Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Christoph Hellwig <hch@infradead.org>
To: Dave Chinner <david@fromorbit.com>
Cc: linux-xfs@vger.kernel.org, linux-mm@kvack.org,
	linux-fsdevel@vger.kernel.org,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
	"Paul E. McKenney" <paulmck@kernel.org>
Subject: Re: [PATCH 25/26] xfs: rework unreferenced inode lookups
Date: Fri, 11 Oct 2019 05:55:22 -0700
Message-ID: <20191011125522.GA13167@infradead.org> (raw)
In-Reply-To: <20191009032124.10541-26-david@fromorbit.com>

On Wed, Oct 09, 2019 at 02:21:23PM +1100, Dave Chinner wrote:
> 	4. it xfs_ilock_nowait() fails until the rcu grace period

Should this be:

> 	4. if xfs_ilock_nowait() fails before the rcu grace period

?

> +	xfs_iunlock(ip, XFS_ILOCK_EXCL);
>  	kmem_zone_free(xfs_inode_zone, ip);
>  }
>  
> @@ -131,6 +132,7 @@ xfs_inode_free(
>  	 * free state. The ip->i_flags_lock provides the barrier against lookup
>  	 * races.
>  	 */
> +	xfs_ilock(ip, XFS_ILOCK_EXCL);

This introduceѕ a non-owner unlock of an exclusively held rwsem.  As-is
this will make lockdep very unhappy.  We have a non-owner unlock version
of up_read, but not of up_write currently.  I'm also not sure if those
are allowed from RCU callback, which IIRC can run from softirq context.

That being said this scheme of only unlocking the inode in the rcu free
callback makes totaly sense to me, so I wish we can accomodate it
somehow.

> @@ -312,7 +327,8 @@ xfs_iget_cache_hit(
>  			rcu_read_lock();
>  			spin_lock(&ip->i_flags_lock);
>  			wake = !!__xfs_iflags_test(ip, XFS_INEW);
> -			ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
> +			ip->i_flags &= ~XFS_INEW | XFS_IRECLAIM;

This change looks wrong to me, or did I miss something?  We now
clear all bits that are not XFS_I_NEW and XFS_IRECLAIM, which
already is set in ~XFS_INEW.  So if that was the intent just:

		ip->i_flags &= ~XFS_INEW;

would do it.

> + * This requires code that requires such pins to do the following under a single

This adds an > 80 char line.  (there are a few more below.

> +		/* push the AIL to clean dirty reclaimable inodes */
> +		xfs_ail_push_all(mp->m_ail);
> +
> +		/* push the AIL to clean dirty reclaimable inodes */
> +		xfs_ail_push_all(mp->m_ail);
> +

This looks spurious vs the rest of the patch.

> +			if (__xfs_iflags_test(ip, XFS_ISTALE)) {
> +				spin_unlock(&ip->i_flags_lock);
> +				if (ip != free_ip)
>  					xfs_iunlock(ip, XFS_ILOCK_EXCL);
> -				}
> +				rcu_read_unlock();
> +				continue;

This unlock out of order.  Should be harmless, but also pointless.

I think this code would be a lot easier to understand if we fatored
this inner loop into a new helper.  Untested patch that does, and
also removes a no incorrect comment below:

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1d7e3f575952..16d425174868 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2510,6 +2510,93 @@ xfs_iunlink_remove(
 	return error;
 }
 
