[PATCHSET v5 00/11] xfs: try harder to reclaim space when we run out

[PATCHSET v5 00/11] xfs: try harder to reclaim space when we run out

[Darrick J. Wong]

Hi all,

Historically, when users ran out of space or quota when trying to write
to the filesystem, XFS didn't try very hard to reclaim space that it
might have speculatively allocated for the purpose of speeding up
front-end filesystem operations (appending writes, cow staging).  The
upcoming deferred inactivation series will greatly increase the amount
of allocated space that isn't actively being used to store user data.

Therefore, try to reduce the circumstances where we return EDQUOT or
ENOSPC to userspace by teaching the write paths to try to clear space
and retry the operation one time before giving up.

Previous iterations of this patchset made massive changes to the
codebase, but thanks to the transaction allocation helpers that Brian
pushed for (in the previous patchset) this is mostly no longer
necessary. :)

v2: clean up and rebase against 5.11.
v3: restructure the retry loops per dchinner suggestion
v4: simplify the calling convention of xfs_trans_reserve_quota_nblks
v5: constrain the open-coded 'goto retry' loops to the hlepers created
    in the previous patchset

If you're going to start using this mess, you probably ought to just
pull from my git trees, which are linked below.

This is an extraordinary way to destroy everything.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=reclaim-space-harder-5.12
---
 fs/xfs/xfs_file.c        |   24 +++---
 fs/xfs/xfs_icache.c      |  184 ++++++++++++++++++++++++++++++----------------
 fs/xfs/xfs_icache.h      |    7 +-
 fs/xfs/xfs_ioctl.c       |   11 +++
 fs/xfs/xfs_iops.c        |   10 ++-
 fs/xfs/xfs_quota.h       |   51 +++++++++++--
 fs/xfs/xfs_reflink.c     |    7 ++
 fs/xfs/xfs_trace.c       |    1 
 fs/xfs/xfs_trace.h       |   42 +++++++++++
 fs/xfs/xfs_trans.c       |   31 +++++++-
 fs/xfs/xfs_trans_dquot.c |  169 +++++++++++++++++++++++++++++++++++++++---
 11 files changed, 433 insertions(+), 104 deletions(-)

[PATCH 01/11] xfs: trigger all block gc scans when low on quota space

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The functions to run an eof/cowblocks scan to try to reduce quota usage
are kind of a mess -- the logic repeatedly initializes an eofb structure
and there are logic bugs in the code that result in the cowblocks scan
never actually happening.

Replace all three functions with a single function that fills out an
eofb and runs both eof and cowblocks scans.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_file.c   |   15 ++++++---------
 fs/xfs/xfs_icache.c |   46 ++++++++++++++++------------------------------
 fs/xfs/xfs_icache.h |    4 ++--
 3 files changed, 24 insertions(+), 41 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5d4a66c72c78..69879237533b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -713,7 +713,7 @@ xfs_file_buffered_write(
 	struct inode		*inode = mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret;
-	int			enospc = 0;
+	bool			cleared_space = false;
 	int			iolock;
 
 	if (iocb->ki_flags & IOCB_NOWAIT)
@@ -745,19 +745,16 @@ xfs_file_buffered_write(
 	 * also behaves as a filter to prevent too many eofblocks scans from
 	 * running at the same time.
 	 */
-	if (ret == -EDQUOT && !enospc) {
+	if (ret == -EDQUOT && !cleared_space) {
 		xfs_iunlock(ip, iolock);
-		enospc = xfs_inode_free_quota_eofblocks(ip);
-		if (enospc)
-			goto write_retry;
-		enospc = xfs_inode_free_quota_cowblocks(ip);
-		if (enospc)
+		cleared_space = xfs_inode_free_quota_blocks(ip);
+		if (cleared_space)
 			goto write_retry;
 		iolock = 0;
-	} else if (ret == -ENOSPC && !enospc) {
+	} else if (ret == -ENOSPC && !cleared_space) {
 		struct xfs_eofblocks eofb = {0};
 
-		enospc = 1;
+		cleared_space = true;
 		xfs_flush_inodes(ip->i_mount);
 
 		xfs_iunlock(ip, iolock);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index deb99300d171..c71eb15e3835 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1397,33 +1397,31 @@ xfs_icache_free_eofblocks(
 }
 
 /*
- * Run eofblocks scans on the quotas applicable to the inode. For inodes with
- * multiple quotas, we don't know exactly which quota caused an allocation
+ * Run cow/eofblocks scans on the quotas applicable to the inode. For inodes
+ * with multiple quotas, we don't know exactly which quota caused an allocation
  * failure. We make a best effort by including each quota under low free space
  * conditions (less than 1% free space) in the scan.
  */
-static int
-__xfs_inode_free_quota_eofblocks(
-	struct xfs_inode	*ip,
-	int			(*execute)(struct xfs_mount *mp,
-					   struct xfs_eofblocks	*eofb))
+bool
+xfs_inode_free_quota_blocks(
+	struct xfs_inode	*ip)
 {
-	int scan = 0;
-	struct xfs_eofblocks eofb = {0};
-	struct xfs_dquot *dq;
+	struct xfs_eofblocks	eofb = {0};
+	struct xfs_dquot	*dq;
+	bool			do_work = false;
 
 	/*
 	 * Run a sync scan to increase effectiveness and use the union filter to
 	 * cover all applicable quotas in a single scan.
 	 */
-	eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;
+	eofb.eof_flags = XFS_EOF_FLAGS_UNION | XFS_EOF_FLAGS_SYNC;
 
 	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
 		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_uid = VFS_I(ip)->i_uid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
-			scan = 1;
+			do_work = true;
 		}
 	}
 
@@ -1432,21 +1430,16 @@ __xfs_inode_free_quota_eofblocks(
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_gid = VFS_I(ip)->i_gid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_GID;
-			scan = 1;
+			do_work = true;
 		}
 	}
 
-	if (scan)
-		execute(ip->i_mount, &eofb);
+	if (!do_work)
+		return false;
 
-	return scan;
-}
-
-int
-xfs_inode_free_quota_eofblocks(
-	struct xfs_inode *ip)
-{
-	return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks);
+	xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+	xfs_icache_free_cowblocks(ip->i_mount, &eofb);
+	return true;
 }
 
 static inline unsigned long
@@ -1646,13 +1639,6 @@ xfs_icache_free_cowblocks(
 			XFS_ICI_COWBLOCKS_TAG);
 }
 
-int
-xfs_inode_free_quota_cowblocks(
-	struct xfs_inode *ip)
-{
-	return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_cowblocks);
-}
-
 void
 xfs_inode_set_cowblocks_tag(
 	xfs_inode_t	*ip)
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 3a4c8b382cd0..3f7ddbca8638 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -54,17 +54,17 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 
+bool xfs_inode_free_quota_blocks(struct xfs_inode *ip);
+
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);
 int xfs_icache_free_eofblocks(struct xfs_mount *, struct xfs_eofblocks *);
-int xfs_inode_free_quota_eofblocks(struct xfs_inode *ip);
 void xfs_eofblocks_worker(struct work_struct *);
 void xfs_queue_eofblocks(struct xfs_mount *);
 
 void xfs_inode_set_cowblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip);
 int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *);
-int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip);
 void xfs_cowblocks_worker(struct work_struct *);
 void xfs_queue_cowblocks(struct xfs_mount *);
 

[PATCH 02/11] xfs: don't stall cowblocks scan if we can't take locks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Don't stall the cowblocks scan on a locked inode if we possibly can.
We'd much rather the background scanner keep moving.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_icache.c |   21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index c71eb15e3835..89f9e692fde7 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1605,17 +1605,31 @@ xfs_inode_free_cowblocks(
 	void			*args)
 {
 	struct xfs_eofblocks	*eofb = args;
+	bool			wait;
 	int			ret = 0;
 
+	wait = eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC);
+
 	if (!xfs_prep_free_cowblocks(ip))
 		return 0;
 
 	if (!xfs_inode_matches_eofb(ip, eofb))
 		return 0;
 
-	/* Free the CoW blocks */
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+	/*
+	 * If the caller is waiting, return -EAGAIN to keep the background
+	 * scanner moving and revisit the inode in a subsequent pass.
+	 */
+	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+		if (wait)
+			return -EAGAIN;
+		return 0;
+	}
+	if (!xfs_ilock_nowait(ip, XFS_MMAPLOCK_EXCL)) {
+		if (wait)
+			ret = -EAGAIN;
+		goto out_iolock;
+	}
 
 	/*
 	 * Check again, nobody else should be able to dirty blocks or change
@@ -1625,6 +1639,7 @@ xfs_inode_free_cowblocks(
 		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
+out_iolock:
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
 	return ret;

[PATCH 03/11] xfs: xfs_inode_free_quota_blocks should scan project quota

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Buffered writers who have run out of quota reservation call
xfs_inode_free_quota_blocks to try to free any space reservations that
might reduce the quota usage.  Unfortunately, the buffered write path
treats "out of project quota" the same as "out of overall space" so this
function has never supported scanning for space that might ease an "out
of project quota" condition.

