From 5f155f27cb7f0670429e2b8bb954094fa4110df9 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 6 Jul 2017 15:40:09 -0700 Subject: [PATCH] mm, cpuset: always use seqlock when changing task's nodemask When updating task's mems_allowed and rebinding its mempolicy due to cpuset's mems being changed, we currently only take the seqlock for writing when either the task has a mempolicy, or the new mems has no intersection with the old mems. This should be enough to prevent a parallel allocation seeing no available nodes, but the optimization is IMHO unnecessary (cpuset updates should not be frequent), and we still potentially risk issues if the intersection of new and old nodes has limited amount of free/reclaimable memory. Let's just use the seqlock for all tasks. Link: http://lkml.kernel.org/r/20170517081140.30654-6-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Anshuman Khandual Cc: Christoph Lameter Cc: David Rientjes Cc: Dimitri Sivanich Cc: Hugh Dickins Cc: Li Zefan Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup/cpuset.c | 29 ++++++++--------------------- 1 file changed, 8 insertions(+), 21 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5fd1bdbaa381..ca8376e5008c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1038,38 +1038,25 @@ static void cpuset_post_attach(void) * @tsk: the task to change * @newmems: new nodes that the task will be set * - * In order to avoid seeing no nodes if the old and new nodes are disjoint, - * we structure updates as setting all new allowed nodes, then clearing newly - * disallowed ones. + * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed + * and rebind an eventual tasks' mempolicy. If the task is allocating in + * parallel, it might temporarily see an empty intersection, which results in + * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { - bool need_loop; - task_lock(tsk); - /* - * Determine if a loop is necessary if another thread is doing - * read_mems_allowed_begin(). If at least one node remains unchanged and - * tsk does not have a mempolicy, then an empty nodemask will not be - * possible when mems_allowed is larger than a word. - */ - need_loop = task_has_mempolicy(tsk) || - !nodes_intersects(*newmems, tsk->mems_allowed); - if (need_loop) { - local_irq_disable(); - write_seqcount_begin(&tsk->mems_allowed_seq); - } + local_irq_disable(); + write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; - if (need_loop) { - write_seqcount_end(&tsk->mems_allowed_seq); - local_irq_enable(); - } + write_seqcount_end(&tsk->mems_allowed_seq); + local_irq_enable(); task_unlock(tsk); }