both objdump and llvm-objdump. Signed-off-by: Hari Bathini Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260127084926.34497-3-hbathini@linux.ibm.com --- arch/powerpc/tools/ftrace-gen-ool-stubs.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh index bac186bdf64a..9218d43aeb54 100755 --- a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh +++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh @@ -15,9 +15,9 @@ if [ -z "$is_64bit" ]; then RELOCATION=R_PPC_ADDR32 fi -num_ool_stubs_total=$($objdump -r -j __patchable_function_entries "$vmlinux_o" | +num_ool_stubs_total=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" | grep -c "$RELOCATION") -num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries "$vmlinux_o" | +num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" | grep -e ".init.text" -e ".text.startup" | grep -c "$RELOCATION") num_ool_stubs_text=$((num_ool_stubs_total - num_ool_stubs_inittext)) From db54c28702f7270e74dce36c84cb0db4cec96389 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 27 Jan 2026 14:19:26 +0530 Subject: [PATCH 195/487] powerpc64/ftrace: workaround clang recording GEP in __patchable_function_entries Support for -fpatchable-function-entry on ppc64le was added in Clang with [1]. However, when no prefix NOPs are specified - as is the case with CONFIG_PPC_FTRACE_OUT_OF_LINE - the first NOP is emitted at LEP, but Clang records the Global Entry Point (GEP) unlike GCC which does record the Local Entry Point (LEP). Issue [2] has been raised to align Clang's behavior with GCC. As a temporary workaround to ensure ftrace initialization works as expected with Clang, derive the LEP using ppc_function_entry() for kernel symbols and by looking for the below module GEP sequence for module addresses, until [2] is resolved: ld r2, -8(r12) add r2, r2, r12 [1] https://github.com/llvm/llvm-project/pull/151569 [2] https://github.com/llvm/llvm-project/issues/163706 Signed-off-by: Hari Bathini Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260127084926.34497-4-hbathini@linux.ibm.com --- arch/powerpc/kernel/trace/ftrace.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 841d077e2825..1b2f293e7dcb 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -37,11 +37,29 @@ unsigned long ftrace_call_adjust(unsigned long addr) if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end) return 0; - if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) && - !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { - addr += MCOUNT_INSN_SIZE; - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) { + if (!IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { addr += MCOUNT_INSN_SIZE; + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + addr += MCOUNT_INSN_SIZE; + } else if (IS_ENABLED(CONFIG_CC_IS_CLANG) && IS_ENABLED(CONFIG_PPC64)) { + /* + * addr points to global entry point though the NOP was emitted at local + * entry point due to https://github.com/llvm/llvm-project/issues/163706 + * Handle that here with ppc_function_entry() for kernel symbols while + * adjusting module addresses in the else case, by looking for the below + * module global entry point sequence: + * ld r2, -8(r12) + * add r2, r2, r12 + */ + if (is_kernel_text(addr) || is_kernel_inittext(addr)) + addr = ppc_function_entry((void *)addr); + else if ((ppc_inst_val(ppc_inst_read((u32 *)addr)) == + PPC_RAW_LD(_R2, _R12, -8)) && + (ppc_inst_val(ppc_inst_read((u32 *)(addr+4))) == + PPC_RAW_ADD(_R2, _R2, _R12))) + addr += 8; + } } return addr; From 521bd39d9d28ce54cbfec7f9b89c94ad4fdb8350 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 3 Mar 2026 23:40:25 +0530 Subject: [PATCH 196/487] powerpc64/bpf: do not increment tailcall count when prog is NULL Do not increment tailcall count, if tailcall did not succeed due to missing BPF program. Fixes: ce0761419fae ("powerpc/bpf: Implement support for tail calls") Cc: stable@vger.kernel.org Tested-by: Venkat Rao Bagalkote Signed-off-by: Hari Bathini Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303181031.390073-2-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit_comp64.c | 39 +++++++++++++++++-------------- 1 file changed, 21 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index b1a3945ccc9f..44ce8a8783f9 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -522,9 +522,30 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o /* * tail_call_info++; <- Actual value of tcc here + * Writeback this updated value only if tailcall succeeds. */ EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 1)); + /* prog = array->ptrs[index]; */ + EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_2), b2p_index, 8)); + EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), b2p_bpf_array)); + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + offsetof(struct bpf_array, ptrs))); + + /* + * if (prog == NULL) + * goto out; + */ + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), 0)); + PPC_BCC_SHORT(COND_EQ, out); + + /* goto *(prog->bpf_func + prologue_size); */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + offsetof(struct bpf_prog, bpf_func))); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size)); + EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_2))); + /* * Before writing updated tail_call_info, distinguish if current frame * is storing a reference to tail_call_info or actual tcc value in @@ -539,24 +560,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o /* Writeback updated value to tail_call_info */ EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0)); - /* prog = array->ptrs[index]; */ - EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_1), b2p_index, 8)); - EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), b2p_bpf_array)); - EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_array, ptrs))); - - /* - * if (prog == NULL) - * goto out; - */ - EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), 0)); - PPC_BCC_SHORT(COND_EQ, out); - - /* goto *(prog->bpf_func + prologue_size); */ - EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_prog, bpf_func))); - EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), - FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size)); - EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1))); - /* tear down stack, restore NVRs, ... */ bpf_jit_emit_common_epilogue(image, ctx); From 157820264ac3dadfafffad63184b883eb28f9ae0 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 3 Mar 2026 23:40:26 +0530 Subject: [PATCH 197/487] powerpc64/bpf: fix the address returned by bpf_get_func_ip bpf_get_func_ip() helper function returns the address of the traced function. It relies on the IP address stored at ctx - 16 by the bpf trampoline. On 64-bit powerpc, this address is recovered from LR accounting for OOL trampoline. But the address stored here was off by 4-bytes. Ensure the address is the actual start of the traced function. Reported-by: Abhishek Dubey Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines") Cc: stable@vger.kernel.org Tested-by: Venkat Rao Bagalkote Signed-off-by: Hari Bathini Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303181031.390073-3-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit_comp.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 52162e4a7f84..95f208229b09 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -785,9 +785,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * retval_off [ return value ] * [ reg argN ] * [ ... ] - * regs_off [ reg_arg1 ] prog ctx context - * nregs_off [ args count ] - * ip_off [ traced function ] + * regs_off [ reg_arg1 ] prog_ctx + * nregs_off [ args count ] ((u64 *)prog_ctx)[-1] + * ip_off [ traced function ] ((u64 *)prog_ctx)[-2] * [ ... ] * run_ctx_off [ bpf_tramp_run_ctx ] * [ reg argN ] @@ -895,7 +895,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off); - /* Save our return address */ + /* Save our LR/return address */ EMIT(PPC_RAW_MFLR(_R3)); if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off)); @@ -903,24 +903,34 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); /* - * Save ip address of the traced function. - * We could recover this from LR, but we will need to address for OOL trampoline, - * and optional GEP area. + * Derive IP address of the traced function. + * In case of CONFIG_PPC_FTRACE_OUT_OF_LINE or BPF program, LR points to the instruction + * after the 'bl' instruction in the OOL stub. Refer to ftrace_init_ool_stub() and + * bpf_arch_text_poke() for OOL stub of kernel functions and bpf programs respectively. + * Relevant stub sequence: + * + * bl + * LR (R3) => mtlr r0 + * b + * + * Recover kernel function/bpf program address from the unconditional + * branch instruction at the end of OOL stub. */ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) || flags & BPF_TRAMP_F_IP_ARG) { EMIT(PPC_RAW_LWZ(_R4, _R3, 4)); EMIT(PPC_RAW_SLWI(_R4, _R4, 6)); EMIT(PPC_RAW_SRAWI(_R4, _R4, 6)); EMIT(PPC_RAW_ADD(_R3, _R3, _R4)); - EMIT(PPC_RAW_ADDI(_R3, _R3, 4)); } if (flags & BPF_TRAMP_F_IP_ARG) EMIT(PPC_RAW_STL(_R3, _R1, ip_off)); - if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) + if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { /* Fake our LR for unwind */ + EMIT(PPC_RAW_ADDI(_R3, _R3, 4)); EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); + } /* Save function arg count -- see bpf_get_func_arg_cnt() */ EMIT(PPC_RAW_LI(_R3, nr_regs)); From 3727d6ec13665c1d99bf6dedb107104368ba42b4 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 3 Mar 2026 23:40:27 +0530 Subject: [PATCH 198/487] powerpc64/bpf: use consistent tailcall offset in trampoline Ideally, the offset used to load the tail call info field and to find the pass by reference address for tail call field should be the same. But while setting up the tail call info in the trampoline, this was not followed. This can be misleading and can lead to unpredictable results if and when bpf_has_stack_frame() ends up returning true for trampoline frame. Since commit 15513beeb673 ("powerpc64/bpf: Moving tail_call_cnt to bottom of frame") and commit 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs") ensured tail call field is at the bottom of the stack frame for BPF programs as well as BPF trampoline, avoid relying on bpf_jit_stack_tailcallinfo_offset() and bpf_has_stack_frame() for trampoline frame and always calculate tail call field offset with reference to older frame. Fixes: 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs") Signed-off-by: Hari Bathini Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303181031.390073-4-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit.h | 5 ----- arch/powerpc/net/bpf_jit_comp.c | 12 +++++------- arch/powerpc/net/bpf_jit_comp64.c | 5 ++++- 3 files changed, 9 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 82bbf63f0e57..7354e1d72f79 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -81,9 +81,6 @@ #ifdef CONFIG_PPC64 -/* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (6 * 8) - /* If dummy pass (!image), account for maximum possible instructions */ #define PPC_LI64(d, i) do { \ if (!image) \ @@ -219,8 +216,6 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass, struct codegen_context *ctx, int insn_idx, int jmp_off, int dst_reg, u32 code); - -int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx); #endif #endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 95f208229b09..a4aa1e4c9f1c 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -642,15 +642,13 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte int bpf_dummy_frame_size, int r4_off) { if (IS_ENABLED(CONFIG_PPC64)) { - /* See Generated stack layout */ - int tailcallinfo_offset = BPF_PPC_TAILCALL; - /* * func_frame_offset = ...(1) * bpf_dummy_frame_size + trampoline_frame_size */ EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset)); - EMIT(PPC_RAW_LD(_R3, _R4, -tailcallinfo_offset)); + /* Refer to trampoline's Generated stack layout */ + EMIT(PPC_RAW_LD(_R3, _R4, -BPF_PPC_TAILCALL)); /* * Setting the tail_call_info in trampoline's frame @@ -658,7 +656,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte */ EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT)); PPC_BCC_CONST_SHORT(COND_GT, 8); - EMIT(PPC_RAW_ADDI(_R3, _R4, bpf_jit_stack_tailcallinfo_offset(ctx))); + EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL)); /* * From ...(1) above: * trampoline_frame_bottom = ...(2) @@ -666,14 +664,14 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte * * Using ...(2) derived above: * trampoline_tail_call_info_offset = ...(3) - * trampoline_frame_bottom - tailcallinfo_offset + * trampoline_frame_bottom - BPF_PPC_TAILCALL * * From ...(3): * Use trampoline_tail_call_info_offset to write reference of main's * tail_call_info in trampoline frame. */ EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size) - - tailcallinfo_offset)); + - BPF_PPC_TAILCALL)); } else { /* See bpf_jit_stack_offsetof() and BPF_PPC_TC */ EMIT(PPC_RAW_LL(_R4, _R1, r4_off)); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 44ce8a8783f9..7655be76f537 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -42,6 +42,9 @@ * exception boundary. */ +/* BPF non-volatile registers save area size */ +#define BPF_PPC_STACK_SAVE (6 * 8) + /* for bpf JIT code internal usage */ #define BPF_PPC_STACK_LOCALS 24 /* @@ -148,7 +151,7 @@ static int bpf_jit_stack_local(struct codegen_context *ctx) } } -int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx) +static int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx) { return bpf_jit_stack_local(ctx) + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE; } From 2d347d10f8e20e28a9eab52edf55079ae1ec0aae Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 3 Mar 2026 23:40:28 +0530 Subject: [PATCH 199/487] powerpc64/bpf: remove BPF redzone protection in trampoline stack Since bpf2bpf tailcall support is enabled for 64-bit powerpc with kernel commit 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs"), 'tailcalls/tailcall_bpf2bpf_hierarchy_fexit' BPF selftest is triggering "corrupted stack end detected inside scheduler" with the config option CONFIG_SCHED_STACK_END_CHECK enabled. While reviewing the stack layout for BPF trampoline, observed that the dummy frame is trying to protect the redzone of BPF program. This is because tail call info and NVRs save area are in redzone at the time of tailcall as the current BPF program stack frame is teared down before the tailcall. But saving this redzone in the dummy frame of trampoline is unnecessary because of the follow reasons: 1) Firstly, trampoline can be attached to BPF entry/main program or subprog. But prologue part of the BPF entry/main program, where the trampoline attachpoint is, is skipped during tailcall. So, protecting the redzone does not arise when the trampoline is not even triggered in this scenario. 2) In case of subprog, the caller's stackframe is already setup and the subprog's stackframe is yet to be setup. So, nothing on the redzone to be protected. Also, using dummy frame in BPF trampoline, wastes critically scarce kernel stack space, especially in tailcall sequence, for marginal benefit in stack unwinding. So, drop setting up the dummy frame. Instead, save return address in bpf trampoline frame and use it as appropriate. Pruning this unnecessary stack usage mitigates the likelihood of stack overflow in scenarios where bpf2bpf tailcalls and fexit programs are mixed. Reported-by: Saket Kumar Bhaskar Fixes: 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs") Tested-by: Venkat Rao Bagalkote Signed-off-by: Hari Bathini Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303181031.390073-5-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit_comp.c | 89 ++++++++++++--------------------- 1 file changed, 33 insertions(+), 56 deletions(-) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index a4aa1e4c9f1c..85457bcb2040 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -638,15 +638,10 @@ static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context * for the traced function (BPF subprog/callee) to fetch it. */ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_context *ctx, - int func_frame_offset, - int bpf_dummy_frame_size, int r4_off) + int bpf_frame_size, int r4_off) { if (IS_ENABLED(CONFIG_PPC64)) { - /* - * func_frame_offset = ...(1) - * bpf_dummy_frame_size + trampoline_frame_size - */ - EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset)); + EMIT(PPC_RAW_LD(_R4, _R1, bpf_frame_size)); /* Refer to trampoline's Generated stack layout */ EMIT(PPC_RAW_LD(_R3, _R4, -BPF_PPC_TAILCALL)); @@ -657,21 +652,13 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT)); PPC_BCC_CONST_SHORT(COND_GT, 8); EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL)); + /* - * From ...(1) above: - * trampoline_frame_bottom = ...(2) - * func_frame_offset - bpf_dummy_frame_size - * - * Using ...(2) derived above: - * trampoline_tail_call_info_offset = ...(3) - * trampoline_frame_bottom - BPF_PPC_TAILCALL - * - * From ...(3): - * Use trampoline_tail_call_info_offset to write reference of main's - * tail_call_info in trampoline frame. + * Trampoline's tail_call_info is at the same offset, as that of + * any bpf program, with reference to previous frame. Update the + * address of main's tail_call_info in trampoline frame. */ - EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size) - - BPF_PPC_TAILCALL)); + EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size - BPF_PPC_TAILCALL)); } else { /* See bpf_jit_stack_offsetof() and BPF_PPC_TC */ EMIT(PPC_RAW_LL(_R4, _R1, r4_off)); @@ -679,7 +666,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte } static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_context *ctx, - int func_frame_offset, int r4_off) + int bpf_frame_size, int r4_off) { if (IS_ENABLED(CONFIG_PPC32)) { /* @@ -690,12 +677,12 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont } } -static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, int func_frame_offset, - int nr_regs, int regs_off) +static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, + int bpf_frame_size, int nr_regs, int regs_off) { int param_save_area_offset; - param_save_area_offset = func_frame_offset; /* the two frames we alloted */ + param_save_area_offset = bpf_frame_size; param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */ for (int i = 0; i < nr_regs; i++) { @@ -718,11 +705,11 @@ static void bpf_trampoline_restore_args_regs(u32 *image, struct codegen_context /* Used when we call into the traced function. Replicate parameter save area */ static void bpf_trampoline_restore_args_stack(u32 *image, struct codegen_context *ctx, - int func_frame_offset, int nr_regs, int regs_off) + int bpf_frame_size, int nr_regs, int regs_off) { int param_save_area_offset; - param_save_area_offset = func_frame_offset; /* the two frames we alloted */ + param_save_area_offset = bpf_frame_size; param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */ for (int i = 8; i < nr_regs; i++) { @@ -739,10 +726,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im void *func_addr) { int regs_off, nregs_off, ip_off, run_ctx_off, retval_off, nvr_off, alt_lr_off, r4_off = 0; - int i, ret, nr_regs, bpf_frame_size = 0, bpf_dummy_frame_size = 0, func_frame_offset; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; + int i, ret, nr_regs, retaddr_off, bpf_frame_size = 0; struct codegen_context codegen_ctx, *ctx; u32 *image = (u32 *)rw_image; ppc_inst_t branch_insn; @@ -768,16 +755,11 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * Generated stack layout: * * func prev back chain [ back chain ] - * [ ] - * bpf prog redzone/tailcallcnt [ ... ] 64 bytes (64-bit powerpc) - * [ ] -- - * LR save area [ r0 save (64-bit) ] | header - * [ r0 save (32-bit) ] | - * dummy frame for unwind [ back chain 1 ] -- * [ tail_call_info ] optional - 64-bit powerpc * [ padding ] align stack frame * r4_off [ r4 (tailcallcnt) ] optional - 32-bit powerpc * alt_lr_off [ real lr (ool stub)] optional - actual lr + * retaddr_off [ return address ] * [ r26 ] * nvr_off [ r25 ] nvr save area * retval_off [ return value ] @@ -841,6 +823,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im nvr_off = bpf_frame_size; bpf_frame_size += 2 * SZL; + /* Save area for return address */ + retaddr_off = bpf_frame_size; + bpf_frame_size += SZL; + /* Optional save area for actual LR in case of ool ftrace */ if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { alt_lr_off = bpf_frame_size; @@ -867,16 +853,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im /* Padding to align stack frame, if any */ bpf_frame_size = round_up(bpf_frame_size, SZL * 2); - /* Dummy frame size for proper unwind - includes 64-bytes red zone for 64-bit powerpc */ - bpf_dummy_frame_size = STACK_FRAME_MIN_SIZE + 64; - - /* Offset to the traced function's stack frame */ - func_frame_offset = bpf_dummy_frame_size + bpf_frame_size; - - /* Create dummy frame for unwind, store original return value */ + /* Store original return value */ EMIT(PPC_RAW_STL(_R0, _R1, PPC_LR_STKOFF)); - /* Protect red zone where tail call count goes */ - EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_dummy_frame_size)); /* Create our stack frame */ EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_frame_size)); @@ -891,14 +869,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im if (IS_ENABLED(CONFIG_PPC32) && nr_regs < 2) EMIT(PPC_RAW_STL(_R4, _R1, r4_off)); - bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off); + bpf_trampoline_save_args(image, ctx, bpf_frame_size, nr_regs, regs_off); /* Save our LR/return address */ EMIT(PPC_RAW_MFLR(_R3)); if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off)); else - EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); + EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off)); /* * Derive IP address of the traced function. @@ -925,9 +903,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im EMIT(PPC_RAW_STL(_R3, _R1, ip_off)); if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { - /* Fake our LR for unwind */ + /* Fake our LR for BPF_TRAMP_F_CALL_ORIG case */ EMIT(PPC_RAW_ADDI(_R3, _R3, 4)); - EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); + EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off)); } /* Save function arg count -- see bpf_get_func_arg_cnt() */ @@ -966,20 +944,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im /* Call the traced function */ if (flags & BPF_TRAMP_F_CALL_ORIG) { /* - * The address in LR save area points to the correct point in the original function + * retaddr on trampoline stack points to the correct point in the original function * with both PPC_FTRACE_OUT_OF_LINE as well as with traditional ftrace instruction * sequence */ - EMIT(PPC_RAW_LL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF)); + EMIT(PPC_RAW_LL(_R3, _R1, retaddr_off)); EMIT(PPC_RAW_MTCTR(_R3)); /* Replicate tail_call_cnt before calling the original BPF prog */ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) - bpf_trampoline_setup_tail_call_info(image, ctx, func_frame_offset, - bpf_dummy_frame_size, r4_off); + bpf_trampoline_setup_tail_call_info(image, ctx, bpf_frame_size, r4_off); /* Restore args */ - bpf_trampoline_restore_args_stack(image, ctx, func_frame_offset, nr_regs, regs_off); + bpf_trampoline_restore_args_stack(image, ctx, bpf_frame_size, nr_regs, regs_off); /* Restore TOC for 64-bit */ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) @@ -993,7 +970,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im /* Restore updated tail_call_cnt */ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) - bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off); + bpf_trampoline_restore_tail_call_cnt(image, ctx, bpf_frame_size, r4_off); /* Reserve space to patch branch instruction to skip fexit progs */ if (ro_image) /* image is NULL for dummy pass */ @@ -1045,7 +1022,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im EMIT(PPC_RAW_LD(_R2, _R1, 24)); if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* Skip the traced function and return to parent */ - EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset)); + EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size)); EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF)); EMIT(PPC_RAW_MTLR(_R0)); EMIT(PPC_RAW_BLR()); @@ -1053,13 +1030,13 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { EMIT(PPC_RAW_LL(_R0, _R1, alt_lr_off)); EMIT(PPC_RAW_MTLR(_R0)); - EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset)); + EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size)); EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF)); EMIT(PPC_RAW_BLR()); } else { - EMIT(PPC_RAW_LL(_R0, _R1, bpf_frame_size + PPC_LR_STKOFF)); + EMIT(PPC_RAW_LL(_R0, _R1, retaddr_off)); EMIT(PPC_RAW_MTCTR(_R0)); - EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset)); + EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size)); EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF)); EMIT(PPC_RAW_MTLR(_R0)); EMIT(PPC_RAW_BCTR()); From 51b8de4b3d27ec12128fa2405e526c527a77ae65 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 3 Mar 2026 23:40:29 +0530 Subject: [PATCH 200/487] powerpc64/bpf: fix handling of BPF stack in exception callback Exception callback reuses the stack frame of exception boundary. When exception boundary and exception callback programs have different BPF stack depth, the current stack unwind in exception callback will fail. Adjust the stack frame size of exception callback, in its prologue, if its BPF stack depth is different from that of exception boundary. Reported-by: bot+bpf-ci@kernel.org Closes: https://lore.kernel.org/bpf/2a310e86a59eb4c44c3ac9e5647814469d9c955580c9c0f1b3d9ca4a44717a34@mail.kernel.org/ Fixes: 11d45eee9f42 ("powerpc64/bpf: Additional NVR handling for bpf_throw") Signed-off-by: Hari Bathini Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303181031.390073-6-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit_comp64.c | 36 +++++++++++++++++++++---------- 1 file changed, 25 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 7655be76f537..04e76440d1ad 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -32,14 +32,15 @@ * * [ prev sp ] <------------- * [ tail_call_info ] 8 | - * [ nv gpr save area ] 6*8 + (12*8) | + * [ nv gpr save area ] (6 * 8) | + * [ addl. nv gpr save area] (12 * 8) | <--- exception boundary/callback program * [ local_tmp_var ] 24 | * fp (r31) --> [ ebpf stack space ] upto 512 | * [ frame header ] 32/112 | * sp (r1) ---> [ stack pointer ] -------------- * - * Additional (12*8) in 'nv gpr save area' only in case of - * exception boundary. + * Additional (12 * 8) in 'nv gpr save area' only in case of + * exception boundary/callback. */ /* BPF non-volatile registers save area size */ @@ -51,7 +52,7 @@ * for additional non volatile registers(r14-r25) to be saved * at exception boundary */ -#define BPF_PPC_EXC_STACK_SAVE (12*8) +#define BPF_PPC_EXC_STACK_SAVE (12 * 8) /* stack frame excluding BPF stack, ensure this is quadword aligned */ #define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ @@ -128,12 +129,13 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- * [ tail_call_info ] 8 - * [ nv gpr save area ] 6*8 + (12*8) + * [ nv gpr save area ] (6 * 8) + * [ addl. nv gpr save area] (12 * 8) <--- exception boundary/callback program * [ local_tmp_var ] 24 * [ unused red zone ] 224 * - * Additional (12*8) in 'nv gpr save area' only in case of - * exception boundary. + * Additional (12 * 8) in 'nv gpr save area' only in case of + * exception boundary/callback. */ static int bpf_jit_stack_local(struct codegen_context *ctx) { @@ -240,10 +242,6 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) if (bpf_has_stack_frame(ctx) && !ctx->exception_cb) { /* - * exception_cb uses boundary frame after stack walk. - * It can simply use redzone, this optimization reduces - * stack walk loop by one level. - * * We need a stack frame, but we don't necessarily need to * save/restore LR unless we call other functions */ @@ -287,6 +285,22 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) * program(main prog) as third arg */ EMIT(PPC_RAW_MR(_R1, _R5)); + /* + * Exception callback reuses the stack frame of exception boundary. + * But BPF stack depth of exception callback and exception boundary + * don't have to be same. If BPF stack depth is different, adjust the + * stack frame size considering BPF stack depth of exception callback. + * The non-volatile register save area remains unchanged. These non- + * volatile registers are restored in exception callback's epilogue. + */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R5, 0)); + EMIT(PPC_RAW_SUB(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_1), _R1)); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), + -BPF_PPC_EXC_STACKFRAME)); + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), ctx->stack_size)); + PPC_BCC_CONST_SHORT(COND_EQ, 12); + EMIT(PPC_RAW_MR(_R1, bpf_to_ppc(TMP_REG_1))); + EMIT(PPC_RAW_STDU(_R1, _R1, -(BPF_PPC_EXC_STACKFRAME + ctx->stack_size))); } /* From 01b6ac72729610ae732ca2a66e3a642e23f6cd60 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 3 Mar 2026 23:40:30 +0530 Subject: [PATCH 201/487] powerpc64/bpf: fix kfunc call support Commit 61688a82e047 ("powerpc/bpf: enable kfunc call") inadvertently enabled kfunc call support for 32-bit powerpc but that support will not be possible until ABI mismatch between 32-bit powerpc and eBPF is handled in 32-bit powerpc JIT code. Till then, advertise support only for 64-bit powerpc. Also, in powerpc ABI, caller needs to extend the arguments properly based on signedness. The JIT code is responsible for handling this explicitly for kfunc calls as verifier can't handle this for each architecture-specific ABI needs. But this was not taken care of while kfunc call support was enabled for powerpc. Fix it by handling this with bpf_jit_find_kfunc_model() and using zero_extend() & sign_extend() helper functions. Fixes: 61688a82e047 ("powerpc/bpf: enable kfunc call") Cc: stable@vger.kernel.org Signed-off-by: Hari Bathini Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303181031.390073-7-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit_comp.c | 2 +- arch/powerpc/net/bpf_jit_comp64.c | 101 +++++++++++++++++++++++++++--- 2 files changed, 94 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 85457bcb2040..a62a9a92b7b5 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -450,7 +450,7 @@ bool bpf_jit_supports_subprog_tailcalls(void) bool bpf_jit_supports_kfunc_call(void) { - return true; + return IS_ENABLED(CONFIG_PPC64); } bool bpf_jit_supports_arena(void) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 04e76440d1ad..c5e26d231cd5 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -499,6 +499,83 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context * return 0; } +static int zero_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size) +{ + switch (size) { + case 1: + /* zero-extend 8 bits into 64 bits */ + EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 56)); + return 0; + case 2: + /* zero-extend 16 bits into 64 bits */ + EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 48)); + return 0; + case 4: + /* zero-extend 32 bits into 64 bits */ + EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 32)); + fallthrough; + case 8: + /* Nothing to do */ + return 0; + default: + return -1; + } +} + +static int sign_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size) +{ + switch (size) { + case 1: + /* sign-extend 8 bits into 64 bits */ + EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); + return 0; + case 2: + /* sign-extend 16 bits into 64 bits */ + EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); + return 0; + case 4: + /* sign-extend 32 bits into 64 bits */ + EMIT(PPC_RAW_EXTSW(dst_reg, src_reg)); + fallthrough; + case 8: + /* Nothing to do */ + return 0; + default: + return -1; + } +} + +/* + * Handle powerpc ABI expectations from caller: + * - Unsigned arguments are zero-extended. + * - Signed arguments are sign-extended. + */ +static int prepare_for_kfunc_call(const struct bpf_prog *fp, u32 *image, + struct codegen_context *ctx, + const struct bpf_insn *insn) +{ + const struct btf_func_model *m = bpf_jit_find_kfunc_model(fp, insn); + int i; + + if (!m) + return -1; + + for (i = 0; i < m->nr_args; i++) { + /* Note that BPF ABI only allows up to 5 args for kfuncs */ + u32 reg = bpf_to_ppc(BPF_REG_1 + i), size = m->arg_size[i]; + + if (!(m->arg_flags[i] & BTF_FMODEL_SIGNED_ARG)) { + if (zero_extend(image, ctx, reg, reg, size)) + return -1; + } else { + if (sign_extend(image, ctx, reg, reg, size)) + return -1; + } + } + + return 0; +} + static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* @@ -1143,14 +1220,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code /* special mov32 for zext */ EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31)); break; - } else if (off == 8) { - EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); - } else if (off == 16) { - EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); - } else if (off == 32) { - EMIT(PPC_RAW_EXTSW(dst_reg, src_reg)); - } else if (dst_reg != src_reg) - EMIT(PPC_RAW_MR(dst_reg, src_reg)); + } + if (off == 0) { + /* MOV */ + if (dst_reg != src_reg) + EMIT(PPC_RAW_MR(dst_reg, src_reg)); + } else { + /* MOVSX: dst = (s8,s16,s32)src (off = 8,16,32) */ + if (sign_extend(image, ctx, src_reg, dst_reg, off / 8)) + return -1; + } goto bpf_alu32_trunc; case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */ case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */ @@ -1618,6 +1697,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code if (ret < 0) return ret; + /* Take care of powerpc ABI requirements before kfunc call */ + if (insn[i].src_reg == BPF_PSEUDO_KFUNC_CALL) { + if (prepare_for_kfunc_call(fp, image, ctx, &insn[i])) + return -1; + } + ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr); if (ret) return ret; From 202d23eeccd4b12047869538d6fb91d1e42c4ddd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2026 17:04:08 +0100 Subject: [PATCH 202/487] dt-bindings: powerpc: Add Freescale/NXP MPC83xx SoCs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new binding for MPC83xx platforms, describing the board compatible strings used in currently existing device trees. Note that the SoC bus is called immr@... in many existing devicetrees, but this contradicts the simple-bus binding. Reviewed-by: Rob Herring (Arm) Reviewed-by: Christophe Leroy Signed-off-by: J. Neuschäfer Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303-ppcyaml-soc-v5-1-2982d5a857bc@posteo.net --- .../bindings/powerpc/fsl/fsl,mpc83xx.yaml | 93 +++++++++++++++++++ 1 file changed, 93 insertions(+) create mode 100644 Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml diff --git a/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml b/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml new file mode 100644 index 000000000000..9e37d155c582 --- /dev/null +++ b/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml @@ -0,0 +1,93 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/powerpc/fsl/fsl,mpc83xx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale PowerQUICC II Pro (MPC83xx) platforms + +maintainers: + - J. Neuschäfer + +properties: + $nodename: + const: '/' + compatible: + oneOf: + - description: MPC83xx Reference Design Boards + items: + - enum: + - fsl,mpc8308rdb + - fsl,mpc8315erdb + - fsl,mpc8360rdk + - fsl,mpc8377rdb + - fsl,mpc8377wlan + - fsl,mpc8378rdb + - fsl,mpc8379rdb + + - description: MPC8313E Reference Design Board + items: + - const: MPC8313ERDB + - const: MPC831xRDB + - const: MPC83xxRDB + + - description: MPC8323E Reference Design Board + items: + - const: MPC8323ERDB + - const: MPC832xRDB + - const: MPC83xxRDB + + - description: MPC8349E-mITX(-GP) Reference Design Platform + items: + - enum: + - MPC8349EMITX + - MPC8349EMITXGP + - const: MPC834xMITX + - const: MPC83xxMITX + + - description: Keymile KMETER1 board + const: keymile,KMETER1 + + - description: MPC8308 P1M board + const: denx,mpc8308_p1m + +patternProperties: + "^soc@.*$": + type: object + properties: + compatible: + oneOf: + - items: + - enum: + - fsl,mpc8315-immr + - fsl,mpc8308-immr + - const: simple-bus + - items: + - const: fsl,mpc8360-immr + - const: fsl,immr + - const: fsl,soc + - const: simple-bus + - const: simple-bus + +additionalProperties: true + +examples: + - | + / { + compatible = "fsl,mpc8315erdb"; + model = "MPC8315E-RDB"; + #address-cells = <1>; + #size-cells = <1>; + + soc@e0000000 { + compatible = "fsl,mpc8315-immr", "simple-bus"; + reg = <0xe0000000 0x00000200>; + #address-cells = <1>; + #size-cells = <1>; + device_type = "soc"; + ranges = <0 0xe0000000 0x00100000>; + bus-frequency = <0>; + }; + }; + +... From 691417ffe7821721e0a28bd25ad8c0dc0d4ae4ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2026 16:31:42 +0100 Subject: [PATCH 203/487] powerpc: 83xx: km83xx: Fix keymile vendor prefix MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When kmeter.c was refactored into km83xx.c in 2011, the "keymile" vendor prefix was changed to upper-case "Keymile". The devicetree at arch/powerpc/boot/dts/kmeter1.dts never underwent the same change, suggesting that this was simply a mistake. Fixes: 93e2b95c81042d ("powerpc/83xx: rename and update kmeter1") Signed-off-by: J. Neuschäfer Reviewed-by: Heiko Schocher Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303-keymile-v1-1-463a11e71702@posteo.net --- arch/powerpc/platforms/83xx/km83xx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index 2b5d187d9b62..9ef8fb39dd1b 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -155,8 +155,8 @@ machine_device_initcall(mpc83xx_km, mpc83xx_declare_of_platform_devices); /* list of the supported boards */ static char *board[] __initdata = { - "Keymile,KMETER1", - "Keymile,kmpbec8321", + "keymile,KMETER1", + "keymile,kmpbec8321", NULL }; From 38ce944d47b717cac6b5f2bae9dd247f87f21ac7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2026 16:50:51 +0100 Subject: [PATCH 204/487] powerpc: dts: mpc8313erdb: Use IRQ_TYPE_* macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This increases readability, because "0x8" isn't very descriptive. mpc8313erdb.dtb remains identical after this patch. Signed-off-by: J. Neuschäfer Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-1-187d3a13effa@posteo.net --- arch/powerpc/boot/dts/mpc8313erdb.dts | 59 +++++++++++++++------------ 1 file changed, 34 insertions(+), 25 deletions(-) diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts index 09508b4c8c73..137217d377e9 100644 --- a/arch/powerpc/boot/dts/mpc8313erdb.dts +++ b/arch/powerpc/boot/dts/mpc8313erdb.dts @@ -6,6 +6,7 @@ */ /dts-v1/; +#include / { model = "MPC8313ERDB"; @@ -48,7 +49,7 @@ localbus@e0005000 { #size-cells = <1>; compatible = "fsl,mpc8313-elbc", "fsl,elbc", "simple-bus"; reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; + interrupts = <77 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; // CS0 and CS1 are swapped when @@ -118,7 +119,7 @@ i2c@3000 { cell-index = <0>; compatible = "fsl-i2c"; reg = <0x3000 0x100>; - interrupts = <14 0x8>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; dfsrr; rtc@68 { @@ -131,7 +132,7 @@ crypto@30000 { compatible = "fsl,sec2.2", "fsl,sec2.1", "fsl,sec2.0"; reg = <0x30000 0x10000>; - interrupts = <11 0x8>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,num-channels = <1>; fsl,channel-fifo-len = <24>; @@ -146,7 +147,7 @@ i2c@3100 { cell-index = <1>; compatible = "fsl-i2c"; reg = <0x3100 0x100>; - interrupts = <15 0x8>; + interrupts = <15 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; dfsrr; }; @@ -155,7 +156,7 @@ spi@7000 { cell-index = <0>; compatible = "fsl,spi"; reg = <0x7000 0x1000>; - interrupts = <16 0x8>; + interrupts = <16 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; mode = "cpu"; }; @@ -167,7 +168,7 @@ usb@23000 { #address-cells = <1>; #size-cells = <0>; interrupt-parent = <&ipic>; - interrupts = <38 0x8>; + interrupts = <38 IRQ_TYPE_LEVEL_LOW>; phy_type = "utmi_wide"; sleep = <&pmc 0x00300000>; }; @@ -175,7 +176,8 @@ usb@23000 { ptp_clock@24E00 { compatible = "fsl,etsec-ptp"; reg = <0x24E00 0xB0>; - interrupts = <12 0x8 13 0x8>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>, + <13 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = < &ipic >; fsl,tclk-period = <10>; fsl,tmr-prsc = <100>; @@ -197,7 +199,9 @@ enet0: ethernet@24000 { compatible = "gianfar"; reg = <0x24000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <37 0x8 36 0x8 35 0x8>; + interrupts = <37 IRQ_TYPE_LEVEL_LOW>, + <36 IRQ_TYPE_LEVEL_LOW>, + <35 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = < &tbi0 >; /* Vitesse 7385 isn't on the MDIO bus */ @@ -211,7 +215,7 @@ mdio@520 { reg = <0x520 0x20>; phy4: ethernet-phy@4 { interrupt-parent = <&ipic>; - interrupts = <20 0x8>; + interrupts = <20 IRQ_TYPE_LEVEL_LOW>; reg = <0x4>; }; tbi0: tbi-phy@11 { @@ -231,7 +235,9 @@ enet1: ethernet@25000 { reg = <0x25000 0x1000>; ranges = <0x0 0x25000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <34 0x8 33 0x8 32 0x8>; + interrupts = <34 IRQ_TYPE_LEVEL_LOW>, + <33 IRQ_TYPE_LEVEL_LOW>, + <32 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = < &tbi1 >; phy-handle = < &phy4 >; @@ -259,7 +265,7 @@ serial0: serial@4500 { compatible = "fsl,ns16550", "ns16550"; reg = <0x4500 0x100>; clock-frequency = <0>; - interrupts = <9 0x8>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -269,15 +275,12 @@ serial1: serial@4600 { compatible = "fsl,ns16550", "ns16550"; reg = <0x4600 0x100>; clock-frequency = <0>; - interrupts = <10 0x8>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; /* IPIC - * interrupts cell = - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change + * interrupts cell = */ ipic: pic@700 { interrupt-controller; @@ -290,7 +293,7 @@ ipic: pic@700 { pmc: power@b00 { compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc"; reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 8>; + interrupts = <80 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,mpc8313-wakeup-timer = <>m1>; @@ -306,14 +309,20 @@ pmc: power@b00 { gtm1: timer@500 { compatible = "fsl,mpc8313-gtm", "fsl,gtm"; reg = <0x500 0x100>; - interrupts = <90 8 78 8 84 8 72 8>; + interrupts = <90 IRQ_TYPE_LEVEL_LOW>, + <78 IRQ_TYPE_LEVEL_LOW>, + <84 IRQ_TYPE_LEVEL_LOW>, + <72 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; timer@600 { compatible = "fsl,mpc8313-gtm", "fsl,gtm"; reg = <0x600 0x100>; - interrupts = <91 8 79 8 85 8 73 8>; + interrupts = <91 IRQ_TYPE_LEVEL_LOW>, + <79 IRQ_TYPE_LEVEL_LOW>, + <85 IRQ_TYPE_LEVEL_LOW>, + <73 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; }; @@ -341,7 +350,7 @@ pci0: pci@e0008500 { 0x7800 0x0 0x0 0x3 &ipic 17 0x8 0x7800 0x0 0x0 0x4 &ipic 18 0x8>; interrupt-parent = <&ipic>; - interrupts = <66 0x8>; + interrupts = <66 IRQ_TYPE_LEVEL_LOW>; bus-range = <0x0 0x0>; ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 @@ -363,14 +372,14 @@ dma@82a8 { reg = <0xe00082a8 4>; ranges = <0 0xe0008100 0x1a8>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; dma-channel@0 { compatible = "fsl,mpc8313-dma-channel", "fsl,elo-dma-channel"; reg = <0 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <0>; }; @@ -379,7 +388,7 @@ dma-channel@80 { "fsl,elo-dma-channel"; reg = <0x80 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <1>; }; @@ -388,7 +397,7 @@ dma-channel@100 { "fsl,elo-dma-channel"; reg = <0x100 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <2>; }; @@ -397,7 +406,7 @@ dma-channel@180 { "fsl,elo-dma-channel"; reg = <0x180 0x28>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <3>; }; }; From 4f439747811977d05a87da65c1ae11246d4f4dee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2026 16:50:52 +0100 Subject: [PATCH 205/487] powerpc: dts: mpc8315erdb: Use IRQ_TYPE_* macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This increases readability, because "0x8" isn't very descriptive. mpc8315erdb.dtb remains identical after this patch. Signed-off-by: J. Neuschäfer Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-2-187d3a13effa@posteo.net --- arch/powerpc/boot/dts/mpc8315erdb.dts | 111 ++++++++++++++------------ 1 file changed, 59 insertions(+), 52 deletions(-) diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index a8f68d6e50b0..1957b6687b29 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -50,7 +50,7 @@ localbus@e0005000 { #size-cells = <1>; compatible = "fsl,mpc8315-elbc", "fsl,elbc", "simple-bus"; reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; + interrupts = <77 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; // CS0 and CS1 are swapped when @@ -112,7 +112,7 @@ i2c@3000 { cell-index = <0>; compatible = "fsl-i2c"; reg = <0x3000 0x100>; - interrupts = <14 0x8>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; dfsrr; rtc@68 { @@ -133,7 +133,7 @@ spi@7000 { cell-index = <0>; compatible = "fsl,spi"; reg = <0x7000 0x1000>; - interrupts = <16 0x8>; + interrupts = <16 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; mode = "cpu"; }; @@ -145,35 +145,35 @@ dma@82a8 { reg = <0x82a8 4>; ranges = <0 0x8100 0x1a8>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; cell-index = <0>; dma-channel@0 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0 0x80>; cell-index = <0>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; dma-channel@80 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0x80 0x80>; cell-index = <1>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; dma-channel@100 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0x100 0x80>; cell-index = <2>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; dma-channel@180 { compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel"; reg = <0x180 0x28>; cell-index = <3>; interrupt-parent = <&ipic>; - interrupts = <71 8>; + interrupts = <71 IRQ_TYPE_LEVEL_LOW>; }; }; @@ -183,7 +183,7 @@ usb@23000 { #address-cells = <1>; #size-cells = <0>; interrupt-parent = <&ipic>; - interrupts = <38 0x8>; + interrupts = <38 IRQ_TYPE_LEVEL_LOW>; phy_type = "utmi"; }; @@ -197,7 +197,9 @@ enet0: ethernet@24000 { reg = <0x24000 0x1000>; ranges = <0x0 0x24000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 0x8 33 0x8 34 0x8>; + interrupts = <32 IRQ_TYPE_LEVEL_LOW>, + <33 IRQ_TYPE_LEVEL_LOW>, + <34 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = <&tbi0>; phy-handle = < &phy0 >; @@ -238,7 +240,9 @@ enet1: ethernet@25000 { reg = <0x25000 0x1000>; ranges = <0x0 0x25000 0x1000>; local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <35 0x8 36 0x8 37 0x8>; + interrupts = <35 IRQ_TYPE_LEVEL_LOW>, + <36 IRQ_TYPE_LEVEL_LOW>, + <37 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; tbi-handle = <&tbi1>; phy-handle = < &phy1 >; @@ -263,7 +267,7 @@ serial0: serial@4500 { compatible = "fsl,ns16550", "ns16550"; reg = <0x4500 0x100>; clock-frequency = <133333333>; - interrupts = <9 0x8>; + interrupts = <9 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -273,7 +277,7 @@ serial1: serial@4600 { compatible = "fsl,ns16550", "ns16550"; reg = <0x4600 0x100>; clock-frequency = <133333333>; - interrupts = <10 0x8>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -282,7 +286,7 @@ crypto@30000 { "fsl,sec2.4", "fsl,sec2.2", "fsl,sec2.1", "fsl,sec2.0"; reg = <0x30000 0x10000>; - interrupts = <11 0x8>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,num-channels = <4>; fsl,channel-fifo-len = <24>; @@ -294,7 +298,7 @@ sata@18000 { compatible = "fsl,mpc8315-sata", "fsl,pq-sata"; reg = <0x18000 0x1000>; cell-index = <1>; - interrupts = <44 0x8>; + interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; @@ -302,14 +306,17 @@ sata@19000 { compatible = "fsl,mpc8315-sata", "fsl,pq-sata"; reg = <0x19000 0x1000>; cell-index = <2>; - interrupts = <45 0x8>; + interrupts = <45 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; }; gtm1: timer@500 { compatible = "fsl,mpc8315-gtm", "fsl,gtm"; reg = <0x500 0x100>; - interrupts = <90 8 78 8 84 8 72 8>; + interrupts = <90 IRQ_TYPE_LEVEL_LOW>, + <78 IRQ_TYPE_LEVEL_LOW>, + <84 IRQ_TYPE_LEVEL_LOW>, + <72 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; clock-frequency = <133333333>; }; @@ -317,16 +324,16 @@ gtm1: timer@500 { timer@600 { compatible = "fsl,mpc8315-gtm", "fsl,gtm"; reg = <0x600 0x100>; - interrupts = <91 8 79 8 85 8 73 8>; + interrupts = <91 IRQ_TYPE_LEVEL_LOW>, + <79 IRQ_TYPE_LEVEL_LOW>, + <85 IRQ_TYPE_LEVEL_LOW>, + <73 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; clock-frequency = <133333333>; }; /* IPIC - * interrupts cell = - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change + * interrupts cell = */ ipic: interrupt-controller@700 { interrupt-controller; @@ -340,14 +347,14 @@ ipic-msi@7c0 { compatible = "fsl,ipic-msi"; reg = <0x7c0 0x40>; msi-available-ranges = <0 0x100>; - interrupts = <0x43 0x8 - 0x4 0x8 - 0x51 0x8 - 0x52 0x8 - 0x56 0x8 - 0x57 0x8 - 0x58 0x8 - 0x59 0x8>; + interrupts = <0x43 IRQ_TYPE_LEVEL_LOW + 0x4 IRQ_TYPE_LEVEL_LOW + 0x51 IRQ_TYPE_LEVEL_LOW + 0x52 IRQ_TYPE_LEVEL_LOW + 0x56 IRQ_TYPE_LEVEL_LOW + 0x57 IRQ_TYPE_LEVEL_LOW + 0x58 IRQ_TYPE_LEVEL_LOW + 0x59 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = < &ipic >; }; @@ -355,7 +362,7 @@ pmc: power@b00 { compatible = "fsl,mpc8315-pmc", "fsl,mpc8313-pmc", "fsl,mpc8349-pmc"; reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 8>; + interrupts = <80 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; fsl,mpc8313-wakeup-timer = <>m1>; }; @@ -374,24 +381,24 @@ pci0: pci@e0008500 { interrupt-map-mask = <0xf800 0x0 0x0 0x7>; interrupt-map = < /* IDSEL 0x0E -mini PCI */ - 0x7000 0x0 0x0 0x1 &ipic 18 0x8 - 0x7000 0x0 0x0 0x2 &ipic 18 0x8 - 0x7000 0x0 0x0 0x3 &ipic 18 0x8 - 0x7000 0x0 0x0 0x4 &ipic 18 0x8 + 0x7000 0x0 0x0 0x1 &ipic 18 IRQ_TYPE_LEVEL_LOW + 0x7000 0x0 0x0 0x2 &ipic 18 IRQ_TYPE_LEVEL_LOW + 0x7000 0x0 0x0 0x3 &ipic 18 IRQ_TYPE_LEVEL_LOW + 0x7000 0x0 0x0 0x4 &ipic 18 IRQ_TYPE_LEVEL_LOW /* IDSEL 0x0F -mini PCI */ - 0x7800 0x0 0x0 0x1 &ipic 17 0x8 - 0x7800 0x0 0x0 0x2 &ipic 17 0x8 - 0x7800 0x0 0x0 0x3 &ipic 17 0x8 - 0x7800 0x0 0x0 0x4 &ipic 17 0x8 + 0x7800 0x0 0x0 0x1 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x7800 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x7800 0x0 0x0 0x3 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x7800 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW /* IDSEL 0x10 - PCI slot */ - 0x8000 0x0 0x0 0x1 &ipic 48 0x8 - 0x8000 0x0 0x0 0x2 &ipic 17 0x8 - 0x8000 0x0 0x0 0x3 &ipic 48 0x8 - 0x8000 0x0 0x0 0x4 &ipic 17 0x8>; + 0x8000 0x0 0x0 0x1 &ipic 48 IRQ_TYPE_LEVEL_LOW + 0x8000 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW + 0x8000 0x0 0x0 0x3 &ipic 48 IRQ_TYPE_LEVEL_LOW + 0x8000 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; - interrupts = <66 0x8>; + interrupts = <66 IRQ_TYPE_LEVEL_LOW>; bus-range = <0x0 0x0>; ranges = <0x02000000 0 0x90000000 0x90000000 0 0x10000000 0x42000000 0 0x80000000 0x80000000 0 0x10000000 @@ -417,10 +424,10 @@ pci1: pcie@e0009000 { 0x01000000 0 0x00000000 0xb1000000 0 0x00800000>; bus-range = <0 255>; interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 1 8 - 0 0 0 2 &ipic 1 8 - 0 0 0 3 &ipic 1 8 - 0 0 0 4 &ipic 1 8>; + interrupt-map = <0 0 0 1 &ipic 1 IRQ_TYPE_LEVEL_LOW + 0 0 0 2 &ipic 1 IRQ_TYPE_LEVEL_LOW + 0 0 0 3 &ipic 1 IRQ_TYPE_LEVEL_LOW + 0 0 0 4 &ipic 1 IRQ_TYPE_LEVEL_LOW>; clock-frequency = <0>; pcie@0 { @@ -448,10 +455,10 @@ pci2: pcie@e000a000 { 0x01000000 0 0x00000000 0xd1000000 0 0x00800000>; bus-range = <0 255>; interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 2 8 - 0 0 0 2 &ipic 2 8 - 0 0 0 3 &ipic 2 8 - 0 0 0 4 &ipic 2 8>; + interrupt-map = <0 0 0 1 &ipic 2 IRQ_TYPE_LEVEL_LOW + 0 0 0 2 &ipic 2 IRQ_TYPE_LEVEL_LOW + 0 0 0 3 &ipic 2 IRQ_TYPE_LEVEL_LOW + 0 0 0 4 &ipic 2 IRQ_TYPE_LEVEL_LOW>; clock-frequency = <0>; pcie@0 { From 31618e0e21c4633c365b26e6d45cae2084f4245b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2026 16:50:53 +0100 Subject: [PATCH 206/487] powerpc: dts: mpc8315erdb: Rename LED nodes to comply with schema MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The leds-gpio.yaml schema requires that GPIO LED nodes contain "led", and preferably start with "led-" Signed-off-by: J. Neuschäfer Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-3-187d3a13effa@posteo.net --- arch/powerpc/boot/dts/mpc8315erdb.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index 1957b6687b29..f4938a7292b9 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -478,12 +478,12 @@ pcie@0 { leds { compatible = "gpio-leds"; - pwr { + led-pwr { gpios = <&mcu_pio 0 0>; default-state = "on"; }; - hdd { + led-hdd { gpios = <&mcu_pio 1 0>; linux,default-trigger = "disk-activity"; }; From fde54f1a4dc7bfd83908380c0b4b6a830a0f9e01 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2026 16:50:54 +0100 Subject: [PATCH 207/487] powerpc: dts: mpc8315erdb: Add missing #cells properties to SPI bus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These properties are required by the spi-controller binding. Signed-off-by: J. Neuschäfer Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-4-187d3a13effa@posteo.net --- arch/powerpc/boot/dts/mpc8315erdb.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index f4938a7292b9..0b087180e181 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -135,6 +135,8 @@ spi@7000 { reg = <0x7000 0x1000>; interrupts = <16 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&ipic>; + #address-cells = <1>; + #size-cells = <0>; mode = "cpu"; }; From 6373a2b5c878e920341d7bda84ac1126f72e6a68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2026 16:50:55 +0100 Subject: [PATCH 208/487] powerpc: dts: mpc83xx: Add unit addresses to /memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes dtschema warnings such as the following: arch/powerpc/boot/dts/mpc8315erdb.dtb: /: memory: False schema does not allow {'device_type': ['memory'], 'reg': [[0, 134217728]]} Signed-off-by: J. Neuschäfer Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-5-187d3a13effa@posteo.net --- arch/powerpc/boot/dts/asp834x-redboot.dts | 2 +- arch/powerpc/boot/dts/mpc8308_p1m.dts | 2 +- arch/powerpc/boot/dts/mpc8308rdb.dts | 2 +- arch/powerpc/boot/dts/mpc8313erdb.dts | 2 +- arch/powerpc/boot/dts/mpc8315erdb.dts | 2 +- arch/powerpc/boot/dts/mpc832x_rdb.dts | 2 +- arch/powerpc/boot/dts/mpc8349emitx.dts | 2 +- arch/powerpc/boot/dts/mpc8349emitxgp.dts | 2 +- arch/powerpc/boot/dts/mpc8377_rdb.dts | 2 +- arch/powerpc/boot/dts/mpc8377_wlan.dts | 2 +- arch/powerpc/boot/dts/mpc8378_rdb.dts | 2 +- arch/powerpc/boot/dts/mpc8379_rdb.dts | 2 +- 12 files changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts index 33ddb17d1876..c541bd367983 100644 --- a/arch/powerpc/boot/dts/asp834x-redboot.dts +++ b/arch/powerpc/boot/dts/asp834x-redboot.dts @@ -37,7 +37,7 @@ PowerPC,8347@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x8000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts index 2638555afcc4..41f917f97dab 100644 --- a/arch/powerpc/boot/dts/mpc8308_p1m.dts +++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts @@ -37,7 +37,7 @@ PowerPC,8308@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts index af2ed8380a86..39ed26fba410 100644 --- a/arch/powerpc/boot/dts/mpc8308rdb.dts +++ b/arch/powerpc/boot/dts/mpc8308rdb.dts @@ -38,7 +38,7 @@ PowerPC,8308@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts index 137217d377e9..c9fe4dabc80a 100644 --- a/arch/powerpc/boot/dts/mpc8313erdb.dts +++ b/arch/powerpc/boot/dts/mpc8313erdb.dts @@ -39,7 +39,7 @@ PowerPC,8313@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index 0b087180e181..7ba1159f8803 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -40,7 +40,7 @@ PowerPC,8315@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts index ba7caaf98fd5..06f134490d95 100644 --- a/arch/powerpc/boot/dts/mpc832x_rdb.dts +++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts @@ -38,7 +38,7 @@ PowerPC,8323@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x04000000>; }; diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts index 13f17232ba83..12d33cb55b72 100644 --- a/arch/powerpc/boot/dts/mpc8349emitx.dts +++ b/arch/powerpc/boot/dts/mpc8349emitx.dts @@ -39,7 +39,7 @@ PowerPC,8349@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; }; diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts index eae0afd5abbc..2998a233a790 100644 --- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts +++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts @@ -37,7 +37,7 @@ PowerPC,8349@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; }; diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts index f137ccb8cfde..fb311a7eb9f2 100644 --- a/arch/powerpc/boot/dts/mpc8377_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts @@ -39,7 +39,7 @@ PowerPC,8377@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; // 256MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8377_wlan.dts b/arch/powerpc/boot/dts/mpc8377_wlan.dts index ce254dd74dd0..f736a15cceff 100644 --- a/arch/powerpc/boot/dts/mpc8377_wlan.dts +++ b/arch/powerpc/boot/dts/mpc8377_wlan.dts @@ -40,7 +40,7 @@ PowerPC,8377@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x20000000>; // 512MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts index 19e5473d4161..32c49622b404 100644 --- a/arch/powerpc/boot/dts/mpc8378_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts @@ -39,7 +39,7 @@ PowerPC,8378@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; // 256MB at 0 }; diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts index 61519acca228..07deb89c5a9b 100644 --- a/arch/powerpc/boot/dts/mpc8379_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts @@ -37,7 +37,7 @@ PowerPC,8379@0 { }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x10000000>; // 256MB at 0 }; From 35e4f2a17eb40288f9bcdb09549fa04a63a96279 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Mon, 2 Mar 2026 01:39:48 +0100 Subject: [PATCH 209/487] powerpc/pseries: Correct MSI allocation tracking The per-device MSI allocation calculation in pseries_irq_domain_alloc() is clearly wrong. It can still happen to work when nr_irqs is 1. Correct it. Fixes: c0215e2d72de ("powerpc/pseries: Fix MSI-X allocation failure when quota is exceeded") Cc: stable@vger.kernel.org Signed-off-by: Nam Cao Reviewed-by: Mahesh Salgaonkar Reviewed-by: Nilay Shroff [maddy: Fixed Nilay's reviewed-by tag] Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260302003948.1452016-1-namcao@linutronix.de --- arch/powerpc/platforms/pseries/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 64ffc6476ad6..8285b9a29fbf 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -605,7 +605,7 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq &pseries_msi_irq_chip, pseries_dev); } - pseries_dev->msi_used++; + pseries_dev->msi_used += nr_irqs; return 0; out: From 57ccf5ccdc56954f2a91a7f66684fd31c566bde5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 7 Mar 2026 04:53:32 -1000 Subject: [PATCH 210/487] sched_ext: Fix enqueue_task_scx() truncation of upper enqueue flags enqueue_task_scx() takes int enq_flags from the sched_class interface. SCX enqueue flags starting at bit 32 (SCX_ENQ_PREEMPT and above) are silently truncated when passed through activate_task(). extra_enq_flags was added as a workaround - storing high bits in rq->scx.extra_enq_flags and OR-ing them back in enqueue_task_scx(). However, the OR target is still the int parameter, so the high bits are lost anyway. The current impact is limited as the only affected flag is SCX_ENQ_PREEMPT which is informational to the BPF scheduler - its loss means the scheduler doesn't know about preemption but doesn't cause incorrect behavior. Fix by renaming the int parameter to core_enq_flags and introducing a u64 enq_flags local that merges both sources. All downstream functions already take u64 enq_flags. Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class") Cc: stable@vger.kernel.org # v6.12+ Acked-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index f323df7be180..174e3650d7fe 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1470,16 +1470,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at) p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; } -static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags) +static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags) { struct scx_sched *sch = scx_root; int sticky_cpu = p->scx.sticky_cpu; + u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags; if (enq_flags & ENQUEUE_WAKEUP) rq->scx.flags |= SCX_RQ_IN_WAKEUP; - enq_flags |= rq->scx.extra_enq_flags; - if (sticky_cpu >= 0) p->scx.sticky_cpu = -1; From 4ce7ada40c008fa21b7e52ab9d04e8746e2e9325 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Wed, 4 Mar 2026 08:46:03 -0800 Subject: [PATCH 211/487] scsi: core: Fix error handling for scsi_alloc_sdev() After scsi_sysfs_device_initialize() was called, error paths must call __scsi_remove_device(). Fixes: 1ac22c8eae81 ("scsi: core: Fix refcount leak for tagset_refcnt") Cc: stable@vger.kernel.org Signed-off-by: Junxiao Bi Reviewed-by: John Garry Reviewed-by: Bart Van Assche Link: https://patch.msgid.link/20260304164603.51528-1-junxiao.bi@oracle.com Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_scan.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 2cfcf1f5d6a4..7b11bc7de0e3 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -360,12 +360,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, * default device queue depth to figure out sbitmap shift * since we use this queue depth most of times. */ - if (scsi_realloc_sdev_budget_map(sdev, depth)) { - kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags); - put_device(&starget->dev); - kfree(sdev); - goto out; - } + if (scsi_realloc_sdev_budget_map(sdev, depth)) + goto out_device_destroy; scsi_change_queue_depth(sdev, depth); From b0bd84c39289ef6a6c3827dd52c875659291970a Mon Sep 17 00:00:00 2001 From: Wang Shuaiwei Date: Sat, 7 Mar 2026 11:51:28 +0800 Subject: [PATCH 212/487] scsi: ufs: core: Fix SError in ufshcd_rtc_work() during UFS suspend In __ufshcd_wl_suspend(), cancel_delayed_work_sync() is called to cancel the UFS RTC work, but it is placed after ufshcd_vops_suspend(hba, pm_op, POST_CHANGE). This creates a race condition where ufshcd_rtc_work() can still be running while ufshcd_vops_suspend() is executing. When UFSHCD_CAP_CLK_GATING is not supported, the condition !hba->clk_gating.active_reqs is always true, causing ufshcd_update_rtc() to be executed. Since ufshcd_vops_suspend() typically performs clock gating operations, executing ufshcd_update_rtc() at that moment triggers an SError. The kernel panic trace is as follows: Kernel panic - not syncing: Asynchronous SError Interrupt Call trace: dump_backtrace+0xec/0x128 show_stack+0x18/0x28 dump_stack_lvl+0x40/0xa0 dump_stack+0x18/0x24 panic+0x148/0x374 nmi_panic+0x3c/0x8c arm64_serror_panic+0x64/0x8c do_serror+0xc4/0xc8 el1h_64_error_handler+0x34/0x4c el1h_64_error+0x68/0x6c el1_interrupt+0x20/0x58 el1h_64_irq_handler+0x18/0x24 el1h_64_irq+0x68/0x6c ktime_get+0xc4/0x12c ufshcd_mcq_sq_stop+0x4c/0xec ufshcd_mcq_sq_cleanup+0x64/0x1dc ufshcd_clear_cmd+0x38/0x134 ufshcd_issue_dev_cmd+0x298/0x4d0 ufshcd_exec_dev_cmd+0x1a4/0x1c4 ufshcd_query_attr+0xbc/0x19c ufshcd_rtc_work+0x10c/0x1c8 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x120/0x1d8 ret_from_fork+0x10/0x20 Fix this by moving cancel_delayed_work_sync() before the call to ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE), ensuring the UFS RTC work is fully completed or cancelled at that point. Cc: Bean Huo Fixes: 6bf999e0eb41 ("scsi: ufs: core: Add UFS RTC support") Reviewed-by: Bart Van Assche Signed-off-by: Wang Shuaiwei Link: https://patch.msgid.link/20260307035128.3419687-1-wangshuaiwei1@xiaomi.com Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 899e663fea6e..9ceb6d6d479d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10066,6 +10066,7 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) } flush_work(&hba->eeh_work); + cancel_delayed_work_sync(&hba->ufs_rtc_update_work); ret = ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE); if (ret) @@ -10120,7 +10121,6 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) if (ret) goto set_link_active; - cancel_delayed_work_sync(&hba->ufs_rtc_update_work); goto out; set_link_active: From c0b7da13a04bd70ef6070bfb9ea85f582294560a Mon Sep 17 00:00:00 2001 From: Vladimir Riabchun Date: Tue, 10 Feb 2026 11:08:22 +0100 Subject: [PATCH 213/487] scsi: qla2xxx: Completely fix fcport double free In qla24xx_els_dcmd_iocb() sp->free is set to qla2x00_els_dcmd_sp_free(). When an error happens, this function is called by qla2x00_sp_release(), when kref_put() releases the first and the last reference. qla2x00_els_dcmd_sp_free() frees fcport by calling qla2x00_free_fcport(). Doing it one more time after kref_put() is a bad idea. Fixes: 82f522ae0d97 ("scsi: qla2xxx: Fix double free of fcport") Fixes: 4895009c4bb7 ("scsi: qla2xxx: Prevent command send on chip reset") Signed-off-by: Vladimir Riabchun Signed-off-by: Farhat Abbas Link: https://patch.msgid.link/aYsDln9NFQQsPDgg@vova-pc Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_iocb.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 9038f6723444..dbe3cd4e274c 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2751,7 +2751,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_logo.els_logo_pyld) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); - qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -2776,7 +2775,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (rval != QLA_SUCCESS) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); - qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } From 8ddc0c26916574395447ebf4cff684314f6873a9 Mon Sep 17 00:00:00 2001 From: Xingui Yang Date: Thu, 5 Mar 2026 14:40:39 +0800 Subject: [PATCH 214/487] scsi: hisi_sas: Fix NULL pointer exception during user_scan() user_scan() invokes updated sas_user_scan() for channel 0, and if successful, iteratively scans remaining channels (1 to shost->max_channel) via scsi_scan_host_selected() in commit 37c4e72b0651 ("scsi: Fix sas_user_scan() to handle wildcard and multi-channel scans"). However, hisi_sas supports only one channel, and the current value of max_channel is 1. sas_user_scan() for channel 1 will trigger the following NULL pointer exception: [ 441.554662] Unable to handle kernel NULL pointer dereference at virtual address 00000000000008b0 [ 441.554699] Mem abort info: [ 441.554710] ESR = 0x0000000096000004 [ 441.554718] EC = 0x25: DABT (current EL), IL = 32 bits [ 441.554723] SET = 0, FnV = 0 [ 441.554726] EA = 0, S1PTW = 0 [ 441.554730] FSC = 0x04: level 0 translation fault [ 441.554735] Data abort info: [ 441.554737] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 441.554742] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 441.554747] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 441.554752] user pgtable: 4k pages, 48-bit VAs, pgdp=00000828377a6000 [ 441.554757] [00000000000008b0] pgd=0000000000000000, p4d=0000000000000000 [ 441.554769] Internal error: Oops: 0000000096000004 [#1] SMP [ 441.629589] Modules linked in: arm_spe_pmu arm_smmuv3_pmu tpm_tis_spi hisi_uncore_sllc_pmu hisi_uncore_pa_pmu hisi_uncore_l3c_pmu hisi_uncore_hha_pmu hisi_uncore_ddrc_pmu hisi_uncore_cpa_pmu hns3_pmu hisi_ptt hisi_pcie_pmu tpm_tis_core spidev spi_hisi_sfc_v3xx hisi_uncore_pmu spi_dw_mmio fuse hclge hclge_common hisi_sec2 hisi_hpre hisi_zip hisi_qm hns3 hisi_sas_v3_hw sm3_ce sbsa_gwdt hnae3 hisi_sas_main uacce hisi_dma i2c_hisi dm_mirror dm_region_hash dm_log dm_mod [ 441.670819] CPU: 46 UID: 0 PID: 6994 Comm: bash Kdump: loaded Not tainted 7.0.0-rc2+ #84 PREEMPT [ 441.691327] pstate: 81400009 (Nzcv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 441.698277] pc : sas_find_dev_by_rphy+0x44/0x118 [ 441.702896] lr : sas_find_dev_by_rphy+0x3c/0x118 [ 441.707502] sp : ffff80009abbba40 [ 441.710805] x29: ffff80009abbba40 x28: ffff082819a40008 x27: ffff082810c37c08 [ 441.717930] x26: ffff082810c37c28 x25: ffff082819a40290 x24: ffff082810c37c00 [ 441.725054] x23: 0000000000000000 x22: 0000000000000001 x21: ffff082819a40000 [ 441.732179] x20: ffff082819a40290 x19: 0000000000000000 x18: 0000000000000020 [ 441.739304] x17: 0000000000000000 x16: ffffb5dad6bda690 x15: 00000000ffffffff [ 441.746428] x14: ffff082814c3b26c x13: 00000000ffffffff x12: ffff082814c3b26a [ 441.753553] x11: 00000000000000c0 x10: 000000000000003a x9 : ffffb5dad5ea94f4 [ 441.760678] x8 : 000000000000003a x7 : ffff80009abbbab0 x6 : 0000000000000030 [ 441.767802] x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 [ 441.774926] x2 : ffff08280f35a300 x1 : ffffb5dad7127180 x0 : 0000000000000000 [ 441.782053] Call trace: [ 441.784488] sas_find_dev_by_rphy+0x44/0x118 (P) [ 441.789095] sas_target_alloc+0x24/0xb0 [ 441.792920] scsi_alloc_target+0x290/0x330 [ 441.797010] __scsi_scan_target+0x88/0x258 [ 441.801096] scsi_scan_channel+0x74/0xb8 [ 441.805008] scsi_scan_host_selected+0x170/0x188 [ 441.809615] sas_user_scan+0xfc/0x148 [ 441.813267] store_scan+0x10c/0x180 [ 441.816743] dev_attr_store+0x20/0x40 [ 441.820398] sysfs_kf_write+0x84/0xa8 [ 441.824054] kernfs_fop_write_iter+0x130/0x1c8 [ 441.828487] vfs_write+0x2c0/0x370 [ 441.831880] ksys_write+0x74/0x118 [ 441.835271] __arm64_sys_write+0x24/0x38 [ 441.839182] invoke_syscall+0x50/0x120 [ 441.842919] el0_svc_common.constprop.0+0xc8/0xf0 [ 441.847611] do_el0_svc+0x24/0x38 [ 441.850913] el0_svc+0x38/0x158 [ 441.854043] el0t_64_sync_handler+0xa0/0xe8 [ 441.858214] el0t_64_sync+0x1ac/0x1b0 [ 441.861865] Code: aa1303e0 97ff70a8 34ffff80 d10a4273 (f9445a75) [ 441.867946] ---[ end trace 0000000000000000 ]--- Therefore, set max_channel to 0. Fixes: e21fe3a52692 ("scsi: hisi_sas: add initialisation for v3 pci-based controller") Signed-off-by: Xingui Yang Signed-off-by: Yihang Li Link: https://patch.msgid.link/20260305064039.4096775-1-liyihang9@huawei.com Signed-off-by: Martin K. Petersen --- drivers/scsi/hisi_sas/hisi_sas_main.c | 2 +- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 30a9c6612651..c2b082f1252c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -2578,7 +2578,7 @@ int hisi_sas_probe(struct platform_device *pdev, shost->transportt = hisi_sas_stt; shost->max_id = HISI_SAS_MAX_DEVICES; shost->max_lun = ~0; - shost->max_channel = 1; + shost->max_channel = 0; shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN; if (hisi_hba->hw->slot_index_alloc) { shost->can_queue = HISI_SAS_MAX_COMMANDS; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 2f9e01717ef3..f69efc6494b8 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -4993,7 +4993,7 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id) shost->transportt = hisi_sas_stt; shost->max_id = HISI_SAS_MAX_DEVICES; shost->max_lun = ~0; - shost->max_channel = 1; + shost->max_channel = 0; shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN; shost->can_queue = HISI_SAS_UNRESERVED_IPTT; shost->cmd_per_lun = HISI_SAS_UNRESERVED_IPTT; From 75aa996ea63f8656b668f8d9acb2c7a77c055e7f Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 6 Mar 2026 12:19:19 +0100 Subject: [PATCH 215/487] s390: Revert "s390/irq/idle: Remove psw bits early" This reverts commit d8b5cf9c63143fae54a734c41e3bb55cf3f365c7. Mikhail Zaslonko reported that linux-next doesn't boot anymore [2]. Reason for this is recent change [2] was supposed to slightly optimize the irq entry/exit path by removing some psw bits early in case of an idle exit. This however is incorrect since irqentry_exit() requires the correct old psw state at irq entry. Otherwise the embedded regs_irqs_disabled() will not provide the correct result. With linux-next and HRTIMER_REARM_DEFERRED this leads to the observed boot problems, however the commit is broken in any case. Revert the commit which introduced this. Thanks to Peter Zijlstra for pointing out that this is a bug in the s390 entry code. Fixes: d8b5cf9c6314 ("s390/irq/idle: Remove psw bits early") [1] Reported-by: Mikhail Zaslonko Reported-by: Peter Zijlstra Closes: https://lore.kernel.org/r/af549a19-db99-4b16-8511-bf315177a13e@linux.ibm.com/ [2] Signed-off-by: Heiko Carstens Acked-by: Mikhail Zaslonko Tested-by: Mikhail Zaslonko Acked-by: Vasily Gorbik Link: https://lore.kernel.org/r/20260306111919.362559-1-hca@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/kernel/irq.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 7fdf960191d3..d10a17e6531d 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -147,10 +147,8 @@ void noinstr do_io_irq(struct pt_regs *regs) bool from_idle; from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); - if (from_idle) { + if (from_idle) update_timer_idle(); - regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); - } irq_enter_rcu(); @@ -176,6 +174,9 @@ void noinstr do_io_irq(struct pt_regs *regs) set_irq_regs(old_regs); irqentry_exit(regs, state); + + if (from_idle) + regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); } void noinstr do_ext_irq(struct pt_regs *regs) @@ -185,10 +186,8 @@ void noinstr do_ext_irq(struct pt_regs *regs) bool from_idle; from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); - if (from_idle) { + if (from_idle) update_timer_idle(); - regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); - } irq_enter_rcu(); @@ -210,6 +209,9 @@ void noinstr do_ext_irq(struct pt_regs *regs) irq_exit_rcu(); set_irq_regs(old_regs); irqentry_exit(regs, state); + + if (from_idle) + regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); } static void show_msi_interrupt(struct seq_file *p, int irq) From 598bbefa8032cc58b564a81d1ad68bd815c8dc0f Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Fri, 27 Feb 2026 14:30:51 +0100 Subject: [PATCH 216/487] s390/zcrypt: Enable AUTOSEL_DOM for CCA serialnr sysfs attribute The serialnr sysfs attribute for CCA cards when queried always used the default domain for sending the request down to the card. If for any reason exactly this default domain is disabled then the attribute code fails to retrieve the CCA info and the sysfs entry shows an empty string. Works as designed but the serial number is a card attribute and thus it does not matter which domain is used for the query. So if there are other domains on this card available, these could be used. So extend the code to use AUTOSEL_DOM for the domain value to address any online domain within the card for querying the cca info and thus show the serialnr as long as there is one domain usable regardless of the default domain setting. Fixes: 8f291ebf3270 ("s390/zcrypt: enable card/domain autoselect on ep11 cprbs") Suggested-by: Ingo Franzki Signed-off-by: Harald Freudenberger Reviewed-by: Ingo Franzki Cc: stable@vger.kernel.org Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_ccamisc.c | 12 +++++++----- drivers/s390/crypto/zcrypt_cex4.c | 3 +-- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 573bad1d6d86..37a157a1d969 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1639,11 +1639,13 @@ int cca_get_info(u16 cardnr, u16 domain, struct cca_info *ci, u32 xflags) memset(ci, 0, sizeof(*ci)); - /* get first info from zcrypt device driver about this apqn */ - rc = zcrypt_device_status_ext(cardnr, domain, &devstat); - if (rc) - return rc; - ci->hwtype = devstat.hwtype; + /* if specific domain given, fetch status and hw info for this apqn */ + if (domain != AUTOSEL_DOM) { + rc = zcrypt_device_status_ext(cardnr, domain, &devstat); + if (rc) + return rc; + ci->hwtype = devstat.hwtype; + } /* * Prep memory for rule array and var array use. diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index e9a984903bff..e7b0ed26a9ec 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -85,8 +85,7 @@ static ssize_t cca_serialnr_show(struct device *dev, memset(&ci, 0, sizeof(ci)); - if (ap_domain_index >= 0) - cca_get_info(ac->id, ap_domain_index, &ci, 0); + cca_get_info(ac->id, AUTOSEL_DOM, &ci, 0); return sysfs_emit(buf, "%s\n", ci.serial); } From 6da5e537f5afe091658e846da1949d7e557d2ade Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 7 Mar 2026 19:11:51 +0000 Subject: [PATCH 217/487] KVM: arm64: vgic: Pick EOIcount deactivations from AP-list tail Valentine reports that their guests fail to boot correctly, losing interrupts, and indicates that the wrong interrupt gets deactivated. What happens here is that if the maintenance interrupt is slow enough to kick us out of the guest, extra interrupts can be activated from the LRs. We then exit and proceed to handle EOIcount deactivations, picking active interrupts from the AP list. But we start from the top of the list, potentially deactivating interrupts that were in the LRs, while EOIcount only denotes deactivation of interrupts that are not present in an LR. Solve this by tracking the last interrupt that made it in the LRs, and start the EOIcount deactivation walk *after* that interrupt. Since this only makes sense while the vcpu is loaded, stash this in the per-CPU host state. Huge thanks to Valentine for doing all the detective work and providing an initial patch. Fixes: 3cfd59f81e0f3 ("KVM: arm64: GICv3: Handle LR overflow when EOImode==0") Fixes: 281c6c06e2a7b ("KVM: arm64: GICv2: Handle LR overflow when EOImode==0") Reported-by: Valentine Burley Tested-by: Valentine Burley Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20260307115955.369455-1-valentine.burley@collabora.com Link: https://patch.msgid.link/20260307191151.3781182-1-maz@kernel.org Cc: stable@vger.kernel.org --- arch/arm64/include/asm/kvm_host.h | 3 +++ arch/arm64/kvm/vgic/vgic-v2.c | 4 ++-- arch/arm64/kvm/vgic/vgic-v3.c | 12 ++++++------ arch/arm64/kvm/vgic/vgic.c | 6 ++++++ 4 files changed, 17 insertions(+), 8 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2ca264b3db5f..70cb9cfd760a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -784,6 +784,9 @@ struct kvm_host_data { /* Number of debug breakpoints/watchpoints for this CPU (minus 1) */ unsigned int debug_brps; unsigned int debug_wrps; + + /* Last vgic_irq part of the AP list recorded in an LR */ + struct vgic_irq *last_lr_irq; }; struct kvm_host_psci_config { diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index 585491fbda80..cafa3cb32bda 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -115,7 +115,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2; u32 eoicount = FIELD_GET(GICH_HCR_EOICOUNT, cpuif->vgic_hcr); - struct vgic_irq *irq; + struct vgic_irq *irq = *host_data_ptr(last_lr_irq); DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -123,7 +123,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) vgic_v2_fold_lr(vcpu, cpuif->vgic_lr[lr]); /* See the GICv3 equivalent for the EOIcount handling rationale */ - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) { u32 lr; if (!eoicount) { diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 386ddf69a9c5..6a355eca1934 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -148,7 +148,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr); - struct vgic_irq *irq; + struct vgic_irq *irq = *host_data_ptr(last_lr_irq); DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -158,12 +158,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) /* * EOIMode=0: use EOIcount to emulate deactivation. We are * guaranteed to deactivate in reverse order of the activation, so - * just pick one active interrupt after the other in the ap_list, - * and replay the deactivation as if the CPU was doing it. We also - * rely on priority drop to have taken place, and the list to be - * sorted by priority. + * just pick one active interrupt after the other in the tail part + * of the ap_list, past the LRs, and replay the deactivation as if + * the CPU was doing it. We also rely on priority drop to have taken + * place, and the list to be sorted by priority. */ - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) { u64 lr; /* diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 430aa98888fd..e22b79cfff96 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -814,6 +814,9 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) { + if (!*host_data_ptr(last_lr_irq)) + return; + if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_fold_lr_state(vcpu); else @@ -960,10 +963,13 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) if (irqs_outside_lrs(&als)) vgic_sort_ap_list(vcpu); + *host_data_ptr(last_lr_irq) = NULL; + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { scoped_guard(raw_spinlock, &irq->irq_lock) { if (likely(vgic_target_oracle(irq) == vcpu)) { vgic_populate_lr(vcpu, irq, count++); + *host_data_ptr(last_lr_irq) = irq; } } From 08da98f18f4f99aa16838397b76086d2d1d364b3 Mon Sep 17 00:00:00 2001 From: Gary Guo Date: Mon, 2 Mar 2026 16:42:34 +0000 Subject: [PATCH 218/487] rust: ptr: add `KnownSize` trait to support DST size info extraction Add a `KnownSize` trait which is used obtain a size from a raw pointer's metadata. This makes it possible to obtain size information on a raw slice pointer. This is similar to Rust `core::mem::size_of_val_raw` which is not yet stable. Signed-off-by: Gary Guo Reviewed-by: Benno Lossin Acked-by: Miguel Ojeda Link: https://patch.msgid.link/20260302164239.284084-2-gary@kernel.org [ Fix wording in doc-comment. - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/lib.rs | 1 + rust/kernel/ptr.rs | 27 ++++++++++++++++++++++++++- 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 3da92f18f4ee..510cc7fe4961 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -20,6 +20,7 @@ #![feature(generic_nonzero)] #![feature(inline_const)] #![feature(pointer_is_aligned)] +#![feature(slice_ptr_len)] // // Stable since Rust 1.80.0. #![feature(slice_flatten)] diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs index 5b6a382637fe..e91de5f0d78f 100644 --- a/rust/kernel/ptr.rs +++ b/rust/kernel/ptr.rs @@ -2,7 +2,10 @@ //! Types and functions to work with pointers and addresses. -use core::mem::align_of; +use core::mem::{ + align_of, + size_of, // +}; use core::num::NonZero; /// Type representing an alignment, which is always a power of two. @@ -225,3 +228,25 @@ fn align_up(self, alignment: Alignment) -> Option { } impl_alignable_uint!(u8, u16, u32, u64, usize); + +/// Trait to represent compile-time known size information. +/// +/// This is a generalization of [`size_of`] that works for dynamically sized types. +pub trait KnownSize { + /// Get the size of an object of this type in bytes, with the metadata of the given pointer. + fn size(p: *const Self) -> usize; +} + +impl KnownSize for T { + #[inline(always)] + fn size(_: *const Self) -> usize { + size_of::() + } +} + +impl KnownSize for [T] { + #[inline(always)] + fn size(p: *const Self) -> usize { + p.len() * size_of::() + } +} From f41941aab3acd33f13d65a2ae496329bc8ae4de0 Mon Sep 17 00:00:00 2001 From: Gary Guo Date: Mon, 2 Mar 2026 16:42:35 +0000 Subject: [PATCH 219/487] rust: ptr: add projection infrastructure Add a generic infrastructure for performing field and index projections on raw pointers. This will form the basis of performing I/O projections. Pointers manipulations are intentionally using the safe wrapping variants instead of the unsafe variants, as the latter requires pointers to be inside an allocation which is not necessarily true for I/O pointers. This projection macro protects against rogue `Deref` implementation, which can causes the projected pointer to be outside the bounds of starting pointer. This is extremely unlikely and Rust has a lint to catch this, but is unsoundness regardless. The protection works by inducing type inference ambiguity when `Deref` is implemented. This projection macro also stops projecting into unaligned fields (i.e. fields of `#[repr(packed)]` structs), as misaligned pointers require special handling. This is implemented by attempting to create reference to projected field inside a `if false` block. Despite being unreachable, Rust still checks that they're not unaligned fields. The projection macro supports both fallible and infallible index projections. These are described in detail inside the documentation. Signed-off-by: Gary Guo Reviewed-by: Benno Lossin Acked-by: Miguel Ojeda Link: https://patch.msgid.link/20260302164239.284084-3-gary@kernel.org [ * Add intro-doc links where possible, * Fix typos and slightly improve wording, e.g. "as documentation describes" -> "as the documentation of [`Self::proj`] describes", * Add an empty line between regular and safety comments, before examples, and between logically independent comments, * Capitalize various safety comments. - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/lib.rs | 3 + rust/kernel/ptr.rs | 3 + rust/kernel/ptr/projection.rs | 305 ++++++++++++++++++++++++++++++++++ scripts/Makefile.build | 4 +- 4 files changed, 314 insertions(+), 1 deletion(-) create mode 100644 rust/kernel/ptr/projection.rs diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 510cc7fe4961..d93292d47420 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -38,6 +38,9 @@ #![feature(const_ptr_write)] #![feature(const_refs_to_cell)] // +// Stable since Rust 1.84.0. +#![feature(strict_provenance)] +// // Expected to become stable. #![feature(arbitrary_self_types)] // diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs index e91de5f0d78f..bdc2d79ff669 100644 --- a/rust/kernel/ptr.rs +++ b/rust/kernel/ptr.rs @@ -2,6 +2,9 @@ //! Types and functions to work with pointers and addresses. +pub mod projection; +pub use crate::project_pointer as project; + use core::mem::{ align_of, size_of, // diff --git a/rust/kernel/ptr/projection.rs b/rust/kernel/ptr/projection.rs new file mode 100644 index 000000000000..140ea8e21617 --- /dev/null +++ b/rust/kernel/ptr/projection.rs @@ -0,0 +1,305 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Infrastructure for handling projections. + +use core::{ + mem::MaybeUninit, + ops::Deref, // +}; + +use crate::prelude::*; + +/// Error raised when a projection is attempted on an array or slice out of bounds. +pub struct OutOfBound; + +impl From for Error { + #[inline(always)] + fn from(_: OutOfBound) -> Self { + ERANGE + } +} + +/// A helper trait to perform index projection. +/// +/// This is similar to [`core::slice::SliceIndex`], but operates on raw pointers safely and +/// fallibly. +/// +/// # Safety +/// +/// The implementation of `index` and `get` (if [`Some`] is returned) must ensure that, if provided +/// input pointer `slice` and returned pointer `output`, then: +/// - `output` has the same provenance as `slice`; +/// - `output.byte_offset_from(slice)` is between 0 to +/// `KnownSize::size(slice) - KnownSize::size(output)`. +/// +/// This means that if the input pointer is valid, then pointer returned by `get` or `index` is +/// also valid. +#[diagnostic::on_unimplemented(message = "`{Self}` cannot be used to index `{T}`")] +#[doc(hidden)] +pub unsafe trait ProjectIndex: Sized { + type Output: ?Sized; + + /// Returns an index-projected pointer, if in bounds. + fn get(self, slice: *mut T) -> Option<*mut Self::Output>; + + /// Returns an index-projected pointer; fail the build if it cannot be proved to be in bounds. + #[inline(always)] + fn index(self, slice: *mut T) -> *mut Self::Output { + Self::get(self, slice).unwrap_or_else(|| build_error!()) + } +} + +// Forward array impl to slice impl. +// +// SAFETY: Safety requirement guaranteed by the forwarded impl. +unsafe impl ProjectIndex<[T; N]> for I +where + I: ProjectIndex<[T]>, +{ + type Output = >::Output; + + #[inline(always)] + fn get(self, slice: *mut [T; N]) -> Option<*mut Self::Output> { + >::get(self, slice) + } + + #[inline(always)] + fn index(self, slice: *mut [T; N]) -> *mut Self::Output { + >::index(self, slice) + } +} + +// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to +// not exceed the required bound. +unsafe impl ProjectIndex<[T]> for usize { + type Output = T; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut T> { + if self >= slice.len() { + None + } else { + Some(slice.cast::().wrapping_add(self)) + } + } +} + +// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to +// not exceed the required bound. +unsafe impl ProjectIndex<[T]> for core::ops::Range { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + let new_len = self.end.checked_sub(self.start)?; + if self.end > slice.len() { + return None; + } + Some(core::ptr::slice_from_raw_parts_mut( + slice.cast::().wrapping_add(self.start), + new_len, + )) + } +} + +// SAFETY: Safety requirement guaranteed by the forwarded impl. +unsafe impl ProjectIndex<[T]> for core::ops::RangeTo { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + (0..self.end).get(slice) + } +} + +// SAFETY: Safety requirement guaranteed by the forwarded impl. +unsafe impl ProjectIndex<[T]> for core::ops::RangeFrom { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + (self.start..slice.len()).get(slice) + } +} + +// SAFETY: `get` returned the pointer as is, so it always has the same provenance and offset of 0. +unsafe impl ProjectIndex<[T]> for core::ops::RangeFull { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + Some(slice) + } +} + +/// A helper trait to perform field projection. +/// +/// This trait has a `DEREF` generic parameter so it can be implemented twice for types that +/// implement [`Deref`]. This will cause an ambiguity error and thus block [`Deref`] types being +/// used as base of projection, as they can inject unsoundness. Users therefore must not specify +/// `DEREF` and should always leave it to be inferred. +/// +/// # Safety +/// +/// `proj` may only invoke `f` with a valid allocation, as the documentation of [`Self::proj`] +/// describes. +#[doc(hidden)] +pub unsafe trait ProjectField { + /// Project a pointer to a type to a pointer of a field. + /// + /// `f` may only be invoked with a valid allocation so it can safely obtain raw pointers to + /// fields using `&raw mut`. + /// + /// This is needed because `base` might not point to a valid allocation, while `&raw mut` + /// requires pointers to be in bounds of a valid allocation. + /// + /// # Safety + /// + /// `f` must return a pointer in bounds of the provided pointer. + unsafe fn proj(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F; +} + +// NOTE: in theory, this API should work for `T: ?Sized` and `F: ?Sized`, too. However, we cannot +// currently support that as we need to obtain a valid allocation that `&raw const` can operate on. +// +// SAFETY: `proj` invokes `f` with valid allocation. +unsafe impl ProjectField for T { + #[inline(always)] + unsafe fn proj(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F { + // Create a valid allocation to start projection, as `base` is not necessarily so. The + // memory is never actually used so it will be optimized out, so it should work even for + // very large `T` (`memoffset` crate also relies on this). To be extra certain, we also + // annotate `f` closure with `#[inline(always)]` in the macro. + let mut place = MaybeUninit::uninit(); + let place_base = place.as_mut_ptr(); + let field = f(place_base); + // SAFETY: `field` is in bounds from `base` per safety requirement. + let offset = unsafe { field.byte_offset_from(place_base) }; + // Use `wrapping_byte_offset` as `base` does not need to be of valid allocation. + base.wrapping_byte_offset(offset).cast() + } +} + +// SAFETY: Vacuously satisfied. +unsafe impl ProjectField for T { + #[inline(always)] + unsafe fn proj(_: *mut Self, _: impl FnOnce(*mut Self) -> *mut F) -> *mut F { + build_error!("this function is a guard against `Deref` impl and is never invoked"); + } +} + +/// Create a projection from a raw pointer. +/// +/// The projected pointer is within the memory region marked by the input pointer. There is no +/// requirement that the input raw pointer needs to be valid, so this macro may be used for +/// projecting pointers outside normal address space, e.g. I/O pointers. However, if the input +/// pointer is valid, the projected pointer is also valid. +/// +/// Supported projections include field projections and index projections. +/// It is not allowed to project into types that implement custom [`Deref`] or +/// [`Index`](core::ops::Index). +/// +/// The macro has basic syntax of `kernel::ptr::project!(ptr, projection)`, where `ptr` is an +/// expression that evaluates to a raw pointer which serves as the base of projection. `projection` +/// can be a projection expression of form `.field` (normally identifier, or numeral in case of +/// tuple structs) or of form `[index]`. +/// +/// If a mutable pointer is needed, the macro input can be prefixed with the `mut` keyword, i.e. +/// `kernel::ptr::project!(mut ptr, projection)`. By default, a const pointer is created. +/// +/// `ptr::project!` macro can perform both fallible indexing and build-time checked indexing. +/// `[index]` form performs build-time bounds checking; if compiler fails to prove `[index]` is in +/// bounds, compilation will fail. `[index]?` can be used to perform runtime bounds checking; +/// `OutOfBound` error is raised via `?` if the index is out of bounds. +/// +/// # Examples +/// +/// Field projections are performed with `.field_name`: +/// +/// ``` +/// struct MyStruct { field: u32, } +/// let ptr: *const MyStruct = core::ptr::dangling(); +/// let field_ptr: *const u32 = kernel::ptr::project!(ptr, .field); +/// +/// struct MyTupleStruct(u32, u32); +/// +/// fn proj(ptr: *const MyTupleStruct) { +/// let field_ptr: *const u32 = kernel::ptr::project!(ptr, .1); +/// } +/// ``` +/// +/// Index projections are performed with `[index]`: +/// +/// ``` +/// fn proj(ptr: *const [u8; 32]) -> Result { +/// let field_ptr: *const u8 = kernel::ptr::project!(ptr, [1]); +/// // The following invocation, if uncommented, would fail the build. +/// // +/// // kernel::ptr::project!(ptr, [128]); +/// +/// // This will raise an `OutOfBound` error (which is convertible to `ERANGE`). +/// kernel::ptr::project!(ptr, [128]?); +/// Ok(()) +/// } +/// ``` +/// +/// If you need to match on the error instead of propagate, put the invocation inside a closure: +/// +/// ``` +/// let ptr: *const [u8; 32] = core::ptr::dangling(); +/// let field_ptr: Result<*const u8> = (|| -> Result<_> { +/// Ok(kernel::ptr::project!(ptr, [128]?)) +/// })(); +/// assert!(field_ptr.is_err()); +/// ``` +/// +/// For mutable pointers, put `mut` as the first token in macro invocation. +/// +/// ``` +/// let ptr: *mut [(u8, u16); 32] = core::ptr::dangling_mut(); +/// let field_ptr: *mut u16 = kernel::ptr::project!(mut ptr, [1].1); +/// ``` +#[macro_export] +macro_rules! project_pointer { + (@gen $ptr:ident, ) => {}; + // Field projection. `$field` needs to be `tt` to support tuple index like `.0`. + (@gen $ptr:ident, .$field:tt $($rest:tt)*) => { + // SAFETY: The provided closure always returns an in-bounds pointer. + let $ptr = unsafe { + $crate::ptr::projection::ProjectField::proj($ptr, #[inline(always)] |ptr| { + // Check unaligned field. Not all users (e.g. DMA) can handle unaligned + // projections. + if false { + let _ = &(*ptr).$field; + } + // SAFETY: `$field` is in bounds, and no implicit `Deref` is possible (if the + // type implements `Deref`, Rust cannot infer the generic parameter `DEREF`). + &raw mut (*ptr).$field + }) + }; + $crate::ptr::project!(@gen $ptr, $($rest)*) + }; + // Fallible index projection. + (@gen $ptr:ident, [$index:expr]? $($rest:tt)*) => { + let $ptr = $crate::ptr::projection::ProjectIndex::get($index, $ptr) + .ok_or($crate::ptr::projection::OutOfBound)?; + $crate::ptr::project!(@gen $ptr, $($rest)*) + }; + // Build-time checked index projection. + (@gen $ptr:ident, [$index:expr] $($rest:tt)*) => { + let $ptr = $crate::ptr::projection::ProjectIndex::index($index, $ptr); + $crate::ptr::project!(@gen $ptr, $($rest)*) + }; + (mut $ptr:expr, $($proj:tt)*) => {{ + let ptr: *mut _ = $ptr; + $crate::ptr::project!(@gen ptr, $($proj)*); + ptr + }}; + ($ptr:expr, $($proj:tt)*) => {{ + let ptr = <*const _>::cast_mut($ptr); + // We currently always project using mutable pointer, as it is not decided whether `&raw + // const` allows the resulting pointer to be mutated (see documentation of `addr_of!`). + $crate::ptr::project!(@gen ptr, $($proj)*); + ptr.cast_const() + }}; +} diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 32e209bc7985..3652b85be545 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -310,16 +310,18 @@ $(obj)/%.lst: $(obj)/%.c FORCE # The features in this list are the ones allowed for non-`rust/` code. # +# - Stable since Rust 1.79.0: `feature(slice_ptr_len)`. # - Stable since Rust 1.81.0: `feature(lint_reasons)`. # - Stable since Rust 1.82.0: `feature(asm_const)`, # `feature(offset_of_nested)`, `feature(raw_ref_op)`. +# - Stable since Rust 1.84.0: `feature(strict_provenance)`. # - Stable since Rust 1.87.0: `feature(asm_goto)`. # - Expected to become stable: `feature(arbitrary_self_types)`. # - To be determined: `feature(used_with_arg)`. # # Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on # the unstable features in use. -rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg +rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,slice_ptr_len,strict_provenance,used_with_arg # `--out-dir` is required to avoid temporaries being created by `rustc` in the # current working directory, which may be not accessible in the out-of-tree From 4da879a0d3fd170a70994b73baa554c6913918b5 Mon Sep 17 00:00:00 2001 From: Gary Guo Date: Mon, 2 Mar 2026 16:42:36 +0000 Subject: [PATCH 220/487] rust: dma: use pointer projection infra for `dma_{read,write}` macro Current `dma_read!`, `dma_write!` macros also use a custom `addr_of!()`-based implementation for projecting pointers, which has soundness issue as it relies on absence of `Deref` implementation on types. It also has a soundness issue where it does not protect against unaligned fields (when `#[repr(packed)]` is used) so it can generate misaligned accesses. This commit migrates them to use the general pointer projection infrastructure, which handles these cases correctly. As part of migration, the macro is updated to have an improved surface syntax. The current macro have dma_read!(a.b.c[d].e.f) to mean `a.b.c` is a DMA coherent allocation and it should project into it with `[d].e.f` and do a read, which is confusing as it makes the indexing operator integral to the macro (so it will break if you have an array of `CoherentAllocation`, for example). This also is problematic as we would like to generalize `CoherentAllocation` from just slices to arbitrary types. Make the macro expects `dma_read!(path.to.dma, .path.inside.dma)` as the canonical syntax. The index operator is no longer special and is just one type of projection (in additional to field projection). Similarly, make `dma_write!(path.to.dma, .path.inside.dma, value)` become the canonical syntax for writing. Another issue of the current macro is that it is always fallible. This makes sense with existing design of `CoherentAllocation`, but once we support fixed size arrays with `CoherentAllocation`, it is desirable to have the ability to perform infallible indexing as well, e.g. doing a `[0]` index of `[Foo; 2]` is okay and can be checked at build-time, so forcing falliblity is non-ideal. To capture this, the macro is changed to use `[idx]` as infallible projection and `[idx]?` as fallible index projection (those syntax are part of the general projection infra). A benefit of this is that while individual indexing operation may fail, the overall read/write operation is not fallible. Fixes: ad2907b4e308 ("rust: add dma coherent allocator abstraction") Reviewed-by: Benno Lossin Signed-off-by: Gary Guo Link: https://patch.msgid.link/20260302164239.284084-4-gary@kernel.org [ Capitalize safety comments; slightly improve wording in doc-comments. - Danilo ] Signed-off-by: Danilo Krummrich --- drivers/gpu/nova-core/gsp.rs | 14 ++-- drivers/gpu/nova-core/gsp/boot.rs | 2 +- drivers/gpu/nova-core/gsp/cmdq.rs | 10 ++- rust/kernel/dma.rs | 114 +++++++++++++----------------- samples/rust/rust_dma.rs | 30 ++++---- 5 files changed, 81 insertions(+), 89 deletions(-) diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs index 174feaca0a6b..25cd48514c77 100644 --- a/drivers/gpu/nova-core/gsp.rs +++ b/drivers/gpu/nova-core/gsp.rs @@ -143,14 +143,14 @@ pub(crate) fn new(pdev: &pci::Device) -> impl PinInit::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?; - dma_write!(wpr_meta[0] = GspFwWprMeta::new(&gsp_fw, &fb_layout))?; + dma_write!(wpr_meta, [0]?, GspFwWprMeta::new(&gsp_fw, &fb_layout)); self.cmdq .send_command(bar, commands::SetSystemInfo::new(pdev))?; diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs index 46819a82a51a..ae54708c38eb 100644 --- a/drivers/gpu/nova-core/gsp/cmdq.rs +++ b/drivers/gpu/nova-core/gsp/cmdq.rs @@ -201,9 +201,13 @@ fn new(dev: &device::Device) -> Result { let gsp_mem = CoherentAllocation::::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?; - dma_write!(gsp_mem[0].ptes = PteArray::new(gsp_mem.dma_handle())?)?; - dma_write!(gsp_mem[0].cpuq.tx = MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES))?; - dma_write!(gsp_mem[0].cpuq.rx = MsgqRxHeader::new())?; + dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?); + dma_write!( + gsp_mem, + [0]?.cpuq.tx, + MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES) + ); + dma_write!(gsp_mem, [0]?.cpuq.rx, MsgqRxHeader::new()); Ok(Self(gsp_mem)) } diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs index 909d56fd5118..a396f8435739 100644 --- a/rust/kernel/dma.rs +++ b/rust/kernel/dma.rs @@ -461,6 +461,19 @@ pub fn size(&self) -> usize { self.count * core::mem::size_of::() } + /// Returns the raw pointer to the allocated region in the CPU's virtual address space. + #[inline] + pub fn as_ptr(&self) -> *const [T] { + core::ptr::slice_from_raw_parts(self.cpu_addr.as_ptr(), self.count) + } + + /// Returns the raw pointer to the allocated region in the CPU's virtual address space as + /// a mutable pointer. + #[inline] + pub fn as_mut_ptr(&self) -> *mut [T] { + core::ptr::slice_from_raw_parts_mut(self.cpu_addr.as_ptr(), self.count) + } + /// Returns the base address to the allocated region in the CPU's virtual address space. pub fn start_ptr(&self) -> *const T { self.cpu_addr.as_ptr() @@ -581,23 +594,6 @@ pub unsafe fn write(&mut self, src: &[T], offset: usize) -> Result { Ok(()) } - /// Returns a pointer to an element from the region with bounds checking. `offset` is in - /// units of `T`, not the number of bytes. - /// - /// Public but hidden since it should only be used from [`dma_read`] and [`dma_write`] macros. - #[doc(hidden)] - pub fn item_from_index(&self, offset: usize) -> Result<*mut T> { - if offset >= self.count { - return Err(EINVAL); - } - // SAFETY: - // - The pointer is valid due to type invariant on `CoherentAllocation` - // and we've just checked that the range and index is within bounds. - // - `offset` can't overflow since it is smaller than `self.count` and we've checked - // that `self.count` won't overflow early in the constructor. - Ok(unsafe { self.cpu_addr.as_ptr().add(offset) }) - } - /// Reads the value of `field` and ensures that its type is [`FromBytes`]. /// /// # Safety @@ -670,6 +666,9 @@ unsafe impl Send for CoherentAllocation {} /// Reads a field of an item from an allocated region of structs. /// +/// The syntax is of the form `kernel::dma_read!(dma, proj)` where `dma` is an expression evaluating +/// to a [`CoherentAllocation`] and `proj` is a [projection specification](kernel::ptr::project!). +/// /// # Examples /// /// ``` @@ -684,36 +683,29 @@ unsafe impl Send for CoherentAllocation {} /// unsafe impl kernel::transmute::AsBytes for MyStruct{}; /// /// # fn test(alloc: &kernel::dma::CoherentAllocation) -> Result { -/// let whole = kernel::dma_read!(alloc[2]); -/// let field = kernel::dma_read!(alloc[1].field); +/// let whole = kernel::dma_read!(alloc, [2]?); +/// let field = kernel::dma_read!(alloc, [1]?.field); /// # Ok::<(), Error>(()) } /// ``` #[macro_export] macro_rules! dma_read { - ($dma:expr, $idx: expr, $($field:tt)*) => {{ - (|| -> ::core::result::Result<_, $crate::error::Error> { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be - // dereferenced. The compiler also further validates the expression on whether `field` - // is a member of `item` when expanded by the macro. - unsafe { - let ptr_field = ::core::ptr::addr_of!((*item) $($field)*); - ::core::result::Result::Ok( - $crate::dma::CoherentAllocation::field_read(&$dma, ptr_field) - ) - } - })() + ($dma:expr, $($proj:tt)*) => {{ + let dma = &$dma; + let ptr = $crate::ptr::project!( + $crate::dma::CoherentAllocation::as_ptr(dma), $($proj)* + ); + // SAFETY: The pointer created by the projection is within the DMA region. + unsafe { $crate::dma::CoherentAllocation::field_read(dma, ptr) } }}; - ($dma:ident [ $idx:expr ] $($field:tt)* ) => { - $crate::dma_read!($dma, $idx, $($field)*) - }; - ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => { - $crate::dma_read!($($dma).*, $idx, $($field)*) - }; } /// Writes to a field of an item from an allocated region of structs. /// +/// The syntax is of the form `kernel::dma_write!(dma, proj, val)` where `dma` is an expression +/// evaluating to a [`CoherentAllocation`], `proj` is a +/// [projection specification](kernel::ptr::project!), and `val` is the value to be written to the +/// projected location. +/// /// # Examples /// /// ``` @@ -728,37 +720,31 @@ macro_rules! dma_read { /// unsafe impl kernel::transmute::AsBytes for MyStruct{}; /// /// # fn test(alloc: &kernel::dma::CoherentAllocation) -> Result { -/// kernel::dma_write!(alloc[2].member = 0xf); -/// kernel::dma_write!(alloc[1] = MyStruct { member: 0xf }); +/// kernel::dma_write!(alloc, [2]?.member, 0xf); +/// kernel::dma_write!(alloc, [1]?, MyStruct { member: 0xf }); /// # Ok::<(), Error>(()) } /// ``` #[macro_export] macro_rules! dma_write { - ($dma:ident [ $idx:expr ] $($field:tt)*) => {{ - $crate::dma_write!($dma, $idx, $($field)*) + (@parse [$dma:expr] [$($proj:tt)*] [, $val:expr]) => {{ + let dma = &$dma; + let ptr = $crate::ptr::project!( + mut $crate::dma::CoherentAllocation::as_mut_ptr(dma), $($proj)* + ); + let val = $val; + // SAFETY: The pointer created by the projection is within the DMA region. + unsafe { $crate::dma::CoherentAllocation::field_write(dma, ptr, val) } }}; - ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => {{ - $crate::dma_write!($($dma).*, $idx, $($field)*) - }}; - ($dma:expr, $idx: expr, = $val:expr) => { - (|| -> ::core::result::Result<_, $crate::error::Error> { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid item. - unsafe { $crate::dma::CoherentAllocation::field_write(&$dma, item, $val) } - ::core::result::Result::Ok(()) - })() + (@parse [$dma:expr] [$($proj:tt)*] [.$field:tt $($rest:tt)*]) => { + $crate::dma_write!(@parse [$dma] [$($proj)* .$field] [$($rest)*]) }; - ($dma:expr, $idx: expr, $(.$field:ident)* = $val:expr) => { - (|| -> ::core::result::Result<_, $crate::error::Error> { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be - // dereferenced. The compiler also further validates the expression on whether `field` - // is a member of `item` when expanded by the macro. - unsafe { - let ptr_field = ::core::ptr::addr_of_mut!((*item) $(.$field)*); - $crate::dma::CoherentAllocation::field_write(&$dma, ptr_field, $val) - } - ::core::result::Result::Ok(()) - })() + (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr]? $($rest:tt)*]) => { + $crate::dma_write!(@parse [$dma] [$($proj)* [$index]?] [$($rest)*]) + }; + (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr] $($rest:tt)*]) => { + $crate::dma_write!(@parse [$dma] [$($proj)* [$index]] [$($rest)*]) + }; + ($dma:expr, $($rest:tt)*) => { + $crate::dma_write!(@parse [$dma] [] [$($rest)*]) }; } diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs index 9c45851c876e..ce39b5545097 100644 --- a/samples/rust/rust_dma.rs +++ b/samples/rust/rust_dma.rs @@ -68,7 +68,7 @@ fn probe(pdev: &pci::Device, _info: &Self::IdInfo) -> impl PinInit, _info: &Self::IdInfo) -> impl PinInit Result { + for (i, value) in TEST_VALUES.into_iter().enumerate() { + let val0 = kernel::dma_read!(self.ca, [i]?.h); + let val1 = kernel::dma_read!(self.ca, [i]?.b); + + assert_eq!(val0, value.0); + assert_eq!(val1, value.1); + } + + Ok(()) + } +} + #[pinned_drop] impl PinnedDrop for DmaSampleDriver { fn drop(self: Pin<&mut Self>) { dev_info!(self.pdev, "Unload DMA test driver.\n"); - for (i, value) in TEST_VALUES.into_iter().enumerate() { - let val0 = kernel::dma_read!(self.ca[i].h); - let val1 = kernel::dma_read!(self.ca[i].b); - assert!(val0.is_ok()); - assert!(val1.is_ok()); - - if let Ok(val0) = val0 { - assert_eq!(val0, value.0); - } - if let Ok(val1) = val1 { - assert_eq!(val1, value.1); - } - } + assert!(self.check_dma().is_ok()); for (i, entry) in self.sgt.iter().enumerate() { dev_info!( From 46d8a07b4ae262e2fec6ce2aa454e06243661265 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Sat, 28 Feb 2026 22:30:30 -0600 Subject: [PATCH 221/487] drm/sitronix/st7586: fix bad pixel data due to byte swap Correctly set dbi->write_memory_bpw for the ST7586 driver. This driver is for a monochrome display that has an unusual data format, so the default value set in mipi_dbi_spi_init() is not correct simply because this controller is non-standard. Previously, we were using dbi->swap_bytes to make the same sort of workaround, but it was removed in the same commit that added dbi->write_memory_bpw, so we need to use the latter now to have the correct behavior. This fixes every 3 columns of pixels being swapped on the display. There are 3 pixels per byte, so the byte swap caused this effect. Fixes: df3fb27a74a4 ("drm/mipi-dbi: Make bits per word configurable for pixel transfers") Acked-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Signed-off-by: David Lechner Link: https://patch.msgid.link/20260228-drm-mipi-dbi-fix-st7586-byte-swap-v1-1-e78f6c24cd28@baylibre.com --- drivers/gpu/drm/sitronix/st7586.