Merge branch 'slab/next' into for-linus

3 files changed, 106 insertions, 87 deletions

diff --git a/mm/slab.c b/mm/slab.c
index 37961d1f584..a18ba57517a 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -191,22 +191,6 @@ typedef unsigned int kmem_bufctl_t;
 #define SLAB_LIMIT      (((kmem_bufctl_t)(~0U))-3)
 
 /*
- * struct slab
- *
- * Manages the objs in a slab. Placed either at the beginning of mem allocated
- * for a slab, or allocated from an general cache.
- * Slabs are chained into three list: fully used, partial, fully free slabs.
- */
-struct slab {
-        struct list_head list;
-        unsigned long colouroff;
-        void *s_mem;            /* including colour offset */
-        unsigned int inuse;     /* num of objs active in slab */
-        kmem_bufctl_t free;
-        unsigned short nodeid;
-};
-
-/*
  * struct slab_rcu
  *
  * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
@@ -219,8 +203,6 @@ struct slab {
  *
  * rcu_read_lock before reading the address, then rcu_read_unlock after
  * taking the spinlock within the structure expected at that address.
- *
- * We assume struct slab_rcu can overlay struct slab when destroying.
  */
 struct slab_rcu {
         struct rcu_head head;
@@ -229,6 +211,27 @@ struct slab_rcu {
 };
 
 /*
+ * struct slab
+ *
+ * Manages the objs in a slab. Placed either at the beginning of mem allocated
+ * for a slab, or allocated from an general cache.
+ * Slabs are chained into three list: fully used, partial, fully free slabs.
+ */
+struct slab {
+        union {
+                struct {
+                        struct list_head list;
+                        unsigned long colouroff;
+                        void *s_mem;            /* including colour offset */
+                        unsigned int inuse;     /* num of objs active in slab */
+                        kmem_bufctl_t free;
+                        unsigned short nodeid;
+                };
+                struct slab_rcu __slab_cover_slab_rcu;
+        };
+};
+
+/*
  * struct array_cache
  *
  * Purpose:
@@ -2147,8 +2150,6 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
  *
  * @name must be valid until the cache is destroyed. This implies that
  * the module calling this has to destroy the cache before getting unloaded.
- * Note that kmem_cache_name() is not guaranteed to return the same pointer,
- * therefore applications must manage it themselves.
  *
  * The flags are
  *
@@ -2288,8 +2289,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
         if (ralign < align) {
                 ralign = align;
         }
-        /* disable debug if not aligning with REDZONE_ALIGN */
-        if (ralign & (__alignof__(unsigned long long) - 1))
+        /* disable debug if necessary */
+        if (ralign > __alignof__(unsigned long long))
                 flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
         /*
          * 4) Store it.
@@ -2315,8 +2316,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
          */
         if (flags & SLAB_RED_ZONE) {
                 /* add space for red zone words */
-                cachep->obj_offset += align;
-                size += align + sizeof(unsigned long long);
+                cachep->obj_offset += sizeof(unsigned long long);
+                size += 2 * sizeof(unsigned long long);
         }
         if (flags & SLAB_STORE_USER) {
                 /* user store requires one word storage behind the end of
@@ -3840,12 +3841,6 @@ unsigned int kmem_cache_size(struct kmem_cache *cachep)
 }
 EXPORT_SYMBOL(kmem_cache_size);
 
-const char *kmem_cache_name(struct kmem_cache *cachep)
-{
-        return cachep->name;
-}
-EXPORT_SYMBOL_GPL(kmem_cache_name);
-
 /*
  * This initializes kmem_list3 or resizes various caches for all nodes.
  */
diff --git a/mm/slob.c b/mm/slob.c
index 3588eaaef72..46e0aee33a2 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -666,12 +666,6 @@ unsigned int kmem_cache_size(struct kmem_cache *c)
 }
 EXPORT_SYMBOL(kmem_cache_size);
 
-const char *kmem_cache_name(struct kmem_cache *c)
-{
-        return c->name;
-}
-EXPORT_SYMBOL(kmem_cache_name);
-
 int kmem_cache_shrink(struct kmem_cache *d)
 {
         return 0;
diff --git a/mm/slub.c b/mm/slub.c
index e15aa7f193c..e841d8921c2 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -281,11 +281,40 @@ static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
         return (p - addr) / s->size;
 }
 
