Merge tag 'xfs-5.8-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "Most of the changes this cycle are refactoring of existing code in
  preparation for things landing in the future.

  We also fixed various problems and deficiencies in the quota
  implementation, and (I hope) the last of the stale read vectors by
  forcing write allocations to go through the unwritten state until the
  write completes.

  Summary:

   - Various cleanups to remove dead code, unnecessary conditionals,
     asserts, etc.

   - Fix a linker warning caused by xfs stuffing '-g' into CFLAGS
     redundantly.

   - Tighten up our dmesg logging to ensure that everything is prefixed
     with 'XFS' for easier grepping.

   - Kill a bunch of typedefs.

   - Refactor the deferred ops code to reduce indirect function calls.

   - Increase type-safety with the deferred ops code.

   - Make the DAX mount options a tri-state.

   - Fix some error handling problems in the inode flush code and clean
     up other inode flush warts.

   - Refactor log recovery so that each log item recovery functions now
     live with the other log item processing code.

   - Fix some SPDX forms.

   - Fix quota counter corruption if the fs crashes after running
     quotacheck but before any dquots get logged.

   - Don't fail metadata verification on zero-entry attr leaf blocks,
     since they're just part of the disk format now due to a historic
     lack of log atomicity.

   - Don't allow SWAPEXT between files with different [ugp]id when
     quotas are enabled.

   - Refactor inode fork reading and verification to run directly from
     the inode-from-disk function. This means that we now actually
     guarantee that _iget'ted inodes are totally verified and ready to
     go.

   - Move the incore inode fork format and extent counts to the ifork
     structure.

   - Scalability improvements by reducing cacheline pingponging in
     struct xfs_mount.

   - More scalability improvements by removing m_active_trans from the
     hot path.

   - Fix inode counter update sanity checking to run /only/ on debug
     kernels.

   - Fix longstanding inconsistency in what error code we return when a
     program hits project quota limits (ENOSPC).

   - Fix group quota returning the wrong error code when a program hits
     group quota limits.

   - Fix per-type quota limits and grace periods for group and project
     quotas so that they actually work.

   - Allow extension of individual grace periods.

   - Refactor the non-reclaim inode radix tree walking code to remove a
     bunch of stupid little functions and straighten out the
     inconsistent naming schemes.

   - Fix a bug in speculative preallocation where we measured a new
     allocation based on the last extent mapping in the file instead of
     looking farther for the last contiguous space allocation.

   - Force delalloc writes to unwritten extents. This closes a stale
     disk contents exposure vector if the system goes down before the
     write completes.

   - More lockdep whackamole"

* tag 'xfs-5.8-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (129 commits)
  xfs: more lockdep whackamole with kmem_alloc*
  xfs: force writes to delalloc regions to unwritten
  xfs: refactor xfs_iomap_prealloc_size
  xfs: measure all contiguous previous extents for prealloc size
  xfs: don't fail unwritten extent conversion on writeback due to edquot
  xfs: rearrange xfs_inode_walk_ag parameters
  xfs: straighten out all the naming around incore inode tree walks
  xfs: move xfs_inode_ag_iterator to be closer to the perag walking code
  xfs: use bool for done in xfs_inode_ag_walk
  xfs: fix inode ag walk predicate function return values
  xfs: refactor eofb matching into a single helper
  xfs: remove __xfs_icache_free_eofblocks
  xfs: remove flags argument from xfs_inode_ag_walk
  xfs: remove xfs_inode_ag_iterator_flags
  xfs: remove unused xfs_inode_ag_iterator function
  xfs: replace open-coded XFS_ICI_NO_TAG
  xfs: move eofblocks conversion function to xfs_ioctl.c
  xfs: allow individual quota grace period extension
  xfs: per-type quota timers and warn limits
  xfs: switch xfs_get_defquota to take explicit type
  ...

1 files changed, 55 insertions, 15 deletions

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 65538d18e64f..20b748f7e186 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1197,8 +1197,10 @@ xfs_buf_ioend(
 		bp->b_ops->verify_read(bp);
 	}
 
