diff options
Diffstat (limited to 'kernel')
54 files changed, 1204 insertions, 574 deletions
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 49a8f7b1beef..40c42e28a616 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -59,6 +59,8 @@ struct bpf_arena { struct list_head vma_list; /* protects vma_list */ struct mutex lock; + u64 zap_gen; + struct mutex zap_mutex; struct irq_work free_irq; struct work_struct free_work; struct llist_head free_spans; @@ -228,6 +230,7 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr) goto err; } mutex_init(&arena->lock); + mutex_init(&arena->zap_mutex); raw_res_spin_lock_init(&arena->spinlock); err = populate_pgtable_except_pte(arena); if (err) { @@ -318,6 +321,7 @@ struct vma_list { struct vm_area_struct *vma; struct list_head head; refcount_t mmap_count; + u64 zap_gen; }; static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) @@ -330,6 +334,7 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) refcount_set(&vml->mmap_count, 1); vma->vm_private_data = vml; vml->vma = vma; + vml->zap_gen = 0; list_add(&vml->head, &arena->vma_list); return 0; } @@ -668,12 +673,60 @@ out_free_pages: */ static void zap_pages(struct bpf_arena *arena, long uaddr, long page_cnt) { + unsigned long size = (unsigned long)page_cnt << PAGE_SHIFT; + struct vm_area_struct *vma; + struct mm_struct *mm; struct vma_list *vml; + unsigned long vm_start; + u64 my_gen; - guard(mutex)(&arena->lock); - /* iterate link list under lock */ - list_for_each_entry(vml, &arena->vma_list, head) - zap_vma_range(vml->vma, uaddr, PAGE_SIZE * page_cnt); + /* + * Taking mmap_read_lock() under arena->lock would deadlock against + * arena_vm_close(), which runs with mmap_write_lock held and then + * acquires arena->lock. Drop arena->lock for mmap_read_lock(). + * + * Use per-call my_gen, recorded in vml->zap_gen, to remember which + * vmls this invocation has already processed across the lock drop. + * Hold zap_mutex around the whole walk so concurrent zap_pages() + * callers cannot overwrite each other's marks on shared vmls -- + * otherwise call B's mark would make call A skip a vml that A has + * not yet zapped for A's uaddr range. + */ + mutex_lock(&arena->zap_mutex); + mutex_lock(&arena->lock); + my_gen = ++arena->zap_gen; + for (;;) { + mm = NULL; + list_for_each_entry(vml, &arena->vma_list, head) { + if (vml->zap_gen >= my_gen) + continue; + vml->zap_gen = my_gen; + if (!mmget_not_zero(vml->vma->vm_mm)) + continue; + mm = vml->vma->vm_mm; + vm_start = vml->vma->vm_start; + break; + } + if (!mm) + break; + mutex_unlock(&arena->lock); + + mmap_read_lock(mm); + /* + * Re-resolve: while we waited the VMA could have been unmapped + * and a different mapping installed at the same address. + */ + vma = find_vma(mm, vm_start); + if (vma && vma->vm_start == vm_start && + vma->vm_file && vma->vm_file->private_data == &arena->map) + zap_vma_range(vma, uaddr, size); + mmap_read_unlock(mm); + mmput(mm); + + mutex_lock(&arena->lock); + } + mutex_unlock(&arena->lock); + mutex_unlock(&arena->zap_mutex); } static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt, bool sleepable) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index dfb2110ab733..4b68d7a2b90e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -386,7 +386,7 @@ static long array_map_update_elem(struct bpf_map *map, void *key, void *value, if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { val = this_cpu_ptr(array->pptrs[index & array->index_mask]); copy_map_value(map, val, value); - bpf_obj_free_fields(array->map.record, val); + bpf_obj_cancel_fields(map, val); } else { val = array->value + (u64)array->elem_size * (index & array->index_mask); @@ -394,7 +394,7 @@ static long array_map_update_elem(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); - bpf_obj_free_fields(array->map.record, val); + bpf_obj_cancel_fields(map, val); } return 0; } @@ -434,14 +434,14 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, cpu = map_flags >> 32; ptr = per_cpu_ptr(pptr, cpu); copy_map_value(map, ptr, value); - bpf_obj_free_fields(array->map.record, ptr); + bpf_obj_cancel_fields(map, ptr); goto unlock; } for_each_possible_cpu(cpu) { ptr = per_cpu_ptr(pptr, cpu); val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; copy_map_value(map, ptr, val); - bpf_obj_free_fields(array->map.record, ptr); + bpf_obj_cancel_fields(map, ptr); } unlock: rcu_read_unlock(); diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index e7a2fc60523f..5ed7cb4b98c0 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -13,23 +13,8 @@ #define PERCPU_FREE_TARGET (4) #define PERCPU_NR_SCANS PERCPU_FREE_TARGET -/* Helpers to get the local list index */ -#define LOCAL_LIST_IDX(t) ((t) - BPF_LOCAL_LIST_T_OFFSET) -#define LOCAL_FREE_LIST_IDX LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_FREE) -#define LOCAL_PENDING_LIST_IDX LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_PENDING) #define IS_LOCAL_LIST_TYPE(t) ((t) >= BPF_LOCAL_LIST_T_OFFSET) -/* Local list helpers */ -static struct list_head *local_free_list(struct bpf_lru_locallist *loc_l) -{ - return &loc_l->lists[LOCAL_FREE_LIST_IDX]; -} - -static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) -{ - return &loc_l->lists[LOCAL_PENDING_LIST_IDX]; -} - /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { @@ -72,6 +57,7 @@ static void __bpf_lru_node_move_to_free(struct bpf_lru_list *l, bpf_lru_list_count_dec(l, node->type); node->type = tgt_free_type; + WRITE_ONCE(node->pending_free, 0); list_move(&node->list, free_list); } @@ -87,6 +73,9 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; bpf_lru_node_clear_ref(node); + /* Reset pending_free only when moving to the free list */ + if (tgt_type == BPF_LRU_LIST_T_FREE) + WRITE_ONCE(node->pending_free, 0); list_move(&node->list, &l->lists[tgt_type]); } @@ -212,9 +201,11 @@ __bpf_lru_list_shrink_inactive(struct bpf_lru *lru, unsigned int i = 0; list_for_each_entry_safe_reverse(node, tmp_node, inactive, list) { - if (bpf_lru_node_is_ref(node)) { + if (bpf_lru_node_is_ref(node) && + !READ_ONCE(node->pending_free)) { __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE); - } else if (lru->del_from_htab(lru->del_arg, node)) { + } else if (READ_ONCE(node->pending_free) || + lru->del_from_htab(lru->del_arg, node)) { __bpf_lru_node_move_to_free(l, node, free_list, tgt_free_type); if (++nshrinked == tgt_nshrink) @@ -273,7 +264,8 @@ static unsigned int __bpf_lru_list_shrink(struct bpf_lru *lru, list_for_each_entry_safe_reverse(node, tmp_node, force_shrink_list, list) { - if (lru->del_from_htab(lru->del_arg, node)) { + if (READ_ONCE(node->pending_free) || + lru->del_from_htab(lru->del_arg, node)) { __bpf_lru_node_move_to_free(l, node, free_list, tgt_free_type); return 1; @@ -290,8 +282,10 @@ static void __local_list_flush(struct bpf_lru_list *l, struct bpf_lru_node *node, *tmp_node; list_for_each_entry_safe_reverse(node, tmp_node, - local_pending_list(loc_l), list) { - if (bpf_lru_node_is_ref(node)) + &loc_l->pending_list, list) { + if (READ_ONCE(node->pending_free)) + __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_FREE); + else if (bpf_lru_node_is_ref(node)) __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_ACTIVE); else __bpf_lru_node_move_in(l, node, @@ -307,9 +301,12 @@ static void bpf_lru_list_push_free(struct bpf_lru_list *l, if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type))) return; - raw_spin_lock_irqsave(&l->lock, flags); + if (raw_res_spin_lock_irqsave(&l->lock, flags)) { + WRITE_ONCE(node->pending_free, 1); + return; + } __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE); - raw_spin_unlock_irqrestore(&l->lock, flags); + raw_res_spin_unlock_irqrestore(&l->lock, flags); } static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, @@ -318,8 +315,10 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, struct bpf_lru_list *l = &lru->common_lru.lru_list; struct bpf_lru_node *node, *tmp_node; unsigned int nfree = 0; + LIST_HEAD(tmp_free); - raw_spin_lock(&l->lock); + if (raw_res_spin_lock(&l->lock)) + return; __local_list_flush(l, loc_l); @@ -327,7 +326,7 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, list_for_each_entry_safe(node, tmp_node, &l->lists[BPF_LRU_LIST_T_FREE], list) { - __bpf_lru_node_move_to_free(l, node, local_free_list(loc_l), + __bpf_lru_node_move_to_free(l, node, &tmp_free, BPF_LRU_LOCAL_LIST_T_FREE); if (++nfree == lru->target_free) break; @@ -335,10 +334,19 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, if (nfree < lru->target_free) __bpf_lru_list_shrink(lru, l, lru->target_free - nfree, - local_free_list(loc_l), + &tmp_free, BPF_LRU_LOCAL_LIST_T_FREE); - raw_spin_unlock(&l->lock); + raw_res_spin_unlock(&l->lock); + + /* + * Transfer the harvested nodes from the temporary list_head into + * the lockless per-CPU free llist. + */ + list_for_each_entry_safe(node, tmp_node, &tmp_free, list) { + list_del(&node->list); + llist_add(&node->llist, &loc_l->free_llist); + } } static void __local_list_add_pending(struct bpf_lru *lru, @@ -350,22 +358,21 @@ static void __local_list_add_pending(struct bpf_lru *lru, *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; + WRITE_ONCE(node->pending_free, 0); bpf_lru_node_clear_ref(node); - list_add(&node->list, local_pending_list(loc_l)); + list_add(&node->list, &loc_l->pending_list); } static struct bpf_lru_node * __local_list_pop_free(struct bpf_lru_locallist *loc_l) { - struct bpf_lru_node *node; + struct llist_node *llnode; - node = list_first_entry_or_null(local_free_list(loc_l), - struct bpf_lru_node, - list); - if (node) - list_del(&node->list); + llnode = llist_del_first(&loc_l->free_llist); + if (!llnode) + return NULL; - return node; + return container_of(llnode, struct bpf_lru_node, llist); } static struct bpf_lru_node * @@ -376,10 +383,10 @@ __local_list_pop_pending(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l) ignore_ref: /* Get from the tail (i.e. older element) of the pending list. */ - list_for_each_entry_reverse(node, local_pending_list(loc_l), - list) { + list_for_each_entry_reverse(node, &loc_l->pending_list, list) { if ((!bpf_lru_node_is_ref(node) || force) && - lru->del_from_htab(lru->del_arg, node)) { + (READ_ONCE(node->pending_free) || + lru->del_from_htab(lru->del_arg, node))) { list_del(&node->list); return node; } @@ -404,7 +411,8 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, l = per_cpu_ptr(lru->percpu_lru, cpu); - raw_spin_lock_irqsave(&l->lock, flags); + if (raw_res_spin_lock_irqsave(&l->lock, flags)) + return NULL; __bpf_lru_list_rotate(lru, l); @@ -420,7 +428,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); } - raw_spin_unlock_irqrestore(&l->lock, flags); + raw_res_spin_unlock_irqrestore(&l->lock, flags); return node; } @@ -437,7 +445,8 @@ static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru, loc_l = per_cpu_ptr(clru->local_list, cpu); - raw_spin_lock_irqsave(&loc_l->lock, flags); + if (raw_res_spin_lock_irqsave(&loc_l->lock, flags)) + return NULL; node = __local_list_pop_free(loc_l); if (!node) { @@ -448,17 +457,22 @@ static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru, if (node) __local_list_add_pending(lru, loc_l, cpu, node, hash); - raw_spin_unlock_irqrestore(&loc_l->lock, flags); + raw_res_spin_unlock_irqrestore(&loc_l->lock, flags); if (node) return node; - /* No free nodes found from the local free list and + /* + * No free nodes found from the local free list and * the global LRU list. * * Steal from the local free/pending list of the * current CPU and remote CPU in RR. It starts * with the loc_l->next_steal CPU. + * + * Acquire the victim's lock before touching either list. On + * acquisition failure (rqspinlock AA or timeout) skip the victim + * and try the next CPU. */ first_steal = loc_l->next_steal; @@ -466,24 +480,36 @@ static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru, do { steal_loc_l = per_cpu_ptr(clru->local_list, steal); - raw_spin_lock_irqsave(&steal_loc_l->lock, flags); - - node = __local_list_pop_free(steal_loc_l); - if (!node) - node = __local_list_pop_pending(lru, steal_loc_l); - - raw_spin_unlock_irqrestore(&steal_loc_l->lock, flags); + if (!raw_res_spin_lock_irqsave(&steal_loc_l->lock, flags)) { + node = __local_list_pop_free(steal_loc_l); + if (!node) + node = __local_list_pop_pending(lru, steal_loc_l); + raw_res_spin_unlock_irqrestore(&steal_loc_l->lock, flags); + } steal = cpumask_next_wrap(steal, cpu_possible_mask); } while (!node && steal != first_steal); loc_l->next_steal = steal; - if (node) { - raw_spin_lock_irqsave(&loc_l->lock, flags); - __local_list_add_pending(lru, loc_l, cpu, node, hash); - raw_spin_unlock_irqrestore(&loc_l->lock, flags); + if (!node) + return NULL; + + if (raw_res_spin_lock_irqsave(&loc_l->lock, flags)) { + /* + * The local pending lock can't be acquired (rqspinlock AA + * or timeout). Return the stolen node to the per-CPU + * free_llist instead of orphaning it; the next pop_free on + * this CPU will pick it up. + */ + node->type = BPF_LRU_LOCAL_LIST_T_FREE; + bpf_lru_node_clear_ref(node); + WRITE_ONCE(node->pending_free, 0); + llist_add(&node->llist, &loc_l->free_llist); + return NULL; } + __local_list_add_pending(lru, loc_l, cpu, node, hash); + raw_res_spin_unlock_irqrestore(&loc_l->lock, flags); return node; } @@ -511,18 +537,24 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru, loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu); - raw_spin_lock_irqsave(&loc_l->lock, flags); + if (raw_res_spin_lock_irqsave(&loc_l->lock, flags)) { + WRITE_ONCE(node->pending_free, 1); + return; + } if (unlikely(node->type != BPF_LRU_LOCAL_LIST_T_PENDING)) { - raw_spin_unlock_irqrestore(&loc_l->lock, flags); + raw_res_spin_unlock_irqrestore(&loc_l->lock, + flags); goto check_lru_list; } node->type = BPF_LRU_LOCAL_LIST_T_FREE; bpf_lru_node_clear_ref(node); - list_move(&node->list, local_free_list(loc_l)); + list_del(&node->list); + + raw_res_spin_unlock_irqrestore(&loc_l->lock, flags); - raw_spin_unlock_irqrestore(&loc_l->lock, flags); + llist_add(&node->llist, &loc_l->free_llist); return; } @@ -538,11 +570,14 @@ static void bpf_percpu_lru_push_free(struct bpf_lru *lru, l = per_cpu_ptr(lru->percpu_lru, node->cpu); - raw_spin_lock_irqsave(&l->lock, flags); + if (raw_res_spin_lock_irqsave(&l->lock, flags)) { + WRITE_ONCE(node->pending_free, 1); + return; + } __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE); - raw_spin_unlock_irqrestore(&l->lock, flags); + raw_res_spin_unlock_irqrestore(&l->lock, flags); } void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) @@ -565,6 +600,7 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; + node->pending_free = 0; bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; @@ -594,6 +630,7 @@ again: node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; + node->pending_free = 0; bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; @@ -618,14 +655,12 @@ void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, static void bpf_lru_locallist_init(struct bpf_lru_locallist *loc_l, int cpu) { - int i; - - for (i = 0; i < NR_BPF_LRU_LOCAL_LIST_T; i++) - INIT_LIST_HEAD(&loc_l->lists[i]); + INIT_LIST_HEAD(&loc_l->pending_list); + init_llist_head(&loc_l->free_llist); loc_l->next_steal = cpu; - raw_spin_lock_init(&loc_l->lock); + raw_res_spin_lock_init(&loc_l->lock); } static void bpf_lru_list_init(struct bpf_lru_list *l) @@ -640,7 +675,7 @@ static void bpf_lru_list_init(struct bpf_lru_list *l) l->next_inactive_rotation = &l->lists[BPF_LRU_LIST_T_INACTIVE]; - raw_spin_lock_init(&l->lock); + raw_res_spin_lock_init(&l->lock); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index fe2661a58ea9..8d0ee61622af 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -6,11 +6,11 @@ #include <linux/cache.h> #include <linux/list.h> -#include <linux/spinlock_types.h> +#include <linux/llist.h> +#include <asm/rqspinlock.h> #define NR_BPF_LRU_LIST_T (3) #define NR_BPF_LRU_LIST_COUNT (2) -#define NR_BPF_LRU_LOCAL_LIST_T (2) #define BPF_LOCAL_LIST_T_OFFSET NR_BPF_LRU_LIST_T enum bpf_lru_list_type { @@ -22,10 +22,22 @@ enum bpf_lru_list_type { }; struct bpf_lru_node { - struct list_head list; + /* + * A node is in at most one list at a time. The free path on the + * per-CPU locallist uses an llist, so share storage via a union. + */ + union { + struct list_head list; + struct llist_node llist; + }; u16 cpu; u8 type; u8 ref; + /* + * Marks nodes whose *_push_free() lock acquire failed; reclaimed + * by flush/shrink which honor the flag instead of del_from_htab(). + */ + u8 pending_free; }; struct bpf_lru_list { @@ -34,13 +46,14 @@ struct bpf_lru_list { /* The next inactive list rotation starts from here */ struct list_head *next_inactive_rotation; - raw_spinlock_t lock ____cacheline_aligned_in_smp; + rqspinlock_t lock ____cacheline_aligned_in_smp; }; struct bpf_lru_locallist { - struct list_head lists[NR_BPF_LRU_LOCAL_LIST_T]; + struct list_head pending_list; + struct llist_head free_llist; u16 next_steal; - raw_spinlock_t lock; + rqspinlock_t lock; }; struct bpf_common_lru { diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index c5c925f00202..1433809bb166 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -51,6 +51,9 @@ BTF_ID(func, bpf_lsm_key_getsecurity) #ifdef CONFIG_AUDIT BTF_ID(func, bpf_lsm_audit_rule_match) #endif +#ifdef CONFIG_SECURITY_NETWORK_XFRM +BTF_ID(func, bpf_lsm_xfrm_decode_session) +#endif BTF_ID(func, bpf_lsm_ismaclabel) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_SET_END(bpf_lsm_disabled_hooks) @@ -427,6 +430,26 @@ BTF_ID(func, bpf_lsm_audit_rule_known) BTF_ID(func, bpf_lsm_inode_xattr_skipcap) BTF_SET_END(bool_lsm_hooks) +/* hooks returning void */ +#define LSM_HOOK_void(DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) +#define LSM_HOOK_int(DEFAULT, NAME, ...) /* nothing */ +#define LSM_HOOK(RET, DEFAULT, NAME, ...) LSM_HOOK_##RET(DEFAULT, NAME, __VA_ARGS__) +BTF_SET_START(void_lsm_hooks) +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK +#undef LSM_HOOK_void +#undef LSM_HOOK_int +BTF_SET_END(void_lsm_hooks) + +bool bpf_lsm_hook_returns_errno(u32 btf_id) +{ + if (btf_id_set_contains(&bool_lsm_hooks, btf_id)) + return false; + if (btf_id_set_contains(&void_lsm_hooks, btf_id)) + return false; + return true; +} + int bpf_lsm_get_retval_range(const struct bpf_prog *prog, struct bpf_retval_range *retval_range) { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index f4eefdacd453..2f87c273e642 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -55,6 +55,28 @@ void __init cgroup_bpf_lifetime_notifier_init(void) &cgroup_bpf_lifetime_nb)); } +#ifdef CONFIG_BPF_LSM +struct cgroup_lsm_atype { + u32 attach_btf_id; + int refcnt; + bool returns_errno; +}; + +static struct cgroup_lsm_atype cgroup_lsm_atype[CGROUP_LSM_NUM]; + +static bool cgroup_bpf_hook_returns_errno(enum cgroup_bpf_attach_type atype) +{ + if (atype >= CGROUP_LSM_START && atype <= CGROUP_LSM_END) + return READ_ONCE(cgroup_lsm_atype[atype - CGROUP_LSM_START].returns_errno); + return true; +} +#else +static bool cgroup_bpf_hook_returns_errno(enum cgroup_bpf_attach_type atype) +{ + return true; +} +#endif + /* __always_inline is necessary to prevent indirect call through run_prog * function pointer. */ @@ -83,7 +105,8 @@ bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, *(ret_flags) |= (func_ret >> 1); func_ret &= 1; } - if (!func_ret && !IS_ERR_VALUE((long)run_ctx.retval)) + if (!func_ret && cgroup_bpf_hook_returns_errno(atype) && + !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; item++; } @@ -156,13 +179,6 @@ unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, } #ifdef CONFIG_BPF_LSM -struct cgroup_lsm_atype { - u32 attach_btf_id; - int refcnt; -}; - -static struct cgroup_lsm_atype cgroup_lsm_atype[CGROUP_LSM_NUM]; - static enum cgroup_bpf_attach_type bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) { @@ -191,10 +207,13 @@ void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) lockdep_assert_held(&cgroup_mutex); - WARN_ON_ONCE(cgroup_lsm_atype[i].attach_btf_id && - cgroup_lsm_atype[i].attach_btf_id != attach_btf_id); - - cgroup_lsm_atype[i].attach_btf_id = attach_btf_id; + if (!cgroup_lsm_atype[i].attach_btf_id) { + cgroup_lsm_atype[i].attach_btf_id = attach_btf_id; + WRITE_ONCE(cgroup_lsm_atype[i].returns_errno, + bpf_lsm_hook_returns_errno(attach_btf_id)); + } else { + WARN_ON_ONCE(cgroup_lsm_atype[i].attach_btf_id != attach_btf_id); + } cgroup_lsm_atype[i].refcnt++; } @@ -203,8 +222,10 @@ void bpf_cgroup_atype_put(int cgroup_atype) int i = cgroup_atype - CGROUP_LSM_START; cgroup_lock(); - if (--cgroup_lsm_atype[i].refcnt <= 0) + if (--cgroup_lsm_atype[i].refcnt <= 0) { + WRITE_ONCE(cgroup_lsm_atype[i].returns_errno, true); cgroup_lsm_atype[i].attach_btf_id = 0; + } WARN_ON_ONCE(cgroup_lsm_atype[i].refcnt < 0); cgroup_unlock(); } @@ -918,19 +939,65 @@ static int cgroup_bpf_attach(struct cgroup *cgrp, return ret; } +static int effective_prog_pos(struct cgroup *cgrp, + enum cgroup_bpf_attach_type atype, + struct bpf_prog_list *target_pl) +{ + int cnt = 0, preorder_cnt = 0, fstart, bstart, init_bstart, pos = -1; + struct bpf_prog_list *pl; + struct cgroup *p = cgrp; + + /* count effective programs to find where the preorder region ends */ + do { + if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) + cnt += prog_list_length(&p->bpf.progs[atype], &preorder_cnt); + p = cgroup_parent(p); + } while (p); + + /* replay compute_effective_progs() placement and record target's slot */ + cnt = 0; + p = cgrp; + fstart = preorder_cnt; + bstart = preorder_cnt - 1; + do { + if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) + continue; + + init_bstart = bstart; + hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { + if (!prog_list_prog(pl)) + continue; + + if (pl->flags & BPF_F_PREORDER) { + if (pl == target_pl) + pos = bstart; + bstart--; + } else { + if (pl == target_pl) + pos = fstart; + fstart++; + } + cnt++; + } + + /* reverse pre-ordering progs at this cgroup level */ + if (pos >= bstart + 1 && pos <= init_bstart) + pos = bstart + 1 + init_bstart - pos; + } while ((p = cgroup_parent(p))); + + return pos; +} + /* Swap updated BPF program for given link in effective program arrays across * all descendant cgroups. This function is guaranteed to succeed. */ static void replace_effective_prog(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype, - struct bpf_cgroup_link *link) + struct bpf_prog_list *pl) { struct bpf_prog_array_item *item; struct cgroup_subsys_state *css; struct bpf_prog_array *progs; - struct bpf_prog_list *pl; - struct hlist_head *head; - struct cgroup *cg; int pos; css_for_each_descendant_pre(css, &cgrp->self) { @@ -939,27 +1006,15 @@ static void replace_effective_prog(struct cgroup *cgrp, if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; - /* find position of link in effective progs array */ - for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { - if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) - continue; + pos = effective_prog_pos(desc, atype, pl); + if (WARN_ON_ONCE(pos < 0)) + continue; - head = &cg->bpf.progs[atype]; - hlist_for_each_entry(pl, head, node) { - if (!prog_list_prog(pl)) - continue; - if (pl->link == link) - goto found; - pos++; - } - } -found: - BUG_ON(!cg); progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); item = &progs->items[pos]; - WRITE_ONCE(item->prog, link->link.prog); + WRITE_ONCE(item->prog, pl->link->link.prog); } } @@ -1003,7 +1058,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, cgrp->bpf.revisions[atype] += 1; old_prog = xchg(&link->link.prog, new_prog); - replace_effective_prog(cgrp, atype, link); + replace_effective_prog(cgrp, atype, pl); bpf_prog_put(old_prog); return 0; } @@ -1070,19 +1125,14 @@ static struct bpf_prog_list *find_detach_entry(struct hlist_head *progs, * recomputing the array in place. * * @cgrp: The cgroup which descendants to travers - * @prog: A program to detach or NULL - * @link: A link to detach or NULL + * @pl: The prog_list entry being detached * @atype: Type of detach operation */ -static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_cgroup_link *link, +static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog_list *pl, enum cgroup_bpf_attach_type atype) { struct cgroup_subsys_state *css; struct bpf_prog_array *progs; - struct bpf_prog_list *pl; - struct hlist_head *head; - struct cgroup *cg; int pos; /* recompute effective prog array in place */ @@ -1092,24 +1142,11 @@ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog, if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; - /* find position of link or prog in effective progs array */ - for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { - if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) - continue; - - head = &cg->bpf.progs[atype]; - hlist_for_each_entry(pl, head, node) { - if (!prog_list_prog(pl)) - continue; - if (pl->prog == prog && pl->link == link) - goto found; - pos++; - } - } - + pos = effective_prog_pos(desc, atype, pl); /* no link or prog match, skip the cgroup of this layer */ - continue; -found: + if (pos < 0) + continue; + progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); @@ -1175,7 +1212,7 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* if update effective array failed replace the prog with a dummy prog*/ pl->prog = old_prog; pl->link = link; - purge_effective_progs(cgrp, old_prog, link, atype); + purge_effective_progs(cgrp, pl, atype); } /* now can actually delete it from this cgroup list */ @@ -1208,7 +1245,7 @@ static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* Must be called with cgroup_mutex held to avoid races. */ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr) + union bpf_attr __user *uattr, u32 uattr_size) { __u32 __user *prog_attach_flags = u64_to_user_ptr(attr->query.prog_attach_flags); bool effective_query = attr->query.query_flags & BPF_F_QUERY_EFFECTIVE; @@ -1259,7 +1296,8 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, return -EFAULT; if (!effective_query && from_atype == to_atype) revision = cgrp->bpf.revisions[from_atype]; - if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision))) + if (uattr_size >= offsetofend(union bpf_attr, query.revision) && + copy_to_user(&uattr->query.revision, &revision, sizeof(revision))) return -EFAULT; if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt) /* return early if user requested only program count + flags */ @@ -1312,12 +1350,12 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, } static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr) + union bpf_attr __user *uattr, u32 uattr_size) { int ret; cgroup_lock(); - ret = __cgroup_bpf_query(cgrp, attr, uattr); + ret = __cgroup_bpf_query(cgrp, attr, uattr, uattr_size); cgroup_unlock(); return ret; } @@ -1520,7 +1558,7 @@ out_put_cgroup: } int cgroup_bpf_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) + union bpf_attr __user *uattr, u32 uattr_size) { struct cgroup *cgrp; int ret; @@ -1529,7 +1567,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, if (IS_ERR(cgrp)) return PTR_ERR(cgrp); - ret = cgroup_bpf_query(cgrp, attr, uattr); + ret = cgroup_bpf_query(cgrp, attr, uattr, uattr_size); cgroup_put(cgrp); return ret; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index de61e1894452..f5d9c27e654d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2527,7 +2527,7 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map, cookie = aux->cgroup_storage[i] ? aux->cgroup_storage[i]->cookie : 0; ret = map->owner->storage_cookie[i] == cookie || - !cookie; + (!cookie && !aux->tail_call_reachable); } if (ret && map->owner->attach_func_proto != aux->attach_func_proto) { diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 5b9eac5342a9..dc7b859e8bbf 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -710,6 +710,18 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, if (unlikely(err)) return err; + if (dst->xdp_prog && skb_cloned(skb)) { + struct sk_buff *nskb; + + nskb = skb_copy(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + + nskb->mac_len = skb->mac_len; + consume_skb(skb); + skb = nskb; + } + /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index f8a3c7eb451e..0391b3bc0073 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -323,7 +323,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, */ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD || - insn->src_reg == BPF_PSEUDO_MAP_VALUE; + insn->src_reg == BPF_PSEUDO_MAP_VALUE || + insn->src_reg == BPF_PSEUDO_MAP_IDX || + insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE || + insn->src_reg == BPF_PSEUDO_BTF_ID; char tmp[64]; if (is_ptr && !allow_ptr_leaks) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3dd9b4924ae4..74c5ced74032 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -242,6 +242,10 @@ static void htab_free_prealloced_fields(struct bpf_htab *htab) if (IS_ERR_OR_NULL(htab->map.record)) return; + /* + * Preallocated maps do not have a bpf_mem_alloc destructor, so fully + * destroy every element, including the extra elements. + */ if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); for (i = 0; i < num_entries; i++) { @@ -834,8 +838,8 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, return insn - insn_buf; } -static void check_and_free_fields(struct bpf_htab *htab, - struct htab_elem *elem) +static void check_and_cancel_fields(struct bpf_htab *htab, + struct htab_elem *elem) { if (IS_ERR_OR_NULL(htab->map.record)) return; @@ -845,11 +849,11 @@ static void check_and_free_fields(struct bpf_htab *htab, int cpu; for_each_possible_cpu(cpu) - bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu)); + bpf_obj_cancel_fields(&htab->map, per_cpu_ptr(pptr, cpu)); } else { void *map_value = htab_elem_value(elem, htab->map.key_size); - bpf_obj_free_fields(htab->map.record, map_value); + bpf_obj_cancel_fields(&htab->map, map_value); } } @@ -884,7 +888,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) htab_unlock_bucket(b, flags); if (l == tgt_l) - check_and_free_fields(htab, l); + check_and_cancel_fields(htab, l); return l == tgt_l; } @@ -949,7 +953,7 @@ find_first_elem: static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { - check_and_free_fields(htab, l); + check_and_cancel_fields(htab, l); if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr); @@ -1002,7 +1006,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) if (htab_is_prealloc(htab)) { bpf_map_dec_elem_count(&htab->map); - check_and_free_fields(htab, l); + check_and_cancel_fields(htab, l); pcpu_freelist_push(&htab->freelist, &l->fnode); } else { dec_elem_count(htab); @@ -1019,7 +1023,7 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, /* copy true value_size bytes */ ptr = this_cpu_ptr(pptr); copy_map_value(&htab->map, ptr, value); - bpf_obj_free_fields(htab->map.record, ptr); + bpf_obj_cancel_fields(&htab->map, ptr); } else { u32 size = round_up(htab->map.value_size, 8); void *val; @@ -1029,7 +1033,7 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, cpu = map_flags >> 32; ptr = per_cpu_ptr(pptr, cpu); copy_map_value(&htab->map, ptr, value); - bpf_obj_free_fields(htab->map.record, ptr); + bpf_obj_cancel_fields(&htab->map, ptr); return; } @@ -1037,7 +1041,7 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, ptr = per_cpu_ptr(pptr, cpu); val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; copy_map_value(&htab->map, ptr, val); - bpf_obj_free_fields(htab->map.record, ptr); + bpf_obj_cancel_fields(&htab->map, ptr); } } } @@ -1253,11 +1257,11 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (l_old) { hlist_nulls_del_rcu(&l_old->hash_node); - /* l_old has already been stashed in htab->extra_elems, free - * its special fields before it is available for reuse. + /* l_old has already been stashed in htab->extra_elems, cancel + * its reusable special fields before it is available for reuse. */ if (htab_is_prealloc(htab)) - check_and_free_fields(htab, l_old); + check_and_cancel_fields(htab, l_old); } htab_unlock_bucket(b, flags); if (l_old && !htab_is_prealloc(htab)) @@ -1270,7 +1274,7 @@ err: static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem) { - check_and_free_fields(htab, elem); + check_and_cancel_fields(htab, elem); bpf_map_dec_elem_count(&htab->map); bpf_lru_push_free(&htab->lru, &elem->lru_node); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b5314c9fed3c..c2032af98e08 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2295,6 +2295,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root, struct bpf_spin_lock *spin_lock) { struct rb_root_cached orig_root, *root = rb_root; + struct bpf_rb_node_kern *node; struct rb_node *pos, *n; void *obj; @@ -2303,14 +2304,20 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root, __bpf_spin_lock_irqsave(spin_lock); orig_root = *root; + bpf_rbtree_postorder_for_each_entry_safe(pos, n, &orig_root.rb_root) { + node = rb_entry(pos, struct bpf_rb_node_kern, rb_node); + WRITE_ONCE(node->owner, BPF_PTR_POISON); + } *root = RB_ROOT_CACHED; __bpf_spin_unlock_irqrestore(spin_lock); bpf_rbtree_postorder_for_each_entry_safe(pos, n, &orig_root.rb_root) { obj = pos; obj -= field->graph_root.node_offset; - - + node = rb_entry(pos, struct bpf_rb_node_kern, rb_node); + RB_CLEAR_NODE(pos); + /* Ensure __bpf_rbtree_add() sees the node as unlinked. */ + smp_store_release(&node->owner, NULL); __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false); } } @@ -2912,11 +2919,13 @@ __bpf_kfunc struct task_struct *bpf_task_from_vpid(s32 vpid) { struct task_struct *p; - rcu_read_lock(); + guard(rcu)(); + if (!task_active_pid_ns(current)) + return NULL; + p = find_task_by_vpid(vpid); if (p) p = bpf_task_acquire(p); - rcu_read_unlock(); return p; } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 25c06a011825..188c774a469c 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -766,10 +766,18 @@ static void bpf_destroy_inode(struct inode *inode) { enum bpf_type type; - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); if (!bpf_inode_type(inode, &type)) bpf_any_put(inode->i_private, type); +} + +/* + * Called after RCU grace period - safe to free inode and anything + * that might be accessed by RCU pathwalk (inode fields, i_link). + */ +static void bpf_free_inode(struct inode *inode) +{ + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); free_inode_nonrcu(inode); } @@ -778,6 +786,7 @@ const struct super_operations bpf_super_ops = { .drop_inode = inode_just_drop, .show_options = bpf_show_options, .destroy_inode = bpf_destroy_inode, + .free_inode = bpf_free_inode, }; enum { diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 645bd30bc9a9..d2cbab4bdf64 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -20,7 +20,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) /* Does not support >1 level map-in-map */ if (inner_map->inner_map_meta) return ERR_PTR(-EINVAL); - + if (inner_map->excl_prog_sha) + return ERR_PTR(-ENOTSUPP); if (!inner_map->ops->map_meta_equal) return ERR_PTR(-ENOTSUPP); @@ -101,6 +102,8 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, inner_map = __bpf_map_get(f); if (IS_ERR(inner_map)) return inner_map; + if (inner_map->excl_prog_sha) + return ERR_PTR(-ENOTSUPP); inner_map_meta = map->inner_map_meta; if (inner_map_meta->ops->map_meta_equal(inner_map_meta, inner_map)) diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 261a03ea73d3..ae0741a09c6d 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -112,6 +112,10 @@ static int bpf_iter_attach_map(struct bpf_prog *prog, map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map); + if (map->excl_prog_sha) { + err = -EPERM; + goto put_map; + } if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || diff --git a/kernel/bpf/states.c b/kernel/bpf/states.c index 8478d2c6ed5b..1dd99b3194d7 100644 --- a/kernel/bpf/states.c +++ b/kernel/bpf/states.c @@ -437,12 +437,10 @@ static void __clean_func_state(struct bpf_verifier_env *env, continue; /* - * Only destroy spilled_ptr when hi half is dead. - * If hi half is still live with STACK_SPILL, the - * spilled_ptr metadata is needed for correct state - * comparison in stacksafe(). - * is_spilled_reg() is using slot_type[7], but - * is_spilled_scalar_after() check either slot_type[0] or [4] + * Only scalar spills can be degraded to raw stack bytes + * when their high half is dead. Pointer spills need the + * saved spilled_ptr metadata so partial fills keep + * rejecting as non-scalar register fills. */ if (!hi_live) { struct bpf_reg_state *spill = &st->stack[i].spilled_ptr; @@ -450,6 +448,9 @@ static void __clean_func_state(struct bpf_verifier_env *env, if (lo_live && stype == STACK_SPILL) { u8 val = STACK_MISC; + if (spill->type != SCALAR_VALUE) + continue; + /* * 8 byte spill of scalar 0 where half slot is dead * should become STACK_ZERO in lo 4 bytes. diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 630d530782fe..96d1b797e152 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -807,6 +807,11 @@ void bpf_obj_free_task_work(const struct btf_record *rec, void *obj) bpf_task_work_cancel_and_free(obj + rec->task_work_off); } +void bpf_obj_cancel_fields(struct bpf_map *map, void *obj) +{ + bpf_map_free_internal_structs(map, obj); +} + void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; @@ -1572,6 +1577,13 @@ static int map_create(union bpf_attr *attr, bpfptr_t uattr) err = -EFAULT; goto free_map; } + + /* See libbpf: emit_signature_match() */ + BUILD_BUG_ON(offsetof(struct bpf_map, excl) != SHA256_DIGEST_SIZE); + BUILD_BUG_ON(!__same_type(map->excl, u32)); + BUILD_BUG_ON(offsetof(struct bpf_map, sha) != 0); + BUILD_BUG_ON(!__same_type(map->sha, u8[SHA256_DIGEST_SIZE])); + map->excl = 1; } else if (attr->excl_prog_hash_size) { err = -EINVAL; goto free_map; @@ -4281,6 +4293,11 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, if (!btp) return -ENOENT; + if (prog->sleepable && !tracepoint_is_faultable(btp->tp)) { + bpf_put_raw_tracepoint(btp); + return -EINVAL; + } + link = kzalloc_obj(*link, GFP_USER); if (!link) { err = -ENOMEM; @@ -4654,7 +4671,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) #define BPF_PROG_QUERY_LAST_FIELD query.revision static int bpf_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) + union bpf_attr __user *uattr, u32 uattr_size) { if (!bpf_net_capable()) return -EPERM; @@ -4693,7 +4710,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: case BPF_LSM_CGROUP: - return cgroup_bpf_prog_query(attr, uattr); + return cgroup_bpf_prog_query(attr, uattr, uattr_size); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: @@ -5045,10 +5062,11 @@ static int bpf_prog_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; struct bpf_prog_kstats stats; char __user *uinsns; - u32 ulen; + u32 ulen, len; int err; - err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); + len = offsetofend(struct bpf_prog_info, attach_btf_id); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), len, info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -5330,10 +5348,11 @@ static int bpf_map_get_info_by_fd(struct file *file, { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_map_info info; - u32 info_len = attr->info.info_len; + u32 info_len = attr->info.info_len, len; int err; - err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); + len = offsetofend(struct bpf_map_info, hash_size); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), len, info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -6189,7 +6208,7 @@ static int prog_stream_read(union bpf_attr *attr) return ret; } -#define BPF_PROG_ASSOC_STRUCT_OPS_LAST_FIELD prog_assoc_struct_ops.prog_fd +#define BPF_PROG_ASSOC_STRUCT_OPS_LAST_FIELD prog_assoc_struct_ops.flags static int prog_assoc_struct_ops(union bpf_attr *attr) { @@ -6286,7 +6305,7 @@ static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: - err = bpf_prog_query(&attr, uattr.user); + err = bpf_prog_query(&attr, uattr.user, size); break; case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr.user); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ff9b1f68ceca..523f00e609e2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3836,7 +3836,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { - u8 type = state->stack[spi].slot_type[i]; + u8 type = state->stack[spi].slot_type[(slot - i) % + BPF_REG_SIZE]; if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; @@ -5558,14 +5559,11 @@ static int check_max_stack_depth(struct bpf_verifier_env *env) static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, - int regno, int off, int size) + int regno, int off, int size, + u32 *access_end) { - if (off < 0) { - verbose(env, - "R%d invalid %s buffer access: off=%d, size=%d\n", - regno, buf_info, off, size); - return -EACCES; - } + s64 start; + if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; @@ -5576,6 +5574,15 @@ static int __check_buffer_access(struct bpf_verifier_env *env, return -EACCES; } + start = (s64)reg->var_off.value + off; + if (start < 0) { + verbose(env, + "R%d invalid negative %s buffer offset: off=%d, var_off=%lld\n", + regno, buf_info, off, (s64)reg->var_off.value); + return -EACCES; + } + + *access_end = start + size; return 0; } @@ -5583,14 +5590,14 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size) { + u32 access_end; int err; - err = __check_buffer_access(env, "tracepoint", reg, regno, off, size); + err = __check_buffer_access(env, "tracepoint", reg, regno, off, size, &access_end); if (err) return err; - env->prog->aux->max_tp_access = max(reg->var_off.value + off + size, - env->prog->aux->max_tp_access); + env->prog->aux->max_tp_access = max(access_end, env->prog->aux->max_tp_access); return 0; } @@ -5602,13 +5609,14 @@ static int check_buffer_access(struct