+static inline size_t slab_ksize(const struct kmem_cache *s)
+{
+#ifdef CONFIG_SLUB_DEBUG
+        /*
+         * Debugging requires use of the padding between object
+         * and whatever may come after it.
+         */
+        if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
+                return s->objsize;
+
+#endif
+        /*
+         * If we have the need to store the freelist pointer
+         * back there or track user information then we can
+         * only use the space before that information.
+         */
+        if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
+                return s->inuse;
+        /*
+         * Else we can use all the padding etc for the allocation
+         */
+        return s->size;
+}
+
+static inline int order_objects(int order, unsigned long size, int reserved)
+{
+        return ((PAGE_SIZE << order) - reserved) / size;
+}
+
 static inline struct kmem_cache_order_objects oo_make(int order,
-                                                unsigned long size)
+                unsigned long size, int reserved)
 {
         struct kmem_cache_order_objects x = {
-                (order << OO_SHIFT) + (PAGE_SIZE << order) / size
+                (order << OO_SHIFT) + order_objects(order, size, reserved)
         };
 
         return x;
@@ -617,7 +646,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
                 return 1;
 
         start = page_address(page);
-        length = (PAGE_SIZE << compound_order(page));
+        length = (PAGE_SIZE << compound_order(page)) - s->reserved;
         end = start + length;
         remainder = length % s->size;
         if (!remainder)
@@ -698,7 +727,7 @@ static int check_slab(struct kmem_cache *s, struct page *page)
                 return 0;
         }
 
-        maxobj = (PAGE_SIZE << compound_order(page)) / s->size;
+        maxobj = order_objects(compound_order(page), s->size, s->reserved);
         if (page->objects > maxobj) {
                 slab_err(s, page, "objects %u > max %u",
                         s->name, page->objects, maxobj);
@@ -748,7 +777,7 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
                 nr++;
         }
 
-        max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
+        max_objects = order_objects(compound_order(page), s->size, s->reserved);
         if (max_objects > MAX_OBJS_PER_PAGE)
                 max_objects = MAX_OBJS_PER_PAGE;
 
@@ -800,7 +829,7 @@ static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
 static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object)
 {
         flags &= gfp_allowed_mask;
-        kmemcheck_slab_alloc(s, flags, object, s->objsize);
+        kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
         kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags);
 }
 
@@ -1249,21 +1278,38 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
         __free_pages(page, order);
 }
 
+#define need_reserve_slab_rcu                                           \
+        (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head))
+
 static void rcu_free_slab(struct rcu_head *h)
 {
         struct page *page;
 
-        page = container_of((struct list_head *)h, struct page, lru);
+        if (need_reserve_slab_rcu)
+                page = virt_to_head_page(h);
+        else
+                page = container_of((struct list_head *)h, struct page, lru);
+
         __free_slab(page->slab, page);
 }
 
 static void free_slab(struct kmem_cache *s, struct page *page)
 {
         if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
-                /*
-                 * RCU free overloads the RCU head over the LRU
-                 */
-                struct rcu_head *head = (void *)&page->lru;
+                struct rcu_head *head;
+
+                if (need_reserve_slab_rcu) {
+                        int order = compound_order(page);
+                        int offset = (PAGE_SIZE << order) - s->reserved;
+
+                        VM_BUG_ON(s->reserved != sizeof(*head));
+                        head = page_address(page) + offset;
+                } else {
+                        /*
+                         * RCU free overloads the RCU head over the LRU
+                         */
+                        head = (void *)&page->lru;
+                }
 
                 call_rcu(head, rcu_free_slab);
         } else
@@ -1988,13 +2034,13 @@ static int slub_nomerge;
  * the smallest order which will fit the object.
  */
 static inline int slab_order(int size, int min_objects,
-                                int max_order, int fract_leftover)
+                                int max_order, int fract_leftover, int reserved)
 {
         int order;
         int rem;
         int min_order = slub_min_order;
 
-        if ((PAGE_SIZE << min_order) / size > MAX_OBJS_PER_PAGE)
+        if (order_objects(min_order, size, reserved) > MAX_OBJS_PER_PAGE)
                 return get_order(size * MAX_OBJS_PER_PAGE) - 1;
 
         for (order = max(min_order,
@@ -2003,10 +2049,10 @@ static inline int slab_order(int size, int min_objects,
 
                 unsigned long slab_size = PAGE_SIZE << order;
 
-                if (slab_size < min_objects * size)
+                if (slab_size < min_objects * size + reserved)
                         continue;
 
-                rem = slab_size % size;
+                rem = (slab_size - reserved) % size;
 
                 if (rem <= slab_size / fract_leftover)
                         break;
@@ -2016,7 +2062,7 @@ static inline int slab_order(int size, int min_objects,
         return order;
 }
 
