From 7912e7fef2aebe577f0b46d3cba261f2783c5695 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:21:45 -0700
Subject: [PATCH 01/48] xfs: push buffer of flush locked dquot to avoid
 quotacheck deadlock

Reclaim during quotacheck can lead to deadlocks on the dquot flush
lock:

 - Quotacheck populates a local delwri queue with the physical dquot
   buffers.
 - Quotacheck performs the xfs_qm_dqusage_adjust() bulkstat and
   dirties all of the dquots.
 - Reclaim kicks in and attempts to flush a dquot whose buffer is
   already queud on the quotacheck queue. The flush succeeds but
   queueing to the reclaim delwri queue fails as the backing buffer is
   already queued. The flush unlock is now deferred to I/O completion
   of the buffer from the quotacheck queue.
 - The dqadjust bulkstat continues and dirties the recently flushed
   dquot once again.
 - Quotacheck proceeds to the xfs_qm_flush_one() walk which requires
   the flush lock to update the backing buffers with the in-core
   recalculated values. It deadlocks on the redirtied dquot as the
   flush lock was already acquired by reclaim, but the buffer resides
   on the local delwri queue which isn't submitted until the end of
   quotacheck.

This is reproduced by running quotacheck on a filesystem with a
couple million inodes in low memory (512MB-1GB) situations. This is
a regression as of commit 43ff2122e6 ("xfs: on-stack delayed write
buffer lists"), which removed a trylock and buffer I/O submission
from the quotacheck dquot flush sequence.

Quotacheck first resets and collects the physical dquot buffers in a
delwri queue. Then, it traverses the filesystem inodes via bulkstat,
updates the in-core dquots, flushes the corrected dquots to the
backing buffers and finally submits the delwri queue for I/O. Since
the backing buffers are queued across the entire quotacheck
operation, dquot reclaim cannot possibly complete a dquot flush
before quotacheck completes.

Therefore, quotacheck must submit the buffer for I/O in order to
cycle the flush lock and flush the dirty in-core dquot to the
buffer. Add a delwri queue buffer push mechanism to submit an
individual buffer for I/O without losing the delwri queue status and
use it from quotacheck to avoid the deadlock. This restores
quotacheck behavior to as before the regression was introduced.

Reported-by: Martin Svec <martin.svec@zoner.cz>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_buf.c   | 60 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_buf.h   |  1 +
 fs/xfs/xfs_qm.c    | 28 +++++++++++++++++++++-
 fs/xfs/xfs_trace.h |  1 +
 4 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 16d6a578fc16..a9640b136b32 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2047,6 +2047,66 @@ xfs_buf_delwri_submit(
 	return error;
 }
 
+/*
+ * Push a single buffer on a delwri queue.
+ *
+ * The purpose of this function is to submit a single buffer of a delwri queue
+ * and return with the buffer still on the original queue. The waiting delwri
+ * buffer submission infrastructure guarantees transfer of the delwri queue
+ * buffer reference to a temporary wait list. We reuse this infrastructure to
+ * transfer the buffer back to the original queue.
+ *
+ * Note the buffer transitions from the queued state, to the submitted and wait
+ * listed state and back to the queued state during this call. The buffer
+ * locking and queue management logic between _delwri_pushbuf() and
+ * _delwri_queue() guarantee that the buffer cannot be queued to another list
+ * before returning.
+ */
+int
+xfs_buf_delwri_pushbuf(
+	struct xfs_buf		*bp,
+	struct list_head	*buffer_list)
+{
+	LIST_HEAD		(submit_list);
+	int			error;
+
+	ASSERT(bp->b_flags & _XBF_DELWRI_Q);
+
+	trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_);
+
+	/*
+	 * Isolate the buffer to a new local list so we can submit it for I/O
+	 * independently from the rest of the original list.
+	 */
+	xfs_buf_lock(bp);
+	list_move(&bp->b_list, &submit_list);
+	xfs_buf_unlock(bp);
+
+	/*
+	 * Delwri submission clears the DELWRI_Q buffer flag and returns with
+	 * the buffer on the wait list with an associated reference. Rather than
+	 * bounce the buffer from a local wait list back to the original list
+	 * after I/O completion, reuse the original list as the wait list.
+	 */
+	xfs_buf_delwri_submit_buffers(&submit_list, buffer_list);
+
+	/*
+	 * The buffer is now under I/O and wait listed as during typical delwri
+	 * submission. Lock the buffer to wait for I/O completion. Rather than
+	 * remove the buffer from the wait list and release the reference, we
+	 * want to return with the buffer queued to the original list. The
+	 * buffer already sits on the original list with a wait list reference,
+	 * however. If we let the queue inherit that wait list reference, all we
+	 * need to do is reset the DELWRI_Q flag.
+	 */
+	xfs_buf_lock(bp);
+	error = bp->b_error;
+	bp->b_flags |= _XBF_DELWRI_Q;
+	xfs_buf_unlock(bp);
+
+	return error;
+}
+
 int __init
 xfs_buf_init(void)
 {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 1508121f29f2..20721261dae5 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -332,6 +332,7 @@ extern void xfs_buf_delwri_cancel(struct list_head *);
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
+extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
 
 /* Buffer Daemon Setup Routines */
 extern int xfs_buf_init(void);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 5fe6e70b88ef..6ce948c436d5 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1247,6 +1247,7 @@ xfs_qm_flush_one(
 	struct xfs_dquot	*dqp,
 	void			*data)
 {
+	struct xfs_mount	*mp = dqp->q_mount;
 	struct list_head	*buffer_list = data;
 	struct xfs_buf		*bp = NULL;
 	int			error = 0;
@@ -1257,7 +1258,32 @@ xfs_qm_flush_one(
 	if (!XFS_DQ_IS_DIRTY(dqp))
 		goto out_unlock;
 
-	xfs_dqflock(dqp);
+	/*
+	 * The only way the dquot is already flush locked by the time quotacheck
+	 * gets here is if reclaim flushed it before the dqadjust walk dirtied
+	 * it for the final time. Quotacheck collects all dquot bufs in the
+	 * local delwri queue before dquots are dirtied, so reclaim can't have
+	 * possibly queued it for I/O. The only way out is to push the buffer to
+	 * cycle the flush lock.
+	 */
+	if (!xfs_dqflock_nowait(dqp)) {
+		/* buf is pinned in-core by delwri list */
+		DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno,
+				      mp->m_quotainfo->qi_dqchunklen);
+		bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL);
+		if (!bp) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+		xfs_buf_unlock(bp);
+
+		xfs_buf_delwri_pushbuf(bp, buffer_list);
+		xfs_buf_rele(bp);
+
+		error = -EAGAIN;
+		goto out_unlock;
+	}
+
 	error = xfs_qm_dqflush(dqp, &bp);
 	if (error)
 		goto out_unlock;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 7c5a16528d8b..306d89c55267 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -367,6 +367,7 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
 DEFINE_BUF_EVENT(xfs_buf_delwri_split);
+DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf);
 DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_buf_item_relse);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone_async);

From d205a7d0ec47d11977882b5e910ad35f7be912b4 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 14 Jun 2017 21:23:05 -0700
Subject: [PATCH 02/48] xfs: refactor dir2 leaf readahead shadow buffer
 cleverness

Currently, the dir2 leaf block getdents function uses a complex state
tracking mechanism to create a shadow copy of the block mappings and
then uses the shadow copy to schedule readahead.  Since the read and
readahead functions are perfectly capable of reading the mappings
themselves, we can tear all that out in favor of a simpler function that
simply keeps pushing the readahead window further out.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_dir2_readdir.c | 318 ++++++++++----------------------------
 1 file changed, 84 insertions(+), 234 deletions(-)

diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 20b7a5c6eb2f..1bc7401ea1b2 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -243,214 +243,100 @@ xfs_dir2_block_getdents(
 	return 0;
 }
 
-struct xfs_dir2_leaf_map_info {
-	xfs_extlen_t	map_blocks;	/* number of fsbs in map */
-	xfs_dablk_t	map_off;	/* last mapped file offset */
-	int		map_size;	/* total entries in *map */
-	int		map_valid;	/* valid entries in *map */
-	int		nmap;		/* mappings to ask xfs_bmapi */
-	xfs_dir2_db_t	curdb;		/* db for current block */
-	int		ra_current;	/* number of read-ahead blks */
-	int		ra_index;	/* *map index for read-ahead */
-	int		ra_offset;	/* map entry offset for ra */
-	int		ra_want;	/* readahead count wanted */
-	struct xfs_bmbt_irec map[];	/* map vector for blocks */
-};
-
+/*
+ * Read a directory block and initiate readahead for blocks beyond that.
+ * We maintain a sliding readahead window of the remaining space in the
+ * buffer rounded up to the nearest block.
+ */
 STATIC int
 xfs_dir2_leaf_readbuf(
 	struct xfs_da_args	*args,
 	size_t			bufsize,
-	struct xfs_dir2_leaf_map_info *mip,
-	xfs_dir2_off_t		*curoff,
-	struct xfs_buf		**bpp,
-	bool			trim_map)
+	xfs_dir2_off_t		*cur_off,
+	xfs_dablk_t		*ra_blk,
+	struct xfs_buf		**bpp)
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_buf		*bp = NULL;
-	struct xfs_bmbt_irec	*map = mip->map;
-	struct blk_plug		plug;
-	int			error = 0;
-	int			length;
-	int			i;
-	int			j;
 	struct xfs_da_geometry	*geo = args->geo;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
+	struct xfs_bmbt_irec	map;
+	struct blk_plug		plug;
+	xfs_dir2_off_t		new_off;
+	xfs_dablk_t		next_ra;
+	xfs_dablk_t		map_off;
+	xfs_dablk_t		last_da;
+	xfs_extnum_t		idx;
+	int			ra_want;
+	int			error = 0;
 
-	/*
-	 * If the caller just finished processing a buffer, it will tell us
-	 * we need to trim that block out of the mapping now it is done.
-	 */
-	if (trim_map) {
-		mip->map_blocks -= geo->fsbcount;
-		/*
-		 * Loop to get rid of the extents for the
-		 * directory block.
-		 */
-		for (i = geo->fsbcount; i > 0; ) {
-			j = min_t(int, map->br_blockcount, i);
-			map->br_blockcount -= j;
-			map->br_startblock += j;
-			map->br_startoff += j;
-			/*
-			 * If mapping is done, pitch it from
-			 * the table.
-			 */
-			if (!map->br_blockcount && --mip->map_valid)
-				memmove(&map[0], &map[1],
-					sizeof(map[0]) * mip->map_valid);
-			i -= j;
-		}
-	}
-
-	/*
-	 * Recalculate the readahead blocks wanted.
-	 */
-	mip->ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog)) - 1;
-	ASSERT(mip->ra_want >= 0);
-
-	/*
-	 * If we don't have as many as we want, and we haven't
-	 * run out of data blocks, get some more mappings.
-	 */
-	if (1 + mip->ra_want > mip->map_blocks &&
-	    mip->map_off < xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET)) {
-		/*
-		 * Get more bmaps, fill in after the ones
-		 * we already have in the table.
-		 */
-		mip->nmap = mip->map_size - mip->map_valid;
-		error = xfs_bmapi_read(dp, mip->map_off,
-				xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET) -
-								mip->map_off,
-				&map[mip->map_valid], &mip->nmap, 0);
-
-		/*
-		 * Don't know if we should ignore this or try to return an
-		 * error.  The trouble with returning errors is that readdir
-		 * will just stop without actually passing the error through.
-		 */
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK);
 		if (error)
-			goto out;	/* XXX */
-
-		/*
-		 * If we got all the mappings we asked for, set the final map
-		 * offset based on the last bmap value received.  Otherwise,
-		 * we've reached the end.
-		 */
-		if (mip->nmap == mip->map_size - mip->map_valid) {
-			i = mip->map_valid + mip->nmap - 1;
-			mip->map_off = map[i].br_startoff + map[i].br_blockcount;
-		} else
-			mip->map_off = xfs_dir2_byte_to_da(geo,
-							XFS_DIR2_LEAF_OFFSET);
-
-		/*
-		 * Look for holes in the mapping, and eliminate them.  Count up
-		 * the valid blocks.
-		 */
-		for (i = mip->map_valid; i < mip->map_valid + mip->nmap; ) {
-			if (map[i].br_startblock == HOLESTARTBLOCK) {
-				mip->nmap--;
-				length = mip->map_valid + mip->nmap - i;
-				if (length)
-					memmove(&map[i], &map[i + 1],
-						sizeof(map[i]) * length);
-			} else {
-				mip->map_blocks += map[i].br_blockcount;
-				i++;
-			}
-		}
-		mip->map_valid += mip->nmap;
+			goto out;
 	}
 
 	/*
-	 * No valid mappings, so no more data blocks.
+	 * Look for mapped directory blocks at or above the current offset.
+	 * Truncate down to the nearest directory block to start the scanning
+	 * operation.
 	 */
-	if (!mip->map_valid) {
-		*curoff = xfs_dir2_da_to_byte(geo, mip->map_off);
+	last_da = xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET);
+	map_off = xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, *cur_off));
+	if (!xfs_iext_lookup_extent(dp, ifp, map_off, &idx, &map))
 		goto out;
-	}
+	if (map.br_startoff >= last_da)
+		goto out;
+	xfs_trim_extent(&map, map_off, last_da - map_off);
 
-	/*
-	 * Read the directory block starting at the first mapping.
-	 */
-	mip->curdb = xfs_dir2_da_to_db(geo, map->br_startoff);
-	error = xfs_dir3_data_read(NULL, dp, map->br_startoff,
-			map->br_blockcount >= geo->fsbcount ?
-			    XFS_FSB_TO_DADDR(dp->i_mount, map->br_startblock) :
-			    -1, &bp);
-	/*
-	 * Should just skip over the data block instead of giving up.
-	 */
+	/* Read the directory block of that first mapping. */
+	new_off = xfs_dir2_da_to_byte(geo, map.br_startoff);
+	if (new_off > *cur_off)
+		*cur_off = new_off;
+	error = xfs_dir3_data_read(args->trans, dp, map.br_startoff, -1, &bp);
 	if (error)
-		goto out;	/* XXX */
+		goto out;
 
 	/*
-	 * Adjust the current amount of read-ahead: we just read a block that
-	 * was previously ra.
+	 * Start readahead for the next bufsize's worth of dir data blocks.
+	 * We may have already issued readahead for some of that range;
+	 * ra_blk tracks the last block we tried to read(ahead).
 	 */
-	if (mip->ra_current)
-		mip->ra_current -= geo->fsbcount;
+	ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
+	if (*ra_blk >= last_da)
+		goto out;
+	else if (*ra_blk == 0)
+		*ra_blk = map.br_startoff;
+	next_ra = map.br_startoff + geo->fsbcount;
+	if (next_ra >= last_da)
+		goto out_no_ra;
+	if (map.br_blockcount < geo->fsbcount &&
+	    !xfs_iext_get_extent(ifp, ++idx, &map))
+		goto out_no_ra;
+	if (map.br_startoff >= last_da)
+		goto out_no_ra;
+	xfs_trim_extent(&map, next_ra, last_da - next_ra);
 
-	/*
-	 * Do we need more readahead?
-	 * Each loop tries to process 1 full dir blk; last may be partial.
-	 */
+	/* Start ra for each dir (not fs) block that has a mapping. */
 	blk_start_plug(&plug);
-	for (mip->ra_index = mip->ra_offset = i = 0;
-	     mip->ra_want > mip->ra_current && i < mip->map_blocks;
-	     i += geo->fsbcount) {
-		ASSERT(mip->ra_index < mip->map_valid);
-		/*
-		 * Read-ahead a contiguous directory block.
-		 */
-		if (i > mip->ra_current &&
-		    (map[mip->ra_index].br_blockcount - mip->ra_offset) >=
-		    geo->fsbcount) {
-			xfs_dir3_data_readahead(dp,
-				map[mip->ra_index].br_startoff + mip->ra_offset,
-				XFS_FSB_TO_DADDR(dp->i_mount,
-					map[mip->ra_index].br_startblock +
-							mip->ra_offset));
-			mip->ra_current = i;
-		}
-
-		/*
-		 * Read-ahead a non-contiguous directory block.  This doesn't
-		 * use our mapping, but this is a very rare case.
-		 */
-		else if (i > mip->ra_current) {
-			xfs_dir3_data_readahead(dp,
-					map[mip->ra_index].br_startoff +
-							mip->ra_offset, -1);
-			mip->ra_current = i;
-		}
-
-		/*
-		 * Advance offset through the mapping table, processing a full
-		 * dir block even if it is fragmented into several extents.
-		 * But stop if we have consumed all valid mappings, even if
-		 * it's not yet a full directory block.
-		 */
-		for (j = 0;
-		     j < geo->fsbcount && mip->ra_index < mip->map_valid;
-		     j += length ) {
-			/*
-			 * The rest of this extent but not more than a dir
-			 * block.
-			 */
-			length = min_t(int, geo->fsbcount - j,
-					map[mip->ra_index].br_blockcount -
-							mip->ra_offset);
-			mip->ra_offset += length;
-
-			/*
-			 * Advance to the next mapping if this one is used up.
-			 */
-			if (mip->ra_offset == map[mip->ra_index].br_blockcount) {
-				mip->ra_offset = 0;
-				mip->ra_index++;
+	while (ra_want > 0) {
+		next_ra = roundup((xfs_dablk_t)map.br_startoff, geo->fsbcount);
+		while (ra_want > 0 &&
+		       next_ra < map.br_startoff + map.br_blockcount) {
+			if (next_ra >= last_da) {
+				*ra_blk = last_da;
+				break;
 			}
+			if (next_ra > *ra_blk) {
+				xfs_dir3_data_readahead(dp, next_ra, -2);
+				*ra_blk = next_ra;
+			}
+			ra_want -= geo->fsbcount;
+			next_ra += geo->fsbcount;
+		}
+		if (!xfs_iext_get_extent(ifp, ++idx, &map)) {
+			*ra_blk = last_da;
+			break;
 		}
 	}
 	blk_finish_plug(&plug);
@@ -458,6 +344,9 @@ xfs_dir2_leaf_readbuf(
 out:
 	*bpp = bp;
 	return error;
+out_no_ra:
+	*ra_blk = last_da;
+	goto out;
 }
 
 /*
@@ -475,14 +364,14 @@ xfs_dir2_leaf_getdents(
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry */
-	int			error = 0;	/* error return value */
+	char			*ptr = NULL;	/* pointer to current data */
+	struct xfs_da_geometry	*geo = args->geo;
+	xfs_dablk_t		rablk = 0;	/* current readahead block */
+	xfs_dir2_off_t		curoff;		/* current overall offset */
 	int			length;		/* temporary length value */
 	int			byteoff;	/* offset in current block */
-	xfs_dir2_off_t		curoff;		/* current overall offset */
-	xfs_dir2_off_t		newoff;		/* new curoff after new blk */
-	char			*ptr = NULL;	/* pointer to current data */
-	struct xfs_dir2_leaf_map_info *map_info;
-	struct xfs_da_geometry	*geo = args->geo;
+	int			lock_mode;
+	int			error = 0;	/* error return value */
 
 	/*
 	 * If the offset is at or past the largest allowed value,
@@ -491,30 +380,12 @@ xfs_dir2_leaf_getdents(
 	if (ctx->pos >= XFS_DIR2_MAX_DATAPTR)
 		return 0;
 
-	/*
-	 * Set up to bmap a number of blocks based on the caller's
-	 * buffer size, the directory block size, and the filesystem
-	 * block size.
-	 */
-	length = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
-	map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) +
-				(length * sizeof(struct xfs_bmbt_irec)),
-			       KM_SLEEP | KM_NOFS);
-	map_info->map_size = length;
-
 	/*
 	 * Inside the loop we keep the main offset value as a byte offset
 	 * in the directory file.
 	 */
 	curoff = xfs_dir2_dataptr_to_byte(ctx->pos);
 
-	/*
-	 * Force this conversion through db so we truncate the offset
-	 * down to get the start of the data block.
-	 */
-	map_info->map_off = xfs_dir2_db_to_da(geo,
-					      xfs_dir2_byte_to_db(geo, curoff));
-
 	/*
 	 * Loop over directory entries until we reach the end offset.
 	 * Get more blocks and readahead as necessary.
@@ -527,38 +398,18 @@ xfs_dir2_leaf_getdents(
 		 * current buffer, need to get another one.
 		 */
 		if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) {
-			int	lock_mode;
-			bool	trim_map = false;
-
 			if (bp) {
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(args->trans, bp);
 				bp = NULL;
-				trim_map = true;
 			}
 
 			lock_mode = xfs_ilock_data_map_shared(dp);
-			error = xfs_dir2_leaf_readbuf(args, bufsize, map_info,
-						      &curoff, &bp, trim_map);
+			error = xfs_dir2_leaf_readbuf(args, bufsize, &curoff,
+					&rablk, &bp);
 			xfs_iunlock(dp, lock_mode);
-			if (error || !map_info->map_valid)
+			if (error || !bp)
 				break;
 
-			/*
-			 * Having done a read, we need to set a new offset.
-			 */
-			newoff = xfs_dir2_db_off_to_byte(geo,
-							 map_info->curdb, 0);
-			/*
-			 * Start of the current block.
-			 */
-			if (curoff < newoff)
-				curoff = newoff;
-			/*
-			 * Make sure we're in the right block.
-			 */
-			else if (curoff > newoff)
-				ASSERT(xfs_dir2_byte_to_db(geo, curoff) ==
-				       map_info->curdb);
 			hdr = bp->b_addr;
 			xfs_dir3_data_check(dp, bp);
 			/*
@@ -643,7 +494,6 @@ xfs_dir2_leaf_getdents(
 		ctx->pos = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
 	else
 		ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
-	kmem_free(map_info);
 	if (bp)
 		xfs_trans_brelse(NULL, bp);
 	return error;

From e1a4e37cc7b665b6804fba812aca2f4d7402c249 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 14 Jun 2017 21:25:57 -0700
Subject: [PATCH 03/48] xfs: try to avoid blowing out the transaction
 reservation when bunmaping a shared extent

In a pathological scenario where we are trying to bunmapi a single
extent in which every other block is shared, it's possible that trying
to unmap the entire large extent in a single transaction can generate so
many EFIs that we overflow the transaction reservation.

