Patched in Tegra support.

1 files changed, 711 insertions, 887 deletions

diff --git a/mm/slub.c b/mm/slub.c
index ba2ca53f6c3..f73234db904 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
-#include "slab.h"
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/kmemcheck.h>
@@ -30,22 +29,18 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 #include <linux/stacktrace.h>
-#include <linux/prefetch.h>
-#include <linux/memcontrol.h>
 
 #include <trace/events/kmem.h>
 
-#include "internal.h"
-
 /*
  * Lock order:
- *   1. slab_mutex (Global Mutex)
+ *   1. slub_lock (Global Semaphore)
  *   2. node->list_lock
  *   3. slab_lock(page) (Only on some arches and for debugging)
  *
- *   slab_mutex
+ *   slub_lock
  *
- *   The role of the slab_mutex is to protect the list of all the slabs
+ *   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
@@ -113,6 +108,9 @@
  *                      the fast path and disables lockless freelists.
  */
 
+#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
+                SLAB_TRACE | SLAB_DEBUG_FREE)
+
 static inline int kmem_cache_debug(struct kmem_cache *s)
 {
 #ifdef CONFIG_SLUB_DEBUG
@@ -177,10 +175,23 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 #define __OBJECT_POISON         0x80000000UL /* Poison object */
 #define __CMPXCHG_DOUBLE        0x40000000UL /* Use cmpxchg_double */
 
+static int kmem_size = sizeof(struct kmem_cache);
+
 #ifdef CONFIG_SMP
 static struct notifier_block slab_notifier;
 #endif
 
+static enum {
+        DOWN,           /* No slab functionality available */
+        PARTIAL,        /* Kmem_cache_node works */
+        UP,             /* Everything works but does not show up in sysfs */
+        SYSFS           /* Sysfs up */
+} slab_state = DOWN;
+
+/* A list of all slab caches on the system */
+static DECLARE_RWSEM(slub_lock);
+static LIST_HEAD(slab_caches);
+
 /*
  * Tracking user of a slab.
  */
@@ -201,14 +212,17 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
 static void sysfs_slab_remove(struct kmem_cache *);
-static void memcg_propagate_slab_attrs(struct kmem_cache *s);
+
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
                                                         { return 0; }
-static inline void sysfs_slab_remove(struct kmem_cache *s) { }
+static inline void sysfs_slab_remove(struct kmem_cache *s)
+{
+        kfree(s->name);
+        kfree(s);
+}
 
-static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
 #endif
 
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
@@ -222,6 +236,11 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
  *                      Core slab cache functions
  *******************************************************************/
 
+int slab_is_available(void)
+{
+        return slab_state >= UP;
+}
+
 static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 {
         return s->node[node];
@@ -250,11 +269,6 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object)
         return *(void **)(object + s->offset);
 }
 
-static void prefetch_freepointer(const struct kmem_cache *s, void *object)
-{
-        prefetch(object + s->offset);
-}
-
 static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 {
         void *p;
@@ -291,7 +305,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
          * and whatever may come after it.
          */
         if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
-                return s->object_size;
+                return s->objsize;
 
 #endif
         /*
@@ -352,10 +366,9 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page
                 const char *n)
 {
         VM_BUG_ON(!irqs_disabled());
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
-    defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
+#ifdef CONFIG_CMPXCHG_DOUBLE
         if (s->flags & __CMPXCHG_DOUBLE) {
-                if (cmpxchg_double(&page->freelist, &page->counters,
+                if (cmpxchg_double(&page->freelist,
                         freelist_old, counters_old,
                         freelist_new, counters_new))
                 return 1;
@@ -387,10 +400,9 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
                 void *freelist_new, unsigned long counters_new,
                 const char *n)
 {
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
-    defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
+#ifdef CONFIG_CMPXCHG_DOUBLE
         if (s->flags & __CMPXCHG_DOUBLE) {
-                if (cmpxchg_double(&page->freelist, &page->counters,
+                if (cmpxchg_double(&page->freelist,
                         freelist_old, counters_old,
                         freelist_new, counters_new))
                 return 1;
@@ -455,8 +467,34 @@ static int disable_higher_order_debug;
  */
 static void print_section(char *text, u8 *addr, unsigned int length)
 {
-        print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
-                        length, 1);
+        int i, offset;
+        int newline = 1;
+        char ascii[17];
+
+        ascii[16] = 0;
+
+        for (i = 0; i < length; i++) {
+                if (newline) {
+                        printk(KERN_ERR "%8s 0x%p: ", text, addr + i);
+                        newline = 0;
+                }
+                printk(KERN_CONT " %02x", addr[i]);
+                offset = i % 16;
+                ascii[offset] = isgraph(addr[i]) ? addr[i] : '.';
+                if (offset == 15) {
+                        printk(KERN_CONT " %s\n", ascii);
+                        newline = 1;
+                }
+        }
+        if (!newline) {
+                i %= 16;
+                while (i < 16) {
+                        printk(KERN_CONT "   ");
+                        ascii[i] = ' ';
+                        i++;
+                }
+                printk(KERN_CONT " %s\n", ascii);
+        }
 }
 
 static struct track *get_track(struct kmem_cache *s, void *object,
@@ -558,11 +596,9 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...)
         va_end(args);
         printk(KERN_ERR "========================================"
                         "=====================================\n");
-        printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf);
+        printk(KERN_ERR "BUG %s: %s\n", s->name, buf);
         printk(KERN_ERR "----------------------------------------"
                         "-------------------------------------\n\n");
-
-        add_taint(TAINT_BAD_PAGE);
 }
 
 static void slab_fix(struct kmem_cache *s, char *fmt, ...)
@@ -589,13 +625,13 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
                         p, p - addr, get_freepointer(s, p));
 
         if (p > addr + 16)
-                print_section("Bytes b4 ", p - 16, 16);
+                print_section("Bytes b4", p - 16, 16);
+
+        print_section("Object", p, min_t(unsigned long, s->objsize, PAGE_SIZE));
 
-        print_section("Object ", p, min_t(unsigned long, s->object_size,
-                                PAGE_SIZE));
         if (s->flags & SLAB_RED_ZONE)
-                print_section("Redzone ", p + s->object_size,
-                        s->inuse - s->object_size);
+                print_section("Redzone", p + s->objsize,
+                        s->inuse - s->objsize);
 
         if (s->offset)
                 off = s->offset + sizeof(void *);
@@ -607,7 +643,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 
         if (off != s->size)
                 /* Beginning of the filler is the free pointer */
-                print_section("Padding ", p + off, s->size - off);
+                print_section("Padding", p + off, s->size - off);
 
         dump_stack();
 }
@@ -619,7 +655,7 @@ static void object_err(struct kmem_cache *s, struct page *page,
         print_trailer(s, page, object);
 }
 
-static void slab_err(struct kmem_cache *s, struct page *page, const char *fmt, ...)
+static void slab_err(struct kmem_cache *s, struct page *page, char *fmt, ...)
 {
         va_list args;
         char buf[100];
@@ -637,12 +673,55 @@ static void init_object(struct kmem_cache *s, void *object, u8 val)
         u8 *p = object;
 
         if (s->flags & __OBJECT_POISON) {
-                memset(p, POISON_FREE, s->object_size - 1);
-                p[s->object_size - 1] = POISON_END;
+                memset(p, POISON_FREE, s->objsize - 1);
+                p[s->objsize - 1] = POISON_END;
         }
 
         if (s->flags & SLAB_RED_ZONE)
-                memset(p + s->object_size, val, s->inuse - s->object_size);
+                memset(p + s->objsize, val, s->inuse - s->objsize);
+}
+
+static u8 *check_bytes8(u8 *start, u8 value, unsigned int bytes)
+{
+        while (bytes) {
+                if (*start != value)
+                        return start;
+                start++;
+                bytes--;
+        }
+        return NULL;
+}
+
+static u8 *check_bytes(u8 *start, u8 value, unsigned int bytes)
+{
+        u64 value64;
+        unsigned int words, prefix;
+
+        if (bytes <= 16)
+                return check_bytes8(start, value, bytes);
+
+        value64 = value | value << 8 | value << 16 | value << 24;
+        value64 = (value64 & 0xffffffff) | value64 << 32;
+        prefix = 8 - ((unsigned long)start) % 8;
+
+        if (prefix) {
+                u8 *r = check_bytes8(start, value, prefix);
+                if (r)
+                        return r;
+                start += prefix;
+                bytes -= prefix;
+        }
+
+        words = bytes / 8;
+
+        while (words) {
+                if (*(u64 *)start != value64)
+                        return check_bytes8(start, value, 8);
+                start += 8;
+                words--;
+        }
+
+        return check_bytes8(start, value, bytes % 8);
 }
 
 static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
@@ -659,7 +738,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
         u8 *fault;
         u8 *end;
 
-        fault = memchr_inv(start, value, bytes);
+        fault = check_bytes(start, value, bytes);
         if (!fault)
                 return 1;
 
@@ -687,10 +766,10 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
  *      Poisoning uses 0x6b (POISON_FREE) and the last byte is
  *      0xa5 (POISON_END)
  *
- * object + s->object_size
+ * object + s->objsize
  *      Padding to reach word boundary. This is also used for Redzoning.
  *      Padding is extended by another word if Redzoning is enabled and
- *      object_size == inuse.
+ *      objsize == inuse.
  *
  *      We fill with 0xbb (RED_INACTIVE) for inactive objects and with
  *      0xcc (RED_ACTIVE) for objects in use.
@@ -709,7 +788,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
  * object + s->size
  *      Nothing is used beyond s->size.
  *
- * If slabcaches are merged then the object_size and inuse boundaries are mostly
+ * If slabcaches are merged then the objsize and inuse boundaries are mostly
  * ignored. And therefore no slab options that rely on these boundaries
  * may be used with merged slabcaches.
  */
@@ -752,14 +831,14 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
         if (!remainder)
                 return 1;
 
