[slubllv4 00/16] SLUB: Lockless freelists for objects V4

[slubllv4 00/16] SLUB: Lockless freelists for objects V4

[Christoph Lameter]

V3->V4	- Diffed against Pekka's slab/next tree plus the ifdef removal patch
		 (which should be in slab/next soon).
	- Numerous cleanups in particular as a result of the removal of the
	  #ifdef CMPXCHG_LOCAL stuff.
	- Smaller cleanups whereever I saw something.

V2->V3
	- Provide statistics
	- Fallback logic to page lock if cmpxchg16b is not available.
	- Better counter support
	- More cleanups and clarifications

Well here is another result of my obsession with SLAB allocators. There must be
some way to get an allocator done that is faster without queueing and I hope
that we are now there (maybe only almost...). Any help with cleaning up the
rough edges would be appreciated.

This patchset implement wider lockless operations in slub affecting most of the
slowpaths. In particular the patch decreases the overhead in the performance
critical section of __slab_free.

One test that I ran was "hackbench 200 process 200" on 2.6.29-rc3 under KVM

Run	SLAB	SLUB	SLUB LL
1st	35.2	35.9	31.9
2nd	34.6	30.8	27.9
3rd	33.8	29.9	28.8

Note that the SLUB version in 2.6.29-rc1 already has an optimized allocation
and free path using this_cpu_cmpxchg_double(). SLUB LL takes it to new heights
by also using cmpxchg_double() in the slowpaths (especially in the kfree()
case where we frequently cannot use the fastpath because there is no queue).

The patch uses a cmpxchg_double (also introduced here) to do an atomic change
on the state of a slab page that includes the following pieces of information:

1. Freelist pointer
2. Number of objects inuse
3. Frozen state of a slab

Disabling of interrupts (which is a significant latency in the
allocator paths) is avoided in the __slab_free case.

There are some concerns with this patch. The use of cmpxchg_double on
fields of the page struct requires alignment of the fields to double
word boundaries. That can only be accomplished by adding some padding
to struct page which blows it up to 64 byte (on x86_64). Comments
in the source describe these things in more detail.

The cmpxchg_double() operation introduced here could also be used to
update other doublewords in the page struct in a lockless fashion. One
can envision page state changes that involved flags and mappings or
maybe do list operations locklessly (but with the current scheme we
would need to update two other words elsewhere at the same time too,
so another scheme would be needed).

[slubllv4 01/16] slub: Per object NUMA support

[Christoph Lameter]

[-- Attachment #1: rr_slabs --]
[-- Type: text/plain, Size: 1549 bytes --]

Currently slub applies NUMA policies per allocated slab page. Change
that to apply memory policies for each individual object allocated.

F.e. before this patch MPOL_INTERLEAVE would return objects from the
same slab page until a new slab page was allocated. Now an object
from a different page is taken for each allocation.

This increases the overhead of the fastpath under NUMA.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |   17 +++++++++++++++++
 1 file changed, 17 insertions(+)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-05 15:21:51.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-05 15:28:33.000000000 -0500
@@ -1873,6 +1873,21 @@ debug:
 	goto unlock_out;
 }
 
+static __always_inline int alternate_slab_node(struct kmem_cache *s,
+						gfp_t flags, int node)
+{
+#ifdef CONFIG_NUMA
+	if (unlikely(node == NUMA_NO_NODE &&
+			!(flags & __GFP_THISNODE) &&
+			!in_interrupt())) {
+		if ((s->flags & SLAB_MEM_SPREAD) && cpuset_do_slab_mem_spread())
+			node = cpuset_slab_spread_node();
+		else if (current->mempolicy)
+		node = slab_node(current->mempolicy);
+	}
+#endif
+	return node;
+}
 /*
  * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
  * have the fastpath folded into their functions. So no function call
@@ -1893,6 +1908,8 @@ static __always_inline void *slab_alloc(
 	if (slab_pre_alloc_hook(s, gfpflags))
 		return NULL;
 
+	node = alternate_slab_node(s, gfpflags, node);
+
 redo:
 
 	/*

[slubllv4 02/16] slub: Do not use frozen page flag but a bit in the page counters

[Christoph Lameter]

[-- Attachment #1: frozen_field --]
[-- Type: text/plain, Size: 3218 bytes --]

Do not use a page flag for the frozen bit. It needs to be part
of the state that is handled with cmpxchg_double(). So use a bit
in the counter struct in the page struct for that purpose.

Also all page start out as frozen pages so set the bit
when the page is allocated.

Signed-off-by: Christoph Lameter <cl@linux.com>


---
 include/linux/mm_types.h   |    5 +++--
 include/linux/page-flags.h |    2 --
 mm/slub.c                  |   12 ++++++------
 3 files changed, 9 insertions(+), 10 deletions(-)

Index: linux-2.6/include/linux/mm_types.h
===================================================================
--- linux-2.6.orig/include/linux/mm_types.h	2011-05-03 08:48:24.000000000 -0500
+++ linux-2.6/include/linux/mm_types.h	2011-05-05 15:28:45.000000000 -0500
@@ -41,8 +41,9 @@ struct page {
 					 * & limit reverse map searches.
 					 */
 		struct {		/* SLUB */
-			u16 inuse;
-			u16 objects;
+			unsigned inuse:16;
+			unsigned objects:15;
+			unsigned frozen:1;
 		};
 	};
 	union {
Index: linux-2.6/include/linux/page-flags.h
===================================================================
--- linux-2.6.orig/include/linux/page-flags.h	2011-05-03 08:48:24.000000000 -0500
+++ linux-2.6/include/linux/page-flags.h	2011-05-05 15:28:45.000000000 -0500
@@ -212,8 +212,6 @@ PAGEFLAG(SwapBacked, swapbacked) __CLEAR
 
 __PAGEFLAG(SlobFree, slob_free)
 
-__PAGEFLAG(SlubFrozen, slub_frozen)
-
 /*
  * Private page markings that may be used by the filesystem that owns the page
  * for its own purposes.
Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-05 15:28:33.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-05 15:28:45.000000000 -0500
@@ -166,7 +166,7 @@ static inline int kmem_cache_debug(struc
 
 #define OO_SHIFT	16
 #define OO_MASK		((1 << OO_SHIFT) - 1)
-#define MAX_OBJS_PER_PAGE	65535 /* since page.objects is u16 */
+#define MAX_OBJS_PER_PAGE	32767 /* since page.objects is u15 */
 
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000UL /* Poison object */
@@ -1013,7 +1013,7 @@ static noinline int free_debug_processin
 	}
 
 	/* Special debug activities for freeing objects */
-	if (!PageSlubFrozen(page) && !page->freelist)
+	if (!page->frozen && !page->freelist)
 		remove_full(s, page);
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_FREE, addr);
@@ -1402,7 +1402,7 @@ static inline int lock_and_freeze_slab(s
 {
 	if (slab_trylock(page)) {
 		__remove_partial(n, page);
-		__SetPageSlubFrozen(page);
+		page->frozen = 1;
 		return 1;
 	}
 	return 0;
@@ -1516,7 +1516,7 @@ static void unfreeze_slab(struct kmem_ca
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 
-	__ClearPageSlubFrozen(page);
+	page->frozen = 0;
 	if (page->inuse) {
 
 		if (page->freelist) {
@@ -1855,7 +1855,7 @@ load_from_page:
 			flush_slab(s, c);
 
 		slab_lock(page);
-		__SetPageSlubFrozen(page);
+		page->frozen = 1;
 
 		goto load_from_page;
 	}
@@ -2048,7 +2048,7 @@ static void __slab_free(struct kmem_cach
 	page->freelist = object;
 	page->inuse--;
 
-	if (unlikely(PageSlubFrozen(page))) {
+	if (unlikely(page->frozen)) {
 		stat(s, FREE_FROZEN);
 		goto out_unlock;
 	}

[slubllv4 03/16] slub: Move page->frozen handling near where the page->freelist handling occurs

[Christoph Lameter]

[-- Attachment #1: frozen_move --]
[-- Type: text/plain, Size: 2006 bytes --]

This is necessary because the frozen bit has to be handled in the same cmpxchg_double
with the freelist and the counters.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-05 15:28:45.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-05 15:29:17.000000000 -0500
@@ -1264,6 +1264,7 @@ static struct page *new_slab(struct kmem
 
 	page->freelist = start;
 	page->inuse = 0;
+	page->frozen = 1;
 out:
 	return page;
 }
@@ -1402,7 +1403,6 @@ static inline int lock_and_freeze_slab(s
 {
 	if (slab_trylock(page)) {
 		__remove_partial(n, page);
-		page->frozen = 1;
 		return 1;
 	}
 	return 0;
@@ -1516,7 +1516,6 @@ static void unfreeze_slab(struct kmem_ca
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 
-	page->frozen = 0;
 	if (page->inuse) {
 
 		if (page->freelist) {
@@ -1649,6 +1648,7 @@ static void deactivate_slab(struct kmem_
 	}
 	c->page = NULL;
 	c->tid = next_tid(c->tid);
+	page->frozen = 0;
 	unfreeze_slab(s, page, tail);
 }
 
@@ -1809,6 +1809,8 @@ static void *__slab_alloc(struct kmem_ca
 	stat(s, ALLOC_REFILL);
 
 load_freelist:
+	VM_BUG_ON(!page->frozen);
+
 	object = page->freelist;
 	if (unlikely(!object))
 		goto another_slab;
@@ -1833,6 +1835,7 @@ new_slab:
 	page = get_partial(s, gfpflags, node);
 	if (page) {
 		stat(s, ALLOC_FROM_PARTIAL);
+		page->frozen = 1;
 load_from_page:
 		c->node = page_to_nid(page);
 		c->page = page;
@@ -1855,7 +1858,6 @@ load_from_page:
 			flush_slab(s, c);
 
 		slab_lock(page);
-		page->frozen = 1;
 
 		goto load_from_page;
 	}
@@ -2375,6 +2377,7 @@ static void early_kmem_cache_node_alloc(
 	BUG_ON(!n);
 	page->freelist = get_freepointer(kmem_cache_node, n);
 	page->inuse++;
+	page->frozen = 0;
 	kmem_cache_node->node[node] = n;
 #ifdef CONFIG_SLUB_DEBUG
 	init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);

[slubllv4 04/16] x86: Add support for cmpxchg_double

[Christoph Lameter]

[-- Attachment #1: cmpxchg_double_x86 --]
[-- Type: text/plain, Size: 5711 bytes --]

A simple implementation that only supports the word size and does not
have a fallback mode (would require a spinlock).

