[PATCH] mm/mempolicy: fix a race between offset_il_node and mpol_rebind_task

[yanghui <yanghui.def@bytedance.com>]

Servers happened below panic:
Kernel version:5.4.56
BUG: unable to handle page fault for address: 0000000000002c48
RIP: 0010:__next_zones_zonelist+0x1d/0x40
[264003.977696] RAX: 0000000000002c40 RBX: 0000000000100dca RCX: 0000000000000014
[264003.977872] Call Trace:
[264003.977888]  __alloc_pages_nodemask+0x277/0x310
[264003.977908]  alloc_page_interleave+0x13/0x70
[264003.977926]  handle_mm_fault+0xf99/0x1390
[264003.977951]  __do_page_fault+0x288/0x500
[264003.977979]  ? schedule+0x39/0xa0
[264003.977994]  do_page_fault+0x30/0x110
[264003.978010]  page_fault+0x3e/0x50

The reason of panic is that MAX_NUMNODES is passd in the third parameter
in function __alloc_pages_nodemask(preferred_nid). So if to access
zonelist->zoneref->zone_idx in __next_zones_zonelist the panic will happen.

In offset_il_node(), first_node() return nid from pol->v.nodes, after
this other threads may changed pol->v.nodes before next_node().
This race condition will let next_node return MAX_NUMNODES.So put
pol->nodes in a local variable.

The race condition is between offset_il_node and cpuset_change_task_nodemask:
CPU0:                                     CPU1:
alloc_pages_vma()
  interleave_nid(pol,)
    offset_il_node(pol,)
      first_node(pol->v.nodes)            cpuset_change_task_nodemask
                      //nodes==0xc          mpol_rebind_task
                                              mpol_rebind_policy
                                                mpol_rebind_nodemask(pol,nodes)
                      //nodes==0x3
      next_node(nid, pol->v.nodes)//return MAX_NUMNODES

Signed-off-by: yanghui <yanghui.def@bytedance.com>
---
 mm/mempolicy.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e32360e90274..9c3c168af3e2 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -193,7 +193,7 @@ static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
 {
 	if (nodes_empty(*nodes))
 		return -EINVAL;
-	pol->nodes = *nodes;
+	WRITE_ONCE(pol->nodes, *nodes);
 	return 0;
 }
 
@@ -211,7 +211,7 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
 {
 	if (nodes_empty(*nodes))
 		return -EINVAL;
-	pol->nodes = *nodes;
+	WRITE_ONCE(pol->nodes, *nodes);
 	return 0;
 }
 
@@ -334,7 +334,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
 	if (nodes_empty(tmp))
 		tmp = *nodes;
 
-	pol->nodes = tmp;
+	WRITE_ONCE(pol->nodes, tmp);
 }
 
 static void mpol_rebind_preferred(struct mempolicy *pol,
@@ -1965,7 +1965,8 @@ unsigned int mempolicy_slab_node(void)
  */
 static unsigned offset_il_node(struct mempolicy *pol, unsigned long n)
 {
-	unsigned nnodes = nodes_weight(pol->nodes);
+	nodemask_t nodemask = READ_ONCE(pol->nodes);
+	unsigned nnodes = nodes_weight(nodemask);
 	unsigned target;
 	int i;
 	int nid;
@@ -1973,9 +1974,9 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n)
 	if (!nnodes)
 		return numa_node_id();
 	target = (unsigned int)n % nnodes;
-	nid = first_node(pol->nodes);
+	nid = first_node(nodemask);
 	for (i = 0; i < target; i++)
-		nid = next_node(nid, pol->nodes);
+		nid = next_node(nid, nodemask);
 	return nid;
 }
 
-- 
2.20.1