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/sitronix/st7586.c b/drivers/gpu/drm/sitronix/st7586.c index b57ebf37a664..16b6b4e368af 100644 --- a/drivers/gpu/drm/sitronix/st7586.c +++ b/drivers/gpu/drm/sitronix/st7586.c @@ -347,6 +347,12 @@ static int st7586_probe(struct spi_device *spi) if (ret) return ret; + /* + * Override value set by mipi_dbi_spi_init(). This driver is a bit + * non-standard, so best to set it explicitly here. + */ + dbi->write_memory_bpw = 8; + /* Cannot read from this controller via SPI */ dbi->read_commands = NULL; @@ -356,15 +362,6 @@ static int st7586_probe(struct spi_device *spi) if (ret) return ret; - /* - * we are using 8-bit data, so we are not actually swapping anything, - * but setting mipi->swap_bytes makes mipi_dbi_typec3_command() do the - * right thing and not use 16-bit transfers (which results in swapped - * bytes on little-endian systems and causes out of order data to be - * sent to the display). - */ - dbi->swap_bytes = true; - drm_mode_config_reset(drm); ret = drm_dev_register(drm, 0); From 7149be786da012afc6bae293d38f8c1fff1fb90d Mon Sep 17 00:00:00 2001 From: Shenghao Yang Date: Sun, 22 Feb 2026 13:45:51 +0800 Subject: [PATCH 222/487] drm/gud: fix NULL crtc dereference on display disable gud_plane_atomic_update() currently handles both crtc state and framebuffer updates - the complexity has led to a few accidental NULL pointer dereferences. Commit dc2d5ddb193e ("drm/gud: fix NULL fb and crtc dereferences on USB disconnect") [1] fixed an earlier dereference but planes can also be disabled in non-hotplug paths (e.g. display disables via the desktop environment). The drm_dev_enter() call would not cause an early return in those and subsequently oops on dereferencing crtc: BUG: kernel NULL pointer dereference, address: 00000000000005c8 CPU: 6 UID: 1000 PID: 3473 Comm: kwin_wayland Not tainted 6.18.2-200.vanilla.gud.fc42.x86_64 #1 PREEMPT(lazy) RIP: 0010:gud_plane_atomic_update+0x148/0x470 [gud] drm_atomic_helper_commit_planes+0x28e/0x310 drm_atomic_helper_commit_tail+0x2a/0x70 commit_tail+0xf1/0x150 drm_atomic_helper_commit+0x13c/0x180 drm_atomic_commit+0xb1/0xe0 info ? __pfx___drm_printfn_info+0x10/0x10 drm_mode_atomic_ioctl+0x70f/0x7c0 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 drm_ioctl_kernel+0xae/0x100 drm_ioctl+0x2a8/0x550 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 __x64_sys_ioctl+0x97/0xe0 do_syscall_64+0x7e/0x7f0 ? __ct_user_enter+0x56/0xd0 ? do_syscall_64+0x158/0x7f0 ? __ct_user_enter+0x56/0xd0 ? do_syscall_64+0x158/0x7f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Split out crtc handling from gud_plane_atomic_update() into atomic_enable() and atomic_disable() functions to delegate crtc state transitioning work to the DRM helpers. To preserve the gud state commit sequence [2], switch to the runtime PM version of drm_atomic_helper_commit_tail() which ensures that crtcs are enabled (hence sending the GUD_REQ_SET_CONTROLLER_ENABLE and GUD_REQ_SET_DISPLAY_ENABLE requests) before a framebuffer update is sent. [1] https://lore.kernel.org/all/20251231055039.44266-1-me@shenghaoyang.info/ [2] https://github.com/notro/gud/wiki/GUD-Protocol#display-state Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202601142159.0v8ilfVs-lkp@intel.com/ Fixes: 73cfd166e045 ("drm/gud: Replace simple display pipe with DRM atomic helpers") Cc: # 6.19.x Cc: # 6.18.x Signed-off-by: Shenghao Yang Reviewed-by: Thomas Zimmermann Acked-by: Ruben Wauters Signed-off-by: Ruben Wauters Link: https://patch.msgid.link/20260222054551.80864-1-me@shenghaoyang.info --- drivers/gpu/drm/gud/gud_drv.c | 9 ++++- drivers/gpu/drm/gud/gud_internal.h | 4 +++ drivers/gpu/drm/gud/gud_pipe.c | 54 ++++++++++++++++++++---------- 3 files changed, 48 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index d0122d477610..17c2dead2c13 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -339,7 +339,9 @@ static int gud_stats_debugfs(struct seq_file *m, void *data) } static const struct drm_crtc_helper_funcs gud_crtc_helper_funcs = { - .atomic_check = drm_crtc_helper_atomic_check + .atomic_check = drm_crtc_helper_atomic_check, + .atomic_enable = gud_crtc_atomic_enable, + .atomic_disable = gud_crtc_atomic_disable, }; static const struct drm_crtc_funcs gud_crtc_funcs = { @@ -364,6 +366,10 @@ static const struct drm_plane_funcs gud_plane_funcs = { DRM_GEM_SHADOW_PLANE_FUNCS, }; +static const struct drm_mode_config_helper_funcs gud_mode_config_helpers = { + .atomic_commit_tail = drm_atomic_helper_commit_tail_rpm, +}; + static const struct drm_mode_config_funcs gud_mode_config_funcs = { .fb_create = drm_gem_fb_create_with_dirty, .atomic_check = drm_atomic_helper_check, @@ -499,6 +505,7 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) drm->mode_config.min_height = le32_to_cpu(desc.min_height); drm->mode_config.max_height = le32_to_cpu(desc.max_height); drm->mode_config.funcs = &gud_mode_config_funcs; + drm->mode_config.helper_private = &gud_mode_config_helpers; /* Format init */ formats_dev = devm_kmalloc(dev, GUD_FORMATS_MAX_NUM, GFP_KERNEL); diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index d27c31648341..8eec8335f5f9 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -62,6 +62,10 @@ int gud_usb_set_u8(struct gud_device *gdrm, u8 request, u8 val); void gud_clear_damage(struct gud_device *gdrm); void gud_flush_work(struct work_struct *work); +void gud_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state); +void gud_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state); int gud_plane_atomic_check(struct drm_plane *plane, struct drm_atomic_state *state); void gud_plane_atomic_update(struct drm_plane *plane, diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 4b77be94348d..b355bf4d3389 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -580,6 +580,39 @@ int gud_plane_atomic_check(struct drm_plane *plane, return ret; } +void gud_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_device *drm = crtc->dev; + struct gud_device *gdrm = to_gud_device(drm); + int idx; + + if (!drm_dev_enter(drm, &idx)) + return; + + gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 1); + gud_usb_set(gdrm, GUD_REQ_SET_STATE_COMMIT, 0, NULL, 0); + gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, 1); + + drm_dev_exit(idx); +} + +void gud_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_device *drm = crtc->dev; + struct gud_device *gdrm = to_gud_device(drm); + int idx; + + if (!drm_dev_enter(drm, &idx)) + return; + + gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, 0); + gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 0); + + drm_dev_exit(idx); +} + void gud_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_state *atomic_state) { @@ -607,24 +640,12 @@ void gud_plane_atomic_update(struct drm_plane *plane, mutex_unlock(&gdrm->damage_lock); } - if (!drm_dev_enter(drm, &idx)) + if (!crtc || !drm_dev_enter(drm, &idx)) return; - if (!old_state->fb) - gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 1); - - if (fb && (crtc->state->mode_changed || crtc->state->connectors_changed)) - gud_usb_set(gdrm, GUD_REQ_SET_STATE_COMMIT, 0, NULL, 0); - - if (crtc->state->active_changed) - gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, crtc->state->active); - - if (!fb) - goto ctrl_disable; - ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE); if (ret) - goto ctrl_disable; + goto out; drm_atomic_helper_damage_iter_init(&iter, old_state, new_state); drm_atomic_for_each_plane_damage(&iter, &damage) @@ -632,9 +653,6 @@ void gud_plane_atomic_update(struct drm_plane *plane, drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE); -ctrl_disable: - if (!crtc->state->enable) - gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 0); - +out: drm_dev_exit(idx); } From d6db827b430bdcca3976cebca7bd69cca03cde2c Mon Sep 17 00:00:00 2001 From: Ravi Hothi Date: Fri, 27 Feb 2026 20:15:34 +0530 Subject: [PATCH 223/487] ASoC: qcom: qdsp6: Fix q6apm remove ordering during ADSP stop and start During ADSP stop and start, the kernel crashes due to the order in which ASoC components are removed. On ADSP stop, the q6apm-audio .remove callback unloads topology and removes PCM runtimes during ASoC teardown. This deletes the RTDs that contain the q6apm DAI components before their removal pass runs, leaving those components still linked to the card and causing crashes on the next rebind. Fix this by ensuring that all dependent (child) components are removed first, and the q6apm component is removed last. [ 48.105720] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0 [ 48.114763] Mem abort info: [ 48.117650] ESR = 0x0000000096000004 [ 48.121526] EC = 0x25: DABT (current EL), IL = 32 bits [ 48.127010] SET = 0, FnV = 0 [ 48.130172] EA = 0, S1PTW = 0 [ 48.133415] FSC = 0x04: level 0 translation fault [ 48.138446] Data abort info: [ 48.141422] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 48.147079] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 48.152354] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 48.157859] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001173cf000 [ 48.164517] [00000000000000d0] pgd=0000000000000000, p4d=0000000000000000 [ 48.171530] Internal error: Oops: 0000000096000004 [#1] SMP [ 48.177348] Modules linked in: q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm 8021q garp mrp stp llc snd_soc_hdmi_codec apr pdr_interface phy_qcom_edp fastrpc qcom_pd_mapper rpmsg_ctrl qrtr_smd rpmsg_char qcom_pdr_msg qcom_iris v4l2_mem2mem videobuf2_dma_contig ath11k_pci msm ubwc_config at24 ath11k videobuf2_memops mac80211 ocmem videobuf2_v4l2 libarc4 drm_gpuvm mhi qrtr videodev drm_exec snd_soc_sc8280xp gpu_sched videobuf2_common nvmem_qcom_spmi_sdam snd_soc_qcom_sdw drm_dp_aux_bus qcom_q6v5_pas qcom_spmi_temp_alarm snd_soc_qcom_common rtc_pm8xxx qcom_pon drm_display_helper cec qcom_pil_info qcom_stats soundwire_bus drm_client_lib mc dispcc0_sa8775p videocc_sa8775p qcom_q6v5 camcc_sa8775p snd_soc_dmic phy_qcom_sgmii_eth snd_soc_max98357a i2c_qcom_geni snd_soc_core dwmac_qcom_ethqos llcc_qcom icc_bwmon qcom_sysmon snd_compress qcom_refgen_regulator coresight_stm stmmac_platform snd_pcm_dmaengine qcom_common coresight_tmc stmmac coresight_replicator qcom_glink_smem coresight_cti stm_core [ 48.177444] coresight_funnel snd_pcm ufs_qcom phy_qcom_qmp_usb gpi phy_qcom_snps_femto_v2 coresight phy_qcom_qmp_ufs qcom_wdt gpucc_sa8775p pcs_xpcs mdt_loader qcom_ice icc_osm_l3 qmi_helpers snd_timer snd soundcore display_connector qcom_rng nvmem_reboot_mode drm_kms_helper phy_qcom_qmp_pcie sha256 cfg80211 rfkill socinfo fuse drm backlight ipv6 [ 48.301059] CPU: 2 UID: 0 PID: 293 Comm: kworker/u32:2 Not tainted 6.19.0-rc6-dirty #10 PREEMPT [ 48.310081] Hardware name: Qualcomm Technologies, Inc. Lemans EVK (DT) [ 48.316782] Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] [ 48.323672] pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 48.330825] pc : mutex_lock+0xc/0x54 [ 48.334514] lr : soc_dapm_shutdown_dapm+0x44/0x174 [snd_soc_core] [ 48.340794] sp : ffff800084ddb7b0 [ 48.344207] x29: ffff800084ddb7b0 x28: ffff00009cd9cf30 x27: ffff00009cd9cc00 [ 48.351544] x26: ffff000099610190 x25: ffffa31d2f19c810 x24: ffffa31d2f185098 [ 48.358869] x23: ffff800084ddb7f8 x22: 0000000000000000 x21: 00000000000000d0 [ 48.366198] x20: ffff00009ba6c338 x19: ffff00009ba6c338 x18: 00000000ffffffff [ 48.373528] x17: 000000040044ffff x16: ffffa31d4ae6dca8 x15: 072007740775076f [ 48.380853] x14: 0765076d07690774 x13: 00313a323a656369 x12: 767265733a637673 [ 48.388182] x11: 00000000000003f9 x10: ffffa31d4c7dea98 x9 : 0000000000000001 [ 48.395519] x8 : ffff00009a2aadc0 x7 : 0000000000000003 x6 : 0000000000000000 [ 48.402854] x5 : 0000000000000000 x4 : 0000000000000028 x3 : ffff000ef397a698 [ 48.410180] x2 : ffff00009a2aadc0 x1 : 0000000000000000 x0 : 00000000000000d0 [ 48.417506] Call trace: [ 48.420025] mutex_lock+0xc/0x54 (P) [ 48.423712] snd_soc_dapm_shutdown+0x44/0xbc [snd_soc_core] [ 48.429447] soc_cleanup_card_resources+0x30/0x2c0 [snd_soc_core] [ 48.435719] snd_soc_bind_card+0x4dc/0xcc0 [snd_soc_core] [ 48.441278] snd_soc_add_component+0x27c/0x2c8 [snd_soc_core] [ 48.447192] snd_soc_register_component+0x9c/0xf4 [snd_soc_core] [ 48.453371] devm_snd_soc_register_component+0x64/0xc4 [snd_soc_core] [ 48.459994] apm_probe+0xb4/0x110 [snd_q6apm] [ 48.464479] apr_device_probe+0x24/0x40 [apr] [ 48.468964] really_probe+0xbc/0x298 [ 48.472651] __driver_probe_device+0x78/0x12c [ 48.477132] driver_probe_device+0x40/0x160 [ 48.481435] __device_attach_driver+0xb8/0x134 [ 48.486011] bus_for_each_drv+0x80/0xdc [ 48.489964] __device_attach+0xa8/0x1b0 [ 48.493916] device_initial_probe+0x50/0x54 [ 48.498219] bus_probe_device+0x38/0xa0 [ 48.502170] device_add+0x590/0x760 [ 48.505761] device_register+0x20/0x30 [ 48.509623] of_register_apr_devices+0x1d8/0x318 [apr] [ 48.514905] apr_pd_status+0x2c/0x54 [apr] [ 48.519114] pdr_notifier_work+0x8c/0xe0 [pdr_interface] [ 48.524570] process_one_work+0x150/0x294 [ 48.528692] worker_thread+0x2d8/0x3d8 [ 48.532551] kthread+0x130/0x204 [ 48.535874] ret_from_fork+0x10/0x20 [ 48.539559] Code: d65f03c0 d5384102 d503201f d2800001 (c8e17c02) [ 48.545823] ---[ end trace 0000000000000000 ]--- Fixes: 5477518b8a0e ("ASoC: qdsp6: audioreach: add q6apm support") Cc: stable@vger.kernel.org Signed-off-by: Ravi Hothi Reviewed-by: Srinivas Kandagatla Link: https://patch.msgid.link/20260227144534.278568-1-ravi.hothi@oss.qualcomm.com Signed-off-by: Mark Brown --- sound/soc/qcom/qdsp6/q6apm-dai.c | 1 + sound/soc/qcom/qdsp6/q6apm-lpass-dais.c | 1 + sound/soc/qcom/qdsp6/q6apm.c | 1 + 3 files changed, 3 insertions(+) diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c index de3bdac3e791..168c166c960d 100644 --- a/sound/soc/qcom/qdsp6/q6apm-dai.c +++ b/sound/soc/qcom/qdsp6/q6apm-dai.c @@ -838,6 +838,7 @@ static const struct snd_soc_component_driver q6apm_fe_dai_component = { .ack = q6apm_dai_ack, .compress_ops = &q6apm_dai_compress_ops, .use_dai_pcm_id = true, + .remove_order = SND_SOC_COMP_ORDER_EARLY, }; static int q6apm_dai_probe(struct platform_device *pdev) diff --git a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c index 528756f1332b..5be37eeea329 100644 --- a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c +++ b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c @@ -278,6 +278,7 @@ static const struct snd_soc_component_driver q6apm_lpass_dai_component = { .of_xlate_dai_name = q6dsp_audio_ports_of_xlate_dai_name, .be_pcm_base = AUDIOREACH_BE_PCM_BASE, .use_dai_pcm_id = true, + .remove_order = SND_SOC_COMP_ORDER_FIRST, }; static int q6apm_lpass_dai_dev_probe(struct platform_device *pdev) diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c index 44841fde3856..970b08c89bb3 100644 --- a/sound/soc/qcom/qdsp6/q6apm.c +++ b/sound/soc/qcom/qdsp6/q6apm.c @@ -715,6 +715,7 @@ static const struct snd_soc_component_driver q6apm_audio_component = { .name = APM_AUDIO_DRV_NAME, .probe = q6apm_audio_probe, .remove = q6apm_audio_remove, + .remove_order = SND_SOC_COMP_ORDER_LAST, }; static int apm_probe(gpr_device_t *gdev) From facfdef64d11c08e6f1e69d02a0b87cb74cee0f5 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 4 Mar 2026 14:12:50 +0000 Subject: [PATCH 224/487] firmware: cs_dsp: Fix fragmentation regression in firmware download Use vmalloc() instead of kmalloc(..., GFP_DMA) to alloc the temporary buffer for firmware download blobs. This avoids the problem that a heavily fragmented system cannot allocate enough physically-contiguous memory for a large blob. The redundant alloc buffer mechanism was removed in commit 900baa6e7bb0 ("firmware: cs_dsp: Remove redundant download buffer allocator"). While doing that I was overly focused on the possibility of the underlying bus requiring DMA-safe memory. So I used GFP_DMA kmalloc()s. I failed to notice that the code I was removing used vmalloc(). This creates a regression. Way back in 2014 the problem of fragmentation with kmalloc()s was fixed by commit cdcd7f728753 ("ASoC: wm_adsp: Use vmalloc to allocate firmware download buffer"). Although we don't need physically-contiguous memory, we don't know if the bus needs some particular alignment of the buffers. Since the change in 2014, the firmware download has always used whatever alignment vmalloc() returns. To avoid introducing a new problem, the temporary buffer is still used, to keep the same alignment of pointers passed to regmap_raw_write(). Signed-off-by: Richard Fitzgerald Fixes: 900baa6e7bb0 ("firmware: cs_dsp: Remove redundant download buffer allocator") Link: https://patch.msgid.link/20260304141250.1578597-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/firmware/cirrus/cs_dsp.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index b4f1c01e3b5b..5d8be0ac7c5e 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -1610,11 +1610,17 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, region_name); if (reg) { + /* + * Although we expect the underlying bus does not require + * physically-contiguous buffers, we pessimistically use + * a temporary buffer instead of trusting that the + * alignment of region->data is ok. + */ region_len = le32_to_cpu(region->len); if (region_len > buf_len) { buf_len = round_up(region_len, PAGE_SIZE); - kfree(buf); - buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA); + vfree(buf); + buf = vmalloc(buf_len); if (!buf) { ret = -ENOMEM; goto out_fw; @@ -1643,7 +1649,7 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, ret = 0; out_fw: - kfree(buf); + vfree(buf); if (ret == -EOVERFLOW) cs_dsp_err(dsp, "%s: file content overflows file data\n", file); @@ -2331,11 +2337,17 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware } if (reg) { + /* + * Although we expect the underlying bus does not require + * physically-contiguous buffers, we pessimistically use + * a temporary buffer instead of trusting that the + * alignment of blk->data is ok. + */ region_len = le32_to_cpu(blk->len); if (region_len > buf_len) { buf_len = round_up(region_len, PAGE_SIZE); - kfree(buf); - buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA); + vfree(buf); + buf = vmalloc(buf_len); if (!buf) { ret = -ENOMEM; goto out_fw; @@ -2366,7 +2378,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware ret = 0; out_fw: - kfree(buf); + vfree(buf); if (ret == -EOVERFLOW) cs_dsp_err(dsp, "%s: file content overflows file data\n", file); From c15e7c62feb3751cbdd458555819df1d70374890 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 26 Feb 2026 21:54:21 -0800 Subject: [PATCH 225/487] smb/server: Fix another refcount leak in smb2_open() If ksmbd_override_fsids() fails, we jump to err_out2. At that point, fp is NULL because it hasn't been assigned dh_info.fp yet, so ksmbd_fd_put(work, fp) will not be called. However, dh_info.fp was already inserted into the session file table by ksmbd_reopen_durable_fd(), so it will leak in the session file table until the session is closed. Move fp = dh_info.fp; ahead of the ksmbd_override_fsids() check to fix the problem. Found by an experimental AI code review agent at Google. Fixes: c8efcc786146a ("ksmbd: add support for durable handles v1/v2") Signed-off-by: Guenter Roeck Reviewed-by: ChenXiaoSong Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 743c629fe7ec..48836b97951b 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3012,13 +3012,14 @@ int smb2_open(struct ksmbd_work *work) goto err_out2; } + fp = dh_info.fp; + if (ksmbd_override_fsids(work)) { rc = -ENOMEM; ksmbd_put_durable_fd(dh_info.fp); goto err_out2; } - fp = dh_info.fp; file_info = FILE_OPENED; rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat); From 40955015fae4908157ac6c959ea696d05e6e9b31 Mon Sep 17 00:00:00 2001 From: Ali Khaledi Date: Mon, 2 Mar 2026 10:15:48 +0900 Subject: [PATCH 226/487] ksmbd: fix use-after-free in proc_show_files due to early rcu_read_unlock The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is dereferenced after rcu_read_unlock(), creating a use-after-free window. A concurrent opinfo_put() can free the opinfo between the unlock and the subsequent access to opinfo->is_lease, opinfo->o_lease->state, and opinfo->level. Fix this by deferring rcu_read_unlock() until after all opinfo field accesses are complete. The values needed (const_names, count, level) are copied into local variables under the RCU read lock, and the potentially-sleeping seq_printf calls happen after the lock is released. Found by AI-assisted code review (Claude Opus 4.6, Anthropic) in collaboration with Ali Khaledi. Cc: stable@vger.kernel.org Fixes: b38f99c1217a ("ksmbd: add procfs interface for runtime monitoring and statistics") Signed-off-by: Ali Khaledi Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/vfs_cache.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index ff4ea412d900..168f2dd7e200 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -87,11 +87,7 @@ static int proc_show_files(struct seq_file *m, void *v) rcu_read_lock(); opinfo = rcu_dereference(fp->f_opinfo); - rcu_read_unlock(); - - if (!opinfo) { - seq_printf(m, " %-15s", " "); - } else { + if (opinfo) { const struct ksmbd_const_name *const_names; int count; unsigned int level; @@ -105,8 +101,12 @@ static int proc_show_files(struct seq_file *m, void *v) count = ARRAY_SIZE(ksmbd_oplock_const_names); level = opinfo->level; } + rcu_read_unlock(); ksmbd_proc_show_const_name(m, " %-15s", const_names, count, level); + } else { + rcu_read_unlock(); + seq_printf(m, " %-15s", " "); } seq_printf(m, " %#010x %#010x %s\n", From 1dfd062caa165ec9d7ee0823087930f3ab8a6294 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 7 Mar 2026 11:32:31 +0900 Subject: [PATCH 227/487] ksmbd: fix use-after-free by using call_rcu() for oplock_info ksmbd currently frees oplock_info immediately using kfree(), even though it is accessed under RCU read-side critical sections in places like opinfo_get() and proc_show_files(). Since there is no RCU grace period delay between nullifying the pointer and freeing the memory, a reader can still access oplock_info structure after it has been freed. This can leads to a use-after-free especially in opinfo_get() where atomic_inc_not_zero() is called on already freed memory. Fix this by switching to deferred freeing using call_rcu(). Fixes: 18b4fac5ef17 ("ksmbd: fix use-after-free in smb_break_all_levII_oplock()") Cc: stable@vger.kernel.org Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 29 +++++++++++++++++++++-------- fs/smb/server/oplock.h | 5 +++-- 2 files changed, 24 insertions(+), 10 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 09d9878db9cb..8c9aa17384f3 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -120,7 +120,7 @@ static void free_lease(struct oplock_info *opinfo) kfree(lease); } -static void free_opinfo(struct oplock_info *opinfo) +static void __free_opinfo(struct oplock_info *opinfo) { if (opinfo->is_lease) free_lease(opinfo); @@ -129,6 +129,18 @@ static void free_opinfo(struct oplock_info *opinfo) kfree(opinfo); } +static void free_opinfo_rcu(struct rcu_head *rcu) +{ + struct oplock_info *opinfo = container_of(rcu, struct oplock_info, rcu); + + __free_opinfo(opinfo); +} + +static void free_opinfo(struct oplock_info *opinfo) +{ + call_rcu(&opinfo->rcu, free_opinfo_rcu); +} + struct oplock_info *opinfo_get(struct ksmbd_file *fp) { struct oplock_info *opinfo; @@ -176,9 +188,9 @@ void opinfo_put(struct oplock_info *opinfo) free_opinfo(opinfo); } -static void opinfo_add(struct oplock_info *opinfo) +static void opinfo_add(struct oplock_info *opinfo, struct ksmbd_file *fp) { - struct ksmbd_inode *ci = opinfo->o_fp->f_ci; + struct ksmbd_inode *ci = fp->f_ci; down_write(&ci->m_lock); list_add(&opinfo->op_entry, &ci->m_op_list); @@ -1277,20 +1289,21 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, set_oplock_level(opinfo, req_op_level, lctx); out: - rcu_assign_pointer(fp->f_opinfo, opinfo); - opinfo->o_fp = fp; - opinfo_count_inc(fp); - opinfo_add(opinfo); + opinfo_add(opinfo, fp); + if (opinfo->is_lease) { err = add_lease_global_list(opinfo); if (err) goto err_out; } + rcu_assign_pointer(fp->f_opinfo, opinfo); + opinfo->o_fp = fp; + return 0; err_out: - free_opinfo(opinfo); + __free_opinfo(opinfo); return err; } diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 9a56eaadd0dd..921e3199e4df 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -69,8 +69,9 @@ struct oplock_info { struct lease *o_lease; struct list_head op_entry; struct list_head lease_entry; - wait_queue_head_t oplock_q; /* Other server threads */ - wait_queue_head_t oplock_brk; /* oplock breaking wait */ + wait_queue_head_t oplock_q; /* Other server threads */ + wait_queue_head_t oplock_brk; /* oplock breaking wait */ + struct rcu_head rcu; }; struct lease_break_info { From eac3361e3d5dd8067b3258c69615888eb45e9f25 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 2 Mar 2026 12:55:02 +0900 Subject: [PATCH 228/487] ksmbd: fix use-after-free in smb_lazy_parent_lease_break_close() opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is being accessed after rcu_read_unlock() has been called. This creates a race condition where the memory could be freed by a concurrent writer between the unlock and the subsequent pointer dereferences (opinfo->is_lease, etc.), leading to a use-after-free. Fixes: 5fb282ba4fef ("ksmbd: fix possible null-deref in smb_lazy_parent_lease_break_close") Cc: stable@vger.kernel.org Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 8c9aa17384f3..393a4ae47cc1 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1135,10 +1135,12 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) rcu_read_lock(); opinfo = rcu_dereference(fp->f_opinfo); - rcu_read_unlock(); - if (!opinfo || !opinfo->is_lease || opinfo->o_lease->version != 2) + if (!opinfo || !opinfo->is_lease || opinfo->o_lease->version != 2) { + rcu_read_unlock(); return; + } + rcu_read_unlock(); p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); if (!p_ci) From 1e689a56173827669a35da7cb2a3c78ed5c53680 Mon Sep 17 00:00:00 2001 From: Marios Makassikis Date: Tue, 3 Mar 2026 11:14:32 +0100 Subject: [PATCH 229/487] smb: server: fix use-after-free in smb2_open() The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is dereferenced after rcu_read_unlock(), creating a use-after-free window. Cc: stable@vger.kernel.org Signed-off-by: Marios Makassikis Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 48836b97951b..9f7ff7491e9a 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3617,10 +3617,8 @@ int smb2_open(struct ksmbd_work *work) reconnected_fp: rsp->StructureSize = cpu_to_le16(89); - rcu_read_lock(); - opinfo = rcu_dereference(fp->f_opinfo); + opinfo = opinfo_get(fp); rsp->OplockLevel = opinfo != NULL ? opinfo->level : 0; - rcu_read_unlock(); rsp->Flags = 0; rsp->CreateAction = cpu_to_le32(file_info); rsp->CreationTime = cpu_to_le64(fp->create_time); @@ -3661,6 +3659,7 @@ int smb2_open(struct ksmbd_work *work) next_ptr = &lease_ccontext->Next; next_off = conn->vals->create_lease_size; } + opinfo_put(opinfo); if (maximal_access_ctxt) { struct create_context *mxac_ccontext; From 441336115df26b966575de56daf7107ed474faed Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 3 Mar 2026 14:25:53 +0100 Subject: [PATCH 230/487] ksmbd: Don't log keys in SMB3 signing and encryption key generation When KSMBD_DEBUG_AUTH logging is enabled, generate_smb3signingkey() and generate_smb3encryptionkey() log the session, signing, encryption, and decryption key bytes. Remove the logs to avoid exposing credentials. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Cc: stable@vger.kernel.org Signed-off-by: Thorsten Blum Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/auth.c | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 5fe8c667c6b1..af5f40304331 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -589,12 +589,8 @@ static int generate_smb3signingkey(struct ksmbd_session *sess, if (!(conn->dialect >= SMB30_PROT_ID && signing->binding)) memcpy(chann->smb3signingkey, key, SMB3_SIGN_KEY_SIZE); - ksmbd_debug(AUTH, "dumping generated AES signing keys\n"); + ksmbd_debug(AUTH, "generated SMB3 signing key\n"); ksmbd_debug(AUTH, "Session Id %llu\n", sess->id); - ksmbd_debug(AUTH, "Session Key %*ph\n", - SMB2_NTLMV2_SESSKEY_SIZE, sess->sess_key); - ksmbd_debug(AUTH, "Signing Key %*ph\n", - SMB3_SIGN_KEY_SIZE, key); return 0; } @@ -652,23 +648,9 @@ static void generate_smb3encryptionkey(struct ksmbd_conn *conn, ptwin->decryption.context, sess->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE); - ksmbd_debug(AUTH, "dumping generated AES encryption keys\n"); + ksmbd_debug(AUTH, "generated SMB3 encryption/decryption keys\n"); ksmbd_debug(AUTH, "Cipher type %d\n", conn->cipher_type); ksmbd_debug(AUTH, "Session Id %llu\n", sess->id); - ksmbd_debug(AUTH, "Session Key %*ph\n", - SMB2_NTLMV2_SESSKEY_SIZE, sess->sess_key); - if (conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM || - conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) { - ksmbd_debug(AUTH, "ServerIn Key %*ph\n", - SMB3_GCM256_CRYPTKEY_SIZE, sess->smb3encryptionkey); - ksmbd_debug(AUTH, "ServerOut Key %*ph\n", - SMB3_GCM256_CRYPTKEY_SIZE, sess->smb3decryptionkey); - } else { - ksmbd_debug(AUTH, "ServerIn Key %*ph\n", - SMB3_GCM128_CRYPTKEY_SIZE, sess->smb3encryptionkey); - ksmbd_debug(AUTH, "ServerOut Key %*ph\n", - SMB3_GCM128_CRYPTKEY_SIZE, sess->smb3decryptionkey); - } } void ksmbd_gen_smb30_encryptionkey(struct ksmbd_conn *conn, From 56fbbe096a89ff4b52af78a21a4afd9d94bdcc80 Mon Sep 17 00:00:00 2001 From: Zhang Heng Date: Thu, 5 Mar 2026 10:35:59 +0800 Subject: [PATCH 231/487] ALSA: hda/realtek: Add quirk for Gigabyte Technology to fix headphone The BIOS of this machine has set 0x19 to mic, which needs to be set to headphone pin in order to work properly. Link: https://bugzilla.kernel.org/show_bug.cgi?id=220814 Signed-off-by: Zhang Heng Link: https://patch.msgid.link/b55f6ebe-7449-49f7-ae85-00d2ba1e7af0@kylinos.cn Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc662.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/hda/codecs/realtek/alc662.c b/sound/hda/codecs/realtek/alc662.c index 5073165d1f3c..3a943adf9087 100644 --- a/sound/hda/codecs/realtek/alc662.c +++ b/sound/hda/codecs/realtek/alc662.c @@ -313,6 +313,7 @@ enum { ALC897_FIXUP_HEADSET_MIC_PIN2, ALC897_FIXUP_UNIS_H3C_X500S, ALC897_FIXUP_HEADSET_MIC_PIN3, + ALC897_FIXUP_H610M_HP_PIN, }; static const struct hda_fixup alc662_fixups[] = { @@ -766,6 +767,13 @@ static const struct hda_fixup alc662_fixups[] = { { } }, }, + [ALC897_FIXUP_H610M_HP_PIN] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x0321403f }, /* HP out */ + { } + }, + }, }; static const struct hda_quirk alc662_fixup_tbl[] = { @@ -815,6 +823,7 @@ static const struct hda_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT), SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2), SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), + SND_PCI_QUIRK(0x1458, 0xa194, "H610M H V2 DDR4", ALC897_FIXUP_H610M_HP_PIN), SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN), From 9b1dbd69ba6f8f8c69bc7b77c2ce3b9c6ed05ba6 Mon Sep 17 00:00:00 2001 From: Mehul Rao Date: Thu, 5 Mar 2026 14:35:07 -0500 Subject: [PATCH 232/487] ALSA: pcm: fix use-after-free on linked stream runtime in snd_pcm_drain() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the drain loop, the local variable 'runtime' is reassigned to a linked stream's runtime (runtime = s->runtime at line 2157). After releasing the stream lock at line 2169, the code accesses runtime->no_period_wakeup, runtime->rate, and runtime->buffer_size (lines 2170-2178) — all referencing the linked stream's runtime without any lock or refcount protecting its lifetime. A concurrent close() on the linked stream's fd triggers snd_pcm_release_substream() → snd_pcm_drop() → pcm_release_private() → snd_pcm_unlink() → snd_pcm_detach_substream() → kfree(runtime). No synchronization prevents kfree(runtime) from completing while the drain path dereferences the stale pointer. Fix by caching the needed runtime fields (no_period_wakeup, rate, buffer_size) into local variables while still holding the stream lock, and using the cached values after the lock is released. Fixes: f2b3614cefb6 ("ALSA: PCM - Don't check DMA time-out too shortly") Cc: stable@vger.kernel.org Signed-off-by: Mehul Rao Link: https://patch.msgid.link/20260305193508.311096-1-mehulrao@gmail.com Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 67cf6a0e17ba..5a64453da728 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2144,6 +2144,10 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, for (;;) { long tout; struct snd_pcm_runtime *to_check; + unsigned int drain_rate; + snd_pcm_uframes_t drain_bufsz; + bool drain_no_period_wakeup; + if (signal_pending(current)) { result = -ERESTARTSYS; break; @@ -2163,16 +2167,25 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, snd_pcm_group_unref(group, substream); if (!to_check) break; /* all drained */ + /* + * Cache the runtime fields needed after unlock. + * A concurrent close() on the linked stream may free + * its runtime via snd_pcm_detach_substream() once we + * release the stream lock below. + */ + drain_no_period_wakeup = to_check->no_period_wakeup; + drain_rate = to_check->rate; + drain_bufsz = to_check->buffer_size; init_waitqueue_entry(&wait, current); set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&to_check->sleep, &wait); snd_pcm_stream_unlock_irq(substream); - if (runtime->no_period_wakeup) + if (drain_no_period_wakeup) tout = MAX_SCHEDULE_TIMEOUT; else { tout = 100; - if (runtime->rate) { - long t = runtime->buffer_size * 1100 / runtime->rate; + if (drain_rate) { + long t = drain_bufsz * 1100 / drain_rate; tout = max(t, tout); } tout = msecs_to_jiffies(tout); From 0d3429f12133c2ca47aa82ddab2342bc360c47d3 Mon Sep 17 00:00:00 2001 From: Zhang Heng Date: Fri, 6 Mar 2026 20:33:17 +0800 Subject: [PATCH 233/487] ALSA: hda/realtek: add quirk for ASUS UM6702RC The sound card of this machine cannot adjust the volume, it can only be 0 or 100%. The reason is that the DAC with pin 0x17 is connected to 0x06. Testing found that connecting 0x02 can fix this problem. Link: https://bugzilla.kernel.org/show_bug.cgi?id=220356 Signed-off-by: Zhang Heng Link: https://patch.msgid.link/20260306123317.575346-1-zhangheng@kylinos.cn Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 4c49f1195e1b..dc4a10aaef60 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7273,6 +7273,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e93, "ASUS ExpertBook B9403CVAR", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2), + HDA_CODEC_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), From 178dd118c0f07fd63a9ed74cfbd8c31ae50e33af Mon Sep 17 00:00:00 2001 From: Liucheng Lu Date: Sat, 7 Mar 2026 11:27:27 +0800 Subject: [PATCH 234/487] ALSA: hda/realtek: add HP Laptop 14s-dr5xxx mute LED quirk HP Laptop 14s-dr5xxx with ALC236 codec does not handle the toggling of the mute LED. This patch adds a quirk entry for subsystem ID 0x8a1f using ALC236_FIXUP_HP_MUTE_LED_COEFBIT2 fixup, enabling correct mute LED behavior. Signed-off-by: Liucheng Lu Link: https://patch.msgid.link/PAVPR03MB9774F3FCE9CCD181C585281AE37BA@PAVPR03MB9774.eurprd03.prod.outlook.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index dc4a10aaef60..4cfbb7922eeb 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6940,6 +6940,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89da, "HP Spectre x360 14t-ea100", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX), SND_PCI_QUIRK(0x103c, 0x89e7, "HP Elite x2 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8a1f, "HP Laptop 14s-dr5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a26, "HP Victus 16-d1xxx (MB 8A26)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), From 542127f6528ca7cc3cf61e1651d6ccb58495f953 Mon Sep 17 00:00:00 2001 From: Uzair Mughal Date: Sat, 7 Mar 2026 06:29:06 +0500 Subject: [PATCH 235/487] ALSA: hda/realtek: Add headset jack quirk for Thinkpad X390 The Lenovo ThinkPad X390 (ALC257 codec, subsystem ID 0x17aa2288) does not report headset button press events. Headphone insertion is detected (SW_HEADPHONE_INSERT), but pressing the inline microphone button on a headset produces no input events. Add a SND_PCI_QUIRK entry that maps this subsystem ID to ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, which enables headset jack button detection through alc_fixup_headset_jack() and ThinkPad ACPI integration. This is the same fixup used by similar ThinkPad models (P1 Gen 3, X1 Extreme Gen 3). Signed-off-by: Uzair Mughal Signed-off-by: Takashi Iwai Link: https://patch.msgid.link/20260307012906.20093-1-contact@uzair.is-a.dev --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 4cfbb7922eeb..ab4b22fcb72e 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7495,6 +7495,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x2288, "Thinkpad X390", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), From ce0123cbb4a40a2f1bbb815f292b26e96088639f Mon Sep 17 00:00:00 2001 From: Max Kellermann Date: Fri, 5 Sep 2025 23:15:30 +0200 Subject: [PATCH 236/487] ceph: fix i_nlink underrun during async unlink During async unlink, we drop the `i_nlink` counter before we receive the completion (that will eventually update the `i_nlink`) because "we assume that the unlink will succeed". That is not a bad idea, but it races against deletions by other clients (or against the completion of our own unlink) and can lead to an underrun which emits a WARNING like this one: WARNING: CPU: 85 PID: 25093 at fs/inode.c:407 drop_nlink+0x50/0x68 Modules linked in: CPU: 85 UID: 3221252029 PID: 25093 Comm: php-cgi8.1 Not tainted 6.14.11-cm4all1-ampere #655 Hardware name: Supermicro ARS-110M-NR/R12SPD-A, BIOS 1.1b 10/17/2023 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : drop_nlink+0x50/0x68 lr : ceph_unlink+0x6c4/0x720 sp : ffff80012173bc90 x29: ffff80012173bc90 x28: ffff086d0a45aaf8 x27: ffff0871d0eb5680 x26: ffff087f2a64a718 x25: 0000020000000180 x24: 0000000061c88647 x23: 0000000000000002 x22: ffff07ff9236d800 x21: 0000000000001203 x20: ffff07ff9237b000 x19: ffff088b8296afc0 x18: 00000000f3c93365 x17: 0000000000070000 x16: ffff08faffcbdfe8 x15: ffff08faffcbdfec x14: 0000000000000000 x13: 45445f65645f3037 x12: 34385f6369706f74 x11: 0000a2653104bb20 x10: ffffd85f26d73290 x9 : ffffd85f25664f94 x8 : 00000000000000c0 x7 : 0000000000000000 x6 : 0000000000000002 x5 : 0000000000000081 x4 : 0000000000000481 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff08727d3f91e8 Call trace: drop_nlink+0x50/0x68 (P) vfs_unlink+0xb0/0x2e8 do_unlinkat+0x204/0x288 __arm64_sys_unlinkat+0x3c/0x80 invoke_syscall.constprop.0+0x54/0xe8 do_el0_svc+0xa4/0xc8 el0_svc+0x18/0x58 el0t_64_sync_handler+0x104/0x130 el0t_64_sync+0x154/0x158 In ceph_unlink(), a call to ceph_mdsc_submit_request() submits the CEPH_MDS_OP_UNLINK to the MDS, but does not wait for completion. Meanwhile, between this call and the following drop_nlink() call, a worker thread may process a CEPH_CAP_OP_IMPORT, CEPH_CAP_OP_GRANT or just a CEPH_MSG_CLIENT_REPLY (the latter of which could be our own completion). These will lead to a set_nlink() call, updating the `i_nlink` counter to the value received from the MDS. If that new `i_nlink` value happens to be zero, it is illegal to decrement it further. But that is exactly what ceph_unlink() will do then. The WARNING can be reproduced this way: 1. Force async unlink; only the async code path is affected. Having no real clue about Ceph internals, I was unable to find out why the MDS wouldn't give me the "Fxr" capabilities, so I patched get_caps_for_async_unlink() to always succeed. (Note that the WARNING dump above was found on an unpatched kernel, without this kludge - this is not a theoretical bug.) 2. Add a sleep call after ceph_mdsc_submit_request() so the unlink completion gets handled by a worker thread before drop_nlink() is called. This guarantees that the `i_nlink` is already zero before drop_nlink() runs. The solution is to skip the counter decrement when it is already zero, but doing so without a lock is still racy (TOCTOU). Since ceph_fill_inode() and handle_cap_grant() both hold the `ceph_inode_info.i_ceph_lock` spinlock while set_nlink() runs, this seems like the proper lock to protect the `i_nlink` updates. I found prior art in NFS and SMB (using `inode.i_lock`) and AFS (using `afs_vnode.cb_lock`). All three have the zero check as well. Cc: stable@vger.kernel.org Fixes: 2ccb45462aea ("ceph: perform asynchronous unlink if we have sufficient caps") Signed-off-by: Max Kellermann Reviewed-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/dir.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 86d7aa594ea9..415db39a56d8 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1339,6 +1339,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) struct ceph_client *cl = fsc->client; struct ceph_mds_client *mdsc = fsc->mdsc; struct inode *inode = d_inode(dentry); + struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req; bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS); struct dentry *dn; @@ -1424,7 +1425,19 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) * We have enough caps, so we assume that the unlink * will succeed. Fix up the target inode and dcache. */ - drop_nlink(inode); + + /* + * Protect the i_nlink update with i_ceph_lock + * to precent racing against ceph_fill_inode() + * handling our completion on a worker thread + * and don't decrement if i_nlink has already + * been updated to zero by this completion. + */ + spin_lock(&ci->i_ceph_lock); + if (inode->i_nlink > 0) + drop_nlink(inode); + spin_unlock(&ci->i_ceph_lock); + d_delete(dentry); } else { spin_lock(&fsc->async_unlink_conflict_lock); From 43323a5934b660afae687e8e4e95ac328615a5c4 Mon Sep 17 00:00:00 2001 From: Max Kellermann Date: Tue, 24 Feb 2026 14:10:29 +0100 Subject: [PATCH 237/487] ceph: add a bunch of missing ceph_path_info initializers ceph_mdsc_build_path() must be called with a zero-initialized ceph_path_info parameter, or else the following ceph_mdsc_free_path_info() may crash. Example crash (on Linux 6.18.12): virt_to_cache: Object is not a Slab page! WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6732 kmem_cache_free+0x316/0x400 [...] Call Trace: [...] ceph_open+0x13d/0x3e0 do_dentry_open+0x134/0x480 vfs_open+0x2a/0xe0 path_openat+0x9a3/0x1160 [...] cache_from_obj: Wrong slab cache. names_cache but object is from ceph_inode_info WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6746 kmem_cache_free+0x2dd/0x400 [...] kernel BUG at mm/slub.c:634! Oops: invalid opcode: 0000 [#1] SMP NOPTI RIP: 0010:__slab_free+0x1a4/0x350 Some of the ceph_mdsc_build_path() callers had initializers, but others had not, even though they were all added by commit 15f519e9f883 ("ceph: fix race condition validating r_parent before applying state"). The ones without initializer are suspectible to random crashes. (I can imagine it could even be possible to exploit this bug to elevate privileges.) Unfortunately, these Ceph functions are undocumented and its semantics can only be derived from the code. I see that ceph_mdsc_build_path() initializes the structure only on success, but not on error. Calling ceph_mdsc_free_path_info() after a failed ceph_mdsc_build_path() call does not even make sense, but that's what all callers do, and for it to be safe, the structure must be zero-initialized. The least intrusive approach to fix this is therefore to add initializers everywhere. Cc: stable@vger.kernel.org Fixes: 15f519e9f883 ("ceph: fix race condition validating r_parent before applying state") Signed-off-by: Max Kellermann Reviewed-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/debugfs.c | 4 ++-- fs/ceph/dir.c | 2 +- fs/ceph/file.c | 4 ++-- fs/ceph/inode.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index f3fe786b4143..7dc307790240 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -79,7 +79,7 @@ static int mdsc_show(struct seq_file *s, void *p) if (req->r_inode) { seq_printf(s, " #%llx", ceph_ino(req->r_inode)); } else if (req->r_dentry) { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; @@ -98,7 +98,7 @@ static int mdsc_show(struct seq_file *s, void *p) } if (req->r_old_dentry) { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 415db39a56d8..bac9cfb6b982 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1364,7 +1364,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) if (!dn) { try_async = false; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 66bbf6d517a9..5e7c73a29aa3 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -397,7 +397,7 @@ int ceph_open(struct inode *inode, struct file *file) if (!dentry) { do_sync = true; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; @@ -807,7 +807,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if (!dn) { try_async = false; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d76f9a79dc0c..d99e12d1100b 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2551,7 +2551,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode, if (!dentry) { do_sync = true; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; From 040d159a45ded7f33201421a81df0aa2a86e5a0b Mon Sep 17 00:00:00 2001 From: Max Kellermann Date: Tue, 24 Feb 2026 14:26:57 +0100 Subject: [PATCH 238/487] ceph: fix memory leaks in ceph_mdsc_build_path() Add __putname() calls to error code paths that did not free the "path" pointer obtained by __getname(). If ownership of this pointer is not passed to the caller via path_info.path, the function must free it before returning. Cc: stable@vger.kernel.org Fixes: 3fd945a79e14 ("ceph: encode encrypted name in ceph_mdsc_build_path and dentry release") Fixes: 550f7ca98ee0 ("ceph: give up on paths longer than PATH_MAX") Signed-off-by: Max Kellermann Reviewed-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 23b6d00643c9..b1746273f186 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2768,6 +2768,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry, if (ret < 0) { dput(parent); dput(cur); + __putname(path); return ERR_PTR(ret); } @@ -2777,6 +2778,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry, if (len < 0) { dput(parent); dput(cur); + __putname(path); return ERR_PTR(len); } } @@ -2813,6 +2815,7 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry, * cannot ever succeed. Creating paths that long is * possible with Ceph, but Linux cannot use them. */ + __putname(path); return ERR_PTR(-ENAMETOOLONG); } From 081a0b78ef30f5746cda3e92e28b4d4ae92901d1 Mon Sep 17 00:00:00 2001 From: Hristo Venev Date: Wed, 25 Feb 2026 19:07:56 +0200 Subject: [PATCH 239/487] ceph: do not skip the first folio of the next object in writeback When `ceph_process_folio_batch` encounters a folio past the end of the current object, it should leave it in the batch so that it is picked up in the next iteration. Removing the folio from the batch means that it does not get written back and remains dirty instead. This makes `fsync()` silently skip some of the data, delays capability release, and breaks coherence with `O_DIRECT`. The link below contains instructions for reproducing the bug. Cc: stable@vger.kernel.org Fixes: ce80b76dd327 ("ceph: introduce ceph_process_folio_batch() method") Link: https://tracker.ceph.com/issues/75156 Signed-off-by: Hristo Venev Reviewed-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/addr.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index e87b3bb94ee8..2090fc78529c 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1326,7 +1326,6 @@ void ceph_process_folio_batch(struct address_space *mapping, continue; } else if (rc == -E2BIG) { folio_unlock(folio); - ceph_wbc->fbatch.folios[i] = NULL; break; } From d800d0bb2009a73630a096d7c7a80a2e64c1e41e Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 25 Feb 2026 13:51:09 +0100 Subject: [PATCH 240/487] dt-bindings: i2c: dw: Update maintainer Jarkko does now work for Intel anymore and since I'm currently maintaining this driver, update my contact information here to make sure patches get Cc'd to me as well. Signed-off-by: Mika Westerberg Reported-by: Andy Shevchenko (internally) Reviewed-by: Andy Shevchenko Acked-by: Rob Herring (Arm) Signed-off-by: Wolfram Sang --- Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml index 914200188809..082fdc2e69ea 100644 --- a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Synopsys DesignWare APB I2C Controller maintainers: - - Jarkko Nikula + - Mika Westerberg allOf: - $ref: /schemas/i2c/i2c-controller.yaml# From b20b437666e1cb26a7c499d1664e8f2a0ac67000 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Fri, 6 Mar 2026 01:24:32 +0800 Subject: [PATCH 241/487] spi: amlogic: spifc-a4: Fix DMA mapping error handling Fix three bugs in aml_sfc_dma_buffer_setup() error paths: 1. Unnecessary goto: When the first DMA mapping (sfc->daddr) fails, nothing needs cleanup. Use direct return instead of goto. 2. Double-unmap bug: When info DMA mapping failed, the code would unmap sfc->daddr inline, then fall through to out_map_data which would unmap it again, causing a double-unmap. 3. Wrong unmap size: The out_map_info label used datalen instead of infolen when unmapping sfc->iaddr, which could lead to incorrect DMA sync behavior. Fixes: 4670db6f32e9 ("spi: amlogic: add driver for Amlogic SPI Flash Controller") Signed-off-by: Felix Gu Link: https://patch.msgid.link/20260306-spifc-a4-v1-1-f22c9965f64a@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi-amlogic-spifc-a4.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-amlogic-spifc-a4.c b/drivers/spi/spi-amlogic-spifc-a4.c index 2aef528cfc1b..3956869cfec1 100644 --- a/drivers/spi/spi-amlogic-spifc-a4.c +++ b/drivers/spi/spi-amlogic-spifc-a4.c @@ -411,7 +411,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf, ret = dma_mapping_error(sfc->dev, sfc->daddr); if (ret) { dev_err(sfc->dev, "DMA mapping error\n"); - goto out_map_data; + return ret; } cmd = CMD_DATA_ADDRL(sfc->daddr); @@ -429,7 +429,6 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf, ret = dma_mapping_error(sfc->dev, sfc->iaddr); if (ret) { dev_err(sfc->dev, "DMA mapping error\n"); - dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir); goto out_map_data; } @@ -448,7 +447,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf, return 0; out_map_info: - dma_unmap_single(sfc->dev, sfc->iaddr, datalen, dir); + dma_unmap_single(sfc->dev, sfc->iaddr, infolen, dir); out_map_data: dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir); From ad0e9ac2d5f5ab7a773c2c07ecf06ee59db9259f Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Thu, 5 Mar 2026 20:22:38 +0800 Subject: [PATCH 242/487] spi: atcspi200: Fix double-free in atcspi_configure_dma() The driver uses devm_dma_request_chan() which registers automatic cleanup via devm_add_action_or_reset(). Calling dma_release_channel() manually on the RX channel when TX channel request fails causes a double-free when the devm cleanup runs. Remove the unnecessary manual cleanup and simplify the error handling since devm will properly release channels on probe failure or driver detach. Fixes: 34e3815ea459 ("spi: atcspi200: Add ATCSPI200 SPI controller driver") Signed-off-by: Felix Gu Link: https://patch.msgid.link/20260305-atcspi2000-v1-1-eafe08dcca60@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi-atcspi200.c | 28 +++++++--------------------- 1 file changed, 7 insertions(+), 21 deletions(-) diff --git a/drivers/spi/spi-atcspi200.c b/drivers/spi/spi-atcspi200.c index 60a37ff5c6f5..fef6954d27e1 100644 --- a/drivers/spi/spi-atcspi200.c +++ b/drivers/spi/spi-atcspi200.c @@ -497,31 +497,17 @@ static int atcspi_init_resources(struct platform_device *pdev, static int atcspi_configure_dma(struct atcspi_dev *spi) { - struct dma_chan *dma_chan; - int ret = 0; + spi->host->dma_rx = devm_dma_request_chan(spi->dev, "rx"); + if (IS_ERR(spi->host->dma_rx)) + return PTR_ERR(spi->host->dma_rx); - dma_chan = devm_dma_request_chan(spi->dev, "rx"); - if (IS_ERR(dma_chan)) { - ret = PTR_ERR(dma_chan); - goto err_exit; - } - spi->host->dma_rx = dma_chan; + spi->host->dma_tx = devm_dma_request_chan(spi->dev, "tx"); + if (IS_ERR(spi->host->dma_tx)) + return PTR_ERR(spi->host->dma_tx); - dma_chan = devm_dma_request_chan(spi->dev, "tx"); - if (IS_ERR(dma_chan)) { - ret = PTR_ERR(dma_chan); - goto free_rx; - } - spi->host->dma_tx = dma_chan; init_completion(&spi->dma_completion); - return ret; - -free_rx: - dma_release_channel(spi->host->dma_rx); - spi->host->dma_rx = NULL; -err_exit: - return ret; + return 0; } static int atcspi_enable_clk(struct atcspi_dev *spi) From 155a3bedccaf57c69aa0b590ba3fb579debf3a4d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 8 Mar 2026 22:39:02 +0800 Subject: [PATCH 243/487] ublk: don't clear GD_SUPPRESS_PART_SCAN for unprivileged daemons When UBLK_F_NO_AUTO_PART_SCAN is set, GD_SUPPRESS_PART_SCAN is cleared unconditionally, including for unprivileged daemons. Keep it consistent with the code block for setting GD_SUPPRESS_PART_SCAN by not clearing it for unprivileged daemons. In reality this isn't a problem because ioctl(BLKRRPART) requires CAP_SYS_ADMIN, but it is more reliable to not clear the bit. Cc: Alexander Atanasov Fixes: 8443e2087e70 ("ublk: add UBLK_F_NO_AUTO_PART_SCAN feature flag") Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 03edabdf8977..9f6e9109d310 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -4440,7 +4440,9 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, /* Skip partition scan if disabled by user */ if (ub->dev_info.flags & UBLK_F_NO_AUTO_PART_SCAN) { - clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state); + /* Not clear for unprivileged daemons, see comment above */ + if (!ub->unprivileged_daemons) + clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state); } else { /* Schedule async partition scan for trusted daemons */ if (!ub->unprivileged_daemons) From 1bc17c67194716f53037685b7059a22cc1a911b2 Mon Sep 17 00:00:00 2001 From: Sheetal Date: Tue, 3 Mar 2026 15:32:49 +0530 Subject: [PATCH 244/487] ASoC: tegra: Add support for Tegra238 soundcard Tegra238 platforms use different clock rates for plla and plla_out0 clocks. Add Tegra238 support in the Tegra sound card driver to apply specific clock configurations. Signed-off-by: Aditya Bavanari Signed-off-by: Sheetal Reviewed-by: Jon Hunter Link: https://patch.msgid.link/20260303100249.3214529-3-sheetal@nvidia.com Signed-off-by: Mark Brown --- sound/soc/tegra/tegra_audio_graph_card.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/sound/soc/tegra/tegra_audio_graph_card.c b/sound/soc/tegra/tegra_audio_graph_card.c index 94b5ab77649b..ea10e6e8a9fe 100644 --- a/sound/soc/tegra/tegra_audio_graph_card.c +++ b/sound/soc/tegra/tegra_audio_graph_card.c @@ -231,6 +231,15 @@ static const struct tegra_audio_cdata tegra186_data = { .plla_out0_rates[x11_RATE] = 45158400, }; +static const struct tegra_audio_cdata tegra238_data = { + /* PLLA */ + .plla_rates[x8_RATE] = 1277952000, + .plla_rates[x11_RATE] = 1264435200, + /* PLLA_OUT0 */ + .plla_out0_rates[x8_RATE] = 49152000, + .plla_out0_rates[x11_RATE] = 45158400, +}; + static const struct tegra_audio_cdata tegra264_data = { /* PLLA1 */ .plla_rates[x8_RATE] = 983040000, @@ -245,6 +254,8 @@ static const struct of_device_id graph_of_tegra_match[] = { .data = &tegra210_data }, { .compatible = "nvidia,tegra186-audio-graph-card", .data = &tegra186_data }, + { .compatible = "nvidia,tegra238-audio-graph-card", + .data = &tegra238_data }, { .compatible = "nvidia,tegra264-audio-graph-card", .data = &tegra264_data }, {}, From 3306a589e598b50a5bbdfe837371670b507043c0 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 9 Mar 2026 15:34:41 +0100 Subject: [PATCH 245/487] io_uring/register: fix comment about task_no_new_privs The actual code is right, but the comment is the wrong way around. Fixes: ed82f35b926b ("io_uring: allow registration of per-task restrictions") Signed-off-by: Jann Horn Signed-off-by: Jens Axboe --- io_uring/register.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/io_uring/register.c b/io_uring/register.c index 594b1f2ce875..a839b22fd392 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -202,7 +202,7 @@ static int io_register_restrictions_task(void __user *arg, unsigned int nr_args) return -EPERM; /* * Similar to seccomp, disallow setting a filter if task_no_new_privs - * is true and we're not CAP_SYS_ADMIN. + * is false and we're not CAP_SYS_ADMIN. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) @@ -238,7 +238,7 @@ static int io_register_bpf_filter_task(void __user *arg, unsigned int nr_args) /* * Similar to seccomp, disallow setting a filter if task_no_new_privs - * is true and we're not CAP_SYS_ADMIN. + * is false and we're not CAP_SYS_ADMIN. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) From 7fdaa640c810cb42090a182c33f905bcc47a616a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 6 Mar 2026 09:35:06 -0800 Subject: [PATCH 246/487] objtool: Handle Clang RSP musical chairs For no apparent reason (possibly related to CONFIG_KMSAN), Clang can randomly pass the value of RSP to other registers and then back again to RSP. Handle that accordingly. Fixes the following warnings: drivers/input/misc/uinput.o: warning: objtool: uinput_str_to_user+0x165: undefined stack state drivers/input/misc/uinput.o: warning: objtool: uinput_str_to_user+0x165: unknown CFA base reg -1 Reported-by: Arnd Bergmann Closes: https://lore.kernel.org/90956545-2066-46e3-b547-10c884582eb0@app.fastmail.com Link: https://patch.msgid.link/240e6a172cc73292499334a3724d02ccb3247fc7.1772818491.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/arch/x86/decode.c | 68 +++++++++++++-------------------- tools/objtool/check.c | 14 +++++++ 2 files changed, 40 insertions(+), 42 deletions(-) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 73bfea220d1b..c5817829cdfa 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -395,52 +395,36 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (!rex_w) break; - if (modrm_reg == CFI_SP) { - - if (mod_is_reg()) { - /* mov %rsp, reg */ - ADD_OP(op) { - op->src.type = OP_SRC_REG; - op->src.reg = CFI_SP; - op->dest.type = OP_DEST_REG; - op->dest.reg = modrm_rm; - } - break; - - } else { - /* skip RIP relative displacement */ - if (is_RIP()) - break; - - /* skip nontrivial SIB */ - if (have_SIB()) { - modrm_rm = sib_base; - if (sib_index != CFI_SP) - break; - } - - /* mov %rsp, disp(%reg) */ - ADD_OP(op) { - op->src.type = OP_SRC_REG; - op->src.reg = CFI_SP; - op->dest.type = OP_DEST_REG_INDIRECT; - op->dest.reg = modrm_rm; - op->dest.offset = ins.displacement.value; - } - break; - } - - break; - } - - if (rm_is_reg(CFI_SP)) { - - /* mov reg, %rsp */ + if (mod_is_reg()) { + /* mov reg, reg */ ADD_OP(op) { op->src.type = OP_SRC_REG; op->src.reg = modrm_reg; op->dest.type = OP_DEST_REG; - op->dest.reg = CFI_SP; + op->dest.reg = modrm_rm; + } + break; + } + + /* skip RIP relative displacement */ + if (is_RIP()) + break; + + /* skip nontrivial SIB */ + if (have_SIB()) { + modrm_rm = sib_base; + if (sib_index != CFI_SP) + break; + } + + /* mov %rsp, disp(%reg) */ + if (modrm_reg == CFI_SP) { + ADD_OP(op) { + op->src.type = OP_SRC_REG; + op->src.reg = CFI_SP; + op->dest.type = OP_DEST_REG_INDIRECT; + op->dest.reg = modrm_rm; + op->dest.offset = ins.displacement.value; } break; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a30379e4ff97..786b2f2adbab 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3000,6 +3000,20 @@ static int update_cfi_state(struct instruction *insn, cfi->stack_size += 8; } + else if (cfi->vals[op->src.reg].base == CFI_CFA) { + /* + * Clang RSP musical chairs: + * + * mov %rsp, %rdx [handled above] + * ... + * mov %rdx, %rbx [handled here] + * ... + * mov %rbx, %rsp [handled above] + */ + cfi->vals[op->dest.reg].base = CFI_CFA; + cfi->vals[op->dest.reg].offset = cfi->vals[op->src.reg].offset; + } + break; From 9a73f085dc91980ab7fcc5e9716f4449424b3b59 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 6 Mar 2026 10:28:14 -0800 Subject: [PATCH 247/487] objtool: Fix another stack overflow in validate_branch() The insn state is getting saved on the stack twice for each recursive iteration. No need for that, once is enough. Fixes the following reported stack overflow: drivers/scsi/qla2xxx/qla_dbg.o: error: SIGSEGV: objtool stack overflow! Segmentation fault Fixes: 70589843b36f ("objtool: Add option to trace function validation") Reported-by: Arnd Bergmann Closes: https://lore.kernel.org/90956545-2066-46e3-b547-10c884582eb0@app.fastmail.com Link: https://patch.msgid.link/8b97f62d083457f3b0a29a424275f7957dd3372f.1772821683.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- tools/objtool/check.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 786b2f2adbab..91b3ff4803cf 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3748,7 +3748,7 @@ static void checksum_update_insn(struct objtool_file *file, struct symbol *func, static int validate_branch(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state state); static int do_validate_branch(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct insn_state state); + struct instruction *insn, struct insn_state *state); static int validate_insn(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state *statep, @@ -4013,7 +4013,7 @@ static int validate_insn(struct objtool_file *file, struct symbol *func, * tools/objtool/Documentation/objtool.txt. */ static int do_validate_branch(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct insn_state state) + struct instruction *insn, struct insn_state *state) { struct instruction *next_insn, *prev_insn = NULL; bool dead_end; @@ -4044,7 +4044,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func, return 1; } - ret = validate_insn(file, func, insn, &state, prev_insn, next_insn, + ret = validate_insn(file, func, insn, state, prev_insn, next_insn, &dead_end); if (!insn->trace) { @@ -4055,7 +4055,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func, } if (!dead_end && !next_insn) { - if (state.cfi.cfa.base == CFI_UNDEFINED) + if (state->cfi.cfa.base == CFI_UNDEFINED) return 0; if (file->ignore_unreachables) return 0; @@ -4080,7 +4080,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, int ret; trace_depth_inc(); - ret = do_validate_branch(file, func, insn, state); + ret = do_validate_branch(file, func, insn, &state); trace_depth_dec(); return ret; From 2fcfe5951eb2e8440fc5e1dd6ea977336ff83a1d Mon Sep 17 00:00:00 2001 From: zhidao su Date: Mon, 9 Mar 2026 10:46:12 +0800 Subject: [PATCH 248/487] sched_ext: Use WRITE_ONCE() for the write side of scx_enable helper pointer scx_enable() uses double-checked locking to lazily initialize a static kthread_worker pointer. The fast path reads helper locklessly: if (!READ_ONCE(helper)) { // lockless read -- no helper_mutex The write side initializes helper under helper_mutex, but previously used a plain assignment: helper = kthread_run_worker(0, "scx_enable_helper"); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ plain write -- KCSAN data race with READ_ONCE() above Since READ_ONCE() on the fast path and the plain write on the initialization path access the same variable without a common lock, they constitute a data race. KCSAN requires that all sides of a lock-free access use READ_ONCE()/WRITE_ONCE() consistently. Use a temporary variable to stage the result of kthread_run_worker(), and only WRITE_ONCE() into helper after confirming the pointer is valid. This avoids a window where a concurrent caller on the fast path could observe an ERR pointer via READ_ONCE(helper) before the error check completes. Fixes: b06ccbabe250 ("sched_ext: Fix starvation of scx_enable() under fair-class saturation") Signed-off-by: zhidao su Acked-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 174e3650d7fe..26a6ac2f8826 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -5258,13 +5258,14 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (!READ_ONCE(helper)) { mutex_lock(&helper_mutex); if (!helper) { - helper = kthread_run_worker(0, "scx_enable_helper"); - if (IS_ERR_OR_NULL(helper)) { - helper = NULL; + struct kthread_worker *w = + kthread_run_worker(0, "scx_enable_helper"); + if (IS_ERR_OR_NULL(w)) { mutex_unlock(&helper_mutex); return -ENOMEM; } - sched_set_fifo(helper->task); + sched_set_fifo(w->task); + WRITE_ONCE(helper, w); } mutex_unlock(&helper_mutex); } From 111e2863372c322e836e0c896f6dd9cf4ee08c71 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Tue, 10 Mar 2026 02:01:34 +0800 Subject: [PATCH 249/487] spi: rockchip-sfc: Fix double-free in remove() callback The driver uses devm_spi_register_controller() for registration, which automatically unregisters the controller via devm cleanup when the device is removed. The manual call to spi_unregister_controller() in the remove() callback can lead to a double-free. And to make sure controller is unregistered before DMA buffer is unmapped, switch to use spi_register_controller() in probe(). Fixes: 8011709906d0 ("spi: rockchip-sfc: Support pm ops") Signed-off-by: Felix Gu Link: https://patch.msgid.link/20260310-sfc-v2-1-67fab04b097f@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi-rockchip-sfc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c index 2990bf85ee47..174995042f53 100644 --- a/drivers/spi/spi-rockchip-sfc.c +++ b/drivers/spi/spi-rockchip-sfc.c @@ -711,7 +711,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) } } - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret) goto err_register; From 785d4625d3e05bb0ac536ff4fd74d096cfe51714 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 Mar 2026 14:20:14 -0600 Subject: [PATCH 250/487] io_uring/bpf_filter: use bpf_prog_run_pin_on_cpu() to prevent migration Since the caller, __io_uring_run_bpf_filters(), doesn't prevent migration, it should use the migration disabling variant for running the BPF program. Fixes: d42eb05e60fe ("io_uring: add support for BPF filtering for opcode restrictions") Signed-off-by: Jens Axboe --- io_uring/bpf_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/bpf_filter.c b/io_uring/bpf_filter.c index 28a23e92ee81..9cc44764e0ac 100644 --- a/io_uring/bpf_filter.c +++ b/io_uring/bpf_filter.c @@ -85,7 +85,7 @@ int __io_uring_run_bpf_filters(struct io_bpf_filter __rcu **filters, do { if (filter == &dummy_filter) return -EACCES; - ret = bpf_prog_run(filter->prog, &bpf_ctx); + ret = bpf_prog_run_pin_on_cpu(filter->prog, &bpf_ctx); if (!ret) return -EACCES; filter = filter->next; From 2f22702dc0fee06a240404e0f7ead5b789b253d8 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Thu, 26 Feb 2026 17:16:44 +0100 Subject: [PATCH 251/487] drm/bridge: ti-sn65dsi83: fix CHA_DSI_CLK_RANGE rounding The DSI frequency must be in the range: (CHA_DSI_CLK_RANGE * 5 MHz) <= DSI freq < ((CHA_DSI_CLK_RANGE + 1) * 5 MHz) So the register value should point to the lower range value, but DIV_ROUND_UP() rounds the division to the higher range value, resulting in an excess of 1 (unless the frequency is an exact multiple of 5 MHz). For example for a 437100000 MHz clock CHA_DSI_CLK_RANGE should be 87 (0x57): (87 * 5 = 435) <= 437.1 < (88 * 5 = 440) but current code returns 88 (0x58). Fix the computation by removing the DIV_ROUND_UP(). Fixes: ceb515ba29ba ("drm/bridge: ti-sn65dsi83: Add TI SN65DSI83 and SN65DSI84 driver") Cc: stable@vger.kernel.org Reviewed-by: Marek Vasut Link: https://patch.msgid.link/20260226-ti-sn65dsi83-dual-lvds-fixes-and-test-pattern-v1-1-2e15f5a9a6a0@bootlin.com Signed-off-by: Luca Ceresoli --- drivers/gpu/drm/bridge/ti-sn65dsi83.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index f6736b4457bb..d2a81175d279 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -351,9 +351,9 @@ static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx, * DSI_CLK = mode clock * bpp / dsi_data_lanes / 2 * the 2 is there because the bus is DDR. */ - return DIV_ROUND_UP(clamp((unsigned int)mode->clock * - mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) / - ctx->dsi->lanes / 2, 40000U, 500000U), 5000U); + return clamp((unsigned int)mode->clock * + mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) / + ctx->dsi->lanes / 2, 40000U, 500000U) / 5000U; } static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx) From d0d727746944096a6681dc6adb5f123fc5aa018d Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Thu, 26 Feb 2026 17:16:45 +0100 Subject: [PATCH 252/487] drm/bridge: ti-sn65dsi83: halve horizontal syncs for dual LVDS output Dual LVDS output (available on the SN65DSI84) requires HSYNC_PULSE_WIDTH and HORIZONTAL_BACK_PORCH to be divided by two with respect to the values used for single LVDS output. While not clearly stated in the datasheet, this is needed according to the DSI Tuner [0] output. It also makes sense intuitively because in dual LVDS output two pixels at a time are output and so the output clock is half of the pixel clock. Some dual-LVDS panels refuse to show any picture without this fix. Divide by two HORIZONTAL_FRONT_PORCH too, even though this register is used only for test pattern generation which is not currently implemented by this driver. [0] https://www.ti.com/tool/DSI-TUNER Fixes: ceb515ba29ba ("drm/bridge: ti-sn65dsi83: Add TI SN65DSI83 and SN65DSI84 driver") Cc: stable@vger.kernel.org Reviewed-by: Marek Vasut Link: https://patch.msgid.link/20260226-ti-sn65dsi83-dual-lvds-fixes-and-test-pattern-v1-2-2e15f5a9a6a0@bootlin.com Signed-off-by: Luca Ceresoli --- drivers/gpu/drm/bridge/ti-sn65dsi83.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index d2a81175d279..17a885244e1e 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -517,6 +517,7 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, struct drm_atomic_state *state) { struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + const unsigned int dual_factor = ctx->lvds_dual_link ? 2 : 1; const struct drm_bridge_state *bridge_state; const struct drm_crtc_state *crtc_state; const struct drm_display_mode *mode; @@ -653,18 +654,18 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, /* 32 + 1 pixel clock to ensure proper operation */ le16val = cpu_to_le16(32 + 1); regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &le16val, 2); - le16val = cpu_to_le16(mode->hsync_end - mode->hsync_start); + le16val = cpu_to_le16((mode->hsync_end - mode->hsync_start) / dual_factor); regmap_bulk_write(ctx->regmap, REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, &le16val, 2); le16val = cpu_to_le16(mode->vsync_end - mode->vsync_start); regmap_bulk_write(ctx->regmap, REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, &le16val, 2); regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_BACK_PORCH, - mode->htotal - mode->hsync_end); + (mode->htotal - mode->hsync_end) / dual_factor); regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_BACK_PORCH, mode->vtotal - mode->vsync_end); regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_FRONT_PORCH, - mode->hsync_start - mode->hdisplay); + (mode->hsync_start - mode->hdisplay) / dual_factor); regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_FRONT_PORCH, mode->vsync_start - mode->vdisplay); regmap_write(ctx->regmap, REG_VID_CHA_TEST_PATTERN, 0x00); From 3c99c9f0ed60582c1c9852b685d78d5d3a50de63 Mon Sep 17 00:00:00 2001 From: "matteo.cotifava" Date: Mon, 9 Mar 2026 22:54:11 +0100 Subject: [PATCH 253/487] ASoC: soc-core: drop delayed_work_pending() check before flush The delayed_work_pending() check before flush_delayed_work() in soc_free_pcm_runtime() is unnecessary and racy. flush_delayed_work() is safe to call unconditionally - it is a no-op when no work is pending. Remove the check. The original check was added by commit 9c9b65203492 ("ASoC: core: only flush inited work during free") but delayed_work_pending() followed by flush_delayed_work() has a time-of-check/time-of-use window where work can become pending between the two calls. Fixes: 9c9b65203492 ("ASoC: core: only flush inited work during free") Signed-off-by: Matteo Cotifava Link: https://patch.msgid.link/20260309215412.545628-2-cotifavamatteo@gmail.com Signed-off-by: Mark Brown --- sound/soc/soc-core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index d0fffef65daf..e5ac8ae1665d 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -462,8 +462,7 @@ static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd) list_del(&rtd->list); - if (delayed_work_pending(&rtd->delayed_work)) - flush_delayed_work(&rtd->delayed_work); + flush_delayed_work(&rtd->delayed_work); snd_soc_pcm_component_free(rtd); /* From 95bc5c225513fc3c4ce169563fb5e3929fbb938b Mon Sep 17 00:00:00 2001 From: "matteo.cotifava" Date: Mon, 9 Mar 2026 22:54:12 +0100 Subject: [PATCH 254/487] ASoC: soc-core: flush delayed work before removing DAIs and widgets When a sound card is unbound while a PCM stream is open, a use-after-free can occur in snd_soc_dapm_stream_event(), called from the close_delayed_work workqueue handler. During unbind, snd_soc_unbind_card() flushes delayed work and then calls soc_cleanup_card_resources(). Inside cleanup, snd_card_disconnect_sync() releases all PCM file descriptors, and the resulting PCM close path can call snd_soc_dapm_stream_stop() which schedules new delayed work with a pmdown_time timer delay. Since this happens after the flush in snd_soc_unbind_card(), the new work is not caught. soc_remove_link_components() then frees DAPM widgets before this work fires, leading to the use-after-free. The existing flush in soc_free_pcm_runtime() also cannot help as it runs after soc_remove_link_components() has already freed the widgets. Add a flush in soc_cleanup_card_resources() after snd_card_disconnect_sync() (after which no new PCM closes can schedule further delayed work) and before soc_remove_link_dais() and soc_remove_link_components() (which tear down the structures the delayed work accesses). Fixes: e894efef9ac7 ("ASoC: core: add support to card rebind") Signed-off-by: Matteo Cotifava Link: https://patch.msgid.link/20260309215412.545628-3-cotifavamatteo@gmail.com Signed-off-by: Mark Brown --- sound/soc/soc-core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index e5ac8ae1665d..cf826c2a8b59 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2121,6 +2121,9 @@ static void soc_cleanup_card_resources(struct snd_soc_card *card) for_each_card_rtds(card, rtd) if (rtd->initialized) snd_soc_link_exit(rtd); + /* flush delayed work before removing DAIs and DAPM widgets */ + snd_soc_flush_all_delayed_work(card); + /* remove and free each DAI */ soc_remove_link_dais(card); soc_remove_link_components(card); From 9063d7e2615f4a7ab321de6b520e23d370e58816 Mon Sep 17 00:00:00 2001 From: Massimiliano Pellizzer Date: Thu, 15 Jan 2026 15:30:50 +0100 Subject: [PATCH 255/487] apparmor: validate DFA start states are in bounds in unpack_pdb Start states are read from untrusted data and used as indexes into the DFA state tables. The aa_dfa_next() function call in unpack_pdb() will access dfa->tables[YYTD_ID_BASE][start], and if the start state exceeds the number of states in the DFA, this results in an out-of-bound read. ================================================================== BUG: KASAN: slab-out-of-bounds in aa_dfa_next+0x2a1/0x360 Read of size 4 at addr ffff88811956fb90 by task su/1097 ... Reject policies with out-of-bounds start states during unpacking to prevent the issue. Fixes: ad5ff3db53c6 ("AppArmor: Add ability to load extended policy") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: Massimiliano Pellizzer Signed-off-by: John Johansen --- security/apparmor/policy_unpack.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 1769417a9962..ba5d40dbeb24 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -1010,7 +1010,17 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy, if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) { /* default start state for xmatch and file dfa */ pdb->start[AA_CLASS_FILE] = DFA_START; - } /* setup class index */ + } + + size_t state_count = pdb->dfa->tables[YYTD_ID_BASE]->td_lolen; + + if (pdb->start[0] >= state_count || + pdb->start[AA_CLASS_FILE] >= state_count) { + *info = "invalid dfa start state"; + goto fail; + } + + /* setup class index */ for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) { pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0], i); From e38c55d9f834e5b848bfed0f5c586aaf45acb825 Mon Sep 17 00:00:00 2001 From: Massimiliano Pellizzer Date: Tue, 20 Jan 2026 15:24:04 +0100 Subject: [PATCH 256/487] apparmor: fix memory leak in verify_header The function sets `*ns = NULL` on every call, leaking the namespace string allocated in previous iterations when multiple profiles are unpacked. This also breaks namespace consistency checking since *ns is always NULL when the comparison is made. Remove the incorrect assignment. The caller (aa_unpack) initializes *ns to NULL once before the loop, which is sufficient. Fixes: dd51c8485763 ("apparmor: provide base for multiple profiles to be replaced at once") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: Massimiliano Pellizzer Signed-off-by: John Johansen --- security/apparmor/policy_unpack.c | 1 - 1 file changed, 1 deletion(-) diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index ba5d40dbeb24..5d90ea55de82 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -1419,7 +1419,6 @@ static int verify_header(struct aa_ext *e, int required, const char **ns) { int error = -EPROTONOSUPPORT; const char *name = NULL; - *ns = NULL; /* get the interface version */ if (!aa_unpack_u32(e, &e->version, "version")) { From ab09264660f9de5d05d1ef4e225aa447c63a8747 Mon Sep 17 00:00:00 2001 From: Massimiliano Pellizzer Date: Tue, 13 Jan 2026 09:09:43 +0100 Subject: [PATCH 257/487] apparmor: replace recursive profile removal with iterative approach The profile removal code uses recursion when removing nested profiles, which can lead to kernel stack exhaustion and system crashes. Reproducer: $ pf='a'; for ((i=0; i<1024; i++)); do echo -e "profile $pf { \n }" | apparmor_parser -K -a; pf="$pf//x"; done $ echo -n a > /sys/kernel/security/apparmor/.remove Replace the recursive __aa_profile_list_release() approach with an iterative approach in __remove_profile(). The function repeatedly finds and removes leaf profiles until the entire subtree is removed, maintaining the same removal semantic without recursion. Fixes: c88d4c7b049e ("AppArmor: core policy routines") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: Massimiliano Pellizzer Signed-off-by: John Johansen --- security/apparmor/policy.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 9108d74c6b46..566821852592 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -191,19 +191,43 @@ static void __list_remove_profile(struct aa_profile *profile) } /** - * __remove_profile - remove old profile, and children - * @profile: profile to be replaced (NOT NULL) + * __remove_profile - remove profile, and children + * @profile: profile to be removed (NOT NULL) * * Requires: namespace list lock be held, or list not be shared */ static void __remove_profile(struct aa_profile *profile) { + struct aa_profile *curr, *to_remove; + AA_BUG(!profile); AA_BUG(!profile->ns); AA_BUG(!mutex_is_locked(&profile->ns->lock)); /* release any children lists first */ - __aa_profile_list_release(&profile->base.profiles); + if (!list_empty(&profile->base.profiles)) { + curr = list_first_entry(&profile->base.profiles, struct aa_profile, base.list); + + while (curr != profile) { + + while (!list_empty(&curr->base.profiles)) + curr = list_first_entry(&curr->base.profiles, + struct aa_profile, base.list); + + to_remove = curr; + if (!list_is_last(&to_remove->base.list, + &aa_deref_parent(curr)->base.profiles)) + curr = list_next_entry(to_remove, base.list); + else + curr = aa_deref_parent(curr); + + /* released by free_profile */ + aa_label_remove(&to_remove->label); + __aafs_profile_rmdir(to_remove); + __list_remove_profile(to_remove); + } + } + /* released by free_profile */ aa_label_remove(&profile->label); __aafs_profile_rmdir(profile); From 306039414932c80f8420695a24d4fe10c84ccfb2 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Tue, 3 Mar 2026 11:08:02 -0800 Subject: [PATCH 258/487] apparmor: fix: limit the number of levels of policy namespaces Currently the number of policy namespaces is not bounded relying on the user namespace limit. However policy namespaces aren't strictly tied to user namespaces and it is possible to create them and nest them arbitrarily deep which can be used to exhaust system resource. Hard cap policy namespaces to the same depth as user namespaces. Fixes: c88d4c7b049e8 ("AppArmor: core policy routines") Reported-by: Qualys Security Advisory Reviewed-by: Ryan Lee Reviewed-by: Cengiz Can Signed-off-by: John Johansen --- security/apparmor/include/policy_ns.h | 2 ++ security/apparmor/policy_ns.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/security/apparmor/include/policy_ns.h b/security/apparmor/include/policy_ns.h index d646070fd966..cc6e84151812 100644 --- a/security/apparmor/include/policy_ns.h +++ b/security/apparmor/include/policy_ns.h @@ -18,6 +18,8 @@ #include "label.h" #include "policy.h" +/* Match max depth of user namespaces */ +#define MAX_NS_DEPTH 32 /* struct aa_ns_acct - accounting of profiles in namespace * @max_size: maximum space allowed for all profiles in namespace diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c index 01b653a3609b..5a907a875d8f 100644 --- a/security/apparmor/policy_ns.c +++ b/security/apparmor/policy_ns.c @@ -223,6 +223,8 @@ static struct aa_ns *__aa_create_ns(struct aa_ns *parent, const char *name, AA_BUG(!name); AA_BUG(!mutex_is_locked(&parent->lock)); + if (parent->level > MAX_NS_DEPTH) + return ERR_PTR(-ENOSPC); ns = alloc_ns(parent->base.hname, name); if (!ns) return ERR_PTR(-ENOMEM); From 8756b68edae37ff546c02091989a4ceab3f20abd Mon Sep 17 00:00:00 2001 From: Massimiliano Pellizzer Date: Thu, 29 Jan 2026 17:08:25 +0100 Subject: [PATCH 259/487] apparmor: fix side-effect bug in match_char() macro usage The match_char() macro evaluates its character parameter multiple times when traversing differential encoding chains. When invoked with *str++, the string pointer advances on each iteration of the inner do-while loop, causing the DFA to check different characters at each iteration and therefore skip input characters. This results in out-of-bounds reads when the pointer advances past the input buffer boundary. [ 94.984676] ================================================================== [ 94.985301] BUG: KASAN: slab-out-of-bounds in aa_dfa_match+0x5ae/0x760 [ 94.985655] Read of size 1 at addr ffff888100342000 by task file/976 [ 94.986319] CPU: 7 UID: 1000 PID: 976 Comm: file Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy) [ 94.986322] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 94.986329] Call Trace: [ 94.986341] [ 94.986347] dump_stack_lvl+0x5e/0x80 [ 94.986374] print_report+0xc8/0x270 [ 94.986384] ? aa_dfa_match+0x5ae/0x760 [ 94.986388] kasan_report+0x118/0x150 [ 94.986401] ? aa_dfa_match+0x5ae/0x760 [ 94.986405] aa_dfa_match+0x5ae/0x760 [ 94.986408] __aa_path_perm+0x131/0x400 [ 94.986418] aa_path_perm+0x219/0x2f0 [ 94.986424] apparmor_file_open+0x345/0x570 [ 94.986431] security_file_open+0x5c/0x140 [ 94.986442] do_dentry_open+0x2f6/0x1120 [ 94.986450] vfs_open+0x38/0x2b0 [ 94.986453] ? may_open+0x1e2/0x2b0 [ 94.986466] path_openat+0x231b/0x2b30 [ 94.986469] ? __x64_sys_openat+0xf8/0x130 [ 94.986477] do_file_open+0x19d/0x360 [ 94.986487] do_sys_openat2+0x98/0x100 [ 94.986491] __x64_sys_openat+0xf8/0x130 [ 94.986499] do_syscall_64+0x8e/0x660 [ 94.986515] ? count_memcg_events+0x15f/0x3c0 [ 94.986526] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986540] ? handle_mm_fault+0x1639/0x1ef0 [ 94.986551] ? vma_start_read+0xf0/0x320 [ 94.986558] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986561] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986563] ? fpregs_assert_state_consistent+0x50/0xe0 [ 94.986572] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986574] ? arch_exit_to_user_mode_prepare+0x9/0xb0 [ 94.986587] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986588] ? irqentry_exit+0x3c/0x590 [ 94.986595] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 94.986597] RIP: 0033:0x7fda4a79c3ea Fix by extracting the character value before invoking match_char, ensuring single evaluation per outer loop. Fixes: 074c1cd798cb ("apparmor: dfa move character match into a macro") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: Massimiliano Pellizzer Signed-off-by: John Johansen --- security/apparmor/match.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/security/apparmor/match.c b/security/apparmor/match.c index 8fa0a1494acd..30c46b119869 100644 --- a/security/apparmor/match.c +++ b/security/apparmor/match.c @@ -463,13 +463,18 @@ aa_state_t aa_dfa_match_len(struct aa_dfa *dfa, aa_state_t start, if (dfa->tables[YYTD_ID_EC]) { /* Equivalence class table defined */ u8 *equiv = EQUIV_TABLE(dfa); - for (; len; len--) - match_char(state, def, base, next, check, - equiv[(u8) *str++]); + for (; len; len--) { + u8 c = equiv[(u8) *str]; + + match_char(state, def, base, next, check, c); + str++; + } } else { /* default is direct to next state */ - for (; len; len--) - match_char(state, def, base, next, check, (u8) *str++); + for (; len; len--) { + match_char(state, def, base, next, check, (u8) *str); + str++; + } } return state; @@ -503,13 +508,18 @@ aa_state_t aa_dfa_match(struct aa_dfa *dfa, aa_state_t start, const char *str) /* Equivalence class table defined */ u8 *equiv = EQUIV_TABLE(dfa); /* default is direct to next state */ - while (*str) - match_char(state, def, base, next, check, - equiv[(u8) *str++]); + while (*str) { + u8 c = equiv[(u8) *str]; + + match_char(state, def, base, next, check, c); + str++; + } } else { /* default is direct to next state */ - while (*str) - match_char(state, def, base, next, check, (u8) *str++); + while (*str) { + match_char(state, def, base, next, check, (u8) *str); + str++; + } } return state; From d352873bbefa7eb39995239d0b44ccdf8aaa79a4 Mon Sep 17 00:00:00 2001 From: Massimiliano Pellizzer Date: Thu, 29 Jan 2026 16:51:11 +0100 Subject: [PATCH 260/487] apparmor: fix missing bounds check on DEFAULT table in verify_dfa() The verify_dfa() function only checks DEFAULT_TABLE bounds when the state is not differentially encoded. When the verification loop traverses the differential encoding chain, it reads k = DEFAULT_TABLE[j] and uses k as an array index without validation. A malformed DFA with DEFAULT_TABLE[j] >= state_count, therefore, causes both out-of-bounds reads and writes. [ 57.179855] ================================================================== [ 57.180549] BUG: KASAN: slab-out-of-bounds in verify_dfa+0x59a/0x660 [ 57.180904] Read of size 4 at addr ffff888100eadec4 by task su/993 [ 57.181554] CPU: 1 UID: 0 PID: 993 Comm: su Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy) [ 57.181558] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 57.181563] Call Trace: [ 57.181572] [ 57.181577] dump_stack_lvl+0x5e/0x80 [ 57.181596] print_report+0xc8/0x270 [ 57.181605] ? verify_dfa+0x59a/0x660 [ 57.181608] kasan_report+0x118/0x150 [ 57.181620] ? verify_dfa+0x59a/0x660 [ 57.181623] verify_dfa+0x59a/0x660 [ 57.181627] aa_dfa_unpack+0x1610/0x1740 [ 57.181629] ? __kmalloc_cache_noprof+0x1d0/0x470 [ 57.181640] unpack_pdb+0x86d/0x46b0 [ 57.181647] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181653] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181656] ? aa_unpack_nameX+0x1a8/0x300 [ 57.181659] aa_unpack+0x20b0/0x4c30 [ 57.181662] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181664] ? stack_depot_save_flags+0x33/0x700 [ 57.181681] ? kasan_save_track+0x4f/0x80 [ 57.181683] ? kasan_save_track+0x3e/0x80 [ 57.181686] ? __kasan_kmalloc+0x93/0xb0 [ 57.181688] ? __kvmalloc_node_noprof+0x44a/0x780 [ 57.181693] ? aa_simple_write_to_buffer+0x54/0x130 [ 57.181697] ? policy_update+0x154/0x330 [ 57.181704] aa_replace_profiles+0x15a/0x1dd0 [ 57.181707] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181710] ? __kvmalloc_node_noprof+0x44a/0x780 [ 57.181712] ? aa_loaddata_alloc+0x77/0x140 [ 57.181715] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181717] ? _copy_from_user+0x2a/0x70 [ 57.181730] policy_update+0x17a/0x330 [ 57.181733] profile_replace+0x153/0x1a0 [ 57.181735] ? rw_verify_area+0x93/0x2d0 [ 57.181740] vfs_write+0x235/0xab0 [ 57.181745] ksys_write+0xb0/0x170 [ 57.181748] do_syscall_64+0x8e/0x660 [ 57.181762] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 57.181765] RIP: 0033:0x7f6192792eb2 Remove the MATCH_FLAG_DIFF_ENCODE condition to validate all DEFAULT_TABLE entries unconditionally. Fixes: 031dcc8f4e84 ("apparmor: dfa add support for state differential encoding") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: Massimiliano Pellizzer Signed-off-by: John Johansen --- security/apparmor/match.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/security/apparmor/match.c b/security/apparmor/match.c index 30c46b119869..2aad2cbed565 100644 --- a/security/apparmor/match.c +++ b/security/apparmor/match.c @@ -160,9 +160,10 @@ static int verify_dfa(struct aa_dfa *dfa) if (state_count == 0) goto out; for (i = 0; i < state_count; i++) { - if (!(BASE_TABLE(dfa)[i] & MATCH_FLAG_DIFF_ENCODE) && - (DEFAULT_TABLE(dfa)[i] >= state_count)) + if (DEFAULT_TABLE(dfa)[i] >= state_count) { + pr_err("AppArmor DFA default state out of bounds"); goto out; + } if (BASE_TABLE(dfa)[i] & MATCH_FLAGS_INVALID) { pr_err("AppArmor DFA state with invalid match flags"); goto out; From 5df0c44e8f5f619d3beb871207aded7c78414502 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Wed, 10 Sep 2025 06:22:17 -0700 Subject: [PATCH 261/487] apparmor: Fix double free of ns_name in aa_replace_profiles() if ns_name is NULL after 1071 error = aa_unpack(udata, &lh, &ns_name); and if ent->ns_name contains an ns_name in 1089 } else if (ent->ns_name) { then ns_name is assigned the ent->ns_name 1095 ns_name = ent->ns_name; however ent->ns_name is freed at 1262 aa_load_ent_free(ent); and then again when freeing ns_name at 1270 kfree(ns_name); Fix this by NULLing out ent->ns_name after it is transferred to ns_name Fixes: 145a0ef21c8e9 ("apparmor: fix blob compression when ns is forced on a policy load ") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: John Johansen --- security/apparmor/policy.c | 1 + 1 file changed, 1 insertion(+) diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 566821852592..4476515d97b1 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -1166,6 +1166,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, goto fail; } ns_name = ent->ns_name; + ent->ns_name = NULL; } else count++; } From 6601e13e82841879406bf9f369032656f441a425 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Fri, 7 Nov 2025 08:36:04 -0800 Subject: [PATCH 262/487] apparmor: fix unprivileged local user can do privileged policy management An unprivileged local user can load, replace, and remove profiles by opening the apparmorfs interfaces, via a confused deputy attack, by passing the opened fd to a privileged process, and getting the privileged process to write to the interface. This does require a privileged target that can be manipulated to do the write for the unprivileged process, but once such access is achieved full policy management is possible and all the possible implications that implies: removing confinement, DoS of system or target applications by denying all execution, by-passing the unprivileged user namespace restriction, to exploiting kernel bugs for a local privilege escalation. The policy management interface can not have its permissions simply changed from 0666 to 0600 because non-root processes need to be able to load policy to different policy namespaces. Instead ensure the task writing the interface has privileges that are a subset of the task that opened the interface. This is already done via policy for confined processes, but unconfined can delegate access to the opened fd, by-passing the usual policy check. Fixes: b7fd2c0340eac ("apparmor: add per policy ns .load, .replace, .remove interface files") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: John Johansen --- security/apparmor/apparmorfs.c | 16 ++++++++------ security/apparmor/include/policy.h | 2 +- security/apparmor/policy.c | 34 +++++++++++++++++++++++++++++- 3 files changed, 43 insertions(+), 9 deletions(-) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 2f84bd23edb6..81e57666a56e 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -417,7 +417,8 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf, } static ssize_t policy_update(u32 mask, const char __user *buf, size_t size, - loff_t *pos, struct aa_ns *ns) + loff_t *pos, struct aa_ns *ns, + const struct cred *ocred) { struct aa_loaddata *data; struct aa_label *label; @@ -428,7 +429,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size, /* high level check about policy management - fine grained in * below after unpack */ - error = aa_may_manage_policy(current_cred(), label, ns, mask); + error = aa_may_manage_policy(current_cred(), label, ns, ocred, mask); if (error) goto end_section; @@ -449,7 +450,8 @@ static ssize_t profile_load(struct file *f, const char __user *buf, size_t size, loff_t *pos) { struct aa_ns *ns = aa_get_ns(f->f_inode->i_private); - int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns); + int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns, + f->f_cred); aa_put_ns(ns); @@ -467,7 +469,7 @@ static ssize_t profile_replace(struct file *f, const char __user *buf, { struct aa_ns *ns = aa_get_ns(f->f_inode->i_private); int error = policy_update(AA_MAY_LOAD_POLICY | AA_MAY_REPLACE_POLICY, - buf, size, pos, ns); + buf, size, pos, ns, f->f_cred); aa_put_ns(ns); return error; @@ -492,7 +494,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf, * below after unpack */ error = aa_may_manage_policy(current_cred(), label, ns, - AA_MAY_REMOVE_POLICY); + f->f_cred, AA_MAY_REMOVE_POLICY); if (error) goto out; @@ -1830,7 +1832,7 @@ static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir, int error; label = begin_current_label_crit_section(); - error = aa_may_manage_policy(current_cred(), label, NULL, + error = aa_may_manage_policy(current_cred(), label, NULL, NULL, AA_MAY_LOAD_POLICY); end_current_label_crit_section(label); if (error) @@ -1880,7 +1882,7 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry) int error; label = begin_current_label_crit_section(); - error = aa_may_manage_policy(current_cred(), label, NULL, + error = aa_may_manage_policy(current_cred(), label, NULL, NULL, AA_MAY_LOAD_POLICY); end_current_label_crit_section(label); if (error) diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index 5115ebae2661..fda9e75b8879 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -443,7 +443,7 @@ bool aa_policy_admin_capable(const struct cred *subj_cred, struct aa_label *label, struct aa_ns *ns); int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label, struct aa_ns *ns, - u32 mask); + const struct cred *ocred, u32 mask); bool aa_current_policy_view_capable(struct aa_ns *ns); bool aa_current_policy_admin_capable(struct aa_ns *ns); diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 4476515d97b1..e2bebf14a4d0 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -942,17 +942,44 @@ bool aa_current_policy_admin_capable(struct aa_ns *ns) return res; } +static bool is_subset_of_obj_privilege(const struct cred *cred, + struct aa_label *label, + const struct cred *ocred) +{ + if (cred == ocred) + return true; + + if (!aa_label_is_subset(label, cred_label(ocred))) + return false; + /* don't allow crossing userns for now */ + if (cred->user_ns != ocred->user_ns) + return false; + if (!cap_issubset(cred->cap_inheritable, ocred->cap_inheritable)) + return false; + if (!cap_issubset(cred->cap_permitted, ocred->cap_permitted)) + return false; + if (!cap_issubset(cred->cap_effective, ocred->cap_effective)) + return false; + if (!cap_issubset(cred->cap_bset, ocred->cap_bset)) + return false; + if (!cap_issubset(cred->cap_ambient, ocred->cap_ambient)) + return false; + return true; +} + + /** * aa_may_manage_policy - can the current task manage policy * @subj_cred: subjects cred * @label: label to check if it can manage policy * @ns: namespace being managed by @label (may be NULL if @label's ns) + * @ocred: object cred if request is coming from an open object * @mask: contains the policy manipulation operation being done * * Returns: 0 if the task is allowed to manipulate policy else error */ int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label, - struct aa_ns *ns, u32 mask) + struct aa_ns *ns, const struct cred *ocred, u32 mask) { const char *op; @@ -968,6 +995,11 @@ int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label, return audit_policy(label, op, NULL, NULL, "policy_locked", -EACCES); + if (ocred && !is_subset_of_obj_privilege(subj_cred, label, ocred)) + return audit_policy(label, op, NULL, NULL, + "not privileged for target profile", + -EACCES); + if (!aa_policy_admin_capable(subj_cred, label, ns)) return audit_policy(label, op, NULL, NULL, "not policy admin", -EACCES); From 39440b137546a3aa383cfdabc605fb73811b6093 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Fri, 17 Oct 2025 01:53:00 -0700 Subject: [PATCH 263/487] apparmor: fix differential encoding verification Differential encoding allows loops to be created if it is abused. To prevent this the unpack should verify that a diff-encode chain terminates. Unfortunately the differential encode verification had two bugs. 1. it conflated states that had gone through check and already been marked, with states that were currently being checked and marked. This means that loops in the current chain being verified are treated as a chain that has already been verified. 2. the order bailout on already checked states compared current chain check iterators j,k instead of using the outer loop iterator i. Meaning a step backwards in states in the current chain verification was being mistaken for moving to an already verified state. Move to a double mark scheme where already verified states get a different mark, than the current chain being kept. This enables us to also drop the backwards verification check that was the cause of the second error as any already verified state is already marked. Fixes: 031dcc8f4e84 ("apparmor: dfa add support for state differential encoding") Reported-by: Qualys Security Advisory Tested-by: Salvatore Bonaccorso Reviewed-by: Georgia Garcia Reviewed-by: Cengiz Can Signed-off-by: John Johansen --- security/apparmor/include/match.h | 1 + security/apparmor/match.c | 23 +++++++++++++++++++---- 2 files changed, 20 insertions(+), 4 deletions(-) diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h index 0dde8eda3d1a..7accb1c39849 100644 --- a/security/apparmor/include/match.h +++ b/security/apparmor/include/match.h @@ -185,6 +185,7 @@ static inline void aa_put_dfa(struct aa_dfa *dfa) #define MATCH_FLAG_DIFF_ENCODE 0x80000000 #define MARK_DIFF_ENCODE 0x40000000 #define MATCH_FLAG_OOB_TRANSITION 0x20000000 +#define MARK_DIFF_ENCODE_VERIFIED 0x10000000 #define MATCH_FLAGS_MASK 0xff000000 #define MATCH_FLAGS_VALID (MATCH_FLAG_DIFF_ENCODE | MATCH_FLAG_OOB_TRANSITION) #define MATCH_FLAGS_INVALID (MATCH_FLAGS_MASK & ~MATCH_FLAGS_VALID) diff --git a/security/apparmor/match.c b/security/apparmor/match.c index 2aad2cbed565..e9fac67e5178 100644 --- a/security/apparmor/match.c +++ b/security/apparmor/match.c @@ -202,16 +202,31 @@ static int verify_dfa(struct aa_dfa *dfa) size_t j, k; for (j = i; - (BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE) && - !(BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE); + ((BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE) && + !(BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE_VERIFIED)); j = k) { + if (BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE) + /* loop in current chain */ + goto out; k = DEFAULT_TABLE(dfa)[j]; if (j == k) + /* self loop */ goto out; - if (k < j) - break; /* already verified */ BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE; } + /* move mark to verified */ + for (j = i; + (BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE); + j = k) { + k = DEFAULT_TABLE(dfa)[j]; + if (j < i) + /* jumps to state/chain that has been + * verified + */ + break; + BASE_TABLE(dfa)[j] &= ~MARK_DIFF_ENCODE; + BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE_VERIFIED; + } } error = 0; From a0b7091c4de45a7325c8780e6934a894f92ac86b Mon Sep 17 00:00:00 2001 From: John Johansen Date: Tue, 24 Feb 2026 10:20:02 -0800 Subject: [PATCH 264/487] apparmor: fix race on rawdata dereference MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a race condition that leads to a use-after-free situation: because the rawdata inodes are not refcounted, an attacker can start open()ing one of the rawdata files, and at the same time remove the last reference to this rawdata (by removing the corresponding profile, for example), which frees its struct aa_loaddata; as a result, when seq_rawdata_open() is reached, i_private is a dangling pointer and freed memory is accessed. The rawdata inodes weren't refcounted to avoid a circular refcount and were supposed to be held by the profile rawdata reference. However during profile removal there is a window where the vfs and profile destruction race, resulting in the use after free. Fix this by moving to a double refcount scheme. Where the profile refcount on rawdata is used to break the circular dependency. Allowing for freeing of the rawdata once all inode references to the rawdata are put. Fixes: 5d5182cae401 ("apparmor: move to per loaddata files, instead of replicating in profiles") Reported-by: Qualys Security Advisory Reviewed-by: Georgia Garcia Reviewed-by: Maxime Bélair Reviewed-by: Cengiz Can Tested-by: Salvatore Bonaccorso Signed-off-by: John Johansen --- security/apparmor/apparmorfs.c | 35 ++++++---- security/apparmor/include/policy_unpack.h | 79 ++++++++++++++--------- security/apparmor/policy.c | 12 ++-- security/apparmor/policy_unpack.c | 46 ++++++++----- 4 files changed, 104 insertions(+), 68 deletions(-) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 81e57666a56e..7a6ca7c5500d 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -79,7 +79,7 @@ static void rawdata_f_data_free(struct rawdata_f_data *private) if (!private) return; - aa_put_loaddata(private->loaddata); + aa_put_i_loaddata(private->loaddata); kvfree(private); } @@ -409,7 +409,8 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf, data->size = copy_size; if (copy_from_user(data->data, userbuf, copy_size)) { - aa_put_loaddata(data); + /* trigger free - don't need to put pcount */ + aa_put_i_loaddata(data); return ERR_PTR(-EFAULT); } @@ -437,7 +438,10 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size, error = PTR_ERR(data); if (!IS_ERR(data)) { error = aa_replace_profiles(ns, label, mask, data); - aa_put_loaddata(data); + /* put pcount, which will put count and free if no + * profiles referencing it. + */ + aa_put_profile_loaddata(data); } end_section: end_current_label_crit_section(label); @@ -508,7 +512,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf, if (!IS_ERR(data)) { data->data[size] = 0; error = aa_remove_profiles(ns, label, data->data, size); - aa_put_loaddata(data); + aa_put_profile_loaddata(data); } out: end_current_label_crit_section(label); @@ -1255,18 +1259,17 @@ static const struct file_operations seq_rawdata_ ##NAME ##_fops = { \ static int seq_rawdata_open(struct inode *inode, struct file *file, int (*show)(struct seq_file *, void *)) { - struct aa_loaddata *data = __aa_get_loaddata(inode->i_private); + struct aa_loaddata *data = aa_get_i_loaddata(inode->i_private); int error; if (!data) - /* lost race this ent is being reaped */ return -ENOENT; error = single_open(file, show, data); if (error) { AA_BUG(file->private_data && ((struct seq_file *)file->private_data)->private); - aa_put_loaddata(data); + aa_put_i_loaddata(data); } return error; @@ -1277,7 +1280,7 @@ static int seq_rawdata_release(struct inode *inode, struct file *file) struct seq_file *seq = (struct seq_file *) file->private_data; if (seq) - aa_put_loaddata(seq->private); + aa_put_i_loaddata(seq->private); return single_release(inode, file); } @@ -1389,9 +1392,8 @@ static int rawdata_open(struct inode *inode, struct file *file) if (!aa_current_policy_view_capable(NULL)) return -EACCES; - loaddata = __aa_get_loaddata(inode->i_private); + loaddata = aa_get_i_loaddata(inode->i_private); if (!loaddata) - /* lost race: this entry is being reaped */ return -ENOENT; private = rawdata_f_data_alloc(loaddata->size); @@ -1416,7 +1418,7 @@ static int rawdata_open(struct inode *inode, struct file *file) return error; fail_private_alloc: - aa_put_loaddata(loaddata); + aa_put_i_loaddata(loaddata); return error; } @@ -1433,9 +1435,9 @@ static void remove_rawdata_dents(struct aa_loaddata *rawdata) for (i = 0; i < AAFS_LOADDATA_NDENTS; i++) { if (!IS_ERR_OR_NULL(rawdata->dents[i])) { - /* no refcounts on i_private */ aafs_remove(rawdata->dents[i]); rawdata->dents[i] = NULL; + aa_put_i_loaddata(rawdata); } } } @@ -1474,18 +1476,21 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata) if (IS_ERR(dir)) /* ->name freed when rawdata freed */ return PTR_ERR(dir); + aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_DIR] = dir; dent = aafs_create_file("abi", S_IFREG | 0444, dir, rawdata, &seq_rawdata_abi_fops); if (IS_ERR(dent)) goto fail; + aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_ABI] = dent; dent = aafs_create_file("revision", S_IFREG | 0444, dir, rawdata, &seq_rawdata_revision_fops); if (IS_ERR(dent)) goto fail; + aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_REVISION] = dent; if (aa_g_hash_policy) { @@ -1493,6 +1498,7 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata) rawdata, &seq_rawdata_hash_fops); if (IS_ERR(dent)) goto fail; + aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_HASH] = dent; } @@ -1501,24 +1507,25 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata) &seq_rawdata_compressed_size_fops); if (IS_ERR(dent)) goto fail; + aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE] = dent; dent = aafs_create_file("raw_data", S_IFREG | 0444, dir, rawdata, &rawdata_fops); if (IS_ERR(dent)) goto fail; + aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_DATA] = dent; d_inode(dent)->i_size = rawdata->size; rawdata->ns = aa_get_ns(ns); list_add(&rawdata->list, &ns->rawdata_list); - /* no refcount on inode rawdata */ return 0; fail: remove_rawdata_dents(rawdata); - + aa_put_i_loaddata(rawdata); return PTR_ERR(dent); } #endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */ diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h index a6f4611ee50c..4f800fbb805a 100644 --- a/security/apparmor/include/policy_unpack.h +++ b/security/apparmor/include/policy_unpack.h @@ -87,17 +87,29 @@ struct aa_ext { u32 version; }; -/* - * struct aa_loaddata - buffer of policy raw_data set +/* struct aa_loaddata - buffer of policy raw_data set + * @count: inode/filesystem refcount - use aa_get_i_loaddata() + * @pcount: profile refcount - use aa_get_profile_loaddata() + * @list: list the loaddata is on + * @work: used to do a delayed cleanup + * @dents: refs to dents created in aafs + * @ns: the namespace this loaddata was loaded into + * @name: + * @size: the size of the data that was loaded + * @compressed_size: the size of the data when it is compressed + * @revision: unique revision count that this data was loaded as + * @abi: the abi number the loaddata uses + * @hash: a hash of the loaddata, used to help dedup data * - * there is no loaddata ref for being on ns list, nor a ref from - * d_inode(@dentry) when grab a ref from these, @ns->lock must be held - * && __aa_get_loaddata() needs to be used, and the return value - * checked, if NULL the loaddata is already being reaped and should be - * considered dead. + * There is no loaddata ref for being on ns->rawdata_list, so + * @ns->lock must be held when walking the list. Dentries and + * inode opens hold refs on @count; profiles hold refs on @pcount. + * When the last @pcount drops, do_ploaddata_rmfs() removes the + * fs entries and drops the associated @count ref. */ struct aa_loaddata { struct kref count; + struct kref pcount; struct list_head list; struct work_struct work; struct dentry *dents[AAFS_LOADDATA_NDENTS]; @@ -118,53 +130,56 @@ struct aa_loaddata { int aa_unpack(struct aa_loaddata *udata, struct list_head *lh, const char **ns); -/** - * __aa_get_loaddata - get a reference count to uncounted data reference - * @data: reference to get a count on - * - * Returns: pointer to reference OR NULL if race is lost and reference is - * being repeated. - * Requires: @data->ns->lock held, and the return code MUST be checked - * - * Use only from inode->i_private and @data->list found references - */ -static inline struct aa_loaddata * -__aa_get_loaddata(struct aa_loaddata *data) -{ - if (data && kref_get_unless_zero(&(data->count))) - return data; - - return NULL; -} - /** * aa_get_loaddata - get a reference count from a counted data reference * @data: reference to get a count on * - * Returns: point to reference + * Returns: pointer to reference * Requires: @data to have a valid reference count on it. It is a bug * if the race to reap can be encountered when it is used. */ static inline struct aa_loaddata * -aa_get_loaddata(struct aa_loaddata *data) +aa_get_i_loaddata(struct aa_loaddata *data) { - struct aa_loaddata *tmp = __aa_get_loaddata(data); - AA_BUG(data && !tmp); + if (data) + kref_get(&(data->count)); + return data; +} - return tmp; + +/** + * aa_get_profile_loaddata - get a profile reference count on loaddata + * @data: reference to get a count on + * + * Returns: pointer to reference + * Requires: @data to have a valid reference count on it. + */ +static inline struct aa_loaddata * +aa_get_profile_loaddata(struct aa_loaddata *data) +{ + if (data) + kref_get(&(data->pcount)); + return data; } void __aa_loaddata_update(struct aa_loaddata *data, long revision); bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r); void aa_loaddata_kref(struct kref *kref); +void aa_ploaddata_kref(struct kref *kref); struct aa_loaddata *aa_loaddata_alloc(size_t size); -static inline void aa_put_loaddata(struct aa_loaddata *data) +static inline void aa_put_i_loaddata(struct aa_loaddata *data) { if (data) kref_put(&data->count, aa_loaddata_kref); } +static inline void aa_put_profile_loaddata(struct aa_loaddata *data) +{ + if (data) + kref_put(&data->pcount, aa_ploaddata_kref); +} + #if IS_ENABLED(CONFIG_KUNIT) bool aa_inbounds(struct aa_ext *e, size_t size); size_t aa_unpack_u16_chunk(struct aa_ext *e, char **chunk); diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index e2bebf14a4d0..b6a5eb4021db 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -350,7 +350,7 @@ void aa_free_profile(struct aa_profile *profile) } kfree_sensitive(profile->hash); - aa_put_loaddata(profile->rawdata); + aa_put_profile_loaddata(profile->rawdata); aa_label_destroy(&profile->label); kfree_sensitive(profile); @@ -1171,7 +1171,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, LIST_HEAD(lh); op = mask & AA_MAY_REPLACE_POLICY ? OP_PROF_REPL : OP_PROF_LOAD; - aa_get_loaddata(udata); + aa_get_profile_loaddata(udata); /* released below */ error = aa_unpack(udata, &lh, &ns_name); if (error) @@ -1223,10 +1223,10 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, if (aa_rawdata_eq(rawdata_ent, udata)) { struct aa_loaddata *tmp; - tmp = __aa_get_loaddata(rawdata_ent); + tmp = aa_get_profile_loaddata(rawdata_ent); /* check we didn't fail the race */ if (tmp) { - aa_put_loaddata(udata); + aa_put_profile_loaddata(udata); udata = tmp; break; } @@ -1239,7 +1239,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, struct aa_profile *p; if (aa_g_export_binary) - ent->new->rawdata = aa_get_loaddata(udata); + ent->new->rawdata = aa_get_profile_loaddata(udata); error = __lookup_replace(ns, ent->new->base.hname, !