-        fault = memchr_inv(end - remainder, POISON_INUSE, remainder);
+        fault = check_bytes(end - remainder, POISON_INUSE, remainder);
         if (!fault)
                 return 1;
         while (end > fault && end[-1] == POISON_INUSE)
                 end--;
 
         slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
-        print_section("Padding ", end - remainder, remainder);
+        print_section("Padding", end - remainder, remainder);
 
         restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
         return 0;
@@ -769,25 +848,25 @@ static int check_object(struct kmem_cache *s, struct page *page,
                                         void *object, u8 val)
 {
         u8 *p = object;
-        u8 *endobject = object + s->object_size;
+        u8 *endobject = object + s->objsize;
 
         if (s->flags & SLAB_RED_ZONE) {
                 if (!check_bytes_and_report(s, page, object, "Redzone",
-                        endobject, val, s->inuse - s->object_size))
+                        endobject, val, s->inuse - s->objsize))
                         return 0;
         } else {
-                if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
+                if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) {
                         check_bytes_and_report(s, page, p, "Alignment padding",
-                                endobject, POISON_INUSE, s->inuse - s->object_size);
+                                endobject, POISON_INUSE, s->inuse - s->objsize);
                 }
         }
 
         if (s->flags & SLAB_POISON) {
                 if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
                         (!check_bytes_and_report(s, page, p, "Poison", p,
-                                        POISON_FREE, s->object_size - 1) ||
+                                        POISON_FREE, s->objsize - 1) ||
                          !check_bytes_and_report(s, page, p, "Poison",
-                                p + s->object_size - 1, POISON_END, 1)))
+                                p + s->objsize - 1, POISON_END, 1)))
                         return 0;
                 /*
                  * check_pad_bytes cleans up on its own.
@@ -908,7 +987,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
                         page->freelist);
 
                 if (!alloc)
-                        print_section("Object ", (void *)object, s->object_size);
+                        print_section("Object", (void *)object, s->objsize);
 
                 dump_stack();
         }
@@ -924,14 +1003,14 @@ static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
         lockdep_trace_alloc(flags);
         might_sleep_if(flags & __GFP_WAIT);
 
-        return should_failslab(s->object_size, flags, s->flags);
+        return should_failslab(s->objsize, flags, s->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, slab_ksize(s));
-        kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags);
+        kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags);
 }
 
 static inline void slab_free_hook(struct kmem_cache *s, void *x)
@@ -948,13 +1027,13 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
                 unsigned long flags;
 
                 local_irq_save(flags);
-                kmemcheck_slab_free(s, x, s->object_size);
-                debug_check_no_locks_freed(x, s->object_size);
+                kmemcheck_slab_free(s, x, s->objsize);
+                debug_check_no_locks_freed(x, s->objsize);
                 local_irq_restore(flags);
         }
 #endif
         if (!(s->flags & SLAB_DEBUG_OBJECTS))
-                debug_check_no_obj_freed(x, s->object_size);
+                debug_check_no_obj_freed(x, s->objsize);
 }
 
 /*
@@ -1064,13 +1143,13 @@ bad:
         return 0;
 }
 
-static noinline struct kmem_cache_node *free_debug_processing(
-        struct kmem_cache *s, struct page *page, void *object,
-        unsigned long addr, unsigned long *flags)
+static noinline int free_debug_processing(struct kmem_cache *s,
+                 struct page *page, void *object, unsigned long addr)
 {
-        struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+        unsigned long flags;
+        int rc = 0;
 
-        spin_lock_irqsave(&n->list_lock, *flags);
+        local_irq_save(flags);
         slab_lock(page);
 
         if (!check_slab(s, page))
@@ -1089,11 +1168,11 @@ static noinline struct kmem_cache_node *free_debug_processing(
         if (!check_object(s, page, object, SLUB_RED_ACTIVE))
                 goto out;
 
-        if (unlikely(s != page->slab_cache)) {
+        if (unlikely(s != page->slab)) {
                 if (!PageSlab(page)) {
                         slab_err(s, page, "Attempt to free object(0x%p) "
                                 "outside of slab", object);
-                } else if (!page->slab_cache) {
+                } else if (!page->slab) {
                         printk(KERN_ERR
                                 "SLUB <none>: no slab for object 0x%p.\n",
                                                 object);
@@ -1108,19 +1187,15 @@ static noinline struct kmem_cache_node *free_debug_processing(
                 set_track(s, object, TRACK_FREE, addr);
         trace(s, page, object, 0);
         init_object(s, object, SLUB_RED_INACTIVE);
+        rc = 1;
 out:
         slab_unlock(page);
-        /*
-         * Keep node_lock to preserve integrity
-         * until the object is actually freed
-         */
-        return n;
+        local_irq_restore(flags);
+        return rc;
 
 fail:
-        slab_unlock(page);
-        spin_unlock_irqrestore(&n->list_lock, *flags);
         slab_fix(s, "Object at 0x%p not freed", object);
-        return NULL;
+        goto out;
 }
 
 static int __init setup_slub_debug(char *str)
@@ -1193,7 +1268,7 @@ out:
 
 __setup("slub_debug", setup_slub_debug);
 
-static unsigned long kmem_cache_flags(unsigned long object_size,
+static unsigned long kmem_cache_flags(unsigned long objsize,
         unsigned long flags, const char *name,
         void (*ctor)(void *))
 {
@@ -1213,9 +1288,8 @@ static inline void setup_object_debug(struct kmem_cache *s,
 static inline int alloc_debug_processing(struct kmem_cache *s,
         struct page *page, void *object, unsigned long addr) { return 0; }
 
-static inline struct kmem_cache_node *free_debug_processing(
-        struct kmem_cache *s, struct page *page, void *object,
-        unsigned long addr, unsigned long *flags) { return NULL; }
+static inline int free_debug_processing(struct kmem_cache *s,
+        struct page *page, void *object, unsigned long addr) { return 0; }
 
 static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
                         { return 1; }
@@ -1224,7 +1298,7 @@ static inline int check_object(struct kmem_cache *s, struct page *page,
 static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
                                         struct page *page) {}
 static inline void remove_full(struct kmem_cache *s, struct page *page) {}
-static inline unsigned long kmem_cache_flags(unsigned long object_size,
+static inline unsigned long kmem_cache_flags(unsigned long objsize,
         unsigned long flags, const char *name,
         void (*ctor)(void *))
 {
@@ -1301,7 +1375,13 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
                         stat(s, ORDER_FALLBACK);
         }
 
-        if (kmemcheck_enabled && page
+        if (flags & __GFP_WAIT)
+                local_irq_disable();
+
+        if (!page)
+                return NULL;
+
+        if (kmemcheck_enabled
                 && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
                 int pages = 1 << oo_order(oo);
 
@@ -1317,11 +1397,6 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
                         kmemcheck_mark_unallocated_pages(page, pages);
         }
 
-        if (flags & __GFP_WAIT)
-                local_irq_disable();
-        if (!page)
-                return NULL;
-
         page->objects = oo_objects(oo);
         mod_zone_page_state(page_zone(page),
                 (s->flags & SLAB_RECLAIM_ACCOUNT) ?
@@ -1345,7 +1420,6 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
         void *start;
         void *last;
         void *p;
-        int order;
 
         BUG_ON(flags & GFP_SLAB_BUG_MASK);
 
@@ -1354,18 +1428,14 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
         if (!page)
                 goto out;
 
-        order = compound_order(page);
         inc_slabs_node(s, page_to_nid(page), page->objects);
-        memcg_bind_pages(s, order);
-        page->slab_cache = s;
-        __SetPageSlab(page);
-        if (page->pfmemalloc)
-                SetPageSlabPfmemalloc(page);
+        page->slab = s;
+        page->flags |= 1 << PG_slab;
 
         start = page_address(page);
 
         if (unlikely(s->flags & SLAB_POISON))
-                memset(start, POISON_INUSE, PAGE_SIZE << order);
+                memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
 
         last = start;
         for_each_object(p, s, start, page->objects) {
@@ -1377,7 +1447,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
         set_freepointer(s, last, NULL);
 
         page->freelist = start;
-        page->inuse = page->objects;
+        page->inuse = 0;
         page->frozen = 1;
 out:
         return page;
@@ -1404,14 +1474,11 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
                 NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
                 -pages);
 
-        __ClearPageSlabPfmemalloc(page);
         __ClearPageSlab(page);
-
-        memcg_release_pages(s, order);
         reset_page_mapcount(page);
         if (current->reclaim_state)
                 current->reclaim_state->reclaimed_slab += pages;
-        __free_memcg_kmem_pages(page, order);
+        __free_pages(page, order);
 }
 
 #define need_reserve_slab_rcu                                           \
@@ -1426,7 +1493,7 @@ static void rcu_free_slab(struct rcu_head *h)
         else
                 page = container_of((struct list_head *)h, struct page, lru);
 
-        __free_slab(page->slab_cache, page);
+        __free_slab(page->slab, page);
 }
 
 static void free_slab(struct kmem_cache *s, struct page *page)
@@ -1467,7 +1534,7 @@ static inline void add_partial(struct kmem_cache_node *n,
                                 struct page *page, int tail)
 {
         n->nr_partial++;
-        if (tail == DEACTIVATE_TO_TAIL)
+        if (tail)
                 list_add_tail(&page->lru, &n->partial);
         else
                 list_add(&page->lru, &n->partial);
@@ -1484,16 +1551,13 @@ static inline void remove_partial(struct kmem_cache_node *n,
 }
 
 /*
- * Remove slab from the partial list, freeze it and
- * return the pointer to the freelist.
+ * Lock slab, remove from the partial list and put the object into the
+ * per cpu freelist.
  *
- * Returns a list of objects or NULL if it fails.
- *
- * Must hold list_lock since we modify the partial list.
+ * Must hold list_lock.
  */
-static inline void *acquire_slab(struct kmem_cache *s,
-                struct kmem_cache_node *n, struct page *page,
-                int mode)
+static inline int acquire_slab(struct kmem_cache *s,
+                struct kmem_cache_node *n, struct page *page)
 {
         void *freelist;
         unsigned long counters;
@@ -1504,41 +1568,47 @@ static inline void *acquire_slab(struct kmem_cache *s,
          * The old freelist is the list of objects for the
          * per cpu allocation list.
          */
-        freelist = page->freelist;
-        counters = page->counters;
-        new.counters = counters;
-        if (mode) {
+        do {
+                freelist = page->freelist;
+                counters = page->counters;
+                new.counters = counters;
                 new.inuse = page->objects;
-                new.freelist = NULL;
-        } else {
-                new.freelist = freelist;
-        }
 
-        VM_BUG_ON(new.frozen);
-        new.frozen = 1;
+                VM_BUG_ON(new.frozen);
+                new.frozen = 1;
 
-        if (!__cmpxchg_double_slab(s, page,
+        } while (!__cmpxchg_double_slab(s, page,
                         freelist, counters,
-                        new.freelist, new.counters,
-                        "acquire_slab"))
-                return NULL;
+                        NULL, new.counters,
+                        "lock and freeze"));
 
         remove_partial(n, page);
-        WARN_ON(!freelist);
-        return freelist;
-}
 
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
-static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
+        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);
+                return 0;
+        }
+}
 
 /*
  * Try to allocate a partial slab from a specific node.
  */
-static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
-                                struct kmem_cache_cpu *c, gfp_t flags)
+static struct page *get_partial_node(struct kmem_cache *s,
+                                        struct kmem_cache_node *n)
 {
-        struct page *page, *page2;
-        void *object = NULL;
+        struct page *page;
 
