diff options
Diffstat (limited to 'include')
78 files changed, 569 insertions, 285 deletions
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index eeb070f330bd..1e1580febe4b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -848,12 +848,14 @@ /* Required sections not related to debugging. */ #define ELF_DETAILS \ - .modinfo : { *(.modinfo) . = ALIGN(8); } \ .comment 0 : { *(.comment) } \ .symtab 0 : { *(.symtab) } \ .strtab 0 : { *(.strtab) } \ .shstrtab 0 : { *(.shstrtab) } +#define MODINFO \ + .modinfo : { *(.modinfo) . = ALIGN(8); } + #ifdef CONFIG_GENERIC_BUG #define BUG_TABLE \ . = ALIGN(8); \ diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index e4eebabab975..8b15d3eeb716 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -571,6 +571,8 @@ # define DP_PANEL_REPLAY_LINK_OFF_SUPPORTED_IN_PR_AFTER_ADAPTIVE_SYNC_SDP (1 << 7) #define DP_PANEL_REPLAY_CAP_X_GRANULARITY 0xb2 +# define DP_PANEL_REPLAY_FULL_LINE_GRANULARITY 0xffff + #define DP_PANEL_REPLAY_CAP_Y_GRANULARITY 0xb4 /* Link Configuration */ diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h index c89b1b1b12dd..bfe60d6cf28d 100644 --- a/include/kunit/run-in-irq-context.h +++ b/include/kunit/run-in-irq-context.h @@ -12,16 +12,16 @@ #include <linux/hrtimer.h> #include <linux/workqueue.h> -#define KUNIT_IRQ_TEST_HRTIMER_INTERVAL us_to_ktime(5) - struct kunit_irq_test_state { bool (*func)(void *test_specific_state); void *test_specific_state; bool task_func_reported_failure; bool hardirq_func_reported_failure; bool softirq_func_reported_failure; + atomic_t task_func_calls; atomic_t hardirq_func_calls; atomic_t softirq_func_calls; + ktime_t interval; struct hrtimer timer; struct work_struct bh_work; }; @@ -30,14 +30,25 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer) { struct kunit_irq_test_state *state = container_of(timer, typeof(*state), timer); + int task_calls, hardirq_calls, softirq_calls; WARN_ON_ONCE(!in_hardirq()); - atomic_inc(&state->hardirq_func_calls); + task_calls = atomic_read(&state->task_func_calls); + hardirq_calls = atomic_inc_return(&state->hardirq_func_calls); + softirq_calls = atomic_read(&state->softirq_func_calls); + + /* + * If the timer is firing too often for the softirq or task to ever have + * a chance to run, increase the timer interval. This is needed on very + * slow systems. + */ + if (hardirq_calls >= 20 && (softirq_calls == 0 || task_calls == 0)) + state->interval = ktime_add_ns(state->interval, 250); if (!state->func(state->test_specific_state)) state->hardirq_func_reported_failure = true; - hrtimer_forward_now(&state->timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL); + hrtimer_forward_now(&state->timer, state->interval); queue_work(system_bh_wq, &state->bh_work); return HRTIMER_RESTART; } @@ -86,10 +97,14 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), struct kunit_irq_test_state state = { .func = func, .test_specific_state = test_specific_state, + /* + * Start with a 5us timer interval. If the system can't keep + * up, kunit_irq_test_timer_func() will increase it. + */ + .interval = us_to_ktime(5), }; unsigned long end_jiffies; - int hardirq_calls, softirq_calls; - bool allctx = false; + int task_calls, hardirq_calls, softirq_calls; /* * Set up a hrtimer (the way we access hardirq context) and a work @@ -104,21 +119,18 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), * and hardirq), or 1 second, whichever comes first. */ end_jiffies = jiffies + HZ; - hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL, - HRTIMER_MODE_REL_HARD); - for (int task_calls = 0, calls = 0; - ((calls < max_iterations) || !allctx) && - !time_after(jiffies, end_jiffies); - task_calls++) { + hrtimer_start(&state.timer, state.interval, HRTIMER_MODE_REL_HARD); + do { if (!func(test_specific_state)) state.task_func_reported_failure = true; + task_calls = atomic_inc_return(&state.task_func_calls); hardirq_calls = atomic_read(&state.hardirq_func_calls); softirq_calls = atomic_read(&state.softirq_func_calls); - calls = task_calls + hardirq_calls + softirq_calls; - allctx = (task_calls > 0) && (hardirq_calls > 0) && - (softirq_calls > 0); - } + } while ((task_calls + hardirq_calls + softirq_calls < max_iterations || + (task_calls == 0 || hardirq_calls == 0 || + softirq_calls == 0)) && + !time_after(jiffies, end_jiffies)); /* Cancel the timer and work. */ hrtimer_cancel(&state.timer); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b78b53198a2e..05b34a6355b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -124,7 +124,7 @@ struct bpf_map_ops { u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); - int (*map_check_btf)(const struct bpf_map *map, + int (*map_check_btf)(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); @@ -656,7 +656,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map) map->ops->map_seq_show_elem; } -int map_check_no_btf(const struct bpf_map *map, +int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 85efa9772530..8157e8da61d4 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -176,7 +176,7 @@ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage); void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache); -int bpf_local_storage_map_check_btf(const struct bpf_map *map, +int bpf_local_storage_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index e45162ef59bb..4ce0d27f8ea2 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -14,6 +14,8 @@ struct bpf_mem_alloc { struct obj_cgroup *objcg; bool percpu; struct work_struct work; + void (*dtor_ctx_free)(void *ctx); + void *dtor_ctx; }; /* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects. @@ -32,6 +34,10 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg /* The percpu allocation with a specific unit size. */ int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma, + void (*dtor)(void *obj, void *ctx), + void (*dtor_ctx_free)(void *ctx), + void *ctx); /* Check the allocation size for kmalloc equivalent allocator */ int bpf_mem_alloc_check_size(bool percpu, size_t size); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 99c3c83ea520..63de5f053c33 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -35,6 +35,8 @@ struct fwnode_handle; * otherwise. It may also return error code if determining that * the driver supports the device is not possible. In case of * -EPROBE_DEFER it will queue the device for deferred probing. + * Note: This callback may be invoked with or without the device + * lock held. * @uevent: Called when a device is added, removed, or a few other things * that generate uevents to add the environment variables. * @probe: Called when a new device or driver add to this bus, and callback diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index ccb478eb174b..ea9ca0e4172a 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -82,11 +82,14 @@ static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { - if (__put_user(revents, &uevent->events) || - __put_user(data, &uevent->data)) - return NULL; - + scoped_user_write_access_size(uevent, sizeof(*uevent), efault) { + unsafe_put_user(revents, &uevent->events, efault); + unsafe_put_user(data, &uevent->data, efault); + } return uevent+1; + +efault: + return NULL; } #endif 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; diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 28a9cb13fbfa..079c18bcdbde 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -495,19 +495,6 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) fsnotify_dentry(dentry, mask); } -static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, - int error) -{ - struct fs_error_report report = { - .error = error, - .inode = inode, - .sb = sb, - }; - - return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, - NULL, NULL, NULL, 0); -} - static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_ATTACH, ns, mnt); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2b30a0529d48..51ef13ed756e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -14,8 +14,8 @@ struct vm_area_struct; struct mempolicy; /* 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) +#define __default_gfp(a,b,...) b +#define default_gfp(...) __default_gfp(,##__VA_ARGS__,GFP_KERNEL) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) @@ -339,8 +339,11 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde { return folio_alloc_noprof(gfp, order); } -#define vma_alloc_folio_noprof(gfp, order, vma, addr) \ - folio_alloc_noprof(gfp, order) +static inline struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, + struct vm_area_struct *vma, unsigned long addr) +{ + return folio_alloc_noprof(gfp, order); +} #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 814bb2892f99..6c75df30a281 100644 --- a/include/linux/gfp_types.h +++ b/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) diff --git a/include/linux/hid.h b/include/linux/hid.h index dce862cafbbd..2990b9f94cb5 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -836,6 +836,12 @@ struct hid_usage_id { * raw_event and event should return negative on error, any other value will * pass the event on to .event() typically return 0 for success. * + * report_fixup must return a report descriptor pointer whose lifetime is at + * least that of the input rdesc. This is usually done by mutating the input + * rdesc and returning it or a sub-portion of it. In case a new buffer is + * allocated and returned, the implementation of report_fixup is responsible for + * freeing it later. + * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this * usage by generic code (no special handling needed) or positive to skip diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 35227d47cfc9..dc272b514a01 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -16,22 +16,26 @@ */ #define INDIRECT_CALL_1(f, f1, ...) \ ({ \ - likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__); \ + typeof(f) __f1 = (f); \ + likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \ }) #define INDIRECT_CALL_2(f, f2, f1, ...) \ ({ \ - likely(f == f2) ? f2(__VA_ARGS__) : \ - INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ + typeof(f) __f2 = (f); \ + likely(__f2 == f2) ? f2(__VA_ARGS__) : \ + INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ ({ \ - likely(f == f3) ? f3(__VA_ARGS__) : \ - INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + typeof(f) __f3 = (f); \ + likely(__f3 == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ ({ \ - likely(f == f4) ? f4(__VA_ARGS__) : \ - INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + typeof(f) __f4 = (f); \ + likely(__f4 == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALLABLE_DECLARE(f) f 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/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/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 70c0948f978e..0225121f3013 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -394,6 +394,7 @@ #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 #define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) +#define GITS_TYPER_IDBITS GENMASK_ULL(12, 8) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS GENMASK_ULL(17, 13) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index fdef2c155c27..d1c3d4941854 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -434,8 +434,44 @@ extern unsigned long preset_lpj; /* * Convert various time units to each other: */ -extern unsigned int jiffies_to_msecs(const unsigned long j); -extern unsigned int jiffies_to_usecs(const unsigned long j); + +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) +/** + * jiffies_to_msecs - Convert jiffies to milliseconds + * @j: jiffies value + * + * This inline version takes care of HZ in {100,250,1000}. + * + * Return: milliseconds value + */ +static inline unsigned int jiffies_to_msecs(const unsigned long j) +{ + return (MSEC_PER_SEC / HZ) * j; +} +#else +unsigned int jiffies_to_msecs(const unsigned long j); +#endif + +#if !(USEC_PER_SEC % HZ) +/** + * jiffies_to_usecs - Convert jiffies to microseconds + * @j: jiffies value + * + * Return: microseconds value + */ +static inline unsigned int jiffies_to_usecs(const unsigned long j) +{ + /* + * Hz usually doesn't go much further MSEC_PER_SEC. + * jiffies_to_usecs() and usecs_to_jiffies() depend on that. + */ + BUILD_BUG_ON(HZ > USEC_PER_SEC); + + return (USEC_PER_SEC / HZ) * j; +} +#else +unsigned int jiffies_to_usecs(const unsigned long j); +#endif /** * jiffies_to_nsecs - Convert jiffies to nanoseconds diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c92c1149ee6e..a01a474719a7 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -7,6 +7,24 @@ struct mm_struct; +/* opaque kthread data */ +struct kthread; + +/* + * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will + * always remain a kthread. For kthreads p->worker_private always + * points to a struct kthread. For tasks that are not kthreads + * p->worker_private is used to point to other things. + * + * Return NULL for any task that is not a kthread. + */ +static inline struct kthread *tsk_is_kthread(struct task_struct *p) +{ + if (p->flags & PF_KTHREAD) + return p->worker_private; + return NULL; +} + __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, @@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_exit(long result) __noreturn; +#define kthread_exit(result) do_exit(result) void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreads_update_housekeeping(void); +void kthread_do_exit(struct kthread *, long); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index dde605cb894e..6b76e7a6f4c2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -253,7 +253,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { unsigned long attributes; }; @@ -275,7 +274,6 @@ struct kvm_gfn_range { bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -#endif enum { OUTSIDE_GUEST_MODE, @@ -849,13 +847,12 @@ struct kvm { struct hlist_head irq_ack_notifier_list; #endif -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER struct mmu_notifier mmu_notifier; unsigned long mmu_invalidate_seq; long mmu_invalidate_in_progress; gfn_t mmu_invalidate_range_start; gfn_t mmu_invalidate_range_end; -#endif + struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; @@ -1943,56 +1940,43 @@ 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) @@ -2069,7 +2053,7 @@ 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); @@ -2114,11 +2098,10 @@ 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) { if (unlikely(kvm->mmu_invalidate_in_progress)) @@ -2196,7 +2179,6 @@ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; } -#endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h index fe82a6c3005f..dd11fdc76a5f 100644 --- a/include/linux/liveupdate.h +++ b/include/linux/liveupdate.h @@ -23,8 +23,11 @@ struct file; /** * struct liveupdate_file_op_args - Arguments for file operation callbacks. * @handler: The file handler being called. - * @retrieved: The retrieve status for the 'can_finish / finish' - * operation. + * @retrieve_status: The retrieve status for the 'can_finish / finish' + * operation. A value of 0 means the retrieve has not been + * attempted, a positive value means the retrieve was + * successful, and a negative value means the retrieve failed, + * and the value is the error code of the call. * @file: The file object. For retrieve: [OUT] The callback sets * this to the new file. For other ops: [IN] The caller sets * this to the file being operated on. @@ -40,7 +43,7 @@ struct file; */ struct liveupdate_file_op_args { struct liveupdate_file_handler *handler; - bool retrieved; + int retrieve_status; struct file *file; u64 serialized_data; void *private_data; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 26ca00c325d9..d5af2b7f577b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -65,7 +65,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); -void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) +void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, @@ -97,6 +97,14 @@ static inline int set_movable_ops(const struct movable_operations *ops, enum pag return -ENOSYS; } +static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) + __releases(ptl) +{ + WARN_ON_ONCE(1); + + spin_unlock(ptl); +} + #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_NUMA_BALANCING 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) diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index e0e2c265e5d1..ba84f02c2a10 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -486,14 +486,12 @@ struct mmc_host { struct mmc_ios ios; /* current io bus settings */ + bool claimed; /* host exclusively claimed */ + /* group bitfields together to minimize padding */ unsigned int use_spi_crc:1; - unsigned int claimed:1; /* host exclusively claimed */ unsigned int doing_init_tune:1; /* initial tuning in progress */ - unsigned int can_retune:1; /* re-tuning can be used */ unsigned int doing_retune:1; /* re-tuning in progress */ - unsigned int retune_now:1; /* do re-tuning at next req */ - unsigned int retune_paused:1; /* re-tuning is temporarily disabled */ unsigned int retune_crc_disable:1; /* don't trigger retune upon crc */ unsigned int can_dma_map_merge:1; /* merging can be used */ unsigned int vqmmc_enabled:1; /* vqmmc regulator is enabled */ @@ -508,6 +506,9 @@ struct mmc_host { int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ + bool can_retune; /* re-tuning can be used */ + bool retune_now; /* do re-tuning at next req */ + bool retune_paused; /* re-tuning is temporarily disabled */ int need_retune; /* re-tuning is needed */ int hold_retune; /* hold off re-tuning */ unsigned int retune_period; /* re-tuning period in secs */ 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, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d4e6e00bb90a..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); @@ -4711,7 +4743,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } @@ -4729,7 +4761,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } @@ -4738,7 +4770,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; @@ -4746,14 +4778,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) static inline void __netif_tx_unlock(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } @@ -4846,6 +4878,23 @@ static inline void netif_tx_disable(struct net_device *dev) local_bh_enable(); } +#ifndef CONFIG_PREEMPT_RT +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + return READ_ONCE(txq->xmit_lock_owner) == cpu; +} + +#else +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + return rt_mutex_owner(&txq->_xmit_lock.lock) == current; +} + +#endif + static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 825f5865bfc5..c8e227a3f9e2 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) +bool may_see_all_namespaces(void); + static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) { return atomic_read(&ns->__ns_ref_active); 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); diff --git a/include/linux/overflow.h b/include/linux/overflow.h index eddd987a8513..a8cb6319b4fb 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -42,7 +42,7 @@ * both the type-agnostic benefits of the macros while also being able to * enforce that the return value is, in fact, checked. */ -static inline bool __must_check __must_check_overflow(bool overflow) +static __always_inline bool __must_check __must_check_overflow(bool overflow) { return unlikely(overflow); } @@ -327,7 +327,7 @@ static inline bool __must_check __must_check_overflow(bool overflow) * 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) +static __always_inline