[PATCH 3/3] mm: add __rcu symbol for task->mempolicy

[Zhongkun He]

The task->mempolicy is protected by task_lock in slow path,
but there is no locking and reference in hot path for performance.
It will be difficult if other processes want to adjust it.
It is for these reasons to add __rcu symbol for task mempolicy.
There is no need to add RCU protection to vma mempolicy, which
is protected by mmap_lock.

Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Zhongkun He <hezhongkun.hzk@xxxxxxxxxxxxx>
---
 include/linux/sched.h | 2 +-
 mm/mempolicy.c        | 9 ++++-----
 mm/slab.c             | 5 +++--
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ffb6eb55cd13..c8a297ca61ab 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1252,7 +1252,7 @@ struct task_struct {
 #endif
 #ifdef CONFIG_NUMA
 	/* Protected by alloc_lock: */
-	struct mempolicy		*mempolicy;
+	struct mempolicy __rcu		*mempolicy;
 	short				il_prev;
 	short				pref_node_fork;
 #endif
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0feffb7ff01e..837083fff9c8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -894,8 +894,7 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 		goto out;
 	}
 
-	old = current->mempolicy;
-	current->mempolicy = new;
+	old = rcu_replace_pointer(current->mempolicy, new, true);
 	if (new && new->mode == MPOL_INTERLEAVE)
 		current->il_prev = MAX_NUMNODES-1;
 	task_unlock(current);
@@ -999,7 +998,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 			if (err < 0)
 				goto out;
 			*policy = err;
-		} else if (pol == current->mempolicy &&
+		} else if (pol == rcu_access_pointer(current->mempolicy) &&
 				pol->mode == MPOL_INTERLEAVE) {
 			*policy = next_node_in(current->il_prev, pol->nodes);
 		} else {
@@ -2065,7 +2064,7 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask)
 {
 	struct mempolicy *mempolicy;
 
-	if (!(mask && current->mempolicy))
+	if (!(mask && rcu_access_pointer(current->mempolicy)))
 		return false;
 
 	task_lock(current);
@@ -2426,7 +2425,7 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 		return ERR_PTR(-ENOMEM);
 
 	/* task's mempolicy is protected by alloc_lock */
-	if (old == current->mempolicy) {
+	if (old == rcu_access_pointer(current->mempolicy)) {
 		task_lock(current);
 		*new = *old;
 		task_unlock(current);
diff --git a/mm/slab.c b/mm/slab.c
index 59c8e28f7b6a..f205869d6c36 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3052,7 +3052,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	nid_alloc = nid_here = numa_mem_id();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
-	else if (current->mempolicy)
+	else if (rcu_access_pointer(current->mempolicy))
 		nid_alloc = mempolicy_slab_node();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
@@ -3188,7 +3188,8 @@ __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	int slab_node = numa_mem_id();
 
 	if (nodeid == NUMA_NO_NODE) {
-		if (current->mempolicy || cpuset_do_slab_mem_spread()) {
+		if (rcu_access_pointer(current->mempolicy) ||
+				cpuset_do_slab_mem_spread()) {
 			objp = alternate_node_alloc(cachep, flags);
 			if (objp)
 				goto out;
-- 
2.25.1