linux-kernel - Re: wait_on_page_bit_common(TASK_KILLABLE, EXCLUSIVE) can miss wakeup?

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20200629151340.GC20323@redhat.com>
Date:   Mon, 29 Jun 2020 17:13:41 +0200
From:   Oleg Nesterov <oleg@...hat.com>
To:     Linus Torvalds <torvalds@...ux-foundation.org>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Nick Piggin <npiggin@...il.com>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Jan Kara <jack@...e.cz>, Davidlohr Bueso <dave@...olabs.net>,
        Andi Kleen <ak@...ux.intel.com>,
        Lukas Czerner <lczerner@...hat.com>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: wait_on_page_bit_common(TASK_KILLABLE, EXCLUSIVE) can miss
 wakeup?

On 06/27, Linus Torvalds wrote:
>
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -1150,6 +1150,12 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
>  			io_schedule();
>  
>  		if (behavior == EXCLUSIVE) {
> +			/*
> +			 * Make sure we don't get any exclusive wakeups
> +			 * after this point!
> +			 */
> +			__set_current_state(TASK_RUNNING);
> +			smp_mb__before_atomic();
>  			if (!test_and_set_bit_lock(bit_nr, &page->flags))
>  				break;
>  		} else if (behavior == SHARED) {

FWIW,

Reviewed-by: Oleg Nesterov <oleg@...hat.com>