Therefore, use a heuristic to guess at the number of blocks we can
safely unmap from a reflink file's data fork in an single transaction.
This should prevent problems such as the log head slamming into the tail
and ASSERTs that trigger because we've exceeded the transaction
reservation.

Note that since bunmapi can fail to unmap the entire range, we must also
teach the deferred unmap code to roll into a new transaction whenever we
get low on reservation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
[hch: random edits, all bugs are my fault]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_bmap.c     | 38 ++++++++++++++++++++++++++++--------
 fs/xfs/libxfs/xfs_bmap.h     |  2 +-
 fs/xfs/libxfs/xfs_refcount.c | 10 +---------
 fs/xfs/libxfs/xfs_refcount.h | 16 +++++++++++++++
 fs/xfs/xfs_bmap_item.c       | 17 ++++++++++++++--
 fs/xfs/xfs_trans.h           |  2 +-
 fs/xfs/xfs_trans_bmap.c      | 11 +++++++++--
 7 files changed, 73 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a7048eafa8e6..19480ed231a4 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5434,6 +5434,7 @@ __xfs_bunmapi(
 	int			whichfork;	/* data or attribute fork */
 	xfs_fsblock_t		sum;
 	xfs_filblks_t		len = *rlen;	/* length to unmap in file */
+	xfs_fileoff_t		max_len;
 
 	trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_);
 
@@ -5455,6 +5456,16 @@ __xfs_bunmapi(
 	ASSERT(len > 0);
 	ASSERT(nexts >= 0);
 
+	/*
+	 * Guesstimate how many blocks we can unmap without running the risk of
+	 * blowing out the transaction with a mix of EFIs and reflink
+	 * adjustments.
+	 */
+	if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
+		max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res));
+	else
+		max_len = len;
+
 	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
 	    (error = xfs_iread_extents(tp, ip, whichfork)))
 		return error;
@@ -5499,7 +5510,7 @@ __xfs_bunmapi(
 
 	extno = 0;
 	while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 &&
-	       (nexts == 0 || extno < nexts)) {
+	       (nexts == 0 || extno < nexts) && max_len > 0) {
 		/*
 		 * Is the found extent after a hole in which bno lives?
 		 * Just back up to the previous extent, if so.
@@ -5531,6 +5542,15 @@ __xfs_bunmapi(
 		}
 		if (del.br_startoff + del.br_blockcount > bno + 1)
 			del.br_blockcount = bno + 1 - del.br_startoff;
+
+		/* How much can we safely unmap? */
+		if (max_len < del.br_blockcount) {
+			del.br_startoff += del.br_blockcount - max_len;
+			if (!wasdel)
+				del.br_startblock += del.br_blockcount - max_len;
+			del.br_blockcount = max_len;
+		}
+
 		sum = del.br_startblock + del.br_blockcount;
 		if (isrt &&
 		    (mod = do_mod(sum, mp->m_sb.sb_rextsize))) {
@@ -5707,6 +5727,7 @@ __xfs_bunmapi(
 		if (!isrt && wasdel)
 			xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false);
 
+		max_len -= del.br_blockcount;
 		bno = del.br_startoff - 1;
 nodelete:
 		/*
@@ -6472,15 +6493,16 @@ xfs_bmap_finish_one(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
-	int				error = 0, done;
+	xfs_fsblock_t			firstfsb;
+	int				error = 0;
 
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
 			XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
-			ip->i_ino, whichfork, startoff, blockcount, state);
+			ip->i_ino, whichfork, startoff, *blockcount, state);
 
 	if (WARN_ON_ONCE(whichfork != XFS_DATA_FORK))
 		return -EFSCORRUPTED;
@@ -6492,13 +6514,13 @@ xfs_bmap_finish_one(
 
 	switch (type) {
 	case XFS_BMAP_MAP:
-		error = xfs_bmapi_remap(tp, ip, startoff, blockcount,
+		error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
 				startblock, dfops);
+		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
-		error = xfs_bunmapi(tp, ip, startoff, blockcount,
-				XFS_BMAPI_REMAP, 1, &startblock, dfops, &done);
-		ASSERT(done);
+		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
+				XFS_BMAPI_REMAP, 1, &firstfsb, dfops);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index c35a14fa1527..851982a5dfbc 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -271,7 +271,7 @@ struct xfs_bmap_intent {
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, enum xfs_bmap_intent_type type,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
 int	xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 82a38d86ebad..e17016163542 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -784,14 +784,6 @@ xfs_refcount_merge_extents(
 }
 
 /*
- * While we're adjusting the refcounts records of an extent, we have
- * to keep an eye on the number of extents we're dirtying -- run too
- * many in a single transaction and we'll exceed the transaction's
- * reservation and crash the fs.  Each record adds 12 bytes to the
- * log (plus any key updates) so we'll conservatively assume 24 bytes
- * per record.  We must also leave space for btree splits on both ends
- * of the range and space for the CUD and a new CUI.
- *
  * XXX: This is a pretty hand-wavy estimate.  The penalty for guessing
  * true incorrectly is a shutdown FS; the penalty for guessing false
  * incorrectly is more transaction rolls than might be necessary.
@@ -822,7 +814,7 @@ xfs_refcount_still_have_space(
 	else if (overhead > cur->bc_tp->t_log_res)
 		return false;
 	return  cur->bc_tp->t_log_res - overhead >
-		cur->bc_private.a.priv.refc.nr_ops * 32;
+		cur->bc_private.a.priv.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 098dc668ab2c..eafb9d1f3b37 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -67,4 +67,20 @@ extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp,
 extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 		xfs_agnumber_t agno);
 
+/*
+ * While we're adjusting the refcounts records of an extent, we have
+ * to keep an eye on the number of extents we're dirtying -- run too
+ * many in a single transaction and we'll exceed the transaction's
+ * reservation and crash the fs.  Each record adds 12 bytes to the
+ * log (plus any key updates) so we'll conservatively assume 32 bytes
+ * per record.  We must also leave space for btree splits on both ends
+ * of the range and space for the CUD and a new CUI.
+ */
+#define XFS_REFCOUNT_ITEM_OVERHEAD	32
+
+static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
+{
+	return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
+}
+
 #endif	/* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index d419d23fa214..88073910fa5d 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -396,6 +396,7 @@ xfs_bui_recover(
 	struct xfs_map_extent		*bmap;
 	xfs_fsblock_t			startblock_fsb;
 	xfs_fsblock_t			inode_fsb;
+	xfs_filblks_t			count;
 	bool				op_ok;
 	struct xfs_bud_log_item		*budp;
 	enum xfs_bmap_intent_type	type;
@@ -404,6 +405,7 @@ xfs_bui_recover(
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_defer_ops		dfops;
+	struct xfs_bmbt_irec		irec;
 	xfs_fsblock_t			firstfsb;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
@@ -481,13 +483,24 @@ xfs_bui_recover(
 	}
 	xfs_trans_ijoin(tp, ip, 0);
 
+	count = bmap->me_len;
 	error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type,
 			ip, whichfork, bmap->me_startoff,
-			bmap->me_startblock, bmap->me_len,
-			state);
+			bmap->me_startblock, &count, state);
 	if (error)
 		goto err_dfops;
 
+	if (count > 0) {
+		ASSERT(type == XFS_BMAP_UNMAP);
+		irec.br_startblock = bmap->me_startblock;
+		irec.br_blockcount = count;
+		irec.br_startoff = bmap->me_startoff;
+		irec.br_state = state;
+		error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec);
+		if (error)
+			goto err_dfops;
+	}
+
 	/* Finish transaction, free inodes. */
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index a07acbf0bd8a..08923e59ea9d 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -275,6 +275,6 @@ int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp,
 		struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops,
 		enum xfs_bmap_intent_type type, struct xfs_inode *ip,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 
 #endif	/* __XFS_TRANS_H__ */
diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c
index 6408e7d7c08c..14543d93cd4b 100644
--- a/fs/xfs/xfs_trans_bmap.c
+++ b/fs/xfs/xfs_trans_bmap.c
@@ -63,7 +63,7 @@ xfs_trans_log_finish_bmap_update(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
 	int				error;
@@ -196,16 +196,23 @@ xfs_bmap_update_finish_item(
 	void				**state)
 {
 	struct xfs_bmap_intent		*bmap;
+	xfs_filblks_t			count;
 	int				error;
 
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
+	count = bmap->bi_bmap.br_blockcount;
 	error = xfs_trans_log_finish_bmap_update(tp, done_item, dop,
 			bmap->bi_type,
 			bmap->bi_owner, bmap->bi_whichfork,
 			bmap->bi_bmap.br_startoff,
 			bmap->bi_bmap.br_startblock,
-			bmap->bi_bmap.br_blockcount,
+			&count,
 			bmap->bi_bmap.br_state);
+	if (!error && count > 0) {
+		ASSERT(bmap->bi_type == XFS_BMAP_UNMAP);
+		bmap->bi_bmap.br_blockcount = count;
+		return -EAGAIN;
+	}
 	kmem_free(bmap);
 	return error;
 }

From ccdab3d6e881649f05110d9098fd248d2753aaf3 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:29:12 -0700
Subject: [PATCH 04/48] xfs: define bug_on_assert debug mode sysfs tunable

In DEBUG mode, assert failures unconditionally trigger a kernel BUG.
This is useful in diagnostic situations to panic a system and
collect detailed state information at the time of a failure.

This can also cause problems in cases where DEBUG mode code is
desired but it is preferable not trigger kernel BUGs on assert
failure. For example, during development of new code or during
certain xfstests tests that intentionally cause corruption and test
the kernel for survival (but otherwise may expect to trigger assert
failures).

To provide additional flexibility, create the
<sysfs>/fs/xfs/debug/bug_on_assert tunable to configure assert
failure behavior at runtime. This tunable is only available in DEBUG
mode and is enabled by default to preserve existing default
behavior. When disabled, assert failures in DEBUG mode result in
kernel warnings.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_globals.c |  2 ++
 fs/xfs/xfs_message.c |  5 ++++-
 fs/xfs/xfs_sysctl.h  |  1 +
 fs/xfs/xfs_sysfs.c   | 33 +++++++++++++++++++++++++++++++++
 4 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 687a4b01fc53..673adf0a40cc 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -47,4 +47,6 @@ xfs_param_t xfs_params = {
 
 struct xfs_globals xfs_globals = {
 	.log_recovery_delay	=	0,	/* no delay by default */
+	.bug_on_assert		=	true,	/* historical default in DEBUG
+						 * mode */
 };
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index 11792d888e4e..e68bd1050eab 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -110,7 +110,10 @@ assfail(char *expr, char *file, int line)
 {
 	xfs_emerg(NULL, "Assertion failed: %s, file: %s, line: %d",
 		expr, file, line);
-	BUG();
+	if (xfs_globals.bug_on_assert)
+		BUG();
+	else
+		WARN_ON(1);
 }
 
 void
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index 984a3499cfe3..82afee005140 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -95,6 +95,7 @@ extern xfs_param_t	xfs_params;
 
 struct xfs_globals {
 	int	log_recovery_delay;	/* log recovery delay (secs) */
+	bool	bug_on_assert;		/* BUG() the kernel on assert failure */
 };
 extern struct xfs_globals	xfs_globals;
 
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 80ac15fb9638..ec6e0e2f95d6 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -145,6 +145,38 @@ struct kobj_type xfs_mp_ktype = {
 #ifdef DEBUG
 /* debug */
 
+STATIC ssize_t
+bug_on_assert_store(
+	struct kobject		*kobject,
+	const char		*buf,
+	size_t			count)
+{
+	int			ret;
+	int			val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val == 1)
+		xfs_globals.bug_on_assert = true;
+	else if (val == 0)
+		xfs_globals.bug_on_assert = false;
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+STATIC ssize_t
+bug_on_assert_show(
+	struct kobject		*kobject,
+	char			*buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bug_on_assert ? 1 : 0);
+}
+XFS_SYSFS_ATTR_RW(bug_on_assert);
+
 STATIC ssize_t
 log_recovery_delay_store(
 	struct kobject	*kobject,
@@ -176,6 +208,7 @@ log_recovery_delay_show(
 XFS_SYSFS_ATTR_RW(log_recovery_delay);
 
 static struct attribute *xfs_dbg_attrs[] = {
+	ATTR_LIST(bug_on_assert),
 	ATTR_LIST(log_recovery_delay),
 	NULL,
 };

From 1040960efaabb8e6c87633c7becbb51fc99d4b9b Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:29:13 -0700
Subject: [PATCH 05/48] xfs: define fatal assert build time tunable

While configurable at runtime, the DEBUG mode assert failure
behavior is usually either desired or not for a particular
situation. For example, developers using kernel modules may prefer
for fatal asserts to remain disabled across module reloads while QE
engineers doing broad regression testing may prefer to have fatal
asserts enabled on boot to facilitate data collection for bug
reports.

To provide a compromise/convenience for developers, create a Kconfig
option that sets the default value of the DEBUG mode 'bug_on_assert'
sysfs tunable. The default behavior remains to trigger kernel BUGs
on assert failures to preserve existing behavior across kernel
configuration updates with DEBUG mode enabled.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/Kconfig       | 13 +++++++++++++
 fs/xfs/xfs.h         |  4 ++++
 fs/xfs/xfs_globals.c |  7 +++++--
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 35faf128f36d..1b98cfa342ab 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -96,3 +96,16 @@ config XFS_DEBUG
 	  not useful unless you are debugging a particular problem.
 
 	  Say N unless you are an XFS developer, or you play one on TV.
+
+config XFS_ASSERT_FATAL
+	bool "XFS fatal asserts"
+	default y
+	depends on XFS_FS && XFS_DEBUG
+	help
+	  Set the default DEBUG mode ASSERT failure behavior.
+
+	  Say Y here to cause DEBUG mode ASSERT failures to result in fatal
+	  errors that BUG() the kernel by default. If you say N, ASSERT failures
+	  result in warnings.
+
+	  This behavior can be modified at runtime via sysfs.
diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index a742c47f7d5a..80cd0fd86783 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -24,6 +24,10 @@
 #define XFS_BUF_LOCK_TRACKING 1
 #endif
 
+#ifdef CONFIG_XFS_ASSERT_FATAL
+#define XFS_ASSERT_FATAL 1
+#endif
+
 #ifdef CONFIG_XFS_WARN
 #define XFS_WARN 1
 #endif
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 673adf0a40cc..3e1cc3001bcb 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -47,6 +47,9 @@ xfs_param_t xfs_params = {
 
 struct xfs_globals xfs_globals = {
 	.log_recovery_delay	=	0,	/* no delay by default */
-	.bug_on_assert		=	true,	/* historical default in DEBUG
-						 * mode */
+#ifdef XFS_ASSERT_FATAL
+	.bug_on_assert		=	true,	/* assert failures BUG() */
+#else
+	.bug_on_assert		=	false,	/* assert failures WARN() */
+#endif
 };

From 7d2d5653460443e0586bd7d2e07811b4f4095e36 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:29:48 -0700
Subject: [PATCH 06/48] xfs: separate shutdown from ticket reservation print
 helper

xlog_print_tic_res() pre-dates delayed logging and the committed
items list (CIL) and thus retains some factoring warts, such as hard
coded function names in the output and the fact that it induces a
shutdown.

In preparation for more detailed logging of regular transaction
overrun situations, refactor xlog_print_tic_res() to be slightly
more generic. Reword some of the warning messages and pull the
shutdown into the callers.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log.c     | 12 ++++++------
 fs/xfs/xfs_log_cil.c |  4 +++-
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 3731f13f63e9..8b283f7cefea 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2024,7 +2024,7 @@ xlog_print_tic_res(
 	};
 #undef REG_TYPE_STR
 
-	xfs_warn(mp, "xlog_write: reservation summary:");
+	xfs_warn(mp, "ticket reservation summary:");
 	xfs_warn(mp, "  unit res    = %d bytes",
 		 ticket->t_unit_res);
 	xfs_warn(mp, "  current res = %d bytes",
@@ -2045,10 +2045,6 @@ xlog_print_tic_res(
 			    "bad-rtype" : res_type_str[r_type]),
 			    ticket->t_res_arr[i].r_len);
 	}
-
-	xfs_alert_tag(mp, XFS_PTAG_LOGRES,
-		"xlog_write: reservation ran out. Need to up reservation");
-	xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
 }
 
 /*
@@ -2321,8 +2317,12 @@ xlog_write(
 	if (flags & (XLOG_COMMIT_TRANS | XLOG_UNMOUNT_TRANS))
 		ticket->t_curr_res -= sizeof(xlog_op_header_t);
 
-	if (ticket->t_curr_res < 0)
+	if (ticket->t_curr_res < 0) {
+		xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES,
+		     "ctx ticket reservation ran out. Need to up reservation");
 		xlog_print_tic_res(log->l_mp, ticket);
+		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
+	}
 
 	index = 0;
 	lv = log_vector;
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 82f1cbcc4de1..52fe04229aa6 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -987,8 +987,10 @@ xfs_log_commit_cil(
 	xlog_cil_insert_items(log, tp);
 
 	/* check we didn't blow the reservation */
-	if (tp->t_ticket->t_curr_res < 0)
+	if (tp->t_ticket->t_curr_res < 0) {
 		xlog_print_tic_res(mp, tp->t_ticket);
+		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
+	}
 
 	tp->t_commit_lsn = cil->xc_ctx->sequence;
 	if (commit_lsn)

From e2f2342639a414b60de3876a8b437eac2b795dbe Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:29:49 -0700
Subject: [PATCH 07/48] xfs: refactor xlog_cil_insert_items() to facilitate
 transaction dump

Transaction reservation overrun detection currently occurs too late
to print useful information about the offending transaction.
Ideally, the transaction data is printed before the associated log
items are moved from the transaction to the CIL, which occurs in
xlog_cil_insert_items(), such that details of the items logged by
the transaction are available for analysis.

Refactor xlog_cil_insert_items() to facilitate moving tx overrun
detection to this function. Update the function to track each bit of
extra log reservation stolen from the transaction (i.e., such as for
the CIL context ticket) and perform the log item migration as the
last operation before the CIL lock is released. This creates a
context where the transaction reservation consumption has been fully
calculated when the log items are moved to the CIL. This patch makes
no functional changes.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log_cil.c | 78 +++++++++++++++++++++++---------------------
 1 file changed, 40 insertions(+), 38 deletions(-)

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 52fe04229aa6..8de3baa7d3f0 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -410,6 +410,7 @@ xlog_cil_insert_items(
 	int			len = 0;
 	int			diff_iovecs = 0;
 	int			iclog_space;
+	int			iovhdr_res = 0, split_res = 0, ctx_res = 0;
 
 	ASSERT(tp);
 
@@ -419,12 +420,50 @@ xlog_cil_insert_items(
 	 */
 	xlog_cil_insert_format_items(log, tp, &len, &diff_iovecs);
 
+	spin_lock(&cil->xc_cil_lock);
+
+	/* account for space used by new iovec headers  */
+	iovhdr_res = diff_iovecs * sizeof(xlog_op_header_t);
+	len += iovhdr_res;
+	ctx->nvecs += diff_iovecs;
+
+	/* attach the transaction to the CIL if it has any busy extents */
+	if (!list_empty(&tp->t_busy))
+		list_splice_init(&tp->t_busy, &ctx->busy_extents);
+
+	/*
+	 * Now transfer enough transaction reservation to the context ticket
+	 * for the checkpoint. The context ticket is special - the unit
+	 * reservation has to grow as well as the current reservation as we
+	 * steal from tickets so we can correctly determine the space used
+	 * during the transaction commit.
+	 */
+	if (ctx->ticket->t_curr_res == 0) {
+		ctx_res = ctx->ticket->t_unit_res;
+		ctx->ticket->t_curr_res = ctx_res;
+		tp->t_ticket->t_curr_res -= ctx_res;
+	}
+
+	/* do we need space for more log record headers? */
+	iclog_space = log->l_iclog_size - log->l_iclog_hsize;
+	if (len > 0 && (ctx->space_used / iclog_space !=
+				(ctx->space_used + len) / iclog_space)) {
+		split_res = (len + iclog_space - 1) / iclog_space;
+		/* need to take into account split region headers, too */
+		split_res *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
+		ctx->ticket->t_unit_res += split_res;
+		ctx->ticket->t_curr_res += split_res;
+		tp->t_ticket->t_curr_res -= split_res;
+		ASSERT(tp->t_ticket->t_curr_res >= len);
+	}
+	tp->t_ticket->t_curr_res -= len;
+	ctx->space_used += len;
+
 	/*
 	 * Now (re-)position everything modified at the tail of the CIL.
 	 * We do this here so we only need to take the CIL lock once during
 	 * the transaction commit.
 	 */
-	spin_lock(&cil->xc_cil_lock);
 	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
 		struct xfs_log_item	*lip = lidp->lid_item;
 
@@ -441,43 +480,6 @@ xlog_cil_insert_items(
 			list_move_tail(&lip->li_cil, &cil->xc_cil);
 	}
 
-	/* account for space used by new iovec headers  */
-	len += diff_iovecs * sizeof(xlog_op_header_t);
-	ctx->nvecs += diff_iovecs;
-
-	/* attach the transaction to the CIL if it has any busy extents */
-	if (!list_empty(&tp->t_busy))
-		list_splice_init(&tp->t_busy, &ctx->busy_extents);
-
-	/*
-	 * Now transfer enough transaction reservation to the context ticket
-	 * for the checkpoint. The context ticket is special - the unit
-	 * reservation has to grow as well as the current reservation as we
-	 * steal from tickets so we can correctly determine the space used
-	 * during the transaction commit.
-	 */
-	if (ctx->ticket->t_curr_res == 0) {
-		ctx->ticket->t_curr_res = ctx->ticket->t_unit_res;
-		tp->t_ticket->t_curr_res -= ctx->ticket->t_unit_res;
-	}
-
-	/* do we need space for more log record headers? */
-	iclog_space = log->l_iclog_size - log->l_iclog_hsize;
-	if (len > 0 && (ctx->space_used / iclog_space !=
-				(ctx->space_used + len) / iclog_space)) {
-		int hdrs;
-
-		hdrs = (len + iclog_space - 1) / iclog_space;
-		/* need to take into account split region headers, too */
-		hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
-		ctx->ticket->t_unit_res += hdrs;
-		ctx->ticket->t_curr_res += hdrs;
-		tp->t_ticket->t_curr_res -= hdrs;
-		ASSERT(tp->t_ticket->t_curr_res >= len);
-	}
-	tp->t_ticket->t_curr_res -= len;
-	ctx->space_used += len;
-
 	spin_unlock(&cil->xc_cil_lock);
 }
 

From d4ca1d550d052accec85ae26ac5b9d3d8b8f81f1 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:29:50 -0700
Subject: [PATCH 08/48] xfs: dump transaction usage details on log reservation
 overrun

If a transaction log reservation overrun occurs, the ticket data
associated with the reservation is dumped in xfs_log_commit_cil().
This occurs long after the transaction items and details have been
removed from the transaction and effectively lost. This limited set
of ticket data provides very little information to support debugging
transaction overruns based on the typical report.