(mask & AA_MAY_REPLACE_POLICY), &ent->old, &info); @@ -1372,7 +1372,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, out: aa_put_ns(ns); - aa_put_loaddata(udata); + aa_put_profile_loaddata(udata); kfree(ns_name); if (error) diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 5d90ea55de82..69a040194e36 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -109,22 +109,8 @@ bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r) return memcmp(l->data, r->data, r->compressed_size ?: r->size) == 0; } -/* - * need to take the ns mutex lock which is NOT safe most places that - * put_loaddata is called, so we have to delay freeing it - */ -static void do_loaddata_free(struct work_struct *work) +static void do_loaddata_free(struct aa_loaddata *d) { - struct aa_loaddata *d = container_of(work, struct aa_loaddata, work); - struct aa_ns *ns = aa_get_ns(d->ns); - - if (ns) { - mutex_lock_nested(&ns->lock, ns->level); - __aa_fs_remove_rawdata(d); - mutex_unlock(&ns->lock); - aa_put_ns(ns); - } - kfree_sensitive(d->hash); kfree_sensitive(d->name); kvfree(d->data); @@ -135,8 +121,35 @@ void aa_loaddata_kref(struct kref *kref) { struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count); + do_loaddata_free(d); +} + +/* + * need to take the ns mutex lock which is NOT safe most places that + * put_loaddata is called, so we have to delay freeing it + */ +static void do_ploaddata_rmfs(struct work_struct *work) +{ + struct aa_loaddata *d = container_of(work, struct aa_loaddata, work); + struct aa_ns *ns = aa_get_ns(d->ns); + + if (ns) { + mutex_lock_nested(&ns->lock, ns->level); + /* remove fs ref to loaddata */ + __aa_fs_remove_rawdata(d); + mutex_unlock(&ns->lock); + aa_put_ns(ns); + } + /* called by dropping last pcount, so drop its associated icount */ + aa_put_i_loaddata(d); +} + +void aa_ploaddata_kref(struct kref *kref) +{ + struct aa_loaddata *d = container_of(kref, struct aa_loaddata, pcount); + if (d) { - INIT_WORK(&d->work, do_loaddata_free); + INIT_WORK(&d->work, do_ploaddata_rmfs); schedule_work(&d->work); } } @@ -154,6 +167,7 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size) return ERR_PTR(-ENOMEM); } kref_init(&d->count); + kref_init(&d->pcount); INIT_LIST_HEAD(&d->list); return d; From 8e135b8aee5a06c52a4347a5a6d51223c6f36ba3 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Sun, 1 Mar 2026 16:10:51 -0800 Subject: [PATCH 265/487] apparmor: fix race between freeing data and fs accessing it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit AppArmor was putting the reference to i_private data on its end after removing the original entry from the file system. However the inode can aand does live beyond that point and it is possible that some of the fs call back functions will be invoked after the reference has been put, which results in a race between freeing the data and accessing it through the fs. While the rawdata/loaddata is the most likely candidate to fail the race, as it has the fewest references. If properly crafted it might be possible to trigger a race for the other types stored in i_private. Fix this by moving the put of i_private referenced data to the correct place which is during inode eviction. Fixes: c961ee5f21b20 ("apparmor: convert from securityfs to apparmorfs for policy ns files") Reported-by: Qualys Security Advisory Reviewed-by: Georgia Garcia Reviewed-by: Maxime Bélair Reviewed-by: Cengiz Can Signed-off-by: John Johansen --- security/apparmor/apparmorfs.c | 194 +++++++++++++--------- security/apparmor/include/label.h | 16 +- security/apparmor/include/lib.h | 12 ++ security/apparmor/include/policy.h | 8 +- security/apparmor/include/policy_unpack.h | 6 +- security/apparmor/label.c | 12 +- security/apparmor/policy_unpack.c | 6 +- 7 files changed, 153 insertions(+), 101 deletions(-) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 7a6ca7c5500d..242c71b3fb6e 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -32,6 +32,7 @@ #include "include/crypto.h" #include "include/ipc.h" #include "include/label.h" +#include "include/lib.h" #include "include/policy.h" #include "include/policy_ns.h" #include "include/resource.h" @@ -62,6 +63,7 @@ * securityfs and apparmorfs filesystems. */ +#define IREF_POISON 101 /* * support fns @@ -153,6 +155,71 @@ static int aafs_show_path(struct seq_file *seq, struct dentry *dentry) return 0; } +static struct aa_ns *get_ns_common_ref(struct aa_common_ref *ref) +{ + if (ref) { + struct aa_label *reflabel = container_of(ref, struct aa_label, + count); + return aa_get_ns(labels_ns(reflabel)); + } + + return NULL; +} + +static struct aa_proxy *get_proxy_common_ref(struct aa_common_ref *ref) +{ + if (ref) + return aa_get_proxy(container_of(ref, struct aa_proxy, count)); + + return NULL; +} + +static struct aa_loaddata *get_loaddata_common_ref(struct aa_common_ref *ref) +{ + if (ref) + return aa_get_i_loaddata(container_of(ref, struct aa_loaddata, + count)); + return NULL; +} + +static void aa_put_common_ref(struct aa_common_ref *ref) +{ + if (!ref) + return; + + switch (ref->reftype) { + case REF_RAWDATA: + aa_put_i_loaddata(container_of(ref, struct aa_loaddata, + count)); + break; + case REF_PROXY: + aa_put_proxy(container_of(ref, struct aa_proxy, + count)); + break; + case REF_NS: + /* ns count is held on its unconfined label */ + aa_put_ns(labels_ns(container_of(ref, struct aa_label, count))); + break; + default: + AA_BUG(true, "unknown refcount type"); + break; + } +} + +static void aa_get_common_ref(struct aa_common_ref *ref) +{ + kref_get(&ref->count); +} + +static void aafs_evict(struct inode *inode) +{ + struct aa_common_ref *ref = inode->i_private; + + clear_inode(inode); + aa_put_common_ref(ref); + inode->i_private = (void *) IREF_POISON; +} + static void aafs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) @@ -162,6 +229,7 @@ static void aafs_free_inode(struct inode *inode) static const struct super_operations aafs_super_ops = { .statfs = simple_statfs, + .evict_inode = aafs_evict, .free_inode = aafs_free_inode, .show_path = aafs_show_path, }; @@ -262,7 +330,8 @@ static int __aafs_setup_d_inode(struct inode *dir, struct dentry *dentry, * aafs_remove(). Will return ERR_PTR on failure. */ static struct dentry *aafs_create(const char *name, umode_t mode, - struct dentry *parent, void *data, void *link, + struct dentry *parent, + struct aa_common_ref *data, void *link, const struct file_operations *fops, const struct inode_operations *iops) { @@ -299,6 +368,9 @@ static struct dentry *aafs_create(const char *name, umode_t mode, goto fail_dentry; inode_unlock(dir); + if (data) + aa_get_common_ref(data); + return dentry; fail_dentry: @@ -323,7 +395,8 @@ static struct dentry *aafs_create(const char *name, umode_t mode, * see aafs_create */ static struct dentry *aafs_create_file(const char *name, umode_t mode, - struct dentry *parent, void *data, + struct dentry *parent, + struct aa_common_ref *data, const struct file_operations *fops) { return aafs_create(name, mode, parent, data, NULL, fops, NULL); @@ -453,7 +526,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size, static ssize_t profile_load(struct file *f, const char __user *buf, size_t size, loff_t *pos) { - struct aa_ns *ns = aa_get_ns(f->f_inode->i_private); + struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private); int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns, f->f_cred); @@ -471,7 +544,7 @@ static const struct file_operations aa_fs_profile_load = { static ssize_t profile_replace(struct file *f, const char __user *buf, size_t size, loff_t *pos) { - struct aa_ns *ns = aa_get_ns(f->f_inode->i_private); + struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private); int error = policy_update(AA_MAY_LOAD_POLICY | AA_MAY_REPLACE_POLICY, buf, size, pos, ns, f->f_cred); aa_put_ns(ns); @@ -491,7 +564,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf, struct aa_loaddata *data; struct aa_label *label; ssize_t error; - struct aa_ns *ns = aa_get_ns(f->f_inode->i_private); + struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private); label = begin_current_label_crit_section(); /* high level check about policy management - fine grained in @@ -581,7 +654,7 @@ static int ns_revision_open(struct inode *inode, struct file *file) if (!rev) return -ENOMEM; - rev->ns = aa_get_ns(inode->i_private); + rev->ns = get_ns_common_ref(inode->i_private); if (!rev->ns) rev->ns = aa_get_current_ns(); file->private_data = rev; @@ -1067,7 +1140,7 @@ static const struct file_operations seq_profile_ ##NAME ##_fops = { \ static int seq_profile_open(struct inode *inode, struct file *file, int (*show)(struct seq_file *, void *)) { - struct aa_proxy *proxy = aa_get_proxy(inode->i_private); + struct aa_proxy *proxy = get_proxy_common_ref(inode->i_private); int error = single_open(file, show, proxy); if (error) { @@ -1259,7 +1332,7 @@ static const struct file_operations seq_rawdata_ ##NAME ##_fops = { \ static int seq_rawdata_open(struct inode *inode, struct file *file, int (*show)(struct seq_file *, void *)) { - struct aa_loaddata *data = aa_get_i_loaddata(inode->i_private); + struct aa_loaddata *data = get_loaddata_common_ref(inode->i_private); int error; if (!data) @@ -1392,7 +1465,7 @@ static int rawdata_open(struct inode *inode, struct file *file) if (!aa_current_policy_view_capable(NULL)) return -EACCES; - loaddata = aa_get_i_loaddata(inode->i_private); + loaddata = get_loaddata_common_ref(inode->i_private); if (!loaddata) return -ENOENT; @@ -1437,7 +1510,6 @@ static void remove_rawdata_dents(struct aa_loaddata *rawdata) if (!IS_ERR_OR_NULL(rawdata->dents[i])) { aafs_remove(rawdata->dents[i]); rawdata->dents[i] = NULL; - aa_put_i_loaddata(rawdata); } } } @@ -1476,45 +1548,41 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata) if (IS_ERR(dir)) /* ->name freed when rawdata freed */ return PTR_ERR(dir); - aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_DIR] = dir; - dent = aafs_create_file("abi", S_IFREG | 0444, dir, rawdata, + dent = aafs_create_file("abi", S_IFREG | 0444, dir, &rawdata->count, &seq_rawdata_abi_fops); if (IS_ERR(dent)) goto fail; - aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_ABI] = dent; - dent = aafs_create_file("revision", S_IFREG | 0444, dir, rawdata, - &seq_rawdata_revision_fops); + dent = aafs_create_file("revision", S_IFREG | 0444, dir, + &rawdata->count, + &seq_rawdata_revision_fops); if (IS_ERR(dent)) goto fail; - aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_REVISION] = dent; if (aa_g_hash_policy) { dent = aafs_create_file("sha256", S_IFREG | 0444, dir, - rawdata, &seq_rawdata_hash_fops); + &rawdata->count, + &seq_rawdata_hash_fops); if (IS_ERR(dent)) goto fail; - aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_HASH] = dent; } dent = aafs_create_file("compressed_size", S_IFREG | 0444, dir, - rawdata, + &rawdata->count, &seq_rawdata_compressed_size_fops); if (IS_ERR(dent)) goto fail; - aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE] = dent; - dent = aafs_create_file("raw_data", S_IFREG | 0444, - dir, rawdata, &rawdata_fops); + dent = aafs_create_file("raw_data", S_IFREG | 0444, dir, + &rawdata->count, &rawdata_fops); if (IS_ERR(dent)) goto fail; - aa_get_i_loaddata(rawdata); rawdata->dents[AAFS_LOADDATA_DATA] = dent; d_inode(dent)->i_size = rawdata->size; @@ -1525,7 +1593,6 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata) fail: remove_rawdata_dents(rawdata); - aa_put_i_loaddata(rawdata); return PTR_ERR(dent); } #endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */ @@ -1549,13 +1616,10 @@ void __aafs_profile_rmdir(struct aa_profile *profile) __aafs_profile_rmdir(child); for (i = AAFS_PROF_SIZEOF - 1; i >= 0; --i) { - struct aa_proxy *proxy; if (!profile->dents[i]) continue; - proxy = d_inode(profile->dents[i])->i_private; aafs_remove(profile->dents[i]); - aa_put_proxy(proxy); profile->dents[i] = NULL; } } @@ -1589,14 +1653,7 @@ static struct dentry *create_profile_file(struct dentry *dir, const char *name, struct aa_profile *profile, const struct file_operations *fops) { - struct aa_proxy *proxy = aa_get_proxy(profile->label.proxy); - struct dentry *dent; - - dent = aafs_create_file(name, S_IFREG | 0444, dir, proxy, fops); - if (IS_ERR(dent)) - aa_put_proxy(proxy); - - return dent; + return aafs_create_file(name, S_IFREG | 0444, dir, &profile->label.proxy->count, fops); } #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY @@ -1646,7 +1703,8 @@ static const char *rawdata_get_link_base(struct dentry *dentry, struct delayed_call *done, const char *name) { - struct aa_proxy *proxy = inode->i_private; + struct aa_common_ref *ref = inode->i_private; + struct aa_proxy *proxy = container_of(ref, struct aa_proxy, count); struct aa_label *label; struct aa_profile *profile; char *target; @@ -1788,27 +1846,24 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent) if (profile->rawdata) { if (aa_g_hash_policy) { dent = aafs_create("raw_sha256", S_IFLNK | 0444, dir, - profile->label.proxy, NULL, NULL, - &rawdata_link_sha256_iops); + &profile->label.proxy->count, NULL, + NULL, &rawdata_link_sha256_iops); if (IS_ERR(dent)) goto fail; - aa_get_proxy(profile->label.proxy); profile->dents[AAFS_PROF_RAW_HASH] = dent; } dent = aafs_create("raw_abi", S_IFLNK | 0444, dir, - profile->label.proxy, NULL, NULL, + &profile->label.proxy->count, NULL, NULL, &rawdata_link_abi_iops); if (IS_ERR(dent)) goto fail; - aa_get_proxy(profile->label.proxy); profile->dents[AAFS_PROF_RAW_ABI] = dent; dent = aafs_create("raw_data", S_IFLNK | 0444, dir, - profile->label.proxy, NULL, NULL, + &profile->label.proxy->count, NULL, NULL, &rawdata_link_data_iops); if (IS_ERR(dent)) goto fail; - aa_get_proxy(profile->label.proxy); profile->dents[AAFS_PROF_RAW_DATA] = dent; } #endif /*CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */ @@ -1845,7 +1900,7 @@ static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir, if (error) return ERR_PTR(error); - parent = aa_get_ns(dir->i_private); + parent = get_ns_common_ref(dir->i_private); AA_BUG(d_inode(ns_subns_dir(parent)) != dir); /* we have to unlock and then relock to get locking order right @@ -1895,7 +1950,7 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry) if (error) return error; - parent = aa_get_ns(dir->i_private); + parent = get_ns_common_ref(dir->i_private); /* rmdir calls the generic securityfs functions to remove files * from the apparmor dir. It is up to the apparmor ns locking * to avoid races. @@ -1965,27 +2020,6 @@ void __aafs_ns_rmdir(struct aa_ns *ns) __aa_fs_list_remove_rawdata(ns); - if (ns_subns_dir(ns)) { - sub = d_inode(ns_subns_dir(ns))->i_private; - aa_put_ns(sub); - } - if (ns_subload(ns)) { - sub = d_inode(ns_subload(ns))->i_private; - aa_put_ns(sub); - } - if (ns_subreplace(ns)) { - sub = d_inode(ns_subreplace(ns))->i_private; - aa_put_ns(sub); - } - if (ns_subremove(ns)) { - sub = d_inode(ns_subremove(ns))->i_private; - aa_put_ns(sub); - } - if (ns_subrevision(ns)) { - sub = d_inode(ns_subrevision(ns))->i_private; - aa_put_ns(sub); - } - for (i = AAFS_NS_SIZEOF - 1; i >= 0; --i) { aafs_remove(ns->dents[i]); ns->dents[i] = NULL; @@ -2010,40 +2044,40 @@ static int __aafs_ns_mkdir_entries(struct aa_ns *ns, struct dentry *dir) return PTR_ERR(dent); ns_subdata_dir(ns) = dent; - dent = aafs_create_file("revision", 0444, dir, ns, + dent = aafs_create_file("revision", 0444, dir, + &ns->unconfined->label.count, &aa_fs_ns_revision_fops); if (IS_ERR(dent)) return PTR_ERR(dent); - aa_get_ns(ns); ns_subrevision(ns) = dent; - dent = aafs_create_file(".load", 0640, dir, ns, - &aa_fs_profile_load); + dent = aafs_create_file(".load", 0640, dir, + &ns->unconfined->label.count, + &aa_fs_profile_load); if (IS_ERR(dent)) return PTR_ERR(dent); - aa_get_ns(ns); ns_subload(ns) = dent; - dent = aafs_create_file(".replace", 0640, dir, ns, - &aa_fs_profile_replace); + dent = aafs_create_file(".replace", 0640, dir, + &ns->unconfined->label.count, + &aa_fs_profile_replace); if (IS_ERR(dent)) return PTR_ERR(dent); - aa_get_ns(ns); ns_subreplace(ns) = dent; - dent = aafs_create_file(".remove", 0640, dir, ns, - &aa_fs_profile_remove); + dent = aafs_create_file(".remove", 0640, dir, + &ns->unconfined->label.count, + &aa_fs_profile_remove); if (IS_ERR(dent)) return PTR_ERR(dent); - aa_get_ns(ns); ns_subremove(ns) = dent; /* use create_dentry so we can supply private data */ - dent = aafs_create("namespaces", S_IFDIR | 0755, dir, ns, NULL, NULL, - &ns_dir_inode_operations); + dent = aafs_create("namespaces", S_IFDIR | 0755, dir, + &ns->unconfined->label.count, + NULL, NULL, &ns_dir_inode_operations); if (IS_ERR(dent)) return PTR_ERR(dent); - aa_get_ns(ns); ns_subns_dir(ns) = dent; return 0; diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h index c0812dbc1b5b..335f21930702 100644 --- a/security/apparmor/include/label.h +++ b/security/apparmor/include/label.h @@ -102,7 +102,7 @@ enum label_flags { struct aa_label; struct aa_proxy { - struct kref count; + struct aa_common_ref count; struct aa_label __rcu *label; }; @@ -125,7 +125,7 @@ struct label_it { * vec: vector of profiles comprising the compound label */ struct aa_label { - struct kref count; + struct aa_common_ref count; struct rb_node node; struct rcu_head rcu; struct aa_proxy *proxy; @@ -357,7 +357,7 @@ int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules, */ static inline struct aa_label *__aa_get_label(struct aa_label *l) { - if (l && kref_get_unless_zero(&l->count)) + if (l && kref_get_unless_zero(&l->count.count)) return l; return NULL; @@ -366,7 +366,7 @@ static inline struct aa_label *__aa_get_label(struct aa_label *l) static inline struct aa_label *aa_get_label(struct aa_label *l) { if (l) - kref_get(&(l->count)); + kref_get(&(l->count.count)); return l; } @@ -386,7 +386,7 @@ static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l) rcu_read_lock(); do { c = rcu_dereference(*l); - } while (c && !kref_get_unless_zero(&c->count)); + } while (c && !kref_get_unless_zero(&c->count.count)); rcu_read_unlock(); return c; @@ -426,7 +426,7 @@ static inline struct aa_label *aa_get_newest_label(struct aa_label *l) static inline void aa_put_label(struct aa_label *l) { if (l) - kref_put(&l->count, aa_label_kref); + kref_put(&l->count.count, aa_label_kref); } /* wrapper fn to indicate semantics of the check */ @@ -443,7 +443,7 @@ void aa_proxy_kref(struct kref *kref); static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy) { if (proxy) - kref_get(&(proxy->count)); + kref_get(&(proxy->count.count)); return proxy; } @@ -451,7 +451,7 @@ static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy) static inline void aa_put_proxy(struct aa_proxy *proxy) { if (proxy) - kref_put(&proxy->count, aa_proxy_kref); + kref_put(&proxy->count.count, aa_proxy_kref); } void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new); diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h index 1c5d1f60f6a7..8c6ce8484552 100644 --- a/security/apparmor/include/lib.h +++ b/security/apparmor/include/lib.h @@ -102,6 +102,18 @@ void aa_info_message(const char *str); /* Security blob offsets */ extern struct lsm_blob_sizes apparmor_blob_sizes; +enum reftype { + REF_NS, + REF_PROXY, + REF_RAWDATA, +}; + +/* common reference count used by data the shows up in aafs */ +struct aa_common_ref { + struct kref count; + enum reftype reftype; +}; + /** * aa_strneq - compare null terminated @str to a non null terminated substring * @str: a null terminated string diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index fda9e75b8879..3895f8774a3f 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -379,7 +379,7 @@ static inline bool profile_mediates_safe(struct aa_profile *profile, static inline struct aa_profile *aa_get_profile(struct aa_profile *p) { if (p) - kref_get(&(p->label.count)); + kref_get(&(p->label.count.count)); return p; } @@ -393,7 +393,7 @@ static inline struct aa_profile *aa_get_profile(struct aa_profile *p) */ static inline struct aa_profile *aa_get_profile_not0(struct aa_profile *p) { - if (p && kref_get_unless_zero(&p->label.count)) + if (p && kref_get_unless_zero(&p->label.count.count)) return p; return NULL; @@ -413,7 +413,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p) rcu_read_lock(); do { c = rcu_dereference(*p); - } while (c && !kref_get_unless_zero(&c->label.count)); + } while (c && !kref_get_unless_zero(&c->label.count.count)); rcu_read_unlock(); return c; @@ -426,7 +426,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p) static inline void aa_put_profile(struct aa_profile *p) { if (p) - kref_put(&p->label.count, aa_label_kref); + kref_put(&p->label.count.count, aa_label_kref); } static inline int AUDIT_MODE(struct aa_profile *profile) diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h index 4f800fbb805a..e5a95dc4da1f 100644 --- a/security/apparmor/include/policy_unpack.h +++ b/security/apparmor/include/policy_unpack.h @@ -108,7 +108,7 @@ struct aa_ext { * fs entries and drops the associated @count ref. */ struct aa_loaddata { - struct kref count; + struct aa_common_ref count; struct kref pcount; struct list_head list; struct work_struct work; @@ -143,7 +143,7 @@ aa_get_i_loaddata(struct aa_loaddata *data) { if (data) - kref_get(&(data->count)); + kref_get(&(data->count.count)); return data; } @@ -171,7 +171,7 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size); static inline void aa_put_i_loaddata(struct aa_loaddata *data) { if (data) - kref_put(&data->count, aa_loaddata_kref); + kref_put(&data->count.count, aa_loaddata_kref); } static inline void aa_put_profile_loaddata(struct aa_loaddata *data) diff --git a/security/apparmor/label.c b/security/apparmor/label.c index e478283bc514..3a721fdf1833 100644 --- a/security/apparmor/label.c +++ b/security/apparmor/label.c @@ -52,7 +52,8 @@ static void free_proxy(struct aa_proxy *proxy) void aa_proxy_kref(struct kref *kref) { - struct aa_proxy *proxy = container_of(kref, struct aa_proxy, count); + struct aa_proxy *proxy = container_of(kref, struct aa_proxy, + count.count); free_proxy(proxy); } @@ -63,7 +64,8 @@ struct aa_proxy *aa_alloc_proxy(struct aa_label *label, gfp_t gfp) new = kzalloc_obj(struct aa_proxy, gfp); if (new) { - kref_init(&new->count); + kref_init(&new->count.count); + new->count.reftype = REF_PROXY; rcu_assign_pointer(new->label, aa_get_label(label)); } return new; @@ -375,7 +377,8 @@ static void label_free_rcu(struct rcu_head *head) void aa_label_kref(struct kref *kref) { - struct aa_label *label = container_of(kref, struct aa_label, count); + struct aa_label *label = container_of(kref, struct aa_label, + count.count); struct aa_ns *ns = labels_ns(label); if (!ns) { @@ -412,7 +415,8 @@ bool aa_label_init(struct aa_label *label, int size, gfp_t gfp) label->size = size; /* doesn't include null */ label->vec[size] = NULL; /* null terminate */ - kref_init(&label->count); + kref_init(&label->count.count); + label->count.reftype = REF_NS; /* for aafs purposes */ RB_CLEAR_NODE(&label->node); return true; diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 69a040194e36..076d3ff14da6 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -119,7 +119,8 @@ static void do_loaddata_free(struct aa_loaddata *d) void aa_loaddata_kref(struct kref *kref) { - struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count); + struct aa_loaddata *d = container_of(kref, struct aa_loaddata, + count.count); do_loaddata_free(d); } @@ -166,7 +167,8 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size) kfree(d); return ERR_PTR(-ENOMEM); } - kref_init(&d->count); + kref_init(&d->count.count); + d->count.reftype = REF_RAWDATA; kref_init(&d->pcount); INIT_LIST_HEAD(&d->list); From 4185b95f8a42d92d68c49289b4644546b51e252b Mon Sep 17 00:00:00 2001 From: Sen Wang Date: Sun, 8 Mar 2026 23:21:09 -0500 Subject: [PATCH 266/487] ASoC: simple-card-utils: fix graph_util_is_ports0() for DT overlays graph_util_is_ports0() identifies DPCM front-end (ports@0) vs back-end (ports@1) by calling of_get_child_by_name() to find the first "ports" child and comparing pointers. This relies on child iteration order matching DTS source order. When the DPCM topology comes from a DT overlay, __of_attach_node() inserts new children at the head of the sibling list, reversing the order. of_get_child_by_name() then returns ports@1 instead of ports@0, causing all front-end links to be classified as back-ends. The card registers with no PCM devices. Fix this by matching the unit address directly from the node name instead of relying on sibling order. Fixes: 92939252458f ("ASoC: simple-card-utils: add asoc_graph_is_ports0()") Signed-off-by: Sen Wang Acked-by: Kuninori Morimoto Link: https://patch.msgid.link/20260309042109.2576612-1-sen@ti.com Signed-off-by: Mark Brown --- sound/soc/generic/simple-card-utils.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index bdc02e85b089..9e5be0eaa77f 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1038,11 +1038,15 @@ int graph_util_is_ports0(struct device_node *np) else port = np; - struct device_node *ports __free(device_node) = of_get_parent(port); - struct device_node *top __free(device_node) = of_get_parent(ports); - struct device_node *ports0 __free(device_node) = of_get_child_by_name(top, "ports"); + struct device_node *ports __free(device_node) = of_get_parent(port); + const char *at = strchr(kbasename(ports->full_name), '@'); - return ports0 == ports; + /* + * Since child iteration order may differ + * between a base DT and DT overlays, + * string match "ports" or "ports@0" in the node name instead. + */ + return !at || !strcmp(at, "@0"); } EXPORT_SYMBOL_GPL(graph_util_is_ports0); From 87d126852158467ab87d5cbc36ccfd3f15464a6c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Fri, 6 Mar 2026 13:29:55 +0100 Subject: [PATCH 267/487] net: sfp: improve Huawei MA5671a fixup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the current sfp_fixup_ignore_tx_fault() fixup we ignore the TX_FAULT signal, but we also need to apply sfp_fixup_ignore_los() in order to be able to communicate with the module even if the fiber isn't connected for configuration purposes. This is needed for all the MA5671a firmwares, excluding the FS modded firmware. Fixes: 2069624dac19 ("net: sfp: Add tx-fault workaround for Huawei MA5671A SFP ONT") Signed-off-by: Álvaro Fernández Rojas Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260306125139.213637-1-noltari@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/sfp.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index f4bf53da3d4f..5db841377199 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -367,6 +367,12 @@ static void sfp_fixup_ignore_tx_fault(struct sfp *sfp) sfp->state_ignore_mask |= SFP_F_TX_FAULT; } +static void sfp_fixup_ignore_tx_fault_and_los(struct sfp *sfp) +{ + sfp_fixup_ignore_tx_fault(sfp); + sfp_fixup_ignore_los(sfp); +} + static void sfp_fixup_ignore_hw(struct sfp *sfp, unsigned int mask) { sfp->state_hw_mask &= ~mask; @@ -530,7 +536,7 @@ static const struct sfp_quirk sfp_quirks[] = { // Huawei MA5671A can operate at 2500base-X, but report 1.2GBd NRZ in // their EEPROM SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex, - sfp_fixup_ignore_tx_fault), + sfp_fixup_ignore_tx_fault_and_los), // Lantech 8330-262D-E and 8330-265D can operate at 2500base-X, but // incorrectly report 2500MBd NRZ in their EEPROM. From 288598d80a068a0e9281de35bcb4ce495f189e2a Mon Sep 17 00:00:00 2001 From: Shuangpeng Bai Date: Thu, 5 Mar 2026 22:40:06 -0500 Subject: [PATCH 268/487] serial: caif: hold tty->link reference in ldisc_open and ser_release A reproducer triggers a KASAN slab-use-after-free in pty_write_room() when caif_serial's TX path calls tty_write_room(). The faulting access is on tty->link->port. Hold an extra kref on tty->link for the lifetime of the caif_serial line discipline: get it in ldisc_open() and drop it in ser_release(), and also drop it on the ldisc_open() error path. With this change applied, the reproducer no longer triggers the UAF in my testing. Link: https://gist.github.com/shuangpengbai/c898debad6bdf170a84be7e6b3d8707f Link: https://lore.kernel.org/netdev/20260301220525.1546355-1-shuangpeng.kernel@gmail.com Fixes: e31d5a05948e ("caif: tty's are kref objects so take a reference") Signed-off-by: Shuangpeng Bai Reviewed-by: Jiayuan Chen Link: https://patch.msgid.link/20260306034006.3395740-1-shuangpeng.kernel@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/caif/caif_serial.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index b90890030751..1873d8287bb9 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -297,6 +297,7 @@ static void ser_release(struct work_struct *work) dev_close(ser->dev); unregister_netdevice(ser->dev); debugfs_deinit(ser); + tty_kref_put(tty->link); tty_kref_put(tty); } rtnl_unlock(); @@ -331,6 +332,7 @@ static int ldisc_open(struct tty_struct *tty) ser = netdev_priv(dev); ser->tty = tty_kref_get(tty); + tty_kref_get(tty->link); ser->dev = dev; debugfs_init(ser, tty); tty->receive_room = 4096; @@ -339,6 +341,7 @@ static int ldisc_open(struct tty_struct *tty) rtnl_lock(); result = register_netdevice(dev); if (result) { + tty_kref_put(tty->link); tty_kref_put(tty); rtnl_unlock(); free_netdev(dev); From b2662e7593e94ae09b1cf7ee5f09160a3612bcb2 Mon Sep 17 00:00:00 2001 From: Mehul Rao Date: Fri, 6 Mar 2026 18:38:20 -0500 Subject: [PATCH 269/487] net: nexthop: fix percpu use-after-free in remove_nh_grp_entry When removing a nexthop from a group, remove_nh_grp_entry() publishes the new group via rcu_assign_pointer() then immediately frees the removed entry's percpu stats with free_percpu(). However, the synchronize_net() grace period in the caller remove_nexthop_from_groups() runs after the free. RCU readers that entered before the publish still see the old group and can dereference the freed stats via nh_grp_entry_stats_inc() -> get_cpu_ptr(nhge->stats), causing a use-after-free on percpu memory. Fix by deferring the free_percpu() until after synchronize_net() in the caller. Removed entries are chained via nh_list onto a local deferred free list. After the grace period completes and all RCU readers have finished, the percpu stats are safely freed. Fixes: f4676ea74b85 ("net: nexthop: Add nexthop group entry stats") Cc: stable@vger.kernel.org Signed-off-by: Mehul Rao Reviewed-by: Eric Dumazet Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260306233821.196789-1-mehulrao@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 1aa2b05ee8de..c942f1282236 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2002,7 +2002,8 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg) } static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, - struct nl_info *nlinfo) + struct nl_info *nlinfo, + struct list_head *deferred_free) { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; @@ -2062,8 +2063,8 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); - free_percpu(nhge->stats); nexthop_put(nhge->nh); + list_add(&nhge->nh_list, deferred_free); /* Removal of a NH from a resilient group is notified through * bucket notifications. @@ -2083,6 +2084,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { struct nh_grp_entry *nhge, *tmp; + LIST_HEAD(deferred_free); /* If there is nothing to do, let's avoid the costly call to * synchronize_net() @@ -2091,10 +2093,16 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, return; list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) - remove_nh_grp_entry(net, nhge, nlinfo); + remove_nh_grp_entry(net, nhge, nlinfo, &deferred_free); /* make sure all see the newly published array before releasing rtnl */ synchronize_net(); + + /* Now safe to free percpu stats — all RCU readers have finished */ + list_for_each_entry_safe(nhge, tmp, &deferred_free, nh_list) { + list_del(&nhge->nh_list); + free_percpu(nhge->stats); + } } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) From 7a85d370bbd0d55791ec57ea8ba13032410e8b9d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Mar 2026 12:06:07 +0000 Subject: [PATCH 270/487] MAINTAINERS: include/net/tc_wrapper.h belongs to TC subsystem include/net/tc_wrapper.h changes should be reviewed by TC maintainers. Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260307120607.3504191-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 4f8e772808c7..07474a56821a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -25750,6 +25750,7 @@ F: include/net/pkt_cls.h F: include/net/pkt_sched.h F: include/net/sch_priv.h F: include/net/tc_act/ +F: include/net/tc_wrapper.h F: include/uapi/linux/pkt_cls.h F: include/uapi/linux/pkt_sched.h F: include/uapi/linux/tc_act/ From e4f774a0cc955ce762aec91c66915a6e15087ab7 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 5 Mar 2026 15:34:26 +0100 Subject: [PATCH 271/487] net: usb: lan78xx: fix silent drop of packets with checksum errors Do not drop packets with checksum errors at the USB driver level; pass them to the network stack. Previously, the driver dropped all packets where the 'Receive Error Detected' (RED) bit was set, regardless of the specific error type. This caused packets with only IP or TCP/UDP checksum errors to be dropped before reaching the kernel, preventing the network stack from accounting for them or performing software fallback. Add a mask for hard hardware errors to safely drop genuinely corrupt frames, while allowing checksum-errored frames to pass with their ip_summed field explicitly set to CHECKSUM_NONE. Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Cc: stable@vger.kernel.org Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20260305143429.530909-2-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/usb/lan78xx.c | 4 +++- drivers/net/usb/lan78xx.h | 3 +++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index a0021df12fde..1c8f69190378 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3829,6 +3829,7 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev, */ if (!(dev->net->features & NETIF_F_RXCSUM) || unlikely(rx_cmd_a & RX_CMD_A_ICSM_) || + unlikely(rx_cmd_a & RX_CMD_A_CSE_MASK_) || ((rx_cmd_a & RX_CMD_A_FVTG_) && !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) { skb->ip_summed = CHECKSUM_NONE; @@ -3901,7 +3902,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb, return 0; } - if (unlikely(rx_cmd_a & RX_CMD_A_RED_)) { + if (unlikely(rx_cmd_a & RX_CMD_A_RED_) && + (rx_cmd_a & RX_CMD_A_RX_HARD_ERRS_MASK_)) { netif_dbg(dev, rx_err, dev->net, "Error rx_cmd_a=0x%08x", rx_cmd_a); } else { diff --git a/drivers/net/usb/lan78xx.h b/drivers/net/usb/lan78xx.h index 968e5e5faee0..17a934acff3d 100644 --- a/drivers/net/usb/lan78xx.h +++ b/drivers/net/usb/lan78xx.h @@ -74,6 +74,9 @@ #define RX_CMD_A_ICSM_ (0x00004000) #define RX_CMD_A_LEN_MASK_ (0x00003FFF) +#define RX_CMD_A_RX_HARD_ERRS_MASK_ \ + (RX_CMD_A_RX_ERRS_MASK_ & ~RX_CMD_A_CSE_MASK_) + /* Rx Command B */ #define RX_CMD_B_CSUM_SHIFT_ (16) #define RX_CMD_B_CSUM_MASK_ (0xFFFF0000) From 50988747c30df47b73b787f234f746027cb7ec6c Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 5 Mar 2026 15:34:27 +0100 Subject: [PATCH 272/487] net: usb: lan78xx: fix TX byte statistics for small packets Account for hardware auto-padding in TX byte counters to reflect actual wire traffic. The LAN7850 hardware automatically pads undersized frames to the minimum Ethernet frame length (ETH_ZLEN, 60 bytes). However, the driver tracks the network statistics based on the unpadded socket buffer length. This results in the tx_bytes counter under-reporting the actual physical bytes placed on the Ethernet wire for small packets (like short ARP or ICMP requests). Use max_t() to ensure the transmission statistics accurately account for the hardware-generated padding. Fixes: d383216a7efe ("lan78xx: Introduce Tx URB processing improvements") Cc: stable@vger.kernel.org Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20260305143429.530909-3-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/usb/lan78xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 1c8f69190378..507dbcf3b7b0 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -4178,7 +4178,7 @@ static struct skb_data *lan78xx_tx_buf_fill(struct lan78xx_net *dev, } tx_data += len; - entry->length += len; + entry->length += max_t(unsigned int, len, ETH_ZLEN); entry->num_of_packet += skb_shinfo(skb)->gso_segs ?: 1; dev_kfree_skb_any(skb); From d9cc0e440f0664f6f3e2c26e39ab9dd5f3badba7 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 5 Mar 2026 15:34:28 +0100 Subject: [PATCH 273/487] net: usb: lan78xx: skip LTM configuration for LAN7850 Do not configure Latency Tolerance Messaging (LTM) on USB 2.0 hardware. The LAN7850 is a High-Speed (USB 2.0) only device and does not support SuperSpeed features like LTM. Currently, the driver unconditionally attempts to configure LTM registers during initialization. On the LAN7850, these registers do not exist, resulting in writes to invalid or undocumented memory space. This issue was identified during a port to the regmap API with strict register validation enabled. While no functional issues or crashes have been observed from these invalid writes, bypassing LTM initialization on the LAN7850 ensures the driver strictly adheres to the hardware's valid register map. Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Cc: stable@vger.kernel.org Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20260305143429.530909-4-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/usb/lan78xx.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 507dbcf3b7b0..f8558b87eaec 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3119,6 +3119,10 @@ static int lan78xx_init_ltm(struct lan78xx_net *dev) int ret; u32 buf; + /* LAN7850 is USB 2.0 and does not support LTM */ + if (dev->chipid == ID_REV_CHIP_ID_7850_) + return 0; + ret = lan78xx_read_reg(dev, USB_CFG1, &buf); if (ret < 0) goto init_ltm_failed; From 312c816c6bc30342bc30dca0d6db617ab4d3ae4e Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 5 Mar 2026 15:34:29 +0100 Subject: [PATCH 274/487] net: usb: lan78xx: fix WARN in __netif_napi_del_locked on disconnect Remove redundant netif_napi_del() call from disconnect path. A WARN may be triggered in __netif_napi_del_locked() during USB device disconnect: WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350 This happens because netif_napi_del() is called in the disconnect path while NAPI is still enabled. However, it is not necessary to call netif_napi_del() explicitly, since unregister_netdev() will handle NAPI teardown automatically and safely. Removing the redundant call avoids triggering the warning. Full trace: lan78xx 1-1:1.0 enu1: Failed to read register index 0x000000c4. ret = -ENODEV lan78xx 1-1:1.0 enu1: Failed to set MAC down with error -ENODEV lan78xx 1-1:1.0 enu1: Link is Down lan78xx 1-1:1.0 enu1: Failed to read register index 0x00000120. ret = -ENODEV ------------[ cut here ]------------ WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350 Modules linked in: flexcan can_dev fuse CPU: 0 UID: 0 PID: 11 Comm: kworker/0:1 Not tainted 6.16.0-rc2-00624-ge926949dab03 #9 PREEMPT Hardware name: SKOV IMX8MP CPU revC - bd500 (DT) Workqueue: usb_hub_wq hub_event pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __netif_napi_del_locked+0x2b4/0x350 lr : __netif_napi_del_locked+0x7c/0x350 sp : ffffffc085b673c0 x29: ffffffc085b673c0 x28: ffffff800b7f2000 x27: ffffff800b7f20d8 x26: ffffff80110bcf58 x25: ffffff80110bd978 x24: 1ffffff0022179eb x23: ffffff80110bc000 x22: ffffff800b7f5000 x21: ffffff80110bc000 x20: ffffff80110bcf38 x19: ffffff80110bcf28 x18: dfffffc000000000 x17: ffffffc081578940 x16: ffffffc08284cee0 x15: 0000000000000028 x14: 0000000000000006 x13: 0000000000040000 x12: ffffffb0022179e8 x11: 1ffffff0022179e7 x10: ffffffb0022179e7 x9 : dfffffc000000000 x8 : 0000004ffdde8619 x7 : ffffff80110bcf3f x6 : 0000000000000001 x5 : ffffff80110bcf38 x4 : ffffff80110bcf38 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 1ffffff0022179e7 x0 : 0000000000000000 Call trace: __netif_napi_del_locked+0x2b4/0x350 (P) lan78xx_disconnect+0xf4/0x360 usb_unbind_interface+0x158/0x718 device_remove+0x100/0x150 device_release_driver_internal+0x308/0x478 device_release_driver+0x1c/0x30 bus_remove_device+0x1a8/0x368 device_del+0x2e0/0x7b0 usb_disable_device+0x244/0x540 usb_disconnect+0x220/0x758 hub_event+0x105c/0x35e0 process_one_work+0x760/0x17b0 worker_thread+0x768/0xce8 kthread+0x3bc/0x690 ret_from_fork+0x10/0x20 irq event stamp: 211604 hardirqs last enabled at (211603): [] _raw_spin_unlock_irqrestore+0x84/0x98 hardirqs last disabled at (211604): [] el1_dbg+0x24/0x80 softirqs last enabled at (211296): [] handle_softirqs+0x820/0xbc8 softirqs last disabled at (210993): [] __do_softirq+0x18/0x20 ---[ end trace 0000000000000000 ]--- lan78xx 1-1:1.0 enu1: failed to kill vid 0081/0 Fixes: e110bc825897 ("net: usb: lan78xx: Convert to PHYLINK for improved PHY and MAC management") Cc: stable@vger.kernel.org Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20260305143429.530909-5-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/usb/lan78xx.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index f8558b87eaec..19cdf69fa589 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -4552,8 +4552,6 @@ static void lan78xx_disconnect(struct usb_interface *intf) phylink_disconnect_phy(dev->phylink); rtnl_unlock(); - netif_napi_del(&dev->napi); - unregister_netdev(net); timer_shutdown_sync(&dev->stat_monitor); From 0d9a60a0618d255530ca56072c5f39eb58e1ed4a Mon Sep 17 00:00:00 2001 From: Pavan Chebbi Date: Fri, 6 Mar 2026 14:58:54 -0800 Subject: [PATCH 275/487] bnxt_en: Fix RSS table size check when changing ethtool channels MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When changing channels, the current check in bnxt_set_channels() is not checking for non-default RSS contexts when the RSS table size changes. The current check for IFF_RXFH_CONFIGURED is only sufficient for the default RSS context. Expand the check to include the presence of any non-default RSS contexts. Allowing such change will result in incorrect configuration of the context's RSS table when the table size changes. Fixes: b3d0083caf9a ("bnxt_en: Support RSS contexts in ethtool .{get|set}_rxfh()") Reported-by: Björn Töpel Link: https://lore.kernel.org/netdev/20260303181535.2671734-1-bjorn@kernel.org/ Reviewed-by: Andy Gospodarek Signed-off-by: Pavan Chebbi Signed-off-by: Michael Chan Link: https://patch.msgid.link/20260306225854.3575672-1-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index ba47e8294fff..28d0ece2e7b1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -979,8 +979,8 @@ static int bnxt_set_channels(struct net_device *dev, if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) && - netif_is_rxfh_configured(dev)) { - netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n"); + (netif_is_rxfh_configured(dev) || bp->num_rss_ctx)) { + netdev_warn(dev, "RSS table size change required, RSS table entries must be default (with no additional RSS contexts present) to proceed\n"); return -EINVAL; } From 237aab549676288d9255bb8dcc284738e56eaa31 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 3 Mar 2026 11:54:14 +0200 Subject: [PATCH 276/487] drm/i915/vrr: Configure VRR timings after enabling TRANS_DDI_FUNC_CTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apparently ICL may hang with an MCE if we write TRANS_VRR_VMAX/FLIPLINE before enabling TRANS_DDI_FUNC_CTL. Personally I was only able to reproduce a hang (on an Dell XPS 7390 2-in-1) with an external display connected via a dock using a dodgy type-C cable that made the link training fail. After the failed link training the machine would hang. TGL seemed immune to the problem for whatever reason. BSpec does tell us to configure VRR after enabling TRANS_DDI_FUNC_CTL as well. The DMC firmware also does the VRR restore in two stages: - first stage seems to be unconditional and includes TRANS_VRR_CTL and a few other VRR registers, among other things - second stage is conditional on the DDI being enabled, and includes TRANS_DDI_FUNC_CTL and TRANS_VRR_VMAX/VMIN/FLIPLINE, among other things So let's reorder the steps to match to avoid the hang, and toss in an extra WARN to make sure we don't screw this up later. BSpec: 22243 Cc: stable@vger.kernel.org Cc: Ankit Nautiyal Reported-by: Benjamin Tissoires Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15777 Tested-by: Benjamin Tissoires Fixes: dda7dcd9da73 ("drm/i915/vrr: Use fixed timings for platforms that support VRR") Signed-off-by: Ville Syrjälä Link: https://patch.msgid.link/20260303095414.4331-1-ville.syrjala@linux.intel.com Reviewed-by: Ankit Nautiyal (cherry picked from commit 93f3a267c3dd4d811b224bb9e179a10d81456a74) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_display.c | 1 - drivers/gpu/drm/i915/display/intel_vrr.c | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3b8ba8ab76a1..c4246481fc2f 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1614,7 +1614,6 @@ static void hsw_configure_cpu_transcoder(const struct intel_crtc_state *crtc_sta } intel_set_transcoder_timings(crtc_state); - intel_vrr_set_transcoder_timings(crtc_state); if (cpu_transcoder != TRANSCODER_EDP) intel_de_write(display, TRANS_MULT(display, cpu_transcoder), diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index db74744ddb31..bea005752327 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -597,6 +597,18 @@ void intel_vrr_set_transcoder_timings(const struct intel_crtc_state *crtc_state) if (!HAS_VRR(display)) return; + /* + * Bspec says: + * "(note: VRR needs to be programmed after + * TRANS_DDI_FUNC_CTL and before TRANS_CONF)." + * + * In practice it turns out that ICL can hang if + * TRANS_VRR_VMAX/FLIPLINE are written before + * enabling TRANS_DDI_FUNC_CTL. + */ + drm_WARN_ON(display->drm, + !(intel_de_read(display, TRANS_DDI_FUNC_CTL(display, cpu_transcoder)) & TRANS_DDI_FUNC_ENABLE)); + /* * This bit seems to have two meanings depending on the platform: * TGL: generate VRR "safe window" for DSB vblank waits @@ -939,6 +951,8 @@ void intel_vrr_transcoder_enable(const struct intel_crtc_state *crtc_state) { struct intel_display *display = to_intel_display(crtc_state); + intel_vrr_set_transcoder_timings(crtc_state); + if (!intel_vrr_possible(crtc_state)) return; From 029ae067431ab9d0fca479bdabe780fa436706ea Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Tue, 24 Feb 2026 10:49:06 +0100 Subject: [PATCH 277/487] drm/i915: Fix potential overflow of shmem scatterlist length When a scatterlists table of a GEM shmem object of size 4 GB or more is populated with pages allocated from a folio, unsigned int .length attribute of a scatterlist may get overflowed if total byte length of pages allocated to that single scatterlist happens to reach or cross the 4GB limit. As a consequence, users of the object may suffer from hitting unexpected, premature end of the object's backing pages. [278.780187] ------------[ cut here ]------------ [278.780377] WARNING: CPU: 1 PID: 2326 at drivers/gpu/drm/i915/i915_mm.c:55 remap_sg+0x199/0x1d0 [i915] ... [278.780654] CPU: 1 UID: 0 PID: 2326 Comm: gem_mmap_offset Tainted: G S U 6.17.0-rc1-CI_DRM_16981-ged823aaa0607+ #1 PREEMPT(voluntary) [278.780656] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER [278.780658] Hardware name: Intel Corporation Meteor Lake Client Platform/MTL-P LP5x T3 RVP, BIOS MTLPFWI1.R00.3471.D91.2401310918 01/31/2024 [278.780659] RIP: 0010:remap_sg+0x199/0x1d0 [i915] ... [278.780786] Call Trace: [278.780787] [278.780788] ? __apply_to_page_range+0x3e6/0x910 [278.780795] ? __pfx_remap_sg+0x10/0x10 [i915] [278.780906] apply_to_page_range+0x14/0x30 [278.780908] remap_io_sg+0x14d/0x260 [i915] [278.781013] vm_fault_cpu+0xd2/0x330 [i915] [278.781137] __do_fault+0x3a/0x1b0 [278.781140] do_fault+0x322/0x640 [278.781143] __handle_mm_fault+0x938/0xfd0 [278.781150] handle_mm_fault+0x12c/0x300 [278.781152] ? lock_mm_and_find_vma+0x4b/0x760 [278.781155] do_user_addr_fault+0x2d6/0x8e0 [278.781160] exc_page_fault+0x96/0x2c0 [278.781165] asm_exc_page_fault+0x27/0x30 ... That issue was apprehended by the author of a change that introduced it, and potential risk even annotated with a comment, but then never addressed. When adding folio pages to a scatterlist table, take care of byte length of any single scatterlist not exceeding max_segment. Fixes: 0b62af28f249b ("i915: convert shmem_sg_free_table() to use a folio_batch") Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14809 Cc: Matthew Wilcox (Oracle) Cc: Andrew Morton Cc: stable@vger.kernel.org # v6.5+ Signed-off-by: Janusz Krzysztofik Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://lore.kernel.org/r/20260224094944.2447913-2-janusz.krzysztofik@linux.intel.com (cherry picked from commit 06249b4e691a75694c014a61708c007fb5755f60) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index c6c64ba29bc4..720a9ad39aa2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -153,8 +153,12 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, } } while (1); - nr_pages = min_t(unsigned long, - folio_nr_pages(folio), page_count - i); + nr_pages = min_array(((unsigned long[]) { + folio_nr_pages(folio), + page_count - i, + max_segment / PAGE_SIZE, + }), 3); + if (!i || sg->length >= max_segment || folio_pfn(folio) != next_pfn) { @@ -164,7 +168,9 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, st->nents++; sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0); } else { - /* XXX: could overflow? */ + nr_pages = min_t(unsigned long, nr_pages, + (max_segment - sg->length) / PAGE_SIZE); + sg->length += nr_pages * PAGE_SIZE; } next_pfn = folio_pfn(folio) + nr_pages; From 1be2fca84f520105413d0d89ed04bb0ff742ab16 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jouni=20H=C3=B6gander?= Date: Wed, 4 Mar 2026 13:30:08 +0200 Subject: [PATCH 278/487] drm/i915/psr: Repeat Selective Update area alignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently we are aligning Selective Update area to cover cursor fully if needed only once. It may happen that cursor is in Selective Update area after pipe alignment and after that covering cursor plane only partially. Fix this by looping alignment as long as alignment isn't needed anymore. v2: - do not unecessarily loop if cursor was already fully covered - rename aligned as su_area_changed Fixes: 1bff93b8bc27 ("drm/i915/psr: Extend SU area to cover cursor fully if needed") Cc: # v6.9+ Signed-off-by: Jouni Högander Reviewed-by: Ankit Nautiyal Link: https://patch.msgid.link/20260304113011.626542-2-jouni.hogander@intel.com (cherry picked from commit 681e12440d8b110350a5709101169f319e10ccbb) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_psr.c | 50 ++++++++++++++++++------ 1 file changed, 38 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 4ce1173a2e91..3848cd4fba0e 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -2689,11 +2689,12 @@ static void clip_area_update(struct drm_rect *overlap_damage_area, overlap_damage_area->y2 = damage_area->y2; } -static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state) +static bool intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state) { struct intel_display *display = to_intel_display(crtc_state); const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; u16 y_alignment; + bool su_area_changed = false; /* ADLP aligns the SU region to vdsc slice height in case dsc is enabled */ if (crtc_state->dsc.compression_enable && @@ -2702,10 +2703,18 @@ static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st else y_alignment = crtc_state->su_y_granularity; - crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment; - if (crtc_state->psr2_su_area.y2 % y_alignment) + if (crtc_state->psr2_su_area.y1 % y_alignment) { + crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment; + su_area_changed = true; + } + + if (crtc_state->psr2_su_area.y2 % y_alignment) { crtc_state->psr2_su_area.y2 = ((crtc_state->psr2_su_area.y2 / y_alignment) + 1) * y_alignment; + su_area_changed = true; + } + + return su_area_changed; } /* @@ -2839,7 +2848,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_plane_state *new_plane_state, *old_plane_state; struct intel_plane *plane; - bool full_update = false, cursor_in_su_area = false; + bool full_update = false, su_area_changed; int i, ret; if (!crtc_state->enable_psr2_sel_fetch) @@ -2946,15 +2955,32 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, if (ret) return ret; - /* - * Adjust su area to cover cursor fully as necessary (early - * transport). This needs to be done after - * drm_atomic_add_affected_planes to ensure visible cursor is added into - * affected planes even when cursor is not updated by itself. - */ - intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area); + do { + bool cursor_in_su_area; - intel_psr2_sel_fetch_pipe_alignment(crtc_state); + /* + * Adjust su area to cover cursor fully as necessary + * (early transport). This needs to be done after + * drm_atomic_add_affected_planes to ensure visible + * cursor is added into affected planes even when + * cursor is not updated by itself. + */ + intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area); + + su_area_changed = intel_psr2_sel_fetch_pipe_alignment(crtc_state); + + /* + * If the cursor was outside the SU area before + * alignment, the alignment step (which only expands + * SU) may pull the cursor partially inside, so we + * must run ET alignment again to fully cover it. But + * if the cursor was already fully inside before + * alignment, expanding the SU area won't change that, + * so no further work is needed. + */ + if (cursor_in_su_area) + break; + } while (su_area_changed); /* * Now that we have the pipe damaged area check if it intersect with From c2c79c6d5b939ae8a42ddb884f576bddae685672 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jouni=20H=C3=B6gander?= Date: Wed, 4 Mar 2026 13:30:09 +0200 Subject: [PATCH 279/487] drm/i915/dsc: Add Selective Update register definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add definitions for DSC_SU_PARAMETER_SET_0_DSC0 and DSC_SU_PARAMETER_SET_0_DSC1 registers. These are for Selective Update Early Transport configuration. Bspec: 71709 Signed-off-by: Jouni Högander Reviewed-by: Ankit Nautiyal Link: https://patch.msgid.link/20260304113011.626542-3-jouni.hogander@intel.com (cherry picked from commit 24f96d903daf3dcf8fafe84d3d22b80ef47ba493) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_vdsc_regs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h index 2d478a84b07c..2b2e3c1b8138 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h +++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h @@ -196,6 +196,18 @@ #define DSC_PPS18_NSL_BPG_OFFSET(offset) REG_FIELD_PREP(DSC_PPS18_NSL_BPG_OFFSET_MASK, offset) #define DSC_PPS18_SL_OFFSET_ADJ(offset) REG_FIELD_PREP(DSC_PPS18_SL_OFFSET_ADJ_MASK, offset) +#define _LNL_DSC0_SU_PARAMETER_SET_0_PA 0x78064 +#define _LNL_DSC1_SU_PARAMETER_SET_0_PA 0x78164 +#define _LNL_DSC0_SU_PARAMETER_SET_0_PB 0x78264 +#define _LNL_DSC1_SU_PARAMETER_SET_0_PB 0x78364 +#define LNL_DSC0_SU_PARAMETER_SET_0(pipe) _MMIO_PIPE((pipe), _LNL_DSC0_SU_PARAMETER_SET_0_PA, _LNL_DSC0_SU_PARAMETER_SET_0_PB) +#define LNL_DSC1_SU_PARAMETER_SET_0(pipe) _MMIO_PIPE((pipe), _LNL_DSC1_SU_PARAMETER_SET_0_PA, _LNL_DSC1_SU_PARAMETER_SET_0_PB) + +#define DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK REG_GENMASK(31, 20) +#define DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(rows) REG_FIELD_PREP(DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK, (rows)) +#define DSC_SUPS0_SU_PIC_HEIGHT_MASK REG_GENMASK(15, 0) +#define DSC_SUPS0_SU_PIC_HEIGHT(h) REG_FIELD_PREP(DSC_SUPS0_SU_PIC_HEIGHT_MASK, (h)) + /* Icelake Rate Control Buffer Threshold Registers */ #define DSCA_RC_BUF_THRESH_0 _MMIO(0x6B230) #define DSCA_RC_BUF_THRESH_0_UDW _MMIO(0x6B230 + 4) From bb5f1cd10101c2567bff4d0e760b74aee7c42f44 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jouni=20H=C3=B6gander?= Date: Wed, 4 Mar 2026 13:30:10 +0200 Subject: [PATCH 280/487] drm/i915/dsc: Add helper for writing DSC Selective Update ET parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are slice row per frame and pic height configuration in DSC Selective Update Parameter Set 1 register. Add helper for configuring these. v2: - Add WARN_ON_ONCE if vdsc instances per pipe > 2 - instead of checking vdsc instances per pipe being > 1 check == 2 Bspec: 71709 Signed-off-by: Jouni Högander Reviewed-by: Ankit Nautiyal Link: https://patch.msgid.link/20260304113011.626542-4-jouni.hogander@intel.com (cherry picked from commit c8698d61aeb3f70fe33761ee9d3d0e131b5bc2eb) Signed-off-by: Tvrtko Ursulin [tursulin: fixup forward declaration conflict] --- drivers/gpu/drm/i915/display/intel_vdsc.c | 23 +++++++++++++++++++++++ drivers/gpu/drm/i915/display/intel_vdsc.h | 3 +++ 2 files changed, 26 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 5493082f30a7..2065dac1e3fd 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -767,6 +767,29 @@ void intel_dsc_dp_pps_write(struct intel_encoder *encoder, sizeof(dp_dsc_pps_sdp)); } +void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, int su_lines) +{ + struct intel_display *display = to_intel_display(crtc_state); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; + enum pipe pipe = crtc->pipe; + int vdsc_instances_per_pipe = intel_dsc_get_vdsc_per_pipe(crtc_state); + int slice_row_per_frame = su_lines / vdsc_cfg->slice_height; + u32 val; + + drm_WARN_ON_ONCE(display->drm, su_lines % vdsc_cfg->slice_height); + drm_WARN_ON_ONCE(display->drm, vdsc_instances_per_pipe > 2); + + val = DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(slice_row_per_frame); + val |= DSC_SUPS0_SU_PIC_HEIGHT(su_lines); + + intel_de_write_dsb(display, dsb, LNL_DSC0_SU_PARAMETER_SET_0(pipe), val); + + if (vdsc_instances_per_pipe == 2) + intel_de_write_dsb(display, dsb, LNL_DSC1_SU_PARAMETER_SET_0(pipe), val); +} + static i915_reg_t dss_ctl1_reg(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { return is_pipe_dsc(crtc, cpu_transcoder) ? diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h index 99f64ac54b27..99bb9042592a 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.h +++ b/drivers/gpu/drm/i915/display/intel_vdsc.h @@ -13,6 +13,7 @@ struct drm_printer; enum transcoder; struct intel_crtc; struct intel_crtc_state; +struct intel_dsb; struct intel_encoder; bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state); @@ -31,6 +32,8 @@ void intel_dsc_dsi_pps_write(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); void intel_dsc_dp_pps_write(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); +void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, int su_lines); void intel_vdsc_state_dump(struct drm_printer *p, int indent, const struct intel_crtc_state *crtc_state); int intel_vdsc_min_cdclk(const struct intel_crtc_state *crtc_state); From 5923a6e0459fdd3edac4ad5abccb24d777d8f1b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jouni=20H=C3=B6gander?= Date: Wed, 4 Mar 2026 13:30:11 +0200 Subject: [PATCH 281/487] drm/i915/psr: Write DSC parameters on Selective Update in ET mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are slice row per frame and pic height parameters in DSC that needs to be configured on every Selective Update in Early Transport mode. Use helper provided by DSC code to configure these on Selective Update when in Early Transport mode. Also fill crtc_state->psr2_su_area with full frame area on full frame update for DSC calculation. v2: move psr2_su_area under skip_sel_fetch_set_loop label Bspec: 68927, 71709 Fixes: 467e4e061c44 ("drm/i915/psr: Enable psr2 early transport as possible") Cc: # v6.9+ Signed-off-by: Jouni Högander Reviewed-by: Ankit Nautiyal Link: https://patch.msgid.link/20260304113011.626542-5-jouni.hogander@intel.com (cherry picked from commit 3140af2fab505a4cd47d516284529bf1585628be) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_psr.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 3848cd4fba0e..b7302a32ded4 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -2619,6 +2619,12 @@ void intel_psr2_program_trans_man_trk_ctl(struct intel_dsb *dsb, intel_de_write_dsb(display, dsb, PIPE_SRCSZ_ERLY_TPT(crtc->pipe), crtc_state->pipe_srcsz_early_tpt); + + if (!crtc_state->dsc.compression_enable) + return; + + intel_dsc_su_et_parameters_configure(dsb, encoder, crtc_state, + drm_rect_height(&crtc_state->psr2_su_area)); } static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, @@ -3040,6 +3046,10 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, } skip_sel_fetch_set_loop: + if (full_update) + clip_area_update(&crtc_state->psr2_su_area, &crtc_state->pipe_src, + &crtc_state->pipe_src); + psr2_man_trk_ctl_calc(crtc_state, full_update); crtc_state->pipe_srcsz_early_tpt = psr2_pipe_srcsz_early_tpt_calc(crtc_state, full_update); From 335b237d902c7362cb7228802e68374406b24acf Mon Sep 17 00:00:00 2001 From: Arun R Murthy Date: Wed, 4 Mar 2026 12:51:57 +0530 Subject: [PATCH 282/487] drm/i915/dp: Read ALPM caps after DPCD init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For eDP read the ALPM DPCD caps after DPCD initalization and just before the PSR init. v2: Move intel_alpm_init to intel_edp_init_dpcd (Jouni) v3: Add Fixes with commit-id (Jouni) v4: Separated the alpm dpcd read caps from alpm_init and moved to intel_edp_init_dpcd. v5: Read alpm_caps always for eDP irrespective of the eDP version (Jouni) v6: replace drm_dp_dpcd_readb with drm_dp_dpcd_read_byte (Jouni) Fixes: 15438b325987 ("drm/i915/alpm: Add compute config for lobf") Signed-off-by: Arun R Murthy Reviewed-by: Animesh Manna Reviewed-by: Jouni Högander Signed-off-by: Animesh Manna Link: https://patch.msgid.link/20260304072157.1123283-1-arun.r.murthy@intel.com (cherry picked from commit 88442ba208dd5d3405de3f5000cf5b2c86876ae3) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_alpm.c | 6 ------ drivers/gpu/drm/i915/display/intel_dp.c | 7 +++++++ 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c index 07ffee38974b..f4f1b68f7543 100644 --- a/drivers/gpu/drm/i915/display/intel_alpm.c +++ b/drivers/gpu/drm/i915/display/intel_alpm.c @@ -43,12 +43,6 @@ bool intel_alpm_is_alpm_aux_less(struct intel_dp *intel_dp, void intel_alpm_init(struct intel_dp *intel_dp) { - u8 dpcd; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, &dpcd) < 0) - return; - - intel_dp->alpm_dpcd = dpcd; mutex_init(&intel_dp->alpm.lock); } diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 559cf3bb23fd..696edf40b243 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4577,6 +4577,7 @@ static bool intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector) { struct intel_display *display = to_intel_display(intel_dp); + int ret; /* this function is meant to be called only once */ drm_WARN_ON(display->drm, intel_dp->dpcd[DP_DPCD_REV] != 0); @@ -4616,6 +4617,12 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector */ intel_dp_init_source_oui(intel_dp); + /* Read the ALPM DPCD caps */ + ret = drm_dp_dpcd_read_byte(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, + &intel_dp->alpm_dpcd); + if (ret < 0) + return false; + /* * This has to be called after intel_dp->edp_dpcd is filled, PSR checks * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1] From df1d8abf36ca3681c21a6809eaa9a1e01ef897a6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 9 Mar 2026 11:46:27 +0100 Subject: [PATCH 283/487] ALSA: usb-audio: Check endpoint numbers at parsing Scarlett2 mixer interfaces The Scarlett2 mixer quirk in USB-audio driver may hit a NULL dereference when a malformed USB descriptor is passed, since it assumes the presence of an endpoint in the parsed interface in scarlett2_find_fc_interface(), as reported by fuzzer. For avoiding the NULL dereference, just add the sanity check of bNumEndpoints and skip the invalid interface. Reported-by: syzbot+8f29539ef9a1c8334f42@syzkaller.appspotmail.com Closes: https://lore.kernel.org/69acbbe1.050a0220.310d8.0001.GAE@google.com Reported-by: syzbot+ae893a8901067fde2741@syzkaller.appspotmail.com Closes: https://lore.kernel.org/69acf72a.050a0220.310d8.0004.GAE@google.com Cc: Link: https://patch.msgid.link/20260309104632.141895-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/mixer_scarlett2.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index ef3150581eab..fd1fb668929a 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -8251,6 +8251,8 @@ static int scarlett2_find_fc_interface(struct usb_device *dev, if (desc->bInterfaceClass != 255) continue; + if (desc->bNumEndpoints < 1) + continue; epd = get_endpoint(intf->altsetting, 0); private->bInterfaceNumber = desc->bInterfaceNumber; From f1d77b863b414586ee45e10d9837c9ab27d8692d Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 5 Mar 2026 16:49:21 +0800 Subject: [PATCH 284/487] xfs: remove redundant set null for ip->i_itemp ip->i_itemp has been set null in xfs_inode_item_destroy(), so there is no need set it null again in xfs_inode_free_callback(). Signed-off-by: Long Li Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_icache.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index a7a09e7eec81..2040a9292ee6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -159,7 +159,6 @@ xfs_inode_free_callback( ASSERT(!test_bit(XFS_LI_IN_AIL, &ip->i_itemp->ili_item.li_flags)); xfs_inode_item_destroy(ip); - ip->i_itemp = NULL; } kmem_cache_free(xfs_inode_cache, ip); From 186ac39b8a7d3ec7ce9c5dd45e5c2730177f375c Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 5 Mar 2026 16:49:22 +0800 Subject: [PATCH 285/487] xfs: ensure dquot item is deleted from AIL only after log shutdown In xfs_qm_dqflush(), when a dquot flush fails due to corruption (the out_abort error path), the original code removed the dquot log item from the AIL before calling xfs_force_shutdown(). This ordering introduces a subtle race condition that can lead to data loss after a crash. The AIL tracks the oldest dirty metadata in the journal. The position of the tail item in the AIL determines the log tail LSN, which is the oldest LSN that must be preserved for crash recovery. When an item is removed from the AIL, the log tail can advance past the LSN of that item. The race window is as follows: if the dquot item happens to be at the tail of the log, removing it from the AIL allows the log tail to advance. If a concurrent log write is sampling the tail LSN at the same time and subsequently writes a complete checkpoint (i.e., one containing a commit record) to disk before the shutdown takes effect, the journal will no longer protect the dquot's last modification. On the next mount, log recovery will not replay the dquot changes, even though they were never written back to disk, resulting in silent data loss. Fix this by calling xfs_force_shutdown() before xfs_trans_ail_delete() in the out_abort path. Once the log is shut down, no new log writes can complete with an updated tail LSN, making it safe to remove the dquot item from the AIL. Cc: stable@vger.kernel.org Fixes: b707fffda6a3 ("xfs: abort consistently on dquot flush failure") Signed-off-by: Long Li Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_dquot.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 2b208e2c5264..69e9bc588c8b 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1439,9 +1439,15 @@ xfs_qm_dqflush( return 0; out_abort: + /* + * Shut down the log before removing the dquot item from the AIL. + * Otherwise, the log tail may advance past this item's LSN while + * log writes are still in progress, making these unflushed changes + * unrecoverable on the next mount. + */ + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); dqp->q_flags &= ~XFS_DQFLAG_DIRTY; xfs_trans_ail_delete(lip, 0); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); xfs_dqfunlock(dqp); return error; } From 246953f33e8cf95621d6c00332e2780ce1594082 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Thu, 5 Mar 2026 11:12:10 +0800 Subject: [PATCH 286/487] net: enetc: fix incorrect fallback PHY address handling The current netc_get_phy_addr() implementation falls back to PHY address 0 when the "mdio" node or the PHY child node is missing. On i.MX95, this causes failures when a real PHY is actually assigned address 0 and is managed through the EMDIO interface. Because the bit 0 of phy_mask will be set, leading imx95_enetc_mdio_phyaddr_config() to return an error, and the netc_blk_ctrl driver probe subsequently fails. Fix this by returning -ENODEV when neither an "mdio" node nor any PHY node is present, it means that ENETC port MDIO is not used to manage the PHY, so there is no need to configure LaBCR[MDIO_PHYAD_PRTAD]. Reported-by: Alexander Stein Closes: https://lore.kernel.org/all/7825188.GXAFRqVoOG@steina-w Fixes: 6633df05f3ad ("net: enetc: set the external PHY address in IERB for port MDIO usage") Reviewed-by: Clark Wang Tested-by: Alexander Stein Signed-off-by: Wei Fang Link: https://patch.msgid.link/20260305031211.904812-2-wei.fang@nxp.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c index 7fd39f895290..f0e103615e88 100644 --- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c +++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c @@ -333,11 +333,13 @@ static int netc_get_phy_addr(struct device_node *np) mdio_node = of_get_child_by_name(np, "mdio"); if (!mdio_node) - return 0; + return -ENODEV; phy_node = of_get_next_child(mdio_node, NULL); - if (!phy_node) + if (!phy_node) { + err = -ENODEV; goto of_put_mdio_node; + } err = of_property_read_u32(phy_node, "reg", &addr); if (err) @@ -423,6 +425,9 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev) addr = netc_get_phy_addr(gchild); if (addr < 0) { + if (addr == -ENODEV) + continue; + dev_err(dev, "Failed to get PHY address\n"); return addr; } @@ -578,6 +583,9 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv, addr = netc_get_phy_addr(np); if (addr < 0) { + if (addr == -ENODEV) + return 0; + dev_err(dev, "Failed to get PHY address\n"); return addr; } From dbe17e7783cb5d6451ff1217d0464865857e97e1 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Thu, 5 Mar 2026 11:12:11 +0800 Subject: [PATCH 287/487] net: enetc: do not skip setting LaBCR[MDIO_PHYAD_PRTAD] for addr 0 Given that some platforms may use PHY address 0 (I suppose the PHY may not treat address 0 as a broadcast address or default response address). It is possible for some boards to connect multiple PHYs to the same ENETC MAC, for example: - a PHY with a non-zero address connects to ENETC MAC through SGMII interface (selected via DTS_A) - a PHY with address 0 connects to ENETC MAC through RGMII interface (selected via DTS_B) For the case where the ENETC port MDIO is used to manage the PHY, when switching from DTS_A to DTS_B via soft reboot, LaBCR[MDIO_PHYAD_PRTAD] must be updated to 0 because the NETCMIX block is not reset during soft reboot. However, the current driver explicitly skips configuring address 0, causing LaBCR[MDIO_PHYAD_PRTAD] to retain its old value. Therefore, remove the special-case skip of PHY address 0 so that valid configurations using address 0 are properly supported. Fixes: 6633df05f3ad ("net: enetc: set the external PHY address in IERB for port MDIO usage") Fixes: 50bfd9c06f0f ("net: enetc: set external PHY address in IERB for i.MX94 ENETC") Reviewed-by: Clark Wang Signed-off-by: Wei Fang Link: https://patch.msgid.link/20260305031211.904812-3-wei.fang@nxp.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c index f0e103615e88..92a0f824dae7 100644 --- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c +++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c @@ -438,12 +438,6 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev) return -EINVAL; } - /* The default value of LaBCR[MDIO_PHYAD_PRTAD ] is - * 0, so no need to set the register. - */ - if (!addr) - continue; - switch (bus_devfn) { case IMX95_ENETC0_BUS_DEVFN: netc_reg_write(priv->ierb, IERB_LBCR(0), @@ -590,12 +584,6 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv, return addr; } - /* The default value of LaBCR[MDIO_PHYAD_PRTAD] is 0, - * so no need to set the register. - */ - if (!addr) - return 0; - if (phy_mask & BIT(addr)) { dev_err(dev, "Find same PHY address in EMDIO and ENETC node\n"); From a79f7b4aeb8e7562cd6dbf9c223e2c2a04b1a85f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 10 Mar 2026 08:54:33 +0000 Subject: [PATCH 288/487] KVM: arm64: pkvm: Don't reprobe for ICH_VTR_EL2.TDS on CPU hotplug Hotplugging a CPU off and back on fails with pKVM, as we try to probe for ICH_VTR_EL2.TDS. In a non-VHE setup, this is achieved by using an EL2 stub helper. However, the stubs are out of reach once pKVM has deprivileged the kernel. The CPU never boots. Since pKVM doesn't allow late onlining of CPUs, we can detect that protected mode is enforced early on, and return the current state of the capability. Fixes: 2a28810cbb8b2 ("KVM: arm64: GICv3: Detect and work around the lack of ICV_DIR_EL1 trapping") Reported-by: Vincent Donnefort Tested-by: Vincent Donnefort Reviewed-by: Suzuki K Poulose Signed-off-by: Marc Zyngier Link: https://patch.msgid.link/20260310085433.3936742-1-maz@kernel.org Cc: stable@vger.kernel.org --- arch/arm64/kernel/cpufeature.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index c31f8e17732a..32c2dbcc0c64 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2345,6 +2345,15 @@ static bool can_trap_icv_dir_el1(const struct arm64_cpu_capabilities *entry, !is_midr_in_range_list(has_vgic_v3)) return false; + /* + * pKVM prevents late onlining of CPUs. This means that whatever + * state the capability is in after deprivilege cannot be affected + * by a new CPU booting -- this is garanteed to be a CPU we have + * already seen, and the cap is therefore unchanged. + */ + if (system_capabilities_finalized() && is_protected_kvm_enabled()) + return cpus_have_final_cap(ARM64_HAS_ICH_HCR_EL2_TDIR); + if (is_kernel_in_hyp_mode()) res.a1 = read_sysreg_s(SYS_ICH_VTR_EL2); else From 8dafa9f5900c4855a65dbfee51e3bd00636deee1 Mon Sep 17 00:00:00 2001 From: Harry Yoo Date: Mon, 9 Mar 2026 16:22:19 +0900 Subject: [PATCH 289/487] mm/slab: fix an incorrect check in obj_exts_alloc_size() obj_exts_alloc_size() prevents recursive allocation of slabobj_ext array from the same cache, to avoid creating slabs that are never freed. There is one mistake that returns the original size when memory allocation profiling is disabled. The assumption was that memcg-triggered slabobj_ext allocation is always served from KMALLOC_CGROUP type. But this is wrong [1]: when the caller specifies both __GFP_RECLAIMABLE and __GFP_ACCOUNT with SLUB_TINY enabled, the allocation is served from normal kmalloc. This is because kmalloc_type() prioritizes __GFP_RECLAIMABLE over __GFP_ACCOUNT, and SLUB_TINY aliases KMALLOC_RECLAIM with KMALLOC_NORMAL. As a result, the recursion guard is bypassed and the problematic slabs can be created. Fix this by removing the mem_alloc_profiling_enabled() check entirely. The remaining is_kmalloc_normal() check is still sufficient to detect whether the cache is of KMALLOC_NORMAL type and avoid bumping the size if it's not. Without SLUB_TINY, no functional change intended. With SLUB_TINY, allocations with __GFP_ACCOUNT|__GFP_RECLAIMABLE now allocate a larger array if the sizes equal. Reported-by: Zw Tang Fixes: 280ea9c3154b ("mm/slab: avoid allocating slabobj_ext array from its own slab") Closes: https://lore.kernel.org/linux-mm/CAPHJ_VKuMKSke8b11AZQw1PTSFN4n2C0gFxC6xGOG0ZLHgPmnA@mail.gmail.com [1] Cc: stable@vger.kernel.org Signed-off-by: Harry Yoo Link: https://patch.msgid.link/20260309072219.22653-1-harry.yoo@oracle.com Tested-by: Zw Tang Signed-off-by: Vlastimil Babka (SUSE) --- mm/slub.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 20cb4f3b636d..6371838d2352 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2119,13 +2119,6 @@ static inline size_t obj_exts_alloc_size(struct kmem_cache *s, size_t sz = sizeof(struct slabobj_ext) * slab->objects; struct kmem_cache *obj_exts_cache; - /* - * slabobj_ext array for KMALLOC_CGROUP allocations - * are served from KMALLOC_NORMAL caches. - */ - if (!mem_alloc_profiling_enabled()) - return sz; - if (sz > KMALLOC_MAX_CACHE_SIZE) return sz; From e3f5e0f22cfc2371e7471c9fd5b4da78f9df7c69 Mon Sep 17 00:00:00 2001 From: Haiyue Wang Date: Thu, 5 Mar 2026 22:32:34 +0800 Subject: [PATCH 290/487] mctp: i2c: fix skb memory leak in receive path When 'midev->allow_rx' is false, the newly allocated skb isn't consumed by netif_rx(), it needs to free the skb directly. Fixes: f5b8abf9fc3d ("mctp i2c: MCTP I2C binding driver") Signed-off-by: Haiyue Wang Link: https://patch.msgid.link/20260305143240.97592-1-haiyuewa@163.com Signed-off-by: Paolo Abeni --- drivers/net/mctp/mctp-i2c.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index de6bc1736734..15fe4d1163c1 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -343,6 +343,7 @@ static int mctp_i2c_recv(struct mctp_i2c_dev *midev) } else { status = NET_RX_DROP; spin_unlock_irqrestore(&midev->lock, flags); + kfree_skb(skb); } if (status == NET_RX_SUCCESS) { From 1eea46908c57abb7109b1fce024f366ae6c69c4f Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Fri, 6 Mar 2026 17:04:48 +0800 Subject: [PATCH 291/487] can: dev: keep the max bitrate error at 5% Commit b360a13d44db ("can: dev: print bitrate error with two decimal digits") changed calculation of the bit rate error from on-tenth of a percent to on-hundredth of a percent, but forgot to adjust the scale of the CAN_CALC_MAX_ERROR constant. Keeping the existing logic unchanged: Only when the bitrate error exceeds 5% should an error be returned. Otherwise, simply output a warning log. Fixes: b360a13d44db ("can: dev: print bitrate error with two decimal digits") Signed-off-by: Haibo Chen Link: https://patch.msgid.link/20260306-can-fix-v1-1-ac526cec6777@nxp.com Cc: stable@kernel.org [mkl: improve commit message] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/calc_bittiming.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c index cc4022241553..42498e9d3f38 100644 --- a/drivers/net/can/dev/calc_bittiming.c +++ b/drivers/net/can/dev/calc_bittiming.c @@ -8,7 +8,7 @@ #include #include -#define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */ +#define CAN_CALC_MAX_ERROR 500 /* max error 5% */ /* CiA recommended sample points for Non Return to Zero encoding. */ static int can_calc_sample_point_nrz(const struct can_bittiming *bt) From 47bba09b14fa21712398febf36cb14fd4fc3bded Mon Sep 17 00:00:00 2001 From: Wenyuan Li <2063309626@qq.com> Date: Tue, 10 Mar 2026 13:08:44 +0800 Subject: [PATCH 292/487] can: hi311x: hi3110_open(): add check for hi3110_power_enable() return value In hi3110_open(), the return value of hi3110_power_enable() is not checked. If power enable fails, the device may not function correctly, while the driver still returns success. Add a check for the return value and propagate the error accordingly. Signed-off-by: Wenyuan Li <2063309626@qq.com> Link: https://patch.msgid.link/tencent_B5E2E7528BB28AA8A2A56E16C49BD58B8B07@qq.com Fixes: 57e83fb9b746 ("can: hi311x: Add Holt HI-311x CAN driver") [mkl: adjust subject, commit message and jump label] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/spi/hi311x.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index e00d3dbc4cf4..91b1fa970f8f 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -755,7 +755,9 @@ static int hi3110_open(struct net_device *net) return ret; mutex_lock(&priv->hi3110_lock); - hi3110_power_enable(priv->transceiver, 1); + ret = hi3110_power_enable(priv->transceiver, 1); + if (ret) + goto out_close_candev; priv->force_quit = 0; priv->tx_skb = NULL; @@ -790,6 +792,7 @@ static int hi3110_open(struct net_device *net) hi3110_hw_sleep(spi); out_close: hi3110_power_enable(priv->transceiver, 0); + out_close_candev: close_candev(net); mutex_unlock(&priv->hi3110_lock); return ret; From 950803f7254721c1c15858fbbfae3deaaeeecb11 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Fri, 6 Mar 2026 10:15:07 +0800 Subject: [PATCH 293/487] bonding: fix type confusion in bond_setup_by_slave() kernel BUG at net/core/skbuff.c:2306! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:pskb_expand_head+0xa08/0xfe0 net/core/skbuff.c:2306 RSP: 0018:ffffc90004aff760 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff88807e3c8780 RCX: ffffffff89593e0e RDX: ffff88807b7c4900 RSI: ffffffff89594747 RDI: ffff88807b7c4900 RBP: 0000000000000820 R08: 0000000000000005 R09: 0000000000000000 R10: 00000000961a63e0 R11: 0000000000000000 R12: ffff88807e3c8780 R13: 00000000961a6560 R14: dffffc0000000000 R15: 00000000961a63e0 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe1a0ed8df0 CR3: 000000002d816000 CR4: 00000000003526f0 Call Trace: ipgre_header+0xdd/0x540 net/ipv4/ip_gre.c:900 dev_hard_header include/linux/netdevice.h:3439 [inline] packet_snd net/packet/af_packet.c:3028 [inline] packet_sendmsg+0x3ae5/0x53c0 net/packet/af_packet.c:3108 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg net/socket.c:742 [inline] ____sys_sendmsg+0xa54/0xc30 net/socket.c:2592 ___sys_sendmsg+0x190/0x1e0 net/socket.c:2646 __sys_sendmsg+0x170/0x220 net/socket.c:2678 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fe1a0e6c1a9 When a non-Ethernet device (e.g. GRE tunnel) is enslaved to a bond, bond_setup_by_slave() directly copies the slave's header_ops to the bond device: bond_dev->header_ops = slave_dev->header_ops; This causes a type confusion when dev_hard_header() is later called on the bond device. Functions like ipgre_header(), ip6gre_header(),all use netdev_priv(dev) to access their device-specific private data. When called with the bond device, netdev_priv() returns the bond's private data (struct bonding) instead of the expected type (e.g. struct ip_tunnel), leading to garbage values being read and kernel crashes. Fix this by introducing bond_header_ops with wrapper functions that delegate to the active slave's header_ops using the slave's own device. This ensures netdev_priv() in the slave's header functions always receives the correct device. The fix is placed in the bonding driver rather than individual device drivers, as the root cause is bond blindly inheriting header_ops from the slave without considering that these callbacks expect a specific netdev_priv() layout. The type confusion can be observed by adding a printk in ipgre_header() and running the following commands: ip link add dummy0 type dummy ip addr add 10.0.0.1/24 dev dummy0 ip link set dummy0 up ip link add gre1 type gre local 10.0.0.1 ip link add bond1 type bond mode active-backup ip link set gre1 master bond1 ip link set gre1 up ip link set bond1 up ip addr add fe80::1/64 dev bond1 Fixes: 1284cd3a2b74 ("bonding: two small fixes for IPoIB support") Suggested-by: Jay Vosburgh Reviewed-by: Eric Dumazet Signed-off-by: Jiayuan Chen Link: https://patch.msgid.link/20260306021508.222062-1-jiayuan.chen@linux.dev Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 47 ++++++++++++++++++++++++++++++++- 1 file changed, 46 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 444519078da3..c1fb92602e46 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1509,6 +1509,50 @@ static netdev_features_t bond_fix_features(struct net_device *dev, return features; } +static int bond_header_create(struct sk_buff *skb, struct net_device *bond_dev, + unsigned short type, const void *daddr, + const void *saddr, unsigned int len) +{ + struct bonding *bond = netdev_priv(bond_dev); + const struct header_ops *slave_ops; + struct slave *slave; + int ret = 0; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) { + slave_ops = READ_ONCE(slave->dev->header_ops); + if (slave_ops && slave_ops->create) + ret = slave_ops->create(skb, slave->dev, + type, daddr, saddr, len); + } + rcu_read_unlock(); + return ret; +} + +static int bond_header_parse(const struct sk_buff *skb, unsigned char *haddr) +{ + struct bonding *bond = netdev_priv(skb->dev); + const struct header_ops *slave_ops; + struct slave *slave; + int ret = 0; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) { + slave_ops = READ_ONCE(slave->dev->header_ops); + if (slave_ops && slave_ops->parse) + ret = slave_ops->parse(skb, haddr); + } + rcu_read_unlock(); + return ret; +} + +static const struct header_ops bond_header_ops = { + .create = bond_header_create, + .parse = bond_header_parse, +}; + static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { @@ -1516,7 +1560,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev, dev_close(bond_dev); - bond_dev->header_ops = slave_dev->header_ops; + bond_dev->header_ops = slave_dev->header_ops ? + &bond_header_ops : NULL; bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; From 7d86aa41c073c4e7eb75fd2e674f1fd8f289728a Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Fri, 6 Mar 2026 03:14:02 +0000 Subject: [PATCH 294/487] mctp: route: hold key->lock in mctp_flow_prepare_output() mctp_flow_prepare_output() checks key->dev and may call mctp_dev_set_key(), but it does not hold key->lock while doing so. mctp_dev_set_key() and mctp_dev_release_key() are annotated with __must_hold(&key->lock), so key->dev access is intended to be serialized by key->lock. The mctp_sendmsg() transmit path reaches mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output() without holding key->lock, so the check-and-set sequence is racy. Example interleaving: CPU0 CPU1 ---- ---- mctp_flow_prepare_output(key, devA) if (!key->dev) // sees NULL mctp_flow_prepare_output( key, devB) if (!key->dev) // still NULL mctp_dev_set_key(devB, key) mctp_dev_hold(devB) key->dev = devB mctp_dev_set_key(devA, key) mctp_dev_hold(devA) key->dev = devA // overwrites devB Now both devA and devB references were acquired, but only the final key->dev value is tracked for release. One reference can be lost, causing a resource leak as mctp_dev_release_key() would only decrease the reference on one dev. Fix by taking key->lock around the key->dev check and mctp_dev_set_key() call. Fixes: 67737c457281 ("mctp: Pass flow data & flow release events to drivers") Signed-off-by: Chengfeng Ye Link: https://patch.msgid.link/20260306031402.857224-1-dg573847474@gmail.com Signed-off-by: Paolo Abeni --- net/mctp/route.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/mctp/route.c b/net/mctp/route.c index 0381377ab760..59ad60b88563 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -359,6 +359,7 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) { struct mctp_sk_key *key; struct mctp_flow *flow; + unsigned long flags; flow = skb_ext_find(skb, SKB_EXT_MCTP); if (!flow) @@ -366,12 +367,14 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) key = flow->key; - if (key->dev) { - WARN_ON(key->dev != dev); - return; - } + spin_lock_irqsave(&key->lock, flags); - mctp_dev_set_key(dev, key); + if (!key->dev) + mctp_dev_set_key(dev, key); + else + WARN_ON(key->dev != dev); + + spin_unlock_irqrestore(&key->lock, flags); } #else static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {} From 8cc7dd77a1466f0ec58c03478b2e735a5b289b96 Mon Sep 17 00:00:00 2001 From: Shashank Balaji Date: Fri, 6 Mar 2026 14:46:28 +0900 Subject: [PATCH 295/487] x86/apic: Disable x2apic on resume if the kernel expects so When resuming from s2ram, firmware may re-enable x2apic mode, which may have been disabled by the kernel during boot either because it doesn't support IRQ remapping or for other reasons. This causes the kernel to continue using the xapic interface, while the hardware is in x2apic mode, which causes hangs. This happens on defconfig + bare metal + s2ram. Fix this in lapic_resume() by disabling x2apic if the kernel expects it to be disabled, i.e. when x2apic_mode = 0. The ACPI v6.6 spec, Section 16.3 [1] says firmware restores either the pre-sleep configuration or initial boot configuration for each CPU, including MSR state: When executing from the power-on reset vector as a result of waking from an S2 or S3 sleep state, the platform firmware performs only the hardware initialization required to restore the system to either the state the platform was in prior to the initial operating system boot, or to the pre-sleep configuration state. In multiprocessor systems, non-boot processors should be placed in the same state as prior to the initial operating system boot. (further ahead) If this is an S2 or S3 wake, then the platform runtime firmware restores minimum context of the system before jumping to the waking vector. This includes: CPU configuration. Platform runtime firmware restores the pre-sleep configuration or initial boot configuration of each CPU (MSR, MTRR, firmware update, SMBase, and so on). Interrupts must be disabled (for IA-32 processors, disabled by CLI instruction). (and other things) So at least as per the spec, re-enablement of x2apic by the firmware is allowed if "x2apic on" is a part of the initial boot configuration. [1] https://uefi.org/specs/ACPI/6.6/16_Waking_and_Sleeping.html#initialization [ bp: Massage. ] Fixes: 6e1cb38a2aef ("x64, x2apic/intr-remap: add x2apic support, including enabling interrupt-remapping") Co-developed-by: Rahul Bukte Signed-off-by: Rahul Bukte Signed-off-by: Shashank Balaji Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Thomas Gleixner Reviewed-by: Sohil Mehta Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260306-x2apic-fix-v2-1-bee99c12efa3@sony.com --- arch/x86/kernel/apic/apic.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d93f87f29d03..961714e6adae 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1894,6 +1894,7 @@ void __init check_x2apic(void) static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } +static inline void __x2apic_disable(void) { } #endif /* !CONFIG_X86_X2APIC */ void __init enable_IR_x2apic(void) @@ -2456,6 +2457,11 @@ static void lapic_resume(void *data) if (x2apic_mode) { __x2apic_enable(); } else { + if (x2apic_enabled()) { + pr_warn_once("x2apic: re-enabled by firmware during resume. Disabling\n"); + __x2apic_disable(); + } + /* * Make sure the APICBASE points to the right address * From 6485cb96be5cd0f4bf39554737ba11322cc9b053 Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Fri, 6 Mar 2026 16:46:27 +0530 Subject: [PATCH 296/487] amd-xgbe: fix link status handling in xgbe_rx_adaptation The link status bit is latched low to allow detection of momentary link drops. If the status indicates that the link is already down, read it again to obtain the current state. Fixes: 4f3b20bfbb75 ("amd-xgbe: add support for rx-adaptation") Signed-off-by: Raju Rangoju Link: https://patch.msgid.link/20260306111629.1515676-2-Raju.Rangoju@amd.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index c63ddb12237e..13c556dc0d67 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -1942,7 +1942,7 @@ static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata, static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; - unsigned int reg; + int reg; /* step 2: force PCS to send RX_ADAPT Req to PHY */ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_EQ_CTRL4, @@ -1964,11 +1964,20 @@ static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata) /* Step 4: Check for Block lock */ - /* Link status is latched low, so read once to clear - * and then read again to get current state + reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (reg < 0) + goto set_mode; + + /* Link status is latched low so that momentary link drops + * can be detected. If link was already down read again + * to get the latest state. */ - reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); - reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) { + reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (reg < 0) + goto set_mode; + } + if (reg & MDIO_STAT1_LSTATUS) { /* If the block lock is found, update the helpers * and declare the link up From 27a4dd0c702b3b2b9cf2c045d100cc2fe8720b81 Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Fri, 6 Mar 2026 16:46:28 +0530 Subject: [PATCH 297/487] amd-xgbe: prevent CRC errors during RX adaptation with AN disabled When operating in 10GBASE-KR mode with auto-negotiation disabled and RX adaptation enabled, CRC errors can occur during the RX adaptation process. This happens because the driver continues transmitting and receiving packets while adaptation is in progress. Fix this by stopping TX/RX immediately when the link goes down and RX adaptation needs to be re-triggered, and only re-enabling TX/RX after adaptation completes and the link is confirmed up. Introduce a flag to track whether TX/RX was disabled for adaptation so it can be restored correctly. This prevents packets from being transmitted or received during the RX adaptation window and avoids CRC errors from corrupted frames. The flag tracking the data path state is synchronized with hardware state in xgbe_start() to prevent stale state after device restarts. This ensures that after a restart cycle (where xgbe_stop disables TX/RX and xgbe_start re-enables them), the flag correctly reflects that the data path is active. Fixes: 4f3b20bfbb75 ("amd-xgbe: add support for rx-adaptation") Signed-off-by: Raju Rangoju Link: https://patch.msgid.link/20260306111629.1515676-3-Raju.Rangoju@amd.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 4 ++ drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 63 ++++++++++++++++++++- drivers/net/ethernet/amd/xgbe/xgbe.h | 4 ++ 3 files changed, 69 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 8b79d88480db..39da2f811858 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1277,6 +1277,10 @@ static int xgbe_start(struct xgbe_prv_data *pdata) hw_if->enable_tx(pdata); hw_if->enable_rx(pdata); + /* Synchronize flag with hardware state after enabling TX/RX. + * This prevents stale state after device restart cycles. + */ + pdata->data_path_stopped = false; udp_tunnel_nic_reset_ntf(netdev); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 13c556dc0d67..b8cf6ccfe641 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -2017,6 +2017,48 @@ static void xgbe_phy_rx_adaptation(struct xgbe_prv_data *pdata) xgbe_rx_adaptation(pdata); } +/* + * xgbe_phy_stop_data_path - Stop TX/RX to prevent packet corruption + * @pdata: driver private data + * + * This function stops the data path (TX and RX) to prevent packet + * corruption during critical PHY operations like RX adaptation. + * Must be called before initiating RX adaptation when link goes down. + */ +static void xgbe_phy_stop_data_path(struct xgbe_prv_data *pdata) +{ + if (pdata->data_path_stopped) + return; + + /* Stop TX/RX to prevent packet corruption during RX adaptation */ + pdata->hw_if.disable_tx(pdata); + pdata->hw_if.disable_rx(pdata); + pdata->data_path_stopped = true; + + netif_dbg(pdata, link, pdata->netdev, + "stopping data path for RX adaptation\n"); +} + +/* + * xgbe_phy_start_data_path - Re-enable TX/RX after RX adaptation + * @pdata: driver private data + * + * This function re-enables the data path (TX and RX) after RX adaptation + * has completed successfully. Only called when link is confirmed up. + */ +static void xgbe_phy_start_data_path(struct xgbe_prv_data *pdata) +{ + if (!pdata->data_path_stopped) + return; + + pdata->hw_if.enable_rx(pdata); + pdata->hw_if.enable_tx(pdata); + pdata->data_path_stopped = false; + + netif_dbg(pdata, link, pdata->netdev, + "restarting data path after RX adaptation\n"); +} + static void xgbe_phy_rx_reset(struct xgbe_prv_data *pdata) { int reg; @@ -2810,13 +2852,27 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) if (pdata->en_rx_adap) { /* if the link is available and adaptation is done, * declare link up + * + * Note: When link is up and adaptation is done, we can + * safely re-enable the data path if it was stopped + * for adaptation. */ - if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) + if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) { + xgbe_phy_start_data_path(pdata); return 1; + } /* If either link is not available or adaptation is not done, * retrigger the adaptation logic. (if the mode is not set, * then issue mailbox command first) */ + + /* CRITICAL: Stop data path BEFORE triggering RX adaptation + * to prevent CRC errors from packets corrupted during + * the adaptation process. This is especially important + * when AN is OFF in 10G KR mode. + */ + xgbe_phy_stop_data_path(pdata); + if (pdata->mode_set) { xgbe_phy_rx_adaptation(pdata); } else { @@ -2824,8 +2880,11 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) xgbe_phy_set_mode(pdata, phy_data->cur_mode); } - if (pdata->rx_adapt_done) + if (pdata->rx_adapt_done) { + /* Adaptation complete, safe to re-enable data path */ + xgbe_phy_start_data_path(pdata); return 1; + } } else if (reg & MDIO_STAT1_LSTATUS) return 1; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index e1d7d7150e16..438033a71523 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1243,6 +1243,10 @@ struct xgbe_prv_data { bool en_rx_adap; int rx_adapt_retries; bool rx_adapt_done; + /* Flag to track if data path (TX/RX) was stopped for RX adaptation. + * This prevents packet corruption during the adaptation window. + */ + bool data_path_stopped; bool mode_set; bool sph; }; From a8ba129af46856112981c124850ec6a85a1c1ab6 Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Fri, 6 Mar 2026 16:46:29 +0530 Subject: [PATCH 298/487] amd-xgbe: reset PHY settings before starting PHY commit f93505f35745 ("amd-xgbe: let the MAC manage PHY PM") moved xgbe_phy_reset() from xgbe_open() to xgbe_start(), placing it after phy_start(). As a result, the PHY settings were being reset after the PHY had already started. Reorder the calls so that the PHY settings are reset before phy_start() is invoked. Fixes: f93505f35745 ("amd-xgbe: let the MAC manage PHY PM") Reviewed-by: Maxime Chevallier Signed-off-by: Raju Rangoju Link: https://patch.msgid.link/20260306111629.1515676-4-Raju.Rangoju@amd.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 39da2f811858..23beea48ae26 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1271,6 +1271,12 @@ static int xgbe_start(struct xgbe_prv_data *pdata) if (ret) goto err_napi; + /* Reset the phy settings */ + ret = xgbe_phy_reset(pdata); + if (ret) + goto err_irqs; + + /* Start the phy */ ret = phy_if->phy_start(pdata); if (ret) goto err_irqs; @@ -1284,11 +1290,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata) udp_tunnel_nic_reset_ntf(netdev); - /* Reset the phy settings */ - ret = xgbe_phy_reset(pdata); - if (ret) - goto err_txrx; - netif_tx_start_all_queues(netdev); xgbe_start_timers(pdata); @@ -1298,10 +1299,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata) return 0; -err_txrx: - hw_if->disable_rx(pdata); - hw_if->disable_tx(pdata); - err_irqs: xgbe_free_irqs(pdata); From 69fb5d91bba44ecf7eb80530b85fa4fb028921d5 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 8 Mar 2026 17:38:00 +0100 Subject: [PATCH 299/487] libceph: prevent potential out-of-bounds reads in process_message_header() If the message frame is (maliciously) corrupted in a way that the length of the control segment ends up being less than the size of the message header or a different frame is made to look like a message frame, out-of-bounds reads may ensue in process_message_header(). Perform an explicit bounds check before decoding the message header. Cc: stable@vger.kernel.org Reported-by: Raphael Zimmer Signed-off-by: Ilya Dryomov Reviewed-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko --- net/ceph/messenger_v2.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 5ec3272cd2dd..ed618435d33a 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -2833,12 +2833,15 @@ static int process_message_header(struct ceph_connection *con, void *p, void *end) { struct ceph_frame_desc *desc = &con->v2.in_desc; - struct ceph_msg_header2 *hdr2 = p; + struct ceph_msg_header2 *hdr2; struct ceph_msg_header hdr; int skip; int ret; u64 seq; + ceph_decode_need(&p, end, sizeof(*hdr2), bad); + hdr2 = p; + /* verify seq# */ seq = le64_to_cpu(hdr2->seq); if ((s64)seq - (s64)con->in_seq < 1) { @@ -2869,6 +2872,10 @@ static int process_message_header(struct ceph_connection *con, WARN_ON(!con->in_msg); WARN_ON(con->in_msg->con != con); return 1; + +bad: + pr_err("failed to decode message header\n"); + return -EINVAL; } static int process_message(struct ceph_connection *con) From a5a373705081d7cc6363e16990e2361b0b362314 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 8 Mar 2026 17:57:23 +0100 Subject: [PATCH 300/487] libceph: admit message frames only in CEPH_CON_S_OPEN state Similar checks are performed for all control frames, but an early check for message frames was missing. process_message() is already set up to terminate the loop in case the state changes while con->ops->dispatch() handler is being executed. Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko --- net/ceph/messenger_v2.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index ed618435d33a..c4ddf7911f7d 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -2905,6 +2905,11 @@ static int __handle_control(struct ceph_connection *con, void *p) if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE) return process_control(con, p, end); + if (con->state != CEPH_CON_S_OPEN) { + con->error_msg = "protocol error, unexpected message"; + return -EINVAL; + } + ret = process_message_header(con, p, end); if (ret < 0) return ret; From c4c22b846eceff05b1129b8844a80310e55a7f87 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 8 Mar 2026 20:01:27 +0100 Subject: [PATCH 301/487] libceph: reject preamble if control segment is empty While head_onwire_len() has a branch to handle ctrl_len == 0 case, prepare_read_control() always sets up a kvec for the CRC meaning that a non-empty control segment is effectively assumed. All frames that clients deal with meet that assumption, so let's make it official and treat the preamble with an empty control segment as malformed. Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Alex Markuze --- net/ceph/messenger_v2.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index c4ddf7911f7d..50f65820f623 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -392,7 +392,7 @@ static int head_onwire_len(int ctrl_len, bool secure) int head_len; int rem_len; - BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); + BUG_ON(ctrl_len < 1 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); if (secure) { head_len = CEPH_PREAMBLE_SECURE_LEN; @@ -401,9 +401,7 @@ static int head_onwire_len(int ctrl_len, bool secure) head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN; } } else { - head_len = CEPH_PREAMBLE_PLAIN_LEN; - if (ctrl_len) - head_len += ctrl_len + CEPH_CRC_LEN; + head_len = CEPH_PREAMBLE_PLAIN_LEN + ctrl_len + CEPH_CRC_LEN; } return head_len; } @@ -528,11 +526,16 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) desc->fd_aligns[i] = ceph_decode_16(&p); } - if (desc->fd_lens[0] < 0 || + /* + * This would fire for FRAME_TAG_WAIT (it has one empty + * segment), but we should never get it as client. + */ + if (desc->fd_lens[0] < 1 || desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) { pr_err("bad control segment length %d\n", desc->fd_lens[0]); return -EINVAL; } + if (desc->fd_lens[1] < 0 || desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) { pr_err("bad front segment length %d\n", desc->fd_lens[1]); @@ -549,10 +552,6 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) return -EINVAL; } - /* - * This would fire for FRAME_TAG_WAIT (it has one empty - * segment), but we should never get it as client. - */ if (!desc->fd_lens[desc->fd_seg_cnt - 1]) { pr_err("last segment empty, segment count %d\n", desc->fd_seg_cnt); From a5f930eebde6f27c1e404f566c09332f42f349fb Mon Sep 17 00:00:00 2001 From: Dongsheng Yang Date: Tue, 10 Mar 2026 07:05:14 +0000 Subject: [PATCH 302/487] MAINTAINERS: update email address of Dongsheng Yang My easystack email will be unreachable soon, update my email address to linux.dev one. Signed-off-by: Dongsheng Yang Signed-off-by: Ilya Dryomov --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 77fdfcb55f06..8a9d35b29dbe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21938,7 +21938,7 @@ F: drivers/media/radio/radio-tea5777.c RADOS BLOCK DEVICE (RBD) M: Ilya Dryomov -R: Dongsheng Yang +R: Dongsheng Yang L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ From 6f1a9140ecda3baba3d945b9a6155af4268aafc4 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Sat, 7 Mar 2026 00:01:34 +0800 Subject: [PATCH 303/487] net: add xmit recursion limit to tunnel xmit functions Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own recursion limit. When a bond device in broadcast mode has GRE tap interfaces as slaves, and those GRE tunnels route back through the bond, multicast/broadcast traffic triggers infinite recursion between bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing kernel stack overflow. The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not sufficient because tunnel recursion involves route lookups and full IP output, consuming much more stack per level. Use a lower limit of 4 (IP_TUNNEL_RECURSION_LIMIT) to prevent overflow. Add recursion detection using dev_xmit_recursion helpers directly in iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.). Move dev_xmit_recursion helpers from net/core/dev.h to public header include/linux/netdevice.h so they can be used by tunnel code. BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11 Workqueue: mld mld_ifc_work Call Trace: __build_flow_key.constprop.0 (net/ipv4/route.c:515) ip_rt_update_pmtu (net/ipv4/route.c:1073) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) mld_sendpack mld_ifc_work process_one_work worker_thread Fixes: 745e20f1b626 ("net: add a recursion limit in xmit path") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Link: https://patch.msgid.link/20260306160133.3852900-2-bestswngs@gmail.com Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++++ include/net/ip6_tunnel.h | 12 ++++++++++++ include/net/ip_tunnels.h | 7 +++++++ net/core/dev.h | 35 ----------------------------------- net/ipv4/ip_tunnel_core.c | 13 +++++++++++++ 5 files changed, 64 insertions(+), 35 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67e25f6d15a4..ae269a2e7f4d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3576,17 +3576,49 @@ struct page_pool_bh { }; DECLARE_PER_CPU(struct page_pool_bh, system_page_pool); +#define XMIT_RECURSION_LIMIT 8 + #ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } + +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} #else static inline int dev_recursion_level(void) { return current->net_xmit.recursion; } +static inline bool dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + current->net_xmit.recursion++; +} + +static inline void dev_xmit_recursion_dec(void) +{ + current->net_xmit.recursion--; +} #endif void __netif_schedule(struct Qdisc *q); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 120db2865811..1253cbb4b0a4 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -156,6 +156,16 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; + if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + kfree_skb(skb); + return; + } + + dev_xmit_recursion_inc(); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->flags = ip6cb_flags; pkt_len = skb->len - skb_inner_network_offset(skb); @@ -166,6 +176,8 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, pkt_len = -1; iptunnel_xmit_stats(dev, pkt_len); } + + dev_xmit_recursion_dec(); } #endif #endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 4021e6a73e32..80662f812080 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -27,6 +27,13 @@ #include #endif +/* Recursion limit for tunnel xmit to detect routing loops. + * Unlike XMIT_RECURSION_LIMIT (8) used in the no-qdisc path, tunnel + * recursion involves route lookups and full IP output, consuming much + * more stack per level, so a lower limit is needed. + */ +#define IP_TUNNEL_RECURSION_LIMIT 4 + /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) diff --git a/net/core/dev.h b/net/core/dev.h index 98793a738f43..781619e76b3e 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -366,41 +366,6 @@ static inline void napi_assert_will_not_race(const struct napi_struct *napi) void kick_defer_list_purge(unsigned int cpu); -#define XMIT_RECURSION_LIMIT 8 - -#ifndef CONFIG_PREEMPT_RT -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - __this_cpu_inc(softnet_data.xmit.recursion); -} - -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} -#else -static inline bool dev_xmit_recursion(void) -{ - return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - current->net_xmit.recursion++; -} - -static inline void dev_xmit_recursion_dec(void) -{ - current->net_xmit.recursion--; -} -#endif - int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 2e61ac137128..b1b6bf949f65 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -58,6 +58,17 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, struct iphdr *iph; int err; + if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + ip_rt_put(rt); + kfree_skb(skb); + return; + } + + dev_xmit_recursion_inc(); + skb_scrub_packet(skb, xnet); skb_clear_hash_if_not_l4(skb); @@ -88,6 +99,8 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, pkt_len = 0; iptunnel_xmit_stats(dev, pkt_len); } + + dev_xmit_recursion_dec(); } EXPORT_SYMBOL_GPL(iptunnel_xmit); From 59bdbabccaa470ed94aae7d94a1229c7b0ff4681 Mon Sep 17 00:00:00 2001 From: Andrzej Kacprowski Date: Thu, 5 Mar 2026 15:22:26 +0100 Subject: [PATCH 304/487] accel/ivpu: Remove boot params address setting via MMIO register The NPU 60XX uses the default boot params location specified in the firmware image header, consistent with earlier generations. Remove the unnecessary MMIO register write, freeing the AON register for future use. Fixes: 44e4c88951fa ("accel/ivpu: Implement warm boot flow for NPU6 and unify boot handling") Signed-off-by: Andrzej Kacprowski Reviewed-by: Karol Wachowski Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20260305142226.194995-1-andrzej.kacprowski@linux.intel.com (cherry picked from commit 81e62e7bf8b9309bf0febdf00940818f98bc23d8) Signed-off-by: Thomas Zimmermann --- drivers/accel/ivpu/ivpu_hw_40xx_reg.h | 6 ------ drivers/accel/ivpu/ivpu_hw_ip.c | 1 - 2 files changed, 7 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h index 421242acb184..fc0ee8d637f9 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h +++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h @@ -121,12 +121,6 @@ #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY 0x0003006cu #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY_STATUS_DLY_MASK GENMASK(7, 0) -#define VPU_40XX_HOST_SS_AON_RETENTION0 0x0003000cu -#define VPU_40XX_HOST_SS_AON_RETENTION1 0x00030010u -#define VPU_40XX_HOST_SS_AON_RETENTION2 0x00030014u -#define VPU_40XX_HOST_SS_AON_RETENTION3 0x00030018u -#define VPU_40XX_HOST_SS_AON_RETENTION4 0x0003001cu - #define VPU_40XX_HOST_SS_AON_IDLE_GEN 0x00030200u #define VPU_40XX_HOST_SS_AON_IDLE_GEN_EN_MASK BIT_MASK(0) #define VPU_40XX_HOST_SS_AON_IDLE_GEN_HW_PG_EN_MASK BIT_MASK(1) diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c index 959984c54341..37f95a0551ed 100644 --- a/drivers/accel/ivpu/ivpu_hw_ip.c +++ b/drivers/accel/ivpu/ivpu_hw_ip.c @@ -931,7 +931,6 @@ static int soc_cpu_boot_40xx(struct ivpu_device *vdev) static int soc_cpu_boot_60xx(struct ivpu_device *vdev) { - REGV_WR64(VPU_40XX_HOST_SS_AON_RETENTION1, vdev->fw->mem_bp->vpu_addr); soc_cpu_set_entry_point_40xx(vdev, vdev->fw->cold_boot_entry_point); return 0; From 3c3b41e5911db7668e3938eae8df7ed80c76c153 Mon Sep 17 00:00:00 2001 From: James Clark Date: Fri, 6 Mar 2026 14:08:34 +0000 Subject: [PATCH 305/487] perf cs-etm: Finish removal of ETM_OPT_* These #defines have been removed from the kernel headers in favour of the string based PMU format attributes. Usages were previously removed from the recording side of cs-etm in Perf. Finish the removal by removing usages from the decode side too. It's a straight replacement of the old #defines with the new register bit definitions. Except cs_etm__setup_timeless_decoding() which wasn't looking at the saved metadata and was instead hard coding an access to 'attr.config'. This was vulnerable to the same issue of .config being moved to .config2 etc that the original removal of ETM_OPT_* tried to fix. So fix that too. Signed-off-by: James Clark Tested-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 14 -------- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 2 +- tools/perf/util/cs-etm.c | 36 +++++++------------ tools/perf/util/cs-etm.h | 15 ++++++++ 4 files changed, 29 insertions(+), 38 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index dc3f4e86b075..4418d21708d6 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -68,20 +68,6 @@ static const char * const metadata_ete_ro[] = { enum cs_etm_version { CS_NOT_PRESENT, CS_ETMV3, CS_ETMV4, CS_ETE }; -/* ETMv4 CONFIGR register bits */ -#define TRCCONFIGR_BB BIT(3) -#define TRCCONFIGR_CCI BIT(4) -#define TRCCONFIGR_CID BIT(6) -#define TRCCONFIGR_VMID BIT(7) -#define TRCCONFIGR_TS BIT(11) -#define TRCCONFIGR_RS BIT(12) -#define TRCCONFIGR_VMIDOPT BIT(15) - -/* ETMv3 ETMCR register bits */ -#define ETMCR_CYC_ACC BIT(12) -#define ETMCR_TIMESTAMP_EN BIT(28) -#define ETMCR_RETURN_STACK BIT(29) - static bool cs_etm_is_ete(struct perf_pmu *cs_etm_pmu, struct perf_cpu cpu); static int cs_etm_get_ro(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path, __u64 *val); static bool cs_etm_pmu_path_exists(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path); diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 3050fe212666..212f17a3dc72 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -549,7 +549,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq, /* * Process the PE_CONTEXT packets if we have a valid contextID or VMID. * If the kernel is running at EL2, the PID is traced in CONTEXTIDR_EL2 - * as VMID, Bit ETM_OPT_CTXTID2 is set in this case. + * as VMID, Format attribute 'contextid2' is set in this case. */ switch (cs_etm__get_pid_fmt(etmq)) { case CS_ETM_PIDFMT_CTXTID: diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 95f439c96180..8a639d2e51a4 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -194,7 +194,7 @@ int cs_etm__get_cpu(struct cs_etm_queue *etmq, u8 trace_chan_id, int *cpu) * CS_ETM_PIDFMT_CTXTID2: CONTEXTIDR_EL2 is traced. * CS_ETM_PIDFMT_NONE: No context IDs * - * It's possible that the two bits ETM_OPT_CTXTID and ETM_OPT_CTXTID2 + * It's possible that the two format attributes 'contextid1' and 'contextid2' * are enabled at the same time when the session runs on an EL2 kernel. * This means the CONTEXTIDR_EL1 and CONTEXTIDR_EL2 both will be * recorded in the trace data, the tool will selectively use @@ -210,15 +210,15 @@ static enum cs_etm_pid_fmt cs_etm__init_pid_fmt(u64 *metadata) if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) { val = metadata[CS_ETM_ETMCR]; /* CONTEXTIDR is traced */ - if (val & BIT(ETM_OPT_CTXTID)) + if (val & ETMCR_CTXTID) return CS_ETM_PIDFMT_CTXTID; } else { val = metadata[CS_ETMV4_TRCCONFIGR]; /* CONTEXTIDR_EL2 is traced */ - if (val & (BIT(ETM4_CFG_BIT_VMID) | BIT(ETM4_CFG_BIT_VMID_OPT))) + if (val & (TRCCONFIGR_VMID | TRCCONFIGR_VMIDOPT)) return CS_ETM_PIDFMT_CTXTID2; /* CONTEXTIDR_EL1 is traced */ - else if (val & BIT(ETM4_CFG_BIT_CTXTID)) + else if (val & TRCCONFIGR_CID) return CS_ETM_PIDFMT_CTXTID; } @@ -2914,29 +2914,21 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, return 0; } -static int cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm) +static void cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm) { - struct evsel *evsel; - struct evlist *evlist = etm->session->evlist; + /* Take first ETM as all options will be the same for all ETMs */ + u64 *metadata = etm->metadata[0]; /* Override timeless mode with user input from --itrace=Z */ if (etm->synth_opts.timeless_decoding) { etm->timeless_decoding = true; - return 0; + return; } - /* - * Find the cs_etm evsel and look at what its timestamp setting was - */ - evlist__for_each_entry(evlist, evsel) - if (cs_etm__evsel_is_auxtrace(etm->session, evsel)) { - etm->timeless_decoding = - !(evsel->core.attr.config & BIT(ETM_OPT_TS)); - return 0; - } - - pr_err("CS ETM: Couldn't find ETM evsel\n"); - return -EINVAL; + if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) + etm->timeless_decoding = !(metadata[CS_ETM_ETMCR] & ETMCR_TIMESTAMP_EN); + else + etm->timeless_decoding = !(metadata[CS_ETMV4_TRCCONFIGR] & TRCCONFIGR_TS); } /* @@ -3499,9 +3491,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace; session->auxtrace = &etm->auxtrace; - err = cs_etm__setup_timeless_decoding(etm); - if (err) - return err; + cs_etm__setup_timeless_decoding(etm); etm->tc.time_shift = tc->time_shift; etm->tc.time_mult = tc->time_mult; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index a8caeea720aa..aa9bb4a32eca 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -230,6 +230,21 @@ struct cs_etm_packet_queue { /* CoreSight trace ID is currently the bottom 7 bits of the value */ #define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) +/* ETMv4 CONFIGR register bits */ +#define TRCCONFIGR_BB BIT(3) +#define TRCCONFIGR_CCI BIT(4) +#define TRCCONFIGR_CID BIT(6) +#define TRCCONFIGR_VMID BIT(7) +#define TRCCONFIGR_TS BIT(11) +#define TRCCONFIGR_RS BIT(12) +#define TRCCONFIGR_VMIDOPT BIT(15) + +/* ETMv3 ETMCR register bits */ +#define ETMCR_CYC_ACC BIT(12) +#define ETMCR_CTXTID BIT(14) +#define ETMCR_TIMESTAMP_EN BIT(28) +#define ETMCR_RETURN_STACK BIT(29) + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr); From e3741935a341983885aba1b09c6dfbc9e6ff5466 Mon Sep 17 00:00:00 2001 From: James Clark Date: Fri, 6 Mar 2026 14:08:35 +0000 Subject: [PATCH 306/487] perf cs-etm: Sync coresight-pmu.h header with the kernel sources Update the header to pull in the changes from commit 3285c471d0c0b991 ("coresight: Remove misleading definitions"). Signed-off-by: James Clark Requested-by: Arnaldo Carvalho de Melo Tested-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Link: https://lore.kernel.org/r/557db631-aef8-43b1-9f45-fae75910ccb4@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/coresight-pmu.h | 24 ------------------------ 1 file changed, 24 deletions(-) diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 89b0ac0014b0..2e179abe472a 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -21,30 +21,6 @@ */ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) -/* - * Below are the definition of bit offsets for perf option, and works as - * arbitrary values for all ETM versions. - * - * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore, - * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and - * directly use below macros as config bits. - */ -#define ETM_OPT_BRANCH_BROADCAST 8 -#define ETM_OPT_CYCACC 12 -#define ETM_OPT_CTXTID 14 -#define ETM_OPT_CTXTID2 15 -#define ETM_OPT_TS 28 -#define ETM_OPT_RETSTK 29 - -/* ETMv4 CONFIGR programming bits for the ETM OPTs */ -#define ETM4_CFG_BIT_BB 3 -#define ETM4_CFG_BIT_CYCACC 4 -#define ETM4_CFG_BIT_CTXTID 6 -#define ETM4_CFG_BIT_VMID 7 -#define ETM4_CFG_BIT_TS 11 -#define ETM4_CFG_BIT_RETSTK 12 -#define ETM4_CFG_BIT_VMID_OPT 15 - /* * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. * Used to associate a CPU with the CoreSight Trace ID. From b7cdc5a97d02c943f4bdde4d5767ad0c13cad92b Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 5 Mar 2026 13:01:44 +0100 Subject: [PATCH 307/487] netfilter: nf_tables: Fix for duplicate device in netdev hooks When handling NETDEV_REGISTER notification, duplicate device registration must be avoided since the device may have been added by nft_netdev_hook_alloc() already when creating the hook. Suggested-by: Florian Westphal Reported-by: syzbot+bb9127e278fa198e110c@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=bb9127e278fa198e110c Fixes: a331b78a5525 ("netfilter: nf_tables: Respect NETDEV_REGISTER events") Tested-by: Helen Koike Signed-off-by: Phil Sutter Signed-off-by: Florian Westphal --- net/netfilter/nf_tables_api.c | 2 +- net/netfilter/nft_chain_filter.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1862bd7fe804..710f0ee21a34 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9688,7 +9688,7 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev, break; case NETDEV_REGISTER: /* NOP if not matching or already registered */ - if (!match || (changename && ops)) + if (!match || ops) continue; ops = kzalloc_obj(struct nf_hook_ops, diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index b16185e9a6dd..041426e3bdbf 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -344,7 +344,7 @@ static int nft_netdev_event(unsigned long event, struct net_device *dev, break; case NETDEV_REGISTER: /* NOP if not matching or already registered */ - if (!match || (changename && ops)) + if (!match || ops) continue; ops = kmemdup(&basechain->ops, From 7cb9a23d7ae40a702577d3d8bacb7026f04ac2a9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 5 Mar 2026 21:32:00 +0100 Subject: [PATCH 308/487] netfilter: nf_tables: always walk all pending catchall elements During transaction processing we might have more than one catchall element: 1 live catchall element and 1 pending element that is coming as part of the new batch. If the map holding the catchall elements is also going away, its required to toggle all catchall elements and not just the first viable candidate. Otherwise, we get: WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404 RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables] [..] __nft_set_elem_destroy+0x106/0x380 [nf_tables] nf_tables_abort_release+0x348/0x8d0 [nf_tables] nf_tables_abort+0xcf2/0x3ac0 [nf_tables] nfnetlink_rcv_batch+0x9c9/0x20e0 [..] Fixes: 628bd3e49cba ("netfilter: nf_tables: drop map element references from preparation phase") Reported-by: Yiming Qian Signed-off-by: Florian Westphal --- net/netfilter/nf_tables_api.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 710f0ee21a34..dacec5f8a11c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -829,7 +829,6 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); - break; } } @@ -5873,7 +5872,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); - break; } } From d6d8cd2db236a9dd13dbc2d05843b3445cc964b5 Mon Sep 17 00:00:00 2001 From: Jenny Guanni Qu Date: Fri, 6 Mar 2026 19:12:38 +0000 Subject: [PATCH 309/487] netfilter: nft_set_pipapo: fix stack out-of-bounds read in pipapo_drop() pipapo_drop() passes rulemap[i + 1].n to pipapo_unmap() as the to_offset argument on every iteration, including the last one where i == m->field_count - 1. This reads one element past the end of the stack-allocated rulemap array (declared as rulemap[NFT_PIPAPO_MAX_FIELDS] with NFT_PIPAPO_MAX_FIELDS == 16). Although pipapo_unmap() returns early when is_last is true without using the to_offset value, the argument is evaluated at the call site before the function body executes, making this a genuine out-of-bounds stack read confirmed by KASAN: BUG: KASAN: stack-out-of-bounds in pipapo_drop+0x50c/0x57c [nf_tables] Read of size 4 at addr ffff8000810e71a4 This frame has 1 object: [32, 160) 'rulemap' The buggy address is at offset 164 -- exactly 4 bytes past the end of the rulemap array. Pass 0 instead of rulemap[i + 1].n on the last iteration to avoid the out-of-bounds read. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Jenny Guanni Qu Signed-off-by: Florian Westphal --- net/netfilter/nft_set_pipapo.