The patch titled
Subject: slab: make size_index[] array u8
has been added to the -mm tree. Its filename is
slab-make-size_index-array-u8.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/slab-make-size_index-array-u8.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/slab-make-size_index-array-u8.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Alexey Dobriyan <adobriyan@xxxxxxxxx>
Subject: slab: make size_index[] array u8
All those small numbers are reverse indexes into kmalloc caches array
and can't be negative.
On x86_64 "unsigned int = fls()" can drop CDQE instruction:
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-2 (-2)
Function old new delta
kmalloc_slab 101 99 -2
Link: http://lkml.kernel.org/r/20180305200730.15812-7-adobriyan@xxxxxxxxx
Signed-off-by: Alexey Dobriyan <adobriyan@xxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/slab_common.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff -puN mm/slab_common.c~slab-make-size_index-array-u8 mm/slab_common.c
--- a/mm/slab_common.c~slab-make-size_index-array-u8
+++ a/mm/slab_common.c
@@ -971,7 +971,7 @@ EXPORT_SYMBOL(kmalloc_dma_caches);
* of two cache sizes there. The size of larger slabs can be determined using
* fls.
*/
-static s8 size_index[24] __ro_after_init = {
+static u8 size_index[24] __ro_after_init = {
3, /* 8 */
4, /* 16 */
5, /* 24 */
@@ -1009,7 +1009,7 @@ static inline int size_index_elem(size_t
*/
struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
{
- int index;
+ unsigned int index;
if (unlikely(size > KMALLOC_MAX_SIZE)) {
WARN_ON_ONCE(!(flags & __GFP_NOWARN));
_
Patches currently in -mm which might be from adobriyan@xxxxxxxxx are
slab-mark-kmalloc-machinery-as-__ro_after_init.patch
slab-fixup-calculate_alignment-argument-type.patch
slab-make-kmalloc_index-return-unsigned-int.patch
slab-make-kmalloc_size-return-unsigned-int.patch
slab-make-create_kmalloc_cache-work-with-32-bit-sizes.patch
slab-make-create_boot_cache-work-with-32-bit-sizes.patch
slab-make-kmem_cache_create-work-with-32-bit-sizes.patch
slab-make-size_index-array-u8.patch
slab-make-size_index_elem-unsigned-int.patch
slub-make-remote_node_defrag_ratio-unsigned-int.patch
slub-make-max_attr_size-unsigned-int.patch
slub-make-red_left_pad-unsigned-int.patch
slub-make-reserved-unsigned-int.patch
slub-make-align-unsigned-int.patch
slub-make-inuse-unsigned-int.patch
slub-make-cpu_partial-unsigned-int.patch
slub-make-offset-unsigned-int.patch
slub-make-object_size-unsigned-int.patch
slub-make-size-unsigned-int.patch
slab-make-kmem_cache_flags-accept-32-bit-object-size.patch
kasan-make-kasan_cache_create-work-with-32-bit-slab-cache-sizes.patch
slab-make-usercopy-region-32-bit.patch
slub-make-slab_index-return-unsigned-int.patch
slub-make-struct-kmem_cache_order_objects-x-unsigned-int.patch
slub-make-size_from_object-return-unsigned-int.patch
slab-use-32-bit-arithmetic-in-freelist_randomize.patch
proc-do-less-stuff-under-pde_unload_lock.patch
proc-move-proc-sysvipc-creation-to-where-it-belongs.patch
proc-faster-open-close-of-files-without-release-hook.patch
proc-randomize-struct-pde_opener.patch
proc-move-struct-pde_opener-to-kmem-cache.patch
proc-account-struct-pde_opener.patch
proc-check-permissions-earlier-for-proc-wchan.patch
proc-use-set_puts-at-proc-wchan.patch
proc-test-proc-self-wchan.patch
proc-test-proc-self-syscall.patch
uts-create-struct-uts_namespace-from-kmem_cache.patch
seq_file-delete-small-value-optimization.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
