X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?p=pandora-kernel.git;a=blobdiff_plain;f=mm%2Fslub.c;h=60c69696eb0bc571fd721154cb7c93ca698a97f5;hp=7d2a996c307e4306bd233f4ae340a02d6915ffb1;hb=9f249188a2927b7809ed790e4b568ea82039d919;hpb=866d43c9ea88daa3751b58aba16a2a9b7f7aa067 diff --git a/mm/slub.c b/mm/slub.c index 7d2a996c307e..60c69696eb0b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1506,15 +1506,19 @@ static inline void *acquire_slab(struct kmem_cache *s, freelist = page->freelist; counters = page->counters; new.counters = counters; - if (mode) + if (mode) { new.inuse = page->objects; + new.freelist = NULL; + } else { + new.freelist = freelist; + } VM_BUG_ON(new.frozen); new.frozen = 1; } while (!__cmpxchg_double_slab(s, page, freelist, counters, - NULL, new.counters, + new.freelist, new.counters, "lock and freeze")); remove_partial(n, page); @@ -1556,7 +1560,6 @@ static void *get_partial_node(struct kmem_cache *s, object = t; available = page->objects - page->inuse; } else { - page->freelist = t; available = put_cpu_partial(s, page, 0); } if (kmem_cache_debug(s) || available > s->cpu_partial / 2) @@ -1579,6 +1582,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags, struct zone *zone; enum zone_type high_zoneidx = gfp_zone(flags); void *object; + unsigned int cpuset_mems_cookie; /* * The defrag ratio allows a configuration of the tradeoffs between @@ -1602,23 +1606,32 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags, get_cycles() % 1024 > s->remote_node_defrag_ratio) return NULL; - 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) { - object = get_partial_node(s, n, c); - if (object) { - put_mems_allowed(); - return object; + 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); + 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; + } } } - } - put_mems_allowed(); + } while (!put_mems_allowed(cpuset_mems_cookie)); #endif return NULL; } @@ -1860,18 +1873,24 @@ redo: /* Unfreeze all the cpu partial slabs */ static void unfreeze_partials(struct kmem_cache *s) { - struct kmem_cache_node *n = NULL; + struct kmem_cache_node *n = NULL, *n2 = 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 }; - enum slab_modes l, m; struct page new; struct page old; c->partial = page->next; - l = M_FREE; + + 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 { @@ -1884,45 +1903,31 @@ static void unfreeze_partials(struct kmem_cache *s) new.frozen = 0; - if (!new.inuse && (!n || n->nr_partial > s->min_partial)) - m = M_FREE; - else { - struct kmem_cache_node *n2 = get_node(s, - page_to_nid(page)); - - m = M_PARTIAL; - if (n != n2) { - if (n) - spin_unlock(&n->list_lock); - - n = n2; - spin_lock(&n->list_lock); - } - } - - if (l != m) { - if (l == M_PARTIAL) - remove_partial(n, page); - else - add_partial(n, page, 1); - - l = m; - } - } while (!cmpxchg_double_slab(s, page, old.freelist, old.counters, new.freelist, new.counters, "unfreezing slab")); - if (m == M_FREE) { - stat(s, DEACTIVATE_EMPTY); - discard_slab(s, page); - stat(s, FREE_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); + } } /* @@ -1969,7 +1974,7 @@ 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; } @@ -2157,6 +2162,11 @@ redo: goto new_slab; } + /* must check again c->freelist in case of cpu migration or IRQ */ + object = c->freelist; + if (object) + goto load_freelist; + stat(s, ALLOC_SLOWPATH); do { @@ -3897,13 +3907,14 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, if (kmem_cache_open(s, n, size, align, flags, ctor)) { list_add(&s->list, &slab_caches); + up_write(&slub_lock); if (sysfs_slab_add(s)) { + down_write(&slub_lock); list_del(&s->list); kfree(n); kfree(s); goto err; } - up_write(&slub_lock); return s; } kfree(n); @@ -4435,30 +4446,37 @@ 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; + node = page_to_nid(page); + if (flags & SO_TOTAL) + WARN_ON_ONCE(1); + else if (flags & SO_OBJECTS) + WARN_ON_ONCE(1); + else + x = page->pages; + total += x; + nodes[node] += x; } - per_cpu[c->node]++; + per_cpu[node]++; } }