And 32 and 64 bit support for cmpxchg_double. cmpxchg double uses
the cmpxchg8b or cmpxchg16b instruction on x86 processors to compare
and swap 2 machine words. This allows lockless algorithms to move more
context information through critical sections.

Set a flag CONFIG_CMPXCHG_DOUBLE to signal the support of that feature
during kernel builds.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 arch/x86/Kconfig.cpu              |    3 ++
 arch/x86/include/asm/cmpxchg_32.h |   46 ++++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/cmpxchg_64.h |   45 +++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/cpufeature.h |    1 
 4 files changed, 95 insertions(+)

Index: linux-2.6/arch/x86/include/asm/cmpxchg_64.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/cmpxchg_64.h	2011-04-13 15:19:53.000000000 -0500
+++ linux-2.6/arch/x86/include/asm/cmpxchg_64.h	2011-04-15 13:14:45.000000000 -0500
@@ -151,4 +151,49 @@ extern void __cmpxchg_wrong_size(void);
 	cmpxchg_local((ptr), (o), (n));					\
 })
 
+#define cmpxchg16b(ptr, o1, o2, n1, n2)				\
+({								\
+	char __ret;						\
+	__typeof__(o2) __junk;					\
+	__typeof__(*(ptr)) __old1 = (o1);			\
+	__typeof__(o2) __old2 = (o2);				\
+	__typeof__(*(ptr)) __new1 = (n1);			\
+	__typeof__(o2) __new2 = (n2);				\
+	asm volatile(LOCK_PREFIX_HERE "lock; cmpxchg16b (%%rsi);setz %1" \
+		       : "=d"(__junk), "=a"(__ret)		\
+		       : "S"(ptr), "b"(__new1),	"c"(__new2),	\
+		         "a"(__old1), "d"(__old2));		\
+	__ret; })
+
+
+#define cmpxchg16b_local(ptr, o1, o2, n1, n2)			\
+({								\
+	char __ret;						\
+	__typeof__(o2) __junk;					\
+	__typeof__(*(ptr)) __old1 = (o1);			\
+	__typeof__(o2) __old2 = (o2);				\
+	__typeof__(*(ptr)) __new1 = (n1);			\
+	__typeof__(o2) __new2 = (n2);				\
+	asm volatile("cmpxchg16b (%%rsi)\n\t\tsetz %1\n\t"	\
+		       : "=d"(__junk)_, "=a"(__ret)		\
+		       : "S"((ptr)), "b"(__new1), "c"(__new2),	\
+ 		         "a"(__old1), "d"(__old2));		\
+	__ret; })
+
+#define cmpxchg_double(ptr, o1, o2, n1, n2)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	VM_BUG_ON((unsigned long)(ptr) % 16);				\
+	cmpxchg16b((ptr), (o1), (o2), (n1), (n2));			\
+})
+
+#define cmpxchg_double_local(ptr, o1, o2, n1, n2)			\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	VM_BUG_ON((unsigned long)(ptr) % 16);				\
+	cmpxchg16b_local((ptr), (o1), (o2), (n1), (n2));		\
+})
+
+#define system_has_cmpxchg_double() cpu_has_cx16
+
 #endif /* _ASM_X86_CMPXCHG_64_H */
Index: linux-2.6/arch/x86/include/asm/cmpxchg_32.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/cmpxchg_32.h	2011-04-13 15:19:53.000000000 -0500
+++ linux-2.6/arch/x86/include/asm/cmpxchg_32.h	2011-04-15 13:14:45.000000000 -0500
@@ -280,4 +280,50 @@ static inline unsigned long cmpxchg_386(
 
 #endif
 
+#define cmpxchg8b(ptr, o1, o2, n1, n2)				\
+({								\
+	char __ret;						\
+	__typeof__(o2) __dummy;					\
+	__typeof__(*(ptr)) __old1 = (o1);			\
+	__typeof__(o2) __old2 = (o2);				\
+	__typeof__(*(ptr)) __new1 = (n1);			\
+	__typeof__(o2) __new2 = (n2);				\
+	asm volatile(LOCK_PREFIX_HERE "lock; cmpxchg8b (%%esi); setz %1"\
+		       : "d="(__dummy), "=a" (__ret) 		\
+		       : "S" ((ptr)), "a" (__old1), "d"(__old2),	\
+		         "b" (__new1), "c" (__new2)		\
+		       : "memory");				\
+	__ret; })
+
+
+#define cmpxchg8b_local(ptr, o1, o2, n1, n2)			\
+({								\
+	char __ret;						\
+	__typeof__(o2) __dummy;					\
+	__typeof__(*(ptr)) __old1 = (o1);			\
+	__typeof__(o2) __old2 = (o2);				\
+	__typeof__(*(ptr)) __new1 = (n1);			\
+	__typeof__(o2) __new2 = (n2);				\
+	asm volatile("cmpxchg8b (%%esi); tsetz %1"		\
+		       : "d="(__dummy), "=a"(__ret)		\
+		       : "S" ((ptr)), "a" (__old), "d"(__old2),	\
+		         "b" (__new1), "c" (__new2),		\
+		       : "memory");				\
+	__ret; })
+
+
+#define cmpxchg_double(ptr, o1, o2, n1, n2)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
+	VM_BUG_ON((unsigned long)(ptr) % 8);				\
+	cmpxchg8b((ptr), (o1), (o2), (n1), (n2));			\
+})
+
+#define cmpxchg_double_local(ptr, o1, o2, n1, n2)			\
+({									\
+       BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
+       VM_BUG_ON((unsigned long)(ptr) % 8);				\
+       cmpxchg16b_local((ptr), (o1), (o2), (n1), (n2));			\
+})
+
 #endif /* _ASM_X86_CMPXCHG_32_H */
Index: linux-2.6/arch/x86/Kconfig.cpu
===================================================================
--- linux-2.6.orig/arch/x86/Kconfig.cpu	2011-04-13 15:19:53.000000000 -0500
+++ linux-2.6/arch/x86/Kconfig.cpu	2011-04-15 13:14:45.000000000 -0500
@@ -308,6 +308,9 @@ config X86_CMPXCHG
 config CMPXCHG_LOCAL
 	def_bool X86_64 || (X86_32 && !M386)
 
+config CMPXCHG_DOUBLE
+	def_bool X86_64 || (X86_32 && !M386)
+
 config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || MPSC
Index: linux-2.6/arch/x86/include/asm/cpufeature.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/cpufeature.h	2011-04-15 12:51:51.000000000 -0500
+++ linux-2.6/arch/x86/include/asm/cpufeature.h	2011-04-15 13:14:45.000000000 -0500
@@ -286,6 +286,7 @@ extern const char * const x86_power_flag
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 #define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
+#define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1

[slubllv4 05/16] mm: Rearrange struct page

[Christoph Lameter]

[-- Attachment #1: resort_struct_page --]
[-- Type: text/plain, Size: 4982 bytes --]

We need to be able to use cmpxchg_double on the freelist and object count
field in struct page. Rearrange the fields in struct page according to
doubleword entities so that the freelist pointer comes before the counters.
Do the rearranging with a future in mind where we use more doubleword
atomics to avoid locking of updates to flags/mapping or lru pointers.

Create another union to allow access to counters in struct page as a
single unsigned long value.

The doublewords must be properly aligned for cmpxchg_double to work.
Sadly this increases the size of page struct by one word on some architectures.
But as a resultpage structs are now cacheline aligned on x86_64.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 include/linux/mm_types.h |   89 +++++++++++++++++++++++++++++++----------------
 1 file changed, 60 insertions(+), 29 deletions(-)

Index: linux-2.6/include/linux/mm_types.h
===================================================================
--- linux-2.6.orig/include/linux/mm_types.h	2011-05-06 12:03:46.000000000 -0500
+++ linux-2.6/include/linux/mm_types.h	2011-05-06 12:50:40.000000000 -0500
@@ -30,52 +30,74 @@ struct address_space;
  * moment. Note that we have no way to track which tasks are using
  * a page, though if it is a pagecache page, rmap structures can tell us
  * who is mapping it.
+ *
+ * The objects in struct page are organized in double word blocks in
+ * order to allows us to use atomic double word operations on portions
+ * of struct page. That is currently only used by slub but the arrangement
+ * allows the use of atomic double word operations on the flags/mapping
+ * and lru list pointers also.
  */
 struct page {
+	/* First double word block */
 	unsigned long flags;		/* Atomic flags, some possibly
 					 * updated asynchronously */
-	atomic_t _count;		/* Usage count, see below. */
+	struct address_space *mapping;	/* If low bit clear, points to
+					 * inode address_space, or NULL.
+					 * If page mapped as anonymous
+					 * memory, low bit is set, and
+					 * it points to anon_vma object:
+					 * see PAGE_MAPPING_ANON below.
+					 */
+	/* Second double word */
 	union {
-		atomic_t _mapcount;	/* Count of ptes mapped in mms,
-					 * to show when page is mapped
-					 * & limit reverse map searches.
+		struct {
+			pgoff_t index;		/* Our offset within mapping. */
+			atomic_t _mapcount;	/* Count of ptes mapped in mms,
+							 * to show when page is mapped
+							 * & limit reverse map searches.
+							 */
+			atomic_t _count;		/* Usage count, see below. */
+		};
+
+		struct {			/* SLUB cmpxchg_double area */
+			void *freelist;
+			union {
+				unsigned long counters;
+				struct {
+					unsigned inuse:16;
+					unsigned objects:15;
+					unsigned frozen:1;
+					/*
+					 * Kernel may make use of this field even when slub
+					 * uses the rest of the double word!
 					 */
-		struct {		/* SLUB */
-			unsigned inuse:16;
-			unsigned objects:15;
-			unsigned frozen:1;
+					atomic_t _count;
+				};
+			};
 		};
 	};
+
+	/* Third double word block */
+	struct list_head lru;		/* Pageout list, eg. active_list
+					 * protected by zone->lru_lock !
+					 */
+
+	/* Remainder is not double word aligned */
 	union {
-	    struct {
-		unsigned long private;		/* Mapping-private opaque data:
+	 	unsigned long private;		/* Mapping-private opaque data:
 					 	 * usually used for buffer_heads
 						 * if PagePrivate set; used for
 						 * swp_entry_t if PageSwapCache;
 						 * indicates order in the buddy
 						 * system if PG_buddy is set.
 						 */
-		struct address_space *mapping;	/* If low bit clear, points to
-						 * inode address_space, or NULL.
-						 * If page mapped as anonymous
-						 * memory, low bit is set, and
-						 * it points to anon_vma object:
-						 * see PAGE_MAPPING_ANON below.
-						 */
-	    };
 #if USE_SPLIT_PTLOCKS
-	    spinlock_t ptl;
+		spinlock_t ptl;
 #endif
-	    struct kmem_cache *slab;	/* SLUB: Pointer to slab */
-	    struct page *first_page;	/* Compound tail pages */
+		struct kmem_cache *slab;	/* SLUB: Pointer to slab */
+		struct page *first_page;	/* Compound tail pages */
 	};
-	union {
-		pgoff_t index;		/* Our offset within mapping. */
-		void *freelist;		/* SLUB: freelist req. slab lock */
-	};
-	struct list_head lru;		/* Pageout list, eg. active_list
-					 * protected by zone->lru_lock !
-					 */
+
 	/*
 	 * On machines where all RAM is mapped into kernel address space,
 	 * we can simply calculate the virtual address. On machines with
@@ -101,7 +123,16 @@ struct page {
 	 */
 	void *shadow;
 #endif
-};
+}
+/*
+ * If another subsystem starts using the double word pairing for atomic
+ * operations on struct page then it must change the #if to ensure
+ * proper alignment of the page struct.
+ */
+#if defined(CONFIG_SLUB) && defined(CONFIG_CMPXCHG_LOCAL)
+	__attribute__((__aligned__(2*sizeof(unsigned long))))
+#endif
+;
 