-static inline int calculate_order(int size)
+static inline int calculate_order(int size, int reserved)
 {
         int order;
         int min_objects;
@@ -2034,14 +2080,14 @@ static inline int calculate_order(int size)
         min_objects = slub_min_objects;
         if (!min_objects)
                 min_objects = 4 * (fls(nr_cpu_ids) + 1);
-        max_objects = (PAGE_SIZE << slub_max_order)/size;
+        max_objects = order_objects(slub_max_order, size, reserved);
         min_objects = min(min_objects, max_objects);
 
         while (min_objects > 1) {
                 fraction = 16;
                 while (fraction >= 4) {
                         order = slab_order(size, min_objects,
-                                                slub_max_order, fraction);
+                                        slub_max_order, fraction, reserved);
                         if (order <= slub_max_order)
                                 return order;
                         fraction /= 2;
@@ -2053,14 +2099,14 @@ static inline int calculate_order(int size)
          * We were unable to place multiple objects in a slab. Now
          * lets see if we can place a single object there.
          */
-        order = slab_order(size, 1, slub_max_order, 1);
+        order = slab_order(size, 1, slub_max_order, 1, reserved);
         if (order <= slub_max_order)
                 return order;
 
         /*
          * Doh this slab cannot be placed using slub_max_order.
          */
-        order = slab_order(size, 1, MAX_ORDER, 1);
+        order = slab_order(size, 1, MAX_ORDER, 1, reserved);
         if (order < MAX_ORDER)
                 return order;
         return -ENOSYS;
@@ -2311,7 +2357,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
         if (forced_order >= 0)
                 order = forced_order;
         else
-                order = calculate_order(size);
+                order = calculate_order(size, s->reserved);
 
         if (order < 0)
                 return 0;
@@ -2329,8 +2375,8 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
         /*
          * Determine the number of objects per slab
          */
-        s->oo = oo_make(order, size);
-        s->min = oo_make(get_order(size), size);
+        s->oo = oo_make(order, size, s->reserved);
+        s->min = oo_make(get_order(size), size, s->reserved);
         if (oo_objects(s->oo) > oo_objects(s->max))
                 s->max = s->oo;
 
@@ -2349,6 +2395,10 @@ static int kmem_cache_open(struct kmem_cache *s,
         s->objsize = size;
         s->align = align;
         s->flags = kmem_cache_flags(size, flags, name, ctor);
+        s->reserved = 0;
+
+        if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
+                s->reserved = sizeof(struct rcu_head);
 
         if (!calculate_sizes(s, -1))
                 goto error;
@@ -2399,12 +2449,6 @@ unsigned int kmem_cache_size(struct kmem_cache *s)
 }
 EXPORT_SYMBOL(kmem_cache_size);
 
-const char *kmem_cache_name(struct kmem_cache *s)
-{
-        return s->name;
-}
-EXPORT_SYMBOL(kmem_cache_name);
-
 static void list_slab_objects(struct kmem_cache *s, struct page *page,
                                                         const char *text)
 {
@@ -2696,7 +2740,6 @@ EXPORT_SYMBOL(__kmalloc_node);
 size_t ksize(const void *object)
 {
         struct page *page;
-        struct kmem_cache *s;
 
         if (unlikely(object == ZERO_SIZE_PTR))
                 return 0;
@@ -2707,28 +2750,8 @@ size_t ksize(const void *object)
                 WARN_ON(!PageCompound(page));
                 return PAGE_SIZE << compound_order(page);
         }
-        s = page->slab;
-
-#ifdef CONFIG_SLUB_DEBUG
-        /*
-         * Debugging requires use of the padding between object
-         * and whatever may come after it.
-         */
-        if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
-                return s->objsize;
 
-#endif
-        /*
-         * If we have the need to store the freelist pointer
-         * back there or track user information then we can
-         * only use the space before that information.
-         */
-        if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
-                return s->inuse;
-        /*
-         * Else we can use all the padding etc for the allocation
-         */
-        return s->size;
+        return slab_ksize(page->slab);
 }
 EXPORT_SYMBOL(ksize);
 
@@ -4017,6 +4040,12 @@ static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(destroy_by_rcu);
 
+static ssize_t reserved_show(struct kmem_cache *s, char *buf)
+{
+        return sprintf(buf, "%d\n", s->reserved);
+}
+SLAB_ATTR_RO(reserved);
+
 #ifdef CONFIG_SLUB_DEBUG
 static ssize_t slabs_show(struct kmem_cache *s, char *buf)
 {
@@ -4303,6 +4332,7 @@ static struct attribute *slab_attrs[] = {
         &reclaim_account_attr.attr,
         &destroy_by_rcu_attr.attr,
         &shrink_attr.attr,
+        &reserved_attr.attr,
 #ifdef CONFIG_SLUB_DEBUG
         &total_objects_attr.attr,
         &slabs_attr.attr,