Support strange discontiguous PFN remappings

[linux-2.6] / mm / mempolicy.c

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2076b1542b8ac9ce32beba96e051bd70a62ebf96..bec88c81244e0d4f9541f4098f5f8c8409ba455b 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -189,17 +189,15 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
        orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
        do {
-               unsigned long pfn;
+               struct page *page;
                unsigned int nid;
 
                if (!pte_present(*pte))
                        continue;
-               pfn = pte_pfn(*pte);
-               if (!pfn_valid(pfn)) {
-                       print_bad_pte(vma, *pte, addr);
+               page = vm_normal_page(vma, addr, *pte);
+               if (!page)
                        continue;
-               }
-               nid = pfn_to_nid(pfn);
+               nid = page_to_nid(page);
                if (!node_isset(nid, *nodes))
                        break;
        } while (pte++, addr += PAGE_SIZE, addr != end);
@@ -269,8 +267,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
        first = find_vma(mm, start);
        if (!first)
                return ERR_PTR(-EFAULT);
-       if (first->vm_flags & VM_RESERVED)
-               return ERR_PTR(-EACCES);
        prev = NULL;
        for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
                if (!vma->vm_next && vma->vm_end < end)
@@ -457,6 +453,7 @@ long do_get_mempolicy(int *policy, nodemask_t *nmask,
        struct vm_area_struct *vma = NULL;
        struct mempolicy *pol = current->mempolicy;
 
+       cpuset_update_current_mems_allowed();
        if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR))
                return -EINVAL;
        if (flags & MPOL_F_ADDR) {
@@ -1206,3 +1203,66 @@ void numa_default_policy(void)
 {
        do_set_mempolicy(MPOL_DEFAULT, NULL);
 }
+
+/* Migrate a policy to a different set of nodes */
+static void rebind_policy(struct mempolicy *pol, const nodemask_t *old,
+                                                       const nodemask_t *new)
+{
+       nodemask_t tmp;
+
+       if (!pol)
+               return;
+
+       switch (pol->policy) {
+       case MPOL_DEFAULT:
+               break;
+       case MPOL_INTERLEAVE:
+               nodes_remap(tmp, pol->v.nodes, *old, *new);
+               pol->v.nodes = tmp;
+               current->il_next = node_remap(current->il_next, *old, *new);
+               break;
+       case MPOL_PREFERRED:
+               pol->v.preferred_node = node_remap(pol->v.preferred_node,
+                                                               *old, *new);
+               break;
+       case MPOL_BIND: {
+               nodemask_t nodes;
+               struct zone **z;
+               struct zonelist *zonelist;
+
+               nodes_clear(nodes);
+               for (z = pol->v.zonelist->zones; *z; z++)
+                       node_set((*z)->zone_pgdat->node_id, nodes);
+               nodes_remap(tmp, nodes, *old, *new);
+               nodes = tmp;
+
+               zonelist = bind_zonelist(&nodes);
+
+               /* If no mem, then zonelist is NULL and we keep old zonelist.
+                * If that old zonelist has no remaining mems_allowed nodes,
+                * then zonelist_policy() will "FALL THROUGH" to MPOL_DEFAULT.
+                */
+
+               if (zonelist) {
+                       /* Good - got mem - substitute new zonelist */
+                       kfree(pol->v.zonelist);
+                       pol->v.zonelist = zonelist;
+               }
+               break;
+       }
+       default:
+               BUG();
+               break;
+       }
+}
+
+/*
+ * Someone moved this task to different nodes.  Fixup mempolicies.
+ *
+ * TODO - fixup current->mm->vma and shmfs/tmpfs/hugetlbfs policies as well,
+ * once we have a cpuset mechanism to mark which cpuset subtree is migrating.
+ */
+void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new)
+{
+       rebind_policy(current->mempolicy, old, new);
+}