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index a34632ae6048..7fd24e0cc428 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1640,6 +1640,7 @@ static void pipapo_drop(struct nft_pipapo_match *m, int i; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; int g; for (g = 0; g < f->groups; g++) { @@ -1659,7 +1660,7 @@ static void pipapo_drop(struct nft_pipapo_match *m, } pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n, - rulemap[i + 1].n, i == m->field_count - 1); + last ? 0 : rulemap[i + 1].n, last); if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) { /* We can ignore this, a failure to shrink tables down * doesn't make tables invalid. From cfe770220ac2dbd3e104c6b45094037455da81d4 Mon Sep 17 00:00:00 2001 From: David Dull Date: Sat, 7 Mar 2026 20:26:21 +0200 Subject: [PATCH 310/487] netfilter: x_tables: guard option walkers against 1-byte tail reads When the last byte of options is a non-single-byte option kind, walkers that advance with i += op[i + 1] ? : 1 can read op[i + 1] past the end of the option area. Add an explicit i == optlen - 1 check before dereferencing op[i + 1] in xt_tcpudp and xt_dccp option walkers. Fixes: 2e4e6a17af35 ("[NETFILTER] x_tables: Abstraction layer for {ip,ip6,arp}_tables") Signed-off-by: David Dull Signed-off-by: Florian Westphal --- net/netfilter/xt_dccp.c | 4 ++-- net/netfilter/xt_tcpudp.c | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c index e5a13ecbe67a..037ab93e25d0 100644 --- a/net/netfilter/xt_dccp.c +++ b/net/netfilter/xt_dccp.c @@ -62,10 +62,10 @@ dccp_find_option(u_int8_t option, return true; } - if (op[i] < 2) + if (op[i] < 2 || i == optlen - 1) i++; else - i += op[i+1]?:1; + i += op[i + 1] ? : 1; } spin_unlock_bh(&dccp_buflock); diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c index e8991130a3de..f76cf18f1a24 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -59,8 +59,10 @@ tcp_find_option(u_int8_t option, for (i = 0; i < optlen; ) { if (op[i] == option) return !invert; - if (op[i] < 2) i++; - else i += op[i+1]?:1; + if (op[i] < 2 || i == optlen - 1) + i++; + else + i += op[i + 1] ? : 1; } return invert; From f1ba83755d81c6fc66ac7acd723d238f974091e9 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Sun, 8 Mar 2026 02:24:06 +0900 Subject: [PATCH 311/487] netfilter: nfnetlink_queue: fix entry leak in bridge verdict error path nfqnl_recv_verdict() calls find_dequeue_entry() to remove the queue entry from the queue data structures, taking ownership of the entry. For PF_BRIDGE packets, it then calls nfqa_parse_bridge() to parse VLAN attributes. If nfqa_parse_bridge() returns an error (e.g. NFQA_VLAN present but NFQA_VLAN_TCI missing), the function returns immediately without freeing the dequeued entry or its sk_buff. This leaks the nf_queue_entry, its associated sk_buff, and all held references (net_device refcounts, struct net refcount). Repeated triggering exhausts kernel memory. Fix this by dropping the entry via nfqnl_reinject() with NF_DROP verdict on the error path, consistent with other error handling in this file. Fixes: 8d45ff22f1b4 ("netfilter: bridge: nf queue verdict to use NFQA_VLAN and NFQA_L2HDR") Reviewed-by: David Dull Signed-off-by: Hyunwoo Kim Signed-off-by: Florian Westphal --- net/netfilter/nfnetlink_queue.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 7f5248b5f1ee..47f7f62906e2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1546,8 +1546,10 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, if (entry->state.pf == PF_BRIDGE) { err = nfqa_parse_bridge(entry, nfqa); - if (err < 0) + if (err < 0) { + nfqnl_reinject(entry, NF_DROP); return err; + } } if (nfqa[NFQA_PAYLOAD]) { From 6dcee8496d53165b2d8a5909b3050b62ae71fe89 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Sun, 8 Mar 2026 02:23:34 +0900 Subject: [PATCH 312/487] netfilter: nfnetlink_cthelper: fix OOB read in nfnl_cthelper_dump_table() nfnl_cthelper_dump_table() has a 'goto restart' that jumps to a label inside the for loop body. When the "last" helper saved in cb->args[1] is deleted between dump rounds, every entry fails the (cur != last) check, so cb->args[1] is never cleared. The for loop finishes with cb->args[0] == nf_ct_helper_hsize, and the 'goto restart' jumps back into the loop body bypassing the bounds check, causing an 8-byte out-of-bounds read on nf_ct_helper_hash[nf_ct_helper_hsize]. The 'goto restart' block was meant to re-traverse the current bucket when "last" is no longer found, but it was placed after the for loop instead of inside it. Move the block into the for loop body so that the restart only occurs while cb->args[0] is still within bounds. BUG: KASAN: slab-out-of-bounds in nfnl_cthelper_dump_table+0x9f/0x1b0 Read of size 8 at addr ffff888104ca3000 by task poc_cthelper/131 Call Trace: nfnl_cthelper_dump_table+0x9f/0x1b0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 sock_recvmsg+0xde/0xf0 __sys_recvfrom+0x150/0x200 __x64_sys_recvfrom+0x76/0x90 do_syscall_64+0xc3/0x6e0 Allocated by task 1: __kvmalloc_node_noprof+0x21b/0x700 nf_ct_alloc_hashtable+0x65/0xd0 nf_conntrack_helper_init+0x21/0x60 nf_conntrack_init_start+0x18d/0x300 nf_conntrack_standalone_init+0x12/0xc0 Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure") Signed-off-by: Hyunwoo Kim Signed-off-by: Florian Westphal --- net/netfilter/nfnetlink_cthelper.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index d658b1478fa0..d545fa459455 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -601,10 +601,10 @@ nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb) goto out; } } - } - if (cb->args[1]) { - cb->args[1] = 0; - goto restart; + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } } out: rcu_read_unlock(); From 329f0b9b48ee6ab59d1ab72fef55fe8c6463a6cf Mon Sep 17 00:00:00 2001 From: Yuan Tan Date: Mon, 9 Mar 2026 03:41:46 -0700 Subject: [PATCH 313/487] netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM timer labels IDLETIMER revision 0 rules reuse existing timers by label and always call mod_timer() on timer->timer. If the label was created first by revision 1 with XT_IDLETIMER_ALARM, the object uses alarm timer semantics and timer->timer is never initialized. Reusing that object from revision 0 causes mod_timer() on an uninitialized timer_list, triggering debugobjects warnings and possible panic when panic_on_warn=1. Fix this by rejecting revision 0 rule insertion when an existing timer with the same label is of ALARM type. Fixes: 68983a354a65 ("netfilter: xtables: Add snapshot of hardidletimer target") Co-developed-by: Yifan Wu Signed-off-by: Yifan Wu Co-developed-by: Juefei Pu Signed-off-by: Juefei Pu Signed-off-by: Yuan Tan Signed-off-by: Xin Liu Signed-off-by: Florian Westphal --- net/netfilter/xt_IDLETIMER.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 5d93e225d0f8..517106165ad2 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -318,6 +318,12 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) info->timer = __idletimer_tg_find_by_label(info->label); if (info->timer) { + if (info->timer->timer_type & XT_IDLETIMER_ALARM) { + pr_debug("Adding/Replacing rule with same label and different timer type is not allowed\n"); + mutex_unlock(&list_mutex); + return -EINVAL; + } + info->timer->refcnt++; mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); From bf29cb3641b80bac759c3332b02e0b270e16bf94 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Fri, 6 Mar 2026 11:56:48 +0800 Subject: [PATCH 314/487] perf annotate: Fix hashmap__new() error checking The hashmap__new() function never returns NULL, it returns error pointers. Fix the error checking to match. Additionally, set src->samples to NULL to prevent any later code from accidentally using the error pointer. Fixes: d3e7cad6f36d9e80 ("perf annotate: Add a hashmap for symbol histogram") Reviewed-by: Ian Rogers Signed-off-by: Chen Ni Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Tianyou Li Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 2e3522905046..63f0ee9d4c03 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -44,6 +44,7 @@ #include "strbuf.h" #include #include +#include #include #include #include @@ -137,8 +138,10 @@ static int annotated_source__alloc_histograms(struct annotated_source *src, return -1; src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL); - if (src->samples == NULL) + if (IS_ERR(src->samples)) { zfree(&src->histograms); + src->samples = NULL; + } return src->histograms ? 0 : -1; } From 6ab3532b4c98f4e51969f0e5f3fc919c535f3ce1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 9 Mar 2026 21:54:17 +0100 Subject: [PATCH 315/487] ACPI: video: Switch over to auxiliary bus type Commit 02c057ddefef ("ACPI: video: Convert the driver to a platform one") switched over the ACPI video bus driver from an ACPI driver to a platform driver, but that change introduced an unwanted and unexpected side effect. Namely, on some systems, the ACPI device object of the ACPI video bus device is an ACPI companion of multiple platform devices and, after adding video_device_ids[] as an acpi_match_table to the acpi_video_bus platform driver, all of those devices started to match that driver and its probe callback is invoked for all of them (it fails, but it leaves a confusing message in the log). Moreover, the MODULE_DEVICE_TABLE() of the ACPI video driver module matches all of the devices sharing the ACPI companion with the ACPI video bus device. To address this, make the core ACPI device enumeration code create an auxiliary device for the ACPI video bus device object instead of a platform device and switch over the ACPI video bus driver (once more) to an auxiliary driver. Auxiliary driver generally is a better match for ACPI video bus than platform driver, among other things because the ACPI video bus device does not require any resources to be allocated for it during enumeration. It also allows the ACPI video bus driver to stop abusing device matching based on ACPI device IDs and it allows a special case to be dropped from acpi_create_platform_device() because that function need not worry about the ACPI video bus device any more. Fixes: 02c057ddefef ("ACPI: video: Convert the driver to a platform one") Reported-by: Pratap Nirujogi Closes: https://lore.kernel.org/linux-acpi/007e3390-6b2b-457e-83c7-c794c5952018@amd.com/ Tested-by: Pratap Nirujogi Signed-off-by: Rafael J. Wysocki Reviewed-by: Mario Limonciello (AMD) [ rjw: Added AUXILIARY_BUS selection to CONFIG_ACPI to fix build issue ] [ rjw: Fixed error path in acpi_create_video_bus_device() ] Link: https://patch.msgid.link/5986516.DvuYhMxLoT@rafael.j.wysocki Signed-off-by: Rafael J. Wysocki --- drivers/acpi/Kconfig | 1 + drivers/acpi/acpi_platform.c | 2 +- drivers/acpi/acpi_video.c | 45 ++++++++++++++++++------------------ drivers/acpi/scan.c | 45 ++++++++++++++++++++++++++++++++++++ 4 files changed, 69 insertions(+), 24 deletions(-) diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index df0ff0764d0d..6f4b545f7377 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -9,6 +9,7 @@ config ARCH_SUPPORTS_ACPI menuconfig ACPI bool "ACPI (Advanced Configuration and Power Interface) Support" depends on ARCH_SUPPORTS_ACPI + select AUXILIARY_BUS select PNP select NLS select CRC32 diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index 64199b19ceff..a09636a4168e 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -135,7 +135,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev, } } - if (adev->device_type == ACPI_BUS_TYPE_DEVICE && !adev->pnp.type.backlight) { + if (adev->device_type == ACPI_BUS_TYPE_DEVICE) { LIST_HEAD(resource_list); count = acpi_dev_get_resources(adev, &resource_list, NULL, NULL); diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 3fa28f1abca3..adbaf0226c90 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "ACPI: video: " fmt +#include #include #include #include @@ -21,7 +22,6 @@ #include #include #include -#include #include #include #include @@ -77,8 +77,9 @@ static int register_count; static DEFINE_MUTEX(register_count_mutex); static DEFINE_MUTEX(video_list_lock); static LIST_HEAD(video_bus_head); -static int acpi_video_bus_probe(struct platform_device *pdev); -static void acpi_video_bus_remove(struct platform_device *pdev); +static int acpi_video_bus_probe(struct auxiliary_device *aux_dev, + const struct auxiliary_device_id *id); +static void acpi_video_bus_remove(struct auxiliary_device *aux); static void acpi_video_bus_notify(acpi_handle handle, u32 event, void *data); /* @@ -93,19 +94,16 @@ enum acpi_video_level_idx { ACPI_VIDEO_FIRST_LEVEL, /* actual supported levels begin here */ }; -static const struct acpi_device_id video_device_ids[] = { - {ACPI_VIDEO_HID, 0}, - {"", 0}, +static const struct auxiliary_device_id video_bus_auxiliary_id_table[] = { + { .name = "acpi.video_bus" }, + {}, }; -MODULE_DEVICE_TABLE(acpi, video_device_ids); +MODULE_DEVICE_TABLE(auxiliary, video_bus_auxiliary_id_table); -static struct platform_driver acpi_video_bus = { +static struct auxiliary_driver acpi_video_bus = { .probe = acpi_video_bus_probe, .remove = acpi_video_bus_remove, - .driver = { - .name = "acpi-video", - .acpi_match_table = video_device_ids, - }, + .id_table = video_bus_auxiliary_id_table, }; struct acpi_video_bus_flags { @@ -1885,7 +1883,7 @@ static void acpi_video_dev_add_notify_handler(struct acpi_video_device *device) } static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video, - struct platform_device *pdev) + struct device *parent) { struct input_dev *input; struct acpi_video_device *dev; @@ -1908,7 +1906,7 @@ static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video, input->phys = video->phys; input->id.bustype = BUS_HOST; input->id.product = 0x06; - input->dev.parent = &pdev->dev; + input->dev.parent = parent; input->evbit[0] = BIT(EV_KEY); set_bit(KEY_SWITCHVIDEOMODE, input->keybit); set_bit(KEY_VIDEO_NEXT, input->keybit); @@ -1980,9 +1978,10 @@ static int acpi_video_bus_put_devices(struct acpi_video_bus *video) static int instance; -static int acpi_video_bus_probe(struct platform_device *pdev) +static int acpi_video_bus_probe(struct auxiliary_device *aux_dev, + const struct auxiliary_device_id *id_unused) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev); struct acpi_video_bus *video; bool auto_detect; int error; @@ -2019,7 +2018,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev) instance++; } - platform_set_drvdata(pdev, video); + auxiliary_set_drvdata(aux_dev, video); video->device = device; strscpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME); @@ -2068,7 +2067,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev) !auto_detect) acpi_video_bus_register_backlight(video); - error = acpi_video_bus_add_notify_handler(video, pdev); + error = acpi_video_bus_add_notify_handler(video, &aux_dev->dev); if (error) goto err_del; @@ -2096,10 +2095,10 @@ static int acpi_video_bus_probe(struct platform_device *pdev) return error; } -static void acpi_video_bus_remove(struct platform_device *pdev) +static void acpi_video_bus_remove(struct auxiliary_device *aux_dev) { - struct acpi_video_bus *video = platform_get_drvdata(pdev); - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_video_bus *video = auxiliary_get_drvdata(aux_dev); + struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev); acpi_dev_remove_notify_handler(device, ACPI_DEVICE_NOTIFY, acpi_video_bus_notify); @@ -2163,7 +2162,7 @@ int acpi_video_register(void) dmi_check_system(video_dmi_table); - ret = platform_driver_register(&acpi_video_bus); + ret = auxiliary_driver_register(&acpi_video_bus); if (ret) goto leave; @@ -2183,7 +2182,7 @@ void acpi_video_unregister(void) { mutex_lock(®ister_count_mutex); if (register_count) { - platform_driver_unregister(&acpi_video_bus); + auxiliary_driver_unregister(&acpi_video_bus); register_count = 0; may_report_brightness_keys = false; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index dfdd004fb1a9..e8cdbdb46fdb 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) "ACPI: " fmt #include +#include #include #include #include @@ -2192,6 +2193,44 @@ static acpi_status acpi_bus_check_add_2(acpi_handle handle, u32 lvl_not_used, return acpi_bus_check_add(handle, false, (struct acpi_device **)ret_p); } +static void acpi_video_bus_device_release(struct device *dev) +{ + struct auxiliary_device *aux_dev = to_auxiliary_dev(dev); + + kfree(aux_dev); +} + +static void acpi_create_video_bus_device(struct acpi_device *adev, + struct acpi_device *parent) +{ + struct auxiliary_device *aux_dev; + static unsigned int aux_dev_id; + + aux_dev = kzalloc_obj(*aux_dev); + if (!aux_dev) + return; + + aux_dev->id = aux_dev_id++; + aux_dev->name = "video_bus"; + aux_dev->dev.parent = acpi_get_first_physical_node(parent); + if (!aux_dev->dev.parent) + goto err; + + aux_dev->dev.release = acpi_video_bus_device_release; + + if (auxiliary_device_init(aux_dev)) + goto err; + + ACPI_COMPANION_SET(&aux_dev->dev, adev); + if (__auxiliary_device_add(aux_dev, "acpi")) + auxiliary_device_uninit(aux_dev); + + return; + +err: + kfree(aux_dev); +} + struct acpi_scan_system_dev { struct list_head node; struct acpi_device *adev; @@ -2229,6 +2268,12 @@ static void acpi_default_enumeration(struct acpi_device *device) sd->adev = device; list_add_tail(&sd->node, &acpi_scan_system_dev_list); } + } else if (device->pnp.type.backlight) { + struct acpi_device *parent; + + parent = acpi_dev_parent(device); + if (parent) + acpi_create_video_bus_device(device, parent); } else { /* For a regular device object, create a platform device. */ acpi_create_platform_device(device, NULL); From e53c0e99fd93da200c413deb57875f9f5fdb314a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 7 Mar 2026 09:50:35 +0000 Subject: [PATCH 316/487] spi: cadence-qspi: Fix requesting of APB and AHB clocks on JH7110 The move of the AHB and APB clocks from a JH7110 specific quirk to the main clock init dropped the specification of the clock names to request for the AHB and APB clocks, resulting in the clock framework requesting a clock with a NULL name three times. On most platforms where the clocks are physically the same or some are always on this makes no difference but the reason we had the specific quirk for JH7110 is that it does actually have separate, controllable clocks. Update the new code to request the AHB and APB clocks by name to restore the original behaviour on JH7110. Fixes: 324ecc7788c2 ("spi: cadence-qspi: Kill cqspi_jh7110_clk_init") Reported-by: Ron Economos Closes: https://lore.kernel.org/r/a3ca5e9b-7446-497e-8df2-7ef2b42a02e9@w6rz.net Tested-by: Ron Economos Link: https://patch.msgid.link/20260307-spi-cadence-qspi-fix-jh7110-v1-1-c9f37b8c58b1@kernel.org Signed-off-by: Mark Brown Link: https://patch.msgid.link/20260307-spi-cadence-qspi-fix-jh7110-v1-1-c9f37b8c58b1@kernel.org --- drivers/spi/spi-cadence-quadspi.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 649ff55333f0..5fb0cb07c110 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -76,6 +76,11 @@ struct cqspi_flash_pdata { u8 cs; }; +static const struct clk_bulk_data cqspi_clks[CLK_QSPI_NUM] = { + [CLK_QSPI_APB] = { .id = "apb" }, + [CLK_QSPI_AHB] = { .id = "ahb" }, +}; + struct cqspi_st { struct platform_device *pdev; struct spi_controller *host; @@ -1823,6 +1828,7 @@ static int cqspi_probe(struct platform_device *pdev) } /* Obtain QSPI clocks. */ + memcpy(&cqspi->clks, &cqspi_clks, sizeof(cqspi->clks)); ret = devm_clk_bulk_get_optional(dev, CLK_QSPI_NUM, cqspi->clks); if (ret) return dev_err_probe(dev, ret, "Failed to get clocks\n"); From 5d0efaf47ee90ac60efae790acee3a3ed99ebf80 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Tue, 10 Mar 2026 12:25:52 +0800 Subject: [PATCH 317/487] regulator: pca9450: Correct interrupt type Kernel warning on i.MX8MP-EVK when doing module test: irq: type mismatch, failed to map hwirq-3 for gpio@30200000! Per PCA945[X] specification: The IRQ_B pin is pulled low when any unmasked interrupt bit status is changed and it is released high once application processor read INT1 register. So the interrupt should be configured as IRQF_TRIGGER_LOW, not IRQF_TRIGGER_FALLING. Fixes: 0935ff5f1f0a4 ("regulator: pca9450: add pca9450 pmic driver") Signed-off-by: Peng Fan Link: https://patch.msgid.link/20260310-pca9450-irq-v1-1-36adf52c2c55@nxp.com Signed-off-by: Mark Brown --- drivers/regulator/pca9450-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 5fa868264250..2205f6de37e7 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -1369,7 +1369,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) if (pca9450->irq) { ret = devm_request_threaded_irq(pca9450->dev, pca9450->irq, NULL, pca9450_irq_handler, - (IRQF_TRIGGER_FALLING | IRQF_ONESHOT), + (IRQF_TRIGGER_LOW | IRQF_ONESHOT), "pca9450-irq", pca9450); if (ret != 0) return dev_err_probe(pca9450->dev, ret, "Failed to request IRQ: %d\n", From 21b3fb7dc19caa488d285e3c47999f7f1a179334 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Tue, 10 Mar 2026 12:25:53 +0800 Subject: [PATCH 318/487] regulator: pca9450: Correct probed name for PCA9452 An incorrect device name was logged for PCA9452 because the dev_info() ternary omitted PCA9452 and fell through to "pca9450bc". Introduce a type_name and set it per device type so the probed message matches the actual PMIC. While here, make the PCA9451A case explicit. No functional changes. Fixes: 017b76fb8e5b6 ("regulator: pca9450: Add PMIC pca9452 support") Signed-off-by: Peng Fan Link: https://patch.msgid.link/20260310-pca9450-irq-v1-2-36adf52c2c55@nxp.com Signed-off-by: Mark Brown --- drivers/regulator/pca9450-regulator.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 2205f6de37e7..45d7dc44c2cd 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -1293,6 +1293,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) struct regulator_dev *ldo5; struct pca9450 *pca9450; unsigned int device_id, i; + const char *type_name; int ret; pca9450 = devm_kzalloc(&i2c->dev, sizeof(struct pca9450), GFP_KERNEL); @@ -1303,15 +1304,22 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) case PCA9450_TYPE_PCA9450A: regulator_desc = pca9450a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9450a_regulators); + type_name = "pca9450a"; break; case PCA9450_TYPE_PCA9450BC: regulator_desc = pca9450bc_regulators; pca9450->rcnt = ARRAY_SIZE(pca9450bc_regulators); + type_name = "pca9450bc"; break; case PCA9450_TYPE_PCA9451A: + regulator_desc = pca9451a_regulators; + pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); + type_name = "pca9451a"; + break; case PCA9450_TYPE_PCA9452: regulator_desc = pca9451a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); + type_name = "pca9452"; break; default: dev_err(&i2c->dev, "Unknown device type"); @@ -1413,9 +1421,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) pca9450_i2c_restart_handler, pca9450)) dev_warn(&i2c->dev, "Failed to register restart handler\n"); - dev_info(&i2c->dev, "%s probed.\n", - type == PCA9450_TYPE_PCA9450A ? "pca9450a" : - (type == PCA9450_TYPE_PCA9451A ? "pca9451a" : "pca9450bc")); + dev_info(&i2c->dev, "%s probed.\n", type_name); return 0; } From be34705aa527872e5ce83927b7bc9307ba8095ca Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Fri, 6 Mar 2026 12:10:52 +0800 Subject: [PATCH 319/487] perf ftrace: Fix hashmap__new() error checking The hashmap__new() function never returns NULL, it returns error pointers. Fix the error checking to match. Additionally, set ftrace->profile_hash to NULL on error, and return the exact error code from hashmap__new(). Fixes: 0f223813edd051a5 ("perf ftrace: Add 'profile' command") Suggested-by: Ian Rogers Signed-off-by: Chen Ni Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-ftrace.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 6b6eec65f93f..4cc33452d79b 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -1209,8 +1210,12 @@ static int prepare_func_profile(struct perf_ftrace *ftrace) ftrace->graph_verbose = 0; ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL); - if (ftrace->profile_hash == NULL) - return -ENOMEM; + if (IS_ERR(ftrace->profile_hash)) { + int err = PTR_ERR(ftrace->profile_hash); + + ftrace->profile_hash = NULL; + return err; + } return 0; } From 40e9cd4ae8ec43b107ed2bff422a8fa39dcf4e4b Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 10 Mar 2026 15:23:29 +0100 Subject: [PATCH 320/487] s390/dasd: Move quiesce state with pprc swap Quiesce and resume is a mechanism to suspend operations on DASD devices. In the context of a controlled copy pair swap operation, the quiesce operation is usually issued before the actual swap and a resume afterwards. During the swap operation, the underlying device is exchanged. Therefore, the quiesce flag must be moved to the secondary device to ensure a consistent quiesce state after the swap. The secondary device itself cannot be suspended separately because there is no separate block device representation for it. Fixes: 413862caad6f ("s390/dasd: add copy pair swap capability") Cc: stable@vger.kernel.org #6.1 Reviewed-by: Jan Hoeppner Signed-off-by: Stefan Haberland Link: https://patch.msgid.link/20260310142330.4080106-2-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_eckd.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index b08e900687f3..e8f0e302a625 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -6182,6 +6182,11 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid dev_name(&secondary->cdev->dev), rc); } + if (primary->stopped & DASD_STOPPED_QUIESCE) { + dasd_device_set_stop_bits(secondary, DASD_STOPPED_QUIESCE); + dasd_device_remove_stop_bits(primary, DASD_STOPPED_QUIESCE); + } + /* re-enable device */ dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC); dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC); From 4c527c7e030672efd788d0806d7a68972a7ba3c1 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 10 Mar 2026 15:23:30 +0100 Subject: [PATCH 321/487] s390/dasd: Copy detected format information to secondary device During online processing for a DASD device an IO operation is started to determine the format of the device. CDL format contains specifically sized blocks at the beginning of the disk. For a PPRC secondary device no real IO operation is possible therefore this IO request can not be started and this step is skipped for online processing of secondary devices. This is generally fine since the secondary is a copy of the primary device. In case of an additional partition detection that is run after a swap operation the format information is needed to properly drive partition detection IO. Currently the information is not passed leading to IO errors during partition detection and a wrongly detected partition table which in turn might lead to data corruption on the disk with the wrong partition table. Fix by passing the format information from primary to secondary device. Fixes: 413862caad6f ("s390/dasd: add copy pair swap capability") Cc: stable@vger.kernel.org #6.1 Reviewed-by: Jan Hoeppner Acked-by: Eduard Shishkin Signed-off-by: Stefan Haberland Link: https://patch.msgid.link/20260310142330.4080106-3-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_eckd.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index e8f0e302a625..c0f665a2929d 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -6135,6 +6135,7 @@ static void copy_pair_set_active(struct dasd_copy_relation *copy, char *new_busi static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid, char *sec_busid) { + struct dasd_eckd_private *prim_priv, *sec_priv; struct dasd_device *primary, *secondary; struct dasd_copy_relation *copy; struct dasd_block *block; @@ -6155,6 +6156,9 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid if (!secondary) return DASD_COPYPAIRSWAP_SECONDARY; + prim_priv = primary->private; + sec_priv = secondary->private; + /* * usually the device should be quiesced for swap * for paranoia stop device and requeue requests again @@ -6187,6 +6191,13 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid dasd_device_remove_stop_bits(primary, DASD_STOPPED_QUIESCE); } + /* + * The secondary device never got through format detection, but since it + * is a copy of the primary device, the format is exactly the same; + * therefore, the detected layout can simply be copied. + */ + sec_priv->uses_cdl = prim_priv->uses_cdl; + /* re-enable device */ dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC); dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC); From d557640e4ce589a24dca5ca7ce3b9680f471325f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 7 Mar 2026 17:12:05 +0100 Subject: [PATCH 322/487] sched: idle: Make skipping governor callbacks more consistent If the cpuidle governor .select() callback is skipped because there is only one idle state in the cpuidle driver, the .reflect() callback should be skipped as well, at least for consistency (if not for correctness), so do it. Fixes: e5c9ffc6ae1b ("cpuidle: Skip governor when only one idle state is available") Signed-off-by: Rafael J. Wysocki Reviewed-by: Christian Loehle Reviewed-by: Aboorva Devarajan Reviewed-by: Frederic Weisbecker Link: https://patch.msgid.link/12857700.O9o76ZdvQC@rafael.j.wysocki --- drivers/cpuidle/cpuidle.c | 10 ---------- kernel/sched/idle.c | 11 ++++++++++- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 65fbb8e807b9..c7876e9e024f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -359,16 +359,6 @@ noinstr int cpuidle_enter_state(struct cpuidle_device *dev, int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, bool *stop_tick) { - /* - * If there is only a single idle state (or none), there is nothing - * meaningful for the governor to choose. Skip the governor and - * always use state 0 with the tick running. - */ - if (drv->state_count <= 1) { - *stop_tick = false; - return 0; - } - return cpuidle_curr_governor->select(drv, dev, stop_tick); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 3681b6ad9276..b95449165122 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -221,7 +221,7 @@ static void cpuidle_idle_call(void) next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns); call_cpuidle(drv, dev, next_state); - } else { + } else if (drv->state_count > 1) { bool stop_tick = true; /* @@ -239,6 +239,15 @@ static void cpuidle_idle_call(void) * Give the governor an opportunity to reflect on the outcome */ cpuidle_reflect(dev, entered_state); + } else { + tick_nohz_idle_retain_tick(); + + /* + * If there is only a single idle state (or none), there is + * nothing meaningful for the governor to choose. Skip the + * governor and always use state 0. + */ + call_cpuidle(drv, dev, 0); } exit_idle: From c7c92f76f90a81dcc5c48cefa3343556501870b9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 6 Mar 2026 10:53:06 -0800 Subject: [PATCH 323/487] perf annotate loongarch: Fix off-by-one bug in outside check A copy-paste of a similar issue fixed by Peter Collingbourne in: https://lore.kernel.org/linux-perf-users/20260304190613.2507582-1-pcc@google.com/ Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Bill Wendling Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Justin Stitt Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Collingbourne Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate-arch/annotate-loongarch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/annotate-arch/annotate-loongarch.c b/tools/perf/util/annotate-arch/annotate-loongarch.c index 3aeab453a059..950f34e59e5c 100644 --- a/tools/perf/util/annotate-arch/annotate-loongarch.c +++ b/tools/perf/util/annotate-arch/annotate-loongarch.c @@ -93,7 +93,7 @@ static int loongarch_jump__parse(const struct arch *arch, struct ins_operands *o start = map__unmap_ip(map, sym->start); end = map__unmap_ip(map, sym->end); - ops->target.outside = target.addr < start || target.addr > end; + ops->target.outside = target.addr < start || target.addr >= end; if (maps__find_ams(thread__maps(ms->thread), &target) == 0 && map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) From 52a8a1ba883defbfe3200baa22cf4cd21985d51a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 4 Mar 2026 20:26:20 -0800 Subject: [PATCH 324/487] xfs: fix undersized l_iclog_roundoff values If the superblock doesn't list a log stripe unit, we set the incore log roundoff value to 512. This leads to corrupt logs and unmountable filesystems in generic/617 on a disk with 4k physical sectors... XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c XFS (sda1): Torn write (CRC failure) detected at log block 0x318e. Truncating head block from 0x3197. XFS (sda1): failed to locate log tail XFS (sda1): log mount/recovery failed: error -74 XFS (sda1): log mount failed XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c XFS (sda1): Ending clean mount ...on the current xfsprogs for-next which has a broken mkfs. xfs_info shows this... meta-data=/dev/sda1 isize=512 agcount=4, agsize=644992 blks = sectsz=4096 attr=2, projid32bit=1 = crc=1 finobt=1, sparse=1, rmapbt=1 = reflink=1 bigtime=1 inobtcount=1 nrext64=1 = exchange=1 metadir=1 data = bsize=4096 blocks=2579968, imaxpct=25 = sunit=0 swidth=0 blks naming =version 2 bsize=4096 ascii-ci=0, ftype=1, parent=1 log =internal log bsize=4096 blocks=16384, version=2 = sectsz=4096 sunit=0 blks, lazy-count=1 realtime =none extsz=4096 blocks=0, rtextents=0 = rgcount=0 rgsize=268435456 extents = zoned=0 start=0 reserved=0 ...observe that the log section has sectsz=4096 sunit=0, which means that the roundoff factor is 512, not 4096 as you'd expect. We should fix mkfs not to generate broken filesystems, but anyone can fuzz the ondisk superblock so we should be more cautious. I think the inadequate logic predates commit a6a65fef5ef8d0, but that's clearly going to require a different backport. Cc: stable@vger.kernel.org # v5.14 Fixes: a6a65fef5ef8d0 ("xfs: log stripe roundoff is a property of the log") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_log.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index b96f262ba139..f807f8f4f705 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1357,6 +1357,8 @@ xlog_alloc_log( if (xfs_has_logv2(mp) && mp->m_sb.sb_logsunit > 1) log->l_iclog_roundoff = mp->m_sb.sb_logsunit; + else if (mp->m_sb.sb_logsectsize > 0) + log->l_iclog_roundoff = mp->m_sb.sb_logsectsize; else log->l_iclog_roundoff = BBSIZE; From b4e78f1427c7d6859229ae9616df54e1fc05a516 Mon Sep 17 00:00:00 2001 From: Sungwoo Kim Date: Sun, 8 Mar 2026 14:20:59 -0400 Subject: [PATCH 325/487] nvme-pci: Fix slab-out-of-bounds in nvme_dbbuf_set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dev->online_queues is a count incremented in nvme_init_queue. Thus, valid indices are 0 through dev->online_queues − 1. This patch fixes the loop condition to ensure the index stays within the valid range. Index 0 is excluded because it is the admin queue. KASAN splat: ================================================================== BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline] BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404 Read of size 2 at addr ffff88800592a574 by task kworker/u8:5/74 CPU: 0 UID: 0 PID: 74 Comm: kworker/u8:5 Not tainted 6.19.0-dirty #10 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 Workqueue: nvme-reset-wq nvme_reset_work Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xea/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xce/0x5d0 mm/kasan/report.c:482 kasan_report+0xdc/0x110 mm/kasan/report.c:595 __asan_report_load2_noabort+0x18/0x20 mm/kasan/report_generic.c:379 nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline] nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404 nvme_reset_work+0x36b/0x8c0 drivers/nvme/host/pci.c:3252 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257 process_scheduled_works kernel/workqueue.c:3340 [inline] worker_thread+0x65c/0xe60 kernel/workqueue.c:3421 kthread+0x41a/0x930 kernel/kthread.c:463 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 Allocated by task 34 on cpu 1 at 4.241550s: kasan_save_stack+0x2c/0x60 mm/kasan/common.c:57 kasan_save_track+0x1c/0x70 mm/kasan/common.c:78 kasan_save_alloc_info+0x3c/0x50 mm/kasan/generic.c:570 poison_kmalloc_redzone mm/kasan/common.c:398 [inline] __kasan_kmalloc+0xb5/0xc0 mm/kasan/common.c:415 kasan_kmalloc include/linux/kasan.h:263 [inline] __do_kmalloc_node mm/slub.c:5657 [inline] __kmalloc_node_noprof+0x2bf/0x8d0 mm/slub.c:5663 kmalloc_array_node_noprof include/linux/slab.h:1075 [inline] nvme_pci_alloc_dev drivers/nvme/host/pci.c:3479 [inline] nvme_probe+0x2f1/0x1820 drivers/nvme/host/pci.c:3534 local_pci_probe+0xef/0x1c0 drivers/pci/pci-driver.c:324 pci_call_probe drivers/pci/pci-driver.c:392 [inline] __pci_device_probe drivers/pci/pci-driver.c:417 [inline] pci_device_probe+0x743/0x920 drivers/pci/pci-driver.c:451 call_driver_probe drivers/base/dd.c:583 [inline] really_probe+0x29b/0xb70 drivers/base/dd.c:661 __driver_probe_device+0x3b0/0x4a0 drivers/base/dd.c:803 driver_probe_device+0x56/0x1f0 drivers/base/dd.c:833 __driver_attach_async_helper+0x155/0x340 drivers/base/dd.c:1159 async_run_entry_fn+0xa6/0x4b0 kernel/async.c:129 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257 process_scheduled_works kernel/workqueue.c:3340 [inline] worker_thread+0x65c/0xe60 kernel/workqueue.c:3421 kthread+0x41a/0x930 kernel/kthread.c:463 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 The buggy address belongs to the object at ffff88800592a000 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 244 bytes to the right of allocated 1152-byte region [ffff88800592a000, ffff88800592a480) The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5928 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 anon flags: 0xfffffc0000040(head|node=0|zone=1|lastcpupid=0x1fffff) page_type: f5(slab) raw: 000fffffc0000040 ffff888001042000 0000000000000000 dead000000000001 raw: 0000000000000000 0000000000080008 00000000f5000000 0000000000000000 head: 000fffffc0000040 ffff888001042000 0000000000000000 dead000000000001 head: 0000000000000000 0000000000080008 00000000f5000000 0000000000000000 head: 000fffffc0000003 ffffea0000164a01 00000000ffffffff 00000000ffffffff head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000008 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88800592a400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff88800592a480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88800592a500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff88800592a580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88800592a600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Fixes: 0f0d2c876c96 (nvme: free sq/cq dbbuf pointers when dbbuf set fails) Acked-by: Chao Shi Acked-by: Weidong Zhu Acked-by: Dave Tian Signed-off-by: Sungwoo Kim Signed-off-by: Keith Busch --- drivers/nvme/host/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9a7863e2001e..d90db12c7cd8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -544,7 +544,7 @@ static void nvme_dbbuf_set(struct nvme_dev *dev) /* Free memory and continue on */ nvme_dbbuf_dma_free(dev); - for (i = 1; i <= dev->online_queues; i++) + for (i = 1; i < dev->online_queues; i++) nvme_dbbuf_free(&dev->queues[i]); } } From 2922e3507f6d5caa7f1d07f145e186fc6f317a4e Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 25 Feb 2026 20:30:03 -0800 Subject: [PATCH 326/487] nvmet: move async event work off nvmet-wq For target nvmet_ctrl_free() flushes ctrl->async_event_work. If nvmet_ctrl_free() runs on nvmet-wq, the flush re-enters workqueue completion for the same worker:- A. Async event work queued on nvmet-wq (prior to disconnect): nvmet_execute_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) nvmet_add_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) B. Full pre-work chain (RDMA CM path): nvmet_rdma_cm_handler() nvmet_rdma_queue_disconnect() __nvmet_rdma_queue_disconnect() queue_work(nvmet_wq, &queue->release_work) process_one_work() lock((wq_completion)nvmet-wq) <--------- 1st nvmet_rdma_release_queue_work() C. Recursive path (same worker): nvmet_rdma_release_queue_work() nvmet_rdma_free_queue() nvmet_sq_destroy() nvmet_ctrl_put() nvmet_ctrl_free() flush_work(&ctrl->async_event_work) __flush_work() touch_wq_lockdep_map() lock((wq_completion)nvmet-wq) <--------- 2nd Lockdep splat: ============================================ WARNING: possible recursive locking detected 6.19.0-rc3nvme+ #14 Tainted: G N -------------------------------------------- kworker/u192:42/44933 is trying to acquire lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90 but task is already holding lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 3 locks held by kworker/u192:42/44933: #0: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 #1: ffffc9000e6cbe28 ((work_completion)(&queue->release_work)){+.+.}-{0:0}, at: process_one_work+0x1c5/0x660 #2: ffffffff82d4db60 (rcu_read_lock){....}-{1:3}, at: __flush_work+0x62/0x530 Workqueue: nvmet-wq nvmet_rdma_release_queue_work [nvmet_rdma] Call Trace: __flush_work+0x268/0x530 nvmet_ctrl_free+0x140/0x310 [nvmet] nvmet_cq_put+0x74/0x90 [nvmet] nvmet_rdma_free_queue+0x23/0xe0 [nvmet_rdma] nvmet_rdma_release_queue_work+0x19/0x50 [nvmet_rdma] process_one_work+0x206/0x660 worker_thread+0x184/0x320 kthread+0x10c/0x240 ret_from_fork+0x319/0x390 Move async event work to a dedicated nvmet-aen-wq to avoid reentrant flush on nvmet-wq. Reviewed-by: Christoph Hellwig Signed-off-by: Chaitanya Kulkarni Signed-off-by: Keith Busch --- drivers/nvme/target/admin-cmd.c | 2 +- drivers/nvme/target/core.c | 14 ++++++++++++-- drivers/nvme/target/nvmet.h | 1 + drivers/nvme/target/rdma.c | 1 + 4 files changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 5e366502fb75..66fc8d2a7fe3 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -1586,7 +1586,7 @@ void nvmet_execute_async_event(struct nvmet_req *req) ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req; mutex_unlock(&ctrl->lock); - queue_work(nvmet_wq, &ctrl->async_event_work); + queue_work(nvmet_aen_wq, &ctrl->async_event_work); } void nvmet_execute_keep_alive(struct nvmet_req *req) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index eab3e4fc0f74..a25ac4bf9972 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -27,6 +27,8 @@ static DEFINE_IDA(cntlid_ida); struct workqueue_struct *nvmet_wq; EXPORT_SYMBOL_GPL(nvmet_wq); +struct workqueue_struct *nvmet_aen_wq; +EXPORT_SYMBOL_GPL(nvmet_aen_wq); /* * This read/write semaphore is used to synchronize access to configuration @@ -206,7 +208,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, list_add_tail(&aen->entry, &ctrl->async_events); mutex_unlock(&ctrl->lock); - queue_work(nvmet_wq, &ctrl->async_event_work); + queue_work(nvmet_aen_wq, &ctrl->async_event_work); } static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid) @@ -1959,9 +1961,14 @@ static int __init nvmet_init(void) if (!nvmet_wq) goto out_free_buffered_work_queue; + nvmet_aen_wq = alloc_workqueue("nvmet-aen-wq", + WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + if (!nvmet_aen_wq) + goto out_free_nvmet_work_queue; + error = nvmet_init_debugfs(); if (error) - goto out_free_nvmet_work_queue; + goto out_free_nvmet_aen_work_queue; error = nvmet_init_discovery(); if (error) @@ -1977,6 +1984,8 @@ static int __init nvmet_init(void) nvmet_exit_discovery(); out_exit_debugfs: nvmet_exit_debugfs(); +out_free_nvmet_aen_work_queue: + destroy_workqueue(nvmet_aen_wq); out_free_nvmet_work_queue: destroy_workqueue(nvmet_wq); out_free_buffered_work_queue: @@ -1994,6 +2003,7 @@ static void __exit nvmet_exit(void) nvmet_exit_discovery(); nvmet_exit_debugfs(); ida_destroy(&cntlid_ida); + destroy_workqueue(nvmet_aen_wq); destroy_workqueue(nvmet_wq); destroy_workqueue(buffered_io_wq); destroy_workqueue(zbd_wq); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index b664b584fdc8..319d6a5e9cf0 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -501,6 +501,7 @@ extern struct kmem_cache *nvmet_bvec_cache; extern struct workqueue_struct *buffered_io_wq; extern struct workqueue_struct *zbd_wq; extern struct workqueue_struct *nvmet_wq; +extern struct workqueue_struct *nvmet_aen_wq; static inline void nvmet_set_result(struct nvmet_req *req, u32 result) { diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 9c12b2361a6d..038432364967 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -2088,6 +2088,7 @@ static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data mutex_unlock(&nvmet_rdma_queue_mutex); flush_workqueue(nvmet_wq); + flush_workqueue(nvmet_aen_wq); } static struct ib_client nvmet_rdma_ib_client = { From fc71f409b22ca831a9f87a2712eaa09ef2bb4a5e Mon Sep 17 00:00:00 2001 From: Sungwoo Kim Date: Sat, 7 Mar 2026 14:46:36 -0500 Subject: [PATCH 327/487] nvme-pci: Fix race bug in nvme_poll_irqdisable() In the following scenario, pdev can be disabled between (1) and (3) by (2). This sets pdev->msix_enabled = 0. Then, pci_irq_vector() will return MSI-X IRQ(>15) for (1) whereas return INTx IRQ(<=15) for (2). This causes IRQ warning because it tries to enable INTx IRQ that has never been disabled before. To fix this, save IRQ number into a local variable and ensure disable_irq() and enable_irq() operate on the same IRQ number. Even if pci_free_irq_vectors() frees the IRQ concurrently, disable_irq() and enable_irq() on a stale IRQ number is still valid and safe, and the depth accounting reamins balanced. task 1: nvme_poll_irqdisable() disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)) ...(1) enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)) ...(3) task 2: nvme_reset_work() nvme_dev_disable() pdev->msix_enable = 0; ...(2) crash log: ------------[ cut here ]------------ Unbalanced enable for IRQ 10 WARNING: kernel/irq/manage.c:753 at __enable_irq+0x102/0x190 kernel/irq/manage.c:753, CPU#1: kworker/1:0H/26 Modules linked in: CPU: 1 UID: 0 PID: 26 Comm: kworker/1:0H Not tainted 6.19.0-dirty #9 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 Workqueue: kblockd blk_mq_timeout_work RIP: 0010:__enable_irq+0x107/0x190 kernel/irq/manage.c:753 Code: ff df 48 89 fa 48 c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 79 48 8d 3d 2e 7a 3f 05 41 8b 74 24 2c <67> 48 0f b9 3a e8 ef b9 21 00 5b 41 5c 5d e9 46 54 66 03 e8 e1 b9 RSP: 0018:ffffc900001bf550 EFLAGS: 00010046 RAX: 0000000000000007 RBX: 0000000000000000 RCX: ffffffffb20c0e90 RDX: 0000000000000000 RSI: 000000000000000a RDI: ffffffffb74b88f0 RBP: ffffc900001bf560 R08: ffff88800197cf00 R09: 0000000000000001 R10: 0000000000000003 R11: 0000000000000003 R12: ffff8880012a6000 R13: 1ffff92000037eae R14: 000000000000000a R15: 0000000000000293 FS: 0000000000000000(0000) GS:ffff8880b49f7000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000555da4a25fa8 CR3: 00000000208e8000 CR4: 00000000000006f0 Call Trace: enable_irq+0x121/0x1e0 kernel/irq/manage.c:797 nvme_poll_irqdisable+0x162/0x1c0 drivers/nvme/host/pci.c:1494 nvme_timeout+0x965/0x14b0 drivers/nvme/host/pci.c:1744 blk_mq_rq_timed_out block/blk-mq.c:1653 [inline] blk_mq_handle_expired+0x227/0x2d0 block/blk-mq.c:1721 bt_iter+0x2fc/0x3a0 block/blk-mq-tag.c:292 __sbitmap_for_each_set include/linux/sbitmap.h:269 [inline] sbitmap_for_each_set include/linux/sbitmap.h:290 [inline] bt_for_each block/blk-mq-tag.c:324 [inline] blk_mq_queue_tag_busy_iter+0x969/0x1e80 block/blk-mq-tag.c:536 blk_mq_timeout_work+0x627/0x870 block/blk-mq.c:1763 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257 process_scheduled_works kernel/workqueue.c:3340 [inline] worker_thread+0x65c/0xe60 kernel/workqueue.c:3421 kthread+0x41a/0x930 kernel/kthread.c:463 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 irq event stamp: 74478 hardirqs last enabled at (74477): [] __raw_spin_unlock_irq include/linux/spinlock_api_smp.h:159 [inline] hardirqs last enabled at (74477): [] _raw_spin_unlock_irq+0x2c/0x60 kernel/locking/spinlock.c:202 hardirqs last disabled at (74478): [] __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline] hardirqs last disabled at (74478): [] _raw_spin_lock_irqsave+0x85/0xa0 kernel/locking/spinlock.c:162 softirqs last enabled at (74304): [] __do_softirq kernel/softirq.c:656 [inline] softirqs last enabled at (74304): [] invoke_softirq kernel/softirq.c:496 [inline] softirqs last enabled at (74304): [] __irq_exit_rcu+0xdc/0x120 kernel/softirq.c:723 softirqs last disabled at (74287): [] __do_softirq kernel/softirq.c:656 [inline] softirqs last disabled at (74287): [] invoke_softirq kernel/softirq.c:496 [inline] softirqs last disabled at (74287): [] __irq_exit_rcu+0xdc/0x120 kernel/softirq.c:723 ---[ end trace 0000000000000000 ]--- Fixes: fa059b856a59 (nvme-pci: Simplify nvme_poll_irqdisable) Acked-by: Chao Shi Acked-by: Weidong Zhu Acked-by: Dave Tian Reviewed-by: Christoph Hellwig Signed-off-by: Sungwoo Kim Signed-off-by: Keith Busch --- drivers/nvme/host/pci.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d90db12c7cd8..93eb9f1cf9c1 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1625,14 +1625,16 @@ static irqreturn_t nvme_irq_check(int irq, void *data) static void nvme_poll_irqdisable(struct nvme_queue *nvmeq) { struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev); + int irq; WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags)); - disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); + irq = pci_irq_vector(pdev, nvmeq->cq_vector); + disable_irq(irq); spin_lock(&nvmeq->cq_poll_lock); nvme_poll_cq(nvmeq, NULL); spin_unlock(&nvmeq->cq_poll_lock); - enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); + enable_irq(irq); } static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) From 0375c81eb2256366cd9602441d48b8b937e79635 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Fri, 20 Feb 2026 14:30:16 +0100 Subject: [PATCH 328/487] nvme-core: do not pass empty queue_limits to blk_mq_alloc_queue() In nvme_alloc_admin_tag_set(), an empty queue_limits struct is currently allocated on the stack and passed by reference to blk_mq_alloc_queue(). This is redundant because blk_mq_alloc_queue() already handles a NULL limits pointer by internally substituting it with a default empty queue_limits struct. Remove the unnecessary local variable and pass a NULL value. Reviewed-by: Kanchan Joshi Signed-off-by: Maurizio Lombardi Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3bc0b9ea00ce..6370aa35cc06 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4834,7 +4834,6 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event); int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int cmd_size) { - struct queue_limits lim = {}; int ret; memset(set, 0, sizeof(*set)); @@ -4861,7 +4860,7 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, if (ctrl->admin_q) blk_put_queue(ctrl->admin_q); - ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL); + ctrl->admin_q = blk_mq_alloc_queue(set, NULL, NULL); if (IS_ERR(ctrl->admin_q)) { ret = PTR_ERR(ctrl->admin_q); goto out_free_tagset; From fa655a9ca73f7df32b8ca4d14ce11742f9578288 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 3 Mar 2026 22:31:01 +0100 Subject: [PATCH 329/487] nvme: Annotate struct nvme_dhchap_key with __counted_by Add the __counted_by() compiler attribute to the flexible array member 'key' to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and CONFIG_FORTIFY_SOURCE. Reviewed-by: Christoph Hellwig Signed-off-by: Thorsten Blum Signed-off-by: Keith Busch --- include/linux/nvme-auth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h index 60e069a6757f..e75c29c51464 100644 --- a/include/linux/nvme-auth.h +++ b/include/linux/nvme-auth.h @@ -11,7 +11,7 @@ struct nvme_dhchap_key { size_t len; u8 hash; - u8 key[]; + u8 key[] __counted_by(len); }; u32 nvme_auth_get_seqnum(void); From bd98c6204d1195973b1760fe45860863deb6200c Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 13 Feb 2026 10:48:41 +0200 Subject: [PATCH 330/487] drivers: net: ice: fix devlink parameters get without irdma If CONFIG_IRDMA isn't enabled but there are ice NICs in the system, the driver will prevent full devlink dev param show dump because its rdma get callbacks return ENODEV and stop the dump. For example: $ devlink dev param show pci/0000:82:00.0: name msix_vec_per_pf_max type generic values: cmode driverinit value 2 name msix_vec_per_pf_min type generic values: cmode driverinit value 2 kernel answers: No such device Returning EOPNOTSUPP allows the dump to continue so we can see all devices' devlink parameters. Fixes: c24a65b6a27c ("iidc/ice/irdma: Update IDC to support multiple consumers") Signed-off-by: Nikolay Aleksandrov Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/devlink/devlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 6c72bd15db6d..6144cee8034d 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1360,7 +1360,7 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, cdev = pf->cdev_info; if (!cdev) - return -ENODEV; + return -EOPNOTSUPP; ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2); @@ -1427,7 +1427,7 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, cdev = pf->cdev_info; if (!cdev) - return -ENODEV; + return -EOPNOTSUPP; ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP); From efc54fb13d79117a825fef17364315a58682c7ec Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Thu, 29 Jan 2026 10:57:23 +0100 Subject: [PATCH 331/487] iavf: fix PTP use-after-free during reset Commit 7c01dbfc8a1c5f ("iavf: periodically cache PHC time") introduced a worker to cache PHC time, but failed to stop it during reset or disable. This creates a race condition where `iavf_reset_task()` or `iavf_disable_vf()` free adapter resources (AQ) while the worker is still running. If the worker triggers `iavf_queue_ptp_cmd()` during teardown, it accesses freed memory/locks, leading to a crash. Fix this by calling `iavf_ptp_release()` before tearing down the adapter. This ensures `ptp_clock_unregister()` synchronously cancels the worker and cleans up the chardev before the backing resources are destroyed. Fixes: 7c01dbfc8a1c5f ("iavf: periodically cache PHC time") Signed-off-by: Petr Oros Reviewed-by: Ivan Vecera Acked-by: Jacob Keller Reviewed-by: Vadim Fedorenko Reviewed-by: Paul Menzel Reviewed-by: Aleksandr Loktionov Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 86c1964f42e1..c7abd3331e03 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3036,6 +3036,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_ptp_release(adapter); + /* We don't use netif_running() because it may be true prior to * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. @@ -3211,6 +3213,8 @@ static void iavf_reset_task(struct work_struct *work) iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + iavf_ptp_release(adapter); + /* free the Tx/Rx rings and descriptors, might be better to just * re-use them sometime in the future */ From fdadbf6e84c44df8dbb85cfdd38bc10e4431501d Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Wed, 11 Feb 2026 20:18:55 +0100 Subject: [PATCH 332/487] iavf: fix incorrect reset handling in callbacks Three driver callbacks schedule a reset and wait for its completion: ndo_change_mtu(), ethtool set_ringparam(), and ethtool set_channels(). Waiting for reset in ndo_change_mtu() and set_ringparam() was added by commit c2ed2403f12c ("iavf: Wait for reset in callbacks which trigger it") to fix a race condition where adding an interface to bonding immediately after MTU or ring parameter change failed because the interface was still in __RESETTING state. The same commit also added waiting in iavf_set_priv_flags(), which was later removed by commit 53844673d555 ("iavf: kill "legacy-rx" for good"). Waiting in set_channels() was introduced earlier by commit 4e5e6b5d9d13 ("iavf: Fix return of set the new channel count") to ensure the PF has enough time to complete the VF reset when changing channel count, and to return correct error codes to userspace. Commit ef490bbb2267 ("iavf: Add net_shaper_ops support") added net_shaper_ops to iavf, which required reset_task to use _locked NAPI variants (napi_enable_locked, napi_disable_locked) that need the netdev instance lock. Later, commit 7e4d784f5810 ("net: hold netdev instance lock during rtnetlink operations") and commit 2bcf4772e45a ("net: ethtool: try to protect all callback with netdev instance lock") started holding the netdev instance lock during ndo and ethtool callbacks for drivers with net_shaper_ops. Finally, commit 120f28a6f314 ("iavf: get rid of the crit lock") replaced the driver's crit_lock with netdev_lock in reset_task, causing incorrect behavior: the callback holds netdev_lock and waits for reset_task, but reset_task needs the same lock: Thread 1 (callback) Thread 2 (reset_task) ------------------- --------------------- netdev_lock() [blocked on workqueue] ndo_change_mtu() or ethtool op iavf_schedule_reset() iavf_wait_for_reset() iavf_reset_task() waiting... netdev_lock() <- blocked This does not strictly deadlock because iavf_wait_for_reset() uses wait_event_interruptible_timeout() with a 5-second timeout. The wait eventually times out, the callback returns an error to userspace, and after the lock is released reset_task completes the reset. This leads to incorrect behavior: userspace sees an error even though the configuration change silently takes effect after the timeout. Fix this by extracting the reset logic from iavf_reset_task() into a new iavf_reset_step() function that expects netdev_lock to be already held. The three callbacks now call iavf_reset_step() directly instead of scheduling the work and waiting, performing the reset synchronously in the caller's context which already holds netdev_lock. This eliminates both the incorrect error reporting and the need for iavf_wait_for_reset(), which is removed along with the now-unused reset_waitqueue. The workqueue-based iavf_reset_task() becomes a thin wrapper that acquires netdev_lock and calls iavf_reset_step(), preserving its use for PF-initiated resets. The callbacks may block for several seconds while iavf_reset_step() polls hardware registers, but this is acceptable since netdev_lock is a per-device mutex and only serializes operations on the same interface. v3: - Remove netif_running() guard from iavf_set_channels(). Unlike set_ringparam where descriptor counts are picked up by iavf_open() directly, num_req_queues is only consumed during iavf_reinit_interrupt_scheme() in the reset path. Skipping the reset on a down device would silently discard the channel count change. - Remove dead reset_waitqueue code (struct field, init, and all wake_up calls) since iavf_wait_for_reset() was the only consumer. Fixes: 120f28a6f314 ("iavf: get rid of the crit lock") Reviewed-by: Jacob Keller Signed-off-by: Petr Oros Reviewed-by: Przemek Kitszel Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 3 +- .../net/ethernet/intel/iavf/iavf_ethtool.c | 19 ++--- drivers/net/ethernet/intel/iavf/iavf_main.c | 77 ++++++------------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 1 - 4 files changed, 31 insertions(+), 69 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index a87e0c6d4017..e9fb0a0919e3 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -260,7 +260,6 @@ struct iavf_adapter { struct work_struct adminq_task; struct work_struct finish_config; wait_queue_head_t down_waitqueue; - wait_queue_head_t reset_waitqueue; wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -626,5 +625,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); -int iavf_wait_for_reset(struct iavf_adapter *adapter); +void iavf_reset_step(struct iavf_adapter *adapter); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index f3a1b2fb9bf8..ab67c709d5a0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -492,7 +492,6 @@ static int iavf_set_ringparam(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 new_rx_count, new_tx_count; - int ret = 0; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; @@ -537,13 +536,11 @@ static int iavf_set_ringparam(struct net_device *netdev, } if (netif_running(netdev)) { - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - ret = iavf_wait_for_reset(adapter); - if (ret) - netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset"); + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + iavf_reset_step(adapter); } - return ret; + return 0; } /** @@ -1723,7 +1720,6 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; - int ret = 0; if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1745,13 +1741,10 @@ static int iavf_set_channels(struct net_device *netdev, adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + iavf_reset_step(adapter); - ret = iavf_wait_for_reset(adapter); - if (ret) - netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset"); - - return ret; + return 0; } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index c7abd3331e03..7925ee152c76 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -185,31 +185,6 @@ static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter) return false; } -/** - * iavf_wait_for_reset - Wait for reset to finish. - * @adapter: board private structure - * - * Returns 0 if reset finished successfully, negative on timeout or interrupt. - */ -int iavf_wait_for_reset(struct iavf_adapter *adapter) -{ - int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue, - !iavf_is_reset_in_progress(adapter), - msecs_to_jiffies(5000)); - - /* If ret < 0 then it means wait was interrupted. - * If ret == 0 then it means we got a timeout while waiting - * for reset to finish. - * If ret > 0 it means reset has finished. - */ - if (ret > 0) - return 0; - else if (ret < 0) - return -EINTR; - else - return -EBUSY; -} - /** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -3113,18 +3088,16 @@ static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter) } /** - * iavf_reset_task - Call-back task to handle hardware reset - * @work: pointer to work_struct + * iavf_reset_step - Perform the VF reset sequence + * @adapter: board private structure * - * During reset we need to shut down and reinitialize the admin queue - * before we can use it to communicate with the PF again. We also clear - * and reinit the rings because that context is lost as well. - **/ -static void iavf_reset_task(struct work_struct *work) + * Requests a reset from PF, polls for completion, and reconfigures + * the driver. Caller must hold the netdev instance lock. + * + * This can sleep for several seconds while polling HW registers. + */ +void iavf_reset_step(struct iavf_adapter *adapter) { - struct iavf_adapter *adapter = container_of(work, - struct iavf_adapter, - reset_task); struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; @@ -3135,7 +3108,7 @@ static void iavf_reset_task(struct work_struct *work) int i = 0, err; bool running; - netdev_lock(netdev); + netdev_assert_locked(netdev); iavf_misc_irq_disable(adapter); if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { @@ -3180,7 +3153,6 @@ static void iavf_reset_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); iavf_disable_vf(adapter); - netdev_unlock(netdev); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3192,7 +3164,6 @@ static void iavf_reset_task(struct work_struct *work) iavf_startup(adapter); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); - netdev_unlock(netdev); return; } @@ -3335,9 +3306,6 @@ static void iavf_reset_task(struct work_struct *work) adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; - wake_up(&adapter->reset_waitqueue); - netdev_unlock(netdev); - return; reset_err: if (running) { @@ -3346,10 +3314,21 @@ static void iavf_reset_task(struct work_struct *work) } iavf_disable_vf(adapter); - netdev_unlock(netdev); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); } +static void iavf_reset_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, + reset_task); + struct net_device *netdev = adapter->netdev; + + netdev_lock(netdev); + iavf_reset_step(adapter); + netdev_unlock(netdev); +} + /** * iavf_adminq_task - worker thread to clean the admin queue * @work: pointer to work_struct containing our data @@ -4615,22 +4594,17 @@ static int iavf_close(struct net_device *netdev) static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { struct iavf_adapter *adapter = netdev_priv(netdev); - int ret = 0; netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) { - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - ret = iavf_wait_for_reset(adapter); - if (ret < 0) - netdev_warn(netdev, "MTU change interrupted waiting for reset"); - else if (ret) - netdev_warn(netdev, "MTU change timed out waiting for reset"); + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + iavf_reset_step(adapter); } - return ret; + return 0; } /** @@ -5435,9 +5409,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); - /* Setup the wait queue for indicating transition to running state */ - init_waitqueue_head(&adapter->reset_waitqueue); - /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 88156082a41d..a52c100dcbc5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2736,7 +2736,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); - wake_up(&adapter->reset_waitqueue); adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: From 22fd7f7fed2ae3702f90d1985c326354e86b9c75 Mon Sep 17 00:00:00 2001 From: Muhammad Amirul Asyraf Mohamad Jamian Date: Thu, 5 Mar 2026 01:31:51 -0800 Subject: [PATCH 333/487] firmware: stratix10-svc: Add Multi SVC clients support In the current implementation, SVC client drivers such as socfpga-hwmon, intel_fcs, stratix10-soc, stratix10-rsu each send an SMC command that triggers a single thread in the stratix10-svc driver. Upon receiving a callback, the initiating client driver sends a stratix10-svc-done signal, terminating the thread without waiting for other pending SMC commands to complete. This leads to a timeout issue in the firmware SVC mailbox service when multiple client drivers send SMC commands concurrently. To resolve this issue, a dedicated thread is now created per channel. The stratix10-svc driver will support up to the number of channels defined by SVC_NUM_CHANNEL. Thread synchronization is handled using a mutex to prevent simultaneous issuance of SMC commands by multiple threads. SVC_NUM_DATA_IN_FIFO is reduced from 32 to 8, since each channel now has its own dedicated FIFO and the SDM processes commands one at a time. 8 entries per channel is sufficient while keeping the total aggregate capacity the same (4 channels x 8 = 32 entries). Additionally, a thread task is now validated before invoking kthread_stop when the user aborts, ensuring safe termination. Timeout values have also been adjusted to accommodate the increased load from concurrent client driver activity. Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver") Cc: stable@vger.kernel.org Signed-off-by: Ang Tien Sung Signed-off-by: Fong, Yan Kei Signed-off-by: Muhammad Amirul Asyraf Mohamad Jamian Link: https://lore.kernel.org/all/20260305093151.2678-1-muhammad.amirul.asyraf.mohamad.jamian@altera.com Signed-off-by: Dinh Nguyen --- drivers/firmware/stratix10-svc.c | 228 ++++++++++-------- .../firmware/intel/stratix10-svc-client.h | 8 +- 2 files changed, 130 insertions(+), 106 deletions(-) diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 6f5c298582ab..e9e35d67ef96 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -37,15 +37,14 @@ * service layer will return error to FPGA manager when timeout occurs, * timeout is set to 30 seconds (30 * 1000) at Intel Stratix10 SoC. */ -#define SVC_NUM_DATA_IN_FIFO 32 +#define SVC_NUM_DATA_IN_FIFO 8 #define SVC_NUM_CHANNEL 4 -#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS 200 +#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS 2000 #define FPGA_CONFIG_STATUS_TIMEOUT_SEC 30 #define BYTE_TO_WORD_SIZE 4 /* stratix10 service layer clients */ #define STRATIX10_RSU "stratix10-rsu" -#define INTEL_FCS "intel-fcs" /* Maximum number of SDM client IDs. */ #define MAX_SDM_CLIENT_IDS 16 @@ -105,11 +104,9 @@ struct stratix10_svc_chan; /** * struct stratix10_svc - svc private data * @stratix10_svc_rsu: pointer to stratix10 RSU device - * @intel_svc_fcs: pointer to the FCS device */ struct stratix10_svc { struct platform_device *stratix10_svc_rsu; - struct platform_device *intel_svc_fcs; }; /** @@ -251,12 +248,10 @@ struct stratix10_async_ctrl { * @num_active_client: number of active service client * @node: list management * @genpool: memory pool pointing to the memory region - * @task: pointer to the thread task which handles SMC or HVC call - * @svc_fifo: a queue for storing service message data * @complete_status: state for completion - * @svc_fifo_lock: protect access to service message data queue * @invoke_fn: function to issue secure monitor call or hypervisor call * @svc: manages the list of client svc drivers + * @sdm_lock: only allows a single command single response to SDM * @actrl: async control structure * * This struct is used to create communication channels for service clients, to @@ -269,12 +264,10 @@ struct stratix10_svc_controller { int num_active_client; struct list_head node; struct gen_pool *genpool; - struct task_struct *task; - struct kfifo svc_fifo; struct completion complete_status; - spinlock_t svc_fifo_lock; svc_invoke_fn *invoke_fn; struct stratix10_svc *svc; + struct mutex sdm_lock; struct stratix10_async_ctrl actrl; }; @@ -283,6 +276,9 @@ struct stratix10_svc_controller { * @ctrl: pointer to service controller which is the provider of this channel * @scl: pointer to service client which owns the channel * @name: service client name associated with the channel + * @task: pointer to the thread task which handles SMC or HVC call + * @svc_fifo: a queue for storing service message data (separate fifo for every channel) + * @svc_fifo_lock: protect access to service message data queue (locking pending fifo) * @lock: protect access to the channel * @async_chan: reference to asynchronous channel object for this channel * @@ -293,6 +289,9 @@ struct stratix10_svc_chan { struct stratix10_svc_controller *ctrl; struct stratix10_svc_client *scl; char *name; + struct task_struct *task; + struct kfifo svc_fifo; + spinlock_t svc_fifo_lock; spinlock_t lock; struct stratix10_async_chan *async_chan; }; @@ -527,10 +526,10 @@ static void svc_thread_recv_status_ok(struct stratix10_svc_data *p_data, */ static int svc_normal_to_secure_thread(void *data) { - struct stratix10_svc_controller - *ctrl = (struct stratix10_svc_controller *)data; - struct stratix10_svc_data *pdata; - struct stratix10_svc_cb_data *cbdata; + struct stratix10_svc_chan *chan = (struct stratix10_svc_chan *)data; + struct stratix10_svc_controller *ctrl = chan->ctrl; + struct stratix10_svc_data *pdata = NULL; + struct stratix10_svc_cb_data *cbdata = NULL; struct arm_smccc_res res; unsigned long a0, a1, a2, a3, a4, a5, a6, a7; int ret_fifo = 0; @@ -555,12 +554,12 @@ static int svc_normal_to_secure_thread(void *data) a6 = 0; a7 = 0; - pr_debug("smc_hvc_shm_thread is running\n"); + pr_debug("%s: %s: Thread is running!\n", __func__, chan->name); while (!kthread_should_stop()) { - ret_fifo = kfifo_out_spinlocked(&ctrl->svc_fifo, + ret_fifo = kfifo_out_spinlocked(&chan->svc_fifo, pdata, sizeof(*pdata), - &ctrl->svc_fifo_lock); + &chan->svc_fifo_lock); if (!ret_fifo) continue; @@ -569,9 +568,25 @@ static int svc_normal_to_secure_thread(void *data) (unsigned int)pdata->paddr, pdata->command, (unsigned int)pdata->size); + /* SDM can only process one command at a time */ + pr_debug("%s: %s: Thread is waiting for mutex!\n", + __func__, chan->name); + if (mutex_lock_interruptible(&ctrl->sdm_lock)) { + /* item already dequeued; notify client to unblock it */ + cbdata->status = BIT(SVC_STATUS_ERROR); + cbdata->kaddr1 = NULL; + cbdata->kaddr2 = NULL; + cbdata->kaddr3 = NULL; + if (pdata->chan->scl) + pdata->chan->scl->receive_cb(pdata->chan->scl, + cbdata); + break; + } + switch (pdata->command) { case COMMAND_RECONFIG_DATA_CLAIM: svc_thread_cmd_data_claim(ctrl, pdata, cbdata); + mutex_unlock(&ctrl->sdm_lock); continue; case COMMAND_RECONFIG: a0 = INTEL_SIP_SMC_FPGA_CONFIG_START; @@ -700,10 +715,11 @@ static int svc_normal_to_secure_thread(void *data) break; default: pr_warn("it shouldn't happen\n"); - break; + mutex_unlock(&ctrl->sdm_lock); + continue; } - pr_debug("%s: before SMC call -- a0=0x%016x a1=0x%016x", - __func__, + pr_debug("%s: %s: before SMC call -- a0=0x%016x a1=0x%016x", + __func__, chan->name, (unsigned int)a0, (unsigned int)a1); pr_debug(" a2=0x%016x\n", (unsigned int)a2); @@ -712,8 +728,8 @@ static int svc_normal_to_secure_thread(void *data) pr_debug(" a5=0x%016x\n", (unsigned int)a5); ctrl->invoke_fn(a0, a1, a2, a3, a4, a5, a6, a7, &res); - pr_debug("%s: after SMC call -- res.a0=0x%016x", - __func__, (unsigned int)res.a0); + pr_debug("%s: %s: after SMC call -- res.a0=0x%016x", + __func__, chan->name, (unsigned int)res.a0); pr_debug(" res.a1=0x%016x, res.a2=0x%016x", (unsigned int)res.a1, (unsigned int)res.a2); pr_debug(" res.a3=0x%016x\n", (unsigned int)res.a3); @@ -728,6 +744,7 @@ static int svc_normal_to_secure_thread(void *data) cbdata->kaddr2 = NULL; cbdata->kaddr3 = NULL; pdata->chan->scl->receive_cb(pdata->chan->scl, cbdata); + mutex_unlock(&ctrl->sdm_lock); continue; } @@ -801,6 +818,8 @@ static int svc_normal_to_secure_thread(void *data) break; } + + mutex_unlock(&ctrl->sdm_lock); } kfree(cbdata); @@ -1696,22 +1715,33 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg) if (!p_data) return -ENOMEM; - /* first client will create kernel thread */ - if (!chan->ctrl->task) { - chan->ctrl->task = - kthread_run_on_cpu(svc_normal_to_secure_thread, - (void *)chan->ctrl, - cpu, "svc_smc_hvc_thread"); - if (IS_ERR(chan->ctrl->task)) { + /* first caller creates the per-channel kthread */ + if (!chan->task) { + struct task_struct *task; + + task = kthread_run_on_cpu(svc_normal_to_secure_thread, + (void *)chan, + cpu, "svc_smc_hvc_thread"); + if (IS_ERR(task)) { dev_err(chan->ctrl->dev, "failed to create svc_smc_hvc_thread\n"); kfree(p_data); return -EINVAL; } + + spin_lock(&chan->lock); + if (chan->task) { + /* another caller won the race; discard our thread */ + spin_unlock(&chan->lock); + kthread_stop(task); + } else { + chan->task = task; + spin_unlock(&chan->lock); + } } - pr_debug("%s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__, - p_msg->payload, p_msg->command, + pr_debug("%s: %s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__, + chan->name, p_msg->payload, p_msg->command, (unsigned int)p_msg->payload_length); if (list_empty(&svc_data_mem)) { @@ -1747,12 +1777,16 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg) p_data->arg[2] = p_msg->arg[2]; p_data->size = p_msg->payload_length; p_data->chan = chan; - pr_debug("%s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n", __func__, - (unsigned int)p_data->paddr, p_data->command, - (unsigned int)p_data->size); - ret = kfifo_in_spinlocked(&chan->ctrl->svc_fifo, p_data, + pr_debug("%s: %s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n", + __func__, + chan->name, + (unsigned int)p_data->paddr, + p_data->command, + (unsigned int)p_data->size); + + ret = kfifo_in_spinlocked(&chan->svc_fifo, p_data, sizeof(*p_data), - &chan->ctrl->svc_fifo_lock); + &chan->svc_fifo_lock); kfree(p_data); @@ -1773,11 +1807,12 @@ EXPORT_SYMBOL_GPL(stratix10_svc_send); */ void stratix10_svc_done(struct stratix10_svc_chan *chan) { - /* stop thread when thread is running AND only one active client */ - if (chan->ctrl->task && chan->ctrl->num_active_client <= 1) { - pr_debug("svc_smc_hvc_shm_thread is stopped\n"); - kthread_stop(chan->ctrl->task); - chan->ctrl->task = NULL; + /* stop thread when thread is running */ + if (chan->task) { + pr_debug("%s: %s: svc_smc_hvc_shm_thread is stopping\n", + __func__, chan->name); + kthread_stop(chan->task); + chan->task = NULL; } } EXPORT_SYMBOL_GPL(stratix10_svc_done); @@ -1817,8 +1852,8 @@ void *stratix10_svc_allocate_memory(struct stratix10_svc_chan *chan, pmem->paddr = pa; pmem->size = s; list_add_tail(&pmem->node, &svc_data_mem); - pr_debug("%s: va=%p, pa=0x%016x\n", __func__, - pmem->vaddr, (unsigned int)pmem->paddr); + pr_debug("%s: %s: va=%p, pa=0x%016x\n", __func__, + chan->name, pmem->vaddr, (unsigned int)pmem->paddr); return (void *)va; } @@ -1855,6 +1890,13 @@ static const struct of_device_id stratix10_svc_drv_match[] = { {}, }; +static const char * const chan_names[SVC_NUM_CHANNEL] = { + SVC_CLIENT_FPGA, + SVC_CLIENT_RSU, + SVC_CLIENT_FCS, + SVC_CLIENT_HWMON +}; + static int stratix10_svc_drv_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1862,11 +1904,11 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) struct stratix10_svc_chan *chans; struct gen_pool *genpool; struct stratix10_svc_sh_memory *sh_memory; - struct stratix10_svc *svc; + struct stratix10_svc *svc = NULL; svc_invoke_fn *invoke_fn; size_t fifo_size; - int ret; + int ret, i = 0; /* get SMC or HVC function */ invoke_fn = get_invoke_func(dev); @@ -1905,8 +1947,8 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) controller->num_active_client = 0; controller->chans = chans; controller->genpool = genpool; - controller->task = NULL; controller->invoke_fn = invoke_fn; + INIT_LIST_HEAD(&controller->node); init_completion(&controller->complete_status); ret = stratix10_svc_async_init(controller); @@ -1917,32 +1959,20 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) } fifo_size = sizeof(struct stratix10_svc_data) * SVC_NUM_DATA_IN_FIFO; - ret = kfifo_alloc(&controller->svc_fifo, fifo_size, GFP_KERNEL); - if (ret) { - dev_err(dev, "failed to allocate FIFO\n"); - goto err_async_exit; + mutex_init(&controller->sdm_lock); + + for (i = 0; i < SVC_NUM_CHANNEL; i++) { + chans[i].scl = NULL; + chans[i].ctrl = controller; + chans[i].name = (char *)chan_names[i]; + spin_lock_init(&chans[i].lock); + ret = kfifo_alloc(&chans[i].svc_fifo, fifo_size, GFP_KERNEL); + if (ret) { + dev_err(dev, "failed to allocate FIFO %d\n", i); + goto err_free_fifos; + } + spin_lock_init(&chans[i].svc_fifo_lock); } - spin_lock_init(&controller->svc_fifo_lock); - - chans[0].scl = NULL; - chans[0].ctrl = controller; - chans[0].name = SVC_CLIENT_FPGA; - spin_lock_init(&chans[0].lock); - - chans[1].scl = NULL; - chans[1].ctrl = controller; - chans[1].name = SVC_CLIENT_RSU; - spin_lock_init(&chans[1].lock); - - chans[2].scl = NULL; - chans[2].ctrl = controller; - chans[2].name = SVC_CLIENT_FCS; - spin_lock_init(&chans[2].lock); - - chans[3].scl = NULL; - chans[3].ctrl = controller; - chans[3].name = SVC_CLIENT_HWMON; - spin_lock_init(&chans[3].lock); list_add_tail(&controller->node, &svc_ctrl); platform_set_drvdata(pdev, controller); @@ -1951,7 +1981,7 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) svc = devm_kzalloc(dev, sizeof(*svc), GFP_KERNEL); if (!svc) { ret = -ENOMEM; - goto err_free_kfifo; + goto err_free_fifos; } controller->svc = svc; @@ -1959,51 +1989,43 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) if (!svc->stratix10_svc_rsu) { dev_err(dev, "failed to allocate %s device\n", STRATIX10_RSU); ret = -ENOMEM; - goto err_free_kfifo; + goto err_free_fifos; } ret = platform_device_add(svc->stratix10_svc_rsu); - if (ret) { - platform_device_put(svc->stratix10_svc_rsu); - goto err_free_kfifo; - } - - svc->intel_svc_fcs = platform_device_alloc(INTEL_FCS, 1); - if (!svc->intel_svc_fcs) { - dev_err(dev, "failed to allocate %s device\n", INTEL_FCS); - ret = -ENOMEM; - goto err_unregister_rsu_dev; - } - - ret = platform_device_add(svc->intel_svc_fcs); - if (ret) { - platform_device_put(svc->intel_svc_fcs); - goto err_unregister_rsu_dev; - } + if (ret) + goto err_put_device; ret = of_platform_default_populate(dev_of_node(dev), NULL, dev); if (ret) - goto err_unregister_fcs_dev; + goto err_unregister_rsu_dev; pr_info("Intel Service Layer Driver Initialized\n"); return 0; -err_unregister_fcs_dev: - platform_device_unregister(svc->intel_svc_fcs); err_unregister_rsu_dev: platform_device_unregister(svc->stratix10_svc_rsu); -err_free_kfifo: - kfifo_free(&controller->svc_fifo); -err_async_exit: + goto err_free_fifos; +err_put_device: + platform_device_put(svc->stratix10_svc_rsu); +err_free_fifos: + /* only remove from list if list_add_tail() was reached */ + if (!list_empty(&controller->node)) + list_del(&controller->node); + /* free only the FIFOs that were successfully allocated */ + while (i--) + kfifo_free(&chans[i].svc_fifo); stratix10_svc_async_exit(controller); err_destroy_pool: gen_pool_destroy(genpool); + return ret; } static void stratix10_svc_drv_remove(struct platform_device *pdev) { + int i; struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev); struct stratix10_svc *svc = ctrl->svc; @@ -2011,14 +2033,16 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev) of_platform_depopulate(ctrl->dev); - platform_device_unregister(svc->intel_svc_fcs); platform_device_unregister(svc->stratix10_svc_rsu); - kfifo_free(&ctrl->svc_fifo); - if (ctrl->task) { - kthread_stop(ctrl->task); - ctrl->task = NULL; + for (i = 0; i < SVC_NUM_CHANNEL; i++) { + if (ctrl->chans[i].task) { + kthread_stop(ctrl->chans[i].task); + ctrl->chans[i].task = NULL; + } + kfifo_free(&ctrl->chans[i].svc_fifo); } + if (ctrl->genpool) gen_pool_destroy(ctrl->genpool); list_del(&ctrl->node); diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index d290060f4c73..91013161e9db 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -68,12 +68,12 @@ * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver */ -#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 300 -#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 720 -#define SVC_RSU_REQUEST_TIMEOUT_MS 300 +#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 5000 +#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 5000 +#define SVC_RSU_REQUEST_TIMEOUT_MS 2000 #define SVC_FCS_REQUEST_TIMEOUT_MS 2000 #define SVC_COMPLETED_TIMEOUT_MS 30000 -#define SVC_HWMON_REQUEST_TIMEOUT_MS 300 +#define SVC_HWMON_REQUEST_TIMEOUT_MS 2000 struct stratix10_svc_chan; From c7940c8bf215b9dc6211781c77ce80e76982a723 Mon Sep 17 00:00:00 2001 From: Tim Kovalenko Date: Mon, 9 Mar 2026 12:34:21 -0400 Subject: [PATCH 334/487] gpu: nova-core: fix stack overflow in GSP memory allocation The `Cmdq::new` function was allocating a `PteArray` struct on the stack and was causing a stack overflow with 8216 bytes. Modify the `PteArray` to calculate and write the Page Table Entries directly into the coherent DMA buffer one-by-one. This reduces the stack usage quite a lot. Reported-by: Gary Guo Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/509436-Nova/topic/.60Cmdq.3A.3Anew.60.20uses.20excessive.20stack.20size/near/570375549 Link: https://lore.kernel.org/rust-for-linux/CANiq72mAQxbRJZDnik3Qmd4phvFwPA01O2jwaaXRh_T+2=L-qA@mail.gmail.com/ Fixes: f38b4f105cfc ("gpu: nova-core: Create initial Gsp") Acked-by: Alexandre Courbot Signed-off-by: Tim Kovalenko Link: https://patch.msgid.link/20260309-drm-rust-next-v4-4-4ef485b19a4c@proton.me [ * Use PteArray::entry() in LogBuffer::new(), * Add TODO comment to use IoView projections once available, * Add PTE_ARRAY_SIZE constant to avoid duplication. - Danilo ] Signed-off-by: Danilo Krummrich --- drivers/gpu/nova-core/gsp.rs | 32 ++++++++++++++++--------------- drivers/gpu/nova-core/gsp/cmdq.rs | 14 ++++++++++++-- 2 files changed, 29 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs index 25cd48514c77..c69adaa92bbe 100644 --- a/drivers/gpu/nova-core/gsp.rs +++ b/drivers/gpu/nova-core/gsp.rs @@ -47,16 +47,12 @@ unsafe impl AsBytes for PteArray {} impl PteArray { - /// Creates a new page table array mapping `NUM_PAGES` GSP pages starting at address `start`. - fn new(start: DmaAddress) -> Result { - let mut ptes = [0u64; NUM_PAGES]; - for (i, pte) in ptes.iter_mut().enumerate() { - *pte = start - .checked_add(num::usize_as_u64(i) << GSP_PAGE_SHIFT) - .ok_or(EOVERFLOW)?; - } - - Ok(Self(ptes)) + /// Returns the page table entry for `index`, for a mapping starting at `start`. + // TODO: Replace with `IoView` projection once available. + fn entry(start: DmaAddress, index: usize) -> Result { + start + .checked_add(num::usize_as_u64(index) << GSP_PAGE_SHIFT) + .ok_or(EOVERFLOW) } } @@ -86,16 +82,22 @@ fn new(dev: &device::Device) -> Result { NUM_PAGES * GSP_PAGE_SIZE, GFP_KERNEL | __GFP_ZERO, )?); - let ptes = PteArray::::new(obj.0.dma_handle())?; + + let start_addr = obj.0.dma_handle(); // SAFETY: `obj` has just been created and we are its sole user. - unsafe { - // Copy the self-mapping PTE at the expected location. + let pte_region = unsafe { obj.0 - .as_slice_mut(size_of::(), size_of_val(&ptes))? - .copy_from_slice(ptes.as_bytes()) + .as_slice_mut(size_of::(), NUM_PAGES * size_of::())? }; + // Write values one by one to avoid an on-stack instance of `PteArray`. + for (i, chunk) in pte_region.chunks_exact_mut(size_of::()).enumerate() { + let pte_value = PteArray::<0>::entry(start_addr, i)?; + + chunk.copy_from_slice(&pte_value.to_ne_bytes()); + } + Ok(obj) } } diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs index ae54708c38eb..9c5efd2daf45 100644 --- a/drivers/gpu/nova-core/gsp/cmdq.rs +++ b/drivers/gpu/nova-core/gsp/cmdq.rs @@ -159,7 +159,7 @@ struct Msgq { #[repr(C)] struct GspMem { /// Self-mapping page table entries. - ptes: PteArray<{ GSP_PAGE_SIZE / size_of::() }>, + ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>, /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the /// write and read pointers that the CPU updates. /// @@ -172,6 +172,10 @@ struct GspMem { gspq: Msgq, } +impl GspMem { + const PTE_ARRAY_SIZE: usize = GSP_PAGE_SIZE / size_of::(); +} + // SAFETY: These structs don't meet the no-padding requirements of AsBytes but // that is not a problem because they are not used outside the kernel. unsafe impl AsBytes for GspMem {} @@ -201,7 +205,13 @@ fn new(dev: &device::Device) -> Result { let gsp_mem = CoherentAllocation::::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?; - dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?); + + let start = gsp_mem.dma_handle(); + // Write values one by one to avoid an on-stack instance of `PteArray`. + for i in 0..GspMem::PTE_ARRAY_SIZE { + dma_write!(gsp_mem, [0]?.ptes.0[i], PteArray::<0>::entry(start, i)?); + } + dma_write!( gsp_mem, [0]?.cpuq.tx, From 620b6ded72a7f0f77be6ec44d0462bb85729ab7a Mon Sep 17 00:00:00 2001 From: Jessica Liu Date: Tue, 10 Mar 2026 14:16:00 +0800 Subject: [PATCH 335/487] irqchip/riscv-aplic: Do not clear ACPI dependencies on probe failure aplic_probe() calls acpi_dev_clear_dependencies() unconditionally at the end, even when the preceding setup (MSI or direct mode) has failed. This is incorrect because if the device failed to probe, it should not be considered as active and should not clear dependencies for other devices waiting on it. Fix this by returning immediately when the setup fails, skipping the ACPI dependency cleanup. Also, explicitly return 0 on success instead of relying on the value of 'rc' to make the success path clear. Fixes: 5122e380c23b ("irqchip/riscv-aplic: Add ACPI support") Signed-off-by: Jessica Liu Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260310141600411Fu8H8-GXOOgKISU48Tjgx@zte.com.cn --- drivers/irqchip/irq-riscv-aplic-main.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c index 4495ca26abf5..8775f188ea4f 100644 --- a/drivers/irqchip/irq-riscv-aplic-main.c +++ b/drivers/irqchip/irq-riscv-aplic-main.c @@ -372,18 +372,21 @@ static int aplic_probe(struct platform_device *pdev) rc = aplic_msi_setup(dev, regs); else rc = aplic_direct_setup(dev, regs); - if (rc) + + if (rc) { dev_err_probe(dev, rc, "failed to setup APLIC in %s mode\n", msi_mode ? "MSI" : "direct"); - else - register_syscore(&aplic_syscore); + return rc; + } + + register_syscore(&aplic_syscore); #ifdef CONFIG_ACPI if (!acpi_disabled) acpi_dev_clear_dependencies(ACPI_COMPANION(dev)); #endif - return rc; + return 0; } static const struct of_device_id aplic_match[] = { From b330fbfd34d7624bec62b99ad88dba2614326a19 Mon Sep 17 00:00:00 2001 From: Jessica Liu Date: Tue, 10 Mar 2026 14:17:31 +0800 Subject: [PATCH 336/487] irqchip/riscv-aplic: Register syscore operations only once Since commit 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC states across suspend/resume"), when multiple NUMA nodes exist and AIA is not configured as "none", aplic_probe() is called multiple times. This leads to register_syscore(&aplic_syscore) being invoked repeatedly, causing the following Oops: list_add double add: new=ffffffffb91461f0, prev=ffffffffb91461f0, next=ffffffffb915c408. [] __list_add_valid_or_report+0x60/0xc0 [] register_syscore+0x3e/0x70 [] aplic_probe+0xc6/0x112 Fix this by registering syscore operations only once, using a static variable aplic_syscore_registered to track registration. [ tglx: Trim backtrace properly ] Fixes: 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC states across suspend/resume") Signed-off-by: Jessica Liu Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260310141731145xMwLsyvXl9Gw-m6A4VRYj@zte.com.cn --- drivers/irqchip/irq-riscv-aplic-main.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c index 8775f188ea4f..9f53979b6962 100644 --- a/drivers/irqchip/irq-riscv-aplic-main.c +++ b/drivers/irqchip/irq-riscv-aplic-main.c @@ -116,6 +116,16 @@ static struct syscore aplic_syscore = { .ops = &aplic_syscore_ops, }; +static bool aplic_syscore_registered __ro_after_init; + +static void aplic_syscore_init(void) +{ + if (!aplic_syscore_registered) { + register_syscore(&aplic_syscore); + aplic_syscore_registered = true; + } +} + static int aplic_pm_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct aplic_priv *priv = container_of(nb, struct aplic_priv, genpd_nb); @@ -379,7 +389,7 @@ static int aplic_probe(struct platform_device *pdev) return rc; } - register_syscore(&aplic_syscore); + aplic_syscore_init(); #ifdef CONFIG_ACPI if (!acpi_disabled) From 6b13cb8f48a42ddf6dd98865b673a82e37ff238b Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Tue, 10 Mar 2026 11:00:58 -0700 Subject: [PATCH 337/487] accel/amdxdna: Fix runtime suspend deadlock when there is pending job The runtime suspend callback drains the running job workqueue before suspending the device. If a job is still executing and calls pm_runtime_resume_and_get(), it can deadlock with the runtime suspend path. Fix this by moving pm_runtime_resume_and_get() from the job execution routine to the job submission routine, ensuring the device is resumed before the job is queued and avoiding the deadlock during runtime suspend. Fixes: 063db451832b ("accel/amdxdna: Enhance runtime power management") Reviewed-by: Mario Limonciello (AMD) Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20260310180058.336348-1-lizhi.hou@amd.com --- drivers/accel/amdxdna/aie2_ctx.c | 14 ++------------ drivers/accel/amdxdna/amdxdna_ctx.c | 10 ++++++++++ 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index afee5e667f77..c0d348884f74 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -165,7 +165,6 @@ aie2_sched_notify(struct amdxdna_sched_job *job) trace_xdna_job(&job->base, job->hwctx->name, "signaled fence", job->seq); - amdxdna_pm_suspend_put(job->hwctx->client->xdna); job->hwctx->priv->completed++; dma_fence_signal(fence); @@ -290,19 +289,11 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; int ret; - ret = amdxdna_pm_resume_get(hwctx->client->xdna); - if (ret) + if (!hwctx->priv->mbox_chann) return NULL; - if (!hwctx->priv->mbox_chann) { - amdxdna_pm_suspend_put(hwctx->client->xdna); - return NULL; - } - - if (!mmget_not_zero(job->mm)) { - amdxdna_pm_suspend_put(hwctx->client->xdna); + if (!mmget_not_zero(job->mm)) return ERR_PTR(-ESRCH); - } kref_get(&job->refcnt); fence = dma_fence_get(job->fence); @@ -333,7 +324,6 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) out: if (ret) { - amdxdna_pm_suspend_put(hwctx->client->xdna); dma_fence_put(job->fence); aie2_job_put(job); mmput(job->mm); diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 666dfd7b2a80..838430903a3e 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -17,6 +17,7 @@ #include "amdxdna_ctx.h" #include "amdxdna_gem.h" #include "amdxdna_pci_drv.h" +#include "amdxdna_pm.h" #define MAX_HWCTX_ID 255 #define MAX_ARG_COUNT 4095 @@ -445,6 +446,7 @@ amdxdna_arg_bos_lookup(struct amdxdna_client *client, void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job) { trace_amdxdna_debug_point(job->hwctx->name, job->seq, "job release"); + amdxdna_pm_suspend_put(job->hwctx->client->xdna); amdxdna_arg_bos_put(job); amdxdna_gem_put_obj(job->cmd_bo); dma_fence_put(job->fence); @@ -482,6 +484,12 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, goto cmd_put; } + ret = amdxdna_pm_resume_get(xdna); + if (ret) { + XDNA_ERR(xdna, "Resume failed, ret %d", ret); + goto put_bos; + } + idx = srcu_read_lock(&client->hwctx_srcu); hwctx = xa_load(&client->hwctx_xa, hwctx_hdl); if (!hwctx) { @@ -522,6 +530,8 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, dma_fence_put(job->fence); unlock_srcu: srcu_read_unlock(&client->hwctx_srcu, idx); + amdxdna_pm_suspend_put(xdna); +put_bos: amdxdna_arg_bos_put(job); cmd_put: amdxdna_gem_put_obj(job->cmd_bo); From 30e4b2290cc2a8d1b9ddb9dcb9c981df1f2a7399 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 10 Mar 2026 08:53:50 +0200 Subject: [PATCH 338/487] ASoC: codecs: rt1011: Use component to get the dapm context in spk_mode_put The correct helper to use in rt1011_recv_spk_mode_put() to retrieve the DAPM context is snd_soc_component_to_dapm(), from kcontrol we will receive NULL pointer. Closes: https://github.com/thesofproject/linux/issues/5691 Fixes: 5b35bb517f27 ("ASoC: codecs: rt1011: convert to snd_soc_dapm_xxx()") Signed-off-by: Peter Ujfalusi Link: https://patch.msgid.link/20260310065350.18921-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt1011.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt1011.c b/sound/soc/codecs/rt1011.c index 9f34a6a35487..03f31d9d916e 100644 --- a/sound/soc/codecs/rt1011.c +++ b/sound/soc/codecs/rt1011.c @@ -1047,7 +1047,7 @@ static int rt1011_recv_spk_mode_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_to_dapm(kcontrol); + struct snd_soc_dapm_context *dapm = snd_soc_component_to_dapm(component); struct rt1011_priv *rt1011 = snd_soc_component_get_drvdata(component); From e809085f492842ce7a519c9ef72d40f4bca89c13 Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Mon, 10 Nov 2025 11:13:38 -0800 Subject: [PATCH 339/487] i40e: fix src IP mask checks and memcpy argument names in cloud filter Fix following issues in the IPv4 and IPv6 cloud filter handling logic in both the add and delete paths: - The source-IP mask check incorrectly compares mask.src_ip[0] against tcf.dst_ip[0]. Update it to compare against tcf.src_ip[0]. This likely goes unnoticed because the check is in an "else if" path that only executes when dst_ip is not set, most cloud filter use cases focus on destination-IP matching, and the buggy condition can accidentally evaluate true in some cases. - memcpy() for the IPv4 source address incorrectly uses ARRAY_SIZE(tcf.dst_ip) instead of ARRAY_SIZE(tcf.src_ip), although both arrays are the same size. - The IPv4 memcpy operations used ARRAY_SIZE(tcf.dst_ip) and ARRAY_SIZE (tcf.src_ip), Update these to use sizeof(cfilter->ip.v4.dst_ip) and sizeof(cfilter->ip.v4.src_ip) to ensure correct and explicit copy size. - In the IPv6 delete path, memcmp() uses sizeof(src_ip6) when comparing dst_ip6 fields. Replace this with sizeof(dst_ip6) to make the intent explicit, even though both fields are struct in6_addr. Fixes: e284fc280473 ("i40e: Add and delete cloud filter") Signed-off-by: Alok Tiwari Reviewed-by: Aleksandr Loktionov Reviewed-by: Paul Menzel Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index fdf40f8fb239..a26c3d47ec15 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3833,10 +3833,10 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) cfilter.n_proto = ETH_P_IP; if (mask.dst_ip[0] & tcf.dst_ip[0]) memcpy(&cfilter.ip.v4.dst_ip, tcf.dst_ip, - ARRAY_SIZE(tcf.dst_ip)); - else if (mask.src_ip[0] & tcf.dst_ip[0]) + sizeof(cfilter.ip.v4.dst_ip)); + else if (mask.src_ip[0] & tcf.src_ip[0]) memcpy(&cfilter.ip.v4.src_ip, tcf.src_ip, - ARRAY_SIZE(tcf.dst_ip)); + sizeof(cfilter.ip.v4.src_ip)); break; case VIRTCHNL_TCP_V6_FLOW: cfilter.n_proto = ETH_P_IPV6; @@ -3891,7 +3891,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) /* for ipv6, mask is set for all sixteen bytes (4 words) */ if (cfilter.n_proto == ETH_P_IPV6 && mask.dst_ip[3]) if (memcmp(&cfilter.ip.v6.dst_ip6, &cf->ip.v6.dst_ip6, - sizeof(cfilter.ip.v6.src_ip6))) + sizeof(cfilter.ip.v6.dst_ip6))) continue; if (mask.vlan_id) if (cfilter.vlan_id != cf->vlan_id) @@ -3979,10 +3979,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) cfilter->n_proto = ETH_P_IP; if (mask.dst_ip[0] & tcf.dst_ip[0]) memcpy(&cfilter->ip.v4.dst_ip, tcf.dst_ip, - ARRAY_SIZE(tcf.dst_ip)); - else if (mask.src_ip[0] & tcf.dst_ip[0]) + sizeof(cfilter->ip.v4.dst_ip)); + else if (mask.src_ip[0] & tcf.src_ip[0]) memcpy(&cfilter->ip.v4.src_ip, tcf.src_ip, - ARRAY_SIZE(tcf.dst_ip)); + sizeof(cfilter->ip.v4.src_ip)); break; case VIRTCHNL_TCP_V6_FLOW: cfilter->n_proto = ETH_P_IPV6; From e94eaef11142b01f77bf8ba4d0b59720b7858109 Mon Sep 17 00:00:00 2001 From: Matt Vollrath Date: Tue, 24 Feb 2026 18:28:33 -0500 Subject: [PATCH 340/487] e1000/e1000e: Fix leak in DMA error cleanup If an error is encountered while mapping TX buffers, the driver should unmap any buffers already mapped for that skb. Because count is incremented after a successful mapping, it will always match the correct number of unmappings needed when dma_error is reached. Decrementing count before the while loop in dma_error causes an off-by-one error. If any mapping was successful before an unsuccessful mapping, exactly one DMA mapping would leak. In these commits, a faulty while condition caused an infinite loop in dma_error: Commit 03b1320dfcee ("e1000e: remove use of skb_dma_map from e1000e driver") Commit 602c0554d7b0 ("e1000: remove use of skb_dma_map from e1000 driver") Commit c1fa347f20f1 ("e1000/e1000e/igb/igbvf/ixgb/ixgbe: Fix tests of unsigned in *_tx_map()") fixed the infinite loop, but introduced the off-by-one error. This issue may still exist in the igbvf driver, but I did not address it in this patch. Fixes: c1fa347f20f1 ("e1000/e1000e/igb/igbvf/ixgb/ixgbe: Fix tests of unsigned in *_tx_map()") Assisted-by: Claude:claude-4.6-opus Signed-off-by: Matt Vollrath Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000/e1000_main.c | 2 -- drivers/net/ethernet/intel/e1000e/netdev.c | 2 -- 2 files changed, 4 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 3d7648a119e5..9b09eb144b81 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2952,8 +2952,6 @@ static int e1000_tx_map(struct e1000_adapter *adapter, dma_error: dev_err(&pdev->dev, "TX DMA map failed\n"); buffer_info->dma = 0; - if (count) - count--; while (count--) { if (i == 0) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 35dab1e3132f..9befdacd6730 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5652,8 +5652,6 @@ static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb, dma_error: dev_err(&pdev->dev, "Tx DMA map failed\n"); buffer_info->dma = 0; - if (count) - count--; while (count--) { if (i == 0) From 4a7d2729dc99437dbb880a64c47828c0d191b308 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sat, 7 Mar 2026 18:20:16 -0300 Subject: [PATCH 341/487] smb: client: fix atomic open with O_DIRECT & O_SYNC When user application requests O_DIRECT|O_SYNC along with O_CREAT on open(2), CREATE_NO_BUFFER and CREATE_WRITE_THROUGH bits were missed in CREATE request when performing an atomic open, thus leading to potentially data integrity issues. Fix this by setting those missing bits in CREATE request when O_DIRECT|O_SYNC has been specified in cifs_do_create(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Paulo Alcantara (Red Hat) Reviewed-by: David Howells Acked-by: Henrique Carvalho Cc: Tom Talpey Cc: linux-cifs@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Steve French --- fs/smb/client/cifsglob.h | 11 +++++++++++ fs/smb/client/dir.c | 1 + fs/smb/client/file.c | 18 +++--------------- 3 files changed, 15 insertions(+), 15 deletions(-) diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 6f9b6c72962b..bb0fe4b60240 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -20,6 +20,7 @@ #include #include #include +#include #include "cifs_fs_sb.h" #include "cifsacl.h" #include @@ -2375,4 +2376,14 @@ static inline bool cifs_forced_shutdown(const struct cifs_sb_info *sbi) return cifs_sb_flags(sbi) & CIFS_MOUNT_SHUTDOWN; } +static inline int cifs_open_create_options(unsigned int oflags, int opts) +{ + /* O_SYNC also has bit for O_DSYNC so following check picks up either */ + if (oflags & O_SYNC) + opts |= CREATE_WRITE_THROUGH; + if (oflags & O_DIRECT) + opts |= CREATE_NO_BUFFER; + return opts; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 953f1fee8cb8..4bc217e9a727 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -308,6 +308,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned goto out; } + create_options |= cifs_open_create_options(oflags, create_options); /* * if we're not using unix extensions, see if we need to set * ATTR_READONLY on the create call diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index cffcf82c1b69..13dda87f7711 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -584,15 +584,8 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ *********************************************************************/ disposition = cifs_get_disposition(f_flags); - /* BB pass O_SYNC flag through on file attributes .. BB */ - - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ - if (f_flags & O_SYNC) - create_options |= CREATE_WRITE_THROUGH; - - if (f_flags & O_DIRECT) - create_options |= CREATE_NO_BUFFER; + create_options |= cifs_open_create_options(f_flags, create_options); retry_open: oparms = (struct cifs_open_parms) { @@ -1314,13 +1307,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) rdwr_for_fscache = 1; desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); - - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ - if (cfile->f_flags & O_SYNC) - create_options |= CREATE_WRITE_THROUGH; - - if (cfile->f_flags & O_DIRECT) - create_options |= CREATE_NO_BUFFER; + create_options |= cifs_open_create_options(cfile->f_flags, + create_options); if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); From fae11330dc0642065568d6c0045322293fe59bc6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Mar 2026 16:07:13 +0100 Subject: [PATCH 342/487] smb: client: fix sbflags initialization The newly introduced variable is initialized in an #ifdef block but used outside of it, leading to undefined behavior when CONFIG_CIFS_ALLOW_INSECURE_LEGACY is disabled: fs/smb/client/dir.c:417:9: error: variable 'sbflags' is uninitialized when used here [-Werror,-Wuninitialized] 417 | if (sbflags & CIFS_MOUNT_DYNPERM) | ^~~~~~~ Move the initialization into the declaration, the same way as the other similar function do it. Fixes: 4fc3a433c139 ("smb: client: use atomic_t for mnt_cifs_flags") Signed-off-by: Arnd Bergmann Reviewed-by: Paulo Alcantara (Red Hat) Signed-off-by: Steve French --- fs/smb/client/dir.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 4bc217e9a727..6d2378eeb7f6 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -187,7 +187,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned const char *full_path; void *page = alloc_dentry_path(); struct inode *newinode = NULL; - unsigned int sbflags; + unsigned int sbflags = cifs_sb_flags(cifs_sb); int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; @@ -368,7 +368,6 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned * If Open reported that we actually created a file then we now have to * set the mode if possible. */ - sbflags = cifs_sb_flags(cifs_sb); if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) { struct cifs_unix_set_info_args args = { .mode = mode, From d78840a6a38d312dc1a51a65317bb67e46f0b929 Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Mon, 9 Mar 2026 16:00:49 +0530 Subject: [PATCH 343/487] smb: client: fix in-place encryption corruption in SMB2_write() SMB2_write() places write payload in iov[1..n] as part of rq_iov. smb3_init_transform_rq() pointer-shares rq_iov, so crypt_message() encrypts iov[1] in-place, replacing the original plaintext with ciphertext. On a replayable error, the retry sends the same iov[1] which now contains ciphertext instead of the original data, resulting in corruption. The corruption is most likely to be observed when connections are unstable, as reconnects trigger write retries that re-send the already-encrypted data. This affects SFU mknod, MF symlinks, etc. On kernels before 6.10 (prior to the netfs conversion), sync writes also used this path and were similarly affected. The async write path wasn't unaffected as it uses rq_iter which gets deep-copied. Fix by moving the write payload into rq_iter via iov_iter_kvec(), so smb3_init_transform_rq() deep-copies it before encryption. Cc: stable@vger.kernel.org #6.3+ Acked-by: Henrique Carvalho Acked-by: Shyam Prasad N Acked-by: Paulo Alcantara (Red Hat) Signed-off-by: Bharath SM Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index c43ca74e8704..5188218c25be 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -5307,7 +5307,10 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, memset(&rqst, 0, sizeof(struct smb_rqst)); rqst.rq_iov = iov; - rqst.rq_nvec = n_vec + 1; + /* iov[0] is the SMB header; move payload to rq_iter for encryption safety */ + rqst.rq_nvec = 1; + iov_iter_kvec(&rqst.rq_iter, ITER_SOURCE, &iov[1], n_vec, + io_parms->length); if (retries) { /* Back-off before retry */ From 88d37abb366be95d772ceb4c7f26772e78447252 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Tue, 10 Mar 2026 21:08:47 +0800 Subject: [PATCH 344/487] smb/client: only export symbol for 'smb2maperror-test' module Only export smb2_get_err_map_test smb2_error_map_table_test and smb2_error_map_num symbol for 'smb2maperror-test' module. Fixes: 7d0bf050a587 ("smb/client: make SMB2 maperror KUnit tests a separate module") Signed-off-by: Ye Bin Reviewed-by: ChenXiaoSong Signed-off-by: Steve French --- fs/smb/client/smb2maperror.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index f4cff44e2796..2b8782c4f684 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -109,6 +109,9 @@ int __init smb2_init_maperror(void) } #if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS) +#define EXPORT_SYMBOL_FOR_SMB_TEST(sym) \ + EXPORT_SYMBOL_FOR_MODULES(sym, "smb2maperror_test") + /* Previous prototype for eliminating the build warning. */ const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status); @@ -116,11 +119,11 @@ const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status) { return smb2_get_err_map(smb2_status); } -EXPORT_SYMBOL_GPL(smb2_get_err_map_test); +EXPORT_SYMBOL_FOR_SMB_TEST(smb2_get_err_map_test); const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table; -EXPORT_SYMBOL_GPL(smb2_error_map_table_test); +EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_table_test); unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table); -EXPORT_SYMBOL_GPL(smb2_error_map_num); +EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_num); #endif From 85b731ad4bbf6eb3fedf267ab00be3596f148432 Mon Sep 17 00:00:00 2001 From: Alan Borzeszkowski Date: Mon, 9 Mar 2026 16:37:03 +0100 Subject: [PATCH 345/487] spi: intel-pci: Add support for Nova Lake mobile SPI flash Add Intel Nova Lake PCD-H SPI serial flash PCI ID to the list of supported devices. Signed-off-by: Alan Borzeszkowski Acked-by: Mika Westerberg Link: https://patch.msgid.link/20260309153703.74282-1-alan.borzeszkowski@linux.intel.com Signed-off-by: Mark Brown --- drivers/spi/spi-intel-pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index bce3d149bea1..d8ef8f89330a 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -96,6 +96,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0xd323), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xe323), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xe423), (unsigned long)&cnl_info }, { }, From 881a0263d502e1a93ebc13a78254e9ad19520232 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Sat, 7 Mar 2026 15:08:54 +0800 Subject: [PATCH 346/487] net: macb: Shuffle the tx ring before enabling tx Quanyang observed that when using an NFS rootfs on an AMD ZynqMp board, the rootfs may take an extended time to recover after a suspend. Upon investigation, it was determined that the issue originates from a problem in the macb driver. According to the Zynq UltraScale TRM [1], when transmit is disabled, the transmit buffer queue pointer resets to point to the address specified by the transmit buffer queue base address register. In the current implementation, the code merely resets `queue->tx_head` and `queue->tx_tail` to '0'. This approach presents several issues: - Packets already queued in the tx ring are silently lost, leading to memory leaks since the associated skbs cannot be released. - Concurrent write access to `queue->tx_head` and `queue->tx_tail` may occur from `macb_tx_poll()` or `macb_start_xmit()` when these values are reset to '0'. - The transmission may become stuck on a packet that has already been sent out, with its 'TX_USED' bit set, but has not yet been processed. However, due to the manipulation of 'queue->tx_head' and 'queue->tx_tail', `macb_tx_poll()` incorrectly assumes there are no packets to handle because `queue->tx_head == queue->tx_tail`. This issue is only resolved when a new packet is placed at this position. This is the root cause of the prolonged recovery time observed for the NFS root filesystem. To resolve this issue, shuffle the tx ring and tx skb array so that the first unsent packet is positioned at the start of the tx ring. Additionally, ensure that updates to `queue->tx_head` and `queue->tx_tail` are properly protected with the appropriate lock. [1] https://docs.amd.com/v/u/en-US/ug1085-zynq-ultrascale-trm Fixes: bf9cf80cab81 ("net: macb: Fix tx/rx malfunction after phy link down and up") Reported-by: Quanyang Wang Signed-off-by: Kevin Hao Cc: stable@vger.kernel.org Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260307-zynqmp-v2-1-6ef98a70e1d0@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 98 +++++++++++++++++++++++- 1 file changed, 95 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 5bc35f651ebd..f290d608b409 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include "macb.h" @@ -668,6 +669,97 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, netif_tx_stop_all_queues(ndev); } +/* Use juggling algorithm to left rotate tx ring and tx skb array */ +static void gem_shuffle_tx_one_ring(struct macb_queue *queue) +{ + unsigned int head, tail, count, ring_size, desc_size; + struct macb_tx_skb tx_skb, *skb_curr, *skb_next; + struct macb_dma_desc *desc_curr, *desc_next; + unsigned int i, cycles, shift, curr, next; + struct macb *bp = queue->bp; + unsigned char desc[24]; + unsigned long flags; + + desc_size = macb_dma_desc_get_size(bp); + + if (WARN_ON_ONCE(desc_size > ARRAY_SIZE(desc))) + return; + + spin_lock_irqsave(&queue->tx_ptr_lock, flags); + head = queue->tx_head; + tail = queue->tx_tail; + ring_size = bp->tx_ring_size; + count = CIRC_CNT(head, tail, ring_size); + + if (!(tail % ring_size)) + goto unlock; + + if (!count) { + queue->tx_head = 0; + queue->tx_tail = 0; + goto unlock; + } + + shift = tail % ring_size; + cycles = gcd(ring_size, shift); + + for (i = 0; i < cycles; i++) { + memcpy(&desc, macb_tx_desc(queue, i), desc_size); + memcpy(&tx_skb, macb_tx_skb(queue, i), + sizeof(struct macb_tx_skb)); + + curr = i; + next = (curr + shift) % ring_size; + + while (next != i) { + desc_curr = macb_tx_desc(queue, curr); + desc_next = macb_tx_desc(queue, next); + + memcpy(desc_curr, desc_next, desc_size); + + if (next == ring_size - 1) + desc_curr->ctrl &= ~MACB_BIT(TX_WRAP); + if (curr == ring_size - 1) + desc_curr->ctrl |= MACB_BIT(TX_WRAP); + + skb_curr = macb_tx_skb(queue, curr); + skb_next = macb_tx_skb(queue, next); + memcpy(skb_curr, skb_next, sizeof(struct macb_tx_skb)); + + curr = next; + next = (curr + shift) % ring_size; + } + + desc_curr = macb_tx_desc(queue, curr); + memcpy(desc_curr, &desc, desc_size); + if (i == ring_size - 1) + desc_curr->ctrl &= ~MACB_BIT(TX_WRAP); + if (curr == ring_size - 1) + desc_curr->ctrl |= MACB_BIT(TX_WRAP); + memcpy(macb_tx_skb(queue, curr), &tx_skb, + sizeof(struct macb_tx_skb)); + } + + queue->tx_head = count; + queue->tx_tail = 0; + + /* Make descriptor updates visible to hardware */ + wmb(); + +unlock: + spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); +} + +/* Rotate the queue so that the tail is at index 0 */ +static void gem_shuffle_tx_rings(struct macb *bp) +{ + struct macb_queue *queue; + int q; + + for (q = 0, queue = bp->queues; q < bp->num_queues; q++, queue++) + gem_shuffle_tx_one_ring(queue); +} + static void macb_mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, @@ -706,8 +798,6 @@ static void macb_mac_link_up(struct phylink_config *config, ctrl |= MACB_BIT(PAE); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - queue->tx_head = 0; - queue->tx_tail = 0; queue_writel(queue, IER, bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -721,8 +811,10 @@ static void macb_mac_link_up(struct phylink_config *config, spin_unlock_irqrestore(&bp->lock, flags); - if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { macb_set_tx_clk(bp, speed); + gem_shuffle_tx_rings(bp); + } /* Enable Rx and Tx; Enable PTP unicast */ ctrl = macb_readl(bp, NCR); From 28b225282d44e2ef40e7f46cfdbd5d1b20b8874f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Mar 2026 17:39:07 -0700 Subject: [PATCH 347/487] page_pool: store detach_time as ktime_t to avoid false-negatives While testing other changes in vng I noticed that nl_netdev.page_pool_check flakes. This never happens in real CI. Turns out vng may boot and get to that test in less than a second. page_pool_detached() records the detach time in seconds, so if vng is fast enough detach time is set to 0. Other code treats 0 as "not detached". detach_time is only used to report the state to the user, so it's not a huge deal in practice but let's fix it. Store the raw ktime_t (nanoseconds) instead. A nanosecond value of 0 is practically impossible. Acked-by: Jesper Dangaard Brouer Fixes: 69cb4952b6f6 ("net: page_pool: report when page pool was destroyed") Link: https://patch.msgid.link/20260310003907.3540019-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/page_pool/types.h | 2 +- net/core/page_pool_user.