size_t __must_check size_mul(size_t factor1, size_t factor2) { size_t bytes; @@ -346,7 +346,7 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2) * 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_add(size_t addend1, size_t addend2) +static __always_inline size_t __must_check size_add(size_t addend1, size_t addend2) { size_t bytes; @@ -367,7 +367,7 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2) * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX). * The lvalue must be size_t to avoid implicit type conversion. */ -static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) +static __always_inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) { size_t bytes; diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index f6cca7a035c7..50b6be57da66 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -13,10 +13,10 @@ /** * enum mlxreg_wdt_type - type of HW watchdog * - * TYPE1 HW watchdog implementation exist in old systems. - * All new systems have TYPE2 HW watchdog. - * TYPE3 HW watchdog can exist on all systems with new CPLD. - * TYPE3 is selected by WD capability bit. + * @MLX_WDT_TYPE1: HW watchdog implementation in old systems. + * @MLX_WDT_TYPE2: All new systems have TYPE2 HW watchdog. + * @MLX_WDT_TYPE3: HW watchdog that can exist on all systems with new CPLD. + * TYPE3 is selected by WD capability bit. */ enum mlxreg_wdt_type { MLX_WDT_TYPE1, @@ -35,7 +35,7 @@ enum mlxreg_wdt_type { * @MLXREG_HOTPLUG_LC_SYNCED: entry for line card synchronization events, coming * after hardware-firmware synchronization handshake; * @MLXREG_HOTPLUG_LC_READY: entry for line card ready events, indicating line card - PHYs ready / unready state; + * PHYs ready / unready state; * @MLXREG_HOTPLUG_LC_ACTIVE: entry for line card active events, indicating firmware * availability / unavailability for the ports on line card; * @MLXREG_HOTPLUG_LC_THERMAL: entry for line card thermal shutdown events, positive @@ -123,8 +123,8 @@ struct mlxreg_hotplug_device { * @reg_pwr: attribute power register; * @reg_ena: attribute enable register; * @mode: access mode; - * @np - pointer to node platform associated with attribute; - * @hpdev - hotplug device data; + * @np: pointer to node platform associated with attribute; + * @hpdev: hotplug device data; * @notifier: pointer to event notifier block; * @health_cntr: dynamic device health indication counter; * @attached: true if device has been attached after good health indication; diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index b1b837583d54..dbe745dc88d5 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -26,6 +26,7 @@ #define INT3472_GPIO_TYPE_POWER_ENABLE 0x0b #define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c #define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d +#define INT3472_GPIO_TYPE_DOVDD 0x10 #define INT3472_GPIO_TYPE_HANDSHAKE 0x12 #define INT3472_GPIO_TYPE_HOTPLUG_DETECT 0x13 @@ -33,8 +34,8 @@ #define INT3472_MAX_SENSOR_GPIOS 3 #define INT3472_MAX_REGULATORS 3 -/* E.g. "avdd\0" */ -#define GPIO_SUPPLY_NAME_LENGTH 5 +/* E.g. "dovdd\0" */ +#define GPIO_SUPPLY_NAME_LENGTH 6 /* 12 chars for acpi_dev_name() + "-", e.g. "ABCD1234:00-" */ #define GPIO_REGULATOR_NAME_LENGTH (12 + GPIO_SUPPLY_NAME_LENGTH) /* lower- and upper-case mapping */ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 41037c513f06..64921b10ac74 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -545,22 +545,10 @@ static inline int pm_runtime_resume_and_get(struct device *dev) * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). - * - * Return: - * * 1: Success. Usage counter dropped to zero, but device was already suspended. - * * 0: Success. - * * -EINVAL: Runtime PM error. - * * -EACCES: Runtime PM disabled. - * * -EAGAIN: Runtime PM usage counter became non-zero or Runtime PM status - * change ongoing. - * * -EBUSY: Runtime PM child_count non-zero. - * * -EPERM: Device PM QoS resume latency 0. - * * -EINPROGRESS: Suspend already in progress. - * * -ENOSYS: CONFIG_PM not enabled. */ -static inline int pm_runtime_put(struct device *dev) +static inline void pm_runtime_put(struct device *dev) { - return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); + __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } /** diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 876358cfe1b1..d862fa610270 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); int ring_buffer_map(struct trace_buffer *buffer, int cpu, struct vm_area_struct *vma); +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu); int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/linux/rseq.h b/include/linux/rseq.h index 7a01a0760405..b9d62fc2140d 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -146,6 +146,18 @@ static inline void rseq_fork(struct task_struct *t, u64 clone_flags) t->rseq = current->rseq; } +/* + * Value returned by getauxval(AT_RSEQ_ALIGN) and expected by rseq + * registration. This is the active rseq area size rounded up to next + * power of 2, which guarantees that the rseq structure will always be + * aligned on the nearest power of two large enough to contain it, even + * as it grows. + */ +static inline unsigned int rseq_alloc_align(void) +{ + return 1U << get_count_order(offsetof(struct rseq, end)); +} + #else /* CONFIG_RSEQ */ static inline void rseq_handle_slowpath(struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index cbc4a791618b..c6831c93cd6e 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -216,10 +216,10 @@ efault: } #else /* CONFIG_RSEQ_SLICE_EXTENSION */ -static inline bool rseq_slice_extension_enabled(void) { return false; } -static inline bool rseq_arm_slice_extension_timer(void) { return false; } -static inline void rseq_slice_clear_grant(struct task_struct *t) { } -static inline bool rseq_grant_slice_extension(bool work_pending) { return false; } +static __always_inline bool rseq_slice_extension_enabled(void) { return false; } +static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; } +static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { } +static __always_inline bool rseq_grant_slice_extension(bool work_pending) { return false; } #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); 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/include/linux/sched.h b/include/linux/sched.h index 074ad4ef3d81..5a5d3dbc9cdf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -579,6 +579,7 @@ struct sched_entity { u64 deadline; u64 min_vruntime; u64 min_slice; + u64 max_slice; struct list_head