To improve transaction log reservation overrun reporting, create a
helper to dump transaction details such as log items, log vector
data, etc., as well as the underlying ticket data for the
transaction. Move the overrun detection from xfs_log_commit_cil() to
xlog_cil_insert_items() so it occurs prior to migration of the
logged items to the CIL. Call the new helper such that it is able to
dump this transaction data before it is lost.

Also, warn on overrun to provide callstack context for the offending
transaction and include a few additional messages from
xlog_cil_insert_items() to display the reservation consumed locally
for overhead such as log vector headers, split region headers and
the context ticket. This provides a complete general breakdown of
the reservation consumption of a transaction when/if it happens to
overrun the reservation.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log.c      | 49 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_log_cil.c  | 24 +++++++++++++++------
 fs/xfs/xfs_log_priv.h |  1 +
 3 files changed, 68 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 8b283f7cefea..c8d048103347 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2047,6 +2047,55 @@ xlog_print_tic_res(
 	}
 }
 
+/*
+ * Print a summary of the transaction.
+ */
+void
+xlog_print_trans(
+	struct xfs_trans		*tp)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_log_item_desc	*lidp;
+
+	/* dump core transaction and ticket info */
+	xfs_warn(mp, "transaction summary:");
+	xfs_warn(mp, "  flags	= 0x%x", tp->t_flags);
+
+	xlog_print_tic_res(mp, tp->t_ticket);
+
+	/* dump each log item */
+	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
+		struct xfs_log_item	*lip = lidp->lid_item;
+		struct xfs_log_vec	*lv = lip->li_lv;
+		struct xfs_log_iovec	*vec;
+		int			i;
+
+		xfs_warn(mp, "log item: ");
+		xfs_warn(mp, "  type	= 0x%x", lip->li_type);
+		xfs_warn(mp, "  flags	= 0x%x", lip->li_flags);
+		if (!lv)
+			continue;
+		xfs_warn(mp, "  niovecs	= %d", lv->lv_niovecs);
+		xfs_warn(mp, "  size	= %d", lv->lv_size);
+		xfs_warn(mp, "  bytes	= %d", lv->lv_bytes);
+		xfs_warn(mp, "  buf len	= %d", lv->lv_buf_len);
+
+		/* dump each iovec for the log item */
+		vec = lv->lv_iovecp;
+		for (i = 0; i < lv->lv_niovecs; i++) {
+			int dumplen = min(vec->i_len, 32);
+
+			xfs_warn(mp, "  iovec[%d]", i);
+			xfs_warn(mp, "    type	= 0x%x", vec->i_type);
+			xfs_warn(mp, "    len	= %d", vec->i_len);
+			xfs_warn(mp, "    first %d bytes of iovec[%d]:", dumplen, i);
+			xfs_hex_dump(vec->i_addr, dumplen);;
+
+			vec++;
+		}
+	}
+}
+
 /*
  * Calculate the potential space needed by the log vector.  Each region gets
  * its own xlog_op_header_t and may need to be double word aligned.
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 8de3baa7d3f0..04b389210cc7 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -459,6 +459,21 @@ xlog_cil_insert_items(
 	tp->t_ticket->t_curr_res -= len;
 	ctx->space_used += len;
 
+	/*
+	 * If we've overrun the reservation, dump the tx details before we move
+	 * the log items. Shutdown is imminent...
+	 */
+	if (WARN_ON(tp->t_ticket->t_curr_res < 0)) {
+		xfs_warn(log->l_mp, "Transaction log reservation overrun:");
+		xfs_warn(log->l_mp,
+			 "  log items: %d bytes (iov hdrs: %d bytes)",
+			 len, iovhdr_res);
+		xfs_warn(log->l_mp, "  split region headers: %d bytes",
+			 split_res);
+		xfs_warn(log->l_mp, "  ctx ticket: %d bytes", ctx_res);
+		xlog_print_trans(tp);
+	}
+
 	/*
 	 * Now (re-)position everything modified at the tail of the CIL.
 	 * We do this here so we only need to take the CIL lock once during
@@ -481,6 +496,9 @@ xlog_cil_insert_items(
 	}
 
 	spin_unlock(&cil->xc_cil_lock);
+
+	if (tp->t_ticket->t_curr_res < 0)
+		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
 }
 
 static void
@@ -988,12 +1006,6 @@ xfs_log_commit_cil(
 
 	xlog_cil_insert_items(log, tp);
 
-	/* check we didn't blow the reservation */
-	if (tp->t_ticket->t_curr_res < 0) {
-		xlog_print_tic_res(mp, tp->t_ticket);
-		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
-	}
-
 	tp->t_commit_lsn = cil->xc_ctx->sequence;
 	if (commit_lsn)
 		*commit_lsn = tp->t_commit_lsn;
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index c2604a5366f2..62113a5d2504 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -456,6 +456,7 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes)
 }
 
 void	xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket);
+void	xlog_print_trans(struct xfs_trans *);
 int
 xlog_write(
 	struct xlog		*log,

From 3398a4005f0c8ced67a9071475562d435d88b7a6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 14 Jun 2017 21:30:44 -0700
Subject: [PATCH 09/48] xfs: remove XFS_HSIZE

XFS_HSIZE is an extremly confusing way to calculate the size of handle_t.
Given that handle_t always only had two sizes, and one of them isn't
even covered by XFS_HSIZE to start with just remove the macro and use
a constant sizeof expression.

Note that XFS_HSIZE isn't used in xfsprogs, xfsdump or xfstests either.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Eric Sandeen <sandeen@sandeen.net>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_fs.h | 4 ----
 fs/xfs/xfs_ioctl.c     | 3 +--
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 095bdf049a3f..a9aa13e66046 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -446,10 +446,6 @@ typedef struct xfs_handle {
 } xfs_handle_t;
 #define ha_fsid ha_u._ha_fsid
 
-#define XFS_HSIZE(handle)	(((char *) &(handle).ha_fid.fid_pad	 \
-				 - (char *) &(handle))			  \
-				 + (handle).ha_fid.fid_len)
-
 /*
  * Structure passed to XFS_IOC_SWAPEXT
  */
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 6190697603c9..f6af76975bc8 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -120,8 +120,7 @@ xfs_find_handle(
 		handle.ha_fid.fid_pad = 0;
 		handle.ha_fid.fid_gen = inode->i_generation;
 		handle.ha_fid.fid_ino = ip->i_ino;
-
-		hsize = XFS_HSIZE(handle);
+		hsize = sizeof(xfs_handle_t);
 	}
 
 	error = -EFAULT;

From f990fc5ad13b8fecdf154f36c252d49d7e9bdfab Mon Sep 17 00:00:00 2001
From: Shan Hai <shan.hai@oracle.com>
Date: Wed, 14 Jun 2017 21:35:07 -0700
Subject: [PATCH 10/48] xfs: remove lsn relevant fields from xfs_trans
 structure and its users

The t_lsn is not used anymore and the t_commit_lsn is used as a tmp
storage for the checkpoint sequence number only in the current code.

And the start/commit lsn are tracked as a transaction group tag in
the xfs_cil_ctx instead of a single transaction, so remove them from
the xfs_trans structure and their users to match with the design.

Signed-off-by: Shan Hai <shan.hai@oracle.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log_cil.c |  7 ++++---
 fs/xfs/xfs_trace.h   | 19 -------------------
 fs/xfs/xfs_trans.h   |  4 ----
 3 files changed, 4 insertions(+), 26 deletions(-)

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 04b389210cc7..fbe72b134bef 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -993,6 +993,7 @@ xfs_log_commit_cil(
 {
 	struct xlog		*log = mp->m_log;
 	struct xfs_cil		*cil = log->l_cilp;
+	xfs_lsn_t		xc_commit_lsn;
 
 	/*
 	 * Do all necessary memory allocation before we lock the CIL.
@@ -1006,9 +1007,9 @@ xfs_log_commit_cil(
 
 	xlog_cil_insert_items(log, tp);
 
-	tp->t_commit_lsn = cil->xc_ctx->sequence;
+	xc_commit_lsn = cil->xc_ctx->sequence;
 	if (commit_lsn)
-		*commit_lsn = tp->t_commit_lsn;
+		*commit_lsn = xc_commit_lsn;
 
 	xfs_log_done(mp, tp->t_ticket, NULL, regrant);
 	xfs_trans_unreserve_and_mod_sb(tp);
@@ -1024,7 +1025,7 @@ xfs_log_commit_cil(
 	 * the log items. This affects (at least) processing of stale buffers,
 	 * inodes and EFIs.
 	 */
-	xfs_trans_free_items(tp, tp->t_commit_lsn, false);
+	xfs_trans_free_items(tp, xc_commit_lsn, false);
 
 	xlog_cil_push_background(log);
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 306d89c55267..a560bfd392c1 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1491,25 +1491,6 @@ TRACE_EVENT(xfs_extent_busy_trim,
 		  __entry->tlen)
 );
 
-TRACE_EVENT(xfs_trans_commit_lsn,
-	TP_PROTO(struct xfs_trans *trans),
-	TP_ARGS(trans),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(struct xfs_trans *, tp)
-		__field(xfs_lsn_t, lsn)
-	),
-	TP_fast_assign(
-		__entry->dev = trans->t_mountp->m_super->s_dev;
-		__entry->tp = trans;
-		__entry->lsn = trans->t_commit_lsn;
-	),
-	TP_printk("dev %d:%d trans 0x%p commit_lsn 0x%llx",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->tp,
-		  __entry->lsn)
-);
-
 TRACE_EVENT(xfs_agf,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags,
 		 unsigned long caller_ip),
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 08923e59ea9d..82bb61e330d9 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -105,10 +105,6 @@ typedef struct xfs_trans {
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
-	xfs_lsn_t		t_lsn;		/* log seq num of start of
-						 * transaction. */
-	xfs_lsn_t		t_commit_lsn;	/* log seq num of end of
-						 * transaction. */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
 	unsigned int		t_flags;	/* misc flags */

From 0cbe48cc5814ae26e4058c5d666914c86a4a6b5d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 14 Jun 2017 21:35:34 -0700
Subject: [PATCH 11/48] xfs: avoid harmless gcc-7 warnings

gcc-7 flags the use of integer math inside of a condition
as a potential bug:

fs/xfs/xfs_bmap_util.c: In function 'xfs_swap_extents_check_format':
fs/xfs/xfs_bmap_util.c:1619:8: error: '<<' in boolean context, did you mean '<' ? [-Werror=int-in-bool-context]
fs/xfs/xfs_bmap_util.c:1629:8: error: '<<' in boolean context, did you mean '<' ? [-Werror=int-in-bool-context]

There is already a helper function for testing the di_forkoff
field for zero, so let's use that instead to shut up the warning.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 9e3cc2146d5b..7493a64f5b99 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1617,7 +1617,7 @@ xfs_swap_extents_check_format(
 	 * extent format...
 	 */
 	if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
-		if (XFS_IFORK_BOFF(ip) &&
+		if (XFS_IFORK_Q(ip) &&
 		    XFS_BMAP_BMDR_SPACE(tip->i_df.if_broot) > XFS_IFORK_BOFF(ip))
 			return -EINVAL;
 		if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
@@ -1627,7 +1627,7 @@ xfs_swap_extents_check_format(
 
 	/* Reciprocal target->temp btree format checks */
 	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
-		if (XFS_IFORK_BOFF(tip) &&
+		if (XFS_IFORK_Q(tip) &&
 		    XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip))
 			return -EINVAL;
 		if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=

From 79e641ce29cfae5b8fc55fb77ac62d11d2d849c0 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:35:35 -0700
Subject: [PATCH 12/48] xfs: release bli from transaction properly on fs
 shutdown

If a filesystem shutdown occurs with a buffer log item in the CIL
and a log force occurs, the ->iop_unpin() handler is generally
expected to tear down the bli properly. This entails freeing the bli
memory and releasing the associated hold on the buffer so it can be
released and the filesystem unmounted.

If this sequence occurs while ->bli_refcount is elevated (i.e.,
another transaction is open and attempting to modify the buffer),
however, ->iop_unpin() may not be responsible for releasing the bli.
Instead, the transaction may release the final ->bli_refcount
reference and thus xfs_trans_brelse() is responsible for tearing
down the bli.

While xfs_trans_brelse() does drop the reference count, it only
attempts to release the bli if it is clean (i.e., not in the
CIL/AIL). If the filesystem is shutdown and the bli is sitting dirty
in the CIL as noted above, this ends up skipping the last
opportunity to release the bli. In turn, this leaves the hold on the
buffer and causes an unmount hang. This can be reproduced by running
generic/388 in repetition.

Update xfs_trans_brelse() to handle this shutdown corner case
correctly. If the final bli reference is dropped and the filesystem
is shutdown, remove the bli from the AIL (if necessary) and release
the bli to drop the buffer hold and ensure an unmount does not hang.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_trans_buf.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 8ee29ca132dc..86987d823d76 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -356,6 +356,7 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 		 xfs_buf_t	*bp)
 {
 	xfs_buf_log_item_t	*bip;
+	int			freed;
 
 	/*
 	 * Default to a normal brelse() call if the tp is NULL.
@@ -419,16 +420,22 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 	/*
 	 * Drop our reference to the buf log item.
 	 */
-	atomic_dec(&bip->bli_refcount);
+	freed = atomic_dec_and_test(&bip->bli_refcount);
 
 	/*
-	 * If the buf item is not tracking data in the log, then
-	 * we must free it before releasing the buffer back to the
-	 * free pool.  Before releasing the buffer to the free pool,
-	 * clear the transaction pointer in b_fsprivate2 to dissolve
-	 * its relation to this transaction.
+	 * If the buf item is not tracking data in the log, then we must free it
+	 * before releasing the buffer back to the free pool.
+	 *
+	 * If the fs has shutdown and we dropped the last reference, it may fall
+	 * on us to release a (possibly dirty) bli if it never made it to the
+	 * AIL (e.g., the aborted unpin already happened and didn't release it
+	 * due to our reference). Since we're already shutdown and need xa_lock,
+	 * just force remove from the AIL and release the bli here.
 	 */
-	if (!xfs_buf_item_dirty(bip)) {
+	if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) {
+		xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR);
+		xfs_buf_item_relse(bp);
+	} else if (!xfs_buf_item_dirty(bip)) {
 /***
 		ASSERT(bp->b_pincount == 0);
 ***/

From 3d4b4a3e30ae7a949c31e1e10268a3da4723d290 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 14 Jun 2017 21:35:35 -0700
Subject: [PATCH 13/48] xfs: remove bli from AIL before release on transaction
 abort

When a buffer is modified, logged and committed, it ultimately ends
up sitting on the AIL with a dirty bli waiting for metadata
writeback. If another transaction locks and invalidates the buffer
(freeing an inode chunk, for example) in the meantime, the bli is
flagged as stale, the dirty state is cleared and the bli remains in
the AIL.

If a shutdown occurs before the transaction that has invalidated the
buffer is committed, the transaction is ultimately aborted. The log
items are flagged as such and ->iop_unlock() handles the aborted
items. Because the bli is clean (due to the invalidation),
->iop_unlock() unconditionally releases it. The log item may still
reside in the AIL, however, which means the I/O completion handler
may still run and attempt to access it. This results in assert
failure due to the release of the bli while still present in the AIL
and a subsequent NULL dereference and panic in the buffer I/O
completion handling. This can be reproduced by running generic/388
in repetition.

To avoid this problem, update xfs_buf_item_unlock() to first check
whether the bli is aborted and if so, remove it from the AIL before
it is released. This ensures that the bli is no longer accessed
during the shutdown sequence after it has been freed.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_buf_item.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 0306168af332..f6a8422e9562 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -636,20 +636,23 @@ xfs_buf_item_unlock(
 
 	/*
 	 * Clean buffers, by definition, cannot be in the AIL. However, aborted
-	 * buffers may be dirty and hence in the AIL. Therefore if we are
-	 * aborting a buffer and we've just taken the last refernce away, we
-	 * have to check if it is in the AIL before freeing it. We need to free
-	 * it in this case, because an aborted transaction has already shut the
-	 * filesystem down and this is the last chance we will have to do so.
+	 * buffers may be in the AIL regardless of dirty state. An aborted
+	 * transaction that invalidates a buffer already in the AIL may have
+	 * marked it stale and cleared the dirty state, for example.
+	 *
+	 * Therefore if we are aborting a buffer and we've just taken the last
+	 * reference away, we have to check if it is in the AIL before freeing
+	 * it. We need to free it in this case, because an aborted transaction
+	 * has already shut the filesystem down and this is the last chance we
+	 * will have to do so.
 	 */
 	if (atomic_dec_and_test(&bip->bli_refcount)) {
-		if (clean)
-			xfs_buf_item_relse(bp);
-		else if (aborted) {
+		if (aborted) {
 			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
 			xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
 			xfs_buf_item_relse(bp);
-		}
+		} else if (clean)
+			xfs_buf_item_relse(bp);
 	}
 
 	if (!(flags & XFS_BLI_HOLD))

From 5a4c73342ad493c61f19a1406f47dcd35e18030f Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:04 -0700
Subject: [PATCH 14/48] xfs: optimize _btree_query_all

Don't bother wandering our way through the leaf nodes when the caller
issues a query_all; just zoom down the left side of the tree and walk
rightwards along level zero.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_btree.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 3a673ba201aa..d50517942273 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4849,12 +4849,14 @@ xfs_btree_query_all(
 	xfs_btree_query_range_fn	fn,
 	void				*priv)
 {
-	union xfs_btree_irec		low_rec;
-	union xfs_btree_irec		high_rec;
+	union xfs_btree_key		low_key;
+	union xfs_btree_key		high_key;
 
-	memset(&low_rec, 0, sizeof(low_rec));
-	memset(&high_rec, 0xFF, sizeof(high_rec));
-	return xfs_btree_query_range(cur, &low_rec, &high_rec, fn, priv);
+	memset(&cur->bc_rec, 0, sizeof(cur->bc_rec));
+	memset(&low_key, 0, sizeof(low_key));
+	memset(&high_key, 0xFF, sizeof(high_key));
+
+	return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv);
 }
 
 /*

From c8ce540db5f67d254aafb14b5d76422c62a906df Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:05 -0700
Subject: [PATCH 15/48] xfs: remove double-underscore integer types

This is a purely mechanical patch that removes the private
__{u,}int{8,16,32,64}_t typedefs in favor of using the system
{u,}int{8,16,32,64}_t typedefs.  This is the sed script used to perform
the transformation and fix the resulting whitespace and indentation
errors:

s/typedef\t__uint8_t/typedef __uint8_t\t/g
s/typedef\t__uint/typedef __uint/g
s/typedef\t__int\([0-9]*\)_t/typedef int\1_t\t/g
s/__uint8_t\t/__uint8_t\t\t/g
s/__uint/uint/g
s/__int\([0-9]*\)_t\t/__int\1_t\t\t/g
s/__int/int/g
/^typedef.*int[0-9]*_t;$/d

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_alloc_btree.c    |  20 +--
 fs/xfs/libxfs/xfs_attr_remote.c    |   8 +-
 fs/xfs/libxfs/xfs_attr_sf.h        |  10 +-
 fs/xfs/libxfs/xfs_bit.h            |  24 +--
 fs/xfs/libxfs/xfs_bmap_btree.c     |   8 +-
 fs/xfs/libxfs/xfs_btree.c          |  22 +--
 fs/xfs/libxfs/xfs_btree.h          |  18 +-
 fs/xfs/libxfs/xfs_cksum.h          |  16 +-
 fs/xfs/libxfs/xfs_da_btree.c       |   2 +-
 fs/xfs/libxfs/xfs_da_btree.h       |   8 +-
 fs/xfs/libxfs/xfs_da_format.c      |  28 ++--
 fs/xfs/libxfs/xfs_da_format.h      |  64 ++++----
 fs/xfs/libxfs/xfs_dir2.h           |   8 +-
 fs/xfs/libxfs/xfs_dir2_leaf.c      |  12 +-
 fs/xfs/libxfs/xfs_dir2_priv.h      |   2 +-
 fs/xfs/libxfs/xfs_dir2_sf.c        |   2 +-
 fs/xfs/libxfs/xfs_format.h         | 112 ++++++-------
 fs/xfs/libxfs/xfs_fs.h             |  12 +-
 fs/xfs/libxfs/xfs_ialloc.c         |   6 +-
 fs/xfs/libxfs/xfs_ialloc_btree.c   |   4 +-
 fs/xfs/libxfs/xfs_inode_buf.c      |   2 +-
 fs/xfs/libxfs/xfs_inode_buf.h      |  28 ++--
 fs/xfs/libxfs/xfs_log_format.h     | 256 ++++++++++++++---------------
 fs/xfs/libxfs/xfs_log_recover.h    |   2 +-
 fs/xfs/libxfs/xfs_quota_defs.h     |   4 +-
 fs/xfs/libxfs/xfs_refcount_btree.c |   8 +-
 fs/xfs/libxfs/xfs_rmap.c           |   8 +-
 fs/xfs/libxfs/xfs_rmap.h           |   8 +-
 fs/xfs/libxfs/xfs_rmap_btree.c     |  30 ++--
 fs/xfs/libxfs/xfs_rtbitmap.c       |   2 +-
 fs/xfs/libxfs/xfs_sb.c             |   4 +-
 fs/xfs/libxfs/xfs_types.h          |  46 +++---
 fs/xfs/xfs_aops.c                  |   4 +-
 fs/xfs/xfs_attr_list.c             |   2 +-
 fs/xfs/xfs_bmap_util.c             |  24 +--
 fs/xfs/xfs_buf.c                   |   2 +-
 fs/xfs/xfs_dir2_readdir.c          |   8 +-
 fs/xfs/xfs_discard.c               |   4 +-
 fs/xfs/xfs_dquot.c                 |   2 +-
 fs/xfs/xfs_fsops.c                 |  16 +-
 fs/xfs/xfs_fsops.h                 |   4 +-
 fs/xfs/xfs_inode.c                 |   6 +-
 fs/xfs/xfs_inode.h                 |   4 +-
 fs/xfs/xfs_ioctl.c                 |  20 +--
 fs/xfs/xfs_ioctl.h                 |  10 +-
 fs/xfs/xfs_ioctl32.h               |   6 +-
 fs/xfs/xfs_linux.h                 |  20 +--
 fs/xfs/xfs_log.c                   |  20 +--
 fs/xfs/xfs_log.h                   |   2 +-
 fs/xfs/xfs_log_priv.h              |   2 +-
 fs/xfs/xfs_log_recover.c           |  28 ++--
 fs/xfs/xfs_mount.c                 |  16 +-
 fs/xfs/xfs_mount.h                 |  34 ++--
 fs/xfs/xfs_qm_bhv.c                |   2 +-
 fs/xfs/xfs_rtalloc.c               |   8 +-
 fs/xfs/xfs_stats.c                 |   8 +-
 fs/xfs/xfs_stats.h                 | 190 ++++++++++-----------
 fs/xfs/xfs_super.c                 |  26 +--
 fs/xfs/xfs_trace.h                 |  20 +--
 fs/xfs/xfs_trans.h                 |   2 +-
 fs/xfs/xfs_trans_rmap.c            |   2 +-
 61 files changed, 634 insertions(+), 642 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index e1fcfe7f0a9a..5020cbc02db8 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -253,7 +253,7 @@ xfs_allocbt_init_ptr_from_cur(
 	ptr->s = agf->agf_roots[cur->bc_btnum];
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_bnobt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
@@ -261,42 +261,42 @@ xfs_bnobt_key_diff(
 	xfs_alloc_rec_incore_t	*rec = &cur->bc_rec.a;
 	xfs_alloc_key_t		*kp = &key->alloc;
 