 /*
  * A region containing a mapping of a non-memory backed file under NOMMU

[slubllv4 06/16] slub: Add cmpxchg_double_slab()

[Christoph Lameter]

[-- Attachment #1: cmpxchg_double_slab --]
[-- Type: text/plain, Size: 3794 bytes --]

Add a function that operates on the second doubleword in the page struct
and manipulates the object counters, the freelist and the frozen attribute.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 include/linux/slub_def.h |    1 +
 mm/slub.c                |   45 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-04-15 13:14:40.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-04-15 13:14:51.000000000 -0500
@@ -131,6 +131,9 @@ static inline int kmem_cache_debug(struc
 /* Enable to test recovery from slab corruption on boot */
 #undef SLUB_RESILIENCY_TEST
 
+/* Enable to log cmpxchg failures */
+#undef SLUB_DEBUG_CMPXCHG
+
 /*
  * Mininum number of partial slabs. These will be left on the partial
  * lists even if they are empty. kmem_cache_shrink may reclaim them.
@@ -170,6 +173,7 @@ static inline int kmem_cache_debug(struc
 
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000UL /* Poison object */
+#define __CMPXCHG_DOUBLE	0x40000000UL /* Use cmpxchg_double */
 
 static int kmem_size = sizeof(struct kmem_cache);
 
@@ -326,6 +330,37 @@ static inline int oo_objects(struct kmem
 	return x.x & OO_MASK;
 }
 
+static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
+		void *freelist_old, unsigned long counters_old,
+		void *freelist_new, unsigned long counters_new,
+		const char *n)
+{
+#ifdef CONFIG_CMPXCHG_DOUBLE
+	if (s->flags & __CMPXCHG_DOUBLE) {
+		if (cmpxchg_double(&page->freelist,
+			freelist_old, counters_old,
+			freelist_new, counters_new))
+		return 1;
+	} else
+#endif
+	{
+		if (page->freelist == freelist_old && page->counters == counters_old) {
+			page->freelist = freelist_new;
+			page->counters = counters_new;
+			return 1;
+		}
+	}
+
+	cpu_relax();
+	stat(s, CMPXCHG_DOUBLE_FAIL);
+
+#ifdef SLUB_DEBUG_CMPXCHG
+	printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name);
+#endif
+
+	return 0;
+}
+
 /*
  * Determine a map of object in use on a page.
  *
@@ -2654,6 +2689,12 @@ static int kmem_cache_open(struct kmem_c
 		}
 	}
 
+#ifdef CONFIG_CMPXCHG_DOUBLE
+	if (system_has_cmpxchg_double() && (s->flags & SLAB_DEBUG_FLAGS) == 0)
+		/* Enable fast mode */
+		s->flags |= __CMPXCHG_DOUBLE;
+#endif
+
 	/*
 	 * The larger the object size is, the more pages we want on the partial
 	 * list to avoid pounding the page allocator excessively.
@@ -4551,6 +4592,8 @@ STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate
 STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail);
 STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees);
 STAT_ATTR(ORDER_FALLBACK, order_fallback);
+STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail);
+STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -4608,6 +4651,8 @@ static struct attribute *slab_attrs[] =
 	&deactivate_to_tail_attr.attr,
 	&deactivate_remote_frees_attr.attr,
 	&order_fallback_attr.attr,
+	&cmpxchg_double_fail_attr.attr,
+	&cmpxchg_double_cpu_fail_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,
Index: linux-2.6/include/linux/slub_def.h
===================================================================
--- linux-2.6.orig/include/linux/slub_def.h	2011-04-13 15:19:53.000000000 -0500
+++ linux-2.6/include/linux/slub_def.h	2011-04-15 13:14:51.000000000 -0500
@@ -33,6 +33,7 @@ enum stat_item {
 	DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
 	ORDER_FALLBACK,		/* Number of times fallback was necessary */
 	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
+	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {

[slubllv4 07/16] slub: explicit list_lock taking

[Christoph Lameter]

[-- Attachment #1: unlock_list_ops --]
[-- Type: text/plain, Size: 6092 bytes --]

The allocator fastpath rework does change the usage of the list_lock.
Remove the list_lock processing from the functions that hide them from the
critical sections and move them into those critical sections.

This in turn simplifies the support functions (no __ variant needed anymore)
and simplifies the lock handling on bootstrap.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |   74 ++++++++++++++++++++++++++++++--------------------------------
 1 file changed, 36 insertions(+), 38 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 12:50:43.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 12:50:48.000000000 -0500
@@ -905,25 +905,21 @@ static inline void slab_free_hook(struct
 /*
  * Tracking of fully allocated slabs for debugging purposes.
  */
-static void add_full(struct kmem_cache_node *n, struct page *page)
+static void add_full(struct kmem_cache *s,
+	struct kmem_cache_node *n, struct page *page)
 {
-	spin_lock(&n->list_lock);
+	if (!(s->flags & SLAB_STORE_USER))
+		return;
+
 	list_add(&page->lru, &n->full);
-	spin_unlock(&n->list_lock);
 }
 
 static void remove_full(struct kmem_cache *s, struct page *page)
 {
-	struct kmem_cache_node *n;
-
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
-	n = get_node(s, page_to_nid(page));
-
-	spin_lock(&n->list_lock);
 	list_del(&page->lru);
-	spin_unlock(&n->list_lock);
 }
 
 /* Tracking of the number of slabs for debugging purposes */
@@ -1048,8 +1044,13 @@ static noinline int free_debug_processin
 	}
 
 	/* Special debug activities for freeing objects */
-	if (!page->frozen && !page->freelist)
+	if (!page->frozen && !page->freelist) {
+		struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+
+		spin_lock(&n->list_lock);
 		remove_full(s, page);
+		spin_unlock(&n->list_lock);
+	}
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_FREE, addr);
 	trace(s, page, object, 0);
@@ -1400,36 +1401,26 @@ static __always_inline int slab_trylock(
 /*
  * Management of partially allocated slabs
  */
-static void add_partial(struct kmem_cache_node *n,
+static inline void add_partial(struct kmem_cache_node *n,
 				struct page *page, int tail)
 {
-	spin_lock(&n->list_lock);
 	n->nr_partial++;
 	if (tail)
 		list_add_tail(&page->lru, &n->partial);
 	else
 		list_add(&page->lru, &n->partial);
-	spin_unlock(&n->list_lock);
 }
 
-static inline void __remove_partial(struct kmem_cache_node *n,
+static inline void remove_partial(struct kmem_cache_node *n,
 					struct page *page)
 {
 	list_del(&page->lru);
 	n->nr_partial--;
 }
 
-static void remove_partial(struct kmem_cache *s, struct page *page)
-{
-	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
-	spin_lock(&n->list_lock);
-	__remove_partial(n, page);
-	spin_unlock(&n->list_lock);
-}
-
 /*
- * Lock slab and remove from the partial list.
+ * Lock slab, remove from the partial list and put the object into the
+ * per cpu freelist.
  *
  * Must hold list_lock.
  */
@@ -1437,7 +1428,7 @@ static inline int lock_and_freeze_slab(s
 							struct page *page)
 {
 	if (slab_trylock(page)) {
-		__remove_partial(n, page);
+		remove_partial(n, page);
 		return 1;
 	}
 	return 0;
@@ -1554,12 +1545,17 @@ static void unfreeze_slab(struct kmem_ca
 	if (page->inuse) {
 
 		if (page->freelist) {
+			spin_lock(&n->list_lock);
 			add_partial(n, page, tail);
+			spin_unlock(&n->list_lock);
 			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
 		} else {
 			stat(s, DEACTIVATE_FULL);
-			if (kmem_cache_debug(s) && (s->flags & SLAB_STORE_USER))
-				add_full(n, page);
+			if (kmem_cache_debug(s) && (s->flags & SLAB_STORE_USER)) {
+				spin_lock(&n->list_lock);
+				add_full(s, n, page);
+				spin_unlock(&n->list_lock);
+			}
 		}
 		slab_unlock(page);
 	} else {
@@ -1575,7 +1571,9 @@ static void unfreeze_slab(struct kmem_ca
 			 * kmem_cache_shrink can reclaim any empty slabs from
 			 * the partial list.
 			 */
+			spin_lock(&n->list_lock);
 			add_partial(n, page, 1);
+			spin_unlock(&n->list_lock);
 			slab_unlock(page);
 		} else {
 			slab_unlock(page);
@@ -2098,7 +2096,11 @@ static void __slab_free(struct kmem_cach
 	 * then add it.
 	 */
 	if (unlikely(!prior)) {
+		struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+
+		spin_lock(&n->list_lock);
 		add_partial(get_node(s, page_to_nid(page)), page, 1);
+		spin_unlock(&n->list_lock);
 		stat(s, FREE_ADD_PARTIAL);
 	}
 