We're about to start using this function for cases where we actually
/can/ tell if we're out of project quota, so add in this functionality.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_icache.c |    9 +++++++++
 1 file changed, 9 insertions(+)


diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 89f9e692fde7..10c1a0dee17d 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1434,6 +1434,15 @@ xfs_inode_free_quota_blocks(
 		}
 	}
 
+	if (XFS_IS_PQUOTA_ENFORCED(ip->i_mount)) {
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_PROJ);
+		if (dq && xfs_dquot_lowsp(dq)) {
+			eofb.eof_prid = ip->i_d.di_projid;
+			eofb.eof_flags |= XFS_EOF_FLAGS_PRID;
+			do_work = true;
+		}
+	}
+
 	if (!do_work)
 		return false;
 

[PATCH 04/11] xfs: move and rename xfs_inode_free_quota_blocks to avoid conflicts

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move this function further down in the file so that later cleanups won't
have to declare static functions.  Change the name because we're about
to rework all the code that performs garbage collection of speculatively
allocated file blocks.  No functional changes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_file.c   |    2 -
 fs/xfs/xfs_icache.c |  110 ++++++++++++++++++++++++++-------------------------
 fs/xfs/xfs_icache.h |    2 -
 3 files changed, 57 insertions(+), 57 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 69879237533b..d69e5abcc1b4 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -747,7 +747,7 @@ xfs_file_buffered_write(
 	 */
 	if (ret == -EDQUOT && !cleared_space) {
 		xfs_iunlock(ip, iolock);
-		cleared_space = xfs_inode_free_quota_blocks(ip);
+		cleared_space = xfs_blockgc_free_quota(ip);
 		if (cleared_space)
 			goto write_retry;
 		iolock = 0;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 10c1a0dee17d..aba901d5637b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1396,61 +1396,6 @@ xfs_icache_free_eofblocks(
 			XFS_ICI_EOFBLOCKS_TAG);
 }
 
-/*
- * Run cow/eofblocks scans on the quotas applicable to the inode. For inodes
- * with multiple quotas, we don't know exactly which quota caused an allocation
- * failure. We make a best effort by including each quota under low free space
- * conditions (less than 1% free space) in the scan.
- */
-bool
-xfs_inode_free_quota_blocks(
-	struct xfs_inode	*ip)
-{
-	struct xfs_eofblocks	eofb = {0};
-	struct xfs_dquot	*dq;
-	bool			do_work = false;
-
-	/*
-	 * Run a sync scan to increase effectiveness and use the union filter to
-	 * cover all applicable quotas in a single scan.
-	 */
-	eofb.eof_flags = XFS_EOF_FLAGS_UNION | XFS_EOF_FLAGS_SYNC;
-
-	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_uid = VFS_I(ip)->i_uid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
-			do_work = true;
-		}
-	}
-
-	if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_gid = VFS_I(ip)->i_gid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_GID;
-			do_work = true;
-		}
-	}
-
-	if (XFS_IS_PQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_PROJ);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_prid = ip->i_d.di_projid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_PRID;
-			do_work = true;
-		}
-	}
-
-	if (!do_work)
-		return false;
-
-	xfs_icache_free_eofblocks(ip->i_mount, &eofb);
-	xfs_icache_free_cowblocks(ip->i_mount, &eofb);
-	return true;
-}
-
 static inline unsigned long
 xfs_iflag_for_tag(
 	int		tag)
@@ -1699,3 +1644,58 @@ xfs_start_block_reaping(
 	xfs_queue_eofblocks(mp);
 	xfs_queue_cowblocks(mp);
 }
+
+/*
+ * Run cow/eofblocks scans on the quotas applicable to the inode. For inodes
+ * with multiple quotas, we don't know exactly which quota caused an allocation
+ * failure. We make a best effort by including each quota under low free space
+ * conditions (less than 1% free space) in the scan.
+ */
+bool
+xfs_blockgc_free_quota(
+	struct xfs_inode	*ip)
+{
+	struct xfs_eofblocks	eofb = {0};
+	struct xfs_dquot	*dq;
+	bool			do_work = false;
+
+	/*
+	 * Run a sync scan to increase effectiveness and use the union filter to
+	 * cover all applicable quotas in a single scan.
+	 */
+	eofb.eof_flags = XFS_EOF_FLAGS_UNION | XFS_EOF_FLAGS_SYNC;
+
+	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
+		if (dq && xfs_dquot_lowsp(dq)) {
+			eofb.eof_uid = VFS_I(ip)->i_uid;
+			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
+			do_work = true;
+		}
+	}
+
+	if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP);
+		if (dq && xfs_dquot_lowsp(dq)) {
+			eofb.eof_gid = VFS_I(ip)->i_gid;
+			eofb.eof_flags |= XFS_EOF_FLAGS_GID;
+			do_work = true;
+		}
+	}
+
+	if (XFS_IS_PQUOTA_ENFORCED(ip->i_mount)) {
+		dq = xfs_inode_dquot(ip, XFS_DQTYPE_PROJ);
+		if (dq && xfs_dquot_lowsp(dq)) {
+			eofb.eof_prid = ip->i_d.di_projid;
+			eofb.eof_flags |= XFS_EOF_FLAGS_PRID;
+			do_work = true;
+		}
+	}
+
+	if (!do_work)
+		return false;
+
+	xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+	xfs_icache_free_cowblocks(ip->i_mount, &eofb);
+	return true;
+}
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 3f7ddbca8638..21b726a05b0d 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -54,7 +54,7 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 
-bool xfs_inode_free_quota_blocks(struct xfs_inode *ip);
+bool xfs_blockgc_free_quota(struct xfs_inode *ip);
 
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);

[PATCH 05/11] xfs: pass flags and return gc errors from xfs_blockgc_free_quota

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Change the signature of xfs_blockgc_free_quota in preparation for the
next few patches.  Callers can now pass EOF_FLAGS into the function to
control scan parameters; and the function will now pass back any
corruption errors seen while scanning, though for our retry loops we'll
just try again unconditionally.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_file.c   |   10 +++++-----
 fs/xfs/xfs_icache.c |   26 +++++++++++++++++---------
 fs/xfs/xfs_icache.h |    2 +-
 3 files changed, 23 insertions(+), 15 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d69e5abcc1b4..3be0b1d81325 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -743,14 +743,14 @@ xfs_file_buffered_write(
 	 * metadata space. This reduces the chances that the eofblocks scan
 	 * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this
 	 * also behaves as a filter to prevent too many eofblocks scans from
-	 * running at the same time.
+	 * running at the same time.  Use a synchronous scan to increase the
+	 * effectiveness of the scan.
 	 */
 	if (ret == -EDQUOT && !cleared_space) {
 		xfs_iunlock(ip, iolock);
-		cleared_space = xfs_blockgc_free_quota(ip);
-		if (cleared_space)
-			goto write_retry;
-		iolock = 0;
+		xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC);
+		cleared_space = true;
+		goto write_retry;
 	} else if (ret == -ENOSPC && !cleared_space) {
 		struct xfs_eofblocks eofb = {0};
 
