[PATCH] slab: Remove SLAB_NO_REAP option

SLAB_NO_REAP is documented as an option that will cause this slab not to be
reaped under memory pressure.  However, that is not what happens.  The only
thing that SLAB_NO_REAP controls at the moment is the reclaim of the unused
slab elements that were allocated in batch in cache_reap().  Cache_reap()
is run every few seconds independently of memory pressure.

Could we remove the whole thing?  Its only used by three slabs anyways and
I cannot find a reason for having this option.

There is an additional problem with SLAB_NO_REAP.  If set then the recovery
of objects from alien caches is switched off.  Objects not freed on the
same node where they were initially allocated will only be reused if a
certain amount of objects accumulates from one alien node (not very likely)
or if the cache is explicitly shrunk.  (Strangely __cache_shrink does not
check for SLAB_NO_REAP)

Getting rid of SLAB_NO_REAP fixes the problems with alien cache freeing.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

drivers/scsi/iscsi_tcp.c

@@ -3639,7 +3639,7 @@ iscsi_tcp_init(void)
 
 	taskcache = kmem_cache_create("iscsi_taskcache",
 			sizeof(struct iscsi_data_task), 0,
-			SLAB_HWCACHE_ALIGN | SLAB_NO_REAP, NULL, NULL);
+			SLAB_HWCACHE_ALIGN, NULL, NULL);
 	if (!taskcache)
 		return -ENOMEM;
 

fs/ocfs2/super.c

@@ -959,7 +959,7 @@ static int ocfs2_initialize_mem_caches(void)
 	ocfs2_lock_cache = kmem_cache_create("ocfs2_lock",
 					     sizeof(struct ocfs2_journal_lock),
 					     0,
-					     SLAB_NO_REAP|SLAB_HWCACHE_ALIGN,
+					     SLAB_HWCACHE_ALIGN,
 					     NULL, NULL);
 	if (!ocfs2_lock_cache)
 		return -ENOMEM;

include/linux/slab.h

@@ -38,7 +38,6 @@ typedef struct kmem_cache kmem_cache_t;
 #define	SLAB_DEBUG_INITIAL	0x00000200UL	/* Call constructor (as verifier) */
 #define	SLAB_RED_ZONE		0x00000400UL	/* Red zone objs in a cache */
 #define	SLAB_POISON		0x00000800UL	/* Poison objects */
-#define	SLAB_NO_REAP		0x00001000UL	/* never reap from the cache */
 #define	SLAB_HWCACHE_ALIGN	0x00002000UL	/* align objs on a h/w cache lines */
 #define SLAB_CACHE_DMA		0x00004000UL	/* use GFP_DMA memory */
 #define SLAB_MUST_HWCACHE_ALIGN	0x00008000UL	/* force alignment */

mm/slab.c

@@ -170,12 +170,12 @@
 #if DEBUG
 # define CREATE_MASK	(SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \
 			 SLAB_POISON | SLAB_HWCACHE_ALIGN | \
-			 SLAB_NO_REAP | SLAB_CACHE_DMA | \
+			 SLAB_CACHE_DMA | \
 			 SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU)
 #else
-# define CREATE_MASK	(SLAB_HWCACHE_ALIGN | SLAB_NO_REAP | \
+# define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
 			 SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU)
@@ -662,7 +662,6 @@ static struct kmem_cache cache_cache = {
 	.limit = BOOT_CPUCACHE_ENTRIES,
 	.shared = 1,
 	.buffer_size = sizeof(struct kmem_cache),
-	.flags = SLAB_NO_REAP,
 	.name = "kmem_cache",
 #if DEBUG
 	.obj_size = sizeof(struct kmem_cache),
@@ -1848,9 +1847,6 @@ static void setup_cpu_cache(struct kmem_cache *cachep)
  * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
  * for buffer overruns.
  *
- * %SLAB_NO_REAP - Don't automatically reap this cache when we're under
- * memory pressure.
- *
  * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
  * cacheline.  This can be beneficial if you're counting cycles as closely
  * as davem.
@@ -3584,10 +3580,6 @@ static void cache_reap(void *unused)
 		struct slab *slabp;
 
 		searchp = list_entry(walk, struct kmem_cache, next);
-
-		if (searchp->flags & SLAB_NO_REAP)
-			goto next;
-
 		check_irq_on();
 
 		l3 = searchp->nodelists[numa_node_id()];
@@ -3635,7 +3627,6 @@ static void cache_reap(void *unused)
 		} while (--tofree > 0);
 next_unlock:
 		spin_unlock_irq(&l3->list_lock);
-next:
 		cond_resched();
 	}
 	check_irq_on();