From: NeilBrown <neilb@suse.de>
To: Jeff Layton <jlayton@kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>
Cc: yangerkun <yangerkun@huawei.com>,
kernel test robot <rong.a.chen@intel.com>,
LKML <linux-kernel@vger.kernel.org>,
lkp@lists.01.org, Bruce Fields <bfields@fieldses.org>,
Al Viro <viro@zeniv.linux.org.uk>
Subject: Re: [locks] 6d390e4b5d: will-it-scale.per_process_ops -96.6% regression
Date: Sat, 14 Mar 2020 13:31:03 +1100 [thread overview]
Message-ID: <877dznu0pk.fsf@notabene.neil.brown.name> (raw)
In-Reply-To: <f000e352d9e103b3ade3506aac225920420d2323.camel@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 4647 bytes --]
On Fri, Mar 13 2020, Jeff Layton wrote:
> On Thu, 2020-03-12 at 09:07 -0700, Linus Torvalds wrote:
>> On Wed, Mar 11, 2020 at 9:42 PM NeilBrown <neilb@suse.de> wrote:
>> > It seems that test_and_set_bit_lock() is the preferred way to handle
>> > flags when memory ordering is important
>>
>> That looks better.
>>
>> The _preferred_ way is actually the one I already posted: do a
>> "smp_store_release()" to store the flag (like a NULL pointer), and a
>> smp_load_acquire() to load it.
>>
>> That's basically optimal on most architectures (all modern ones -
>> there are bad architectures from before people figured out that
>> release/acquire is better than separate memory barriers), not needing
>> any atomics and only minimal memory ordering.
>>
>> I wonder if a special flags value (keeping it "unsigned int" to avoid
>> the issue Jeff pointed out) might be acceptable?
>>
>> IOW, could we do just
>>
>> smp_store_release(&waiter->fl_flags, FL_RELEASED);
>>
>> to say that we're done with the lock? Or do people still look at and
>> depend on the flag values at that point?
>
> I think nlmsvc_grant_block does. We could probably work around it
> there, but we'd need to couple this change with some clear
> documentation to make it clear that you can't rely on fl_flags after
> locks_delete_block returns.
>
> If avoiding new locks is preferred here (and I'm fine with that), then
> maybe we should just go with the patch you sent originally (along with
> changing the waiters to wait on fl_blocked_member going empty instead
> of the fl_blocker going NULL)?
I agree. I've poked at this for a while and come to the conclusion that
I cannot really come up with anything that is structurally better than
your patch.
The idea of list_del_init_release() and list_empty_acquire() is growing
on me though. See below.
list_empty_acquire() might be appropriate for waitqueue_active(), which
is documented as requiring a memory barrier, but in practice seems to
often be used without one.
But I'm happy for you to go with your patch that changes all the wait
calls.
NeilBrown
diff --git a/fs/locks.c b/fs/locks.c
index 426b55d333d5..2e5eb677c324 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -174,6 +174,20 @@
#include <linux/uaccess.h>
+/* Should go in list.h */
+static inline int list_empty_acquire(const struct list_head *head)
+{
+ return smp_load_acquire(&head->next) == head;
+}
+
+static inline void list_del_init_release(struct list_head *entry)
+{
+ __list_del_entry(entry);
+ entry->prev = entry;
+ smp_store_release(&entry->next, entry);
+}
+
+
#define IS_POSIX(fl) (fl->fl_flags & FL_POSIX)
#define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK)
#define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
@@ -724,7 +738,6 @@ static void locks_delete_global_blocked(struct file_lock *waiter)
static void __locks_delete_block(struct file_lock *waiter)
{
locks_delete_global_blocked(waiter);
- list_del_init(&waiter->fl_blocked_member);
waiter->fl_blocker = NULL;
}
@@ -740,6 +753,11 @@ static void __locks_wake_up_blocks(struct file_lock *blocker)
waiter->fl_lmops->lm_notify(waiter);
else
wake_up(&waiter->fl_wait);
+ /*
+ * Tell the world that we're done with it - see comment at
+ * top of locks_delete_block().
+ */
+ list_del_init_release(&waiter->fl_blocked_member);
}
}
@@ -753,6 +771,25 @@ int locks_delete_block(struct file_lock *waiter)
{
int status = -ENOENT;
+ /*
+ * If fl_blocker is NULL, it won't be set again as this thread
+ * "owns" the lock and is the only one that might try to claim
+ * the lock. So it is safe to test fl_blocker locklessly.