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index aba901d5637b..4a074aa12b52 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1650,20 +1650,26 @@ xfs_start_block_reaping(
  * with multiple quotas, we don't know exactly which quota caused an allocation
  * failure. We make a best effort by including each quota under low free space
  * conditions (less than 1% free space) in the scan.
+ *
+ * Callers must not hold any inode's ILOCK.  If requesting a synchronous scan
+ * (XFS_EOF_FLAGS_SYNC), the caller also must not hold any inode's IOLOCK or
+ * MMAPLOCK.
  */
-bool
+int
 xfs_blockgc_free_quota(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	unsigned int		eof_flags)
 {
 	struct xfs_eofblocks	eofb = {0};
 	struct xfs_dquot	*dq;
 	bool			do_work = false;
+	int			error;
 
 	/*
-	 * Run a sync scan to increase effectiveness and use the union filter to
-	 * cover all applicable quotas in a single scan.
+	 * Run a scan to free blocks using the union filter to cover all
+	 * applicable quotas in a single scan.
 	 */
-	eofb.eof_flags = XFS_EOF_FLAGS_UNION | XFS_EOF_FLAGS_SYNC;
+	eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags;
 
 	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
 		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
@@ -1693,9 +1699,11 @@ xfs_blockgc_free_quota(
 	}
 
 	if (!do_work)
-		return false;
+		return 0;
 
-	xfs_icache_free_eofblocks(ip->i_mount, &eofb);
-	xfs_icache_free_cowblocks(ip->i_mount, &eofb);
-	return true;
+	error = xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+	if (error)
+		return error;
+
+	return xfs_icache_free_cowblocks(ip->i_mount, &eofb);
 }
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 21b726a05b0d..d64ea8f5c589 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -54,7 +54,7 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 
-bool xfs_blockgc_free_quota(struct xfs_inode *ip);
+int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags);
 
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);

[PATCH 06/11] xfs: flush eof/cowblocks if we can't reserve quota for file blocks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If a fs modification (data write, reflink, xattr set, fallocate, etc.)
is unable to reserve enough quota to handle the modification, try
clearing whatever space the filesystem might have been hanging onto in
the hopes of speeding up the filesystem.  The flushing behavior will
become particularly important when we add deferred inode inactivation
because that will increase the amount of space that isn't actively tied
to user data.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_quota.h       |   15 ++++++--
 fs/xfs/xfs_reflink.c     |    7 +++-
 fs/xfs/xfs_trans.c       |    9 ++++-
 fs/xfs/xfs_trans_dquot.c |   87 +++++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 107 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index c3a5b48f5860..dcdc3cd0361a 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -82,7 +82,9 @@ extern void xfs_trans_mod_dquot_byino(struct xfs_trans *, struct xfs_inode *,
 extern void xfs_trans_apply_dquot_deltas(struct xfs_trans *);
 extern void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *);
 int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip,
-		int64_t dblocks, int64_t rblocks, bool force);
+		int64_t dblocks, int64_t rblocks, bool force,
+		unsigned int *retry);
+void xfs_trans_cancel_qretry_nblks(struct xfs_trans *tp, struct xfs_inode *ip);
 extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *,
 		struct xfs_mount *, struct xfs_dquot *,
 		struct xfs_dquot *, struct xfs_dquot *, int64_t, long, uint);
@@ -114,7 +116,8 @@ extern void xfs_qm_unmount_quotas(struct xfs_mount *);
 static inline int
 xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t dblocks)
 {
-	return xfs_trans_reserve_quota_nblks(NULL, ip, dblocks, 0, false);
+	return xfs_trans_reserve_quota_nblks(NULL, ip, dblocks, 0, false,
+			NULL);
 }
 #else
 static inline int
@@ -134,7 +137,7 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid,
 #define xfs_trans_unreserve_and_mod_dquots(tp)
 static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp,
 		struct xfs_inode *ip, int64_t dblocks, int64_t rblocks,
-		bool force)
+		bool force, unsigned int *retry)
 {
 	return 0;
 }
@@ -159,6 +162,12 @@ xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp,
 	return 0;
 }
 
+static inline void
+xfs_trans_cancel_qretry_nblks(struct xfs_trans *tp, struct xfs_inode *ip)
+{
+	ASSERT(0);
+}
+
 #define xfs_qm_vop_create_dqattach(tp, ip, u, g, p)
 #define xfs_qm_vop_rename_dqattach(it)					(0)
 #define xfs_qm_vop_chown(tp, ip, old, new)				(NULL)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index c6296fd1512f..068e70d7a3bc 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1093,10 +1093,15 @@ xfs_reflink_remap_extent(
 	 * count.  This is suboptimal, but the VFS flushed the dest range
 	 * before we started.  That should have removed all the delalloc
 	 * reservations, but we code defensively.
+	 *
+	 * xfs_trans_alloc_inode above already tried to grab an even larger
+	 * quota reservation, and kicked off a blockgc scan if it couldn't.
+	 * If we can't get a potentially smaller quota reservation now, we're
+	 * done.
 	 */
 	if (!quota_reserved && !smap_real && dmap_written) {
 		error = xfs_trans_reserve_quota_nblks(tp, ip,
-				dmap->br_blockcount, 0, false);
+				dmap->br_blockcount, 0, false, NULL);
 		if (error)
 			goto out_cancel;
 	}
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index bfb8b2a1594f..3d1f745b721a 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1046,8 +1046,10 @@ xfs_trans_alloc_inode(
 {
 	struct xfs_trans	*tp;
 	struct xfs_mount	*mp = ip->i_mount;
+	unsigned int		qretry = 0;
 	int			error;
 
+retry:
 	error = xfs_trans_alloc(mp, resv, dblocks,
 			rblocks / mp->m_sb.sb_rextsize,
 			force ? XFS_TRANS_RESERVE : 0, &tp);
@@ -1064,9 +1066,14 @@ xfs_trans_alloc_inode(
 		goto out_cancel;
 	}
 
-	error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, force);
+	error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, force,
+			&qretry);
 	if (error)
 		goto out_cancel;
+	if (qretry) {
+		xfs_trans_cancel_qretry_nblks(tp, ip);
+		goto retry;
+	}
 
 	*tpp = tp;
 	return 0;
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 73ef5994d09d..229e2a20889f 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -16,6 +16,7 @@
 #include "xfs_quota.h"
 #include "xfs_qm.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 STATIC void	xfs_trans_alloc_dqinfo(xfs_trans_t *);
 
@@ -770,11 +771,67 @@ xfs_trans_reserve_quota_bydquots(
 	return error;
 }
 
+/*
+ * Decide what to do after an attempt to reserve some quota.  This will set
+ * the retry and error parameters as needed, and returns true if the quota
+ * reservation succeeded.
+ */
+static inline bool
+reservation_success(
+	unsigned int		qflag,
+	unsigned int		*retry,
+	int			*error)
+{
+	/*
+	 * The caller is not interested in retries.  Return whether or not we
+	 * got an error code.
+	 */
+	if (retry == NULL)
+		return *error == 0;
+
+	if (*error == -EDQUOT || *error == -ENOSPC) {
+		/*
+		 * There isn't enough quota left to allow the reservation.
+		 *
+		 * If none of the retry bits are set, this is the first time
+		 * that we failed a quota reservation.  Zero the error code and
+		 * set the appropriate quota flag in *retry to encourage the
+		 * xfs_trans_reserve_quota_nblks caller to clear some space and
+		 * call back.
+		 *
+		 * If any of the retry bits are set, this means that we failed
+		 * the quota reservation once before, tried to free some quota,
+		 * and have now failed the second quota reservation attempt.
+		 * Pass the error back to the caller; we're done.
+		 */
+		if (!(*retry))
+			*error = 0;
+
+		*retry |= qflag;
+		return false;
+	}
+
+	/* A non-quota error occurred; there is no retry. */
+	if (error)
+		return false;
+
+	/*
+	 * The reservation succeeded.  Clear the quota flag from the retry
+	 * state because there is nothing to retry.
+	 */
+	*retry &= ~qflag;
+	return true;
+}
 
