diff options
author | Uladzislau Rezki (Sony) <urezki@gmail.com> | 2021-04-29 22:59:19 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-04-30 11:20:40 -0700 |
commit | 187f8cc456f83e4745e326f3026a83a97e7814a1 (patch) | |
tree | 2a492e9c3cd9594eb198346046005f94e21f65c7 /mm/vmalloc.c | |
parent | 7bc4ca3ea956669b4e14ee03108c6623a136edfa (diff) | |
download | linux-187f8cc456f83e4745e326f3026a83a97e7814a1.tar.bz2 |
mm/vmalloc: refactor the preloading loagic
Instead of keeping open-coded style, move the code related to preloading
into a separate function. Therefore introduce the preload_this_cpu_lock()
routine that prelaods a current CPU with one extra vmap_area object.
There is no functional change as a result of this patch.
Link: https://lkml.kernel.org/r/20210402202237.20334-4-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/vmalloc.c')
-rw-r--r-- | mm/vmalloc.c | 60 |
1 files changed, 27 insertions, 33 deletions
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 51874a341ab0..83a83f672c09 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1430,6 +1430,29 @@ static void free_vmap_area(struct vmap_area *va) spin_unlock(&free_vmap_area_lock); } +static inline void +preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) +{ + struct vmap_area *va = NULL; + + /* + * Preload this CPU with one extra vmap_area object. It is used + * when fit type of free area is NE_FIT_TYPE. It guarantees that + * a CPU that does an allocation is preloaded. + * + * We do it in non-atomic context, thus it allows us to use more + * permissive allocation masks to be more stable under low memory + * condition and high memory pressure. + */ + if (!this_cpu_read(ne_fit_preload_node)) + va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + + spin_lock(lock); + + if (va && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, va)) + kmem_cache_free(vmap_area_cachep, va); +} + /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. @@ -1439,7 +1462,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask) { - struct vmap_area *va, *pva; + struct vmap_area *va; unsigned long addr; int purged = 0; int ret; @@ -1465,43 +1488,14 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); retry: - /* - * Preload this CPU with one extra vmap_area object. It is used - * when fit type of free area is NE_FIT_TYPE. Please note, it - * does not guarantee that an allocation occurs on a CPU that - * is preloaded, instead we minimize the case when it is not. - * It can happen because of cpu migration, because there is a - * race until the below spinlock is taken. - * - * The preload is done in non-atomic context, thus it allows us - * to use more permissive allocation masks to be more stable under - * low memory condition and high memory pressure. In rare case, - * if not preloaded, GFP_NOWAIT is used. - * - * Set "pva" to NULL here, because of "retry" path. - */ - pva = NULL; - - if (!this_cpu_read(ne_fit_preload_node)) - /* - * Even if it fails we do not really care about that. - * Just proceed as it is. If needed "overflow" path - * will refill the cache we allocate from. - */ - pva = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); - - spin_lock(&free_vmap_area_lock); - - if (pva && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) - kmem_cache_free(vmap_area_cachep, pva); + preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); + addr = __alloc_vmap_area(size, align, vstart, vend); + spin_unlock(&free_vmap_area_lock); /* * If an allocation fails, the "vend" address is * returned. Therefore trigger the overflow path. */ - addr = __alloc_vmap_area(size, align, vstart, vend); - spin_unlock(&free_vmap_area_lock); - if (unlikely(addr == vend)) goto overflow; |