mm, slub: don't aggressively inline with CONFIG_SLUB_TINY

SLUB fastpaths use __always_inline to avoid function calls. With
CONFIG_SLUB_TINY we would rather save the memory. Add a
__fastpath_inline macro that's __always_inline normally but empty with
CONFIG_SLUB_TINY.

bloat-o-meter results on x86_64 mm/slub.o:

add/remove: 3/1 grow/shrink: 1/8 up/down: 865/-1784 (-919)
Function                                     old     new   delta
kmem_cache_free                               20     281    +261
slab_alloc_node.isra                           -     245    +245
slab_free.constprop.isra                       -     231    +231
__kmem_cache_alloc_lru.isra                    -     128    +128
__kmem_cache_release                          88      83      -5
__kmem_cache_create                         1446    1436     -10
__kmem_cache_free                            271     142    -129
kmem_cache_alloc_node                        330     127    -203
kmem_cache_free_bulk.part                    826     613    -213
__kmem_cache_alloc_node                      230      10    -220
kmem_cache_alloc_lru                         325      12    -313
kmem_cache_alloc                             325      10    -315
kmem_cache_free.part                         376       -    -376
Total: Before=26103, After=25184, chg -3.52%

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>

diff --git a/mm/slub.c b/mm/slub.c
index 00d921bd5417d70eff492f578eee421ba3b3176e..ac9e4a15fa32aa0ef79249932297144b423408c9 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -187,6 +187,12 @@ do {                                       \
 #define USE_LOCKLESS_FAST_PATH()       (false)
 #endif
 
+#ifndef CONFIG_SLUB_TINY
+#define __fastpath_inline __always_inline
+#else
+#define __fastpath_inline
+#endif
+
 #ifdef CONFIG_SLUB_DEBUG
 #ifdef CONFIG_SLUB_DEBUG_ON
 DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
@@ -3386,7 +3392,7 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
  *
  * Otherwise we can simply pick the next object from the lockless free list.
  */
-static __always_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
+static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
                gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
 {
        void *object;
@@ -3412,13 +3418,13 @@ out:
        return object;
 }
 
-static __always_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
+static __fastpath_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
                gfp_t gfpflags, unsigned long addr, size_t orig_size)
 {
        return slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, addr, orig_size);
 }
 
-static __always_inline
+static __fastpath_inline
 void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
                             gfp_t gfpflags)
 {
@@ -3733,7 +3739,7 @@ static void do_slab_free(struct kmem_cache *s,
 }
 #endif /* CONFIG_SLUB_TINY */
 
-static __always_inline void slab_free(struct kmem_cache *s, struct slab *slab,
+static __fastpath_inline void slab_free(struct kmem_cache *s, struct slab *slab,
                                      void *head, void *tail, void **p, int cnt,
                                      unsigned long addr)
 {