vserver 2.0 rc7

[linux-2.6.git] / mm / mempolicy.c

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1511786..08c41da 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -67,6 +67,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/nodemask.h>
+#include <linux/cpuset.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -167,6 +168,10 @@ static int get_nodes(unsigned long *nodes, unsigned long __user *nmask,
        if (copy_from_user(nodes, nmask, nlongs*sizeof(unsigned long)))
                return -EFAULT;
        nodes[nlongs-1] &= endmask;
+       /* Update current mems_allowed */
+       cpuset_update_current_mems_allowed();
+       /* Ignore nodes not set in current->mems_allowed */
+       cpuset_restrict_to_mems_allowed(nodes);
        return mpol_check_policy(mode, nodes);
 }
 
@@ -643,7 +648,7 @@ get_vma_policy(struct vm_area_struct *vma, unsigned long addr)
 }
 
 /* Return a zonelist representing a mempolicy */
-static struct zonelist *zonelist_policy(unsigned gfp, struct mempolicy *policy)
+static struct zonelist *zonelist_policy(unsigned int __nocast gfp, struct mempolicy *policy)
 {
        int nd;
 
@@ -655,8 +660,10 @@ static struct zonelist *zonelist_policy(unsigned gfp, struct mempolicy *policy)
                break;
        case MPOL_BIND:
                /* Lower zones don't get a policy applied */
-               if (gfp >= policy_zone)
-                       return policy->v.zonelist;
+               /* Careful: current->mems_allowed might have moved */
+               if ((gfp & GFP_ZONEMASK) >= policy_zone)
+                       if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
+                               return policy->v.zonelist;
                /*FALL THROUGH*/
        case MPOL_INTERLEAVE: /* should not happen */
        case MPOL_DEFAULT:
@@ -705,7 +712,7 @@ static unsigned offset_il_node(struct mempolicy *pol,
 
 /* Allocate a page in interleaved policy.
    Own path because it needs to do special accounting. */
-static struct page *alloc_page_interleave(unsigned gfp, unsigned order, unsigned nid)
+static struct page *alloc_page_interleave(unsigned int __nocast gfp, unsigned order, unsigned nid)
 {
        struct zonelist *zl;
        struct page *page;
@@ -743,10 +750,12 @@ static struct page *alloc_page_interleave(unsigned gfp, unsigned order, unsigned
  *     Should be called with the mm_sem of the vma hold.
  */
 struct page *
-alloc_page_vma(unsigned gfp, struct vm_area_struct *vma, unsigned long addr)
+alloc_page_vma(unsigned int __nocast gfp, struct vm_area_struct *vma, unsigned long addr)
 {
        struct mempolicy *pol = get_vma_policy(vma, addr);
 
+       cpuset_update_current_mems_allowed();
+
        if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
                unsigned nid;
                if (vma) {
@@ -779,11 +788,17 @@ alloc_page_vma(unsigned gfp, struct vm_area_struct *vma, unsigned long addr)
  *     Allocate a page from the kernel page pool.  When not in
  *     interrupt context and apply the current process NUMA policy.
  *     Returns NULL when no page can be allocated.
+ *
+ *     Don't call cpuset_update_current_mems_allowed() unless
+ *     1) it's ok to take cpuset_sem (can WAIT), and
+ *     2) allocating for current task (not interrupt).
  */
-struct page *alloc_pages_current(unsigned gfp, unsigned order)
+struct page *alloc_pages_current(unsigned int __nocast gfp, unsigned order)
 {
        struct mempolicy *pol = current->mempolicy;
 
+       if ((gfp & __GFP_WAIT) && !in_interrupt())
+               cpuset_update_current_mems_allowed();
        if (!pol || in_interrupt())
                pol = &default_policy;
        if (pol->policy == MPOL_INTERLEAVE)