1 files changed, 161 insertions, 100 deletions

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 5a0ce0c2c4bb..2277f21c4f14 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -31,7 +31,7 @@
 #include "xfs_reflink.h"
 #include "xfs_extent_busy.h"
 #include "xfs_health.h"
-
+#include "xfs_trace.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
 static int xfs_uuid_table_size;
@@ -365,66 +365,119 @@ release_buf:
 }
 
 /*
- * Update alignment values based on mount options and sb values
+ * If the sunit/swidth change would move the precomputed root inode value, we
+ * must reject the ondisk change because repair will stumble over that.
+ * However, we allow the mount to proceed because we never rejected this
+ * combination before.  Returns true to update the sb, false otherwise.
+ */
+static inline int
+xfs_check_new_dalign(
+	struct xfs_mount	*mp,
+	int			new_dalign,
+	bool			*update_sb)
+{
+	struct xfs_sb		*sbp = &mp->m_sb;
+	xfs_ino_t		calc_ino;
+
+	calc_ino = xfs_ialloc_calc_rootino(mp, new_dalign);
+	trace_xfs_check_new_dalign(mp, new_dalign, calc_ino);
+
+	if (sbp->sb_rootino == calc_ino) {
+		*update_sb = true;
+		return 0;
+	}
+
+	xfs_warn(mp,
+"Cannot change stripe alignment; would require moving root inode.");
+
+	/*
+	 * XXX: Next time we add a new incompat feature, this should start
+	 * returning -EINVAL to fail the mount.  Until then, spit out a warning
+	 * that we're ignoring the administrator's instructions.
+	 */
+	xfs_warn(mp, "Skipping superblock stripe alignment update.");
+	*update_sb = false;
+	return 0;
+}
+
+/*
+ * If we were provided with new sunit/swidth values as mount options, make sure
+ * that they pass basic alignment and superblock feature checks, and convert
+ * them into the same units (FSB) that everything else expects.  This step
+ * /must/ be done before computing the inode geometry.
  */
 STATIC int
-xfs_update_alignment(xfs_mount_t *mp)
+xfs_validate_new_dalign(
+	struct xfs_mount	*mp)
 {
-	xfs_sb_t	*sbp = &(mp->m_sb);
+	if (mp->m_dalign == 0)
+		return 0;
 
-	if (mp->m_dalign) {
+	/*
+	 * If stripe unit and stripe width are not multiples
+	 * of the fs blocksize turn off alignment.
+	 */
+	if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
+	    (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
+		xfs_warn(mp,
+	"alignment check failed: sunit/swidth vs. blocksize(%d)",
+			mp->m_sb.sb_blocksize);
+		return -EINVAL;
+	} else {
 		/*
-		 * If stripe unit and stripe width are not multiples
-		 * of the fs blocksize turn off alignment.
+		 * Convert the stripe unit and width to FSBs.
 		 */
-		if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
-		    (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
+		mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
+		if (mp->m_dalign && (mp->m_sb.sb_agblocks % mp->m_dalign)) {
 			xfs_warn(mp,
-		"alignment check failed: sunit/swidth vs. blocksize(%d)",
-				sbp->sb_blocksize);
+		"alignment check failed: sunit/swidth vs. agsize(%d)",
+				 mp->m_sb.sb_agblocks);
 			return -EINVAL;
-		} else {
-			/*
-			 * Convert the stripe unit and width to FSBs.
-			 */
-			mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
-			if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) {
-				xfs_warn(mp,
-			"alignment check failed: sunit/swidth vs. agsize(%d)",
-					 sbp->sb_agblocks);
-				return -EINVAL;
-			} else if (mp->m_dalign) {
-				mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
-			} else {
-				xfs_warn(mp,
-			"alignment check failed: sunit(%d) less than bsize(%d)",
-					 mp->m_dalign, sbp->sb_blocksize);
-				return -EINVAL;
-			}
-		}
-
-		/*
-		 * Update superblock with new values
-		 * and log changes
-		 */
-		if (xfs_sb_version_hasdalign(sbp)) {
-			if (sbp->sb_unit != mp->m_dalign) {
-				sbp->sb_unit = mp->m_dalign;
-				mp->m_update_sb = true;
-			}
-			if (sbp->sb_width != mp->m_swidth) {
-				sbp->sb_width = mp->m_swidth;
-				mp->m_update_sb = true;
-			}
+		} else if (mp->m_dalign) {
+			mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
 		} else {
 			xfs_warn(mp,
-	"cannot change alignment: superblock does not support data alignment");
+		"alignment check failed: sunit(%d) less than bsize(%d)",
+				 mp->m_dalign, mp->m_sb.sb_blocksize);
 			return -EINVAL;
 		}
+	}
+
+	if (!xfs_sb_version_hasdalign(&mp->m_sb)) {
+		xfs_warn(mp,
+"cannot change alignment: superblock does not support data alignment");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Update alignment values based on mount options and sb values. */
+STATIC int
+xfs_update_alignment(
+	struct xfs_mount	*mp)
+{
+	struct xfs_sb		*sbp = &mp->m_sb;
+
+	if (mp->m_dalign) {
+		bool		update_sb;
+		int		error;
+
+		if (sbp->sb_unit == mp->m_dalign &&
+		    sbp->sb_width == mp->m_swidth)
+			return 0;
+
+		error = xfs_check_new_dalign(mp, mp->m_dalign, &update_sb);
+		if (error || !update_sb)
+			return error;
+
+		sbp->sb_unit = mp->m_dalign;
+		sbp->sb_width = mp->m_swidth;
+		mp->m_update_sb = true;
 	} else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN &&
 		    xfs_sb_version_hasdalign(&mp->m_sb)) {
-			mp->m_dalign = sbp->sb_unit;
-			mp->m_swidth = sbp->sb_width;
+		mp->m_dalign = sbp->sb_unit;
+		mp->m_swidth = sbp->sb_width;
 	}
 