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 0d453484a585..cdd95477af7a 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -247,7 +247,7 @@ struct page_pool { /* User-facing fields, protected by page_pools_lock */ struct { struct hlist_node list; - u64 detach_time; + ktime_t detach_time; u32 id; } user; }; diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index c82a95beceff..ee5060d8eec0 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -245,7 +245,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, goto err_cancel; if (pool->user.detach_time && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, - pool->user.detach_time)) + ktime_divns(pool->user.detach_time, NSEC_PER_SEC))) goto err_cancel; if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL)) @@ -337,7 +337,7 @@ int page_pool_list(struct page_pool *pool) void page_pool_detached(struct page_pool *pool) { mutex_lock(&page_pools_lock); - pool->user.detach_time = ktime_get_boottime_seconds(); + pool->user.detach_time = ktime_get_boottime(); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); mutex_unlock(&page_pools_lock); } From 2503d08f8a2de618e5c3a8183b250ff4a2e2d52c Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Mon, 9 Mar 2026 13:24:09 +0000 Subject: [PATCH 348/487] net: ethernet: arc: emac: quiesce interrupts before requesting IRQ Normal RX/TX interrupts are enabled later, in arc_emac_open(), so probe should not see interrupt delivery in the usual case. However, hardware may still present stale or latched interrupt status left by firmware or the bootloader. If probe later unwinds after devm_request_irq() has installed the handler, such a stale interrupt can still reach arc_emac_intr() during teardown and race with release of the associated net_device. Avoid that window by putting the device into a known quiescent state before requesting the IRQ: disable all EMAC interrupt sources and clear any pending EMAC interrupt status bits. This keeps the change hardware-focused and minimal, while preventing spurious IRQ delivery from leftover state. Fixes: e4f2379db6c6 ("ethernet/arc/arc_emac - Add new driver") Cc: stable@vger.kernel.org Signed-off-by: Fan Wu Link: https://patch.msgid.link/20260309132409.584966-1-fanwu01@zju.edu.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/arc/emac_main.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 8283aeee35fb..dde4046cbf01 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -934,6 +934,17 @@ int arc_emac_probe(struct net_device *ndev, int interface) /* Set poll rate so that it polls every 1 ms */ arc_reg_set(priv, R_POLLRATE, clock_frequency / 1000000); + /* + * Put the device into a known quiescent state before requesting + * the IRQ. Clear only EMAC interrupt status bits here; leave the + * MDIO completion bit alone and avoid writing TXPL_MASK, which is + * used to force TX polling rather than acknowledge interrupts. + */ + arc_reg_set(priv, R_ENABLE, 0); + arc_reg_set(priv, R_STATUS, RXINT_MASK | TXINT_MASK | ERR_MASK | + TXCH_MASK | MSER_MASK | RXCR_MASK | + RXFR_MASK | RXFL_MASK); + ndev->irq = irq; dev_info(dev, "IRQ is %d\n", ndev->irq); From f441b489cc66fbc44d78b6c123e74283b8077431 Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Tue, 10 Mar 2026 00:41:56 +0000 Subject: [PATCH 349/487] net: dsa: mxl862xx: don't set user_mii_bus The PHY addresses in the MII bus are not equal to the port addresses, so the bus cannot be assigned as user_mii_bus. Falling back on the user_mii_bus in case a PHY isn't declared in device tree will result in using the wrong (in this case: off-by-+1) PHY. Remove the wrong assignment. Fixes: 23794bec1cb60 ("net: dsa: add basic initial driver for MxL862xx switches") Suggested-by: Vladimir Oltean Signed-off-by: Daniel Golle Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/0f0df310fd8cab57e0e5e3d0831dd057fd05bcd5.1773103271.git.daniel@makrotopia.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mxl862xx/mxl862xx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c index b1e2094b5816..d7ab04f5afef 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx.c +++ b/drivers/net/dsa/mxl862xx/mxl862xx.c @@ -149,7 +149,6 @@ static int mxl862xx_setup_mdio(struct dsa_switch *ds) return -ENOMEM; bus->priv = priv; - ds->user_mii_bus = bus; bus->name = KBUILD_MODNAME "-mii"; snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev)); bus->read_c45 = mxl862xx_phy_read_c45_mii_bus; From 57885276cc16a2e2b76282c808a4e84cbecb3aae Mon Sep 17 00:00:00 2001 From: Paul Moses Date: Mon, 9 Mar 2026 17:35:10 +0000 Subject: [PATCH 350/487] net-shapers: don't free reply skb after genlmsg_reply() genlmsg_reply() hands the reply skb to netlink, and netlink_unicast() consumes it on all return paths, whether the skb is queued successfully or freed on an error path. net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit() currently jump to free_msg after genlmsg_reply() fails and call nlmsg_free(msg), which can hit the same skb twice. Return the genlmsg_reply() error directly and keep free_msg only for pre-reply failures. Fixes: 4b623f9f0f59 ("net-shapers: implement NL get operation") Fixes: 553ea9f1efd6 ("net: shaper: implement introspection support") Cc: stable@vger.kernel.org Signed-off-by: Paul Moses Link: https://patch.msgid.link/20260309173450.538026-2-p@1g4.org Signed-off-by: Jakub Kicinski --- net/shaper/shaper.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 005bfc766e22..3fd6629cb999 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -759,11 +759,7 @@ int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_msg; - ret = genlmsg_reply(msg, info); - if (ret) - goto free_msg; - - return 0; + return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); @@ -1313,10 +1309,7 @@ int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_msg; - ret = genlmsg_reply(msg, info); - if (ret) - goto free_msg; - return 0; + return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); From 908c344d5cfac4160f49715da9efacdf5b6a28bd Mon Sep 17 00:00:00 2001 From: Nicolai Buchwitz Date: Tue, 10 Mar 2026 06:49:35 +0100 Subject: [PATCH 351/487] net: bcmgenet: fix broken EEE by converting to phylib-managed state The bcmgenet EEE implementation is broken in several ways. phy_support_eee() is never called, so the PHY never advertises EEE and phylib never sets phydev->enable_tx_lpi. bcmgenet_mac_config() checks priv->eee.eee_enabled to decide whether to enable the MAC LPI logic, but that field is never initialised to true, so the MAC never enters Low Power Idle even when EEE is negotiated - wasting the power savings EEE is designed to provide. The only way to get EEE working at all is a manual 'ethtool --set-eee eth0 eee on' after every link-up, and even then bcmgenet_get_eee() immediately clobbers the reported state because phy_ethtool_get_eee() overwrites eee_enabled and tx_lpi_enabled with the uninitialised PHY eee_cfg values. Finally, bcmgenet_mac_config() is only called on link-up, so EEE is never disabled in hardware on link-down. Fix all of this by removing the MAC-side EEE state tracking (priv->eee) and aligning with the pattern used by other non-phylink MAC drivers such as FEC. Call phy_support_eee() in bcmgenet_mii_probe() so the PHY advertises EEE link modes and phylib tracks negotiation state. Move the EEE hardware control to bcmgenet_mii_setup(), which is called on every link event, and drive it directly from phydev->enable_tx_lpi - the flag phylib sets when EEE is negotiated and the user has not disabled it. This enables EEE automatically once the link partner agrees and disables it cleanly on link-down. Make bcmgenet_get_eee() and bcmgenet_set_eee() pure passthroughs to phy_ethtool_get_eee() and phy_ethtool_set_eee(), with the MAC hardware register read/written for tx_lpi_timer. Drop struct ethtool_keee eee from struct bcmgenet_priv. Fixes: fe0d4fd9285e ("net: phy: Keep track of EEE configuration") Link: https://lore.kernel.org/netdev/d352039f-4cbb-41e6-9aeb-0b4f3941b54c@lunn.ch/ Suggested-by: Andrew Lunn Signed-off-by: Nicolai Buchwitz Reviewed-by: Florian Fainelli Tested-by: Florian Fainelli Link: https://patch.msgid.link/20260310054935.1238594-1-nb@tipi-net.de Signed-off-by: Jakub Kicinski --- .../net/ethernet/broadcom/genet/bcmgenet.c | 31 +++++++------------ .../net/ethernet/broadcom/genet/bcmgenet.h | 5 +-- drivers/net/ethernet/broadcom/genet/bcmmii.c | 10 +++--- 3 files changed, 18 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index a71cd729fde6..482a31e7b72b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1342,8 +1342,7 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev, } } -void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, - bool tx_lpi_enabled) +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) { struct bcmgenet_priv *priv = netdev_priv(dev); u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL; @@ -1363,7 +1362,7 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, /* Enable EEE and switch to a 27Mhz clock automatically */ reg = bcmgenet_readl(priv->base + off); - if (tx_lpi_enabled) + if (enable) reg |= TBUF_EEE_EN | TBUF_PM_EN; else reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); @@ -1382,14 +1381,12 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, priv->clk_eee_enabled = false; } - priv->eee.eee_enabled = enable; - priv->eee.tx_lpi_enabled = tx_lpi_enabled; } static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct ethtool_keee *p = &priv->eee; + int ret; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1397,17 +1394,21 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e) if (!dev->phydev) return -ENODEV; - e->tx_lpi_enabled = p->tx_lpi_enabled; + ret = phy_ethtool_get_eee(dev->phydev, e); + if (ret) + return ret; + + /* tx_lpi_timer is maintained by the MAC hardware register; the + * PHY-level eee_cfg timer is not set for GENET. + */ e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER); - return phy_ethtool_get_eee(dev->phydev, e); + return 0; } static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct ethtool_keee *p = &priv->eee; - bool active; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1415,15 +1416,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e) if (!dev->phydev) return -ENODEV; - p->eee_enabled = e->eee_enabled; - - if (!p->eee_enabled) { - bcmgenet_eee_enable_set(dev, false, false); - } else { - active = phy_init_eee(dev->phydev, false) >= 0; - bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER); - bcmgenet_eee_enable_set(dev, active, e->tx_lpi_enabled); - } + bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER); return phy_ethtool_set_eee(dev->phydev, e); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 5ec3979779ec..9e4110c7fdf6 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -665,8 +665,6 @@ struct bcmgenet_priv { u8 sopass[SOPASS_MAX]; struct bcmgenet_mib_counters mib; - - struct ethtool_keee eee; }; static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv) @@ -749,7 +747,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode); -void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, - bool tx_lpi_enabled); +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable); #endif /* __BCMGENET_H__ */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 38f854b94a79..a4e0d5a68268 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -29,7 +29,6 @@ static void bcmgenet_mac_config(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; u32 reg, cmd_bits = 0; - bool active; /* speed */ if (phydev->speed == SPEED_1000) @@ -90,10 +89,6 @@ static void bcmgenet_mac_config(struct net_device *dev) bcmgenet_umac_writel(priv, reg, UMAC_CMD); spin_unlock_bh(&priv->reg_lock); - active = phy_init_eee(phydev, 0) >= 0; - bcmgenet_eee_enable_set(dev, - priv->eee.eee_enabled && active, - priv->eee.tx_lpi_enabled); } /* setup netdev link state when PHY link status change and @@ -113,6 +108,8 @@ void bcmgenet_mii_setup(struct net_device *dev) bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } + bcmgenet_eee_enable_set(dev, phydev->enable_tx_lpi); + phy_print_status(phydev); } @@ -412,6 +409,9 @@ int bcmgenet_mii_probe(struct net_device *dev) /* Indicate that the MAC is responsible for PHY PM */ dev->phydev->mac_managed_pm = true; + if (!GENET_IS_V1(priv)) + phy_support_eee(dev->phydev); + return 0; } From 5182e5ec4355dd690307f5d5c28cbfc5b2c06a97 Mon Sep 17 00:00:00 2001 From: Lianqin Hu Date: Wed, 11 Mar 2026 07:22:38 +0000 Subject: [PATCH 352/487] ALSA: usb-audio: Add iface reset and delay quirk for SPACETOUCH USB Audio Setting up the interface when suspended/resumeing fail on this card. Adding a reset and delay quirk will eliminate this problem. usb 1-1: New USB device found, idVendor=0666, idProduct=0880 usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3 usb 1-1: Product: USB Audio usb 1-1: Manufacturer: SPACETOUCH usb 1-1: SerialNumber: 000000000 Signed-off-by: Lianqin Hu Signed-off-by: Takashi Iwai Link: https://patch.msgid.link/TYUPR06MB6217ACC80B70BE25D87456B0D247A@TYUPR06MB6217.apcprd06.prod.outlook.com --- sound/usb/quirks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index d54a1a44a69b..049a94079f9e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2243,6 +2243,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IFACE_DELAY | QUIRK_FLAG_FORCE_IFACE_RESET), DEVICE_FLG(0x0661, 0x0883, /* iBasso DC04 Ultra */ QUIRK_FLAG_DSD_RAW), + DEVICE_FLG(0x0666, 0x0880, /* SPACETOUCH USB Audio */ + QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x06f8, 0xb000, /* Hercules DJ Console (Windows Edition) */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */ From 49973e2a4156a88e46ba1c1c484b7c214199a181 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 9 Mar 2026 09:14:49 +0100 Subject: [PATCH 353/487] drm/loongson: Mark driver as orphaned The maintainer's email address has been bouncing for months. Mark the loongson DRM driver as orphaned. Signed-off-by: Thomas Zimmermann Acked-by: Maxime Ripard Link: https://patch.msgid.link/20260309081503.67123-1-tzimmermann@suse.de --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 55af015174a5..b35fc8e062c3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8630,9 +8630,8 @@ F: drivers/gpu/drm/lima/ F: include/uapi/drm/lima_drm.h DRM DRIVERS FOR LOONGSON -M: Sui Jingfeng L: dri-devel@lists.freedesktop.org -S: Supported +S: Orphan T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/loongson/ From 770444611f047dbfd4517ec0bc1b179d40c2f346 Mon Sep 17 00:00:00 2001 From: Raphael Zimmer Date: Thu, 26 Feb 2026 16:07:31 +0100 Subject: [PATCH 354/487] libceph: Use u32 for non-negative values in ceph_monmap_decode() This patch fixes unnecessary implicit conversions that change signedness of blob_len and num_mon in ceph_monmap_decode(). Currently blob_len and num_mon are (signed) int variables. They are used to hold values that are always non-negative and get assigned in ceph_decode_32_safe(), which is meant to assign u32 values. Both variables are subsequently used as unsigned values, and the value of num_mon is further assigned to monmap->num_mon, which is of type u32. Therefore, both variables should be of type u32. This is especially relevant for num_mon. If the value read from the incoming message is very large, it is interpreted as a negative value, and the check for num_mon > CEPH_MAX_MON does not catch it. This leads to the attempt to allocate a very large chunk of memory for monmap, which will most likely fail. In this case, an unnecessary attempt to allocate memory is performed, and -ENOMEM is returned instead of -EINVAL. Cc: stable@vger.kernel.org Signed-off-by: Raphael Zimmer Reviewed-by: Viacheslav Dubeyko Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- net/ceph/mon_client.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 5136b3766c44..d5080530ce0c 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -72,8 +72,8 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2) struct ceph_monmap *monmap = NULL; struct ceph_fsid fsid; u32 struct_len; - int blob_len; - int num_mon; + u32 blob_len; + u32 num_mon; u8 struct_v; u32 epoch; int ret; @@ -112,7 +112,7 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2) } ceph_decode_32_safe(p, end, num_mon, e_inval); - dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch, + dout("%s fsid %pU epoch %u num_mon %u\n", __func__, &fsid, epoch, num_mon); if (num_mon > CEPH_MAX_MON) goto e_inval; From b282c43ed156ae15ea76748fc15cd5c39dc9ab72 Mon Sep 17 00:00:00 2001 From: Raphael Zimmer Date: Tue, 10 Mar 2026 15:28:15 +0100 Subject: [PATCH 355/487] libceph: Fix potential out-of-bounds access in ceph_handle_auth_reply() This patch fixes an out-of-bounds access in ceph_handle_auth_reply() that can be triggered by a message of type CEPH_MSG_AUTH_REPLY. In ceph_handle_auth_reply(), the value of the payload_len field of such a message is stored in a variable of type int. A value greater than INT_MAX leads to an integer overflow and is interpreted as a negative value. This leads to decrementing the pointer address by this value and subsequently accessing it because ceph_decode_need() only checks that the memory access does not exceed the end address of the allocation. This patch fixes the issue by changing the data type of payload_len to u32. Additionally, the data type of result_msg_len is changed to u32, as it is also a variable holding a non-negative length. Also, an additional layer of sanity checks is introduced, ensuring that directly after reading it from the message, payload_len and result_msg_len are not greater than the overall segment length. BUG: KASAN: slab-out-of-bounds in ceph_handle_auth_reply+0x642/0x7a0 [libceph] Read of size 4 at addr ffff88811404df14 by task kworker/20:1/262 CPU: 20 UID: 0 PID: 262 Comm: kworker/20:1 Not tainted 6.19.2 #5 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Workqueue: ceph-msgr ceph_con_workfn [libceph] Call Trace: dump_stack_lvl+0x76/0xa0 print_report+0xd1/0x620 ? __pfx__raw_spin_lock_irqsave+0x10/0x10 ? kasan_complete_mode_report_info+0x72/0x210 kasan_report+0xe7/0x130 ? ceph_handle_auth_reply+0x642/0x7a0 [libceph] ? ceph_handle_auth_reply+0x642/0x7a0 [libceph] __asan_report_load_n_noabort+0xf/0x20 ceph_handle_auth_reply+0x642/0x7a0 [libceph] mon_dispatch+0x973/0x23d0 [libceph] ? apparmor_socket_recvmsg+0x6b/0xa0 ? __pfx_mon_dispatch+0x10/0x10 [libceph] ? __kasan_check_write+0x14/0x30i ? mutex_unlock+0x7f/0xd0 ? __pfx_mutex_unlock+0x10/0x10 ? __pfx_do_recvmsg+0x10/0x10 [libceph] ceph_con_process_message+0x1f1/0x650 [libceph] process_message+0x1e/0x450 [libceph] ceph_con_v2_try_read+0x2e48/0x6c80 [libceph] ? __pfx_ceph_con_v2_try_read+0x10/0x10 [libceph] ? save_fpregs_to_fpstate+0xb0/0x230 ? raw_spin_rq_unlock+0x17/0xa0 ? finish_task_switch.isra.0+0x13b/0x760 ? __switch_to+0x385/0xda0 ? __kasan_check_write+0x14/0x30 ? mutex_lock+0x8d/0xe0 ? __pfx_mutex_lock+0x10/0x10 ceph_con_workfn+0x248/0x10c0 [libceph] process_one_work+0x629/0xf80 ? __kasan_check_write+0x14/0x30 worker_thread+0x87f/0x1570 ? __pfx__raw_spin_lock_irqsave+0x10/0x10 ? __pfx_try_to_wake_up+0x10/0x10 ? kasan_print_address_stack_frame+0x1f7/0x280 ? __pfx_worker_thread+0x10/0x10 kthread+0x396/0x830 ? __pfx__raw_spin_lock_irq+0x10/0x10 ? __pfx_kthread+0x10/0x10 ? __kasan_check_write+0x14/0x30 ? recalc_sigpending+0x180/0x210 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x3f7/0x610 ? __pfx_ret_from_fork+0x10/0x10 ? __switch_to+0x385/0xda0 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 [ idryomov: replace if statements with ceph_decode_need() for payload_len and result_msg_len ] Cc: stable@vger.kernel.org Signed-off-by: Raphael Zimmer Reviewed-by: Viacheslav Dubeyko Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- net/ceph/auth.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ceph/auth.c b/net/ceph/auth.c index 343c841784ce..901b93530b21 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -205,9 +205,9 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, s32 result; u64 global_id; void *payload, *payload_end; - int payload_len; + u32 payload_len; char *result_msg; - int result_msg_len; + u32 result_msg_len; int ret = -EINVAL; mutex_lock(&ac->mutex); @@ -217,10 +217,12 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, result = ceph_decode_32(&p); global_id = ceph_decode_64(&p); payload_len = ceph_decode_32(&p); + ceph_decode_need(&p, end, payload_len, bad); payload = p; p += payload_len; ceph_decode_need(&p, end, sizeof(u32), bad); result_msg_len = ceph_decode_32(&p); + ceph_decode_need(&p, end, result_msg_len, bad); result_msg = p; p += result_msg_len; if (p != end) From 755a648e78f12574482d4698d877375793867fa1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 6 Mar 2026 21:24:03 -0500 Subject: [PATCH 356/487] time/jiffies: Mark jiffies_64_to_clock_t() notrace The trace_clock_jiffies() function that handles the "uptime" clock for tracing calls jiffies_64_to_clock_t(). This causes the function tracer to constantly recurse when the tracing clock is set to "uptime". Mark it notrace to prevent unnecessary recursion when using the "uptime" clock. Fixes: 58d4e21e50ff3 ("tracing: Fix wraparound problems in "uptime" trace clock") Signed-off-by: Steven Rostedt (Google) Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260306212403.72270bb2@robin --- kernel/time/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/time.c b/kernel/time/time.c index 36fd2313ae7e..0d832317d576 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -697,7 +697,7 @@ EXPORT_SYMBOL(clock_t_to_jiffies); * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ -u64 jiffies_64_to_clock_t(u64 x) +notrace u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ From b2e48c429ec54715d16fefa719dd2fbded2e65be Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:28:53 +0100 Subject: [PATCH 357/487] sched/mmcid: Prevent CID stalls due to concurrent forks A newly forked task is accounted as MMCID user before the task is visible in the process' thread list and the global task list. This creates the following problem: CPU1 CPU2 fork() sched_mm_cid_fork(tnew1) tnew1->mm.mm_cid_users++; tnew1->mm_cid.cid = getcid() -> preemption fork() sched_mm_cid_fork(tnew2) tnew2->mm.mm_cid_users++; // Reaches the per CPU threshold mm_cid_fixup_tasks_to_cpus() for_each_other(current, p) .... As tnew1 is not visible yet, this fails to fix up the already allocated CID of tnew1. As a consequence a subsequent schedule in might fail to acquire a (transitional) CID and the machine stalls. Move the invocation of sched_mm_cid_fork() after the new task becomes visible in the thread and the task list to prevent this. This also makes it symmetrical vs. exit() where the task is removed as CID user before the task is removed from the thread and task lists. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202525.969061974@kernel.org --- include/linux/sched.h | 2 -- kernel/fork.c | 2 -- kernel/sched/core.c | 22 +++++++++++++++------- 3 files changed, 15 insertions(+), 11 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index a7b4a980eb2f..5a5d3dbc9cdf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2354,7 +2354,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit(struct task_struct *t); static __always_inline int task_mm_cid(struct task_struct *t) { @@ -2363,7 +2362,6 @@ static __always_inline int task_mm_cid(struct task_struct *t) #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit(struct task_struct *t) { } static __always_inline int task_mm_cid(struct task_struct *t) { diff --git a/kernel/fork.c b/kernel/fork.c index 65113a304518..7febf4c2889e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1586,7 +1586,6 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk) tsk->mm = mm; tsk->active_mm = mm; - sched_mm_cid_fork(tsk); return 0; } @@ -2498,7 +2497,6 @@ __latent_entropy struct task_struct *copy_process( exit_nsproxy_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { - sched_mm_cid_exit(p); mm_clear_owner(p->mm, p); mmput(p->mm); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b7f77c165a6e..d25427855b5d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4729,8 +4729,11 @@ void sched_cancel_fork(struct task_struct *p) scx_cancel_fork(p); } +static void sched_mm_cid_fork(struct task_struct *t); + void sched_post_fork(struct task_struct *p) { + sched_mm_cid_fork(p); uclamp_post_fork(p); scx_post_fork(p); } @@ -10646,12 +10649,13 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm) * possible switch back to per task mode happens either in the * deferred handler function or in the next fork()/exit(). * - * The caller has already transferred. The newly incoming task is - * already accounted for, but not yet visible. + * The caller has already transferred so remove it from the users + * count. The incoming task is already visible and has mm_cid.active, + * but has task::mm_cid::cid == UNSET. Still it needs to be accounted + * for. Concurrent fork()s might add more threads, but all of them have + * task::mm_cid::active = 0, so they don't affect the accounting here. */ - users = mm->mm_cid.users - 2; - if (!users) - return; + users = mm->mm_cid.users - 1; guard(rcu)(); for_other_threads(current, t) { @@ -10688,12 +10692,15 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) return mm_update_max_cids(mm); } -void sched_mm_cid_fork(struct task_struct *t) +static void sched_mm_cid_fork(struct task_struct *t) { struct mm_struct *mm = t->mm; bool percpu; - WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET); + if (!mm) + return; + + WARN_ON_ONCE(t->mm_cid.cid != MM_CID_UNSET); guard(mutex)(&mm->mm_cid.mutex); scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) { @@ -10885,6 +10892,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p) } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { } +static inline void sched_mm_cid_fork(struct task_struct *t) { } #endif /* !CONFIG_SCHED_MM_CID */ static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx); From 28b5a1395036d6c7a6c8034d85ad3d7d365f192c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:28:58 +0100 Subject: [PATCH 358/487] sched/mmcid: Handle vfork()/CLONE_VM correctly Matthieu and Jiri reported stalls where a task endlessly loops in mm_get_cid() when scheduling in. It turned out that the logic which handles vfork()'ed tasks is broken. It is invoked when the number of tasks associated to a process is smaller than the number of MMCID users. It then walks the task list to find the vfork()'ed task, but accounts all the already processed tasks as well. If that double processing brings the number of to be handled tasks to 0, the walk stops and the vfork()'ed task's CID is not fixed up. As a consequence a subsequent schedule in fails to acquire a (transitional) CID and the machine stalls. Cure this by removing the accounting condition and make the fixup always walk the full task list if it could not find the exact number of users in the process' thread list. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Closes: https://lore.kernel.org/b24ffcb3-09d5-4e48-9070-0b69bc654281@kernel.org Reported-by: Matthieu Baerts Reported-by: Jiri Slaby Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202526.048657665@kernel.org --- kernel/sched/core.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d25427855b5d..ee59cd19b9a8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10670,10 +10670,7 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm) for_each_process_thread(p, t) { if (t == current || t->mm != mm) continue; - if (mm_cid_fixup_task_to_cpu(t, mm)) { - if (--users == 0) - return; - } + mm_cid_fixup_task_to_cpu(t, mm); } } From 7574ac6e49789ddee1b1be9b2afb42b4a1b4b1f4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:29:04 +0100 Subject: [PATCH 359/487] sched/mmcid: Remove pointless preempt guard This is a leftover from the early versions of this function where it could be invoked without mm::mm_cid::lock held. Remove it and add lockdep asserts instead. Fixes: 653fda7ae73d ("sched/mmcid: Switch over to the new mechanism") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202526.116363613@kernel.org --- kernel/sched/core.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ee59cd19b9a8..f56156f91d08 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10684,6 +10684,8 @@ static void mm_cid_fixup_tasks_to_cpus(void) static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) { + lockdep_assert_held(&mm->mm_cid.lock); + t->mm_cid.active = 1; mm->mm_cid.users++; return mm_update_max_cids(mm); @@ -10736,12 +10738,12 @@ static void sched_mm_cid_fork(struct task_struct *t) static bool sched_mm_cid_remove_user(struct task_struct *t) { + lockdep_assert_held(&t->mm->mm_cid.lock); + t->mm_cid.active = 0; - scoped_guard(preempt) { - /* Clear the transition bit */ - t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); - mm_unset_cid_on_task(t); - } + /* Clear the transition bit */ + t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); + mm_unset_cid_on_task(t); t->mm->mm_cid.users--; return mm_update_max_cids(t->mm); } From 192d852129b1b7c4f0ddbab95d0de1efd5ee1405 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:29:09 +0100 Subject: [PATCH 360/487] sched/mmcid: Avoid full tasklist walks Chasing vfork()'ed tasks on a CID ownership mode switch requires a full task list walk, which is obviously expensive on large systems. Avoid that by keeping a list of tasks using a mm MMCID entity in mm::mm_cid and walk this list instead. This removes the proven to be flaky counting logic and avoids a full task list walk in the case of vfork()'ed tasks. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202526.183824481@kernel.org --- include/linux/rseq_types.h | 6 +++- kernel/fork.c | 1 + kernel/sched/core.c | 56 +++++++++----------------------------- 3 files changed, 19 insertions(+), 44 deletions(-) diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index da5fa6f40294..0b42045988db 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -133,10 +133,12 @@ struct rseq_data { }; * @active: MM CID is active for the task * @cid: The CID associated to the task either permanently or * borrowed from the CPU + * @node: Queued in the per MM MMCID list */ struct sched_mm_cid { unsigned int active; unsigned int cid; + struct hlist_node node; }; /** @@ -157,6 +159,7 @@ struct mm_cid_pcpu { * @work: Regular work to handle the affinity mode change case * @lock: Spinlock to protect against affinity setting which can't take @mutex * @mutex: Mutex to serialize forks and exits related to this mm + * @user_list: List of the MM CID users of a MM * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map * is growth only. * @users: The number of tasks sharing this MM. Separate from mm::mm_users @@ -177,13 +180,14 @@ struct mm_mm_cid { raw_spinlock_t lock; struct mutex mutex; + struct hlist_head user_list; /* Low frequency modified */ unsigned int nr_cpus_allowed; unsigned int users; unsigned int pcpu_thrs; unsigned int update_deferred; -}____cacheline_aligned_in_smp; +} ____cacheline_aligned; #else /* CONFIG_SCHED_MM_CID */ struct mm_mm_cid { }; struct sched_mm_cid { }; diff --git a/kernel/fork.c b/kernel/fork.c index 7febf4c2889e..bc2bf58b93b6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1000,6 +1000,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid.cid = MM_CID_UNSET; tsk->mm_cid.active = 0; + INIT_HLIST_NODE(&tsk->mm_cid.node); #endif return tsk; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f56156f91d08..496dff740dca 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10620,13 +10620,10 @@ static inline void mm_cid_transit_to_cpu(struct task_struct *t, struct mm_cid_pc } } -static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm) +static void mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm) { /* Remote access to mm::mm_cid::pcpu requires rq_lock */ guard(task_rq_lock)(t); - /* If the task is not active it is not in the users count */ - if (!t->mm_cid.active) - return false; if (cid_on_task(t->mm_cid.cid)) { /* If running on the CPU, put the CID in transit mode, otherwise drop it */ if (task_rq(t)->curr == t) @@ -10634,51 +10631,21 @@ static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm else mm_unset_cid_on_task(t); } - return true; -} - -static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm) -{ - struct task_struct *p, *t; - unsigned int users; - - /* - * This can obviously race with a concurrent affinity change, which - * increases the number of allowed CPUs for this mm, but that does - * not affect the mode and only changes the CID constraints. A - * possible switch back to per task mode happens either in the - * deferred handler function or in the next fork()/exit(). - * - * The caller has already transferred so remove it from the users - * count. The incoming task is already visible and has mm_cid.active, - * but has task::mm_cid::cid == UNSET. Still it needs to be accounted - * for. Concurrent fork()s might add more threads, but all of them have - * task::mm_cid::active = 0, so they don't affect the accounting here. - */ - users = mm->mm_cid.users - 1; - - guard(rcu)(); - for_other_threads(current, t) { - if (mm_cid_fixup_task_to_cpu(t, mm)) - users--; - } - - if (!users) - return; - - /* Happens only for VM_CLONE processes. */ - for_each_process_thread(p, t) { - if (t == current || t->mm != mm) - continue; - mm_cid_fixup_task_to_cpu(t, mm); - } } static void mm_cid_fixup_tasks_to_cpus(void) { struct mm_struct *mm = current->mm; + struct task_struct *t; + + lockdep_assert_held(&mm->mm_cid.mutex); + + hlist_for_each_entry(t, &mm->mm_cid.user_list, mm_cid.node) { + /* Current has already transferred before invoking the fixup. */ + if (t != current) + mm_cid_fixup_task_to_cpu(t, mm); + } - mm_cid_do_fixup_tasks_to_cpus(mm); mm_cid_complete_transit(mm, MM_CID_ONCPU); } @@ -10687,6 +10654,7 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) lockdep_assert_held(&mm->mm_cid.lock); t->mm_cid.active = 1; + hlist_add_head(&t->mm_cid.node, &mm->mm_cid.user_list); mm->mm_cid.users++; return mm_update_max_cids(mm); } @@ -10744,6 +10712,7 @@ static bool sched_mm_cid_remove_user(struct task_struct *t) /* Clear the transition bit */ t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); mm_unset_cid_on_task(t); + hlist_del_init(&t->mm_cid.node); t->mm->mm_cid.users--; return mm_update_max_cids(t->mm); } @@ -10886,6 +10855,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p) mutex_init(&mm->mm_cid.mutex); mm->mm_cid.irq_work = IRQ_WORK_INIT_HARD(mm_cid_irq_work); INIT_WORK(&mm->mm_cid.work, mm_cid_work_fn); + INIT_HLIST_HEAD(&mm->mm_cid.user_list); cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); bitmap_zero(mm_cidmask(mm), num_possible_cpus()); } From 393815f57651101f1590632092986d1d5a3a41bd Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 11 Mar 2026 10:58:35 +0000 Subject: [PATCH 361/487] ACPI: OSL: fix __iomem type on return from acpi_os_map_generic_address() The pointer returned from acpi_os_map_generic_address() is tagged with __iomem, so make the rv it is returned to also of void __iomem * type. Fixes the following sparse warning: drivers/acpi/osl.c:1686:20: warning: incorrect type in assignment (different address spaces) drivers/acpi/osl.c:1686:20: expected void *rv drivers/acpi/osl.c:1686:20: got void [noderef] __iomem * Fixes: 6915564dc5a8 ("ACPI: OSL: Change the type of acpi_os_map_generic_address() return value") Signed-off-by: Ben Dooks [ rjw: Subject tweak, added Fixes tag ] Link: https://patch.msgid.link/20260311105835.463030-1-ben.dooks@codethink.co.uk Signed-off-by: Rafael J. Wysocki --- drivers/acpi/osl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 5b777316b9ac..62b9c83d4f20 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -1681,7 +1681,7 @@ acpi_status __init acpi_os_initialize(void) * Use acpi_os_map_generic_address to pre-map the reset * register if it's in system memory. */ - void *rv; + void __iomem *rv; rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register); pr_debug("%s: Reset register mapping %s\n", __func__, From 743956bb9990214ff1dac66ef59e27221dc3c2d8 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 2 Mar 2026 23:35:56 +0800 Subject: [PATCH 362/487] spi: dt-bindings: sun6i: Allow Dual SPI and Quad SPI for newer SoCs Support for Dual SPI and Quad SPI was added to the Linux driver in commit 0605d9fb411f ("spi: sun6i: add quirk for dual and quad SPI modes support") and commit 25453d797d7a ("spi: sun6i: add dual and quad SPI modes support for R329/D1/R528/T113s"). However the binding was never updated to allow these modes. Allow them by adding 2 and 4 to the allowed bus widths for the newer variants. While at it, also add 0 to the allowed bus widths. This signals that RX or TX is not available, i.e. the MISO or MOSI pin is disconnected. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Chen-Yu Tsai Link: https://patch.msgid.link/20260302153559.3199783-2-wens@kernel.org Signed-off-by: Mark Brown --- .../bindings/spi/allwinner,sun6i-a31-spi.yaml | 29 +++++++++++++++---- 1 file changed, 24 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml index a6067030c5ed..6af4ff233158 100644 --- a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml +++ b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml @@ -6,9 +6,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A31 SPI Controller -allOf: - - $ref: spi-controller.yaml - maintainers: - Chen-Yu Tsai - Maxime Ripard @@ -82,11 +79,11 @@ patternProperties: spi-rx-bus-width: items: - - const: 1 + enum: [0, 1, 2, 4] spi-tx-bus-width: items: - - const: 1 + enum: [0, 1, 2, 4] required: - compatible @@ -95,6 +92,28 @@ required: - clocks - clock-names +allOf: + - $ref: spi-controller.yaml + - if: + not: + properties: + compatible: + contains: + enum: + - allwinner,sun50i-r329-spi + - allwinner,sun55i-a523-spi + then: + patternProperties: + "^.*@[0-9a-f]+": + properties: + spi-rx-bus-width: + items: + enum: [0, 1] + + spi-tx-bus-width: + items: + enum: [0, 1] + unevaluatedProperties: false examples: From 362c490980867930a098b99f421268fbd7ca05fd Mon Sep 17 00:00:00 2001 From: Long Li Date: Tue, 10 Mar 2026 20:32:33 +0800 Subject: [PATCH 363/487] xfs: fix integer overflow in bmap intent sort comparator xfs_bmap_update_diff_items() sorts bmap intents by inode number using a subtraction of two xfs_ino_t (uint64_t) values, with the result truncated to int. This is incorrect when two inode numbers differ by more than INT_MAX (2^31 - 1), which is entirely possible on large XFS filesystems. Fix this by replacing the subtraction with cmp_int(). Cc: # v4.9 Fixes: 9f3afb57d5f1 ("xfs: implement deferred bmbt map/unmap operations") Signed-off-by: Long Li Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_bmap_item.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index e8775f254c89..b237a25d6045 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -245,7 +245,7 @@ xfs_bmap_update_diff_items( struct xfs_bmap_intent *ba = bi_entry(a); struct xfs_bmap_intent *bb = bi_entry(b); - return ba->bi_owner->i_ino - bb->bi_owner->i_ino; + return cmp_int(ba->bi_owner->i_ino, bb->bi_owner->i_ino); } /* Log bmap updates in the intent item. */ From 53f3a900e9a383d47af7253076e19f510c5708d0 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Tue, 10 Mar 2026 10:42:46 +0800 Subject: [PATCH 364/487] ASoC: amd: acp3x-rt5682-max9836: Add missing error check for clock acquisition The acp3x_5682_init() function did not check the return value of clk_get(), which could lead to dereferencing error pointers in rt5682_clk_enable(). Fix this by: 1. Changing clk_get() to the device-managed devm_clk_get(). 2. Adding proper IS_ERR() checks for both clock acquisitions. Fixes: 6b8e4e7db3cd ("ASoC: amd: Add machine driver for Raven based platform") Signed-off-by: Chen Ni Link: https://patch.msgid.link/20260310024246.2153827-1-nichen@iscas.ac.cn Signed-off-by: Mark Brown --- sound/soc/amd/acp3x-rt5682-max9836.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c index 4ca1978020a9..d1eb6f12a183 100644 --- a/sound/soc/amd/acp3x-rt5682-max9836.c +++ b/sound/soc/amd/acp3x-rt5682-max9836.c @@ -94,8 +94,13 @@ static int acp3x_5682_init(struct snd_soc_pcm_runtime *rtd) return ret; } - rt5682_dai_wclk = clk_get(component->dev, "rt5682-dai-wclk"); - rt5682_dai_bclk = clk_get(component->dev, "rt5682-dai-bclk"); + rt5682_dai_wclk = devm_clk_get(component->dev, "rt5682-dai-wclk"); + if (IS_ERR(rt5682_dai_wclk)) + return PTR_ERR(rt5682_dai_wclk); + + rt5682_dai_bclk = devm_clk_get(component->dev, "rt5682-dai-bclk"); + if (IS_ERR(rt5682_dai_bclk)) + return PTR_ERR(rt5682_dai_bclk); ret = snd_soc_card_jack_new_pins(card, "Headset Jack", SND_JACK_HEADSET | From e293015ba76eb96ce4ebed7e3b2cb1a7d319f3e9 Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Wed, 18 Feb 2026 21:21:07 +0100 Subject: [PATCH 365/487] usb: core: don't power off roothub PHYs if phy_set_mode() fails Remove the error path from the usb_phy_roothub_set_mode() function. The code is clearly wrong, because phy_set_mode() calls can't be balanced with phy_power_off() calls. Additionally, the usb_phy_roothub_set_mode() function is called only from usb_add_hcd() before it powers on the PHYs, so powering off those makes no sense anyway. Presumably, the code is copy-pasted from the phy_power_on() function without adjusting the error handling. Cc: stable@vger.kernel.org # v5.1+ Fixes: b97a31348379 ("usb: core: comply to PHY framework") Signed-off-by: Gabor Juhos Reviewed-by: Miquel Raynal Link: https://patch.msgid.link/20260218-usb-phy-poweroff-fix-v1-1-66e6831e860e@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/phy.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/usb/core/phy.c b/drivers/usb/core/phy.c index faa20054ad5a..4bba1c275740 100644 --- a/drivers/usb/core/phy.c +++ b/drivers/usb/core/phy.c @@ -200,16 +200,10 @@ int usb_phy_roothub_set_mode(struct usb_phy_roothub *phy_roothub, list_for_each_entry(roothub_entry, head, list) { err = phy_set_mode(roothub_entry->phy, mode); if (err) - goto err_out; + return err; } return 0; - -err_out: - list_for_each_entry_continue_reverse(roothub_entry, head, list) - phy_power_off(roothub_entry->phy); - - return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_set_mode); From 416909962e7cdf29fd01ac523c953f37708df93d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 17 Feb 2026 22:07:47 -0500 Subject: [PATCH 366/487] USB: usbcore: Introduce usb_bulk_msg_killable() The synchronous message API in usbcore (usb_control_msg(), usb_bulk_msg(), and so on) uses uninterruptible waits. However, drivers may call these routines in the context of a user thread, which means it ought to be possible to at least kill them. For this reason, introduce a new usb_bulk_msg_killable() function which behaves the same as usb_bulk_msg() except for using wait_for_completion_killable_timeout() instead of wait_for_completion_timeout(). The same can be done later for usb_control_msg() later on, if it turns out to be needed. Signed-off-by: Alan Stern Suggested-by: Oliver Neukum Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Link: https://patch.msgid.link/248628b4-cc83-4e81-a620-3ce4e0376d41@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/message.c | 79 +++++++++++++++++++++++++++++++++----- include/linux/usb.h | 5 ++- 2 files changed, 72 insertions(+), 12 deletions(-) diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index ea970ddf8879..d97ec7e8c280 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -42,16 +42,17 @@ static void usb_api_blocking_completion(struct urb *urb) /* - * Starts urb and waits for completion or timeout. Note that this call - * is NOT interruptible. Many device driver i/o requests should be - * interruptible and therefore these drivers should implement their - * own interruptible routines. + * Starts urb and waits for completion or timeout. + * Whether or not the wait is killable depends on the flag passed in. + * For example, compare usb_bulk_msg() and usb_bulk_msg_killable(). */ -static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length) +static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length, + bool killable) { struct api_context ctx; unsigned long expire; int retval; + long rc; init_completion(&ctx.done); urb->context = &ctx; @@ -61,12 +62,21 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length) goto out; expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT; - if (!wait_for_completion_timeout(&ctx.done, expire)) { + if (killable) + rc = wait_for_completion_killable_timeout(&ctx.done, expire); + else + rc = wait_for_completion_timeout(&ctx.done, expire); + if (rc <= 0) { usb_kill_urb(urb); - retval = (ctx.status == -ENOENT ? -ETIMEDOUT : ctx.status); + if (ctx.status != -ENOENT) + retval = ctx.status; + else if (rc == 0) + retval = -ETIMEDOUT; + else + retval = rc; dev_dbg(&urb->dev->dev, - "%s timed out on ep%d%s len=%u/%u\n", + "%s timed out or killed on ep%d%s len=%u/%u\n", current->comm, usb_endpoint_num(&urb->ep->desc), usb_urb_dir_in(urb) ? "in" : "out", @@ -100,7 +110,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev, usb_fill_control_urb(urb, usb_dev, pipe, (unsigned char *)cmd, data, len, usb_api_blocking_completion, NULL); - retv = usb_start_wait_urb(urb, timeout, &length); + retv = usb_start_wait_urb(urb, timeout, &length, false); if (retv < 0) return retv; else @@ -385,10 +395,59 @@ int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, usb_fill_bulk_urb(urb, usb_dev, pipe, data, len, usb_api_blocking_completion, NULL); - return usb_start_wait_urb(urb, timeout, actual_length); + return usb_start_wait_urb(urb, timeout, actual_length, false); } EXPORT_SYMBOL_GPL(usb_bulk_msg); +/** + * usb_bulk_msg_killable - Builds a bulk urb, sends it off and waits for completion in a killable state + * @usb_dev: pointer to the usb device to send the message to + * @pipe: endpoint "pipe" to send the message to + * @data: pointer to the data to send + * @len: length in bytes of the data to send + * @actual_length: pointer to a location to put the actual length transferred + * in bytes + * @timeout: time in msecs to wait for the message to complete before + * timing out (if 0 the wait is forever) + * + * Context: task context, might sleep. + * + * This function is just like usb_blk_msg() except that it waits in a + * killable state. + * + * Return: + * If successful, 0. Otherwise a negative error number. The number of actual + * bytes transferred will be stored in the @actual_length parameter. + * + */ +int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, + void *data, int len, int *actual_length, int timeout) +{ + struct urb *urb; + struct usb_host_endpoint *ep; + + ep = usb_pipe_endpoint(usb_dev, pipe); + if (!ep || len < 0) + return -EINVAL; + + urb = usb_alloc_urb(0, GFP_KERNEL); + if (!urb) + return -ENOMEM; + + if ((ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_INT) { + pipe = (pipe & ~(3 << 30)) | (PIPE_INTERRUPT << 30); + usb_fill_int_urb(urb, usb_dev, pipe, data, len, + usb_api_blocking_completion, NULL, + ep->desc.bInterval); + } else + usb_fill_bulk_urb(urb, usb_dev, pipe, data, len, + usb_api_blocking_completion, NULL); + + return usb_start_wait_urb(urb, timeout, actual_length, true); +} +EXPORT_SYMBOL_GPL(usb_bulk_msg_killable); + /*-------------------------------------------------------------------*/ static void sg_clean(struct usb_sg_request *io) diff --git a/include/linux/usb.h b/include/linux/usb.h index fbfcc70b07fb..57ceeb02a7cb 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1868,8 +1868,9 @@ extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout); extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, - void *data, int len, int *actual_length, - int timeout); + void *data, int len, int *actual_length, int timeout); +extern int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, + void *data, int len, int *actual_length, int timeout); /* wrappers around usb_control_msg() for the most common standard requests */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, From 7784caa413a89487dd14dd5c41db8753483b2acb Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 17 Feb 2026 22:09:22 -0500 Subject: [PATCH 367/487] USB: usbtmc: Use usb_bulk_msg_killable() with user-specified timeouts The usbtmc driver accepts timeout values specified by the user in an ioctl command, and uses these timeouts for some usb_bulk_msg() calls. Since the user can specify arbitrarily long timeouts and usb_bulk_msg() uses unkillable waits, call usb_bulk_msg_killable() instead to avoid the possibility of the user hanging a kernel thread indefinitely. Reported-by: syzbot+25ba18e2c5040447585d@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-usb/8e1c7ac5-e076-44b0-84b8-1b34b20f0ae1@suse.com/T/#t Tested-by: syzbot+25ba18e2c5040447585d@syzkaller.appspotmail.com Signed-off-by: Alan Stern Fixes: 048c6d88a021 ("usb: usbtmc: Add ioctls to set/get usb timeout") CC: stable@vger.kernel.org Link: https://patch.msgid.link/81c6fc24-0607-40f1-8c20-5270dab2fad5@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/usbtmc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 2526a0e03cde..d39bbfd7fd18 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -727,7 +727,7 @@ static int usbtmc488_ioctl_trigger(struct usbtmc_file_data *file_data) buffer[1] = data->bTag; buffer[2] = ~data->bTag; - retval = usb_bulk_msg(data->usb_dev, + retval = usb_bulk_msg_killable(data->usb_dev, usb_sndbulkpipe(data->usb_dev, data->bulk_out), buffer, USBTMC_HEADER_SIZE, @@ -1347,7 +1347,7 @@ static int send_request_dev_dep_msg_in(struct usbtmc_file_data *file_data, buffer[11] = 0; /* Reserved */ /* Send bulk URB */ - retval = usb_bulk_msg(data->usb_dev, + retval = usb_bulk_msg_killable(data->usb_dev, usb_sndbulkpipe(data->usb_dev, data->bulk_out), buffer, USBTMC_HEADER_SIZE, @@ -1419,7 +1419,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, actual = 0; /* Send bulk URB */ - retval = usb_bulk_msg(data->usb_dev, + retval = usb_bulk_msg_killable(data->usb_dev, usb_rcvbulkpipe(data->usb_dev, data->bulk_in), buffer, bufsize, &actual, From 1015c27a5e1a63efae2b18a9901494474b4d1dc3 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 17 Feb 2026 22:10:32 -0500 Subject: [PATCH 368/487] USB: core: Limit the length of unkillable synchronous timeouts The usb_control_msg(), usb_bulk_msg(), and usb_interrupt_msg() APIs in usbcore allow unlimited timeout durations. And since they use uninterruptible waits, this leaves open the possibility of hanging a task for an indefinitely long time, with no way to kill it short of unplugging the target device. To prevent this sort of problem, enforce a maximum limit on the length of these unkillable timeouts. The limit chosen here, somewhat arbitrarily, is 60 seconds. On many systems (although not all) this is short enough to avoid triggering the kernel's hung-task detector. In addition, clear up the ambiguity of negative timeout values by treating them the same as 0, i.e., using the maximum allowed timeout. Signed-off-by: Alan Stern Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Link: https://patch.msgid.link/15fc9773-a007-47b0-a703-df89a8cf83dd@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/message.c | 27 +++++++++++++-------------- include/linux/usb.h | 3 +++ 2 files changed, 16 insertions(+), 14 deletions(-) diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index d97ec7e8c280..2ab120ce2fa8 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -45,6 +45,8 @@ static void usb_api_blocking_completion(struct urb *urb) * Starts urb and waits for completion or timeout. * Whether or not the wait is killable depends on the flag passed in. * For example, compare usb_bulk_msg() and usb_bulk_msg_killable(). + * + * For non-killable waits, we enforce a maximum limit on the timeout value. */ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length, bool killable) @@ -61,7 +63,9 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length, if (unlikely(retval)) goto out; - expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT; + if (!killable && (timeout <= 0 || timeout > USB_MAX_SYNCHRONOUS_TIMEOUT)) + timeout = USB_MAX_SYNCHRONOUS_TIMEOUT; + expire = (timeout > 0) ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT; if (killable) rc = wait_for_completion_killable_timeout(&ctx.done, expire); else @@ -127,8 +131,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev, * @index: USB message index value * @data: pointer to the data to send * @size: length in bytes of the data to send - * @timeout: time in msecs to wait for the message to complete before timing - * out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * @@ -183,8 +186,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg); * @index: USB message index value * @driver_data: pointer to the data to send * @size: length in bytes of the data to send - * @timeout: time in msecs to wait for the message to complete before timing - * out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * @memflags: the flags for memory allocation for buffers * * Context: !in_interrupt () @@ -242,8 +244,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send); * @index: USB message index value * @driver_data: pointer to the data to be filled in by the message * @size: length in bytes of the data to be received - * @timeout: time in msecs to wait for the message to complete before timing - * out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * @memflags: the flags for memory allocation for buffers * * Context: !in_interrupt () @@ -314,8 +315,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_recv); * @len: length in bytes of the data to send * @actual_length: pointer to a location to put the actual length transferred * in bytes - * @timeout: time in msecs to wait for the message to complete before - * timing out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * @@ -347,8 +347,7 @@ EXPORT_SYMBOL_GPL(usb_interrupt_msg); * @len: length in bytes of the data to send * @actual_length: pointer to a location to put the actual length transferred * in bytes - * @timeout: time in msecs to wait for the message to complete before - * timing out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * @@ -408,12 +407,12 @@ EXPORT_SYMBOL_GPL(usb_bulk_msg); * @actual_length: pointer to a location to put the actual length transferred * in bytes * @timeout: time in msecs to wait for the message to complete before - * timing out (if 0 the wait is forever) + * timing out (if <= 0, the wait is as long as possible) * * Context: task context, might sleep. * - * This function is just like usb_blk_msg() except that it waits in a - * killable state. + * This function is just like usb_blk_msg(), except that it waits in a + * killable state and there is no limit on the timeout length. * * Return: * If successful, 0. Otherwise a negative error number. The number of actual diff --git a/include/linux/usb.h b/include/linux/usb.h index 57ceeb02a7cb..04277af4bb9d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1862,6 +1862,9 @@ void usb_free_noncoherent(struct usb_device *dev, size_t size, * SYNCHRONOUS CALL SUPPORT * *-------------------------------------------------------------------*/ +/* Maximum value allowed for timeout in synchronous routines below */ +#define USB_MAX_SYNCHRONOUS_TIMEOUT 60000 /* ms */ + extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout); From 45dba8011efac11a2f360383221b541f5ea53ce5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 23 Feb 2026 13:19:43 +0100 Subject: [PATCH 369/487] usb: misc: uss720: properly clean up reference in uss720_probe() If get_1284_register() fails, the usb device reference count is incorrect and needs to be properly dropped before returning. That will happen when the kref is dropped in the call to destroy_priv(), so jump to that error path instead of returning directly. Cc: stable Assisted-by: gkh_clanker_2000 Signed-off-by: Greg Kroah-Hartman Link: https://patch.msgid.link/2026022342-smokiness-stove-d792@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/uss720.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index ec8bd968c4de..a8af7615b1bf 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -736,7 +736,7 @@ static int uss720_probe(struct usb_interface *intf, ret = get_1284_register(pp, 0, ®, GFP_KERNEL); dev_dbg(&intf->dev, "reg: %7ph\n", priv->reg); if (ret < 0) - return ret; + goto probe_abort; ret = usb_find_last_int_in_endpoint(interface, &epd); if (!ret) { From 9f6a983cfa22ac662c86e60816d3a357d4b551e9 Mon Sep 17 00:00:00 2001 From: Jie Deng Date: Fri, 27 Feb 2026 16:49:31 +0800 Subject: [PATCH 370/487] usb: core: new quirk to handle devices with zero configurations Some USB devices incorrectly report bNumConfigurations as 0 in their device descriptor, which causes the USB core to reject them during enumeration. logs: usb 1-2: device descriptor read/64, error -71 usb 1-2: no configurations usb 1-2: can't read configurations, error -22 However, these devices actually work correctly when treated as having a single configuration. Add a new quirk USB_QUIRK_FORCE_ONE_CONFIG to handle such devices. When this quirk is set, assume the device has 1 configuration instead of failing with -EINVAL. This quirk is applied to the device with VID:PID 5131:2007 which exhibits this behavior. Signed-off-by: Jie Deng Link: https://patch.msgid.link/20260227084931.1527461-1-dengjie03@kylinos.cn Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/kernel-parameters.txt | 3 +++ drivers/usb/core/config.c | 6 +++++- drivers/usb/core/quirks.c | 5 +++++ include/linux/usb/quirks.h | 3 +++ 4 files changed, 16 insertions(+), 1 deletion(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index cb850e5290c2..7d907efe9f49 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -8183,6 +8183,9 @@ Kernel parameters p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT (Reduce timeout of the SET_ADDRESS request from 5000 ms to 500 ms); + q = USB_QUIRK_FORCE_ONE_CONFIG (Device + claims zero configurations, + forcing to 1); Example: quirks=0781:5580:bk,0a5c:5834:gij usbhid.mousepoll= diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 1cd5fa61dc76..6a1fd967e0a6 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -927,7 +927,11 @@ int usb_get_configuration(struct usb_device *dev) dev->descriptor.bNumConfigurations = ncfg = USB_MAXCONFIG; } - if (ncfg < 1) { + if (ncfg < 1 && dev->quirks & USB_QUIRK_FORCE_ONE_CONFIG) { + dev_info(ddev, "Device claims zero configurations, forcing to 1\n"); + dev->descriptor.bNumConfigurations = 1; + ncfg = 1; + } else if (ncfg < 1) { dev_err(ddev, "no configurations\n"); return -EINVAL; } diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index e347236d83e8..7bd408db05f4 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -140,6 +140,8 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp) case 'p': flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT; break; + case 'q': + flags |= USB_QUIRK_FORCE_ONE_CONFIG; /* Ignore unrecognized flag characters */ } } @@ -589,6 +591,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* VCOM device */ { USB_DEVICE(0x4296, 0x7570), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Noji-MCS SmartCard Reader */ + { USB_DEVICE(0x5131, 0x2007), .driver_info = USB_QUIRK_FORCE_ONE_CONFIG }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 2f7bd2fdc616..b3cc7beab4a3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -78,4 +78,7 @@ /* skip BOS descriptor request */ #define USB_QUIRK_NO_BOS BIT(17) +/* Device claims zero configurations, forcing to 1 */ +#define USB_QUIRK_FORCE_ONE_CONFIG BIT(18) + #endif /* __LINUX_USB_QUIRKS_H */ From 7f58b4148ef5d8ee0fb7d8113dcc38ff5374babc Mon Sep 17 00:00:00 2001 From: John Keeping Date: Fri, 27 Feb 2026 11:15:39 +0000 Subject: [PATCH 371/487] usb: gadget: f_hid: fix SuperSpeed descriptors When adding dynamic configuration for bInterval, the value was removed from the static SuperSpeed endpoint descriptors but was not set from the configured value in hidg_bind(). Thus at SuperSpeed the interrupt endpoints have bInterval as zero which is not valid per the USB specification. Add the missing setting for SuperSpeed endpoints. Fixes: ea34925f5b2ee ("usb: gadget: hid: allow dynamic interval configuration via configfs") Cc: stable Signed-off-by: John Keeping Acked-by: Peter Korsgaard Link: https://patch.msgid.link/20260227111540.431521-1-jkeeping@inmusicbrands.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_hid.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 8c855c00b887..8812ebf33d14 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -1207,9 +1207,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) if (!hidg->interval_user_set) { hidg_fs_in_ep_desc.bInterval = 10; hidg_hs_in_ep_desc.bInterval = 4; + hidg_ss_in_ep_desc.bInterval = 4; } else { hidg_fs_in_ep_desc.bInterval = hidg->interval; hidg_hs_in_ep_desc.bInterval = hidg->interval; + hidg_ss_in_ep_desc.bInterval = hidg->interval; } hidg_ss_out_comp_desc.wBytesPerInterval = @@ -1239,9 +1241,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) if (!hidg->interval_user_set) { hidg_fs_out_ep_desc.bInterval = 10; hidg_hs_out_ep_desc.bInterval = 4; + hidg_ss_out_ep_desc.bInterval = 4; } else { hidg_fs_out_ep_desc.bInterval = hidg->interval; hidg_hs_out_ep_desc.bInterval = hidg->interval; + hidg_ss_out_ep_desc.bInterval = hidg->interval; } status = usb_assign_descriptors(f, hidg_fs_descriptors_intout, From 8479891d1f04a8ce55366fe4ca361ccdb96f02e1 Mon Sep 17 00:00:00 2001 From: Seungjin Bae Date: Sat, 28 Feb 2026 05:43:25 -0500 Subject: [PATCH 372/487] usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks() The `check_command_size_in_blocks()` function calculates the data size in bytes by left shifting `common->data_size_from_cmnd` by the block size (`common->curlun->blkbits`). However, it does not validate whether this shift operation will cause an integer overflow. Initially, the block size is set up in `fsg_lun_open()` , and the `common->data_size_from_cmnd` is set up in `do_scsi_command()`. During initialization, there is no integer overflow check for the interaction between two variables. So if a malicious USB host sends a SCSI READ or WRITE command requesting a large amount of data (`common->data_size_from_cmnd`), the left shift operation can wrap around. This results in a truncated data size, which can bypass boundary checks and potentially lead to memory corruption or out-of-bounds accesses. Fix this by using the check_shl_overflow() macro to safely perform the shift and catch any overflows. Fixes: 144974e7f9e3 ("usb: gadget: mass_storage: support multi-luns with different logic block size") Signed-off-by: Seungjin Bae Reviewed-by: Alan Stern Link: https://patch.msgid.link/20260228104324.1696455-2-eeodqql09@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_mass_storage.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 6af96e2b44eb..b7b06cb79ff5 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -180,6 +180,7 @@ #include #include #include +#include #include #include #include @@ -1853,8 +1854,15 @@ static int check_command_size_in_blocks(struct fsg_common *common, int cmnd_size, enum data_direction data_dir, unsigned int mask, int needs_medium, const char *name) { - if (common->curlun) - common->data_size_from_cmnd <<= common->curlun->blkbits; + if (common->curlun) { + if (check_shl_overflow(common->data_size_from_cmnd, + common->curlun->blkbits, + &common->data_size_from_cmnd)) { + common->phase_error = 1; + return -EINVAL; + } + } + return check_command(common, cmnd_size, data_dir, mask, needs_medium, name); } From 14ae24cba291bddfdc296bbcbfd00cd09d0498ef Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 1 Mar 2026 12:44:40 +0000 Subject: [PATCH 373/487] usb: cdc-acm: Restore CAP_BRK functionnality to CH343 The CH343 USB/serial adapter is as buggy as it is popular (very). One of its quirks is that despite being capable of signalling a BREAK condition, it doesn't advertise it. This used to work nonetheless until 66aad7d8d3ec5 ("usb: cdc-acm: return correct error code on unsupported break") applied some reasonable restrictions, preventing breaks from being emitted on devices that do not advertise CAP_BRK. Add a quirk for this particular device, so that breaks can still be produced on some of my machines attached to my console server. Fixes: 66aad7d8d3ec5 ("usb: cdc-acm: return correct error code on unsupported break") Signed-off-by: Marc Zyngier Cc: stable Cc: Oliver Neukum Cc: Greg Kroah-Hartman Acked-by: Oliver Neukum Link: https://patch.msgid.link/20260301124440.1192752-1-maz@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 5 +++++ drivers/usb/class/cdc-acm.h | 1 + 2 files changed, 6 insertions(+) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index ad38c746270a..7ede29d4c7c1 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1379,6 +1379,8 @@ static int acm_probe(struct usb_interface *intf, acm->ctrl_caps = h.usb_cdc_acm_descriptor->bmCapabilities; if (quirks & NO_CAP_LINE) acm->ctrl_caps &= ~USB_CDC_CAP_LINE; + if (quirks & MISSING_CAP_BRK) + acm->ctrl_caps |= USB_CDC_CAP_BRK; acm->ctrlsize = ctrlsize; acm->readsize = readsize; acm->rx_buflimit = num_rx_buf; @@ -2002,6 +2004,9 @@ static const struct usb_device_id acm_ids[] = { .driver_info = IGNORE_DEVICE, }, + /* CH343 supports CAP_BRK, but doesn't advertise it */ + { USB_DEVICE(0x1a86, 0x55d3), .driver_info = MISSING_CAP_BRK, }, + /* control interfaces without any protocol set */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM, USB_CDC_PROTO_NONE) }, diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 759ac15631d3..76f73853a60b 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -113,3 +113,4 @@ struct acm { #define CLEAR_HALT_CONDITIONS BIT(5) #define SEND_ZERO_PACKET BIT(6) #define DISABLE_ECHO BIT(7) +#define MISSING_CAP_BRK BIT(8) From 3cbc242b88c607f55da3d0d0d336b49bf1e20412 Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Tue, 3 Mar 2026 07:33:44 +0000 Subject: [PATCH 374/487] usb: renesas_usbhs: fix use-after-free in ISR during device removal In usbhs_remove(), the driver frees resources (including the pipe array) while the interrupt handler (usbhs_interrupt) is still registered. If an interrupt fires after usbhs_pipe_remove() but before the driver is fully unbound, the ISR may access freed memory, causing a use-after-free. Fix this by calling devm_free_irq() before freeing resources. This ensures the interrupt handler is both disabled and synchronized (waits for any running ISR to complete) before usbhs_pipe_remove() is called. Fixes: f1407d5c6624 ("usb: renesas_usbhs: Add Renesas USBHS common code") Cc: stable Suggested-by: Alan Stern Signed-off-by: Fan Wu Link: https://patch.msgid.link/20260303073344.34577-1-fanwu01@zju.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/renesas_usbhs/common.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index cf4a0367d6d6..8c93bde4b816 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -815,6 +815,15 @@ static void usbhs_remove(struct platform_device *pdev) usbhs_platform_call(priv, hardware_exit, pdev); reset_control_assert(priv->rsts); + + /* + * Explicitly free the IRQ to ensure the interrupt handler is + * disabled and synchronized before freeing resources. + * devm_free_irq() calls free_irq() which waits for any running + * ISR to complete, preventing UAF. + */ + devm_free_irq(&pdev->dev, priv->irq, priv); + usbhs_mod_remove(priv); usbhs_fifo_remove(priv); usbhs_pipe_remove(priv); From 8df672bfe3ec2268c2636584202755898e547173 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 4 Mar 2026 14:01:12 +0100 Subject: [PATCH 375/487] usb: class: cdc-wdm: fix reordering issue in read code path Quoting the bug report: Due to compiler optimization or CPU out-of-order execution, the desc->length update can be reordered before the memmove. If this happens, wdm_read() can see the new length and call copy_to_user() on uninitialized memory. This also violates LKMM data race rules [1]. Fix it by using WRITE_ONCE and memory barriers. Fixes: afba937e540c9 ("USB: CDC WDM driver") Cc: stable Signed-off-by: Oliver Neukum Closes: https://lore.kernel.org/linux-usb/CALbr=LbrUZn_cfp7CfR-7Z5wDTHF96qeuM=3fO2m-q4cDrnC4A@mail.gmail.com/ Reported-by: Gui-Dong Han Reviewed-by: Gui-Dong Han Link: https://patch.msgid.link/20260304130116.1721682-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-wdm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index f2d94cfc70af..7556c0dac908 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -225,7 +225,8 @@ static void wdm_in_callback(struct urb *urb) /* we may already be in overflow */ if (!test_bit(WDM_OVERFLOW, &desc->flags)) { memmove(desc->ubuf + desc->length, desc->inbuf, length); - desc->length += length; + smp_wmb(); /* against wdm_read() */ + WRITE_ONCE(desc->length, desc->length + length); } } skip_error: @@ -533,6 +534,7 @@ static ssize_t wdm_read return -ERESTARTSYS; cntr = READ_ONCE(desc->length); + smp_rmb(); /* against wdm_in_callback() */ if (cntr == 0) { desc->read = 0; retry: From c1c8550e70401159184130a1afc6261db01fc0ce Mon Sep 17 00:00:00 2001 From: Zilin Guan Date: Thu, 5 Mar 2026 00:36:37 +0200 Subject: [PATCH 376/487] usb: xhci: Fix memory leak in xhci_disable_slot() xhci_alloc_command() allocates a command structure and, when the second argument is true, also allocates a completion structure. Currently, the error handling path in xhci_disable_slot() only frees the command structure using kfree(), causing the completion structure to leak. Use xhci_free_command() instead of kfree(). xhci_free_command() correctly frees both the command structure and the associated completion structure. Since the command structure is allocated with zero-initialization, command->in_ctx is NULL and will not be erroneously freed by xhci_free_command(). This bug was found using an experimental static analysis tool we are developing. The tool is based on the LLVM framework and is specifically designed to detect memory management issues. It is currently under active development and not yet publicly available, but we plan to open-source it after our research is published. The bug was originally detected on v6.13-rc1 using our static analysis tool, and we have verified that the issue persists in the latest mainline kernel. We performed build testing on x86_64 with allyesconfig using GCC=11.4.0. Since triggering these error paths in xhci_disable_slot() requires specific hardware conditions or abnormal state, we were unable to construct a test case to reliably trigger these specific error paths at runtime. Fixes: 7faac1953ed1 ("xhci: avoid race between disable slot command and host runtime suspend") CC: stable@vger.kernel.org Signed-off-by: Zilin Guan Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260304223639.3882398-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index c36ab323d68e..ef6d8662adec 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4146,7 +4146,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) if (state == 0xffffffff || (xhci->xhc_state & XHCI_STATE_DYING) || (xhci->xhc_state & XHCI_STATE_HALTED)) { spin_unlock_irqrestore(&xhci->lock, flags); - kfree(command); + xhci_free_command(xhci, command); return -ENODEV; } @@ -4154,7 +4154,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) slot_id); if (ret) { spin_unlock_irqrestore(&xhci->lock, flags); - kfree(command); + xhci_free_command(xhci, command); return ret; } xhci_ring_cmd_db(xhci); From d6d5febd12452b7fd951fdd15c3ec262f01901a4 Mon Sep 17 00:00:00 2001 From: Dayu Jiang Date: Thu, 5 Mar 2026 00:36:38 +0200 Subject: [PATCH 377/487] usb: xhci: Prevent interrupt storm on host controller error (HCE) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The xHCI controller reports a Host Controller Error (HCE) in UAS Storage Device plug/unplug scenarios on Android devices. HCE is checked in xhci_irq() function and causes an interrupt storm (since the interrupt isn’t cleared), leading to severe system-level faults. When the xHC controller reports HCE in the interrupt handler, the driver only logs a warning and assumes xHC activity will stop as stated in xHCI specification. An interrupt storm does however continue on some hosts even after HCE, and only ceases after manually disabling xHC interrupt and stopping the controller by calling xhci_halt(). Add xhci_halt() to xhci_irq() function where STS_HCE status is checked, mirroring the existing error handling pattern used for STS_FATAL errors. This only fixes the interrupt storm. Proper HCE recovery requires resetting and re-initializing the xHC. CC: stable@vger.kernel.org Signed-off-by: Dayu Jiang Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260304223639.3882398-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 9315ba18310d..1cbefee3c4ca 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3195,6 +3195,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) if (status & STS_HCE) { xhci_warn(xhci, "WARNING: Host Controller Error\n"); + xhci_halt(xhci); goto out; } From ae4ff9dead5efa2025eddfcdb29411432bf40a7c Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 5 Mar 2026 00:36:39 +0200 Subject: [PATCH 378/487] xhci: Fix NULL pointer dereference when reading portli debugfs files Michal reported and debgged a NULL pointer dereference bug in the recently added portli debugfs files Oops is caused when there are more port registers counted in xhci->max_ports than ports reported by Supported Protocol capabilities. This is possible if max_ports is more than maximum port number, or if there are gaps between ports of different speeds the 'Supported Protocol' capabilities. In such cases port->rhub will be NULL so we can't reach xhci behind it. Add an explicit NULL check for this case, and print portli in hex without dereferencing port->rhub. Reported-by: Michal Pecio Closes: https://lore.kernel.org/linux-usb/20260304103856.48b785fd.michal.pecio@gmail.com Fixes: 384c57ec7205 ("usb: xhci: Add debugfs support for xHCI Port Link Info (PORTLI) register.") Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260304223639.3882398-4-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-debugfs.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index 890fc5e892f1..ade178ab34a7 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -386,11 +386,19 @@ static const struct file_operations port_fops = { static int xhci_portli_show(struct seq_file *s, void *unused) { struct xhci_port *port = s->private; - struct xhci_hcd *xhci = hcd_to_xhci(port->rhub->hcd); + struct xhci_hcd *xhci; u32 portli; portli = readl(&port->port_reg->portli); + /* port without protocol capability isn't added to a roothub */ + if (!port->rhub) { + seq_printf(s, "0x%08x\n", portli); + return 0; + } + + xhci = hcd_to_xhci(port->rhub->hcd); + /* PORTLI fields are valid if port is a USB3 or eUSB2V2 port */ if (port->rhub == &xhci->usb3_rhub) seq_printf(s, "0x%08x LEC=%u RLC=%u TLC=%u\n", portli, From 56135c0c60b07729401af9d329fa9c0eded845a6 Mon Sep 17 00:00:00 2001 From: Junzhong Pan Date: Fri, 6 Mar 2026 11:30:09 +0800 Subject: [PATCH 379/487] usb: gadget: uvc: fix interval_duration calculation To correctly convert bInterval as interval_duration: interval_duration = 2^(bInterval-1) * frame_interval Current code uses a wrong left shift operand, computing 2^bInterval instead of 2^(bInterval-1). Fixes: 010dc57cb516 ("usb: gadget: uvc: fix interval_duration calculation") Cc: stable Signed-off-by: Junzhong Pan Reviewed-by: Xu Yang Link: https://patch.msgid.link/20260306-fix-uvc-interval-v1-1-9a2df6859859@linux.spacemit.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/uvc_video.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index 7cea641b06b4..2f9700b3f1b6 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -513,7 +513,7 @@ uvc_video_prep_requests(struct uvc_video *video) return; } - interval_duration = 2 << (video->ep->desc->bInterval - 1); + interval_duration = 1 << (video->ep->desc->bInterval - 1); if (cdev->gadget->speed < USB_SPEED_HIGH) interval_duration *= 10000; else From 0326ff28d56b4fa202de36ffc8462a354f383a64 Mon Sep 17 00:00:00 2001 From: Christoffer Sandberg Date: Fri, 6 Mar 2026 18:28:14 +0100 Subject: [PATCH 380/487] usb/core/quirks: Add Huawei ME906S-device to wakeup quirk Similar to other Huawei LTE modules using this quirk, this version with another vid/pid suffers from spurious wakeups. Setting the quirk fixes the issue for this device as well. Cc: stable Signed-off-by: Christoffer Sandberg Signed-off-by: Werner Sembach Link: https://patch.msgid.link/20260306172817.2098898-1-wse@tuxedocomputers.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 7bd408db05f4..e3f402e0c351 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -209,6 +209,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* HP v222w 16GB Mini USB Drive */ { USB_DEVICE(0x03f0, 0x3f40), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Huawei 4G LTE module ME906S */ + { USB_DEVICE(0x03f0, 0xa31d), .driver_info = + USB_QUIRK_DISCONNECT_SUSPEND }, + /* Creative SB Audigy 2 NX */ { USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME }, From 17ab4d4078e22be7fd8fd6fc710c15c085a4cb1b Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 9 Mar 2026 14:02:04 +0100 Subject: [PATCH 381/487] usb: dwc3: pci: add support for the Intel Nova Lake -H This patch adds the necessary PCI ID for Intel Nova Lake -H devices. Signed-off-by: Heikki Krogerus Cc: stable Acked-by: Thinh Nguyen Link: https://patch.msgid.link/20260309130204.208661-1-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 6ecadc81bd6b..6c1cbb722ca8 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -56,6 +56,7 @@ #define PCI_DEVICE_ID_INTEL_CNPH 0xa36e #define PCI_DEVICE_ID_INTEL_CNPV 0xa3b0 #define PCI_DEVICE_ID_INTEL_RPL 0xa70e +#define PCI_DEVICE_ID_INTEL_NVLH 0xd37f #define PCI_DEVICE_ID_INTEL_PTLH 0xe332 #define PCI_DEVICE_ID_INTEL_PTLH_PCH 0xe37e #define PCI_DEVICE_ID_INTEL_PTLU 0xe432 @@ -447,6 +448,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, CNPH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, CNPV, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, RPL, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, NVLH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, PTLH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, PTLH_PCH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, PTLU, &dwc3_pci_intel_swnode) }, From e8557acfa079a54b59a21f447c82a31aec7717df Mon Sep 17 00:00:00 2001 From: RD Babiera Date: Tue, 10 Mar 2026 20:41:05 +0000 Subject: [PATCH 382/487] usb: typec: altmode/displayport: set displayport signaling rate in configure message dp_altmode_configure sets the signaling rate to the current configuration's rate and then shifts the value to the Select Configuration bitfield. On the initial configuration, dp->data.conf is 0 to begin with, so the signaling rate field is never set, which leads to some DisplayPort Alt Mode partners sending NAK to the Configure message. Set the signaling rate to the capabilities supported by both the port and the port partner. If the cable supports DisplayPort Alt Mode, then include its capabilities as well. Fixes: a17fae8fc38e ("usb: typec: Add Displayport Alternate Mode 2.1 Support") Cc: stable Signed-off-by: RD Babiera Acked-by: Heikki Krogerus Link: https://patch.msgid.link/20260310204106.3939862-2-rdbabiera@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index d185688a16b1..35d9c3086990 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -100,9 +100,14 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con) { u8 pin_assign = 0; u32 conf; + u32 signal; /* DP Signalling */ - conf = (dp->data.conf & DP_CONF_SIGNALLING_MASK) >> DP_CONF_SIGNALLING_SHIFT; + signal = DP_CAP_DP_SIGNALLING(dp->port->vdo) & DP_CAP_DP_SIGNALLING(dp->alt->vdo); + if (dp->plug_prime) + signal &= DP_CAP_DP_SIGNALLING(dp->plug_prime->vdo); + + conf = signal << DP_CONF_SIGNALLING_SHIFT; switch (con) { case DP_STATUS_CON_DISABLED: From 11199720fac2debbe718aec11e026ab3330dc80d Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Mon, 9 Mar 2026 20:04:46 +0800 Subject: [PATCH 383/487] Revert "usb: gadget: f_ncm: Fix atomic context locking issue" This reverts commit 0d6c8144ca4d93253de952a5ea0028c19ed7ab68. This commit is being reverted as part of a series-wide revert. By deferring the net_device allocation to the bind() phase, a single function instance will spawn multiple network devices if it is symlinked to multiple USB configurations. This causes regressions for userspace tools (like the postmarketOS DHCP daemon) that rely on reading the interface name (e.g., "usb0") from configfs. Currently, configfs returns the template "usb%d", causing the userspace network setup to fail. Crucially, because this patch breaks the 1:1 mapping between the function instance and the network device, this naming issue cannot simply be patched. Configfs only exposes a single 'ifname' attribute per instance, making it impossible to accurately report the actual interface name when multiple underlying network devices can exist for that single instance. All configurations tied to the same function instance are meant to share a single network device. Revert this change to restore the 1:1 mapping by allocating the network device at the instance level (alloc_inst). Reported-by: David Heidelberg Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/ Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-1-ea2afbc7d9b2@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_ncm.c | 29 +++++++++++-------- .../usb/gadget/function/u_ether_configfs.h | 11 ++++++- drivers/usb/gadget/function/u_ncm.h | 1 + 3 files changed, 28 insertions(+), 13 deletions(-) diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 4da19864d70b..14fc7dce6f39 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -58,7 +58,6 @@ struct f_ncm { u8 notify_state; atomic_t notify_count; bool is_open; - bool is_connected; const struct ndp_parser_opts *parser_opts; bool is_crc; @@ -865,6 +864,7 @@ static int ncm_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) { struct f_ncm *ncm = func_to_ncm(f); + struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; /* Control interface has only altsetting 0 */ @@ -887,12 +887,13 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (alt > 1) goto fail; - if (ncm->is_connected) { - DBG(cdev, "reset ncm\n"); - ncm->is_connected = false; - gether_disconnect(&ncm->port); - ncm_reset_values(ncm); - } + scoped_guard(mutex, &opts->lock) + if (opts->net) { + DBG(cdev, "reset ncm\n"); + opts->net = NULL; + gether_disconnect(&ncm->port); + ncm_reset_values(ncm); + } /* * CDC Network only sends data in non-default altsettings. @@ -925,7 +926,8 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) net = gether_connect(&ncm->port); if (IS_ERR(net)) return PTR_ERR(net); - ncm->is_connected = true; + scoped_guard(mutex, &opts->lock) + opts->net = net; } spin_lock(&ncm->lock); @@ -1372,14 +1374,16 @@ static int ncm_unwrap_ntb(struct gether *port, static void ncm_disable(struct usb_function *f) { struct f_ncm *ncm = func_to_ncm(f); + struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; DBG(cdev, "ncm deactivated\n"); - if (ncm->is_connected) { - ncm->is_connected = false; - gether_disconnect(&ncm->port); - } + scoped_guard(mutex, &opts->lock) + if (opts->net) { + opts->net = NULL; + gether_disconnect(&ncm->port); + } if (ncm->notify->enabled) { usb_ep_disable(ncm->notify); @@ -1683,6 +1687,7 @@ static struct usb_function_instance *ncm_alloc_inst(void) if (!opts) return ERR_PTR(-ENOMEM); + opts->net = NULL; opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id; gether_setup_opts_default(&opts->net_opts, "usb"); diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h index 25d8fb05b598..217990a266b2 100644 --- a/drivers/usb/gadget/function/u_ether_configfs.h +++ b/drivers/usb/gadget/function/u_ether_configfs.h @@ -327,9 +327,18 @@ out: \ char *page) \ { \ struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ + const char *name; \ \ guard(mutex)(&opts->lock); \ - return sysfs_emit(page, "%s\n", opts->net_opts.name); \ + rtnl_lock(); \ + if (opts->net_opts.ifname_set) \ + name = opts->net_opts.name; \ + else if (opts->net) \ + name = netdev_name(opts->net); \ + else \ + name = "(inactive net_device)"; \ + rtnl_unlock(); \ + return sysfs_emit(page, "%s\n", name); \ } \ \ static ssize_t _f_##_opts_ifname_store(struct config_item *item, \ diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h index 6d7538855744..d99330fe31e8 100644 --- a/drivers/usb/gadget/function/u_ncm.h +++ b/drivers/usb/gadget/function/u_ncm.h @@ -19,6 +19,7 @@ struct f_ncm_opts { struct usb_function_instance func_inst; + struct net_device *net; struct gether_opts net_opts; struct config_group *ncm_interf_group; From f2524c0e6ff0a5f72f1e1a32441c69d3b56430c4 Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Mon, 9 Mar 2026 20:04:47 +0800 Subject: [PATCH 384/487] Revert "usb: legacy: ncm: Fix NPE in gncm_bind" This reverts commit fde0634ad9856b3943a2d1a8cc8de174a63ac840. This commit is being reverted as part of a series-wide revert. By deferring the net_device allocation to the bind() phase, a single function instance will spawn multiple network devices if it is symlinked to multiple USB configurations. This causes regressions for userspace tools (like the postmarketOS DHCP daemon) that rely on reading the interface name (e.g., "usb0") from configfs. Currently, configfs returns the template "usb%d", causing the userspace network setup to fail. Crucially, because this patch breaks the 1:1 mapping between the function instance and the network device, this naming issue cannot simply be patched. Configfs only exposes a single 'ifname' attribute per instance, making it impossible to accurately report the actual interface name when multiple underlying network devices can exist for that single instance. All configurations tied to the same function instance are meant to share a single network device. Revert this change to restore the 1:1 mapping by allocating the network device at the instance level (alloc_inst). Reported-by: David Heidelberg Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/ Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-2-ea2afbc7d9b2@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/ncm.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c index e8d565534053..0f1b45e3abd1 100644 --- a/drivers/usb/gadget/legacy/ncm.c +++ b/drivers/usb/gadget/legacy/ncm.c @@ -15,10 +15,8 @@ /* #define DEBUG */ /* #define VERBOSE_DEBUG */ -#include #include #include -#include #include #include "u_ether.h" @@ -131,7 +129,6 @@ static int gncm_bind(struct usb_composite_dev *cdev) struct usb_gadget *gadget = cdev->gadget; struct f_ncm_opts *ncm_opts; int status; - u8 mac[ETH_ALEN]; f_ncm_inst = usb_get_function_instance("ncm"); if (IS_ERR(f_ncm_inst)) @@ -139,15 +136,11 @@ static int gncm_bind(struct usb_composite_dev *cdev) ncm_opts = container_of(f_ncm_inst, struct f_ncm_opts, func_inst); - ncm_opts->net_opts.qmult = qmult; - if (host_addr && mac_pton(host_addr, mac)) { - memcpy(&ncm_opts->net_opts.host_mac, mac, ETH_ALEN); + gether_set_qmult(ncm_opts->net, qmult); + if (!gether_set_host_addr(ncm_opts->net, host_addr)) pr_info("using host ethernet address: %s", host_addr); - } - if (dev_addr && mac_pton(dev_addr, mac)) { - memcpy(&ncm_opts->net_opts.dev_mac, mac, ETH_ALEN); + if (!gether_set_dev_addr(ncm_opts->net, dev_addr)) pr_info("using self ethernet address: %s", dev_addr); - } /* Allocate string descriptor numbers ... note that string * contents can be overridden by the composite_dev glue. From 37893bc5de2460c543ec1aa8250c37a305234054 Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Mon, 9 Mar 2026 20:04:48 +0800 Subject: [PATCH 385/487] Revert "usb: gadget: f_ncm: align net_device lifecycle with bind/unbind" This reverts commit 56a512a9b4107079f68701e7d55da8507eb963d9. This commit is being reverted as part of a series-wide revert. By deferring the net_device allocation to the bind() phase, a single function instance will spawn multiple network devices if it is symlinked to multiple USB configurations. This causes regressions for userspace tools (like the postmarketOS DHCP daemon) that rely on reading the interface name (e.g., "usb0") from configfs. Currently, configfs returns the template "usb%d", causing the userspace network setup to fail. Crucially, because this patch breaks the 1:1 mapping between the function instance and the network device, this naming issue cannot simply be patched. Configfs only exposes a single 'ifname' attribute per instance, making it impossible to accurately report the actual interface name when multiple underlying network devices can exist for that single instance. All configurations tied to the same function instance are meant to share a single network device. Revert this change to restore the 1:1 mapping by allocating the network device at the instance level (alloc_inst). Reported-by: David Heidelberg Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/ Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-3-ea2afbc7d9b2@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_ncm.c | 128 ++++++++++++++-------------- drivers/usb/gadget/function/u_ncm.h | 4 +- 2 files changed, 66 insertions(+), 66 deletions(-) diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 14fc7dce6f39..3d772c9beb91 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -83,11 +83,6 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f) return container_of(f, struct f_ncm, port.func); } -static inline struct f_ncm_opts *func_to_ncm_opts(struct usb_function *f) -{ - return container_of(f->fi, struct f_ncm_opts, func_inst); -} - /*-------------------------------------------------------------------------*/ /* @@ -864,7 +859,6 @@ static int ncm_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) { struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; /* Control interface has only altsetting 0 */ @@ -887,13 +881,12 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (alt > 1) goto fail; - scoped_guard(mutex, &opts->lock) - if (opts->net) { - DBG(cdev, "reset ncm\n"); - opts->net = NULL; - gether_disconnect(&ncm->port); - ncm_reset_values(ncm); - } + if (ncm->netdev) { + DBG(cdev, "reset ncm\n"); + ncm->netdev = NULL; + gether_disconnect(&ncm->port); + ncm_reset_values(ncm); + } /* * CDC Network only sends data in non-default altsettings. @@ -926,8 +919,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) net = gether_connect(&ncm->port); if (IS_ERR(net)) return PTR_ERR(net); - scoped_guard(mutex, &opts->lock) - opts->net = net; + ncm->netdev = net; } spin_lock(&ncm->lock); @@ -1374,16 +1366,14 @@ static int ncm_unwrap_ntb(struct gether *port, static void ncm_disable(struct usb_function *f) { struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; DBG(cdev, "ncm deactivated\n"); - scoped_guard(mutex, &opts->lock) - if (opts->net) { - opts->net = NULL; - gether_disconnect(&ncm->port); - } + if (ncm->netdev) { + ncm->netdev = NULL; + gether_disconnect(&ncm->port); + } if (ncm->notify->enabled) { usb_ep_disable(ncm->notify); @@ -1443,44 +1433,39 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) { struct usb_composite_dev *cdev = c->cdev; struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *ncm_opts = func_to_ncm_opts(f); struct usb_string *us; int status = 0; struct usb_ep *ep; + struct f_ncm_opts *ncm_opts; struct usb_os_desc_table *os_desc_table __free(kfree) = NULL; - struct net_device *netdev __free(free_gether_netdev) = NULL; struct usb_request *request __free(free_usb_request) = NULL; if (!can_support_ecm(cdev->gadget)) return -EINVAL; + ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst); + if (cdev->use_os_string) { os_desc_table = kzalloc(sizeof(*os_desc_table), GFP_KERNEL); if (!os_desc_table) return -ENOMEM; } - netdev = gether_setup_default(); - if (IS_ERR(netdev)) - return -ENOMEM; - - scoped_guard(mutex, &ncm_opts->lock) { - gether_apply_opts(netdev, &ncm_opts->net_opts); - netdev->mtu = ncm_opts->max_segment_size - ETH_HLEN; + mutex_lock(&ncm_opts->lock); + gether_set_gadget(ncm_opts->net, cdev->gadget); + if (!ncm_opts->bound) { + ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN); + status = gether_register_netdev(ncm_opts->net); } + mutex_unlock(&ncm_opts->lock); - gether_set_gadget(netdev, cdev->gadget); - status = gether_register_netdev(netdev); if (status) return status; - /* export host's Ethernet address in CDC format */ - status = gether_get_host_addr_cdc(netdev, ncm->ethaddr, - sizeof(ncm->ethaddr)); - if (status < 12) - return -EINVAL; - ncm_string_defs[STRING_MAC_IDX].s = ncm->ethaddr; + ncm_opts->bound = true; + + ncm_string_defs[1].s = ncm->ethaddr; us = usb_gstrings_attach(cdev, ncm_strings, ARRAY_SIZE(ncm_string_defs)); @@ -1578,8 +1563,6 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) f->os_desc_n = 1; } ncm->notify_req = no_free_ptr(request); - ncm->netdev = no_free_ptr(netdev); - ncm->port.ioport = netdev_priv(ncm->netdev); DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n", ncm->port.in_ep->name, ncm->port.out_ep->name, @@ -1594,19 +1577,19 @@ static inline struct f_ncm_opts *to_f_ncm_opts(struct config_item *item) } /* f_ncm_item_ops */ -USB_ETHER_OPTS_ITEM(ncm); +USB_ETHERNET_CONFIGFS_ITEM(ncm); /* f_ncm_opts_dev_addr */ -USB_ETHER_OPTS_ATTR_DEV_ADDR(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_DEV_ADDR(ncm); /* f_ncm_opts_host_addr */ -USB_ETHER_OPTS_ATTR_HOST_ADDR(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_HOST_ADDR(ncm); /* f_ncm_opts_qmult */ -USB_ETHER_OPTS_ATTR_QMULT(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_QMULT(ncm); /* f_ncm_opts_ifname */ -USB_ETHER_OPTS_ATTR_IFNAME(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_IFNAME(ncm); static ssize_t ncm_opts_max_segment_size_show(struct config_item *item, char *page) @@ -1672,27 +1655,34 @@ static void ncm_free_inst(struct usb_function_instance *f) struct f_ncm_opts *opts; opts = container_of(f, struct f_ncm_opts, func_inst); + if (opts->bound) + gether_cleanup(netdev_priv(opts->net)); + else + free_netdev(opts->net); kfree(opts->ncm_interf_group); kfree(opts); } static struct usb_function_instance *ncm_alloc_inst(void) { - struct usb_function_instance *ret; + struct f_ncm_opts *opts; struct usb_os_desc *descs[1]; char *names[1]; struct config_group *ncm_interf_group; - struct f_ncm_opts *opts __free(kfree) = kzalloc_obj(*opts); + opts = kzalloc_obj(*opts); if (!opts) return ERR_PTR(-ENOMEM); - - opts->net = NULL; opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id; - gether_setup_opts_default(&opts->net_opts, "usb"); mutex_init(&opts->lock); opts->func_inst.free_func_inst = ncm_free_inst; + opts->net = gether_setup_default(); + if (IS_ERR(opts->net)) { + struct net_device *net = opts->net; + kfree(opts); + return ERR_CAST(net); + } opts->max_segment_size = ETH_FRAME_LEN; INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop); @@ -1703,22 +1693,26 @@ static struct usb_function_instance *ncm_alloc_inst(void) ncm_interf_group = usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs, names, THIS_MODULE); - if (IS_ERR(ncm_interf_group)) + if (IS_ERR(ncm_interf_group)) { + ncm_free_inst(&opts->func_inst); return ERR_CAST(ncm_interf_group); + } opts->ncm_interf_group = ncm_interf_group; - ret = &opts->func_inst; - retain_and_null_ptr(opts); - return ret; + return &opts->func_inst; } static void ncm_free(struct usb_function *f) { - struct f_ncm_opts *opts = func_to_ncm_opts(f); + struct f_ncm *ncm; + struct f_ncm_opts *opts; - scoped_guard(mutex, &opts->lock) - opts->refcnt--; - kfree(func_to_ncm(f)); + ncm = func_to_ncm(f); + opts = container_of(f->fi, struct f_ncm_opts, func_inst); + kfree(ncm); + mutex_lock(&opts->lock); + opts->refcnt--; + mutex_unlock(&opts->lock); } static void ncm_unbind(struct usb_configuration *c, struct usb_function *f) @@ -1742,15 +1736,13 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f) kfree(ncm->notify_req->buf); usb_ep_free_request(ncm->notify, ncm->notify_req); - - ncm->port.ioport = NULL; - gether_cleanup(netdev_priv(ncm->netdev)); } static struct usb_function *ncm_alloc(struct usb_function_instance *fi) { struct f_ncm *ncm; struct f_ncm_opts *opts; + int status; /* allocate and initialize one new instance */ ncm = kzalloc(sizeof(*ncm), GFP_KERNEL); @@ -1758,12 +1750,22 @@ static struct usb_function *ncm_alloc(struct usb_function_instance *fi) return ERR_PTR(-ENOMEM); opts = container_of(fi, struct f_ncm_opts, func_inst); + mutex_lock(&opts->lock); + opts->refcnt++; - scoped_guard(mutex, &opts->lock) - opts->refcnt++; + /* export host's Ethernet address in CDC format */ + status = gether_get_host_addr_cdc(opts->net, ncm->ethaddr, + sizeof(ncm->ethaddr)); + if (status < 12) { /* strlen("01234567890a") */ + kfree(ncm); + mutex_unlock(&opts->lock); + return ERR_PTR(-EINVAL); + } spin_lock_init(&ncm->lock); ncm_reset_values(ncm); + ncm->port.ioport = netdev_priv(opts->net); + mutex_unlock(&opts->lock); ncm->port.is_fixed = true; ncm->port.supports_multi_frame = true; diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h index d99330fe31e8..49ec095cdb4b 100644 --- a/drivers/usb/gadget/function/u_ncm.h +++ b/drivers/usb/gadget/function/u_ncm.h @@ -15,13 +15,11 @@ #include -#include "u_ether.h" - struct f_ncm_opts { struct usb_function_instance func_inst; struct net_device *net; + bool bound; - struct gether_opts net_opts; struct config_group *ncm_interf_group; struct usb_os_desc ncm_os_desc; char ncm_ext_compat_id[16]; From 46662d3a1ad40282ba9f753cccc6f909ec4468cc Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Mon, 9 Mar 2026 20:04:49 +0800 Subject: [PATCH 386/487] Revert "usb: gadget: u_ether: Add auto-cleanup helper for freeing net_device" This reverts commit 0c0981126b99288ed354d3d414c8a5fd42ac9e25. This commit is being reverted as part of a series-wide revert. By deferring the net_device allocation to the bind() phase, a single function instance will spawn multiple network devices if it is symlinked to multiple USB configurations. This causes regressions for userspace tools (like the postmarketOS DHCP daemon) that rely on reading the interface name (e.g., "usb0") from configfs. Currently, configfs returns the template "usb%d", causing the userspace network setup to fail. Crucially, because this patch breaks the 1:1 mapping between the function instance and the network device, this naming issue cannot simply be patched. Configfs only exposes a single 'ifname' attribute per instance, making it impossible to accurately report the actual interface name when multiple underlying network devices can exist for that single instance. All configurations tied to the same function instance are meant to share a single network device. Revert this change to restore the 1:1 mapping by allocating the network device at the instance level (alloc_inst). Reported-by: David Heidelberg Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/ Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-4-ea2afbc7d9b2@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_ether.c | 15 --------------- drivers/usb/gadget/function/u_ether.h | 2 -- 2 files changed, 17 deletions(-) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 338f6e2a85a9..15685b2f8887 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -1126,21 +1126,6 @@ void gether_cleanup(struct eth_dev *dev) } EXPORT_SYMBOL_GPL(gether_cleanup); -void gether_unregister_free_netdev(struct net_device *net) -{ - if (!net) - return; - - struct eth_dev *dev = netdev_priv(net); - - if (net->reg_state == NETREG_REGISTERED) { - unregister_netdev(net); - flush_work(&dev->work); - } - free_netdev(net); -} -EXPORT_SYMBOL_GPL(gether_unregister_free_netdev); - /** * gether_connect - notify network layer that USB link is active * @link: the USB link, set up with endpoints, descriptors matching diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h index a212a8ec5eb1..63a0240df4d7 100644 --- a/drivers/usb/gadget/function/u_ether.h +++ b/drivers/usb/gadget/function/u_ether.h @@ -283,8 +283,6 @@ int gether_get_ifname(struct net_device *net, char *name, int len); int gether_set_ifname(struct net_device *net, const char *name, int len); void gether_cleanup(struct eth_dev *dev); -void gether_unregister_free_netdev(struct net_device *net); -DEFINE_FREE(free_gether_netdev, struct net_device *, gether_unregister_free_netdev(_T)); void gether_setup_opts_default(struct gether_opts *opts, const char *name); void gether_apply_opts(struct net_device *net, struct gether_opts *opts); From 3549d0ae5f7e647ffd09d69f927a18ae7a520f6f Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Mon, 9 Mar 2026 20:04:50 +0800 Subject: [PATCH 387/487] Revert "usb: gadget: u_ether: use header file" This reverts commit 7a7930c0f934fb0c46de6e7ca08e14e11df35dd6. This commit is being reverted as part of a series-wide revert. By deferring the net_device allocation to the bind() phase, a single function instance will spawn multiple network devices if it is symlinked to multiple USB configurations. This causes regressions for userspace tools (like the postmarketOS DHCP daemon) that rely on reading the interface name (e.g., "usb0") from configfs. Currently, configfs returns the template "usb%d", causing the userspace network setup to fail. Crucially, because this patch breaks the 1:1 mapping between the function instance and the network device, this naming issue cannot simply be patched. Configfs only exposes a single 'ifname' attribute per instance, making it impossible to accurately report the actual interface name when multiple underlying network devices can exist for that single instance. All configurations tied to the same function instance are meant to share a single network device. Revert this change to restore the 1:1 mapping by allocating the network device at the instance level (alloc_inst). Reported-by: David Heidelberg Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/ Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-5-ea2afbc7d9b2@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_ether_configfs.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h index 217990a266b2..39d3a261496d 100644 --- a/drivers/usb/gadget/function/u_ether_configfs.h +++ b/drivers/usb/gadget/function/u_ether_configfs.h @@ -14,7 +14,6 @@ #define __U_ETHER_CONFIGFS_H #include -#include #include #include #include From 3131c1aff7cdffb96239f06f98e16188cbc2083f Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Mon, 9 Mar 2026 20:04:51 +0800 Subject: [PATCH 388/487] Revert "usb: gadget: u_ether: add gether_opts for config caching" This reverts commit e065c6a7e46c2ee9c677fdbf50035323d2de1215. This commit is being reverted as part of a series-wide revert. By deferring the net_device allocation to the bind() phase, a single function instance will spawn multiple network devices if it is symlinked to multiple USB configurations. This causes regressions for userspace tools (like the postmarketOS DHCP daemon) that rely on reading the interface name (e.g., "usb0") from configfs. Currently, configfs returns the template "usb%d", causing the userspace network setup to fail. Crucially, because this patch breaks the 1:1 mapping between the function instance and the network device, this naming issue cannot simply be patched. Configfs only exposes a single 'ifname' attribute per instance, making it impossible to accurately report the actual interface name when multiple underlying network devices can exist for that single instance. All configurations tied to the same function instance are meant to share a single network device. Revert this change to restore the 1:1 mapping by allocating the network device at the instance level (alloc_inst). Reported-by: David Heidelberg Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/ Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind") Cc: stable Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-6-ea2afbc7d9b2@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_ether.c | 30 --- drivers/usb/gadget/function/u_ether.h | 28 --- .../usb/gadget/function/u_ether_configfs.h | 176 ------------------ 3 files changed, 234 deletions(-) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 15685b2f8887..c47965d850d4 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -1040,36 +1040,6 @@ int gether_set_ifname(struct net_device *net, const char *name, int len) } EXPORT_SYMBOL_GPL(gether_set_ifname); -void gether_setup_opts_default(struct gether_opts *opts, const char *name) -{ - opts->qmult = QMULT_DEFAULT; - snprintf(opts->name, sizeof(opts->name), "%s%%d", name); - eth_random_addr(opts->dev_mac); - opts->addr_assign_type = NET_ADDR_RANDOM; - eth_random_addr(opts->host_mac); -} -EXPORT_SYMBOL_GPL(gether_setup_opts_default); - -void gether_apply_opts(struct net_device *net, struct gether_opts *opts) -{ - struct eth_dev *dev = netdev_priv(net); - - dev->qmult = opts->qmult; - - if (opts->ifname_set) { - strscpy(net->name, opts->name, sizeof(net->name)); - dev->ifname_set = true; - } - - memcpy(dev->host_mac, opts->host_mac, sizeof(dev->host_mac)); - - if (opts->addr_assign_type == NET_ADDR_SET) { - memcpy(dev->dev_mac, opts->dev_mac, sizeof(dev->dev_mac)); - net->addr_assign_type = opts->addr_assign_type; - } -} -EXPORT_SYMBOL_GPL(gether_apply_opts); - void gether_suspend(struct gether *link) { struct eth_dev *dev = link->ioport; diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h index 63a0240df4d7..34be220cef77 100644 --- a/drivers/usb/gadget/function/u_ether.h +++ b/drivers/usb/gadget/function/u_ether.h @@ -38,31 +38,6 @@ struct eth_dev; -/** - * struct gether_opts - Options for Ethernet gadget function instances - * @name: Pattern for the network interface name (e.g., "usb%d"). - * Used to generate the net device name. - * @qmult: Queue length multiplier for high/super speed. - * @host_mac: The MAC address to be used by the host side. - * @dev_mac: The MAC address to be used by the device side. - * @ifname_set: True if the interface name pattern has been set by userspace. - * @addr_assign_type: The method used for assigning the device MAC address - * (e.g., NET_ADDR_RANDOM, NET_ADDR_SET). - * - * This structure caches network-related settings provided through configfs - * before the net_device is fully instantiated. This allows for early - * configuration while deferring net_device allocation until the function - * is bound. - */ -struct gether_opts { - char name[IFNAMSIZ]; - unsigned int qmult; - u8 host_mac[ETH_ALEN]; - u8 dev_mac[ETH_ALEN]; - bool ifname_set; - unsigned char addr_assign_type; -}; - /* * This represents the USB side of an "ethernet" link, managed by a USB * function which provides control and (maybe) framing. Two functions @@ -284,9 +259,6 @@ int gether_set_ifname(struct net_device *net, const char *name, int len); void gether_cleanup(struct eth_dev *dev); -void gether_setup_opts_default(struct gether_opts *opts, const char *name); -void gether_apply_opts(struct net_device *net, struct gether_opts *opts); - void gether_suspend(struct gether *link); void gether_resume(struct gether *link); diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h index 39d3a261496d..51f0d79e5eca 100644 --- a/drivers/usb/gadget/function/u_ether_configfs.h +++ b/drivers/usb/gadget/function/u_ether_configfs.h @@ -13,12 +13,6 @@ #ifndef __U_ETHER_CONFIGFS_H #define __U_ETHER_CONFIGFS_H -#include -#include -#include -#include -#include - #define USB_ETHERNET_CONFIGFS_ITEM(_f_) \ static void _f_##_attr_release(struct config_item *item) \ { \ @@ -203,174 +197,4 @@ out: \ \ CONFIGFS_ATTR(_f_##_opts_, _n_) -#define USB_ETHER_OPTS_ITEM(_f_) \ - static void _f_##_attr_release(struct config_item *item) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - usb_put_function_instance(&opts->func_inst); \ - } \ - \ - static struct configfs_item_operations _f_##_item_ops = { \ - .release = _f_##_attr_release, \ - } - -#define USB_ETHER_OPTS_ATTR_DEV_ADDR(_f_) \ - static ssize_t _f_##_opts_dev_addr_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - guard(mutex)(&opts->lock); \ - return sysfs_emit(page, "%pM\n", opts->net_opts.dev_mac); \ - } \ - \ - static ssize_t _f_##_opts_dev_addr_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - u8 new_addr[ETH_ALEN]; \ - const char *p = page; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - \ - for (int i = 0; i < ETH_ALEN; i++) { \ - unsigned char num; \ - if ((*p == '.') || (*p == ':')) \ - p++; \ - num = hex_to_bin(*p++) << 4; \ - num |= hex_to_bin(*p++); \ - new_addr[i] = num; \ - } \ - if (!is_valid_ether_addr(new_addr)) \ - return -EINVAL; \ - memcpy(opts->net_opts.dev_mac, new_addr, ETH_ALEN); \ - opts->net_opts.addr_assign_type = NET_ADDR_SET; \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, dev_addr) - -#define USB_ETHER_OPTS_ATTR_HOST_ADDR(_f_) \ - static ssize_t _f_##_opts_host_addr_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - guard(mutex)(&opts->lock); \ - return sysfs_emit(page, "%pM\n", opts->net_opts.host_mac); \ - } \ - \ - static ssize_t _f_##_opts_host_addr_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - u8 new_addr[ETH_ALEN]; \ - const char *p = page; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - \ - for (int i = 0; i < ETH_ALEN; i++) { \ - unsigned char num; \ - if ((*p == '.') || (*p == ':')) \ - p++; \ - num = hex_to_bin(*p++) << 4; \ - num |= hex_to_bin(*p++); \ - new_addr[i] = num; \ - } \ - if (!is_valid_ether_addr(new_addr)) \ - return -EINVAL; \ - memcpy(opts->net_opts.host_mac, new_addr, ETH_ALEN); \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, host_addr) - -#define USB_ETHER_OPTS_ATTR_QMULT(_f_) \ - static ssize_t _f_##_opts_qmult_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - guard(mutex)(&opts->lock); \ - return sysfs_emit(page, "%u\n", opts->net_opts.qmult); \ - } \ - \ - static ssize_t _f_##_opts_qmult_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - u32 val; \ - int ret; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - \ - ret = kstrtou32(page, 0, &val); \ - if (ret) \ - return ret; \ - \ - opts->net_opts.qmult = val; \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, qmult) - -#define USB_ETHER_OPTS_ATTR_IFNAME(_f_) \ - static ssize_t _f_##_opts_ifname_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - const char *name; \ - \ - guard(mutex)(&opts->lock); \ - rtnl_lock(); \ - if (opts->net_opts.ifname_set) \ - name = opts->net_opts.name; \ - else if (opts->net) \ - name = netdev_name(opts->net); \ - else \ - name = "(inactive net_device)"; \ - rtnl_unlock(); \ - return sysfs_emit(page, "%s\n", name); \ - } \ - \ - static ssize_t _f_##_opts_ifname_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - char tmp[IFNAMSIZ]; \ - const char *p; \ - size_t c_len = len; \ - \ - if (c_len > 0 && page[c_len - 1] == '\n') \ - c_len--; \ - \ - if (c_len >= sizeof(tmp)) \ - return -E2BIG; \ - \ - strscpy(tmp, page, c_len + 1); \ - if (!dev_valid_name(tmp)) \ - return -EINVAL; \ - \ - /* Require exactly one %d */ \ - p = strchr(tmp, '%'); \ - if (!p || p[1] != 'd' || strchr(p + 2, '%')) \ - return -EINVAL; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - strscpy(opts->net_opts.name, tmp, sizeof(opts->net_opts.name)); \ - opts->net_opts.ifname_set = true; \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, ifname) - #endif /* __U_ETHER_CONFIGFS_H */ From ec35c1969650e7cb6c8a91020e568ed46e3551b0 Mon Sep 17 00:00:00 2001 From: Kuen-Han Tsai Date: Mon, 9 Mar 2026 20:04:52 +0800 Subject: [PATCH 389/487] usb: gadget: f_ncm: Fix net_device lifecycle with device_move The network device outlived its parent gadget device during disconnection, resulting in dangling sysfs links and null pointer dereference problems. A prior attempt to solve this by removing SET_NETDEV_DEV entirely [1] was reverted due to power management ordering concerns and a NO-CARRIER regression. A subsequent attempt to defer net_device allocation to bind [2] broke 1:1 mapping between function instance and network device, making it impossible for configfs to report the resolved interface name. This results in a regression where the DHCP server fails on pmOS. Use device_move to reparent the net_device between the gadget device and /sys/devices/virtual/ across bind/unbind cycles. This preserves the network interface across USB reconnection, allowing the DHCP server to retain their binding. Introduce gether_attach_gadget()/gether_detach_gadget() helpers and use __free(detach_gadget) macro to undo attachment on bind failure. The bind_count ensures device_move executes only on the first bind. [1] https://lore.kernel.org/lkml/f2a4f9847617a0929d62025748384092e5f35cce.camel@crapouillou.net/ [2] https://lore.kernel.org/linux-usb/795ea759-7eaf-4f78-81f4-01ffbf2d7961@ixit.cz/ Fixes: 40d133d7f542 ("usb: gadget: f_ncm: convert to new function interface with backward compatibility") Cc: stable Signed-off-by: Kuen-Han Tsai Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-7-ea2afbc7d9b2@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_ncm.c | 36 ++++++++++++++++++--------- drivers/usb/gadget/function/u_ether.c | 22 ++++++++++++++++ drivers/usb/gadget/function/u_ether.h | 26 +++++++++++++++++++ drivers/usb/gadget/function/u_ncm.h | 2 +- 4 files changed, 73 insertions(+), 13 deletions(-) diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 3d772c9beb91..a6fa5ed3d6cb 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1439,6 +1439,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) struct f_ncm_opts *ncm_opts; struct usb_os_desc_table *os_desc_table __free(kfree) = NULL; + struct net_device *net __free(detach_gadget) = NULL; struct usb_request *request __free(free_usb_request) = NULL; if (!can_support_ecm(cdev->gadget)) @@ -1452,18 +1453,19 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) return -ENOMEM; } - mutex_lock(&ncm_opts->lock); - gether_set_gadget(ncm_opts->net, cdev->gadget); - if (!ncm_opts->bound) { - ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN); - status = gether_register_netdev(ncm_opts->net); - } - mutex_unlock(&ncm_opts->lock); + scoped_guard(mutex, &ncm_opts->lock) + if (ncm_opts->bind_count == 0) { + if (!device_is_registered(&ncm_opts->net->dev)) { + ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN); + gether_set_gadget(ncm_opts->net, cdev->gadget); + status = gether_register_netdev(ncm_opts->net); + } else + status = gether_attach_gadget(ncm_opts->net, cdev->gadget); - if (status) - return status; - - ncm_opts->bound = true; + if (status) + return status; + net = ncm_opts->net; + } ncm_string_defs[1].s = ncm->ethaddr; @@ -1564,6 +1566,9 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) } ncm->notify_req = no_free_ptr(request); + ncm_opts->bind_count++; + retain_and_null_ptr(net); + DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n", ncm->port.in_ep->name, ncm->port.out_ep->name, ncm->notify->name); @@ -1655,7 +1660,7 @@ static void ncm_free_inst(struct usb_function_instance *f) struct f_ncm_opts *opts; opts = container_of(f, struct f_ncm_opts, func_inst); - if (opts->bound) + if (device_is_registered(&opts->net->dev)) gether_cleanup(netdev_priv(opts->net)); else free_netdev(opts->net); @@ -1718,9 +1723,12 @@ static void ncm_free(struct usb_function *f) static void ncm_unbind(struct usb_configuration *c, struct usb_function *f) { struct f_ncm *ncm = func_to_ncm(f); + struct f_ncm_opts *ncm_opts; DBG(c->cdev, "ncm unbind\n"); + ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst); + hrtimer_cancel(&ncm->task_timer); kfree(f->os_desc_table); @@ -1736,6 +1744,10 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f) kfree(ncm->notify_req->buf); usb_ep_free_request(ncm->notify, ncm->notify_req); + + ncm_opts->bind_count--; + if (ncm_opts->bind_count == 0) + gether_detach_gadget(ncm_opts->net); } static struct usb_function *ncm_alloc(struct usb_function_instance *fi) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index c47965d850d4..1a9e7c495e2e 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -897,6 +897,28 @@ void gether_set_gadget(struct net_device *net, struct usb_gadget *g) } EXPORT_SYMBOL_GPL(gether_set_gadget); +int gether_attach_gadget(struct net_device *net, struct usb_gadget *g) +{ + int ret; + + ret = device_move(&net->dev, &g->dev, DPM_ORDER_DEV_AFTER_PARENT); + if (ret) + return ret; + + gether_set_gadget(net, g); + return 0; +} +EXPORT_SYMBOL_GPL(gether_attach_gadget); + +void gether_detach_gadget(struct net_device *net) +{ + struct eth_dev *dev = netdev_priv(net); + + device_move(&net->dev, NULL, DPM_ORDER_NONE); + dev->gadget = NULL; +} +EXPORT_SYMBOL_GPL(gether_detach_gadget); + int gether_set_dev_addr(struct net_device *net, const char *dev_addr) { struct eth_dev *dev; diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h index 34be220cef77..c85a1cf3c115 100644 --- a/drivers/usb/gadget/function/u_ether.h +++ b/drivers/usb/gadget/function/u_ether.h @@ -150,6 +150,32 @@ static inline struct net_device *gether_setup_default(void) */ void gether_set_gadget(struct net_device *net, struct usb_gadget *g); +/** + * gether_attach_gadget - Reparent net_device to the gadget device. + * @net: The network device to reparent. + * @g: The target USB gadget device to parent to. + * + * This function moves the network device to be a child of the USB gadget + * device in the device hierarchy. This is typically done when the function + * is bound to a configuration. + * + * Returns 0 on success, or a negative error code on failure. + */ +int gether_attach_gadget(struct net_device *net, struct usb_gadget *g); + +/** + * gether_detach_gadget - Detach net_device from its gadget parent. + * @net: The network device to detach. + * + * This function moves the network device to be a child of the virtual + * devices parent, effectively detaching it from the USB gadget device + * hierarchy. This is typically done when the function is unbound + * from a configuration but the instance is not yet freed. + */ +void gether_detach_gadget(struct net_device *net); + +DEFINE_FREE(detach_gadget, struct net_device *, if (_T) gether_detach_gadget(_T)) + /** * gether_set_dev_addr - initialize an ethernet-over-usb link with eth address * @net: device representing this link diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h index 49ec095cdb4b..b1f3db8b68c1 100644 --- a/drivers/usb/gadget/function/u_ncm.h +++ b/drivers/usb/gadget/function/u_ncm.h @@ -18,7 +18,7 @@ struct f_ncm_opts { struct usb_function_instance func_inst; struct net_device *net; - bool bound; + int bind_count; struct config_group *ncm_interf_group; struct usb_os_desc ncm_os_desc; From 6b275bfaa16be3fb1689fa6794e445ecd127a1b4 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Mon, 9 Mar 2026 15:43:12 +0800 Subject: [PATCH 390/487] Revert "tcpm: allow looking for role_sw device in the main node" This reverts commit 1366cd228b0c67b60a2c0c26ef37fe9f7cfedb7f. The fwnode_usb_role_switch_get() returns NULL only if no connection is found, returns ERR_PTR(-EPROBE_DEFER) if connection is found but deferred probe is needed, or a valid pointer of usb_role_switch. When switching from a NULL check to IS_ERR_OR_NULL(), usb_role_switch_get() returns NULL and overwrites the ERR_PTR(-EPROBE_DEFER) returned by fwnode_usb_role_switch_get(). This causes the deferred probe indication to be lost, preventing the USB role switch from ever being retrieved. Fixes: 1366cd228b0c ("tcpm: allow looking for role_sw device in the main node") Cc: stable Signed-off-by: Xu Yang Tested-by: Arnaud Ferraris Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260309074313.2809867-2-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 1d2f3af034c5..8e0e14a2704e 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -7890,7 +7890,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) port->partner_desc.identity = &port->partner_ident; port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode); - if (IS_ERR_OR_NULL(port->role_sw)) + if (!port->role_sw) port->role_sw = usb_role_switch_get(port->dev); if (IS_ERR(port->role_sw)) { err = PTR_ERR(port->role_sw); From 8345b1539faa49fcf9c9439c3cbd97dac6eca171 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Mon, 9 Mar 2026 15:43:13 +0800 Subject: [PATCH 391/487] usb: roles: get usb role switch from parent only for usb-b-connector usb_role_switch_is_parent() was walking up to the parent node and checking for the "usb-role-switch" property regardless of the type of the passed fwnode. This could cause unrelated device nodes to be probed as potential role switch parent, leading to spurious matches and "-EPROBE_DEFER" being returned infinitely. Till now only Type-B connector node will have a parent node which may present "usb-role-switch" property and register the role switch device. For Type-C connector node, its parent node will always be a Type-C chip device which will never register the role switch device. However, it may still present a non-boolean "usb-role-switch = <&usb_controller>" property for historical compatibility. So restrict the helper to only operate on Type-B connector when attempting to get the role switch from parent node. Fixes: 6fadd72943b8 ("usb: roles: get usb-role-switch from parent") Cc: stable Signed-off-by: Xu Yang Tested-by: Arnaud Ferraris Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260309074313.2809867-3-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/roles/class.