+static void
+xfs_ifree_one_inode(
+	struct xfs_perag	*pag,
+	struct xfs_inode	*free_ip,
+	struct xfs_buf		*bp,
+	xfs_ino_t		ino)
+{
+	struct xfs_mount	*mp = free_ip->i_mount;
+	struct xfs_inode	*ip;
+	struct xfs_inode_log_item *iip;
+
+retry:
+	rcu_read_lock();
+	ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ino));
+	if (!ip)
+		goto out_rcu_unlock;
+
+	/*
+	 * See xfs_dispose_inode() for an explanation of the tests here to avoid
+	 * inode reclaim races.
+	 */
+	spin_lock(&ip->i_flags_lock);
+	if (!ip->i_ino || __xfs_iflags_test(ip, XFS_IRECLAIM))
+		goto out_unlock_iflags;
+
+	/*
+	 * The inode isn't in reclaim, but it might be locked by someone else.
+	 * In that case, we retry the inode rather than skipping it completely.
+	 */
+	if (ip != free_ip && !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+		spin_unlock(&ip->i_flags_lock);
+		rcu_read_unlock();
+		delay(1);
+		goto retry;
+	}
+
+	/*
+	 * Inode is now pinned against reclaim until we unlock it, so now we can
+	 * do the work necessary to mark the inode stale and get it held until
+	 * the cluster freeing transaction is logged. If it's stale, then it has
+	 * already been attached to the buffer and we're done.
+	 */
+	if (__xfs_iflags_test(ip, XFS_ISTALE))
+		goto out_unlock_ilock;
+	__xfs_iflags_set(ip, XFS_ISTALE);
+	spin_unlock(&ip->i_flags_lock);
+	rcu_read_unlock();
+
+	/*
+	 * Flush lock will hold off inode reclaim until the buffer completion
+	 * routine runs the xfs_istale_done callback on the inode and unlocks
+	 * it.
+	 */
+	xfs_iflock(ip);
+
+	/*
+	 * We don't need to attach clean inodes or those only with unlogged
+	 * changes (which we throw away, anyway).
+	 */
+	iip = ip->i_itemp;
+	if (!iip || xfs_inode_clean(ip)) {
+		ASSERT(ip != free_ip);
+		xfs_ifunlock(ip);
+		goto done;
+	}
+
+	iip->ili_last_fields = iip->ili_fields;
+	iip->ili_fields = 0;
+	iip->ili_fsync_fields = 0;
+	iip->ili_logged = 1;
+	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
+				&iip->ili_item.li_lsn);
+
+	xfs_buf_attach_iodone(bp, xfs_istale_done, &iip->ili_item);
+done:
+	if (ip != free_ip)
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return;
+out_unlock_ilock:
+	if (ip != free_ip)
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_unlock_iflags:
+	spin_unlock(&ip->i_flags_lock);
+out_rcu_unlock:
+	rcu_read_unlock();
+}
+
 /*
  * A big issue when freeing the inode cluster is that we _cannot_ skip any
  * inodes that are in memory - they all must be marked stale and attached to
@@ -2527,7 +2614,6 @@ xfs_ifree_cluster(
 	int			ioffset;
 	xfs_daddr_t		blkno;
 	xfs_buf_t		*bp;
-	xfs_inode_t		*ip;
 	xfs_inode_log_item_t	*iip;
 	struct xfs_log_item	*lip;
 	struct xfs_perag	*pag;
@@ -2604,99 +2690,9 @@ xfs_ifree_cluster(
 		 * buffer and set it up for being staled on buffer IO