@@ -2112,7 +2114,11 @@ slab_empty:
 		/*
 		 * Slab still on the partial list.
 		 */
-		remove_partial(s, page);
+		struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+
+		spin_lock(&n->list_lock);
+		remove_partial(n, page);
+		spin_unlock(&n->list_lock);
 		stat(s, FREE_REMOVE_PARTIAL);
 	}
 	slab_unlock(page);
@@ -2394,7 +2400,6 @@ static void early_kmem_cache_node_alloc(
 {
 	struct page *page;
 	struct kmem_cache_node *n;
-	unsigned long flags;
 
 	BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
 
@@ -2421,14 +2426,7 @@ static void early_kmem_cache_node_alloc(
 	init_kmem_cache_node(n, kmem_cache_node);
 	inc_slabs_node(kmem_cache_node, node, page->objects);
 
-	/*
-	 * lockdep requires consistent irq usage for each lock
-	 * so even though there cannot be a race this early in
-	 * the boot sequence, we still disable irqs.
-	 */
-	local_irq_save(flags);
 	add_partial(n, page, 0);
-	local_irq_restore(flags);
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -2712,7 +2710,7 @@ static void free_partial(struct kmem_cac
 	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			__remove_partial(n, page);
+			remove_partial(n, page);
 			discard_slab(s, page);
 		} else {
 			list_slab_objects(s, page,
@@ -3050,7 +3048,7 @@ int kmem_cache_shrink(struct kmem_cache
 				 * may have freed the last object and be
 				 * waiting to release the slab.
 				 */
-				__remove_partial(n, page);
+				remove_partial(n, page);
 				slab_unlock(page);
 				discard_slab(s, page);
 			} else {

[slubllv4 08/16] slub: Pass kmem_cache struct to lock and freeze slab

[Christoph Lameter]

[-- Attachment #1: pass_kmem_cache_to_lock_and_freeze --]
[-- Type: text/plain, Size: 1957 bytes --]

We need more information about the slab for the cmpxchg implementation.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |   13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-04-28 15:53:45.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-04-28 15:53:50.000000000 -0500
@@ -1424,8 +1424,8 @@ static inline void remove_partial(struct
  *
  * Must hold list_lock.
  */
-static inline int lock_and_freeze_slab(struct kmem_cache_node *n,
-							struct page *page)
+static inline int lock_and_freeze_slab(struct kmem_cache *s,
+		struct kmem_cache_node *n, struct page *page)
 {
 	if (slab_trylock(page)) {
 		remove_partial(n, page);
@@ -1437,7 +1437,8 @@ static inline int lock_and_freeze_slab(s
 /*
  * Try to allocate a partial slab from a specific node.
  */
-static struct page *get_partial_node(struct kmem_cache_node *n)
+static struct page *get_partial_node(struct kmem_cache *s,
+					struct kmem_cache_node *n)
 {
 	struct page *page;
 
@@ -1452,7 +1453,7 @@ static struct page *get_partial_node(str
 
 	spin_lock(&n->list_lock);
 	list_for_each_entry(page, &n->partial, lru)
-		if (lock_and_freeze_slab(n, page))
+		if (lock_and_freeze_slab(s, n, page))
 			goto out;
 	page = NULL;
 out:
@@ -1503,7 +1504,7 @@ static struct page *get_any_partial(stru
 
 		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
 				n->nr_partial > s->min_partial) {
-			page = get_partial_node(n);
+			page = get_partial_node(s, n);
 			if (page) {
 				put_mems_allowed();
 				return page;
@@ -1523,7 +1524,7 @@ static struct page *get_partial(struct k
 	struct page *page;
 	int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
 
-	page = get_partial_node(get_node(s, searchnode));
+	page = get_partial_node(s, get_node(s, searchnode));
 	if (page || node != NUMA_NO_NODE)
 		return page;
 

[slubllv4 09/16] slub: Rework allocator fastpaths

[Christoph Lameter]

[-- Attachment #1: rework_fastpaths --]
[-- Type: text/plain, Size: 13734 bytes --]

Rework the allocation paths so that updates of the page freelist, frozen state
and number of objects use cmpxchg_double_slab().

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |  414 ++++++++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 285 insertions(+), 129 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 12:51:33.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 12:54:02.000000000 -0500
@@ -975,11 +975,6 @@ static noinline int alloc_debug_processi
 	if (!check_slab(s, page))
 		goto bad;
 
-	if (!on_freelist(s, page, object)) {
-		object_err(s, page, object, "Object already allocated");
-		goto bad;
-	}
-
 	if (!check_valid_pointer(s, page, object)) {
 		object_err(s, page, object, "Freelist Pointer check fails");
 		goto bad;
@@ -1043,14 +1038,6 @@ static noinline int free_debug_processin
 		goto fail;
 	}
 
-	/* Special debug activities for freeing objects */
-	if (!page->frozen && !page->freelist) {
-		struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
-		spin_lock(&n->list_lock);
-		remove_full(s, page);
-		spin_unlock(&n->list_lock);
-	}
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_FREE, addr);
 	trace(s, page, object, 0);
@@ -1427,11 +1414,52 @@ static inline void remove_partial(struct
 static inline int lock_and_freeze_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page)
 {
-	if (slab_trylock(page)) {
-		remove_partial(n, page);
+	void *freelist;
+	unsigned long counters;
+	struct page new;
+
+
+	if (!slab_trylock(page))
+		return 0;
+
+	/*
+	 * Zap the freelist and set the frozen bit.
+	 * The old freelist is the list of objects for the
+	 * per cpu allocation list.
+	 */
+	do {
+		freelist = page->freelist;
+		counters = page->counters;
+		new.counters = counters;
+		new.inuse = page->objects;
+
+		VM_BUG_ON(new.frozen);
+		new.frozen = 1;
+
+	} while (!cmpxchg_double_slab(s, page,
+			freelist, counters,
+			NULL, new.counters,
+			"lock and freeze"));
+
+	remove_partial(n, page);
+
+	if (freelist) {
+		/* Populate the per cpu freelist */
+		this_cpu_write(s->cpu_slab->freelist, freelist);
+		this_cpu_write(s->cpu_slab->page, page);
+		this_cpu_write(s->cpu_slab->node, page_to_nid(page));
 		return 1;
+	} else {
+		/*
+		 * Slab page came from the wrong list. No object to allocate
+		 * from. Put it onto the correct list and continue partial
+		 * scan.
+		 */
+		printk(KERN_ERR "SLUB: %s : Page without available objects on"
+			" partial list\n", s->name);
+		slab_unlock(page);
+		return 0;
 	}
-	return 0;
 }
 
 /*
@@ -1531,59 +1559,6 @@ static struct page *get_partial(struct k
 	return get_any_partial(s, flags);
 }
 
-/*
- * Move a page back to the lists.
- *
- * Must be called with the slab lock held.
- *
- * On exit the slab lock will have been dropped.
- */
-static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
-	__releases(bitlock)
-{
-	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
-	if (page->inuse) {
-
-		if (page->freelist) {
-			spin_lock(&n->list_lock);
-			add_partial(n, page, tail);
-			spin_unlock(&n->list_lock);
-			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
-		} else {
-			stat(s, DEACTIVATE_FULL);
-			if (kmem_cache_debug(s) && (s->flags & SLAB_STORE_USER)) {
-				spin_lock(&n->list_lock);
-				add_full(s, n, page);
-				spin_unlock(&n->list_lock);
-			}
-		}
-		slab_unlock(page);
-	} else {
-		stat(s, DEACTIVATE_EMPTY);
-		if (n->nr_partial < s->min_partial) {
-			/*
-			 * Adding an empty slab to the partial slabs in order
-			 * to avoid page allocator overhead. This slab needs
-			 * to come after the other slabs with objects in
-			 * so that the others get filled first. That way the
-			 * size of the partial list stays small.
-			 *
-			 * kmem_cache_shrink can reclaim any empty slabs from
-			 * the partial list.
-			 */
-			spin_lock(&n->list_lock);
-			add_partial(n, page, 1);
-			spin_unlock(&n->list_lock);
-			slab_unlock(page);
-		} else {
-			slab_unlock(page);
-			stat(s, FREE_SLAB);
-			discard_slab(s, page);
-		}
-	}
-}
-
 #ifdef CONFIG_PREEMPT
 /*
  * Calculate the next globally unique transaction for disambiguiation
@@ -1653,37 +1628,157 @@ void init_kmem_cache_cpus(struct kmem_ca
 /*
  * Remove the cpu slab
  */
+
+/*
+ * Remove the cpu slab
+ */
 static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
-	__releases(bitlock)
 {
+	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
 	struct page *page = c->page;
-	int tail = 1;
+	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+	int lock = 0;
+	enum slab_modes l = M_NONE, m = M_NONE;
+	void *freelist;
+	void *nextfree;
+	int tail = 0;
+	struct page new;
+	struct page old;
 
