From: Alan Stern <stern@rowland.harvard.edu>
To: Mikulas Patocka <mpatocka@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Will Deacon <will@kernel.org>,
"Paul E. McKenney" <paulmck@kernel.org>,
Ard Biesheuvel <ardb@kernel.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Andrea Parri <parri.andrea@gmail.com>,
Peter Zijlstra <peterz@infradead.org>,
Boqun Feng <boqun.feng@gmail.com>,
Nicholas Piggin <npiggin@gmail.com>,
David Howells <dhowells@redhat.com>,
Jade Alglave <j.alglave@ucl.ac.uk>,
Luc Maranget <luc.maranget@inria.fr>,
Akira Yokosawa <akiyks@gmail.com>,
Daniel Lustig <dlustig@nvidia.com>,
Joel Fernandes <joel@joelfernandes.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
linux-arch <linux-arch@vger.kernel.org>,
linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH v3 1/2] wait_bit: do read barrier after testing a bit
Date: Sun, 31 Jul 2022 20:27:51 -0400 [thread overview]
Message-ID: <YuceB1x8twgpM7Bl@rowland.harvard.edu> (raw)
In-Reply-To: <alpine.LRH.2.02.2207311639360.21350@file01.intranet.prod.int.rdu2.redhat.com>
On Sun, Jul 31, 2022 at 04:40:59PM -0400, Mikulas Patocka wrote:
> wait_on_bit tests the bit without any memory barriers, consequently the
> code that follows wait_on_bit may be moved before testing the bit on
> architectures with weak memory ordering. When the code tests for some
> event using wait_on_bit and then performs a load operation, the load may
> be unexpectedly moved before wait_on_bit and it may return data that
> existed before the event occurred.
>
> Such bugs exist in fs/buffer.c:__wait_on_buffer,
> drivers/md/dm-bufio.c:new_read,
> drivers/media/usb/dvb-usb-v2/dvb_usb_core.c:dvb_usb_start_feed,
> drivers/bluetooth/btusb.c:btusb_mtk_hci_wmt_sync
> and perhaps in other places.
>
> We fix this class of bugs by adding a read barrier after test_bit().
>
> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
> Cc: stable@vger.kernel.org
>
> Index: linux-2.6/include/linux/wait_bit.h
> ===================================================================
> --- linux-2.6.orig/include/linux/wait_bit.h
> +++ linux-2.6/include/linux/wait_bit.h
> @@ -71,8 +71,10 @@ static inline int
> wait_on_bit(unsigned long *word, int bit, unsigned mode)
> {
> might_sleep();
> - if (!test_bit(bit, word))
> + if (!test_bit(bit, word)) {
> + smp_rmb();
Any new code using smp_rmb or an acquire access should always include a
comment that explains where the matching smp_wmb or release access is.
Alan Stern
> return 0;
> + }
> return out_of_line_wait_on_bit(word, bit,
> bit_wait,
> mode);
> @@ -96,8 +98,10 @@ static inline int
> wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
> {
> might_sleep();
> - if (!test_bit(bit, word))
> + if (!test_bit(bit, word)) {
> + smp_rmb();
> return 0;
> + }
> return out_of_line_wait_on_bit(word, bit,
> bit_wait_io,
> mode);
> @@ -123,8 +127,10 @@ wait_on_bit_timeout(unsigned long *word,
> unsigned long timeout)
> {
> might_sleep();
> - if (!test_bit(bit, word))
> + if (!test_bit(bit, word)) {
> + smp_rmb();
> return 0;
> + }
> return out_of_line_wait_on_bit_timeout(word, bit,
> bit_wait_timeout,
> mode, timeout);
> @@ -151,8 +157,10 @@ wait_on_bit_action(unsigned long *word,
> unsigned mode)
> {
> might_sleep();
> - if (!test_bit(bit, word))