 		 * completion.  This is safe as we've locked out tail pushing
 		 * and flushing by locking the buffer.
-		 *
-		 * We have already marked every inode that was part of a
-		 * transaction stale above, which means there is no point in
-		 * even trying to lock them.
 		 */
-		for (i = 0; i < igeo->inodes_per_cluster; i++) {
-retry:
-			rcu_read_lock();
-			ip = radix_tree_lookup(&pag->pag_ici_root,
-					XFS_INO_TO_AGINO(mp, (inum + i)));
-
-			/* Inode not in memory, nothing to do */
-			if (!ip) {
-				rcu_read_unlock();
-				continue;
-			}
-
-			/*
-			 * See xfs_dispose_inode() for an explanation of the
-			 * tests here to avoid inode reclaim races.
-			 */
-			spin_lock(&ip->i_flags_lock);
-			if (!ip->i_ino ||
-			    __xfs_iflags_test(ip, XFS_IRECLAIM)) {
-				spin_unlock(&ip->i_flags_lock);
-				rcu_read_unlock();
-				continue;
-			}
-
-			/*
-			 * The inode isn't in reclaim, but it might be locked by
-			 * someone else. In that case, we retry the inode rather
-			 * than skipping it completely.
-			 */
-			if (ip != free_ip &&
-			    !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
-				spin_unlock(&ip->i_flags_lock);
-				rcu_read_unlock();
-				delay(1);
-				goto retry;
-			}
-
-			/*
-			 * Inode is now pinned against reclaim until we unlock
-			 * it, so now we can do the work necessary to mark the
-			 * inode stale and get it held until the cluster freeing
-			 * transaction is logged. If it's stale, then it has
-			 * already been attached to the buffer and we're done.
-			 */
-			if (__xfs_iflags_test(ip, XFS_ISTALE)) {
-				spin_unlock(&ip->i_flags_lock);
-				if (ip != free_ip)
-					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				rcu_read_unlock();
-				continue;
-			}
-			__xfs_iflags_set(ip, XFS_ISTALE);
-			spin_unlock(&ip->i_flags_lock);
-			rcu_read_unlock();
-
-			/*
-			 * Flush lock will hold off inode reclaim until the
-			 * buffer completion routine runs the xfs_istale_done
-			 * callback on the inode and unlocks it.
-			 */
-			xfs_iflock(ip);
-
-			/*
-			 * we don't need to attach clean inodes or those only
-			 * with unlogged changes (which we throw away, anyway).
-			 */
-			iip = ip->i_itemp;
-			if (!iip || xfs_inode_clean(ip)) {
-				ASSERT(ip != free_ip);
-				xfs_ifunlock(ip);
-				if (ip != free_ip)
-					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				continue;
-			}
-
-			iip->ili_last_fields = iip->ili_fields;
-			iip->ili_fields = 0;
-			iip->ili_fsync_fields = 0;
-			iip->ili_logged = 1;
-			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
-						&iip->ili_item.li_lsn);
-
-			xfs_buf_attach_iodone(bp, xfs_istale_done,
-						  &iip->ili_item);
-
-			if (ip != free_ip)
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		}
+		for (i = 0; i < igeo->inodes_per_cluster; i++)
+			xfs_ifree_one_inode(pag, free_ip, bp, inum + i);
 