 /*
- * Lock the dquot and change the reservation if we can.
- * This doesn't change the actual usage, just the reservation.
- * The inode sent in is locked.
+ * Lock the dquot and change the reservation if we can.  This doesn't change
+ * the actual usage, just the reservation.  The caller must hold ILOCK_EXCL on
+ * the inode.  If @retry is not a NULL pointer, the caller must ensure that
+ * *retry is set to 0 before the first time this function is called.
+ *
+ * If the quota reservation fails because we hit a quota limit (and retry is
+ * not a NULL pointer, and *retry is zero), this function will set *retry to
+ * nonzero and return zero.
  */
 int
 xfs_trans_reserve_quota_nblks(
@@ -782,7 +839,8 @@ xfs_trans_reserve_quota_nblks(
 	struct xfs_inode	*ip,
 	int64_t			dblocks,
 	int64_t			rblocks,
-	bool			force)
+	bool			force,
+	unsigned int		*retry)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	unsigned int		qflags = 0;
@@ -801,14 +859,14 @@ xfs_trans_reserve_quota_nblks(
 	error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot,
 			ip->i_gdquot, ip->i_pdquot, dblocks, 0,
 			XFS_QMOPT_RES_REGBLKS | qflags);
-	if (error)
+	if (!reservation_success(XFS_QMOPT_RES_REGBLKS, retry, &error))
 		return error;
 
 	/* Do the same but for realtime blocks. */
 	error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot,
 			ip->i_gdquot, ip->i_pdquot, rblocks, 0,
 			XFS_QMOPT_RES_RTBLKS | qflags);
-	if (error) {
+	if (!reservation_success(XFS_QMOPT_RES_RTBLKS, retry, &error)) {
 		xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot,
 				ip->i_gdquot, ip->i_pdquot, -dblocks, 0,
 				XFS_QMOPT_RES_REGBLKS);
@@ -818,6 +876,23 @@ xfs_trans_reserve_quota_nblks(
 	return 0;
 }
 
+/*
+ * Cancel a transaction and try to clear some space so that we can reserve some
+ * quota.  The caller must hold the ILOCK; when this function returns, the
+ * transaction will be cancelled and the ILOCK will have been released.
+ */
+void
+xfs_trans_cancel_qretry_nblks(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	xfs_trans_cancel(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_blockgc_free_quota(ip, 0);
+}
+
 /* Change the quota reservations for an inode creation activity. */
 int
 xfs_trans_reserve_quota_icreate(

[PATCH 07/11] xfs: flush eof/cowblocks if we can't reserve quota for inode creation

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If an inode creation is unable to reserve enough quota to handle the
modification, try clearing whatever space the filesystem might have been
hanging onto in the hopes of speeding up the filesystem.  The flushing
behavior will become particularly important when we add deferred inode
inactivation because that will increase the amount of space that isn't
actively tied to user data.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_icache.c      |   73 +++++++++++++++++++++++++++-------------------
 fs/xfs/xfs_icache.h      |    2 +
 fs/xfs/xfs_quota.h       |   18 ++++++++++-
 fs/xfs/xfs_trans.c       |    9 +++++-
 fs/xfs/xfs_trans_dquot.c |   36 +++++++++++++++++++++--
 5 files changed, 102 insertions(+), 36 deletions(-)


diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 4a074aa12b52..cd369dd48818 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1646,64 +1646,77 @@ xfs_start_block_reaping(
 }
 
 /*
- * Run cow/eofblocks scans on the quotas applicable to the inode. For inodes
- * with multiple quotas, we don't know exactly which quota caused an allocation
- * failure. We make a best effort by including each quota under low free space
- * conditions (less than 1% free space) in the scan.
+ * Run cow/eofblocks scans on the supplied dquots.  We don't know exactly which
+ * quota caused an allocation failure, so we make a best effort by including
+ * each quota under low free space conditions (less than 1% free space) in the
+ * scan.
  *
  * Callers must not hold any inode's ILOCK.  If requesting a synchronous scan
  * (XFS_EOF_FLAGS_SYNC), the caller also must not hold any inode's IOLOCK or
  * MMAPLOCK.
  */
 int
-xfs_blockgc_free_quota(
-	struct xfs_inode	*ip,
+xfs_blockgc_free_dquots(
+	struct xfs_dquot	*udqp,
+	struct xfs_dquot	*gdqp,
+	struct xfs_dquot	*pdqp,
 	unsigned int		eof_flags)
 {
 	struct xfs_eofblocks	eofb = {0};
-	struct xfs_dquot	*dq;
+	struct xfs_mount	*mp = NULL;
 	bool			do_work = false;
 	int			error;
 
+	if (!udqp && !gdqp && !pdqp)
+		return 0;
+	if (udqp)
+		mp = udqp->q_mount;
+	if (!mp && gdqp)
+		mp = gdqp->q_mount;
+	if (!mp && pdqp)
+		mp = pdqp->q_mount;
+
 	/*
 	 * Run a scan to free blocks using the union filter to cover all
 	 * applicable quotas in a single scan.
 	 */
 	eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags;
 
-	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_uid = VFS_I(ip)->i_uid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
-			do_work = true;
-		}
+	if (XFS_IS_UQUOTA_ENFORCED(mp) && udqp && xfs_dquot_lowsp(udqp)) {
+		eofb.eof_uid = make_kuid(mp->m_super->s_user_ns, udqp->q_id);
+		eofb.eof_flags |= XFS_EOF_FLAGS_UID;
+		do_work = true;
 	}
 
-	if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_gid = VFS_I(ip)->i_gid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_GID;
-			do_work = true;
-		}
+	if (XFS_IS_UQUOTA_ENFORCED(mp) && gdqp && xfs_dquot_lowsp(gdqp)) {
+		eofb.eof_gid = make_kgid(mp->m_super->s_user_ns, gdqp->q_id);
+		eofb.eof_flags |= XFS_EOF_FLAGS_GID;
+		do_work = true;
 	}
 
-	if (XFS_IS_PQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_PROJ);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_prid = ip->i_d.di_projid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_PRID;
-			do_work = true;
-		}
+	if (XFS_IS_PQUOTA_ENFORCED(mp) && pdqp && xfs_dquot_lowsp(pdqp)) {
+		eofb.eof_prid = pdqp->q_id;
+		eofb.eof_flags |= XFS_EOF_FLAGS_PRID;
+		do_work = true;
 	}
 
 	if (!do_work)
 		return 0;
 
-	error = xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+	error = xfs_icache_free_eofblocks(mp, &eofb);
 	if (error)
 		return error;
 
-	return xfs_icache_free_cowblocks(ip->i_mount, &eofb);
+	return xfs_icache_free_cowblocks(mp, &eofb);
+}
+
+/* Run cow/eofblocks scans on the quotas attached to the inode. */
+int
+xfs_blockgc_free_quota(
+	struct xfs_inode	*ip,
+	unsigned int		eof_flags)
+{
+	return xfs_blockgc_free_dquots(xfs_inode_dquot(ip, XFS_DQTYPE_USER),
+			xfs_inode_dquot(ip, XFS_DQTYPE_GROUP),
+			xfs_inode_dquot(ip, XFS_DQTYPE_PROJ), eof_flags);
 }
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index d64ea8f5c589..5f520de637f6 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -54,6 +54,8 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 
+int xfs_blockgc_free_dquots(struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
+		struct xfs_dquot *pdqp, unsigned int eof_flags);
 int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags);
 