group_node; unsigned char on_rq; @@ -2353,7 +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) { @@ -2362,7 +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/include/linux/slab.h b/include/linux/slab.h index a5a5e4108ae5..15a60b501b95 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -517,18 +517,6 @@ void kfree_sensitive(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) -/** - * ksize - Report actual allocation size of associated object - * - * @objp: Pointer returned from a prior kmalloc()-family allocation. - * - * This should not be used for writing beyond the originally requested - * allocation size. Either use krealloc() or round up the allocation size - * with kmalloc_size_roundup() prior to allocation. If this is used to - * access beyond the originally requested allocation size, UBSAN_BOUNDS - * and/or FORTIFY_SOURCE may trip, since they only know about the - * originally allocated size via the __alloc_size attribute. - */ size_t ksize(const void *objp); #ifdef CONFIG_PRINTK diff --git a/include/linux/tnum.h b/include/linux/tnum.h index fa4654ffb621..ca2cfec8de08 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -131,4 +131,7 @@ static inline bool tnum_subreg_is_const(struct tnum a) return !(tnum_subreg(a)).mask; } +/* Returns the smallest member of t larger than z */ +u64 tnum_step(struct tnum t, u64 z); + #endif /* _LINUX_TNUM_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1f3804245c06..4fe63169d5a2 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { } /* Define RW variant so the below _mode macro expansion works */ #define masked_user_rw_access_begin(u) masked_user_access_begin(u) #define user_rw_access_begin(u, s) user_access_begin(u, s) -#define user_rw_access_end() user_access_end() /* Scoped user access */ -#define USER_ACCESS_GUARD(_mode) \ -static __always_inline void __user * \ -class_user_##_mode##_begin(void __user *ptr) \ -{ \ - return ptr; \ -} \ - \ -static __always_inline void \ -class_user_##_mode##_end(void __user *ptr) \ -{ \ - user_##_mode##_access_end(); \ -} \ - \ -DEFINE_CLASS(user_ ##_mode## _access, void __user *, \ - class_user_##_mode##_end(_T), \ - class_user_##_mode##_begin(ptr), void __user *ptr) \ - \ -static __always_inline class_user_##_mode##_access_t \ -class_user_##_mode##_access_ptr(void __user *scope) \ -{ \ - return scope; \ -} -USER_ACCESS_GUARD(read) -USER_ACCESS_GUARD(write) -USER_ACCESS_GUARD(rw) -#undef USER_ACCESS_GUARD +/* Cleanup wrapper functions */ +static __always_inline void __scoped_user_read_access_end(const void *p) +{ + user_read_access_end(); +}; +static __always_inline void __scoped_user_write_access_end(const void *p) +{ + user_write_access_end(); +}; +static __always_inline void __scoped_user_rw_access_end(const void *p) +{ + user_access_end(); +}; /** * __scoped_user_access_begin - Start a scoped user access @@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw) * * Don't use directly. Use scoped_masked_user_$MODE_access() instead. */ -#define __scoped_user_access(mode, uptr, size, elbl) \ -for (bool done = false; !done; done = true) \ - for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ - !done; done = true) \ - for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true) \ - /* Force modified pointer usage within the scope */ \ - for (const typeof(uptr) uptr = _tmpptr; !done; done = true) +#define __scoped_user_access(mode, uptr, size, elbl) \ +for (bool done = false; !done; done = true) \ + for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ + !done; done = true) \ + /* Force modified pointer usage within the scope */ \ + for (const auto uptr __cleanup(__scoped_user_##mode##_access_end) = \ + _tmpptr; !done; done = true) /** * scoped_user_read_access_size - Start a scoped user read access with given size @@ -806,7 +792,7 @@ 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 +803,7 @@ 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)). diff --git a/include/linux/usb.h b/include/linux/usb.h index fbfcc70b07fb..04277af4bb9d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1862,14 +1862,18 @@ 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); 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, 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 */ diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 2ca60828f28b..1502b2a355f9 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -32,6 +32,7 @@ #define VENDOR_ID_DLINK 0x2001 #define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 +#define VENDOR_ID_TRENDNET 0x20f4 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); 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 *); diff --git a/include/net/act_api.h b/include/net/act_api.h index e1e8f0f7dacb..d11b79107930 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -70,6 +70,7 @@ struct tc_action { #define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) #define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) #define TCA_ACT_FLAGS_AT_INGRESS (1U << (TCA_ACT_FLAGS_USER_BITS + 4)) +#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT (1U << (TCA_ACT_FLAGS_USER_BITS + 5)) /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index d3ff48a2fbe0..533d8e75f7bb 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -276,10 +276,19 @@ static inline bool vsock_net_mode_global(struct vsock_sock *vsk) return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL; } -static inline void vsock_net_set_child_mode(struct net *net, +static inline bool vsock_net_set_child_mode(struct net *net, enum vsock_net_mode mode) { - WRITE_ONCE(net->vsock.child_ns_mode, mode); + int new_locked = mode + 1; + int old_locked = 0; /* unlocked */ + + if (try_cmpxchg(&net->vsock.child_ns_mode_locked, + &old_locked, new_locked)) { + WRITE_ONCE(net->vsock.child_ns_mode, mode); + return true; + } + + return old_locked == new_locked; } static inline enum vsock_net_mode vsock_net_child_mode(struct net *net) diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index ec3af01e4db9..010f1a8fd15f 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -284,9 +284,9 @@ struct l2cap_conn_rsp { #define L2CAP_CR_LE_BAD_KEY_SIZE 0x0007 #define L2CAP_CR_LE_ENCRYPTION 0x0008 #define L2CAP_CR_LE_INVALID_SCID 0x0009 -#define L2CAP_CR_LE_SCID_IN_USE 0X000A -#define L2CAP_CR_LE_UNACCEPT_PARAMS 0X000B -#define L2CAP_CR_LE_INVALID_PARAMS 0X000C +#define L2CAP_CR_LE_SCID_IN_USE 0x000A +#define L2CAP_CR_LE_UNACCEPT_PARAMS 0x000B +#define L2CAP_CR_LE_INVALID_PARAMS 0x000C /* connect/create channel status */ #define L2CAP_CS_NO_INFO 0x0000 @@ -493,6 +493,8 @@ struct l2cap_ecred_reconf_req { #define L2CAP_RECONF_SUCCESS 0x0000 #define L2CAP_RECONF_INVALID_MTU 0x0001 #define L2CAP_RECONF_INVALID_MPS 0x0002 +#define L2CAP_RECONF_INVALID_CID 0x0003 +#define L2CAP_RECONF_INVALID_PARAMS 0x0004 struct l2cap_ecred_reconf_rsp { __le16 result; diff --git a/include/net/bonding.h b/include/net/bonding.h index 4ad5521e7731..395c6e281c5f 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -699,6 +699,7 @@ void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); +bool __bond_xdp_check(int mode, int xmit_policy); bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 282e29237d93..c16de5b7963f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk, { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ecb362025c4e..5cb3056d6ddc 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -42,7 +42,9 @@ struct inet_connection_sock_af_ops { struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, - bool *own_req); + bool *own_req, + void (*opt_child_init)(struct sock *newsk, + const struct sock *sk)); u16 net_header_len; int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ac05a52d9e13..5a979dcab538 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -345,7 +345,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk, int dif, int sdif) { if (!net_eq(sock_net(sk), net) || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || sk->sk_addrpair != cookie) return false; diff --git a/include/net/ip.h b/include/net/ip.h index 69d5cef46004..7f9abd457e01 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; - ipcm->protocol = inet->inet_num; + ipcm->protocol = READ_ONCE(inet->inet_num); } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 120db2865811..359b595f1df9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -156,6 +156,18 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; + 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; + } + + 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 +178,8 @@ 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_fib.h b/include/net/ip_fib.h index b4495c38e0a0..318593743b6e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -559,7 +559,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net, siphash_aligned_key_t hash_key; u32 mp_seed; - mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; + mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed); fib_multipath_hash_construct_key(&hash_key, mp_seed); return flow_hash_from_keys_seed(keys, &hash_key); 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 <net/ip6_route.h> #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/include/net/libeth/xsk.h b/include/net/libeth/xsk.h index 481a7b28e6f2..82b5d21aae87 100644 --- a/include/net/libeth/xsk.h +++ b/include/net/libeth/xsk.h @@ -597,6 +597,7 @@ __libeth_xsk_run_pass(struct libeth_xdp_buff *xdp, * @pending: current number of XSkFQEs to refill * @thresh: threshold below which the queue is refilled * @buf_len: HW-writeable length per each buffer + * @truesize: step between consecutive buffers, 0 if none exists * @nid: ID of the closest NUMA node with memory */ struct libeth_xskfq { @@ -614,6 +615,8 @@ struct libeth_xskfq { u32 thresh; u32 buf_len; + u32 truesize; + int nid; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 426534a711b0..e2d2bfc1f989 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -320,11 +320,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state + * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element */ enum nft_iter_type { NFT_ITER_UNSPEC, NFT_ITER_READ, NFT_ITER_UPDATE, + NFT_ITER_UPDATE_CLONE, }; struct nft_set; @@ -1861,6 +1863,11 @@ struct nft_trans_gc { struct rcu_head rcu; }; +static inline int nft_trans_gc_space(const struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + static inline void nft_ctx_update(struct nft_ctx *ctx, const struct nft_trans *trans) { diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h index b34d69a22fa8..dc8cbe45f406 100644 --- a/include/net/netns/vsock.h +++ b/include/net/netns/vsock.h @@ -17,5 +17,8 @@ struct netns_vsock { enum vsock_net_mode mode; enum vsock_net_mode child_ns_mode; + + /* 0 = unlocked, 1 = locked to global, 2 = locked to local */ + int child_ns_mode_locked; }; #endif /* __NET_NET_NAMESPACE_VSOCK_H */ 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/include/net/sch_generic.h b/include/net/sch_generic.h index c3a7268b567e..d5d55cb21686 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -778,13 +778,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb) static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; + bool nolock; for (; i < dev->num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); + spin_unlock_bh(&qdisc->seqlock); + } } } } diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index cddebafb9f77..6f996229167b 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -5,16 +5,47 @@ #include <linux/types.h> struct net; +extern struct net init_net; + +union tcp_seq_and_ts_off { + struct { + u32 seq; + u32 ts_off; + }; + u64 hash64; +}; u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr); -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport); -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr); +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); + +static inline u32 secure_tcp_seq(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcp_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + + return ts.seq; +} + +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, + __be16 sport, __be16 dport); + +static inline u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcpv6_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + return ts.seq; +} #endif /* _NET_SECURE_SEQ */ diff --git a/include/net/sock.h b/include/net/sock.h index 66b56288c1d3..6c9a83016e95 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2098,7 +2098,7 @@ static inline int sk_rx_queue_get(const struct sock *sk) static inline void sk_set_socket(struct sock *sk, struct socket *sock) { - sk->sk_socket = sock; + WRITE_ONCE(sk->sk_socket, sock); if (sock) { WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid); WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino); diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h index b147a3bb1a46..e0fded18e18c 100644 --- a/include/net/tc_act/tc_gate.h +++ b/include/net/tc_act/tc_gate.h @@ -32,6 +32,7 @@ struct tcf_gate_params { s32 tcfg_clockid; size_t num_entries; struct list_head entries; + struct rcu_head