Rongwei Wang reports [1] that cache validation triggered by writing to /sys/kernel/slab/<cache>/validate is racy against normal cache operations (e.g. freeing) in a way that can cause false positive inconsistency reports for caches with debugging enabled. The problem is that debugging actions that mark object free or active and actual freelist operations are not atomic, and the validation can see an inconsistent state. For caches that do or don't have debugging enabled, additional races involving n->nr_slabs are possible that result in false reports of wrong slab counts. This patch attempts to solve these issues while not adding overhead to normal (especially fastpath) operations for caches that do not have debugging enabled. Such overhead would not be justified to make possible userspace-triggered validation safe. Instead, disable the validation for caches that don't have debugging enabled and make their sysfs validate handler return -EINVAL. For caches that do have debugging enabled, we can instead extend the existing approach of not using percpu freelists to force all alloc/free perations to the slow paths where debugging flags is checked and acted upon. There can adjust the debug-specific paths to increase lock coverage against concurrent validation as necessary. The processing on free in free_debug_processing() already happens under n->list_lock and slab_lock() so we can extend it to actually do the freeing as well and thus make it atomic against concurrent validation. The processing on alloc in alloc_debug_processing() currently doesn't take any locks, but we have to first allocate the object from a slab on the partial list (as debugging caches have no percpu slabs) and thus take the n->list_lock anyway. Add a function alloc_single_from_partial() that additionally takes slab_lock() for the debug processing and then grabs just the allocated object instead of the whole freelist. This again makes it atomic against validation and it is also ultimately more efficient than the current grabbing of freelist immediately followed by slab deactivation. To prevent races on n->nr_slabs updates, make sure that for caches with debugging enabled, inc_slabs_node() or dec_slabs_node() is called under n->list_lock. When allocating a new slab for a debug cache, handle the allocation by a new function alloc_single_from_new_slab() instead of the current forced deactivation path. Neither of these changes affect the fast paths at all. The changes in slow paths are negligible for non-debug caches. The function free_debug_processing() is moved so that it is placed later than the definitions of add_partial(), remove_partial() and discard_slab(), to avoid a need for forward declarations. [1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@xxxxxxxxxxxxxxxxx/ Reported-by: Rongwei Wang <rongwei.wang@xxxxxxxxxxxxxxxxx> Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx> --- Changes from RFC: - addressed feedback from Hyeonggon Yoo - rebased on current mainline The plan is to add to slab tree/linux-next after rc1. Please test and review. mm/slub.c | 334 ++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 238 insertions(+), 96 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 862dbd9af4f5..6de667bcfe91 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1324,17 +1324,14 @@ static inline int alloc_consistency_checks(struct kmem_cache *s, } static noinline int alloc_debug_processing(struct kmem_cache *s, - struct slab *slab, - void *object, unsigned long addr) + struct slab *slab, void *object) { if (s->flags & SLAB_CONSISTENCY_CHECKS) { if (!alloc_consistency_checks(s, slab, object)) goto bad; } - /* Success perform special debug activities for allocs */ - if (s->flags & SLAB_STORE_USER) - set_track(s, object, TRACK_ALLOC, addr); + /* Success. Perform special debug