SLUB: direct pass through of page size or higher kmalloc requests
This gets rid of all kmalloc caches larger than page size. A kmalloc
request larger than PAGE_SIZE > 2 is going to be passed through to the page
allocator. This works both inline where we will call __get_free_pages
instead of kmem_cache_alloc and in __kmalloc.
kfree is modified to check if the object is in a slab page. If not then
the page is freed via the page allocator instead. Roughly similar to what
SLOB does.
Advantages:
- Reduces memory overhead for kmalloc array
- Large kmalloc operations are faster since they do not
need to pass through the slab allocator to get to the
page allocator.
- Performance increase of 10%-20% on alloc and 50% on free for
PAGE_SIZEd allocations.
SLUB must call page allocator for each alloc anyways since
the higher order pages which that allowed avoiding the page alloc calls
are not available in a reliable way anymore. So we are basically removing
useless slab allocator overhead.
- Large kmallocs yields page aligned object which is what
SLAB did. Bad things like using page sized kmalloc allocations to
stand in for page allocate allocs can be transparently handled and are not
distinguishable from page allocator uses.
- Checking for too large objects can be removed since
it is done by the page allocator.
Drawbacks:
- No accounting for large kmalloc slab allocations anymore
- No debugging of large kmalloc slab allocations.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 7496207..3b361b2 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -72,7 +72,7 @@
* We keep the general caches in an array of slab caches that are used for
* 2^x bytes of allocations.
*/
-extern struct kmem_cache kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+extern struct kmem_cache kmalloc_caches[PAGE_SHIFT];
/*
* Sorry that the following has to be that ugly but some versions of GCC
@@ -83,9 +83,6 @@
if (!size)
return 0;
- if (size > KMALLOC_MAX_SIZE)
- return -1;
-
if (size <= KMALLOC_MIN_SIZE)
return KMALLOC_SHIFT_LOW;
@@ -102,6 +99,10 @@
if (size <= 512) return 9;
if (size <= 1024) return 10;
if (size <= 2 * 1024) return 11;
+/*
+ * The following is only needed to support architectures with a larger page
+ * size than 4k.
+ */
if (size <= 4 * 1024) return 12;
if (size <= 8 * 1024) return 13;
if (size <= 16 * 1024) return 14;
@@ -109,13 +110,9 @@
if (size <= 64 * 1024) return 16;
if (size <= 128 * 1024) return 17;
if (size <= 256 * 1024) return 18;
- if (size <= 512 * 1024) return 19;
+ if (size <= 512 * 1024) return 19;
if (size <= 1024 * 1024) return 20;
if (size <= 2 * 1024 * 1024) return 21;
- if (size <= 4 * 1024 * 1024) return 22;
- if (size <= 8 * 1024 * 1024) return 23;
- if (size <= 16 * 1024 * 1024) return 24;
- if (size <= 32 * 1024 * 1024) return 25;
return -1;
/*
@@ -140,19 +137,6 @@
if (index == 0)
return NULL;
- /*
- * This function only gets expanded if __builtin_constant_p(size), so
- * testing it here shouldn't be needed. But some versions of gcc need
- * help.
- */
- if (__builtin_constant_p(size) && index < 0) {
- /*
- * Generate a link failure. Would be great if we could
- * do something to stop the compile here.