         /*
          * Racy check. If we mistakenly see no partial slabs then we
@@ -1550,47 +1620,26 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
                 return NULL;
 
         spin_lock(&n->list_lock);
-        list_for_each_entry_safe(page, page2, &n->partial, lru) {
-                void *t;
-                int available;
-
-                if (!pfmemalloc_match(page, flags))
-                        continue;
-
-                t = acquire_slab(s, n, page, object == NULL);
-                if (!t)
-                        break;
-
-                if (!object) {
-                        c->page = page;
-                        stat(s, ALLOC_FROM_PARTIAL);
-                        object = t;
-                        available =  page->objects - page->inuse;
-                } else {
-                        available = put_cpu_partial(s, page, 0);
-                        stat(s, CPU_PARTIAL_NODE);
-                }
-                if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
-                        break;
-
-        }
+        list_for_each_entry(page, &n->partial, lru)
+                if (acquire_slab(s, n, page))
+                        goto out;
+        page = NULL;
+out:
         spin_unlock(&n->list_lock);
-        return object;
+        return page;
 }
 
 /*
  * Get a page from somewhere. Search in increasing NUMA distances.
  */
-static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
-                struct kmem_cache_cpu *c)
+static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 {
 #ifdef CONFIG_NUMA
         struct zonelist *zonelist;
         struct zoneref *z;
         struct zone *zone;
         enum zone_type high_zoneidx = gfp_zone(flags);
-        void *object;
-        unsigned int cpuset_mems_cookie;
+        struct page *page;
 
         /*
          * The defrag ratio allows a configuration of the tradeoffs between
@@ -1614,32 +1663,23 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
                         get_cycles() % 1024 > s->remote_node_defrag_ratio)
                 return NULL;
 
-        do {
-                cpuset_mems_cookie = get_mems_allowed();
-                zonelist = node_zonelist(slab_node(), flags);
-                for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-                        struct kmem_cache_node *n;
-
-                        n = get_node(s, zone_to_nid(zone));
-
-                        if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
-                                        n->nr_partial > s->min_partial) {
-                                object = get_partial_node(s, n, c, flags);
-                                if (object) {
-                                        /*
-                                         * Return the object even if
-                                         * put_mems_allowed indicated that
-                                         * the cpuset mems_allowed was
-                                         * updated in parallel. It's a
-                                         * harmless race between the alloc
-                                         * and the cpuset update.
-                                         */
-                                        put_mems_allowed(cpuset_mems_cookie);
-                                        return object;
-                                }
+        get_mems_allowed();
+        zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+        for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+                struct kmem_cache_node *n;
+
+                n = get_node(s, zone_to_nid(zone));
+
+                if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+                                n->nr_partial > s->min_partial) {
+                        page = get_partial_node(s, n);
+                        if (page) {
+                                put_mems_allowed();
+                                return page;
                         }
                 }
-        } while (!put_mems_allowed(cpuset_mems_cookie));
+        }
+        put_mems_allowed();
 #endif
         return NULL;
 }
@@ -1647,17 +1687,16 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 /*
  * Get a partial page, lock it and return it.
  */
-static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
-                struct kmem_cache_cpu *c)
+static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
 {
-        void *object;
+        struct page *page;
         int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
 
-        object = get_partial_node(s, get_node(s, searchnode), c, flags);
-        if (object || node != NUMA_NO_NODE)
-                return object;
+        page = get_partial_node(s, get_node(s, searchnode));
+        if (page || node != NUMA_NO_NODE)
+                return page;
 
-        return get_any_partial(s, flags, c);
+        return get_any_partial(s, flags);
 }
 
 #ifdef CONFIG_PREEMPT
@@ -1719,33 +1758,43 @@ static inline void note_cmpxchg_failure(const char *n,
         stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
 }
 
-static void init_kmem_cache_cpus(struct kmem_cache *s)
+void init_kmem_cache_cpus(struct kmem_cache *s)
 {
         int cpu;
 
         for_each_possible_cpu(cpu)
                 per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu);
 }
+/*
+ * Remove the cpu slab
+ */
 
 /*
  * Remove the cpu slab
  */
-static void deactivate_slab(struct kmem_cache *s, struct page *page, void *freelist)
+static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
         enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
+        struct page *page = c->page;
         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 = DEACTIVATE_TO_HEAD;
+        int tail = 0;
         struct page new;
         struct page old;
 
         if (page->freelist) {
                 stat(s, DEACTIVATE_REMOTE_FREES);
-                tail = DEACTIVATE_TO_TAIL;
+                tail = 1;
         }
 
+        c->tid = next_tid(c->tid);
+        c->page = NULL;
+        freelist = c->freelist;
+        c->freelist = NULL;
+
         /*
          * Stage one: Free all available per cpu objects back
          * to the page freelist while it is still frozen. Leave the
@@ -1844,7 +1893,7 @@ redo:
                 if (m == M_PARTIAL) {
 
                         add_partial(n, page, tail);
-                        stat(s, tail);
+                        stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
 
                 } else if (m == M_FULL) {
 
@@ -1871,130 +1920,10 @@ redo:
         }
 }
 
-/*
- * Unfreeze all the cpu partial slabs.
- *
- * This function must be called with interrupts disabled
- * for the cpu using c (or some other guarantee must be there
- * to guarantee no concurrent accesses).
- */
-static void unfreeze_partials(struct kmem_cache *s,
-                struct kmem_cache_cpu *c)
-{
-        struct kmem_cache_node *n = NULL, *n2 = NULL;
-        struct page *page, *discard_page = NULL;
-
-        while ((page = c->partial)) {
-                struct page new;
-                struct page old;
-
-                c->partial = page->next;
-
-                n2 = get_node(s, page_to_nid(page));
-                if (n != n2) {
-                        if (n)
-                                spin_unlock(&n->list_lock);
-
-                        n = n2;
-                        spin_lock(&n->list_lock);
-                }
-
-                do {
-
-                        old.freelist = page->freelist;
-                        old.counters = page->counters;
-                        VM_BUG_ON(!old.frozen);
-
-                        new.counters = old.counters;
-                        new.freelist = old.freelist;
-
-                        new.frozen = 0;
-
-                } while (!__cmpxchg_double_slab(s, page,
-                                old.freelist, old.counters,
-                                new.freelist, new.counters,
-                                "unfreezing slab"));
-
-                if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) {
-                        page->next = discard_page;
-                        discard_page = page;
-                } else {
-                        add_partial(n, page, DEACTIVATE_TO_TAIL);
-                        stat(s, FREE_ADD_PARTIAL);
-                }
-        }
-
-        if (n)
-                spin_unlock(&n->list_lock);
-
-        while (discard_page) {
-                page = discard_page;
-                discard_page = discard_page->next;
-
-                stat(s, DEACTIVATE_EMPTY);
-                discard_slab(s, page);
-                stat(s, FREE_SLAB);
-        }
-}
-
-/*
- * Put a page that was just frozen (in __slab_free) into a partial page
- * slot if available. This is done without interrupts disabled and without
- * preemption disabled. The cmpxchg is racy and may put the partial page
- * onto a random cpus partial slot.
- *
- * If we did not find a slot then simply move all the partials to the
- * per node partial list.
- */
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
-{
-        struct page *oldpage;
-        int pages;
-        int pobjects;
-
-        do {
-                pages = 0;
-                pobjects = 0;
-                oldpage = this_cpu_read(s->cpu_slab->partial);
-
-                if (oldpage) {
-                        pobjects = oldpage->pobjects;
-                        pages = oldpage->pages;
-                        if (drain && pobjects > s->cpu_partial) {
-                                unsigned long flags;
-                                /*
-                                 * partial array is full. Move the existing
-                                 * set to the per node partial list.
-                                 */
-                                local_irq_save(flags);
-                                unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
-                                local_irq_restore(flags);
-                                oldpage = NULL;
-                                pobjects = 0;
-                                pages = 0;
-                                stat(s, CPU_PARTIAL_DRAIN);
-                        }
-                }
-
-                pages++;
-                pobjects += page->objects - page->inuse;
-
-                page->pages = pages;
-                page->pobjects = pobjects;
-                page->next = oldpage;
-
-        } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
-        return pobjects;
-}
-
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
         stat(s, CPUSLAB_FLUSH);
-        deactivate_slab(s, c->page, c->freelist);
-
-        c->tid = next_tid(c->tid);
-        c->page = NULL;
-        c->freelist = NULL;
+        deactivate_slab(s, c);
 }
 
 /*
@@ -2006,12 +1935,8 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 {
         struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
-        if (likely(c)) {
-                if (c->page)
-                        flush_slab(s, c);
-
-                unfreeze_partials(s, c);
-        }
+        if (likely(c && c->page))
+                flush_slab(s, c);
 }
 
 static void flush_cpu_slab(void *d)
@@ -2021,27 +1946,19 @@ static void flush_cpu_slab(void *d)
         __flush_cpu_slab(s, smp_processor_id());
 }
 
-static bool has_cpu_slab(int cpu, void *info)
-{
-        struct kmem_cache *s = info;
-        struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
-
-        return c->page || c->partial;
-}
-
 static void flush_all(struct kmem_cache *s)
 {
-        on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
+        on_each_cpu(flush_cpu_slab, s, 1);
 }
 
 /*
  * Check if the objects in a per cpu structure fit numa
  * locality expectations.
  */
-static inline int node_match(struct page *page, int node)
+static inline int node_match(struct kmem_cache_cpu *c, int node)
 {
 #ifdef CONFIG_NUMA
-        if (node != NUMA_NO_NODE && page_to_nid(page) != node)
+        if (node != NUMA_NO_NODE && c->node != node)
                 return 0;
 #endif
         return 1;
@@ -2084,10 +2001,10 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
                 "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n",
                 nid, gfpflags);
         printk(KERN_WARNING "  cache: %s, object size: %d, buffer size: %d, "
-                "default order: %d, min order: %d\n", s->name, s->object_size,
+                "default order: %d, min order: %d\n", s->name, s->objsize,
                 s->size, oo_order(s->oo), oo_order(s->min));
 
-        if (oo_order(s->min) > get_order(s->object_size))
+        if (oo_order(s->min) > get_order(s->objsize))
                 printk(KERN_WARNING "  %s debugging increased min order, use "
                        "slub_debug=O to disable.\n", s->name);
 
@@ -2110,86 +2027,12 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
         }
 }
 