-	if (page->freelist)
+	if (page->freelist) {
 		stat(s, DEACTIVATE_REMOTE_FREES);
+		tail = 1;
+	}
+
+	c->tid = next_tid(c->tid);
+	c->page = NULL;
+	freelist = c->freelist;
+	c->freelist = NULL;
+
 	/*
-	 * Merge cpu freelist into slab freelist. Typically we get here
-	 * because both freelists are empty. So this is unlikely
-	 * to occur.
+	 * Stage one: Free all available per cpu objects back
+	 * to the page freelist while it is still frozen. Leave the
+	 * last one.
+	 *
+	 * There is no need to take the list->lock because the page
+	 * is still frozen.
 	 */
-	while (unlikely(c->freelist)) {
-		void **object;
+	while (freelist && (nextfree = get_freepointer(s, freelist))) {
+		void *prior;
+		unsigned long counters;
+
+		do {
+			prior = page->freelist;
+			counters = page->counters;
+			set_freepointer(s, freelist, prior);
+			new.counters = counters;
+			new.inuse--;
+			VM_BUG_ON(!new.frozen);
+
+		} while (!cmpxchg_double_slab(s, page,
+			prior, counters,
+			freelist, new.counters,
+			"drain percpu freelist"));
 
-		tail = 0;	/* Hot objects. Put the slab first */
+		freelist = nextfree;
+	}
 
-		/* Retrieve object from cpu_freelist */
-		object = c->freelist;
-		c->freelist = get_freepointer(s, c->freelist);
+	/*
+	 * Stage two: Ensure that the page is unfrozen while the
+	 * list presence reflects the actual number of objects
+	 * during unfreeze.
+	 *
+	 * We setup the list membership and then perform a cmpxchg
+	 * with the count. If there is a mismatch then the page
+	 * is not unfrozen but the page is on the wrong list.
+	 *
+	 * Then we restart the process which may have to remove
+	 * the page from the list that we just put it on again
+	 * because the number of objects in the slab may have
+	 * changed.
+	 */
+redo:
+
+	old.freelist = page->freelist;
+	old.counters = page->counters;
+	VM_BUG_ON(!old.frozen);
+
+	/* Determine target state of the slab */
+	new.counters = old.counters;
+	if (freelist) {
+		new.inuse--;
+		set_freepointer(s, freelist, old.freelist);
+		new.freelist = freelist;
+	} else
+		new.freelist = old.freelist;
 
-		/* And put onto the regular freelist */
-		set_freepointer(s, object, page->freelist);
-		page->freelist = object;
-		page->inuse--;
+	new.frozen = 0;
+
+	if (!new.inuse && n->nr_partial < s->min_partial)
+		m = M_FREE;
+	else if (new.freelist) {
+		m = M_PARTIAL;
+		if (!lock) {
+			lock = 1;
+			/*
+			 * Taking the spinlock removes the possiblity
+			 * that acquire_slab() will see a slab page that
+			 * is frozen
+			 */
+			spin_lock(&n->list_lock);
+		}
+	} else {
+		m = M_FULL;
+		if (kmem_cache_debug(s) && !lock) {
+			lock = 1;
+			/*
+			 * This also ensures that the scanning of full
+			 * slabs from diagnostic functions will not see
+			 * any frozen slabs.
+			 */
+			spin_lock(&n->list_lock);
+		}
+	}
+
+	if (l != m) {
+
+		if (l == M_PARTIAL)
+
+			remove_partial(n, page);
+
+		else if (l == M_FULL)
+
+			remove_full(s, page);
+
+		if (m == M_PARTIAL) {
+
+			add_partial(n, page, tail);
+			stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
+
+		} else if (m == M_FULL) {
+
+			stat(s, DEACTIVATE_FULL);
+			add_full(s, n, page);
+
+		}
+	}
+
+	l = m;
+	if (!cmpxchg_double_slab(s, page,
+				old.freelist, old.counters,
+				new.freelist, new.counters,
+				"unfreezing slab"))
+		goto redo;
+
+	slab_unlock(page);
+
+	if (lock)
+		spin_unlock(&n->list_lock);
+
+	if (m == M_FREE) {
+		discard_slab(s, page);
+		stat(s, FREE_SLAB);
 	}
-	c->page = NULL;
-	c->tid = next_tid(c->tid);
-	page->frozen = 0;
-	unfreeze_slab(s, page, tail);
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
@@ -1842,21 +1937,32 @@ static void *__slab_alloc(struct kmem_ca
 
 	stat(s, ALLOC_REFILL);
 
+	{
+		struct page new;
+		unsigned long counters;
+
+		do {
+			object = page->freelist;
+			counters = page->counters;
+			new.counters = counters;
+			new.inuse = page->objects;
+			VM_BUG_ON(!new.frozen);
+
+		} while (!cmpxchg_double_slab(s, page,
+				object, counters,
+				NULL, new.counters,
+				"__slab_alloc"));
+	}
+
 load_freelist:
 	VM_BUG_ON(!page->frozen);
 
-	object = page->freelist;
 	if (unlikely(!object))
 		goto another_slab;
-	if (kmem_cache_debug(s))
-		goto debug;
-
-	c->freelist = get_freepointer(s, object);
-	page->inuse = page->objects;
-	page->freelist = NULL;
 
-unlock_out:
 	slab_unlock(page);
+
+	c->freelist = get_freepointer(s, object);
 	c->tid = next_tid(c->tid);
 	local_irq_restore(flags);
 	stat(s, ALLOC_SLOWPATH);
@@ -1869,10 +1975,11 @@ new_slab:
 	page = get_partial(s, gfpflags, node);
 	if (page) {
 		stat(s, ALLOC_FROM_PARTIAL);
-		page->frozen = 1;
 load_from_page:
-		c->node = page_to_nid(page);
-		c->page = page;
+		object = c->freelist;
+
+		if (kmem_cache_debug(s))
+			goto debug;
 		goto load_freelist;
 	}
 
@@ -1887,10 +1994,21 @@ load_from_page:
 
 	if (page) {
 		c = __this_cpu_ptr(s->cpu_slab);
-		stat(s, ALLOC_SLAB);
 		if (c->page)
 			flush_slab(s, c);
 
+		/*
+		 * No other reference to the page yet so we can
+		 * muck around with it freely without cmpxchg
+		 */
+		c->freelist = page->freelist;
+		page->freelist = NULL;
+		page->inuse = page->objects;
+
+		c->node = page_to_nid(page);
+		c->page = page;
+
+		stat(s, ALLOC_SLAB);
 		slab_lock(page);
 
 		goto load_from_page;
@@ -1899,14 +2017,16 @@ load_from_page:
 		slab_out_of_memory(s, gfpflags, node);
 	local_irq_restore(flags);
 	return NULL;
+
 debug:
-	if (!alloc_debug_processing(s, page, object, addr))
-		goto another_slab;
+	if (!object || !alloc_debug_processing(s, page, object, addr))
+		goto new_slab;
 
-	page->inuse++;
-	page->freelist = get_freepointer(s, object);
+	c->freelist = get_freepointer(s, object);
+	deactivate_slab(s, c);
 	c->node = NUMA_NO_NODE;
-	goto unlock_out;
+	local_irq_restore(flags);
+	return object;
 }
 
 static __always_inline int alternate_slab_node(struct kmem_cache *s,
@@ -2070,6 +2190,11 @@ static void __slab_free(struct kmem_cach
 {
 	void *prior;
 	void **object = (void *)x;
+	int was_frozen;
+	int inuse;
+	struct page new;
+	unsigned long counters;
+	struct kmem_cache_node *n = NULL;
 	unsigned long flags;
 
 	local_irq_save(flags);
@@ -2079,32 +2204,65 @@ static void __slab_free(struct kmem_cach
 	if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
 		goto out_unlock;
 
-	prior = page->freelist;
-	set_freepointer(s, object, prior);
-	page->freelist = object;
-	page->inuse--;
-
-	if (unlikely(page->frozen)) {
-		stat(s, FREE_FROZEN);
-		goto out_unlock;
-	}
+	do {
+		prior = page->freelist;
+		counters = page->counters;
+		set_freepointer(s, object, prior);
+		new.counters = counters;
+		was_frozen = new.frozen;
+		new.inuse--;
+		if ((!new.inuse || !prior) && !was_frozen && !n) {
+                        n = get_node(s, page_to_nid(page));
+			/*
+			 * Speculatively acquire the list_lock.
+			 * If the cmpxchg does not succeed then we may
+			 * drop the list_lock without any processing.
+			 *
+			 * Otherwise the list_lock will synchronize with
+			 * other processors updating the list of slabs.
+			 */
+                        spin_lock(&n->list_lock);
+		}
+		inuse = new.inuse;
 
-	if (unlikely(!page->inuse))
-		goto slab_empty;
+	} while (!cmpxchg_double_slab(s, page,
+		prior, counters,
+		object, new.counters,
+		"__slab_free"));
+
+	if (likely(!n)) {
+                /*
+		 * The list lock was not taken therefore no list
+		 * activity can be necessary.
+		 */
+                if (was_frozen)
+                        stat(s, FREE_FROZEN);
+                goto out_unlock;
+        }
 
 	/*
-	 * Objects left in the slab. If it was not on the partial list before
-	 * then add it.
+	 * was_frozen may have been set after we acquired the list_lock in
+	 * an earlier loop. So we need to check it here again.
 	 */
-	if (unlikely(!prior)) {
-		struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+	if (was_frozen)
+		stat(s, FREE_FROZEN);
+	else {
+		if (unlikely(!inuse && n->nr_partial > s->min_partial))
+                        goto slab_empty;
 
-		spin_lock(&n->list_lock);
-		add_partial(get_node(s, page_to_nid(page)), page, 1);
-		spin_unlock(&n->list_lock);
-		stat(s, FREE_ADD_PARTIAL);
+		/*
+		 * Objects left in the slab. If it was not on the partial list before
+		 * then add it.
+		 */
+		if (unlikely(!prior)) {
+			remove_full(s, page);
+			add_partial(n, page, 0);
+			stat(s, FREE_ADD_PARTIAL);
+		}
 	}
 
+	spin_unlock(&n->list_lock);
+
 out_unlock:
 	slab_unlock(page);
 	local_irq_restore(flags);
@@ -2115,13 +2273,11 @@ slab_empty:
 		/*
 		 * Slab still on the partial list.
 		 */
-		struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
-		spin_lock(&n->list_lock);
 		remove_partial(n, page);
-		spin_unlock(&n->list_lock);
 		stat(s, FREE_REMOVE_PARTIAL);
 	}
+
+	spin_unlock(&n->list_lock);
 	slab_unlock(page);
 	local_irq_restore(flags);
 	stat(s, FREE_SLAB);

[slubllv4 10/16] slub: Invert locking and avoid slab lock

[Christoph Lameter]

[-- Attachment #1: slab_lock_subsume --]
[-- Type: text/plain, Size: 10314 bytes --]

Locking slabs is no longer necesary if the arch supports cmpxchg operations
and if no debuggin features are used on a slab. If the arch does not support
cmpxchg then we fallback to use the slab lock to do a cmpxchg like operation.

