8 files changed, 51 insertions, 10 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 54e968650855..876bc595d0f8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2129,13 +2129,20 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
          * After a write we want buffered reads to be sure to go to disk to get
          * the new data.  We invalidate clean cached page from the region we're
          * about to write.  We do this *before* the write so that we can return
-         * -EIO without clobbering -EIOCBQUEUED from ->direct_IO().
+         * without clobbering -EIOCBQUEUED from ->direct_IO().
          */
         if (mapping->nrpages) {
                 written = invalidate_inode_pages2_range(mapping,
                                         pos >> PAGE_CACHE_SHIFT, end);
-                if (written)
+                /*
+                 * If a page can not be invalidated, return 0 to fall back
+                 * to buffered write.
+                 */
+                if (written) {
+                        if (written == -EBUSY)
+                                return 0;
                         goto out;
+                }
         }
 
         written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs);
diff --git a/mm/mmap.c b/mm/mmap.c
index 339cf5c4d5d8..e7a5a68a9c2e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1030,6 +1030,10 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
         } else {
                 switch (flags & MAP_TYPE) {
                 case MAP_SHARED:
+                        /*
+                         * Ignore pgoff.
+                         */
+                        pgoff = 0;
                         vm_flags |= VM_SHARED | VM_MAYSHARE;
                         break;
                 case MAP_PRIVATE:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index af982f7cdb2a..e293c58bea58 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -694,6 +694,9 @@ static int move_freepages(struct zone *zone,
 #endif
 
         for (page = start_page; page <= end_page;) {
+                /* Make sure we are not inadvertently changing nodes */
+                VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone));
+
                 if (!pfn_valid_within(page_to_pfn(page))) {
                         page++;
                         continue;
@@ -2516,6 +2519,10 @@ static void setup_zone_migrate_reserve(struct zone *zone)
                         continue;
                 page = pfn_to_page(pfn);
 
+                /* Watch out for overlapping nodes */
+                if (page_to_nid(page) != zone_to_nid(zone))
+                        continue;
+
                 /* Blocks with reserved pages will never free, skip them. */
                 if (PageReserved(page))
                         continue;
@@ -4064,7 +4071,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-struct pglist_data contig_page_data = { .bdata = &bootmem_node_data[0] };
+struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
 EXPORT_SYMBOL(contig_page_data);
 #endif
 
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 3444b58033c8..c69f84fe038d 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -2,7 +2,6 @@
  * linux/mm/page_isolation.c
  */
 
-#include <stddef.h>
 #include <linux/mm.h>
 #include <linux/page-isolation.h>
 #include <linux/pageblock-flags.h>
diff --git a/mm/quicklist.c b/mm/quicklist.c
index 3f703f7cb398..8dbb6805ef35 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -26,7 +26,10 @@ DEFINE_PER_CPU(struct quicklist, quicklist)[CONFIG_NR_QUICK];
 static unsigned long max_pages(unsigned long min_pages)
 {
         unsigned long node_free_pages, max;
-        struct zone *zones = NODE_DATA(numa_node_id())->node_zones;
+        int node = numa_node_id();
+        struct zone *zones = NODE_DATA(node)->node_zones;
+        int num_cpus_on_node;
+        node_to_cpumask_ptr(cpumask_on_node, node);
 
         node_free_pages =
 #ifdef CONFIG_ZONE_DMA
@@ -38,6 +41,10 @@ static unsigned long max_pages(unsigned long min_pages)
                 zone_page_state(&zones[ZONE_NORMAL], NR_FREE_PAGES);
 
         max = node_free_pages / FRACTION_OF_NODE_MEM;
+
+        num_cpus_on_node = cpus_weight_nr(*cpumask_on_node);
+        max /= num_cpus_on_node;
+
         return max(max, min_pages);
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index 4f5b96149458..fb486d5540f8 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2312,7 +2312,7 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 
         s->refcount = 1;
 #ifdef CONFIG_NUMA
-        s->remote_node_defrag_ratio = 100;
+        s->remote_node_defrag_ratio = 1000;
 #endif
         if (!init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))
                 goto error;
@@ -4058,7 +4058,7 @@ static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s,
         if (err)
                 return err;
 
-        if (ratio < 100)
+        if (ratio <= 100)
                 s->remote_node_defrag_ratio = ratio * 10;
 
         return length;
diff --git a/mm/truncate.c b/mm/truncate.c
index 250505091d37..6650c1d878b4 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -380,7 +380,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page)
  * Any pages which are found to be mapped into pagetables are unmapped prior to
  * invalidation.
  *
- * Returns -EIO if any pages could not be invalidated.
+ * Returns -EBUSY if any pages could not be invalidated.
  */
 int invalidate_inode_pages2_range(struct address_space *mapping,
                                   pgoff_t start, pgoff_t end)
@@ -440,7 +440,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
                         ret2 = do_launder_page(mapping, page);
                         if (ret2 == 0) {
                                 if (!invalidate_complete_page2(mapping, page))
-                                        ret2 = -EIO;
+                                        ret2 = -EBUSY;
                         }
                         if (ret2 < 0)
                                 ret = ret2;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b0d08e667ece..d7826af2fb07 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -516,9 +516,26 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m,
                         continue;
 
                 page = pfn_to_page(pfn);
+#ifdef CONFIG_ARCH_FLATMEM_HAS_HOLES
+                /*
+                 * Ordinarily, memory holes in flatmem still have a valid
+                 * memmap for the PFN range. However, an architecture for
+                 * embedded systems (e.g. ARM) can free up the memmap backing
+                 * holes to save memory on the assumption the memmap is
+                 * never used. The page_zone linkages are then broken even
+                 * though pfn_valid() returns true. Skip the page if the
+                 * linkages are broken. Even if this test passed, the impact
+                 * is that the counters for the movable type are off but
+                 * fragmentation monitoring is likely meaningless on small
+                 * systems.
+                 */
+                if (page_zone(page) != zone)
+                        continue;
+#endif
                 mtype = get_pageblock_migratetype(page);
 
-                count[mtype]++;
+                if (mtype < MIGRATE_TYPES)
+                        count[mtype]++;
         }
 
         /* Print counts */