+ * Also if fl_blocker is NULL, this waiter is not listed on
+ * fl_blocked_requests for some lock, so no other request can
+ * be added to the list of fl_blocked_requests for this
+ * request. So if fl_blocker is NULL, it is safe to
+ * locklessly check if fl_blocked_requests is empty. If both
+ * of these checks succeed, there is no need to take the lock.
+ * However, some other thread could still be in__locks_wake_up_blocks()
+ * and may yet access 'waiter', so we cannot return and possibly
+ * free the 'waiter' unless we check that __locks_wake_up_blocks()
+ * is done. For that we carefully test fl_blocked_member.
+ */
+ if (waiter->fl_blocker == NULL &&
+ list_empty(&waiter->fl_blocked_requests) &&
+ list_empty_acquire(&waiter->fl_blocked_member))
+ return status;
spin_lock(&blocked_lock_lock);
if (waiter->fl_blocker)
status = 0;
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]
next prev parent reply other threads:[~2020-03-14 2:31 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-08 14:03 [locks] 6d390e4b5d: will-it-scale.per_process_ops -96.6% regression kernel test robot
2020-03-09 14:36 ` Jeff Layton
2020-03-09 15:52 ` Linus Torvalds
2020-03-09 17:22 ` Jeff Layton
2020-03-09 19:09 ` Jeff Layton
2020-03-09 19:53 ` Jeff Layton
2020-03-09 21:42 ` NeilBrown
2020-03-09 21:58 ` Jeff Layton
2020-03-10 7:52 ` kernel test robot
2020-03-09 22:11 ` Jeff Layton
2020-03-10 3:24 ` yangerkun
2020-03-10 7:54 ` kernel test robot
2020-03-10 12:52 ` Jeff Layton
2020-03-10 14:18 ` yangerkun
2020-03-10 15:06 ` Jeff Layton
2020-03-10 17:27 ` Jeff Layton
2020-03-10 21:01 ` NeilBrown
2020-03-10 21:14 ` Jeff Layton
2020-03-10 21:21 ` NeilBrown
2020-03-10 21:47 ` Linus Torvalds
2020-03-10 22:07 ` Jeff Layton
2020-03-10 22:31 ` Linus Torvalds
2020-03-11 22:22 ` NeilBrown
2020-03-12 0:38 ` Linus Torvalds
2020-03-12 4:42 ` NeilBrown
2020-03-12 12:31 ` Jeff Layton
2020-03-12 22:19 ` NeilBrown
2020-03-14 1:11 ` Jeff Layton
2020-03-12 16:07 ` Linus Torvalds
2020-03-14 1:31 ` Jeff Layton
2020-03-14 2:31 ` NeilBrown [this message]
2020-03-14 15:58 ` Linus Torvalds
2020-03-15 13:54 ` Jeff Layton
2020-03-16 5:06 ` NeilBrown
2020-03-16 11:07 ` Jeff Layton
2020-03-16 17:26 ` Linus Torvalds
2020-03-17 1:41 ` yangerkun
2020-03-17 14:05 ` yangerkun
2020-03-17 16:07 ` Jeff Layton
2020-03-18 1:09 ` yangerkun
2020-03-19 17:51 ` Jeff Layton
2020-03-19 19:23 ` Linus Torvalds
2020-03-19 19:24 ` Jeff Layton
2020-03-19 19:35 ` Linus Torvalds
2020-03-19 20:10 ` Jeff Layton
2020-03-16 22:45 ` NeilBrown
2020-03-17 15:59 ` Jeff Layton
2020-03-17 21:27 ` NeilBrown
2020-03-18 5:12 ` kernel test robot
2020-03-16 4:26 ` NeilBrown
2020-03-11 1:57 ` yangerkun
2020-03-11 12:52 ` Jeff Layton
2020-03-11 13:26 ` yangerkun
2020-03-11 22:15 ` NeilBrown
2020-03-10 7:50 ` kernel test robot
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=877dznu0pk.fsf@notabene.neil.brown.name \
--to=neilb@suse.de \
--cc=bfields@fieldses.org \
--cc=jlayton@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lkp@lists.01.org \
--cc=rong.a.chen@intel.com \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=yangerkun@huawei.com \
/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).