bpf_verifier_env *env, u32 *max_access) { const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr"; + u32 access_end; int err; - err = __check_buffer_access(env, buf_info, reg, regno, off, size); + err = __check_buffer_access(env, buf_info, reg, regno, off, size, &access_end); if (err) return err; - *max_access = max(reg->var_off.value + off + size, *max_access); + *max_access = max(access_end, *max_access); return 0; } @@ -6453,6 +6461,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn */ if (info.reg_type == SCALAR_VALUE) { if (info.is_retval && get_func_retval_range(env->prog, &range)) { + mark_reg_unknown(env, regs, value_regno); err = __mark_reg_s32_range(env, regs, value_regno, range.minval, range.maxval); if (err) @@ -19317,6 +19326,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, btp = bpf_get_raw_tracepoint(tname); if (!btp) return -EINVAL; + if (prog->sleepable && !tracepoint_is_faultable(btp->tp)) { + bpf_log(log, "Sleepable program cannot attach to non-faultable tracepoint %s\n", + tname); + bpf_put_raw_tracepoint(btp); + return -EINVAL; + } fname = kallsyms_lookup((unsigned long)btp->bpf_func, NULL, NULL, NULL, trace_symbol); bpf_put_raw_tracepoint(btp); @@ -19533,14 +19548,19 @@ static bool can_be_sleepable(struct bpf_prog *prog) case BPF_MODIFY_RETURN: case BPF_TRACE_ITER: case BPF_TRACE_FSESSION: + case BPF_TRACE_RAW_TP: return true; default: return false; } } - return prog->type == BPF_PROG_TYPE_LSM || - prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ || - prog->type == BPF_PROG_TYPE_STRUCT_OPS; + if (prog->type == BPF_PROG_TYPE_LSM) + return prog->expected_attach_type != BPF_LSM_CGROUP; + + return prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ || + prog->type == BPF_PROG_TYPE_STRUCT_OPS || + prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT || + prog->type == BPF_PROG_TYPE_TRACEPOINT; } static int check_attach_btf_id(struct bpf_verifier_env *env) @@ -19562,7 +19582,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) } if (prog->sleepable && !can_be_sleepable(prog)) { - verbose(env, "Only fentry/fexit/fsession/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n"); + verbose(env, "Program of this type cannot be sleepable\n"); return -EINVAL; } @@ -20209,13 +20229,13 @@ err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); bpf_clear_insn_aux_data(env, 0, env->prog->len); - vfree(env->insn_aux_data); err_free_env: bpf_stack_liveness_free(env); kvfree(env->cfg.insn_postorder); kvfree(env->scc_info); kvfree(env->succ); kvfree(env->gotox_tmp_buf); + vfree(env->insn_aux_data); kvfree(env); return ret; } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c9e14fda3d6f..8407bf44e807 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2650,7 +2650,12 @@ void cpuset_update_tasks_nodemask(struct cpuset *cs) migrate = is_memory_migrate(cs); - mpol_rebind_mm(mm, &cs->mems_allowed); + /* + * For v1 we can have empty effective_mems, but we cannot + * attach any tasks (see cpuset_can_attach_check()). For v2, + * effective_mems is guaranteed to not be empty. + */ + mpol_rebind_mm(mm, &cs->effective_mems); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else diff --git a/kernel/cpu.c b/kernel/cpu.c index bc4f7a9ba64e..b9acc261b127 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -174,7 +174,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); - int ret, cnt; + int ret, cnt, rollback_ret; if (st->fail == state) { st->fail = CPUHP_INVALID; @@ -238,12 +238,12 @@ err: break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); - ret = cbm(cpu, node); - trace_cpuhp_exit(cpu, st->state, state, ret); + rollback_ret = cbm(cpu, node); + trace_cpuhp_exit(cpu, st->state, state, rollback_ret); /* * Rollback must not fail, */ - WARN_ON_ONCE(ret); + WARN_ON_ONCE(rollback_ret); } return ret; } @@ -2854,21 +2854,17 @@ static const struct attribute_group cpuhp_cpu_attr_group = { .name = "hotplug", }; -static ssize_t states_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { - ssize_t cur, res = 0; + ssize_t res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); - if (sp->name) { - cur = sprintf(buf, "%3d: %s\n", i, sp->name); - buf += cur; - res += cur; - } + if (sp->name) + res += sysfs_emit_at(buf, res, "%3d: %s\n", i, sp->name); } mutex_unlock(&cpuhp_state_mutex); return res; diff --git a/kernel/exit.c b/kernel/exit.c index f50d73c272d6..7ba7966a23b9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -212,7 +212,12 @@ static void __exit_signal(struct release_task_post *post, struct task_struct *ts __unhash_process(post, tsk, group_dead); write_sequnlock(&sig->stats_lock); - tsk->sighand = NULL; + /* + * Ensure that all preceeding state is visible. Pairs with + * the smp_acquire__after_ctrl_dep() in the sighand == NULL + * path of lock_task_sighand(). + */ + smp_store_release(&tsk->sighand, NULL); spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); diff --git a/kernel/fork.c b/kernel/fork.c index 145bcc4c8e12..5a4623b058a2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1004,6 +1004,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->mm_cid.active = 0; INIT_HLIST_NODE(&tsk->mm_cid.node); #endif + +#ifdef CONFIG_BPF_SYSCALL + RCU_INIT_POINTER(tsk->bpf_storage, NULL); + tsk->bpf_ctx = NULL; +#endif return tsk; free_stack: @@ -2223,10 +2228,6 @@ __latent_entropy struct task_struct *copy_process( p->sequential_io = 0; p->sequential_io_avg = 0; #endif -#ifdef CONFIG_BPF_SYSCALL - RCU_INIT_POINTER(p->bpf_storage, NULL); - p->bpf_ctx = NULL; -#endif unwind_task_init(p); diff --git a/kernel/kcov.c b/kernel/kcov.c index 0b369e88c7c9..f3a5ae960ce5 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -1109,10 +1109,10 @@ static void __init selftest(void) * potentially traced functions in this region. */ start = jiffies; - current->kcov_mode = KCOV_MODE_TRACE_PC; + WRITE_ONCE(current->kcov_mode, KCOV_MODE_TRACE_PC); while ((jiffies - start) * MSEC_PER_SEC / HZ < 300) ; - current->kcov_mode = 0; + WRITE_ONCE(current->kcov_mode, 0); pr_err("done running self test\n"); } #endif diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index a43d2da0fe3e..dc770b9a6d05 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1146,9 +1146,11 @@ int kernel_kexec(void) goto Unlock; } - error = liveupdate_reboot(); - if (error) - goto Unlock; + if (!kexec_image->preserve_context) { + error = liveupdate_reboot(); + if (error) + goto Unlock; + } #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 1b592d86dc48..48d98fa9621e 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -593,20 +593,30 @@ early_param("kho_scratch", kho_parse_scratch_size); static void __init scratch_size_update(void) { - phys_addr_t size; + /* + * If fixed sizes are not provided via command line, calculate them + * now. + */ + if (scratch_scale) { + phys_addr_t size; - if (!scratch_scale) - return; + size = memblock_reserved_kern_size(ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); + size = size * scratch_scale / 100; + scratch_size_lowmem = size; - size = memblock_reserved_kern_size(ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); - size = size * scratch_scale / 100; - scratch_size_lowmem = round_up(size, CMA_MIN_ALIGNMENT_BYTES); + size = memblock_reserved_kern_size(MEMBLOCK_ALLOC_ANYWHERE, + NUMA_NO_NODE); + size = size * scratch_scale / 100 - scratch_size_lowmem; + scratch_size_global = size; + } - size = memblock_reserved_kern_size(MEMBLOCK_ALLOC_ANYWHERE, - NUMA_NO_NODE); - size = size * scratch_scale / 100 - scratch_size_lowmem; - scratch_size_global = round_up(size, CMA_MIN_ALIGNMENT_BYTES); + /* + * Scratch areas are released as MIGRATE_CMA. Round them up to the right + * size. + */ + scratch_size_lowmem = round_up(scratch_size_lowmem, CMA_MIN_ALIGNMENT_BYTES); + scratch_size_global = round_up(scratch_size_global, CMA_MIN_ALIGNMENT_BYTES); } static phys_addr_t __init scratch_size_node(int nid) diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index a0a419085e28..208987502f73 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -385,10 +385,11 @@ void luo_file_unpreserve_files(struct luo_file_set *file_set) args.private_data = luo_file->private_data; luo_file->fh->ops->unpreserve(&args); luo_flb_file_unpreserve(luo_file->fh); - module_put(luo_file->fh->ops->owner); xa_erase(&luo_preserved_files, luo_get_id(luo_file->fh, luo_file->file)); + module_put(luo_file->fh->ops->owner); + list_del(&luo_file->list); file_set->count--; @@ -677,7 +678,6 @@ static void luo_file_finish_one(struct luo_file_set *file_set, luo_file->fh->ops->finish(&args); luo_flb_file_finish(luo_file->fh); - module_put(luo_file->fh->ops->owner); } /** @@ -738,6 +738,7 @@ int luo_file_finish(struct luo_file_set *file_set) luo_get_id(luo_file->fh, luo_file->file)); fput(luo_file->file); } + module_put(luo_file->fh->ops->owner); list_del(&luo_file->list); file_set->count--; mutex_destroy(&luo_file->mutex); diff --git a/kernel/liveupdate/luo_flb.c b/kernel/liveupdate/luo_flb.c index 00f5494812c4..8f5c5dd01cd0 100644 --- a/kernel/liveupdate/luo_flb.c +++ b/kernel/liveupdate/luo_flb.c @@ -111,7 +111,7 @@ static int luo_flb_file_preserve_one(struct liveupdate_flb *flb) struct luo_flb_private *private = luo_flb_get_private(flb); scoped_guard(mutex, &private->outgoing.lock) { - if (!private->outgoing.count) { + if (!refcount_read(&private->outgoing.count)) { struct liveupdate_flb_op_args args = {0}; int err; @@ -126,8 +126,10 @@ static int luo_flb_file_preserve_one(struct liveupdate_flb *flb) } private->outgoing.data = args.data; private->outgoing.obj = args.obj; + refcount_set(&private->outgoing.count, 1); + } else { + refcount_inc(&private->outgoing.count); } - private->outgoing.count++; } return 0; @@ -138,8 +140,7 @@ static void luo_flb_file_unpreserve_one(struct liveupdate_flb *flb) struct luo_flb_private *private = luo_flb_get_private(flb); scoped_guard(mutex, &private->outgoing.lock) { - private->outgoing.count--; - if (!private->outgoing.count) { + if (refcount_dec_and_test(&private->outgoing.count)) { struct liveupdate_flb_op_args args = {0}; args.flb = flb; @@ -164,7 +165,7 @@ static int luo_flb_retrieve_one(struct liveupdate_flb *flb) bool found = false; int err; - guard(mutex)(&private->incoming.lock); + lockdep_assert_held(&private->incoming.lock); if (private->incoming.finished) return -ENODATA; @@ -178,7 +179,7 @@ static int luo_flb_retrieve_one(struct liveupdate_flb *flb) for (int i = 0; i < fh->header_ser->count; i++) { if (!strcmp(fh->ser[i].name, flb->compatible)) { private->incoming.data = fh->ser[i].data; - private->incoming.count = fh->ser[i].count; + refcount_set(&private->incoming.count, fh->ser[i].count); found = true; break; } @@ -205,16 +206,14 @@ static int luo_flb_retrieve_one(struct liveupdate_flb *flb) return 0; } -static void luo_flb_file_finish_one(struct liveupdate_flb *flb) +void liveupdate_flb_put_incoming(struct liveupdate_flb *flb) { struct luo_flb_private *private = luo_flb_get_private(flb); - u64 count; - - scoped_guard(mutex, &private->incoming.lock) - count = --private->incoming.count; + struct liveupdate_flb_op_args args = {0}; - if (!count) { - struct liveupdate_flb_op_args args = {0}; + scoped_guard(mutex, &private->incoming.lock) { + if (!refcount_dec_and_test(&private->incoming.count)) + return; if (!private->incoming.retrieved) { int err = luo_flb_retrieve_one(flb); @@ -223,16 +222,14 @@ static void luo_flb_file_finish_one(struct liveupdate_flb *flb) return; } - scoped_guard(mutex, &private->incoming.lock) { - args.flb = flb; - args.obj = private->incoming.obj; - flb->ops->finish(&args); + args.flb = flb; + args.obj = private->incoming.obj; + flb->ops->finish(&args); - private->incoming.data = 0; - private->incoming.obj = NULL; - private->incoming.finished = true; - module_put(flb->ops->owner); - } + private->incoming.data = 0; + private->incoming.obj = NULL; + private->incoming.finished = true; + module_put(flb->ops->owner); } } @@ -315,7 +312,7 @@ void luo_flb_file_finish(struct liveupdate_file_handler *fh) guard(rwsem_read)(&luo_register_rwlock); list_for_each_entry_reverse(iter, flb_list, list) - luo_flb_file_finish_one(iter->flb); + liveupdate_flb_put_incoming(iter->flb); } static void luo_flb_unregister_one(struct liveupdate_file_handler *fh, @@ -512,6 +509,8 @@ int liveupdate_flb_get_incoming(struct liveupdate_flb *flb, void **objp) if (!liveupdate_enabled()) return -EOPNOTSUPP; + guard(mutex)(&private->incoming.lock); + if (!private->incoming.obj) { int err = luo_flb_retrieve_one(flb); @@ -519,7 +518,7 @@ int liveupdate_flb_get_incoming(struct liveupdate_flb *flb, void **objp) return err; } - guard(mutex)(&private->incoming.lock); + refcount_inc(&private->incoming.count); *objp = private->incoming.obj; return 0; @@ -652,12 +651,13 @@ void luo_flb_serialize(void) guard(rwsem_read)(&luo_register_rwlock); list_private_for_each_entry(gflb, &luo_flb_global.list, private.list) { struct luo_flb_private *private = luo_flb_get_private(gflb); + long count = refcount_read(&private->outgoing.count); - if (private->outgoing.count > 0) { + if (count > 0) { strscpy(fh->ser[i].name, gflb->compatible, sizeof(fh->ser[i].name)); fh->ser[i].data = private->outgoing.data; - fh->ser[i].count = private->outgoing.count; + fh->ser[i].count = count; i++; } } diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c index ec7aebc15a80..174de2cc56a6 100644 --- a/kernel/liveupdate/luo_session.c +++ b/kernel/liveupdate/luo_session.c @@ -46,6 +46,38 @@ * 4. Retrieval: A userspace agent in the new kernel can then call * `luo_session_retrieve()` with a session name to get a new file * descriptor and access the preserved state. + * + * Locking: + * + * The LUO session subsystem uses a three-tier locking hierarchy to ensure thread + * safety and prevent deadlocks during concurrent session mutations and kexec + * serialization: + * + * 1. `luo_session_serialize_rwsem` (global rwsem): + * Protects session