 		xfs_trans_stale_inode_buf(tp, bp);
 		xfs_trans_binval(tp, bp);


  reply index

Thread overview: 87+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-09  3:20 [PATCH V2 00/26] mm, xfs: non-blocking inode reclaim Dave Chinner
2019-10-09  3:20 ` [PATCH 01/26] xfs: Lower CIL flush limit for large logs Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:08   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 02/26] xfs: Throttle commits on delayed background CIL push Dave Chinner
2019-10-11 12:38   ` Brian Foster
2019-10-09  3:21 ` [PATCH 03/26] xfs: don't allow log IO to be throttled Dave Chinner
2019-10-11  9:35   ` Christoph Hellwig
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:14   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 04/26] xfs: Improve metadata buffer reclaim accountability Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-11 12:57     ` Christoph Hellwig
2019-10-11 23:14       ` Dave Chinner
2019-10-11 23:13     ` Dave Chinner
2019-10-12 12:05       ` Brian Foster
2019-10-13  3:14         ` Dave Chinner
2019-10-14 13:05           ` Brian Foster
2019-10-30 17:25   ` Darrick J. Wong
2019-10-30 21:43     ` Dave Chinner
2019-10-31  3:06       ` Darrick J. Wong
2019-10-31 20:50         ` Dave Chinner
2019-10-31 21:05           ` Darrick J. Wong
2019-10-31 21:22             ` Christoph Hellwig
2019-11-03 21:26             ` Dave Chinner
2019-11-04 23:08               ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 05/26] xfs: correctly acount for reclaimable slabs Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:16   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 06/26] xfs: synchronous AIL pushing Dave Chinner
2019-10-11  9:42   ` Christoph Hellwig
2019-10-11 12:40   ` Brian Foster
2019-10-11 23:15     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 07/26] xfs: tail updates only need to occur when LSN changes Dave Chinner
2019-10-11  9:50   ` Christoph Hellwig
2019-10-11 12:40   ` Brian Foster
2019-10-09  3:21 ` [PATCH 08/26] mm: directed shrinker work deferral Dave Chinner
2019-10-14  8:46   ` Christoph Hellwig
2019-10-14 13:06     ` Brian Foster
2019-10-18  7:59     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 09/26] shrinkers: use defer_work for GFP_NOFS sensitive shrinkers Dave Chinner
2019-10-09  3:21 ` [PATCH 10/26] mm: factor shrinker work calculations Dave Chinner
2019-10-09  3:21 ` [PATCH 11/26] shrinker: defer work only to kswapd Dave Chinner
2019-10-09  3:21 ` [PATCH 12/26] shrinker: clean up variable types and tracepoints Dave Chinner
2019-10-09  3:21 ` [PATCH 13/26] mm: reclaim_state records pages reclaimed, not slabs Dave Chinner
2019-10-09  3:21 ` [PATCH 14/26] mm: back off direct reclaim on excessive shrinker deferral Dave Chinner
2019-10-11 16:21   ` Matthew Wilcox
2019-10-11 23:20     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 15/26] mm: kswapd backoff for shrinkers Dave Chinner
2019-10-09  3:21 ` [PATCH 16/26] xfs: synchronous AIL pushing Dave Chinner
2019-10-11 10:18   ` Christoph Hellwig
2019-10-11 15:29     ` Brian Foster
2019-10-11 23:27       ` Dave Chinner
2019-10-12 12:08         ` Brian Foster
2019-10-09  3:21 ` [PATCH 17/26] xfs: don't block kswapd in inode reclaim Dave Chinner
2019-10-11 15:29   ` Brian Foster
2019-10-09  3:21 ` [PATCH 18/26] xfs: reduce kswapd blocking on inode locking Dave Chinner
2019-10-11 10:29   ` Christoph Hellwig
2019-10-09  3:21 ` [PATCH 19/26] xfs: kill background reclaim work Dave Chinner
2019-10-11 10:31   ` Christoph Hellwig
2019-10-09  3:21 ` [PATCH 20/26] xfs: use AIL pushing for inode reclaim IO Dave Chinner
2019-10-11 17:38   ` Brian Foster
2019-10-09  3:21 ` [PATCH 21/26] xfs: remove mode from xfs_reclaim_inodes() Dave Chinner
2019-10-11 10:39   ` Christoph Hellwig
2019-10-14 13:07   ` Brian Foster
2019-10-09  3:21 ` [PATCH 22/26] xfs: track reclaimable inodes using a LRU list Dave Chinner
2019-10-11 10:42   ` Christoph Hellwig
2019-10-14 13:07   ` Brian Foster
2019-10-09  3:21 ` [PATCH 23/26] xfs: reclaim inodes from the LRU Dave Chinner
2019-10-11 10:56   ` Christoph Hellwig
2019-10-30 23:25     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 24/26] xfs: remove unusued old inode reclaim code Dave Chinner
2019-10-09  3:21 ` [PATCH 25/26] xfs: rework unreferenced inode lookups Dave Chinner
2019-10-11 12:55   ` Christoph Hellwig [this message]
2019-10-11 13:39     ` Peter Zijlstra
2019-10-11 23:38     ` Dave Chinner
2019-10-14 13:07   ` Brian Foster
2019-10-17  1:24     ` Dave Chinner
2019-10-17  7:57       ` Brian Foster
2019-10-18 20:29         ` Dave Chinner
2019-10-09  3:21 ` [PATCH 26/26] xfs: use xfs_ail_push_all_sync in xfs_reclaim_inodes Dave Chinner
2019-10-11  9:55   ` Christoph Hellwig
2019-10-09  7:06 ` [PATCH V2 00/26] mm, xfs: non-blocking inode reclaim Christoph Hellwig
2019-10-11 19:03 ` Josef Bacik
2019-10-11 23:48   ` Dave Chinner
2019-10-12  0:19     ` Josef Bacik
2019-10-12  0:48       ` Dave Chinner

Reply instructions:

You may reply publically 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=20191011125522.GA13167@infradead.org \
    --to=hch@infradead.org \
    --cc=david@fromorbit.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git