[PATCH for-v3.7 2/2] slub: optimize kmalloc* inlining for GFP_DMA

[Joonsoo Kim <js1304@xxxxxxxxx>]

kmalloc() and kmalloc_node() of the SLUB isn't inlined when @flags = __GFP_DMA.
This patch optimize this case,
so when @flags = __GFP_DMA, it will be inlined into generic code.

Cc: Christoph Lameter <cl@xxxxxxxxx>
Signed-off-by: Joonsoo Kim <js1304@xxxxxxxxx>

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 4c75f2b..4adf50b 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -147,6 +147,7 @@ struct kmem_cache {
  * 2^x bytes of allocations.
  */
 extern struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
+extern struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
 
 /*
  * Sorry that the following has to be that ugly but some versions of GCC
@@ -266,19 +267,24 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
 
 static __always_inline void *kmalloc(size_t size, gfp_t flags)
 {
+	struct kmem_cache *s;
+	int index;
+
 	if (__builtin_constant_p(size)) {
 		if (size > SLUB_MAX_SIZE)
 			return kmalloc_large(size, flags);
 
-		if (!(flags & SLUB_DMA)) {
-			int index = kmalloc_index(size);
-			struct kmem_cache *s = kmalloc_caches[index];
-
-			if (!index)
-				return ZERO_SIZE_PTR;
+		index = kmalloc_index(size);
+		if (!index)
+			return ZERO_SIZE_PTR;
+#ifdef CONFIG_ZONE_DMA
+		if (unlikely(flags & SLUB_DMA)) {
+			s = kmalloc_dma_caches[index];
+		} else
+#endif
+			s = kmalloc_caches[index];
 
-			return kmem_cache_alloc_trace(s, flags, size);
-		}
+		return kmem_cache_alloc_trace(s, flags, size);
 	}
 	return __kmalloc(size, flags);
 }
@@ -303,13 +309,19 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s,
 
 static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
-	if (__builtin_constant_p(size) &&
-		size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
-		int index = kmalloc_index(size);
-		struct kmem_cache *s = kmalloc_caches[index];
+	struct kmem_cache *s;
+	int index;
 
+	if (__builtin_constant_p(size) && size <= SLUB_MAX_SIZE) {
+		index = kmalloc_index(size);
 		if (!index)
 			return ZERO_SIZE_PTR;
+#ifdef CONFIG_ZONE_DMA
+		if (unlikely(flags & SLUB_DMA)) {
+			s = kmalloc_dma_caches[index];
+		} else
+#endif
+			s = kmalloc_caches[index];
 
 		return kmem_cache_alloc_node_trace(s, flags, node, size);
 	}
diff --git a/mm/slub.c b/mm/slub.c
index a0d6984..a94533c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3222,7 +3222,8 @@ struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
 EXPORT_SYMBOL(kmalloc_caches);
 
 #ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
+struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
+EXPORT_SYMBOL(kmalloc_dma_caches);
 #endif
 
 static int __init setup_slub_min_order(char *str)
-- 
1.7.9.5

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>