summaryrefslogtreecommitdiff
path: root/mm/mempolicy.c
diff options
context:
space:
mode:
authorAbel Wu <wuyun.abel@bytedance.com>2022-08-11 15:41:57 +0300
committerAndrew Morton <akpm@linux-foundation.org>2022-09-12 06:25:50 +0300
commit12c1dc8e7441773c74dc62fab76553c24015f6e1 (patch)
tree418783ab74bc0256a5b7e499ec9badb82a23b793 /mm/mempolicy.c
parent9a79443ddc3b9c3e1c4766209b86770585b5f7cc (diff)
downloadlinux-12c1dc8e7441773c74dc62fab76553c24015f6e1.tar.xz
mm/mempolicy: fix lock contention on mems_allowed
The mems_allowed field can be modified by other tasks, so it isn't safe to access it with alloc_lock unlocked even in the current process context. Say there are two tasks: A from cpusetA is performing set_mempolicy(2), and B is changing cpusetA's cpuset.mems: A (set_mempolicy) B (echo xx > cpuset.mems) ------------------------------------------------------- pol = mpol_new(); update_tasks_nodemask(cpusetA) { foreach t in cpusetA { cpuset_change_task_nodemask(t) { mpol_set_nodemask(pol) { task_lock(t); // t could be A new = f(A->mems_allowed); update t->mems_allowed; pol.create(pol, new); task_unlock(t); } } } } task_lock(A); A->mempolicy = pol; task_unlock(A); In this case A's pol->nodes is computed by old mems_allowed, and could be inconsistent with A's new mems_allowed. While it is different when replacing vmas' policy: the pol->nodes is gone wild only when current_cpuset_is_being_rebound(): A (mbind) B (echo xx > cpuset.mems) ------------------------------------------------------- pol = mpol_new(); mmap_write_lock(A->mm); cpuset_being_rebound = cpusetA; update_tasks_nodemask(cpusetA) { foreach t in cpusetA { cpuset_change_task_nodemask(t) { mpol_set_nodemask(pol) { task_lock(t); // t could be A mask = f(A->mems_allowed); update t->mems_allowed; pol.create(pol, mask); task_unlock(t); } } foreach v in A->mm { if (cpuset_being_rebound == cpusetA) pol.rebind(pol, cpuset.mems); v->vma_policy = pol; } mmap_write_unlock(A->mm); mmap_write_lock(t->mm); mpol_rebind_mm(t->mm); mmap_write_unlock(t->mm); } } cpuset_being_rebound = NULL; In this case, the cpuset.mems, which has already done updating, is finally used for calculating pol->nodes, rather than A->mems_allowed. So it is OK to call mpol_set_nodemask() with alloc_lock unlocked when doing mbind(2). Link: https://lkml.kernel.org/r/20220811124157.74888-1-wuyun.abel@bytedance.com Fixes: 78b132e9bae9 ("mm/mempolicy: remove or narrow the lock on current") Signed-off-by: Abel Wu <wuyun.abel@bytedance.com> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Wei Yang <richard.weiyang@gmail.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r--mm/mempolicy.c4
1 files changed, 3 insertions, 1 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b73d3248d976..ff6a88114bb8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -853,12 +853,14 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
goto out;
}
+ task_lock(current);
ret = mpol_set_nodemask(new, nodes, scratch);
if (ret) {
+ task_unlock(current);
mpol_put(new);
goto out;
}
- task_lock(current);
+
old = current->mempolicy;
current->mempolicy = new;
if (new && new->mode == MPOL_INTERLEAVE)