activities for allocs */ trace(s, slab, object, 1); init_object(s, object, SLUB_RED_ACTIVE); return 1; @@ -1385,63 +1382,6 @@ static inline int free_consistency_checks(struct kmem_cache *s, return 1; } -/* Supports checking bulk free of a constructed freelist */ -static noinline int free_debug_processing( - struct kmem_cache *s, struct slab *slab, - void *head, void *tail, int bulk_cnt, - unsigned long addr) -{ - struct kmem_cache_node *n = get_node(s, slab_nid(slab)); - void *object = head; - int cnt = 0; - unsigned long flags, flags2; - int ret = 0; - depot_stack_handle_t handle = 0; - - if (s->flags & SLAB_STORE_USER) - handle = set_track_prepare(); - - spin_lock_irqsave(&n->list_lock, flags); - slab_lock(slab, &flags2); - - if (s->flags & SLAB_CONSISTENCY_CHECKS) { - if (!check_slab(s, slab)) - goto out; - } - -next_object: - cnt++; - - if (s->flags & SLAB_CONSISTENCY_CHECKS) { - if (!free_consistency_checks(s, slab, object, addr)) - goto out; - } - - if (s->flags & SLAB_STORE_USER) - set_track_update(s, object, TRACK_FREE, addr, handle); - trace(s, slab, object, 0); - /* Freepointer not overwritten by init_object(), SLAB_POISON moved it */ - init_object(s, object, SLUB_RED_INACTIVE); - - /* Reached end of constructed freelist yet? */ - if (object != tail) { - object = get_freepointer(s, object); - goto next_object; - } - ret = 1; - -out: - if (cnt != bulk_cnt) - slab_err(s, slab, "Bulk freelist count(%d) invalid(%d)\n", - bulk_cnt, cnt); - - slab_unlock(slab, &flags2); - spin_unlock_irqrestore(&n->list_lock, flags); - if (!ret) - slab_fix(s, "Object at 0x%p not freed", object); - return ret; -} - /* * Parse a block of slub_debug options. Blocks are delimited by ';' * @@ -1661,9 +1601,9 @@ static inline void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {} static inline int alloc_debug_processing(struct kmem_cache *s, - struct slab *slab, void *object, unsigned long addr) { return 0; } + struct slab *slab, void *object) { return 0; } -static inline int free_debug_processing( +static inline void free_debug_processing( struct kmem_cache *s, struct slab *slab, void *head, void *tail, int bulk_cnt, unsigned long addr) { return 0; } @@ -1671,6 +1611,8 @@ static inline int free_debug_processing( static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } +static inline void set_track(struct kmem_cache *s, void *object, + enum track_item alloc, unsigned long addr) {} static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -1976,11 +1918,13 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) */ slab = alloc_slab_page(alloc_gfp, node, oo); if (unlikely(!slab)) - goto out; + return NULL; stat(s, ORDER_FALLBACK); } slab->objects = oo_objects(oo); + slab->inuse = 0; + slab->frozen = 0; account_slab(slab, oo_order(oo), s, flags); @@ -2007,15 +1951,6 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) set_freepointer(s, p, NULL); } - slab->inuse = slab->objects; - slab->frozen = 1; - -out: - if (!slab) - return NULL; - - inc_slabs_node(s, slab_nid(slab), slab->objects); - return slab; } @@ -2102,6 +2037,86 @@ static inline void remove_partial(struct kmem_cache_node *n, n->nr_partial--; } +/* + * Called only for kmem_cache_debug() caches instead of acquire_slab(), with a + * slab from the n->partial list. Removes only a single object from the slab + * under slab_lock(), does the alloc_debug_processing() checks and leaves the + * slab on the list, or moves it to full list if it was the last object. + */ +static void *alloc_single_from_partial(struct kmem_cache *s, + struct kmem_cache_node *n, struct slab *slab) +{ + void *object; + unsigned long flags; + + lockdep_assert_held(&n->list_lock); + + slab_lock(slab, &flags); + + object = slab->freelist; + slab->freelist = get_freepointer(s, object); + slab->inuse++; + + if (!alloc_debug_processing(s, slab, object)) { + slab_unlock(slab, &flags); + remove_partial(n, slab); + return NULL; + } + + slab_unlock(slab, &flags); + + if (slab->inuse == slab->objects) { + remove_partial(n, slab); + add_full(s, n, slab); + } + + return object; +} + +/* + * Called only for kmem_cache_debug() caches to allocate from a freshly + * allocated slab. Allocates a single object instead of whole freelist + * and puts the slab to the partial (or full) list. + */ +static void *alloc_single_from_new_slab(struct kmem_cache *s, + struct slab *slab) +{ + int nid = slab_nid(slab); + struct kmem_cache_node *n = get_node(s, nid); + unsigned long flags, flags2; + void *object; + + spin_lock_irqsave(&n->list_lock, flags); + slab_lock(slab, &flags2); + + object = slab->freelist; + slab->freelist = get_freepointer(s, object); + slab->inuse = 1; + + if (!alloc_debug_processing(s, slab, object)) { + /* + * It's not really expected that this would fail on a + * freshly allocated slab, but a concurrent memory + * corruption in theory could cause that. + */ + slab_unlock(slab, &flags2); + spin_unlock_irqrestore(&n->list_lock, flags); + return NULL; + } + + slab_unlock(slab, &flags2); + + if (slab->inuse == slab->objects) + add_full(s, n, slab); + else + add_partial(n, slab, DEACTIVATE_TO_HEAD); + + inc_slabs_node(s, nid, slab->objects); + spin_unlock_irqrestore(&n->list_lock, flags); + + return object; +} + /* * Remove slab from the partial list, freeze it and * return the pointer to the freelist. @@ -2182,6 +2197,13 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!pfmemalloc_match(slab, gfpflags)) continue; + if (kmem_cache_debug(s)) { + object = alloc_single_from_partial(s, n, slab); + if (object) + break; + continue; + } + t = acquire_slab(s, n, slab, object == NULL); if (!t) break; @@ -2788,6 +2810,114 @@ static inline unsigned long node_nr_objs(struct kmem_cache_node *n) { return atomic_long_read(&n->total_objects); } + +/* Supports checking bulk free of a constructed freelist */ +static noinline void free_debug_processing( + struct kmem_cache *s, struct slab *slab, + void *head, void *tail, int bulk_cnt, + unsigned long addr) +{ + struct kmem_cache_node *n = get_node(s, slab_nid(slab)); + struct slab *slab_free = NULL; + void *object = head; + int cnt = 0; + unsigned long flags, flags2; + bool checks_ok = false; + depot_stack_handle_t handle = 0; + + if (s->flags & SLAB_STORE_USER) + handle = set_track_prepare(); + + spin_lock_irqsave(&n->list_lock, flags); + slab_lock(slab, &flags2); + + if (s->flags & SLAB_CONSISTENCY_CHECKS) { + if (!check_slab(s, slab)) + goto out; + } + + if (slab->inuse < bulk_cnt) { + slab_err(s, slab, "Slab has %d allocated objects but %d are to be freed\n", + slab->inuse, bulk_cnt); + goto out; + } + +next_object: + + if (++cnt > bulk_cnt) + goto out_cnt; + + if (s->flags & SLAB_CONSISTENCY_CHECKS) { + if (!free_consistency_checks(s, slab, object, addr)) + goto out; + } + + if (s->flags & SLAB_STORE_USER) + set_track_update(s, object, TRACK_FREE, addr, handle); + trace(s, slab, object, 0); + /* Freepointer not overwritten by init_object(), SLAB_POISON moved it */ + init_object(s, object, SLUB_RED_INACTIVE); + + /* Reached end of constructed freelist yet? */ + if (object != tail) { + object = get_freepointer(s, object); + goto next_object; + } + checks_ok = true; + +out_cnt: + if (cnt != bulk_cnt) + slab_err(s, slab, "Bulk free expected %d objects but found %d\n", + bulk_cnt, cnt); + +out: + if (checks_ok) { + void *prior = slab->freelist; + + /* Perform the actual freeing while we still hold the locks */ + slab->inuse -= cnt; + set_freepointer(s, tail, prior); + slab->freelist = head; + + slab_unlock(slab, &flags2); + + /* Do we need to remove the slab from full or partial list? */ + if (!prior) { + remove_full(s, n, slab); + } else if (slab->inuse == 