Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
  mm: SLOB fix reclaim_state
  mm: SLUB fix reclaim_state
  slub: add Documentation/ABI/testing/sysfs-kernel-slab
  slub: enforce MAX_ORDER

3 files changed, 488 insertions, 2 deletions

diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
new file mode 100644
index 0000000..6dcf75e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -0,0 +1,479 @@
+What:		/sys/kernel/slab
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The /sys/kernel/slab directory contains a snapshot of the
+		internal state of the SLUB allocator for each cache.  Certain
+		files may be modified to change the behavior of the cache (and
+		any cache it aliases, if any).
+Users:		kernel memory tuning tools
+
+What:		/sys/kernel/slab/cache/aliases
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The aliases file is read-only and specifies how many caches
+		have merged into this cache.
+
+What:		/sys/kernel/slab/cache/align
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The align file is read-only and specifies the cache's object
+		alignment in bytes.
+
+What:		/sys/kernel/slab/cache/alloc_calls
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_calls file is read-only and lists the kernel code
+		locations from which allocations for this cache were performed.
+		The alloc_calls file only contains information if debugging is
+		enabled for that cache (see Documentation/vm/slub.txt).
+
+What:		/sys/kernel/slab/cache/alloc_fastpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_fastpath file is read-only and specifies how many
+		objects have been allocated using the fast path.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_from_partial
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_from_partial file is read-only and specifies how
+		many times a cpu slab has been full and it has been refilled
+		by using a slab from the list of partially used slabs.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_refill
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_refill file is read-only and specifies how many
+		times the per-cpu freelist was empty but there were objects
+		available as the result of remote cpu frees.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_slab
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_slab file is read-only and specifies how many times
+		a new slab had to be allocated from the page allocator.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_slowpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_slowpath file is read-only and specifies how many
+		objects have been allocated using the slow path because of a
+		refill or allocation from a partial or new slab.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/cache_dma
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The cache_dma file is read-only and specifies whether objects
+		are from ZONE_DMA.
+		Available when CONFIG_ZONE_DMA is enabled.
+
+What:		/sys/kernel/slab/cache/cpu_slabs
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The cpu_slabs file is read-only and displays how many cpu slabs
+		are active and their NUMA locality.
+
+What:		/sys/kernel/slab/cache/cpuslab_flush
+Date:		April 2009
+KernelVersion:	2.6.31
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file cpuslab_flush is read-only and specifies how many
+		times a cache's cpu slabs have been flushed as the result of
+		destroying or shrinking a cache, a cpu going offline, or as
+		the result of forcing an allocation from a certain node.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/ctor
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The ctor file is read-only and specifies the cache's object
+		constructor function, which is invoked for each object when a
+		new slab is allocated.
+
+What:		/sys/kernel/slab/cache/deactivate_empty
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_empty is read-only and specifies how many
+		times an empty cpu slab was deactivated.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_full
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_full is read-only and specifies how many
+		times a full cpu slab was deactivated.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_remote_frees
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_remote_frees is read-only and specifies how
+		many times a cpu slab has been deactivated and contained free
+		objects that were freed remotely.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_to_head
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_to_head is read-only and specifies how
+		many times a partial cpu slab was deactivated and added to the
+		head of its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_to_tail
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_to_tail is read-only and specifies how
+		many times a partial cpu slab was deactivated and added to the
+		tail of its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/destroy_by_rcu
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The destroy_by_rcu file is read-only and specifies whether
+		slabs (not objects) are freed by rcu.
+
+What:		/sys/kernel/slab/cache/free_add_partial
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file free_add_partial is read-only and specifies how many
+		times an object has been freed in a full slab so that it had to
+		added to its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_calls
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_calls file is read-only and lists the locations of
+		object frees if slab debugging is enabled (see
+		Documentation/vm/slub.txt).
+
+What:		/sys/kernel/slab/cache/free_fastpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_fastpath file is read-only and specifies how many
+		objects have been freed using the fast path because it was an
+		object from the cpu slab.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_frozen
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_frozen file is read-only and specifies how many
+		objects have been freed to a frozen slab (i.e. a remote cpu
+		slab).
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_remove_partial
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file free_remove_partial is read-only and specifies how
+		many times an object has been freed to a now-empty slab so
+		that it had to be removed from its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_slab
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_slab file is read-only and specifies how many times an
+		empty slab has been freed back to the page allocator.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_slowpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_slowpath file is read-only and specifies how many
+		objects have been freed using the slow path (i.e. to a full or
+		partial slab).
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/hwcache_align
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The hwcache_align file is read-only and specifies whether
+		objects are aligned on cachelines.
+
+What:		/sys/kernel/slab/cache/min_partial
+Date:		February 2009
+KernelVersion:	2.6.30
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		David Rientjes <rientjes@google.com>
+Description:
+		The min_partial file specifies how many empty slabs shall
+		remain on a node's partial list to avoid the overhead of
+		allocating new slabs.  Such slabs may be reclaimed by utilizing
+		the shrink file.
+
+What:		/sys/kernel/slab/cache/object_size
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The object_size file is read-only and specifies the cache's
+		object size.
+
+What:		/sys/kernel/slab/cache/objects
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The objects file is read-only and displays how many objects are
+		active and from which nodes they are from.
+
+What:		/sys/kernel/slab/cache/objects_partial
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The objects_partial file is read-only and displays how many
+		objects are on partial slabs and from which nodes they are
+		from.
+
+What:		/sys/kernel/slab/cache/objs_per_slab
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file objs_per_slab is read-only and specifies how many
+		objects may be allocated from a single slab of the order
+		specified in /sys/kernel/slab/cache/order.
+
+What:		/sys/kernel/slab/cache/order
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The order file specifies the page order at which new slabs are
+		allocated.  It is writable and can be changed to increase the
+		number of objects per slab.  If a slab cannot be allocated
+		because of fragmentation, SLUB will retry with the minimum order
+		possible depending on its characteristics.
+
+What:		/sys/kernel/slab/cache/order_fallback
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file order_fallback is read-only and specifies how many
+		times an allocation of a new slab has not been possible at the
+		cache's order and instead fallen back to its minimum possible
+		order.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/partial
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The partial file is read-only and displays how long many
+		partial slabs there are and how long each node's list is.
+
+What:		/sys/kernel/slab/cache/poison
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The poison file specifies whether objects should be poisoned
+		when a new slab is allocated.
+
+What:		/sys/kernel/slab/cache/reclaim_account
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The reclaim_account file specifies whether the cache's objects
+		are reclaimable (and grouped by their mobility).
+
+What:		/sys/kernel/slab/cache/red_zone
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The red_zone file specifies whether the cache's objects are red
+		zoned.
+
+What:		/sys/kernel/slab/cache/remote_node_defrag_ratio
+Date:		January 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file remote_node_defrag_ratio specifies the percentage of
+		times SLUB will attempt to refill the cpu slab with a partial
+		slab from a remote node as opposed to allocating a new slab on
+		the local node.  This reduces the amount of wasted memory over
+		the entire system but can be expensive.
+		Available when CONFIG_NUMA is enabled.
+
+What:		/sys/kernel/slab/cache/sanity_checks
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The sanity_checks file specifies whether expensive checks
+		should be performed on free and, at minimum, enables double free
+		checks.  Caches that enable sanity_checks cannot be merged with
+		caches that do not.
+
+What:		/sys/kernel/slab/cache/shrink
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The shrink file is written when memory should be reclaimed from
+		a cache.  Empty partial slabs are freed and the partial list is
+		sorted so the slabs with the fewest available objects are used
+		first.
+
+What:		/sys/kernel/slab/cache/slab_size
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The slab_size file is read-only and specifies the object size
+		with metadata (debugging information and alignment) in bytes.
+
+What:		/sys/kernel/slab/cache/slabs
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The slabs file is read-only and displays how long many slabs
+		there are (both cpu and partial) and from which nodes they are
+		from.
+
+What:		/sys/kernel/slab/cache/store_user
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The store_user file specifies whether the location of
+		allocation or free should be tracked for a cache.
+
+What:		/sys/kernel/slab/cache/total_objects
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The total_objects file is read-only and displays how many total
+		objects a cache has and from which nodes they are from.
+
+What:		/sys/kernel/slab/cache/trace
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The trace file specifies whether object allocations and frees
+		should be traced.
+
+What:		/sys/kernel/slab/cache/validate
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		Writing to the validate file causes SLUB to traverse all of its
+		cache's objects and check the validity of metadata.
diff --git a/mm/slob.c b/mm/slob.c
index a2d4ab3..f92e66d 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -60,6 +60,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/swap.h> /* struct reclaim_state */
 #include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -255,6 +256,8 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 
 static void slob_free_pages(void *b, int order)
 {
+	if (current->reclaim_state)
+		current->reclaim_state->reclaimed_slab += 1 << order;
 	free_pages((unsigned long)b, order);
 }
 