- */
- extern void __kmalloc_size_too_large(void);
- __kmalloc_size_too_large();
- }
return &kmalloc_caches[index];
}
@@ -168,15 +152,21 @@
static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
- if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) {
- struct kmem_cache *s = kmalloc_slab(size);
+ if (__builtin_constant_p(size)) {
+ if (size > PAGE_SIZE / 2)
+ return (void *)__get_free_pages(flags | __GFP_COMP,
+ get_order(size));
- if (!s)
- return ZERO_SIZE_PTR;
+ if (!(flags & SLUB_DMA)) {
+ struct kmem_cache *s = kmalloc_slab(size);
- return kmem_cache_alloc(s, flags);
- } else
- return __kmalloc(size, flags);
+ if (!s)
+ return ZERO_SIZE_PTR;
+
+ return kmem_cache_alloc(s, flags);
+ }
+ }
+ return __kmalloc(size, flags);
}
#ifdef CONFIG_NUMA
@@ -185,15 +175,16 @@
static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
- if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) {
- struct kmem_cache *s = kmalloc_slab(size);
+ if (__builtin_constant_p(size) &&
+ size <= PAGE_SIZE / 2 && !(flags & SLUB_DMA)) {
+ struct kmem_cache *s = kmalloc_slab(size);
if (!s)
return ZERO_SIZE_PTR;
return kmem_cache_alloc_node(s, flags, node);
- } else
- return __kmalloc_node(size, flags, node);
+ }
+ return __kmalloc_node(size, flags, node);
}
#endif
diff --git a/mm/slub.c b/mm/slub.c
index 0eab12b..edeb942 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2227,11 +2227,11 @@
* Kmalloc subsystem
*******************************************************************/
-struct kmem_cache kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __cacheline_aligned;
+struct kmem_cache kmalloc_caches[PAGE_SHIFT] __cacheline_aligned;
EXPORT_SYMBOL(kmalloc_caches);
#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_caches_dma[KMALLOC_SHIFT_HIGH + 1];
+static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT];
#endif
static int __init setup_slub_min_order(char *str)
@@ -2397,12 +2397,8 @@
return ZERO_SIZE_PTR;
index = size_index[(size - 1) / 8];
- } else {
- if (size > KMALLOC_MAX_SIZE)
- return NULL;
-
+ } else
index = fls(size - 1);
- }
#ifdef CONFIG_ZONE_DMA
if (unlikely((flags & SLUB_DMA)))
@@ -2414,9 +2410,15 @@
void *__kmalloc(size_t size, gfp_t flags)
{
- struct kmem_cache *s = get_slab(size, flags);
+ struct kmem_cache *s;
- if (ZERO_OR_NULL_PTR(s))
+ if (unlikely(size > PAGE_SIZE / 2))
+ return (void *)__get_free_pages(flags | __GFP_COMP,
+ get_order(size));
+
+ s = get_slab(size, flags);
+
+ if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
return slab_alloc(s, flags, -1, __builtin_return_address(0));
@@ -2426,9 +2428,15 @@
#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
- struct kmem_cache *s = get_slab(size, flags);
+ struct kmem_cache *s;
- if (ZERO_OR_NULL_PTR(s))
+ if (unlikely(size > PAGE_SIZE / 2))
+ return (void *)__get_free_pages(flags | __GFP_COMP,
+ get_order(size));
+
+ s = get_slab(size, flags);
+
+ if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
return slab_alloc(s, flags, node, __builtin_return_address(0));
@@ -2473,22 +2481,17 @@
void kfree(const void *x)
{
- struct kmem_cache *s;
struct page *page;
- /*
- * This has to be an unsigned comparison. According to Linus
- * some gcc version treat a pointer as a signed entity. Then
- * this comparison would be true for all "negative" pointers
- * (which would cover the whole upper half of the address space).
- */
if (ZERO_OR_NULL_PTR(x))
return;
page = virt_to_head_page(x);
- s = page->slab;
-
- slab_free(s, page, (void *)x, __builtin_return_address(0));
+ if (unlikely(!PageSlab(page))) {
+ put_page(page);
+ return;
+ }
+ slab_free(page->slab, page, (void *)x, __builtin_return_address(0));
}
EXPORT_SYMBOL(kfree);
@@ -2602,7 +2605,7 @@
caches++;
}
- for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
+ for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++) {
create_kmalloc_cache(&kmalloc_caches[i],
"kmalloc", 1 << i, GFP_KERNEL);
caches++;
@@ -2629,7 +2632,7 @@
slab_state = UP;
/* Provide the correct kmalloc names now that the caches are up */
- for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
+ for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++)
kmalloc_caches[i]. name =
kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);
@@ -2790,7 +2793,12 @@
void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
{
- struct kmem_cache *s = get_slab(size, gfpflags);
+ struct kmem_cache *s;
+
+ if (unlikely(size > PAGE_SIZE / 2))
+ return (void *)__get_free_pages(gfpflags | __GFP_COMP,
+ get_order(size));
+ s = get_slab(size, gfpflags);
if (ZERO_OR_NULL_PTR(s))
return s;
@@ -2801,7 +2809,12 @@
void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
int node, void *caller)
{
- struct kmem_cache *s = get_slab(size, gfpflags);
+ struct kmem_cache *s;
+
+ if (unlikely(size > PAGE_SIZE / 2))
+ return (void *)__get_free_pages(gfpflags | __GFP_COMP,
+ get_order(size));
+ s = get_slab(size, gfpflags);
if (ZERO_OR_NULL_PTR(s))
return s;