From a77d6d338685025cbf84f6e3abd92a8e59a4d894 Mon Sep 17 00:00:00 2001 From: Harry Yoo Date: Tue, 13 Jan 2026 15:18:45 +0900 Subject: mm/slab: place slabobj_ext metadata in unused space within s->size When a cache has high s->align value and s->object_size is not aligned to it, each object ends up with some unused space because of alignment. If this wasted space is big enough, we can use it to store the slabobj_ext metadata instead of wasting it. On my system, this happens with caches like kmem_cache, mm_struct, pid, task_struct, sighand_cache, xfs_inode, and others. To place the slabobj_ext metadata within each object, the existing slab_obj_ext() logic can still be used by setting: - slab->obj_exts = slab_address(slab) + (slabobj_ext offset) - stride = s->size slab_obj_ext() doesn't need know where the metadata is stored, so this method works without adding extra overhead to slab_obj_ext(). A good example benefiting from this optimization is xfs_inode (object_size: 992, align: 64). To measure memory savings, 2 millions of files were created on XFS. [ MEMCG=y, MEM_ALLOC_PROFILING=n ] Before patch (creating ~2.64M directories on xfs): Slab: 5175976 kB SReclaimable: 3837524 kB SUnreclaim: 1338452 kB After patch (creating ~2.64M directories on xfs): Slab: 5152912 kB SReclaimable: 3838568 kB SUnreclaim: 1314344 kB (-23.54 MiB) Enjoy the memory savings! Suggested-by: Vlastimil Babka Signed-off-by: Harry Yoo Link: https://patch.msgid.link/20260113061845.159790-10-harry.yoo@oracle.com Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 93e367b6a5f6..34db237319c1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -59,6 +59,9 @@ enum _slab_flag_bits { _SLAB_CMPXCHG_DOUBLE, #ifdef CONFIG_SLAB_OBJ_EXT _SLAB_NO_OBJ_EXT, +#endif +#if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) + _SLAB_OBJ_EXT_IN_OBJ, #endif _SLAB_FLAGS_LAST_BIT }; @@ -244,6 +247,12 @@ enum _slab_flag_bits { #define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED #endif +#if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) +#define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_BIT(_SLAB_OBJ_EXT_IN_OBJ) +#else +#define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_UNUSED +#endif + /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * -- cgit v1.2.3