7 files changed, 88 insertions, 44 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 2dead9adf8b7..1e6a7d34874f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1461,6 +1461,11 @@ page_not_uptodate:
          */
         ClearPageError(page);
         error = mapping->a_ops->readpage(file, page);
+        if (!error) {
+                wait_on_page_locked(page);
+                if (!PageUptodate(page))
+                        error = -EIO;
+        }
         page_cache_release(page);
 
         if (!error || error == AOP_TRUNCATED_PAGE)
diff --git a/mm/memory.c b/mm/memory.c
index 48c122d42ed7..fb5608a120ed 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -311,6 +311,21 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
         if (!new)
                 return -ENOMEM;
 
+        /*
+         * Ensure all pte setup (eg. pte page lock and page clearing) are
+         * visible before the pte is made visible to other CPUs by being
+         * put into page tables.
+         *
+         * The other side of the story is the pointer chasing in the page
+         * table walking code (when walking the page table without locking;
+         * ie. most of the time). Fortunately, these data accesses consist
+         * of a chain of data-dependent loads, meaning most CPUs (alpha
+         * being the notable exception) will already guarantee loads are
+         * seen in-order. See the alpha page table accessors for the
+         * smp_read_barrier_depends() barriers in page table walking code.
+         */
+        smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
+
         spin_lock(&mm->page_table_lock);
         if (!pmd_present(*pmd)) {       /* Has another populated it ? */
                 mm->nr_ptes++;
@@ -329,6 +344,8 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
         if (!new)
                 return -ENOMEM;
 
+        smp_wmb(); /* See comment in __pte_alloc */
+
         spin_lock(&init_mm.page_table_lock);
         if (!pmd_present(*pmd)) {       /* Has another populated it ? */
                 pmd_populate_kernel(&init_mm, pmd, new);
@@ -2619,6 +2636,8 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
         if (!new)
                 return -ENOMEM;
 
+        smp_wmb(); /* See comment in __pte_alloc */
+
         spin_lock(&mm->page_table_lock);
         if (pgd_present(*pgd))          /* Another has populated it */
                 pud_free(mm, new);
@@ -2640,6 +2659,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
         if (!new)
                 return -ENOMEM;
 
+        smp_wmb(); /* See comment in __pte_alloc */
+
         spin_lock(&mm->page_table_lock);
 #ifndef __ARCH_HAS_4LEVEL_HACK
         if (pud_present(*pud))          /* Another has populated it */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b17dca7249f8..833f854eabe5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -159,21 +159,58 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 }
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
+static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
+                           unsigned long end_pfn)
+{
+        unsigned long old_zone_end_pfn;
+
+        zone_span_writelock(zone);
+
+        old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+        if (start_pfn < zone->zone_start_pfn)
+                zone->zone_start_pfn = start_pfn;
+
+        zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
+                                zone->zone_start_pfn;
+
+        zone_span_writeunlock(zone);
+}
+
+static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
+                            unsigned long end_pfn)
+{
+        unsigned long old_pgdat_end_pfn =
+                pgdat->node_start_pfn + pgdat->node_spanned_pages;
+
+        if (start_pfn < pgdat->node_start_pfn)
+                pgdat->node_start_pfn = start_pfn;
+
+        pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
+                                        pgdat->node_start_pfn;
+}
+
 static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 {
         struct pglist_data *pgdat = zone->zone_pgdat;
         int nr_pages = PAGES_PER_SECTION;
         int nid = pgdat->node_id;
         int zone_type;
+        unsigned long flags;
 
         zone_type = zone - pgdat->node_zones;
         if (!zone->wait_table) {
-                int ret = 0;
+                int ret;
+
                 ret = init_currently_empty_zone(zone, phys_start_pfn,
                                                 nr_pages, MEMMAP_HOTPLUG);
-                if (ret < 0)
+                if (ret)
                         return ret;
         }
+        pgdat_resize_lock(zone->zone_pgdat, &flags);
+        grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages);
+        grow_pgdat_span(zone->zone_pgdat, phys_start_pfn,
+                        phys_start_pfn + nr_pages);
+        pgdat_resize_unlock(zone->zone_pgdat, &flags);
         memmap_init_zone(nr_pages, nid, zone_type,
                          phys_start_pfn, MEMMAP_HOTPLUG);
         return 0;
@@ -299,36 +336,6 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 }
 EXPORT_SYMBOL_GPL(__remove_pages);
 
