alloc_tag: uninline code gated by mem_alloc_profiling_key in slab allocator

When a sizable code section is protected by a disabled static key, that
code gets into the instruction cache even though it's not executed and
consumes the cache, increasing cache misses.  This can be remedied by
moving such code into a separate uninlined function.  On a Pixel6 phone,
slab allocation profiling overhead measured with
CONFIG_MEM_ALLOC_PROFILING=y and profiling disabled is:

             baseline             modified
Big core     3.31%                0.17%
Medium core  3.79%                0.57%
Little core  6.68%                1.28%

This improvement comes at the expense of the configuration when profiling
gets enabled, since there is now an additional function call.  The
overhead from this additional call on Pixel6 is:

Big core     0.66%
Middle core  1.23%
Little core  2.42%

However this is negligible when compared with the overall overhead of the
memory allocation profiling when it is enabled.

On x86 this patch does not make noticeable difference because the overhead
with mem_alloc_profiling_key disabled is much lower (under 1%) to start
with, so any improvement is less visible and hard to distinguish from the
noise.  The overhead from additional call when profiling is enabled is
also within noise levels.

Link: https://lkml.kernel.org/r/20250201231803.2661189-2-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: David Wang <00107082@163.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Minchan Kim <minchan@google.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Sourav Panda <souravpanda@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/slub.c b/mm/slub.c
index 1f50129dcfb3cd1fc76ac9398fa7718cedb42385..184fd2b147584f3cc36ab9a5803089ed677061de 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2000,7 +2000,8 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
        return 0;
 }
 
-static inline void free_slab_obj_exts(struct slab *slab)
+/* Should be called only if mem_alloc_profiling_enabled() */
+static noinline void free_slab_obj_exts(struct slab *slab)
 {
        struct slabobj_ext *obj_exts;
 
@@ -2077,33 +2078,37 @@ prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p)
        return slab_obj_exts(slab) + obj_to_index(s, slab, p);
 }
 
-static inline void
-alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
+/* Should be called only if mem_alloc_profiling_enabled() */
+static noinline void
+__alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
 {
-       if (need_slab_obj_ext()) {
-               struct slabobj_ext *obj_exts;
+       struct slabobj_ext *obj_exts;
 
-               obj_exts = prepare_slab_obj_exts_hook(s, flags, object);
-               /*
-                * Currently obj_exts is used only for allocation profiling.
-                * If other users appear then mem_alloc_profiling_enabled()
-                * check should be added before alloc_tag_add().
-                */
-               if (likely(obj_exts))
-                       alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size);
-       }
+       obj_exts = prepare_slab_obj_exts_hook(s, flags, object);
+       /*
+        * Currently obj_exts is used only for allocation profiling.
+        * If other users appear then mem_alloc_profiling_enabled()
+        * check should be added before alloc_tag_add().
+        */
+       if (likely(obj_exts))
+               alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size);
 }
 
 static inline void
-alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
-                            int objects)
+alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
+{
+       if (need_slab_obj_ext())
+               __alloc_tagging_slab_alloc_hook(s, object, flags);
+}
+
+/* Should be called only if mem_alloc_profiling_enabled() */
+static noinline void
+__alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
+                              int objects)
 {
        struct slabobj_ext *obj_exts;
        int i;
 
-       if (!mem_alloc_profiling_enabled())
-               return;
-
        /* slab->obj_exts might not be NULL if it was created for MEMCG accounting. */
        if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE))
                return;
@@ -2119,6 +2124,14 @@ alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
        }
 }
 
+static inline void
+alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
+                            int objects)
+{
+       if (mem_alloc_profiling_enabled())
+               __alloc_tagging_slab_free_hook(s, slab, p, objects);
+}
+
 #else /* CONFIG_MEM_ALLOC_PROFILING */
 
 static inline void