Merge remote-tracking branch 'xfs/xfs-5.12-fixes' into 2021-03-15/xfstests2021-03-15/xfstests

Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

6 files changed, 125 insertions, 64 deletions

diff --git a/Documentation/ABI/testing/sysfs-fs-xfs b/Documentation/ABI/testing/sysfs-fs-xfs
index ea0cc8c42093f..f704925f6fe93 100644
--- a/Documentation/ABI/testing/sysfs-fs-xfs
+++ b/Documentation/ABI/testing/sysfs-fs-xfs
@@ -33,7 +33,7 @@ Contact:	xfs@oss.sgi.com
 Description:
 		The current state of the log write grant head. It
 		represents the total log reservation of all currently
-		oustanding transactions, including regrants due to
+		outstanding transactions, including regrants due to
 		rolling transactions. The grant head is exported in
 		"cycle:bytes" format.
 Users:		xfstests
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index aa924db90cd9d..601b4b5bd7d34 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1007,9 +1007,10 @@ xfs_create(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
-					XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
-					&udqp, &gdqp, &pdqp);
+	error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+			fsgid_into_mnt(mnt_userns), prid,
+			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+			&udqp, &gdqp, &pdqp);
 	if (error)
 		return error;
 
@@ -1157,9 +1158,10 @@ xfs_create_tmpfile(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
-				XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
-				&udqp, &gdqp, &pdqp);
+	error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+			fsgid_into_mnt(mnt_userns), prid,
+			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+			&udqp, &gdqp, &pdqp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index ca310a125d1e1..75b0b443215cf 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -19,6 +19,7 @@
 #include "xfs_error.h"
 #include "xfs_icache.h"
 #include "xfs_health.h"
+#include "xfs_trans.h"
 
 /*
  * Bulk Stat
@@ -166,8 +167,15 @@ xfs_bulkstat_one(
 		.formatter	= formatter,
 		.breq		= breq,
 	};
+	struct xfs_trans	*tp;
 	int			error;
 
+	if (breq->mnt_userns != &init_user_ns) {
+		xfs_warn_ratelimited(breq->mp,
+			"bulkstat not supported inside of idmapped mounts.");
+		return -EINVAL;
+	}
+
 	ASSERT(breq->icount == 1);
 
 	bc.buf = kmem_zalloc(sizeof(struct xfs_bulkstat),
@@ -175,9 +183,18 @@ xfs_bulkstat_one(
 	if (!bc.buf)
 		return -ENOMEM;
 
-	error = xfs_bulkstat_one_int(breq->mp, breq->mnt_userns, NULL,
-				     breq->startino, &bc);
+	/*
+	 * Grab an empty transaction so that we can use its recursive buffer
+	 * locking abilities to detect cycles in the inobt without deadlocking.
+	 */
+	error = xfs_trans_alloc_empty(breq->mp, &tp);
+	if (error)
+		goto out;
 
+	error = xfs_bulkstat_one_int(breq->mp, breq->mnt_userns, tp,
+			breq->startino, &bc);
+	xfs_trans_cancel(tp);
+out:
 	kmem_free(bc.buf);
 
 	/*
@@ -241,6 +258,7 @@ xfs_bulkstat(
 		.formatter	= formatter,
 		.breq		= breq,
 	};
+	struct xfs_trans	*tp;
 	int			error;
 
 	if (breq->mnt_userns != &init_user_ns) {
@@ -256,9 +274,18 @@ xfs_bulkstat(
 	if (!bc.buf)
 		return -ENOMEM;
 
-	error = xfs_iwalk(breq->mp, NULL, breq->startino, breq->flags,
-			xfs_bulkstat_iwalk, breq->icount, &bc);
+	/*
+	 * Grab an empty transaction so that we can use its recursive buffer
+	 * locking abilities to detect cycles in the inobt without deadlocking.
+	 */
+	error = xfs_trans_alloc_empty(breq->mp, &tp);
+	if (error)
+		goto out;
 
+	error = xfs_iwalk(breq->mp, tp, breq->startino, breq->flags,
+			xfs_bulkstat_iwalk, breq->icount, &bc);
+	xfs_trans_cancel(tp);
+out:
 	kmem_free(bc.buf);
 
 	/*
@@ -371,13 +398,24 @@ xfs_inumbers(
 		.formatter	= formatter,
 		.breq		= breq,
 	};
+	struct xfs_trans	*tp;
 	int			error = 0;
 
 	if (xfs_bulkstat_already_done(breq->mp, breq->startino))
 		return 0;
 