@@ -407,7 +410,7 @@ static void slob_free(void *block, int size)
 		spin_unlock_irqrestore(&slob_lock, flags);
 		clear_slob_page(sp);
 		free_slob_page(sp);
-		free_page((unsigned long)b);
+		slob_free_pages(b, 0);
 		return;
 	}
 
diff --git a/mm/slub.c b/mm/slub.c
index 7ab54ec..65ffda5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/swap.h> /* struct reclaim_state */
 #include <linux/module.h>
 #include <linux/bit_spinlock.h>
 #include <linux/interrupt.h>
@@ -1170,6 +1171,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
 	__ClearPageSlab(page);
 	reset_page_mapcount(page);
+	if (current->reclaim_state)
+		current->reclaim_state->reclaimed_slab += pages;
 	__free_pages(page, order);
 }
 
@@ -1909,7 +1912,7 @@ static inline int calculate_order(int size)
 	 * Doh this slab cannot be placed using slub_max_order.
 	 */
 	order = slab_order(size, 1, MAX_ORDER, 1);
-	if (order <= MAX_ORDER)
+	if (order < MAX_ORDER)
 		return order;
 	return -ENOSYS;
 }
@@ -2522,6 +2525,7 @@ __setup("slub_min_order=", setup_slub_min_order);
 static int __init setup_slub_max_order(char *str)
 {
 	get_option(&str, &slub_max_order);
+	slub_max_order = min(slub_max_order, MAX_ORDER - 1);
 
 	return 1;
 }