-static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
-                        int node, struct kmem_cache_cpu **pc)
-{
-        void *freelist;
-        struct kmem_cache_cpu *c = *pc;
-        struct page *page;
-
-        freelist = get_partial(s, flags, node, c);
-
-        if (freelist)
-                return freelist;
-
-        page = new_slab(s, flags, node);
-        if (page) {
-                c = __this_cpu_ptr(s->cpu_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
-                 */
-                freelist = page->freelist;
-                page->freelist = NULL;
-
-                stat(s, ALLOC_SLAB);
-                c->page = page;
-                *pc = c;
-        } else
-                freelist = NULL;
-
-        return freelist;
-}
-
-static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
-{
-        if (unlikely(PageSlabPfmemalloc(page)))
-                return gfp_pfmemalloc_allowed(gfpflags);
-
-        return true;
-}
-
-/*
- * Check the page->freelist of a page and either transfer the freelist to the per cpu freelist
- * or deactivate the page.
- *
- * The page is still frozen if the return value is not NULL.
- *
- * If this function returns NULL then the page has been unfrozen.
- *
- * This function must be called with interrupt disabled.
- */
-static inline void *get_freelist(struct kmem_cache *s, struct page *page)
-{
-        struct page new;
-        unsigned long counters;
-        void *freelist;
-
-        do {
-                freelist = page->freelist;
-                counters = page->counters;
-
-                new.counters = counters;
-                VM_BUG_ON(!new.frozen);
-
-                new.inuse = page->objects;
-                new.frozen = freelist != NULL;
-
-        } while (!__cmpxchg_double_slab(s, page,
-                freelist, counters,
-                NULL, new.counters,
-                "get_freelist"));
-
-        return freelist;
-}
-
 /*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
  *
+ * Interrupts are disabled.
+ *
  * Processing is still very fast if new objects have been freed to the
  * regular freelist. In that case we simply take over the regular freelist
  * as the lockless freelist and zap the regular freelist.
@@ -2205,9 +2048,11 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
 static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
                           unsigned long addr, struct kmem_cache_cpu *c)
 {
-        void *freelist;
+        void **object;
         struct page *page;
         unsigned long flags;
+        struct page new;
+        unsigned long counters;
 
         local_irq_save(flags);
 #ifdef CONFIG_PREEMPT
@@ -2219,41 +2064,51 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
         c = this_cpu_ptr(s->cpu_slab);
 #endif
 
+        /* We handle __GFP_ZERO in the caller */
+        gfpflags &= ~__GFP_ZERO;
+
         page = c->page;
         if (!page)
                 goto new_slab;
-redo:
 
-        if (unlikely(!node_match(page, node))) {
+        if (unlikely(!node_match(c, node))) {
                 stat(s, ALLOC_NODE_MISMATCH);
-                deactivate_slab(s, page, c->freelist);
-                c->page = NULL;
-                c->freelist = NULL;
-                goto new_slab;
-        }
-
-        /*
-         * By rights, we should be searching for a slab page that was
-         * PFMEMALLOC but right now, we are losing the pfmemalloc
-         * information when the page leaves the per-cpu allocator
-         */
-        if (unlikely(!pfmemalloc_match(page, gfpflags))) {
-                deactivate_slab(s, page, c->freelist);
-                c->page = NULL;
-                c->freelist = NULL;
+                deactivate_slab(s, c);
                 goto new_slab;
         }
 
         /* must check again c->freelist in case of cpu migration or IRQ */
-        freelist = c->freelist;
-        if (freelist)
+        object = c->freelist;
+        if (object)
                 goto load_freelist;
 
         stat(s, ALLOC_SLOWPATH);
 
-        freelist = get_freelist(s, page);
+        do {
+                object = page->freelist;
+                counters = page->counters;
+                new.counters = counters;
+                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,
+                        "__slab_alloc"));
 
-        if (!freelist) {
+        if (unlikely(!object)) {
                 c->page = NULL;
                 stat(s, DEACTIVATE_BYPASS);
                 goto new_slab;
@@ -2262,50 +2117,61 @@ redo:
         stat(s, ALLOC_REFILL);
 
 load_freelist:
-        /*
-         * freelist is pointing to the list of objects to be used.
-         * page is pointing to the page from which the objects are obtained.
-         * That page must be frozen for per cpu allocations to work.
-         */
-        VM_BUG_ON(!c->page->frozen);
-        c->freelist = get_freepointer(s, freelist);
+        VM_BUG_ON(!page->frozen);
+        c->freelist = get_freepointer(s, object);
         c->tid = next_tid(c->tid);
         local_irq_restore(flags);
-        return freelist;
+        return object;
 
 new_slab:
+        page = get_partial(s, gfpflags, node);
+        if (page) {
+                stat(s, ALLOC_FROM_PARTIAL);
+                object = c->freelist;
 
-        if (c->partial) {
-                page = c->page = c->partial;
-                c->partial = page->next;
-                stat(s, CPU_PARTIAL_ALLOC);
-                c->freelist = NULL;
-                goto redo;
+                if (kmem_cache_debug(s))
+                        goto debug;
+                goto load_freelist;
         }
 
-        freelist = new_slab_objects(s, gfpflags, node, &c);
+        page = new_slab(s, gfpflags, node);
 
-        if (unlikely(!freelist)) {
-                if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
-                        slab_out_of_memory(s, gfpflags, node);
+        if (page) {
+                c = __this_cpu_ptr(s->cpu_slab);
+                if (c->page)
+                        flush_slab(s, c);
 
-                local_irq_restore(flags);
-                return NULL;
-        }
+                /*
+                 * No other reference to the page yet so we can
+                 * muck around with it freely without cmpxchg
+                 */
+                object = page->freelist;
+                page->freelist = NULL;
+                page->inuse = page->objects;
 
-        page = c->page;
-        if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags)))
+                stat(s, ALLOC_SLAB);
+                c->node = page_to_nid(page);
+                c->page = page;
+
+                if (kmem_cache_debug(s))
+                        goto debug;
                 goto load_freelist;
+        }
+        if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
+                slab_out_of_memory(s, gfpflags, node);
+        local_irq_restore(flags);
+        return NULL;
 
-        /* Only entered in the debug case */
-        if (kmem_cache_debug(s) && !alloc_debug_processing(s, page, freelist, addr))
-                goto new_slab;  /* Slab failed checks. Next slab needed */
+debug:
+        if (!object || !alloc_debug_processing(s, page, object, addr))
+                goto new_slab;
 
-        deactivate_slab(s, page, get_freepointer(s, freelist));
+        c->freelist = get_freepointer(s, object);
+        deactivate_slab(s, c);
         c->page = NULL;
-        c->freelist = NULL;
+        c->node = NUMA_NO_NODE;
         local_irq_restore(flags);
-        return freelist;
+        return object;
 }
 
 /*
@@ -2318,18 +2184,16 @@ new_slab:
  *
  * Otherwise we can simply pick the next object from the lockless free list.
  */
-static __always_inline void *slab_alloc_node(struct kmem_cache *s,
+static __always_inline void *slab_alloc(struct kmem_cache *s,
                 gfp_t gfpflags, int node, unsigned long addr)
 {
         void **object;
         struct kmem_cache_cpu *c;
-        struct page *page;
         unsigned long tid;
 
         if (slab_pre_alloc_hook(s, gfpflags))
                 return NULL;
 
-        s = memcg_kmem_get_cache(s, gfpflags);
 redo:
 
         /*
@@ -2350,13 +2214,11 @@ redo:
         barrier();
 
         object = c->freelist;
-        page = c->page;
-        if (unlikely(!object || !node_match(page, node)))
+        if (unlikely(!object || !node_match(c, node)))
+
                 object = __slab_alloc(s, gfpflags, node, addr, c);
 
         else {
-                void *next_object = get_freepointer_safe(s, object);
-
                 /*
                  * The cmpxchg will only match if there was no additional
                  * operation and if we are on the right processor.
@@ -2369,37 +2231,30 @@ redo:
                  * Since this is without lock semantics the protection is only against
                  * code executing on this cpu *not* from access by other cpus.
                  */
-                if (unlikely(!this_cpu_cmpxchg_double(
+                if (unlikely(!irqsafe_cpu_cmpxchg_double(
                                 s->cpu_slab->freelist, s->cpu_slab->tid,
                                 object, tid,
-                                next_object, next_tid(tid)))) {
+                                get_freepointer_safe(s, object), next_tid(tid)))) {
 
                         note_cmpxchg_failure("slab_alloc", s, tid);
                         goto redo;
                 }
-                prefetch_freepointer(s, next_object);
                 stat(s, ALLOC_FASTPATH);
         }
 
         if (unlikely(gfpflags & __GFP_ZERO) && object)
-                memset(object, 0, s->object_size);
+                memset(object, 0, s->objsize);
 
         slab_post_alloc_hook(s, gfpflags, object);
 
         return object;
 }
 
-static __always_inline void *slab_alloc(struct kmem_cache *s,
-                gfp_t gfpflags, unsigned long addr)
-{
-        return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr);
-}
-
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 {
-        void *ret = slab_alloc(s, gfpflags, _RET_IP_);
+        void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
 
-        trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags);
+        trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags);
 
         return ret;
 }
@@ -2408,7 +2263,7 @@ EXPORT_SYMBOL(kmem_cache_alloc);
 #ifdef CONFIG_TRACING
 void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
 {
-        void *ret = slab_alloc(s, gfpflags, _RET_IP_);
+        void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
         trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
         return ret;
 }
@@ -2426,10 +2281,10 @@ EXPORT_SYMBOL(kmalloc_order_trace);
 #ifdef CONFIG_NUMA
 void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
-        void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
+        void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
 
         trace_kmem_cache_alloc_node(_RET_IP_, ret,
-                                    s->object_size, s->size, gfpflags, node);
+                                    s->objsize, s->size, gfpflags, node);
 
         return ret;
 }
@@ -2440,7 +2295,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
                                     gfp_t gfpflags,
                                     int node, size_t size)
 {
-        void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
+        void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
 
         trace_kmalloc_node(_RET_IP_, ret,
                            size, s->size, gfpflags, node);
@@ -2464,6 +2319,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
         void *prior;
         void **object = (void *)x;
         int was_frozen;
+        int inuse;
         struct page new;
         unsigned long counters;
         struct kmem_cache_node *n = NULL;
@@ -2471,46 +2327,29 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 
         stat(s, FREE_SLOWPATH);
 
-        if (kmem_cache_debug(s) &&
-                !(n = free_debug_processing(s, page, x, addr, &flags)))
+        if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
                 return;
 
         do {
-                if (unlikely(n)) {
-                        spin_unlock_irqrestore(&n->list_lock, flags);
-                        n = NULL;
-                }
                 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) {
-
-                        if (!kmem_cache_debug(s) && !prior)
-
-                                /*
-                                 * Slab was on no list before and will be partially empty
-                                 * We can defer the list move and instead freeze it.
-                                 */
-                                new.frozen = 1;
-
-                        else { /* Needs to be taken off a list */
-
-                                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_irqsave(&n->list_lock, flags);
-
-                        }
+                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_irqsave(&n->list_lock, flags);
                 }
+                inuse = new.inuse;
 