-	return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
+	return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_cntbt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
 {
 	xfs_alloc_rec_incore_t	*rec = &cur->bc_rec.a;
 	xfs_alloc_key_t		*kp = &key->alloc;
-	__int64_t		diff;
+	int64_t			diff;
 
-	diff = (__int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
+	diff = (int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
 	if (diff)
 		return diff;
 
-	return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
+	return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_bnobt_diff_two_keys(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
 	union xfs_btree_key	*k2)
 {
-	return (__int64_t)be32_to_cpu(k1->alloc.ar_startblock) -
+	return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) -
 			  be32_to_cpu(k2->alloc.ar_startblock);
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_cntbt_diff_two_keys(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
 	union xfs_btree_key	*k2)
 {
-	__int64_t		diff;
+	int64_t			diff;
 
 	diff =  be32_to_cpu(k1->alloc.ar_blockcount) -
 		be32_to_cpu(k2->alloc.ar_blockcount);
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index d52f525f5b2d..da72b16bef8e 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -253,7 +253,7 @@ xfs_attr_rmtval_copyout(
 	xfs_ino_t	ino,
 	int		*offset,
 	int		*valuelen,
-	__uint8_t	**dst)
+	uint8_t		**dst)
 {
 	char		*src = bp->b_addr;
 	xfs_daddr_t	bno = bp->b_bn;
@@ -301,7 +301,7 @@ xfs_attr_rmtval_copyin(
 	xfs_ino_t	ino,
 	int		*offset,
 	int		*valuelen,
-	__uint8_t	**src)
+	uint8_t		**src)
 {
 	char		*dst = bp->b_addr;
 	xfs_daddr_t	bno = bp->b_bn;
@@ -355,7 +355,7 @@ xfs_attr_rmtval_get(
 	struct xfs_mount	*mp = args->dp->i_mount;
 	struct xfs_buf		*bp;
 	xfs_dablk_t		lblkno = args->rmtblkno;
-	__uint8_t		*dst = args->value;
+	uint8_t			*dst = args->value;
 	int			valuelen;
 	int			nmap;
 	int			error;
@@ -421,7 +421,7 @@ xfs_attr_rmtval_set(
 	struct xfs_bmbt_irec	map;
 	xfs_dablk_t		lblkno;
 	xfs_fileoff_t		lfileoff = 0;
-	__uint8_t		*src = args->value;
+	uint8_t			*src = args->value;
 	int			blkcnt;
 	int			valuelen;
 	int			nmap;
diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h
index 90928bbe693c..afd684ae3136 100644
--- a/fs/xfs/libxfs/xfs_attr_sf.h
+++ b/fs/xfs/libxfs/xfs_attr_sf.h
@@ -31,10 +31,10 @@ typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t;
  * We generate this then sort it, attr_list() must return things in hash-order.
  */
 typedef struct xfs_attr_sf_sort {
-	__uint8_t	entno;		/* entry number in original list */
-	__uint8_t	namelen;	/* length of name value (no null) */
-	__uint8_t	valuelen;	/* length of value */
-	__uint8_t	flags;		/* flags bits (see xfs_attr_leaf.h) */
+	uint8_t		entno;		/* entry number in original list */
+	uint8_t		namelen;	/* length of name value (no null) */
+	uint8_t		valuelen;	/* length of value */
+	uint8_t		flags;		/* flags bits (see xfs_attr_leaf.h) */
 	xfs_dahash_t	hash;		/* this entry's hash value */
 	unsigned char	*name;		/* name value, pointer into buffer */
 } xfs_attr_sf_sort_t;
@@ -42,7 +42,7 @@ typedef struct xfs_attr_sf_sort {
 #define XFS_ATTR_SF_ENTSIZE_BYNAME(nlen,vlen)	/* space name/value uses */ \
 	(((int)sizeof(xfs_attr_sf_entry_t)-1 + (nlen)+(vlen)))
 #define XFS_ATTR_SF_ENTSIZE_MAX			/* max space for name&value */ \
-	((1 << (NBBY*(int)sizeof(__uint8_t))) - 1)
+	((1 << (NBBY*(int)sizeof(uint8_t))) - 1)
 #define XFS_ATTR_SF_ENTSIZE(sfep)		/* space an entry uses */ \
 	((int)sizeof(xfs_attr_sf_entry_t)-1 + (sfep)->namelen+(sfep)->valuelen)
 #define XFS_ATTR_SF_NEXTENTRY(sfep)		/* next entry in struct */ \
diff --git a/fs/xfs/libxfs/xfs_bit.h b/fs/xfs/libxfs/xfs_bit.h
index e1649c0d3e02..61c6b2025d0c 100644
--- a/fs/xfs/libxfs/xfs_bit.h
+++ b/fs/xfs/libxfs/xfs_bit.h
@@ -25,47 +25,47 @@
 /*
  * masks with n high/low bits set, 64-bit values
  */
-static inline __uint64_t xfs_mask64hi(int n)
+static inline uint64_t xfs_mask64hi(int n)
 {
-	return (__uint64_t)-1 << (64 - (n));
+	return (uint64_t)-1 << (64 - (n));
 }
-static inline __uint32_t xfs_mask32lo(int n)
+static inline uint32_t xfs_mask32lo(int n)
 {
-	return ((__uint32_t)1 << (n)) - 1;
+	return ((uint32_t)1 << (n)) - 1;
 }
-static inline __uint64_t xfs_mask64lo(int n)
+static inline uint64_t xfs_mask64lo(int n)
 {
-	return ((__uint64_t)1 << (n)) - 1;
+	return ((uint64_t)1 << (n)) - 1;
 }
 
 /* Get high bit set out of 32-bit argument, -1 if none set */
-static inline int xfs_highbit32(__uint32_t v)
+static inline int xfs_highbit32(uint32_t v)
 {
 	return fls(v) - 1;
 }
 
 /* Get high bit set out of 64-bit argument, -1 if none set */
-static inline int xfs_highbit64(__uint64_t v)
+static inline int xfs_highbit64(uint64_t v)
 {
 	return fls64(v) - 1;
 }
 
 /* Get low bit set out of 32-bit argument, -1 if none set */
-static inline int xfs_lowbit32(__uint32_t v)
+static inline int xfs_lowbit32(uint32_t v)
 {
 	return ffs(v) - 1;
 }
 
 /* Get low bit set out of 64-bit argument, -1 if none set */
-static inline int xfs_lowbit64(__uint64_t v)
+static inline int xfs_lowbit64(uint64_t v)
 {
-	__uint32_t	w = (__uint32_t)v;
+	uint32_t	w = (uint32_t)v;
 	int		n = 0;
 
 	if (w) {	/* lower bits */
 		n = ffs(w);
 	} else {	/* upper bits */
-		w = (__uint32_t)(v >> 32);
+		w = (uint32_t)(v >> 32);
 		if (w) {
 			n = ffs(w);
 			if (n)
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 6cba69aff077..5e2b3dc138ad 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -94,8 +94,8 @@ xfs_bmdr_to_bmbt(
  */
 STATIC void
 __xfs_bmbt_get_all(
-		__uint64_t l0,
-		__uint64_t l1,
+		uint64_t l0,
+		uint64_t l1,
 		xfs_bmbt_irec_t *s)
 {
 	int	ext_flag;
@@ -588,12 +588,12 @@ xfs_bmbt_init_ptr_from_cur(
 	ptr->l = 0;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_bmbt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
 {
-	return (__int64_t)be64_to_cpu(key->bmbt.br_startoff) -
+	return (int64_t)be64_to_cpu(key->bmbt.br_startoff) -
 				      cur->bc_rec.b.br_startoff;
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index d50517942273..2aac3f499d97 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -43,7 +43,7 @@ kmem_zone_t	*xfs_btree_cur_zone;
 /*
  * Btree magic numbers.
  */
-static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
+static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
 	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, 0, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
 	  XFS_FIBT_MAGIC, 0 },
 	{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC, XFS_RMAP_CRC_MAGIC,
@@ -51,12 +51,12 @@ static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
 	  XFS_REFC_CRC_MAGIC }
 };
 
-__uint32_t
+uint32_t
 xfs_btree_magic(
 	int			crc,
 	xfs_btnum_t		btnum)
 {
-	__uint32_t		magic = xfs_magics[crc][btnum];
+	uint32_t		magic = xfs_magics[crc][btnum];
 
 	/* Ensure we asked for crc for crc-only magics. */
 	ASSERT(magic != 0);
@@ -778,14 +778,14 @@ xfs_btree_lastrec(
  */
 void
 xfs_btree_offsets(
-	__int64_t	fields,		/* bitmask of fields */
+	int64_t		fields,		/* bitmask of fields */
 	const short	*offsets,	/* table of field offsets */
 	int		nbits,		/* number of bits to inspect */
 	int		*first,		/* output: first byte offset */
 	int		*last)		/* output: last byte offset */
 {
 	int		i;		/* current bit number */
-	__int64_t	imask;		/* mask for current bit number */
+	int64_t		imask;		/* mask for current bit number */
 
 	ASSERT(fields != 0);
 	/*
@@ -1846,7 +1846,7 @@ xfs_btree_lookup(
 	int			*stat)	/* success/failure */
 {
 	struct xfs_btree_block	*block;	/* current btree block */
-	__int64_t		diff;	/* difference for the current key */
+	int64_t			diff;	/* difference for the current key */
 	int			error;	/* error return value */
 	int			keyno;	/* current key number */
 	int			level;	/* level in the btree */
@@ -4435,7 +4435,7 @@ xfs_btree_visit_blocks(
  * recovery completion writes the changes to disk.
  */
 struct xfs_btree_block_change_owner_info {
-	__uint64_t		new_owner;
+	uint64_t		new_owner;
 	struct list_head	*buffer_list;
 };
 
@@ -4481,7 +4481,7 @@ xfs_btree_block_change_owner(
 int
 xfs_btree_change_owner(
 	struct xfs_btree_cur	*cur,
-	__uint64_t		new_owner,
+	uint64_t		new_owner,
 	struct list_head	*buffer_list)
 {
 	struct xfs_btree_block_change_owner_info	bbcoi;
@@ -4585,7 +4585,7 @@ xfs_btree_simple_query_range(
 {
 	union xfs_btree_rec		*recp;
 	union xfs_btree_key		rec_key;
-	__int64_t			diff;
+	int64_t				diff;
 	int				stat;
 	bool				firstrec = true;
 	int				error;
@@ -4682,8 +4682,8 @@ xfs_btree_overlapped_query_range(
 	union xfs_btree_key		*hkp;
 	union xfs_btree_rec		*recp;
 	struct xfs_btree_block		*block;
-	__int64_t			ldiff;
-	__int64_t			hdiff;
+	int64_t				ldiff;
+	int64_t				hdiff;
 	int				level;
 	struct xfs_buf			*bp;
 	int				i;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 27bed08261c5..0a931f644103 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -76,7 +76,7 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_RMAP	((xfs_btnum_t)XFS_BTNUM_RMAPi)
 #define	XFS_BTNUM_REFC	((xfs_btnum_t)XFS_BTNUM_REFCi)
 
-__uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
+uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
 
 /*
  * For logging record fields.
@@ -150,14 +150,14 @@ struct xfs_btree_ops {
 					  union xfs_btree_rec *rec);
 
 	/* difference between key value and cursor value */
-	__int64_t (*key_diff)(struct xfs_btree_cur *cur,
+	int64_t (*key_diff)(struct xfs_btree_cur *cur,
 			      union xfs_btree_key *key);
 
 	/*
 	 * Difference between key2 and key1 -- positive if key1 > key2,
 	 * negative if key1 < key2, and zero if equal.
 	 */
-	__int64_t (*diff_two_keys)(struct xfs_btree_cur *cur,
+	int64_t (*diff_two_keys)(struct xfs_btree_cur *cur,
 				   union xfs_btree_key *key1,
 				   union xfs_btree_key *key2);
 
@@ -213,11 +213,11 @@ typedef struct xfs_btree_cur
 	union xfs_btree_irec	bc_rec;	/* current insert/search record value */
 	struct xfs_buf	*bc_bufs[XFS_BTREE_MAXLEVELS];	/* buf ptr per level */
 	int		bc_ptrs[XFS_BTREE_MAXLEVELS];	/* key/record # */
-	__uint8_t	bc_ra[XFS_BTREE_MAXLEVELS];	/* readahead bits */
+	uint8_t		bc_ra[XFS_BTREE_MAXLEVELS];	/* readahead bits */
 #define	XFS_BTCUR_LEFTRA	1	/* left sibling has been read-ahead */
 #define	XFS_BTCUR_RIGHTRA	2	/* right sibling has been read-ahead */
-	__uint8_t	bc_nlevels;	/* number of levels in the tree */
-	__uint8_t	bc_blocklog;	/* log2(blocksize) of btree blocks */
+	uint8_t		bc_nlevels;	/* number of levels in the tree */
+	uint8_t		bc_blocklog;	/* log2(blocksize) of btree blocks */
 	xfs_btnum_t	bc_btnum;	/* identifies which btree type */
 	int		bc_statoff;	/* offset of btre stats array */
 	union {
@@ -330,7 +330,7 @@ xfs_btree_islastblock(
  */
 void
 xfs_btree_offsets(
-	__int64_t		fields,	/* bitmask of fields */
+	int64_t			fields,	/* bitmask of fields */
 	const short		*offsets,/* table of field offsets */
 	int			nbits,	/* number of bits to inspect */
 	int			*first,	/* output: first byte offset */
@@ -408,7 +408,7 @@ int xfs_btree_new_iroot(struct xfs_btree_cur *, int *, int *);
 int xfs_btree_insert(struct xfs_btree_cur *, int *);
 int xfs_btree_delete(struct xfs_btree_cur *, int *);
 int xfs_btree_get_rec(struct xfs_btree_cur *, union xfs_btree_rec **, int *);
-int xfs_btree_change_owner(struct xfs_btree_cur *cur, __uint64_t new_owner,
+int xfs_btree_change_owner(struct xfs_btree_cur *cur, uint64_t new_owner,
 			   struct list_head *buffer_list);
 
 /*
@@ -434,7 +434,7 @@ static inline int xfs_btree_get_numrecs(struct xfs_btree_block *block)
 }
 
 static inline void xfs_btree_set_numrecs(struct xfs_btree_block *block,
-		__uint16_t numrecs)
+		uint16_t numrecs)
 {
 	block->bb_numrecs = cpu_to_be16(numrecs);
 }
diff --git a/fs/xfs/libxfs/xfs_cksum.h b/fs/xfs/libxfs/xfs_cksum.h
index a416c7cb23ea..8211f48b98e6 100644
--- a/fs/xfs/libxfs/xfs_cksum.h
+++ b/fs/xfs/libxfs/xfs_cksum.h
@@ -1,7 +1,7 @@
 #ifndef _XFS_CKSUM_H
 #define _XFS_CKSUM_H 1
 
-#define XFS_CRC_SEED	(~(__uint32_t)0)
+#define XFS_CRC_SEED	(~(uint32_t)0)
 
 /*
  * Calculate the intermediate checksum for a buffer that has the CRC field
@@ -9,11 +9,11 @@
  * cksum_offset parameter. We do not modify the buffer during verification,
  * hence we have to split the CRC calculation across the cksum_offset.
  */
-static inline __uint32_t
+static inline uint32_t
 xfs_start_cksum_safe(char *buffer, size_t length, unsigned long cksum_offset)
 {
-	__uint32_t zero = 0;
-	__uint32_t crc;
+	uint32_t zero = 0;
+	uint32_t crc;
 
 	/* Calculate CRC up to the checksum. */
 	crc = crc32c(XFS_CRC_SEED, buffer, cksum_offset);
@@ -30,7 +30,7 @@ xfs_start_cksum_safe(char *buffer, size_t length, unsigned long cksum_offset)
  * Fast CRC method where the buffer is modified. Callers must have exclusive
  * access to the buffer while the calculation takes place.
  */
-static inline __uint32_t
+static inline uint32_t
 xfs_start_cksum_update(char *buffer, size_t length, unsigned long cksum_offset)
 {
 	/* zero the CRC field */
@@ -48,7 +48,7 @@ xfs_start_cksum_update(char *buffer, size_t length, unsigned long cksum_offset)
  * so that it is consistent on disk.
  */
 static inline __le32
-xfs_end_cksum(__uint32_t crc)
+xfs_end_cksum(uint32_t crc)
 {
 	return ~cpu_to_le32(crc);
 }
@@ -62,7 +62,7 @@ xfs_end_cksum(__uint32_t crc)
 static inline void
 xfs_update_cksum(char *buffer, size_t length, unsigned long cksum_offset)
 {
-	__uint32_t crc = xfs_start_cksum_update(buffer, length, cksum_offset);
+	uint32_t crc = xfs_start_cksum_update(buffer, length, cksum_offset);
 
 	*(__le32 *)(buffer + cksum_offset) = xfs_end_cksum(crc);
 }
@@ -73,7 +73,7 @@ xfs_update_cksum(char *buffer, size_t length, unsigned long cksum_offset)
 static inline int
 xfs_verify_cksum(char *buffer, size_t length, unsigned long cksum_offset)
 {
-	__uint32_t crc = xfs_start_cksum_safe(buffer, length, cksum_offset);
+	uint32_t crc = xfs_start_cksum_safe(buffer, length, cksum_offset);
 
 	return *(__le32 *)(buffer + cksum_offset) == xfs_end_cksum(crc);
 }
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 1bdf2888295b..48f1136b80bf 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -1952,7 +1952,7 @@ xfs_da3_path_shift(
  * This is implemented with some source-level loop unrolling.
  */
 xfs_dahash_t
-xfs_da_hashname(const __uint8_t *name, int namelen)
+xfs_da_hashname(const uint8_t *name, int namelen)
 {
 	xfs_dahash_t hash;
 
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 4e29cb6a3627..ae6de17467f2 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -60,10 +60,10 @@ enum xfs_dacmp {
  */
 typedef struct xfs_da_args {
 	struct xfs_da_geometry *geo;	/* da block geometry */
-	const __uint8_t	*name;		/* string (maybe not NULL terminated) */
+	const uint8_t		*name;		/* string (maybe not NULL terminated) */
 	int		namelen;	/* length of string (maybe no NULL) */
-	__uint8_t	filetype;	/* filetype of inode for directories */
-	__uint8_t	*value;		/* set of bytes (maybe contain NULLs) */
+	uint8_t		filetype;	/* filetype of inode for directories */
+	uint8_t		*value;		/* set of bytes (maybe contain NULLs) */
 	int		valuelen;	/* length of value */
 	int		flags;		/* argument flags (eg: ATTR_NOCREATE) */
 	xfs_dahash_t	hashval;	/* hash value of name */
@@ -207,7 +207,7 @@ int	xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 					  struct xfs_buf *dead_buf);
 
-uint xfs_da_hashname(const __uint8_t *name_string, int name_length);
+uint xfs_da_hashname(const uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
 				const unsigned char *name, int len);
 
diff --git a/fs/xfs/libxfs/xfs_da_format.c b/fs/xfs/libxfs/xfs_da_format.c
index f1e8d4dbb600..6d77d1a8498a 100644
--- a/fs/xfs/libxfs/xfs_da_format.c
+++ b/fs/xfs/libxfs/xfs_da_format.c
@@ -49,7 +49,7 @@ xfs_dir3_sf_entsize(
 	struct xfs_dir2_sf_hdr	*hdr,
 	int			len)
 {
-	return xfs_dir2_sf_entsize(hdr, len) + sizeof(__uint8_t);
+	return xfs_dir2_sf_entsize(hdr, len) + sizeof(uint8_t);
 }
 
 static struct xfs_dir2_sf_entry *
@@ -77,7 +77,7 @@ xfs_dir3_sf_nextentry(
  * not necessary. For non-filetype enable directories, the type is always
  * unknown and we never store the value.
  */
-static __uint8_t
+static uint8_t
 xfs_dir2_sfe_get_ftype(
 	struct xfs_dir2_sf_entry *sfep)
 {
@@ -87,16 +87,16 @@ xfs_dir2_sfe_get_ftype(
 static void
 xfs_dir2_sfe_put_ftype(
 	struct xfs_dir2_sf_entry *sfep,
-	__uint8_t		ftype)
+	uint8_t			ftype)
 {
 	ASSERT(ftype < XFS_DIR3_FT_MAX);
 }
 