mutations (creation, retrieval, release, and ioctls) + * against the serialization process during reboot. + * + * - Readers: Taken by any path modifying or accessing session state (e.g., + * `luo_session_create()`, `luo_session_retrieve()`, `luo_session_release()`, + * and `luo_session_ioctl()`). + * - Writer: Taken by the serialization process (`luo_session_serialize()`) + * during reboot. On success, the write lock is held indefinitely to freeze + * the subsystem. On failure, it is released to allow recovery. + * + * 2. `luo_session_header->rwsem` (per-list rwsem): + * Synchronizes list-level operations for the incoming and outgoing session headers. + * + * - Writer: Taken during list mutation operations (inserting or removing a + * session from the list). + * - Reader: Taken when traversing the list (e.g., retrieving a session by name). + * + * 3. `luo_session->mutex` (per-session mutex): + * Protects the internal state and file sets of an individual session. It is + * acquired during per-session operations such as preserving, retrieving, + * or freezing files. + * + * Lock Hierarchy: + * `luo_session_serialize_rwsem` -> `luo_session_header->rwsem` -> `luo_session->mutex` */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -75,6 +107,8 @@ sizeof(struct luo_session_header_ser)) / \ sizeof(struct luo_session_ser)) +static DECLARE_RWSEM(luo_session_serialize_rwsem); + /** * struct luo_session_header - Header struct for managing LUO sessions. * @count: The number of sessions currently tracked in the @list. @@ -205,6 +239,7 @@ static int luo_session_release(struct inode *inodep, struct file *filep) struct luo_session *session = filep->private_data; struct luo_session_header *sh; + guard(rwsem_read)(&luo_session_serialize_rwsem); /* If retrieved is set, it means this session is from incoming list */ if (session->retrieved) { int err = luo_session_finish_one(session); @@ -295,32 +330,58 @@ union ucmd_buffer { struct liveupdate_session_retrieve_fd retrieve; }; +/* Type of sessions the ioctl applies to. */ +enum luo_ioctl_type { + LUO_IOCTL_INCOMING, + LUO_IOCTL_OUTGOING, + LUO_IOCTL_ALL, +}; + struct luo_ioctl_op { unsigned int size; unsigned int min_size; unsigned int ioctl_num; + enum luo_ioctl_type type; int (*execute)(struct luo_session *session, struct luo_ucmd *ucmd); }; -#define IOCTL_OP(_ioctl, _fn, _struct, _last) \ +#define IOCTL_OP(_ioctl, _fn, _struct, _last, _type) \ [_IOC_NR(_ioctl) - LIVEUPDATE_CMD_SESSION_BASE] = { \ .size = sizeof(_struct) + \ BUILD_BUG_ON_ZERO(sizeof(union ucmd_buffer) < \ sizeof(_struct)), \ .min_size = offsetofend(_struct, _last), \ .ioctl_num = _ioctl, \ + .type = _type, \ .execute = _fn, \ } static const struct luo_ioctl_op luo_session_ioctl_ops[] = { IOCTL_OP(LIVEUPDATE_SESSION_FINISH, luo_session_finish, - struct liveupdate_session_finish, reserved), + struct liveupdate_session_finish, reserved, LUO_IOCTL_INCOMING), IOCTL_OP(LIVEUPDATE_SESSION_PRESERVE_FD, luo_session_preserve_fd, - struct liveupdate_session_preserve_fd, token), + struct liveupdate_session_preserve_fd, token, LUO_IOCTL_OUTGOING), IOCTL_OP(LIVEUPDATE_SESSION_RETRIEVE_FD, luo_session_retrieve_fd, - struct liveupdate_session_retrieve_fd, token), + struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_INCOMING), }; +static bool luo_ioctl_type_valid(struct luo_session *session, + const struct luo_ioctl_op *op) +{ + switch (op->type) { + case LUO_IOCTL_INCOMING: + /* Retrieved is only set on incoming sessions */ + return session->retrieved; + case LUO_IOCTL_OUTGOING: + return !session->retrieved; + case LUO_IOCTL_ALL: + return true; + } + + /* Catch-all. */ + return false; +} + static long luo_session_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { @@ -345,6 +406,8 @@ static long luo_session_ioctl(struct file *filep, unsigned int cmd, op = &luo_session_ioctl_ops[nr - LIVEUPDATE_CMD_SESSION_BASE]; if (op->ioctl_num != cmd) return -ENOIOCTLCMD; + if (!luo_ioctl_type_valid(session, op)) + return -EINVAL; if (ucmd.user_size < op->min_size) return -EINVAL; @@ -354,6 +417,7 @@ static long luo_session_ioctl(struct file *filep, unsigned int cmd, if (ret) return ret; + guard(rwsem_read)(&luo_session_serialize_rwsem); return op->execute(session, &ucmd); } @@ -393,14 +457,17 @@ int luo_session_create(const char *name, struct file **filep) if (IS_ERR(session)) return PTR_ERR(session); + down_read(&luo_session_serialize_rwsem); err = luo_session_insert(&luo_session_global.outgoing, session); if (err) goto err_free; - scoped_guard(mutex, &session->mutex) - err = luo_session_getfile(session, filep); + mutex_lock(&session->mutex); + err = luo_session_getfile(session, filep); + mutex_unlock(&session->mutex); if (err) goto err_remove; + up_read(&luo_session_serialize_rwsem); return 0; @@ -408,6 +475,7 @@ err_remove: luo_session_remove(&luo_session_global.outgoing, session); err_free: luo_session_free(session); + up_read(&luo_session_serialize_rwsem); return err; } @@ -419,12 +487,12 @@ int luo_session_retrieve(const char *name, struct file **filep) struct luo_session *it; int err; - scoped_guard(rwsem_read, &sh->rwsem) { - list_for_each_entry(it, &sh->list, list) { - if (!strncmp(it->name, name, sizeof(it->name))) { - session = it; - break; - } + guard(rwsem_read)(&luo_session_serialize_rwsem); + guard(rwsem_read)(&sh->rwsem); + list_for_each_entry(it, &sh->list, list) { + if (!strncmp(it->name, name, sizeof(it->name))) { + session = it; + break; } } @@ -592,7 +660,8 @@ int luo_session_serialize(void) int i = 0; int err; - guard(rwsem_write)(&sh->rwsem); + down_write(&luo_session_serialize_rwsem); + down_write(&sh->rwsem); list_for_each_entry(session, &sh->list, list) { err = luo_session_freeze_one(session, &sh->ser[i]); if (err) @@ -603,6 +672,7 @@ int luo_session_serialize(void) i++; } sh->header_ser->count = sh->count; + up_write(&sh->rwsem); return 0; @@ -612,7 +682,8 @@ err_undo: luo_session_unfreeze_one(session, &sh->ser[i]); memset(sh->ser[i].name, 0, sizeof(sh->ser[i].name)); } + up_write(&sh->rwsem); + up_write(&luo_session_serialize_rwsem); return err; } - diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c index db1e11b45de6..1d5e1b3c60bf 100644 --- a/kernel/locking/spinlock_rt.c +++ b/kernel/locking/spinlock_rt.c @@ -79,10 +79,27 @@ void __sched rt_spin_unlock(spinlock_t *lock) __releases(RCU) { spin_release(&lock->dep_map, _RET_IP_); migrate_enable(); - rcu_read_unlock(); if (unlikely(!rt_mutex_cmpxchg_release(&lock->lock, current, NULL))) rt_mutex_slowunlock(&lock->lock); + + /* + * This must be last to prevent the following UAF: + * + * T1 T2 + * spin_lock(&p->lock); rcu_read_lock(); + * invalidate(p); p = rcu_dereference(ptr); + * rcu_assign_pointer(ptr, NULL); if (!p) return; + * spin_unlock(&p->lock); spin_lock(&p->lock); + * kfree_rcu(p); rcu_read_unlock(); + * .... + * spin_unlock(&p->lock) + * rcu_read_unlock(); // Ends grace period + * rcu_do_batch() + * kfree(p); + * UAF -> rt_mutex_cmpxchg_release(&p->lock.lock...) + */ + rcu_read_unlock(); } EXPORT_SYMBOL(rt_spin_unlock); @@ -262,17 +279,21 @@ void __sched rt_read_unlock(rwlock_t *rwlock) __releases(RCU) { rwlock_release(&rwlock->dep_map, _RET_IP_); migrate_enable(); - rcu_read_unlock(); rwbase_read_unlock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + + /* This must be last. See comment in rt_spin_unlock() */ + rcu_read_unlock(); } EXPORT_SYMBOL(rt_read_unlock); void __sched rt_write_unlock(rwlock_t *rwlock) __releases(RCU) { rwlock_release(&rwlock->dep_map, _RET_IP_); - rcu_read_unlock(); migrate_enable(); rwbase_write_unlock(&rwlock->rwbase); + + /* This must be last. See comment in rt_spin_unlock() */ + rcu_read_unlock(); } EXPORT_SYMBOL(rt_write_unlock); diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 398b994b73aa..1944dbeb0d4c 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -519,18 +519,23 @@ static int __init cpu_latency_qos_init(void) int ret; ret = misc_register(&cpu_latency_qos_miscdev); - if (ret < 0) + if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_latency_qos_miscdev.name); + return ret; + } #ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP ret = misc_register(&cpu_wakeup_latency_qos_miscdev); - if (ret < 0) + if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_wakeup_latency_qos_miscdev.name); + misc_deregister(&cpu_latency_qos_miscdev); + return ret; + } #endif - return ret; + return 0; } late_initcall(cpu_latency_qos_init); #endif /* CONFIG_CPU_IDLE */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 091ee8d2b17a..69c2aa8c6246 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4710,6 +4710,7 @@ int sched_fork(u64 clone_flags, struct task_struct *p) p->policy = SCHED_NORMAL; p->static_prio = NICE_TO_PRIO(0); p->rt_priority = 0; + p->timer_slack_ns = p->default_timer_slack_ns; } else if (PRIO_TO_NICE(p->static_prio) < 0) p->static_prio = NICE_TO_PRIO(0); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index ae9fd211cec1..a4e689eefdfb 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -486,6 +486,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, cpufreq_driver_adjust_perf(sg_policy->policy, sg_cpu->bw_min, sg_cpu->util, max_cap); + sg_policy->need_freq_update = false; sg_policy->last_freq_update_time = time; } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 74c1617cf652..6f74bde68437 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -373,6 +373,9 @@ static ssize_t sched_server_write_common(struct file *filp, const char __user *u return -EINVAL; } + if (!cpu_online(cpu_of(rq))) + return -EBUSY; + update_rq_clock(rq); dl_server_stop(dl_se); retval = dl_server_apply_params(dl_se, runtime, period, 0); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3ebec186f982..abb76775aa72 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4959,13 +4959,86 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s trace_pelt_cfs_tp(cfs_rq); } +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) + +static inline void util_est_update(struct sched_entity *se) +{ + unsigned int ewma, dequeued, last_ewma_diff; + + if (!sched_feat(UTIL_EST)) + return; + + /* Get current estimate of utilization */ + ewma = READ_ONCE(se->avg.util_est); + + /* + * If the PELT values haven't changed since enqueue time, + * skip the util_est update. + */ + if (ewma & UTIL_AVG_UNCHANGED) + return; + + /* Get utilization at dequeue */ + dequeued = READ_ONCE(se->avg.util_avg); + + /* + * Reset EWMA on utilization increases, the moving average is used only + * to smooth utilization decreases. + */ + if (ewma <= dequeued) { + ewma = dequeued; + goto done; + } + + /* + * Skip update of task's estimated utilization when its members are + * already ~1% close to its last activation value. + */ + last_ewma_diff = ewma - dequeued; + if (last_ewma_diff < UTIL_EST_MARGIN) + goto done; + + /* + * To avoid underestimate of task utilization, skip updates of EWMA if + * we cannot grant that thread got all CPU time it wanted. + */ + if ((dequeued + UTIL_EST_MARGIN) < READ_ONCE(se->avg.runnable_avg)) + goto done; + + /* + * Update Task's estimated utilization + * + * When *p completes an activation we can consolidate another sample + * of the task size. This is done by using this value to update the + * Exponential Weighted Moving Average (EWMA): + * + * ewma(t) = w * task_util(p) + (1-w) * ewma(t-1) + * = w * task_util(p) + ewma(t-1) - w * ewma(t-1) + * = w * (task_util(p) - ewma(t-1)) + ewma(t-1) + * = w * ( -last_ewma_diff ) + ewma(t-1) + * = w * (-last_ewma_diff + ewma(t-1) / w) + * + * Where 'w' is the weight of new samples, which is configured to be + * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT) + */ + ewma <<= UTIL_EST_WEIGHT_SHIFT; + ewma -= last_ewma_diff; + ewma >>= UTIL_EST_WEIGHT_SHIFT; +done: + ewma |= UTIL_AVG_UNCHANGED; + WRITE_ONCE(se->avg.util_est, ewma); + + trace_sched_util_est_se_tp(se); +} + /* * Optional action to be done while updating the load average */ -#define UPDATE_TG 0x1 -#define SKIP_AGE_LOAD 0x2 -#define DO_ATTACH 0x4 -#define DO_DETACH 0x8 +#define UPDATE_TG 0x01 +#define SKIP_AGE_LOAD 0x02 +#define DO_ATTACH 0x04 +#define DO_DETACH 0x08 +#define UPDATE_UTIL_EST 0x10 /* Update task and its cfs_rq load average */ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) @@ -5008,6 +5081,9 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s if (flags & UPDATE_TG) update_tg_load_avg(cfs_rq); } + + if (flags & UPDATE_UTIL_EST) + util_est_update(se); } /* @@ -5066,11 +5142,6 @@ static inline unsigned long task_util(struct task_struct *p) return READ_ONCE(p->se.avg.util_avg); } -static inline unsigned long task_runnable(struct task_struct *p) -{ - return READ_ONCE(p->se.avg.runnable_avg); -} - static inline unsigned long _task_util_est(struct task_struct *p) { return READ_ONCE(p->se.avg.util_est) & ~UTIL_AVG_UNCHANGED; @@ -5113,88 +5184,6 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq, trace_sched_util_est_cfs_tp(cfs_rq); } -#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) - -static inline void util_est_update(struct cfs_rq *cfs_rq, - struct task_struct *p, - bool task_sleep) -{ - unsigned int ewma, dequeued, last_ewma_diff; - - if (!sched_feat(UTIL_EST)) - return; - - /* - * Skip update of task's estimated utilization when the task has not - * yet completed an activation, e.g. being migrated. - */ - if (!task_sleep) - return; - - /* Get current estimate of utilization */ - ewma = READ_ONCE(p->se.avg.util_est); - - /* - * If the PELT values haven't changed since enqueue time, - * skip the util_est update. - */ - if (ewma & UTIL_AVG_UNCHANGED) - return; - - /* Get utilization at dequeue */ - dequeued = task_util(p); - - /* - * Reset EWMA on utilization increases, the moving average is used only - * to smooth utilization decreases. - */ - if (ewma <= dequeued) { - ewma = dequeued; - goto done; - } - - /* - * Skip update of task's estimated utilization when its members are - * already ~1% close to its last activation value. - */ - last_ewma_diff = ewma - dequeued; - if (last_ewma_diff < UTIL_EST_MARGIN) - goto done; - - /* - * To avoid underestimate of task utilization, skip updates of EWMA if - * we cannot grant that thread got all CPU time it wanted. - */ - if ((dequeued + UTIL_EST_MARGIN) < task_runnable(p)) - goto done; - - - /* - * Update Task's estimated utilization - * - * When *p completes an activation we can consolidate another sample - * of the task size. This is done by using this value to update the - * Exponential Weighted Moving Average (EWMA): - * - * ewma(t) = w * task_util(p) + (1-w) * ewma(t-1) - * = w * task_util(p) + ewma(t-1) - w * ewma(t-1) - * = w * (task_util(p) - ewma(t-1)) + ewma(t-1) - * = w * ( -last_ewma_diff ) + ewma(t-1) - * = w * (-last_ewma_diff + ewma(t-1) / w) - * - * Where 'w' is the weight of new samples, which is configured to be - * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT) - */ - ewma <<= UTIL_EST_WEIGHT_SHIFT; - ewma -= last_ewma_diff; - ewma >>= UTIL_EST_WEIGHT_SHIFT; -done: - ewma |= UTIL_AVG_UNCHANGED; - WRITE_ONCE(p->se.avg.util_est, ewma); - - trace_sched_util_est_se_tp(&p->se); -} - static inline unsigned long get_actual_cpu_capacity(int cpu) { unsigned long capacity = arch_scale_cpu_capacity(cpu); @@ -5647,7 +5636,7 @@ static bool dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { bool sleep = flags & DEQUEUE_SLEEP; - int action = UPDATE_TG; + int action = 0; update_curr(cfs_rq); clear_buddies(cfs_rq, se); @@ -5667,15 +5656,23 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (sched_feat(DELAY_DEQUEUE) && delay && !entity_eligible(cfs_rq, se)) { - update_load_avg(cfs_rq, se, 0); + if (entity_is_task(se)) + action |= UPDATE_UTIL_EST; + update_load_avg(cfs_rq, se, action); update_entity_lag(cfs_rq, se); set_delayed(se); return false; } } - if (entity_is_task(se) && task_on_rq_migrating(task_of(se))) - action |= DO_DETACH; + action = UPDATE_TG; + if (entity_is_task(se)) { + if (task_on_rq_migrating(task_of(se))) + action |= DO_DETACH; + + if (sleep && !