From: Vlastimil Babka Date: Wed, 15 Nov 2023 10:38:15 +0000 (+0100) Subject: mm/slub: add opt-in slub_percpu_array X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=7006ea219e83a7c76054db8cf2fe6fd5afde0d68;p=users%2Fjedix%2Flinux-maple.git mm/slub: add opt-in slub_percpu_array kmem_cache_setup_percpu_array() will allocate a per-cpu array for caching alloc/free objects of given size for the cache. The cache has to be created with SLAB_NO_MERGE flag. When empty, half of the array is filled by an internal bulk alloc operation. When full, half of the array is flushed by an internal bulk free operation. The bulk operations exposed to slab users also try to utilize the array when possible, but leave the array empty or full and use the bulk alloc/free only for the operation itself. If kmemcg is enabled and active, bulk freeing skips the array as it would be less efficient. The locking is copied from the page allocator's pcplists, based on embedded spin locks. Interrupts are not disabled, only preemption (cpu migration on RT). Trylock is attempted to avoid deadlock due to an intnerrupt, trylock failure means the array is bypassed. Sysfs stat counters alloc_cpu_cache and free_cpu_cache count operations that used the percpu array. kmem_cache_prefill_percpu_array() can be called to ensure the array on the current cpu to at least the given number of objects. However this is only opportunistic as there's no cpu pinning between the prefill and usage, and trylocks may fail when the usage is in an irq handler. Therefore allocations cannot rely on the array for success even after the prefill. But misses should be rare enough that e.g. GFP_ATOMIC allocations should be acceptable after the refill. Mark SLAB_DEPRECATED as BROKEN so the new prefill call doesn't need to be reimplemented there and the bots don't complain. SLAB has percpu arrays by design but their sizes are determined internally and lack prefill. More TODO/FIXMEs: - NUMA awareness - preferred node currently ignored, __GFP_THISNODE not honored - slub_debug - will not work for allocations from the array. Normally in SLUB implementation the enabling slub_debug for a cache effectively disables all the fast paths and makes every operation work with the shared list, but that could lead to depleting the reserves if we ignore the prefill and use GFP_ATOMIC. Needs more thought. --- diff --git a/include/linux/slab.h b/include/linux/slab.h index d6d6ffeeb9a2..fe0c0981be59 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -197,6 +197,8 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); +int kmem_cache_setup_percpu_array(struct kmem_cache *s, unsigned int count); + /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. @@ -512,6 +514,8 @@ void kmem_cache_free(struct kmem_cache *s, void *objp); void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); +int kmem_cache_prefill_percpu_array(struct kmem_cache *s, unsigned int count, gfp_t gfp); + static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index deb90cf4bffb..2083aa849766 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -13,8 +13,10 @@ #include enum stat_item { + ALLOC_PCA, /* Allocation from percpu array cache */ ALLOC_FASTPATH, /* Allocation from cpu slab */ ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */ + FREE_PCA, /* Free to percpu array cache */ FREE_FASTPATH, /* Free to cpu slab */ FREE_SLOWPATH, /* Freeing not to cpu slab */ FREE_FROZEN, /* Freeing to frozen slab */ @@ -39,6 +41,8 @@ enum stat_item { CPU_PARTIAL_FREE, /* Refill cpu partial on free */ CPU_PARTIAL_NODE, /* Refill cpu partial from node partial */ CPU_PARTIAL_DRAIN, /* Drain cpu partial to node partial */ + PCA_REFILL, /* Refilling empty percpu array cache */ + PCA_FLUSH, /* Flushing full percpu array cache */ NR_SLUB_STAT_ITEMS }; @@ -66,6 +70,13 @@ struct kmem_cache_cpu { }; #endif /* CONFIG_SLUB_TINY */ +struct slub_percpu_array { + spinlock_t lock; + unsigned int count; + unsigned int used; + void * objects[]; +}; + #ifdef CONFIG_SLUB_CPU_PARTIAL #define slub_percpu_partial(c) ((c)->partial) @@ -99,6 +110,7 @@ struct kmem_cache { #ifndef CONFIG_SLUB_TINY struct kmem_cache_cpu __percpu *cpu_slab; #endif + struct slub_percpu_array __percpu *cpu_array; /* Used for retrieving partial slabs, etc. */ slab_flags_t flags; unsigned