-static __uint8_t
+static uint8_t
 xfs_dir3_sfe_get_ftype(
 	struct xfs_dir2_sf_entry *sfep)
 {
-	__uint8_t	ftype;
+	uint8_t		ftype;
 
 	ftype = sfep->name[sfep->namelen];
 	if (ftype >= XFS_DIR3_FT_MAX)
@@ -107,7 +107,7 @@ xfs_dir3_sfe_get_ftype(
 static void
 xfs_dir3_sfe_put_ftype(
 	struct xfs_dir2_sf_entry *sfep,
-	__uint8_t		ftype)
+	uint8_t			ftype)
 {
 	ASSERT(ftype < XFS_DIR3_FT_MAX);
 
@@ -124,7 +124,7 @@ xfs_dir3_sfe_put_ftype(
 static xfs_ino_t
 xfs_dir2_sf_get_ino(
 	struct xfs_dir2_sf_hdr	*hdr,
-	__uint8_t		*from)
+	uint8_t			*from)
 {
 	if (hdr->i8count)
 		return get_unaligned_be64(from) & 0x00ffffffffffffffULL;
@@ -135,7 +135,7 @@ xfs_dir2_sf_get_ino(
 static void
 xfs_dir2_sf_put_ino(
 	struct xfs_dir2_sf_hdr	*hdr,
-	__uint8_t		*to,
+	uint8_t			*to,
 	xfs_ino_t		ino)
 {
 	ASSERT((ino & 0xff00000000000000ULL) == 0);
@@ -225,7 +225,7 @@ xfs_dir3_sfe_put_ino(
 
 #define XFS_DIR3_DATA_ENTSIZE(n)					\
 	round_up((offsetof(struct xfs_dir2_data_entry, name[0]) + (n) +	\
-		 sizeof(xfs_dir2_data_off_t) + sizeof(__uint8_t)),	\
+		 sizeof(xfs_dir2_data_off_t) + sizeof(uint8_t)),	\
 		XFS_DIR2_DATA_ALIGN)
 
 static int
@@ -242,7 +242,7 @@ xfs_dir3_data_entsize(
 	return XFS_DIR3_DATA_ENTSIZE(n);
 }
 
-static __uint8_t
+static uint8_t
 xfs_dir2_data_get_ftype(
 	struct xfs_dir2_data_entry *dep)
 {
@@ -252,16 +252,16 @@ xfs_dir2_data_get_ftype(
 static void
 xfs_dir2_data_put_ftype(
 	struct xfs_dir2_data_entry *dep,
-	__uint8_t		ftype)
+	uint8_t			ftype)
 {
 	ASSERT(ftype < XFS_DIR3_FT_MAX);
 }
 
-static __uint8_t
+static uint8_t
 xfs_dir3_data_get_ftype(
 	struct xfs_dir2_data_entry *dep)
 {
-	__uint8_t	ftype = dep->name[dep->namelen];
+	uint8_t		ftype = dep->name[dep->namelen];
 
 	if (ftype >= XFS_DIR3_FT_MAX)
 		return XFS_DIR3_FT_UNKNOWN;
@@ -271,7 +271,7 @@ xfs_dir3_data_get_ftype(
 static void
 xfs_dir3_data_put_ftype(
 	struct xfs_dir2_data_entry *dep,
-	__uint8_t		type)
+	uint8_t			type)
 {
 	ASSERT(type < XFS_DIR3_FT_MAX);
 	ASSERT(dep->namelen != 0);
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 9a492a9e19bd..3771edcb301d 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -111,11 +111,11 @@ struct xfs_da3_intnode {
  * appropriate.
  */
 struct xfs_da3_icnode_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	level;
+	uint32_t	forw;
+	uint32_t	back;
+	uint16_t	magic;
+	uint16_t	count;
+	uint16_t	level;
 };
 
 /*
@@ -187,14 +187,14 @@ struct xfs_da3_icnode_hdr {
 /*
  * Byte offset in data block and shortform entry.
  */
-typedef	__uint16_t	xfs_dir2_data_off_t;
+typedef uint16_t	xfs_dir2_data_off_t;
 #define	NULLDATAOFF	0xffffU
 typedef uint		xfs_dir2_data_aoff_t;	/* argument form */
 
 /*
  * Offset in data space of a data entry.
  */
-typedef	__uint32_t	xfs_dir2_dataptr_t;
+typedef uint32_t	xfs_dir2_dataptr_t;
 #define	XFS_DIR2_MAX_DATAPTR	((xfs_dir2_dataptr_t)0xffffffff)
 #define	XFS_DIR2_NULL_DATAPTR	((xfs_dir2_dataptr_t)0)
 
@@ -206,7 +206,7 @@ typedef	xfs_off_t	xfs_dir2_off_t;
 /*
  * Directory block number (logical dirblk in file)
  */
-typedef	__uint32_t	xfs_dir2_db_t;
+typedef uint32_t	xfs_dir2_db_t;
 
 #define XFS_INO32_SIZE	4
 #define XFS_INO64_SIZE	8
@@ -226,9 +226,9 @@ typedef	__uint32_t	xfs_dir2_db_t;
  * over them.
  */
 typedef struct xfs_dir2_sf_hdr {
-	__uint8_t		count;		/* count of entries */
-	__uint8_t		i8count;	/* count of 8-byte inode #s */
-	__uint8_t		parent[8];	/* parent dir inode number */
+	uint8_t			count;		/* count of entries */
+	uint8_t			i8count;	/* count of 8-byte inode #s */
+	uint8_t			parent[8];	/* parent dir inode number */
 } __packed xfs_dir2_sf_hdr_t;
 
 typedef struct xfs_dir2_sf_entry {
@@ -447,11 +447,11 @@ struct xfs_dir3_leaf_hdr {
 };
 
 struct xfs_dir3_icleaf_hdr {
-	__uint32_t		forw;
-	__uint32_t		back;
-	__uint16_t		magic;
-	__uint16_t		count;
-	__uint16_t		stale;
+	uint32_t		forw;
+	uint32_t		back;
+	uint16_t		magic;
+	uint16_t		count;
+	uint16_t		stale;
 };
 
 /*
@@ -538,10 +538,10 @@ struct xfs_dir3_free {
  * xfs_dir3_free_hdr_from_disk/xfs_dir3_free_hdr_to_disk.
  */
 struct xfs_dir3_icfree_hdr {
-	__uint32_t	magic;
-	__uint32_t	firstdb;
-	__uint32_t	nvalid;
-	__uint32_t	nused;
+	uint32_t	magic;
+	uint32_t	firstdb;
+	uint32_t	nvalid;
+	uint32_t	nused;
 
 };
 
@@ -632,10 +632,10 @@ typedef struct xfs_attr_shortform {
 		__u8	padding;
 	} hdr;
 	struct xfs_attr_sf_entry {
-		__uint8_t namelen;	/* actual length of name (no NULL) */
-		__uint8_t valuelen;	/* actual length of value (no NULL) */
-		__uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
-		__uint8_t nameval[1];	/* name & value bytes concatenated */
+		uint8_t namelen;	/* actual length of name (no NULL) */
+		uint8_t valuelen;	/* actual length of value (no NULL) */
+		uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
+		uint8_t nameval[1];	/* name & value bytes concatenated */
 	} list[1];			/* variable sized array */
 } xfs_attr_shortform_t;
 
@@ -725,22 +725,22 @@ struct xfs_attr3_leafblock {
  * incore, neutral version of the attribute leaf header
  */
 struct xfs_attr3_icleaf_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	usedbytes;
+	uint32_t	forw;
+	uint32_t	back;
+	uint16_t	magic;
+	uint16_t	count;
+	uint16_t	usedbytes;
 	/*
 	 * firstused is 32-bit here instead of 16-bit like the on-disk variant
 	 * to support maximum fsb size of 64k without overflow issues throughout
 	 * the attr code. Instead, the overflow condition is handled on
 	 * conversion to/from disk.
 	 */
-	__uint32_t	firstused;
+	uint32_t	firstused;
 	__u8		holes;
 	struct {
-		__uint16_t	base;
-		__uint16_t	size;
+		uint16_t	base;
+		uint16_t	size;
 	} freemap[XFS_ATTR_LEAF_MAPSIZE];
 };
 
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index d6e6d9d16f6c..21c8f8bf94d5 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -47,9 +47,9 @@ struct xfs_dir_ops {
 	struct xfs_dir2_sf_entry *
 		(*sf_nextentry)(struct xfs_dir2_sf_hdr *hdr,
 				struct xfs_dir2_sf_entry *sfep);
-	__uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep);
+	uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep);
 	void	(*sf_put_ftype)(struct xfs_dir2_sf_entry *sfep,
-				__uint8_t ftype);
+				uint8_t ftype);
 	xfs_ino_t (*sf_get_ino)(struct xfs_dir2_sf_hdr *hdr,
 				struct xfs_dir2_sf_entry *sfep);
 	void	(*sf_put_ino)(struct xfs_dir2_sf_hdr *hdr,
@@ -60,9 +60,9 @@ struct xfs_dir_ops {
 				     xfs_ino_t ino);
 
 	int	(*data_entsize)(int len);
-	__uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep);
+	uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep);
 	void	(*data_put_ftype)(struct xfs_dir2_data_entry *dep,
-				__uint8_t ftype);
+				uint8_t ftype);
 	__be16 * (*data_entry_tag_p)(struct xfs_dir2_data_entry *dep);
 	struct xfs_dir2_data_free *
 		(*data_bestfree_p)(struct xfs_dir2_data_hdr *hdr);
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index b887fb2a2bcf..68bf3e860a90 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -145,7 +145,7 @@ xfs_dir3_leaf_check_int(
 static bool
 xfs_dir3_leaf_verify(
 	struct xfs_buf		*bp,
-	__uint16_t		magic)
+	uint16_t		magic)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
@@ -154,7 +154,7 @@ xfs_dir3_leaf_verify(
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
-		__uint16_t		magic3;
+		uint16_t		magic3;
 
 		magic3 = (magic == XFS_DIR2_LEAF1_MAGIC) ? XFS_DIR3_LEAF1_MAGIC
 							 : XFS_DIR3_LEAFN_MAGIC;
@@ -178,7 +178,7 @@ xfs_dir3_leaf_verify(
 static void
 __read_verify(
 	struct xfs_buf  *bp,
-	__uint16_t	magic)
+	uint16_t	magic)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
@@ -195,7 +195,7 @@ __read_verify(
 static void
 __write_verify(
 	struct xfs_buf  *bp,
-	__uint16_t	magic)
+	uint16_t	magic)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_buf_log_item	*bip = bp->b_fspriv;
@@ -299,7 +299,7 @@ xfs_dir3_leaf_init(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*bp,
 	xfs_ino_t		owner,
-	__uint16_t		type)
+	uint16_t		type)
 {
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
 
@@ -343,7 +343,7 @@ xfs_dir3_leaf_get_buf(
 	xfs_da_args_t		*args,
 	xfs_dir2_db_t		bno,
 	struct xfs_buf		**bpp,
-	__uint16_t		magic)
+	uint16_t		magic)
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_trans	*tp = args->trans;
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 39f8604f764e..011df4da6cc2 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -69,7 +69,7 @@ extern void xfs_dir3_leaf_compact_x1(struct xfs_dir3_icleaf_hdr *leafhdr,
 		struct xfs_dir2_leaf_entry *ents, int *indexp,
 		int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
 extern int xfs_dir3_leaf_get_buf(struct xfs_da_args *args, xfs_dir2_db_t bno,
-		struct xfs_buf **bpp, __uint16_t magic);
+		struct xfs_buf **bpp, uint16_t magic);
 extern void xfs_dir3_leaf_log_ents(struct xfs_da_args *args,
 		struct xfs_buf *bp, int first, int last);
 extern void xfs_dir3_leaf_log_header(struct xfs_da_args *args,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index e84af093b2ab..be8b9755f66a 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -647,7 +647,7 @@ xfs_dir2_sf_verify(
 	int				offset;
 	int				size;
 	int				error;
-	__uint8_t			filetype;
+	uint8_t				filetype;
 
 	ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
 	/*
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index a1dccd8d96bc..e204a942e5bf 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -103,8 +103,8 @@ struct xfs_ifork;
  * Must be padded to 64 bit alignment.
  */
 typedef struct xfs_sb {
-	__uint32_t	sb_magicnum;	/* magic number == XFS_SB_MAGIC */
-	__uint32_t	sb_blocksize;	/* logical block size, bytes */
+	uint32_t	sb_magicnum;	/* magic number == XFS_SB_MAGIC */
+	uint32_t	sb_blocksize;	/* logical block size, bytes */
 	xfs_rfsblock_t	sb_dblocks;	/* number of data blocks */
 	xfs_rfsblock_t	sb_rblocks;	/* number of realtime blocks */
 	xfs_rtblock_t	sb_rextents;	/* number of realtime extents */
@@ -118,45 +118,45 @@ typedef struct xfs_sb {
 	xfs_agnumber_t	sb_agcount;	/* number of allocation groups */
 	xfs_extlen_t	sb_rbmblocks;	/* number of rt bitmap blocks */
 	xfs_extlen_t	sb_logblocks;	/* number of log blocks */
-	__uint16_t	sb_versionnum;	/* header version == XFS_SB_VERSION */
-	__uint16_t	sb_sectsize;	/* volume sector size, bytes */
-	__uint16_t	sb_inodesize;	/* inode size, bytes */
-	__uint16_t	sb_inopblock;	/* inodes per block */
+	uint16_t	sb_versionnum;	/* header version == XFS_SB_VERSION */
+	uint16_t	sb_sectsize;	/* volume sector size, bytes */
+	uint16_t	sb_inodesize;	/* inode size, bytes */
+	uint16_t	sb_inopblock;	/* inodes per block */
 	char		sb_fname[12];	/* file system name */
-	__uint8_t	sb_blocklog;	/* log2 of sb_blocksize */
-	__uint8_t	sb_sectlog;	/* log2 of sb_sectsize */
-	__uint8_t	sb_inodelog;	/* log2 of sb_inodesize */
-	__uint8_t	sb_inopblog;	/* log2 of sb_inopblock */
-	__uint8_t	sb_agblklog;	/* log2 of sb_agblocks (rounded up) */
-	__uint8_t	sb_rextslog;	/* log2 of sb_rextents */
-	__uint8_t	sb_inprogress;	/* mkfs is in progress, don't mount */
-	__uint8_t	sb_imax_pct;	/* max % of fs for inode space */
+	uint8_t		sb_blocklog;	/* log2 of sb_blocksize */
+	uint8_t		sb_sectlog;	/* log2 of sb_sectsize */
+	uint8_t		sb_inodelog;	/* log2 of sb_inodesize */
+	uint8_t		sb_inopblog;	/* log2 of sb_inopblock */
+	uint8_t		sb_agblklog;	/* log2 of sb_agblocks (rounded up) */
+	uint8_t		sb_rextslog;	/* log2 of sb_rextents */
+	uint8_t		sb_inprogress;	/* mkfs is in progress, don't mount */
+	uint8_t		sb_imax_pct;	/* max % of fs for inode space */
 					/* statistics */
 	/*
 	 * These fields must remain contiguous.  If you really
 	 * want to change their layout, make sure you fix the
 	 * code in xfs_trans_apply_sb_deltas().
 	 */
-	__uint64_t	sb_icount;	/* allocated inodes */
-	__uint64_t	sb_ifree;	/* free inodes */
-	__uint64_t	sb_fdblocks;	/* free data blocks */
-	__uint64_t	sb_frextents;	/* free realtime extents */
+	uint64_t	sb_icount;	/* allocated inodes */
+	uint64_t	sb_ifree;	/* free inodes */
+	uint64_t	sb_fdblocks;	/* free data blocks */
+	uint64_t	sb_frextents;	/* free realtime extents */
 	/*
 	 * End contiguous fields.
 	 */
 	xfs_ino_t	sb_uquotino;	/* user quota inode */
 	xfs_ino_t	sb_gquotino;	/* group quota inode */
-	__uint16_t	sb_qflags;	/* quota flags */
-	__uint8_t	sb_flags;	/* misc. flags */
-	__uint8_t	sb_shared_vn;	/* shared version number */
+	uint16_t	sb_qflags;	/* quota flags */
+	uint8_t		sb_flags;	/* misc. flags */
+	uint8_t		sb_shared_vn;	/* shared version number */
 	xfs_extlen_t	sb_inoalignmt;	/* inode chunk alignment, fsblocks */
-	__uint32_t	sb_unit;	/* stripe or raid unit */
-	__uint32_t	sb_width;	/* stripe or raid width */
-	__uint8_t	sb_dirblklog;	/* log2 of dir block size (fsbs) */
-	__uint8_t	sb_logsectlog;	/* log2 of the log sector size */
-	__uint16_t	sb_logsectsize;	/* sector size for the log, bytes */
-	__uint32_t	sb_logsunit;	/* stripe unit size for the log */
-	__uint32_t	sb_features2;	/* additional feature bits */
+	uint32_t	sb_unit;	/* stripe or raid unit */
+	uint32_t	sb_width;	/* stripe or raid width */
+	uint8_t		sb_dirblklog;	/* log2 of dir block size (fsbs) */
+	uint8_t		sb_logsectlog;	/* log2 of the log sector size */
+	uint16_t	sb_logsectsize;	/* sector size for the log, bytes */
+	uint32_t	sb_logsunit;	/* stripe unit size for the log */
+	uint32_t	sb_features2;	/* additional feature bits */
 
 	/*
 	 * bad features2 field as a result of failing to pad the sb structure to
@@ -167,17 +167,17 @@ typedef struct xfs_sb {
 	 * the value in sb_features2 when formatting the incore superblock to
 	 * the disk buffer.
 	 */
-	__uint32_t	sb_bad_features2;
+	uint32_t	sb_bad_features2;
 
 	/* version 5 superblock fields start here */
 
 	/* feature masks */
-	__uint32_t	sb_features_compat;
-	__uint32_t	sb_features_ro_compat;
-	__uint32_t	sb_features_incompat;
-	__uint32_t	sb_features_log_incompat;
+	uint32_t	sb_features_compat;
+	uint32_t	sb_features_ro_compat;
+	uint32_t	sb_features_incompat;
+	uint32_t	sb_features_log_incompat;
 
-	__uint32_t	sb_crc;		/* superblock crc */
+	uint32_t	sb_crc;		/* superblock crc */
 	xfs_extlen_t	sb_spino_align;	/* sparse inode chunk alignment */
 
 	xfs_ino_t	sb_pquotino;	/* project quota inode */
@@ -449,7 +449,7 @@ static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp)
 static inline bool
 xfs_sb_has_compat_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_compat & feature) != 0;
 }
@@ -465,7 +465,7 @@ xfs_sb_has_compat_feature(
 static inline bool
 xfs_sb_has_ro_compat_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_ro_compat & feature) != 0;
 }
@@ -482,7 +482,7 @@ xfs_sb_has_ro_compat_feature(
 static inline bool
 xfs_sb_has_incompat_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_incompat & feature) != 0;
 }
@@ -492,7 +492,7 @@ xfs_sb_has_incompat_feature(
 static inline bool
 xfs_sb_has_incompat_log_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_log_incompat & feature) != 0;
 }
@@ -594,8 +594,8 @@ xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
  */
 #define XFS_FSB_TO_B(mp,fsbno)	((xfs_fsize_t)(fsbno) << (mp)->m_sb.sb_blocklog)
 #define XFS_B_TO_FSB(mp,b)	\
-	((((__uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog)
-#define XFS_B_TO_FSBT(mp,b)	(((__uint64_t)(b)) >> (mp)->m_sb.sb_blocklog)
+	((((uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog)
+#define XFS_B_TO_FSBT(mp,b)	(((uint64_t)(b)) >> (mp)->m_sb.sb_blocklog)
 #define XFS_B_FSB_OFFSET(mp,b)	((b) & (mp)->m_blockmask)
 
 /*
@@ -1072,7 +1072,7 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
  * next agno_log bits - ag number
  * high agno_log-agblklog-inopblog bits - 0
  */
-#define	XFS_INO_MASK(k)			(__uint32_t)((1ULL << (k)) - 1)
+#define	XFS_INO_MASK(k)			(uint32_t)((1ULL << (k)) - 1)
 #define	XFS_INO_OFFSET_BITS(mp)		(mp)->m_sb.sb_inopblog
 #define	XFS_INO_AGBNO_BITS(mp)		(mp)->m_sb.sb_agblklog
 #define	XFS_INO_AGINO_BITS(mp)		(mp)->m_agino_log
@@ -1269,16 +1269,16 @@ typedef __be32 xfs_alloc_ptr_t;
 #define	XFS_FIBT_MAGIC		0x46494254	/* 'FIBT' */
 #define	XFS_FIBT_CRC_MAGIC	0x46494233	/* 'FIB3' */
 
-typedef	__uint64_t	xfs_inofree_t;
+typedef uint64_t	xfs_inofree_t;
 #define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
 #define	XFS_INODES_PER_CHUNK_LOG	(XFS_NBBYLOG + 3)
 #define	XFS_INOBT_ALL_FREE		((xfs_inofree_t)-1)
 #define	XFS_INOBT_MASK(i)		((xfs_inofree_t)1 << (i))
 
 #define XFS_INOBT_HOLEMASK_FULL		0	/* holemask for full chunk */
-#define XFS_INOBT_HOLEMASK_BITS		(NBBY * sizeof(__uint16_t))
+#define XFS_INOBT_HOLEMASK_BITS		(NBBY * sizeof(uint16_t))
 #define XFS_INODES_PER_HOLEMASK_BIT	\
-	(XFS_INODES_PER_CHUNK / (NBBY * sizeof(__uint16_t)))
+	(XFS_INODES_PER_CHUNK / (NBBY * sizeof(uint16_t)))
 
 static inline xfs_inofree_t xfs_inobt_maskn(int i, int n)
 {
@@ -1312,9 +1312,9 @@ typedef struct xfs_inobt_rec {
 
 typedef struct xfs_inobt_rec_incore {
 	xfs_agino_t	ir_startino;	/* starting inode number */
-	__uint16_t	ir_holemask;	/* hole mask for sparse chunks */
-	__uint8_t	ir_count;	/* total inode count */
-	__uint8_t	ir_freecount;	/* count of free inodes (set bits) */
+	uint16_t	ir_holemask;	/* hole mask for sparse chunks */
+	uint8_t		ir_count;	/* total inode count */
+	uint8_t		ir_freecount;	/* count of free inodes (set bits) */
 	xfs_inofree_t	ir_free;	/* free inode mask */
 } xfs_inobt_rec_incore_t;
 