The patch also changes the lock order. Slab locks are subsumed to the node lock
now. With that approach slab_trylocking is no longer necessary.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |  131 +++++++++++++++++++++++++-------------------------------------
 1 file changed, 53 insertions(+), 78 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 12:54:35.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 12:54:36.000000000 -0500
@@ -2,10 +2,11 @@
  * SLUB: A slab allocator that limits cache line use instead of queuing
  * objects in per cpu and per node lists.
  *
- * The allocator synchronizes using per slab locks and only
- * uses a centralized lock to manage a pool of partial slabs.
+ * The allocator synchronizes using per slab locks or atomic operatios
+ * and only uses a centralized lock to manage a pool of partial slabs.
  *
  * (C) 2007 SGI, Christoph Lameter
+ * (C) 2011 Linux Foundation, Christoph Lameter
  */
 
 #include <linux/mm.h>
@@ -32,15 +33,27 @@
 
 /*
  * Lock order:
- *   1. slab_lock(page)
- *   2. slab->list_lock
- *
- *   The slab_lock protects operations on the object of a particular
- *   slab and its metadata in the page struct. If the slab lock
- *   has been taken then no allocations nor frees can be performed
- *   on the objects in the slab nor can the slab be added or removed
- *   from the partial or full lists since this would mean modifying
- *   the page_struct of the slab.
+ *   1. slub_lock (Global Semaphore)
+ *   2. node->list_lock
+ *   3. slab_lock(page) (Only on some arches and for debugging)
+ *
+ *   slub_lock
+ *
+ *   The role of the slub_lock is to protect the list of all the slabs
+ *   and to synchronize major metadata changes to slab cache structures.
+ *
+ *   The slab_lock is only used for debugging and on arches that do not
+ *   have the ability to do a cmpxchg_double. It only protects the second
+ *   double word in the page struct. Meaning
+ *	A. page->freelist	-> List of object free in a page
+ *	B. page->counters	-> Counters of objects
+ *	C. page->frozen		-> frozen state
+ *
+ *   If a slab is frozen then it is exempt from list management. It is not
+ *   on any list. The processor that froze the slab is the one who can
+ *   perform list operations on the page. Other processors may put objects
+ *   onto the freelist but the processor that froze the slab is the only
+ *   one that can retrieve the objects from the page's freelist.
  *
  *   The list_lock protects the partial and full list on each node and
  *   the partial slab counter. If taken then no new slabs may be added or
@@ -53,20 +66,6 @@
  *   slabs, operations can continue without any centralized lock. F.e.
  *   allocating a long series of objects that fill up slabs does not require
  *   the list lock.
- *
- *   The lock order is sometimes inverted when we are trying to get a slab
- *   off a list. We take the list_lock and then look for a page on the list
- *   to use. While we do that objects in the slabs may be freed. We can
- *   only operate on the slab if we have also taken the slab_lock. So we use
- *   a slab_trylock() on the slab. If trylock was successful then no frees
- *   can occur anymore and we can use the slab for allocations etc. If the
- *   slab_trylock() does not succeed then frees are in progress in the slab and
- *   we must stay away from it for a while since we may cause a bouncing
- *   cacheline if we try to acquire the lock. So go onto the next slab.
- *   If all pages are busy then we may allocate a new slab instead of reusing
- *   a partial slab. A new slab has no one operating on it and thus there is
- *   no danger of cacheline contention.
- *
  *   Interrupts are disabled during allocation and deallocation in order to
  *   make the slab allocator safe to use in the context of an irq. In addition
  *   interrupts are disabled to ensure that the processor does not change
@@ -330,6 +329,19 @@ static inline int oo_objects(struct kmem
 	return x.x & OO_MASK;
 }
 
+/*
+ * Per slab locking using the pagelock
+ */
+static __always_inline void slab_lock(struct page *page)
+{
+	bit_spin_lock(PG_locked, &page->flags);
+}
+
+static __always_inline void slab_unlock(struct page *page)
+{
+	__bit_spin_unlock(PG_locked, &page->flags);
+}
+
 static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
 		void *freelist_old, unsigned long counters_old,
 		void *freelist_new, unsigned long counters_new,
@@ -344,11 +356,14 @@ static inline bool cmpxchg_double_slab(s
 	} else
 #endif
 	{
+		slab_lock(page);
 		if (page->freelist == freelist_old && page->counters == counters_old) {
 			page->freelist = freelist_new;
 			page->counters = counters_new;
+			slab_unlock(page);
 			return 1;
 		}
+		slab_unlock(page);
 	}
 
 	cpu_relax();
@@ -364,7 +379,7 @@ static inline bool cmpxchg_double_slab(s
 /*
  * Determine a map of object in use on a page.
  *
- * Slab lock or node listlock must be held to guarantee that the page does
+ * Node listlock must be held to guarantee that the page does
  * not vanish from under us.
  */
 static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
@@ -796,10 +811,11 @@ static int check_slab(struct kmem_cache
 static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 {
 	int nr = 0;
-	void *fp = page->freelist;
+	void *fp;
 	void *object = NULL;
 	unsigned long max_objects;
 
+	fp = page->freelist;
 	while (fp && nr <= page->objects) {
 		if (fp == search)
 			return 1;
@@ -1007,6 +1023,8 @@ bad:
 static noinline int free_debug_processing(struct kmem_cache *s,
 		 struct page *page, void *object, unsigned long addr)
 {
+	slab_lock(page);
+
 	if (!check_slab(s, page))
 		goto fail;
 
@@ -1042,10 +1060,12 @@ static noinline int free_debug_processin
 		set_track(s, object, TRACK_FREE, addr);
 	trace(s, page, object, 0);
 	init_object(s, object, SLUB_RED_INACTIVE);
+	slab_unlock(page);
 	return 1;
 
 fail:
 	slab_fix(s, "Object at 0x%p not freed", object);
+	slab_unlock(page);
 	return 0;
 }
 
@@ -1365,27 +1385,6 @@ static void discard_slab(struct kmem_cac
 }
 
 /*
- * Per slab locking using the pagelock
- */
-static __always_inline void slab_lock(struct page *page)
-{
-	bit_spin_lock(PG_locked, &page->flags);
-}
-
-static __always_inline void slab_unlock(struct page *page)
-{
-	__bit_spin_unlock(PG_locked, &page->flags);
-}
-
-static __always_inline int slab_trylock(struct page *page)
-{
-	int rc = 1;
-
-	rc = bit_spin_trylock(PG_locked, &page->flags);
-	return rc;
-}
-
-/*
  * Management of partially allocated slabs
  */
 static inline void add_partial(struct kmem_cache_node *n,
@@ -1411,17 +1410,13 @@ static inline void remove_partial(struct
  *
  * Must hold list_lock.
  */
-static inline int lock_and_freeze_slab(struct kmem_cache *s,
+static inline int acquire_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page)
 {
 	void *freelist;
 	unsigned long counters;
 	struct page new;
 
-
-	if (!slab_trylock(page))
-		return 0;
-
 	/*
 	 * Zap the freelist and set the frozen bit.
 	 * The old freelist is the list of objects for the
@@ -1457,7 +1452,6 @@ static inline int lock_and_freeze_slab(s
 		 */
 		printk(KERN_ERR "SLUB: %s : Page without available objects on"
 			" partial list\n", s->name);
-		slab_unlock(page);
 		return 0;
 	}
 }
@@ -1481,7 +1475,7 @@ static struct page *get_partial_node(str
 
 	spin_lock(&n->list_lock);
 	list_for_each_entry(page, &n->partial, lru)
-		if (lock_and_freeze_slab(s, n, page))
+		if (acquire_slab(s, n, page))
 			goto out;
 	page = NULL;
 out:
@@ -1770,8 +1764,6 @@ redo:
 				"unfreezing slab"))
 		goto redo;
 
-	slab_unlock(page);
-
 	if (lock)
 		spin_unlock(&n->list_lock);
 
@@ -1784,7 +1776,6 @@ redo:
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
 	stat(s, CPUSLAB_FLUSH);
-	slab_lock(c->page);
 	deactivate_slab(s, c);
 }
 
@@ -1931,7 +1922,6 @@ static void *__slab_alloc(struct kmem_ca
 	if (!page)
 		goto new_slab;
 
-	slab_lock(page);
 	if (unlikely(!node_match(c, node)))
 		goto another_slab;
 
@@ -1960,8 +1950,6 @@ load_freelist:
 	if (unlikely(!object))
 		goto another_slab;
 
-	slab_unlock(page);
-
 	c->freelist = get_freepointer(s, object);
 	c->tid = next_tid(c->tid);
 	local_irq_restore(flags);
@@ -2009,7 +1997,6 @@ load_from_page:
 		c->page = page;
 
 		stat(s, ALLOC_SLAB);
-		slab_lock(page);
 
 		goto load_from_page;
 	}
@@ -2198,7 +2185,6 @@ static void __slab_free(struct kmem_cach
 	unsigned long flags;
 
 	local_irq_save(flags);
-	slab_lock(page);
 	stat(s, FREE_SLOWPATH);
 
 	if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
@@ -2264,7 +2250,6 @@ static void __slab_free(struct kmem_cach
 	spin_unlock(&n->list_lock);
 
 out_unlock:
-	slab_unlock(page);
 	local_irq_restore(flags);
 	return;
 
@@ -2278,7 +2263,6 @@ slab_empty:
 	}
 
 	spin_unlock(&n->list_lock);
-	slab_unlock(page);
 	local_irq_restore(flags);
 	stat(s, FREE_SLAB);
 	discard_slab(s, page);
@@ -3199,14 +3183,8 @@ int kmem_cache_shrink(struct kmem_cache
 		 * list_lock. page->inuse here is the upper limit.
 		 */
 		list_for_each_entry_safe(page, t, &n->partial, lru) {
-			if (!page->inuse && slab_trylock(page)) {
-				/*
-				 * Must hold slab lock here because slab_free
-				 * may have freed the last object and be
-				 * waiting to release the slab.
-				 */
+			if (!page->inuse) {
 				remove_partial(n, page);
-				slab_unlock(page);
 				discard_slab(s, page);
 			} else {
 				list_move(&page->lru,
@@ -3794,12 +3772,9 @@ static int validate_slab(struct kmem_cac
 static void validate_slab_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
 {
-	if (slab_trylock(page)) {
-		validate_slab(s, page, map);
-		slab_unlock(page);
-	} else
-		printk(KERN_INFO "SLUB %s: Skipped busy slab 0x%p\n",
-			s->name, page);
+	slab_lock(page);
+	validate_slab(s, page, map);
+	slab_unlock(page);
 }
 
 static int validate_slab_node(struct kmem_cache *s,

[slubllv4 11/16] slub: Disable interrupts in free_debug processing

[Christoph Lameter]

[-- Attachment #1: irqoff_in_free_debug_processing --]
[-- Type: text/plain, Size: 1113 bytes --]

We will be calling free_debug_processing with interrupts disabled
in some case when the later patches are applied. Some of the
functions called by free_debug_processing expect interrupts to be
off.

