The task->il_next variable stores the next allocation node id for task's
MPOL_INTERLEAVE policy. mpol_rebind_nodemask() updates interleave and
bind mempolicies due to changing cpuset mems. Currently it also tries to
make sure that current->il_next is valid within the updated nodemask. This is
bogus, because 1) we are updating potentially any task's mempolicy, not just
current, and 2) we might be updating a per-vma mempolicy, not task one.
The interleave_nodes() function that uses il_next can cope fine with the value
not being within the currently allowed nodes, so this hasn't manifested as an
actual issue.
We can remove the need for updating il_next completely by changing it to
il_prev and store the node id of the previous interleave allocation instead of
the next id. Then interleave_nodes() can calculate the next id using the
current nodemask and also store it as il_prev, except when querying the next
node via do_get_mempolicy().
Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
---
include/linux/sched.h | 2 +-
mm/mempolicy.c | 22 +++++++---------------
2 files changed, 8 insertions(+), 16 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6a97386c785e..b72bbfec01f9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -884,7 +884,7 @@ struct task_struct {
#ifdef CONFIG_NUMA
/* Protected by alloc_lock: */
struct mempolicy *mempolicy;
- short il_next;
+ short il_prev;
short pref_node_fork;
#endif
#ifdef CONFIG_NUMA_BALANCING
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 37d0b334bfe9..d77177c7283b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -349,12 +349,6 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes,
pol->v.nodes = tmp;
else
BUG();
-
- if (!node_isset(current->il_next, tmp)) {
- current->il_next = next_node_in(current->il_next, tmp);
- if (current->il_next >= MAX_NUMNODES)
- current->il_next = numa_node_id();
- }
}
static void mpol_rebind_preferred(struct mempolicy *pol,
@@ -812,9 +806,8 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
}
old = current->mempolicy;
current->mempolicy = new;
- if (new && new->mode == MPOL_INTERLEAVE &&
- nodes_weight(new->v.nodes))
- current->il_next = first_node(new->v.nodes);
+ if (new && new->mode == MPOL_INTERLEAVE)
+ current->il_prev = MAX_NUMNODES-1;
task_unlock(current);
mpol_put(old);
ret = 0;
@@ -916,7 +909,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
*policy = err;
} else if (pol == current->mempolicy &&
pol->mode == MPOL_INTERLEAVE) {
- *policy = current->il_next;
+ *policy = next_node_in(current->il_prev, pol->v.nodes);
} else {
err = -EINVAL;
goto out;
@@ -1697,14 +1690,13 @@ static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy,
/* Do dynamic interleaving for a process */
static unsigned interleave_nodes(struct mempolicy *policy)
{
- unsigned nid, next;
+ unsigned next;
struct task_struct *me = current;
- nid = me->il_next;
- next = next_node_in(nid, policy->v.nodes);
+ next = next_node_in(me->il_prev, policy->v.nodes);
if (next < MAX_NUMNODES)
- me->il_next = next;
- return nid;
+ me->il_prev = next;
+ return next;
}
/*
--
2.12.2
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