         } while (!cmpxchg_double_slab(s, page,
                 prior, counters,
@@ -2518,16 +2357,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
                 "__slab_free"));
 
         if (likely(!n)) {
-
-                /*
-                 * If we just froze the page then put it onto the
-                 * per cpu partial list.
-                 */
-                if (new.frozen && !was_frozen) {
-                        put_cpu_partial(s, page, 1);
-                        stat(s, CPU_PARTIAL_FREE);
-                }
-                /*
+                /*
                  * The list lock was not taken therefore no list
                  * activity can be necessary.
                  */
@@ -2536,17 +2366,25 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
                 return;
         }
 
-        if (unlikely(!new.inuse && n->nr_partial > s->min_partial))
-                goto slab_empty;
-
         /*
-         * 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 (kmem_cache_debug(s) && unlikely(!prior)) {
-                remove_full(s, page);
-                add_partial(n, page, DEACTIVATE_TO_TAIL);
-                stat(s, FREE_ADD_PARTIAL);
+        if (was_frozen)
+                stat(s, FREE_FROZEN);
+        else {
+                if (unlikely(!inuse && n->nr_partial > s->min_partial))
+                        goto slab_empty;
+
+                /*
+                 * 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, 1);
+                        stat(s, FREE_ADD_PARTIAL);
+                }
         }
         spin_unlock_irqrestore(&n->list_lock, flags);
         return;
@@ -2588,6 +2426,7 @@ static __always_inline void slab_free(struct kmem_cache *s,
         slab_free_hook(s, x);
 
 redo:
+
         /*
          * Determine the currently cpus per cpu slab.
          * The cpu may change afterward. However that does not matter since
@@ -2602,7 +2441,7 @@ redo:
         if (likely(page == c->page)) {
                 set_freepointer(s, object, c->freelist);
 
-                if (unlikely(!this_cpu_cmpxchg_double(
+                if (unlikely(!irqsafe_cpu_cmpxchg_double(
                                 s->cpu_slab->freelist, s->cpu_slab->tid,
                                 c->freelist, tid,
                                 object, next_tid(tid)))) {
@@ -2618,10 +2457,12 @@ redo:
 
 void kmem_cache_free(struct kmem_cache *s, void *x)
 {
-        s = cache_from_obj(s, x);
-        if (!s)
-                return;
-        slab_free(s, virt_to_head_page(x), x, _RET_IP_);
+        struct page *page;
+
+        page = virt_to_head_page(x);
+
+        slab_free(s, page, x, _RET_IP_);
+
         trace_kmem_cache_free(_RET_IP_, x);
 }
 EXPORT_SYMBOL(kmem_cache_free);
@@ -2759,8 +2600,34 @@ static inline int calculate_order(int size, int reserved)
         return -ENOSYS;
 }
 
+/*
+ * Figure out what the alignment of the objects will be.
+ */
+static unsigned long calculate_alignment(unsigned long flags,
+                unsigned long align, unsigned long size)
+{
+        /*
+         * If the user wants hardware cache aligned objects then follow that
+         * suggestion if the object is sufficiently large.
+         *
+         * The hardware cache alignment cannot override the specified
+         * alignment though. If that is greater then use it.
+         */
+        if (flags & SLAB_HWCACHE_ALIGN) {
+                unsigned long ralign = cache_line_size();
+                while (size <= ralign / 2)
+                        ralign /= 2;
+                align = max(align, ralign);
+        }
+
+        if (align < ARCH_SLAB_MINALIGN)
+                align = ARCH_SLAB_MINALIGN;
+
+        return ALIGN(align, sizeof(void *));
+}
+
 static void
-init_kmem_cache_node(struct kmem_cache_node *n)
+init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 {
         n->nr_partial = 0;
         spin_lock_init(&n->list_lock);
@@ -2823,17 +2690,17 @@ static void early_kmem_cache_node_alloc(int node)
         n = page->freelist;
         BUG_ON(!n);
         page->freelist = get_freepointer(kmem_cache_node, n);
-        page->inuse = 1;
+        page->inuse++;
         page->frozen = 0;
         kmem_cache_node->node[node] = n;
 #ifdef CONFIG_SLUB_DEBUG
         init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
         init_tracking(kmem_cache_node, n);
 #endif
-        init_kmem_cache_node(n);
+        init_kmem_cache_node(n, kmem_cache_node);
         inc_slabs_node(kmem_cache_node, node, page->objects);
 
-        add_partial(n, page, DEACTIVATE_TO_HEAD);
+        add_partial(n, page, 0);
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -2870,7 +2737,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s)
                 }
 
                 s->node[node] = n;
-                init_kmem_cache_node(n);
+                init_kmem_cache_node(n, s);
         }
         return 1;
 }
@@ -2891,7 +2758,8 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min)
 static int calculate_sizes(struct kmem_cache *s, int forced_order)
 {
         unsigned long flags = s->flags;
-        unsigned long size = s->object_size;
+        unsigned long size = s->objsize;
+        unsigned long align = s->align;
         int order;
 
         /*
@@ -2919,7 +2787,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
          * end of the object and the free pointer. If not then add an
          * additional word to have some bytes to store Redzone information.
          */
-        if ((flags & SLAB_RED_ZONE) && size == s->object_size)
+        if ((flags & SLAB_RED_ZONE) && size == s->objsize)
                 size += sizeof(void *);
 #endif
 
@@ -2963,11 +2831,19 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 #endif
 
         /*
+         * Determine the alignment based on various parameters that the
+         * user specified and the dynamic determination of cache line size
+         * on bootup.
+         */
+        align = calculate_alignment(flags, align, s->objsize);
+        s->align = align;
+
+        /*
          * SLUB stores one object immediately after another beginning from
          * offset 0. In order to align the objects we have to simply size
          * each object to conform to the alignment.
          */
-        size = ALIGN(size, s->align);
+        size = ALIGN(size, align);
         s->size = size;
         if (forced_order >= 0)
                 order = forced_order;
@@ -2996,11 +2872,20 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
                 s->max = s->oo;
 
         return !!oo_objects(s->oo);
+
 }
 
-static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
+static int kmem_cache_open(struct kmem_cache *s,
+                const char *name, size_t size,
+                size_t align, unsigned long flags,
+                void (*ctor)(void *))
 {
-        s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor);
+        memset(s, 0, kmem_size);
+        s->name = name;
+        s->ctor = ctor;
+        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))
@@ -3013,7 +2898,7 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
                  * Disable debugging flags that store metadata if the min slab
                  * order increased.
                  */
-                if (get_order(s->size) > get_order(s->object_size)) {
+                if (get_order(s->size) > get_order(s->objsize)) {
                         s->flags &= ~DEBUG_METADATA_FLAGS;
                         s->offset = 0;
                         if (!calculate_sizes(s, -1))
@@ -3021,8 +2906,7 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
                 }
         }
 
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
-    defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
+#ifdef CONFIG_CMPXCHG_DOUBLE
         if (system_has_cmpxchg_double() && (s->flags & SLAB_DEBUG_FLAGS) == 0)
                 /* Enable fast mode */
                 s->flags |= __CMPXCHG_DOUBLE;
@@ -3032,36 +2916,8 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
          * The larger the object size is, the more pages we want on the partial
          * list to avoid pounding the page allocator excessively.
          */
-        set_min_partial(s, ilog2(s->size) / 2);
-
-        /*
-         * cpu_partial determined the maximum number of objects kept in the
-         * per cpu partial lists of a processor.
-         *
-         * Per cpu partial lists mainly contain slabs that just have one
-         * object freed. If they are used for allocation then they can be
-         * filled up again with minimal effort. The slab will never hit the
-         * per node partial lists and therefore no locking will be required.
-         *
-         * This setting also determines
-         *
-         * A) The number of objects from per cpu partial slabs dumped to the
-         *    per node list when we reach the limit.
-         * B) The number of objects in cpu partial slabs to extract from the
-         *    per node list when we run out of per cpu objects. We only fetch 50%
-         *    to keep some capacity around for frees.
-         */
-        if (kmem_cache_debug(s))
-                s->cpu_partial = 0;
-        else if (s->size >= PAGE_SIZE)
-                s->cpu_partial = 2;
-        else if (s->size >= 1024)
-                s->cpu_partial = 6;
-        else if (s->size >= 256)
-                s->cpu_partial = 13;
-        else
-                s->cpu_partial = 30;
-
+        set_min_partial(s, ilog2(s->size));
+        s->refcount = 1;
 #ifdef CONFIG_NUMA
         s->remote_node_defrag_ratio = 1000;
 #endif
@@ -3069,17 +2925,26 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
                 goto error;
 
         if (alloc_kmem_cache_cpus(s))
-                return 0;
+                return 1;
 
         free_kmem_cache_nodes(s);
 error:
         if (flags & SLAB_PANIC)
                 panic("Cannot create slab %s size=%lu realsize=%u "
                         "order=%u offset=%u flags=%lx\n",
-                        s->name, (unsigned long)s->size, s->size, oo_order(s->oo),
+                        s->name, (unsigned long)size, s->size, oo_order(s->oo),
                         s->offset, flags);
-        return -EINVAL;
+        return 0;
+}
+
+/*
+ * Determine the size of a slab object
+ */
+unsigned int kmem_cache_size(struct kmem_cache *s)
+{
+        return s->objsize;
 }
+EXPORT_SYMBOL(kmem_cache_size);
 
 static void list_slab_objects(struct kmem_cache *s, struct page *page,
                                                         const char *text)
@@ -3091,7 +2956,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
                                      sizeof(long), GFP_ATOMIC);
         if (!map)
                 return;
-        slab_err(s, page, text, s->name);
+        slab_err(s, page, "%s", text);
         slab_lock(page);
 
         get_map(s, page, map);
@@ -3110,22 +2975,23 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 
 /*
  * Attempt to free all partial slabs on a node.
- * This is called from kmem_cache_close(). We must be the last thread
- * using the cache and therefore we do not need to lock anymore.
  */
 static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
+        unsigned long flags;
         struct page *page, *h;
 
+        spin_lock_irqsave(&n->list_lock, flags);
         list_for_each_entry_safe(page, h, &n->partial, lru) {
                 if (!page->inuse) {
                         remove_partial(n, page);
                         discard_slab(s, page);
                 } else {
                         list_slab_objects(s, page,
-                        "Objects remaining in %s on kmem_cache_close()");
+                                "Objects remaining on kmem_cache_close()");
                 }
         }
+        spin_unlock_irqrestore(&n->list_lock, flags);
 }
 