> + if (!test_bit(bit, word)) {
> + smp_rmb();
> return 0;
> + }
> return out_of_line_wait_on_bit(word, bit, action, mode);
> }
>
> Index: linux-2.6/kernel/sched/wait_bit.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched/wait_bit.c
> +++ linux-2.6/kernel/sched/wait_bit.c
> @@ -51,6 +51,8 @@ __wait_on_bit(struct wait_queue_head *wq
>
> finish_wait(wq_head, &wbq_entry->wq_entry);
>
> + smp_rmb();
> +
> return ret;
> }
> EXPORT_SYMBOL(__wait_on_bit);
>
next prev parent reply other threads:[~2022-08-01 0:27 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-31 11:43 [PATCH] Add a read memory barrier to wait_on_buffer Mikulas Patocka
2022-07-31 12:00 ` Ard Biesheuvel
2022-07-31 13:41 ` Mikulas Patocka
2022-07-31 15:08 ` [PATCH v2] make buffer_locked provide an acquire semantics Mikulas Patocka
2022-07-31 16:51 ` Linus Torvalds
2022-07-31 17:30 ` Paul E. McKenney
2022-07-31 22:48 ` Matthew Wilcox
2022-08-01 3:20 ` Paul E. McKenney
2022-08-01 15:41 ` Will Deacon
2022-08-01 19:20 ` Paul E. McKenney
2022-08-02 8:54 ` Will Deacon
2022-08-02 13:49 ` Paul E. McKenney
2022-08-02 15:29 ` Paul E. McKenney
2022-07-31 20:39 ` Mikulas Patocka
2022-07-31 20:40 ` [PATCH v3 1/2] wait_bit: do read barrier after testing a bit Mikulas Patocka
2022-07-31 20:57 ` Linus Torvalds
2022-08-01 10:40 ` Mikulas Patocka
2022-08-01 10:43 ` [PATCH v4 2/2] change buffer_locked, so that it has acquire semantics Mikulas Patocka
2022-08-01 14:37 ` Matthew Wilcox
2022-08-01 15:01 ` Mikulas Patocka
2022-08-05 3:22 ` Matthew Wilcox
2022-08-07 11:37 ` [PATCH v5] add barriers to buffer functions Mikulas Patocka
2022-08-07 14:50 ` Matthew Wilcox
2022-08-08 14:26 ` Mikulas Patocka
2022-08-08 14:40 ` Matthew Wilcox
2022-08-08 14:57 ` Mikulas Patocka
2022-08-08 15:31 ` Paul E. McKenney
2022-08-08 15:39 ` Matthew Wilcox
2022-08-09 18:32 ` [PATCH v6] add barriers to buffer_uptodate and set_buffer_uptodate Mikulas Patocka
2022-08-09 19:44 ` Matthew Wilcox
2022-08-09 22:06 ` Linus Torvalds
2022-08-01 10:42 ` [PATCH v4 1/2] introduce test_bit_acquire and use it in wait_on_bit Mikulas Patocka
2022-08-01 15:54 ` Will Deacon
2022-08-01 16:12 ` Mikulas Patocka
2022-08-01 18:17 ` Boqun Feng
2022-08-02 8:00 ` David Laight
2022-08-02 8:40 ` Will Deacon
2022-08-02 11:38 ` Mikulas Patocka
2022-08-02 13:36 ` Will Deacon
2022-08-02 15:57 ` Mikulas Patocka
2022-08-01 0:27 ` Alan Stern [this message]
2022-07-31 20:43 ` [PATCH v3 2/2] make buffer_locked provide an acquire semantics Mikulas Patocka
2022-07-31 20:51 ` Linus Torvalds
2022-07-31 22:14 ` Matthew Wilcox
2022-07-31 22:31 ` Ard Biesheuvel
2022-07-31 22:48 ` Ard Biesheuvel
2022-07-31 20:46 ` [PATCH v2] " Linus Torvalds
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=YuceB1x8twgpM7Bl@rowland.harvard.edu \
--to=stern@rowland.harvard.edu \
--cc=akiyks@gmail.com \
--cc=ardb@kernel.org \
--cc=boqun.feng@gmail.com \
--cc=dhowells@redhat.com \
--cc=dlustig@nvidia.com \
--cc=j.alglave@ucl.ac.uk \
--cc=joel@joelfernandes.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luc.maranget@inria.fr \
--cc=mpatocka@redhat.com \
--cc=npiggin@gmail.com \
--cc=parri.andrea@gmail.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=will@kernel.org \
/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