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index dcdc3cd0361a..7d87a1244256 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -90,7 +90,10 @@ extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *,
 		struct xfs_dquot *, struct xfs_dquot *, int64_t, long, uint);
 int xfs_trans_reserve_quota_icreate(struct xfs_trans *tp,
 		struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
-		struct xfs_dquot *pdqp, int64_t dblocks);
+		struct xfs_dquot *pdqp, int64_t dblocks, unsigned int *retry);
+void xfs_trans_cancel_qretry_icreate(struct xfs_trans *tp,
+		struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
+		struct xfs_dquot *pdqp);
 
 extern int xfs_qm_vop_dqalloc(struct xfs_inode *, kuid_t, kgid_t,
 		prid_t, uint, struct xfs_dquot **, struct xfs_dquot **,
@@ -157,7 +160,8 @@ xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t dblocks)
 
 static inline int
 xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp,
-		struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, int64_t dblocks)
+		struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, int64_t dblocks,
+		unsigned int *retry)
 {
 	return 0;
 }
@@ -168,6 +172,16 @@ xfs_trans_cancel_qretry_nblks(struct xfs_trans *tp, struct xfs_inode *ip)
 	ASSERT(0);
 }
 
+static inline void
+xfs_trans_cancel_qretry_icreate(
+	struct xfs_trans	*tp,
+	struct xfs_dquot	*udqp,
+	struct xfs_dquot	*gdqp,
+	struct xfs_dquot	*pdqp)
+{
+	ASSERT(0);
+}
+
 #define xfs_qm_vop_create_dqattach(tp, ip, u, g, p)
 #define xfs_qm_vop_rename_dqattach(it)					(0)
 #define xfs_qm_vop_chown(tp, ip, old, new)				(NULL)
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 3d1f745b721a..7d4823cbd7c0 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1099,17 +1099,24 @@ xfs_trans_alloc_icreate(
 	struct xfs_trans	**tpp)
 {
 	struct xfs_trans	*tp;
+	unsigned int		qretry = 0;
 	int			error;
 
+retry:
 	error = xfs_trans_alloc(mp, resv, dblocks, 0, 0, &tp);
 	if (error)
 		return error;
 
-	error = xfs_trans_reserve_quota_icreate(tp, udqp, gdqp, pdqp, dblocks);
+	error = xfs_trans_reserve_quota_icreate(tp, udqp, gdqp, pdqp, dblocks,
+			&qretry);
 	if (error) {
 		xfs_trans_cancel(tp);
 		return error;
 	}
+	if (qretry) {
+		xfs_trans_cancel_qretry_icreate(tp, udqp, gdqp, pdqp);
+		goto retry;
+	}
 
 	*tpp = tp;
 	return 0;
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 229e2a20889f..2358c9e35be8 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -893,22 +893,52 @@ xfs_trans_cancel_qretry_nblks(
 	xfs_blockgc_free_quota(ip, 0);
 }
 
-/* Change the quota reservations for an inode creation activity. */
+/*
+ * Change the quota reservations for an inode creation activity.  This doesn't
+ * change the actual usage, just the reservation.  If @retry is not a NULL
+ * pointer, the caller must ensure that *retry is set to zero before the first
+ * time this function is called.
+ *
+ * If the quota reservation fails because we hit a quota limit (and retry is
+ * not a NULL pointer, and *retry is zero), this function will set *retry to
+ * nonzero and return zero.
+ */
 int
 xfs_trans_reserve_quota_icreate(
 	struct xfs_trans	*tp,
 	struct xfs_dquot	*udqp,
 	struct xfs_dquot	*gdqp,
 	struct xfs_dquot	*pdqp,
-	int64_t			dblocks)
+	int64_t			dblocks,
+	unsigned int		*retry)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
+	int			error;
 
 	if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp))
 		return 0;
 
-	return xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, pdqp,
+	error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, pdqp,
 			dblocks, 1, XFS_QMOPT_RES_REGBLKS);
+	if (!reservation_success(XFS_QMOPT_RES_REGBLKS, retry, &error))
+		return error;
+
+	return 0;
+}
+
+/*
+ * Cancel a transaction and try to clear some space so that we can reserve some
+ * quota.  When this function returns, the transaction will be cancelled.
+ */
+void
+xfs_trans_cancel_qretry_icreate(
+	struct xfs_trans	*tp,
+	struct xfs_dquot	*udqp,
+	struct xfs_dquot	*gdqp,
+	struct xfs_dquot	*pdqp)
+{
+	xfs_trans_cancel(tp);
+	xfs_blockgc_free_dquots(udqp, gdqp, pdqp, 0);
 }
 
 /*

[PATCH 08/11] xfs: flush eof/cowblocks if we can't reserve quota for chown

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If a file user, group, or project change is unable to reserve enough
quota to handle the modification, try clearing whatever space the
filesystem might have been hanging onto in the hopes of speeding up the
filesystem.  The flushing behavior will become particularly important
when we add deferred inode inactivation because that will increase the
amount of space that isn't actively tied to user data.

Note that the retry loop is open-coded here because there are only two
places in the codebase where we ever change [ugp]id; and the setattr and
setxattr code is already tricky enough.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_ioctl.c       |    9 ++++++++-
 fs/xfs/xfs_iops.c        |   10 +++++++++-
 fs/xfs/xfs_quota.h       |   18 ++++++++++++++++--
 fs/xfs/xfs_trans_dquot.c |   46 ++++++++++++++++++++++++++++++++++++++++++----
 4 files changed, 75 insertions(+), 8 deletions(-)


diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 73cfee8007a8..6adfc8541d61 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1436,6 +1436,7 @@ xfs_ioctl_setattr(
 	struct xfs_trans	*tp;
 	struct xfs_dquot	*pdqp = NULL;
 	struct xfs_dquot	*olddquot = NULL;
+	unsigned int		quota_retry = 0;
 	int			code;
 
 	trace_xfs_ioctl_setattr(ip);
@@ -1462,6 +1463,7 @@ xfs_ioctl_setattr(
 
 	xfs_ioctl_setattr_prepare_dax(ip, fa);
 
+retry:
 	tp = xfs_ioctl_setattr_get_trans(ip);
 	if (IS_ERR(tp)) {
 		code = PTR_ERR(tp);
@@ -1471,9 +1473,14 @@ xfs_ioctl_setattr(
 	if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) &&
 	    ip->i_d.di_projid != fa->fsx_projid) {
 		code = xfs_trans_reserve_quota_chown(tp, ip, NULL, NULL, pdqp,
-				capable(CAP_FOWNER));
+				capable(CAP_FOWNER), &quota_retry);
 		if (code)	/* out of quota */
 			goto error_trans_cancel;
+		if (quota_retry) {
+			xfs_trans_cancel_qretry_chown(tp, ip, NULL, NULL,
+					pdqp);
+			goto retry;
+		}
 	}
 
 	xfs_fill_fsxattr(ip, false, &old_fa);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 51c877ce90bc..9453c984d715 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -660,6 +660,7 @@ xfs_setattr_nonsize(
 	kgid_t			gid = GLOBAL_ROOT_GID, igid = GLOBAL_ROOT_GID;
 	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
 	struct xfs_dquot	*olddquot1 = NULL, *olddquot2 = NULL;
+	unsigned int		quota_retry = 0;
 
 	ASSERT((mask & ATTR_SIZE) == 0);
 
@@ -700,6 +701,7 @@ xfs_setattr_nonsize(
 			return error;
 	}
 
+retry:
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
 	if (error)
 		goto out_dqrele;
@@ -731,9 +733,15 @@ xfs_setattr_nonsize(
 		     (XFS_IS_GQUOTA_ON(mp) && !gid_eq(igid, gid)))) {
 			ASSERT(tp);
 			error = xfs_trans_reserve_quota_chown(tp, ip, udqp,
-					gdqp, NULL, capable(CAP_FOWNER));
+					gdqp, NULL, capable(CAP_FOWNER),
+					&quota_retry);
 			if (error)	/* out of quota */
 				goto out_cancel;
+			if (quota_retry) {
+				xfs_trans_cancel_qretry_chown(tp, ip, udqp,
+						gdqp, NULL);
+				goto retry;
+			}
 		}
 
