From: John Ogness <john.ogness@linutronix.de>
To: Petr Mladek <pmladek@suse.com>
Cc: Andrea Parri <parri.andrea@gmail.com>,
Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>,
"Paul E. McKenney" <paulmck@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
kexec@lists.infradead.org, linux-kernel@vger.kernel.org,
Steven Rostedt <rostedt@goodmis.org>,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
Thomas Gleixner <tglx@linutronix.de>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH v2 2/3] printk: add lockless buffer
Date: Mon, 18 May 2020 15:03:53 +0200 [thread overview]
Message-ID: <87v9ktcs3q.fsf@vostro.fn.ogness.net> (raw)
In-Reply-To: <20200501094010.17694-3-john.ogness@linutronix.de> (John Ogness's message of "Fri, 1 May 2020 11:46:09 +0206")
Hi,
For the v2 I was supposed to have fixed a bug in v1. The cover letter
stated:
- data_push_tail(): continue loop rather than try cmpxchg() if
tail LPOS was pushed
Unfortunately, the fix was incorrect and actually made it worse. The
explanation and patch are below.
On 2020-05-01, John Ogness <john.ogness@linutronix.de> wrote:
> diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c
> new file mode 100644
> index 000000000000..e0a66468d4f3
> --- /dev/null
> +++ b/kernel/printk/printk_ringbuffer.c
...
> +/*
> + * Advance the data ring tail to at least @lpos. This function puts
> + * descriptors into the reusable state if the tail is pushed beyond
> + * their associated data block.
> + */
> +static bool data_push_tail(struct printk_ringbuffer *rb,
> + struct prb_data_ring *data_ring,
> + unsigned long lpos)
> +{
> + unsigned long tail_lpos;
> + unsigned long next_lpos;
> +
> + /* If @lpos is not valid, there is nothing to do. */
> + if (lpos == INVALID_LPOS)
> + return true;
> +
> + tail_lpos = atomic_long_read(&data_ring->tail_lpos);
> +
> + do {
> + /* Done, if the tail lpos is already at or beyond @lpos. */
> + if ((lpos - tail_lpos) - 1 >= DATA_SIZE(data_ring))
> + break;
> +
> + /*
> + * Make all descriptors reusable that are associated with
> + * data blocks before @lpos.
> + */
> + if (!data_make_reusable(rb, data_ring, tail_lpos, lpos,
> + &next_lpos)) {
> + /*
> + * Guarantee the descriptor state loaded in
> + * data_make_reusable() is performed before reloading
> + * the tail lpos. The failed data_make_reusable() may
> + * be due to a newly recycled descriptor causing
> + * the tail lpos to have been previously pushed. This
> + * pairs with desc_reserve:D.
> + *
> + * Memory barrier involvement:
> + *
> + * If data_make_reusable:D reads from desc_reserve:G,
> + * then data_push_tail:B reads from data_push_tail:D.
> + *
> + * Relies on:
> + *
> + * MB from data_push_tail:D to desc_reserve:G
> + * matching
> + * RMB from data_make_reusable:D to data_push_tail:B
> + *
> + * Note: data_push_tail:D and desc_reserve:G can be
> + * different CPUs. However, the desc_reserve:G
> + * CPU (which performs the full memory barrier)
> + * must have previously seen data_push_tail:D.
> + */
> + smp_rmb(); /* LMM(data_push_tail:A) */
> +
> + next_lpos = atomic_long_read(&data_ring->tail_lpos
> + ); /* LMM(data_push_tail:B) */
> + if (next_lpos == tail_lpos)
> + return false;
> +
> + /* Another task pushed the tail. Try again. */
> + tail_lpos = next_lpos;
> + continue;
The purpose of the continue is to try again _without_ attempting a
cmpxchg(). However, since the cmpxchg() is in the while condition, it
_is_ called. This is a major problem because if the cmpxchg() succeeds
(highly likely at this point) then the smp_mb() is not called and
success is returned even though the tail may not have been pushed far
enough.
The cmpxchg() needs to be moved out of the while condition so that a
continue can be used as intended. Patch below.
> + }
> +
> + /*
> + * Guarantee any descriptor states that have transitioned to
> + * reusable are stored before pushing the tail lpos. This
> + * allows readers to identify if data has expired while
> + * reading the descriptor. This pairs with desc_read:D.
