Merge branch 'slab/urgent' into slab/for-linus

[cascardo/linux.git] / mm / slub.c

diff --git a/mm/slub.c b/mm/slub.c
index 7d2a996..19436f5 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -570,7 +570,7 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...)
        va_end(args);
        printk(KERN_ERR "========================================"
                        "=====================================\n");
-       printk(KERN_ERR "BUG %s: %s\n", s->name, buf);
+       printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf);
        printk(KERN_ERR "----------------------------------------"
                        "-------------------------------------\n\n");
 }
@@ -1862,7 +1862,7 @@ static void unfreeze_partials(struct kmem_cache *s)
 {
        struct kmem_cache_node *n = NULL;
        struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
-       struct page *page;
+       struct page *page, *discard_page = NULL;
 
        while ((page = c->partial)) {
                enum slab_modes { M_PARTIAL, M_FREE };
@@ -1901,10 +1901,14 @@ static void unfreeze_partials(struct kmem_cache *s)
                        }
 
                        if (l != m) {
-                               if (l == M_PARTIAL)
+                               if (l == M_PARTIAL) {
                                        remove_partial(n, page);
-                               else
-                                       add_partial(n, page, 1);
+                                       stat(s, FREE_REMOVE_PARTIAL);
+                               } else {
+                                       add_partial(n, page,
+                                               DEACTIVATE_TO_TAIL);
+                                       stat(s, FREE_ADD_PARTIAL);
+                               }
 
                                l = m;
                        }
@@ -1915,14 +1919,22 @@ static void unfreeze_partials(struct kmem_cache *s)
                                "unfreezing slab"));
 
                if (m == M_FREE) {
-                       stat(s, DEACTIVATE_EMPTY);
-                       discard_slab(s, page);
-                       stat(s, FREE_SLAB);
+                       page->next = discard_page;
+                       discard_page = page;
                }
        }
 
        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);
+       }
 }
 
 /*
@@ -1969,7 +1981,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
                page->pobjects = pobjects;
                page->next = oldpage;
 
-       } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
+       } while (irqsafe_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
        stat(s, CPU_PARTIAL_FREE);
        return pobjects;
 }
@@ -2114,6 +2126,37 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
        return object;
 }
 
+/*
+ * 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.
+ */
+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.
@@ -2135,8 +2178,6 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 {
        void **object;
        unsigned long flags;
-       struct page new;
-       unsigned long counters;
 
        local_irq_save(flags);
 #ifdef CONFIG_PREEMPT
@@ -2157,31 +2198,14 @@ redo:
                goto new_slab;
        }
 
-       stat(s, ALLOC_SLOWPATH);
-
-       do {
-               object = c->page->freelist;
-               counters = c->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.
-                */
+       /* must check again c->freelist in case of cpu migration or IRQ */
+       object = c->freelist;
+       if (object)
+               goto load_freelist;
 
-               new.inuse = c->page->objects;
-               new.frozen = object != NULL;
+       stat(s, ALLOC_SLOWPATH);
 
-       } while (!__cmpxchg_double_slab(s, c->page,
-                       object, counters,
-                       NULL, new.counters,
-                       "__slab_alloc"));
+       object = get_freelist(s, c->page);
 
        if (!object) {
                c->page = NULL;
@@ -3019,7 +3043,9 @@ static int kmem_cache_open(struct kmem_cache *s,
         *    per node list when we run out of per cpu objects. We only fetch 50%
         *    to keep some capacity around for frees.
         */
-       if (s->size >= PAGE_SIZE)
+       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;
@@ -4435,30 +4461,31 @@ 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 = ACCESS_ONCE(c->node);
                        struct page *page;
 
-                       if (!c || c->node < 0)
+                       if (node < 0)
                                continue;
-
-                       if (c->page) {
-                                       if (flags & SO_TOTAL)
-                                               x = c->page->objects;
+                       page = ACCESS_ONCE(c->page);
+                       if (page) {
+                               if (flags & SO_TOTAL)
+                                       x = page->objects;
                                else if (flags & SO_OBJECTS)
-                                       x = c->page->inuse;
+                                       x = page->inuse;
                                else
                                        x = 1;
 
                                total += x;
-                               nodes[c->node] += x;
+                               nodes[node] += x;
                        }
                        page = c->partial;
 
                        if (page) {
                                x = page->pobjects;
-                                total += x;
-                                nodes[c->node] += x;
+                               total += x;
+                               nodes[node] += x;
                        }
-                       per_cpu[c->node]++;
+                       per_cpu[node]++;
                }
        }
 
@@ -4624,6 +4651,8 @@ static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
        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);