Signed-off-by: Christoph Lameter <cl@linux.com>


---
 mm/slub.c |    6 ++++++
 1 file changed, 6 insertions(+)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-04-15 13:15:04.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-04-15 13:15:06.000000000 -0500
@@ -1023,6 +1023,10 @@ bad:
 static noinline int free_debug_processing(struct kmem_cache *s,
 		 struct page *page, void *object, unsigned long addr)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
+
 	slab_lock(page);
 
 	if (!check_slab(s, page))
@@ -1061,11 +1065,13 @@ static noinline int free_debug_processin
 	trace(s, page, object, 0);
 	init_object(s, object, SLUB_RED_INACTIVE);
 	slab_unlock(page);
+	local_irq_restore(flags);
 	return 1;
 
 fail:
 	slab_fix(s, "Object at 0x%p not freed", object);
 	slab_unlock(page);
+	local_irq_restore(flags);
 	return 0;
 }
 

[slubllv4 12/16] slub: Avoid disabling interrupts in free slowpath

[Christoph Lameter]

[-- Attachment #1: slab_free_without_irqoff --]
[-- Type: text/plain, Size: 2204 bytes --]

Disabling interrupts can be avoided now. However, list operation still require
disabling interrupts since allocations can occur from interrupt
contexts and there is no way to perform atomic list operations. So
acquire the list lock opportunistically if there is a chance
that list operations would be needed. This may result in
needless synchronizations but allows the avoidance of synchronization
in the majority of the cases.

Dropping interrupt handling significantly simplifies the slowpath.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |   16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 12:55:26.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 12:55:42.000000000 -0500
@@ -2190,11 +2190,10 @@ static void __slab_free(struct kmem_cach
 	struct kmem_cache_node *n = NULL;
 	unsigned long flags;
 
-	local_irq_save(flags);
 	stat(s, FREE_SLOWPATH);
 
 	if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
-		goto out_unlock;
+		return;
 
 	do {
 		prior = page->freelist;
@@ -2213,7 +2212,7 @@ static void __slab_free(struct kmem_cach
 			 * Otherwise the list_lock will synchronize with
 			 * other processors updating the list of slabs.
 			 */
-                        spin_lock(&n->list_lock);
+                        spin_lock_irqsave(&n->list_lock, flags);
 		}
 		inuse = new.inuse;
 
@@ -2229,7 +2228,7 @@ static void __slab_free(struct kmem_cach
 		 */
                 if (was_frozen)
                         stat(s, FREE_FROZEN);
-                goto out_unlock;
+                return;
         }
 
 	/*
@@ -2252,11 +2251,7 @@ static void __slab_free(struct kmem_cach
 			stat(s, FREE_ADD_PARTIAL);
 		}
 	}
-
-	spin_unlock(&n->list_lock);
-
-out_unlock:
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	return;
 
 slab_empty:
@@ -2268,8 +2263,7 @@ slab_empty:
 		stat(s, FREE_REMOVE_PARTIAL);
 	}
 
-	spin_unlock(&n->list_lock);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	stat(s, FREE_SLAB);
 	discard_slab(s, page);
 }

[slubllv4 13/16] slub: Get rid of the another_slab label

[Christoph Lameter]

[-- Attachment #1: eliminate_another_slab --]
[-- Type: text/plain, Size: 1150 bytes --]

We can avoid deactivate slab in special cases if we do the
deactivation of slabs in each code flow that leads to new_slab.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |   11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 12:55:42.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 12:56:13.000000000 -0500
@@ -1928,8 +1928,10 @@ static void *__slab_alloc(struct kmem_ca
 	if (!page)
 		goto new_slab;
 
-	if (unlikely(!node_match(c, node)))
-		goto another_slab;
+	if (unlikely(!node_match(c, node))) {
+		deactivate_slab(s, c);
+		goto new_slab;
+	}
 
 	stat(s, ALLOC_REFILL);
 
@@ -1954,7 +1956,7 @@ load_freelist:
 	VM_BUG_ON(!page->frozen);
 
 	if (unlikely(!object))
-		goto another_slab;
+		goto new_slab;
 
 	c->freelist = get_freepointer(s, object);
 	c->tid = next_tid(c->tid);
@@ -1962,9 +1964,6 @@ load_freelist:
 	stat(s, ALLOC_SLOWPATH);
 	return object;
 
-another_slab:
-	deactivate_slab(s, c);
-
 new_slab:
 	page = get_partial(s, gfpflags, node);
 	if (page) {

[slubllv4 14/16] slub: fast release on full slab

[Christoph Lameter]

[-- Attachment #1: slab_alloc_fast_release --]
[-- Type: text/plain, Size: 1512 bytes --]

Make deactivation occur implicitly while checking out the current freelist.

This avoids one cmpxchg operation on a slab that is now fully in use.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |   18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 12:56:13.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 12:56:38.000000000 -0500
@@ -1943,9 +1943,21 @@ static void *__slab_alloc(struct kmem_ca
 			object = page->freelist;
 			counters = page->counters;
 			new.counters = counters;
-			new.inuse = page->objects;
 			VM_BUG_ON(!new.frozen);
 
+			/*
+			 * If there is no object left then we use this loop to
+			 * deactivate the slab which is simple since no objects
+			 * are left in the slab and therefore we do not need to
+			 * put the page back onto the partial list.
+			 *
+			 * If there are objects left then we retrieve them
+			 * and use them to refill the per cpu queue.
+			*/
+
+			new.inuse = page->objects;
+			new.frozen = object != NULL;
+
 		} while (!cmpxchg_double_slab(s, page,
 				object, counters,
 				NULL, new.counters,
@@ -1955,8 +1967,10 @@ static void *__slab_alloc(struct kmem_ca
 load_freelist:
 	VM_BUG_ON(!page->frozen);
 
-	if (unlikely(!object))
+	if (unlikely(!object)) {
+		c->page = NULL;
 		goto new_slab;
+	}
 
 	c->freelist = get_freepointer(s, object);
 	c->tid = next_tid(c->tid);

[slubllv4 15/16] slub: Not necessary to check for empty slab on load_freelist

[Christoph Lameter]

[-- Attachment #1: goto_load_freelist --]
[-- Type: text/plain, Size: 746 bytes --]

Load freelist is now only branched to if there are objects available.
So no need to check.

---
 mm/slub.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 09:06:34.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 09:06:37.000000000 -0500
@@ -1966,14 +1966,13 @@ static void *__slab_alloc(struct kmem_ca
 				"__slab_alloc"));
 	}
 
-load_freelist:
-	VM_BUG_ON(!page->frozen);
-
 	if (unlikely(!object)) {
 		c->page = NULL;
 		goto new_slab;
 	}
 
+load_freelist:
+	VM_BUG_ON(!page->frozen);
 	c->freelist = get_freepointer(s, object);
 	c->tid = next_tid(c->tid);
 	local_irq_restore(flags);

[slubllv4 16/16] slub: update statistics for cmpxchg handling

[Christoph Lameter]

[-- Attachment #1: statfixes --]
[-- Type: text/plain, Size: 9712 bytes --]

Update the statistics handling and the slabinfo tool to include the new
statistics in the reports it generates.

Signed-off-by: Christoph Lameter <cl@linux.com>


---
 include/linux/slub_def.h |    2 +
 mm/slub.c                |   12 ++++++++-
 tools/slub/slabinfo.c    |   57 ++++++++++++++++++++++++++++++++---------------
 3 files changed, 51 insertions(+), 20 deletions(-)

Index: linux-2.6/include/linux/slub_def.h
===================================================================
--- linux-2.6.orig/include/linux/slub_def.h	2011-05-06 12:54:31.000000000 -0500
+++ linux-2.6/include/linux/slub_def.h	2011-05-06 12:57:25.000000000 -0500
@@ -24,6 +24,7 @@ enum stat_item {
 	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from partial list */
 	ALLOC_SLAB,		/* Cpu slab acquired from page allocator */
 	ALLOC_REFILL,		/* Refill cpu slab from slab freelist */
+	ALLOC_NODE_MISMATCH,	/* Switching cpu slab */
 	FREE_SLAB,		/* Slab freed to the page allocator */
 	CPUSLAB_FLUSH,		/* Abandoning of the cpu slab */
 	DEACTIVATE_FULL,	/* Cpu slab was full when deactivated */
@@ -31,6 +32,7 @@ enum stat_item {
 	DEACTIVATE_TO_HEAD,	/* Cpu slab was moved to the head of partials */
 	DEACTIVATE_TO_TAIL,	/* Cpu slab was moved to the tail of partials */
 	DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
+	DEACTIVATE_BYPASS,	/* Implicit deactivation */
 	ORDER_FALLBACK,		/* Number of times fallback was necessary */
 	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
 	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-06 12:57:10.000000000 -0500
+++ linux-2.6/mm/slub.c	2011-05-06 12:57:25.000000000 -0500
@@ -1774,6 +1774,7 @@ redo:
 		spin_unlock(&n->list_lock);
 
 	if (m == M_FREE) {
+		stat(s, DEACTIVATE_EMPTY);
 		discard_slab(s, page);
 		stat(s, FREE_SLAB);
 	}
@@ -1929,12 +1930,12 @@ static void *__slab_alloc(struct kmem_ca
 		goto new_slab;
 
 	if (unlikely(!node_match(c, node))) {
+		stat(s, ALLOC_NODE_MISMATCH);
 		deactivate_slab(s, c);
 		goto new_slab;
 	}
 