(flags & DEQUEUE_DELAYED)) + action |= UPDATE_UTIL_EST; + } /* * When dequeuing a sched_entity, we must: @@ -7438,7 +7435,6 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!p->se.sched_delayed) util_est_dequeue(&rq->cfs, p); - util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP); if (dequeue_entities(rq, &p->se, flags) < 0) return false; @@ -8260,25 +8256,32 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) static unsigned long cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost) { + bool add_task = p && task_cpu(p) != cpu && dst_cpu == cpu; + bool sub_task = p && task_cpu(p) == cpu && dst_cpu != cpu; struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; unsigned long util = READ_ONCE(cfs_rq->avg.util_avg); unsigned long runnable; - if (boost) { - runnable = READ_ONCE(cfs_rq->avg.runnable_avg); - util = max(util, runnable); - } - /* * If @dst_cpu is -1 or @p migrates from @cpu to @dst_cpu remove its * contribution. If @p migrates from another CPU to @cpu add its * contribution. In all the other cases @cpu is not impacted by the * migration so its util_avg is already correct. */ - if (p && task_cpu(p) == cpu && dst_cpu != cpu) - lsub_positive(&util, task_util(p)); - else if (p && task_cpu(p) != cpu && dst_cpu == cpu) + if (add_task) util += task_util(p); + else if (sub_task) + lsub_positive(&util, task_util(p)); + + if (boost) { + runnable = READ_ONCE(cfs_rq->avg.runnable_avg); + if (add_task) + runnable += READ_ONCE(p->se.avg.runnable_avg); + else if (sub_task) + lsub_positive(&runnable, + READ_ONCE(p->se.avg.runnable_avg)); + util = max(util, runnable); + } if (sched_feat(UTIL_EST)) { unsigned long util_est; diff --git a/kernel/signal.c b/kernel/signal.c index 9c2b32c4d755..bbc0fd4cc4d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1362,8 +1362,16 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, rcu_read_lock(); for (;;) { sighand = rcu_dereference(tsk->sighand); - if (unlikely(sighand == NULL)) + if (unlikely(sighand == NULL)) { + /* + * Pairs with the smp_store_release() in + * __exit_signal(). It ensures that all state + * modifications to the task preceeding the store are + * visible to the callers of lock_task_sighand(). + */ + smp_acquire__after_ctrl_dep(); break; + } /* * This sighand can be already freed and even reused, but diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 73bd6a6a7893..2cd0172d0516 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -210,13 +210,39 @@ static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) return 0; } +static void tgid_stats_add_task(struct taskstats *stats, + struct task_struct *tsk, u64 now_ns) +{ + u64 delta, utime, stime; + + /* + * Each accounting subsystem calls its functions here to + * accumulate its per-task stats for tsk, into the per-tgid structure + * + * per-task-foo(stats, tsk); + */ + delayacct_add_tsk(stats, tsk); + + /* calculate task elapsed time in nsec */ + delta = now_ns - tsk->start_time; + /* Convert to micro seconds */ + do_div(delta, NSEC_PER_USEC); + stats->ac_etime += delta; + + task_cputime(tsk, &utime, &stime); + stats->ac_utime += div_u64(utime, NSEC_PER_USEC); + stats->ac_stime += div_u64(stime, NSEC_PER_USEC); + + stats->nvcsw += tsk->nvcsw; + stats->nivcsw += tsk->nivcsw; +} + static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) { struct task_struct *tsk, *first; unsigned long flags; int rc = -ESRCH; - u64 delta, utime, stime; - u64 start_time; + u64 now_ns; /* * Add additional stats from live tasks except zombie thread group @@ -233,30 +259,12 @@ static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) else memset(stats, 0, sizeof(*stats)); - start_time = ktime_get_ns(); + now_ns = ktime_get_ns(); for_each_thread(first, tsk) { if (tsk->exit_state) continue; - /* - * Accounting subsystem can call its functions here to - * fill in relevant parts of struct taskstsats as follows - * - * per-task-foo(stats, tsk); - */ - delayacct_add_tsk(stats, tsk); - - /* calculate task elapsed time in nsec */ - delta = start_time - tsk->start_time; - /* Convert to micro seconds */ - do_div(delta, NSEC_PER_USEC); - stats->ac_etime += delta; - task_cputime(tsk, &utime, &stime); - stats->ac_utime += div_u64(utime, NSEC_PER_USEC); - stats->ac_stime += div_u64(stime, NSEC_PER_USEC); - - stats->nvcsw += tsk->nvcsw; - stats->nivcsw += tsk->nivcsw; + tgid_stats_add_task(stats, tsk, now_ns); } unlock_task_sighand(first, &flags); @@ -275,18 +283,14 @@ out: static void fill_tgid_exit(struct task_struct *tsk) { unsigned long flags; + u64 now_ns; spin_lock_irqsave(&tsk->sighand->siglock, flags); if (!tsk->signal->stats) goto ret; - /* - * Each accounting subsystem calls its functions here to - * accumalate its per-task stats for tsk, into the per-tgid structure - * - * per-task-foo(tsk->signal->stats, tsk); - */ - delayacct_add_tsk(tsk->signal->stats, tsk); + now_ns = ktime_get_ns(); + tgid_stats_add_task(tsk->signal->stats, tsk, now_ns); ret: spin_unlock_irqrestore(&tsk->sighand->siglock, flags); return; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 6e173d70d825..c9aac73ba97a 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -512,8 +512,6 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) * @now: time at the timer expiration * * Posix timer callback for expired alarm timers. - * - * Return: whether the timer is to be restarted */ static void alarm_handle_timer(struct alarm *alarm, ktime_t now) { @@ -527,12 +525,13 @@ static void alarm_handle_timer(struct alarm *alarm, ktime_t now) * alarm_timer_rearm - Posix timer callback for rearming timer * @timr: Pointer to the posixtimer data struct */ -static void alarm_timer_rearm(struct k_itimer *timr) +static bool alarm_timer_rearm(struct k_itimer *timr) { struct alarm *alarm = &timr->it.alarm.alarmtimer; timr->it_overrun += alarm_forward_now(alarm, timr->it_interval); alarm_start(alarm, alarm->node.expires); + return true; } /** @@ -588,7 +587,7 @@ static void alarm_timer_wait_running(struct k_itimer *timr) * @absolute: Expiry value is absolute time * @sigev_none: Posix timer does not deliver signals */ -static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, +static bool alarm_timer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct alarm *alarm = &timr->it.alarm.alarmtimer; @@ -600,6 +599,7 @@ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, alarm->node.expires = expires; else alarm_start(&timr->it.alarm.alarmtimer, expires); + return true; } /** diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 6f3ddb2b1f46..a7d3e8229c4b 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -19,7 +19,7 @@ #include "posix-timers.h" -static void posix_cpu_timer_rearm(struct k_itimer *timer); +static bool posix_cpu_timer_rearm(struct k_itimer *timer); void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { @@ -41,7 +41,7 @@ void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) */ int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) { - u64 nsecs = rlim_new * NSEC_PER_SEC; + u64 nsecs = (u64)rlim_new * NSEC_PER_SEC; unsigned long irq_fl; if (!lock_task_sighand(task, &irq_fl)) @@ -461,6 +461,109 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) trigger_base_recalc_expires(timer, p); } +/* + * Lookup the task via timer->it.cpu.pid and attempt to lock the task's sighand. + * + * This can race with the reaping of the task: + * + * CPU0 CPU1 + * + * // Finds task + * p = pid_task(pid, pid_type); __exit_signal(p) + * lock(p, sighand); + * posix_cpu_timers*_exit(); + * sighand = lock_task_sighand(p); unhash_task(p); + * p->sighand = NULL; + * unlock(sighand); + * + * In this case sighand is NULL, which means the task and the associated timer + * queue cannot be longer accessed safely. + * + * __exit_signal() invokes posix_cpu_timers_exit() and if the thread group is + * dead it also invokes posix_cpu_timers_group_exit(). These functions delete + * all pending timers from the related timer queues. The POSIX timers (k_itimer) + * themself are still accessible, but not longer connected to the task. + * + * exec() works slightly differently. The task which exec()'s terminates all + * other threads in the thread group and runs __exit_signal() on them. As the + * thread group is not dead they only clean up the per task timers via + * posix_cpu_timers_exit(). + * + * As the TGID on exec() stays the same per process timers stay queued, if they + * are armed. This works without a problem when exec() is done by the thread + * group leader. If a non-leader thread exec()'s this can end up in the + * following scenario: + * + * CPU0 CPU1 + * // Returns old leader + * p = pid_task(pid, pid_type); de_thread() + * switch_leader() + * release_task(old leader) + * __exit_signal() + * old_leader->sighand = NULL; + * // Returns NULL + * sighand = lock_task_sighand(p) + * + * That's problematic for several functions: + * + * - posix_cpu_timer_del(): If the timer is still enqueued on the task the + * underlying k_itimer will be freed which results in a UAF in + * run_posix_cpu_timers() or on timerqueue related add/delete operations. + * If the timer is not enqueued, the failure is harmless + * + * - posix_cpu_timer_set(): Independent of the enqueued state that results in a + * transient failure which is user space visible (-ESRCH) for regular posix + * timers. But for the use case in do_cpu_nanosleep() it's the same UAF + * problem just that the timer is allocated on the stack. + * + * - posix_cpu_timer_rearm(): Timer is not enqueued at that point, but this + * silently ignores the rearm request, which is a functional problem as the + * timer wont expire anymore. + */ +static struct task_struct *timer_lock_sighand(struct k_itimer *timer, unsigned long *flags) +{ + enum pid_type type = clock_pid_type(timer->it_clock); + struct cpu_timer *ctmr = &timer->it.cpu; + + guard(rcu)(); + + for (;;) { + struct task_struct *t = pid_task(timer->it.cpu.pid, type); + + /* Fail if the task cannot be found. */ + if (!t) + break; + + /* Try to lock the task's sighand */ + if (lock_task_sighand(t, flags)) + return t; + + /* + * The next PID lookup might either fail or return the new + * leader. This is correct for both exit() and exec(). + */ + } + + /* + * If the timer is still enqueued, warn. There is nothing safe to do + * here as there might be two timers in there which are removed in + * parallel and that will cause more damage than good. This should never + * happen! + * + * Ensure that the stores to the timer and timerqueue are visible: + * + * __exit_signal() + * posix_cpu_timers*_exit() + * write_seqlock(seqlock) + * smp_wmb(); <------- + * __unhash_process() | !pid_task() + * ----> smp_rmb(); + * WARN_ON_ONCE(...) + */ + smp_rmb(); + WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); + return NULL; +} /* * Clean up a CPU-clock timer that is about to be destroyed. @@ -470,29 +573,13 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) */ static int posix_cpu_timer_del(struct k_itimer *timer) { - struct cpu_timer *ctmr = &timer->it.cpu; - struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; - rcu_read_lock(); - p = cpu_timer_task_rcu(timer); - if (!p) - goto out; + p = timer_lock_sighand(timer, &flags); - /* - * Protect against sighand release/switch in exit/exec and process/ - * thread timer list entry concurrent read/writes. - */ - sighand = lock_task_sighand(p, &flags); - if (unlikely(sighand == NULL)) { - /* - * This raced with the reaping of the task. The exit cleanup - * should have removed this timer from the timer queue. - */ - WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); - } else { + if (likely(p)) { if (timer->it.cpu.firing) { /* * Prevent signal delivery. The timer cannot be dequeued @@ -508,11 +595,8 @@ static int posix_cpu_timer_del(struct k_itimer *timer) unlock_task_sighand(p, &flags); } -out: - rcu_read_unlock(); - if (!ret) { - put_pid(ctmr->pid); + put_pid(timer->it.cpu.pid); timer->it_status = POSIX_TIMER_DISARMED; } return ret; @@ -626,21 +710,17 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct cpu_timer *ctmr = &timer->it.cpu; u64 old_expires, new_expires, now; - struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; - rcu_read_lock(); - p = cpu_timer_task_rcu(timer); - if (!p) { - /* - * If p has just been reaped, we can no - * longer get any information about it at all. - */ - rcu_read_unlock(); + p = timer_lock_sighand(timer, &flags); + /* + * If p has just been reaped, we can no longer get any information about + * it at all. + */ + if (!p) return -ESRCH; - } /* * Use the to_ktime conversion because that clamps the maximum @@ -648,20 +728,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, */ new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value)); - /* - * Protect against sighand release/switch in exit/exec and p->cpu_timers - * and p->signal->cpu_timers read/write in arm_timer() - */ - sighand = lock_task_sighand(p, &flags); - /* - * If p has just been reaped, we can no - * longer get any information about it at all. - */ - if (unlikely(sighand == NULL)) { - rcu_read_unlock(); - return -ESRCH; - } - /* Retrieve the current expiry time before disarming the timer */ old_expires = cpu_timer_getexpires(ctmr); @@ -698,7 +764,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, /* Retry if the timer expiry is running concurrently */ if (unlikely(ret)) { unlock_task_sighand(p, &flags); - goto out; + return ret; } /* Convert relative expiry time to absolute */ @@ -733,8 +799,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, */ if (!sigev_none && new_expires && now >= new_expires) cpu_timer_fire(timer); -out: - rcu_read_unlock(); return ret; } @@ -1011,24 +1075,20 @@ static void check_process_timers(struct task_struct *tsk, /* * This is called from the signal code (via posixtimer_rearm) * when the last timer signal was delivered and we have to reload the timer. + * + * Return true unconditionally so the core code assumes the timer to be + * armed. Otherwise it would requeue the signal. */ -static void posix_cpu_timer_rearm(struct k_itimer *timer) +static bool posix_cpu_timer_rearm(struct k_itimer *timer) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct task_struct *p; - struct sighand_struct *sighand; unsigned long flags; u64 now; - rcu_read_lock(); - p = cpu_timer_task_rcu(timer); - if (!p) - goto out; - - /* Protect timer list r/w in arm_timer() */ - sighand = lock_task_sighand(p, &flags); - if (unlikely(sighand == NULL)) - goto out; + p = timer_lock_sighand(timer, &flags); + if (unlikely(!p)) + return true; /* * Fetch the current sample and update the timer's expiry time. @@ -1045,8 +1105,7 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) */ arm_timer(timer, p); unlock_task_sighand(p, &flags); -out: - rcu_read_unlock(); + return true; } /** diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 9331e1614124..da04ed42bf82 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -288,12 +288,13 @@ static inline int timer_overrun_to_int(struct k_itimer *timr) return (int)timr->it_overrun_last; } -static void common_hrtimer_rearm(struct k_itimer *timr) +static bool common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; timr->it_overrun += hrtimer_forward_now(timer, timr->it_interval); hrtimer_restart(timer); + return true; } static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr) @@ -795,7 +796,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) return timer_overrun_to_int(scoped_timer); } -static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, +static bool common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct hrtimer *timer = &timr->it.real.timer; @@ -822,6 +823,7 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, if (!sigev_none) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + return true; } static int common_hrtimer_try_to_cancel(struct k_itimer *timr) diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 7f259e845d24..4ea9611dd716 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -27,11 +27,11 @@ struct k_clock { int (*timer_del)(struct k_itimer *timr); void (*timer_get)(struct k_itimer *timr, struct itimerspec64 *cur_setting); - void (*timer_rearm)(struct k_itimer *timr); + bool (*timer_rearm)(struct k_itimer *timr); s64 (*timer_forward)(struct k_itimer *timr, ktime_t now); ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now); int (*timer_try_to_cancel)(struct k_itimer *timr); - void (*timer_arm)(struct k_itimer *timr, ktime_t expires, + bool (*timer_arm)(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none); void (*timer_wait_running)(struct k_itimer *timr); }; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index cbbb87a0c6e7..171393367b5c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -797,15 +797,16 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, *last_update_time = ktime_to_us(now); do { + ktime_t delta = 0; + seq = read_seqcount_begin(&ts->idle_sleeptime_seq); if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) { - ktime_t delta = ktime_sub(now, ts->idle_entrytime); - - idle = ktime_add(*sleeptime, delta); - } else { - idle = *sleeptime; + if (now > ts->idle_entrytime) + delta = ktime_sub(now, ts->idle_entrytime); } + + idle = ktime_add(*sleeptime, delta); } while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq)); return ktime_to_us(idle); diff --git a/kernel/time/time.c b/kernel/time/time.c index 771cef87ad3b..0dd63a91e7c5 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -251,7 +251,7 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; - if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) + if (new_ts.tv_nsec >= USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index 70879cde6fdd..4c0073f3d321 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -75,15 +75,17 @@ struct tmigr_group { /** * struct tmigr_cpu - timer migration per CPU group * @lock: Lock protecting the tmigr_cpu group information - * @online: Indicates whether the CPU is online; In deactivate path - * it is required to know whether the migrator in the top - * level group is to be set offline, while a timer is - * pending. Then another online CPU needs to be notified to - * take over the migrator role. Furthermore the information - * is required in CPU hotplug path as the CPU is able to go - * idle before the timer migration hierarchy hotplug AP is - * reached. During this phase, the CPU has to handle the + * @available: Indicates whether the CPU is available for handling + * global timers. In the deactivate path it is required to + * know whether the migrator in the top level group is to + * be set offline, while a timer is pending. Then another + * available CPU needs to be notified to take over the + * migrator role. Furthermore the information is required + * in the CPU hotplug path as the CPU is able to go idle + * before the timer migration hierarchy hotplug callback is + * reached. During this phase, the CPU has to handle the * global timers on its own and must not act as a migrator. + * @idle: Indicates whether the CPU is idle in the timer migration * hierarchy * @remote: Is set when timers of the CPU are expired remotely diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a02bd258677e..91309df69184 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2331,9 +2331,12 @@ static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 int err = -ENOMEM; unsigned int i; + if (!access_ok(usyms, cnt * sizeof(*usyms))) + return -EFAULT; + syms = kvmalloc_array(cnt, sizeof(*syms), GFP_KERNEL); if (!syms) - goto error; + return -ENOMEM; buf = kvmalloc_array(cnt, KSYM_NAME_LEN, GFP_KERNEL); if (!buf) @@ -2358,10 +2361,8 @@ static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 return 0; error: - if (err) { - kvfree(syms); - kvfree(buf); - } + kvfree(syms); + kvfree(buf); return err; } @@ -3180,6 +3181,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr unsigned long __user *uoffsets; u64 __user *ucookies; void __user *upath; + unsigned long size; u32 flags, cnt, i; struct path path; char *name; @@ -3217,6 +3219,16 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets); ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies); + /* + * All uoffsets/uref_ctr_offsets/ucookies arrays have the same value + * size, we need to check their address range is safe for __get_user + * calls. + */ + size = sizeof(*uoffsets) * cnt; + if (!access_ok(uoffsets, size) || !access_ok(uref_ctr_offsets, size) || + !access_ok(ucookies, size)) + return -EFAULT; + name = strndup_user(upath, PATH_MAX); if (IS_ERR(name)) { err = PTR_ERR(name); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index f378613ad120..f215990b9061 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -613,6 +613,16 @@ static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops continue; data_size = fp->entry_data_size; + /* + * The list may have grown since it was sized, so this node + * may not fit. Skip it as missed rather than overrun the + * reservation. + */ + if (fp->exit_handler && + used + FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(data_size) > reserved_words) { + fp->nmissed++; + continue; + } if (data_size && fp->exit_handler) data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG; else diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7b07d2004cc6..da9339466bdd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -266,7 +266,8 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event) if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX) return length; length -= RB_EVNT_HDR_SIZE; - if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0])) + if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]) || + RB_FORCE_8BYTE_ALIGNMENT) length -= sizeof(event->array[0]); return length; } @@ -2219,10 +2220,7 @@ static struct ring_buffer_desc *ring_buffer_desc(struct trace_buffer_desc *trace size_t len; int i; - if (!trace_desc) - return NULL; - - if (cpu >= trace_desc->nr_cpus) + if (!trace_desc || !trace_desc->nr_cpus) return NULL; end = (struct ring_buffer_desc *)((void *)trace_desc + trace_desc->struct_len); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6eb4d3097a4d..4c3729c8d5e2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -87,7 +87,7 @@ void __init disable_tracing_selftest(const char *reason) /* Pipe tracepoints to printk */ static struct trace_iterator *tracepoint_print_iter; -int tracepoint_printk; +static int tracepoint_printk; static bool tracepoint_printk_stop_on_boot __initdata; static bool traceoff_after_boot __initdata; static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key); diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index b66d6196338d..50518b071414 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -315,7 +315,7 @@ get_event_field(struct fetch_insn *code, void *rec) val = (unsigned long)addr; break; case FILTER_PTR_STRING: - val = (unsigned long)(*(char *)addr); + val = *(unsigned long *)addr; break; default: WARN_ON_ONCE(1); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index eb2c2bc8bc3d..9701650c89b2 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/security.h> +#include <linux/seq_buf.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/stacktrace.h> @@ -2967,13 +2968,22 @@ find_synthetic_field_var(struct hist_trigger_data *target_hist_data, { struct hist_field *event_var; char *synthetic_name; + struct seq_buf s; synthetic_name = kzalloc(MAX_FILTER_STR_VAL, GFP_KERNEL); if (!synthetic_name) return ERR_PTR(-ENOMEM); - strcpy(synthetic_name, "synthetic_"); - strcat(synthetic_name, field_name); + seq_buf_init(&s, synthetic_name, MAX_FILTER_STR_VAL); + seq_buf_printf(&s, "synthetic_%s", field_name); + + /* Terminate synthetic_name with a NUL. */ + seq_buf_str(&s); + + if (seq_buf_has_overflowed(&s)) { + kfree(synthetic_name); + return ERR_PTR(-E2BIG); + } event_var = find_event_var(target_hist_data, system, event_name, synthetic_name); @@ -3019,6 +3029,7 @@ create_field_var_hist(struct hist_trigger_data *target_hist_data, struct hist_field *key_field; struct hist_field *event_var; char *saved_filter; + struct seq_buf s; char *cmd; int ret; @@ -3063,28 +3074,34 @@ create_field_var_hist(struct hist_trigger_data *target_hist_data, return ERR_PTR(-ENOMEM); } + seq_buf_init(&s, cmd, MAX_FILTER_STR_VAL); + /* Use the same keys as the compatible histogram */ - strcat(cmd, "keys="); + seq_buf_puts(&s, "keys="); for_each_hist_key_field(i, hist_data) { key_field = hist_data->fields[i]; if (!first) - strcat(cmd, ","); - strcat(cmd, key_field->field->name); + seq_buf_putc(&s, ','); + seq_buf_puts(&s, key_field->field->name); first = false; } /* Create the synthetic field variable specification */ - strcat(cmd, ":synthetic_"); - strcat(cmd, field_name); - strcat(cmd, "="); - strcat(cmd, field_name); + seq_buf_printf(&s, ":synthetic_%s=%s", field_name, field_name); /* Use the same filter as the compatible histogram */ saved_filter = find_trigger_filter(hist_data, file); - if (saved_filter) { - strcat(cmd, " if "); - strcat(cmd, saved_filter); + if (saved_filter) + seq_buf_printf(&s, " if %s", saved_filter); + + /* Terminate cmd with a NUL. */ + seq_buf_str(&s); + + if (seq_buf_has_overflowed(&s)) { + kfree(cmd); + kfree(var_hist); + return ERR_PTR(-E2BIG); } var_hist->cmd = kstrdup(cmd, GFP_KERNEL); diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index c4ba484f7b38..8c82ecb735f4 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -109,6 +109,9 @@ struct user_event_enabler { /* Track enable bit, flags, etc. Aligned for bitops. */ unsigned long values; + + /* Defer the event put and enabler free past an RCU grace period. */ + struct rcu_work put_rwork; }; /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ @@ -396,17 +399,39 @@ error: return NULL; }; -static