 		/*
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 7d87a1244256..4f45e7feb841 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -105,7 +105,10 @@ extern struct xfs_dquot *xfs_qm_vop_chown(struct xfs_trans *,
 		struct xfs_inode *, struct xfs_dquot **, struct xfs_dquot *);
 int xfs_trans_reserve_quota_chown(struct xfs_trans *tp, struct xfs_inode *ip,
 		struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
-		struct xfs_dquot *pdqp, bool force);
+		struct xfs_dquot *pdqp, bool force, unsigned int *retry);
+void xfs_trans_cancel_qretry_chown(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
+		struct xfs_dquot *pdqp);
 extern int xfs_qm_dqattach(struct xfs_inode *);
 extern int xfs_qm_dqattach_locked(struct xfs_inode *ip, bool doalloc);
 extern void xfs_qm_dqdetach(struct xfs_inode *);
@@ -182,13 +185,24 @@ xfs_trans_cancel_qretry_icreate(
 	ASSERT(0);
 }
 
+static inline void
+xfs_trans_cancel_qretry_chown(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct xfs_dquot	*udqp,
+	struct xfs_dquot	*gdqp,
+	struct xfs_dquot	*pdqp)
+{
+	ASSERT(0);
+}
+
 #define xfs_qm_vop_create_dqattach(tp, ip, u, g, p)
 #define xfs_qm_vop_rename_dqattach(it)					(0)
 #define xfs_qm_vop_chown(tp, ip, old, new)				(NULL)
 static inline int
 xfs_trans_reserve_quota_chown(struct xfs_trans *tp, struct xfs_inode *ip,
 		struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
-		struct xfs_dquot *pdqp, bool force)
+		struct xfs_dquot *pdqp, bool force, unsigned int *retry)
 {
 	return 0;
 }
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 2358c9e35be8..7518424ee8b4 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -942,7 +942,15 @@ xfs_trans_cancel_qretry_icreate(
 }
 
 /*
- * Quota reservations for setattr(AT_UID|AT_GID|AT_PROJID).
+ * Chagnge quota reservations for setattr(AT_UID|AT_GID|AT_PROJID).  This
+ * doesn't change the actual usage, just the reservation.  The caller must hold
+ * ILOCK_EXCL on the inode.  If @retry is not a NULL pointer, the caller must
+ * ensure that *retry is set to zero before the first time this function is
+ * called.
+ *
+ * If the quota reservation fails because we hit a quota limit (and retry is
+ * not a NULL pointer, and *retry is zero), this function will set *retry to
+ * nonzero and return zero.
  */
 int
 xfs_trans_reserve_quota_chown(
@@ -951,7 +959,8 @@ xfs_trans_reserve_quota_chown(
 	struct xfs_dquot	*udqp,
 	struct xfs_dquot	*gdqp,
 	struct xfs_dquot	*pdqp,
-	bool			force)
+	bool			force,
+	unsigned int		*retry)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_dquot	*udq_unres = NULL;	/* old dquots */
@@ -1011,7 +1020,7 @@ xfs_trans_reserve_quota_chown(
 			gdq_delblks, pdq_delblks, ip->i_d.di_nblocks, 1,
 			qflags);
 	if (error)
-		return error;
+		goto err;
 
 	/*
 	 * Do the delayed blks reservations/unreservations now. Since, these
@@ -1029,13 +1038,42 @@ xfs_trans_reserve_quota_chown(
 				udq_delblks, gdq_delblks, pdq_delblks,
 				(xfs_qcnt_t)delblks, 0, qflags);
 		if (error)
-			return error;
+			goto err;
 		xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount, udq_unres,
 				gdq_unres, pdq_unres, -((xfs_qcnt_t)delblks),
 				0, qflags);
 	}
 
 	return 0;
+err:
+	/*
+	 * Handle all quota reservation failures in the same place because we
+	 * don't want the success predicate to clear REGBLKS from the retry
+	 * flags after we _reserve_quota for the ondisk blocks but before we
+	 * _reserve_quota for the delalloc blocks.  If we were called with a
+	 * nonzero *retry, that means we failed to get the quota reservation
+	 * once before and do not want to schedule a retry on a second error.
+	 */
+	reservation_success(XFS_QMOPT_RES_REGBLKS, retry, &error);
+	return error;
+}
+
+/*
+ * Cancel a transaction and try to clear some space so that we can reserve some
+ * quota.  When this function returns, the transaction will be cancelled and
+ * ILOCK_EXCL will no longer be held.
+ */
+void
+xfs_trans_cancel_qretry_chown(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct xfs_dquot	*udqp,
+	struct xfs_dquot	*gdqp,
+	struct xfs_dquot	*pdqp)
+{
+	xfs_trans_cancel(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_blockgc_free_dquots(udqp, gdqp, pdqp, 0);
 }
 
 /*

[PATCH 09/11] xfs: add a tracepoint for blockgc scans

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add some tracepoints so that we can observe when the speculative
preallocation garbage collector runs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_ioctl.c |    2 ++
 fs/xfs/xfs_trace.c |    1 +
 fs/xfs/xfs_trace.h |   41 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 44 insertions(+)


diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 6adfc8541d61..cc6ddc6d22a0 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -2355,6 +2355,8 @@ xfs_file_ioctl(
 		if (error)
 			return error;
 
+		trace_xfs_ioc_free_eofblocks(mp, &keofb, _RET_IP_);
+
 		sb_start_write(mp->m_super);
 		error = xfs_icache_free_eofblocks(mp, &keofb);
 		sb_end_write(mp->m_super);
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 120398a37c2a..9b8d703dc9fd 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -29,6 +29,7 @@
 #include "xfs_filestream.h"
 #include "xfs_fsmap.h"
 #include "xfs_btree_staging.h"
+#include "xfs_icache.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 407c3a5208ab..38649e3341cb 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -37,6 +37,7 @@ struct xfs_trans_res;
 struct xfs_inobt_rec_incore;
 union xfs_btree_ptr;
 struct xfs_dqtrx;
+struct xfs_eofblocks;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -3888,6 +3889,46 @@ DEFINE_EVENT(xfs_timestamp_range_class, name, \
 DEFINE_TIMESTAMP_RANGE_EVENT(xfs_inode_timestamp_range);
 DEFINE_TIMESTAMP_RANGE_EVENT(xfs_quota_expiry_range);
 
+DECLARE_EVENT_CLASS(xfs_eofblocks_class,
+	TP_PROTO(struct xfs_mount *mp, struct xfs_eofblocks *eofb,
+		 unsigned long caller_ip),
+	TP_ARGS(mp, eofb, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(__u32, flags)
+		__field(uint32_t, uid)
+		__field(uint32_t, gid)
+		__field(prid_t, prid)
+		__field(__u64, min_file_size)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->flags = eofb ? eofb->eof_flags : 0;
+		__entry->uid = eofb ? from_kuid(mp->m_super->s_user_ns,
+						eofb->eof_uid) : 0;
+		__entry->gid = eofb ? from_kgid(mp->m_super->s_user_ns,
+						eofb->eof_gid) : 0;
+		__entry->prid = eofb ? eofb->eof_prid : 0;
+		__entry->min_file_size = eofb ? eofb->eof_min_file_size : 0;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->flags,
+		  __entry->uid,
+		  __entry->gid,
+		  __entry->prid,
+		  __entry->min_file_size,
+		  (char *)__entry->caller_ip)
+);
+#define DEFINE_EOFBLOCKS_EVENT(name)	\
+DEFINE_EVENT(xfs_eofblocks_class, name,	\
+	TP_PROTO(struct xfs_mount *mp, struct xfs_eofblocks *eofb, \
+		 unsigned long caller_ip), \
+	TP_ARGS(mp, eofb, caller_ip))
+DEFINE_EOFBLOCKS_EVENT(xfs_ioc_free_eofblocks);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH

[PATCH 10/11] xfs: refactor xfs_icache_free_{eof,cow}blocks call sites

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In anticipation of more restructuring of the eof/cowblocks gc code,
refactor calling of those two functions into a single internal helper
function, then present a new standard interface to purge speculative
block preallocations and start shifting higher level code to use that.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_file.c   |    3 +--
 fs/xfs/xfs_icache.c |   39 +++++++++++++++++++++++++++++++++------
 fs/xfs/xfs_icache.h |    1 +
 fs/xfs/xfs_trace.h  |    1 +
 4 files changed, 36 insertions(+), 8 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 3be0b1d81325..dc91973c0b4f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -759,8 +759,7 @@ xfs_file_buffered_write(
 
 		xfs_iunlock(ip, iolock);
 		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
-		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
-		xfs_icache_free_cowblocks(ip->i_mount, &eofb);
+		xfs_blockgc_free_space(ip->i_mount, &eofb);
 		goto write_retry;
 	}
 
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index cd369dd48818..97c15fcdd6f7 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1645,6 +1645,38 @@ xfs_start_block_reaping(
 	xfs_queue_cowblocks(mp);
 }
 
+/* Scan all incore inodes for block preallocations that we can remove. */
+static inline int
+xfs_blockgc_scan(
+	struct xfs_mount	*mp,
+	struct xfs_eofblocks	*eofb)
+{
+	int			error;
+
+	error = xfs_icache_free_eofblocks(mp, eofb);
+	if (error)
+		return error;
+
+	error = xfs_icache_free_cowblocks(mp, eofb);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+/*
+ * Try to free space in the filesystem by purging eofblocks and cowblocks.
+ */
+int
+xfs_blockgc_free_space(
+	struct xfs_mount	*mp,
+	struct xfs_eofblocks	*eofb)
+{
+	trace_xfs_blockgc_free_space(mp, eofb, _RET_IP_);
+
+	return xfs_blockgc_scan(mp, eofb);
+}
+
 /*
  * Run cow/eofblocks scans on the supplied dquots.  We don't know exactly which
  * quota caused an allocation failure, so we make a best effort by including
@@ -1665,7 +1697,6 @@ xfs_blockgc_free_dquots(
 	struct xfs_eofblocks	eofb = {0};
 	struct xfs_mount	*mp = NULL;
 	bool			do_work = false;
-	int			error;
 
 	if (!udqp && !gdqp && !pdqp)
 		return 0;
@@ -1703,11 +1734,7 @@ xfs_blockgc_free_dquots(
 	if (!do_work)
 		return 0;
 
-	error = xfs_icache_free_eofblocks(mp, &eofb);
-	if (error)
-		return error;
-
-	return xfs_icache_free_cowblocks(mp, &eofb);
+	return xfs_blockgc_free_space(mp, &eofb);
 }
 
 /* Run cow/eofblocks scans on the quotas attached to the inode. */
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 5f520de637f6..583c132ae0fb 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -57,6 +57,7 @@ void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 int xfs_blockgc_free_dquots(struct xfs_dquot *udqp, struct xfs_dquot *gdqp,
 		struct xfs_dquot *pdqp, unsigned int eof_flags);
 int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags);
+int xfs_blockgc_free_space(struct xfs_mount *mp, struct xfs_eofblocks *eofb);
 
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 38649e3341cb..27929c6ca43a 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3928,6 +3928,7 @@ DEFINE_EVENT(xfs_eofblocks_class, name,	\
 		 unsigned long caller_ip), \
 	TP_ARGS(mp, eofb, caller_ip))
 DEFINE_EOFBLOCKS_EVENT(xfs_ioc_free_eofblocks);
+DEFINE_EOFBLOCKS_EVENT(xfs_blockgc_free_space);
 
 #endif /* _TRACE_XFS_H */
 

[PATCH 11/11] xfs: flush speculative space allocations when we run out of space

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If a fs modification (creation, file write, reflink, etc.) is unable to
reserve enough space to handle the modification, try clearing whatever
space the filesystem might have been hanging onto in the hopes of
speeding up the filesystem.  The flushing behavior will become
particularly important when we add deferred inode inactivation because
that will increase the amount of space that isn't actively tied to user
data.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_trans.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)


diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 7d4823cbd7c0..eb39baddff35 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -23,6 +23,7 @@
 #include "xfs_inode.h"
 #include "xfs_dquot_item.h"
 #include "xfs_dquot.h"
+#include "xfs_icache.h"
 
 kmem_zone_t	*xfs_trans_zone;
 
@@ -288,6 +289,18 @@ xfs_trans_alloc(
 	tp->t_firstblock = NULLFSBLOCK;
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
+	if (error == -ENOSPC) {
+		/*
+		 * We weren't able to reserve enough space for the transaction.
+		 * Flush the other speculative space allocations to free space.
+		 * Do not perform a synchronous scan because callers can hold
+		 * other locks.
+		 */
+		error = xfs_blockgc_free_space(mp, NULL);
+		if (error)
+			return error;
+		error = xfs_trans_reserve(tp, resp, blocks, rtextents);
+	}
 	if (error) {
 		xfs_trans_cancel(tp);
 		return error;

Re: [PATCH 06/11] xfs: flush eof/cowblocks if we can't reserve quota for file blocks

[Christoph Hellwig]

> +void
> +xfs_trans_cancel_qretry_nblks(
> +	struct xfs_trans	*tp,
> +	struct xfs_inode	*ip)
> +{
> +	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
> +
> +	xfs_trans_cancel(tp);
> +	xfs_iunlock(ip, XFS_ILOCK_EXCL);
> +	xfs_blockgc_free_quota(ip, 0);
> +}

I still find this helper a little weird.  Why not cancel the transaction
in xfs_trans_reserve_quota_nblks, and then just open code the calls to
xfs_iunlock and xfs_blockgc_free_quota in the callers?

Re: [PATCH 11/11] xfs: flush speculative space allocations when we run out of space

[Christoph Hellwig]

On Wed, Jan 27, 2021 at 10:03:23PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> If a fs modification (creation, file write, reflink, etc.) is unable to
> reserve enough space to handle the modification, try clearing whatever
> space the filesystem might have been hanging onto in the hopes of
> speeding up the filesystem.  The flushing behavior will become
> particularly important when we add deferred inode inactivation because
> that will increase the amount of space that isn't actively tied to user
> data.
> 
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 05/11] xfs: pass flags and return gc errors from xfs_blockgc_free_quota

[Brian Foster]

On Sat, Jan 23, 2021 at 10:52:27AM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Change the signature of xfs_blockgc_free_quota in preparation for the
> next few patches.  Callers can now pass EOF_FLAGS into the function to
> control scan parameters; and the function will now pass back any
> corruption errors seen while scanning, though for our retry loops we'll
> just try again unconditionally.
> 
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> ---
>  fs/xfs/xfs_file.c   |    7 +++----
>  fs/xfs/xfs_icache.c |   20 ++++++++++++--------
>  fs/xfs/xfs_icache.h |    2 +-
>  3 files changed, 16 insertions(+), 13 deletions(-)
> 
> 
...
> diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
> index aba901d5637b..68b6f72593dc 100644
> --- a/fs/xfs/xfs_icache.c
> +++ b/fs/xfs/xfs_icache.c
> @@ -1651,19 +1651,21 @@ xfs_start_block_reaping(
>   * failure. We make a best effort by including each quota under low free space
>   * conditions (less than 1% free space) in the scan.
>   */
> -bool
> +int
>  xfs_blockgc_free_quota(
> -	struct xfs_inode	*ip)
> +	struct xfs_inode	*ip,
> +	unsigned int		eof_flags)
>  {
>  	struct xfs_eofblocks	eofb = {0};
>  	struct xfs_dquot	*dq;
>  	bool			do_work = false;
> +	int			error;
>  
>  	/*
> -	 * Run a sync scan to increase effectiveness and use the union filter to
> +	 * Run a scan to increase effectiveness and use the union filter to

