[PATCH 3.2 121/131] slab/mempolicy: always use local policy from interrupt context

[Ben Hutchings]

3.2.63-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

commit e7b691b085fda913830e5280ae6f724b2a63c824 upstream.

slab_node() could access current->mempolicy from interrupt context.
However there's a race condition during exit where the mempolicy
is first freed and then the pointer zeroed.

Using this from interrupts seems bogus anyways. The interrupt
will interrupt a random process and therefore get a random
mempolicy. Many times, this will be idle's, which noone can change.

Just disable this here and always use local for slab
from interrupts. I also cleaned up the callers of slab_node a bit
which always passed the same argument.

I believe the original mempolicy code did that in fact,
so it's likely a regression.

v2: send version with correct logic
v3: simplify. fix typo.
Reported-by: Arun Sharma <asharma@xxxxxx>
Cc: penberg@xxxxxxxxxx
Cc: cl@xxxxxxxxx
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
[tdmackey@xxxxxxxxxxx: Rework control flow based on feedback from
cl@xxxxxxxxx, fix logic, and cleanup current task_struct reference]
Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
Acked-by: Christoph Lameter <cl@xxxxxxxxx>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Signed-off-by: David Mackey <tdmackey@xxxxxxxxxxx>
Signed-off-by: Pekka Enberg <penberg@xxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 include/linux/mempolicy.h | 2 +-
 mm/mempolicy.c            | 8 +++++++-
 mm/slab.c                 | 4 ++--
 mm/slub.c                 | 2 +-
 4 files changed, 11 insertions(+), 5 deletions(-)

--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -205,7 +205,7 @@ extern struct zonelist *huge_zonelist(st
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				const nodemask_t *mask);
-extern unsigned slab_node(struct mempolicy *policy);
+extern unsigned slab_node(void);
 
 extern enum zone_type policy_zone;
 
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1601,8 +1601,14 @@ static unsigned interleave_nodes(struct
  * task can change it's policy.  The system default policy requires no
  * such protection.
  */
-unsigned slab_node(struct mempolicy *policy)
+unsigned slab_node(void)
 {
+	struct mempolicy *policy;
+
+	if (in_interrupt())
+		return numa_node_id();
+
+	policy = current->mempolicy;
 	if (!policy || policy->flags & MPOL_F_LOCAL)
 		return numa_node_id();
 
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3270,7 +3270,7 @@ static void *alternate_node_alloc(struct
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
-		nid_alloc = slab_node(current->mempolicy);
+		nid_alloc = slab_node();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;
@@ -3302,7 +3302,7 @@ static void *fallback_alloc(struct kmem_
 
 retry_cpuset:
 	cpuset_mems_cookie = get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+	zonelist = node_zonelist(slab_node(), flags);
 
 retry:
 	/*
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1608,7 +1608,7 @@ static struct page *get_any_partial(stru
 
 	do {
 		cpuset_mems_cookie = get_mems_allowed();
-		zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+		zonelist = node_zonelist(slab_node(), flags);
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 			struct kmem_cache_node *n;
 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/