-	stat(s, ALLOC_REFILL);
-
+	stat(s, ALLOC_SLOWPATH);
 	{
 		struct page new;
 		unsigned long counters;
@@ -1966,9 +1967,12 @@ static void *__slab_alloc(struct kmem_ca
 
 	if (unlikely(!object)) {
 		c->page = NULL;
+		stat(s, DEACTIVATE_BYPASS);
 		goto new_slab;
 	}
 
+	stat(s, ALLOC_REFILL);
+
 load_freelist:
 	VM_BUG_ON(!page->frozen);
 	c->freelist = get_freepointer(s, object);
@@ -4671,6 +4675,7 @@ STAT_ATTR(FREE_REMOVE_PARTIAL, free_remo
 STAT_ATTR(ALLOC_FROM_PARTIAL, alloc_from_partial);
 STAT_ATTR(ALLOC_SLAB, alloc_slab);
 STAT_ATTR(ALLOC_REFILL, alloc_refill);
+STAT_ATTR(ALLOC_NODE_MISMATCH, alloc_node_mismatch);
 STAT_ATTR(FREE_SLAB, free_slab);
 STAT_ATTR(CPUSLAB_FLUSH, cpuslab_flush);
 STAT_ATTR(DEACTIVATE_FULL, deactivate_full);
@@ -4678,6 +4683,7 @@ STAT_ATTR(DEACTIVATE_EMPTY, deactivate_e
 STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head);
 STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail);
 STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees);
+STAT_ATTR(DEACTIVATE_BYPASS, deactivate_bypass);
 STAT_ATTR(ORDER_FALLBACK, order_fallback);
 STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail);
 STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
@@ -4730,6 +4736,7 @@ static struct attribute *slab_attrs[] =
 	&alloc_from_partial_attr.attr,
 	&alloc_slab_attr.attr,
 	&alloc_refill_attr.attr,
+	&alloc_node_mismatch_attr.attr,
 	&free_slab_attr.attr,
 	&cpuslab_flush_attr.attr,
 	&deactivate_full_attr.attr,
@@ -4737,6 +4744,7 @@ static struct attribute *slab_attrs[] =
 	&deactivate_to_head_attr.attr,
 	&deactivate_to_tail_attr.attr,
 	&deactivate_remote_frees_attr.attr,
+	&deactivate_bypass_attr.attr,
 	&order_fallback_attr.attr,
 	&cmpxchg_double_fail_attr.attr,
 	&cmpxchg_double_cpu_fail_attr.attr,
Index: linux-2.6/tools/slub/slabinfo.c
===================================================================
--- linux-2.6.orig/tools/slub/slabinfo.c	2011-05-06 12:41:41.000000000 -0500
+++ linux-2.6/tools/slub/slabinfo.c	2011-05-06 12:57:25.000000000 -0500
@@ -2,8 +2,9 @@
  * Slabinfo: Tool to get reports about slabs
  *
  * (C) 2007 sgi, Christoph Lameter
+ * (C) 2011 Linux Foundation, Christoph Lameter
  *
- * Compile by:
+ * Compile with:
  *
  * gcc -o slabinfo slabinfo.c
  */
@@ -39,6 +40,8 @@ struct slabinfo {
 	unsigned long cpuslab_flush, deactivate_full, deactivate_empty;
 	unsigned long deactivate_to_head, deactivate_to_tail;
 	unsigned long deactivate_remote_frees, order_fallback;
+	unsigned long cmpxchg_double_cpu_fail, cmpxchg_double_fail;
+	unsigned long alloc_node_mismatch, deactivate_bypass;
 	int numa[MAX_NODES];
 	int numa_partial[MAX_NODES];
 } slabinfo[MAX_SLABS];
@@ -99,7 +102,7 @@ static void fatal(const char *x, ...)
 
 static void usage(void)
 {
-	printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n"
+	printf("slabinfo 4/15/2011. (c) 2007 sgi/(c) 2011 Linux Foundation.\n\n"
 		"slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n"
 		"-a|--aliases           Show aliases\n"
 		"-A|--activity          Most active slabs first\n"
@@ -293,7 +296,7 @@ int line = 0;
 static void first_line(void)
 {
 	if (show_activity)
-		printf("Name                   Objects      Alloc       Free   %%Fast Fallb O\n");
+		printf("Name                   Objects      Alloc       Free   %%Fast Fallb O CmpX   UL\n");
 	else
 		printf("Name                   Objects Objsize    Space "
 			"Slabs/Part/Cpu  O/S O %%Fr %%Ef Flg\n");
@@ -379,14 +382,14 @@ static void show_tracking(struct slabinf
 	printf("\n%s: Kernel object allocation\n", s->name);
 	printf("-----------------------------------------------------------------------\n");
 	if (read_slab_obj(s, "alloc_calls"))
-		printf(buffer);
+		printf("%s", buffer);
 	else
 		printf("No Data\n");
 
 	printf("\n%s: Kernel object freeing\n", s->name);
 	printf("------------------------------------------------------------------------\n");
 	if (read_slab_obj(s, "free_calls"))
-		printf(buffer);
+		printf("%s", buffer);
 	else
 		printf("No Data\n");
 
@@ -400,7 +403,7 @@ static void ops(struct slabinfo *s)
 	if (read_slab_obj(s, "ops")) {
 		printf("\n%s: kmem_cache operations\n", s->name);
 		printf("--------------------------------------------\n");
-		printf(buffer);
+		printf("%s", buffer);
 	} else
 		printf("\n%s has no kmem_cache operations\n", s->name);
 }
@@ -462,19 +465,32 @@ static void slab_stats(struct slabinfo *
 	if (s->cpuslab_flush)
 		printf("Flushes %8lu\n", s->cpuslab_flush);
 
-	if (s->alloc_refill)
-		printf("Refill %8lu\n", s->alloc_refill);
-
 	total = s->deactivate_full + s->deactivate_empty +
-			s->deactivate_to_head + s->deactivate_to_tail;
+			s->deactivate_to_head + s->deactivate_to_tail + s->deactivate_bypass;
 
-	if (total)
-		printf("Deactivate Full=%lu(%lu%%) Empty=%lu(%lu%%) "
-			"ToHead=%lu(%lu%%) ToTail=%lu(%lu%%)\n",
-			s->deactivate_full, (s->deactivate_full * 100) / total,
-			s->deactivate_empty, (s->deactivate_empty * 100) / total,
-			s->deactivate_to_head, (s->deactivate_to_head * 100) / total,
+	if (total) {
+		printf("\nSlab Deactivation             Ocurrences  %%\n");
+		printf("-------------------------------------------------\n");
+		printf("Slab full                     %7lu  %3lu%%\n",
+			s->deactivate_full, (s->deactivate_full * 100) / total);
+		printf("Slab empty                    %7lu  %3lu%%\n",
+			s->deactivate_empty, (s->deactivate_empty * 100) / total);
+		printf("Moved to head of partial list %7lu  %3lu%%\n",
+			s->deactivate_to_head, (s->deactivate_to_head * 100) / total);
+		printf("Moved to tail of partial list %7lu  %3lu%%\n",
 			s->deactivate_to_tail, (s->deactivate_to_tail * 100) / total);
+		printf("Deactivation bypass           %7lu  %3lu%%\n",
+			s->deactivate_bypass, (s->deactivate_bypass * 100) / total);
+		printf("Refilled from foreign frees   %7lu  %3lu%%\n",
+			s->alloc_refill, (s->alloc_refill * 100) / total);
+		printf("Node mismatch                 %7lu  %3lu%%\n",
+			s->alloc_node_mismatch, (s->alloc_node_mismatch * 100) / total);
+	}
+
+	if (s->cmpxchg_double_fail || s->cmpxchg_double_cpu_fail)
+		printf("\nCmpxchg_double Looping\n------------------------\n");
+		printf("Locked Cmpxchg Double redos   %lu\nUnlocked Cmpxchg Double redos %lu\n",
+			s->cmpxchg_double_fail, s->cmpxchg_double_cpu_fail);
 }
 
 static void report(struct slabinfo *s)
@@ -573,12 +589,13 @@ static void slabcache(struct slabinfo *s
 		total_alloc = s->alloc_fastpath + s->alloc_slowpath;
 		total_free = s->free_fastpath + s->free_slowpath;
 
-		printf("%-21s %8ld %10ld %10ld %3ld %3ld %5ld %1d\n",
+		printf("%-21s %8ld %10ld %10ld %3ld %3ld %5ld %1d %4ld %4ld\n",
 			s->name, s->objects,
 			total_alloc, total_free,
 			total_alloc ? (s->alloc_fastpath * 100 / total_alloc) : 0,
 			total_free ? (s->free_fastpath * 100 / total_free) : 0,
-			s->order_fallback, s->order);
+			s->order_fallback, s->order, s->cmpxchg_double_fail,
+			s->cmpxchg_double_cpu_fail);
 	}
 	else
 		printf("%-21s %8ld %7d %8s %14s %4d %1d %3ld %3ld %s\n",
@@ -1190,6 +1207,10 @@ static void read_slab_dir(void)
 			slab->deactivate_to_tail = get_obj("deactivate_to_tail");
 			slab->deactivate_remote_frees = get_obj("deactivate_remote_frees");
 			slab->order_fallback = get_obj("order_fallback");
+			slab->cmpxchg_double_cpu_fail = get_obj("cmpxchg_double_cpu_fail");
+			slab->cmpxchg_double_fail = get_obj("cmpxchg_double_fail");
+			slab->alloc_node_mismatch = get_obj("alloc_node_mismatch");
+			slab->deactivate_bypass = get_obj("deactivate_bypass");
 			chdir("..");
 			if (slab->name[0] == ':')
 				alias_targets++;