@@ -1397,15 +1397,15 @@ struct xfs_rmap_rec {
  *  rm_offset:54-60 aren't used and should be zero
  *  rm_offset:0-53 is the block offset within the inode
  */
-#define XFS_RMAP_OFF_ATTR_FORK	((__uint64_t)1ULL << 63)
-#define XFS_RMAP_OFF_BMBT_BLOCK	((__uint64_t)1ULL << 62)
-#define XFS_RMAP_OFF_UNWRITTEN	((__uint64_t)1ULL << 61)
+#define XFS_RMAP_OFF_ATTR_FORK	((uint64_t)1ULL << 63)
+#define XFS_RMAP_OFF_BMBT_BLOCK	((uint64_t)1ULL << 62)
+#define XFS_RMAP_OFF_UNWRITTEN	((uint64_t)1ULL << 61)
 
-#define XFS_RMAP_LEN_MAX	((__uint32_t)~0U)
+#define XFS_RMAP_LEN_MAX	((uint32_t)~0U)
 #define XFS_RMAP_OFF_FLAGS	(XFS_RMAP_OFF_ATTR_FORK | \
 				 XFS_RMAP_OFF_BMBT_BLOCK | \
 				 XFS_RMAP_OFF_UNWRITTEN)
-#define XFS_RMAP_OFF_MASK	((__uint64_t)0x3FFFFFFFFFFFFFULL)
+#define XFS_RMAP_OFF_MASK	((uint64_t)0x3FFFFFFFFFFFFFULL)
 
 #define XFS_RMAP_OFF(off)		((off) & XFS_RMAP_OFF_MASK)
 
@@ -1431,8 +1431,8 @@ struct xfs_rmap_rec {
 struct xfs_rmap_irec {
 	xfs_agblock_t	rm_startblock;	/* extent start block */
 	xfs_extlen_t	rm_blockcount;	/* extent length */
-	__uint64_t	rm_owner;	/* extent owner */
-	__uint64_t	rm_offset;	/* offset within the owner */
+	uint64_t	rm_owner;	/* extent owner */
+	uint64_t	rm_offset;	/* offset within the owner */
 	unsigned int	rm_flags;	/* state flags */
 };
 
@@ -1544,11 +1544,11 @@ typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;
 } xfs_bmbt_rec_t;
 
-typedef __uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
+typedef uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
 typedef xfs_bmbt_rec_t xfs_bmdr_rec_t;
 
 typedef struct xfs_bmbt_rec_host {
-	__uint64_t		l0, l1;
+	uint64_t		l0, l1;
 } xfs_bmbt_rec_host_t;
 
 /*
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index a9aa13e66046..8c61f21535d4 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -302,10 +302,10 @@ typedef struct xfs_bstat {
  * and using two 16bit values to hold new 32bit projid was choosen
  * to retain compatibility with "old" filesystems).
  */
-static inline __uint32_t
+static inline uint32_t
 bstat_get_projid(struct xfs_bstat *bs)
 {
-	return (__uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo;
+	return (uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo;
 }
 
 /*
@@ -451,10 +451,10 @@ typedef struct xfs_handle {
  */
 typedef struct xfs_swapext
 {
-	__int64_t	sx_version;	/* version */
+	int64_t		sx_version;	/* version */
 #define XFS_SX_VERSION		0
-	__int64_t	sx_fdtarget;	/* fd of target file */
-	__int64_t	sx_fdtmp;	/* fd of tmp file */
+	int64_t		sx_fdtarget;	/* fd of target file */
+	int64_t		sx_fdtmp;	/* fd of tmp file */
 	xfs_off_t	sx_offset;	/* offset into file */
 	xfs_off_t	sx_length;	/* leng from offset */
 	char		sx_pad[16];	/* pad space, unused */
@@ -542,7 +542,7 @@ typedef struct xfs_swapext
 #define XFS_IOC_ATTRLIST_BY_HANDLE   _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq)
 #define XFS_IOC_ATTRMULTI_BY_HANDLE  _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq)
 #define XFS_IOC_FSGEOMETRY	     _IOR ('X', 124, struct xfs_fsop_geom)
-#define XFS_IOC_GOINGDOWN	     _IOR ('X', 125, __uint32_t)
+#define XFS_IOC_GOINGDOWN	     _IOR ('X', 125, uint32_t)
 /*	XFS_IOC_GETFSUUID ---------- deprecated 140	 */
 
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index d41ade5d293e..1e5ed940b84d 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -140,9 +140,9 @@ xfs_inobt_get_rec(
 STATIC int
 xfs_inobt_insert_rec(
 	struct xfs_btree_cur	*cur,
-	__uint16_t		holemask,
-	__uint8_t		count,
-	__int32_t		freecount,
+	uint16_t		holemask,
+	uint8_t			count,
+	int32_t			freecount,
 	xfs_inofree_t		free,
 	int			*stat)
 {
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 7c471881c9a6..ed52d99732b8 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -219,12 +219,12 @@ xfs_finobt_init_ptr_from_cur(
 	ptr->s = agi->agi_free_root;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_inobt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
 {
-	return (__int64_t)be32_to_cpu(key->inobt.ir_startino) -
+	return (int64_t)be32_to_cpu(key->inobt.ir_startino) -
 			  cur->bc_rec.i.ir_startino;
 }
 
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 09c3d1aecef2..d887af940f09 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -444,7 +444,7 @@ xfs_dinode_calc_crc(
 	struct xfs_mount	*mp,
 	struct xfs_dinode	*dip)
 {
-	__uint32_t		crc;
+	uint32_t		crc;
 
 	if (dip->di_version < 3)
 		return;
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 6848a0afbce7..0827d7def1ce 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -28,26 +28,26 @@ struct xfs_dinode;
  * format specific structures at the appropriate time.
  */
 struct xfs_icdinode {
-	__int8_t	di_version;	/* inode version */
-	__int8_t	di_format;	/* format of di_c data */
-	__uint16_t	di_flushiter;	/* incremented on flush */
-	__uint32_t	di_uid;		/* owner's user id */
-	__uint32_t	di_gid;		/* owner's group id */
-	__uint16_t	di_projid_lo;	/* lower part of owner's project id */
-	__uint16_t	di_projid_hi;	/* higher part of owner's project id */
+	int8_t		di_version;	/* inode version */
+	int8_t		di_format;	/* format of di_c data */
+	uint16_t	di_flushiter;	/* incremented on flush */
+	uint32_t	di_uid;		/* owner's user id */
+	uint32_t	di_gid;		/* owner's group id */
+	uint16_t	di_projid_lo;	/* lower part of owner's project id */
+	uint16_t	di_projid_hi;	/* higher part of owner's project id */
 	xfs_fsize_t	di_size;	/* number of bytes in file */
 	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
 	xfs_extnum_t	di_nextents;	/* number of extents in data fork */
 	xfs_aextnum_t	di_anextents;	/* number of extents in attribute fork*/
-	__uint8_t	di_forkoff;	/* attr fork offs, <<3 for 64b align */
-	__int8_t	di_aformat;	/* format of attr fork's data */
-	__uint32_t	di_dmevmask;	/* DMIG event mask */
-	__uint16_t	di_dmstate;	/* DMIG state info */
-	__uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
+	uint8_t		di_forkoff;	/* attr fork offs, <<3 for 64b align */
+	int8_t		di_aformat;	/* format of attr fork's data */
+	uint32_t	di_dmevmask;	/* DMIG event mask */
+	uint16_t	di_dmstate;	/* DMIG state info */
+	uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
 
-	__uint64_t	di_flags2;	/* more random flags */
-	__uint32_t	di_cowextsize;	/* basic cow extent size for file */
+	uint64_t	di_flags2;	/* more random flags */
+	uint32_t	di_cowextsize;	/* basic cow extent size for file */
 
 	xfs_ictimestamp_t di_crtime;	/* time created */
 };
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 7ae571f8e34a..8372e9bcd7b6 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -31,7 +31,7 @@ struct xfs_trans_res;
  * through all the log items definitions and everything they encode into the
  * log.
  */
-typedef __uint32_t xlog_tid_t;
+typedef uint32_t xlog_tid_t;
 
 #define XLOG_MIN_ICLOGS		2
 #define XLOG_MAX_ICLOGS		8
@@ -211,7 +211,7 @@ typedef struct xfs_log_iovec {
 typedef struct xfs_trans_header {
 	uint		th_magic;		/* magic number */
 	uint		th_type;		/* transaction type */
-	__int32_t	th_tid;			/* transaction id (unused) */
+	int32_t		th_tid;			/* transaction id (unused) */
 	uint		th_num_items;		/* num items logged by trans */
 } xfs_trans_header_t;
 
@@ -265,52 +265,52 @@ typedef struct xfs_trans_header {
  * must be added on to the end.
  */
 typedef struct xfs_inode_log_format {
-	__uint16_t		ilf_type;	/* inode log item type */
-	__uint16_t		ilf_size;	/* size of this item */
-	__uint32_t		ilf_fields;	/* flags for fields logged */
-	__uint16_t		ilf_asize;	/* size of attr d/ext/root */
-	__uint16_t		ilf_dsize;	/* size of data/ext/root */
-	__uint64_t		ilf_ino;	/* inode number */
+	uint16_t		ilf_type;	/* inode log item type */
+	uint16_t		ilf_size;	/* size of this item */
+	uint32_t		ilf_fields;	/* flags for fields logged */
+	uint16_t		ilf_asize;	/* size of attr d/ext/root */
+	uint16_t		ilf_dsize;	/* size of data/ext/root */
+	uint64_t		ilf_ino;	/* inode number */
 	union {
-		__uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
+		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
 		uuid_t		ilfu_uuid;	/* mount point value */
 	} ilf_u;
-	__int64_t		ilf_blkno;	/* blkno of inode buffer */
-	__int32_t		ilf_len;	/* len of inode buffer */
-	__int32_t		ilf_boffset;	/* off of inode in buffer */
+	int64_t			ilf_blkno;	/* blkno of inode buffer */
+	int32_t			ilf_len;	/* len of inode buffer */
+	int32_t			ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_t;
 
 typedef struct xfs_inode_log_format_32 {
-	__uint16_t		ilf_type;	/* inode log item type */
-	__uint16_t		ilf_size;	/* size of this item */
-	__uint32_t		ilf_fields;	/* flags for fields logged */
-	__uint16_t		ilf_asize;	/* size of attr d/ext/root */
-	__uint16_t		ilf_dsize;	/* size of data/ext/root */
-	__uint64_t		ilf_ino;	/* inode number */
+	uint16_t		ilf_type;	/* inode log item type */
+	uint16_t		ilf_size;	/* size of this item */
+	uint32_t		ilf_fields;	/* flags for fields logged */
+	uint16_t		ilf_asize;	/* size of attr d/ext/root */
+	uint16_t		ilf_dsize;	/* size of data/ext/root */
+	uint64_t		ilf_ino;	/* inode number */
 	union {
-		__uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
+		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
 		uuid_t		ilfu_uuid;	/* mount point value */
 	} ilf_u;
-	__int64_t		ilf_blkno;	/* blkno of inode buffer */
-	__int32_t		ilf_len;	/* len of inode buffer */
-	__int32_t		ilf_boffset;	/* off of inode in buffer */
+	int64_t			ilf_blkno;	/* blkno of inode buffer */
+	int32_t			ilf_len;	/* len of inode buffer */
+	int32_t			ilf_boffset;	/* off of inode in buffer */
 } __attribute__((packed)) xfs_inode_log_format_32_t;
 
 typedef struct xfs_inode_log_format_64 {
-	__uint16_t		ilf_type;	/* inode log item type */
-	__uint16_t		ilf_size;	/* size of this item */
-	__uint32_t		ilf_fields;	/* flags for fields logged */
-	__uint16_t		ilf_asize;	/* size of attr d/ext/root */
-	__uint16_t		ilf_dsize;	/* size of data/ext/root */
-	__uint32_t		ilf_pad;	/* pad for 64 bit boundary */
-	__uint64_t		ilf_ino;	/* inode number */
+	uint16_t		ilf_type;	/* inode log item type */
+	uint16_t		ilf_size;	/* size of this item */
+	uint32_t		ilf_fields;	/* flags for fields logged */
+	uint16_t		ilf_asize;	/* size of attr d/ext/root */
+	uint16_t		ilf_dsize;	/* size of data/ext/root */
+	uint32_t		ilf_pad;	/* pad for 64 bit boundary */
+	uint64_t		ilf_ino;	/* inode number */
 	union {
-		__uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
+		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
 		uuid_t		ilfu_uuid;	/* mount point value */
 	} ilf_u;
-	__int64_t		ilf_blkno;	/* blkno of inode buffer */
-	__int32_t		ilf_len;	/* len of inode buffer */
-	__int32_t		ilf_boffset;	/* off of inode in buffer */
+	int64_t			ilf_blkno;	/* blkno of inode buffer */
+	int32_t			ilf_len;	/* len of inode buffer */
+	int32_t			ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_64_t;
 
 
@@ -379,8 +379,8 @@ static inline int xfs_ilog_fdata(int w)
  * information.
  */
 typedef struct xfs_ictimestamp {
-	__int32_t	t_sec;		/* timestamp seconds */
-	__int32_t	t_nsec;		/* timestamp nanoseconds */
+	int32_t		t_sec;		/* timestamp seconds */
+	int32_t		t_nsec;		/* timestamp nanoseconds */
 } xfs_ictimestamp_t;
 
 /*
@@ -388,18 +388,18 @@ typedef struct xfs_ictimestamp {
  * kept identical to struct xfs_dinode except for the endianness annotations.
  */
 struct xfs_log_dinode {
-	__uint16_t	di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
-	__uint16_t	di_mode;	/* mode and type of file */
-	__int8_t	di_version;	/* inode version */
-	__int8_t	di_format;	/* format of di_c data */
-	__uint8_t	di_pad3[2];	/* unused in v2/3 inodes */
-	__uint32_t	di_uid;		/* owner's user id */
-	__uint32_t	di_gid;		/* owner's group id */
-	__uint32_t	di_nlink;	/* number of links to file */
-	__uint16_t	di_projid_lo;	/* lower part of owner's project id */
-	__uint16_t	di_projid_hi;	/* higher part of owner's project id */
-	__uint8_t	di_pad[6];	/* unused, zeroed space */
-	__uint16_t	di_flushiter;	/* incremented on flush */
+	uint16_t	di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
+	uint16_t	di_mode;	/* mode and type of file */
+	int8_t		di_version;	/* inode version */
+	int8_t		di_format;	/* format of di_c data */
+	uint8_t		di_pad3[2];	/* unused in v2/3 inodes */
+	uint32_t	di_uid;		/* owner's user id */
+	uint32_t	di_gid;		/* owner's group id */
+	uint32_t	di_nlink;	/* number of links to file */
+	uint16_t	di_projid_lo;	/* lower part of owner's project id */
+	uint16_t	di_projid_hi;	/* higher part of owner's project id */
+	uint8_t		di_pad[6];	/* unused, zeroed space */
+	uint16_t	di_flushiter;	/* incremented on flush */
 	xfs_ictimestamp_t di_atime;	/* time last accessed */
 	xfs_ictimestamp_t di_mtime;	/* time last modified */
 	xfs_ictimestamp_t di_ctime;	/* time created/inode modified */
@@ -408,23 +408,23 @@ struct xfs_log_dinode {
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
 	xfs_extnum_t	di_nextents;	/* number of extents in data fork */
 	xfs_aextnum_t	di_anextents;	/* number of extents in attribute fork*/
-	__uint8_t	di_forkoff;	/* attr fork offs, <<3 for 64b align */
-	__int8_t	di_aformat;	/* format of attr fork's data */
-	__uint32_t	di_dmevmask;	/* DMIG event mask */
-	__uint16_t	di_dmstate;	/* DMIG state info */
-	__uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
-	__uint32_t	di_gen;		/* generation number */
+	uint8_t		di_forkoff;	/* attr fork offs, <<3 for 64b align */
+	int8_t		di_aformat;	/* format of attr fork's data */
+	uint32_t	di_dmevmask;	/* DMIG event mask */
+	uint16_t	di_dmstate;	/* DMIG state info */
+	uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
+	uint32_t	di_gen;		/* generation number */
 
 	/* di_next_unlinked is the only non-core field in the old dinode */
 	xfs_agino_t	di_next_unlinked;/* agi unlinked list ptr */
 
 	/* start of the extended dinode, writable fields */
-	__uint32_t	di_crc;		/* CRC of the inode */
-	__uint64_t	di_changecount;	/* number of attribute changes */
+	uint32_t	di_crc;		/* CRC of the inode */
+	uint64_t	di_changecount;	/* number of attribute changes */
 	xfs_lsn_t	di_lsn;		/* flush sequence */
-	__uint64_t	di_flags2;	/* more random flags */
-	__uint32_t	di_cowextsize;	/* basic cow extent size for file */
-	__uint8_t	di_pad2[12];	/* more padding for future expansion */
+	uint64_t	di_flags2;	/* more random flags */
+	uint32_t	di_cowextsize;	/* basic cow extent size for file */
+	uint8_t		di_pad2[12];	/* more padding for future expansion */
 
 	/* fields only written to during inode creation */
 	xfs_ictimestamp_t di_crtime;	/* time created */
@@ -483,7 +483,7 @@ typedef struct xfs_buf_log_format {
 	unsigned short	blf_size;	/* size of this item */
 	unsigned short	blf_flags;	/* misc state */
 	unsigned short	blf_len;	/* number of blocks in this buf */
-	__int64_t	blf_blkno;	/* starting blkno of this buf */
+	int64_t		blf_blkno;	/* starting blkno of this buf */
 	unsigned int	blf_map_size;	/* used size of data bitmap in words */
 	unsigned int	blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */
 } xfs_buf_log_format_t;
@@ -533,7 +533,7 @@ xfs_blft_to_flags(struct xfs_buf_log_format *blf, enum xfs_blft type)
 	blf->blf_flags |= ((type << XFS_BLFT_SHIFT) & XFS_BLFT_MASK);
 }
 
-static inline __uint16_t
+static inline uint16_t
 xfs_blft_from_flags(struct xfs_buf_log_format *blf)
 {
 	return (blf->blf_flags & XFS_BLFT_MASK) >> XFS_BLFT_SHIFT;
@@ -554,14 +554,14 @@ typedef struct xfs_extent {
  * conversion routine.
  */
 typedef struct xfs_extent_32 {
-	__uint64_t	ext_start;
-	__uint32_t	ext_len;
+	uint64_t	ext_start;
+	uint32_t	ext_len;
 } __attribute__((packed)) xfs_extent_32_t;
 
 typedef struct xfs_extent_64 {
-	__uint64_t	ext_start;
-	__uint32_t	ext_len;
-	__uint32_t	ext_pad;
+	uint64_t	ext_start;
+	uint32_t	ext_len;
+	uint32_t	ext_pad;
 } xfs_extent_64_t;
 
 /*
@@ -570,26 +570,26 @@ typedef struct xfs_extent_64 {
  * size is given by efi_nextents.
  */
 typedef struct xfs_efi_log_format {
-	__uint16_t		efi_type;	/* efi log item type */
-	__uint16_t		efi_size;	/* size of this item */
-	__uint32_t		efi_nextents;	/* # extents to free */
-	__uint64_t		efi_id;		/* efi identifier */
+	uint16_t		efi_type;	/* efi log item type */
+	uint16_t		efi_size;	/* size of this item */
+	uint32_t		efi_nextents;	/* # extents to free */
+	uint64_t		efi_id;		/* efi identifier */
 	xfs_extent_t		efi_extents[1];	/* array of extents to free */
 } xfs_efi_log_format_t;
 
 typedef struct xfs_efi_log_format_32 {
-	__uint16_t		efi_type;	/* efi log item type */
-	__uint16_t		efi_size;	/* size of this item */
-	__uint32_t		efi_nextents;	/* # extents to free */
-	__uint64_t		efi_id;		/* efi identifier */
+	uint16_t		efi_type;	/* efi log item type */
+	uint16_t		efi_size;	/* size of this item */
+	uint32_t		efi_nextents;	/* # extents to free */
+	uint64_t		efi_id;		/* efi identifier */
 	xfs_extent_32_t		efi_extents[1];	/* array of extents to free */
 } __attribute__((packed)) xfs_efi_log_format_32_t;
 
 typedef struct xfs_efi_log_format_64 {
-	__uint16_t		efi_type;	/* efi log item type */
-	__uint16_t		efi_size;	/* size of this item */
-	__uint32_t		efi_nextents;	/* # extents to free */
-	__uint64_t		efi_id;		/* efi identifier */
+	uint16_t		efi_type;	/* efi log item type */
+	uint16_t		efi_size;	/* size of this item */
+	uint32_t		efi_nextents;	/* # extents to free */
+	uint64_t		efi_id;		/* efi identifier */
 	xfs_extent_64_t		efi_extents[1];	/* array of extents to free */
 } xfs_efi_log_format_64_t;
 