-static void grow_zone_span(struct zone *zone,
-                unsigned long start_pfn, unsigned long end_pfn)
-{
-        unsigned long old_zone_end_pfn;
-
-        zone_span_writelock(zone);
-
-        old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
-        if (start_pfn < zone->zone_start_pfn)
-                zone->zone_start_pfn = start_pfn;
-
-        zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
-                                zone->zone_start_pfn;
-
-        zone_span_writeunlock(zone);
-}
-
-static void grow_pgdat_span(struct pglist_data *pgdat,
-                unsigned long start_pfn, unsigned long end_pfn)
-{
-        unsigned long old_pgdat_end_pfn =
-                pgdat->node_start_pfn + pgdat->node_spanned_pages;
-
-        if (start_pfn < pgdat->node_start_pfn)
-                pgdat->node_start_pfn = start_pfn;
-
-        pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
-                                        pgdat->node_start_pfn;
-}
-
 void online_page(struct page *page)
 {
         totalram_pages++;
@@ -367,7 +374,6 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 
 int online_pages(unsigned long pfn, unsigned long nr_pages)
 {
-        unsigned long flags;
         unsigned long onlined_pages = 0;
         struct zone *zone;
         int need_zonelists_rebuild = 0;
@@ -395,11 +401,6 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
          * memory_block->state_mutex.
          */
         zone = page_zone(pfn_to_page(pfn));
-        pgdat_resize_lock(zone->zone_pgdat, &flags);
-        grow_zone_span(zone, pfn, pfn + nr_pages);
-        grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
-        pgdat_resize_unlock(zone->zone_pgdat, &flags);
-
         /*
          * If this zone is not populated, then it is not in zonelist.
          * This means the page allocator ignores this zone.
@@ -408,8 +409,15 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         if (!populated_zone(zone))
                 need_zonelists_rebuild = 1;
 
-        walk_memory_resource(pfn, nr_pages, &onlined_pages,
+        ret = walk_memory_resource(pfn, nr_pages, &onlined_pages,
                 online_pages_range);
+        if (ret) {
+                printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
+                        nr_pages, pfn);
+                memory_notify(MEM_CANCEL_ONLINE, &arg);
+                return ret;
+        }
+
         zone->present_pages += onlined_pages;
         zone->zone_pgdat->node_present_pages += onlined_pages;
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 4de546899dc1..a5bf31c27375 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -26,6 +26,13 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+#ifndef pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+        return newprot;
+}
+#endif
+
 static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
                 unsigned long addr, unsigned long end, pgprot_t newprot,
                 int dirty_accountable)
@@ -192,7 +199,9 @@ success:
          * held in write mode.
          */
         vma->vm_flags = newflags;
-        vma->vm_page_prot = vm_get_page_prot(newflags);
+        vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
+                                          vm_get_page_prot(newflags));
+
         if (vma_wants_writenotify(vma)) {
                 vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
                 dirty_accountable = 1;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bdd5c432c426..63835579323a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2862,8 +2862,6 @@ __meminit int init_currently_empty_zone(struct zone *zone,
 
         zone->zone_start_pfn = zone_start_pfn;
 
-        memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
-
         zone_init_free_lists(zone);
 
         return 0;
@@ -3433,6 +3431,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
                 ret = init_currently_empty_zone(zone, zone_start_pfn,
                                                 size, MEMMAP_EARLY);
                 BUG_ON(ret);
+                memmap_init(size, nid, j, zone_start_pfn);
                 zone_start_pfn += size;
         }
 }
diff --git a/mm/pdflush.c b/mm/pdflush.c
index 1c96cfc9e040..9d834aa4b979 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -207,7 +207,6 @@ int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
 
         spin_lock_irqsave(&pdflush_lock, flags);
         if (list_empty(&pdflush_list)) {
-                spin_unlock_irqrestore(&pdflush_lock, flags);
                 ret = -1;
         } else {
                 struct pdflush_work *pdf;
@@ -219,8 +218,9 @@ int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
                 pdf->fn = fn;
                 pdf->arg0 = arg0;
                 wake_up_process(pdf->who);
-                spin_unlock_irqrestore(&pdflush_lock, flags);
         }
+        spin_unlock_irqrestore(&pdflush_lock, flags);
+
         return ret;
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 1a32130b958c..db9eabb2c5b3 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -41,7 +41,9 @@ static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask)
 */
 void all_vm_events(unsigned long *ret)
 {
+        get_online_cpus();
         sum_vm_events(ret, &cpu_online_map);
+        put_online_cpus();
 }
 EXPORT_SYMBOL_GPL(all_vm_events);