-	error = xfs_inobt_walk(breq->mp, NULL, breq->startino, breq->flags,
+	/*
+	 * Grab an empty transaction so that we can use its recursive buffer
+	 * locking abilities to detect cycles in the inobt without deadlocking.
+	 */
+	error = xfs_trans_alloc_empty(breq->mp, &tp);
+	if (error)
+		goto out;
+
+	error = xfs_inobt_walk(breq->mp, tp, breq->startino, breq->flags,
 			xfs_inumbers_walk, breq->icount, &ic);
+	xfs_trans_cancel(tp);
+out:
 
 	/*
 	 * We found some inode groups, so clear the error status and return
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index c4a340f1f1e1c..e1e889f3647fa 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -81,6 +81,9 @@ struct xfs_iwalk_ag {
 
 	/* Skip empty inobt records? */
 	unsigned int			skip_empty:1;
+
+	/* Drop the (hopefully empty) transaction when calling iwalk_fn. */
+	unsigned int			drop_trans:1;
 };
 
 /*
@@ -351,7 +354,6 @@ xfs_iwalk_run_callbacks(
 	int				*has_more)
 {
 	struct xfs_mount		*mp = iwag->mp;
-	struct xfs_trans		*tp = iwag->tp;
 	struct xfs_inobt_rec_incore	*irec;
 	xfs_agino_t			next_agino;
 	int				error;
@@ -361,10 +363,15 @@ xfs_iwalk_run_callbacks(
 	ASSERT(iwag->nr_recs > 0);
 
 	/* Delete cursor but remember the last record we cached... */
-	xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0);
+	xfs_iwalk_del_inobt(iwag->tp, curpp, agi_bpp, 0);
 	irec = &iwag->recs[iwag->nr_recs - 1];
 	ASSERT(next_agino >= irec->ir_startino + XFS_INODES_PER_CHUNK);
 
+	if (iwag->drop_trans) {
+		xfs_trans_cancel(iwag->tp);
+		iwag->tp = NULL;
+	}
+
 	error = xfs_iwalk_ag_recs(iwag);
 	if (error)
 		return error;
@@ -375,8 +382,14 @@ xfs_iwalk_run_callbacks(
 	if (!has_more)
 		return 0;
 
+	if (iwag->drop_trans) {
+		error = xfs_trans_alloc_empty(mp, &iwag->tp);
+		if (error)
+			return error;
+	}
+
 	/* ...and recreate the cursor just past where we left off. */
-	error = xfs_inobt_cur(mp, tp, agno, XFS_BTNUM_INO, curpp, agi_bpp);
+	error = xfs_inobt_cur(mp, iwag->tp, agno, XFS_BTNUM_INO, curpp, agi_bpp);
 	if (error)
 		return error;
 
@@ -389,7 +402,6 @@ xfs_iwalk_ag(
 	struct xfs_iwalk_ag		*iwag)
 {
 	struct xfs_mount		*mp = iwag->mp;
-	struct xfs_trans		*tp = iwag->tp;
 	struct xfs_buf			*agi_bp = NULL;
 	struct xfs_btree_cur		*cur = NULL;
 	xfs_agnumber_t			agno;
@@ -469,7 +481,7 @@ xfs_iwalk_ag(
 	error = xfs_iwalk_run_callbacks(iwag, agno, &cur, &agi_bp, &has_more);
 
 out:
-	xfs_iwalk_del_inobt(tp, &cur, &agi_bp, error);
+	xfs_iwalk_del_inobt(iwag->tp, &cur, &agi_bp, error);
 	return error;
 }
 
@@ -594,8 +606,18 @@ xfs_iwalk_ag_work(
 	error = xfs_iwalk_alloc(iwag);
 	if (error)
 		goto out;
+	/*
+	 * Grab an empty transaction so that we can use its recursive buffer
+	 * locking abilities to detect cycles in the inobt without deadlocking.
+	 */
+	error = xfs_trans_alloc_empty(mp, &iwag->tp);
+	if (error)
+		goto out;
+	iwag->drop_trans = 1;
 
 	error = xfs_iwalk_ag(iwag);
+	if (iwag->tp)
+		xfs_trans_cancel(iwag->tp);
 	xfs_iwalk_free(iwag);
 out:
 	kmem_free(iwag);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 52370d0a3f434..1c97b155a8ee7 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -635,6 +635,47 @@ xfs_check_summary_counts(
 }
 