0) { + remove_partial(n, slab); + stat(s, FREE_REMOVE_PARTIAL); + } + + /* Do we need to discard the slab or add to partial list? */ + if (slab->inuse == 0) { + slab_free = slab; + } else if (!prior) { + add_partial(n, slab, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } + } else { + slab_unlock(slab, &flags2); + } + + if (slab_free) { + /* + * Update the counters while still holding n->list_lock to + * prevent spurious validation warnings + */ + dec_slabs_node(s, slab_nid(slab_free), slab_free->objects); + } + + spin_unlock_irqrestore(&n->list_lock, flags); + + if (!checks_ok) + slab_fix(s, "Object at 0x%p not freed", object); + + if (slab_free) { + stat(s, FREE_SLAB); + free_slab(s, slab_free); + } +} #endif /* CONFIG_SLUB_DEBUG */ #if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS) @@ -3036,36 +3166,52 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, return NULL; } + stat(s, ALLOC_SLAB); + + if (kmem_cache_debug(s)) { + freelist = alloc_single_from_new_slab(s, slab); + + if (unlikely(!freelist)) + goto new_objects; + + if (s->flags & SLAB_STORE_USER) + set_track(s, freelist, TRACK_ALLOC, addr); + + return freelist; + } + /* * No other reference to the slab yet so we can * muck around with it freely without cmpxchg */ freelist = slab->freelist; slab->freelist = NULL; + slab->inuse = slab->objects; + slab->frozen = 1; - stat(s, ALLOC_SLAB); + inc_slabs_node(s, slab_nid(slab), slab->objects); check_new_slab: if (kmem_cache_debug(s)) { - if (!alloc_debug_processing(s, slab, freelist, addr)) { - /* Slab failed checks. Next slab needed */ - goto new_slab; - } else { - /* - * For debug case, we don't load freelist so that all - * allocations go through alloc_debug_processing() - */ - goto return_single; - } + /* + * For debug caches here we had to go through + * alloc_single_from_partial() so just store the tracking info + * and return the object + */ + if (s->flags & SLAB_STORE_USER) + set_track(s, freelist, TRACK_ALLOC, addr); + return freelist; } - if (unlikely(!pfmemalloc_match(slab, gfpflags))) + if (unlikely(!pfmemalloc_match(slab, gfpflags))) { /* * For !pfmemalloc_match() case we don't load freelist so that * we don't make further mismatched allocations easier. */ - goto return_single; + deactivate_slab(s, slab, get_freepointer(s, freelist)); + return freelist; + } retry_load_slab: @@ -3089,11 +3235,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, c->slab = slab; goto load_freelist; - -return_single: - - deactivate_slab(s, slab, get_freepointer(s, freelist)); - return freelist; } /* @@ -3341,9 +3482,10 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, if (kfence_free(head)) return; - if (kmem_cache_debug(s) && - !free_debug_processing(s, slab, head, tail, cnt, addr)) + if (kmem_cache_debug(s)) { + free_debug_processing(s, slab, head, tail, cnt, addr); return; + } do { if (unlikely(n)) { @@ -3936,6 +4078,7 @@ static void early_kmem_cache_node_alloc(int node) slab = new_slab(kmem_cache_node, GFP_NOWAIT, node); BUG_ON(!slab); + inc_slabs_node(kmem_cache_node, slab_nid(slab), slab->objects); if (slab_nid(slab) != node) { pr_err("SLUB: Unable to allocate memory from node %d\n", node); pr_err("SLUB: Allocating a useless per node structure in order to be able to continue\n"); @@ -3950,7 +4093,6 @@ static void early_kmem_cache_node_alloc(int node) n = kasan_slab_alloc(kmem_cache_node, n, GFP_KERNEL, false); slab->freelist = get_freepointer(kmem_cache_node, n); slab->inuse = 1; - slab->frozen = 0; kmem_cache_node->node[node] = n; init_kmem_cache_node(n); inc_slabs_node(kmem_cache_node, node, slab->objects); @@ -5601,7 +5743,7 @@ static ssize_t validate_store(struct kmem_cache *s, { int ret = -EINVAL; - if (buf[0] == '1') { + if (buf[0] == '1' && kmem_cache_debug(s)) { ret = validate_slab_cache(s); if (ret >= 0) ret = length; -- 2.37.1