@@ -599,26 +599,26 @@ typedef struct xfs_efi_log_format_64 {
  * size is given by efd_nextents;
  */
 typedef struct xfs_efd_log_format {
-	__uint16_t		efd_type;	/* efd log item type */
-	__uint16_t		efd_size;	/* size of this item */
-	__uint32_t		efd_nextents;	/* # of extents freed */
-	__uint64_t		efd_efi_id;	/* id of corresponding efi */
+	uint16_t		efd_type;	/* efd log item type */
+	uint16_t		efd_size;	/* size of this item */
+	uint32_t		efd_nextents;	/* # of extents freed */
+	uint64_t		efd_efi_id;	/* id of corresponding efi */
 	xfs_extent_t		efd_extents[1];	/* array of extents freed */
 } xfs_efd_log_format_t;
 
 typedef struct xfs_efd_log_format_32 {
-	__uint16_t		efd_type;	/* efd log item type */
-	__uint16_t		efd_size;	/* size of this item */
-	__uint32_t		efd_nextents;	/* # of extents freed */
-	__uint64_t		efd_efi_id;	/* id of corresponding efi */
+	uint16_t		efd_type;	/* efd log item type */
+	uint16_t		efd_size;	/* size of this item */
+	uint32_t		efd_nextents;	/* # of extents freed */
+	uint64_t		efd_efi_id;	/* id of corresponding efi */
 	xfs_extent_32_t		efd_extents[1];	/* array of extents freed */
 } __attribute__((packed)) xfs_efd_log_format_32_t;
 
 typedef struct xfs_efd_log_format_64 {
-	__uint16_t		efd_type;	/* efd log item type */
-	__uint16_t		efd_size;	/* size of this item */
-	__uint32_t		efd_nextents;	/* # of extents freed */
-	__uint64_t		efd_efi_id;	/* id of corresponding efi */
+	uint16_t		efd_type;	/* efd log item type */
+	uint16_t		efd_size;	/* size of this item */
+	uint32_t		efd_nextents;	/* # of extents freed */
+	uint64_t		efd_efi_id;	/* id of corresponding efi */
 	xfs_extent_64_t		efd_extents[1];	/* array of extents freed */
 } xfs_efd_log_format_64_t;
 
@@ -626,11 +626,11 @@ typedef struct xfs_efd_log_format_64 {
  * RUI/RUD (reverse mapping) log format definitions
  */
 struct xfs_map_extent {
-	__uint64_t		me_owner;
-	__uint64_t		me_startblock;
-	__uint64_t		me_startoff;
-	__uint32_t		me_len;
-	__uint32_t		me_flags;
+	uint64_t		me_owner;
+	uint64_t		me_startblock;
+	uint64_t		me_startoff;
+	uint32_t		me_len;
+	uint32_t		me_flags;
 };
 
 /* rmap me_flags: upper bits are flags, lower byte is type code */
@@ -659,10 +659,10 @@ struct xfs_map_extent {
  * size is given by rui_nextents.
  */
 struct xfs_rui_log_format {
-	__uint16_t		rui_type;	/* rui log item type */
-	__uint16_t		rui_size;	/* size of this item */
-	__uint32_t		rui_nextents;	/* # extents to free */
-	__uint64_t		rui_id;		/* rui identifier */
+	uint16_t		rui_type;	/* rui log item type */
+	uint16_t		rui_size;	/* size of this item */
+	uint32_t		rui_nextents;	/* # extents to free */
+	uint64_t		rui_id;		/* rui identifier */
 	struct xfs_map_extent	rui_extents[];	/* array of extents to rmap */
 };
 
@@ -680,19 +680,19 @@ xfs_rui_log_format_sizeof(
  * size is given by rud_nextents;
  */
 struct xfs_rud_log_format {
-	__uint16_t		rud_type;	/* rud log item type */
-	__uint16_t		rud_size;	/* size of this item */
-	__uint32_t		__pad;
-	__uint64_t		rud_rui_id;	/* id of corresponding rui */
+	uint16_t		rud_type;	/* rud log item type */
+	uint16_t		rud_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		rud_rui_id;	/* id of corresponding rui */
 };
 
 /*
  * CUI/CUD (refcount update) log format definitions
  */
 struct xfs_phys_extent {
-	__uint64_t		pe_startblock;
-	__uint32_t		pe_len;
-	__uint32_t		pe_flags;
+	uint64_t		pe_startblock;
+	uint32_t		pe_len;
+	uint32_t		pe_flags;
 };
 
 /* refcount pe_flags: upper bits are flags, lower byte is type code */
@@ -707,10 +707,10 @@ struct xfs_phys_extent {
  * size is given by cui_nextents.
  */
 struct xfs_cui_log_format {
-	__uint16_t		cui_type;	/* cui log item type */
-	__uint16_t		cui_size;	/* size of this item */
-	__uint32_t		cui_nextents;	/* # extents to free */
-	__uint64_t		cui_id;		/* cui identifier */
+	uint16_t		cui_type;	/* cui log item type */
+	uint16_t		cui_size;	/* size of this item */
+	uint32_t		cui_nextents;	/* # extents to free */
+	uint64_t		cui_id;		/* cui identifier */
 	struct xfs_phys_extent	cui_extents[];	/* array of extents */
 };
 
@@ -728,10 +728,10 @@ xfs_cui_log_format_sizeof(
  * size is given by cud_nextents;
  */
 struct xfs_cud_log_format {
-	__uint16_t		cud_type;	/* cud log item type */
-	__uint16_t		cud_size;	/* size of this item */
-	__uint32_t		__pad;
-	__uint64_t		cud_cui_id;	/* id of corresponding cui */
+	uint16_t		cud_type;	/* cud log item type */
+	uint16_t		cud_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		cud_cui_id;	/* id of corresponding cui */
 };
 
 /*
@@ -755,10 +755,10 @@ struct xfs_cud_log_format {
  * size is given by bui_nextents.
  */
 struct xfs_bui_log_format {
-	__uint16_t		bui_type;	/* bui log item type */
-	__uint16_t		bui_size;	/* size of this item */
-	__uint32_t		bui_nextents;	/* # extents to free */
-	__uint64_t		bui_id;		/* bui identifier */
+	uint16_t		bui_type;	/* bui log item type */
+	uint16_t		bui_size;	/* size of this item */
+	uint32_t		bui_nextents;	/* # extents to free */
+	uint64_t		bui_id;		/* bui identifier */
 	struct xfs_map_extent	bui_extents[];	/* array of extents to bmap */
 };
 
@@ -776,10 +776,10 @@ xfs_bui_log_format_sizeof(
  * size is given by bud_nextents;
  */
 struct xfs_bud_log_format {
-	__uint16_t		bud_type;	/* bud log item type */
-	__uint16_t		bud_size;	/* size of this item */
-	__uint32_t		__pad;
-	__uint64_t		bud_bui_id;	/* id of corresponding bui */
+	uint16_t		bud_type;	/* bud log item type */
+	uint16_t		bud_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		bud_bui_id;	/* id of corresponding bui */
 };
 
 /*
@@ -789,12 +789,12 @@ struct xfs_bud_log_format {
  * 32 bits : log_recovery code assumes that.
  */
 typedef struct xfs_dq_logformat {
-	__uint16_t		qlf_type;      /* dquot log item type */
-	__uint16_t		qlf_size;      /* size of this item */
+	uint16_t		qlf_type;      /* dquot log item type */
+	uint16_t		qlf_size;      /* size of this item */
 	xfs_dqid_t		qlf_id;	       /* usr/grp/proj id : 32 bits */
-	__int64_t		qlf_blkno;     /* blkno of dquot buffer */
-	__int32_t		qlf_len;       /* len of dquot buffer */
-	__uint32_t		qlf_boffset;   /* off of dquot in buffer */
+	int64_t			qlf_blkno;     /* blkno of dquot buffer */
+	int32_t			qlf_len;       /* len of dquot buffer */
+	uint32_t		qlf_boffset;   /* off of dquot in buffer */
 } xfs_dq_logformat_t;
 
 /*
@@ -853,8 +853,8 @@ typedef struct xfs_qoff_logformat {
  * decoding can be done correctly.
  */
 struct xfs_icreate_log {
-	__uint16_t	icl_type;	/* type of log format structure */
-	__uint16_t	icl_size;	/* size of log format structure */
+	uint16_t	icl_type;	/* type of log format structure */
+	uint16_t	icl_size;	/* size of log format structure */
 	__be32		icl_ag;		/* ag being allocated in */
 	__be32		icl_agbno;	/* start block of inode range */
 	__be32		icl_count;	/* number of inodes to initialise */
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 29a01ec89dd0..66948a9fd486 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -26,7 +26,7 @@
 #define XLOG_RHASH_SIZE	16
 #define XLOG_RHASH_SHIFT 2
 #define XLOG_RHASH(tid)	\
-	((((__uint32_t)tid)>>XLOG_RHASH_SHIFT) & (XLOG_RHASH_SIZE-1))
+	((((uint32_t)tid)>>XLOG_RHASH_SHIFT) & (XLOG_RHASH_SIZE-1))
 
 #define XLOG_MAX_REGIONS_IN_ITEM   (XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK / 2 + 1)
 
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index 8eed51275bb3..d69c772271cb 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -27,8 +27,8 @@
  * they may need 64-bit accounting. Hence, 64-bit quota-counters,
  * and quota-limits. This is a waste in the common case, but hey ...
  */
-typedef __uint64_t	xfs_qcnt_t;
-typedef __uint16_t	xfs_qwarncnt_t;
+typedef uint64_t	xfs_qcnt_t;
+typedef uint16_t	xfs_qwarncnt_t;
 
 /*
  * flags for q_flags field in the dquot.
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 50add5272807..65c222ae5b04 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -202,7 +202,7 @@ xfs_refcountbt_init_ptr_from_cur(
 	ptr->s = agf->agf_refcount_root;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_refcountbt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
@@ -210,16 +210,16 @@ xfs_refcountbt_key_diff(
 	struct xfs_refcount_irec	*rec = &cur->bc_rec.rc;
 	struct xfs_refcount_key		*kp = &key->refc;
 
-	return (__int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
+	return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_refcountbt_diff_two_keys(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
 	union xfs_btree_key	*k2)
 {
-	return (__int64_t)be32_to_cpu(k1->refc.rc_startblock) -
+	return (int64_t)be32_to_cpu(k1->refc.rc_startblock) -
 			  be32_to_cpu(k2->refc.rc_startblock);
 }
 
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 06cfb93c2ef9..1bcb41fe0156 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2061,7 +2061,7 @@ int
 xfs_rmap_finish_one(
 	struct xfs_trans		*tp,
 	enum xfs_rmap_intent_type	type,
-	__uint64_t			owner,
+	uint64_t			owner,
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
@@ -2182,7 +2182,7 @@ __xfs_rmap_add(
 	struct xfs_mount		*mp,
 	struct xfs_defer_ops		*dfops,
 	enum xfs_rmap_intent_type	type,
-	__uint64_t			owner,
+	uint64_t			owner,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
@@ -2266,7 +2266,7 @@ xfs_rmap_alloc_extent(
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
-	__uint64_t		owner)
+	uint64_t		owner)
 {
 	struct xfs_bmbt_irec	bmap;
 
@@ -2290,7 +2290,7 @@ xfs_rmap_free_extent(
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
-	__uint64_t		owner)
+	uint64_t		owner)
 {
 	struct xfs_bmbt_irec	bmap;
 
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 98f908fea103..265116d044f4 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -179,7 +179,7 @@ enum xfs_rmap_intent_type {
 struct xfs_rmap_intent {
 	struct list_head			ri_list;
 	enum xfs_rmap_intent_type		ri_type;
-	__uint64_t				ri_owner;
+	uint64_t				ri_owner;
 	int					ri_whichfork;
 	struct xfs_bmbt_irec			ri_bmap;
 };
@@ -196,15 +196,15 @@ int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		struct xfs_bmbt_irec *imap);
 int xfs_rmap_alloc_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		__uint64_t owner);
+		uint64_t owner);
 int xfs_rmap_free_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		__uint64_t owner);
+		uint64_t owner);
 
 void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
 int xfs_rmap_finish_one(struct xfs_trans *tp, enum xfs_rmap_intent_type type,
-		__uint64_t owner, int whichfork, xfs_fileoff_t startoff,
+		uint64_t owner, int whichfork, xfs_fileoff_t startoff,
 		xfs_fsblock_t startblock, xfs_filblks_t blockcount,
 		xfs_exntst_t state, struct xfs_btree_cur **pcur);
 
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 74e5a54bc428..c5b4a1c862b0 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -199,7 +199,7 @@ xfs_rmapbt_init_high_key_from_rec(
 	union xfs_btree_key	*key,
 	union xfs_btree_rec	*rec)
 {
-	__uint64_t		off;
+	uint64_t		off;
 	int			adj;
 
 	adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1;
@@ -241,7 +241,7 @@ xfs_rmapbt_init_ptr_from_cur(
 	ptr->s = agf->agf_roots[cur->bc_btnum];
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_rmapbt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
@@ -249,9 +249,9 @@ xfs_rmapbt_key_diff(
 	struct xfs_rmap_irec	*rec = &cur->bc_rec.r;
 	struct xfs_rmap_key	*kp = &key->rmap;
 	__u64			x, y;
-	__int64_t		d;
+	int64_t			d;
 
-	d = (__int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock;
+	d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock;
 	if (d)
 		return d;
 
@@ -271,7 +271,7 @@ xfs_rmapbt_key_diff(
 	return 0;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_rmapbt_diff_two_keys(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
@@ -279,10 +279,10 @@ xfs_rmapbt_diff_two_keys(
 {
 	struct xfs_rmap_key	*kp1 = &k1->rmap;
 	struct xfs_rmap_key	*kp2 = &k2->rmap;
-	__int64_t		d;
+	int64_t			d;
 	__u64			x, y;
 
-	d = (__int64_t)be32_to_cpu(kp1->rm_startblock) -
+	d = (int64_t)be32_to_cpu(kp1->rm_startblock) -
 		       be32_to_cpu(kp2->rm_startblock);
 	if (d)
 		return d;
@@ -384,10 +384,10 @@ xfs_rmapbt_keys_inorder(
 	union xfs_btree_key	*k1,
 	union xfs_btree_key	*k2)
 {
-	__uint32_t		x;
-	__uint32_t		y;
-	__uint64_t		a;
-	__uint64_t		b;
+	uint32_t		x;
+	uint32_t		y;
+	uint64_t		a;
+	uint64_t		b;
 
 	x = be32_to_cpu(k1->rmap.rm_startblock);
 	y = be32_to_cpu(k2->rmap.rm_startblock);
@@ -414,10 +414,10 @@ xfs_rmapbt_recs_inorder(
 	union xfs_btree_rec	*r1,
 	union xfs_btree_rec	*r2)
 {
-	__uint32_t		x;
-	__uint32_t		y;
-	__uint64_t		a;
-	__uint64_t		b;
+	uint32_t		x;
+	uint32_t		y;
+	uint64_t		a;
+	uint64_t		b;
 
 	x = be32_to_cpu(r1->rmap.rm_startblock);
 	y = be32_to_cpu(r2->rmap.rm_startblock);
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index e47b99e59f60..26bba7f90fdf 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1011,7 +1011,7 @@ xfs_rtfree_extent(
 	    mp->m_sb.sb_rextents) {
 		if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
 			mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
-		*(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
+		*(uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
 		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
 	}
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 584ec896a533..9b5aae2bcc0b 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -448,7 +448,7 @@ xfs_sb_quota_to_disk(
 	struct xfs_dsb	*to,
 	struct xfs_sb	*from)
 {
-	__uint16_t	qflags = from->sb_qflags;
+	uint16_t	qflags = from->sb_qflags;
 
 	to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
 	if (xfs_sb_version_has_pquotino(from)) {
@@ -756,7 +756,7 @@ xfs_sb_mount_common(
 	mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2;
 
 	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
-	mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK,
+	mp->m_ialloc_inos = (int)MAX((uint16_t)XFS_INODES_PER_CHUNK,
 					sbp->sb_inopblock);
 	mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
 
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 717909f2f7b7..0220159bd463 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -18,34 +18,34 @@
 #ifndef __XFS_TYPES_H__
 #define	__XFS_TYPES_H__
 
-typedef __uint32_t	prid_t;		/* project ID */
+typedef uint32_t	prid_t;		/* project ID */
 
-typedef __uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
-typedef	__uint32_t	xfs_agino_t;	/* inode # within allocation grp */
-typedef	__uint32_t	xfs_extlen_t;	/* extent length in blocks */
-typedef	__uint32_t	xfs_agnumber_t;	/* allocation group number */
-typedef __int32_t	xfs_extnum_t;	/* # of extents in a file */
-typedef __int16_t	xfs_aextnum_t;	/* # extents in an attribute fork */
-typedef	__int64_t	xfs_fsize_t;	/* bytes in a file */
-typedef __uint64_t	xfs_ufsize_t;	/* unsigned bytes in a file */
+typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
+typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
+typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
+typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
+typedef int32_t		xfs_extnum_t;	/* # of extents in a file */
+typedef int16_t		xfs_aextnum_t;	/* # extents in an attribute fork */
+typedef int64_t		xfs_fsize_t;	/* bytes in a file */
+typedef uint64_t	xfs_ufsize_t;	/* unsigned bytes in a file */
 
-typedef	__int32_t	xfs_suminfo_t;	/* type of bitmap summary info */
-typedef	__int32_t	xfs_rtword_t;	/* word type for bitmap manipulations */
+typedef int32_t		xfs_suminfo_t;	/* type of bitmap summary info */
+typedef int32_t		xfs_rtword_t;	/* word type for bitmap manipulations */
 
-typedef	__int64_t	xfs_lsn_t;	/* log sequence number */
-typedef	__int32_t	xfs_tid_t;	/* transaction identifier */
+typedef int64_t		xfs_lsn_t;	/* log sequence number */
+typedef int32_t		xfs_tid_t;	/* transaction identifier */
 
-typedef	__uint32_t	xfs_dablk_t;	/* dir/attr block number (in file) */
-typedef	__uint32_t	xfs_dahash_t;	/* dir/attr hash value */
+typedef uint32_t	xfs_dablk_t;	/* dir/attr block number (in file) */
+typedef uint32_t	xfs_dahash_t;	/* dir/attr hash value */
 
-typedef	__uint64_t	xfs_fsblock_t;	/* blockno in filesystem (agno|agbno) */
-typedef __uint64_t	xfs_rfsblock_t;	/* blockno in filesystem (raw) */
-typedef __uint64_t	xfs_rtblock_t;	/* extent (block) in realtime area */
-typedef __uint64_t	xfs_fileoff_t;	/* block number in a file */
-typedef __uint64_t	xfs_filblks_t;	/* number of blocks in a file */
+typedef uint64_t	xfs_fsblock_t;	/* blockno in filesystem (agno|agbno) */
+typedef uint64_t	xfs_rfsblock_t;	/* blockno in filesystem (raw) */
+typedef uint64_t	xfs_rtblock_t;	/* extent (block) in realtime area */
+typedef uint64_t	xfs_fileoff_t;	/* block number in a file */
+typedef uint64_t	xfs_filblks_t;	/* number of blocks in a file */
 
-typedef	__int64_t	xfs_srtblock_t;	/* signed version of xfs_rtblock_t */
-typedef __int64_t	xfs_sfiloff_t;	/* signed block number in a file */
+typedef int64_t		xfs_srtblock_t;	/* signed version of xfs_rtblock_t */
+typedef int64_t		xfs_sfiloff_t;	/* signed block number in a file */
 
 /*
  * Null values for the types.
@@ -125,7 +125,7 @@ struct xfs_name {
  * uid_t and gid_t are hard-coded to 32 bits in the inode.
  * Hence, an 'id' in a dquot is 32 bits..
  */
-typedef __uint32_t	xfs_dqid_t;
+typedef uint32_t	xfs_dqid_t;
 
 /*
  * Constants for bit manipulations.
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 09af0f7cd55e..6bab8c449b81 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -836,7 +836,7 @@ xfs_writepage_map(
 	struct inode		*inode,
 	struct page		*page,
 	loff_t			offset,
-	__uint64_t              end_offset)
+	uint64_t              end_offset)
 {
 	LIST_HEAD(submit_list);
 	struct xfs_ioend	*ioend, *next;
@@ -991,7 +991,7 @@ xfs_do_writepage(
 	struct xfs_writepage_ctx *wpc = data;
 	struct inode		*inode = page->mapping->host;
 	loff_t			offset;
-	__uint64_t              end_offset;
+	uint64_t              end_offset;
 	pgoff_t                 end_index;
 
 	trace_xfs_writepage(inode, page, 0, 0);
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 97c45b6eb91e..9bc1e1217989 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -279,7 +279,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	if (bp == NULL) {
 		cursor->blkno = 0;
 		for (;;) {
-			__uint16_t magic;
+			uint16_t magic;
 
 			error = xfs_da3_node_read(NULL, dp,
 						      cursor->blkno, -1, &bp,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 7493a64f5b99..0ea70a44c1a7 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -389,11 +389,11 @@ xfs_getbmapx_fix_eof_hole(
 	struct getbmapx		*out,		/* output structure */
 	int			prealloced,	/* this is a file with
 						 * preallocated data space */
-	__int64_t		end,		/* last block requested */
+	int64_t			end,		/* last block requested */
 	xfs_fsblock_t		startblock,
 	bool			moretocome)
 {
-	__int64_t		fixlen;
+	int64_t			fixlen;
 	xfs_mount_t		*mp;		/* file system mount point */
 	xfs_ifork_t		*ifp;		/* inode fork pointer */
 	xfs_extnum_t		lastx;		/* last extent pointer */
@@ -514,9 +514,9 @@ xfs_getbmap(
 	xfs_bmap_format_t	formatter,	/* format to user */
 	void			*arg)		/* formatter arg */
 {
-	__int64_t		bmvend;		/* last block requested */
+	int64_t			bmvend;		/* last block requested */
 	int			error = 0;	/* return value */
-	__int64_t		fixlen;		/* length for -1 case */
+	int64_t			fixlen;		/* length for -1 case */
 	int			i;		/* extent number */
 	int			lock;		/* lock state */
 	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
@@ -605,7 +605,7 @@ xfs_getbmap(
 	if (bmv->bmv_length == -1) {
 		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
 		bmv->bmv_length =
-			max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
+			max_t(int64_t, fixlen - bmv->bmv_offset, 0);
 	} else if (bmv->bmv_length == 0) {
 		bmv->bmv_entries = 0;
 		return 0;
@@ -742,7 +742,7 @@ xfs_getbmap(
 				out[cur_ext].bmv_offset +
 				out[cur_ext].bmv_length;
 			bmv->bmv_length =
-				max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
+				max_t(int64_t, 0, bmvend - bmv->bmv_offset);
 
