slub: Add cmpxchg_double_slab()

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>
Signed-off-by: Pekka Enberg <penberg@kernel.org>

2 files changed, 61 insertions, 5 deletions

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index c8668d161dd8..b42715294147 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -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 {
diff --git a/mm/slub.c b/mm/slub.c
index 5a2d3d8e0558..be6715dd0ee8 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -131,6 +131,9 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 /* 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(struct kmem_cache *s)
 
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000UL /* Poison object */
+#define __CMPXCHG_DOUBLE	0x40000000UL /* Use cmpxchg_double */
 
 static int kmem_size = sizeof(struct kmem_cache);
 
@@ -338,6 +342,37 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
 	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;
+}
+
 #ifdef CONFIG_SLUB_DEBUG
 /*
  * Determine a map of object in use on a page.
@@ -2596,6 +2631,12 @@ static int kmem_cache_open(struct kmem_cache *s,
 		}
 	}
 
+#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.
@@ -4248,8 +4289,10 @@ static ssize_t sanity_checks_store(struct kmem_cache *s,
 				const char *buf, size_t length)
 {
 	s->flags &= ~SLAB_DEBUG_FREE;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_DEBUG_FREE;
+	}
 	return length;
 }
 SLAB_ATTR(sanity_checks);
@@ -4263,8 +4306,10 @@ static ssize_t trace_store(struct kmem_cache *s, const char *buf,
 							size_t length)
 {
 	s->flags &= ~SLAB_TRACE;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_TRACE;
+	}
 	return length;
 }
 SLAB_ATTR(trace);
@@ -4281,8 +4326,10 @@ static ssize_t red_zone_store(struct kmem_cache *s,
 		return -EBUSY;
 
 	s->flags &= ~SLAB_RED_ZONE;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_RED_ZONE;
+	}
 	calculate_sizes(s, -1);
 	return length;
 }
@@ -4300,8 +4347,10 @@ static ssize_t poison_store(struct kmem_cache *s,
 		return -EBUSY;
 
 	s->flags &= ~SLAB_POISON;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_POISON;
+	}
 	calculate_sizes(s, -1);
 	return length;
 }
@@ -4319,8 +4368,10 @@ static ssize_t store_user_store(struct kmem_cache *s,
 		return -EBUSY;
 
 	s->flags &= ~SLAB_STORE_USER;
-	if (buf[0] == '1')
+	if (buf[0] == '1') {
+		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_STORE_USER;
+	}
 	calculate_sizes(s, -1);
 	return length;
 }
@@ -4493,6 +4544,8 @@ 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(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[] = {
@@ -4550,6 +4603,8 @@ 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,