linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Al Viro <viro@ZenIV.linux.org.uk>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org
Subject: Re: do we need that smp_wmb() in __d_alloc()?
Date: Thu, 10 Mar 2016 21:17:29 +0000	[thread overview]
Message-ID: <20160310211729.GN17997@ZenIV.linux.org.uk> (raw)
In-Reply-To: <20160310203428.GM17997@ZenIV.linux.org.uk>

On Thu, Mar 10, 2016 at 08:34:28PM +0000, Al Viro wrote:

> Speaking of barriers - why do we need one there at all?  In __d_alloc(), that
> is.  Look: callers of __d_alloc() are:
> 	* d_alloc() - cycles parent's ->d_lock, inserts into the list of
> parent's children.  Anyone observing it on that list of children will be
> holding the same parent's ->d_lock.  And anyone finding it in any other way
> will have to observe the effect of store done after the write barrier in
> spin_unlock.

... which still leaves the possibility of both stores migrating inside the
lock/unlock pair and past each other.  IOW,
	lock parent's d_lock
	lock child's d_lock
	put into hash
	store terminating NUL in ->d_name
	unlock parent's d_lock
	unlock child's d_lock
is a possible sequence of events, with RCU access on another CPU observing
the damn without seeing the NUL-terminated name ;-/

Oh, well...

  reply	other threads:[~2016-03-10 21:17 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-08 16:05 races in ll_splice_alias() Al Viro
2016-03-08 20:44 ` Drokin, Oleg
2016-03-08 21:11   ` Al Viro
2016-03-08 23:18     ` Drokin, Oleg
2016-03-09  0:34       ` Al Viro
2016-03-09  0:53         ` Drokin, Oleg
2016-03-09  1:26           ` Al Viro
2016-03-09  5:20             ` Drokin, Oleg
2016-03-09 23:47             ` Drokin, Oleg
2016-03-10  2:20               ` races in ll_splice_alias() and elsewhere (ext4, ocfs2) Al Viro
2016-03-10  2:59                 ` Al Viro
2016-03-10 23:55                   ` Theodore Ts'o
2016-03-11  3:18                     ` Al Viro
2016-03-11 15:42                       ` Theodore Ts'o
2016-03-10  3:08                 ` Drokin, Oleg
2016-03-10  3:34                   ` Al Viro
2016-03-10  3:46                     ` Drokin, Oleg
2016-03-10  4:22                       ` Drokin, Oleg
2016-03-10  4:43                       ` Al Viro
2016-03-10  5:15                         ` Al Viro
2016-03-11  3:47                           ` Drokin, Oleg
2016-03-10  5:47                         ` Drokin, Oleg
2016-03-10 19:59                 ` Al Viro
2016-03-10 20:34                   ` do we need that smp_wmb() in __d_alloc()? Al Viro
2016-03-10 21:17                     ` Al Viro [this message]
2016-03-10 21:22                   ` races in ll_splice_alias() and elsewhere (ext4, ocfs2) Drokin, Oleg
2016-03-10 23:23                     ` Al Viro
2016-03-11  3:25                       ` Drokin, Oleg
2016-03-12 17:22                         ` Al Viro
2016-03-13 14:35                           ` Sage Weil

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=20160310211729.GN17997@ZenIV.linux.org.uk \
    --to=viro@zeniv.linux.org.uk \
    --cc=linux-fsdevel@vger.kernel.org \
    --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;
as well as URLs for NNTP newsgroup(s).