> + */
> + smp_mb(); /* LMM(data_push_tail:C) */
> +
> + } while (!atomic_long_try_cmpxchg_relaxed(&data_ring->tail_lpos,
> + &tail_lpos, next_lpos)); /* LMM(data_push_tail:D) */
> +
> + return true;
> +}
John Ogness
diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c
index e0a66468d4f3..ac542bdb8deb 100644
--- a/kernel/printk/printk_ringbuffer.c
+++ b/kernel/printk/printk_ringbuffer.c
@@ -546,11 +546,8 @@ static bool data_push_tail(struct printk_ringbuffer *rb,
tail_lpos = atomic_long_read(&data_ring->tail_lpos);
- do {
- /* Done, if the tail lpos is already at or beyond @lpos. */
- if ((lpos - tail_lpos) - 1 >= DATA_SIZE(data_ring))
- break;
-
+ /* Done, if the tail lpos is already at or beyond @lpos. */
+ while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) {
/*
* Make all descriptors reusable that are associated with
* data blocks before @lpos.
@@ -601,8 +598,12 @@ static bool data_push_tail(struct printk_ringbuffer *rb,
*/
smp_mb(); /* LMM(data_push_tail:C) */
- } while (!atomic_long_try_cmpxchg_relaxed(&data_ring->tail_lpos,
- &tail_lpos, next_lpos)); /* LMM(data_push_tail:D) */
+ if (atomic_long_try_cmpxchg_relaxed(&data_ring->tail_lpos,
+ &tail_lpos,
+ next_lpos)) { /* LMM(data_push_tail:D) */
+ break;
+ }
+ }
return true;
}
_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec
next prev parent reply other threads:[~2020-05-18 13:04 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-01 9:40 [PATCH v2 0/3] printk: replace ringbuffer John Ogness
2020-05-01 9:40 ` [PATCH v2 1/3] crash: add VMCOREINFO macro for anonymous structs John Ogness
2020-06-03 10:16 ` Petr Mladek
2020-05-01 9:40 ` [PATCH v2 2/3] printk: add lockless buffer John Ogness
2020-05-18 13:03 ` John Ogness [this message]
2020-05-18 17:22 ` Linus Torvalds
2020-05-19 20:34 ` John Ogness
2020-06-09 7:10 ` blk->id read race: was: " Petr Mladek
2020-06-09 14:18 ` John Ogness
2020-06-10 8:42 ` Petr Mladek
2020-06-10 13:55 ` John Ogness
2020-06-09 9:31 ` redundant check in make_data_reusable(): was " Petr Mladek
2020-06-09 14:48 ` John Ogness
2020-06-10 9:38 ` Petr Mladek
2020-06-10 10:24 ` John Ogness
2020-06-10 14:56 ` John Ogness
2020-06-11 19:51 ` John Ogness
2020-06-11 13:55 ` Petr Mladek
2020-06-11 20:25 ` John Ogness
2020-06-09 9:48 ` Full barrier in data_push_tail(): " Petr Mladek
2020-06-09 15:03 ` John Ogness
2020-06-09 11:37 ` Barrier before pushing desc_ring tail: " Petr Mladek
2020-06-09 15:56 ` John Ogness
2020-06-11 12:01 ` Petr Mladek
2020-06-11 23:06 ` John Ogness
2020-06-09 14:38 ` data_ring head_lpos and tail_lpos synchronization: " Petr Mladek
2020-06-10 7:53 ` John Ogness
2020-05-01 9:40 ` [PATCH v2 3/3] printk: use the lockless ringbuffer John Ogness
2020-05-06 14:50 ` John Ogness
2020-05-13 12:05 ` [PATCH v2 0/3] printk: replace ringbuffer Prarit Bhargava
2020-05-15 10:24 ` Sergey Senozhatsky
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=87v9ktcs3q.fsf@vostro.fn.ogness.net \
--to=john.ogness@linutronix.de \
--cc=gregkh@linuxfoundation.org \
--cc=kexec@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=parri.andrea@gmail.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=pmladek@suse.com \
--cc=rostedt@goodmis.org \
--cc=sergey.senozhatsky.work@gmail.com \
--cc=sergey.senozhatsky@gmail.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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