 /*
@@ -3136,6 +3002,7 @@ static inline int kmem_cache_close(struct kmem_cache *s)
         int node;
 
         flush_all(s);
+        free_percpu(s->cpu_slab);
         /* Attempt to free all objects */
         for_each_node_state(node, N_NORMAL_MEMORY) {
                 struct kmem_cache_node *n = get_node(s, node);
@@ -3144,31 +3011,32 @@ static inline int kmem_cache_close(struct kmem_cache *s)
                 if (n->nr_partial || slabs_node(s, node))
                         return 1;
         }
-        free_percpu(s->cpu_slab);
         free_kmem_cache_nodes(s);
         return 0;
 }
 
-int __kmem_cache_shutdown(struct kmem_cache *s)
-{
-        int rc = kmem_cache_close(s);
-
-        if (!rc) {
-                /*
-                 * We do the same lock strategy around sysfs_slab_add, see
-                 * __kmem_cache_create. Because this is pretty much the last
-                 * operation we do and the lock will be released shortly after
-                 * that in slab_common.c, we could just move sysfs_slab_remove
-                 * to a later point in common code. We should do that when we
-                 * have a common sysfs framework for all allocators.
-                 */
-                mutex_unlock(&slab_mutex);
+/*
+ * Close a cache and release the kmem_cache structure
+ * (must be used for caches created using kmem_cache_create)
+ */
+void kmem_cache_destroy(struct kmem_cache *s)
+{
+        down_write(&slub_lock);
+        s->refcount--;
+        if (!s->refcount) {
+                list_del(&s->list);
+                if (kmem_cache_close(s)) {
+                        printk(KERN_ERR "SLUB %s: %s called for cache that "
+                                "still has objects.\n", s->name, __func__);
+                        dump_stack();
+                }
+                if (s->flags & SLAB_DESTROY_BY_RCU)
+                        rcu_barrier();
                 sysfs_slab_remove(s);
-                mutex_lock(&slab_mutex);
         }
-
-        return rc;
+        up_write(&slub_lock);
 }
+EXPORT_SYMBOL(kmem_cache_destroy);
 
 /********************************************************************
  *              Kmalloc subsystem
@@ -3177,6 +3045,8 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
 EXPORT_SYMBOL(kmalloc_caches);
 
+static struct kmem_cache *kmem_cache;
+
 #ifdef CONFIG_ZONE_DMA
 static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
 #endif
@@ -3217,6 +3087,29 @@ static int __init setup_slub_nomerge(char *str)
 
 __setup("slub_nomerge", setup_slub_nomerge);
 
+static struct kmem_cache *__init create_kmalloc_cache(const char *name,
+                                                int size, unsigned int flags)
+{
+        struct kmem_cache *s;
+
+        s = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+
+        /*
+         * This function is called with IRQs disabled during early-boot on
+         * single CPU so there's no need to take slub_lock here.
+         */
+        if (!kmem_cache_open(s, name, size, ARCH_KMALLOC_MINALIGN,
+                                                                flags, NULL))
+                goto panic;
+
+        list_add(&s->list, &slab_caches);
+        return s;
+
+panic:
+        panic("Creation of kmalloc slab %s size=%d failed.\n", name, size);
+        return NULL;
+}
+
 /*
  * Conversion table for small slabs sizes / 8 to the index in the
  * kmalloc array. This is necessary for slabs < 192 since we have non power
@@ -3288,7 +3181,7 @@ void *__kmalloc(size_t size, gfp_t flags)
         if (unlikely(ZERO_OR_NULL_PTR(s)))
                 return s;
 
-        ret = slab_alloc(s, flags, _RET_IP_);
+        ret = slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_);
 
         trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
 
@@ -3302,7 +3195,7 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
         struct page *page;
         void *ptr = NULL;
 
-        flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG;
+        flags |= __GFP_COMP | __GFP_NOTRACK;
         page = alloc_pages_node(node, flags, get_order(size));
         if (page)
                 ptr = page_address(page);
@@ -3331,7 +3224,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
         if (unlikely(ZERO_OR_NULL_PTR(s)))
                 return s;
 
-        ret = slab_alloc_node(s, flags, node, _RET_IP_);
+        ret = slab_alloc(s, flags, node, _RET_IP_);
 
         trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
 
@@ -3354,7 +3247,7 @@ size_t ksize(const void *object)
                 return PAGE_SIZE << compound_order(page);
         }
 
-        return slab_ksize(page->slab_cache);
+        return slab_ksize(page->slab);
 }
 EXPORT_SYMBOL(ksize);
 
@@ -3379,8 +3272,8 @@ bool verify_mem_not_deleted(const void *x)
         }
 
         slab_lock(page);
-        if (on_freelist(page->slab_cache, page, object)) {
-                object_err(page->slab_cache, page, object, "Object is on free-list");
+        if (on_freelist(page->slab, page, object)) {
+                object_err(page->slab, page, object, "Object is on free-list");
                 rv = false;
         } else {
                 rv = true;
@@ -3408,10 +3301,10 @@ void kfree(const void *x)
         if (unlikely(!PageSlab(page))) {
                 BUG_ON(!PageCompound(page));
                 kmemleak_free(x);
-                __free_memcg_kmem_pages(page, compound_order(page));
+                put_page(page);
                 return;
         }
-        slab_free(page->slab_cache, page, object, _RET_IP_);
+        slab_free(page->slab, page, object, _RET_IP_);
 }
 EXPORT_SYMBOL(kfree);
 
@@ -3459,23 +3352,23 @@ int kmem_cache_shrink(struct kmem_cache *s)
                  * list_lock. page->inuse here is the upper limit.
                  */
                 list_for_each_entry_safe(page, t, &n->partial, lru) {
-                        list_move(&page->lru, slabs_by_inuse + page->inuse);
-                        if (!page->inuse)
-                                n->nr_partial--;
+                        if (!page->inuse) {
+                                remove_partial(n, page);
+                                discard_slab(s, page);
+                        } else {
+                                list_move(&page->lru,
+                                slabs_by_inuse + page->inuse);
+                        }
                 }
 
                 /*
                  * Rebuild the partial list with the slabs filled up most
                  * first and the least used slabs at the end.
                  */
-                for (i = objects - 1; i > 0; i--)
+                for (i = objects - 1; i >= 0; i--)
                         list_splice(slabs_by_inuse + i, n->partial.prev);
 
                 spin_unlock_irqrestore(&n->list_lock, flags);
-
-                /* Release empty slabs */
-                list_for_each_entry_safe(page, t, slabs_by_inuse, lru)
-                        discard_slab(s, page);
         }
 
         kfree(slabs_by_inuse);
@@ -3488,10 +3381,10 @@ static int slab_mem_going_offline_callback(void *arg)
 {
         struct kmem_cache *s;
 
-        mutex_lock(&slab_mutex);
+        down_read(&slub_lock);
         list_for_each_entry(s, &slab_caches, list)
                 kmem_cache_shrink(s);
-        mutex_unlock(&slab_mutex);
+        up_read(&slub_lock);
 
         return 0;
 }
@@ -3503,7 +3396,7 @@ static void slab_mem_offline_callback(void *arg)
         struct memory_notify *marg = arg;
         int offline_node;
 
-        offline_node = marg->status_change_nid_normal;
+        offline_node = marg->status_change_nid;
 
         /*
          * If the node still has available memory. we need kmem_cache_node
@@ -3512,7 +3405,7 @@ static void slab_mem_offline_callback(void *arg)
         if (offline_node < 0)
                 return;
 
-        mutex_lock(&slab_mutex);
+        down_read(&slub_lock);
         list_for_each_entry(s, &slab_caches, list) {
                 n = get_node(s, offline_node);
                 if (n) {
@@ -3528,7 +3421,7 @@ static void slab_mem_offline_callback(void *arg)
                         kmem_cache_free(kmem_cache_node, n);
                 }
         }
-        mutex_unlock(&slab_mutex);
+        up_read(&slub_lock);
 }
 
 static int slab_mem_going_online_callback(void *arg)
@@ -3536,7 +3429,7 @@ static int slab_mem_going_online_callback(void *arg)
         struct kmem_cache_node *n;
         struct kmem_cache *s;
         struct memory_notify *marg = arg;
-        int nid = marg->status_change_nid_normal;
+        int nid = marg->status_change_nid;
         int ret = 0;
 
         /*
@@ -3551,7 +3444,7 @@ static int slab_mem_going_online_callback(void *arg)
          * allocate a kmem_cache_node structure in order to bring the node
          * online.
          */
-        mutex_lock(&slab_mutex);
+        down_read(&slub_lock);
         list_for_each_entry(s, &slab_caches, list) {
                 /*
                  * XXX: kmem_cache_alloc_node will fallback to other nodes
@@ -3563,11 +3456,11 @@ static int slab_mem_going_online_callback(void *arg)
                         ret = -ENOMEM;
                         goto out;
                 }
-                init_kmem_cache_node(n);
+                init_kmem_cache_node(n, s);
                 s->node[nid] = n;
         }
 out:
-        mutex_unlock(&slab_mutex);
+        up_read(&slub_lock);
         return ret;
 }
 
@@ -3606,16 +3499,15 @@ static int slab_memory_callback(struct notifier_block *self,
 
 /*
  * Used for early kmem_cache structures that were allocated using
- * the page allocator. Allocate them properly then fix up the pointers
- * that may be pointing to the wrong kmem_cache structure.
+ * the page allocator
  */
 
-static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
+static void __init kmem_cache_bootstrap_fixup(struct kmem_cache *s)
 {
         int node;
-        struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
 
-        memcpy(s, static_cache, kmem_cache->object_size);
+        list_add(&s->list, &slab_caches);
+        s->refcount = -1;
 
         for_each_node_state(node, N_NORMAL_MEMORY) {
                 struct kmem_cache_node *n = get_node(s, node);
@@ -3623,52 +3515,72 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 
                 if (n) {
                         list_for_each_entry(p, &n->partial, lru)
-                                p->slab_cache = s;
+                                p->slab = s;
 
 #ifdef CONFIG_SLUB_DEBUG
                         list_for_each_entry(p, &n->full, lru)
-                                p->slab_cache = s;
+                                p->slab = s;
 #endif
                 }
         }
-        list_add(&s->list, &slab_caches);
-        return s;
 }
 
 void __init kmem_cache_init(void)
 {
-        static __initdata struct kmem_cache boot_kmem_cache,
-                boot_kmem_cache_node;
         int i;
-        int caches = 2;
+        int caches = 0;
+        struct kmem_cache *temp_kmem_cache;
+        int order;
+        struct kmem_cache *temp_kmem_cache_node;
+        unsigned long kmalloc_size;
 
