1 files changed, 50 insertions, 27 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5717f27a0704..850c4a7e2fe5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -234,6 +234,12 @@ static void bad_page(struct page *page)
         static unsigned long nr_shown;
         static unsigned long nr_unshown;
 
+        /* Don't complain about poisoned pages */
+        if (PageHWPoison(page)) {
+                __ClearPageBuddy(page);
+                return;
+        }
+
         /*
          * Allow a burst of 60 reports, then keep quiet for that minute;
          * or allow a steady drip of one report per second.
@@ -480,7 +486,6 @@ static inline void __free_one_page(struct page *page,
         zone->free_area[order].nr_free++;
 }
 
-#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
 /*
  * free_page_mlock() -- clean up attempts to free and mlocked() page.
  * Page should not be on lru, so no need to fix that up.
@@ -491,9 +496,6 @@ static inline void free_page_mlock(struct page *page)
         __dec_zone_page_state(page, NR_MLOCK);
         __count_vm_event(UNEVICTABLE_MLOCKFREED);
 }
-#else
-static void free_page_mlock(struct page *page) { }
-#endif
 
 static inline int free_pages_check(struct page *page)
 {
@@ -666,7 +668,7 @@ static inline void expand(struct zone *zone, struct page *page,
 /*
  * This page is about to be returned from the page allocator
  */
-static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+static inline int check_new_page(struct page *page)
 {
         if (unlikely(page_mapcount(page) |
                 (page->mapping != NULL)  |
@@ -675,6 +677,18 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
                 bad_page(page);
                 return 1;
         }
+        return 0;
+}
+
+static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+{
+        int i;
+
+        for (i = 0; i < (1 << order); i++) {
+                struct page *p = page + i;
+                if (unlikely(check_new_page(p)))
+                        return 1;
+        }
 
         set_page_private(page, 0);
         set_page_refcounted(page);
@@ -1640,12 +1654,22 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
         if (page)
                 goto out;
 
-        /* The OOM killer will not help higher order allocs */
-        if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_NOFAIL))
-                goto out;
-
+        if (!(gfp_mask & __GFP_NOFAIL)) {
+                /* The OOM killer will not help higher order allocs */
+                if (order > PAGE_ALLOC_COSTLY_ORDER)
+                        goto out;
+                /*
+                 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
+                 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
+                 * The caller should handle page allocation failure by itself if
+                 * it specifies __GFP_THISNODE.
+                 * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER.
+                 */
+                if (gfp_mask & __GFP_THISNODE)
+                        goto out;
+        }
         /* Exhausted what can be done so it's blamo time */
-        out_of_memory(zonelist, gfp_mask, order);
+        out_of_memory(zonelist, gfp_mask, order, nodemask);
 
 out:
         clear_zonelist_oom(zonelist, gfp_mask);
@@ -1751,7 +1775,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
                  * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
                  */
                 alloc_flags &= ~ALLOC_CPUSET;
-        } else if (unlikely(rt_task(p)))
+        } else if (unlikely(rt_task(p)) && !in_interrupt())
                 alloc_flags |= ALLOC_HARDER;
 
         if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
@@ -1799,9 +1823,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
         if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
                 goto nopage;
 
+restart:
         wake_all_kswapd(order, zonelist, high_zoneidx);
 
-restart:
         /*
          * OK, we're below the kswapd watermark and have kicked background
          * reclaim. Now things get more complex, so set up alloc_flags according
@@ -2165,7 +2189,7 @@ void show_free_areas(void)
         printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
                 " active_file:%lu inactive_file:%lu isolated_file:%lu\n"
                 " unevictable:%lu"
-                " dirty:%lu writeback:%lu unstable:%lu buffer:%lu\n"
+                " dirty:%lu writeback:%lu unstable:%lu\n"
                 " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n"
                 " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n",
                 global_page_state(NR_ACTIVE_ANON),
@@ -2178,7 +2202,6 @@ void show_free_areas(void)
                 global_page_state(NR_FILE_DIRTY),
                 global_page_state(NR_WRITEBACK),
                 global_page_state(NR_UNSTABLE_NFS),
-                nr_blockdev_pages(),
                 global_page_state(NR_FREE_PAGES),
                 global_page_state(NR_SLAB_RECLAIMABLE),
                 global_page_state(NR_SLAB_UNRECLAIMABLE),
@@ -2373,7 +2396,7 @@ early_param("numa_zonelist_order", setup_numa_zonelist_order);
  * sysctl handler for numa_zonelist_order
  */
 int numa_zonelist_order_handler(ctl_table *table, int write,
-                struct file *file, void __user *buffer, size_t *length,
+                void __user *buffer, size_t *length,
                 loff_t *ppos)
 {
         char saved_string[NUMA_ZONELIST_ORDER_LEN];
@@ -2382,7 +2405,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
         if (write)
                 strncpy(saved_string, (char*)table->data,
                         NUMA_ZONELIST_ORDER_LEN);
-        ret = proc_dostring(table, write, file, buffer, length, ppos);
+        ret = proc_dostring(table, write, buffer, length, ppos);
         if (ret)
                 return ret;
         if (write) {
@@ -3110,7 +3133,7 @@ static int __cpuinit process_zones(int cpu)
 
                 if (percpu_pagelist_fraction)
                         setup_pagelist_highmark(zone_pcp(zone, cpu),
-                                (zone->present_pages / percpu_pagelist_fraction));
+                            (zone->present_pages / percpu_pagelist_fraction));
         }
 
         return 0;
@@ -4706,9 +4729,9 @@ module_init(init_per_zone_wmark_min)
  *      changes.
  */
 int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 
-        struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+        void __user *buffer, size_t *length, loff_t *ppos)
 {
-        proc_dointvec(table, write, file, buffer, length, ppos);
+        proc_dointvec(table, write, buffer, length, ppos);
         if (write)
                 setup_per_zone_wmarks();
         return 0;
@@ -4716,12 +4739,12 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 
 #ifdef CONFIG_NUMA
 int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
-        struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+        void __user *buffer, size_t *length, loff_t *ppos)
 {
         struct zone *zone;
         int rc;
 
-        rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+        rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
         if (rc)
                 return rc;
 
@@ -4732,12 +4755,12 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
 }
 
 int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
-        struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+        void __user *buffer, size_t *length, loff_t *ppos)
 {
         struct zone *zone;
         int rc;
 
-        rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+        rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
         if (rc)
                 return rc;
 
@@ -4758,9 +4781,9 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
  * if in function of the boot time zone sizes.
  */
 int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
-        struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+        void __user *buffer, size_t *length, loff_t *ppos)
 {
-        proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+        proc_dointvec_minmax(table, write, buffer, length, ppos);
         setup_per_zone_lowmem_reserve();
         return 0;
 }
@@ -4772,13 +4795,13 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
  */
 
 int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
-        struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+        void __user *buffer, size_t *length, loff_t *ppos)
 {
         struct zone *zone;
         unsigned int cpu;
         int ret;
 
-        ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+        ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
         if (!write || (ret == -EINVAL))
                 return ret;
         for_each_populated_zone(zone) {