The original comment referred to the increased effectiveness of a sync
scan. It doesn't make a whole lot of sense without that qualification
IMO (even though the scan is still sync). We could move that bit of
comment to the caller where the flag is now set, but it's probably fine
to just remove that text also. With that tweak:

Reviewed-by: Brian Foster <bfoster@redhat.com>

>  	 * cover all applicable quotas in a single scan.
>  	 */
> -	eofb.eof_flags = XFS_EOF_FLAGS_UNION | XFS_EOF_FLAGS_SYNC;
> +	eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags;
>  
>  	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
>  		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
> @@ -1693,9 +1695,11 @@ xfs_blockgc_free_quota(
>  	}
>  
>  	if (!do_work)
> -		return false;
> +		return 0;
>  
> -	xfs_icache_free_eofblocks(ip->i_mount, &eofb);
> -	xfs_icache_free_cowblocks(ip->i_mount, &eofb);
> -	return true;
> +	error = xfs_icache_free_eofblocks(ip->i_mount, &eofb);
> +	if (error)
> +		return error;
> +
> +	return xfs_icache_free_cowblocks(ip->i_mount, &eofb);
>  }
> diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
> index 21b726a05b0d..d64ea8f5c589 100644
> --- a/fs/xfs/xfs_icache.h
> +++ b/fs/xfs/xfs_icache.h
> @@ -54,7 +54,7 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
>  
>  void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
>  
> -bool xfs_blockgc_free_quota(struct xfs_inode *ip);
> +int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags);
>  
>  void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
>  void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);
> 

Re: [PATCH 05/11] xfs: pass flags and return gc errors from xfs_blockgc_free_quota

[Christoph Hellwig]

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

[PATCH 05/11] xfs: pass flags and return gc errors from xfs_blockgc_free_quota

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Change the signature of xfs_blockgc_free_quota in preparation for the
next few patches.  Callers can now pass EOF_FLAGS into the function to
control scan parameters; and the function will now pass back any
corruption errors seen while scanning, though for our retry loops we'll
just try again unconditionally.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_file.c   |    7 +++----
 fs/xfs/xfs_icache.c |   20 ++++++++++++--------
 fs/xfs/xfs_icache.h |    2 +-
 3 files changed, 16 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d69e5abcc1b4..57086838a676 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -747,10 +747,9 @@ xfs_file_buffered_write(
 	 */
 	if (ret == -EDQUOT && !cleared_space) {
 		xfs_iunlock(ip, iolock);
-		cleared_space = xfs_blockgc_free_quota(ip);
-		if (cleared_space)
-			goto write_retry;
-		iolock = 0;
+		xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC);
+		cleared_space = true;
+		goto write_retry;
 	} else if (ret == -ENOSPC && !cleared_space) {
 		struct xfs_eofblocks eofb = {0};
 
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index aba901d5637b..68b6f72593dc 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1651,19 +1651,21 @@ xfs_start_block_reaping(
  * failure. We make a best effort by including each quota under low free space
  * conditions (less than 1% free space) in the scan.
  */
-bool
+int
 xfs_blockgc_free_quota(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	unsigned int		eof_flags)
 {
 	struct xfs_eofblocks	eofb = {0};
 	struct xfs_dquot	*dq;
 	bool			do_work = false;
+	int			error;
 
 	/*
-	 * Run a sync scan to increase effectiveness and use the union filter to
+	 * Run a scan to increase effectiveness and use the union filter to
 	 * cover all applicable quotas in a single scan.
 	 */
-	eofb.eof_flags = XFS_EOF_FLAGS_UNION | XFS_EOF_FLAGS_SYNC;
+	eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags;
 
 	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
 		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
@@ -1693,9 +1695,11 @@ xfs_blockgc_free_quota(
 	}
 
 	if (!do_work)
-		return false;
+		return 0;
 
-	xfs_icache_free_eofblocks(ip->i_mount, &eofb);
-	xfs_icache_free_cowblocks(ip->i_mount, &eofb);
-	return true;
+	error = xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+	if (error)
+		return error;
+
+	return xfs_icache_free_cowblocks(ip->i_mount, &eofb);
 }
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 21b726a05b0d..d64ea8f5c589 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -54,7 +54,7 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 
-bool xfs_blockgc_free_quota(struct xfs_inode *ip);
+int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags);
 
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);

Re: [PATCH 05/11] xfs: pass flags and return gc errors from xfs_blockgc_free_quota

[Christoph Hellwig]

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

[PATCH 05/11] xfs: pass flags and return gc errors from xfs_blockgc_free_quota

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Change the signature of xfs_blockgc_free_quota in preparation for the
next few patches.  Callers can now pass EOF_FLAGS into the function to
control scan parameters; and the function will now pass back any
corruption errors seen while scanning, so that we can fail fast.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_file.c   |    7 ++++++-
 fs/xfs/xfs_icache.c |   35 ++++++++++++++++++++++-------------
 fs/xfs/xfs_icache.h |    3 ++-
 3 files changed, 30 insertions(+), 15 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 54c658d0f738..a318a4749b59 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -685,8 +685,13 @@ xfs_file_buffered_aio_write(
 	 * running at the same time.
 	 */
 	if (ret == -EDQUOT && !cleared_space) {
+		int	ret2;
+
 		xfs_iunlock(ip, iolock);
-		cleared_space = xfs_blockgc_free_quota(ip);
+		ret2 = xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC,
+				&cleared_space);
+		if (ret2)
+			return ret2;
 		if (cleared_space)
 			goto write_retry;
 		iolock = 0;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index aba901d5637b..1e0ffc0fb73c 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1651,26 +1651,30 @@ xfs_start_block_reaping(
  * failure. We make a best effort by including each quota under low free space
  * conditions (less than 1% free space) in the scan.
  */
-bool
+int
 xfs_blockgc_free_quota(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	unsigned int		eof_flags,
+	bool			*found_work)
 {
 	struct xfs_eofblocks	eofb = {0};
 	struct xfs_dquot	*dq;
-	bool			do_work = false;
+	int			error;
+
+	*found_work = false;
 
 	/*
-	 * Run a sync scan to increase effectiveness and use the union filter to
+	 * Run a scan to increase effectiveness and use the union filter to
 	 * cover all applicable quotas in a single scan.
 	 */
-	eofb.eof_flags = XFS_EOF_FLAGS_UNION | XFS_EOF_FLAGS_SYNC;
+	eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags;
 
 	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
 		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_uid = VFS_I(ip)->i_uid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
-			do_work = true;
+			*found_work = true;
 		}
 	}
 
@@ -1679,7 +1683,7 @@ xfs_blockgc_free_quota(
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_gid = VFS_I(ip)->i_gid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_GID;
-			do_work = true;
+			*found_work = true;
 		}
 	}
 
@@ -1688,14 +1692,19 @@ xfs_blockgc_free_quota(
 		if (dq && xfs_dquot_lowsp(dq)) {
 			eofb.eof_prid = ip->i_d.di_projid;
 			eofb.eof_flags |= XFS_EOF_FLAGS_PRID;
-			do_work = true;
+			*found_work = true;
 		}
 	}
 
-	if (!do_work)
-		return false;
+	if (*found_work) {
+		error = xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+		if (error)
+			return error;
 
-	xfs_icache_free_eofblocks(ip->i_mount, &eofb);
-	xfs_icache_free_cowblocks(ip->i_mount, &eofb);
-	return true;
+		error = xfs_icache_free_cowblocks(ip->i_mount, &eofb);
+		if (error)
+			return error;
+	}
+
+	return 0;
 }
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 21b726a05b0d..f7b6ead6fc08 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -54,7 +54,8 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 
-bool xfs_blockgc_free_quota(struct xfs_inode *ip);
+int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags,
+		bool *found_work);
 
 void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
 void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);