-        if (debug_guardpage_minorder())
-                slub_max_order = 0;
+        kmem_size = offsetof(struct kmem_cache, node) +
+                                nr_node_ids * sizeof(struct kmem_cache_node *);
 
-        kmem_cache_node = &boot_kmem_cache_node;
-        kmem_cache = &boot_kmem_cache;
+        /* Allocate two kmem_caches from the page allocator */
+        kmalloc_size = ALIGN(kmem_size, cache_line_size());
+        order = get_order(2 * kmalloc_size);
+        kmem_cache = (void *)__get_free_pages(GFP_NOWAIT, order);
 
-        create_boot_cache(kmem_cache_node, "kmem_cache_node",
-                sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN);
+        /*
+         * Must first have the slab cache available for the allocations of the
+         * struct kmem_cache_node's. There is special bootstrap code in
+         * kmem_cache_open for slab_state == DOWN.
+         */
+        kmem_cache_node = (void *)kmem_cache + kmalloc_size;
+
+        kmem_cache_open(kmem_cache_node, "kmem_cache_node",
+                sizeof(struct kmem_cache_node),
+                0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 
         hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
 
         /* Able to allocate the per node structures */
         slab_state = PARTIAL;
 
-        create_boot_cache(kmem_cache, "kmem_cache",
-                        offsetof(struct kmem_cache, node) +
-                                nr_node_ids * sizeof(struct kmem_cache_node *),
-                       SLAB_HWCACHE_ALIGN);
-
-        kmem_cache = bootstrap(&boot_kmem_cache);
+        temp_kmem_cache = kmem_cache;
+        kmem_cache_open(kmem_cache, "kmem_cache", kmem_size,
+                0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+        kmem_cache = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+        memcpy(kmem_cache, temp_kmem_cache, kmem_size);
 
         /*
          * Allocate kmem_cache_node properly from the kmem_cache slab.
          * kmem_cache_node is separately allocated so no need to
          * update any list pointers.
          */
-        kmem_cache_node = bootstrap(&boot_kmem_cache_node);
+        temp_kmem_cache_node = kmem_cache_node;
+
+        kmem_cache_node = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+        memcpy(kmem_cache_node, temp_kmem_cache_node, kmem_size);
+
+        kmem_cache_bootstrap_fixup(kmem_cache_node);
+
+        caches++;
+        kmem_cache_bootstrap_fixup(kmem_cache);
+        caches++;
+        /* Free temporary boot structure */
+        free_pages((unsigned long)temp_kmem_cache, order);
 
         /* Now we can use the kmem_cache to allocate kmalloc slabs */
 
@@ -3756,11 +3668,11 @@ void __init kmem_cache_init(void)
 
                 if (s && s->size) {
                         char *name = kasprintf(GFP_NOWAIT,
-                                 "dma-kmalloc-%d", s->object_size);
+                                 "dma-kmalloc-%d", s->objsize);
 
                         BUG_ON(!name);
                         kmalloc_dma_caches[i] = create_kmalloc_cache(name,
-                                s->object_size, SLAB_CACHE_DMA);
+                                s->objsize, SLAB_CACHE_DMA);
                 }
         }
 #endif
@@ -3796,7 +3708,7 @@ static int slab_unmergeable(struct kmem_cache *s)
         return 0;
 }
 
-static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
+static struct kmem_cache *find_mergeable(size_t size,
                 size_t align, unsigned long flags, const char *name,
                 void (*ctor)(void *))
 {
@@ -3832,61 +3744,70 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
                 if (s->size - size >= sizeof(void *))
                         continue;
 
-                if (!cache_match_memcg(s, memcg))
-                        continue;
-
                 return s;
         }
         return NULL;
 }
 
-struct kmem_cache *
-__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
-                   size_t align, unsigned long flags, void (*ctor)(void *))
+struct kmem_cache *kmem_cache_create(const char *name, size_t size,
+                size_t align, unsigned long flags, void (*ctor)(void *))
 {
         struct kmem_cache *s;
+        char *n;
+
+        if (WARN_ON(!name))
+                return NULL;
 
-        s = find_mergeable(memcg, size, align, flags, name, ctor);
+        down_write(&slub_lock);
+        s = find_mergeable(size, align, flags, name, ctor);
         if (s) {
                 s->refcount++;
                 /*
                  * Adjust the object sizes so that we clear
                  * the complete object on kzalloc.
                  */
-                s->object_size = max(s->object_size, (int)size);
+                s->objsize = max(s->objsize, (int)size);
                 s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
 
                 if (sysfs_slab_alias(s, name)) {
                         s->refcount--;
-                        s = NULL;
+                        goto err;
                 }
+                up_write(&slub_lock);
+                return s;
         }
 
-        return s;
-}
+        n = kstrdup(name, GFP_KERNEL);
+        if (!n)
+                goto err;
 
-int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
-{
-        int err;
-
-        err = kmem_cache_open(s, flags);
-        if (err)
-                return err;
-
-        /* Mutex is not taken during early boot */
-        if (slab_state <= UP)
-                return 0;
-
-        memcg_propagate_slab_attrs(s);
-        mutex_unlock(&slab_mutex);
-        err = sysfs_slab_add(s);
-        mutex_lock(&slab_mutex);
-
-        if (err)
-                kmem_cache_close(s);
+        s = kmalloc(kmem_size, GFP_KERNEL);
+        if (s) {
+                if (kmem_cache_open(s, n,
+                                size, align, flags, ctor)) {
+                        list_add(&s->list, &slab_caches);
+                        if (sysfs_slab_add(s)) {
+                                list_del(&s->list);
+                                kfree(n);
+                                kfree(s);
+                                goto err;
+                        }
+                        up_write(&slub_lock);
+                        return s;
+                }
+                kfree(n);
+                kfree(s);
+        }
+err:
+        up_write(&slub_lock);
 
-        return err;
+        if (flags & SLAB_PANIC)
+                panic("Cannot create slabcache %s\n", name);
+        else
+                s = NULL;
+        return s;
 }
+EXPORT_SYMBOL(kmem_cache_create);
 
 #ifdef CONFIG_SMP
 /*
@@ -3905,13 +3826,13 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
         case CPU_UP_CANCELED_FROZEN:
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                mutex_lock(&slab_mutex);
+                down_read(&slub_lock);
                 list_for_each_entry(s, &slab_caches, list) {
                         local_irq_save(flags);
                         __flush_cpu_slab(s, cpu);
                         local_irq_restore(flags);
                 }
-                mutex_unlock(&slab_mutex);
+                up_read(&slub_lock);
                 break;
         default:
                 break;
@@ -3938,7 +3859,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
         if (unlikely(ZERO_OR_NULL_PTR(s)))
                 return s;
 
-        ret = slab_alloc(s, gfpflags, caller);
+        ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, caller);
 
         /* Honor the call site pointer we received. */
         trace_kmalloc(caller, ret, size, s->size, gfpflags);
@@ -3968,7 +3889,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
         if (unlikely(ZERO_OR_NULL_PTR(s)))
                 return s;
 
-        ret = slab_alloc_node(s, gfpflags, node, caller);
+        ret = slab_alloc(s, gfpflags, node, caller);
 
         /* Honor the call site pointer we received. */
         trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node);
@@ -4403,32 +4324,22 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
                 for_each_possible_cpu(cpu) {
                         struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
-                        int node;
-                        struct page *page;
 
-                        page = ACCESS_ONCE(c->page);
-                        if (!page)
+                        if (!c || c->node < 0)
                                 continue;
 
-                        node = page_to_nid(page);
-                        if (flags & SO_TOTAL)
-                                x = page->objects;
-                        else if (flags & SO_OBJECTS)
-                                x = page->inuse;
-                        else
-                                x = 1;
-
-                        total += x;
-                        nodes[node] += x;
+                        if (c->page) {
+                                        if (flags & SO_TOTAL)
+                                                x = c->page->objects;
+                                else if (flags & SO_OBJECTS)
+                                        x = c->page->inuse;
+                                else
+                                        x = 1;
 
-                        page = ACCESS_ONCE(c->partial);
-                        if (page) {
-                                x = page->pobjects;
                                 total += x;
-                                nodes[node] += x;
+                                nodes[c->node] += x;
                         }
-
-                        per_cpu[node]++;
+                        per_cpu[c->node]++;
                 }
         }
 
@@ -4506,12 +4417,11 @@ struct slab_attribute {
 };
 
 #define SLAB_ATTR_RO(_name) \
-        static struct slab_attribute _name##_attr = \
-        __ATTR(_name, 0400, _name##_show, NULL)
+        static struct slab_attribute _name##_attr = __ATTR_RO(_name)
 
 #define SLAB_ATTR(_name) \
         static struct slab_attribute _name##_attr =  \
-        __ATTR(_name, 0600, _name##_show, _name##_store)
+        __ATTR(_name, 0644, _name##_show, _name##_store)
 
 static ssize_t slab_size_show(struct kmem_cache *s, char *buf)
 {
@@ -4527,7 +4437,7 @@ SLAB_ATTR_RO(align);
 
 static ssize_t object_size_show(struct kmem_cache *s, char *buf)
 {
-        return sprintf(buf, "%d\n", s->object_size);
+        return sprintf(buf, "%d\n", s->objsize);
 }
 SLAB_ATTR_RO(object_size);
 
@@ -4580,29 +4490,6 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
 }
 SLAB_ATTR(min_partial);
 
-static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf)
-{
-        return sprintf(buf, "%u\n", s->cpu_partial);
-}
-
-static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
-                                 size_t length)
-{
-        unsigned long objects;
-        int err;
-
-        err = strict_strtoul(buf, 10, &objects);
-        if (err)
-                return err;
-        if (objects && kmem_cache_debug(s))
-                return -EINVAL;
-
-        s->cpu_partial = objects;
-        flush_all(s);
-        return length;
-}
-SLAB_ATTR(cpu_partial);
-
 static ssize_t ctor_show(struct kmem_cache *s, char *buf)
 {
         if (!s->ctor)
@@ -4641,37 +4528,6 @@ static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(objects_partial);
 
