From 4ba9515d32bac1c54c2357796e32d68eeab784ce Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 2 Sep 2021 14:56:05 -0700 Subject: [PATCH] memcg: make memcg->event_list_lock irqsafe The memcg->event_list_lock is usually taken in the normal context but when the userspace closes the corresponding eventfd, eventfd_release through memcg_event_wake takes memcg->event_list_lock with interrupts disabled. This is not an issue on its own but it creates a nested dependency from eventfd_ctx->wqh.lock to memcg->event_list_lock. Independently, for unrelated eventfd, eventfd_signal() can be called in the irq context, thus making eventfd_ctx->wqh.lock an irq lock. For example, FPGA DFL driver, VHOST VPDA driver and couple of VFIO drivers. This will force memcg->event_list_lock to be an irqsafe lock as well. One way to break the nested dependency between eventfd_ctx->wqh.lock and memcg->event_list_lock is to add an indirection. However the simplest solution would be to make memcg->event_list_lock irqsafe. This is cgroup v1 feature, is in maintenance and may get deprecated in near future. So, no need to add more code. BTW this has been discussed previously [1] but there weren't irq users of eventfd_signal() at the time. [1] https://www.spinics.net/lists/cgroups/msg06248.html Link: https://lkml.kernel.org/r/20210830172953.207257-1-shakeelb@google.com Signed-off-by: Shakeel Butt Cc: Tejun Heo Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 81fa831..06ae007 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4839,9 +4839,9 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, vfs_poll(efile.file, &event->pt); - spin_lock(&memcg->event_list_lock); + spin_lock_irq(&memcg->event_list_lock); list_add(&event->list, &memcg->event_list); - spin_unlock(&memcg->event_list_lock); + spin_unlock_irq(&memcg->event_list_lock); fdput(cfile); fdput(efile); @@ -5268,12 +5268,12 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) * Notify userspace about cgroup removing only after rmdir of cgroup * directory to avoid race between userspace and kernelspace. */ - spin_lock(&memcg->event_list_lock); + spin_lock_irq(&memcg->event_list_lock); list_for_each_entry_safe(event, tmp, &memcg->event_list, list) { list_del_init(&event->list); schedule_work(&event->remove); } - spin_unlock(&memcg->event_list_lock); + spin_unlock_irq(&memcg->event_list_lock); page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0); -- 2.7.4