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index b8e28ceca51e..edec139b68b5 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -139,9 +139,14 @@ static void *usb_role_switch_match(const struct fwnode_handle *fwnode, const cha static struct usb_role_switch * usb_role_switch_is_parent(struct fwnode_handle *fwnode) { - struct fwnode_handle *parent = fwnode_get_parent(fwnode); + struct fwnode_handle *parent; struct device *dev; + if (!fwnode_device_is_compatible(fwnode, "usb-b-connector")) + return NULL; + + parent = fwnode_get_parent(fwnode); + if (!fwnode_property_present(parent, "usb-role-switch")) { fwnode_handle_put(parent); return NULL; From 163cc462dea7d5b75be4db49ca78a2b99c55375e Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 5 Mar 2026 16:17:28 +0100 Subject: [PATCH 392/487] gpib: lpvo_usb: fix unintended binding of FTDI 8U232AM devices The LPVO USB GPIB adapter apparently uses an FTDI 8U232AM with the default PID, but this device id is already handled by the ftdi_sio serial driver. Stop binding to the default PID to avoid breaking existing setups with FTDI 8U232AM. Anyone using this driver should blacklist the ftdi_sio driver and add the device id manually through sysfs (e.g. using udev rules). Fixes: fce79512a96a ("staging: gpib: Add LPVO DIY USB GPIB driver") Fixes: e6ab504633e4 ("staging: gpib: Destage gpib") Cc: Dave Penkler Cc: stable Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260305151729.10501-2-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c index 6fc4e3452b88..ee781d2f0b8e 100644 --- a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c +++ b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c @@ -38,8 +38,10 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices"); /* * Table of devices that work with this driver. * - * Currently, only one device is known to be used in the - * lpvo_usb_gpib adapter (FTDI 0403:6001). + * Currently, only one device is known to be used in the lpvo_usb_gpib + * adapter (FTDI 0403:6001) but as this device id is already handled by the + * ftdi_sio USB serial driver the LPVO driver must not bind to it by default. + * * If your adapter uses a different chip, insert a line * in the following table with proper , . * @@ -50,7 +52,6 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices"); */ static const struct usb_device_id skel_table[] = { - { USB_DEVICE(0x0403, 0x6001) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, skel_table); From 0073a17b466684413ac87cf8ff6c19560db44e7a Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Mon, 9 Mar 2026 23:53:24 +0100 Subject: [PATCH 393/487] gpu: nova-core: gsp: fix UB in DmaGspMem pointer accessors The DmaGspMem pointer accessor methods (gsp_write_ptr, gsp_read_ptr, cpu_read_ptr, cpu_write_ptr, advance_cpu_read_ptr, advance_cpu_write_ptr) dereference a raw pointer to DMA memory, creating an intermediate reference before calling volatile read/write methods. This is undefined behavior since DMA memory can be concurrently modified by the device. Fix this by moving the implementations into a gsp_mem module in fw.rs that uses the dma_read!() / dma_write!() macros, making the original methods on DmaGspMem thin forwarding wrappers. An alternative approach would have been to wrap the shared memory in Opaque, but that would have required even more unsafe code. Since the gsp_mem module lives in fw.rs (to access firmware-specific binding field names), GspMem, Msgq and their relevant fields are temporarily widened to pub(super). This will be reverted once IoView projections are available. Cc: Gary Guo Closes: https://lore.kernel.org/nouveau/DGUT14ILG35P.1UMNRKU93JUM1@kernel.org/ Fixes: 75f6b1de8133 ("gpu: nova-core: gsp: Add GSP command queue bindings and handling") Reviewed-by: Alexandre Courbot Link: https://patch.msgid.link/20260309225408.27714-1-dakr@kernel.org [ Use pub(super) where possible; replace bitwise-and with modulo operator analogous to [1]. - Danilo ] Link: https://lore.kernel.org/all/20260129-nova-core-cmdq1-v3-1-2ede85493a27@nvidia.com/ [1] Signed-off-by: Danilo Krummrich --- drivers/gpu/nova-core/gsp/cmdq.rs | 71 +++++---------------- drivers/gpu/nova-core/gsp/fw.rs | 101 ++++++++++++++++++++---------- 2 files changed, 84 insertions(+), 88 deletions(-) diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs index 9c5efd2daf45..03a4f3599849 100644 --- a/drivers/gpu/nova-core/gsp/cmdq.rs +++ b/drivers/gpu/nova-core/gsp/cmdq.rs @@ -2,11 +2,7 @@ use core::{ cmp, - mem, - sync::atomic::{ - fence, - Ordering, // - }, // + mem, // }; use kernel::{ @@ -146,30 +142,32 @@ struct MsgqData { #[repr(C)] // There is no struct defined for this in the open-gpu-kernel-source headers. // Instead it is defined by code in `GspMsgQueuesInit()`. -struct Msgq { +// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module. +pub(super) struct Msgq { /// Header for sending messages, including the write pointer. - tx: MsgqTxHeader, + pub(super) tx: MsgqTxHeader, /// Header for receiving messages, including the read pointer. - rx: MsgqRxHeader, + pub(super) rx: MsgqRxHeader, /// The message queue proper. msgq: MsgqData, } /// Structure shared between the driver and the GSP and containing the command and message queues. #[repr(C)] -struct GspMem { +// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module. +pub(super) struct GspMem { /// Self-mapping page table entries. ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>, /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the /// write and read pointers that the CPU updates. /// /// This member is read-only for the GSP. - cpuq: Msgq, + pub(super) cpuq: Msgq, /// GSP queue: the GSP writes messages here, and the driver reads them. It also contains the /// write and read pointers that the GSP updates. /// /// This member is read-only for the driver. - gspq: Msgq, + pub(super) gspq: Msgq, } impl GspMem { @@ -331,12 +329,7 @@ fn allocate_command(&mut self, size: usize) -> Result> { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn gsp_write_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - (unsafe { (*gsp_mem).gspq.tx.write_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::gsp_write_ptr(&self.0) } // Returns the index of the memory page the GSP will read the next command from. @@ -345,12 +338,7 @@ fn gsp_write_ptr(&self) -> u32 { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn gsp_read_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - (unsafe { (*gsp_mem).gspq.rx.read_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::gsp_read_ptr(&self.0) } // Returns the index of the memory page the CPU can read the next message from. @@ -359,27 +347,12 @@ fn gsp_read_ptr(&self) -> u32 { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn cpu_read_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The ['CoherentAllocation'] contains at least one object. - // - By the invariants of CoherentAllocation the pointer is valid. - (unsafe { (*gsp_mem).cpuq.rx.read_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::cpu_read_ptr(&self.0) } // Informs the GSP that it can send `elem_count` new pages into the message queue. fn advance_cpu_read_ptr(&mut self, elem_count: u32) { - let rptr = self.cpu_read_ptr().wrapping_add(elem_count) % MSGQ_NUM_PAGES; - - // Ensure read pointer is properly ordered. - fence(Ordering::SeqCst); - - let gsp_mem = self.0.start_ptr_mut(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - unsafe { (*gsp_mem).cpuq.rx.set_read_ptr(rptr) }; + super::fw::gsp_mem::advance_cpu_read_ptr(&self.0, elem_count) } // Returns the index of the memory page the CPU can write the next command to. @@ -388,26 +361,12 @@ fn advance_cpu_read_ptr(&mut self, elem_count: u32) { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn cpu_write_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - (unsafe { (*gsp_mem).cpuq.tx.write_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::cpu_write_ptr(&self.0) } // Informs the GSP that it can process `elem_count` new pages from the command queue. fn advance_cpu_write_ptr(&mut self, elem_count: u32) { - let wptr = self.cpu_write_ptr().wrapping_add(elem_count) & MSGQ_NUM_PAGES; - let gsp_mem = self.0.start_ptr_mut(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - unsafe { (*gsp_mem).cpuq.tx.set_write_ptr(wptr) }; - - // Ensure all command data is visible before triggering the GSP read. - fence(Ordering::SeqCst); + super::fw::gsp_mem::advance_cpu_write_ptr(&self.0, elem_count) } } diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs index 83ff91614e36..040b30ec3089 100644 --- a/drivers/gpu/nova-core/gsp/fw.rs +++ b/drivers/gpu/nova-core/gsp/fw.rs @@ -40,6 +40,75 @@ }, }; +// TODO: Replace with `IoView` projections once available; the `unwrap()` calls go away once we +// switch to the new `dma::Coherent` API. +pub(super) mod gsp_mem { + use core::sync::atomic::{ + fence, + Ordering, // + }; + + use kernel::{ + dma::CoherentAllocation, + dma_read, + dma_write, + prelude::*, // + }; + + use crate::gsp::cmdq::{ + GspMem, + MSGQ_NUM_PAGES, // + }; + + pub(in crate::gsp) fn gsp_write_ptr(qs: &CoherentAllocation) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { Ok(dma_read!(qs, [0]?.gspq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn gsp_read_ptr(qs: &CoherentAllocation) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { Ok(dma_read!(qs, [0]?.gspq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn cpu_read_ptr(qs: &CoherentAllocation) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { Ok(dma_read!(qs, [0]?.cpuq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn advance_cpu_read_ptr(qs: &CoherentAllocation, count: u32) { + let rptr = cpu_read_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES; + + // Ensure read pointer is properly ordered. + fence(Ordering::SeqCst); + + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { + dma_write!(qs, [0]?.cpuq.rx.0.readPtr, rptr); + Ok(()) + }() + .unwrap() + } + + pub(in crate::gsp) fn cpu_write_ptr(qs: &CoherentAllocation) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { Ok(dma_read!(qs, [0]?.cpuq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn advance_cpu_write_ptr(qs: &CoherentAllocation, count: u32) { + let wptr = cpu_write_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES; + + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { + dma_write!(qs, [0]?.cpuq.tx.0.writePtr, wptr); + Ok(()) + }() + .unwrap(); + + // Ensure all command data is visible before triggering the GSP read. + fence(Ordering::SeqCst); + } +} + /// Empty type to group methods related to heap parameters for running the GSP firmware. enum GspFwHeapParams {} @@ -708,22 +777,6 @@ pub(crate) fn new(msgq_size: u32, rx_hdr_offset: u32, msg_count: u32) -> Self { entryOff: num::usize_into_u32::(), }) } - - /// Returns the value of the write pointer for this queue. - pub(crate) fn write_ptr(&self) -> u32 { - let ptr = core::ptr::from_ref(&self.0.writePtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.read_volatile() } - } - - /// Sets the value of the write pointer for this queue. - pub(crate) fn set_write_ptr(&mut self, val: u32) { - let ptr = core::ptr::from_mut(&mut self.0.writePtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.write_volatile(val) } - } } // SAFETY: Padding is explicit and does not contain uninitialized data. @@ -739,22 +792,6 @@ impl MsgqRxHeader { pub(crate) fn new() -> Self { Self(Default::default()) } - - /// Returns the value of the read pointer for this queue. - pub(crate) fn read_ptr(&self) -> u32 { - let ptr = core::ptr::from_ref(&self.0.readPtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.read_volatile() } - } - - /// Sets the value of the read pointer for this queue. - pub(crate) fn set_read_ptr(&mut self, val: u32) { - let ptr = core::ptr::from_mut(&mut self.0.readPtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.write_volatile(val) } - } } // SAFETY: Padding is explicit and does not contain uninitialized data. From a9683730e8b1d632674f81844ed03ddfbe4821c0 Mon Sep 17 00:00:00 2001 From: Casey Connolly Date: Fri, 6 Mar 2026 18:47:07 +0100 Subject: [PATCH 394/487] ASoC: detect empty DMI strings Some bootloaders like recent versions of U-Boot may install some DMI properties with empty values rather than not populate them. This manages to make its way through the validator and cleanup resulting in a rogue hyphen being appended to the card longname. Fixes: 4e01e5dbba96 ("ASoC: improve the DMI long card code in asoc-core") Signed-off-by: Casey Connolly Link: https://patch.msgid.link/20260306174707.283071-2-casey.connolly@linaro.org Signed-off-by: Mark Brown --- sound/soc/soc-core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index cf826c2a8b59..573693e21780 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1863,12 +1863,15 @@ static void cleanup_dmi_name(char *name) /* * Check if a DMI field is valid, i.e. not containing any string - * in the black list. + * in the black list and not the empty string. */ static int is_dmi_valid(const char *field) { int i = 0; + if (!field[0]) + return 0; + while (dmi_blacklist[i]) { if (strstr(field, dmi_blacklist[i])) return 0; From 464b1c115852fe025635ae2065e00caced184d92 Mon Sep 17 00:00:00 2001 From: Qing Wang Date: Wed, 11 Mar 2026 17:36:17 +0800 Subject: [PATCH 395/487] slab: fix memory leak when refill_sheaf() fails When refill_sheaf() partially fills one sheaf (e.g., fills 5 objects but need to fill 10), it will update sheaf->size and return -ENOMEM. However, the callers (alloc_full_sheaf() and __pcs_replace_empty_main()) directly call free_empty_sheaf() on failure, which only does kfree(sheaf), causing the partially allocated objects memory in sheaf->objects[] leaked. Fix this by calling sheaf_flush_unused() before free_empty_sheaf() to free objects of sheaf->objects[]. And also add a WARN_ON() in free_empty_sheaf() to catch any future cases where a non-empty sheaf is being freed. Fixes: ed30c4adfc2b ("slab: add optimized sheaf refill from partial list") Signed-off-by: Qing Wang Link: https://patch.msgid.link/20260311093617.4155965-1-wangqing7171@gmail.com Reviewed-by: Harry Yoo Reviewed-by: Hao Li Signed-off-by: Vlastimil Babka (SUSE) --- mm/slub.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/mm/slub.c b/mm/slub.c index 6371838d2352..2b2d33cc735c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2790,6 +2790,7 @@ static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf) if (s->flags & SLAB_KMALLOC) mark_obj_codetag_empty(sheaf); + VM_WARN_ON_ONCE(sheaf->size > 0); kfree(sheaf); stat(s, SHEAF_FREE); @@ -2821,6 +2822,7 @@ static int refill_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf, return 0; } +static void sheaf_flush_unused(struct kmem_cache *s, struct slab_sheaf *sheaf); static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp) { @@ -2830,6 +2832,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp) return NULL; if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) { + sheaf_flush_unused(s, sheaf); free_empty_sheaf(s, sheaf); return NULL; } @@ -4616,6 +4619,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, * we must be very low on memory so don't bother * with the barn */ + sheaf_flush_unused(s, empty); free_empty_sheaf(s, empty); } } else { From cf534a09fb621b0aa875613e3cd88aee336e16d7 Mon Sep 17 00:00:00 2001 From: Kai Huang Date: Tue, 3 Mar 2026 09:51:58 +1300 Subject: [PATCH 396/487] KVM: selftests: Increase 'maxnode' for guest_memfd tests Increase 'maxnode' when using 'get_mempolicy' syscall in guest_memfd mmap and NUMA policy tests to fix a failure on one Intel GNR platform. On a CXL-capable platform, the memory affinity of CXL memory regions may not be covered by the SRAT. Since each CXL memory region is enumerated via a CFMWS table, at early boot the kernel parses all CFMWS tables to detect all CXL memory regions and assigns a 'faked' NUMA node for each of them, starting from the highest NUMA node ID enumerated via the SRAT. This increases the 'nr_node_ids'. E.g., on the aforementioned Intel GNR platform which has 4 NUMA nodes and 18 CFMWS tables, it increases to 22. This results in the 'get_mempolicy' syscall failure on that platform, because currently 'maxnode' is hard-coded to 8 but the 'get_mempolicy' syscall requires the 'maxnode' to be not smaller than the 'nr_node_ids'. Increase the 'maxnode' to the number of bits of 'nodemask', which is 'unsigned long', to fix this. This may not cover all systems. Perhaps a better way is to always set the 'nodemask' and 'maxnode' based on the actual maximum NUMA node ID on the system, but for now just do the simple way. Reported-by: Yi Lai Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221014 Closes: https://lore.kernel.org/all/bug-221014-28872@https.bugzilla.kernel.org%2F Signed-off-by: Kai Huang Reviewed-by: Yuan Yao Link: https://patch.msgid.link/20260302205158.178058-1-kai.huang@intel.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/guest_memfd_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 618c937f3c90..cc329b57ce2e 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -80,7 +80,7 @@ static void test_mbind(int fd, size_t total_size) { const unsigned long nodemask_0 = 1; /* nid: 0 */ unsigned long nodemask = 0; - unsigned long maxnode = 8; + unsigned long maxnode = BITS_PER_TYPE(nodemask); int policy; char *mem; int ret; From 4c0134639694fcdc4ab041d7c53d6188a3e18040 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 3 Mar 2026 11:03:38 -0800 Subject: [PATCH 397/487] KVM: PPC: e500: Fix build error due to using kmalloc_obj() with wrong type Fix a build error in kvmppc_e500_tlb_init() that was introduced by the conversion to use kzalloc_objs(), as KVM confusingly uses the size of the structure that is one and only field in tlbe_priv: arch/powerpc/kvm/e500_mmu.c:923:33: error: assignment to 'struct tlbe_priv *' from incompatible pointer type 'struct tlbe_ref *' [-Wincompatible-pointer-types] 923 | vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref, | ^ KVM has been flawed since commit 0164c0f0c404 ("KVM: PPC: e500: clear up confusion between host and guest entries"), but the issue went unnoticed until kmalloc_obj() came along and enforced types, as "struct tlbe_priv" was just a wrapper of "struct tlbe_ref" (why on earth the two ever existed separately...). Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types") Cc: Kees Cook Reviewed-by: Christophe Leroy (CS GROUP) Link: https://patch.msgid.link/20260303190339.974325-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/e500_mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 48580c85f23b..75ed1496ead5 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -920,12 +920,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) vcpu_e500->gtlb_offset[0] = 0; vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE; - vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref, + vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_priv, vcpu_e500->gtlb_params[0].entries); if (!vcpu_e500->gtlb_priv[0]) goto free_vcpu; - vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_ref, + vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_priv, vcpu_e500->gtlb_params[1].entries); if (!vcpu_e500->gtlb_priv[1]) goto free_vcpu; From fe2a08eca5caa77398bfa321bd321d087b0b44b0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 3 Mar 2026 11:03:39 -0800 Subject: [PATCH 398/487] KVM: PPC: e500: Rip out "struct tlbe_ref" Complete the ~13 year journey started by commit 47bf379742bf ("kvm/ppc/e500: eliminate tlb_refs"), and actually remove "struct tlbe_ref". No functional change intended (verified disassembly of e500_mmu.o and e500_mmu_host.o is identical before and after). Link: https://patch.msgid.link/20260303190339.974325-3-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/e500.h | 6 +-- arch/powerpc/kvm/e500_mmu_host.c | 91 +++++++++++++++----------------- 2 files changed, 45 insertions(+), 52 deletions(-) diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index f9acf866c709..e4469ad73a2e 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -39,15 +39,11 @@ enum vcpu_ftr { /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) -struct tlbe_ref { +struct tlbe_priv { kvm_pfn_t pfn; /* valid only for TLB0, except briefly */ unsigned int flags; /* E500_TLB_* */ }; -struct tlbe_priv { - struct tlbe_ref ref; -}; - #ifdef CONFIG_KVM_E500V2 struct vcpu_id_table; #endif diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 06caf8bbbe2b..37e0d3d9e244 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -189,16 +189,16 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, { struct kvm_book3e_206_tlb_entry *gtlbe = get_entry(vcpu_e500, tlbsel, esel); - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) { - WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), - "%s: flags %x\n", __func__, ref->flags); + if (!(tlbe->flags & E500_TLB_VALID)) { + WARN(tlbe->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, tlbe->flags); WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); } - if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; int hw_tlb_indx; unsigned long flags; @@ -216,28 +216,28 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, } mb(); vcpu_e500->g2h_tlb1_map[esel] = 0; - ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); local_irq_restore(flags); } - if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_TLB0) { /* * TLB1 entry is backed by 4k pages. This should happen * rarely and is not worth optimizing. Invalidate everything. */ kvmppc_e500_tlbil_all(vcpu_e500); - ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); } /* * If TLB entry is still valid then it's a TLB0 entry, and thus * backed by at most one host tlbe per shadow pid */ - if (ref->flags & E500_TLB_VALID) + if (tlbe->flags & E500_TLB_VALID) kvmppc_e500_tlbil_one(vcpu_e500, gtlbe); /* Mark the TLB as not backed by the host anymore */ - ref->flags = 0; + tlbe->flags = 0; } static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) @@ -245,26 +245,26 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, - struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg, - bool writable) +static inline void kvmppc_e500_tlbe_setup(struct tlbe_priv *tlbe, + struct kvm_book3e_206_tlb_entry *gtlbe, + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { - ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + tlbe->pfn = pfn; + tlbe->flags = E500_TLB_VALID; if (writable) - ref->flags |= E500_TLB_WRITABLE; + tlbe->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ - ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; + tlbe->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; } -static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) +static inline void kvmppc_e500_tlbe_release(struct tlbe_priv *tlbe) { - if (ref->flags & E500_TLB_VALID) { + if (tlbe->flags & E500_TLB_VALID) { /* FIXME: don't log bogus pfn for TLB1 */ - trace_kvm_booke206_ref_release(ref->pfn, ref->flags); - ref->flags = 0; + trace_kvm_booke206_ref_release(tlbe->pfn, tlbe->flags); + tlbe->flags = 0; } } @@ -284,11 +284,8 @@ static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) int i; for (tlbsel = 0; tlbsel <= 1; tlbsel++) { - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) + kvmppc_e500_tlbe_release(&vcpu_e500->gtlb_priv[tlbsel][i]); } } @@ -304,18 +301,18 @@ void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) static void kvmppc_e500_setup_stlbe( struct kvm_vcpu *vcpu, struct kvm_book3e_206_tlb_entry *gtlbe, - int tsize, struct tlbe_ref *ref, u64 gvaddr, + int tsize, struct tlbe_priv *tlbe, u64 gvaddr, struct kvm_book3e_206_tlb_entry *stlbe) { - kvm_pfn_t pfn = ref->pfn; + kvm_pfn_t pfn = tlbe->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; - bool writable = !!(ref->flags & E500_TLB_WRITABLE); + bool writable = !!(tlbe->flags & E500_TLB_WRITABLE); - BUG_ON(!(ref->flags & E500_TLB_VALID)); + BUG_ON(!(tlbe->flags & E500_TLB_VALID)); /* Force IPROT=0 for all guest mappings. */ stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; - stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); + stlbe->mas2 = (gvaddr & MAS2_EPN) | (tlbe->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } @@ -323,7 +320,7 @@ static void kvmppc_e500_setup_stlbe( static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe, - struct tlbe_ref *ref) + struct tlbe_priv *tlbe) { struct kvm_memory_slot *slot; unsigned int psize; @@ -455,9 +452,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, } } - kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); + kvmppc_e500_tlbe_setup(tlbe, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, - ref, gvaddr, stlbe); + tlbe, gvaddr, stlbe); writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ @@ -474,17 +471,17 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, struct kvm_book3e_206_tlb_entry *stlbe) { struct kvm_book3e_206_tlb_entry *gtlbe; - struct tlbe_ref *ref; + struct tlbe_priv *tlbe; int stlbsel = 0; int sesel = 0; int r; gtlbe = get_entry(vcpu_e500, 0, esel); - ref = &vcpu_e500->gtlb_priv[0][esel].ref; + tlbe = &vcpu_e500->gtlb_priv[0][esel]; r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe), get_tlb_raddr(gtlbe) >> PAGE_SHIFT, - gtlbe, 0, stlbe, ref); + gtlbe, 0, stlbe, tlbe); if (r) return r; @@ -494,7 +491,7 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, } static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, - struct tlbe_ref *ref, + struct tlbe_priv *tlbe, int esel) { unsigned int sesel = vcpu_e500->host_tlb1_nv++; @@ -507,10 +504,10 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_BITMAP; vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; - WARN_ON(!(ref->flags & E500_TLB_VALID)); + WARN_ON(!(tlbe->flags & E500_TLB_VALID)); return sesel; } @@ -522,24 +519,24 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[1][esel]; int sesel; int r; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - ref); + tlbe); if (r) return r; /* Use TLB0 when we can only map a page with 4k */ if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) { - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_TLB0; write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0); return 0; } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, tlbe, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -561,11 +558,11 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Triggers after clear_tlb_privs or on initial mapping */ - if (!(priv->ref.flags & E500_TLB_VALID)) { + if (!(priv->flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K, - &priv->ref, eaddr, &stlbe); + priv, eaddr, &stlbe); write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0); } break; From 4b3b8a8b0df1a5e7a1af04ff512df2c80db35dc8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Carlos=20L=C3=B3pez?= Date: Mon, 9 Feb 2026 16:31:09 +0100 Subject: [PATCH 399/487] KVM: x86: synthesize CPUID bits only if CPU capability is set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM incorrectly synthesizes CPUID bits for KVM-only leaves, as the following branch in kvm_cpu_cap_init() is never taken: if (leaf < NCAPINTS) kvm_cpu_caps[leaf] &= kernel_cpu_caps[leaf]; This means that bits set via SYNTHESIZED_F() for KVM-only leaves are unconditionally set. This for example can cause issues for SEV-SNP guests running on Family 19h CPUs, as TSA_SQ_NO and TSA_L1_NO are always enabled by KVM in 80000021[ECX]. When userspace issues a SNP_LAUNCH_UPDATE command to update the CPUID page for the guest, SNP firmware will explicitly reject the command if the page sets sets these bits on vulnerable CPUs. To fix this, check in SYNTHESIZED_F() that the corresponding X86 capability is set before adding it to to kvm_cpu_cap_features. Fixes: 31272abd5974 ("KVM: SVM: Advertise TSA CPUID bits to guests") Link: https://lore.kernel.org/all/20260208164233.30405-1-clopez@suse.de/ Signed-off-by: Carlos López Reviewed-by: Nikolay Borisov Link: https://patch.msgid.link/20260209153108.70667-2-clopez@suse.de Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d2486506a808..8137927e7387 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -776,7 +776,10 @@ do { \ #define SYNTHESIZED_F(name) \ ({ \ kvm_cpu_cap_synthesized |= feature_bit(name); \ - F(name); \ + \ + BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ + if (boot_cpu_has(X86_FEATURE_##name)) \ + F(name); \ }) /* From a5264387c2ee42fca92ac792199008fc60ee82f1 Mon Sep 17 00:00:00 2001 From: Manuel Andreas Date: Thu, 19 Feb 2026 21:05:49 +0100 Subject: [PATCH 400/487] KVM: x86: hyper-v: Validate all GVAs during PV TLB flush In KVM guests with Hyper-V hypercalls enabled, the hypercalls HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST and HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX allow a guest to request invalidation of portions of a virtual TLB. For this, the hypercall parameter includes a list of GVAs that are supposed to be invalidated. Currently, only the base GVA is checked to be canonical. In reality, this check needs to be performed for the entire range of GVAs, as checking only the base GVA enables guests running on Intel hardware to trigger a WARN_ONCE in the host (see Fixes commit below). Move the check for non-canonical addresses to be performed for every GVA of the supplied range to avoid the splat, and to be more in line with the Hyper-V specification, since, although unlikely, a range starting with an invalid GVA may still contain GVAs that are valid. Fixes: fa787ac07b3c ("KVM: x86/hyper-v: Skip non-canonical addresses during PV TLB flush") Signed-off-by: Manuel Andreas Reviewed-by: Vitaly Kuznetsov Link: https://patch.msgid.link/00a7a31b-573b-4d92-91f8-7d7e2f88ea48@tum.de [sean: massage changelog] Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 30202942289a..9b140bbdc1d8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1981,16 +1981,17 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) goto out_flush_all; - if (is_noncanonical_invlpg_address(entries[i], vcpu)) - continue; - /* * Lower 12 bits of 'address' encode the number of additional * pages to flush. */ gva = entries[i] & PAGE_MASK; - for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) + for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) { + if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu)) + continue; + kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE); + } ++vcpu->stat.tlb_flush; } From f78e627a01bd4ec0219566d2c9c40f3c3614f875 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 20 Feb 2026 14:02:16 -0800 Subject: [PATCH 401/487] KVM: VMX: Fix a wrong MSR update in add_atomic_switch_msr() The previous change had a bug to update a guest MSR with a host value. Fixes: c3d6a7210a4de9096 ("KVM: VMX: Dedup code for adding MSR to VMCS's auto list") Signed-off-by: Namhyung Kim Reviewed-by: Dapeng Mi Link: https://patch.msgid.link/20260220220216.389475-1-namhyung@kernel.org Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 967b58a8ab9d..83d057cfa816 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1149,7 +1149,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, } vmx_add_auto_msr(&m->guest, msr, guest_val, VM_ENTRY_MSR_LOAD_COUNT, kvm); - vmx_add_auto_msr(&m->guest, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm); + vmx_add_auto_msr(&m->host, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm); } static bool update_transition_efer(struct vcpu_vmx *vmx) From b54e4707a64be93a8ab3348e32e89817229b5eaa Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Wed, 4 Feb 2026 04:12:06 -0500 Subject: [PATCH 402/487] KVM: x86: Fix SRCU list traversal in kvm_fire_mask_notifiers() The mask_notifier_list is protected by kvm->irq_srcu, but the traversal in kvm_fire_mask_notifiers() incorrectly uses hlist_for_each_entry_rcu(). This leads to lockdep warnings because the standard RCU iterator expects to be under rcu_read_lock(), not SRCU. Replace the RCU variant with hlist_for_each_entry_srcu() and provide the proper srcu_read_lock_held() annotation to ensure correct synchronization and silence lockdep. Signed-off-by: Li RongQing Link: https://patch.msgid.link/20260204091206.2617-1-lirongqing@baidu.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/ioapic.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index bb257793b6cb..eed96ff6e722 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -321,7 +321,8 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, idx = srcu_read_lock(&kvm->irq_srcu); gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); if (gsi != -1) - hlist_for_each_entry_rcu(kimn, &ioapic->mask_notifier_list, link) + hlist_for_each_entry_srcu(kimn, &ioapic->mask_notifier_list, link, + srcu_read_lock_held(&kvm->irq_srcu)) if (kimn->irq == gsi) kimn->func(kimn, mask); srcu_read_unlock(&kvm->irq_srcu, idx); From e2ffe85b6d2bb7780174b87aa4468a39be17eb81 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Thu, 5 Feb 2026 15:15:26 -0800 Subject: [PATCH 403/487] KVM: x86: Introduce KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM Add KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM to allow L1 to set FREEZE_IN_SMM in vmcs12's GUEST_IA32_DEBUGCTL field, as permitted prior to commit 6b1dd26544d0 ("KVM: VMX: Preserve host's DEBUGCTLMSR_FREEZE_IN_SMM while running the guest"). Enable the quirk by default for backwards compatibility (like all quirks); userspace can disable it via KVM_CAP_DISABLE_QUIRKS2 for consistency with the constraints on WRMSR(IA32_DEBUGCTL). Note that the quirk only bypasses the consistency check. The vmcs02 bit is still owned by the host, and PMCs are not frozen during virtualized SMM. In particular, if a host administrator decides that PMCs should not be frozen during physical SMM, then L1 has no say in the matter. Fixes: 095686e6fcb4 ("KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter") Cc: stable@vger.kernel.org Signed-off-by: Jim Mattson Link: https://patch.msgid.link/20260205231537.1278753-1-jmattson@google.com [sean: tag for stable@, clean-up and fix goofs in the comment and docs] Signed-off-by: Sean Christopherson [Rename quirk. - Paolo] Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 8 ++++++++ arch/x86/include/asm/kvm_host.h | 3 ++- arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/vmx/nested.c | 22 ++++++++++++++++++---- 4 files changed, 29 insertions(+), 5 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 6f85e1b321dd..19365b284395 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8543,6 +8543,14 @@ KVM_X86_QUIRK_IGNORE_GUEST_PAT By default, on Intel platforms, KVM ignores guest software, for example if it does not expose a bochs graphics device (which is known to have had a buggy driver). + +KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM By default, KVM relaxes the consistency + check for GUEST_IA32_DEBUGCTL in vmcs12 + to allow FREEZE_IN_SMM to be set. When + this quirk is disabled, KVM requires this + bit to be cleared. Note that the vmcs02 + bit is still completely controlled by the + host, regardless of the quirk setting. =================================== ============================================ 7.32 KVM_CAP_MAX_VCPU_ID diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ff07c45e3c73..6e4e3ef9b8c7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2485,7 +2485,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \ KVM_X86_QUIRK_SLOT_ZAP_ALL | \ KVM_X86_QUIRK_STUFF_FEATURE_MSRS | \ - KVM_X86_QUIRK_IGNORE_GUEST_PAT) + KVM_X86_QUIRK_IGNORE_GUEST_PAT | \ + KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM) #define KVM_X86_CONDITIONAL_QUIRKS \ (KVM_X86_QUIRK_CD_NW_CLEARED | \ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 846a63215ce1..0d4538fa6c31 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -476,6 +476,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8) #define KVM_X86_QUIRK_IGNORE_GUEST_PAT (1 << 9) +#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 248635da6766..603c98de2cc8 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3300,10 +3300,24 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP))) return -EINVAL; - if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || - CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) - return -EINVAL; + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + u64 debugctl = vmcs12->guest_ia32_debugctl; + + /* + * FREEZE_IN_SMM is not virtualized, but allow L1 to set it in + * vmcs12's DEBUGCTL under a quirk for backwards compatibility. + * Note that the quirk only relaxes the consistency check. The + * vmcc02 bit is still under the control of the host. In + * particular, if a host administrator decides to clear the bit, + * then L1 has no say in the matter. + */ + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM)) + debugctl &= ~DEBUGCTLMSR_FREEZE_IN_SMM; + + if (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || + CC(!vmx_is_valid_debugctl(vcpu, debugctl, false))) + return -EINVAL; + } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && CC(!kvm_pat_valid(vmcs12->guest_ia32_pat))) From 3989a6d036c8ec82c0de3614bed23a1dacd45de5 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 3 Feb 2026 11:07:09 -0800 Subject: [PATCH 404/487] KVM: SVM: Initialize AVIC VMCB fields if AVIC is enabled with in-kernel APIC Initialize all per-vCPU AVIC control fields in the VMCB if AVIC is enabled in KVM and the VM has an in-kernel local APIC, i.e. if it's _possible_ the vCPU could activate AVIC at any point in its lifecycle. Configuring the VMCB if and only if AVIC is active "works" purely because of optimizations in kvm_create_lapic() to speculatively set apicv_active if AVIC is enabled *and* to defer updates until the first KVM_RUN. In quotes because KVM likely won't do the right thing if kvm_apicv_activated() is false, i.e. if a vCPU is created while APICv is inhibited at the VM level for whatever reason. E.g. if the inhibit is *removed* before KVM_REQ_APICV_UPDATE is handled in KVM_RUN, then __kvm_vcpu_update_apicv() will elide calls to vendor code due to seeing "apicv_active == activate". Cleaning up the initialization code will also allow fixing a bug where KVM incorrectly leaves CR8 interception enabled when AVIC is activated without creating a mess with respect to whether AVIC is activated or not. Cc: stable@vger.kernel.org Fixes: 67034bb9dd5e ("KVM: SVM: Add irqchip_split() checks before enabling AVIC") Fixes: 6c3e4422dd20 ("svm: Add support for dynamic APICv") Reviewed-by: Naveen N Rao (AMD) Reviewed-by: Jim Mattson Link: https://patch.msgid.link/20260203190711.458413-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/avic.c | 2 +- arch/x86/kvm/svm/svm.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index f92214b1a938..44e07c27b190 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -368,7 +368,7 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) vmcb->control.avic_physical_id = __sme_set(__pa(kvm_svm->avic_physical_id_table)); vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE; - if (kvm_apicv_activated(svm->vcpu.kvm)) + if (kvm_vcpu_apicv_active(&svm->vcpu)) avic_activate_vmcb(svm); else avic_deactivate_vmcb(svm); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8f8bc863e214..7806321c37bc 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1189,7 +1189,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event) if (guest_cpu_cap_has(vcpu, X86_FEATURE_ERAPS)) svm->vmcb->control.erap_ctl |= ERAP_CONTROL_ALLOW_LARGER_RAP; - if (kvm_vcpu_apicv_active(vcpu)) + if (enable_apicv && irqchip_in_kernel(vcpu->kvm)) avic_init_vmcb(svm, vmcb); if (vnmi) From 87d0f901a9bd8ae6be57249c737f20ac0cace93d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 3 Feb 2026 11:07:10 -0800 Subject: [PATCH 405/487] KVM: SVM: Set/clear CR8 write interception when AVIC is (de)activated Explicitly set/clear CR8 write interception when AVIC is (de)activated to fix a bug where KVM leaves the interception enabled after AVIC is activated. E.g. if KVM emulates INIT=>WFS while AVIC is deactivated, CR8 will remain intercepted in perpetuity. On its own, the dangling CR8 intercept is "just" a performance issue, but combined with the TPR sync bug fixed by commit d02e48830e3f ("KVM: SVM: Sync TPR from LAPIC into VMCB::V_TPR even if AVIC is active"), the danging intercept is fatal to Windows guests as the TPR seen by hardware gets wildly out of sync with reality. Note, VMX isn't affected by the bug as TPR_THRESHOLD is explicitly ignored when Virtual Interrupt Delivery is enabled, i.e. when APICv is active in KVM's world. I.e. there's no need to trigger update_cr8_intercept(), this is firmly an SVM implementation flaw/detail. WARN if KVM gets a CR8 write #VMEXIT while AVIC is active, as KVM should never enter the guest with AVIC enabled and CR8 writes intercepted. Fixes: 3bbf3565f48c ("svm: Do not intercept CR8 when enable AVIC") Cc: stable@vger.kernel.org Cc: Jim Mattson Cc: Naveen N Rao (AMD) Cc: Maciej S. Szmigiero Reviewed-by: Naveen N Rao (AMD) Reviewed-by: Jim Mattson Link: https://patch.msgid.link/20260203190711.458413-3-seanjc@google.com Signed-off-by: Sean Christopherson [Squash fix to avic_deactivate_vmcb. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/avic.c | 7 +++++-- arch/x86/kvm/svm/svm.c | 7 ++++--- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 44e07c27b190..f7ec7914e3c4 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -189,12 +189,12 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); - vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; vmcb->control.avic_physical_id |= avic_get_max_physical_id(vcpu); - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + svm_clr_intercept(svm, INTERCEPT_CR8_WRITE); + /* * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR * accesses, while interrupt injection to a running vCPU can be @@ -226,6 +226,9 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm) vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); + /* * If running nested and the guest uses its own MSR bitmap, there * is no need to update L0's msr bitmap diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7806321c37bc..2772f22df7ed 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1077,8 +1077,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event) svm_set_intercept(svm, INTERCEPT_CR0_WRITE); svm_set_intercept(svm, INTERCEPT_CR3_WRITE); svm_set_intercept(svm, INTERCEPT_CR4_WRITE); - if (!kvm_vcpu_apicv_active(vcpu)) - svm_set_intercept(svm, INTERCEPT_CR8_WRITE); + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); set_dr_intercepts(svm); @@ -2674,9 +2673,11 @@ static int dr_interception(struct kvm_vcpu *vcpu) static int cr8_write_interception(struct kvm_vcpu *vcpu) { + u8 cr8_prev = kvm_get_cr8(vcpu); int r; - u8 cr8_prev = kvm_get_cr8(vcpu); + WARN_ON_ONCE(kvm_vcpu_apicv_active(vcpu)); + /* instruction emulation calls kvm_set_cr8() */ r = cr_interception(vcpu); if (lapic_in_kernel(vcpu)) From 5a30e8aea079b3e4e79d6ce7a878f5f42efe9d0b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Mar 2026 12:40:40 +0100 Subject: [PATCH 406/487] KVM: VMX: check validity of VMCS controls when returning from SMM The VMCS12 is not available while in SMM. However, it can be overwritten if userspace manages to trigger copy_enlightened_to_vmcs12() - for example via KVM_GET_NESTED_STATE. Because of this, the VMCS12 has to be checked for validity before it is used to generate the VMCS02. Move the check code out of vmx_set_nested_state() (the other "not a VMLAUNCH/VMRESUME" path that emulates a nested vmentry) and reuse it in vmx_leave_smm(). Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 39 +++++++++++++++++++++++++++------------ arch/x86/kvm/vmx/nested.h | 1 + arch/x86/kvm/vmx/vmx.c | 4 ++++ 3 files changed, 32 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 603c98de2cc8..937aeb474af7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6856,13 +6856,34 @@ void vmx_leave_nested(struct kvm_vcpu *vcpu) free_nested(vcpu); } +int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu) +{ + enum vm_entry_failure_code ignored; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + if (nested_cpu_has_shadow_vmcs(vmcs12) && + vmcs12->vmcs_link_pointer != INVALID_GPA) { + struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); + + if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || + !shadow_vmcs12->hdr.shadow_vmcs) + return -EINVAL; + } + + if (nested_vmx_check_controls(vcpu, vmcs12) || + nested_vmx_check_host_state(vcpu, vmcs12) || + nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) + return -EINVAL; + + return 0; +} + static int vmx_set_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12; - enum vm_entry_failure_code ignored; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = &user_kvm_nested_state->data.vmx[0]; int ret; @@ -6993,25 +7014,20 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.mtf_pending = !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); - ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != INVALID_GPA) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); + ret = -EINVAL; if (kvm_state->size < sizeof(*kvm_state) + sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12)) goto error_guest_mode; + ret = -EFAULT; if (copy_from_user(shadow_vmcs12, user_vmx_nested_state->shadow_vmcs12, - sizeof(*shadow_vmcs12))) { - ret = -EFAULT; - goto error_guest_mode; - } - - if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || - !shadow_vmcs12->hdr.shadow_vmcs) + sizeof(*shadow_vmcs12))) goto error_guest_mode; } @@ -7022,9 +7038,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, kvm_state->hdr.vmx.preemption_timer_deadline; } - if (nested_vmx_check_controls(vcpu, vmcs12) || - nested_vmx_check_host_state(vcpu, vmcs12) || - nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) + ret = nested_vmx_check_restored_vmcs12(vcpu); + if (ret < 0) goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index b844c5d59025..213a448104af 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -22,6 +22,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); +int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 83d057cfa816..bccc91a999d9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -8528,6 +8528,10 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) } if (vmx->nested.smm.guest_mode) { + /* Triple fault if the state is invalid. */ + if (nested_vmx_check_restored_vmcs12(vcpu) < 0) + return 1; + ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) return ret; From be5fa8737d42c5ba16d2ea72c23681f8abbb07e8 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Mar 2026 12:40:52 +0100 Subject: [PATCH 407/487] KVM: SVM: check validity of VMCB controls when returning from SMM The VMCB12 is stored in guest memory and can be mangled while in SMM; it is then reloaded by svm_leave_smm(), but it is not checked again for validity. Move the cached vmcb12 control and save consistency checks out of svm_set_nested_state() and into a helper, and reuse it in svm_leave_smm(). Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 12 ++++++++++-- arch/x86/kvm/svm/svm.c | 4 ++++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 53ab6ce3cc26..b36c33255bed 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -418,6 +418,15 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) return __nested_vmcb_check_controls(vcpu, ctl); } +int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu) +{ + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) + return -EINVAL; + + return 0; +} + /* * If a feature is not advertised to L1, clear the corresponding vmcb12 * intercept. @@ -1028,8 +1037,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_check_save(vcpu) || - !nested_vmcb_check_controls(vcpu)) { + if (nested_svm_check_cached_vmcb12(vcpu) < 0) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_info_1 = 0; vmcb12->control.exit_info_2 = 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2772f22df7ed..4eb2c36b8ff2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4880,6 +4880,10 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); + + if (nested_svm_check_cached_vmcb12(vcpu) < 0) + goto unmap_save; + ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false); if (ret) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index ebd7b36b1ceb..6942e6b0eda6 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -797,6 +797,7 @@ static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) int nested_svm_exit_handled(struct vcpu_svm *svm); int nested_svm_check_permissions(struct kvm_vcpu *vcpu); +int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); From c52b534f26574ddf2f67cf07992ae2c25e8932c8 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Mar 2026 13:43:57 +0100 Subject: [PATCH 408/487] selftests: kvm: extract common functionality out of smm_test.c Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/include/x86/smm.h | 17 ++++++++++++ .../testing/selftests/kvm/lib/x86/processor.c | 26 ++++++++++++++++++ tools/testing/selftests/kvm/x86/smm_test.c | 27 ++----------------- 3 files changed, 45 insertions(+), 25 deletions(-) create mode 100644 tools/testing/selftests/kvm/include/x86/smm.h diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h new file mode 100644 index 000000000000..19337c34f13e --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86/smm.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef SELFTEST_KVM_SMM_H +#define SELFTEST_KVM_SMM_H + +#include "kvm_util.h" + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t smram_gpa, + const void *smi_handler, size_t handler_size); + +void inject_smi(struct kvm_vcpu *vcpu); + +#endif /* SELFTEST_KVM_SMM_H */ diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index fab18e9be66c..23a44941e283 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -8,6 +8,7 @@ #include "kvm_util.h" #include "pmu.h" #include "processor.h" +#include "smm.h" #include "svm_util.h" #include "sev.h" #include "vmx.h" @@ -1444,3 +1445,28 @@ bool kvm_arch_has_default_irqchip(void) { return true; } + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t smram_gpa, + const void *smi_handler, size_t handler_size) +{ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, smram_gpa, + SMRAM_MEMSLOT, SMRAM_PAGES, 0); + TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, smram_gpa, + SMRAM_MEMSLOT) == smram_gpa, + "Could not allocate guest physical addresses for SMRAM"); + + memset(addr_gpa2hva(vm, smram_gpa), 0x0, SMRAM_SIZE); + memcpy(addr_gpa2hva(vm, smram_gpa) + 0x8000, smi_handler, handler_size); + vcpu_set_msr(vcpu, MSR_IA32_SMBASE, smram_gpa); +} + +void inject_smi(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vcpu, &events); + events.smi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_SMM; + vcpu_events_set(vcpu, &events); +} diff --git a/tools/testing/selftests/kvm/x86/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c index 55c88d664a94..ade8412bf94a 100644 --- a/tools/testing/selftests/kvm/x86/smm_test.c +++ b/tools/testing/selftests/kvm/x86/smm_test.c @@ -14,13 +14,11 @@ #include "test_util.h" #include "kvm_util.h" +#include "smm.h" #include "vmx.h" #include "svm_util.h" -#define SMRAM_SIZE 65536 -#define SMRAM_MEMSLOT ((1 << 16) | 1) -#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) #define SMRAM_GPA 0x1000000 #define SMRAM_STAGE 0xfe @@ -113,18 +111,6 @@ static void guest_code(void *arg) sync_with_host(DONE); } -void inject_smi(struct kvm_vcpu *vcpu) -{ - struct kvm_vcpu_events events; - - vcpu_events_get(vcpu, &events); - - events.smi.pending = 1; - events.flags |= KVM_VCPUEVENT_VALID_SMM; - - vcpu_events_set(vcpu, &events); -} - int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; @@ -140,16 +126,7 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, - SMRAM_MEMSLOT, SMRAM_PAGES, 0); - TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) - == SMRAM_GPA, "could not allocate guest physical addresses?"); - - memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE); - memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, - sizeof(smi_handler)); - - vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA); + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { if (kvm_cpu_has(X86_FEATURE_SVM)) From 3e745694b032b405ff1ced74a8b3b95cdd00a385 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Mar 2026 13:44:40 +0100 Subject: [PATCH 409/487] selftests: kvm: add a test that VMX validates controls on RSM Add a test checking that invalid eVMCS contents are validated after an RSM instruction is emulated. The failure mode is simply that the RSM succeeds, because KVM virtualizes NMIs anyway while running L2; the two pin-based execution controls used by the test are entirely handled by KVM and not by the processor. Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/Makefile.kvm | 1 + .../kvm/x86/evmcs_smm_controls_test.c | 150 ++++++++++++++++++ 2 files changed, 151 insertions(+) create mode 100644 tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index fdec90e85467..dc68371f76a3 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86 += x86/cpuid_test TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test TEST_GEN_PROGS_x86 += x86/feature_msrs_test +TEST_GEN_PROGS_x86 += x86/evmcs_smm_controls_test TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test TEST_GEN_PROGS_x86 += x86/fastops_test TEST_GEN_PROGS_x86 += x86/fix_hypercall_test diff --git a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c new file mode 100644 index 000000000000..af7c90103396 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026, Red Hat, Inc. + * + * Test that vmx_leave_smm() validates vmcs12 controls before re-entering + * nested guest mode on RSM. + */ +#include +#include +#include +#include +#include + +#include "test_util.h" +#include "kvm_util.h" +#include "smm.h" +#include "hyperv.h" +#include "vmx.h" + +#define SMRAM_GPA 0x1000000 +#define SMRAM_STAGE 0xfe + +#define SYNC_PORT 0xe + +#define STR(x) #x +#define XSTR(s) STR(s) + +/* + * SMI handler: runs in real-address mode. + * Reports SMRAM_STAGE via port IO, then does RSM. + */ +static uint8_t smi_handler[] = { + 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ + 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ + 0x0f, 0xaa, /* rsm */ +}; + +static inline void sync_with_host(uint64_t phase) +{ + asm volatile("in $" XSTR(SYNC_PORT) ", %%al \n" + : "+a" (phase)); +} + +static void l2_guest_code(void) +{ + sync_with_host(1); + + /* After SMI+RSM with invalid controls, we should not reach here. */ + vmcall(); +} + +static void guest_code(struct vmx_pages *vmx_pages, + struct hyperv_test_pages *hv_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + /* Set up Hyper-V enlightenments and eVMCS */ + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist); + evmcs_enable(); + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_evmcs(hv_pages)); + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_ASSERT(!vmlaunch()); + + /* L2 exits via vmcall if test fails */ + sync_with_host(2); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0; + struct hyperv_test_pages *hv; + struct hv_enlightened_vmcs *evmcs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_regs regs; + int stage_reported; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); + + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + hv = vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); + vcpu_args_set(vcpu, 2, vmx_pages_gva, hv_pages_gva); + + vcpu_run(vcpu); + + /* L2 is running and syncs with host. */ + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == 1, + "Expected stage 1, got %d", stage_reported); + + /* Inject SMI while L2 is running. */ + inject_smi(vcpu); + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == SMRAM_STAGE, + "Expected SMM handler stage %#x, got %#x", + SMRAM_STAGE, stage_reported); + + /* + * Guest is now paused in the SMI handler, about to execute RSM. + * Hack the eVMCS page to set-up invalid pin-based execution + * control (PIN_BASED_VIRTUAL_NMIS without PIN_BASED_NMI_EXITING). + */ + evmcs = hv->enlightened_vmcs_hva; + evmcs->pin_based_vm_exec_control |= PIN_BASED_VIRTUAL_NMIS; + evmcs->hv_clean_fields = 0; + + /* + * Trigger copy_enlightened_to_vmcs12() via KVM_GET_NESTED_STATE, + * copying the invalid pin_based_vm_exec_control into cached_vmcs12. + */ + union { + struct kvm_nested_state state; + char state_[16384]; + } nested_state_buf; + + memset(&nested_state_buf, 0, sizeof(nested_state_buf)); + nested_state_buf.state.size = sizeof(nested_state_buf); + vcpu_nested_state_get(vcpu, &nested_state_buf.state); + + /* + * Resume the guest. The SMI handler executes RSM, which calls + * vmx_leave_smm(). nested_vmx_check_controls() should detect + * VIRTUAL_NMIS without NMI_EXITING and cause a triple fault. + */ + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + + kvm_vm_free(vm); + return 0; +} From 6b1ca262a943a3307ee905faac0f4ff61ec3d656 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 10 Mar 2026 20:33:39 +0100 Subject: [PATCH 410/487] KVM: x86: clarify leave_smm() return value The return value of vmx_leave_smm() is unrelated from that of nested_vmx_enter_non_root_mode(). Check explicitly for success (which happens to be 0) and return 1 just like everywhere else in vmx_leave_smm(). Likewise, in svm_leave_smm() return 0/1 instead of the 0/1/-errno returned by tenter_svm_guest_mode(). Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 6 +++--- arch/x86/kvm/vmx/vmx.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4eb2c36b8ff2..e6477affac9a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4884,11 +4884,11 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) if (nested_svm_check_cached_vmcb12(vcpu) < 0) goto unmap_save; - ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false); - - if (ret) + if (enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, + vmcb12, false) != 0) goto unmap_save; + ret = 0; svm->nested.nested_run_pending = 1; unmap_save: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index bccc91a999d9..8b24e682535b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -8533,8 +8533,8 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) return 1; ret = nested_vmx_enter_non_root_mode(vcpu, false); - if (ret) - return ret; + if (ret != NVMX_VMENTRY_SUCCESS) + return 1; vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; From 33efc6346e8cf75219673fe1ca1916ab40643728 Mon Sep 17 00:00:00 2001 From: Ivan Lipski Date: Tue, 24 Feb 2026 16:28:00 -0500 Subject: [PATCH 411/487] drm/amd/display: Add missing DCCG register entries for DCN20-DCN316 Commit 4c595e75110e ("drm/amd/display: Migrate DCCG registers access from hwseq to dccg component.") moved register writes from hwseq to dccg2_*() functions but did not add the registers to the DCCG register list macros. The struct fields default to 0, so REG_WRITE() targets MMIO offset 0, causing a GPU hang on resume (seen on DCN21/DCN30 during IGT kms_cursor_crc@cursor-suspend). Add - MICROSECOND_TIME_BASE_DIV - MILLISECOND_TIME_BASE_DIV - DCCG_GATE_DISABLE_CNTL - DCCG_GATE_DISABLE_CNTL2 - DC_MEM_GLOBAL_PWR_REQ_CNTL to macros in dcn20_dccg.h, dcn301_dccg.h, dcn31_dccg.h, and dcn314_dccg.h. Fixes: 4c595e75110e ("drm/amd/display: Migrate DCCG registers access from hwseq to dccg component.") Reported-by: Rafael Passos Reviewed-by: Aurabindo Pillai Signed-off-by: Ivan Lipski Signed-off-by: Alex Hung Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit e6e2b956fc814de766d3480be7018297c41d3ce0) --- drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h | 6 +++++- drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h | 8 +++++++- drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h | 5 ++++- drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h | 5 ++++- 4 files changed, 20 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h index 3711d400773a..4c4e61bc91b5 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h @@ -38,7 +38,11 @@ DCCG_SRII(PIXEL_RATE_CNTL, OTG, 0),\ DCCG_SRII(PIXEL_RATE_CNTL, OTG, 1),\ SR(DISPCLK_FREQ_CHANGE_CNTL),\ - SR(DC_MEM_GLOBAL_PWR_REQ_CNTL) + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV),\ + SR(MILLISECOND_TIME_BASE_DIV),\ + SR(DCCG_GATE_DISABLE_CNTL),\ + SR(DCCG_GATE_DISABLE_CNTL2) #define DCCG_REG_LIST_DCN2() \ DCCG_COMMON_REG_LIST_DCN_BASE(),\ diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h index 067e49cb238e..e2381ca0be0b 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h @@ -34,7 +34,13 @@ DCCG_SRII(DTO_PARAM, DPPCLK, 1),\ DCCG_SRII(DTO_PARAM, DPPCLK, 2),\ DCCG_SRII(DTO_PARAM, DPPCLK, 3),\ - SR(REFCLK_CNTL) + SR(REFCLK_CNTL),\ + SR(DISPCLK_FREQ_CHANGE_CNTL),\ + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV),\ + SR(MILLISECOND_TIME_BASE_DIV),\ + SR(DCCG_GATE_DISABLE_CNTL),\ + SR(DCCG_GATE_DISABLE_CNTL2) #define DCCG_MASK_SH_LIST_DCN301(mask_sh) \ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h index bf659920d4cc..b5e3849ef12a 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h @@ -64,9 +64,12 @@ SR(DSCCLK1_DTO_PARAM),\ SR(DSCCLK2_DTO_PARAM),\ SR(DSCCLK_DTO_CTRL),\ + SR(DCCG_GATE_DISABLE_CNTL),\ SR(DCCG_GATE_DISABLE_CNTL2),\ SR(DCCG_GATE_DISABLE_CNTL3),\ - SR(HDMISTREAMCLK0_DTO_PARAM) + SR(HDMISTREAMCLK0_DTO_PARAM),\ + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV) #define DCCG_MASK_SH_LIST_DCN31(mask_sh) \ diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h index a609635f35db..ecbdc05f7c45 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h @@ -70,11 +70,14 @@ SR(DSCCLK2_DTO_PARAM),\ SR(DSCCLK3_DTO_PARAM),\ SR(DSCCLK_DTO_CTRL),\ + SR(DCCG_GATE_DISABLE_CNTL),\ SR(DCCG_GATE_DISABLE_CNTL2),\ SR(DCCG_GATE_DISABLE_CNTL3),\ SR(HDMISTREAMCLK0_DTO_PARAM),\ SR(OTG_PIXEL_RATE_DIV),\ - SR(DTBCLK_P_CNTL) + SR(DTBCLK_P_CNTL),\ + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV) #define DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh) \ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 0, mask_sh),\ From becbab4a5a02156000f3aaff8bb70e8fd3e0d4cf Mon Sep 17 00:00:00 2001 From: Ivan Lipski Date: Wed, 25 Feb 2026 21:48:36 -0500 Subject: [PATCH 412/487] drm/amd/display: Check for S0i3 to be done before DCCG init on DCN21 [WHY] On DCN21, dccg2_init() is called in dcn10_init_hw() before bios_golden_init(). During S0i3 resume, BIOS sets MICROSECOND_TIME_BASE_DIV to 0x00120464 as a marker. dccg2_init() overwrites this to 0x00120264, causing dcn21_s0i3_golden_init_wa() to misdetect the state and skip golden init. Eventually during the resume sequence, a flip timeout occurs. [HOW] Skip DCCG on dccg2_is_s0i3_golden_init_wa_done() on DCN21. Fixes: 4c595e75110e ("drm/amd/display: Migrate DCCG registers access from hwseq to dccg component.") Reviewed-by: Aurabindo Pillai Signed-off-by: Ivan Lipski Signed-off-by: Alex Hung Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit c61eda434336cf2c033aa35efdc9a08b31d2fdfa) --- .../amd/display/dc/dccg/dcn21/dcn21_dccg.c | 21 ++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c index 75c69348027e..c4d4eea140f3 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c @@ -96,6 +96,25 @@ static void dccg21_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppcl dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk; } +/* + * On DCN21 S0i3 resume, BIOS programs MICROSECOND_TIME_BASE_DIV to + * 0x00120464 as a marker that golden init has already been done. + * dcn21_s0i3_golden_init_wa() reads this marker later in bios_golden_init() + * to decide whether to skip golden init. + * + * dccg2_init() unconditionally overwrites MICROSECOND_TIME_BASE_DIV to + * 0x00120264, destroying the marker before it can be read. + * + * Guard the call: if the S0i3 marker is present, skip dccg2_init() so the + * WA can function correctly. bios_golden_init() will handle init in that case. + */ +static void dccg21_init(struct dccg *dccg) +{ + if (dccg2_is_s0i3_golden_init_wa_done(dccg)) + return; + + dccg2_init(dccg); +} static const struct dccg_funcs dccg21_funcs = { .update_dpp_dto = dccg21_update_dpp_dto, @@ -103,7 +122,7 @@ static const struct dccg_funcs dccg21_funcs = { .set_fifo_errdet_ovr_en = dccg2_set_fifo_errdet_ovr_en, .otg_add_pixel = dccg2_otg_add_pixel, .otg_drop_pixel = dccg2_otg_drop_pixel, - .dccg_init = dccg2_init, + .dccg_init = dccg21_init, .refclk_setup = dccg2_refclk_setup, /* Deprecated - for backward compatibility only */ .allow_clock_gating = dccg2_allow_clock_gating, .enable_memory_low_power = dccg2_enable_memory_low_power, From 2ce75a0b7e1bfddbcb9bc8aeb2e5e7fa99971acf Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Tue, 9 Dec 2025 15:13:23 -0500 Subject: [PATCH 413/487] drm/amdkfd: Unreserve bo if queue update failed Error handling path should unreserve bo then return failed. Fixes: 305cd109b761 ("drm/amdkfd: Validate user queue update") Signed-off-by: Philip Yang Reviewed-by: Alex Sierra Signed-off-by: Alex Deucher (cherry picked from commit c24afed7de9ecce341825d8ab55a43a254348b33) --- drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 8ea31699d38b..f5d2847e1cbb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -593,6 +593,7 @@ int pqm_update_queue_properties(struct process_queue_manager *pqm, p->queue_size)) { pr_debug("ring buf 0x%llx size 0x%llx not mapped on GPU\n", p->queue_address, p->queue_size); + amdgpu_bo_unreserve(vm->root.bo); return -EFAULT; } From 3646ff28780b4c52c5b5081443199e7a430110e5 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 10 Mar 2026 11:58:22 -0500 Subject: [PATCH 414/487] drm/amd: Set num IP blocks to 0 if discovery fails If discovery has failed for any reason (such as no support for a block) then there is no need to unwind all the IP blocks in fini. In this condition there can actually be failures during the unwind too. Reset num_ip_blocks to zero during failure path and skip the unnecessary cleanup path. Suggested-by: Lijo Lazar Reviewed-by: Lijo Lazar Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit fae5984296b981c8cc3acca35b701c1f332a6cd8) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +++- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 761ee5ebb4f5..d8296dfc5e8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2690,8 +2690,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) break; default: r = amdgpu_discovery_set_ip_blocks(adev); - if (r) + if (r) { + adev->num_ip_blocks = 0; return r; + } break; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 77e2133de5cf..7f19554b9ad1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -83,7 +83,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev) { struct amdgpu_device *adev = drm_to_adev(dev); - if (adev == NULL) + if (adev == NULL || !adev->num_ip_blocks) return; amdgpu_unregister_gpu_instance(adev); From dca01b0a264642929732c4db4a07e7b213304c15 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 11 Mar 2026 19:16:52 +0100 Subject: [PATCH 415/487] Documentation: kvm: fix formatting of the quirks table A recently added quirk does not fit in the left column of the table, so it all has to be reformatted and realigned. Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 210 ++++++++++++++++----------------- 1 file changed, 105 insertions(+), 105 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 19365b284395..032516783e96 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8435,123 +8435,123 @@ KVM_CHECK_EXTENSION. The valid bits in cap.args[0] are: -=================================== ============================================ - KVM_X86_QUIRK_LINT0_REENABLED By default, the reset value for the LVT - LINT0 register is 0x700 (APIC_MODE_EXTINT). - When this quirk is disabled, the reset value - is 0x10000 (APIC_LVT_MASKED). +======================================== ================================================ +KVM_X86_QUIRK_LINT0_REENABLED By default, the reset value for the LVT + LINT0 register is 0x700 (APIC_MODE_EXTINT). + When this quirk is disabled, the reset value + is 0x10000 (APIC_LVT_MASKED). - KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW on - AMD CPUs to workaround buggy guest firmware - that runs in perpetuity with CR0.CD, i.e. - with caches in "no fill" mode. +KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW on + AMD CPUs to workaround buggy guest firmware + that runs in perpetuity with CR0.CD, i.e. + with caches in "no fill" mode. - When this quirk is disabled, KVM does not - change the value of CR0.CD and CR0.NW. + When this quirk is disabled, KVM does not + change the value of CR0.CD and CR0.NW. - KVM_X86_QUIRK_LAPIC_MMIO_HOLE By default, the MMIO LAPIC interface is - available even when configured for x2APIC - mode. When this quirk is disabled, KVM - disables the MMIO LAPIC interface if the - LAPIC is in x2APIC mode. +KVM_X86_QUIRK_LAPIC_MMIO_HOLE By default, the MMIO LAPIC interface is + available even when configured for x2APIC + mode. When this quirk is disabled, KVM + disables the MMIO LAPIC interface if the + LAPIC is in x2APIC mode. - KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before - exiting to userspace for an OUT instruction - to port 0x7e. When this quirk is disabled, - KVM does not pre-increment %rip before - exiting to userspace. +KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before + exiting to userspace for an OUT instruction + to port 0x7e. When this quirk is disabled, + KVM does not pre-increment %rip before + exiting to userspace. - KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets - CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if - IA32_MISC_ENABLE[bit 18] (MWAIT) is set. - Additionally, when this quirk is disabled, - KVM clears CPUID.01H:ECX[bit 3] if - IA32_MISC_ENABLE[bit 18] is cleared. +KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets + CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if + IA32_MISC_ENABLE[bit 18] (MWAIT) is set. + Additionally, when this quirk is disabled, + KVM clears CPUID.01H:ECX[bit 3] if + IA32_MISC_ENABLE[bit 18] is cleared. - KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest - VMMCALL/VMCALL instructions to match the - vendor's hypercall instruction for the - system. When this quirk is disabled, KVM - will no longer rewrite invalid guest - hypercall instructions. Executing the - incorrect hypercall instruction will - generate a #UD within the guest. +KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest + VMMCALL/VMCALL instructions to match the + vendor's hypercall instruction for the + system. When this quirk is disabled, KVM + will no longer rewrite invalid guest + hypercall instructions. Executing the + incorrect hypercall instruction will + generate a #UD within the guest. -KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if - they are intercepted) as NOPs regardless of - whether or not MONITOR/MWAIT are supported - according to guest CPUID. When this quirk - is disabled and KVM_X86_DISABLE_EXITS_MWAIT - is not set (MONITOR/MWAIT are intercepted), - KVM will inject a #UD on MONITOR/MWAIT if - they're unsupported per guest CPUID. Note, - KVM will modify MONITOR/MWAIT support in - guest CPUID on writes to MISC_ENABLE if - KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is - disabled. +KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if + they are intercepted) as NOPs regardless of + whether or not MONITOR/MWAIT are supported + according to guest CPUID. When this quirk + is disabled and KVM_X86_DISABLE_EXITS_MWAIT + is not set (MONITOR/MWAIT are intercepted), + KVM will inject a #UD on MONITOR/MWAIT if + they're unsupported per guest CPUID. Note, + KVM will modify MONITOR/MWAIT support in + guest CPUID on writes to MISC_ENABLE if + KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is + disabled. -KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM - invalidates all SPTEs in all memslots and - address spaces when a memslot is deleted or - moved. When this quirk is disabled (or the - VM type isn't KVM_X86_DEFAULT_VM), KVM only - ensures the backing memory of the deleted - or moved memslot isn't reachable, i.e KVM - _may_ invalidate only SPTEs related to the - memslot. +KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM + invalidates all SPTEs in all memslots and + address spaces when a memslot is deleted or + moved. When this quirk is disabled (or the + VM type isn't KVM_X86_DEFAULT_VM), KVM only + ensures the backing memory of the deleted + or moved memslot isn't reachable, i.e KVM + _may_ invalidate only SPTEs related to the + memslot. -KVM_X86_QUIRK_STUFF_FEATURE_MSRS By default, at vCPU creation, KVM sets the - vCPU's MSR_IA32_PERF_CAPABILITIES (0x345), - MSR_IA32_ARCH_CAPABILITIES (0x10a), - MSR_PLATFORM_INFO (0xce), and all VMX MSRs - (0x480..0x492) to the maximal capabilities - supported by KVM. KVM also sets - MSR_IA32_UCODE_REV (0x8b) to an arbitrary - value (which is different for Intel vs. - AMD). Lastly, when guest CPUID is set (by - userspace), KVM modifies select VMX MSR - fields to force consistency between guest - CPUID and L2's effective ISA. When this - quirk is disabled, KVM zeroes the vCPU's MSR - values (with two exceptions, see below), - i.e. treats the feature MSRs like CPUID - leaves and gives userspace full control of - the vCPU model definition. This quirk does - not affect VMX MSRs CR0/CR4_FIXED1 (0x487 - and 0x489), as KVM does now allow them to - be set by userspace (KVM sets them based on - guest CPUID, for safety purposes). +KVM_X86_QUIRK_STUFF_FEATURE_MSRS By default, at vCPU creation, KVM sets the + vCPU's MSR_IA32_PERF_CAPABILITIES (0x345), + MSR_IA32_ARCH_CAPABILITIES (0x10a), + MSR_PLATFORM_INFO (0xce), and all VMX MSRs + (0x480..0x492) to the maximal capabilities + supported by KVM. KVM also sets + MSR_IA32_UCODE_REV (0x8b) to an arbitrary + value (which is different for Intel vs. + AMD). Lastly, when guest CPUID is set (by + userspace), KVM modifies select VMX MSR + fields to force consistency between guest + CPUID and L2's effective ISA. When this + quirk is disabled, KVM zeroes the vCPU's MSR + values (with two exceptions, see below), + i.e. treats the feature MSRs like CPUID + leaves and gives userspace full control of + the vCPU model definition. This quirk does + not affect VMX MSRs CR0/CR4_FIXED1 (0x487 + and 0x489), as KVM does now allow them to + be set by userspace (KVM sets them based on + guest CPUID, for safety purposes). -KVM_X86_QUIRK_IGNORE_GUEST_PAT By default, on Intel platforms, KVM ignores - guest PAT and forces the effective memory - type to WB in EPT. The quirk is not available - on Intel platforms which are incapable of - safely honoring guest PAT (i.e., without CPU - self-snoop, KVM always ignores guest PAT and - forces effective memory type to WB). It is - also ignored on AMD platforms or, on Intel, - when a VM has non-coherent DMA devices - assigned; KVM always honors guest PAT in - such case. The quirk is needed to avoid - slowdowns on certain Intel Xeon platforms - (e.g. ICX, SPR) where self-snoop feature is - supported but UC is slow enough to cause - issues with some older guests that use - UC instead of WC to map the video RAM. - Userspace can disable the quirk to honor - guest PAT if it knows that there is no such - guest software, for example if it does not - expose a bochs graphics device (which is - known to have had a buggy driver). +KVM_X86_QUIRK_IGNORE_GUEST_PAT By default, on Intel platforms, KVM ignores + guest PAT and forces the effective memory + type to WB in EPT. The quirk is not available + on Intel platforms which are incapable of + safely honoring guest PAT (i.e., without CPU + self-snoop, KVM always ignores guest PAT and + forces effective memory type to WB). It is + also ignored on AMD platforms or, on Intel, + when a VM has non-coherent DMA devices + assigned; KVM always honors guest PAT in + such case. The quirk is needed to avoid + slowdowns on certain Intel Xeon platforms + (e.g. ICX, SPR) where self-snoop feature is + supported but UC is slow enough to cause + issues with some older guests that use + UC instead of WC to map the video RAM. + Userspace can disable the quirk to honor + guest PAT if it knows that there is no such + guest software, for example if it does not + expose a bochs graphics device (which is + known to have had a buggy driver). KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM By default, KVM relaxes the consistency - check for GUEST_IA32_DEBUGCTL in vmcs12 - to allow FREEZE_IN_SMM to be set. When - this quirk is disabled, KVM requires this - bit to be cleared. Note that the vmcs02 - bit is still completely controlled by the - host, regardless of the quirk setting. -=================================== ============================================ + check for GUEST_IA32_DEBUGCTL in vmcs12 + to allow FREEZE_IN_SMM to be set. When + this quirk is disabled, KVM requires this + bit to be cleared. Note that the vmcs02 + bit is still completely controlled by the + host, regardless of the quirk setting. +======================================== ================================================ 7.32 KVM_CAP_MAX_VCPU_ID ------------------------ From f879365c5bb210ed0d0b0aae1a0202d0c0b4b9d0 Mon Sep 17 00:00:00 2001 From: CL Wang Date: Tue, 3 Mar 2026 10:47:37 +0800 Subject: [PATCH 416/487] spi: atcspi200: Handle invalid buswidth and fix compiler warning The kernel test robot reported a compile-time error regarding the FIELD_PREP() value being too large for the TRANS_DUAL_QUAD field: error: FIELD_PREP: value too large for the field note: in expansion of macro 'TRANS_DUAL_QUAD' tc |= TRANS_DUAL_QUAD(ffs(op->data.buswidth) - 1); This occurs because TRANS_DUAL_QUAD is defined as a 2-bit field, and GCC's static analysis cannot deduce that `ffs(op->data.buswidth) - 1` will strictly fall within the 0~3 range. Although the SPI framework guarantees that `op->data.buswidth` is valid at runtime (e.g., 1, 2, 4, 8), an explicit bounds check is necessary to satisfy the compiler. To resolve the build warning, introduce a safe fallback mechanism. If an unexpected buswidth is encountered, the driver will trigger a WARN_ON_ONCE to leave a trace and fall back to width_code = 0 (standard 1-bit SPI mode). This approach guarantees predictable hardware behavior. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202602140738.P7ZozxzI-lkp@intel.com/ Suggested-by: Pei Xiao Signed-off-by: CL Wang Link: https://patch.msgid.link/20260303024737.1791196-1-cl634@andestech.com Signed-off-by: Mark Brown --- drivers/spi/spi-atcspi200.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-atcspi200.c b/drivers/spi/spi-atcspi200.c index fef6954d27e1..2665f31a49ce 100644 --- a/drivers/spi/spi-atcspi200.c +++ b/drivers/spi/spi-atcspi200.c @@ -195,7 +195,15 @@ static void atcspi_set_trans_ctl(struct atcspi_dev *spi, if (op->addr.buswidth > 1) tc |= TRANS_ADDR_FMT; if (op->data.nbytes) { - tc |= TRANS_DUAL_QUAD(ffs(op->data.buswidth) - 1); + unsigned int width_code; + + width_code = ffs(op->data.buswidth) - 1; + if (unlikely(width_code > 3)) { + WARN_ON_ONCE(1); + width_code = 0; + } + tc |= TRANS_DUAL_QUAD(width_code); + if (op->data.dir == SPI_MEM_DATA_IN) { if (op->dummy.nbytes) tc |= TRANS_MODE_DMY_READ | From 30c64fb9839949f085c8eb55b979cbd8a4c51f00 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Tue, 10 Mar 2026 12:43:27 +0800 Subject: [PATCH 417/487] ASoC: amd: acp-mach-common: Add missing error check for clock acquisition The acp_card_rt5682_init() and acp_card_rt5682s_init() functions did not check the return values of clk_get(). This could lead to a kernel crash when the invalid pointers are later dereferenced by clock core functions. Fix this by: 1. Changing clk_get() to the device-managed devm_clk_get(). 2. Adding IS_ERR() checks immediately after each clock acquisition. Fixes: 8b7256266848 ("ASoC: amd: acp: Add support for RT5682-VS codec") Fixes: d4c750f2c7d4 ("ASoC: amd: acp: Add generic machine driver support for ACP cards") Signed-off-by: Chen Ni Link: https://patch.msgid.link/20260310044327.2582018-1-nichen@iscas.ac.cn Signed-off-by: Mark Brown --- sound/soc/amd/acp/acp-mach-common.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c index 4d99472c75ba..09f6c9a2c041 100644 --- a/sound/soc/amd/acp/acp-mach-common.c +++ b/sound/soc/amd/acp/acp-mach-common.c @@ -127,8 +127,13 @@ static int acp_card_rt5682_init(struct snd_soc_pcm_runtime *rtd) if (drvdata->hs_codec_id != RT5682) return -EINVAL; - drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk"); - drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk"); + drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk"); + if (IS_ERR(drvdata->wclk)) + return PTR_ERR(drvdata->wclk); + + drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk"); + if (IS_ERR(drvdata->bclk)) + return PTR_ERR(drvdata->bclk); ret = snd_soc_dapm_new_controls(dapm, rt5682_widgets, ARRAY_SIZE(rt5682_widgets)); @@ -370,8 +375,13 @@ static int acp_card_rt5682s_init(struct snd_soc_pcm_runtime *rtd) return -EINVAL; if (!drvdata->soc_mclk) { - drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk"); - drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk"); + drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk"); + if (IS_ERR(drvdata->wclk)) + return PTR_ERR(drvdata->wclk); + + drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk"); + if (IS_ERR(drvdata->bclk)) + return PTR_ERR(drvdata->bclk); } ret = snd_soc_dapm_new_controls(dapm, rt5682s_widgets, From 96189080265e6bb5dde3a4afbaf947af493e3f82 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 Mar 2026 14:21:37 -0600 Subject: [PATCH 418/487] io_uring: ensure ctx->rings is stable for task work flags manipulation If DEFER_TASKRUN | SETUP_TASKRUN is used and task work is added while the ring is being resized, it's possible for the OR'ing of IORING_SQ_TASKRUN to happen in the small window of swapping into the new rings and the old rings being freed. Prevent this by adding a 2nd ->rings pointer, ->rings_rcu, which is protected by RCU. The task work flags manipulation is inside RCU already, and if the resize ring freeing is done post an RCU synchronize, then there's no need to add locking to the fast path of task work additions. Note: this is only done for DEFER_TASKRUN, as that's the only setup mode that supports ring resizing. If this ever changes, then they too need to use the io_ctx_mark_taskrun() helper. Link: https://lore.kernel.org/io-uring/20260309062759.482210-1-naup96721@gmail.com/ Cc: stable@vger.kernel.org Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS") Reported-by: Hao-Yu Yang Suggested-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + io_uring/io_uring.c | 2 ++ io_uring/register.c | 11 +++++++++++ io_uring/tw.c | 22 ++++++++++++++++++++-- 4 files changed, 34 insertions(+), 2 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3e4a82a6f817..dd1420bfcb73 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -388,6 +388,7 @@ struct io_ring_ctx { * regularly bounce b/w CPUs. */ struct { + struct io_rings __rcu *rings_rcu; struct llist_head work_llist; struct llist_head retry_llist; unsigned long check_cq; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ccab8562d273..20fdc442e014 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2066,6 +2066,7 @@ static void io_rings_free(struct io_ring_ctx *ctx) io_free_region(ctx->user, &ctx->sq_region); io_free_region(ctx->user, &ctx->ring_region); ctx->rings = NULL; + RCU_INIT_POINTER(ctx->rings_rcu, NULL); ctx->sq_sqes = NULL; } @@ -2703,6 +2704,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, if (ret) return ret; ctx->rings = rings = io_region_get_ptr(&ctx->ring_region); + rcu_assign_pointer(ctx->rings_rcu, rings); if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) ctx->sq_array = (u32 *)((char *)rings + rl->sq_array_offset); diff --git a/io_uring/register.c b/io_uring/register.c index a839b22fd392..5f3eb018fb32 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -633,7 +633,15 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) ctx->sq_entries = p->sq_entries; ctx->cq_entries = p->cq_entries; + /* + * Just mark any flag we may have missed and that the application + * should act on unconditionally. Worst case it'll be an extra + * syscall. + */ + atomic_or(IORING_SQ_TASKRUN | IORING_SQ_NEED_WAKEUP, &n.rings->sq_flags); ctx->rings = n.rings; + rcu_assign_pointer(ctx->rings_rcu, n.rings); + ctx->sq_sqes = n.sq_sqes; swap_old(ctx, o, n, ring_region); swap_old(ctx, o, n, sq_region); @@ -642,6 +650,9 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) out: spin_unlock(&ctx->completion_lock); mutex_unlock(&ctx->mmap_lock); + /* Wait for concurrent io_ctx_mark_taskrun() */ + if (to_free == &o) + synchronize_rcu_expedited(); io_register_free_rings(ctx, to_free); if (ctx->sq_data) diff --git a/io_uring/tw.c b/io_uring/tw.c index 1ee2b8ab07c8..2f2b4ac4b126 100644 --- a/io_uring/tw.c +++ b/io_uring/tw.c @@ -152,6 +152,21 @@ void tctx_task_work(struct callback_head *cb) WARN_ON_ONCE(ret); } +/* + * Sets IORING_SQ_TASKRUN in the sq_flags shared with userspace, using the + * RCU protected rings pointer to be safe against concurrent ring resizing. + */ +static void io_ctx_mark_taskrun(struct io_ring_ctx *ctx) +{ + lockdep_assert_in_rcu_read_lock(); + + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) { + struct io_rings *rings = rcu_dereference(ctx->rings_rcu); + + atomic_or(IORING_SQ_TASKRUN, &rings->sq_flags); + } +} + void io_req_local_work_add(struct io_kiocb *req, unsigned flags) { struct io_ring_ctx *ctx = req->ctx; @@ -206,8 +221,7 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags) */ if (!head) { - if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) - atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + io_ctx_mark_taskrun(ctx); if (ctx->has_evfd) io_eventfd_signal(ctx, false); } @@ -231,6 +245,10 @@ void io_req_normal_work_add(struct io_kiocb *req) if (!llist_add(&req->io_task_work.node, &tctx->task_list)) return; + /* + * Doesn't need to use ->rings_rcu, as resizing isn't supported for + * !DEFER_TASKRUN. + */ if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); From 177c69432161f6e4bab07ccacf8a1748a6898a6b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 Mar 2026 14:35:49 -0600 Subject: [PATCH 419/487] io_uring/eventfd: use ctx->rings_rcu for flags checking Similarly to what commit e78f7b70e837 did for local task work additions, use ->rings_rcu under RCU rather than dereference ->rings directly. See that commit for more details. Cc: stable@vger.kernel.org Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS") Signed-off-by: Jens Axboe --- io_uring/eventfd.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index 78f8ab7db104..ab789e1ebe91 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -76,11 +76,15 @@ void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event) { bool skip = false; struct io_ev_fd *ev_fd; - - if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) - return; + struct io_rings *rings; guard(rcu)(); + + rings = rcu_dereference(ctx->rings_rcu); + if (!rings) + return; + if (READ_ONCE(rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) + return; ev_fd = rcu_dereference(ctx->io_ev_fd); /* * Check again if ev_fd exists in case an io_eventfd_unregister call From 6f02c6b196036dbb6defb4647d8707d29b7fe95b Mon Sep 17 00:00:00 2001 From: Tom Ryan Date: Mon, 9 Mar 2026 22:20:02 -0700 Subject: [PATCH 420/487] io_uring: fix physical SQE bounds check for SQE_MIXED 128-byte ops When IORING_SETUP_SQE_MIXED is used without IORING_SETUP_NO_SQARRAY, the boundary check for 128-byte SQE operations in io_init_req() validated the logical SQ head position rather than the physical SQE index. The existing check: !(ctx->cached_sq_head & (ctx->sq_entries - 1)) ensures the logical position isn't at the end of the ring, which is correct for NO_SQARRAY rings where physical == logical. However, when sq_array is present, an unprivileged user can remap any logical position to an arbitrary physical index via sq_array. Setting sq_array[N] = sq_entries - 1 places a 128-byte operation at the last physical SQE slot, causing the 128-byte memcpy in io_uring_cmd_sqe_copy() to read 64 bytes past the end of the SQE array. Replace the cached_sq_head alignment check with a direct validation of the physical SQE index, which correctly handles both sq_array and NO_SQARRAY cases. Fixes: 1cba30bf9fdd ("io_uring: add support for IORING_SETUP_SQE_MIXED") Signed-off-by: Tom Ryan Link: https://patch.msgid.link/20260310052003.72871-1-ryan36005@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 20fdc442e014..20ec8fdafcae 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1745,7 +1745,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, * well as 2 contiguous entries. */ if (!(ctx->flags & IORING_SETUP_SQE_MIXED) || *left < 2 || - !(ctx->cached_sq_head & (ctx->sq_entries - 1))) + (unsigned)(sqe - ctx->sq_sqes) >= ctx->sq_entries - 1) return io_init_fail_req(req, -EINVAL); /* * A 128b operation on a mixed SQ uses two entries, so we have From 35b16a7a2c4fc458304447128b86514ce9f70f3c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 10 Mar 2026 13:59:51 -0400 Subject: [PATCH 421/487] perf synthetic-events: Fix stale build ID in module MMAP2 records perf_event__synthesize_modules() allocates a single union perf_event and reuses it across every kernel module callback. After the first module is processed, perf_record_mmap2__read_build_id() sets PERF_RECORD_MISC_MMAP_BUILD_ID in header.misc and writes that module's build ID into the event. On subsequent iterations the callback overwrites start, len, pid, and filename for the next module but never clears the stale build ID fields or the MMAP_BUILD_ID flag. When perf_record_mmap2__read_build_id() runs for the second module it sees the flag, reads the stale build ID into a dso_id, and __dso__improve_id() permanently poisons the DSO with the wrong build ID. Every module after the first therefore receives the first module's build ID in its MMAP2 record. On a system with the sunrpc and nfsd modules loaded, this causes perf script and perf report to show [unknown] for all module symbols. The latent bug has existed since commit d9f2ecbc5e47fca7 ("perf dso: Move build_id to dso_id") introduced the PERF_RECORD_MISC_MMAP_BUILD_ID check in perf_record_mmap2__read_build_id(). Commit 53b00ff358dc75b1 ("perf record: Make --buildid-mmap the default") then exposed it to all users by making the MMAP2-with-build-ID path the default. Both commits were merged in the same series. Clear the MMAP_BUILD_ID flag and zero the build_id union before each call to perf_record_mmap2__read_build_id() so that every module starts with a clean slate. Fixes: d9f2ecbc5e47fca7 ("perf dso: Move build_id to dso_id") Reviewed-by: Ian Rogers Signed-off-by: Chuck Lever Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/synthetic-events.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index ef79433ebc3a..ddf1cbda1902 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -703,6 +703,11 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data) memcpy(event->mmap2.filename, dso__long_name(dso), dso__long_name_len(dso) + 1); + /* Clear stale build ID from previous module iteration */ + event->mmap2.header.misc &= ~PERF_RECORD_MISC_MMAP_BUILD_ID; + memset(event->mmap2.build_id, 0, sizeof(event->mmap2.build_id)); + event->mmap2.build_id_size = 0; + perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false); } else { size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64)); From 4167b8914463132654e01e16259847d097f8a7f7 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:38 +0200 Subject: [PATCH 422/487] i3c: mipi-i3c-hci: Use ETIMEDOUT instead of ETIME for timeout errors The MIPI I3C HCI driver currently returns -ETIME for various timeout conditions, while other I3C master drivers consistently use -ETIMEDOUT for the same class of errors. Align the HCI driver with the rest of the subsystem by replacing all uses of -ETIME with -ETIMEDOUT. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-2-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/cmd_v1.c | 2 +- drivers/i3c/master/mipi-i3c-hci/cmd_v2.c | 2 +- drivers/i3c/master/mipi-i3c-hci/core.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c index fe260461e7e6..831a261f6c56 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c +++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c @@ -334,7 +334,7 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci) hci->io->queue_xfer(hci, xfer, 1); if (!wait_for_completion_timeout(&done, HZ) && hci->io->dequeue_xfer(hci, xfer, 1)) { - ret = -ETIME; + ret = -ETIMEDOUT; break; } if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER || diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c index 3729e6419581..054beee36da5 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c +++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c @@ -275,7 +275,7 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci) hci->io->queue_xfer(hci, xfer, 2); if (!wait_for_completion_timeout(&done, HZ) && hci->io->dequeue_xfer(hci, xfer, 2)) { - ret = -ETIME; + ret = -ETIMEDOUT; break; } if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) { diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index 5879bba78164..dbe93df0c70e 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -261,7 +261,7 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m, goto out; if (!wait_for_completion_timeout(&done, HZ) && hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIME; + ret = -ETIMEDOUT; goto out; } for (i = prefixed; i < nxfers; i++) { @@ -340,7 +340,7 @@ static int i3c_hci_i3c_xfers(struct i3c_dev_desc *dev, goto out; if (!wait_for_completion_timeout(&done, HZ) && hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIME; + ret = -ETIMEDOUT; goto out; } for (i = 0; i < nxfers; i++) { @@ -388,7 +388,7 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev, goto out; if (!wait_for_completion_timeout(&done, m->i2c.timeout) && hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIME; + ret = -ETIMEDOUT; goto out; } for (i = 0; i < nxfers; i++) { From fa9586bd77ada1e3861c7bef65f6bb9dcf8d9481 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:39 +0200 Subject: [PATCH 423/487] i3c: mipi-i3c-hci: Fix Hot-Join NACK The MIPI I3C HCI host controller driver does not implement Hot-Join handling, yet Hot-Join response control defaults to allowing devices to Hot-Join the bus. Configure HC_CONTROL_HOT_JOIN_CTRL to NACK all Hot-Join attempts. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-3-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index dbe93df0c70e..4877a321edf9 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -152,7 +152,8 @@ static int i3c_hci_bus_init(struct i3c_master_controller *m) if (hci->quirks & HCI_QUIRK_RESP_BUF_THLD) amd_set_resp_buf_thld(hci); - reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE); + /* Enable bus with Hot-Join disabled */ + reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL); dev_dbg(&hci->master.dev, "HC_CONTROL = %#x", reg_read(HC_CONTROL)); return 0; @@ -764,7 +765,8 @@ static int i3c_hci_runtime_resume(struct device *dev) hci->io->resume(hci); - reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE); + /* Enable bus with Hot-Join disabled */ + reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL); return 0; } From f3bcbfe1b8b0b836b772927f75f8cb6e759eb00a Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:40 +0200 Subject: [PATCH 424/487] i3c: mipi-i3c-hci: Factor out DMA mapping from queuing path Prepare for fixing a race in the DMA ring enqueue path when handling parallel transfers. Move all DMA mapping out of hci_dma_queue_xfer() and into a new helper that performs the mapping up front. This refactoring allows the upcoming fix to extend the spinlock coverage around the enqueue operation without performing DMA mapping under the spinlock. No functional change is intended in this patch. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-4-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/dma.c | 49 ++++++++++++++++++--------- 1 file changed, 33 insertions(+), 16 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index b903a2da1fd1..ba451f026386 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -439,6 +439,33 @@ static void hci_dma_unmap_xfer(struct i3c_hci *hci, } } +static struct i3c_dma *hci_dma_map_xfer(struct device *dev, struct hci_xfer *xfer) +{ + enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + bool need_bounce = device_iommu_mapped(dev) && xfer->rnw && (xfer->data_len & 3); + + return i3c_master_dma_map_single(dev, xfer->data, xfer->data_len, need_bounce, dir); +} + +static int hci_dma_map_xfer_list(struct i3c_hci *hci, struct device *dev, + struct hci_xfer *xfer_list, int n) +{ + for (int i = 0; i < n; i++) { + struct hci_xfer *xfer = xfer_list + i; + + if (!xfer->data) + continue; + + xfer->dma = hci_dma_map_xfer(dev, xfer); + if (!xfer->dma) { + hci_dma_unmap_xfer(hci, xfer_list, i); + return -ENOMEM; + } + } + + return 0; +} + static int hci_dma_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer_list, int n) { @@ -446,6 +473,11 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, struct hci_rh_data *rh; unsigned int i, ring, enqueue_ptr; u32 op1_val, op2_val; + int ret; + + ret = hci_dma_map_xfer_list(hci, rings->sysdev, xfer_list, n); + if (ret) + return ret; /* For now we only use ring 0 */ ring = 0; @@ -456,9 +488,6 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, for (i = 0; i < n; i++) { struct hci_xfer *xfer = xfer_list + i; u32 *ring_data = rh->xfer + rh->xfer_struct_sz * enqueue_ptr; - enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE : - DMA_TO_DEVICE; - bool need_bounce; /* store cmd descriptor */ *ring_data++ = xfer->cmd_desc[0]; @@ -477,18 +506,6 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, /* 2nd and 3rd words of Data Buffer Descriptor Structure */ if (xfer->data) { - need_bounce = device_iommu_mapped(rings->sysdev) && - xfer->rnw && - xfer->data_len != ALIGN(xfer->data_len, 4); - xfer->dma = i3c_master_dma_map_single(rings->sysdev, - xfer->data, - xfer->data_len, - need_bounce, - dir); - if (!xfer->dma) { - hci_dma_unmap_xfer(hci, xfer_list, i); - return -ENOMEM; - } *ring_data++ = lower_32_bits(xfer->dma->addr); *ring_data++ = upper_32_bits(xfer->dma->addr); } else { @@ -511,7 +528,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, op2_val = rh_reg_read(RING_OPERATION2); if (enqueue_ptr == FIELD_GET(RING_OP2_CR_DEQ_PTR, op2_val)) { /* the ring is full */ - hci_dma_unmap_xfer(hci, xfer_list, i + 1); + hci_dma_unmap_xfer(hci, xfer_list, n); return -EBUSY; } } From fa12bb903bc3ed1826e355d267fe134bde95e23c Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:41 +0200 Subject: [PATCH 425/487] i3c: mipi-i3c-hci: Consolidate spinlocks The MIPI I3C HCI driver currently uses separate spinlocks for different contexts (PIO vs. DMA rings). This split is unnecessary and complicates upcoming fixes. The driver does not support concurrent PIO and DMA operation, and it only supports a single DMA ring, so a single lock is sufficient for all paths. Introduce a unified spinlock in struct i3c_hci, switch both PIO and DMA code to use it, and remove the per-context locks. No functional change is intended in this patch. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-5-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 2 ++ drivers/i3c/master/mipi-i3c-hci/dma.c | 14 ++++++-------- drivers/i3c/master/mipi-i3c-hci/hci.h | 1 + drivers/i3c/master/mipi-i3c-hci/pio.c | 16 +++++++--------- 4 files changed, 16 insertions(+), 17 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index 4877a321edf9..faf5eae2409f 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -926,6 +926,8 @@ static int i3c_hci_probe(struct platform_device *pdev) if (!hci) return -ENOMEM; + spin_lock_init(&hci->lock); + /* * Multi-bus instances share the same MMIO address range, but not * necessarily in separate contiguous sub-ranges. To avoid overlapping diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index ba451f026386..2442cedd5c2a 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -131,7 +131,6 @@ struct hci_rh_data { unsigned int xfer_struct_sz, resp_struct_sz, ibi_status_sz, ibi_chunk_sz; unsigned int done_ptr, ibi_chunk_ptr; struct hci_xfer **src_xfers; - spinlock_t lock; struct completion op_done; }; @@ -344,7 +343,6 @@ static int hci_dma_init(struct i3c_hci *hci) goto err_out; rh = &rings->headers[i]; rh->regs = hci->base_regs + offset; - spin_lock_init(&rh->lock); init_completion(&rh->op_done); rh->xfer_entries = XFER_RING_ENTRIES; @@ -534,12 +532,12 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, } /* take care to update the hardware enqueue pointer atomically */ - spin_lock_irq(&rh->lock); + spin_lock_irq(&hci->lock); op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_CR_ENQ_PTR; op1_val |= FIELD_PREP(RING_OP1_CR_ENQ_PTR, enqueue_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock_irq(&rh->lock); + spin_unlock_irq(&hci->lock); return 0; } @@ -637,12 +635,12 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) } /* take care to update the software dequeue pointer atomically */ - spin_lock(&rh->lock); + spin_lock(&hci->lock); op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_CR_SW_DEQ_PTR; op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock(&rh->lock); + spin_unlock(&hci->lock); } static int hci_dma_request_ibi(struct i3c_hci *hci, struct i3c_dev_desc *dev, @@ -823,12 +821,12 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh) done: /* take care to update the ibi dequeue pointer atomically */ - spin_lock(&rh->lock); + spin_lock(&hci->lock); op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_IBI_DEQ_PTR; op1_val |= FIELD_PREP(RING_OP1_IBI_DEQ_PTR, deq_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock(&rh->lock); + spin_unlock(&hci->lock); /* update the chunk pointer */ rh->ibi_chunk_ptr += ibi_chunks; diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h index 337b7ab1cb06..f1dd502c071f 100644 --- a/drivers/i3c/master/mipi-i3c-hci/hci.h +++ b/drivers/i3c/master/mipi-i3c-hci/hci.h @@ -50,6 +50,7 @@ struct i3c_hci { const struct hci_io_ops *io; void *io_data; const struct hci_cmd_ops *cmd; + spinlock_t lock; atomic_t next_cmd_tid; bool irq_inactive; u32 caps; diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c index f8825ac81408..02866c2237fa 100644 --- a/drivers/i3c/master/mipi-i3c-hci/pio.c +++ b/drivers/i3c/master/mipi-i3c-hci/pio.c @@ -123,7 +123,6 @@ struct hci_pio_ibi_data { }; struct hci_pio_data { - spinlock_t lock; struct hci_xfer *curr_xfer, *xfer_queue; struct hci_xfer *curr_rx, *rx_queue; struct hci_xfer *curr_tx, *tx_queue; @@ -212,7 +211,6 @@ static int hci_pio_init(struct i3c_hci *hci) return -ENOMEM; hci->io_data = pio; - spin_lock_init(&pio->lock); __hci_pio_init(hci, &size_val); @@ -631,7 +629,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n) xfer[i].data_left = xfer[i].data_len; } - spin_lock_irq(&pio->lock); + spin_lock_irq(&hci->lock); prev_queue_tail = pio->xfer_queue; pio->xfer_queue = &xfer[n - 1]; if (pio->curr_xfer) { @@ -645,7 +643,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n) pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE)); } - spin_unlock_irq(&pio->lock); + spin_unlock_irq(&hci->lock); return 0; } @@ -716,14 +714,14 @@ static bool hci_pio_dequeue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int struct hci_pio_data *pio = hci->io_data; int ret; - spin_lock_irq(&pio->lock); + spin_lock_irq(&hci->lock); dev_dbg(&hci->master.dev, "n=%d status=%#x/%#x", n, pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE)); dev_dbg(&hci->master.dev, "main_status = %#x/%#x", readl(hci->base_regs + 0x20), readl(hci->base_regs + 0x28)); ret = hci_pio_dequeue_xfer_common(hci, pio, xfer, n); - spin_unlock_irq(&pio->lock); + spin_unlock_irq(&hci->lock); return ret; } @@ -1016,13 +1014,13 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci) struct hci_pio_data *pio = hci->io_data; u32 status; - spin_lock(&pio->lock); + spin_lock(&hci->lock); status = pio_reg_read(INTR_STATUS); dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x", status, pio->enabled_irqs); status &= pio->enabled_irqs | STAT_LATENCY_WARNINGS; if (!status) { - spin_unlock(&pio->lock); + spin_unlock(&hci->lock); return false; } @@ -1058,7 +1056,7 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci) pio_reg_write(INTR_SIGNAL_ENABLE, pio->enabled_irqs); dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x", pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE)); - spin_unlock(&pio->lock); + spin_unlock(&hci->lock); return true; } From 4decbbc8a8cf0a69ab011d7c2c88ed3cd0a00ddd Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:42 +0200 Subject: [PATCH 426/487] i3c: mipi-i3c-hci: Fix race in DMA ring enqueue for parallel xfers The I3C subsystem allows multiple transfers to be queued concurrently. However, the MIPI I3C HCI driver's DMA enqueue path, hci_dma_queue_xfer(), lacks sufficient serialization. In particular, the allocation of the enqueue_ptr and its subsequent update in the RING_OPERATION1 register, must be done atomically. Otherwise, for example, it would be possible for 2 transfers to be allocated the same enqueue_ptr. Extend the use of the existing spinlock for that purpose. Keep a count of the number of xfers enqueued so that it is easy to determine if the ring has enough space. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-6-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/dma.c | 32 +++++++++++++-------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index 2442cedd5c2a..74b255ad6d0f 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -129,7 +129,7 @@ struct hci_rh_data { dma_addr_t xfer_dma, resp_dma, ibi_status_dma, ibi_data_dma; unsigned int xfer_entries, ibi_status_entries, ibi_chunks_total; unsigned int xfer_struct_sz, resp_struct_sz, ibi_status_sz, ibi_chunk_sz; - unsigned int done_ptr, ibi_chunk_ptr; + unsigned int done_ptr, ibi_chunk_ptr, xfer_space; struct hci_xfer **src_xfers; struct completion op_done; }; @@ -260,6 +260,7 @@ static void hci_dma_init_rh(struct i3c_hci *hci, struct hci_rh_data *rh, int i) rh->done_ptr = 0; rh->ibi_chunk_ptr = 0; + rh->xfer_space = rh->xfer_entries; } static void hci_dma_init_rings(struct i3c_hci *hci) @@ -470,7 +471,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, struct hci_rings_data *rings = hci->io_data; struct hci_rh_data *rh; unsigned int i, ring, enqueue_ptr; - u32 op1_val, op2_val; + u32 op1_val; int ret; ret = hci_dma_map_xfer_list(hci, rings->sysdev, xfer_list, n); @@ -481,6 +482,14 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, ring = 0; rh = &rings->headers[ring]; + spin_lock_irq(&hci->lock); + + if (n > rh->xfer_space) { + spin_unlock_irq(&hci->lock); + hci_dma_unmap_xfer(hci, xfer_list, n); + return -EBUSY; + } + op1_val = rh_reg_read(RING_OPERATION1); enqueue_ptr = FIELD_GET(RING_OP1_CR_ENQ_PTR, op1_val); for (i = 0; i < n; i++) { @@ -518,22 +527,10 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, xfer->ring_entry = enqueue_ptr; enqueue_ptr = (enqueue_ptr + 1) % rh->xfer_entries; - - /* - * We may update the hardware view of the enqueue pointer - * only if we didn't reach its dequeue pointer. - */ - op2_val = rh_reg_read(RING_OPERATION2); - if (enqueue_ptr == FIELD_GET(RING_OP2_CR_DEQ_PTR, op2_val)) { - /* the ring is full */ - hci_dma_unmap_xfer(hci, xfer_list, n); - return -EBUSY; - } } - /* take care to update the hardware enqueue pointer atomically */ - spin_lock_irq(&hci->lock); - op1_val = rh_reg_read(RING_OPERATION1); + rh->xfer_space -= n; + op1_val &= ~RING_OP1_CR_ENQ_PTR; op1_val |= FIELD_PREP(RING_OP1_CR_ENQ_PTR, enqueue_ptr); rh_reg_write(RING_OPERATION1, op1_val); @@ -601,6 +598,7 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) { u32 op1_val, op2_val, resp, *ring_resp; unsigned int tid, done_ptr = rh->done_ptr; + unsigned int done_cnt = 0; struct hci_xfer *xfer; for (;;) { @@ -632,10 +630,12 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) done_ptr = (done_ptr + 1) % rh->xfer_entries; rh->done_ptr = done_ptr; + done_cnt += 1; } /* take care to update the software dequeue pointer atomically */ spin_lock(&hci->lock); + rh->xfer_space += done_cnt; op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_CR_SW_DEQ_PTR; op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr); From 1dca8aee80eea76d2aae21265de5dd64f6ba0f09 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:43 +0200 Subject: [PATCH 427/487] i3c: mipi-i3c-hci: Fix race in DMA ring dequeue The HCI DMA dequeue path (hci_dma_dequeue_xfer()) may be invoked for multiple transfers that timeout around the same time. However, the function is not serialized and can race with itself. When a timeout occurs, hci_dma_dequeue_xfer() stops the ring, processes incomplete transfers, and then restarts the ring. If another timeout triggers a parallel call into the same function, the two instances may interfere with each other - stopping or restarting the ring at unexpected times. Add a mutex so that hci_dma_dequeue_xfer() is serialized with respect to itself. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-7-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 1 + drivers/i3c/master/mipi-i3c-hci/dma.c | 2 ++ drivers/i3c/master/mipi-i3c-hci/hci.h | 1 + 3 files changed, 4 insertions(+) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index faf5eae2409f..061e84a5c412 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -927,6 +927,7 @@ static int i3c_hci_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&hci->lock); + mutex_init(&hci->control_mutex); /* * Multi-bus instances share the same MMIO address range, but not diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index 74b255ad6d0f..f7d411e5e11f 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -547,6 +547,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, unsigned int i; bool did_unqueue = false; + guard(mutex)(&hci->control_mutex); + /* stop the ring */ rh_reg_write(RING_CONTROL, RING_CTRL_ABORT); if (wait_for_completion_timeout(&rh->op_done, HZ) == 0) { diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h index f1dd502c071f..9c63d80f7fc4 100644 --- a/drivers/i3c/master/mipi-i3c-hci/hci.h +++ b/drivers/i3c/master/mipi-i3c-hci/hci.h @@ -51,6 +51,7 @@ struct i3c_hci { void *io_data; const struct hci_cmd_ops *cmd; spinlock_t lock; + struct mutex control_mutex; atomic_t next_cmd_tid; bool irq_inactive; u32 caps; From f0b5159637ca0b8feaaa95de0f5ea38f1ba26729 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:44 +0200 Subject: [PATCH 428/487] i3c: mipi-i3c-hci: Fix race between DMA ring dequeue and interrupt handler The DMA ring bookkeeping in the MIPI I3C HCI driver is updated from two contexts: the DMA ring dequeue path (hci_dma_dequeue_xfer()) and the interrupt handler (hci_dma_xfer_done()). Both modify the ring's in-flight transfer state - specifically rh->src_xfers[] and xfer->ring_entry - but without any serialization. This allows the two paths to race, potentially leading to inconsistent ring state. Serialize access to the shared ring state by extending the existing spinlock to cover the DMA dequeue path and the entire interrupt handler. Since the core IRQ handler now holds this lock, remove the per-function locking from the PIO and DMA sub-handlers. Additionally, clear the completed entry in rh->src_xfers[] in hci_dma_xfer_done() so it cannot be matched or completed again. Finally, place the ring restart sequence under the same lock in hci_dma_dequeue_xfer() to avoid concurrent enqueue or completion operations while the ring state is being modified. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-8-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 2 ++ drivers/i3c/master/mipi-i3c-hci/dma.c | 11 +++++------ drivers/i3c/master/mipi-i3c-hci/pio.c | 6 +----- 3 files changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index 061e84a5c412..adf35b7fa498 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -567,6 +567,8 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id) irqreturn_t result = IRQ_NONE; u32 val; + guard(spinlock)(&hci->lock); + /* * The IRQ can be shared, so the handler may be called when the IRQ is * due to a different device. That could happen when runtime suspended, diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index f7d411e5e11f..d7840ff69e59 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -560,6 +560,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, WARN_ON(1); } + spin_lock_irq(&hci->lock); + for (i = 0; i < n; i++) { struct hci_xfer *xfer = xfer_list + i; int idx = xfer->ring_entry; @@ -593,6 +595,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, /* restart the ring */ rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE); + spin_unlock_irq(&hci->lock); + return did_unqueue; } @@ -618,6 +622,7 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) dev_dbg(&hci->master.dev, "orphaned ring entry"); } else { hci_dma_unmap_xfer(hci, xfer, 1); + rh->src_xfers[done_ptr] = NULL; xfer->ring_entry = -1; xfer->response = resp; if (tid != xfer->cmd_tid) { @@ -635,14 +640,11 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) done_cnt += 1; } - /* take care to update the software dequeue pointer atomically */ - spin_lock(&hci->lock); rh->xfer_space += done_cnt; op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_CR_SW_DEQ_PTR; op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock(&hci->lock); } static int hci_dma_request_ibi(struct i3c_hci *hci, struct i3c_dev_desc *dev, @@ -822,13 +824,10 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh) i3c_master_queue_ibi(dev, slot); done: - /* take care to update the ibi dequeue pointer atomically */ - spin_lock(&hci->lock); op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_IBI_DEQ_PTR; op1_val |= FIELD_PREP(RING_OP1_IBI_DEQ_PTR, deq_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock(&hci->lock); /* update the chunk pointer */ rh->ibi_chunk_ptr += ibi_chunks; diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c index 02866c2237fa..8f48a81e65ab 100644 --- a/drivers/i3c/master/mipi-i3c-hci/pio.c +++ b/drivers/i3c/master/mipi-i3c-hci/pio.c @@ -1014,15 +1014,12 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci) struct hci_pio_data *pio = hci->io_data; u32 status; - spin_lock(&hci->lock); status = pio_reg_read(INTR_STATUS); dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x", status, pio->enabled_irqs); status &= pio->enabled_irqs | STAT_LATENCY_WARNINGS; - if (!status) { - spin_unlock(&hci->lock); + if (!status) return false; - } if (status & STAT_IBI_STATUS_THLD) hci_pio_process_ibi(hci, pio); @@ -1056,7 +1053,6 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci) pio_reg_write(INTR_SIGNAL_ENABLE, pio->enabled_irqs); dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x", pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE)); - spin_unlock(&hci->lock); return true; } From b795e68bf3073d67bebbb5a44d93f49efc5b8cc7 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:45 +0200 Subject: [PATCH 429/487] i3c: mipi-i3c-hci: Correct RING_CTRL_ABORT handling in DMA dequeue The logic used to abort the DMA ring contains several flaws: 1. The driver unconditionally issues a ring abort even when the ring has already stopped. 2. The completion used to wait for abort completion is never re-initialized, resulting in incorrect wait behavior. 3. The abort sequence unintentionally clears RING_CTRL_ENABLE, which resets hardware ring pointers and disrupts the controller state. 4. If the ring is already stopped, the abort operation should be considered successful without attempting further action. Fix the abort handling by checking whether the ring is running before issuing an abort, re-initializing the completion when needed, ensuring that RING_CTRL_ENABLE remains asserted during abort, and treating an already stopped ring as a successful condition. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-9-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/dma.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index d7840ff69e59..a3e8e01a35c9 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -546,18 +546,25 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, struct hci_rh_data *rh = &rings->headers[xfer_list[0].ring_number]; unsigned int i; bool did_unqueue = false; + u32 ring_status; guard(mutex)(&hci->control_mutex); - /* stop the ring */ - rh_reg_write(RING_CONTROL, RING_CTRL_ABORT); - if (wait_for_completion_timeout(&rh->op_done, HZ) == 0) { - /* - * We're deep in it if ever this condition is ever met. - * Hardware might still be writing to memory, etc. - */ - dev_crit(&hci->master.dev, "unable to abort the ring\n"); - WARN_ON(1); + ring_status = rh_reg_read(RING_STATUS); + if (ring_status & RING_STATUS_RUNNING) { + /* stop the ring */ + reinit_completion(&rh->op_done); + rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_ABORT); + wait_for_completion_timeout(&rh->op_done, HZ); + ring_status = rh_reg_read(RING_STATUS); + if (ring_status & RING_STATUS_RUNNING) { + /* + * We're deep in it if ever this condition is ever met. + * Hardware might still be writing to memory, etc. + */ + dev_crit(&hci->master.dev, "unable to abort the ring\n"); + WARN_ON(1); + } } spin_lock_irq(&hci->lock); From ec3cfd835f7c4bbd23bc9ad909d2fdc772a578bb Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:46 +0200 Subject: [PATCH 430/487] i3c: mipi-i3c-hci: Add missing TID field to no-op command descriptor The internal control command descriptor used for no-op commands includes a Transaction ID (TID) field, but the no-op command constructed in hci_dma_dequeue_xfer() omitted it. As a result, the hardware receives a no-op descriptor without the expected TID. This bug has gone unnoticed because the TID is currently not validated in the no-op completion path, but the descriptor format requires it to be present. Add the missing TID field when generating a no-op descriptor so that its layout matches the defined command structure. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-10-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/cmd.h | 1 + drivers/i3c/master/mipi-i3c-hci/dma.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd.h b/drivers/i3c/master/mipi-i3c-hci/cmd.h index 1d6dd2c5d01a..b1bf87daa651 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd.h +++ b/drivers/i3c/master/mipi-i3c-hci/cmd.h @@ -17,6 +17,7 @@ #define CMD_0_TOC W0_BIT_(31) #define CMD_0_ROC W0_BIT_(30) #define CMD_0_ATTR W0_MASK(2, 0) +#define CMD_0_TID W0_MASK(6, 3) /* * Response Descriptor Structure diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index a3e8e01a35c9..239a195df7c7 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -582,7 +582,7 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, u32 *ring_data = rh->xfer + rh->xfer_struct_sz * idx; /* store no-op cmd descriptor */ - *ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7); + *ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7) | FIELD_PREP(CMD_0_TID, xfer->cmd_tid); *ring_data++ = 0; if (hci->cmd == &mipi_i3c_hci_cmd_v2) { *ring_data++ = 0; From b6d586431ae20d5157ee468d0ef62ad26798ef13 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:47 +0200 Subject: [PATCH 431/487] i3c: mipi-i3c-hci: Restart DMA ring correctly after dequeue abort The DMA dequeue path attempts to restart the ring after aborting an in-flight transfer, but the current sequence is incomplete. The controller must be brought out of the aborted state and the ring control registers must be programmed in the correct order: first clearing ABORT, then re-enabling the ring and asserting RUN_STOP to resume operation. Add the missing controller resume step and update the ring control writes so that the ring is restarted using the proper sequence. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-11-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/dma.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index 239a195df7c7..41b83f07fdab 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -600,7 +600,9 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, } /* restart the ring */ + mipi_i3c_hci_resume(hci); rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE); + rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_RUN_STOP); spin_unlock_irq(&hci->lock); From 7ac45bc68f089887ab3a70358057edb7e6b6084e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:48 +0200 Subject: [PATCH 432/487] i3c: mipi-i3c-hci: Consolidate common xfer processing logic Several parts of the MIPI I3C HCI driver duplicate the same sequence for queuing a transfer, waiting for completion, and handling timeouts. This logic appears in five separate locations and will be affected by an upcoming fix. Refactor the repeated code into a new helper, i3c_hci_process_xfer(), and store the timeout value in the hci_xfer structure so that callers do not need to pass it as a separate parameter. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-12-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/cmd_v1.c | 8 ++--- drivers/i3c/master/mipi-i3c-hci/cmd_v2.c | 8 ++--- drivers/i3c/master/mipi-i3c-hci/core.c | 43 ++++++++++++++---------- drivers/i3c/master/mipi-i3c-hci/hci.h | 2 ++ 4 files changed, 33 insertions(+), 28 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c index 831a261f6c56..75d452d7f6af 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c +++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c @@ -331,12 +331,10 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci) CMD_A0_ROC | CMD_A0_TOC; xfer->cmd_desc[1] = 0; xfer->completion = &done; - hci->io->queue_xfer(hci, xfer, 1); - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, 1)) { - ret = -ETIMEDOUT; + xfer->timeout = HZ; + ret = i3c_hci_process_xfer(hci, xfer, 1); + if (ret) break; - } if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER || RESP_STATUS(xfer->response) == RESP_ERR_NACK) && RESP_DATA_LENGTH(xfer->response) == 1) { diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c index 054beee36da5..39eec26a363c 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c +++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c @@ -253,6 +253,7 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci) xfer[0].rnw = true; xfer[0].cmd_desc[1] = CMD_A1_DATA_LENGTH(8); xfer[1].completion = &done; + xfer[1].timeout = HZ; for (;;) { ret = i3c_master_get_free_addr(&hci->master, next_addr); @@ -272,12 +273,9 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci) CMD_A0_ASSIGN_ADDRESS(next_addr) | CMD_A0_ROC | CMD_A0_TOC; - hci->io->queue_xfer(hci, xfer, 2); - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, 2)) { - ret = -ETIMEDOUT; + ret = i3c_hci_process_xfer(hci, xfer, 2); + if (ret) break; - } if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) { ret = 0; /* no more devices to be assigned */ break; diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index adf35b7fa498..4a80671536f0 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -213,6 +213,25 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci) reg_write(DCT_SECTION, FIELD_PREP(DCT_TABLE_INDEX, 0)); } +int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n) +{ + struct completion *done = xfer[n - 1].completion; + unsigned long timeout = xfer[n - 1].timeout; + int ret; + + ret = hci->io->queue_xfer(hci, xfer, n); + if (ret) + return ret; + + if (!wait_for_completion_timeout(done, timeout) && + hci->io->dequeue_xfer(hci, xfer, n)) { + dev_err(&hci->master.dev, "%s: timeout error\n", __func__); + return -ETIMEDOUT; + } + + return 0; +} + static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m, struct i3c_ccc_cmd *ccc) { @@ -253,18 +272,14 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m, last = i - 1; xfer[last].cmd_desc[0] |= CMD_0_TOC; xfer[last].completion = &done; + xfer[last].timeout = HZ; if (prefixed) xfer--; - ret = hci->io->queue_xfer(hci, xfer, nxfers); + ret = i3c_hci_process_xfer(hci, xfer, nxfers); if (ret) goto out; - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIMEDOUT; - goto out; - } for (i = prefixed; i < nxfers; i++) { if (ccc->rnw) ccc->dests[i - prefixed].payload.len = @@ -335,15 +350,11 @@ static int i3c_hci_i3c_xfers(struct i3c_dev_desc *dev, last = i - 1; xfer[last].cmd_desc[0] |= CMD_0_TOC; xfer[last].completion = &done; + xfer[last].timeout = HZ; - ret = hci->io->queue_xfer(hci, xfer, nxfers); + ret = i3c_hci_process_xfer(hci, xfer, nxfers); if (ret) goto out; - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIMEDOUT; - goto out; - } for (i = 0; i < nxfers; i++) { if (i3c_xfers[i].rnw) i3c_xfers[i].len = RESP_DATA_LENGTH(xfer[i].response); @@ -383,15 +394,11 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev, last = i - 1; xfer[last].cmd_desc[0] |= CMD_0_TOC; xfer[last].completion = &done; + xfer[last].timeout = m->i2c.timeout; - ret = hci->io->queue_xfer(hci, xfer, nxfers); + ret = i3c_hci_process_xfer(hci, xfer, nxfers); if (ret) goto out; - if (!wait_for_completion_timeout(&done, m->i2c.timeout) && - hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIMEDOUT; - goto out; - } for (i = 0; i < nxfers; i++) { if (RESP_STATUS(xfer[i].response) != RESP_SUCCESS) { ret = -EIO; diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h index 9c63d80f7fc4..850016e3d4fe 100644 --- a/drivers/i3c/master/mipi-i3c-hci/hci.h +++ b/drivers/i3c/master/mipi-i3c-hci/hci.h @@ -89,6 +89,7 @@ struct hci_xfer { unsigned int data_len; unsigned int cmd_tid; struct completion *completion; + unsigned long timeout; union { struct { /* PIO specific */ @@ -156,5 +157,6 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci); void amd_set_od_pp_timing(struct i3c_hci *hci); void amd_set_resp_buf_thld(struct i3c_hci *hci); void i3c_hci_sync_irq_inactive(struct i3c_hci *hci); +int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n); #endif From e44d2719225e618dde74c7056f8e6949f884095e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:49 +0200 Subject: [PATCH 433/487] i3c: mipi-i3c-hci: Fix race in DMA error handling in interrupt context The DMA ring halts whenever a transfer encounters an error. The interrupt handler previously attempted to detect this situation and restart the ring if a transfer completed at the same time. However, this restart logic runs entirely in interrupt context and is inherently racy: it interacts with other paths manipulating the ring state, and fully serializing it within the interrupt handler is not practical. Move this error-recovery logic out of the interrupt handler and into the transfer-processing path (i3c_hci_process_xfer()), where serialization and state management are already controlled. Introduce a new optional I/O-ops callback, handle_error(), invoked when a completed transfer reports an error. For DMA operation, the implementation simply calls the existing dequeue function, which safely aborts and restarts the ring when needed. This removes the fragile ring-restart logic from the interrupt handler and centralizes error handling where proper sequencing can be ensured. Fixes: ccdb2e0e3b00d ("i3c: mipi-i3c-hci: Add Intel specific quirk to ring resuming") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-13-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 19 ++++++++++++---- drivers/i3c/master/mipi-i3c-hci/dma.c | 31 +++++++------------------- drivers/i3c/master/mipi-i3c-hci/hci.h | 1 + 3 files changed, 24 insertions(+), 27 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index 4a80671536f0..b98952d12d7c 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -223,10 +223,21 @@ int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n) if (ret) return ret; - if (!wait_for_completion_timeout(done, timeout) && - hci->io->dequeue_xfer(hci, xfer, n)) { - dev_err(&hci->master.dev, "%s: timeout error\n", __func__); - return -ETIMEDOUT; + if (!wait_for_completion_timeout(done, timeout)) { + if (hci->io->dequeue_xfer(hci, xfer, n)) { + dev_err(&hci->master.dev, "%s: timeout error\n", __func__); + return -ETIMEDOUT; + } + return 0; + } + + if (hci->io->handle_error) { + bool error = false; + + for (int i = 0; i < n && !error; i++) + error = RESP_STATUS(xfer[i].response); + if (error) + return hci->io->handle_error(hci, xfer, n); } return 0; diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index 41b83f07fdab..e487ef52f6b4 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -609,6 +609,11 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, return did_unqueue; } +static int hci_dma_handle_error(struct i3c_hci *hci, struct hci_xfer *xfer_list, int n) +{ + return hci_dma_dequeue_xfer(hci, xfer_list, n) ? -EIO : 0; +} + static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) { u32 op1_val, op2_val, resp, *ring_resp; @@ -870,29 +875,8 @@ static bool hci_dma_irq_handler(struct i3c_hci *hci) hci_dma_xfer_done(hci, rh); if (status & INTR_RING_OP) complete(&rh->op_done); - - if (status & INTR_TRANSFER_ABORT) { - u32 ring_status; - - dev_notice_ratelimited(&hci->master.dev, - "Ring %d: Transfer Aborted\n", i); - mipi_i3c_hci_resume(hci); - ring_status = rh_reg_read(RING_STATUS); - if (!(ring_status & RING_STATUS_RUNNING) && - status & INTR_TRANSFER_COMPLETION && - status & INTR_TRANSFER_ERR) { - /* - * Ring stop followed by run is an Intel - * specific required quirk after resuming the - * halted controller. Do it only when the ring - * is not in running state after a transfer - * error. - */ - rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE); - rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | - RING_CTRL_RUN_STOP); - } - } + if (status & INTR_TRANSFER_ABORT) + dev_dbg(&hci->master.dev, "Ring %d: Transfer Aborted\n", i); if (status & INTR_IBI_RING_FULL) dev_err_ratelimited(&hci->master.dev, "Ring %d: IBI Ring Full Condition\n", i); @@ -908,6 +892,7 @@ const struct hci_io_ops mipi_i3c_hci_dma = { .cleanup = hci_dma_cleanup, .queue_xfer = hci_dma_queue_xfer, .dequeue_xfer = hci_dma_dequeue_xfer, + .handle_error = hci_dma_handle_error, .irq_handler = hci_dma_irq_handler, .request_ibi = hci_dma_request_ibi, .free_ibi = hci_dma_free_ibi, diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h index 850016e3d4fe..9ac9d0e342f4 100644 --- a/drivers/i3c/master/mipi-i3c-hci/hci.h +++ b/drivers/i3c/master/mipi-i3c-hci/hci.h @@ -123,6 +123,7 @@ struct hci_io_ops { bool (*irq_handler)(struct i3c_hci *hci); int (*queue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n); bool (*dequeue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n); + int (*handle_error)(struct i3c_hci *hci, struct hci_xfer *xfer, int n); int (*request_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev, const struct i3c_ibi_setup *req); void (*free_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev); From c6396b835a5e599c4df656112140f065bb544a24 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:50 +0200 Subject: [PATCH 434/487] i3c: mipi-i3c-hci: Fix handling of shared IRQs during early initialization Shared interrupts may fire unexpectedly, including during periods when the controller is not yet fully initialized. Commit b9a15012a1452 ("i3c: mipi-i3c-hci: Add optional Runtime PM support") addressed this issue for the runtime-suspended state, but the same problem can also occur before the bus is enabled for the first time. Ensure the IRQ handler ignores interrupts until initialization is complete by making consistent use of the existing irq_inactive flag. The flag is now set to false immediately before enabling the bus. To guarantee correct ordering with respect to the IRQ handler, protect all transitions of irq_inactive with the same spinlock used inside the handler. Fixes: b8460480f62e1 ("i3c: mipi-i3c-hci: Allow for Multi-Bus Instances") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-14-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index b98952d12d7c..d5e91af7d569 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -152,6 +152,9 @@ static int i3c_hci_bus_init(struct i3c_master_controller *m) if (hci->quirks & HCI_QUIRK_RESP_BUF_THLD) amd_set_resp_buf_thld(hci); + scoped_guard(spinlock_irqsave, &hci->lock) + hci->irq_inactive = false; + /* Enable bus with Hot-Join disabled */ reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL); dev_dbg(&hci->master.dev, "HC_CONTROL = %#x", reg_read(HC_CONTROL)); @@ -184,8 +187,9 @@ void i3c_hci_sync_irq_inactive(struct i3c_hci *hci) int irq = platform_get_irq(pdev, 0); reg_write(INTR_SIGNAL_ENABLE, 0x0); - hci->irq_inactive = true; synchronize_irq(irq); + scoped_guard(spinlock_irqsave, &hci->lock) + hci->irq_inactive = true; } static void i3c_hci_bus_cleanup(struct i3c_master_controller *m) @@ -781,10 +785,11 @@ static int i3c_hci_runtime_resume(struct device *dev) mipi_i3c_hci_dat_v1.restore(hci); - hci->irq_inactive = false; - hci->io->resume(hci); + scoped_guard(spinlock_irqsave, &hci->lock) + hci->irq_inactive = false; + /* Enable bus with Hot-Join disabled */ reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL); @@ -975,6 +980,8 @@ static int i3c_hci_probe(struct platform_device *pdev) if (ret) return ret; + hci->irq_inactive = true; + irq = platform_get_irq(pdev, 0); ret = devm_request_irq(&pdev->dev, irq, i3c_hci_irq_handler, IRQF_SHARED, NULL, hci); From 9a258d1336f7ff3add8b92d566d3a421f03bf4d2 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 6 Mar 2026 09:24:51 +0200 Subject: [PATCH 435/487] i3c: mipi-i3c-hci: Fallback to software reset when bus disable fails Disruption of the MIPI I3C HCI controller's internal state can cause i3c_hci_bus_disable() to fail when attempting to shut down the bus. In the code paths where bus disable is invoked - bus clean-up and runtime suspend - the controller does not need to remain operational afterward, so a full controller reset is a safe recovery mechanism. Add a fallback to issue a software reset when disabling the bus fails. This ensures the bus is reliably halted even if the controller's state machine is stuck or unresponsive. The fallback is used both during bus clean-up and in the runtime suspend path. In the latter case, ensure interrupts are quiesced after reset. Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Reviewed-by: Frank Li Link: https://patch.msgid.link/20260306072451.11131-15-adrian.hunter@intel.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 65 ++++++++++++++------------ 1 file changed, 35 insertions(+), 30 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index d5e91af7d569..284f3ed7af8c 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -181,6 +181,34 @@ static int i3c_hci_bus_disable(struct i3c_hci *hci) return ret; } +static int i3c_hci_software_reset(struct i3c_hci *hci) +{ + u32 regval; + int ret; + + /* + * SOFT_RST must be clear before we write to it. + * Then we must wait until it clears again. + */ + ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, + !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); + if (ret) { + dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__); + return ret; + } + + reg_write(RESET_CONTROL, SOFT_RST); + + ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, + !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); + if (ret) { + dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__); + return ret; + } + + return 0; +} + void i3c_hci_sync_irq_inactive(struct i3c_hci *hci) { struct platform_device *pdev = to_platform_device(hci->master.dev.parent); @@ -196,7 +224,8 @@ static void i3c_hci_bus_cleanup(struct i3c_master_controller *m) { struct i3c_hci *hci = to_i3c_hci(m); - i3c_hci_bus_disable(hci); + if (i3c_hci_bus_disable(hci)) + i3c_hci_software_reset(hci); hci->io->cleanup(hci); } @@ -626,34 +655,6 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id) return result; } -static int i3c_hci_software_reset(struct i3c_hci *hci) -{ - u32 regval; - int ret; - - /* - * SOFT_RST must be clear before we write to it. - * Then we must wait until it clears again. - */ - ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, - !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); - if (ret) { - dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__); - return ret; - } - - reg_write(RESET_CONTROL, SOFT_RST); - - ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, - !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); - if (ret) { - dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__); - return ret; - } - - return 0; -} - static inline bool is_version_1_1_or_newer(struct i3c_hci *hci) { return hci->version_major > 1 || (hci->version_major == 1 && hci->version_minor > 0); @@ -764,8 +765,12 @@ static int i3c_hci_runtime_suspend(struct device *dev) int ret; ret = i3c_hci_bus_disable(hci); - if (ret) + if (ret) { + /* Fall back to software reset to disable the bus */ + ret = i3c_hci_software_reset(hci); + i3c_hci_sync_irq_inactive(hci); return ret; + } hci->io->suspend(hci); From f26ecaa0f0abfe5db173416214098a00d3b7db79 Mon Sep 17 00:00:00 2001 From: Peter Yin Date: Mon, 2 Mar 2026 15:56:42 +0800 Subject: [PATCH 436/487] i3c: master: dw-i3c: Fix missing of_node for virtual I2C adapter The DesignWare I3C master driver creates a virtual I2C adapter to provide backward compatibility with I2C devices. However, the current implementation does not associate this virtual adapter with any Device Tree node. Propagate the of_node from the I3C master platform device to the virtual I2C adapter's device structure. This ensures that standard I2C aliases are correctly resolved and bus numbering remains consistent. Signed-off-by: Peter Yin Reviewed-by: Frank Li Link: https://patch.msgid.link/20260302075645.1492766-1-peteryin.openbmc@gmail.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index d87bde3f7700..d334c217c7a3 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1659,6 +1659,8 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, pm_runtime_get_noresume(&pdev->dev); INIT_WORK(&master->hj_work, dw_i3c_hj_work); + + device_set_of_node_from_dev(&master->base.i2c.dev, &pdev->dev); ret = i3c_master_register(&master->base, &pdev->dev, &dw_mipi_i3c_ops, false); if (ret) From f311a05784634febd299f03476b80f3f18489767 Mon Sep 17 00:00:00 2001 From: Adrian Ng Ho Yin Date: Fri, 13 Feb 2026 14:00:48 +0800 Subject: [PATCH 437/487] i3c: dw-i3c-master: Set SIR_REJECT in DAT on device attach and reattach The DesignWare I3C master controller ACKs IBIs as soon as a valid Device Address Table (DAT) entry is present. This can create a race between device attachment (after DAA) and the point where the client driver enables IBIs via i3c_device_enable_ibi(). Set DEV_ADDR_TABLE_SIR_REJECT in the DAT entry during attach_i3c_dev() and reattach_i3c_dev() so that IBIs are rejected by default. The bit is managed thereafter by the existing dw_i3c_master_set_sir_enabled() function, which clears it in enable_ibi() after ENEC is issued, and restores it in disable_ibi() after DISEC. Fixes: 1dd728f5d4d4 ("i3c: master: Add driver for Synopsys DesignWare IP") Signed-off-by: Adrian Ng Ho Yin Reviewed-by: Frank Li Link: https://patch.msgid.link/53f5b8cbdd8af789ec38b95b02873f32f9182dd6.1770962368.git.adrianhoyin.ng@altera.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index d334c217c7a3..d6bdb32397fb 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1024,7 +1024,7 @@ static int dw_i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev, master->free_pos &= ~BIT(pos); } - writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr), + writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr) | DEV_ADDR_TABLE_SIR_REJECT, master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); @@ -1053,7 +1053,7 @@ static int dw_i3c_master_attach_i3c_dev(struct i3c_dev_desc *dev) master->free_pos &= ~BIT(pos); i3c_dev_set_master_data(dev, data); - writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr), + writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr) | DEV_ADDR_TABLE_SIR_REJECT, master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); From d4c7210d2f3ea481a6481f03040a64d9077a6172 Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Wed, 11 Mar 2026 20:17:23 -0300 Subject: [PATCH 438/487] smb: client: fix iface port assignment in parse_server_interfaces parse_server_interfaces() initializes interface socket addresses with CIFS_PORT. When the mount uses a non-default port this overwrites the configured destination port. Later, cifs_chan_update_iface() copies this sockaddr into server->dstaddr, causing reconnect attempts to use the wrong port after server interface updates. Use the existing port from server->dstaddr instead. Cc: stable@vger.kernel.org Fixes: fe856be475f7 ("CIFS: parse and store info on iface queries") Tested-by: Dr. Thomas Orgis Reviewed-by: Enzo Matsumiya Signed-off-by: Henrique Carvalho Signed-off-by: Steve French --- fs/smb/client/smb2ops.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7f2d3459cbf9..612057318de2 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -628,6 +628,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, struct smb_sockaddr_in6 *p6; struct cifs_server_iface *info = NULL, *iface = NULL, *niface = NULL; struct cifs_server_iface tmp_iface; + __be16 port; ssize_t bytes_left; size_t next = 0; int nb_iface = 0; @@ -662,6 +663,15 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, goto out; } + spin_lock(&ses->server->srv_lock); + if (ses->server->dstaddr.ss_family == AF_INET) + port = ((struct sockaddr_in *)&ses->server->dstaddr)->sin_port; + else if (ses->server->dstaddr.ss_family == AF_INET6) + port = ((struct sockaddr_in6 *)&ses->server->dstaddr)->sin6_port; + else + port = cpu_to_be16(CIFS_PORT); + spin_unlock(&ses->server->srv_lock); + while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); /* default to 1Gbps when link speed is unset */ @@ -682,7 +692,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, memcpy(&addr4->sin_addr, &p4->IPv4Address, 4); /* [MS-SMB2] 2.2.32.5.1.1 Clients MUST ignore these */ - addr4->sin_port = cpu_to_be16(CIFS_PORT); + addr4->sin_port = port; cifs_dbg(FYI, "%s: ipv4 %pI4\n", __func__, &addr4->sin_addr); @@ -696,7 +706,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, /* [MS-SMB2] 2.2.32.5.1.2 Clients MUST ignore these */ addr6->sin6_flowinfo = 0; addr6->sin6_scope_id = 0; - addr6->sin6_port = cpu_to_be16(CIFS_PORT); + addr6->sin6_port = port; cifs_dbg(FYI, "%s: ipv6 %pI6\n", __func__, &addr6->sin6_addr); From 40e75e42f49ca54b4ff41f3edb94f5ef0299140c Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Wed, 11 Mar 2026 15:00:52 -0300 Subject: [PATCH 439/487] smb: client: fix open handle lookup in cifs_open() When looking up open handles to be re-used in cifs_open(), calling cifs_get_{writable,readable}_path() is wrong as it will look up for the first matching open handle, and if @file->f_flags doesn't match, it will ignore the remaining open handles in cifsInodeInfo::openFileList that might potentially match @file->f_flags. For writable and readable handles, fix this by calling __cifs_get_writable_file() and __find_readable_file(), respectively, with FIND_OPEN_FLAGS set. With the patch, the following program ends up with two opens instead of three sent over the wire. ``` #define _GNU_SOURCE #include #include #include int main(int argc, char *argv[]) { int fd; fd = open("/mnt/1/foo", O_CREAT | O_WRONLY | O_TRUNC, 0664); close(fd); fd = open("/mnt/1/foo", O_DIRECT | O_WRONLY); close(fd); fd = open("/mnt/1/foo", O_WRONLY); close(fd); fd = open("/mnt/1/foo", O_DIRECT | O_WRONLY); close(fd); return 0; } ``` ``` $ mount.cifs //srv/share /mnt/1 -o ... $ gcc test.c && ./a.out ``` Signed-off-by: Paulo Alcantara (Red Hat) Reviewed-by: ChenXiaoSong Cc: David Howells Cc: linux-cifs@vger.kernel.org Signed-off-by: Steve French --- fs/smb/client/cifsacl.c | 2 +- fs/smb/client/cifsfs.c | 2 +- fs/smb/client/cifsglob.h | 12 ++--- fs/smb/client/cifsproto.h | 26 +++++++-- fs/smb/client/file.c | 111 ++++++++++++++++++++++---------------- fs/smb/client/inode.c | 6 +-- fs/smb/client/smb1ops.c | 2 +- fs/smb/client/smb2inode.c | 22 ++++---- fs/smb/client/smb2ops.c | 4 +- 9 files changed, 112 insertions(+), 75 deletions(-) diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index f4cb3018a358..c920039d733c 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1489,7 +1489,7 @@ struct smb_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, struct cifsFileInfo *open_file = NULL; if (inode) - open_file = find_readable_file(CIFS_I(inode), true); + open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY); if (!open_file) return get_cifs_acl_by_path(cifs_sb, path, pacllen, info); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index b6e3db993cc6..32d0305a1239 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1269,7 +1269,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s struct cifsFileInfo *writeable_srcfile; int rc = -EINVAL; - writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY); + writeable_srcfile = find_writable_file(src_cifsi, FIND_FSUID_ONLY); if (writeable_srcfile) { if (src_tcon->ses->server->ops->set_file_size) rc = src_tcon->ses->server->ops->set_file_size( diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index bb0fe4b60240..7877d327dbb0 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1885,12 +1885,12 @@ static inline bool is_replayable_error(int error) } -/* cifs_get_writable_file() flags */ -enum cifs_writable_file_flags { - FIND_WR_ANY = 0U, - FIND_WR_FSUID_ONLY = (1U << 0), - FIND_WR_WITH_DELETE = (1U << 1), - FIND_WR_NO_PENDING_DELETE = (1U << 2), +enum cifs_find_flags { + FIND_ANY = 0U, + FIND_FSUID_ONLY = (1U << 0), + FIND_WITH_DELETE = (1U << 1), + FIND_NO_PENDING_DELETE = (1U << 2), + FIND_OPEN_FLAGS = (1U << 3), }; #define MID_FREE 0 diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 800a7e418c32..884bfa1cf0b4 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -138,12 +138,14 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result); struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, int flags); -int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, - struct cifsFileInfo **ret_file); +int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, unsigned int open_flags, + struct cifsFileInfo **ret_file); int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, int flags, struct cifsFileInfo **ret_file); -struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, - bool fsuid_only); +struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, + unsigned int open_flags); int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, struct cifsFileInfo **ret_file); int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, @@ -596,4 +598,20 @@ static inline void cifs_sg_set_buf(struct sg_table *sgtable, } } +static inline int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, + struct cifsFileInfo **ret_file) +{ + find_flags &= ~FIND_OPEN_FLAGS; + return __cifs_get_writable_file(cifs_inode, find_flags, 0, ret_file); +} + +static inline struct cifsFileInfo * +find_readable_file(struct cifsInodeInfo *cinode, unsigned int find_flags) +{ + find_flags &= ~FIND_OPEN_FLAGS; + find_flags |= FIND_NO_PENDING_DELETE; + return __find_readable_file(cinode, find_flags, 0); +} + #endif /* _CIFSPROTO_H */ diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 13dda87f7711..27f61fe7e4e2 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -255,7 +255,7 @@ static void cifs_begin_writeback(struct netfs_io_request *wreq) struct cifs_io_request *req = container_of(wreq, struct cifs_io_request, rreq); int ret; - ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_WR_ANY, &req->cfile); + ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_ANY, &req->cfile); if (ret) { cifs_dbg(VFS, "No writable handle in writepages ret=%d\n", ret); return; @@ -956,7 +956,7 @@ int cifs_file_flush(const unsigned int xid, struct inode *inode, return tcon->ses->server->ops->flush(xid, tcon, &cfile->fid); } - rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile); + rc = cifs_get_writable_file(CIFS_I(inode), FIND_ANY, &cfile); if (!rc) { tcon = tlink_tcon(cfile->tlink); rc = tcon->ses->server->ops->flush(xid, tcon, &cfile->fid); @@ -981,7 +981,7 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) return -ERESTARTSYS; mapping_set_error(inode->i_mapping, rc); - cfile = find_writable_file(cinode, FIND_WR_FSUID_ONLY); + cfile = find_writable_file(cinode, FIND_FSUID_ONLY); rc = cifs_file_flush(xid, inode, cfile); if (!rc) { if (cfile) { @@ -1061,32 +1061,29 @@ int cifs_open(struct inode *inode, struct file *file) /* Get the cached handle as SMB2 close is deferred */ if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { - rc = cifs_get_writable_path(tcon, full_path, - FIND_WR_FSUID_ONLY | - FIND_WR_NO_PENDING_DELETE, - &cfile); + rc = __cifs_get_writable_file(CIFS_I(inode), + FIND_FSUID_ONLY | + FIND_NO_PENDING_DELETE | + FIND_OPEN_FLAGS, + file->f_flags, &cfile); } else { - rc = cifs_get_readable_path(tcon, full_path, &cfile); + cfile = __find_readable_file(CIFS_I(inode), + FIND_NO_PENDING_DELETE | + FIND_OPEN_FLAGS, + file->f_flags); + rc = cfile ? 0 : -ENOENT; } if (rc == 0) { - unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC); - unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC); - - if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) && - (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) { - file->private_data = cfile; - spin_lock(&CIFS_I(inode)->deferred_lock); - cifs_del_deferred_close(cfile); - spin_unlock(&CIFS_I(inode)->deferred_lock); - goto use_cache; - } - _cifsFileInfo_put(cfile, true, false); - } else { - /* hard link on the defeered close file */ - rc = cifs_get_hardlink_path(tcon, inode, file); - if (rc) - cifs_close_deferred_file(CIFS_I(inode)); + file->private_data = cfile; + spin_lock(&CIFS_I(inode)->deferred_lock); + cifs_del_deferred_close(cfile); + spin_unlock(&CIFS_I(inode)->deferred_lock); + goto use_cache; } + /* hard link on the deferred close file */ + rc = cifs_get_hardlink_path(tcon, inode, file); + if (rc) + cifs_close_deferred_file(CIFS_I(inode)); if (server->oplocks) oplock = REQ_OPLOCK; @@ -2512,10 +2509,33 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t netfs_write_subrequest_terminated(&wdata->subreq, result); } -struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, - bool fsuid_only) +static bool open_flags_match(struct cifsInodeInfo *cinode, + unsigned int oflags, unsigned int cflags) +{ + struct inode *inode = &cinode->netfs.inode; + int crw = 0, orw = 0; + + oflags &= ~(O_CREAT | O_EXCL | O_TRUNC); + cflags &= ~(O_CREAT | O_EXCL | O_TRUNC); + + if (cifs_fscache_enabled(inode)) { + if (OPEN_FMODE(cflags) & FMODE_WRITE) + crw = 1; + if (OPEN_FMODE(oflags) & FMODE_WRITE) + orw = 1; + } + if (cifs_convert_flags(oflags, orw) != cifs_convert_flags(cflags, crw)) + return false; + + return (oflags & (O_SYNC | O_DIRECT)) == (cflags & (O_SYNC | O_DIRECT)); +} + +struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, + unsigned int open_flags) { struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode); + bool fsuid_only = find_flags & FIND_FSUID_ONLY; struct cifsFileInfo *open_file = NULL; /* only filter by fsuid on multiuser mounts */ @@ -2529,6 +2549,13 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { if (fsuid_only && !uid_eq(open_file->uid, current_fsuid())) continue; + if ((find_flags & FIND_NO_PENDING_DELETE) && + open_file->status_file_deleted) + continue; + if ((find_flags & FIND_OPEN_FLAGS) && + !open_flags_match(cifs_inode, open_flags, + open_file->f_flags)) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) { if ((!open_file->invalidHandle)) { /* found a good file */ @@ -2547,17 +2574,17 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, } /* Return -EBADF if no handle is found and general rc otherwise */ -int -cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, - struct cifsFileInfo **ret_file) +int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, unsigned int open_flags, + struct cifsFileInfo **ret_file) { struct cifsFileInfo *open_file, *inv_file = NULL; struct cifs_sb_info *cifs_sb; bool any_available = false; int rc = -EBADF; unsigned int refind = 0; - bool fsuid_only = flags & FIND_WR_FSUID_ONLY; - bool with_delete = flags & FIND_WR_WITH_DELETE; + bool fsuid_only = find_flags & FIND_FSUID_ONLY; + bool with_delete = find_flags & FIND_WITH_DELETE; *ret_file = NULL; /* @@ -2591,9 +2618,13 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, continue; if (with_delete && !(open_file->fid.access & DELETE)) continue; - if ((flags & FIND_WR_NO_PENDING_DELETE) && + if ((find_flags & FIND_NO_PENDING_DELETE) && open_file->status_file_deleted) continue; + if ((find_flags & FIND_OPEN_FLAGS) && + !open_flags_match(cifs_inode, open_flags, + open_file->f_flags)) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { if (!open_file->invalidHandle) { /* found a good writable file */ @@ -2710,17 +2741,7 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, cinode = CIFS_I(d_inode(cfile->dentry)); spin_unlock(&tcon->open_file_lock); free_dentry_path(page); - *ret_file = find_readable_file(cinode, 0); - if (*ret_file) { - spin_lock(&cinode->open_file_lock); - if ((*ret_file)->status_file_deleted) { - spin_unlock(&cinode->open_file_lock); - cifsFileInfo_put(*ret_file); - *ret_file = NULL; - } else { - spin_unlock(&cinode->open_file_lock); - } - } + *ret_file = find_readable_file(cinode, FIND_ANY); return *ret_file ? 0 : -ENOENT; } @@ -2792,7 +2813,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) } if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { - smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); + smbfile = find_writable_file(CIFS_I(inode), FIND_ANY); if (smbfile) { rc = server->ops->flush(xid, tcon, &smbfile->fid); cifsFileInfo_put(smbfile); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 3e844c55ab8a..143fa2e665ed 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -2997,7 +2997,7 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, } } - cfile = find_readable_file(cifs_i, false); + cfile = find_readable_file(cifs_i, FIND_ANY); if (cfile == NULL) return -EINVAL; @@ -3050,7 +3050,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, size, false); cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); } else { - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY); if (open_file) { tcon = tlink_tcon(open_file->tlink); server = tcon->ses->server; @@ -3219,7 +3219,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) open_file->fid.netfid, open_file->pid); } else { - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY); if (open_file) { pTcon = tlink_tcon(open_file->tlink); rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 9643eca0cb70..9694117050a6 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -960,7 +960,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, struct cifs_tcon *tcon; /* if the file is already open for write, just use that fileid */ - open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY); + open_file = find_writable_file(cinode, FIND_FSUID_ONLY); if (open_file) { fid.netfid = open_file->fid.netfid; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 5280c5c869ad..364bdcff9c9d 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -1156,7 +1156,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, cifs_i = CIFS_I(inode); dosattrs = cifs_i->cifsAttrs | ATTR_READONLY; data.Attributes = cpu_to_le32(dosattrs); - cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, name, FIND_ANY, &cfile); oparms = CIFS_OPARMS(cifs_sb, tcon, name, FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE); tmprc = smb2_compound_op(xid, tcon, cifs_sb, name, @@ -1336,14 +1336,13 @@ int smb2_rename_path(const unsigned int xid, __u32 co = file_create_options(source_dentry); drop_cached_dir_by_name(xid, tcon, from_name, cifs_sb); - cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile); + cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile); int rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, co, DELETE, SMB2_OP_RENAME, cfile, source_dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); - cifs_get_writable_path(tcon, from_name, - FIND_WR_WITH_DELETE, &cfile); + cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile); rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, co, DELETE, SMB2_OP_RENAME, cfile, NULL); } @@ -1377,7 +1376,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, in_iov.iov_base = &eof; in_iov.iov_len = sizeof(eof); - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE); @@ -1387,7 +1386,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, cfile, NULL, NULL, dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, &in_iov, &(int){SMB2_OP_SET_EOF}, 1, @@ -1417,7 +1416,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path, (buf->LastWriteTime == 0) && (buf->ChangeTime == 0)) { if (buf->Attributes == 0) goto out; /* would be a no op, no sense sending this */ - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); } oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES, @@ -1476,7 +1475,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data, if (tcon->posix_extensions) { cmds[1] = SMB2_OP_POSIX_QUERY_INFO; - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL); if (!rc) { @@ -1485,7 +1484,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data, } } else { cmds[1] = SMB2_OP_QUERY_INFO; - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL); if (!rc) { @@ -1636,13 +1635,12 @@ int smb2_rename_pending_delete(const char *full_path, iov[1].iov_base = utf16_path; iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path); - cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_WITH_DELETE, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, cmds, num_cmds, cfile, NULL, NULL, dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease\n"); - cifs_get_writable_path(tcon, full_path, - FIND_WR_WITH_DELETE, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_WITH_DELETE, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, cmds, num_cmds, cfile, NULL, NULL, NULL); } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 612057318de2..98ac4e86bf99 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3362,7 +3362,7 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb, struct cifsFileInfo *open_file = NULL; if (inode && !(info & SACL_SECINFO)) - open_file = find_readable_file(CIFS_I(inode), true); + open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY); if (!open_file || (info & SACL_SECINFO)) return get_smb2_acl_by_path(cifs_sb, path, pacllen, info); @@ -3908,7 +3908,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs * some servers (Windows2016) will not reflect recent writes in * QUERY_ALLOCATED_RANGES until SMB2_flush is called. */ - wrcfile = find_writable_file(cifsi, FIND_WR_ANY); + wrcfile = find_writable_file(cifsi, FIND_ANY); if (wrcfile) { filemap_write_and_wait(inode->i_mapping); smb2_flush_file(xid, tcon, &wrcfile->fid); From e3beefd3af09f8e460ddaf39063d3d7664d7ab59 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Wed, 11 Mar 2026 10:48:54 +0530 Subject: [PATCH 440/487] cifs: make default value of retrans as zero When retrans mount option was introduced, the default value was set as 1. However, in the light of some bugs that this has exposed recently we should change it to 0 and retain the old behaviour before this option was introduced. Cc: Reviewed-by: Bharath SM Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/fs_context.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 54090739535f..a4a7c7eee038 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1997,7 +1997,7 @@ int smb3_init_fs_context(struct fs_context *fc) ctx->backupuid_specified = false; /* no backup intent for a user */ ctx->backupgid_specified = false; /* no backup intent for a group */ - ctx->retrans = 1; + ctx->retrans = 0; ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; ctx->nonativesocket = 0; From 94a4b1f959989de9c54d43c3a102fb1ee92e1414 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 7 Mar 2026 17:50:53 -0300 Subject: [PATCH 441/487] ipv6: move the disable_ipv6_mod knob to core code From: Jakub Kicinski Make sure disable_ipv6_mod itself is not part of the IPv6 module, in case core code wants to refer to it. We will remove support for IPv6=m soon, this change helps make fixes we commit before that less messy. Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-1-e2677e85628c@suse.com Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 7 ++++++- net/ipv4/af_inet.c | 6 ++++++ net/ipv6/af_inet6.c | 8 -------- 3 files changed, 12 insertions(+), 9 deletions(-) diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 443053a76dcf..a7421382a916 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -333,7 +333,12 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -bool ipv6_mod_enabled(void); +extern int disable_ipv6_mod; + +static inline bool ipv6_mod_enabled(void) +{ + return disable_ipv6_mod == 0; +} static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8036e76aa1e4..c7731e300a44 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -124,6 +124,12 @@ #include +/* Keep the definition of IPv6 disable here for now, to avoid annoying linker + * issues in case IPv6=m + */ +int disable_ipv6_mod; +EXPORT_SYMBOL(disable_ipv6_mod); + /* The inetsw table contains everything that inet_create needs to * build a new socket. */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 23cc9b4cb2f1..4cbd45b68088 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -86,8 +86,6 @@ struct ipv6_params ipv6_defaults = { .autoconf = 1, }; -static int disable_ipv6_mod; - module_param_named(disable, disable_ipv6_mod, int, 0444); MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); @@ -97,12 +95,6 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); -bool ipv6_mod_enabled(void) -{ - return disable_ipv6_mod == 0; -} -EXPORT_SYMBOL_GPL(ipv6_mod_enabled); - static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->ipv6_pinfo_offset; From 30021e969d48e5819d5ae56936c2f34c0f7ce997 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= Date: Sat, 7 Mar 2026 17:50:54 -0300 Subject: [PATCH 442/487] net: bonding: Fix nd_tbl NULL dereference when IPv6 is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If bonding ARP/NS validation is enabled, an IPv6 NS/NA packet received on a slave can reach bond_validate_na(), which calls bond_has_this_ip6(). That path calls ipv6_chk_addr() and can crash in __ipv6_chk_addr_and_flags(). BUG: kernel NULL pointer dereference, address: 00000000000005d8 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:__ipv6_chk_addr_and_flags+0x69/0x170 Call Trace: ipv6_chk_addr+0x1f/0x30 bond_validate_na+0x12e/0x1d0 [bonding] ? __pfx_bond_handle_frame+0x10/0x10 [bonding] bond_rcv_validate+0x1a0/0x450 [bonding] bond_handle_frame+0x5e/0x290 [bonding] ? srso_alias_return_thunk+0x5/0xfbef5 __netif_receive_skb_core.constprop.0+0x3e8/0xe50 ? srso_alias_return_thunk+0x5/0xfbef5 ? update_cfs_rq_load_avg+0x1a/0x240 ? srso_alias_return_thunk+0x5/0xfbef5 ? __enqueue_entity+0x5e/0x240 __netif_receive_skb_one_core+0x39/0xa0 process_backlog+0x9c/0x150 __napi_poll+0x30/0x200 ? srso_alias_return_thunk+0x5/0xfbef5 net_rx_action+0x338/0x3b0 handle_softirqs+0xc9/0x2a0 do_softirq+0x42/0x60 __local_bh_enable_ip+0x62/0x70 __dev_queue_xmit+0x2d3/0x1000 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? packet_parse_headers+0x10a/0x1a0 packet_sendmsg+0x10da/0x1700 ? kick_pool+0x5f/0x140 ? srso_alias_return_thunk+0x5/0xfbef5 ? __queue_work+0x12d/0x4f0 __sys_sendto+0x1f3/0x220 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x101/0xf80 ? exc_page_fault+0x6e/0x170 ? srso_alias_return_thunk+0x5/0xfbef5 entry_SYSCALL_64_after_hwframe+0x77/0x7f Fix this by checking ipv6_mod_enabled() before dispatching IPv6 packets to bond_na_rcv(). If IPv6 is disabled, return early from bond_rcv_validate() and avoid the path to ipv6_chk_addr(). Suggested-by: Fernando Fernandez Mancera Fixes: 4e24be018eb9 ("bonding: add new parameter ns_targets") Signed-off-by: Ricardo B. Marlière Reviewed-by: Hangbin Liu Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-2-e2677e85628c@suse.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c1fb92602e46..707419270ebf 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3428,7 +3428,7 @@ int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, } else if (is_arp) { return bond_arp_rcv(skb, bond, slave); #if IS_ENABLED(CONFIG_IPV6) - } else if (is_ipv6) { + } else if (is_ipv6 && likely(ipv6_mod_enabled())) { return bond_na_rcv(skb, bond, slave); #endif } else { From dcb4e2231469523d20cf0a2477d68245795c205d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= Date: Sat, 7 Mar 2026 17:50:55 -0300 Subject: [PATCH 443/487] bpf: bpf_out_neigh_v4: Fix nd_tbl NULL dereference when IPv6 is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If bpf_redirect_neigh() is called from tc with an explicit nexthop of nh_family == AF_INET6, bpf_out_neigh_v4() takes the AF_INET6 branch and calls ip_neigh_gw6(), which relies on ipv6_stub->nd_tbl. BUG: kernel NULL pointer dereference, address: 0000000000000248 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:skb_do_redirect+0xb93/0xf00 Call Trace: ? srso_alias_return_thunk+0x5/0xfbef5 ? __tcf_classify.constprop.0+0x83/0x160 ? srso_alias_return_thunk+0x5/0xfbef5 ? tcf_classify+0x2b/0x50 ? srso_alias_return_thunk+0x5/0xfbef5 ? tc_run+0xb8/0x120 ? srso_alias_return_thunk+0x5/0xfbef5 __dev_queue_xmit+0x6fa/0x1000 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? alloc_skb_with_frags+0x58/0x200 packet_sendmsg+0x10da/0x1700 ? srso_alias_return_thunk+0x5/0xfbef5 __sys_sendto+0x1f3/0x220 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x101/0xf80 ? exc_page_fault+0x6e/0x170 ? srso_alias_return_thunk+0x5/0xfbef5 entry_SYSCALL_64_after_hwframe+0x77/0x7f Fix this by adding an early check in the AF_INET6 branch of bpf_out_neigh_v4(). If IPv6 is disabled, unlock RCU and drop the packet. Suggested-by: Fernando Fernandez Mancera Fixes: ba452c9e996d ("bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop") Signed-off-by: Ricardo B. Marlière Acked-by: Daniel Borkmann Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-3-e2677e85628c@suse.com Signed-off-by: Jakub Kicinski --- net/core/filter.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index a77d23fe2359..fd38b6f8b7a8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2335,6 +2335,10 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { + if (unlikely(!ipv6_mod_enabled())) { + rcu_read_unlock(); + goto out_drop; + } neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { From d56b5d163458c45ab8fa1f00bd875af01b3ce28c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= Date: Sat, 7 Mar 2026 17:50:56 -0300 Subject: [PATCH 444/487] bpf: bpf_out_neigh_v6: Fix nd_tbl NULL dereference when IPv6 is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If bpf_redirect_neigh() is called with explicit AF_INET6 nexthop parameters, __bpf_redirect_neigh_v6() can skip the IPv6 FIB lookup and call bpf_out_neigh_v6() directly. bpf_out_neigh_v6() then calls ip_neigh_gw6(), which uses ipv6_stub->nd_tbl. BUG: kernel NULL pointer dereference, address: 0000000000000248 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:skb_do_redirect+0x44f/0xf40 Call Trace: ? srso_alias_return_thunk+0x5/0xfbef5 ? __tcf_classify.constprop.0+0x83/0x160 ? srso_alias_return_thunk+0x5/0xfbef5 ? tcf_classify+0x2b/0x50 ? srso_alias_return_thunk+0x5/0xfbef5 ? tc_run+0xb8/0x120 ? srso_alias_return_thunk+0x5/0xfbef5 __dev_queue_xmit+0x6fa/0x1000 ? srso_alias_return_thunk+0x5/0xfbef5 packet_sendmsg+0x10da/0x1700 ? srso_alias_return_thunk+0x5/0xfbef5 __sys_sendto+0x1f3/0x220 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x101/0xf80 ? exc_page_fault+0x6e/0x170 ? srso_alias_return_thunk+0x5/0xfbef5 entry_SYSCALL_64_after_hwframe+0x77/0x7f Fix this by adding an early check in bpf_out_neigh_v6(). If IPv6 is disabled, drop the packet before neighbor lookup. Suggested-by: Fernando Fernandez Mancera Fixes: ba452c9e996d ("bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop") Signed-off-by: Ricardo B. Marlière Acked-by: Daniel Borkmann Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-4-e2677e85628c@suse.com Signed-off-by: Jakub Kicinski --- net/core/filter.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index fd38b6f8b7a8..78b548158fb0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2228,6 +2228,9 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, return -ENOMEM; } + if (unlikely(!ipv6_mod_enabled())) + goto out_drop; + rcu_read_lock(); if (!nh) { dst = skb_dst(skb); From 99c8c16a4aad0b37293cae213e15957c573cf79b Mon Sep 17 00:00:00 2001 From: "Bastien Curutchet (Schneider Electric)" Date: Mon, 9 Mar 2026 14:15:43 +0100 Subject: [PATCH 445/487] net: dsa: microchip: Fix error path in PTP IRQ setup If request_threaded_irq() fails during the PTP message IRQ setup, the newly created IRQ mapping is never disposed. Indeed, the ksz_ptp_irq_setup()'s error path only frees the mappings that were successfully set up. Dispose the newly created mapping if the associated request_threaded_irq() fails at setup. Cc: stable@vger.kernel.org Fixes: d0b8fec8ae505 ("net: dsa: microchip: Fix symetry in ksz_ptp_msg_irq_{setup/free}()") Signed-off-by: Bastien Curutchet (Schneider Electric) Reviewed-by: Simon Horman Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20260309-ksz-ptp-irq-fix-v1-1-757b3b985955@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz_ptp.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index 4a2cc57a628f..8b98039320ad 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -1108,6 +1108,7 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n) const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops; struct ksz_irq *ptpirq = &port->ptpirq; struct ksz_ptp_irq *ptpmsg_irq; + int ret; ptpmsg_irq = &port->ptpmsg_irq[n]; ptpmsg_irq->num = irq_create_mapping(ptpirq->domain, n); @@ -1119,9 +1120,13 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n) strscpy(ptpmsg_irq->name, name[n]); - return request_threaded_irq(ptpmsg_irq->num, NULL, - ksz_ptp_msg_thread_fn, IRQF_ONESHOT, - ptpmsg_irq->name, ptpmsg_irq); + ret = request_threaded_irq(ptpmsg_irq->num, NULL, + ksz_ptp_msg_thread_fn, IRQF_ONESHOT, + ptpmsg_irq->name, ptpmsg_irq); + if (ret) + irq_dispose_mapping(ptpmsg_irq->num); + + return ret; } int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p) From 6c5a9baa15de240e747263aba435a0951da8d8d2 Mon Sep 17 00:00:00 2001 From: Mehul Rao Date: Tue, 10 Mar 2026 13:07:30 -0400 Subject: [PATCH 446/487] tipc: fix divide-by-zero in tipc_sk_filter_connect() A user can set conn_timeout to any value via setsockopt(TIPC_CONN_TIMEOUT), including values less than 4. When a SYN is rejected with TIPC_ERR_OVERLOAD and the retry path in tipc_sk_filter_connect() executes: delay %= (tsk->conn_timeout / 4); If conn_timeout is in the range [0, 3], the integer division yields 0, and the modulo operation triggers a divide-by-zero exception, causing a kernel oops/panic. Fix this by clamping conn_timeout to a minimum of 4 at the point of use in tipc_sk_filter_connect(). Oops: divide error: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 119 Comm: poc-F144 Not tainted 7.0.0-rc2+ RIP: 0010:tipc_sk_filter_rcv (net/tipc/socket.c:2236 net/tipc/socket.c:2362) Call Trace: tipc_sk_backlog_rcv (include/linux/instrumented.h:82 include/linux/atomic/atomic-instrumented.h:32 include/net/sock.h:2357 net/tipc/socket.c:2406) __release_sock (include/net/sock.h:1185 net/core/sock.c:3213) release_sock (net/core/sock.c:3797) tipc_connect (net/tipc/socket.c:2570) __sys_connect (include/linux/file.h:62 include/linux/file.h:83 net/socket.c:2098) Fixes: 6787927475e5 ("tipc: buffer overflow handling in listener socket") Cc: stable@vger.kernel.org Signed-off-by: Mehul Rao Reviewed-by: Tung Nguyen Link: https://patch.msgid.link/20260310170730.28841-1-mehulrao@gmail.com Signed-off-by: Jakub Kicinski --- net/tipc/socket.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 4c618c2b871d..9329919fb07f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2233,6 +2233,8 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb, if (skb_queue_empty(&sk->sk_write_queue)) break; get_random_bytes(&delay, 2); + if (tsk->conn_timeout < 4) + tsk->conn_timeout = 4; delay %= (tsk->conn_timeout / 4); delay = msecs_to_jiffies(delay + 100); sk_reset_timer(sk, &sk->sk_timer, jiffies + delay); From e8f0dc024ce55451ebd54bad975134ba802e4fcc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Wed, 11 Mar 2026 12:12:37 +0100 Subject: [PATCH 447/487] net: dsa: realtek: Fix LED group port bit for non-zero LED group MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The rtl8366rb_led_group_port_mask() function always returns LED port bit in LED group 0; the switch statement returns the same thing in all non-default cases. This means that the driver does not currently support configuring LEDs in non-zero LED groups. Fix this. Fixes: 32d617005475a71e ("net: dsa: realtek: add LED drivers for rtl8366rb") Signed-off-by: Marek Behún Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260311111237.29002-1-kabel@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/realtek/rtl8366rb-leds.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c index 99c890681ae6..509ffd3f8db5 100644 --- a/drivers/net/dsa/realtek/rtl8366rb-leds.c +++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c @@ -12,11 +12,11 @@ static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port) case 0: return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); case 1: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + return FIELD_PREP(RTL8366RB_LED_X_1_CTRL_MASK, BIT(port)); case 2: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + return FIELD_PREP(RTL8366RB_LED_2_X_CTRL_MASK, BIT(port)); case 3: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + return FIELD_PREP(RTL8366RB_LED_X_3_CTRL_MASK, BIT(port)); default: return 0; } From cbada1048847a348797aec63a1d8056621cbe653 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 10 Mar 2026 22:59:16 +0100 Subject: [PATCH 448/487] neighbour: restore protocol != 0 check in pneigh update Prior to commit dc2a27e524ac ("neighbour: Update pneigh_entry in pneigh_create()."), a pneigh's protocol was updated only when the value of the NDA_PROTOCOL attribute was non-0. While moving the code, that check was removed. This is a small change of user-visible behavior, and inconsistent with the (non-proxy) neighbour behavior. Fixes: dc2a27e524ac ("neighbour: Update pneigh_entry in pneigh_create().") Signed-off-by: Sabrina Dubroca Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/38c61de1bb032871a886aff9b9b52fe1cdd4cada.1772894876.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- net/core/neighbour.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a95cfe77f7f0..c56a4e7bf790 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -820,7 +820,8 @@ int pneigh_create(struct neigh_table *tbl, struct net *net, update: WRITE_ONCE(n->flags, flags); n->permanent = permanent; - WRITE_ONCE(n->protocol, protocol); + if (protocol) + WRITE_ONCE(n->protocol, protocol); out: mutex_unlock(&tbl->phash_lock); return err; From 68e76fc12df091b04ede5f6244385a35abae0a80 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 10 Mar 2026 22:59:17 +0100 Subject: [PATCH 449/487] selftests: rtnetlink: add neighbour update test Check that protocol and flags are updated correctly for neighbour and pneigh entries. Signed-off-by: Sabrina Dubroca Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/d28f72b5b4ff4c9ecbbbde06146a938dcc4c264a.1772894876.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/rtnetlink.sh | 55 ++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 248c2b91fe42..5a5ff88321d5 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -28,6 +28,7 @@ ALL_TESTS=" kci_test_fdb_get kci_test_fdb_del kci_test_neigh_get + kci_test_neigh_update kci_test_bridge_parent_id kci_test_address_proto kci_test_enslave_bonding @@ -1160,6 +1161,60 @@ kci_test_neigh_get() end_test "PASS: neigh get" } +kci_test_neigh_update() +{ + dstip=10.0.2.4 + dstmac=de:ad:be:ef:13:37 + local ret=0 + + for proxy in "" "proxy" ; do + # add a neighbour entry without any flags + run_cmd ip neigh add $proxy $dstip dev "$devdummy" lladdr $dstmac nud permanent + run_cmd_grep $dstip ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .*\(managed\|use\|router\|extern\)" ip neigh show $proxy + + # set the extern_learn flag, but no other + run_cmd ip neigh change $proxy $dstip dev "$devdummy" extern_learn + run_cmd_grep "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .* \(managed\|use\|router\)" ip neigh show $proxy + + # flags are reset when not provided + run_cmd ip neigh change $proxy $dstip dev "$devdummy" + run_cmd_grep $dstip ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy + + # add a protocol + run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol boot + run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy + + # protocol is retained when not provided + run_cmd ip neigh change $proxy $dstip dev "$devdummy" + run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy + + # change protocol + run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol static + run_cmd_grep "$dstip dev $devdummy .* proto static" ip neigh show $proxy + + # also check an extended flag for non-proxy neighs + if [ "$proxy" = "" ]; then + run_cmd ip neigh change $proxy $dstip dev "$devdummy" managed + run_cmd_grep "$dstip dev $devdummy managed" ip neigh show $proxy + + run_cmd ip neigh change $proxy $dstip dev "$devdummy" lladdr $dstmac + run_cmd_grep_fail "$dstip dev $devdummy managed" ip neigh show $proxy + fi + + run_cmd ip neigh del $proxy $dstip dev "$devdummy" + done + + if [ $ret -ne 0 ];then + end_test "FAIL: neigh update" + return 1 + fi + + end_test "PASS: neigh update" +} + kci_test_bridge_parent_id() { local ret=0 From 87c2302813abc55c46485711a678e3c312b00666 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Mon, 9 Mar 2026 10:24:43 -0700 Subject: [PATCH 450/487] net/mana: Null service_wq on setup error to prevent double destroy In mana_gd_setup() error path, set gc->service_wq to NULL after destroy_workqueue() to match the cleanup in mana_gd_cleanup(). This prevents a use-after-free if the workqueue pointer is checked after a failed setup. Fixes: f975a0955276 ("net: mana: Fix double destroy_workqueue on service rescan PCI path") Signed-off-by: Shiraz Saleem Signed-off-by: Konstantin Taranov Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260309172443.688392-1-kotaranov@linux.microsoft.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 37d2f108a839..786186c9a115 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1934,6 +1934,7 @@ static int mana_gd_setup(struct pci_dev *pdev) mana_gd_remove_irqs(pdev); free_workqueue: destroy_workqueue(gc->service_wq); + gc->service_wq = NULL; dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err); return err; } From 840c9d13cb1ca96683a5307ee8e221be163a2c1e Mon Sep 17 00:00:00 2001 From: Chintan Vankar Date: Tue, 10 Mar 2026 21:39:40 +0530 Subject: [PATCH 451/487] net: ethernet: ti: am65-cpsw-nuss: Fix rx_filter value for PTP support The "rx_filter" member of "hwtstamp_config" structure is an enum field and does not support bitwise OR combination of multiple filter values. It causes error while linuxptp application tries to match rx filter version. Fix this by storing the requested filter type in a new port field. Fixes: 97248adb5a3b ("net: ti: am65-cpsw: Update hw timestamping filter for PTPv1 RX packets") Signed-off-by: Chintan Vankar Link: https://patch.msgid.link/20260310160940.109822-1-c-vankar@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 16 +++++++++------- drivers/net/ethernet/ti/am65-cpsw-nuss.h | 2 +- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 967918050433..265ce5479915 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1351,7 +1351,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, ndev_priv = netdev_priv(ndev); am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark); skb_put(skb, pkt_len); - if (port->rx_ts_enabled) + if (port->rx_ts_filter) am65_cpts_rx_timestamp(common->cpts, skb); skb_mark_for_recycle(skb); skb->protocol = eth_type_trans(skb, ndev); @@ -1811,11 +1811,14 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, switch (cfg->rx_filter) { case HWTSTAMP_FILTER_NONE: - port->rx_ts_enabled = false; + port->rx_ts_filter = HWTSTAMP_FILTER_NONE; break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + break; case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: @@ -1825,8 +1828,8 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - port->rx_ts_enabled = true; - cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT | HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; break; case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_SOME: @@ -1863,7 +1866,7 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, ts_ctrl |= AM65_CPSW_TS_TX_ANX_ALL_EN | AM65_CPSW_PN_TS_CTL_TX_VLAN_LT1_EN; - if (port->rx_ts_enabled) + if (port->rx_ts_filter) ts_ctrl |= AM65_CPSW_TS_RX_ANX_ALL_EN | AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN; @@ -1888,8 +1891,7 @@ static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev, cfg->flags = 0; cfg->tx_type = port->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - cfg->rx_filter = port->rx_ts_enabled ? HWTSTAMP_FILTER_PTP_V2_EVENT | - HWTSTAMP_FILTER_PTP_V1_L4_EVENT : HWTSTAMP_FILTER_NONE; + cfg->rx_filter = port->rx_ts_filter; return 0; } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 917c37e4e89b..7750448e4746 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -52,7 +52,7 @@ struct am65_cpsw_port { bool disabled; struct am65_cpsw_slave_data slave; bool tx_ts_enabled; - bool rx_ts_enabled; + enum hwtstamp_rx_filters rx_ts_filter; struct am65_cpsw_qos qos; struct devlink_port devlink_port; struct bpf_prog *xdp_prog; From dc26ca99b835e21e76a58b1463b84adb0ca34f58 Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Tue, 10 Mar 2026 11:48:16 -0700 Subject: [PATCH 452/487] octeontx2-af: devlink: fix NIX RAS reporter recovery condition The NIX RAS health reporter recovery routine checks nix_af_rvu_int to decide whether to re-enable NIX_AF_RAS interrupts. This is the RVU interrupt status field and is unrelated to RAS events, so the recovery flow may incorrectly skip re-enabling NIX_AF_RAS interrupts. Check nix_af_rvu_ras instead before writing NIX_AF_RAS_ENA_W1S. Fixes: 5ed66306eab6 ("octeontx2-af: Add devlink health reporters for NIX") Signed-off-by: Alok Tiwari Link: https://patch.msgid.link/20260310184824.1183651-1-alok.a.tiwari@oracle.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index fb15c794efc9..7ef3da0f6a88 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -475,7 +475,7 @@ static int rvu_hw_nix_ras_recover(struct devlink_health_reporter *reporter, if (blkaddr < 0) return blkaddr; - if (nix_event_ctx->nix_af_rvu_int) + if (nix_event_ctx->nix_af_rvu_ras) rvu_write64(rvu, blkaddr, NIX_AF_RAS_ENA_W1S, ~0ULL); return 0; From 87f7dff3ec75b91def0024ebaaf732457f47a63b Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Tue, 10 Mar 2026 11:48:17 -0700 Subject: [PATCH 453/487] octeontx2-af: devlink: fix NIX RAS reporter to use RAS interrupt status The NIX RAS health report path uses nix_af_rvu_err when handling the NIX_AF_RVU_RAS case, so the report prints the ERR interrupt status rather than the RAS interrupt status. Use nix_af_rvu_ras for the NIX_AF_RVU_RAS report. Fixes: 5ed66306eab6 ("octeontx2-af: Add devlink health reporters for NIX") Signed-off-by: Alok Tiwari Link: https://patch.msgid.link/20260310184824.1183651-2-alok.a.tiwari@oracle.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 7ef3da0f6a88..a29f1ea04c7d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -327,10 +327,10 @@ static int rvu_nix_report_show(struct devlink_fmsg *fmsg, void *ctx, rvu_report_pair_end(fmsg); break; case NIX_AF_RVU_RAS: - intr_val = nix_event_context->nix_af_rvu_err; + intr_val = nix_event_context->nix_af_rvu_ras; rvu_report_pair_start(fmsg, "NIX_AF_RAS"); devlink_fmsg_u64_pair_put(fmsg, "\tNIX RAS Interrupt Reg ", - nix_event_context->nix_af_rvu_err); + nix_event_context->nix_af_rvu_ras); devlink_fmsg_string_put(fmsg, "\n\tPoison Data on:"); if (intr_val & BIT_ULL(34)) devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_INST_S"); From 0a8321dde01ffdbd9455a028194d57484def59eb Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Sun, 1 Mar 2026 00:17:59 +0530 Subject: [PATCH 454/487] powerpc/mem: Move CMA reservations to arch_mm_preinit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE memory model"), changed the initialization order of "pageblock_order" from... start_kernel() - setup_arch() - initmem_init() - sparse_init() - set_pageblock_order(); // this sets the pageblock_order - xxx_cma_reserve(); to... start_kernel() - setup_arch() - xxx_cma_reserve(); - mm_core_init_early() - free_area_init() - sparse_init() - set_pageblock_order() // this sets the pageblock_order. So this means, pageblock_order is not initialized before these cma reservation function calls, hence we are seeing CMA failures like... [ 0.000000] kvm_cma_reserve: reserving 3276 MiB for global area [ 0.000000] cma: pageblock_order not yet initialized. Called during early boot? [ 0.000000] cma: Failed to reserve 3276 MiB .... [ 0.000000][ T0] cma: pageblock_order not yet initialized. Called during early boot? [ 0.000000][ T0] cma: Failed to reserve 1024 MiB This patch moves these CMA reservations to arch_mm_preinit() which happens in mm_core_init() (which happens after pageblock_order is initialized), but before the memblock moves the free memory to buddy. Fixes: 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE memory model") Suggested-by: Mike Rapoport Reported-and-tested-by: Sourabh Jain Closes: https://lore.kernel.org/linuxppc-dev/4c338a29-d190-44f3-8874-6cfa0a031f0b@linux.ibm.com/ Signed-off-by: Ritesh Harjani (IBM) Tested-by: Dan Horák Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/6e532cf0db5be99afbe20eed699163d5e86cd71f.1772303986.git.ritesh.list@gmail.com --- arch/powerpc/kernel/setup-common.c | 10 ---------- arch/powerpc/mm/mem.c | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index cb5b73adc250..b1761909c23f 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include @@ -995,15 +994,6 @@ void __init setup_arch(char **cmdline_p) initmem_init(); - /* - * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and - * hugetlb. These must be called after initmem_init(), so that - * pageblock_order is initialised. - */ - fadump_cma_init(); - kdump_cma_reserve(); - kvm_cma_reserve(); - early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); if (ppc_md.setup_arch) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index a985fc96b953..b7982d0243d4 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -30,6 +30,10 @@ #include #include +#include +#include +#include + #include unsigned long long memory_limit __initdata; @@ -268,6 +272,16 @@ void __init paging_init(void) void __init arch_mm_preinit(void) { + + /* + * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM + * and hugetlb. These must be called after pageblock_order is + * initialised. + */ + fadump_cma_init(); + kdump_cma_reserve(); + kvm_cma_reserve(); + /* * book3s is limited to 16 page sizes due to encoding this in * a 4-bit field for slices. From e9bbfb4bfa86c6b5515b868d6982ac60505d7e39 Mon Sep 17 00:00:00 2001 From: Viktor Malik Date: Mon, 9 Mar 2026 15:40:45 +0100 Subject: [PATCH 455/487] powerpc, perf: Check that current->mm is alive before getting user callchain It may happen that mm is already released, which leads to kernel panic. This adds the NULL check for current->mm, similarly to commit 20afc60f892d ("x86, perf: Check that current->mm is alive before getting user callchain"). I was getting this panic when running a profiling BPF program (profile.py from bcc-tools): [26215.051935] Kernel attempted to read user page (588) - exploit attempt? (uid: 0) [26215.051950] BUG: Kernel NULL pointer dereference on read at 0x00000588 [26215.051952] Faulting instruction address: 0xc00000000020fac0 [26215.051957] Oops: Kernel access of bad area, sig: 11 [#1] [...] [26215.052049] Call Trace: [26215.052050] [c000000061da6d30] [c00000000020fc10] perf_callchain_user_64+0x2d0/0x490 (unreliable) [26215.052054] [c000000061da6dc0] [c00000000020f92c] perf_callchain_user+0x1c/0x30 [26215.052057] [c000000061da6de0] [c0000000005ab2a0] get_perf_callchain+0x100/0x360 [26215.052063] [c000000061da6e70] [c000000000573bc8] bpf_get_stackid+0x88/0xf0 [26215.052067] [c000000061da6ea0] [c008000000042258] bpf_prog_16d4ab9ab662f669_do_perf_event+0xf8/0x274 [...] In addition, move storing the top-level stack entry to generic perf_callchain_user to make sure the top-evel entry is always captured, even if current->mm is NULL. Fixes: 20002ded4d93 ("perf_counter: powerpc: Add callchain support") Signed-off-by: Viktor Malik Tested-by: Qiao Zhao Tested-by: Venkat Rao Bagalkote Reviewed-by: Saket Kumar Bhaskar [Maddy: fixed message to avoid checkpatch format style error] Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260309144045.169427-1-vmalik@redhat.com --- arch/powerpc/perf/callchain.c | 5 +++++ arch/powerpc/perf/callchain_32.c | 1 - arch/powerpc/perf/callchain_64.c | 1 - 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 26aa26482c9a..992cc5c98214 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -103,6 +103,11 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + perf_callchain_store(entry, perf_arch_instruction_pointer(regs)); + + if (!current->mm) + return; + if (!is_32bit_task()) perf_callchain_user_64(entry, regs); else diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index ddcc2d8aa64a..0de21c5d272c 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -142,7 +142,6 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry, next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, next_ip); while (entry->nr < entry->max_stack) { fp = (unsigned int __user *) (unsigned long) sp; diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 115d1c105e8a..30fb61c5f0cb 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -77,7 +77,6 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry, next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, next_ip); while (entry->nr < entry->max_stack) { fp = (unsigned long __user *) sp; From 6bc9c0a905228bea5c53ec195fe54f5f0233dccc Mon Sep 17 00:00:00 2001 From: Sayali Patil Date: Wed, 4 Mar 2026 17:52:00 +0530 Subject: [PATCH 456/487] powerpc: fix KUAP warning in VMX usercopy path On powerpc with PREEMPT_FULL or PREEMPT_LAZY and function tracing enabled, KUAP warnings can be triggered from the VMX usercopy path under memory stress workloads. KUAP requires that no subfunctions are called once userspace access has been enabled. The existing VMX copy implementation violates this requirement by invoking enter_vmx_usercopy() from the assembly path after userspace access has already been enabled. If preemption occurs in this window, the AMR state may not be preserved correctly, leading to unexpected userspace access state and resulting in KUAP warnings. Fix this by restructuring the VMX usercopy flow so that VMX selection and VMX state management are centralized in raw_copy_tofrom_user(), which is invoked by the raw_copy_{to,from,in}_user() wrappers. The new flow is: - raw_copy_{to,from,in}_user() calls raw_copy_tofrom_user() - raw_copy_tofrom_user() decides whether to use the VMX path based on size and CPU capability - Call enter_vmx_usercopy() before enabling userspace access - Enable userspace access as per the copy direction and perform the VMX copy - Disable userspace access as per the copy direction - Call exit_vmx_usercopy() - Fall back to the base copy routine if the VMX copy faults With this change, the VMX assembly routines no longer perform VMX state management or call helper functions; they only implement the copy operations. The previous feature-section based VMX selection inside __copy_tofrom_user_power7() is removed, and a dedicated __copy_tofrom_user_power7_vmx() entry point is introduced. This ensures correct KUAP ordering, avoids subfunction calls while KUAP is unlocked, and eliminates the warnings while preserving the VMX fast path. Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection") Reported-by: Shrikanth Hegde Closes: https://lore.kernel.org/all/20260109064917.777587-2-sshegde@linux.ibm.com/ Suggested-by: Christophe Leroy (CS GROUP) Reviewed-by: Christophe Leroy (CS GROUP) Co-developed-by: Aboorva Devarajan Signed-off-by: Aboorva Devarajan Signed-off-by: Sayali Patil Tested-by: Shrikanth Hegde Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260304122201.153049-1-sayalip@linux.ibm.com --- arch/powerpc/include/asm/uaccess.h | 69 ++++++++++++++++++++---------- arch/powerpc/lib/copyuser_64.S | 1 + arch/powerpc/lib/copyuser_power7.S | 45 +++++++------------ arch/powerpc/lib/vmx-helper.c | 2 + 4 files changed, 65 insertions(+), 52 deletions(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 570b3d91e2e4..17e63244e885 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -15,6 +15,9 @@ #define TASK_SIZE_MAX TASK_SIZE_USER64 #endif +/* Threshold above which VMX copy path is used */ +#define VMX_COPY_THRESHOLD 3328 + #include /* @@ -326,40 +329,62 @@ do { \ extern unsigned long __copy_tofrom_user(void __user *to, const void __user *from, unsigned long size); -#ifdef __powerpc64__ +unsigned long __copy_tofrom_user_base(void __user *to, + const void __user *from, unsigned long size); + +unsigned long __copy_tofrom_user_power7_vmx(void __user *to, + const void __user *from, unsigned long size); + +static __always_inline bool will_use_vmx(unsigned long n) +{ + return IS_ENABLED(CONFIG_ALTIVEC) && cpu_has_feature(CPU_FTR_VMX_COPY) && + n > VMX_COPY_THRESHOLD; +} + +static __always_inline unsigned long +raw_copy_tofrom_user(void __user *to, const void __user *from, + unsigned long n, unsigned long dir) +{ + unsigned long ret; + + if (will_use_vmx(n) && enter_vmx_usercopy()) { + allow_user_access(to, dir); + ret = __copy_tofrom_user_power7_vmx(to, from, n); + prevent_user_access(dir); + exit_vmx_usercopy(); + + if (unlikely(ret)) { + allow_user_access(to, dir); + ret = __copy_tofrom_user_base(to, from, n); + prevent_user_access(dir); + } + return ret; + } + + allow_user_access(to, dir); + ret = __copy_tofrom_user(to, from, n); + prevent_user_access(dir); + return ret; +} + +#ifdef CONFIG_PPC64 static inline unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { - unsigned long ret; - barrier_nospec(); - allow_user_access(to, KUAP_READ_WRITE); - ret = __copy_tofrom_user(to, from, n); - prevent_user_access(KUAP_READ_WRITE); - return ret; + return raw_copy_tofrom_user(to, from, n, KUAP_READ_WRITE); } -#endif /* __powerpc64__ */ +#endif /* CONFIG_PPC64 */ -static inline unsigned long raw_copy_from_user(void *to, - const void __user *from, unsigned long n) +static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) { - unsigned long ret; - - allow_user_access(NULL, KUAP_READ); - ret = __copy_tofrom_user((__force void __user *)to, from, n); - prevent_user_access(KUAP_READ); - return ret; + return raw_copy_tofrom_user((__force void __user *)to, from, n, KUAP_READ); } static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - unsigned long ret; - - allow_user_access(to, KUAP_WRITE); - ret = __copy_tofrom_user(to, (__force const void __user *)from, n); - prevent_user_access(KUAP_WRITE); - return ret; + return raw_copy_tofrom_user(to, (__force const void __user *)from, n, KUAP_WRITE); } unsigned long __arch_clear_user(void __user *addr, unsigned long size); diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S index 9af969d2cc0c..25a99108caff 100644 --- a/arch/powerpc/lib/copyuser_64.S +++ b/arch/powerpc/lib/copyuser_64.S @@ -562,3 +562,4 @@ exc; std r10,32(3) li r5,4096 b .Ldst_aligned EXPORT_SYMBOL(__copy_tofrom_user) +EXPORT_SYMBOL(__copy_tofrom_user_base) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 8474c682a178..17dbcfbae25f 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -5,13 +5,9 @@ * * Author: Anton Blanchard */ +#include #include -#ifndef SELFTEST_CASE -/* 0 == don't use VMX, 1 == use VMX */ -#define SELFTEST_CASE 0 -#endif - #ifdef __BIG_ENDIAN__ #define LVS(VRT,RA,RB) lvsl VRT,RA,RB #define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC @@ -47,10 +43,14 @@ ld r15,STK_REG(R15)(r1) ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl CFUNC(exit_vmx_usercopy) + ld r6,STK_REG(R31)(r1) /* original destination pointer */ + ld r5,STK_REG(R29)(r1) /* original number of bytes */ + subf r7,r6,r3 /* #bytes copied */ + subf r3,r7,r5 /* #bytes not copied in r3 */ ld r0,STACKFRAMESIZE+16(r1) mtlr r0 - b .Lexit + addi r1,r1,STACKFRAMESIZE + blr #endif /* CONFIG_ALTIVEC */ .Ldo_err2: @@ -74,7 +74,6 @@ _GLOBAL(__copy_tofrom_user_power7) cmpldi r5,16 - cmpldi cr1,r5,3328 std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) @@ -82,12 +81,6 @@ _GLOBAL(__copy_tofrom_user_power7) blt .Lshort_copy -#ifdef CONFIG_ALTIVEC -test_feature = SELFTEST_CASE -BEGIN_FTR_SECTION - bgt cr1,.Lvmx_copy -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif .Lnonvmx_copy: /* Get the source 8B aligned */ @@ -263,23 +256,14 @@ err1; stb r0,0(r3) 15: li r3,0 blr -.Lunwind_stack_nonvmx_copy: - addi r1,r1,STACKFRAMESIZE - b .Lnonvmx_copy - -.Lvmx_copy: #ifdef CONFIG_ALTIVEC +_GLOBAL(__copy_tofrom_user_power7_vmx) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl CFUNC(enter_vmx_usercopy) - cmpwi cr1,r3,0 - ld r0,STACKFRAMESIZE+16(r1) - ld r3,STK_REG(R31)(r1) - ld r4,STK_REG(R30)(r1) - ld r5,STK_REG(R29)(r1) - mtlr r0 + std r3,STK_REG(R31)(r1) + std r5,STK_REG(R29)(r1) /* * We prefetch both the source and destination using enhanced touch * instructions. We use a stream ID of 0 for the load side and @@ -300,8 +284,6 @@ err1; stb r0,0(r3) DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8) - beq cr1,.Lunwind_stack_nonvmx_copy - /* * If source and destination are not relatively aligned we use a * slower permute loop. @@ -478,7 +460,8 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b CFUNC(exit_vmx_usercopy) /* tail call optimise */ + li r3,0 + blr .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -681,5 +664,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b CFUNC(exit_vmx_usercopy) /* tail call optimise */ + li r3,0 + blr +EXPORT_SYMBOL(__copy_tofrom_user_power7_vmx) #endif /* CONFIG_ALTIVEC */ diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 54340912398f..554b248002b4 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -27,6 +27,7 @@ int enter_vmx_usercopy(void) return 1; } +EXPORT_SYMBOL(enter_vmx_usercopy); /* * This function must return 0 because we tail call optimise when calling @@ -49,6 +50,7 @@ int exit_vmx_usercopy(void) set_dec(1); return 0; } +EXPORT_SYMBOL(exit_vmx_usercopy); int enter_vmx_ops(void) { From 146c9ab38b48004b40735b6c1e1c2b5adf6436f9 Mon Sep 17 00:00:00 2001 From: Sayali Patil Date: Wed, 4 Mar 2026 17:52:01 +0530 Subject: [PATCH 457/487] powerpc/selftests/copyloops: extend selftest to exercise __copy_tofrom_user_power7_vmx The new PowerPC VMX fast path (__copy_tofrom_user_power7_vmx) is not exercised by existing copyloops selftests. This patch updates the selftest to exercise the VMX variant, ensuring the VMX copy path is validated. Changes include: - COPY_LOOP=test___copy_tofrom_user_power7_vmx with -D VMX_TEST is used in existing selftest build targets. - Inclusion of ../utils.c to provide get_auxv_entry() for hardware feature detection. - At runtime, the test skips execution if Altivec is not available. - Copy sizes above VMX_COPY_THRESHOLD are used to ensure the VMX path is taken. This enables validation of the VMX fast path without affecting systems that do not support Altivec. Signed-off-by: Sayali Patil Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260304122201.153049-2-sayalip@linux.ibm.com --- .../selftests/powerpc/copyloops/.gitignore | 4 ++-- .../testing/selftests/powerpc/copyloops/Makefile | 11 ++++++++--- tools/testing/selftests/powerpc/copyloops/stubs.S | 8 -------- .../selftests/powerpc/copyloops/validate.c | 15 ++++++++++++++- 4 files changed, 24 insertions(+), 14 deletions(-) diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore index 7283e8b07b75..80d4270a71ac 100644 --- a/tools/testing/selftests/powerpc/copyloops/.gitignore +++ b/tools/testing/selftests/powerpc/copyloops/.gitignore @@ -2,8 +2,8 @@ copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 -copyuser_p7_t0 -copyuser_p7_t1 +copyuser_p7 +copyuser_p7_vmx memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 42940f92d832..0c8efb0bddeb 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \ - copyuser_p7_t0 copyuser_p7_t1 \ + copyuser_p7 copyuser_p7_vmx \ memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \ memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \ copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 \ @@ -28,10 +28,15 @@ $(OUTPUT)/copyuser_64_t%: copyuser_64.S $(EXTRA_SOURCES) -D SELFTEST_CASE=$(subst copyuser_64_t,,$(notdir $@)) \ -o $@ $^ -$(OUTPUT)/copyuser_p7_t%: copyuser_power7.S $(EXTRA_SOURCES) +$(OUTPUT)/copyuser_p7: copyuser_power7.S $(EXTRA_SOURCES) $(CC) $(CPPFLAGS) $(CFLAGS) \ -D COPY_LOOP=test___copy_tofrom_user_power7 \ - -D SELFTEST_CASE=$(subst copyuser_p7_t,,$(notdir $@)) \ + -o $@ $^ + +$(OUTPUT)/copyuser_p7_vmx: copyuser_power7.S $(EXTRA_SOURCES) ../utils.c + $(CC) $(CPPFLAGS) $(CFLAGS) \ + -D COPY_LOOP=test___copy_tofrom_user_power7_vmx \ + -D VMX_TEST \ -o $@ $^ # Strictly speaking, we only need the memcpy_64 test cases for big-endian diff --git a/tools/testing/selftests/powerpc/copyloops/stubs.S b/tools/testing/selftests/powerpc/copyloops/stubs.S index ec8bcf2bf1c2..3a9cb8c9a3ee 100644 --- a/tools/testing/selftests/powerpc/copyloops/stubs.S +++ b/tools/testing/selftests/powerpc/copyloops/stubs.S @@ -1,13 +1,5 @@ #include -FUNC_START(enter_vmx_usercopy) - li r3,1 - blr - -FUNC_START(exit_vmx_usercopy) - li r3,0 - blr - FUNC_START(enter_vmx_ops) li r3,1 blr diff --git a/tools/testing/selftests/powerpc/copyloops/validate.c b/tools/testing/selftests/powerpc/copyloops/validate.c index 0f6873618552..fb822534fbe9 100644 --- a/tools/testing/selftests/powerpc/copyloops/validate.c +++ b/tools/testing/selftests/powerpc/copyloops/validate.c @@ -12,6 +12,10 @@ #define BUFLEN (MAX_LEN+MAX_OFFSET+2*MIN_REDZONE) #define POISON 0xa5 +#ifdef VMX_TEST +#define VMX_COPY_THRESHOLD 3328 +#endif + unsigned long COPY_LOOP(void *to, const void *from, unsigned long size); static void do_one(char *src, char *dst, unsigned long src_off, @@ -81,8 +85,12 @@ int test_copy_loop(void) /* Fill with sequential bytes */ for (i = 0; i < BUFLEN; i++) fill[i] = i & 0xff; - +#ifdef VMX_TEST + /* Force sizes above kernel VMX threshold (3328) */ + for (len = VMX_COPY_THRESHOLD + 1; len < MAX_LEN; len++) { +#else for (len = 1; len < MAX_LEN; len++) { +#endif for (src_off = 0; src_off < MAX_OFFSET; src_off++) { for (dst_off = 0; dst_off < MAX_OFFSET; dst_off++) { do_one(src, dst, src_off, dst_off, len, @@ -96,5 +104,10 @@ int test_copy_loop(void) int main(void) { +#ifdef VMX_TEST + /* Skip if Altivec not present */ + SKIP_IF_MSG(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC), "ALTIVEC not supported"); +#endif + return test_harness(test_copy_loop, str(COPY_LOOP)); } From fdbaa9d2b78e0da9e1aeb303bbdc3adfe6d8e749 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Wed, 11 Mar 2026 11:50:49 +0100 Subject: [PATCH 458/487] rust: pin-init: replace shadowed return token by `unsafe`-to-create token We use a unit struct `__InitOk` in the closure generated by the initializer macros as the return value. We shadow it by creating a struct with the same name again inside of the closure, preventing early returns of `Ok` in the initializer (before all fields have been initialized). In the face of Type Alias Impl Trait (TAIT) and the next trait solver, this solution no longer works [1]. The shadowed struct can be named through type inference. In addition, there is an RFC proposing to add the feature of path inference to Rust, which would similarly allow [2]. Thus remove the shadowed token and replace it with an `unsafe` to create token. The reason we initially used the shadowing solution was because an alternative solution used a builder pattern. Gary writes [3]: In the early builder-pattern based InitOk, having a single InitOk type for token is unsound because one can launder an InitOk token used for one place to another initializer. I used a branded lifetime solution, and then you figured out that using a shadowed type would work better because nobody could construct it at all. The laundering issue does not apply to the approach we ended up with today. With this change, the example by Tim Chirananthavat in [1] no longer compiles and results in this error: error: cannot construct `pin_init::__internal::InitOk` with struct literal syntax due to private fields --> src/main.rs:26:17 | 26 | InferredType {} | ^^^^^^^^^^^^ | = note: private field `0` that was not provided help: you might have meant to use the `new` associated function | 26 - InferredType {} 26 + InferredType::new() | Applying the suggestion of using the `::new()` function, results in another expected error: error[E0133]: call to unsafe function `pin_init::__internal::InitOk::new` is unsafe and requires unsafe block --> src/main.rs:26:17 | 26 | InferredType::new() | ^^^^^^^^^^^^^^^^^^^ call to unsafe function | = note: consult the function's documentation for information on how to avoid undefined behavior Reported-by: Tim Chirananthavat Link: https://github.com/rust-lang/rust/issues/153535 [1] Link: https://github.com/rust-lang/rfcs/pull/3444#issuecomment-4016145373 [2] Link: https://github.com/rust-lang/rust/issues/153535#issuecomment-4017620804 [3] Fixes: fc6c6baa1f40 ("rust: init: add initialization macros") Cc: stable@vger.kernel.org Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260311105056.1425041-1-lossin@kernel.org [ Added period as mentioned. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/pin-init/internal/src/init.rs | 22 +++++++--------------- rust/pin-init/src/__internal.rs | 28 ++++++++++++++++++++++++---- 2 files changed, 31 insertions(+), 19 deletions(-) diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs index 738f62c8105c..2fe918f4d82a 100644 --- a/rust/pin-init/internal/src/init.rs +++ b/rust/pin-init/internal/src/init.rs @@ -148,11 +148,6 @@ fn assert_zeroable(_: *mut T) let init_fields = init_fields(&fields, pinned, &data, &slot); let field_check = make_field_check(&fields, init_kind, &path); Ok(quote! {{ - // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return - // type and shadow it later when we insert the arbitrary user code. That way there will be - // no possibility of returning without `unsafe`. - struct __InitOk; - // Get the data about fields from the supplied type. // SAFETY: TODO let #data = unsafe { @@ -162,18 +157,15 @@ fn assert_zeroable(_: *mut T) #path::#get_data() }; // Ensure that `#data` really is of type `#data` and help with type inference: - let init = ::pin_init::__internal::#data_trait::make_closure::<_, __InitOk, #error>( + let init = ::pin_init::__internal::#data_trait::make_closure::<_, #error>( #data, move |slot| { - { - // Shadow the structure so it cannot be used to return early. - struct __InitOk; - #zeroable_check - #this - #init_fields - #field_check - } - Ok(__InitOk) + #zeroable_check + #this + #init_fields + #field_check + // SAFETY: we are the `init!` macro that is allowed to call this. + Ok(unsafe { ::pin_init::__internal::InitOk::new() }) } ); let init = move |slot| -> ::core::result::Result<(), #error> { diff --git a/rust/pin-init/src/__internal.rs b/rust/pin-init/src/__internal.rs index 90f18e9a2912..90adbdc1893b 100644 --- a/rust/pin-init/src/__internal.rs +++ b/rust/pin-init/src/__internal.rs @@ -46,6 +46,24 @@ unsafe fn __pinned_init(self, slot: *mut T) -> Result<(), E> { } } +/// Token type to signify successful initialization. +/// +/// Can only be constructed via the unsafe [`Self::new`] function. The initializer macros use this +/// token type to prevent returning `Ok` from an initializer without initializing all fields. +pub struct InitOk(()); + +impl InitOk { + /// Creates a new token. + /// + /// # Safety + /// + /// This function may only be called from the `init!` macro in `../internal/src/init.rs`. + #[inline(always)] + pub unsafe fn new() -> Self { + Self(()) + } +} + /// This trait is only implemented via the `#[pin_data]` proc-macro. It is used to facilitate /// the pin projections within the initializers. /// @@ -68,9 +86,10 @@ pub unsafe trait PinData: Copy { type Datee: ?Sized + HasPinData; /// Type inference helper function. - fn make_closure(self, f: F) -> F + #[inline(always)] + fn make_closure(self, f: F) -> F where - F: FnOnce(*mut Self::Datee) -> Result, + F: FnOnce(*mut Self::Datee) -> Result, { f } @@ -98,9 +117,10 @@ pub unsafe trait InitData: Copy { type Datee: ?Sized + HasInitData; /// Type inference helper function. - fn make_closure(self, f: F) -> F + #[inline(always)] + fn make_closure(self, f: F) -> F where - F: FnOnce(*mut Self::Datee) -> Result, + F: FnOnce(*mut Self::Datee) -> Result, { f } From 487f9b3dc6e507a982f1b984aa6bfbd9dc4b0567 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 11 Mar 2026 21:19:34 -0700 Subject: [PATCH 459/487] rust: cpufreq: suppress clippy::double_parens in Policy doctest The kernel fmt! proc macro wraps each format argument as &(arg). Passing a tuple such as (a, b) produces &((a, b)) after expansion. Clippy flags that as double_parens, but it is a false positive fixed in Clippy 1.92 [1] [2]. Suppress the warning on the affected doctest function with a reason attribute so it can be removed once the minimum toolchain moves past 1.92. [ We may end up deciding to support per-version Clippy lints, in which case we will need [3]. In the future, if [4] gets fixed, we may be able to use `Delimiter::None` as Gary suggested in [5]. Link: https://lore.kernel.org/rust-for-linux/20260307170929.153892-1-ojeda@kernel.org/ [3] Link: https://github.com/rust-lang/rust/issues/67062 [4] Link: https://lore.kernel.org/rust-for-linux/DGUA5GY2DGYN.3PG0FKLG7GFN1@garyguo.net/ [5] - Miguel ] Link: https://github.com/rust-lang/rust-clippy/issues/15852 [1] Link: https://github.com/rust-lang/rust-clippy/pull/15939 [2] Suggested-by: Gary Guo Signed-off-by: John Hubbard Acked-by: Viresh Kumar Link: https://patch.msgid.link/20260312041934.362840-2-jhubbard@nvidia.com [ Reworded to replace GitHub-like short link with full URLs in Link tags. Reworded reason string to match the style of a couple others we have elsewhere. - Miguel ] Signed-off-by: Miguel Ojeda --- rust/kernel/cpufreq.rs | 1 + 1 file changed, 1 insertion(+) diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs index 76faa1ac8501..f5adee48d40c 100644 --- a/rust/kernel/cpufreq.rs +++ b/rust/kernel/cpufreq.rs @@ -401,6 +401,7 @@ pub fn to_table(mut self) -> Result { /// ``` /// use kernel::cpufreq::{DEFAULT_TRANSITION_LATENCY_NS, Policy}; /// +/// #[allow(clippy::double_parens, reason = "False positive before 1.92.0")] /// fn update_policy(policy: &mut Policy) { /// policy /// .set_dvfs_possible_from_any_cpu(true) From 592c61f3bfceaa29f8275696bd67c3dfad7ef72e Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 12 Mar 2026 12:10:14 +0100 Subject: [PATCH 460/487] rust: kbuild: allow `unused_features` Starting with the upcoming Rust 1.96.0 (to be released 2026-05-28), `rustc` introduces the new lint `unused_features` [1], which warns [2]: warning: feature `used_with_arg` is declared but not used --> :1:93 | 1 | #![feature(asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg)] | ^^^^^^^^^^^^^ | = note: `#[warn(unused_features)]` (part of `#[warn(unused)]`) on by default The original goal of using `-Zcrate-attr` automatically was that there is a consistent set of features enabled and managed globally for all Rust kernel code (modulo exceptions like the `rust/` crated). While we could require crates to enable features manually (even if we still keep the `-Zallow-features=` list, i.e. removing the `-Zcrate-attr` list), it is not really worth making all developers worry about it just for a new lint. The features are expected to eventually become stable anyway (most already did), and thus having to remove features in every file that may use them is not worth it either. Thus just allow the new lint globally. The lint actually existed for a long time, which is why `rustc` does not complain about an unknown lint in the stable versions we support, but it was "disabled" years ago [3], and now it was made to work again. For extra context, the new implementation of the lint has already been improved to avoid linting about features that became stable thanks to Benno's report and the ensuing discussion [4] [5], but while that helps, it is still the case that we may have features enabled that are not used for one reason or another in a particular crate. Cc: stable@vger.kernel.org # Needed in 6.12.y and later (Rust is pinned in older LTSs). Link: https://github.com/rust-lang/rust/pull/152164 [1] Link: https://github.com/Rust-for-Linux/pin-init/pull/114 [2] Link: https://github.com/rust-lang/rust/issues/44232 [3] Link: https://github.com/rust-lang/rust/issues/153523 [4] Link: https://github.com/rust-lang/rust/pull/153610 [5] Reviewed-by: Benno Lossin Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260312111014.74198-1-ojeda@kernel.org Signed-off-by: Miguel Ojeda --- Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/Makefile b/Makefile index 73a39592f112..587345f16c97 100644 --- a/Makefile +++ b/Makefile @@ -476,6 +476,7 @@ KBUILD_USERLDFLAGS := $(USERLDFLAGS) export rust_common_flags := --edition=2021 \ -Zbinary_dep_depinfo=y \ -Astable_features \ + -Aunused_features \ -Dnon_ascii_idents \ -Dunsafe_op_in_unsafe_fn \ -Wmissing_docs \ From c2c185be5c85d37215397c8e8781abf0a69bec1f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 12 Mar 2026 08:59:25 -0600 Subject: [PATCH 461/487] io_uring/kbuf: check if target buffer list is still legacy on recycle There's a gap between when the buffer was grabbed and when it potentially gets recycled, where if the list is empty, someone could've upgraded it to a ring provided type. This can happen if the request is forced via io-wq. The legacy recycling is missing checking if the buffer_list still exists, and if it's of the correct type. Add those checks. Cc: stable@vger.kernel.org Fixes: c7fb19428d67 ("io_uring: add support for ring mapped supplied buffers") Reported-by: Keenan Dong Signed-off-by: Jens Axboe --- io_uring/kbuf.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index dae5b4ab3819..e7f444953dfb 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -111,9 +111,18 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags) buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); - list_add(&buf->list, &bl->buf_list); - bl->nbufs++; + /* + * If the buffer list was upgraded to a ring-based one, or removed, + * while the request was in-flight in io-wq, drop it. + */ + if (bl && !(bl->flags & IOBL_BUF_RING)) { + list_add(&buf->list, &bl->buf_list); + bl->nbufs++; + } else { + kfree(buf); + } req->flags &= ~REQ_F_BUFFER_SELECTED; + req->kbuf = NULL; io_ring_submit_unlock(ctx, issue_flags); return true; From c38b8f5f791ecce13ab77e2257f8fd2444ba80f6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2026 04:39:08 +0000 Subject: [PATCH 462/487] net: prevent NULL deref in ip[6]tunnel_xmit() Blamed commit missed that both functions can be called with dev == NULL. Also add unlikely() hints for these conditions that only fuzzers can hit. Fixes: 6f1a9140ecda ("net: add xmit recursion limit to tunnel xmit functions") Signed-off-by: Eric Dumazet CC: Weiming Shi Link: https://patch.msgid.link/20260312043908.2790803-1-edumazet@google.com Signed-off-by: Paolo Abeni --- include/net/ip6_tunnel.h | 10 ++++++---- net/ipv4/ip_tunnel_core.c | 10 ++++++---- 2 files changed, 12 insertions(+), 8 deletions(-) diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 1253cbb4b0a4..359b595f1df9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -156,10 +156,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; - if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) { - net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", - dev->name); - DEV_STATS_INC(dev, tx_errors); + if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) { + if (dev) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + } kfree_skb(skb); return; } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index b1b6bf949f65..5683c328990f 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -58,10 +58,12 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, struct iphdr *iph; int err; - if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) { - net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", - dev->name); - DEV_STATS_INC(dev, tx_errors); + if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) { + if (dev) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + } ip_rt_put(rt); kfree_skb(skb); return; From d2ea4ff1ce50787a98a3900b3fb1636f3620b7cf Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 10 Mar 2026 14:18:41 -0700 Subject: [PATCH 463/487] KVM: selftests: Verify SEV+ guests can read and write EFER, CR0, CR4, and CR8 Add "do no harm" testing of EFER, CR0, CR4, and CR8 for SEV+ guests to verify that the guest can read and write the registers, without hitting e.g. a #VC on SEV-ES guests due to KVM incorrectly trying to intercept a register. Signed-off-by: Sean Christopherson Message-ID: <20260310211841.2552361-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- .../selftests/kvm/include/x86/processor.h | 23 ++++++++++++++ .../selftests/kvm/x86/sev_smoke_test.c | 30 +++++++++++++++++++ 2 files changed, 53 insertions(+) diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 4ebae4269e68..469a22122157 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -557,6 +557,11 @@ static inline uint64_t get_cr0(void) return cr0; } +static inline void set_cr0(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory"); +} + static inline uint64_t get_cr3(void) { uint64_t cr3; @@ -566,6 +571,11 @@ static inline uint64_t get_cr3(void) return cr3; } +static inline void set_cr3(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory"); +} + static inline uint64_t get_cr4(void) { uint64_t cr4; @@ -580,6 +590,19 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline uint64_t get_cr8(void) +{ + uint64_t cr8; + + __asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8)); + return cr8; +} + +static inline void set_cr8(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory"); +} + static inline void set_idt(const struct desc_ptr *idt_desc) { __asm__ __volatile__("lidt %0"::"m"(*idt_desc)); diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index 86ad1c7d068f..8bd37a476f15 100644 --- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -13,6 +13,30 @@ #include "linux/psp-sev.h" #include "sev.h" +static void guest_sev_test_msr(uint32_t msr) +{ + uint64_t val = rdmsr(msr); + + wrmsr(msr, val); + GUEST_ASSERT(val == rdmsr(msr)); +} + +#define guest_sev_test_reg(reg) \ +do { \ + uint64_t val = get_##reg(); \ + \ + set_##reg(val); \ + GUEST_ASSERT(val == get_##reg()); \ +} while (0) + +static void guest_sev_test_regs(void) +{ + guest_sev_test_msr(MSR_EFER); + guest_sev_test_reg(cr0); + guest_sev_test_reg(cr3); + guest_sev_test_reg(cr4); + guest_sev_test_reg(cr8); +} #define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM) @@ -24,6 +48,8 @@ static void guest_snp_code(void) GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED); GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_SNP_ENABLED); + guest_sev_test_regs(); + wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ); vmgexit(); } @@ -34,6 +60,8 @@ static void guest_sev_es_code(void) GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED); + guest_sev_test_regs(); + /* * TODO: Add GHCB and ucall support for SEV-ES guests. For now, simply * force "termination" to signal "done" via the GHCB MSR protocol. @@ -47,6 +75,8 @@ static void guest_sev_code(void) GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV)); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + guest_sev_test_regs(); + GUEST_DONE(); } From 39ebc8d7f561e1b64eca87353ef9b18e2825e591 Mon Sep 17 00:00:00 2001 From: Josh Law Date: Thu, 12 Mar 2026 19:11:41 +0000 Subject: [PATCH 464/487] lib/bootconfig: fix off-by-one in xbc_verify_tree() unclosed brace error __xbc_open_brace() pushes entries with post-increment (open_brace[brace_index++]), so brace_index always points one past the last valid entry. xbc_verify_tree() reads open_brace[brace_index] to report which brace is unclosed, but this is one past the last pushed entry and contains stale/zero data, causing the error message to reference the wrong node. Use open_brace[brace_index - 1] to correctly identify the unclosed brace. brace_index is known to be > 0 here since we are inside the if (brace_index) guard. Link: https://lore.kernel.org/all/20260312191143.28719-2-objecting@objecting.org/ Fixes: ead1e19ad905 ("lib/bootconfig: Fix a bug of breaking existing tree nodes") Cc: stable@vger.kernel.org Signed-off-by: Josh Law Reviewed-by: Steven Rostedt (Google) Signed-off-by: Masami Hiramatsu (Google) --- lib/bootconfig.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 449369a60846..ce25714351d5 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -802,7 +802,7 @@ static int __init xbc_verify_tree(void) /* Brace closing */ if (brace_index) { - n = &xbc_nodes[open_brace[brace_index]]; + n = &xbc_nodes[open_brace[brace_index - 1]]; return xbc_parse_error("Brace is not closed", xbc_node_get_data(n)); } From 82f73ef9c41e0623e0a8bdce4fa44a7237709f0c Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Tue, 10 Mar 2026 13:51:24 +0530 Subject: [PATCH 465/487] powerpc/iommu: fix lockdep warning during PCI enumeration Commit a75b2be249d6 ("iommu: Add iommu_driver_get_domain_for_dev() helper") introduced iommu_driver_get_domain_for_dev() for driver code paths that hold iommu_group->mutex while attaching a device to an IOMMU domain. The same commit also added a lockdep assertion in iommu_get_domain_for_dev() to ensure that callers do not hold iommu_group->mutex when invoking it. On powerpc platforms, when PCI device ownership is switched from BLOCKED to the PLATFORM domain, the attach callback spapr_tce_platform_iommu_attach_dev() still calls iommu_get_domain_for_dev(). This happens while iommu_group->mutex is held during domain switching, which triggers the lockdep warning below during PCI enumeration: WARNING: drivers/iommu/iommu.c:2252 at iommu_get_domain_for_dev+0x38/0x80, CPU#2: swapper/0/1 Modules linked in: CPU: 2 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc2+ #35 PREEMPT Hardware name: IBM,9105-22A Power11 (architected) 0x820200 0xf000007 of:IBM,FW1120.00 (RB1120_115) hv:phyp pSeries NIP: c000000000c244c4 LR: c00000000005b5a4 CTR: c00000000005b578 REGS: c00000000a7bf280 TRAP: 0700 Not tainted (7.0.0-rc2+) MSR: 8000000002029033 CR: 22004422 XER: 0000000a CFAR: c000000000c24508 IRQMASK: 0 GPR00: c00000000005b5a4 c00000000a7bf520 c000000001dc8100 0000000000000001 GPR04: c00000000f972f10 0000000000000000 0000000000000000 0000000000000001 GPR08: 0000001ffbc60000 0000000000000001 0000000000000000 0000000000000000 GPR12: c00000000005b578 c000001fffffe480 c000000000011618 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: ffffffffffffefff 0000000000000000 c000000002d30eb0 0000000000000001 GPR24: c0000000017881f8 0000000000000000 0000000000000001 c00000000f972e00 GPR28: c00000000bbba0d0 0000000000000000 c00000000bbba0d0 c00000000f972e00 NIP [c000000000c244c4] iommu_get_domain_for_dev+0x38/0x80 LR [c00000000005b5a4] spapr_tce_platform_iommu_attach_dev+0x2c/0x98 Call Trace: iommu_get_domain_for_dev+0x68/0x80 (unreliable) spapr_tce_platform_iommu_attach_dev+0x2c/0x98 __iommu_attach_device+0x44/0x220 __iommu_device_set_domain+0xf4/0x194 __iommu_group_set_domain_internal+0xec/0x228 iommu_setup_default_domain+0x5f4/0x6a4 __iommu_probe_device+0x674/0x724 iommu_probe_device+0x50/0xb4 iommu_add_device+0x48/0x198 pci_dma_dev_setup_pSeriesLP+0x198/0x4f0 pcibios_bus_add_device+0x80/0x464 pci_bus_add_device+0x40/0x100 pci_bus_add_devices+0x54/0xb0 pcibios_init+0xd8/0x140 do_one_initcall+0x8c/0x598 kernel_init_freeable+0x3ec/0x850 kernel_init+0x34/0x270 ret_from_kernel_user_thread+0x14/0x1c Fix this by using iommu_driver_get_domain_for_dev() instead of iommu_get_domain_for_dev() in spapr_tce_platform_iommu_attach_dev(), which is the appropriate helper for callers holding the group mutex. Cc: stable@vger.kernel.org Fixes: a75b2be249d6 ("iommu: Add iommu_driver_get_domain_for_dev() helper") Closes: https://patchwork.ozlabs.org/project/linuxppc-dev/patch/d5c834ff-4c95-44dd-8bef-57242d63aeee@linux.ibm.com/ Signed-off-by: Nilay Shroff Reviewed-by: Nicolin Chen Tested-by: Venkat Rao Bagalkote [Maddy: Added Closes, tested and reviewed by tags] Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260310082129.3630996-1-nilay@linux.ibm.com --- arch/powerpc/kernel/iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0ce71310b7d9..d122e8447831 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1159,7 +1159,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, struct device *dev, struct iommu_domain *old) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + struct iommu_domain *domain = iommu_driver_get_domain_for_dev(dev); struct iommu_table_group *table_group; struct iommu_group *grp; From 560f763baa0f2c9a44da4294c06af071405ac46f Mon Sep 17 00:00:00 2001 From: Josh Law Date: Thu, 12 Mar 2026 19:11:42 +0000 Subject: [PATCH 466/487] lib/bootconfig: check bounds before writing in __xbc_open_brace() The bounds check for brace_index happens after the array write. While the current call pattern prevents an actual out-of-bounds access (the previous call would have returned an error), the write-before-check pattern is fragile and would become a real out-of-bounds write if the error return were ever not propagated. Move the bounds check before the array write so the function is self-contained and safe regardless of caller behavior. Link: https://lore.kernel.org/all/20260312191143.28719-3-objecting@objecting.org/ Fixes: ead1e19ad905 ("lib/bootconfig: Fix a bug of breaking existing tree nodes") Cc: stable@vger.kernel.org Signed-off-by: Josh Law Signed-off-by: Masami Hiramatsu (Google) --- lib/bootconfig.