-	if (!bp->b_error)
+	if (!bp->b_error) {
+		bp->b_flags &= ~XBF_WRITE_FAIL;
 		bp->b_flags |= XBF_DONE;
+	}
 
 	if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
@@ -1242,10 +1244,26 @@ xfs_buf_ioerror_alert(
 	struct xfs_buf		*bp,
 	xfs_failaddr_t		func)
 {
-	xfs_alert_ratelimited(bp->b_mount,
-"metadata I/O error in \"%pS\" at daddr 0x%llx len %d error %d",
-			func, (uint64_t)XFS_BUF_ADDR(bp), bp->b_length,
-			-bp->b_error);
+	xfs_buf_alert_ratelimited(bp, "XFS: metadata IO error",
+		"metadata I/O error in \"%pS\" at daddr 0x%llx len %d error %d",
+				  func, (uint64_t)XFS_BUF_ADDR(bp),
+				  bp->b_length, -bp->b_error);
+}
+
+/*
+ * To simulate an I/O failure, the buffer must be locked and held with at least
+ * three references. The LRU reference is dropped by the stale call. The buf
+ * item reference is dropped via ioend processing. The third reference is owned
+ * by the caller and is dropped on I/O completion if the buffer is XBF_ASYNC.
+ */
+void
+xfs_buf_ioend_fail(
+	struct xfs_buf	*bp)
+{
+	bp->b_flags &= ~XBF_DONE;
+	xfs_buf_stale(bp);
+	xfs_buf_ioerror(bp, -EIO);
+	xfs_buf_ioend(bp);
 }
 
 int
@@ -1258,7 +1276,7 @@ xfs_bwrite(
 
 	bp->b_flags |= XBF_WRITE;
 	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
-			 XBF_WRITE_FAIL | XBF_DONE);
+			 XBF_DONE);
 
 	error = xfs_buf_submit(bp);
 	if (error)
@@ -1272,6 +1290,11 @@ xfs_buf_bio_end_io(
 {
 	struct xfs_buf		*bp = (struct xfs_buf *)bio->bi_private;
 
+	if (!bio->bi_status &&
+	    (bp->b_flags & XBF_WRITE) && (bp->b_flags & XBF_ASYNC) &&
+	    XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR))
+		bio->bi_status = BLK_STS_IOERR;
+
 	/*
 	 * don't overwrite existing errors - otherwise we can lose errors on
 	 * buffers that require multiple bios to complete.
@@ -1480,10 +1503,7 @@ __xfs_buf_submit(
 
 	/* on shutdown we stale and complete the buffer immediately */
 	if (XFS_FORCED_SHUTDOWN(bp->b_mount)) {
-		xfs_buf_ioerror(bp, -EIO);
-		bp->b_flags &= ~XBF_DONE;
-		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp);
+		xfs_buf_ioend_fail(bp);
 		return -EIO;
 	}
 
@@ -1642,7 +1662,8 @@ xfs_wait_buftarg(
 	struct xfs_buftarg	*btp)
 {
 	LIST_HEAD(dispose);
-	int loop = 0;
+	int			loop = 0;
+	bool			write_fail = false;
 
 	/*
 	 * First wait on the buftarg I/O count for all in-flight buffers to be
@@ -1670,17 +1691,29 @@ xfs_wait_buftarg(
 			bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
 			list_del_init(&bp->b_lru);
 			if (bp->b_flags & XBF_WRITE_FAIL) {
-				xfs_alert(btp->bt_mount,
+				write_fail = true;
+				xfs_buf_alert_ratelimited(bp,
+					"XFS: Corruption Alert",
 "Corruption Alert: Buffer at daddr 0x%llx had permanent write failures!",
 					(long long)bp->b_bn);
-				xfs_alert(btp->bt_mount,
-"Please run xfs_repair to determine the extent of the problem.");
 			}
 			xfs_buf_rele(bp);
 		}
 		if (loop++ != 0)
 			delay(100);
 	}
+
+	/*
+	 * If one or more failed buffers were freed, that means dirty metadata
+	 * was thrown away. This should only ever happen after I/O completion
+	 * handling has elevated I/O error(s) to permanent failures and shuts
+	 * down the fs.
+	 */
+	if (write_fail) {
+		ASSERT(XFS_FORCED_SHUTDOWN(btp->bt_mount));
+		xfs_alert(btp->bt_mount,
+	      "Please run xfs_repair to determine the extent of the problem.");
+	}
 }
 
 static enum lru_status
@@ -1813,6 +1846,13 @@ xfs_alloc_buftarg(
 	btp->bt_bdev = bdev;
 	btp->bt_daxdev = dax_dev;
 
+	/*
+	 * Buffer IO error rate limiting. Limit it to no more than 10 messages
+	 * per 30 seconds so as to not spam logs too much on repeated errors.
+	 */
+	ratelimit_state_init(&btp->bt_ioerror_rl, 30 * HZ,
+			     DEFAULT_RATELIMIT_BURST);
+
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error_free;
 
@@ -1983,7 +2023,7 @@ xfs_buf_delwri_submit_buffers(
 		 * synchronously. Otherwise, drop the buffer from the delwri
 		 * queue and submit async.
 		 */
-		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
+		bp->b_flags &= ~_XBF_DELWRI_Q;
 		bp->b_flags |= XBF_WRITE;
 		if (wait_list) {
 			bp->b_flags &= ~XBF_ASYNC;