 	return 0;
@@ -622,6 +675,47 @@ 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, SYNC_WAIT);
+	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
@@ -692,12 +786,12 @@ xfs_mountfs(
 	}
 
 	/*
-	 * Check if sb_agblocks is aligned at stripe boundary
-	 * If sb_agblocks is NOT aligned turn off m_dalign since
-	 * allocator alignment is within an ag, therefore ag has
-	 * to be aligned at stripe boundary.
+	 * If we were given new sunit/swidth options, do some basic validation
+	 * checks and convert the incore dalign and swidth values to the
+	 * same units (FSB) that everything else uses.  This /must/ happen
+	 * before computing the inode geometry.
 	 */
-	error = xfs_update_alignment(mp);
+	error = xfs_validate_new_dalign(mp);
 	if (error)
 		goto out;
 
@@ -708,6 +802,17 @@ xfs_mountfs(
 	xfs_rmapbt_compute_maxlevels(mp);
 	xfs_refcountbt_compute_maxlevels(mp);
 
+	/*
+	 * Check if sb_agblocks is aligned at stripe boundary.  If sb_agblocks
+	 * is NOT aligned turn off m_dalign since allocator alignment is within
+	 * an ag, therefore ag has to be aligned at stripe boundary.  Note that
+	 * we must compute the free space and rmap btree geometry before doing
+	 * this.
+	 */
+	error = xfs_update_alignment(mp);
+	if (error)
+		goto out;
+
 	/* enable fail_at_unmount as default */
 	mp->m_fail_unmount = true;
 
@@ -983,7 +1088,7 @@ 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.
 	 *
@@ -993,11 +1098,8 @@ 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, SYNC_WAIT);
-	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)
@@ -1038,47 +1140,7 @@ 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 have their flush locks held until the
-	 * transaction hits the disk and the callbacks run. the inode
-	 * flush takes the flush lock unconditionally and with nothing to
-	 * push out the iclog we will never get that unlocked. hence we
-	 * need to force the log first.
-	 */
-	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);
-
-	/*
-	 * And reclaim all inodes.  At this point there should be no dirty
-	 * inodes and none should be pinned or locked, but use synchronous
-	 * reclaim just to be sure. We can stop background inode reclaim
-	 * here as well if it is still running.
-	 */
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	xfs_reclaim_inodes(mp, SYNC_WAIT);
-	xfs_health_unmount(mp);
+	xfs_unmount_flush_inodes(mp);
 
 	xfs_qm_unmount(mp);
 
@@ -1154,8 +1216,7 @@ xfs_fs_writable(
 int
 xfs_log_sbcount(xfs_mount_t *mp)
 {
-	/* allow this to proceed during the freeze sequence... */
-	if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE))
+	if (!xfs_log_writable(mp))
 		return 0;
 
 	/*