linux-rt-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Paul Gortmaker <paul.gortmaker@windriver.com>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: <linux-kernel@vger.kernel.org>,
	linux-rt-users <linux-rt-users@vger.kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Carsten Emde <C.Emde@osadl.org>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	John Kacur <jkacur@redhat.com>, <stable-rt@vger.kernel.org>,
	Nikita Yushchenko <nyushchenko@dev.rtsoft.ru>,
	Mike Galbraith <umgwanakikbuti@gmail.com>
Subject: Re: [PATCH RT 26/39] scheduling while atomic in cgroup code
Date: Tue, 17 Mar 2015 16:10:11 -0400	[thread overview]
Message-ID: <20150317201010.GB26043@windriver.com> (raw)
In-Reply-To: <20150312191411.381735145@goodmis.org>

[[PATCH RT 26/39] scheduling while atomic in cgroup code] On 12/03/2015 (Thu 15:13) Steven Rostedt wrote:

> 3.14.34-rt32-rc1 stable review patch.
> If anyone has any objections, please let me know.
> 
> ------------------
> 
> From: Mike Galbraith <umgwanakikbuti@gmail.com>
> 
> mm, memcg: make refill_stock() use get_cpu_light()

This looks like only 1/2 of Mike's original patch:

https://lkml.org/lkml/2014/6/21/11 

I suspect that is because 3.18 could only use 1/2 of it, and based on
the SOB lines, this is backported from 3.18.

The other half applies to 3.14 -- testing in progress; not sure about
the 3.10-rt and earlier....

P.
--

> 
> Nikita reported the following memcg scheduling while atomic bug:
> 
> Call Trace:
> [e22d5a90] [c0007ea8] show_stack+0x4c/0x168 (unreliable)
> [e22d5ad0] [c0618c04] __schedule_bug+0x94/0xb0
> [e22d5ae0] [c060b9ec] __schedule+0x530/0x550
> [e22d5bf0] [c060bacc] schedule+0x30/0xbc
> [e22d5c00] [c060ca24] rt_spin_lock_slowlock+0x180/0x27c
> [e22d5c70] [c00b39dc] res_counter_uncharge_until+0x40/0xc4
> [e22d5ca0] [c013ca88] drain_stock.isra.20+0x54/0x98
> [e22d5cc0] [c01402ac] __mem_cgroup_try_charge+0x2e8/0xbac
> [e22d5d70] [c01410d4] mem_cgroup_charge_common+0x3c/0x70
> [e22d5d90] [c0117284] __do_fault+0x38c/0x510
> [e22d5df0] [c011a5f4] handle_pte_fault+0x98/0x858
> [e22d5e50] [c060ed08] do_page_fault+0x42c/0x6fc
> [e22d5f40] [c000f5b4] handle_page_fault+0xc/0x80
> 
> What happens:
> 
>    refill_stock()
>       get_cpu_var()
>       drain_stock()
>          res_counter_uncharge()
>             res_counter_uncharge_until()
>                spin_lock() <== boom
> 
> Fix it by replacing get/put_cpu_var() with get/put_cpu_light().
> 
> Cc: stable-rt@vger.kernel.org
> Reported-by: Nikita Yushchenko <nyushchenko@dev.rtsoft.ru>
> Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> ---
>  mm/memcontrol.c | 7 +++++--
>  1 file changed, 5 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index fa54408b66b2..be24d2d186fa 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2512,14 +2512,17 @@ static void __init memcg_stock_init(void)
>   */
>  static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
>  {
> -	struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
> +	struct memcg_stock_pcp *stock;
> +	int cpu = get_cpu_light();
> +
> +	stock = &per_cpu(memcg_stock, cpu);
>  
>  	if (stock->cached != memcg) { /* reset if necessary */
>  		drain_stock(stock);
>  		stock->cached = memcg;
>  	}
>  	stock->nr_pages += nr_pages;
> -	put_cpu_var(memcg_stock);
> +	put_cpu_light();
>  }
>  
>  /*
> -- 
> 2.1.4
> 
> 

