From e6cdb58d1c8307f66039b04203e378d89938281c Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 15 Mar 2016 14:53:56 -0700 Subject: [PATCH] slab: implement bulk free in SLAB allocator This patch implements the free side of bulk API for the SLAB allocator kmem_cache_free_bulk(), and concludes the implementation of optimized bulk API for SLAB allocator. Benchmarked[1] cost of alloc+free (obj size 256 bytes) on CPU i7-4790K @ 4.00GHz, with no debug options, no PREEMPT and CONFIG_MEMCG_KMEM=y but no active user of kmemcg. SLAB single alloc+free cost: 87 cycles(tsc) 21.814 ns with this optimized config. bulk- Current fallback - optimized SLAB bulk 1 - 102 cycles(tsc) 25.747 ns - 41 cycles(tsc) 10.490 ns - improved 59.8% 2 - 94 cycles(tsc) 23.546 ns - 26 cycles(tsc) 6.567 ns - improved 72.3% 3 - 92 cycles(tsc) 23.127 ns - 20 cycles(tsc) 5.244 ns - improved 78.3% 4 - 90 cycles(tsc) 22.663 ns - 18 cycles(tsc) 4.588 ns - improved 80.0% 8 - 88 cycles(tsc) 22.242 ns - 14 cycles(tsc) 3.656 ns - improved 84.1% 16 - 88 cycles(tsc) 22.010 ns - 13 cycles(tsc) 3.480 ns - improved 85.2% 30 - 89 cycles(tsc) 22.305 ns - 13 cycles(tsc) 3.303 ns - improved 85.4% 32 - 89 cycles(tsc) 22.277 ns - 13 cycles(tsc) 3.309 ns - improved 85.4% 34 - 88 cycles(tsc) 22.246 ns - 13 cycles(tsc) 3.294 ns - improved 85.2% 48 - 88 cycles(tsc) 22.121 ns - 13 cycles(tsc) 3.492 ns - improved 85.2% 64 - 88 cycles(tsc) 22.052 ns - 13 cycles(tsc) 3.411 ns - improved 85.2% 128 - 89 cycles(tsc) 22.452 ns - 15 cycles(tsc) 3.841 ns - improved 83.1% 158 - 89 cycles(tsc) 22.403 ns - 14 cycles(tsc) 3.746 ns - improved 84.3% 250 - 91 cycles(tsc) 22.775 ns - 16 cycles(tsc) 4.111 ns - improved 82.4% Notice it is not recommended to do very large bulk operation with this bulk API, because local IRQs are disabled in this period. [1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c Signed-off-by: Jesper Dangaard Brouer Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/mm/slab.c b/mm/slab.c index 207fa92502de..2e075c0acfcf 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3385,12 +3385,6 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) } EXPORT_SYMBOL(kmem_cache_alloc); -void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) -{ - __kmem_cache_free_bulk(s, size, p); -} -EXPORT_SYMBOL(kmem_cache_free_bulk); - static __always_inline void cache_alloc_debugcheck_after_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p, unsigned long caller) @@ -3584,6 +3578,29 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) } EXPORT_SYMBOL(kmem_cache_free); +void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p) +{ + struct kmem_cache *s; + size_t i; + + local_irq_disable(); + for (i = 0; i < size; i++) { + void *objp = p[i]; + + s = cache_from_obj(orig_s, objp); + + debug_check_no_locks_freed(objp, s->object_size); + if (!(s->flags & SLAB_DEBUG_OBJECTS)) + debug_check_no_obj_freed(objp, s->object_size); + + __cache_free(s, objp, _RET_IP_); + } + local_irq_enable(); + + /* FIXME: add tracing */ +} +EXPORT_SYMBOL(kmem_cache_free_bulk); + /** * kfree - free previously allocated memory * @objp: pointer returned by kmalloc.