From: Vivek Goyal <vgoyal@redhat.com>
To: linux-fsdevel@vger.kernel.org, dan.j.williams@intel.com,
jack@suse.cz, willy@infradead.org
Cc: virtio-fs@redhat.com, slp@redhat.com, miklos@szeredi.hu,
linux-nvdimm@lists.01.org, linux-kernel@vger.kernel.org,
vgoyal@redhat.com
Subject: [PATCH v3 3/3] dax: Wake up all waiters after invalidating dax entry
Date: Mon, 19 Apr 2021 17:36:36 -0400 [thread overview]
Message-ID: <20210419213636.1514816-4-vgoyal@redhat.com> (raw)
In-Reply-To: <20210419213636.1514816-1-vgoyal@redhat.com>
I am seeing missed wakeups which ultimately lead to a deadlock when I am
using virtiofs with DAX enabled and running "make -j". I had to mount
virtiofs as rootfs and also reduce to dax window size to 256M to reproduce
the problem consistently.
So here is the problem. put_unlocked_entry() wakes up waiters only
if entry is not null as well as !dax_is_conflict(entry). But if I
call multiple instances of invalidate_inode_pages2() in parallel,
then I can run into a situation where there are waiters on
this index but nobody will wait these.
invalidate_inode_pages2()
invalidate_inode_pages2_range()
invalidate_exceptional_entry2()
dax_invalidate_mapping_entry_sync()
__dax_invalidate_entry() {
xas_lock_irq(&xas);
entry = get_unlocked_entry(&xas, 0);
...
...
dax_disassociate_entry(entry, mapping, trunc);
xas_store(&xas, NULL);
...
...
put_unlocked_entry(&xas, entry);
xas_unlock_irq(&xas);
}
Say a fault in in progress and it has locked entry at offset say "0x1c".
Now say three instances of invalidate_inode_pages2() are in progress
(A, B, C) and they all try to invalidate entry at offset "0x1c". Given
dax entry is locked, all tree instances A, B, C will wait in wait queue.
When dax fault finishes, say A is woken up. It will store NULL entry
at index "0x1c" and wake up B. When B comes along it will find "entry=0"
at page offset 0x1c and it will call put_unlocked_entry(&xas, 0). And
this means put_unlocked_entry() will not wake up next waiter, given
the current code. And that means C continues to wait and is not woken
up.
This patch fixes the issue by waking up all waiters when a dax entry
has been invalidated. This seems to fix the deadlock I am facing
and I can make forward progress.
Reported-by: Sergio Lopez <slp@redhat.com>
Fixes: ac401cc78242 ("dax: New fault locking")
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
fs/dax.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/dax.c b/fs/dax.c
index f19d76a6a493..cc497519be83 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -676,7 +676,7 @@ static int __dax_invalidate_entry(struct address_space *mapping,
mapping->nrexceptional--;
ret = 1;
out:
- put_unlocked_entry(&xas, entry, WAKE_NEXT);
+ put_unlocked_entry(&xas, entry, WAKE_ALL);
xas_unlock_irq(&xas);
return ret;
}
--
2.25.4
next prev parent reply other threads:[~2021-04-19 21:39 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-19 21:36 [PATCH v3 0/3] dax: Fix missed wakeup in put_unlocked_entry() Vivek Goyal
2021-04-19 21:36 ` [PATCH v3 1/3] dax: Add an enum for specifying dax wakup mode Vivek Goyal
2021-04-20 7:19 ` [Virtio-fs] " Greg Kurz
2021-04-21 9:24 ` Jan Kara
2021-04-21 15:56 ` Vivek Goyal
2021-04-21 16:16 ` Matthew Wilcox
2021-04-21 17:21 ` Vivek Goyal
2021-04-19 21:36 ` [PATCH v3 2/3] dax: Add a wakeup mode parameter to put_unlocked_entry() Vivek Goyal
2021-04-20 7:34 ` [Virtio-fs] " Greg Kurz
2021-04-20 14:00 ` Vivek Goyal
2021-04-21 19:09 ` Dan Williams
2021-04-21 19:13 ` Vivek Goyal
2021-04-22 6:24 ` Christoph Hellwig
2021-04-22 16:12 ` Darrick J. Wong
2021-04-22 20:01 ` Dan Williams
2021-04-22 20:07 ` Vivek Goyal
2021-05-17 17:10 ` Dan Williams
2021-04-21 17:39 ` Vivek Goyal
2021-04-21 9:25 ` Jan Kara
2021-04-19 21:36 ` Vivek Goyal [this message]
2021-04-21 9:26 ` [PATCH v3 3/3] dax: Wake up all waiters after invalidating dax entry Jan Kara
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=20210419213636.1514816-4-vgoyal@redhat.com \
--to=vgoyal@redhat.com \
--cc=dan.j.williams@intel.com \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=miklos@szeredi.hu \
--cc=slp@redhat.com \
--cc=virtio-fs@redhat.com \
--cc=willy@infradead.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).