void user_event_enabler_destroy(struct user_event_enabler *enabler, - bool locked) +static void delayed_user_event_enabler_put(struct work_struct *work) { - list_del_rcu(&enabler->mm_enablers_link); + struct user_event_enabler *enabler = container_of(to_rcu_work(work), + struct user_event_enabler, put_rwork); /* No longer tracking the event via the enabler */ - user_event_put(enabler->event, locked); + user_event_put(enabler->event, false); + /* Run from queue_rcu_work(), the RCU grace period has elapsed */ kfree(enabler); } +static void user_event_enabler_destroy(struct user_event_enabler *enabler) +{ + list_del_rcu(&enabler->mm_enablers_link); + + /* + * The enabler is removed from an RCU-traversed list + * (user_event_mm_dup() walks mm->enablers under rcu_read_lock() only), + * and readers there dereference enabler->event and take a new ref on + * it. Both the put of that event reference and the free of the enabler + * therefore have to wait for a grace period so no reader can be looking + * at the enabler or racing the last put of its event. + * + * The put itself must not run in RCU context: when it drops the last + * reference user_event_put() takes event_mutex, which cannot be taken + * from a softirq/RCU callback. Defer both to a work item scheduled + * after a grace period via queue_rcu_work(). + */ + INIT_RCU_WORK(&enabler->put_rwork, delayed_user_event_enabler_put); + queue_rcu_work(system_percpu_wq, &enabler->put_rwork); +} + static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr, int attempt) { @@ -464,7 +489,7 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) /* User asked for enabler to be removed during fault */ if (test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))) { - user_event_enabler_destroy(enabler, true); + user_event_enabler_destroy(enabler); goto out; } @@ -764,7 +789,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) struct user_event_enabler *enabler, *next; list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) - user_event_enabler_destroy(enabler, false); + user_event_enabler_destroy(enabler); mmdrop(mm->mm); kfree(mm); @@ -2645,7 +2670,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) flags |= enabler->values & ENABLE_VAL_COMPAT_MASK; if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) - user_event_enabler_destroy(enabler, true); + user_event_enabler_destroy(enabler); /* Removed at least one */ ret = 0; diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 75678053b21c..7a244ef81438 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -162,7 +162,9 @@ static void osnoise_unregister_instance(struct trace_array *tr) if (!found) return; - kvfree_rcu_mightsleep(inst); + /* Do a full sync to ensure that tr remains valid, not just inst */ + synchronize_rcu(); + kvfree(inst); } /* diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 44c22d4e7881..733ce83e1e11 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -332,6 +332,19 @@ static int parse_trace_event_arg(char *arg, struct fetch_insn *code, return -ENOENT; } +static int parse_trace_event(char *arg, struct fetch_insn *code, + struct traceprobe_parse_context *ctx) +{ + int ret; + + if (code->data) + return -EFAULT; + ret = parse_trace_event_arg(arg, code, ctx); + if (!ret) + return 0; + return -EINVAL; +} + #ifdef CONFIG_PROBE_EVENTS_BTF_ARGS static u32 btf_type_int(const struct btf_type *t) @@ -376,11 +389,16 @@ static bool btf_type_is_char_array(struct btf *btf, const struct btf_type *type) && BTF_INT_BITS(intdata) == 8; } +static struct btf *ctx_btf(struct traceprobe_parse_context *ctx) +{ + return ctx->struct_btf ? : ctx->btf; +} + static int check_prepare_btf_string_fetch(char *typename, struct fetch_insn **pcode, struct traceprobe_parse_context *ctx) { - struct btf *btf = ctx->btf; + struct btf *btf = ctx_btf(ctx); if (!btf || !ctx->last_type) return 0; @@ -506,6 +524,15 @@ static int query_btf_context(struct traceprobe_parse_context *ctx) return 0; } +static void clear_struct_btf(struct traceprobe_parse_context *ctx) +{ + if (ctx->struct_btf) { + btf_put(ctx->struct_btf); + ctx->struct_btf = NULL; + ctx->last_struct = NULL; + } +} + static void clear_btf_context(struct traceprobe_parse_context *ctx) { if (ctx->btf) { @@ -554,22 +581,29 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, struct fetch_insn *code = *pcode; const struct btf_member *field; u32 bitoffs, anon_offs; + bool is_struct = ctx->struct_btf != NULL; + struct btf *btf = ctx_btf(ctx); char *next; int is_ptr; s32 tid; do { - /* Outer loop for solving arrow operator ('->') */ - if (BTF_INFO_KIND(type->info) != BTF_KIND_PTR) { - trace_probe_log_err(ctx->offset, NO_PTR_STRCT); - return -EINVAL; - } - /* Convert a struct pointer type to a struct type */ - type = btf_type_skip_modifiers(ctx->btf, type->type, &tid); - if (!type) { - trace_probe_log_err(ctx->offset, BAD_BTF_TID); - return -EINVAL; + if (!is_struct) { + /* Outer loop for solving arrow operator ('->') */ + if (BTF_INFO_KIND(type->info) != BTF_KIND_PTR) { + trace_probe_log_err(ctx->offset, NO_PTR_STRCT); + return -EINVAL; + } + + /* Convert a struct pointer type to a struct type */ + type = btf_type_skip_modifiers(btf, type->type, &tid); + if (!type) { + trace_probe_log_err(ctx->offset, BAD_BTF_TID); + return -EINVAL; + } } + /* Only the first type can skip being a pointer */ + is_struct = false; bitoffs = 0; do { @@ -580,7 +614,7 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, return is_ptr; anon_offs = 0; - field = btf_find_struct_member(ctx->btf, type, fieldname, + field = btf_find_struct_member(btf, type, fieldname, &anon_offs); if (IS_ERR(field)) { trace_probe_log_err(ctx->offset, BAD_BTF_TID); @@ -602,7 +636,7 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, ctx->last_bitsize = 0; } - type = btf_type_skip_modifiers(ctx->btf, field->type, &tid); + type = btf_type_skip_modifiers(btf, field->type, &tid); if (!type) { trace_probe_log_err(ctx->offset, BAD_BTF_TID); return -EINVAL; @@ -640,7 +674,7 @@ static int parse_btf_arg(char *varname, int i, is_ptr, ret; u32 tid; - if (WARN_ON_ONCE(!ctx->funcname)) + if (!ctx->funcname && !(ctx->flags & TPARG_FL_TEVENT)) return -EINVAL; is_ptr = split_next_field(varname, &field, ctx); @@ -653,6 +687,19 @@ static int parse_btf_arg(char *varname, return -EOPNOTSUPP; } + if (ctx->flags & TPARG_FL_TEVENT) { + ret = parse_trace_event(varname, code, ctx); + if (ret < 0) { + trace_probe_log_err(ctx->offset, BAD_ATTACH_ARG); + return ret; + } + /* TEVENT is only here via a typecast */ + if (WARN_ON_ONCE(ctx->struct_btf == NULL)) + return -EINVAL; + type = ctx->last_struct; + goto found_type; + } + if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) { code->op = FETCH_OP_RETVAL; /* Check whether the function return type is not void */ @@ -709,6 +756,7 @@ static int parse_btf_arg(char *varname, found: type = btf_type_skip_modifiers(ctx->btf, tid, &tid); +found_type: if (!type) { trace_probe_log_err(ctx->offset, BAD_BTF_TID); return -EINVAL; @@ -727,7 +775,7 @@ found: static const struct fetch_type *find_fetch_type_from_btf_type( struct traceprobe_parse_context *ctx) { - struct btf *btf = ctx->btf; + struct btf *btf = ctx_btf(ctx); const char *typestr = NULL; if (btf && ctx->last_type) @@ -758,7 +806,67 @@ static int parse_btf_bitfield(struct fetch_insn **pcode, return 0; } -#else +static int query_btf_struct(const char *sname, struct traceprobe_parse_context *ctx) +{ + struct btf *btf = NULL; + int id; + + /* A struct_btf should only be used by a single argument */ + if (WARN_ON_ONCE(ctx->struct_btf)) { + btf_put(ctx->struct_btf); + ctx->struct_btf = NULL; + } + + id = bpf_find_btf_id(sname, BTF_KIND_STRUCT, &btf); + if (id < 0) + return id; + ctx->struct_btf = btf; + ctx->last_struct = btf_type_by_id(ctx->struct_btf, id); + return 0; +} + +static int handle_typecast(char *arg, struct fetch_insn **pcode, + struct fetch_insn *end, + struct traceprobe_parse_context *ctx) +{ + char *tmp; + int ret; + + /* Currently this only works for eprobes */ + if (!(ctx->flags & TPARG_FL_TEVENT)) { + trace_probe_log_err(ctx->offset, TYPECAST_NOT_EVENT); + return -EINVAL; + } + + tmp = strchr(arg, ')'); + if (!tmp) { + trace_probe_log_err(ctx->offset + strlen(arg), + DEREF_OPEN_BRACE); + return -EINVAL; + } + *tmp = '\0'; + ret = query_btf_struct(arg + 1, ctx); + *tmp = ')'; + + if (ret < 0) { + trace_probe_log_err(ctx->offset + 1, NO_PTR_STRCT); + return -EINVAL; + } + + tmp++; + + ctx->offset += tmp - arg; + ret = parse_btf_arg(tmp, pcode, end, ctx); + return ret; +} + +#else /* !CONFIG_PROBE_EVENTS_BTF_ARGS */ + +static void clear_struct_btf(struct traceprobe_parse_context *ctx) +{ + ctx->struct_btf = NULL; +} + static void clear_btf_context(struct traceprobe_parse_context *ctx) { ctx->btf = NULL; @@ -794,7 +902,15 @@ static int check_prepare_btf_string_fetch(char *typename, return 0; } -#endif +static int handle_typecast(char *arg, struct fetch_insn **pcode, + struct fetch_insn *end, + struct traceprobe_parse_context *ctx) +{ + trace_probe_log_err(ctx->offset, NOSUP_BTFARG); + return -EOPNOTSUPP; +} + +#endif /* CONFIG_PROBE_EVENTS_BTF_ARGS */ #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API @@ -953,16 +1069,15 @@ static int parse_probe_vars(char *orig_arg, const struct fetch_type *t, int len; if (ctx->flags & TPARG_FL_TEVENT) { - if (code->data) - return -EFAULT; - ret = parse_trace_event_arg(arg, code, ctx); - if (!ret) - return 0; - if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) { - code->op = FETCH_OP_COMM; - return 0; + if (parse_trace_event(arg, code, ctx) < 0) { + /* 'comm' should be checked after field parsing. */ + if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) { + code->op = FETCH_OP_COMM; + return 0; + } + goto inval; } - goto inval; + return 0; } if (str_has_prefix(arg, "retval")) { @@ -1133,6 +1248,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type, code->op = FETCH_OP_FOFFS; code->immediate = (unsigned long)offset; // imm64? + offset = 0; } else { /* uprobes don't support symbols */ if (!(ctx->flags & TPARG_FL_KERNEL)) { @@ -1229,6 +1345,9 @@ parse_probe_arg(char *arg, const struct fetch_type *type, code->op = FETCH_OP_IMM; } break; + case '(': + ret = handle_typecast(arg, pcode, end, ctx); + break; default: if (isalpha(arg[0]) || arg[0] == '_') { /* BTF variable */ if (!tparg_is_function_entry(ctx->flags) && @@ -1561,6 +1680,9 @@ fail: } kfree(tmp); + /* struct_btf should not be passed to other arguments */ + clear_struct_btf(ctx); + return ret; } diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 262d8707a3df..de489f98b8a7 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -422,7 +422,9 @@ struct traceprobe_parse_context { const struct btf_param *params; /* Parameter of the function */ s32 nr_params; /* The number of the parameters */ struct btf *btf; /* The BTF to be used */ + struct btf *struct_btf; /* The BTF to be used for structs */ const struct btf_type *last_type; /* Saved type */ + const struct btf_type *last_struct; /* Saved structure */ u32 last_bitoffs; /* Saved bitoffs */ u32 last_bitsize; /* Saved bitsize */ struct trace_probe *tp; @@ -509,7 +511,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(NO_RETVAL, "This function returns 'void' type"), \ C(BAD_STACK_NUM, "Invalid stack number"), \ C(BAD_ARG_NUM, "Invalid argument number"), \ - C(BAD_VAR, "Invalid $-valiable specified"), \ + C(BAD_VAR, "Invalid $-variable specified"), \ C(BAD_REG_NAME, "Invalid register name"), \ C(BAD_MEM_ADDR, "Invalid memory address"), \ C(BAD_IMM, "Invalid immediate value"), \ @@ -563,7 +565,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"),\ C(TOO_MANY_ARGS, "Too many arguments are specified"), \ C(TOO_MANY_EARGS, "Too many entry arguments specified"), \ - C(EVENT_TOO_BIG, "Event too big (too many fields?)"), + C(EVENT_TOO_BIG, "Event too big (too many fields?)"), \ + C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), #undef C #define C(a, b) TP_ERR_##a diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index d6c3f94d67cd..6dde6bdcbde7 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -979,33 +979,30 @@ EXPORT_SYMBOL_GPL(trace_remote_free_buffer); int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, size_t buffer_size, const struct cpumask *cpumask) { + size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask)); unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1; - void *desc_end = desc + desc_size; struct ring_buffer_desc *rb_desc; int cpu, ret = -ENOMEM; - if (desc_size < struct_size(desc, __data, 0)) + if (desc_size < min_desc_size) return -EINVAL; desc->nr_cpus = 0; - desc->struct_len = struct_size(desc, __data, 0); + desc->struct_len = min_desc_size; - rb_desc = (struct ring_buffer_desc *)&desc->__data[0]; + rb_desc = __first_ring_buffer_desc(desc); for_each_cpu(cpu, cpumask) { unsigned int id; - if ((void *)rb_desc + struct_size(rb_desc, page_va, nr_pages) > desc_end) { - ret = -EINVAL; - goto err; - } - rb_desc->cpu = cpu; rb_desc->nr_page_va = 0; rb_desc->meta_va = (unsigned long)__get_free_page(GFP_KERNEL); if (!rb_desc->meta_va) goto err; + desc->nr_cpus++; + for (id = 0; id < nr_pages; id++) { rb_desc->page_va[id] = (unsigned long)__get_free_page(GFP_KERNEL); if (!rb_desc->page_va[id]) @@ -1013,9 +1010,6 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, rb_desc->nr_page_va++; } - desc->nr_cpus++; - desc->struct_len += offsetof(struct ring_buffer_desc, page_va); - desc->struct_len += struct_size(rb_desc, page_va, rb_desc->nr_page_va); rb_desc = __next_ring_buffer_desc(rb_desc); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33b721a9af02..bd79b3b5ca87 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6310,7 +6310,7 @@ EXPORT_SYMBOL_GPL(set_worker_desc); */ void print_worker_info(const char *log_lvl, struct task_struct *task) { - work_func_t *fn = NULL; + work_func_t fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; |