long min_partial; diff --git a/mm/Kconfig b/mm/Kconfig index 89971a894b60..aa53c51bb4a6 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -237,6 +237,7 @@ choice config SLAB_DEPRECATED bool "SLAB (DEPRECATED)" depends on !PREEMPT_RT + depends on BROKEN help Deprecated and scheduled for removal in a few cycles. Replaced by SLUB. diff --git a/mm/slub.c b/mm/slub.c index 59912a376c6d..b0879714279b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -188,6 +188,79 @@ do { \ #define USE_LOCKLESS_FAST_PATH() (false) #endif +/* copy/pasted from mm/page_alloc.c */ + +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +/* + * On SMP, spin_trylock is sufficient protection. + * On PREEMPT_RT, spin_trylock is equivalent on both SMP and UP. + */ +#define pcp_trylock_prepare(flags) do { } while (0) +#define pcp_trylock_finish(flag) do { } while (0) +#else + +/* UP spin_trylock always succeeds so disable IRQs to prevent re-entrancy. */ +#define pcp_trylock_prepare(flags) local_irq_save(flags) +#define pcp_trylock_finish(flags) local_irq_restore(flags) +#endif + +/* + * Locking a pcp requires a PCP lookup followed by a spinlock. To avoid + * a migration causing the wrong PCP to be locked and remote memory being + * potentially allocated, pin the task to the CPU for the lookup+lock. + * preempt_disable is used on !RT because it is faster than migrate_disable. + * migrate_disable is used on RT because otherwise RT spinlock usage is + * interfered with and a high priority task cannot preempt the allocator. + */ +#ifndef CONFIG_PREEMPT_RT +#define pcpu_task_pin() preempt_disable() +#define pcpu_task_unpin() preempt_enable() +#else +#define pcpu_task_pin() migrate_disable() +#define pcpu_task_unpin() migrate_enable() +#endif + +/* + * Generic helper to lookup and a per-cpu variable with an embedded spinlock. + * Return value should be used with equivalent unlock helper. + */ +#define pcpu_spin_lock(type, member, ptr) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + spin_lock(&_ret->member); \ + _ret; \ +}) + +#define pcpu_spin_trylock(type, member, ptr) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + if (!spin_trylock(&_ret->member)) { \ + pcpu_task_unpin(); \ + _ret = NULL; \ + } \ + _ret; \ +}) + +#define pcpu_spin_unlock(member, ptr) \ +({ \ + spin_unlock(&ptr->member); \ + pcpu_task_unpin(); \ +}) + +/* struct slub_percpu_array specific helpers. */ +#define pca_spin_lock(ptr) \ + pcpu_spin_lock(struct slub_percpu_array, lock, ptr) + +#define pca_spin_trylock(ptr) \ + pcpu_spin_trylock(struct slub_percpu_array, lock, ptr) + +#define pca_spin_unlock(ptr) \ + pcpu_spin_unlock(lock, ptr) + #ifndef CONFIG_SLUB_TINY #define __fastpath_inline __always_inline #else @@ -3454,6 +3527,78 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, 0, sizeof(void *)); } +static bool refill_pca(struct kmem_cache *s, unsigned int count, gfp_t gfp); + +static __fastpath_inline +void *alloc_from_pca(struct kmem_cache *s, gfp_t gfp) +{ + unsigned long __maybe_unused UP_flags; + struct slub_percpu_array *pca; + void *object; + +retry: + pcp_trylock_prepare(UP_flags); + pca = pca_spin_trylock(s->cpu_array); + + if (unlikely(!pca)) { + pcp_trylock_finish(UP_flags); + return NULL; + } + + if (unlikely(pca->used == 0)) { + unsigned int batch = pca->count / 2; + + pca_spin_unlock(pca); + pcp_trylock_finish(UP_flags); + + if (!gfpflags_allow_blocking(gfp) || in_irq()) + return NULL; + + if (refill_pca(s, batch, gfp)) + goto retry; + + return NULL; + } + + object = pca->objects[--pca->used]; + + pca_spin_unlock(pca); + pcp_trylock_finish(UP_flags); + + stat(s, ALLOC_PCA); + + return object; +} + +static __fastpath_inline +int alloc_from_pca_bulk(struct kmem_cache *s, size_t size, void **p) +{ + unsigned long __maybe_unused UP_flags; + struct slub_percpu_array *pca; + + pcp_trylock_prepare(UP_flags); + pca = pca_spin_trylock(s->cpu_array); + + if (unlikely(!pca)) { + size = 0; + goto failed; + } + + if (pca->used < size) + size = pca->used; + + for (int i = size; i > 0;) { + p[--i] = pca->objects[--pca->used]; + } + + pca_spin_unlock(pca); + stat_add(s, ALLOC_PCA, size); + +failed: + pcp_trylock_finish(UP_flags); + return size; +} + /* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call @@ -3479,7 +3624,11 @@ static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list if (unlikely(object)) goto out; - object = __slab_alloc_node(s, gfpflags, node, addr, orig_size); + if (s->cpu_array) + object = alloc_from_pca(s, gfpflags); + + if (!object) + object = __slab_alloc_node(s, gfpflags, node, addr, orig_size); maybe_wipe_obj_freeptr(s, object); init = slab_want_init_on_alloc(gfpflags, s); @@ -3726,6 +3875,81 @@ slab_empty: discard_slab(s, slab); } +static bool flush_pca(struct kmem_cache *s, unsigned int count); + +static __fastpath_inline +bool free_to_pca(struct kmem_cache *s, void *object) +{ + unsigned long __maybe_unused UP_flags; + struct slub_percpu_array *pca; + +retry: + pcp_trylock_prepare(UP_flags); + pca = pca_spin_trylock(s->cpu_array); + + if (!pca) { + pcp_trylock_finish(UP_flags); + return false; + } + + if (pca->used == pca->count) { + unsigned int batch = pca->count / 2; + + pca_spin_unlock(pca); + pcp_trylock_finish(UP_flags); + + if (in_irq()) + return false; + + if (!flush_pca(s, batch)) + return false; + + goto retry; + } + + pca->objects[pca->used++] = object; + + pca_spin_unlock(pca); + pcp_trylock_finish(UP_flags); + + stat(s, FREE_PCA); + + return true; +} + +static __fastpath_inline +size_t free_to_pca_bulk(struct kmem_cache *s, size_t size, void **p) +{ + unsigned long __maybe_unused UP_flags; + struct slub_percpu_array *pca; + bool init; + + pcp_trylock_prepare(UP_flags); + pca = pca_spin_trylock(s->cpu_array); + + if (unlikely(!pca)) { + size = 0; + goto failed; + } + + if (pca->count - pca->used < size) + size = pca->count - pca->used; + + init = slab_want_init_on_free(s); + + for (size_t i = 0; i < size; i++) { + if (likely(slab_free_hook(s, p[i], init))) + pca->objects[pca->used++] = p[i]; + } + + pca_spin_unlock(pca); + stat_add(s, FREE_PCA, size); + +failed: + pcp_trylock_finish(UP_flags); + return size; +} + #ifndef CONFIG_SLUB_TINY /* * Fastpath with forced inlining to produce a kfree and kmem_cache_free that @@ -3811,7 +4035,12 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object, { memcg_slab_free_hook(s, slab, &object, 1); - if (likely(slab_free_hook(s, object, slab_want_init_on_free(s)))) + if (unlikely(!slab_free_hook(s, object, slab_want_init_on_free(s)))) + return; + + if (s->cpu_array) + free_to_pca(s, object); + else do_slab_free(s, slab, object, object, 1, addr); } @@ -3956,6 +4185,26 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) if (!size) return; + /* + * In case the objects might need memcg_slab_free_hook(), skip the array + * because the hook is not effective with single objects and benefits + * from groups of objects from a single slab that the detached freelist + * builds. But once we build the detached freelist, it's wasteful to + * throw it away and put the objects into the array. + * + * XXX: This test could be cache-specific if it was not possible to use + * __GFP_ACCOUNT with caches that are not SLAB_ACCOUNT + */ + if (s && s->cpu_array && !memcg_kmem_online()) { + size_t pca_freed = free_to_pca_bulk(s, size, p); + + if (pca_freed == size) + return; + + p += pca_freed; + size -= pca_freed; + } + do { struct detached_freelist df; @@ -4073,7 +4322,8 @@ error: int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p) { - int i; + int from_pca = 0; + int allocated = 0; struct obj_cgroup *objcg = NULL; if (!size) @@ -4084,19 +4334,147 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, if (unlikely(!s)) return 0; - i = __kmem_cache_alloc_bulk(s, flags, size, p); + if (s->cpu_array) + from_pca = alloc_from_pca_bulk(s, size, p); + + if (from_pca < size) { + allocated = __kmem_cache_alloc_bulk(s, flags, size-from_pca, + p+from_pca); + if (allocated == 0 && from_pca > 0) { + __kmem_cache_free_bulk(s, from_pca, p); + } + } + + allocated += from_pca; /* * memcg and kmem_cache debug support and memory initialization. * Done outside of the IRQ disabled fastpath loop. */ - if (i != 0) + if (allocated != 0) slab_post_alloc_hook(s, objcg, flags, size, p, slab_want_init_on_alloc(flags, s), s->object_size); - return i; + return allocated; } EXPORT_SYMBOL(kmem_cache_alloc_bulk); +static bool refill_pca(struct kmem_cache *s, unsigned int count, gfp_t gfp) +{ + void *objects[32]; + unsigned int batch, allocated; + unsigned long __maybe_unused UP_flags; + struct slub_percpu_array *pca; + +bulk_alloc: + batch = min(count, 32U); + + allocated = __kmem_cache_alloc_bulk(s, gfp, batch, &objects[0]); + if (!allocated) + return false; + + pcp_trylock_prepare(UP_flags); + pca = pca_spin_trylock(s->cpu_array); + if (!pca) { + pcp_trylock_finish(UP_flags); + return false; + } + + batch = min(allocated, pca->count - pca->used); + + for (unsigned int i = 0; i < batch; i++) { + pca->objects[pca->used++] = objects[i]; + } + + pca_spin_unlock(pca); + pcp_trylock_finish(UP_flags); + + stat_add(s, PCA_REFILL, batch); + + /* + * We could have migrated to a different cpu or somebody else freed to the + * pca while we were bulk allocating, and now we have too many objects + */ + if (batch < allocated) { + __kmem_cache_free_bulk(s, allocated - batch, &objects[batch]); + } else { + count -= batch; + if (count > 0) + goto bulk_alloc; + } + + return true; +} + +static bool flush_pca(struct kmem_cache *s, unsigned int count) +{ + void *objects[32]; + unsigned int batch, remaining; + unsigned long __maybe_unused UP_flags; + struct slub_percpu_array *pca; + +next_batch: + batch = min(count, 32); + + pcp_trylock_prepare(UP_flags); + pca = pca_spin_trylock(s->cpu_array); + if (!pca) { + pcp_trylock_finish(UP_flags); + return false; + } + + batch = min(batch, pca->used); + + for (unsigned int i = 0; i < batch; i++) { + objects[i] = pca->objects[--pca->used]; + } + + remaining = pca->used; + + pca_spin_unlock(pca); + pcp_trylock_finish(UP_flags); + + __kmem_cache_free_bulk(s, batch, &objects[0]); + + stat_add(s, PCA_FLUSH, batch); + + if (batch < count && remaining > 0) { + count -= batch; + goto next_batch; + } + + return true; +} + +/* Do not call from irq handler nor with irqs disabled */ +int kmem_cache_prefill_percpu_array(struct kmem_cache *s, unsigned int count, + gfp_t gfp) +{ + struct slub_percpu_array *pca; + unsigned int used; + + lockdep_assert_no_hardirq(); + + if (!s->cpu_array) + return -EINVAL; + + /* racy but we don't care */ + pca = raw_cpu_ptr(s->cpu_array); + + used = READ_ONCE(pca->used); + + if (used >= count) + return 0; + + if (pca->count < count) + return -EINVAL; + + count -= used; + + if (!refill_pca(s, count, gfp)) + return -ENOMEM; + + return 0; +} /* * Object placement in a slab is made very easy because we always start at @@ -5167,6 +5545,30 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags) return 0; } +int kmem_cache_setup_percpu_array(struct kmem_cache *s, unsigned int count) +{ + int cpu; + + if (WARN_ON_ONCE(!(s->flags & SLAB_NO_MERGE))) + return -EINVAL; + + s->cpu_array = __alloc_percpu(struct_size(s->cpu_array, objects, count), + sizeof(void *)); + + if (!s->cpu_array) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct slub_percpu_array *pca = per_cpu_ptr(s->cpu_array, cpu); + + spin_lock_init(&pca->lock); + pca->count = count; + pca->used = 0; + } + + return 0; +} + #ifdef SLAB_SUPPORTS_SYSFS static int count_inuse(struct slab *slab) { @@ -5944,8 +6346,10 @@ static ssize_t text##_store(struct kmem_cache *s, \ } \ SLAB_ATTR(text); \ +STAT_ATTR(ALLOC_PCA, alloc_cpu_cache); STAT_ATTR(ALLOC_FASTPATH, alloc_fastpath); STAT_ATTR(ALLOC_SLOWPATH, alloc_slowpath); +STAT_ATTR(FREE_PCA, free_cpu_cache); STAT_ATTR(FREE_FASTPATH, free_fastpath); STAT_ATTR(FREE_SLOWPATH, free_slowpath); STAT_ATTR(FREE_FROZEN, free_frozen); @@ -5970,6 +6374,8 @@ STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc); STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free); STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node); STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain); +STAT_ATTR(PCA_REFILL, cpu_cache_refill); +STAT_ATTR(PCA_FLUSH, cpu_cache_flush); #endif /* CONFIG_SLUB_STATS */ #ifdef CONFIG_KFENCE @@ -6031,8 +6437,10 @@ static struct attribute *slab_attrs[] = { &remote_node_defrag_ratio_attr.attr, #endif #ifdef CONFIG_SLUB_STATS + &alloc_cpu_cache_attr.attr, &alloc_fastpath_attr.attr, &alloc_slowpath_attr.attr, + &free_cpu_cache_attr.attr, &free_fastpath_attr.attr, &free_slowpath_attr.attr, &free_frozen_attr.attr, @@ -6057,6 +6465,8 @@ static struct attribute *slab_attrs[] = { &cpu_partial_free_attr.attr, &cpu_partial_node_attr.attr, &cpu_partial_drain_attr.attr, + &cpu_cache_refill_attr.attr, + &cpu_cache_flush_attr.attr, #endif #ifdef CONFIG_FAILSLAB &failslab_attr.attr,