  reply	other threads:[~2015-03-17 20:10 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-12 19:13 [PATCH RT 00/39] Linux 3.14.34-rt32-rc1 Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 01/39] gpio: omap: use raw locks for locking Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 02/39] rtmutex: Simplify rtmutex_slowtrylock() Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 03/39] rtmutex: Simplify and document try_to_take_rtmutex() Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 04/39] rtmutex: No need to keep task ref for lock owner check Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 05/39] rtmutex: Clarify the boost/deboost part Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 06/39] rtmutex: Document pi chain walk Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 07/39] rtmutex: Simplify remove_waiter() Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 08/39] rtmutex: Confine deadlock logic to futex Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 09/39] rtmutex: Cleanup deadlock detector debug logic Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 10/39] rtmutex: Avoid pointless requeueing in the deadlock detection chain walk Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 11/39] futex: Make unlock_pi more robust Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 12/39] futex: Use futex_top_waiter() in lookup_pi_state() Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 13/39] futex: Split out the waiter check from lookup_pi_state() Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 14/39] futex: Split out the first waiter attachment " Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 15/39] futex: Simplify futex_lock_pi_atomic() and make it more robust Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 16/39] locking/rt-mutex: avoid a NULL pointer dereference on deadlock Steven Rostedt
2015-03-13 10:40   ` Sebastian Andrzej Siewior
2015-03-13 10:56     ` Sebastian Andrzej Siewior
2015-03-12 19:13 ` [PATCH RT 17/39] rtmutex.c: Fix incorrect waiter check Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 18/39] rt,locking: fix __ww_mutex_lock_interruptible() lockdep annotation Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 19/39] rtmutex: enable deadlock detection in ww_mutex_lock functions Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 20/39] x86: UV: raw_spinlock conversion Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 22/39] arm/futex: disable preemption during futex_atomic_cmpxchg_inatomic() Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 23/39] ARM: cmpxchg: define __HAVE_ARCH_CMPXCHG for armv6 and later Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 24/39] mips: rt: Replace pagefault_* to raw version Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 25/39] sas-ata/isci: dontt disable interrupts in qc_issue handler Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 26/39] scheduling while atomic in cgroup code Steven Rostedt
2015-03-17 20:10   ` Paul Gortmaker [this message]
2015-03-17 20:13     ` Steven Rostedt
2015-03-18  8:37     ` Sebastian Andrzej Siewior
2015-03-18 13:20       ` Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 27/39] work-simple: Simple work queue implemenation Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 28/39] sunrpc: make svc_xprt_do_enqueue() use get_cpu_light() Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 29/39] Revert "rwsem-rt: Do not allow readers to nest" Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 30/39] locking: ww_mutex: fix ww_mutex vs self-deadlock Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 31/39] thermal: Defer thermal wakups to threads Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 32/39] lockdep: selftest: fix warnings due to missing PREEMPT_RT conditionals Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 33/39] fs/aio: simple simple work Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 34/39] timers: Track total number of timers in list Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 35/39] timers: Reduce __run_timers() latency for empty list Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 36/39] timers: Reduce future __run_timers() latency for newly emptied list Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 37/39] timers: Reduce future __run_timers() latency for first add to empty list Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 38/39] staging: Mark rtl8821ae as broken Steven Rostedt
2015-03-12 19:13 ` [PATCH RT 39/39] Linux 3.14.34-rt32-rc1 Steven Rostedt
2015-03-13  4:49 ` [PATCH RT 00/39] " Mike Galbraith
2015-03-13 13:50   ` Steven Rostedt
2015-03-13 15:11   ` Steven Rostedt
2015-03-13 15:24     ` Steven Rostedt
2015-03-13 11:01 ` Sebastian Andrzej Siewior
2015-03-13 11:33 ` Sebastian Andrzej Siewior
2015-03-16 13:59 ` Sebastian Andrzej Siewior
2015-03-16 14:02   ` Steven Rostedt
2015-03-16 14:10     ` Sebastian Andrzej Siewior

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20150317201010.GB26043@windriver.com \
    --to=paul.gortmaker@windriver.com \
    --cc=C.Emde@osadl.org \
    --cc=bigeasy@linutronix.de \
    --cc=jkacur@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=nyushchenko@dev.rtsoft.ru \
    --cc=rostedt@goodmis.org \
    --cc=stable-rt@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=umgwanakikbuti@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).