-static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf)
-{
-        int objects = 0;
-        int pages = 0;
-        int cpu;
-        int len;
-
-        for_each_online_cpu(cpu) {
-                struct page *page = per_cpu_ptr(s->cpu_slab, cpu)->partial;
-
-                if (page) {
-                        pages += page->pages;
-                        objects += page->pobjects;
-                }
-        }
-
-        len = sprintf(buf, "%d(%d)", objects, pages);
-
-#ifdef CONFIG_SMP
-        for_each_online_cpu(cpu) {
-                struct page *page = per_cpu_ptr(s->cpu_slab, cpu) ->partial;
-
-                if (page && len < PAGE_SIZE - 20)
-                        len += sprintf(buf + len, " C%d=%d(%d)", cpu,
-                                page->pobjects, page->pages);
-        }
-#endif
-        return len + sprintf(buf + len, "\n");
-}
-SLAB_ATTR_RO(slabs_cpu_partial);
-
 static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf)
 {
         return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT));
@@ -4994,10 +4850,6 @@ 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);
-STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc);
-STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free);
-STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node);
-STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -5006,7 +4858,6 @@ static struct attribute *slab_attrs[] = {
         &objs_per_slab_attr.attr,
         &order_attr.attr,
         &min_partial_attr.attr,
-        &cpu_partial_attr.attr,
         &objects_attr.attr,
         &objects_partial_attr.attr,
         &partial_attr.attr,
@@ -5019,7 +4870,6 @@ static struct attribute *slab_attrs[] = {
         &destroy_by_rcu_attr.attr,
         &shrink_attr.attr,
         &reserved_attr.attr,
-        &slabs_cpu_partial_attr.attr,
 #ifdef CONFIG_SLUB_DEBUG
         &total_objects_attr.attr,
         &slabs_attr.attr,
@@ -5061,10 +4911,6 @@ static struct attribute *slab_attrs[] = {
         &order_fallback_attr.attr,
         &cmpxchg_double_fail_attr.attr,
         &cmpxchg_double_cpu_fail_attr.attr,
-        &cpu_partial_alloc_attr.attr,
-        &cpu_partial_free_attr.attr,
-        &cpu_partial_node_attr.attr,
-        &cpu_partial_drain_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
         &failslab_attr.attr,
@@ -5111,93 +4957,16 @@ static ssize_t slab_attr_store(struct kobject *kobj,
                 return -EIO;
 
         err = attribute->store(s, buf, len);
-#ifdef CONFIG_MEMCG_KMEM
-        if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
-                int i;
-
-                mutex_lock(&slab_mutex);
-                if (s->max_attr_size < len)
-                        s->max_attr_size = len;
 
-                /*
-                 * This is a best effort propagation, so this function's return
-                 * value will be determined by the parent cache only. This is
-                 * basically because not all attributes will have a well
-                 * defined semantics for rollbacks - most of the actions will
-                 * have permanent effects.
-                 *
-                 * Returning the error value of any of the children that fail
-                 * is not 100 % defined, in the sense that users seeing the
-                 * error code won't be able to know anything about the state of
-                 * the cache.
-                 *
-                 * Only returning the error code for the parent cache at least
-                 * has well defined semantics. The cache being written to
-                 * directly either failed or succeeded, in which case we loop
-                 * through the descendants with best-effort propagation.
-                 */
-                for_each_memcg_cache_index(i) {
-                        struct kmem_cache *c = cache_from_memcg(s, i);
-                        if (c)
-                                attribute->store(c, buf, len);
-                }
-                mutex_unlock(&slab_mutex);
-        }
-#endif
         return err;
 }
 
-static void memcg_propagate_slab_attrs(struct kmem_cache *s)
+static void kmem_cache_release(struct kobject *kobj)
 {
-#ifdef CONFIG_MEMCG_KMEM
-        int i;
-        char *buffer = NULL;
-
-        if (!is_root_cache(s))
-                return;
-
-        /*
-         * This mean this cache had no attribute written. Therefore, no point
-         * in copying default values around
-         */
-        if (!s->max_attr_size)
-                return;
+        struct kmem_cache *s = to_slab(kobj);
 
-        for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
-                char mbuf[64];
-                char *buf;
-                struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
-
-                if (!attr || !attr->store || !attr->show)
-                        continue;
-
-                /*
-                 * It is really bad that we have to allocate here, so we will
-                 * do it only as a fallback. If we actually allocate, though,
-                 * we can just use the allocated buffer until the end.
-                 *
-                 * Most of the slub attributes will tend to be very small in
-                 * size, but sysfs allows buffers up to a page, so they can
-                 * theoretically happen.
-                 */
-                if (buffer)
-                        buf = buffer;
-                else if (s->max_attr_size < ARRAY_SIZE(mbuf))
-                        buf = mbuf;
-                else {
-                        buffer = (char *) get_zeroed_page(GFP_KERNEL);
-                        if (WARN_ON(!buffer))
-                                continue;
-                        buf = buffer;
-                }
-
-                attr->show(s->memcg_params->root_cache, buf);
-                attr->store(s, buf, strlen(buf));
-        }
-
-        if (buffer)
-                free_page((unsigned long)buffer);
-#endif
+        kfree(s->name);
+        kfree(s);
 }
 
 static const struct sysfs_ops slab_sysfs_ops = {
@@ -5207,6 +4976,7 @@ static const struct sysfs_ops slab_sysfs_ops = {
 
 static struct kobj_type slab_ktype = {
         .sysfs_ops = &slab_sysfs_ops,
+        .release = kmem_cache_release
 };
 
 static int uevent_filter(struct kset *kset, struct kobject *kobj)
@@ -5256,12 +5026,6 @@ static char *create_unique_id(struct kmem_cache *s)
         if (p != name + 1)
                 *p++ = '-';
         p += sprintf(p, "%07d", s->size);
-
-#ifdef CONFIG_MEMCG_KMEM
-        if (!is_root_cache(s))
-                p += sprintf(p, "-%08d", memcg_cache_id(s->memcg_params->memcg));
-#endif
-
         BUG_ON(p > name + ID_STR_LENGTH - 1);
         return name;
 }
@@ -5270,8 +5034,13 @@ static int sysfs_slab_add(struct kmem_cache *s)
 {
         int err;
         const char *name;
-        int unmergeable = slab_unmergeable(s);
+        int unmergeable;
+
+        if (slab_state < SYSFS)
+                /* Defer until later */
+                return 0;
 
+        unmergeable = slab_unmergeable(s);
         if (unmergeable) {
                 /*
                  * Slabcache can never be merged so we can use the name proper.
@@ -5312,7 +5081,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
 
 static void sysfs_slab_remove(struct kmem_cache *s)
 {
-        if (slab_state < FULL)
+        if (slab_state < SYSFS)
                 /*
                  * Sysfs has not been setup yet so no need to remove the
                  * cache from sysfs.
@@ -5340,7 +5109,7 @@ static int sysfs_slab_alias(struct kmem_cache *s, const char *name)
 {
         struct saved_alias *al;
 
-        if (slab_state == FULL) {
+        if (slab_state == SYSFS) {
                 /*
                  * If we have a leftover link then remove it.
                  */
@@ -5364,16 +5133,16 @@ static int __init slab_sysfs_init(void)
         struct kmem_cache *s;
         int err;
 
-        mutex_lock(&slab_mutex);
+        down_write(&slub_lock);
 
         slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj);
         if (!slab_kset) {
-                mutex_unlock(&slab_mutex);
+                up_write(&slub_lock);
                 printk(KERN_ERR "Cannot register slab subsystem.\n");
                 return -ENOSYS;
         }
 
-        slab_state = FULL;
+        slab_state = SYSFS;
 
         list_for_each_entry(s, &slab_caches, list) {
                 err = sysfs_slab_add(s);
@@ -5389,11 +5158,11 @@ static int __init slab_sysfs_init(void)
                 err = sysfs_slab_alias(al->s, al->name);
                 if (err)
                         printk(KERN_ERR "SLUB: Unable to add boot slab alias"
-                                        " %s to sysfs\n", al->name);
+                                        " %s to sysfs\n", s->name);
                 kfree(al);
         }
 
-        mutex_unlock(&slab_mutex);
+        up_write(&slub_lock);
         resiliency_test();
         return 0;
 }
@@ -5405,14 +5174,49 @@ __initcall(slab_sysfs_init);
  * The /proc/slabinfo ABI
  */
 #ifdef CONFIG_SLABINFO
-void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
+static void print_slabinfo_header(struct seq_file *m)
+{
+        seq_puts(m, "slabinfo - version: 2.1\n");
+        seq_puts(m, "# name            <active_objs> <num_objs> <objsize> "
+                 "<objperslab> <pagesperslab>");
+        seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
+        seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
+        seq_putc(m, '\n');
+}
+
+static void *s_start(struct seq_file *m, loff_t *pos)
+{
+        loff_t n = *pos;
+
+        down_read(&slub_lock);
+        if (!n)
+                print_slabinfo_header(m);
+
+        return seq_list_start(&slab_caches, *pos);
+}
+
+static void *s_next(struct seq_file *m, void *p, loff_t *pos)
+{
+        return seq_list_next(p, &slab_caches, pos);
+}
+
+static void s_stop(struct seq_file *m, void *p)
+{
+        up_read(&slub_lock);
+}
+
+static int s_show(struct seq_file *m, void *p)
 {
         unsigned long nr_partials = 0;
         unsigned long nr_slabs = 0;
+        unsigned long nr_inuse = 0;
         unsigned long nr_objs = 0;
         unsigned long nr_free = 0;
+        struct kmem_cache *s;
         int node;
 
+        s = list_entry(p, struct kmem_cache, list);
+
         for_each_online_node(node) {
                 struct kmem_cache_node *n = get_node(s, node);
 
@@ -5425,21 +5229,41 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
                 nr_free += count_partial(n, count_free);
         }
 
-        sinfo->active_objs = nr_objs - nr_free;
-        sinfo->num_objs = nr_objs;
-        sinfo->active_slabs = nr_slabs;
-        sinfo->num_slabs = nr_slabs;
-        sinfo->objects_per_slab = oo_objects(s->oo);
-        sinfo->cache_order = oo_order(s->oo);
+        nr_inuse = nr_objs - nr_free;
+
+        seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", s->name, nr_inuse,
+                   nr_objs, s->size, oo_objects(s->oo),
+                   (1 << oo_order(s->oo)));
+        seq_printf(m, " : tunables %4u %4u %4u", 0, 0, 0);
+        seq_printf(m, " : slabdata %6lu %6lu %6lu", nr_slabs, nr_slabs,
+                   0UL);
+        seq_putc(m, '\n');
+        return 0;
 }
 
-void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)
+static const struct seq_operations slabinfo_op = {
+        .start = s_start,
+        .next = s_next,
+        .stop = s_stop,
+        .show = s_show,
+};
+
+static int slabinfo_open(struct inode *inode, struct file *file)
 {
+        return seq_open(file, &slabinfo_op);
 }
 
-ssize_t slabinfo_write(struct file *file, const char __user *buffer,
-                       size_t count, loff_t *ppos)
+static const struct file_operations proc_slabinfo_operations = {
+        .open           = slabinfo_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+static int __init slab_proc_init(void)
 {
-        return -EIO;
+        proc_create("slabinfo", S_IRUGO, NULL, &proc_slabinfo_operations);
+        return 0;
 }
+module_init(slab_proc_init);
 #endif /* CONFIG_SLABINFO */