1 files changed, 64 insertions, 18 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7dd9d9f80694..290fb5bf0440 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -85,10 +85,12 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/migrate.h>
+#include <linux/ksm.h>
 #include <linux/rmap.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
 #include <linux/ctype.h>
+#include <linux/mm_inline.h>
 
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -412,17 +414,11 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                 if (!page)
                         continue;
                 /*
-                 * The check for PageReserved here is important to avoid
-                 * handling zero pages and other pages that may have been
-                 * marked special by the system.
-                 *
-                 * If the PageReserved would not be checked here then f.e.
-                 * the location of the zero page could have an influence
-                 * on MPOL_MF_STRICT, zero pages would be counted for
-                 * the per node stats, and there would be useless attempts
-                 * to put zero pages on the migration list.
+                 * vm_normal_page() filters out zero pages, but there might
+                 * still be PageReserved pages to skip, perhaps in a VDSO.
+                 * And we cannot move PageKsm pages sensibly or safely yet.
                  */
-                if (PageReserved(page))
+                if (PageReserved(page) || PageKsm(page))
                         continue;
                 nid = page_to_nid(page);
                 if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
@@ -809,6 +805,8 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
         if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
                 if (!isolate_lru_page(page)) {
                         list_add_tail(&page->lru, pagelist);
+                        inc_zone_page_state(page, NR_ISOLATED_ANON +
+                                            page_is_file_cache(page));
                 }
         }
 }
@@ -836,7 +834,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
                         flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 
         if (!list_empty(&pagelist))
-                err = migrate_pages(&pagelist, new_node_page, dest);
+                err = migrate_pages(&pagelist, new_node_page, dest, 0);
 
         return err;
 }
@@ -1024,7 +1022,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 
                 err = migrate_prep();
                 if (err)
-                        return err;
+                        goto mpol_out;
         }
         {
                 NODEMASK_SCRATCH(scratch);
@@ -1039,10 +1037,9 @@ static long do_mbind(unsigned long start, unsigned long len,
                         err = -ENOMEM;
                 NODEMASK_SCRATCH_FREE(scratch);
         }
-        if (err) {
-                mpol_put(new);
-                return err;
-        }
+        if (err)
+                goto mpol_out;
+
         vma = check_range(mm, start, end, nmask,
                           flags | MPOL_MF_INVERT, &pagelist);
 
@@ -1054,13 +1051,15 @@ static long do_mbind(unsigned long start, unsigned long len,
 
                 if (!list_empty(&pagelist))
                         nr_failed = migrate_pages(&pagelist, new_vma_page,
-                                                (unsigned long)vma);
+                                                (unsigned long)vma, 0);
 
                 if (!err && nr_failed && (flags & MPOL_MF_STRICT))
                         err = -EIO;
-        }
+        } else
+                putback_lru_pages(&pagelist);
 
         up_write(&mm->mmap_sem);
+ mpol_out:
         mpol_put(new);
         return err;
 }
@@ -1564,6 +1563,53 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
         }
         return zl;
 }
+
+/*
+ * init_nodemask_of_mempolicy
+ *
+ * If the current task's mempolicy is "default" [NULL], return 'false'
+ * to indicate default policy.  Otherwise, extract the policy nodemask
+ * for 'bind' or 'interleave' policy into the argument nodemask, or
+ * initialize the argument nodemask to contain the single node for
+ * 'preferred' or 'local' policy and return 'true' to indicate presence
+ * of non-default mempolicy.
+ *
+ * We don't bother with reference counting the mempolicy [mpol_get/put]
+ * because the current task is examining it's own mempolicy and a task's
+ * mempolicy is only ever changed by the task itself.
+ *
+ * N.B., it is the caller's responsibility to free a returned nodemask.
+ */
+bool init_nodemask_of_mempolicy(nodemask_t *mask)
+{
+        struct mempolicy *mempolicy;
+        int nid;
+
+        if (!(mask && current->mempolicy))
+                return false;
+
+        mempolicy = current->mempolicy;
+        switch (mempolicy->mode) {
+        case MPOL_PREFERRED:
+                if (mempolicy->flags & MPOL_F_LOCAL)
+                        nid = numa_node_id();
+                else
+                        nid = mempolicy->v.preferred_node;
+                init_nodemask_of_node(mask, nid);
+                break;
+
+        case MPOL_BIND:
+                /* Fall through */
+        case MPOL_INTERLEAVE:
+                *mask =  mempolicy->v.nodes;
+                break;
+
+        default:
+                BUG();
+        }
+
+        return true;
+}
 #endif
 
 /* Allocate a page in interleaved policy.