rcu; }; #define GATE_ACT_GATE_OPEN BIT(0) @@ -39,7 +40,7 @@ struct tcf_gate_params { struct tcf_gate { struct tc_action common; - struct tcf_gate_params param; + struct tcf_gate_params __rcu *param; u8 current_gate_status; ktime_t current_close_time; u32 current_entry_octets; @@ -51,47 +52,65 @@ struct tcf_gate { #define to_gate(a) ((struct tcf_gate *)a) +static inline struct tcf_gate_params *tcf_gate_params_locked(const struct tc_action *a) +{ + struct tcf_gate *gact = to_gate(a); + + return rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); +} + static inline s32 tcf_gate_prio(const struct tc_action *a) { + struct tcf_gate_params *p; s32 tcfg_prio; - tcfg_prio = to_gate(a)->param.tcfg_priority; + p = tcf_gate_params_locked(a); + tcfg_prio = p->tcfg_priority; return tcfg_prio; } static inline u64 tcf_gate_basetime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_basetime; - tcfg_basetime = to_gate(a)->param.tcfg_basetime; + p = tcf_gate_params_locked(a); + tcfg_basetime = p->tcfg_basetime; return tcfg_basetime; } static inline u64 tcf_gate_cycletime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletime; - tcfg_cycletime = to_gate(a)->param.tcfg_cycletime; + p = tcf_gate_params_locked(a); + tcfg_cycletime = p->tcfg_cycletime; return tcfg_cycletime; } static inline u64 tcf_gate_cycletimeext(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletimeext; - tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext; + p = tcf_gate_params_locked(a); + tcfg_cycletimeext = p->tcfg_cycletime_ext; return tcfg_cycletimeext; } static inline u32 tcf_gate_num_entries(const struct tc_action *a) { + struct tcf_gate_params *p; u32 num_entries; - num_entries = to_gate(a)->param.num_entries; + p = tcf_gate_params_locked(a); + num_entries = p->num_entries; return num_entries; } @@ -105,7 +124,7 @@ static inline struct action_gate_entry u32 num_entries; int i = 0; - p = &to_gate(a)->param; + p = tcf_gate_params_locked(a); num_entries = p->num_entries; list_for_each_entry(entry, &p->entries, list) diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index c7f24a2da1ca..24d4d5a62b3c 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -13,15 +13,13 @@ struct tcf_ife_params { u8 eth_src[ETH_ALEN]; u16 eth_type; u16 flags; - + struct list_head metalist; struct rcu_head rcu; }; struct tcf_ife_info { struct tc_action common; struct tcf_ife_params __rcu *params; - /* list of metaids allowed */ - struct list_head metalist; }; #define to_ife(a) ((struct tcf_ife_info *)a) diff --git a/include/net/tcp.h b/include/net/tcp.h index 40e72b9cb85f..978eea2d5df0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -43,6 +43,7 @@ #include <net/dst.h> #include <net/mptcp.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -544,7 +545,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, - bool *own_req); + bool *own_req, + void (*opt_child_init)(struct sock *newsk, + const struct sock *sk)); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int tcp_connect(struct sock *sk); @@ -2462,8 +2465,9 @@ struct tcp_request_sock_ops { struct flowi *fl, struct request_sock *req, u32 tw_isn); - u32 (*init_seq)(const struct sk_buff *skb); - u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); + union tcp_seq_and_ts_off (*init_seq_and_ts_off)( + const struct net *net, + const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 242e34f771cc..6b9ebae2dc95 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -51,6 +51,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool); +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { @@ -122,7 +127,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) goto out; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { - list_del(&pos->list_node); + list_del_init(&pos->list_node); xp_free(pos); } @@ -157,7 +162,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) frag = list_first_entry_or_null(&xskb->pool->xskb_list, struct xdp_buff_xsk, list_node); if (frag) { - list_del(&frag->list_node); + list_del_init(&frag->list_node); ret = &frag->xdp; } @@ -168,7 +173,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); - list_del(&xskb->list_node); + list_del_init(&xskb->list_node); } static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first) @@ -337,6 +342,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return 0; } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return 0; +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index 6de6fd8bd15e..d639ff889e64 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -181,7 +181,7 @@ void rdma_destroy_id(struct rdma_cm_id *id); * * It needs to be called before the RDMA identifier is bound * to an device, which mean it should be called before - * rdma_bind_addr(), rdma_bind_addr() and rdma_listen(). + * rdma_bind_addr(), rdma_resolve_addr() and rdma_listen(). */ int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type); diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index ae1e1489b671..28f9f5940ab6 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -406,6 +406,7 @@ extern const char * const cs35l56_cal_set_status_text[3]; extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC]; extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC]; +int cs35l56_set_asp_patch(struct cs35l56_base *cs35l56_base); int cs35l56_set_patch(struct cs35l56_base *cs35l56_base); int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command); int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base); diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h index 7c03bdc951bb..e847cf51878c 100644 --- a/include/sound/tas2781.h +++ b/include/sound/tas2781.h @@ -151,6 +151,7 @@ struct tasdevice { struct bulk_reg_val *cali_data_backup; struct bulk_reg_val alp_cali_bckp; struct tasdevice_fw *cali_data_fmw; + void *cali_specific; unsigned int dev_addr; unsigned int err_code; unsigned char cur_book; diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 7f93e754da5c..cd7920c81f85 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -440,7 +440,13 @@ TRACE_EVENT(rss_stat, TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); - __entry->curr = !!