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/bootconfig.c b/lib/bootconfig.c index ce25714351d5..9c3d59fb96ed 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -532,9 +532,9 @@ static char *skip_spaces_until_newline(char *p) static int __init __xbc_open_brace(char *p) { /* Push the last key as open brace */ - open_brace[brace_index++] = xbc_node_index(last_parent); if (brace_index >= XBC_DEPTH_MAX) return xbc_parse_error("Exceed max depth of braces", p); + open_brace[brace_index++] = xbc_node_index(last_parent); return 0; } From 1120a36bb1e9b9e22de75ecb4ef0b998f73a97f1 Mon Sep 17 00:00:00 2001 From: Josh Law Date: Thu, 12 Mar 2026 19:11:43 +0000 Subject: [PATCH 467/487] lib/bootconfig: fix snprintf truncation check in xbc_node_compose_key_after() snprintf() returns the number of characters that would have been written excluding the NUL terminator. Output is truncated when the return value is >= the buffer size, not just > the buffer size. When ret == size, the current code takes the non-truncated path, advancing buf by ret and reducing size to 0. This is wrong because the output was actually truncated (the last character was replaced by NUL). Fix by using >= so the truncation path is taken correctly. Link: https://lore.kernel.org/all/20260312191143.28719-4-objecting@objecting.org/ Fixes: 76db5a27a827 ("bootconfig: Add Extra Boot Config support") Cc: stable@vger.kernel.org Signed-off-by: Josh Law Signed-off-by: Masami Hiramatsu (Google) --- lib/bootconfig.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 9c3d59fb96ed..2da049216fe0 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -316,7 +316,7 @@ int __init xbc_node_compose_key_after(struct xbc_node *root, depth ? "." : ""); if (ret < 0) return ret; - if (ret > size) { + if (ret >= size) { size = 0; } else { size -= ret; From e2715ea5fb352cd43fce437b91aa0fd50aaaf384 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 13 Mar 2026 13:18:55 +0900 Subject: [PATCH 468/487] bootconfig: Add bootconfig tests about braces Add more bootconfig tests for checking the error message of non closing brace and max number of nested braces. Link: https://lore.kernel.org/all/177337553551.416919.11217619471547711262.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) --- .../samples/bad-non-closed-brace.bconf | 4 ++++ .../samples/bad-over-max-brace.bconf | 19 +++++++++++++++++++ .../samples/exp-good-nested-brace.bconf | 1 + .../samples/good-nested-brace.bconf | 18 ++++++++++++++++++ tools/bootconfig/test-bootconfig.sh | 9 +++++++++ 5 files changed, 51 insertions(+) create mode 100644 tools/bootconfig/samples/bad-non-closed-brace.bconf create mode 100644 tools/bootconfig/samples/bad-over-max-brace.bconf create mode 100644 tools/bootconfig/samples/exp-good-nested-brace.bconf create mode 100644 tools/bootconfig/samples/good-nested-brace.bconf diff --git a/tools/bootconfig/samples/bad-non-closed-brace.bconf b/tools/bootconfig/samples/bad-non-closed-brace.bconf new file mode 100644 index 000000000000..6ed9f3363dde --- /dev/null +++ b/tools/bootconfig/samples/bad-non-closed-brace.bconf @@ -0,0 +1,4 @@ +foo { + bar { + buz + } diff --git a/tools/bootconfig/samples/bad-over-max-brace.bconf b/tools/bootconfig/samples/bad-over-max-brace.bconf new file mode 100644 index 000000000000..74b5dc9e21dc --- /dev/null +++ b/tools/bootconfig/samples/bad-over-max-brace.bconf @@ -0,0 +1,19 @@ +key1 { +key2 { +key3 { +key4 { +key5 { +key6 { +key7 { +key8 { +key9 { +key10 { +key11 { +key12 { +key13 { +key14 { +key15 { +key16 { +key17 { +}}}}}}}}}}}}}}}}} + diff --git a/tools/bootconfig/samples/exp-good-nested-brace.bconf b/tools/bootconfig/samples/exp-good-nested-brace.bconf new file mode 100644 index 000000000000..19e0f51b4553 --- /dev/null +++ b/tools/bootconfig/samples/exp-good-nested-brace.bconf @@ -0,0 +1 @@ +key1.key2.key3.key4.key5.key6.key7.key8.key9.key10.key11.key12.key13.key14.key15.key16; diff --git a/tools/bootconfig/samples/good-nested-brace.bconf b/tools/bootconfig/samples/good-nested-brace.bconf new file mode 100644 index 000000000000..980d094f296e --- /dev/null +++ b/tools/bootconfig/samples/good-nested-brace.bconf @@ -0,0 +1,18 @@ +key1 { +key2 { +key3 { +key4 { +key5 { +key6 { +key7 { +key8 { +key9 { +key10 { +key11 { +key12 { +key13 { +key14 { +key15 { +key16 { +}}}}}}}}}}}}}}}} + diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index be9bd18b1d56..fc69f815ce4a 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -171,6 +171,15 @@ $BOOTCONF $INITRD > $OUTFILE xfail grep -q 'val[[:space:]]' $OUTFILE xpass grep -q 'val2[[:space:]]' $OUTFILE +echo "Showing correct line:column of no closing brace" +cat > $TEMPCONF << EOF +foo { +bar { +} +EOF +$BOOTCONF -a $TEMPCONF $INITRD 2> $OUTFILE +xpass grep -q "1:1" $OUTFILE + echo "=== expected failure cases ===" for i in samples/bad-* ; do xfail $BOOTCONF -a $i $INITRD From e113f0b46d19626ec15388bcb91432c9a4fd6261 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 13 Mar 2026 23:14:14 +0900 Subject: [PATCH 469/487] kprobes: avoid crash when rmmod/insmod after ftrace killed After we hit ftrace is killed by some errors, the kernel crash if we remove modules in which kprobe probes. BUG: unable to handle page fault for address: fffffbfff805000d PGD 817fcc067 P4D 817fcc067 PUD 817fc8067 PMD 101555067 PTE 0 Oops: Oops: 0000 [#1] SMP KASAN PTI CPU: 4 UID: 0 PID: 2012 Comm: rmmod Tainted: G W OE Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE RIP: 0010:kprobes_module_callback+0x89/0x790 RSP: 0018:ffff88812e157d30 EFLAGS: 00010a02 RAX: 1ffffffff805000d RBX: dffffc0000000000 RCX: ffffffff86a8de90 RDX: ffffed1025c2af9b RSI: 0000000000000008 RDI: ffffffffc0280068 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed1025c2af9a R10: ffff88812e157cd7 R11: 205d323130325420 R12: 0000000000000002 R13: ffffffffc0290488 R14: 0000000000000002 R15: ffffffffc0280040 FS: 00007fbc450dd740(0000) GS:ffff888420331000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff805000d CR3: 000000010f624000 CR4: 00000000000006f0 Call Trace: notifier_call_chain+0xc6/0x280 blocking_notifier_call_chain+0x60/0x90 __do_sys_delete_module.constprop.0+0x32a/0x4e0 do_syscall_64+0x5d/0xfa0 entry_SYSCALL_64_after_hwframe+0x76/0x7e This is because the kprobe on ftrace does not correctly handles the kprobe_ftrace_disabled flag set by ftrace_kill(). To prevent this error, check kprobe_ftrace_disabled in __disarm_kprobe_ftrace() and skip all ftrace related operations. Link: https://lore.kernel.org/all/176473947565.1727781.13110060700668331950.stgit@mhiramat.tok.corp.google.com/ Reported-by: Ye Bin Closes: https://lore.kernel.org/all/20251125020536.2484381-1-yebin@huaweicloud.com/ Fixes: ae6aa16fdc16 ("kprobes: introduce ftrace based optimization") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Acked-by: Steven Rostedt (Google) --- kernel/kprobes.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ab25b4aa9095..025af57ad3ed 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1178,6 +1178,10 @@ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int ret; lockdep_assert_held(&kprobe_mutex); + if (unlikely(kprobe_ftrace_disabled)) { + /* Now ftrace is disabled forever, disarm is already done. */ + return 0; + } if (*cnt == 1) { ret = unregister_ftrace_function(ops); From 5ef268cb7a0aac55521fd9881f1939fa94a8988e Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 13 Mar 2026 23:04:11 +0900 Subject: [PATCH 470/487] kprobes: Remove unneeded warnings from __arm_kprobe_ftrace() Remove unneeded warnings for handled errors from __arm_kprobe_ftrace() because all caller handled the error correctly. Link: https://lore.kernel.org/all/177261531182.1312989.8737778408503961141.stgit@mhiramat.tok.corp.google.com/ Reported-by: Zw Tang Closes: https://lore.kernel.org/all/CAPHJ_V+J6YDb_wX2nhXU6kh466Dt_nyDSas-1i_Y8s7tqY-Mzw@mail.gmail.com/ Fixes: 9c89bb8e3272 ("kprobes: treewide: Cleanup the error messages for kprobes") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/kprobes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 025af57ad3ed..bfc89083daa9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1144,12 +1144,12 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, lockdep_assert_held(&kprobe_mutex); ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); - if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret)) + if (ret < 0) return ret; if (*cnt == 0) { ret = register_ftrace_function(ops); - if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) { + if (ret < 0) { /* * At this point, sinec ops is not registered, we should be sefe from * registering empty filter. From d0d9b1f4f5391e6a00cee81d73ed2e8f98446d5f Mon Sep 17 00:00:00 2001 From: Vyacheslav Vahnenko Date: Fri, 13 Mar 2026 15:36:38 +0300 Subject: [PATCH 471/487] USB: ezcap401 needs USB_QUIRK_NO_BOS to function on 10gbs usb speed Add USB_QUIRK_NO_BOS for ezcap401 capture card, without it dmesg will show "unable to get BOS descriptor or descriptor too short" and "unable to read config index 0 descriptor/start: -71" errors and device will not able to work at full speed at 10gbs Signed-off-by: Vyacheslav Vahnenko Cc: stable Link: https://patch.msgid.link/20260313123638.20481-1-vahnenko2003@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index e3f402e0c351..5523a8e29021 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -589,6 +589,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Alcor Link AK9563 SC Reader used in 2022 Lenovo ThinkPads */ { USB_DEVICE(0x2ce3, 0x9563), .driver_info = USB_QUIRK_NO_LPM }, + /* ezcap401 - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x32ed, 0x0401), .driver_info = USB_QUIRK_NO_BOS }, + /* DELL USB GEN2 */ { USB_DEVICE(0x413c, 0xb062), .driver_info = USB_QUIRK_NO_LPM | USB_QUIRK_RESET_RESUME }, From f338e77383789c0cae23ca3d48adcc5e9e137e3c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 15 Mar 2026 13:52:05 -0700 Subject: [PATCH 472/487] Linux 7.0-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index ec0f2d8466ea..c9b7bee102e8 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* From e2d599021c843d97ee38ba351cb0117eb984e038 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Feb 2026 15:00:15 +0900 Subject: [PATCH 473/487] rust: io: turn IoCapable into a functional trait `IoCapable` is currently used as a marker trait to signal that the methods of the `Io` trait corresponding to `T` have been overridden by the implementor (the default implementations triggering a build-time error). This goes against the DRY principle and separates the signaling of the capability from its implementation, making it possible to forget a step while implementing a new `Io`. Another undesirable side-effect is that it makes the implementation of I/O backends boilerplate-y and convoluted: currently this is done using two levels of imbricated macros that generate unsafe code. Fix these issues by turning `IoCapable` into a functional trait that includes the raw implementation of the I/O access for `T` using unsafe methods that work with an arbitrary address. This allows us to turn the default methods of `Io` into regular methods that check the passed offset, turn it into an address, and call into the corresponding `IoCapable` functions, removing the need to overload them at all. `IoCapable` must still be implemented for all supported primitive types, which is still done more concisely using a macro, but this macro becomes much simpler and does not require calling into another one. Reviewed-by: Daniel Almeida Acked-by: Alice Ryhl Signed-off-by: Alexandre Courbot Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260206-io-v2-1-71dea20a06e6@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 169 ++++++++++++++++++++++++++++++++---------- rust/kernel/pci/io.rs | 37 ++++++++- 2 files changed, 163 insertions(+), 43 deletions(-) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index e5fba6bf6db0..ec78c614c959 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -320,14 +320,29 @@ const fn offset_valid(offset: usize, size: usize) -> bool { } } -/// Marker trait indicating that an I/O backend supports operations of a certain type. +/// Trait indicating that an I/O backend supports operations of a certain type and providing an +/// implementation for these operations. /// /// Different I/O backends can implement this trait to expose only the operations they support. /// /// For example, a PCI configuration space may implement `IoCapable`, `IoCapable`, /// and `IoCapable`, but not `IoCapable`, while an MMIO region on a 64-bit /// system might implement all four. -pub trait IoCapable {} +pub trait IoCapable { + /// Performs an I/O read of type `T` at `address` and returns the result. + /// + /// # Safety + /// + /// The range `[address..address + size_of::()]` must be within the bounds of `Self`. + unsafe fn io_read(&self, address: usize) -> T; + + /// Performs an I/O write of `value` at `address`. + /// + /// # Safety + /// + /// The range `[address..address + size_of::()]` must be within the bounds of `Self`. + unsafe fn io_write(&self, value: T, address: usize); +} /// Types implementing this trait (e.g. MMIO BARs or PCI config regions) /// can perform I/O operations on regions of memory. @@ -369,146 +384,198 @@ fn io_addr(&self, offset: usize) -> Result { /// Fallible 8-bit read with runtime bounds check. #[inline(always)] - fn try_read8(&self, _offset: usize) -> Result + fn try_read8(&self, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 8-bit read") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + Ok(unsafe { self.io_read(address) }) } /// Fallible 16-bit read with runtime bounds check. #[inline(always)] - fn try_read16(&self, _offset: usize) -> Result + fn try_read16(&self, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 16-bit read") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + Ok(unsafe { self.io_read(address) }) } /// Fallible 32-bit read with runtime bounds check. #[inline(always)] - fn try_read32(&self, _offset: usize) -> Result + fn try_read32(&self, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 32-bit read") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + Ok(unsafe { self.io_read(address) }) } /// Fallible 64-bit read with runtime bounds check. #[inline(always)] - fn try_read64(&self, _offset: usize) -> Result + fn try_read64(&self, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 64-bit read") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + Ok(unsafe { self.io_read(address) }) } /// Fallible 8-bit write with runtime bounds check. #[inline(always)] - fn try_write8(&self, _value: u8, _offset: usize) -> Result + fn try_write8(&self, value: u8, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 8-bit write") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + unsafe { self.io_write(value, address) }; + Ok(()) } /// Fallible 16-bit write with runtime bounds check. #[inline(always)] - fn try_write16(&self, _value: u16, _offset: usize) -> Result + fn try_write16(&self, value: u16, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 16-bit write") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + unsafe { self.io_write(value, address) }; + Ok(()) } /// Fallible 32-bit write with runtime bounds check. #[inline(always)] - fn try_write32(&self, _value: u32, _offset: usize) -> Result + fn try_write32(&self, value: u32, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 32-bit write") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + unsafe { self.io_write(value, address) }; + Ok(()) } /// Fallible 64-bit write with runtime bounds check. #[inline(always)] - fn try_write64(&self, _value: u64, _offset: usize) -> Result + fn try_write64(&self, value: u64, offset: usize) -> Result where Self: IoCapable, { - build_error!("Backend does not support fallible 64-bit write") + let address = self.io_addr::(offset)?; + + // SAFETY: `address` has been validated by `io_addr`. + unsafe { self.io_write(value, address) }; + Ok(()) } /// Infallible 8-bit read with compile-time bounds check. #[inline(always)] - fn read8(&self, _offset: usize) -> u8 + fn read8(&self, offset: usize) -> u8 where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 8-bit read") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_read(address) } } /// Infallible 16-bit read with compile-time bounds check. #[inline(always)] - fn read16(&self, _offset: usize) -> u16 + fn read16(&self, offset: usize) -> u16 where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 16-bit read") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_read(address) } } /// Infallible 32-bit read with compile-time bounds check. #[inline(always)] - fn read32(&self, _offset: usize) -> u32 + fn read32(&self, offset: usize) -> u32 where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 32-bit read") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_read(address) } } /// Infallible 64-bit read with compile-time bounds check. #[inline(always)] - fn read64(&self, _offset: usize) -> u64 + fn read64(&self, offset: usize) -> u64 where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 64-bit read") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_read(address) } } /// Infallible 8-bit write with compile-time bounds check. #[inline(always)] - fn write8(&self, _value: u8, _offset: usize) + fn write8(&self, value: u8, offset: usize) where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 8-bit write") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_write(value, address) } } /// Infallible 16-bit write with compile-time bounds check. #[inline(always)] - fn write16(&self, _value: u16, _offset: usize) + fn write16(&self, value: u16, offset: usize) where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 16-bit write") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_write(value, address) } } /// Infallible 32-bit write with compile-time bounds check. #[inline(always)] - fn write32(&self, _value: u32, _offset: usize) + fn write32(&self, value: u32, offset: usize) where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 32-bit write") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_write(value, address) } } /// Infallible 64-bit write with compile-time bounds check. #[inline(always)] - fn write64(&self, _value: u64, _offset: usize) + fn write64(&self, value: u64, offset: usize) where Self: IoKnownSize + IoCapable, { - build_error!("Backend does not support infallible 64-bit write") + let address = self.io_addr_assert::(offset); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_write(value, address) } } } @@ -534,14 +601,36 @@ fn io_addr_assert(&self, offset: usize) -> usize { } } -// MMIO regions support 8, 16, and 32-bit accesses. -impl IoCapable for Mmio {} -impl IoCapable for Mmio {} -impl IoCapable for Mmio {} +/// Implements [`IoCapable`] on `$mmio` for `$ty` using `$read_fn` and `$write_fn`. +macro_rules! impl_mmio_io_capable { + ($mmio:ident, $(#[$attr:meta])* $ty:ty, $read_fn:ident, $write_fn:ident) => { + $(#[$attr])* + impl IoCapable<$ty> for $mmio { + unsafe fn io_read(&self, address: usize) -> $ty { + // SAFETY: By the trait invariant `address` is a valid address for MMIO operations. + unsafe { bindings::$read_fn(address as *const c_void) } + } + unsafe fn io_write(&self, value: $ty, address: usize) { + // SAFETY: By the trait invariant `address` is a valid address for MMIO operations. + unsafe { bindings::$write_fn(value, address as *mut c_void) } + } + } + }; +} + +// MMIO regions support 8, 16, and 32-bit accesses. +impl_mmio_io_capable!(Mmio, u8, readb, writeb); +impl_mmio_io_capable!(Mmio, u16, readw, writew); +impl_mmio_io_capable!(Mmio, u32, readl, writel); // MMIO regions on 64-bit systems also support 64-bit accesses. -#[cfg(CONFIG_64BIT)] -impl IoCapable for Mmio {} +impl_mmio_io_capable!( + Mmio, + #[cfg(CONFIG_64BIT)] + u64, + readq, + writeq +); impl Io for Mmio { /// Returns the base address of this mapping. diff --git a/rust/kernel/pci/io.rs b/rust/kernel/pci/io.rs index fb6edab2aea7..4feca8033eb4 100644 --- a/rust/kernel/pci/io.rs +++ b/rust/kernel/pci/io.rs @@ -142,10 +142,41 @@ macro_rules! call_config_write { }; } +/// Implements [`IoCapable`] on [`ConfigSpace`] for `$ty` using `$read_fn` and `$write_fn`. +macro_rules! impl_config_space_io_capable { + ($ty:ty, $read_fn:ident, $write_fn:ident) => { + impl<'a, S: ConfigSpaceKind> IoCapable<$ty> for ConfigSpace<'a, S> { + unsafe fn io_read(&self, address: usize) -> $ty { + let mut val: $ty = 0; + + // Return value from C function is ignored in infallible accessors. + let _ret = + // SAFETY: By the type invariant `self.pdev` is a valid address. + // CAST: The offset is cast to `i32` because the C functions expect a 32-bit + // signed offset parameter. PCI configuration space size is at most 4096 bytes, + // so the value always fits within `i32` without truncation or sign change. + unsafe { bindings::$read_fn(self.pdev.as_raw(), address as i32, &mut val) }; + + val + } + + unsafe fn io_write(&self, value: $ty, address: usize) { + // Return value from C function is ignored in infallible accessors. + let _ret = + // SAFETY: By the type invariant `self.pdev` is a valid address. + // CAST: The offset is cast to `i32` because the C functions expect a 32-bit + // signed offset parameter. PCI configuration space size is at most 4096 bytes, + // so the value always fits within `i32` without truncation or sign change. + unsafe { bindings::$write_fn(self.pdev.as_raw(), address as i32, value) }; + } + } + }; +} + // PCI configuration space supports 8, 16, and 32-bit accesses. -impl<'a, S: ConfigSpaceKind> IoCapable for ConfigSpace<'a, S> {} -impl<'a, S: ConfigSpaceKind> IoCapable for ConfigSpace<'a, S> {} -impl<'a, S: ConfigSpaceKind> IoCapable for ConfigSpace<'a, S> {} +impl_config_space_io_capable!(u8, pci_read_config_byte, pci_write_config_byte); +impl_config_space_io_capable!(u16, pci_read_config_word, pci_write_config_word); +impl_config_space_io_capable!(u32, pci_read_config_dword, pci_write_config_dword); impl<'a, S: ConfigSpaceKind> Io for ConfigSpace<'a, S> { /// Returns the base address of the I/O region. It is always 0 for configuration space. From 19103d4f93673c804ef82dd797cd2b935d0bf70f Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Feb 2026 15:00:16 +0900 Subject: [PATCH 474/487] rust: io: mem: use non-relaxed I/O ops in examples The `_relaxed` I/O variant methods are about to be replaced by a wrapper type exposing this access pattern with the regular methods of the `Io` trait. Thus replace the examples to use the regular I/O methods. Since these are examples, we want them to use the most standard ops anyway, and the relaxed variants were but an addition that was MMIO-specific. Reviewed-by: Daniel Almeida Acked-by: Alice Ryhl Signed-off-by: Alexandre Courbot Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260206-io-v2-2-71dea20a06e6@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/io/mem.rs | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/rust/kernel/io/mem.rs b/rust/kernel/io/mem.rs index 620022cff401..7dc78d547f7a 100644 --- a/rust/kernel/io/mem.rs +++ b/rust/kernel/io/mem.rs @@ -54,6 +54,7 @@ pub(crate) unsafe fn new(device: &'a Device, resource: &'a Resource) -> S /// use kernel::{ /// bindings, /// device::Core, + /// io::Io, /// of, /// platform, /// }; @@ -78,9 +79,9 @@ pub(crate) unsafe fn new(device: &'a Device, resource: &'a Resource) -> S /// let io = iomem.access(pdev.as_ref())?; /// /// // Read and write a 32-bit value at `offset`. - /// let data = io.read32_relaxed(offset); + /// let data = io.read32(offset); /// - /// io.write32_relaxed(data, offset); + /// io.write32(data, offset); /// /// # Ok(SampleDriver) /// } @@ -117,6 +118,7 @@ pub fn iomap_exclusive_sized( /// use kernel::{ /// bindings, /// device::Core, + /// io::Io, /// of, /// platform, /// }; @@ -141,9 +143,9 @@ pub fn iomap_exclusive_sized( /// /// let io = iomem.access(pdev.as_ref())?; /// - /// let data = io.try_read32_relaxed(offset)?; + /// let data = io.try_read32(offset)?; /// - /// io.try_write32_relaxed(data, offset)?; + /// io.try_write32(data, offset)?; /// /// # Ok(SampleDriver) /// } From 1d1c5c73d7e8f166b6b55ae06a3c509561b854cd Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Feb 2026 15:00:17 +0900 Subject: [PATCH 475/487] rust: io: provide Mmio relaxed ops through a wrapper type Relaxed I/O accessors for `Mmio` are currently implemented as an extra set of methods that mirror the ones defined in `Io`, but with the `_relaxed` suffix. This makes these methods impossible to use with generic code, which is a highly plausible proposition now that we have the `Io` trait. Address this by adding a new `RelaxedMmio` wrapper type for `Mmio` that provides its own `IoCapable` implementations relying on the relaxed C accessors. This makes it possible to use relaxed operations on a `Mmio` simply by wrapping it, and to use `RelaxedMmio` in code generic against `Io`. Acked-by: Alice Ryhl Signed-off-by: Alexandre Courbot Reviewed-by: Daniel Almeida Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260206-io-v2-3-71dea20a06e6@nvidia.com [ Use kernel import style in examples. - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 66 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index ec78c614c959..8a0e35070153 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -742,3 +742,69 @@ pub unsafe fn from_raw(raw: &MmioRaw) -> &Self { call_mmio_write(writeq_relaxed) <- u64 ); } + +/// [`Mmio`] wrapper using relaxed accessors. +/// +/// This type provides an implementation of [`Io`] that uses relaxed I/O MMIO operands instead of +/// the regular ones. +/// +/// See [`Mmio::relaxed`] for a usage example. +#[repr(transparent)] +pub struct RelaxedMmio(Mmio); + +impl Io for RelaxedMmio { + #[inline] + fn addr(&self) -> usize { + self.0.addr() + } + + #[inline] + fn maxsize(&self) -> usize { + self.0.maxsize() + } +} + +impl IoKnownSize for RelaxedMmio { + const MIN_SIZE: usize = SIZE; +} + +impl Mmio { + /// Returns a [`RelaxedMmio`] reference that performs relaxed I/O operations. + /// + /// Relaxed accessors do not provide ordering guarantees with respect to DMA or memory accesses + /// and can be used when such ordering is not required. + /// + /// # Examples + /// + /// ```no_run + /// use kernel::io::{ + /// Io, + /// Mmio, + /// RelaxedMmio, + /// }; + /// + /// fn do_io(io: &Mmio<0x100>) { + /// // The access is performed using `readl_relaxed` instead of `readl`. + /// let v = io.relaxed().read32(0x10); + /// } + /// + /// ``` + pub fn relaxed(&self) -> &RelaxedMmio { + // SAFETY: `RelaxedMmio` is `#[repr(transparent)]` over `Mmio`, so `Mmio` and + // `RelaxedMmio` have identical layout. + unsafe { core::mem::transmute(self) } + } +} + +// MMIO regions support 8, 16, and 32-bit accesses. +impl_mmio_io_capable!(RelaxedMmio, u8, readb_relaxed, writeb_relaxed); +impl_mmio_io_capable!(RelaxedMmio, u16, readw_relaxed, writew_relaxed); +impl_mmio_io_capable!(RelaxedMmio, u32, readl_relaxed, writel_relaxed); +// MMIO regions on 64-bit systems also support 64-bit accesses. +impl_mmio_io_capable!( + RelaxedMmio, + #[cfg(CONFIG_64BIT)] + u64, + readq_relaxed, + writeq_relaxed +); From e385eb0d1c2c4d2dbc48d1bcbc44fd43cbb154a4 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Feb 2026 15:00:18 +0900 Subject: [PATCH 476/487] rust: io: remove legacy relaxed accessors of Mmio The relaxed access functionality is now provided by the `RelaxedMmio` wrapper type, and we don't have any user of the legacy methods left. Remove them. Reviewed-by: Daniel Almeida Acked-by: Alice Ryhl Signed-off-by: Alexandre Courbot Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260206-io-v2-4-71dea20a06e6@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 40 ---------------------------------------- 1 file changed, 40 deletions(-) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index 8a0e35070153..0d946e0c5d4f 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -701,46 +701,6 @@ pub unsafe fn from_raw(raw: &MmioRaw) -> &Self { // SAFETY: `Mmio` is a transparent wrapper around `MmioRaw`. unsafe { &*core::ptr::from_ref(raw).cast() } } - - io_define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8); - io_define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16); - io_define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32); - io_define_read!( - infallible, - #[cfg(CONFIG_64BIT)] - pub read64_relaxed, - call_mmio_read(readq_relaxed) -> u64 - ); - - io_define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8); - io_define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16); - io_define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32); - io_define_read!( - fallible, - #[cfg(CONFIG_64BIT)] - pub try_read64_relaxed, - call_mmio_read(readq_relaxed) -> u64 - ); - - io_define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8); - io_define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16); - io_define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32); - io_define_write!( - infallible, - #[cfg(CONFIG_64BIT)] - pub write64_relaxed, - call_mmio_write(writeq_relaxed) <- u64 - ); - - io_define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8); - io_define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16); - io_define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32); - io_define_write!( - fallible, - #[cfg(CONFIG_64BIT)] - pub try_write64_relaxed, - call_mmio_write(writeq_relaxed) <- u64 - ); } /// [`Mmio`] wrapper using relaxed accessors. From 50aad5510fbbf8dd8f5f63380e1a1e7ae73216c4 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Feb 2026 15:00:19 +0900 Subject: [PATCH 477/487] rust: pci: io: remove overloaded Io methods of ConfigSpace Since `ConfigSpace` now has the relevant implementations of `IoCapable`, the default methods of `Io` can be used in place of the overloaded ones. Remove them as well as the macros generating them. Reviewed-by: Daniel Almeida Acked-by: Alice Ryhl Signed-off-by: Alexandre Courbot Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260206-io-v2-5-71dea20a06e6@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 4 --- rust/kernel/pci/io.rs | 70 ------------------------------------------- 2 files changed, 74 deletions(-) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index 0d946e0c5d4f..2ae2420be344 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -215,7 +215,6 @@ macro_rules! call_mmio_write { /// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the /// `$call_macro`. /// * `$type_name:ty` - The Rust type of the value being read (e.g., `u8`, `u32`). -#[macro_export] macro_rules! io_define_read { (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) -> $type_name:ty) => { @@ -249,7 +248,6 @@ macro_rules! io_define_read { } }; } -pub use io_define_read; /// Generates an accessor method for writing to an I/O backend. /// @@ -274,7 +272,6 @@ macro_rules! io_define_read { /// `$call_macro`. /// * `$type_name:ty` - The Rust type of the value being written (e.g., `u8`, `u32`). Note the use /// of `<-` before the type to denote a write operation. -#[macro_export] macro_rules! io_define_write { (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) <- $type_name:ty) => { @@ -306,7 +303,6 @@ macro_rules! io_define_write { } }; } -pub use io_define_write; /// Checks whether an access of type `U` at the given `offset` /// is valid within this region. diff --git a/rust/kernel/pci/io.rs b/rust/kernel/pci/io.rs index 4feca8033eb4..ae78676c927f 100644 --- a/rust/kernel/pci/io.rs +++ b/rust/kernel/pci/io.rs @@ -8,8 +8,6 @@ device, devres::Devres, io::{ - io_define_read, - io_define_write, Io, IoCapable, IoKnownSize, @@ -85,63 +83,6 @@ pub struct ConfigSpace<'a, S: ConfigSpaceKind = Extended> { _marker: PhantomData, } -/// Internal helper macros used to invoke C PCI configuration space read functions. -/// -/// This macro is intended to be used by higher-level PCI configuration space access macros -/// (io_define_read) and provides a unified expansion for infallible vs. fallible read semantics. It -/// emits a direct call into the corresponding C helper and performs the required cast to the Rust -/// return type. -/// -/// # Parameters -/// -/// * `$c_fn` – The C function performing the PCI configuration space write. -/// * `$self` – The I/O backend object. -/// * `$ty` – The type of the value to read. -/// * `$addr` – The PCI configuration space offset to read. -/// -/// This macro does not perform any validation; all invariants must be upheld by the higher-level -/// abstraction invoking it. -macro_rules! call_config_read { - (infallible, $c_fn:ident, $self:ident, $ty:ty, $addr:expr) => {{ - let mut val: $ty = 0; - // SAFETY: By the type invariant `$self.pdev` is a valid address. - // CAST: The offset is cast to `i32` because the C functions expect a 32-bit signed offset - // parameter. PCI configuration space size is at most 4096 bytes, so the value always fits - // within `i32` without truncation or sign change. - // Return value from C function is ignored in infallible accessors. - let _ret = unsafe { bindings::$c_fn($self.pdev.as_raw(), $addr as i32, &mut val) }; - val - }}; -} - -/// Internal helper macros used to invoke C PCI configuration space write functions. -/// -/// This macro is intended to be used by higher-level PCI configuration space access macros -/// (io_define_write) and provides a unified expansion for infallible vs. fallible read semantics. -/// It emits a direct call into the corresponding C helper and performs the required cast to the -/// Rust return type. -/// -/// # Parameters -/// -/// * `$c_fn` – The C function performing the PCI configuration space write. -/// * `$self` – The I/O backend object. -/// * `$ty` – The type of the written value. -/// * `$addr` – The configuration space offset to write. -/// * `$value` – The value to write. -/// -/// This macro does not perform any validation; all invariants must be upheld by the higher-level -/// abstraction invoking it. -macro_rules! call_config_write { - (infallible, $c_fn:ident, $self:ident, $ty:ty, $addr:expr, $value:expr) => { - // SAFETY: By the type invariant `$self.pdev` is a valid address. - // CAST: The offset is cast to `i32` because the C functions expect a 32-bit signed offset - // parameter. PCI configuration space size is at most 4096 bytes, so the value always fits - // within `i32` without truncation or sign change. - // Return value from C function is ignored in infallible accessors. - let _ret = unsafe { bindings::$c_fn($self.pdev.as_raw(), $addr as i32, $value) }; - }; -} - /// Implements [`IoCapable`] on [`ConfigSpace`] for `$ty` using `$read_fn` and `$write_fn`. macro_rules! impl_config_space_io_capable { ($ty:ty, $read_fn:ident, $write_fn:ident) => { @@ -190,17 +131,6 @@ fn addr(&self) -> usize { fn maxsize(&self) -> usize { self.pdev.cfg_size().into_raw() } - - // PCI configuration space does not support fallible operations. - // The default implementations from the Io trait are not used. - - io_define_read!(infallible, read8, call_config_read(pci_read_config_byte) -> u8); - io_define_read!(infallible, read16, call_config_read(pci_read_config_word) -> u16); - io_define_read!(infallible, read32, call_config_read(pci_read_config_dword) -> u32); - - io_define_write!(infallible, write8, call_config_write(pci_write_config_byte) <- u8); - io_define_write!(infallible, write16, call_config_write(pci_write_config_word) <- u16); - io_define_write!(infallible, write32, call_config_write(pci_write_config_dword) <- u32); } impl<'a, S: ConfigSpaceKind> IoKnownSize for ConfigSpace<'a, S> { From 6291ee23da4224a7584ece2d292104e872b9b5fc Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Feb 2026 15:00:20 +0900 Subject: [PATCH 478/487] rust: io: remove overloaded Io methods of Mmio Since `Mmio` now has the relevant implementations of `IoCapable`, the default methods of `Io` can be used in place of the overloaded ones. Remove them as well as the macros generating them. Reviewed-by: Daniel Almeida Acked-by: Alice Ryhl Signed-off-by: Alexandre Courbot Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260206-io-v2-6-71dea20a06e6@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 207 ---------------------------------------------- 1 file changed, 207 deletions(-) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index 2ae2420be344..947eb378d297 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -137,173 +137,6 @@ pub fn maxsize(&self) -> usize { #[repr(transparent)] pub struct Mmio(MmioRaw); -/// Internal helper macros used to invoke C MMIO read functions. -/// -/// This macro is intended to be used by higher-level MMIO access macros (io_define_read) and -/// provides a unified expansion for infallible vs. fallible read semantics. It emits a direct call -/// into the corresponding C helper and performs the required cast to the Rust return type. -/// -/// # Parameters -/// -/// * `$c_fn` – The C function performing the MMIO read. -/// * `$self` – The I/O backend object. -/// * `$ty` – The type of the value to be read. -/// * `$addr` – The MMIO address to read. -/// -/// This macro does not perform any validation; all invariants must be upheld by the higher-level -/// abstraction invoking it. -macro_rules! call_mmio_read { - (infallible, $c_fn:ident, $self:ident, $type:ty, $addr:expr) => { - // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. - unsafe { bindings::$c_fn($addr as *const c_void) as $type } - }; - - (fallible, $c_fn:ident, $self:ident, $type:ty, $addr:expr) => {{ - // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. - Ok(unsafe { bindings::$c_fn($addr as *const c_void) as $type }) - }}; -} - -/// Internal helper macros used to invoke C MMIO write functions. -/// -/// This macro is intended to be used by higher-level MMIO access macros (io_define_write) and -/// provides a unified expansion for infallible vs. fallible write semantics. It emits a direct call -/// into the corresponding C helper and performs the required cast to the Rust return type. -/// -/// # Parameters -/// -/// * `$c_fn` – The C function performing the MMIO write. -/// * `$self` – The I/O backend object. -/// * `$ty` – The type of the written value. -/// * `$addr` – The MMIO address to write. -/// * `$value` – The value to write. -/// -/// This macro does not perform any validation; all invariants must be upheld by the higher-level -/// abstraction invoking it. -macro_rules! call_mmio_write { - (infallible, $c_fn:ident, $self:ident, $ty:ty, $addr:expr, $value:expr) => { - // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. - unsafe { bindings::$c_fn($value, $addr as *mut c_void) } - }; - - (fallible, $c_fn:ident, $self:ident, $ty:ty, $addr:expr, $value:expr) => {{ - // SAFETY: By the type invariant `addr` is a valid address for MMIO operations. - unsafe { bindings::$c_fn($value, $addr as *mut c_void) }; - Ok(()) - }}; -} - -/// Generates an accessor method for reading from an I/O backend. -/// -/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked -/// (infallible) or runtime bounds-checked (fallible) read methods. It abstracts the address -/// calculation and bounds checking, and delegates the actual I/O read operation to a specified -/// helper macro, making it generic over different I/O backends. -/// -/// # Parameters -/// -/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on -/// `IoKnownSize` for compile-time checks and returns the value directly. `fallible` performs -/// runtime checks against `maxsize()` and returns a `Result`. -/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g., -/// `#[cfg(CONFIG_64BIT)]` or inline directives). -/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`). -/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `read32`, -/// `try_read8`). -/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call -/// (e.g., `call_mmio_read`). -/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the -/// `$call_macro`. -/// * `$type_name:ty` - The Rust type of the value being read (e.g., `u8`, `u32`). -macro_rules! io_define_read { - (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) -> - $type_name:ty) => { - /// Read IO data from a given offset known at compile time. - /// - /// Bound checks are performed on compile time, hence if the offset is not known at compile - /// time, the build will fail. - $(#[$attr])* - // Always inline to optimize out error path of `io_addr_assert`. - #[inline(always)] - $vis fn $name(&self, offset: usize) -> $type_name { - let addr = self.io_addr_assert::<$type_name>(offset); - - // SAFETY: By the type invariant `addr` is a valid address for IO operations. - $call_macro!(infallible, $c_fn, self, $type_name, addr) - } - }; - - (fallible, $(#[$attr:meta])* $vis:vis $try_name:ident, $call_macro:ident($c_fn:ident) -> - $type_name:ty) => { - /// Read IO data from a given offset. - /// - /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is - /// out of bounds. - $(#[$attr])* - $vis fn $try_name(&self, offset: usize) -> Result<$type_name> { - let addr = self.io_addr::<$type_name>(offset)?; - - // SAFETY: By the type invariant `addr` is a valid address for IO operations. - $call_macro!(fallible, $c_fn, self, $type_name, addr) - } - }; -} - -/// Generates an accessor method for writing to an I/O backend. -/// -/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked -/// (infallible) or runtime bounds-checked (fallible) write methods. It abstracts the address -/// calculation and bounds checking, and delegates the actual I/O write operation to a specified -/// helper macro, making it generic over different I/O backends. -/// -/// # Parameters -/// -/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on -/// `IoKnownSize` for compile-time checks and returns `()`. `fallible` performs runtime checks -/// against `maxsize()` and returns a `Result`. -/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g., -/// `#[cfg(CONFIG_64BIT)]` or inline directives). -/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`). -/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `write32`, -/// `try_write8`). -/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call -/// (e.g., `call_mmio_write`). -/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the -/// `$call_macro`. -/// * `$type_name:ty` - The Rust type of the value being written (e.g., `u8`, `u32`). Note the use -/// of `<-` before the type to denote a write operation. -macro_rules! io_define_write { - (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) <- - $type_name:ty) => { - /// Write IO data from a given offset known at compile time. - /// - /// Bound checks are performed on compile time, hence if the offset is not known at compile - /// time, the build will fail. - $(#[$attr])* - // Always inline to optimize out error path of `io_addr_assert`. - #[inline(always)] - $vis fn $name(&self, value: $type_name, offset: usize) { - let addr = self.io_addr_assert::<$type_name>(offset); - - $call_macro!(infallible, $c_fn, self, $type_name, addr, value); - } - }; - - (fallible, $(#[$attr:meta])* $vis:vis $try_name:ident, $call_macro:ident($c_fn:ident) <- - $type_name:ty) => { - /// Write IO data from a given offset. - /// - /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is - /// out of bounds. - $(#[$attr])* - $vis fn $try_name(&self, value: $type_name, offset: usize) -> Result { - let addr = self.io_addr::<$type_name>(offset)?; - - $call_macro!(fallible, $c_fn, self, $type_name, addr, value) - } - }; -} - /// Checks whether an access of type `U` at the given `offset` /// is valid within this region. #[inline] @@ -640,46 +473,6 @@ fn addr(&self) -> usize { fn maxsize(&self) -> usize { self.0.maxsize() } - - io_define_read!(fallible, try_read8, call_mmio_read(readb) -> u8); - io_define_read!(fallible, try_read16, call_mmio_read(readw) -> u16); - io_define_read!(fallible, try_read32, call_mmio_read(readl) -> u32); - io_define_read!( - fallible, - #[cfg(CONFIG_64BIT)] - try_read64, - call_mmio_read(readq) -> u64 - ); - - io_define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8); - io_define_write!(fallible, try_write16, call_mmio_write(writew) <- u16); - io_define_write!(fallible, try_write32, call_mmio_write(writel) <- u32); - io_define_write!( - fallible, - #[cfg(CONFIG_64BIT)] - try_write64, - call_mmio_write(writeq) <- u64 - ); - - io_define_read!(infallible, read8, call_mmio_read(readb) -> u8); - io_define_read!(infallible, read16, call_mmio_read(readw) -> u16); - io_define_read!(infallible, read32, call_mmio_read(readl) -> u32); - io_define_read!( - infallible, - #[cfg(CONFIG_64BIT)] - read64, - call_mmio_read(readq) -> u64 - ); - - io_define_write!(infallible, write8, call_mmio_write(writeb) <- u8); - io_define_write!(infallible, write16, call_mmio_write(writew) <- u16); - io_define_write!(infallible, write32, call_mmio_write(writel) <- u32); - io_define_write!( - infallible, - #[cfg(CONFIG_64BIT)] - write64, - call_mmio_write(writeq) <- u64 - ); } impl IoKnownSize for Mmio { From 3cc319d5f433a4d560cc944ecfb1fe50b866cd66 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:11 +0900 Subject: [PATCH 479/487] rust: enable the `generic_arg_infer` feature This feature is stable since 1.89, and used in subsequent patches. Reviewed-by: Gary Guo Tested-by: Dirk Behme Acked-by: Miguel Ojeda Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-1-86805b2f7e9d@nvidia.com [ Resolve merge conflict. - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/lib.rs | 3 +++ scripts/Makefile.build | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index d93292d47420..34b924819288 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -41,6 +41,9 @@ // Stable since Rust 1.84.0. #![feature(strict_provenance)] // +// Stable since Rust 1.89.0. +#![feature(generic_arg_infer)] +// // Expected to become stable. #![feature(arbitrary_self_types)] // diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 3652b85be545..010d08472fb2 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -316,12 +316,13 @@ $(obj)/%.lst: $(obj)/%.c FORCE # `feature(offset_of_nested)`, `feature(raw_ref_op)`. # - Stable since Rust 1.84.0: `feature(strict_provenance)`. # - Stable since Rust 1.87.0: `feature(asm_goto)`. +# - Stable since Rust 1.89.0: `feature(generic_arg_infer)`. # - Expected to become stable: `feature(arbitrary_self_types)`. # - To be determined: `feature(used_with_arg)`. # # Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on # the unstable features in use. -rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,slice_ptr_len,strict_provenance,used_with_arg +rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,generic_arg_infer,lint_reasons,offset_of_nested,raw_ref_op,slice_ptr_len,strict_provenance,used_with_arg # `--out-dir` is required to avoid temporaries being created by `rustc` in the # current working directory, which may be not accessible in the out-of-tree From c59a2d14cd248c77457b821b15c72e6a6a268553 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:12 +0900 Subject: [PATCH 480/487] rust: num: add `shr` and `shl` methods to `Bounded` Shifting a `Bounded` left or right changes the number of bits required to represent the value. Add methods that perform the shift and return a `Bounded` with the appropriately adjusted bit width. These methods are particularly useful for bitfield extraction. Suggested-by: Alice Ryhl Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Reviewed-by: Daniel Almeida Tested-by: Dirk Behme Acked-by: Miguel Ojeda Acked-by: Yury Norov Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-2-86805b2f7e9d@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/num/bounded.rs | 42 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/rust/kernel/num/bounded.rs b/rust/kernel/num/bounded.rs index fa81acbdc8c2..2f5f13ecd3d6 100644 --- a/rust/kernel/num/bounded.rs +++ b/rust/kernel/num/bounded.rs @@ -473,6 +473,48 @@ pub fn cast(self) -> Bounded // `N` bits, and with the same signedness. unsafe { Bounded::__new(value) } } + + /// Right-shifts `self` by `SHIFT` and returns the result as a `Bounded<_, RES>`, where `RES >= + /// N - SHIFT`. + /// + /// # Examples + /// + /// ``` + /// use kernel::num::Bounded; + /// + /// let v = Bounded::::new::<0xff00>(); + /// let v_shifted: Bounded:: = v.shr::<8, _>(); + /// + /// assert_eq!(v_shifted.get(), 0xff); + /// ``` + pub fn shr(self) -> Bounded { + const { assert!(RES + SHIFT >= N) } + + // SAFETY: We shift the value right by `SHIFT`, reducing the number of bits needed to + // represent the shifted value by as much, and just asserted that `RES >= N - SHIFT`. + unsafe { Bounded::__new(self.0 >> SHIFT) } + } + + /// Left-shifts `self` by `SHIFT` and returns the result as a `Bounded<_, RES>`, where `RES >= + /// N + SHIFT`. + /// + /// # Examples + /// + /// ``` + /// use kernel::num::Bounded; + /// + /// let v = Bounded::::new::<0xff>(); + /// let v_shifted: Bounded:: = v.shl::<8, _>(); + /// + /// assert_eq!(v_shifted.get(), 0xff00); + /// ``` + pub fn shl(self) -> Bounded { + const { assert!(RES >= N + SHIFT) } + + // SAFETY: We shift the value left by `SHIFT`, augmenting the number of bits needed to + // represent the shifted value by as much, and just asserted that `RES >= N + SHIFT`. + unsafe { Bounded::__new(self.0 << SHIFT) } + } } impl Deref for Bounded From 164f8634bfd8eef7b90c429156c59706635cfb88 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:13 +0900 Subject: [PATCH 481/487] rust: num: add `into_bool` method to `Bounded` Single-bit numbers are typically treated as booleans. There is an `Into` implementation for those, but invoking it from contexts that lack type expectations is not always convenient. Add an `into_bool` method as a simpler shortcut. Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Reviewed-by: Daniel Almeida Reviewed-by: Yury Norov Tested-by: Dirk Behme Acked-by: Miguel Ojeda Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-3-86805b2f7e9d@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/num/bounded.rs | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/rust/kernel/num/bounded.rs b/rust/kernel/num/bounded.rs index 2f5f13ecd3d6..d28d118abd8e 100644 --- a/rust/kernel/num/bounded.rs +++ b/rust/kernel/num/bounded.rs @@ -1101,3 +1101,24 @@ fn from(value: bool) -> Self { unsafe { Self::__new(T::from(value)) } } } + +impl Bounded +where + T: Integer + Zeroable, +{ + /// Converts this [`Bounded`] into a [`bool`]. + /// + /// This is a shorter way of writing `bool::from(self)`. + /// + /// # Examples + /// + /// ``` + /// use kernel::num::Bounded; + /// + /// assert_eq!(Bounded::::new::<0>().into_bool(), false); + /// assert_eq!(Bounded::::new::<1>().into_bool(), true); + /// ``` + pub fn into_bool(self) -> bool { + self.into() + } +} From 7836ec76ec5cd8d45759a6a360b1fda4829d2734 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:14 +0900 Subject: [PATCH 482/487] rust: num: make Bounded::get const There is a need to access the inner value of a `Bounded` in const context, notably for bitfields and registers. Remove the invariant check of `Bounded::get`, which allows us to make it const. Reviewed-by: Gary Guo Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-4-86805b2f7e9d@nvidia.com Signed-off-by: Danilo Krummrich --- rust/kernel/num/bounded.rs | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/rust/kernel/num/bounded.rs b/rust/kernel/num/bounded.rs index d28d118abd8e..bbab6bbcb315 100644 --- a/rust/kernel/num/bounded.rs +++ b/rust/kernel/num/bounded.rs @@ -379,6 +379,9 @@ pub fn from_expr(expr: T) -> Self { /// Returns the wrapped value as the backing type. /// + /// This is similar to the [`Deref`] implementation, but doesn't enforce the size invariant of + /// the [`Bounded`], which might produce slightly less optimal code. + /// /// # Examples /// /// ``` @@ -387,8 +390,8 @@ pub fn from_expr(expr: T) -> Self { /// let v = Bounded::::new::<7>(); /// assert_eq!(v.get(), 7u32); /// ``` - pub fn get(self) -> T { - *self.deref() + pub const fn get(self) -> T { + self.0 } /// Increases the number of bits usable for `self`. From 498823541be1e2d9f947b37a10cc98e681da9828 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:15 +0900 Subject: [PATCH 483/487] rust: io: add IoLoc type and generic I/O accessors I/O accesses are defined by the following properties: - An I/O location, which consists of a start address, a width, and a type to interpret the read value as, - A value, which is returned for reads or provided for writes. Introduce the `IoLoc` trait, which allows implementing types to fully specify an I/O location. This allows I/O operations to be made generic through the new `read` and `write` methods. This design will allow us to factorize the I/O code working with primitives, and to introduce ways to perform I/O with a higher degree of control through register types. Co-developed-by: Gary Guo Signed-off-by: Gary Guo Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-5-86805b2f7e9d@nvidia.com [ Fix incorrect reference to io_addr_assert() in try_update(). - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 124 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 124 insertions(+) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index 947eb378d297..e1e9802bb603 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -173,6 +173,30 @@ pub trait IoCapable { unsafe fn io_write(&self, value: T, address: usize); } +/// Describes a given I/O location: its offset, width, and type to convert the raw value from and +/// into. +/// +/// This trait is the key abstraction allowing [`Io::read`], [`Io::write`], and [`Io::update`] (and +/// their fallible [`try_read`](Io::try_read), [`try_write`](Io::try_write) and +/// [`try_update`](Io::try_update) counterparts) to work uniformly with both raw [`usize`] offsets +/// (for primitive types like [`u32`]) and typed ones. +/// +/// An `IoLoc` carries three pieces of information: +/// +/// - The offset to access (returned by [`IoLoc::offset`]), +/// - The width of the access (determined by [`IoLoc::IoType`]), +/// - The type `T` in which the raw data is returned or provided. +/// +/// `T` and `IoLoc::IoType` may differ: for instance, a typed register has `T` = the register type +/// with its bitfields, and `IoType` = its backing primitive (e.g. `u32`). +pub trait IoLoc { + /// Size ([`u8`], [`u16`], etc) of the I/O performed on the returned [`offset`](IoLoc::offset). + type IoType: Into + From; + + /// Consumes `self` and returns the offset of this location. + fn offset(self) -> usize; +} + /// Types implementing this trait (e.g. MMIO BARs or PCI config regions) /// can perform I/O operations on regions of memory. /// @@ -406,6 +430,106 @@ fn write64(&self, value: u64, offset: usize) // SAFETY: `address` has been validated by `io_addr_assert`. unsafe { self.io_write(value, address) } } + + /// Generic fallible read with runtime bounds check. + #[inline(always)] + fn try_read(&self, location: L) -> Result + where + L: IoLoc, + Self: IoCapable, + { + let address = self.io_addr::(location.offset())?; + + // SAFETY: `address` has been validated by `io_addr`. + Ok(unsafe { self.io_read(address) }.into()) + } + + /// Generic fallible write with runtime bounds check. + #[inline(always)] + fn try_write(&self, location: L, value: T) -> Result + where + L: IoLoc, + Self: IoCapable, + { + let address = self.io_addr::(location.offset())?; + let io_value = value.into(); + + // SAFETY: `address` has been validated by `io_addr`. + unsafe { self.io_write(io_value, address) } + + Ok(()) + } + + /// Generic fallible update with runtime bounds check. + /// + /// Note: this does not perform any synchronization. The caller is responsible for ensuring + /// exclusive access if required. + #[inline(always)] + fn try_update(&self, location: L, f: F) -> Result + where + L: IoLoc, + Self: IoCapable, + F: FnOnce(T) -> T, + { + let address = self.io_addr::(location.offset())?; + + // SAFETY: `address` has been validated by `io_addr`. + let value: T = unsafe { self.io_read(address) }.into(); + let io_value = f(value).into(); + + // SAFETY: `address` has been validated by `io_addr`. + unsafe { self.io_write(io_value, address) } + + Ok(()) + } + + /// Generic infallible read with compile-time bounds check. + #[inline(always)] + fn read(&self, location: L) -> T + where + L: IoLoc, + Self: IoKnownSize + IoCapable, + { + let address = self.io_addr_assert::(location.offset()); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_read(address) }.into() + } + + /// Generic infallible write with compile-time bounds check. + #[inline(always)] + fn write(&self, location: L, value: T) + where + L: IoLoc, + Self: IoKnownSize + IoCapable, + { + let address = self.io_addr_assert::(location.offset()); + let io_value = value.into(); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_write(io_value, address) } + } + + /// Generic infallible update with compile-time bounds check. + /// + /// Note: this does not perform any synchronization. The caller is responsible for ensuring + /// exclusive access if required. + #[inline(always)] + fn update(&self, location: L, f: F) + where + L: IoLoc, + Self: IoKnownSize + IoCapable + Sized, + F: FnOnce(T) -> T, + { + let address = self.io_addr_assert::(location.offset()); + + // SAFETY: `address` has been validated by `io_addr_assert`. + let value: T = unsafe { self.io_read(address) }.into(); + let io_value = f(value).into(); + + // SAFETY: `address` has been validated by `io_addr_assert`. + unsafe { self.io_write(io_value, address) } + } } /// Trait for types with a known size at compile time. From 147b41ba23d63f43ed34e6940417a5506e323370 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:16 +0900 Subject: [PATCH 484/487] rust: io: use generic read/write accessors for primitive accesses By providing the required `IoLoc` implementations on `usize`, we can leverage the generic accessors and reduce the number of unsafe blocks in the module. This also allows us to directly call the generic `read/write/update` methods with primitive types, so add examples illustrating this. Signed-off-by: Alexandre Courbot Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260314-register-v9-6-86805b2f7e9d@nvidia.com [ Slightly improve wording in doc-comment. - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 218 +++++++++++++++++++++++++++++++--------------- 1 file changed, 150 insertions(+), 68 deletions(-) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index e1e9802bb603..c51a87b9169b 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -197,6 +197,26 @@ pub trait IoLoc { fn offset(self) -> usize; } +/// Implements [`IoLoc<$ty>`] for [`usize`], allowing [`usize`] to be used as a parameter of +/// [`Io::read`] and [`Io::write`]. +macro_rules! impl_usize_ioloc { + ($($ty:ty),*) => { + $( + impl IoLoc<$ty> for usize { + type IoType = $ty; + + #[inline(always)] + fn offset(self) -> usize { + self + } + } + )* + } +} + +// Provide the ability to read any primitive type from a [`usize`]. +impl_usize_ioloc!(u8, u16, u32, u64); + /// Types implementing this trait (e.g. MMIO BARs or PCI config regions) /// can perform I/O operations on regions of memory. /// @@ -241,10 +261,7 @@ fn try_read8(&self, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - Ok(unsafe { self.io_read(address) }) + self.try_read(offset) } /// Fallible 16-bit read with runtime bounds check. @@ -253,10 +270,7 @@ fn try_read16(&self, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - Ok(unsafe { self.io_read(address) }) + self.try_read(offset) } /// Fallible 32-bit read with runtime bounds check. @@ -265,10 +279,7 @@ fn try_read32(&self, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - Ok(unsafe { self.io_read(address) }) + self.try_read(offset) } /// Fallible 64-bit read with runtime bounds check. @@ -277,10 +288,7 @@ fn try_read64(&self, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - Ok(unsafe { self.io_read(address) }) + self.try_read(offset) } /// Fallible 8-bit write with runtime bounds check. @@ -289,11 +297,7 @@ fn try_write8(&self, value: u8, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - unsafe { self.io_write(value, address) }; - Ok(()) + self.try_write(offset, value) } /// Fallible 16-bit write with runtime bounds check. @@ -302,11 +306,7 @@ fn try_write16(&self, value: u16, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - unsafe { self.io_write(value, address) }; - Ok(()) + self.try_write(offset, value) } /// Fallible 32-bit write with runtime bounds check. @@ -315,11 +315,7 @@ fn try_write32(&self, value: u32, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - unsafe { self.io_write(value, address) }; - Ok(()) + self.try_write(offset, value) } /// Fallible 64-bit write with runtime bounds check. @@ -328,11 +324,7 @@ fn try_write64(&self, value: u64, offset: usize) -> Result where Self: IoCapable, { - let address = self.io_addr::(offset)?; - - // SAFETY: `address` has been validated by `io_addr`. - unsafe { self.io_write(value, address) }; - Ok(()) + self.try_write(offset, value) } /// Infallible 8-bit read with compile-time bounds check. @@ -341,10 +333,7 @@ fn read8(&self, offset: usize) -> u8 where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_read(address) } + self.read(offset) } /// Infallible 16-bit read with compile-time bounds check. @@ -353,10 +342,7 @@ fn read16(&self, offset: usize) -> u16 where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_read(address) } + self.read(offset) } /// Infallible 32-bit read with compile-time bounds check. @@ -365,10 +351,7 @@ fn read32(&self, offset: usize) -> u32 where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_read(address) } + self.read(offset) } /// Infallible 64-bit read with compile-time bounds check. @@ -377,10 +360,7 @@ fn read64(&self, offset: usize) -> u64 where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_read(address) } + self.read(offset) } /// Infallible 8-bit write with compile-time bounds check. @@ -389,10 +369,7 @@ fn write8(&self, value: u8, offset: usize) where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_write(value, address) } + self.write(offset, value) } /// Infallible 16-bit write with compile-time bounds check. @@ -401,10 +378,7 @@ fn write16(&self, value: u16, offset: usize) where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_write(value, address) } + self.write(offset, value) } /// Infallible 32-bit write with compile-time bounds check. @@ -413,10 +387,7 @@ fn write32(&self, value: u32, offset: usize) where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_write(value, address) } + self.write(offset, value) } /// Infallible 64-bit write with compile-time bounds check. @@ -425,13 +396,31 @@ fn write64(&self, value: u64, offset: usize) where Self: IoKnownSize + IoCapable, { - let address = self.io_addr_assert::(offset); - - // SAFETY: `address` has been validated by `io_addr_assert`. - unsafe { self.io_write(value, address) } + self.write(offset, value) } /// Generic fallible read with runtime bounds check. + /// + /// # Examples + /// + /// Read a primitive type from an I/O address: + /// + /// ```no_run + /// use kernel::io::{ + /// Io, + /// Mmio, + /// }; + /// + /// fn do_reads(io: &Mmio) -> Result { + /// // 32-bit read from address `0x10`. + /// let v: u32 = io.try_read(0x10)?; + /// + /// // 8-bit read from address `0xfff`. + /// let v: u8 = io.try_read(0xfff)?; + /// + /// Ok(()) + /// } + /// ``` #[inline(always)] fn try_read(&self, location: L) -> Result where @@ -445,6 +434,27 @@ fn try_read(&self, location: L) -> Result } /// Generic fallible write with runtime bounds check. + /// + /// # Examples + /// + /// Write a primitive type to an I/O address: + /// + /// ```no_run + /// use kernel::io::{ + /// Io, + /// Mmio, + /// }; + /// + /// fn do_writes(io: &Mmio) -> Result { + /// // 32-bit write of value `1` at address `0x10`. + /// io.try_write(0x10, 1u32)?; + /// + /// // 8-bit write of value `0xff` at address `0xfff`. + /// io.try_write(0xfff, 0xffu8)?; + /// + /// Ok(()) + /// } + /// ``` #[inline(always)] fn try_write(&self, location: L, value: T) -> Result where @@ -464,6 +474,23 @@ fn try_write(&self, location: L, value: T) -> Result /// /// Note: this does not perform any synchronization. The caller is responsible for ensuring /// exclusive access if required. + /// + /// # Examples + /// + /// Read the u32 value at address `0x10`, increment it, and store the updated value back: + /// + /// ```no_run + /// use kernel::io::{ + /// Io, + /// Mmio, + /// }; + /// + /// fn do_update(io: &Mmio<0x1000>) -> Result { + /// io.try_update(0x10, |v: u32| { + /// v + 1 + /// }) + /// } + /// ``` #[inline(always)] fn try_update(&self, location: L, f: F) -> Result where @@ -484,6 +511,25 @@ fn try_update(&self, location: L, f: F) -> Result } /// Generic infallible read with compile-time bounds check. + /// + /// # Examples + /// + /// Read a primitive type from an I/O address: + /// + /// ```no_run + /// use kernel::io::{ + /// Io, + /// Mmio, + /// }; + /// + /// fn do_reads(io: &Mmio<0x1000>) { + /// // 32-bit read from address `0x10`. + /// let v: u32 = io.read(0x10); + /// + /// // 8-bit read from the top of the I/O space. + /// let v: u8 = io.read(0xfff); + /// } + /// ``` #[inline(always)] fn read(&self, location: L) -> T where @@ -497,6 +543,25 @@ fn read(&self, location: L) -> T } /// Generic infallible write with compile-time bounds check. + /// + /// # Examples + /// + /// Write a primitive type to an I/O address: + /// + /// ```no_run + /// use kernel::io::{ + /// Io, + /// Mmio, + /// }; + /// + /// fn do_writes(io: &Mmio<0x1000>) { + /// // 32-bit write of value `1` at address `0x10`. + /// io.write(0x10, 1u32); + /// + /// // 8-bit write of value `0xff` at the top of the I/O space. + /// io.write(0xfff, 0xffu8); + /// } + /// ``` #[inline(always)] fn write(&self, location: L, value: T) where @@ -514,6 +579,23 @@ fn write(&self, location: L, value: T) /// /// Note: this does not perform any synchronization. The caller is responsible for ensuring /// exclusive access if required. + /// + /// # Examples + /// + /// Read the u32 value at address `0x10`, increment it, and store the updated value back: + /// + /// ```no_run + /// use kernel::io::{ + /// Io, + /// Mmio, + /// }; + /// + /// fn do_update(io: &Mmio<0x1000>) { + /// io.update(0x10, |v: u32| { + /// v + 1 + /// }) + /// } + /// ``` #[inline(always)] fn update(&self, location: L, f: F) where From 20ba6a1dbcb957152f6d858015b3a3311dd6da49 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:17 +0900 Subject: [PATCH 485/487] rust: io: add `register!` macro Add a macro for defining hardware register types with I/O accessors. Each register field is represented as a `Bounded` of the appropriate bit width, ensuring field values are never silently truncated. Fields can optionally be converted to/from custom types, either fallibly or infallibly. The address of registers can be direct, relative, or indexed, supporting most of the patterns in which registers are arranged. Suggested-by: Danilo Krummrich Link: https://lore.kernel.org/all/20250306222336.23482-6-dakr@kernel.org/ Co-developed-by: Gary Guo Signed-off-by: Gary Guo Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-7-86805b2f7e9d@nvidia.com [ * Improve wording and formatting of doc-comments, * Import build_assert!(), * Add missing inline annotations, * Call static_assert!() with absolute path, * Use expect instead of allow. - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 5 +- rust/kernel/io/register.rs | 1229 ++++++++++++++++++++++++++++++++++++ 2 files changed, 1233 insertions(+), 1 deletion(-) create mode 100644 rust/kernel/io/register.rs diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index c51a87b9169b..4950cecf30ca 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -11,8 +11,10 @@ pub mod mem; pub mod poll; +pub mod register; pub mod resource; +pub use crate::register; pub use resource::Resource; /// Physical address type. @@ -179,7 +181,8 @@ pub trait IoCapable { /// This trait is the key abstraction allowing [`Io::read`], [`Io::write`], and [`Io::update`] (and /// their fallible [`try_read`](Io::try_read), [`try_write`](Io::try_write) and /// [`try_update`](Io::try_update) counterparts) to work uniformly with both raw [`usize`] offsets -/// (for primitive types like [`u32`]) and typed ones. +/// (for primitive types like [`u32`]) and typed ones (like those generated by the [`register!`] +/// macro). /// /// An `IoLoc` carries three pieces of information: /// diff --git a/rust/kernel/io/register.rs b/rust/kernel/io/register.rs new file mode 100644 index 000000000000..dbd458aaa761 --- /dev/null +++ b/rust/kernel/io/register.rs @@ -0,0 +1,1229 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Macro to define register layout and accessors. +//! +//! The [`register!`](kernel::io::register!) macro provides an intuitive and readable syntax for +//! defining a dedicated type for each register and accessing it using [`Io`](super::Io). Each such +//! type comes with its own field accessors that can return an error if a field's value is invalid. +//! +//! Note: most of the items in this module are public so they can be referenced by the macro, but +//! most are not to be used directly by users. Outside of the `register!` macro itself, the only +//! items you might want to import from this module are [`WithBase`] and [`Array`]. +//! +//! # Simple example +//! +//! ```no_run +//! use kernel::io::register; +//! +//! register! { +//! /// Basic information about the chip. +//! pub BOOT_0(u32) @ 0x00000100 { +//! /// Vendor ID. +//! 15:8 vendor_id; +//! /// Major revision of the chip. +//! 7:4 major_revision; +//! /// Minor revision of the chip. +//! 3:0 minor_revision; +//! } +//! } +//! ``` +//! +//! This defines a 32-bit `BOOT_0` type which can be read from or written to offset `0x100` of an +//! `Io` region, with the described bitfields. For instance, `minor_revision` consists of the 4 +//! least significant bits of the type. +//! +//! Fields are instances of [`Bounded`](kernel::num::Bounded) and can be read by calling their +//! getter method, which is named after them. They also have setter methods prefixed with `with_` +//! for runtime values and `with_const_` for constant values. All setters return the updated +//! register value. +//! +//! Fields can also be transparently converted from/to an arbitrary type by using the `=>` and +//! `?=>` syntaxes. +//! +//! If present, doc comments above register or fields definitions are added to the relevant item +//! they document (the register type itself, or the field's setter and getter methods). +//! +//! Note that multiple registers can be defined in a single `register!` invocation. This can be +//! useful to group related registers together. +//! +//! Here is how the register defined above can be used in code: +//! +//! +//! ```no_run +//! use kernel::{ +//! io::{ +//! register, +//! Io, +//! IoLoc, +//! }, +//! num::Bounded, +//! }; +//! # use kernel::io::Mmio; +//! # register! { +//! # pub BOOT_0(u32) @ 0x00000100 { +//! # 15:8 vendor_id; +//! # 7:4 major_revision; +//! # 3:0 minor_revision; +//! # } +//! # } +//! # fn test(io: &Mmio<0x1000>) { +//! # fn obtain_vendor_id() -> u8 { 0xff } +//! +//! // Read from the register's defined offset (0x100). +//! let boot0 = io.read(BOOT_0); +//! pr_info!("chip revision: {}.{}", boot0.major_revision().get(), boot0.minor_revision().get()); +//! +//! // Update some fields and write the new value back. +//! let new_boot0 = boot0 +//! // Constant values. +//! .with_const_major_revision::<3>() +//! .with_const_minor_revision::<10>() +//! // Runtime value. +//! .with_vendor_id(obtain_vendor_id()); +//! io.write((), new_boot0); +//! +//! // Or, build a new value from zero and write it: +//! io.write((), BOOT_0::zeroed() +//! .with_const_major_revision::<3>() +//! .with_const_minor_revision::<10>() +//! .with_vendor_id(obtain_vendor_id()) +//! ); +//! +//! // Or, read and update the register in a single step. +//! io.update(BOOT_0, |r| r +//! .with_const_major_revision::<3>() +//! .with_const_minor_revision::<10>() +//! .with_vendor_id(obtain_vendor_id()) +//! ); +//! +//! // Constant values can also be built using the const setters. +//! const V: BOOT_0 = pin_init::zeroed::() +//! .with_const_major_revision::<3>() +//! .with_const_minor_revision::<10>(); +//! # } +//! ``` +//! +//! For more extensive documentation about how to define registers, see the +//! [`register!`](kernel::io::register!) macro. + +use core::marker::PhantomData; + +use crate::io::IoLoc; + +use kernel::build_assert; + +/// Trait implemented by all registers. +pub trait Register: Sized { + /// Backing primitive type of the register. + type Storage: Into + From; + + /// Start offset of the register. + /// + /// The interpretation of this offset depends on the type of the register. + const OFFSET: usize; +} + +/// Trait implemented by registers with a fixed offset. +pub trait FixedRegister: Register {} + +/// Allows `()` to be used as the `location` parameter of [`Io::write`](super::Io::write) when +/// passing a [`FixedRegister`] value. +impl IoLoc for () +where + T: FixedRegister, +{ + type IoType = T::Storage; + + #[inline(always)] + fn offset(self) -> usize { + T::OFFSET + } +} + +/// A [`FixedRegister`] carries its location in its type. Thus `FixedRegister` values can be used +/// as an [`IoLoc`]. +impl IoLoc for T +where + T: FixedRegister, +{ + type IoType = T::Storage; + + #[inline(always)] + fn offset(self) -> usize { + T::OFFSET + } +} + +/// Location of a fixed register. +pub struct FixedRegisterLoc(PhantomData); + +impl FixedRegisterLoc { + /// Returns the location of `T`. + #[inline(always)] + // We do not implement `Default` so we can be const. + #[expect(clippy::new_without_default)] + pub const fn new() -> Self { + Self(PhantomData) + } +} + +impl IoLoc for FixedRegisterLoc +where + T: FixedRegister, +{ + type IoType = T::Storage; + + #[inline(always)] + fn offset(self) -> usize { + T::OFFSET + } +} + +/// Trait providing a base address to be added to the offset of a relative register to obtain +/// its actual offset. +/// +/// The `T` generic argument is used to distinguish which base to use, in case a type provides +/// several bases. It is given to the `register!` macro to restrict the use of the register to +/// implementors of this particular variant. +pub trait RegisterBase { + /// Base address to which register offsets are added. + const BASE: usize; +} + +/// Trait implemented by all registers that are relative to a base. +pub trait WithBase { + /// Family of bases applicable to this register. + type BaseFamily; + + /// Returns the absolute location of this type when using `B` as its base. + #[inline(always)] + fn of>() -> RelativeRegisterLoc + where + Self: Register, + { + RelativeRegisterLoc::new() + } +} + +/// Trait implemented by relative registers. +pub trait RelativeRegister: Register + WithBase {} + +/// Location of a relative register. +/// +/// This can either be an immediately accessible regular [`RelativeRegister`], or a +/// [`RelativeRegisterArray`] that needs one additional resolution through +/// [`RelativeRegisterLoc::at`]. +pub struct RelativeRegisterLoc(PhantomData, PhantomData); + +impl RelativeRegisterLoc +where + T: Register + WithBase, + B: RegisterBase + ?Sized, +{ + /// Returns the location of a relative register or register array. + #[inline(always)] + // We do not implement `Default` so we can be const. + #[expect(clippy::new_without_default)] + pub const fn new() -> Self { + Self(PhantomData, PhantomData) + } + + // Returns the absolute offset of the relative register using base `B`. + // + // This is implemented as a private const method so it can be reused by the [`IoLoc`] + // implementations of both [`RelativeRegisterLoc`] and [`RelativeRegisterArrayLoc`]. + #[inline] + const fn offset(self) -> usize { + B::BASE + T::OFFSET + } +} + +impl IoLoc for RelativeRegisterLoc +where + T: RelativeRegister, + B: RegisterBase + ?Sized, +{ + type IoType = T::Storage; + + #[inline(always)] + fn offset(self) -> usize { + RelativeRegisterLoc::offset(self) + } +} + +/// Trait implemented by arrays of registers. +pub trait RegisterArray: Register { + /// Number of elements in the registers array. + const SIZE: usize; + /// Number of bytes between the start of elements in the registers array. + const STRIDE: usize; +} + +/// Location of an array register. +pub struct RegisterArrayLoc(usize, PhantomData); + +impl RegisterArrayLoc { + /// Returns the location of register `T` at position `idx`, with build-time validation. + #[inline(always)] + pub fn new(idx: usize) -> Self { + build_assert!(idx < T::SIZE); + + Self(idx, PhantomData) + } + + /// Attempts to return the location of register `T` at position `idx`, with runtime validation. + #[inline(always)] + pub fn try_new(idx: usize) -> Option { + if idx < T::SIZE { + Some(Self(idx, PhantomData)) + } else { + None + } + } +} + +impl IoLoc for RegisterArrayLoc +where + T: RegisterArray, +{ + type IoType = T::Storage; + + #[inline(always)] + fn offset(self) -> usize { + T::OFFSET + self.0 * T::STRIDE + } +} + +/// Trait providing location builders for [`RegisterArray`]s. +pub trait Array { + /// Returns the location of the register at position `idx`, with build-time validation. + #[inline(always)] + fn at(idx: usize) -> RegisterArrayLoc + where + Self: RegisterArray, + { + RegisterArrayLoc::new(idx) + } + + /// Returns the location of the register at position `idx`, with runtime validation. + #[inline(always)] + fn try_at(idx: usize) -> Option> + where + Self: RegisterArray, + { + RegisterArrayLoc::try_new(idx) + } +} + +/// Trait implemented by arrays of relative registers. +pub trait RelativeRegisterArray: RegisterArray + WithBase {} + +/// Location of a relative array register. +pub struct RelativeRegisterArrayLoc< + T: RelativeRegisterArray, + B: RegisterBase + ?Sized, +>(RelativeRegisterLoc, usize); + +impl RelativeRegisterArrayLoc +where + T: RelativeRegisterArray, + B: RegisterBase + ?Sized, +{ + /// Returns the location of register `T` from the base `B` at index `idx`, with build-time + /// validation. + #[inline(always)] + pub fn new(idx: usize) -> Self { + build_assert!(idx < T::SIZE); + + Self(RelativeRegisterLoc::new(), idx) + } + + /// Attempts to return the location of register `T` from the base `B` at index `idx`, with + /// runtime validation. + #[inline(always)] + pub fn try_new(idx: usize) -> Option { + if idx < T::SIZE { + Some(Self(RelativeRegisterLoc::new(), idx)) + } else { + None + } + } +} + +/// Methods exclusive to [`RelativeRegisterLoc`]s created with a [`RelativeRegisterArray`]. +impl RelativeRegisterLoc +where + T: RelativeRegisterArray, + B: RegisterBase + ?Sized, +{ + /// Returns the location of the register at position `idx`, with build-time validation. + #[inline(always)] + pub fn at(self, idx: usize) -> RelativeRegisterArrayLoc { + RelativeRegisterArrayLoc::new(idx) + } + + /// Returns the location of the register at position `idx`, with runtime validation. + #[inline(always)] + pub fn try_at(self, idx: usize) -> Option> { + RelativeRegisterArrayLoc::try_new(idx) + } +} + +impl IoLoc for RelativeRegisterArrayLoc +where + T: RelativeRegisterArray, + B: RegisterBase + ?Sized, +{ + type IoType = T::Storage; + + #[inline(always)] + fn offset(self) -> usize { + self.0.offset() + self.1 * T::STRIDE + } +} + +/// Defines a dedicated type for a register, including getter and setter methods for its fields and +/// methods to read and write it from an [`Io`](kernel::io::Io) region. +/// +/// This documentation focuses on how to declare registers. See the [module-level +/// documentation](mod@kernel::io::register) for examples of how to access them. +/// +/// There are 4 possible kinds of registers: fixed offset registers, relative registers, arrays of +/// registers, and relative arrays of registers. +/// +/// ## Fixed offset registers +/// +/// These are the simplest kind of registers. Their location is simply an offset inside the I/O +/// region. For instance: +/// +/// ```ignore +/// register! { +/// pub FIXED_REG(u16) @ 0x80 { +/// ... +/// } +/// } +/// ``` +/// +/// This creates a 16-bit register named `FIXED_REG` located at offset `0x80` of an I/O region. +/// +/// These registers' location can be built simply by referencing their name: +/// +/// ```no_run +/// use kernel::{ +/// io::{ +/// register, +/// Io, +/// }, +/// }; +/// # use kernel::io::Mmio; +/// +/// register! { +/// FIXED_REG(u32) @ 0x100 { +/// 16:8 high_byte; +/// 7:0 low_byte; +/// } +/// } +/// +/// # fn test(io: &Mmio<0x1000>) { +/// let val = io.read(FIXED_REG); +/// +/// // Write from an already-existing value. +/// io.write(FIXED_REG, val.with_low_byte(0xff)); +/// +/// // Create a register value from scratch. +/// let val2 = FIXED_REG::zeroed().with_high_byte(0x80); +/// +/// // The location of fixed offset registers is already contained in their type. Thus, the +/// // `location` argument of `Io::write` is technically redundant and can be replaced by `()`. +/// io.write((), val2); +/// # } +/// +/// ``` +/// +/// It is possible to create an alias of an existing register with new field definitions by using +/// the `=> ALIAS` syntax. This is useful for cases where a register's interpretation depends on +/// the context: +/// +/// ```no_run +/// use kernel::io::register; +/// +/// register! { +/// /// Scratch register. +/// pub SCRATCH(u32) @ 0x00000200 { +/// 31:0 value; +/// } +/// +/// /// Boot status of the firmware. +/// pub SCRATCH_BOOT_STATUS(u32) => SCRATCH { +/// 0:0 completed; +/// } +/// } +/// ``` +/// +/// In this example, `SCRATCH_BOOT_STATUS` uses the same I/O address as `SCRATCH`, while providing +/// its own `completed` field. +/// +/// ## Relative registers +/// +/// Relative registers can be instantiated several times at a relative offset of a group of bases. +/// For instance, imagine the following I/O space: +/// +/// ```text +/// +-----------------------------+ +/// | ... | +/// | | +/// 0x100--->+------------CPU0-------------+ +/// | | +/// 0x110--->+-----------------------------+ +/// | CPU_CTL | +/// +-----------------------------+ +/// | ... | +/// | | +/// | | +/// 0x200--->+------------CPU1-------------+ +/// | | +/// 0x210--->+-----------------------------+ +/// | CPU_CTL | +/// +-----------------------------+ +/// | ... | +/// +-----------------------------+ +/// ``` +/// +/// `CPU0` and `CPU1` both have a `CPU_CTL` register that starts at offset `0x10` of their I/O +/// space segment. Since both instances of `CPU_CTL` share the same layout, we don't want to define +/// them twice and would prefer a way to select which one to use from a single definition. +/// +/// This can be done using the `Base + Offset` syntax when specifying the register's address: +/// +/// ```ignore +/// register! { +/// pub RELATIVE_REG(u32) @ Base + 0x80 { +/// ... +/// } +/// } +/// ``` +/// +/// This creates a register with an offset of `0x80` from a given base. +/// +/// `Base` is an arbitrary type (typically a ZST) to be used as a generic parameter of the +/// [`RegisterBase`] trait to provide the base as a constant, i.e. each type providing a base for +/// this register needs to implement `RegisterBase`. +/// +/// The location of relative registers can be built using the [`WithBase::of`] method to specify +/// its base. All relative registers implement [`WithBase`]. +/// +/// Here is the above layout translated into code: +/// +/// ```no_run +/// use kernel::{ +/// io::{ +/// register, +/// register::{ +/// RegisterBase, +/// WithBase, +/// }, +/// Io, +/// }, +/// }; +/// # use kernel::io::Mmio; +/// +/// // Type used to identify the base. +/// pub struct CpuCtlBase; +/// +/// // ZST describing `CPU0`. +/// struct Cpu0; +/// impl RegisterBase for Cpu0 { +/// const BASE: usize = 0x100; +/// } +/// +/// // ZST describing `CPU1`. +/// struct Cpu1; +/// impl RegisterBase for Cpu1 { +/// const BASE: usize = 0x200; +/// } +/// +/// // This makes `CPU_CTL` accessible from all implementors of `RegisterBase`. +/// register! { +/// /// CPU core control. +/// pub CPU_CTL(u32) @ CpuCtlBase + 0x10 { +/// 0:0 start; +/// } +/// } +/// +/// # fn test(io: Mmio<0x1000>) { +/// // Read the status of `Cpu0`. +/// let cpu0_started = io.read(CPU_CTL::of::()); +/// +/// // Stop `Cpu0`. +/// io.write(WithBase::of::(), CPU_CTL::zeroed()); +/// # } +/// +/// // Aliases can also be defined for relative register. +/// register! { +/// /// Alias to CPU core control. +/// pub CPU_CTL_ALIAS(u32) => CpuCtlBase + CPU_CTL { +/// /// Start the aliased CPU core. +/// 1:1 alias_start; +/// } +/// } +/// +/// # fn test2(io: Mmio<0x1000>) { +/// // Start the aliased `CPU0`, leaving its other fields untouched. +/// io.update(CPU_CTL_ALIAS::of::(), |r| r.with_alias_start(true)); +/// # } +/// ``` +/// +/// ## Arrays of registers +/// +/// Some I/O areas contain consecutive registers that share the same field layout. These areas can +/// be defined as an array of identical registers, allowing them to be accessed by index with +/// compile-time or runtime bound checking: +/// +/// ```ignore +/// register! { +/// pub REGISTER_ARRAY(u8)[10, stride = 4] @ 0x100 { +/// ... +/// } +/// } +/// ``` +/// +/// This defines `REGISTER_ARRAY`, an array of 10 byte registers starting at offset `0x100`. Each +/// register is separated from its neighbor by 4 bytes. +/// +/// The `stride` parameter is optional; if unspecified, the registers are placed consecutively from +/// each other. +/// +/// A location for a register in a register array is built using the [`Array::at`] trait method. +/// All arrays of registers implement [`Array`]. +/// +/// ```no_run +/// use kernel::{ +/// io::{ +/// register, +/// register::Array, +/// Io, +/// }, +/// }; +/// # use kernel::io::Mmio; +/// # fn get_scratch_idx() -> usize { +/// # 0x15 +/// # } +/// +/// // Array of 64 consecutive registers with the same layout starting at offset `0x80`. +/// register! { +/// /// Scratch registers. +/// pub SCRATCH(u32)[64] @ 0x00000080 { +/// 31:0 value; +/// } +/// } +/// +/// # fn test(io: &Mmio<0x1000>) +/// # -> Result<(), Error>{ +/// // Read scratch register 0, i.e. I/O address `0x80`. +/// let scratch_0 = io.read(SCRATCH::at(0)).value(); +/// +/// // Write scratch register 15, i.e. I/O address `0x80 + (15 * 4)`. +/// io.write(Array::at(15), SCRATCH::from(0xffeeaabb)); +/// +/// // This is out of bounds and won't build. +/// // let scratch_128 = io.read(SCRATCH::at(128)).value(); +/// +/// // Runtime-obtained array index. +/// let idx = get_scratch_idx(); +/// // Access on a runtime index returns an error if it is out-of-bounds. +/// let some_scratch = io.read(SCRATCH::try_at(idx).ok_or(EINVAL)?).value(); +/// +/// // Alias to a specific register in an array. +/// // Here `SCRATCH[8]` is used to convey the firmware exit code. +/// register! { +/// /// Firmware exit status code. +/// pub FIRMWARE_STATUS(u32) => SCRATCH[8] { +/// 7:0 status; +/// } +/// } +/// +/// let status = io.read(FIRMWARE_STATUS).status(); +/// +/// // Non-contiguous register arrays can be defined by adding a stride parameter. +/// // Here, each of the 16 registers of the array is separated by 8 bytes, meaning that the +/// // registers of the two declarations below are interleaved. +/// register! { +/// /// Scratch registers bank 0. +/// pub SCRATCH_INTERLEAVED_0(u32)[16, stride = 8] @ 0x000000c0 { +/// 31:0 value; +/// } +/// +/// /// Scratch registers bank 1. +/// pub SCRATCH_INTERLEAVED_1(u32)[16, stride = 8] @ 0x000000c4 { +/// 31:0 value; +/// } +/// } +/// # Ok(()) +/// # } +/// ``` +/// +/// ## Relative arrays of registers +/// +/// Combining the two features described in the sections above, arrays of registers accessible from +/// a base can also be defined: +/// +/// ```ignore +/// register! { +/// pub RELATIVE_REGISTER_ARRAY(u8)[10, stride = 4] @ Base + 0x100 { +/// ... +/// } +/// } +/// ``` +/// +/// Like relative registers, they implement the [`WithBase`] trait. However the return value of +/// [`WithBase::of`] cannot be used directly as a location and must be further specified using the +/// [`at`](RelativeRegisterLoc::at) method. +/// +/// ```no_run +/// use kernel::{ +/// io::{ +/// register, +/// register::{ +/// RegisterBase, +/// WithBase, +/// }, +/// Io, +/// }, +/// }; +/// # use kernel::io::Mmio; +/// # fn get_scratch_idx() -> usize { +/// # 0x15 +/// # } +/// +/// // Type used as parameter of `RegisterBase` to specify the base. +/// pub struct CpuCtlBase; +/// +/// // ZST describing `CPU0`. +/// struct Cpu0; +/// impl RegisterBase for Cpu0 { +/// const BASE: usize = 0x100; +/// } +/// +/// // ZST describing `CPU1`. +/// struct Cpu1; +/// impl RegisterBase for Cpu1 { +/// const BASE: usize = 0x200; +/// } +/// +/// // 64 per-cpu scratch registers, arranged as a contiguous array. +/// register! { +/// /// Per-CPU scratch registers. +/// pub CPU_SCRATCH(u32)[64] @ CpuCtlBase + 0x00000080 { +/// 31:0 value; +/// } +/// } +/// +/// # fn test(io: &Mmio<0x1000>) -> Result<(), Error> { +/// // Read scratch register 0 of CPU0. +/// let scratch = io.read(CPU_SCRATCH::of::().at(0)); +/// +/// // Write the retrieved value into scratch register 15 of CPU1. +/// io.write(WithBase::of::().at(15), scratch); +/// +/// // This won't build. +/// // let cpu0_scratch_128 = io.read(CPU_SCRATCH::of::().at(128)).value(); +/// +/// // Runtime-obtained array index. +/// let scratch_idx = get_scratch_idx(); +/// // Access on a runtime index returns an error if it is out-of-bounds. +/// let cpu0_scratch = io.read( +/// CPU_SCRATCH::of::().try_at(scratch_idx).ok_or(EINVAL)? +/// ).value(); +/// # Ok(()) +/// # } +/// +/// // Alias to `SCRATCH[8]` used to convey the firmware exit code. +/// register! { +/// /// Per-CPU firmware exit status code. +/// pub CPU_FIRMWARE_STATUS(u32) => CpuCtlBase + CPU_SCRATCH[8] { +/// 7:0 status; +/// } +/// } +/// +/// // Non-contiguous relative register arrays can be defined by adding a stride parameter. +/// // Here, each of the 16 registers of the array is separated by 8 bytes, meaning that the +/// // registers of the two declarations below are interleaved. +/// register! { +/// /// Scratch registers bank 0. +/// pub CPU_SCRATCH_INTERLEAVED_0(u32)[16, stride = 8] @ CpuCtlBase + 0x00000d00 { +/// 31:0 value; +/// } +/// +/// /// Scratch registers bank 1. +/// pub CPU_SCRATCH_INTERLEAVED_1(u32)[16, stride = 8] @ CpuCtlBase + 0x00000d04 { +/// 31:0 value; +/// } +/// } +/// +/// # fn test2(io: &Mmio<0x1000>) -> Result<(), Error> { +/// let cpu0_status = io.read(CPU_FIRMWARE_STATUS::of::()).status(); +/// # Ok(()) +/// # } +/// ``` +#[macro_export] +macro_rules! register { + // Entry point for the macro, allowing multiple registers to be defined in one call. + // It matches all possible register declaration patterns to dispatch them to corresponding + // `@reg` rule that defines a single register. + ( + $( + $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) + $([ $size:expr $(, stride = $stride:expr)? ])? + $(@ $($base:ident +)? $offset:literal)? + $(=> $alias:ident $(+ $alias_offset:ident)? $([$alias_idx:expr])? )? + { $($fields:tt)* } + )* + ) => { + $( + $crate::register!( + @reg $(#[$attr])* $vis $name ($storage) $([$size $(, stride = $stride)?])? + $(@ $($base +)? $offset)? + $(=> $alias $(+ $alias_offset)? $([$alias_idx])? )? + { $($fields)* } + ); + )* + }; + + // All the rules below are private helpers. + + // Creates a register at a fixed offset of the MMIO space. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) @ $offset:literal + { $($fields:tt)* } + ) => { + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!(@io_base $name($storage) @ $offset); + $crate::register!(@io_fixed $(#[$attr])* $vis $name($storage)); + }; + + // Creates an alias register of fixed offset register `alias` with its own fields. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) => $alias:ident + { $($fields:tt)* } + ) => { + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!( + @io_base $name($storage) @ + <$alias as $crate::io::register::Register>::OFFSET + ); + $crate::register!(@io_fixed $(#[$attr])* $vis $name($storage)); + }; + + // Creates a register at a relative offset from a base address provider. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) @ $base:ident + $offset:literal + { $($fields:tt)* } + ) => { + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!(@io_base $name($storage) @ $offset); + $crate::register!(@io_relative $vis $name($storage) @ $base); + }; + + // Creates an alias register of relative offset register `alias` with its own fields. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) => $base:ident + $alias:ident + { $($fields:tt)* } + ) => { + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!( + @io_base $name($storage) @ <$alias as $crate::io::register::Register>::OFFSET + ); + $crate::register!(@io_relative $vis $name($storage) @ $base); + }; + + // Creates an array of registers at a fixed offset of the MMIO space. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) + [ $size:expr, stride = $stride:expr ] @ $offset:literal { $($fields:tt)* } + ) => { + ::kernel::static_assert!(::core::mem::size_of::<$storage>() <= $stride); + + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!(@io_base $name($storage) @ $offset); + $crate::register!(@io_array $vis $name($storage) [ $size, stride = $stride ]); + }; + + // Shortcut for contiguous array of registers (stride == size of element). + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) [ $size:expr ] @ $offset:literal + { $($fields:tt)* } + ) => { + $crate::register!( + $(#[$attr])* $vis $name($storage) [ $size, stride = ::core::mem::size_of::<$storage>() ] + @ $offset { $($fields)* } + ); + }; + + // Creates an alias of register `idx` of array of registers `alias` with its own fields. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) => $alias:ident [ $idx:expr ] + { $($fields:tt)* } + ) => { + ::kernel::static_assert!($idx < <$alias as $crate::io::register::RegisterArray>::SIZE); + + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!( + @io_base $name($storage) @ + <$alias as $crate::io::register::Register>::OFFSET + + $idx * <$alias as $crate::io::register::RegisterArray>::STRIDE + ); + $crate::register!(@io_fixed $(#[$attr])* $vis $name($storage)); + }; + + // Creates an array of registers at a relative offset from a base address provider. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) + [ $size:expr, stride = $stride:expr ] + @ $base:ident + $offset:literal { $($fields:tt)* } + ) => { + ::kernel::static_assert!(::core::mem::size_of::<$storage>() <= $stride); + + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!(@io_base $name($storage) @ $offset); + $crate::register!( + @io_relative_array $vis $name($storage) [ $size, stride = $stride ] @ $base + $offset + ); + }; + + // Shortcut for contiguous array of relative registers (stride == size of element). + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) [ $size:expr ] + @ $base:ident + $offset:literal { $($fields:tt)* } + ) => { + $crate::register!( + $(#[$attr])* $vis $name($storage) [ $size, stride = ::core::mem::size_of::<$storage>() ] + @ $base + $offset { $($fields)* } + ); + }; + + // Creates an alias of register `idx` of relative array of registers `alias` with its own + // fields. + ( + @reg $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty) + => $base:ident + $alias:ident [ $idx:expr ] { $($fields:tt)* } + ) => { + ::kernel::static_assert!($idx < <$alias as $crate::io::register::RegisterArray>::SIZE); + + $crate::register!(@bitfield $(#[$attr])* $vis struct $name($storage) { $($fields)* }); + $crate::register!( + @io_base $name($storage) @ + <$alias as $crate::io::register::Register>::OFFSET + + $idx * <$alias as $crate::io::register::RegisterArray>::STRIDE + ); + $crate::register!(@io_relative $vis $name($storage) @ $base); + }; + + // Generates the bitfield for the register. + // + // `#[allow(non_camel_case_types)]` is added since register names typically use + // `SCREAMING_CASE`. + ( + @bitfield $(#[$attr:meta])* $vis:vis struct $name:ident($storage:ty) { $($fields:tt)* } + ) => { + $crate::register!(@bitfield_core + #[allow(non_camel_case_types)] + $(#[$attr])* $vis $name $storage + ); + $crate::register!(@bitfield_fields $vis $name $storage { $($fields)* }); + }; + + // Implementations shared by all registers types. + (@io_base $name:ident($storage:ty) @ $offset:expr) => { + impl $crate::io::register::Register for $name { + type Storage = $storage; + + const OFFSET: usize = $offset; + } + }; + + // Implementations of fixed registers. + (@io_fixed $(#[$attr:meta])* $vis:vis $name:ident ($storage:ty)) => { + impl $crate::io::register::FixedRegister for $name {} + + $(#[$attr])* + $vis const $name: $crate::io::register::FixedRegisterLoc<$name> = + $crate::io::register::FixedRegisterLoc::<$name>::new(); + }; + + // Implementations of relative registers. + (@io_relative $vis:vis $name:ident ($storage:ty) @ $base:ident) => { + impl $crate::io::register::WithBase for $name { + type BaseFamily = $base; + } + + impl $crate::io::register::RelativeRegister for $name {} + }; + + // Implementations of register arrays. + (@io_array $vis:vis $name:ident ($storage:ty) [ $size:expr, stride = $stride:expr ]) => { + impl $crate::io::register::Array for $name {} + + impl $crate::io::register::RegisterArray for $name { + const SIZE: usize = $size; + const STRIDE: usize = $stride; + } + }; + + // Implementations of relative array registers. + ( + @io_relative_array $vis:vis $name:ident ($storage:ty) [ $size:expr, stride = $stride:expr ] + @ $base:ident + $offset:literal + ) => { + impl $crate::io::register::WithBase for $name { + type BaseFamily = $base; + } + + impl $crate::io::register::RegisterArray for $name { + const SIZE: usize = $size; + const STRIDE: usize = $stride; + } + + impl $crate::io::register::RelativeRegisterArray for $name {} + }; + + // Defines the wrapper `$name` type and its conversions from/to the storage type. + (@bitfield_core $(#[$attr:meta])* $vis:vis $name:ident $storage:ty) => { + $(#[$attr])* + #[repr(transparent)] + #[derive(Clone, Copy, PartialEq, Eq)] + $vis struct $name { + inner: $storage, + } + + #[allow(dead_code)] + impl $name { + /// Creates a bitfield from a raw value. + #[inline(always)] + $vis const fn from_raw(value: $storage) -> Self { + Self{ inner: value } + } + + /// Turns this bitfield into its raw value. + /// + /// This is similar to the [`From`] implementation, but is shorter to invoke in + /// most cases. + #[inline(always)] + $vis const fn into_raw(self) -> $storage { + self.inner + } + } + + // SAFETY: `$storage` is `Zeroable` and `$name` is transparent. + unsafe impl ::pin_init::Zeroable for $name {} + + impl ::core::convert::From<$name> for $storage { + #[inline(always)] + fn from(val: $name) -> $storage { + val.into_raw() + } + } + + impl ::core::convert::From<$storage> for $name { + #[inline(always)] + fn from(val: $storage) -> $name { + Self::from_raw(val) + } + } + }; + + // Definitions requiring knowledge of individual fields: private and public field accessors, + // and `Debug` implementation. + (@bitfield_fields $vis:vis $name:ident $storage:ty { + $($(#[doc = $doc:expr])* $hi:literal:$lo:literal $field:ident + $(?=> $try_into_type:ty)? + $(=> $into_type:ty)? + ; + )* + } + ) => { + #[allow(dead_code)] + impl $name { + $( + $crate::register!(@private_field_accessors $vis $name $storage : $hi:$lo $field); + $crate::register!( + @public_field_accessors $(#[doc = $doc])* $vis $name $storage : $hi:$lo $field + $(?=> $try_into_type)? + $(=> $into_type)? + ); + )* + } + + $crate::register!(@debug $name { $($field;)* }); + }; + + // Private field accessors working with the exact `Bounded` type for the field. + ( + @private_field_accessors $vis:vis $name:ident $storage:ty : $hi:tt:$lo:tt $field:ident + ) => { + ::kernel::macros::paste!( + $vis const [<$field:upper _RANGE>]: ::core::ops::RangeInclusive = $lo..=$hi; + $vis const [<$field:upper _MASK>]: $storage = + ((((1 << $hi) - 1) << 1) + 1) - ((1 << $lo) - 1); + $vis const [<$field:upper _SHIFT>]: u32 = $lo; + ); + + ::kernel::macros::paste!( + fn [<__ $field>](self) -> + ::kernel::num::Bounded<$storage, { $hi + 1 - $lo }> { + // Left shift to align the field's MSB with the storage MSB. + const ALIGN_TOP: u32 = $storage::BITS - ($hi + 1); + // Right shift to move the top-aligned field to bit 0 of the storage. + const ALIGN_BOTTOM: u32 = ALIGN_TOP + $lo; + + // Extract the field using two shifts. `Bounded::shr` produces the correctly-sized + // output type. + let val = ::kernel::num::Bounded::<$storage, { $storage::BITS }>::from( + self.inner << ALIGN_TOP + ); + val.shr::() + } + + const fn [<__with_ $field>]( + mut self, + value: ::kernel::num::Bounded<$storage, { $hi + 1 - $lo }>, + ) -> Self + { + const MASK: $storage = <$name>::[<$field:upper _MASK>]; + const SHIFT: u32 = <$name>::[<$field:upper _SHIFT>]; + + let value = value.get() << SHIFT; + self.inner = (self.inner & !MASK) | value; + + self + } + ); + }; + + // Public accessors for fields infallibly (`=>`) converted to a type. + ( + @public_field_accessors $(#[doc = $doc:expr])* $vis:vis $name:ident $storage:ty : + $hi:literal:$lo:literal $field:ident => $into_type:ty + ) => { + ::kernel::macros::paste!( + + $(#[doc = $doc])* + #[doc = "Returns the value of this field."] + #[inline(always)] + $vis fn $field(self) -> $into_type + { + self.[<__ $field>]().into() + } + + $(#[doc = $doc])* + #[doc = "Sets this field to the given `value`."] + #[inline(always)] + $vis fn [](self, value: $into_type) -> Self + { + self.[<__with_ $field>](value.into()) + } + + ); + }; + + // Public accessors for fields fallibly (`?=>`) converted to a type. + ( + @public_field_accessors $(#[doc = $doc:expr])* $vis:vis $name:ident $storage:ty : + $hi:tt:$lo:tt $field:ident ?=> $try_into_type:ty + ) => { + ::kernel::macros::paste!( + + $(#[doc = $doc])* + #[doc = "Returns the value of this field."] + #[inline(always)] + $vis fn $field(self) -> + Result< + $try_into_type, + <$try_into_type as ::core::convert::TryFrom< + ::kernel::num::Bounded<$storage, { $hi + 1 - $lo }> + >>::Error + > + { + self.[<__ $field>]().try_into() + } + + $(#[doc = $doc])* + #[doc = "Sets this field to the given `value`."] + #[inline(always)] + $vis fn [](self, value: $try_into_type) -> Self + { + self.[<__with_ $field>](value.into()) + } + + ); + }; + + // Public accessors for fields not converted to a type. + ( + @public_field_accessors $(#[doc = $doc:expr])* $vis:vis $name:ident $storage:ty : + $hi:tt:$lo:tt $field:ident + ) => { + ::kernel::macros::paste!( + + $(#[doc = $doc])* + #[doc = "Returns the value of this field."] + #[inline(always)] + $vis fn $field(self) -> + ::kernel::num::Bounded<$storage, { $hi + 1 - $lo }> + { + self.[<__ $field>]() + } + + $(#[doc = $doc])* + #[doc = "Sets this field to the compile-time constant `VALUE`."] + #[inline(always)] + $vis const fn [](self) -> Self { + self.[<__with_ $field>]( + ::kernel::num::Bounded::<$storage, { $hi + 1 - $lo }>::new::() + ) + } + + $(#[doc = $doc])* + #[doc = "Sets this field to the given `value`."] + #[inline(always)] + $vis fn []( + self, + value: T, + ) -> Self + where T: Into<::kernel::num::Bounded<$storage, { $hi + 1 - $lo }>>, + { + self.[<__with_ $field>](value.into()) + } + + $(#[doc = $doc])* + #[doc = "Tries to set this field to `value`, returning an error if it is out of range."] + #[inline(always)] + $vis fn []( + self, + value: T, + ) -> ::kernel::error::Result + where T: ::kernel::num::TryIntoBounded<$storage, { $hi + 1 - $lo }>, + { + Ok( + self.[<__with_ $field>]( + value.try_into_bounded().ok_or(::kernel::error::code::EOVERFLOW)? + ) + ) + } + + ); + }; + + // `Debug` implementation. + (@debug $name:ident { $($field:ident;)* }) => { + impl ::kernel::fmt::Debug for $name { + fn fmt(&self, f: &mut ::kernel::fmt::Formatter<'_>) -> ::kernel::fmt::Result { + f.debug_struct(stringify!($name)) + .field("", &::kernel::prelude::fmt!("{:#x}", self.inner)) + $( + .field(stringify!($field), &self.$field()) + )* + .finish() + } + } + }; +} From 9a52a8f5ed97d47c9641248874f4c6a78e136d97 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:18 +0900 Subject: [PATCH 486/487] rust: io: introduce `write_reg` and `LocatedRegister` Some I/O types, like fixed address registers, carry their location alongside their values. For these types, the regular `Io::write` method can lead into repeating the location information twice: once to provide the location itself, another time to build the value. We are also considering supporting making all register values carry their full location information for convenience and safety. Add a new `Io::write_reg` method that takes a single argument implementing `LocatedRegister`, a trait that decomposes implementors into a `(location, value)` tuple. This allows write operations on fixed offset registers to be done while specifying their name only once. Suggested-by: Danilo Krummrich Link: https://lore.kernel.org/all/DH0XBLXZD81K.22SWIZ1ZAOW1@kernel.org/ Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-8-86805b2f7e9d@nvidia.com [ Replace FIFO with VERSION register in the examples. - Danilo ] Signed-off-by: Danilo Krummrich --- rust/kernel/io.rs | 87 ++++++++++++++++++++++++++++++++++++++ rust/kernel/io/register.rs | 35 ++++++++++++++- 2 files changed, 120 insertions(+), 2 deletions(-) diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index 4950cecf30ca..fcc7678fd9e3 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -17,6 +17,8 @@ pub use crate::register; pub use resource::Resource; +use register::LocatedRegister; + /// Physical address type. /// /// This is a type alias to either `u32` or `u64` depending on the config option @@ -473,6 +475,49 @@ fn try_write(&self, location: L, value: T) -> Result Ok(()) } + /// Generic fallible write of a fully-located register value. + /// + /// # Examples + /// + /// Tuples carrying a location and a value can be used with this method: + /// + /// ```no_run + /// use kernel::io::{ + /// register, + /// Io, + /// Mmio, + /// }; + /// + /// register! { + /// VERSION(u32) @ 0x100 { + /// 15:8 major; + /// 7:0 minor; + /// } + /// } + /// + /// impl VERSION { + /// fn new(major: u8, minor: u8) -> Self { + /// VERSION::zeroed().with_major(major).with_minor(minor) + /// } + /// } + /// + /// fn do_write_reg(io: &Mmio) -> Result { + /// + /// io.try_write_reg(VERSION::new(1, 0)) + /// } + /// ``` + #[inline(always)] + fn try_write_reg(&self, value: V) -> Result + where + L: IoLoc, + V: LocatedRegister, + Self: IoCapable, + { + let (location, value) = value.into_io_op(); + + self.try_write(location, value) + } + /// Generic fallible update with runtime bounds check. /// /// Note: this does not perform any synchronization. The caller is responsible for ensuring @@ -578,6 +623,48 @@ fn write(&self, location: L, value: T) unsafe { self.io_write(io_value, address) } } + /// Generic infallible write of a fully-located register value. + /// + /// # Examples + /// + /// Tuples carrying a location and a value can be used with this method: + /// + /// ```no_run + /// use kernel::io::{ + /// register, + /// Io, + /// Mmio, + /// }; + /// + /// register! { + /// VERSION(u32) @ 0x100 { + /// 15:8 major; + /// 7:0 minor; + /// } + /// } + /// + /// impl VERSION { + /// fn new(major: u8, minor: u8) -> Self { + /// VERSION::zeroed().with_major(major).with_minor(minor) + /// } + /// } + /// + /// fn do_write_reg(io: &Mmio<0x1000>) { + /// io.write_reg(VERSION::new(1, 0)); + /// } + /// ``` + #[inline(always)] + fn write_reg(&self, value: V) + where + L: IoLoc, + V: LocatedRegister, + Self: IoKnownSize + IoCapable, + { + let (location, value) = value.into_io_op(); + + self.write(location, value) + } + /// Generic infallible update with compile-time bounds check. /// /// Note: this does not perform any synchronization. The caller is responsible for ensuring diff --git a/rust/kernel/io/register.rs b/rust/kernel/io/register.rs index dbd458aaa761..abc49926abfe 100644 --- a/rust/kernel/io/register.rs +++ b/rust/kernel/io/register.rs @@ -80,10 +80,10 @@ //! .with_const_minor_revision::<10>() //! // Runtime value. //! .with_vendor_id(obtain_vendor_id()); -//! io.write((), new_boot0); +//! io.write_reg(new_boot0); //! //! // Or, build a new value from zero and write it: -//! io.write((), BOOT_0::zeroed() +//! io.write_reg(BOOT_0::zeroed() //! .with_const_major_revision::<3>() //! .with_const_minor_revision::<10>() //! .with_vendor_id(obtain_vendor_id()) @@ -382,6 +382,34 @@ fn offset(self) -> usize { } } +/// Trait implemented by items that contain both a register value and the absolute I/O location at +/// which to write it. +/// +/// Implementors can be used with [`Io::write_reg`](super::Io::write_reg). +pub trait LocatedRegister { + /// Register value to write. + type Value: Register; + /// Full location information at which to write the value. + type Location: IoLoc; + + /// Consumes `self` and returns a `(location, value)` tuple describing a valid I/O write + /// operation. + fn into_io_op(self) -> (Self::Location, Self::Value); +} + +impl LocatedRegister for T +where + T: FixedRegister, +{ + type Location = FixedRegisterLoc; + type Value = T; + + #[inline(always)] + fn into_io_op(self) -> (FixedRegisterLoc, T) { + (FixedRegisterLoc::new(), self) + } +} + /// Defines a dedicated type for a register, including getter and setter methods for its fields and /// methods to read and write it from an [`Io`](kernel::io::Io) region. /// @@ -436,6 +464,9 @@ fn offset(self) -> usize { /// // The location of fixed offset registers is already contained in their type. Thus, the /// // `location` argument of `Io::write` is technically redundant and can be replaced by `()`. /// io.write((), val2); +/// +/// // Or, the single-argument `Io::write_reg` can be used. +/// io.write_reg(val2); /// # } /// /// ``` From 79cf41692aadc3d0ac9b1d8e2c2f620ce2103918 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 14 Mar 2026 10:06:19 +0900 Subject: [PATCH 487/487] sample: rust: pci: use `register!` macro Convert the direct IO accesses to properly defined registers. Tested-by: Zhi Wang Signed-off-by: Alexandre Courbot Link: https://patch.msgid.link/20260314-register-v9-9-86805b2f7e9d@nvidia.com [ Fix up kernel import style. - Danilo ] Signed-off-by: Danilo Krummrich --- samples/rust/rust_driver_pci.rs | 90 +++++++++++++++++++++++++-------- 1 file changed, 68 insertions(+), 22 deletions(-) diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs index d3d4a7931deb..47d3e84fab63 100644 --- a/samples/rust/rust_driver_pci.rs +++ b/samples/rust/rust_driver_pci.rs @@ -5,30 +5,63 @@ //! To make this driver probe, QEMU must be run with `-device pci-testdev`. use kernel::{ - device::Bound, - device::Core, + device::{ + Bound, + Core, // + }, devres::Devres, - io::Io, + io::{ + register, + register::Array, + Io, // + }, + num::Bounded, pci, prelude::*, sync::aref::ARef, // }; -struct Regs; +mod regs { + use super::*; -impl Regs { - const TEST: usize = 0x0; - const OFFSET: usize = 0x4; - const DATA: usize = 0x8; - const COUNT: usize = 0xC; - const END: usize = 0x10; + register! { + pub(super) TEST(u8) @ 0x0 { + 7:0 index => TestIndex; + } + + pub(super) OFFSET(u32) @ 0x4 { + 31:0 offset; + } + + pub(super) DATA(u8) @ 0x8 { + 7:0 data; + } + + pub(super) COUNT(u32) @ 0xC { + 31:0 count; + } + } + + pub(super) const END: usize = 0x10; } -type Bar0 = pci::Bar<{ Regs::END }>; +type Bar0 = pci::Bar<{ regs::END }>; #[derive(Copy, Clone, Debug)] struct TestIndex(u8); +impl From> for TestIndex { + fn from(value: Bounded) -> Self { + Self(value.into()) + } +} + +impl From for Bounded { + fn from(value: TestIndex) -> Self { + value.0.into() + } +} + impl TestIndex { const NO_EVENTFD: Self = Self(0); } @@ -54,40 +87,53 @@ struct SampleDriver { impl SampleDriver { fn testdev(index: &TestIndex, bar: &Bar0) -> Result { // Select the test. - bar.write8(index.0, Regs::TEST); + bar.write_reg(regs::TEST::zeroed().with_index(*index)); - let offset = bar.read32(Regs::OFFSET) as usize; - let data = bar.read8(Regs::DATA); + let offset = bar.read(regs::OFFSET).into_raw() as usize; + let data = bar.read(regs::DATA).into(); // Write `data` to `offset` to increase `count` by one. // // Note that we need `try_write8`, since `offset` can't be checked at compile-time. bar.try_write8(data, offset)?; - Ok(bar.read32(Regs::COUNT)) + Ok(bar.read(regs::COUNT).into()) } fn config_space(pdev: &pci::Device) { let config = pdev.config_space(); - // TODO: use the register!() macro for defining PCI configuration space registers once it - // has been move out of nova-core. + // Some PCI configuration space registers. + register! { + VENDOR_ID(u16) @ 0x0 { + 15:0 vendor_id; + } + + REVISION_ID(u8) @ 0x8 { + 7:0 revision_id; + } + + BAR(u32)[6] @ 0x10 { + 31:0 value; + } + } + dev_info!( pdev, "pci-testdev config space read8 rev ID: {:x}\n", - config.read8(0x8) + config.read(REVISION_ID).revision_id() ); dev_info!( pdev, "pci-testdev config space read16 vendor ID: {:x}\n", - config.read16(0) + config.read(VENDOR_ID).vendor_id() ); dev_info!( pdev, "pci-testdev config space read32 BAR 0: {:x}\n", - config.read32(0x10) + config.read(BAR::at(0)).value() ); } } @@ -111,7 +157,7 @@ fn probe(pdev: &pci::Device, info: &Self::IdInfo) -> impl PinInit(0, c"rust_driver_pci"), + bar <- pdev.iomap_region_sized::<{ regs::END }>(0, c"rust_driver_pci"), index: *info, _: { let bar = bar.access(pdev.as_ref())?; @@ -131,7 +177,7 @@ fn probe(pdev: &pci::Device, info: &Self::IdInfo) -> impl PinInit, this: Pin<&Self>) { if let Ok(bar) = this.bar.access(pdev.as_ref()) { // Reset pci-testdev by writing a new test index. - bar.write8(this.index.0, Regs::TEST); + bar.write_reg(regs::TEST::zeroed().with_index(this.index)); } } }