slab/mempolicy: always use local policy from interrupt context
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@fb.com>
Cc: penberg@kernel.org
Cc: cl@linux.com
Signed-off-by: Andi Kleen <ak@linux.intel.com>
[tdmackey@twitter.com: Rework control flow based on feedback from
cl@linux.com, fix logic, and cleanup current task_struct reference]
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: David Mackey <tdmackey@twitter.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 4aa4273..95b738c 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -215,7 +215,7 @@
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;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f15c1b2..cb0b230 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1602,8 +1602,14 @@
* 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();
diff --git a/mm/slab.c b/mm/slab.c
index fc4a774..dd607a8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3310,7 +3310,7 @@
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;
@@ -3342,7 +3342,7 @@
retry_cpuset:
cpuset_mems_cookie = get_mems_allowed();
- zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+ zonelist = node_zonelist(slab_node(), flags);
retry:
/*
diff --git a/mm/slub.c b/mm/slub.c
index 797271f..348fed1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1617,7 +1617,7 @@
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;