SLUB: Get rid of dynamic DMA kmalloc cache allocation

Dynamic DMA kmalloc cache allocation is troublesome since the
new percpu allocator does not support allocations in atomic contexts.
Reserve some statically allocated kmalloc_cpu structures instead.

Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>

2 files changed, 21 insertions, 22 deletions

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 17ebe0f89bf3..a78fb4ac2015 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -131,11 +131,21 @@ struct kmem_cache {
 
 #define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2)
 
+#ifdef CONFIG_ZONE_DMA
+#define SLUB_DMA __GFP_DMA
+/* Reserve extra caches for potential DMA use */
+#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT - 6)
+#else
+/* Disable DMA functionality */
+#define SLUB_DMA (__force gfp_t)0
+#define KMALLOC_CACHES SLUB_PAGE_SHIFT
+#endif
+
 /*
  * We keep the general caches in an array of slab caches that are used for
  * 2^x bytes of allocations.
  */
-extern struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT];
+extern struct kmem_cache kmalloc_caches[KMALLOC_CACHES];
 
 /*
  * Sorry that the following has to be that ugly but some versions of GCC
@@ -203,13 +213,6 @@ static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
         return &kmalloc_caches[index];
 }
 
-#ifdef CONFIG_ZONE_DMA
-#define SLUB_DMA __GFP_DMA
-#else
-/* Disable DMA functionality */
-#define SLUB_DMA (__force gfp_t)0
-#endif
-
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *__kmalloc(size_t size, gfp_t flags);
 
diff --git a/mm/slub.c b/mm/slub.c
index d6c9ecf629d5..cdb7f0214af0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2092,7 +2092,7 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
 {
         int cpu;
 
-        if (s < kmalloc_caches + SLUB_PAGE_SHIFT && s >= kmalloc_caches)
+        if (s < kmalloc_caches + KMALLOC_CACHES && s >= kmalloc_caches)
                 /*
                  * Boot time creation of the kmalloc array. Use static per cpu data
                  * since the per cpu allocator is not available yet.
@@ -2539,7 +2539,7 @@ EXPORT_SYMBOL(kmem_cache_destroy);
  *              Kmalloc subsystem
  *******************************************************************/
 
-struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT] __cacheline_aligned;
+struct kmem_cache kmalloc_caches[KMALLOC_CACHES] __cacheline_aligned;
 EXPORT_SYMBOL(kmalloc_caches);
 
 static int __init setup_slub_min_order(char *str)
@@ -2629,6 +2629,7 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
         char *text;
         size_t realsize;
         unsigned long slabflags;
+        int i;
 
         s = kmalloc_caches_dma[index];
         if (s)
@@ -2649,18 +2650,13 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
         text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d",
                          (unsigned int)realsize);
 
-        if (flags & __GFP_WAIT)
-                s = kmalloc(kmem_size, flags & ~SLUB_DMA);
-        else {
-                int i;
+        s = NULL;
+        for (i = 0; i < KMALLOC_CACHES; i++)
+                if (!kmalloc_caches[i].size)
+                        break;
 
-                s = NULL;
-                for (i = 0; i < SLUB_PAGE_SHIFT; i++)
-                        if (kmalloc_caches[i].size) {
-                                s = kmalloc_caches + i;
-                                break;
-                        }
-        }
+        BUG_ON(i >= KMALLOC_CACHES);
+        s = kmalloc_caches + i;
 
         /*
          * Must defer sysfs creation to a workqueue because we don't know
@@ -2674,7 +2670,7 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 
         if (!s || !text || !kmem_cache_open(s, flags, text,
                         realsize, ARCH_KMALLOC_MINALIGN, slabflags, NULL)) {
-                kfree(s);
+                s->size = 0;
                 kfree(text);
                 goto unlock_out;
         }