Teach kfree_rcu_sheaf() how to handle the !allow_spin case. Try to get an empty sheaf from pcs->spare or the barn even when spinning is not allowed. Unlike __pcs_replace_full_main(), try harder to allocate an empty sheaf because the fallback path will be more expensive than kfree_nolock(). Now that slab has internal alloc_flags to describe context, introduce free_flags analogously and convert free_flags to alloc_flags when allocating memory in the free path. When trylock fails or the kernel observes non-NULL pcs->rcu_free after lock acquisition, free the sheaf instead of putting it to the barn. This is rare and not worth complicating the code. Since call_rcu() cannot be called in an unknown context, kfree_rcu_sheaf() fails when the rcu sheaf becomes full. Link: https://lore.kernel.org/linux-mm/872bd673-3d45-4111-8a41-31185db3ece5@kernel.org Reviewed-by: Vlastimil Babka (SUSE) Signed-off-by: Harry Yoo (Oracle) --- mm/slab.h | 18 +++++++++++++++++- mm/slab_common.c | 2 +- mm/slub.c | 34 ++++++++++++++++++++++++++-------- 3 files changed, 44 insertions(+), 10 deletions(-) diff --git a/mm/slab.h b/mm/slab.h index aec0047ed943..7e7f986b49e9 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -24,11 +24,27 @@ #define SLAB_ALLOC_NO_RECURSE 0x04 /* prevent kmalloc() recursion */ #define SLAB_ALLOC_NO_OBJ_EXT 0x08 /* prevent obj_exts array allocation */ +#define SLAB_FREE_DEFAULT 0x00 /* no flags */ +#define SLAB_FREE_NOLOCK 0x01 /* spinning not allowed */ + +static inline unsigned int to_alloc_flags(unsigned int free_flags) +{ + if (free_flags & SLAB_FREE_NOLOCK) + return SLAB_ALLOC_NOLOCK; + else + return SLAB_ALLOC_DEFAULT; +} + static inline bool alloc_flags_allow_spinning(const unsigned int alloc_flags) { return !(alloc_flags & SLAB_ALLOC_NOLOCK); } +static inline bool free_flags_allow_spinning(const unsigned int free_flags) +{ + return !(free_flags & SLAB_FREE_NOLOCK); +} + void *__kmalloc_flags_noprof(DECL_TOKEN_PARAMS(size, token), gfp_t flags, unsigned int alloc_flags, int node) __assume_kmalloc_alignment __alloc_size(1); @@ -431,7 +447,7 @@ static inline bool is_kmalloc_normal(struct kmem_cache *s) return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT|SLAB_NO_OBJ_EXT)); } -bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj); +bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj, unsigned int free_flags); void flush_all_rcu_sheaves(void); void flush_rcu_sheaves_on_cache(struct kmem_cache *s); diff --git a/mm/slab_common.c b/mm/slab_common.c index 1e1d3feec353..42db62f3e801 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1638,7 +1638,7 @@ static bool kfree_rcu_sheaf(void *obj) s = slab->slab_cache; if (likely(!IS_ENABLED(CONFIG_NUMA) || slab_nid(slab) == numa_mem_id())) - return __kfree_rcu_sheaf(s, obj); + return __kfree_rcu_sheaf(s, obj, SLAB_FREE_DEFAULT); return false; } diff --git a/mm/slub.c b/mm/slub.c index d14226ad0982..2c5ba8c326e7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2833,7 +2833,8 @@ static inline struct slab_sheaf *alloc_empty_sheaf(struct kmem_cache *s, return __alloc_empty_sheaf(s, gfp, alloc_flags, s->sheaf_capacity); } -static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf) +static void __free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf, + unsigned int free_flags) { /* * If the sheaf was created with SLAB_ALLOC_NO_RECURSE flag then its @@ -2845,11 +2846,20 @@ static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf) mark_obj_codetag_empty(sheaf); VM_WARN_ON_ONCE(sheaf->size > 0); - kfree(sheaf); + + if (unlikely(free_flags & SLAB_FREE_NOLOCK)) + kfree_nolock(sheaf); + else + kfree(sheaf); stat(s, SHEAF_FREE); } +static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf) +{ + __free_empty_sheaf(s, sheaf, SLAB_FREE_DEFAULT); +} + static unsigned int refill_objects(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int min, unsigned int max); @@ -6067,10 +6077,11 @@ static void rcu_free_sheaf(struct rcu_head *head) */ static DEFINE_WAIT_OVERRIDE_MAP(kfree_rcu_sheaf_map, LD_WAIT_CONFIG); -bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) +bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj, unsigned int free_flags) { struct slub_percpu_sheaves *pcs; struct slab_sheaf *rcu_sheaf; + bool allow_spin = free_flags_allow_spinning(free_flags); if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) return false; @@ -6083,9 +6094,10 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) pcs = this_cpu_ptr(s->cpu_sheaves); if (unlikely(!pcs->rcu_free)) { - struct slab_sheaf *empty; struct node_barn *barn; + unsigned int alloc_flags = to_alloc_flags(free_flags); + gfp_t gfp = allow_spin ? GFP_NOWAIT : __GFP_NOWARN; /* Bootstrap or debug cache, fall back */ if (unlikely(!cache_has_sheaves(s))) { @@ -6105,7 +6117,7 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) goto fail; } - empty = barn_get_empty_sheaf(barn, true); + empty = barn_get_empty_sheaf(barn, allow_spin); if (empty) { pcs->rcu_free = empty; @@ -6114,20 +6126,20 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) local_unlock(&s->cpu_sheaves->lock); - empty = alloc_empty_sheaf(s, GFP_NOWAIT, SLAB_ALLOC_DEFAULT); + empty = alloc_empty_sheaf(s, gfp, alloc_flags); if (!empty) goto fail; if (!local_trylock(&s->cpu_sheaves->lock)) { - barn_put_empty_sheaf(barn, empty); + __free_empty_sheaf(s, empty, free_flags); goto fail; } pcs = this_cpu_ptr(s->cpu_sheaves); if (unlikely(pcs->rcu_free)) - barn_put_empty_sheaf(barn, empty); + __free_empty_sheaf(s, empty, free_flags); else pcs->rcu_free = empty; } @@ -6145,6 +6157,12 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) if (likely(rcu_sheaf->size < s->sheaf_capacity)) { rcu_sheaf = NULL; } else { + if (unlikely(!allow_spin)) { + /* call_rcu() cannot be called in an unknown context */ + rcu_sheaf->size--; + local_unlock(&s->cpu_sheaves->lock); + goto fail; + } pcs->rcu_free = NULL; rcu_sheaf->node = numa_node_id(); } -- 2.53.0