6 files changed, 59 insertions, 38 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1ae2b2cc3a54..70df5c0d957e 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -91,8 +91,8 @@ static void grow_zone_span(struct zone *zone,
         if (start_pfn < zone->zone_start_pfn)
                 zone->zone_start_pfn = start_pfn;
 
-        if (end_pfn > old_zone_end_pfn)
-                zone->spanned_pages = end_pfn - zone->zone_start_pfn;
+        zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
+                                zone->zone_start_pfn;
 
         zone_span_writeunlock(zone);
 }
@@ -106,8 +106,8 @@ static void grow_pgdat_span(struct pglist_data *pgdat,
         if (start_pfn < pgdat->node_start_pfn)
                 pgdat->node_start_pfn = start_pfn;
 
-        if (end_pfn > old_pgdat_end_pfn)
-                pgdat->node_spanned_pages = end_pfn - pgdat->node_start_pfn;
+        pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
+                                        pgdat->node_start_pfn;
 }
 
 int online_pages(unsigned long pfn, unsigned long nr_pages)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ea77c999047e..253a450c400d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -39,6 +39,7 @@
 #include <linux/mempolicy.h>
 
 #include <asm/tlbflush.h>
+#include <asm/div64.h>
 #include "internal.h"
 
 /*
@@ -950,7 +951,7 @@ restart:
                 goto got_pg;
 
         do {
-                if (cpuset_zone_allowed(*z, gfp_mask))
+                if (cpuset_zone_allowed(*z, gfp_mask|__GFP_HARDWALL))
                         wakeup_kswapd(*z, order);
         } while (*(++z));
 
@@ -969,7 +970,8 @@ restart:
                 alloc_flags |= ALLOC_HARDER;
         if (gfp_mask & __GFP_HIGH)
                 alloc_flags |= ALLOC_HIGH;
-        alloc_flags |= ALLOC_CPUSET;
+        if (wait)
+                alloc_flags |= ALLOC_CPUSET;
 
         /*
          * Go through the zonelist again. Let __GFP_HIGH and allocations
@@ -2123,14 +2125,22 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)
 #ifdef CONFIG_FLAT_NODE_MEM_MAP
         /* ia64 gets its own node_mem_map, before this, without bootmem */
         if (!pgdat->node_mem_map) {
-                unsigned long size;
+                unsigned long size, start, end;
                 struct page *map;
 
-                size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
+                /*
+                 * The zone's endpoints aren't required to be MAX_ORDER
+                 * aligned but the node_mem_map endpoints must be in order
+                 * for the buddy allocator to function correctly.
+                 */
+                start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
+                end = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+                end = ALIGN(end, MAX_ORDER_NR_PAGES);
+                size =  (end - start) * sizeof(struct page);
                 map = alloc_remap(pgdat->node_id, size);
                 if (!map)
                         map = alloc_bootmem_node(pgdat, size);
-                pgdat->node_mem_map = map;
+                pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
         }
 #ifdef CONFIG_FLATMEM
         /*
@@ -2566,9 +2576,11 @@ void setup_per_zone_pages_min(void)
         }
 
         for_each_zone(zone) {
-                unsigned long tmp;
+                u64 tmp;
+
                 spin_lock_irqsave(&zone->lru_lock, flags);
-                tmp = (pages_min * zone->present_pages) / lowmem_pages;
+                tmp = (u64)pages_min * zone->present_pages;
+                do_div(tmp, lowmem_pages);
                 if (is_highmem(zone)) {
                         /*
                          * __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -2595,8 +2607,8 @@ void setup_per_zone_pages_min(void)
                         zone->pages_min = tmp;
                 }
 
-                zone->pages_low   = zone->pages_min + tmp / 4;
-                zone->pages_high  = zone->pages_min + tmp / 2;
+                zone->pages_low   = zone->pages_min + (tmp >> 2);
+                zone->pages_high  = zone->pages_min + (tmp >> 1);
                 spin_unlock_irqrestore(&zone->lru_lock, flags);
         }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 4c5e68e4e9ae..1e43c8a865ba 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1780,6 +1780,7 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
         if (!simple_empty(dentry))
                 return -ENOTEMPTY;
 
+        dentry->d_inode->i_nlink--;
         dir->i_nlink--;
         return shmem_unlink(dir, dentry);
 }
@@ -2102,6 +2103,7 @@ static int shmem_fill_super(struct super_block *sb,
         sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
         sb->s_magic = TMPFS_MAGIC;
         sb->s_op = &shmem_ops;
+        sb->s_time_gran = 1;
 
         inode = shmem_get_inode(sb, S_IFDIR | mode, 0);
         if (!inode)
diff --git a/mm/slab.c b/mm/slab.c
index c32af7e7581e..f1b644eb39d8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -207,11 +207,6 @@ typedef unsigned int kmem_bufctl_t;
 #define BUFCTL_ACTIVE   (((kmem_bufctl_t)(~0U))-2)
 #define SLAB_LIMIT      (((kmem_bufctl_t)(~0U))-3)
 
