| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 23 Jan 2020 16:56:19 -0500
From: Phil Auld <pauld@...hat.com>
To: Kirill Tkhai <ktkhai@...tuozzo.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
Juri Lelli <juri.lelli@...il.com>, mingo@...hat.com,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3]sched/rt: Stop for_each_process_thread() iterations in
tg_has_rt_tasks()
Hi,
On Thu, Apr 26, 2018 at 12:54:41PM +0300 Kirill Tkhai wrote:
> From: Kirill Tkhai <ktkhai@...tuozzo.com>
>
> tg_rt_schedulable() iterates over all child task groups,
> while tg_has_rt_tasks() iterates over all linked tasks.
> In case of systems with big number of tasks, this may
> take a lot of time.
>
> I observed hard LOCKUP on machine with 20000+ processes
> after write to "cpu.rt_period_us" of cpu cgroup with
> 39 children. The problem occurred because of tasklist_lock
> is held for a long time and other processes can't do fork().
>
> PID: 1036268 TASK: ffff88766c310000 CPU: 36 COMMAND: "criu"
> #0 [ffff887f7f408e48] crash_nmi_callback at ffffffff81050601
> #1 [ffff887f7f408e58] nmi_handle at ffffffff816e0cc7
> #2 [ffff887f7f408eb0] do_nmi at ffffffff816e0fb0
> #3 [ffff887f7f408ef0] end_repeat_nmi at ffffffff816e00b9
> [exception RIP: tg_rt_schedulable+463]
> RIP: ffffffff810bf49f RSP: ffff886537ad7d50 RFLAGS: 00000202
> RAX: 0000000000000000 RBX: 000000003b9aca00 RCX: ffff883e9cb4b1b0
> RDX: ffff887d0be43608 RSI: ffff886537ad7dd8 RDI: ffff8840a6ad0000
> RBP: ffff886537ad7d68 R8: ffff887d0be431b0 R9: 00000000000e7ef0
> R10: ffff88164fc39400 R11: 0000000000023380 R12: ffffffff81ef8d00
> R13: ffffffff810bea40 R14: 0000000000000000 R15: ffff8840a6ad0000
> ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
> --- <NMI exception stack> ---
> #4 [ffff886537ad7d50] tg_rt_schedulable at ffffffff810bf49f
> #5 [ffff886537ad7d70] walk_tg_tree_from at ffffffff810c6c91
> #6 [ffff886537ad7dc0] tg_set_rt_bandwidth at ffffffff810c6dd0
> #7 [ffff886537ad7e28] cpu_rt_period_write_uint at ffffffff810c6eea
> #8 [ffff886537ad7e38] cgroup_file_write at ffffffff8111cfd3
> #9 [ffff886537ad7ec8] vfs_write at ffffffff8121eced
> #10 [ffff886537ad7f08] sys_write at ffffffff8121faff
> #11 [ffff886537ad7f50] system_call_fastpath at ffffffff816e8a7d
>
> The patch reworks tg_has_rt_tasks() and makes it to iterate over
> task group process list instead of iteration over all tasks list.
> This makes the function to scale well, and reduces its execution
> time.
>
> Note, that since tasklist_lock doesn't protect a task against
> sched_class changing, we don't introduce new races in comparison
> to that we had before.
>
> Signed-off-by: Kirill Tkhai <ktkhai@...tuozzo.com>
> ---
> kernel/sched/rt.c | 21 +++++++++++----------
> 1 file changed, 11 insertions(+), 10 deletions(-)
>
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index 7aef6b4e885a..a40535c604b8 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -2395,10 +2395,11 @@ const struct sched_class rt_sched_class = {
> */
> static DEFINE_MUTEX(rt_constraints_mutex);
>
> -/* Must be called with tasklist_lock held */
> static inline int tg_has_rt_tasks(struct task_group *tg)
> {
> - struct task_struct *g, *p;
> + struct task_struct *task;
> + struct css_task_iter it;
> + int ret = 0;
>
> /*
> * Autogroups do not have RT tasks; see autogroup_create().
> @@ -2406,12 +2407,16 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
> if (task_group_is_autogroup(tg))
> return 0;
>
> - for_each_process_thread(g, p) {
> - if (rt_task(p) && task_group(p) == tg)
> - return 1;
> + css_task_iter_start(&tg->css, 0, &it);
> + while ((task = css_task_iter_next(&it))) {
> + if (rt_task(task)) {
> + ret = 1;
> + break;
> + }
> }
> + css_task_iter_end(&it);
>
> - return 0;
> + return ret;
> }
>
> struct rt_schedulable_data {
> @@ -2510,7 +2515,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
> return -EINVAL;
>
> mutex_lock(&rt_constraints_mutex);
> - read_lock(&tasklist_lock);
> err = __rt_schedulable(tg, rt_period, rt_runtime);
> if (err)
> goto unlock;
> @@ -2528,7 +2532,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
> }
> raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
> unlock:
> - read_unlock(&tasklist_lock);
> mutex_unlock(&rt_constraints_mutex);
>
> return err;
> @@ -2582,9 +2585,7 @@ static int sched_rt_global_constraints(void)
> int ret = 0;
>
> mutex_lock(&rt_constraints_mutex);
> - read_lock(&tasklist_lock);
> ret = __rt_schedulable(NULL, 0, 0);
> - read_unlock(&tasklist_lock);
> mutex_unlock(&rt_constraints_mutex);
>
> return ret;
Sorry to necro this...
I have a customer case that has hit the issue here. It looks like this
fix didn't end up going in.
The only way I could reproduce it myself was to add a udelay(2) to
the tg_has_rt_tasks loop. With this patch applied, even with the
udelay nothing bad happens.
Kirill, did you have a good way to reproduce it without adding
delays?
Peter, is there any chance of taking something like this?
Is there a better fix?
Thanks,
Phil
--
Powered by blists - more mailing lists