 /*
+ * Flush and reclaim dirty inodes in preparation for unmount. Inodes and
+ * internal inode structures can be sitting in the CIL and AIL at this point,
+ * so we need to unpin them, write them back and/or reclaim them before unmount
+ * can proceed.
+ *
+ * An inode cluster that has been freed can have its buffer still pinned in
+ * memory because the transaction is still sitting in a iclog. The stale inodes
+ * on that buffer will be pinned to the buffer until the transaction hits the
+ * disk and the callbacks run. Pushing the AIL will skip the stale inodes and
+ * may never see the pinned buffer, so nothing will push out the iclog and
+ * unpin the buffer.
+ *
+ * Hence we need to force the log to unpin everything first. However, log
+ * forces don't wait for the discards they issue to complete, so we have to
+ * explicitly wait for them to complete here as well.
+ *
+ * Then we can tell the world we are unmounting so that error handling knows
+ * that the filesystem is going away and we should error out anything that we
+ * have been retrying in the background.  This will prevent never-ending
+ * retries in AIL pushing from hanging the unmount.
+ *
+ * Finally, we can push the AIL to clean all the remaining dirty objects, then
+ * reclaim the remaining inodes that are still in memory at this point in time.
+ */
+static void
+xfs_unmount_flush_inodes(
+	struct xfs_mount	*mp)
+{
+	xfs_log_force(mp, XFS_LOG_SYNC);
+	xfs_extent_busy_wait_all(mp);
+	flush_workqueue(xfs_discard_wq);
+
+	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
+
+	xfs_ail_push_all_sync(mp->m_ail);
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	xfs_reclaim_inodes(mp);
+	xfs_health_unmount(mp);
+}
+
+/*
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
  *	- if we're a 32-bit kernel, do a size check on the superblock
@@ -1008,7 +1049,7 @@ xfs_mountfs(
 	/* Clean out dquots that might be in memory after quotacheck. */
 	xfs_qm_unmount(mp);
 	/*
-	 * Cancel all delayed reclaim work and reclaim the inodes directly.
+	 * Flush all inode reclamation work and flush the log.
 	 * We have to do this /after/ rtunmount and qm_unmount because those
 	 * two will have scheduled delayed reclaim for the rt/quota inodes.
 	 *
@@ -1018,11 +1059,8 @@ xfs_mountfs(
 	 * qm_unmount_quotas and therefore rely on qm_unmount to release the
 	 * quota inodes.
 	 */
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	xfs_reclaim_inodes(mp);
-	xfs_health_unmount(mp);
+	xfs_unmount_flush_inodes(mp);
  out_log_dealloc:
-	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
 	xfs_log_mount_cancel(mp);
  out_fail_wait:
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
@@ -1063,47 +1101,7 @@ xfs_unmountfs(
 	xfs_rtunmount_inodes(mp);
 	xfs_irele(mp->m_rootip);
 
-	/*
-	 * We can potentially deadlock here if we have an inode cluster
-	 * that has been freed has its buffer still pinned in memory because
-	 * the transaction is still sitting in a iclog. The stale inodes
-	 * on that buffer will be pinned to the buffer until the
-	 * transaction hits the disk and the callbacks run. Pushing the AIL will
-	 * skip the stale inodes and may never see the pinned buffer, so
-	 * nothing will push out the iclog and unpin the buffer. Hence we
-	 * need to force the log here to ensure all items are flushed into the
-	 * AIL before we go any further.
-	 */
-	xfs_log_force(mp, XFS_LOG_SYNC);
-
-	/*
-	 * Wait for all busy extents to be freed, including completion of
-	 * any discard operation.
-	 */
-	xfs_extent_busy_wait_all(mp);
-	flush_workqueue(xfs_discard_wq);
-
-	/*
-	 * We now need to tell the world we are unmounting. This will allow
-	 * us to detect that the filesystem is going away and we should error
-	 * out anything that we have been retrying in the background. This will
-	 * prevent neverending retries in AIL pushing from hanging the unmount.
-	 */
-	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
-
-	/*
-	 * Flush all pending changes from the AIL.
-	 */
-	xfs_ail_push_all_sync(mp->m_ail);
-
-	/*
-	 * Reclaim all inodes. At this point there should be no dirty inodes and
-	 * none should be pinned or locked. Stop background inode reclaim here
-	 * if it is still running.
-	 */
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	xfs_reclaim_inodes(mp);
-	xfs_health_unmount(mp);
+	xfs_unmount_flush_inodes(mp);
 
 	xfs_qm_unmount(mp);
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 1379013d74b88..7f368b10ded1b 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -182,7 +182,8 @@ xfs_symlink(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
+	error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+			fsgid_into_mnt(mnt_userns), prid,
 			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
 			&udqp, &gdqp, &pdqp);
 	if (error)