-/* Max number of objs-per-slab for caches which use off-slab slabs.
- * Needed to avoid a possible looping condition in cache_grow().
- */
-static unsigned long offslab_limit;
-
 /*
  * struct slab
  *
@@ -700,6 +695,14 @@ static enum {
         FULL
 } g_cpucache_up;
 
+/*
+ * used by boot code to determine if it can use slab based allocator
+ */
+int slab_is_available(void)
+{
+        return g_cpucache_up == FULL;
+}
+
 static DEFINE_PER_CPU(struct work_struct, reap_work);
 
 static void free_block(struct kmem_cache *cachep, void **objpp, int len,
@@ -1348,12 +1351,6 @@ void __init kmem_cache_init(void)
                                         NULL, NULL);
                 }
 
-                /* Inc off-slab bufctl limit until the ceiling is hit. */
-                if (!(OFF_SLAB(sizes->cs_cachep))) {
-                        offslab_limit = sizes->cs_size - sizeof(struct slab);
-                        offslab_limit /= sizeof(kmem_bufctl_t);
-                }
-
                 sizes->cs_dmacachep = kmem_cache_create(names->name_dma,
                                         sizes->cs_size,
                                         ARCH_KMALLOC_MINALIGN,
@@ -1772,6 +1769,7 @@ static void set_up_list3s(struct kmem_cache *cachep, int index)
 static size_t calculate_slab_order(struct kmem_cache *cachep,
                         size_t size, size_t align, unsigned long flags)
 {
+        unsigned long offslab_limit;
         size_t left_over = 0;
         int gfporder;
 
@@ -1783,9 +1781,18 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
                 if (!num)
                         continue;
 
-                /* More than offslab_limit objects will cause problems */
-                if ((flags & CFLGS_OFF_SLAB) && num > offslab_limit)
-                        break;
+                if (flags & CFLGS_OFF_SLAB) {
+                        /*
+                         * Max number of objs-per-slab for caches which
+                         * use off-slab slabs. Needed to avoid a possible
+                         * looping condition in cache_grow().
+                         */
+                        offslab_limit = size - sizeof(struct slab);
+                        offslab_limit /= sizeof(kmem_bufctl_t);
+
+                        if (num > offslab_limit)
+                                break;
+                }
 
                 /* Found something acceptable - save it away */
                 cachep->num = num;
@@ -2192,11 +2199,14 @@ static void drain_cpu_caches(struct kmem_cache *cachep)
         check_irq_on();
         for_each_online_node(node) {
                 l3 = cachep->nodelists[node];
-                if (l3) {
+                if (l3 && l3->alien)
+                        drain_alien_cache(cachep, l3->alien);
+        }
+
+        for_each_online_node(node) {
+                l3 = cachep->nodelists[node];
+                if (l3)
                         drain_array(cachep, l3, l3->shared, 1, node);
-                        if (l3->alien)
-                                drain_alien_cache(cachep, l3->alien);
-                }
         }
 }
 
diff --git a/mm/sparse.c b/mm/sparse.c
index d7c32de99ee8..100040c0dfb6 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -32,7 +32,7 @@ static struct mem_section *sparse_index_alloc(int nid)
         unsigned long array_size = SECTIONS_PER_ROOT *
                                    sizeof(struct mem_section);
 
-        if (system_state == SYSTEM_RUNNING)
+        if (slab_is_available())
                 section = kmalloc_node(array_size, GFP_KERNEL, nid);
         else
                 section = alloc_bootmem_node(NODE_DATA(nid), array_size);
@@ -87,11 +87,8 @@ int __section_nr(struct mem_section* ms)
         unsigned long root_nr;
         struct mem_section* root;
 
-        for (root_nr = 0;
-             root_nr < NR_MEM_SECTIONS;
-             root_nr += SECTIONS_PER_ROOT) {
-                root = __nr_to_section(root_nr);
-
+        for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
+                root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
                 if (!root)
                         continue;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4649a63a8cb6..440a733fe2e9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1061,7 +1061,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages,
 loop_again:
         total_scanned = 0;
         nr_reclaimed = 0;
-        sc.may_writepage = !laptop_mode,
+        sc.may_writepage = !laptop_mode;
         sc.nr_mapped = read_page_state(nr_mapped);
 
         inc_page_state(pageoutrun);