(current->mm == mm); + /* + * curr is true if the mm matches the current task's mm_struct. + * Since kthreads (PF_KTHREAD) have no mm_struct of their own + * but can borrow one via kthread_use_mm(), we must filter them + * out to avoid incorrectly attributing the RSS update to them. + */ + __entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 64a382fbc31a..2d366be46a1c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -57,6 +57,7 @@ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_end_copy_to_cache, "END-C2C") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_intr, "INTR ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ @@ -169,7 +170,8 @@ EM(netfs_sreq_trace_put_oom, "PUT OOM ") \ EM(netfs_sreq_trace_put_wip, "PUT WIP ") \ EM(netfs_sreq_trace_put_work, "PUT WORK ") \ - E_(netfs_sreq_trace_put_terminated, "PUT TERM ") + EM(netfs_sreq_trace_put_terminated, "PUT TERM ") \ + E_(netfs_sreq_trace_see_failed, "SEE FAILED ") #define netfs_folio_traces \ EM(netfs_folio_is_uptodate, "mod-uptodate") \ diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index e527b24bd824..c89aede3cb12 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -401,8 +401,8 @@ extern "C" { * implementation can multiply the values by 2^6=64. For that reason the padding * must only contain zeros. * index 0 = Y plane, [15:0] z:Y [6:10] little endian - * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian - * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian + * index 1 = Cb plane, [15:0] z:Cb [6:10] little endian + * index 2 = Cr plane, [15:0] z:Cr [6:10] little endian */ #define DRM_FORMAT_S010 fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */ #define DRM_FORMAT_S210 fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */ @@ -414,8 +414,8 @@ extern "C" { * implementation can multiply the values by 2^4=16. For that reason the padding * must only contain zeros. * index 0 = Y plane, [15:0] z:Y [4:12] little endian - * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian - * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian + * index 1 = Cb plane, [15:0] z:Cb [4:12] little endian + * index 2 = Cr plane, [15:0] z:Cr [4:12] little endian */ #define DRM_FORMAT_S012 fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */ #define DRM_FORMAT_S212 fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */ @@ -424,8 +424,8 @@ extern "C" { /* * 3 plane YCbCr * index 0 = Y plane, [15:0] Y little endian - * index 1 = Cr plane, [15:0] Cr little endian - * index 2 = Cb plane, [15:0] Cb little endian + * index 1 = Cb plane, [15:0] Cb little endian + * index 2 = Cr plane, [15:0] Cr little endian */ #define DRM_FORMAT_S016 fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */ #define DRM_FORMAT_S216 fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */ diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 5a6fda66d9ad..e827c9d20c5d 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -20,6 +20,7 @@ #ifndef _DMA_BUF_UAPI_H_ #define _DMA_BUF_UAPI_H_ +#include <linux/ioctl.h> #include <linux/types.h> /** diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6750c383a2ab..1ff16141c8a5 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -188,7 +188,8 @@ enum io_uring_sqe_flags_bit { /* * If COOP_TASKRUN is set, get notified if task work is available for * running and a kernel transition would be needed to run it. This sets - * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + * IORING_SQ_TASKRUN in the sq ring flags. Not valid without COOP_TASKRUN + * or DEFER_TASKRUN. */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 65500f5db379..80364d4dbebb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -14,6 +14,10 @@ #include <linux/ioctl.h> #include <asm/kvm.h> +#ifdef __KERNEL__ +#include <linux/kvm_types.h> +#endif + #define KVM_API_VERSION 12 /* @@ -1601,7 +1605,11 @@ 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/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index ec1c54b5a310..14f634ab9350 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -712,7 +712,7 @@ #define PCI_EXP_LNKCTL2_HASD 0x0020 /* HW Autonomous Speed Disable */ #define PCI_EXP_LNKSTA2 0x32 /* Link Status 2 */ #define PCI_EXP_LNKSTA2_FLIT 0x0400 /* Flit Mode Status */ -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32 /* end of v2 EPs w/ link */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x34 /* end of v2 EPs w/ link */ #define PCI_EXP_SLTCAP2 0x34 /* Slot Capabilities 2 */ #define PCI_EXP_SLTCAP2_IBPD 0x00000001 /* In-band PD Disable Supported */ #define PCI_EXP_SLTCTL2 0x38 /* Slot Control 2 */ diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 863c4a00a66b..f69344fe6c08 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -87,10 +87,17 @@ struct rseq_slice_ctrl { }; /* - * struct rseq is aligned on 4 * 8 bytes to ensure it is always - * contained within a single cache-line. + * The original size and alignment of the allocation for struct rseq is + * 32 bytes. * - * A single struct rseq per thread is allowed. + * The allocation size needs to be greater or equal to + * max(getauxval(AT_RSEQ_FEATURE_SIZE), 32), and the allocation needs to + * be aligned on max(getauxval(AT_RSEQ_ALIGN), 32). + * + * As an alternative, userspace is allowed to use both the original size + * and alignment of 32 bytes for backward compatibility. + * + * A single active struct rseq registration per thread is allowed. */ struct rseq { /* @@ -181,9 +188,20 @@ struct rseq { struct rseq_slice_ctrl slice_ctrl; /* + * Before rseq became extensible, its original size was 32 bytes even + * though the active rseq area was only 20 bytes. + * Exposing a 32 bytes feature size would make life needlessly painful + * for userspace. Therefore, add a reserved byte after byte 32 + * to bump the rseq feature size from 32 to 33. + * The next field to be added to the rseq area will be larger + * than one byte, and will replace this reserved byte. + */ + __u8 __reserved; + + /* * Flexible array member at end of structure, after last feature field. */ char end[]; -} __attribute__((aligned(4 * sizeof(__u64)))); +} __attribute__((aligned(32))); #endif /* _UAPI_LINUX_RSEQ_H */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index c94caf852aea..8ca15743af7f 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -80,6 +80,7 @@ struct xenbus_device { const char *devicetype; const char *nodename; const char *otherend; + bool vanished; int otherend_id; struct xenbus_watch otherend_watch; struct device dev; @@ -228,7 +229,8 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr); int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port); int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port); -enum xenbus_state xenbus_read_driver_state(const char *path); +enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev, + const char *path); __printf(3, 4) void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...); |