From 18fa84a2db0e15b02baa5d94bdb5bd509175d2f6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 29 May 2019 13:46:25 -0700 Subject: cgroup: Use css_tryget() instead of css_tryget_online() in task_get_css() A PF_EXITING task can stay associated with an offline css. If such task calls task_get_css(), it can get stuck indefinitely. This can be triggered by BSD process accounting which writes to a file with PF_EXITING set when racing against memcg disable as in the backtrace at the end. After this change, task_get_css() may return a css which was already offline when the function was called. None of the existing users are affected by this change. INFO: rcu_sched self-detected stall on CPU INFO: rcu_sched detected stalls on CPUs/tasks: ... NMI backtrace for cpu 0 ... Call Trace: dump_stack+0x46/0x68 nmi_cpu_backtrace.cold.2+0x13/0x57 nmi_trigger_cpumask_backtrace+0xba/0xca rcu_dump_cpu_stacks+0x9e/0xce rcu_check_callbacks.cold.74+0x2af/0x433 update_process_times+0x28/0x60 tick_sched_timer+0x34/0x70 __hrtimer_run_queues+0xee/0x250 hrtimer_interrupt+0xf4/0x210 smp_apic_timer_interrupt+0x56/0x110 apic_timer_interrupt+0xf/0x20 RIP: 0010:balance_dirty_pages_ratelimited+0x28f/0x3d0 ... btrfs_file_write_iter+0x31b/0x563 __vfs_write+0xfa/0x140 __kernel_write+0x4f/0x100 do_acct_process+0x495/0x580 acct_process+0xb9/0xdb do_exit+0x748/0xa00 do_group_exit+0x3a/0xa0 get_signal+0x254/0x560 do_signal+0x23/0x5c0 exit_to_usermode_loop+0x5d/0xa0 prepare_exit_to_usermode+0x53/0x80 retint_user+0x8/0x8 Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v4.2+ Fixes: ec438699a9ae ("cgroup, block: implement task_get_css() and use it in bio_associate_current()") --- include/linux/cgroup.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c0077adeea83..a7e4611e20c8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -487,7 +487,7 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, * * Find the css for the (@task, @subsys_id) combination, increment a * reference on and return it. This function is guaranteed to return a - * valid css. + * valid css. The returned css may already have been offlined. */ static inline struct cgroup_subsys_state * task_get_css(struct task_struct *task, int subsys_id) @@ -497,7 +497,13 @@ task_get_css(struct task_struct *task, int subsys_id) rcu_read_lock(); while (true) { css = task_css(task, subsys_id); - if (likely(css_tryget_online(css))) + /* + * Can't use css_tryget_online() here. A task which has + * PF_EXITING set may stay associated with an offline css. + * If such task calls this function, css_tryget_online() + * will keep failing. + */ + if (likely(css_tryget(css))) break; cpu_relax(); } -- cgit v1.2.3