 			/*
 			 * In case we don't want to return the hole,
@@ -1676,7 +1676,7 @@ xfs_swap_extent_rmap(
 	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
 	int				nimaps;
-	__uint64_t			tip_flags2;
+	uint64_t			tip_flags2;
 
 	/*
 	 * If the source file has shared blocks, we must flag the donor
@@ -1792,7 +1792,7 @@ xfs_swap_extent_forks(
 	int			aforkblks = 0;
 	int			taforkblks = 0;
 	xfs_extnum_t		nextents;
-	__uint64_t		tmp;
+	uint64_t		tmp;
 	int			error;
 
 	/*
@@ -1850,15 +1850,15 @@ xfs_swap_extent_forks(
 	/*
 	 * Fix the on-disk inode values
 	 */
-	tmp = (__uint64_t)ip->i_d.di_nblocks;
+	tmp = (uint64_t)ip->i_d.di_nblocks;
 	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
 	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
 
-	tmp = (__uint64_t) ip->i_d.di_nextents;
+	tmp = (uint64_t) ip->i_d.di_nextents;
 	ip->i_d.di_nextents = tip->i_d.di_nextents;
 	tip->i_d.di_nextents = tmp;
 
-	tmp = (__uint64_t) ip->i_d.di_format;
+	tmp = (uint64_t) ip->i_d.di_format;
 	ip->i_d.di_format = tip->i_d.di_format;
 	tip->i_d.di_format = tmp;
 
@@ -1927,7 +1927,7 @@ xfs_swap_extents(
 	int			error = 0;
 	int			lock_flags;
 	struct xfs_ifork	*cowfp;
-	__uint64_t		f;
+	uint64_t		f;
 	int			resblks;
 
 	/*
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a9640b136b32..89b586f688b0 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1194,7 +1194,7 @@ xfs_buf_ioerror_alert(
 {
 	xfs_alert(bp->b_target->bt_mount,
 "metadata I/O error: block 0x%llx (\"%s\") error %d numblks %d",
-		(__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
+		(uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
 }
 
 int
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 1bc7401ea1b2..ede4790753bc 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -44,7 +44,7 @@ static unsigned char xfs_dir3_filetype_table[] = {
 static unsigned char
 xfs_dir3_get_dtype(
 	struct xfs_mount	*mp,
-	__uint8_t		filetype)
+	uint8_t			filetype)
 {
 	if (!xfs_sb_version_hasftype(&mp->m_sb))
 		return DT_UNKNOWN;
@@ -117,7 +117,7 @@ xfs_dir2_sf_getdents(
 	 */
 	sfep = xfs_dir2_sf_firstentry(sfp);
 	for (i = 0; i < sfp->count; i++) {
-		__uint8_t filetype;
+		uint8_t filetype;
 
 		off = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
 				xfs_dir2_sf_get_offset(sfep));
@@ -194,7 +194,7 @@ xfs_dir2_block_getdents(
 	 * Each object is a real entry (dep) or an unused one (dup).
 	 */
 	while (ptr < endptr) {
-		__uint8_t filetype;
+		uint8_t filetype;
 
 		dup = (xfs_dir2_data_unused_t *)ptr;
 		/*
@@ -391,7 +391,7 @@ xfs_dir2_leaf_getdents(
 	 * Get more blocks and readahead as necessary.
 	 */
 	while (curoff < XFS_DIR2_LEAF_OFFSET) {
-		__uint8_t filetype;
+		uint8_t filetype;
 
 		/*
 		 * If we have no buffer, or we're off the end of the
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 6a05d278da64..b2cde5426182 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -39,7 +39,7 @@ xfs_trim_extents(
 	xfs_daddr_t		start,
 	xfs_daddr_t		end,
 	xfs_daddr_t		minlen,
-	__uint64_t		*blocks_trimmed)
+	uint64_t		*blocks_trimmed)
 {
 	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;
 	struct xfs_btree_cur	*cur;
@@ -166,7 +166,7 @@ xfs_ioc_trim(
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end, minlen;
 	xfs_agnumber_t		start_agno, end_agno, agno;
-	__uint64_t		blocks_trimmed = 0;
+	uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 9d06cc30e875..e57c6cce91aa 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -276,7 +276,7 @@ xfs_qm_init_dquot_blk(
 void
 xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp)
 {
-	__uint64_t space;
+	uint64_t space;
 
 	dqp->q_prealloc_hi_wmark = be64_to_cpu(dqp->q_core.d_blk_hardlimit);
 	dqp->q_prealloc_lo_wmark = be64_to_cpu(dqp->q_core.d_blk_softlimit);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 6ccaae9eb0ee..8f22fc579dbb 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -602,7 +602,7 @@ xfs_growfs_data_private(
 	if (nagimax)
 		mp->m_maxagi = nagimax;
 	if (mp->m_sb.sb_imax_pct) {
-		__uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
+		uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
 		do_div(icount, 100);
 		mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
 	} else
@@ -793,17 +793,17 @@ xfs_fs_counts(
 int
 xfs_reserve_blocks(
 	xfs_mount_t             *mp,
-	__uint64_t              *inval,
+	uint64_t              *inval,
 	xfs_fsop_resblks_t      *outval)
 {
-	__int64_t		lcounter, delta;
-	__int64_t		fdblks_delta = 0;
-	__uint64_t		request;
-	__int64_t		free;
+	int64_t			lcounter, delta;
+	int64_t			fdblks_delta = 0;
+	uint64_t		request;
+	int64_t			free;
 	int			error = 0;
 
 	/* If inval is null, report current values and return */
-	if (inval == (__uint64_t *)NULL) {
+	if (inval == (uint64_t *)NULL) {
 		if (!outval)
 			return -EINVAL;
 		outval->resblks = mp->m_resblks;
@@ -904,7 +904,7 @@ out:
 int
 xfs_fs_goingdown(
 	xfs_mount_t	*mp,
-	__uint32_t	inflags)
+	uint32_t	inflags)
 {
 	switch (inflags) {
 	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index f34915898fea..2954c13a3acd 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -22,9 +22,9 @@ extern int xfs_fs_geometry(xfs_mount_t *mp, xfs_fsop_geom_t *geo, int nversion);
 extern int xfs_growfs_data(xfs_mount_t *mp, xfs_growfs_data_t *in);
 extern int xfs_growfs_log(xfs_mount_t *mp, xfs_growfs_log_t *in);
 extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
-extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval,
+extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval,
 				xfs_fsop_resblks_t *outval);
-extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags);
+extern int xfs_fs_goingdown(xfs_mount_t *mp, uint32_t inflags);
 
 extern int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp);
 extern int xfs_fs_unreserve_ag_blocks(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ec9826c56500..ffbfe7d8bc6d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -632,7 +632,7 @@ __xfs_iflock(
 
 STATIC uint
 _xfs_dic2xflags(
-	__uint16_t		di_flags,
+	uint16_t		di_flags,
 	uint64_t		di_flags2,
 	bool			has_attr)
 {
@@ -855,8 +855,8 @@ xfs_ialloc(
 		inode->i_version = 1;
 		ip->i_d.di_flags2 = 0;
 		ip->i_d.di_cowextsize = 0;
-		ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
-		ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
+		ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec;
+		ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec;
 	}
 
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 10e89fcb49d7..677d0bfe1c2d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -192,8 +192,8 @@ static inline void
 xfs_set_projid(struct xfs_inode *ip,
 		prid_t projid)
 {
-	ip->i_d.di_projid_hi = (__uint16_t) (projid >> 16);
-	ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff);
+	ip->i_d.di_projid_hi = (uint16_t) (projid >> 16);
+	ip->i_d.di_projid_lo = (uint16_t) (projid & 0xffff);
 }
 
 static inline prid_t
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index f6af76975bc8..8ffe4eac0b48 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -443,8 +443,8 @@ xfs_attrmulti_attr_get(
 	struct inode		*inode,
 	unsigned char		*name,
 	unsigned char		__user *ubuf,
-	__uint32_t		*len,
-	__uint32_t		flags)
+	uint32_t		*len,
+	uint32_t		flags)
 {
 	unsigned char		*kbuf;
 	int			error = -EFAULT;
@@ -472,8 +472,8 @@ xfs_attrmulti_attr_set(
 	struct inode		*inode,
 	unsigned char		*name,
 	const unsigned char	__user *ubuf,
-	__uint32_t		len,
-	__uint32_t		flags)
+	uint32_t		len,
+	uint32_t		flags)
 {
 	unsigned char		*kbuf;
 	int			error;
@@ -498,7 +498,7 @@ int
 xfs_attrmulti_attr_remove(
 	struct inode		*inode,
 	unsigned char		*name,
-	__uint32_t		flags)
+	uint32_t		flags)
 {
 	int			error;
 
@@ -876,7 +876,7 @@ xfs_merge_ioc_xflags(
 
 STATIC unsigned int
 xfs_di2lxflags(
-	__uint16_t	di_flags)
+	uint16_t	di_flags)
 {
 	unsigned int	flags = 0;
 
@@ -1287,7 +1287,7 @@ xfs_ioctl_setattr_check_projid(
 	struct fsxattr		*fa)
 {
 	/* Disallow 32bit project ids if projid32bit feature is not enabled. */
-	if (fa->fsx_projid > (__uint16_t)-1 &&
+	if (fa->fsx_projid > (uint16_t)-1 &&
 	    !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
 		return -EINVAL;
 
@@ -1931,7 +1931,7 @@ xfs_file_ioctl(
 
 	case XFS_IOC_SET_RESBLKS: {
 		xfs_fsop_resblks_t inout;
-		__uint64_t	   in;
+		uint64_t	   in;
 
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
@@ -2017,12 +2017,12 @@ xfs_file_ioctl(
 	}
 
 	case XFS_IOC_GOINGDOWN: {
-		__uint32_t in;
+		uint32_t in;
 
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		if (get_user(in, (__uint32_t __user *)arg))
+		if (get_user(in, (uint32_t __user *)arg))
 			return -EFAULT;
 
 		return xfs_fs_goingdown(mp, in);
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index 8b52881bfd90..e86c3ea137d2 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -48,22 +48,22 @@ xfs_attrmulti_attr_get(
 	struct inode		*inode,
 	unsigned char		*name,
 	unsigned char		__user *ubuf,
-	__uint32_t		*len,
-	__uint32_t		flags);
+	uint32_t		*len,
+	uint32_t		flags);
 
 extern int
 xfs_attrmulti_attr_set(
 	struct inode		*inode,
 	unsigned char		*name,
 	const unsigned char	__user *ubuf,
-	__uint32_t		len,
-	__uint32_t		flags);
+	uint32_t		len,
+	uint32_t		flags);
 
 extern int
 xfs_attrmulti_attr_remove(
 	struct inode		*inode,
 	unsigned char		*name,
-	__uint32_t		flags);
+	uint32_t		flags);
 
 extern struct dentry *
 xfs_handle_to_dentry(
diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index b1bb45444df8..5492bcf6f442 100644
--- a/fs/xfs/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
@@ -112,9 +112,9 @@ typedef struct compat_xfs_fsop_handlereq {
 
 /* The bstat field in the swapext struct needs translation */
 typedef struct compat_xfs_swapext {
-	__int64_t		sx_version;	/* version */
-	__int64_t		sx_fdtarget;	/* fd of target file */
-	__int64_t		sx_fdtmp;	/* fd of tmp file */
+	int64_t			sx_version;	/* version */
+	int64_t			sx_fdtarget;	/* fd of target file */
+	int64_t			sx_fdtmp;	/* fd of tmp file */
 	xfs_off_t		sx_offset;	/* offset into file */
 	xfs_off_t		sx_length;	/* leng from offset */
 	char			sx_pad[16];	/* pad space, unused */
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 044fb0e15390..ecdae42267d3 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -23,14 +23,6 @@
 /*
  * Kernel specific type declarations for XFS
  */
-typedef signed char		__int8_t;
-typedef unsigned char		__uint8_t;
-typedef signed short int	__int16_t;
-typedef unsigned short int	__uint16_t;
-typedef signed int		__int32_t;
-typedef unsigned int		__uint32_t;
-typedef signed long long int	__int64_t;
-typedef unsigned long long int	__uint64_t;
 
 typedef __s64			xfs_off_t;	/* <file offset> type */
 typedef unsigned long long	xfs_ino_t;	/* <inode> type */
@@ -186,22 +178,22 @@ extern struct xstats xfsstats;
  * are converting to the init_user_ns. The uid is later mapped to a particular
  * user namespace value when crossing the kernel/user boundary.
  */
-static inline __uint32_t xfs_kuid_to_uid(kuid_t uid)
+static inline uint32_t xfs_kuid_to_uid(kuid_t uid)
 {
 	return from_kuid(&init_user_ns, uid);
 }
 
-static inline kuid_t xfs_uid_to_kuid(__uint32_t uid)
+static inline kuid_t xfs_uid_to_kuid(uint32_t uid)
 {
 	return make_kuid(&init_user_ns, uid);
 }
 
-static inline __uint32_t xfs_kgid_to_gid(kgid_t gid)
+static inline uint32_t xfs_kgid_to_gid(kgid_t gid)
 {
 	return from_kgid(&init_user_ns, gid);
 }
 
-static inline kgid_t xfs_gid_to_kgid(__uint32_t gid)
+static inline kgid_t xfs_gid_to_kgid(uint32_t gid)
 {
 	return make_kgid(&init_user_ns, gid);
 }
@@ -231,14 +223,14 @@ static inline __u32 xfs_do_mod(void *a, __u32 b, int n)
 
 #define do_mod(a, b)	xfs_do_mod(&(a), (b), sizeof(a))
 
-static inline __uint64_t roundup_64(__uint64_t x, __uint32_t y)
+static inline uint64_t roundup_64(uint64_t x, uint32_t y)
 {
 	x += y - 1;
 	do_div(x, y);
 	return x * y;
 }
 
-static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
+static inline uint64_t howmany_64(uint64_t x, uint32_t y)
 {
 	x += y - 1;
 	do_div(x, y);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index c8d048103347..98b39cbae42d 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -434,7 +434,7 @@ xfs_log_reserve(
 	int		 	unit_bytes,
 	int		 	cnt,
 	struct xlog_ticket	**ticp,
-	__uint8_t	 	client,
+	uint8_t		 	client,
 	bool			permanent)
 {
 	struct xlog		*log = mp->m_log;
@@ -825,9 +825,9 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		if (!error) {
 			/* the data section must be 32 bit size aligned */
 			struct {
-			    __uint16_t magic;
-			    __uint16_t pad1;
-			    __uint32_t pad2; /* may as well make it 64 bits */
+			    uint16_t magic;
+			    uint16_t pad1;
+			    uint32_t pad2; /* may as well make it 64 bits */
 			} magic = {
 				.magic = XLOG_UNMOUNT_TYPE,
 			};
@@ -1665,7 +1665,7 @@ xlog_cksum(
 	char			*dp,
 	int			size)
 {
-	__uint32_t		crc;
+	uint32_t		crc;
 
 	/* first generate the crc for the record header ... */
 	crc = xfs_start_cksum_update((char *)rhead,
@@ -1828,7 +1828,7 @@ xlog_sync(
 		 */
 		dptr = (char *)&iclog->ic_header + count;
 		for (i = 0; i < split; i += BBSIZE) {
-			__uint32_t cycle = be32_to_cpu(*(__be32 *)dptr);
+			uint32_t cycle = be32_to_cpu(*(__be32 *)dptr);
 			if (++cycle == XLOG_HEADER_MAGIC_NUM)
 				cycle++;
 			*(__be32 *)dptr = cpu_to_be32(cycle);
@@ -2412,8 +2412,8 @@ xlog_write(
 			}
 
 			reg = &vecp[index];
-			ASSERT(reg->i_len % sizeof(__int32_t) == 0);
-			ASSERT((unsigned long)ptr % sizeof(__int32_t) == 0);
+			ASSERT(reg->i_len % sizeof(int32_t) == 0);
+			ASSERT((unsigned long)ptr % sizeof(int32_t) == 0);
 
 			start_rec_copy = xlog_write_start_rec(ptr, ticket);
 			if (start_rec_copy) {
@@ -3192,7 +3192,7 @@ xlog_state_switch_iclogs(
 	/* Round up to next log-sunit */
 	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb) &&
 	    log->l_mp->m_sb.sb_logsunit > 1) {
-		__uint32_t sunit_bb = BTOBB(log->l_mp->m_sb.sb_logsunit);
+		uint32_t sunit_bb = BTOBB(log->l_mp->m_sb.sb_logsunit);
 		log->l_curr_block = roundup(log->l_curr_block, sunit_bb);
 	}
 
@@ -3820,7 +3820,7 @@ xlog_verify_iclog(
 	xlog_in_core_2_t	*xhdr;
 	void			*base_ptr, *ptr, *p;
 	ptrdiff_t		field_offset;
-	__uint8_t		clientid;
+	uint8_t			clientid;
 	int			len, i, j, k, op_len;
 	int			idx;
 
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index cc5a9f1574e7..bf212772595c 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -159,7 +159,7 @@ int	  xfs_log_reserve(struct xfs_mount *mp,
 			  int		   length,
 			  int		   count,
 			  struct xlog_ticket **ticket,
-			  __uint8_t	   clientid,
+			  uint8_t		   clientid,
 			  bool		   permanent);
 int	  xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic);
 void      xfs_log_unmount(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 62113a5d2504..51bf7b827387 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -419,7 +419,7 @@ struct xlog {
 };
 
 #define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
-	((log)->l_buf_cancel_table + ((__uint64_t)blkno % XLOG_BC_TABLE_SIZE))
+	((log)->l_buf_cancel_table + ((uint64_t)blkno % XLOG_BC_TABLE_SIZE))
 
 #define XLOG_FORCED_SHUTDOWN(log)	((log)->l_flags & XLOG_IO_ERROR)
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index cd0b077deb35..e19b20c87f35 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2230,9 +2230,9 @@ xlog_recover_get_buf_lsn(
 	struct xfs_mount	*mp,
 	struct xfs_buf		*bp)
 {
-	__uint32_t		magic32;
-	__uint16_t		magic16;
-	__uint16_t		magicda;
+	uint32_t		magic32;
+	uint16_t		magic16;
+	uint16_t		magicda;
 	void			*blk = bp->b_addr;
 	uuid_t			*uuid;
 	xfs_lsn_t		lsn = -1;
@@ -2381,9 +2381,9 @@ xlog_recover_validate_buf_type(
 	xfs_lsn_t		current_lsn)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
-	__uint32_t		magic32;
-	__uint16_t		magic16;
-	__uint16_t		magicda;
+	uint32_t		magic32;
+	uint16_t		magic16;
+	uint16_t		magicda;
 	char			*warnmsg = NULL;
 
 	/*
@@ -2852,7 +2852,7 @@ xlog_recover_buffer_pass2(
 	if (XFS_DINODE_MAGIC ==
 	    be16_to_cpu(*((__be16 *)xfs_buf_offset(bp, 0))) &&
 	    (BBTOB(bp->b_io_length) != MAX(log->l_mp->m_sb.sb_blocksize,
-			(__uint32_t)log->l_mp->m_inode_cluster_size))) {
+			(uint32_t)log->l_mp->m_inode_cluster_size))) {
 		xfs_buf_stale(bp);
 		error = xfs_bwrite(bp);
 	} else {
@@ -3423,7 +3423,7 @@ xlog_recover_efd_pass2(
 	xfs_efd_log_format_t	*efd_formatp;
 	xfs_efi_log_item_t	*efip = NULL;
 	xfs_log_item_t		*lip;
-	__uint64_t		efi_id;
+	uint64_t		efi_id;
 	struct xfs_ail_cursor	cur;
 	struct xfs_ail		*ailp = log->l_ailp;
 
@@ -3519,7 +3519,7 @@ xlog_recover_rud_pass2(
 	struct xfs_rud_log_format	*rud_formatp;
 	struct xfs_rui_log_item		*ruip = NULL;
 	struct xfs_log_item		*lip;
-	__uint64_t			rui_id;
+	uint64_t			rui_id;
 	struct xfs_ail_cursor		cur;
 	struct xfs_ail			*ailp = log->l_ailp;
 
@@ -3635,7 +3635,7 @@ xlog_recover_cud_pass2(
 	struct xfs_cud_log_format	*cud_formatp;
 	struct xfs_cui_log_item		*cuip = NULL;
 	struct xfs_log_item		*lip;
-	__uint64_t			cui_id;
+	uint64_t			cui_id;
 	struct xfs_ail_cursor		cur;
 	struct xfs_ail			*ailp = log->l_ailp;
 
@@ -3754,7 +3754,7 @@ xlog_recover_bud_pass2(
 	struct xfs_bud_log_format	*bud_formatp;
 	struct xfs_bui_log_item		*buip = NULL;
 	struct xfs_log_item		*lip;
-	__uint64_t			bui_id;
+	uint64_t			bui_id;
 	struct xfs_ail_cursor		cur;
 	struct xfs_ail			*ailp = log->l_ailp;
 
@@ -5772,9 +5772,9 @@ xlog_recover_check_summary(
 	xfs_buf_t	*agfbp;
 	xfs_buf_t	*agibp;
 	xfs_agnumber_t	agno;
-	__uint64_t	freeblks;
-	__uint64_t	itotal;
-	__uint64_t	ifree;
+	uint64_t	freeblks;
+	uint64_t	itotal;
+	uint64_t	ifree;
 	int		error;
 
 	mp = log->l_mp;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 2eaf81859166..cc6789d35232 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -174,7 +174,7 @@ xfs_free_perag(
 int
 xfs_sb_validate_fsb_count(
 	xfs_sb_t	*sbp,
-	__uint64_t	nblocks)
+	uint64_t	nblocks)
 {
 	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
@@ -436,7 +436,7 @@ STATIC void
 xfs_set_maxicount(xfs_mount_t *mp)
 {
 	xfs_sb_t	*sbp = &(mp->m_sb);
-	__uint64_t	icount;
+	uint64_t	icount;
 
 	if (sbp->sb_imax_pct) {
 		/*
@@ -502,7 +502,7 @@ xfs_set_low_space_thresholds(
 	int i;
 
 	for (i = 0; i < XFS_LOWSP_MAX; i++) {
-		__uint64_t space = mp->m_sb.sb_dblocks;
+		uint64_t space = mp->m_sb.sb_dblocks;
 
 		do_div(space, 100);
 		mp->m_low_space[i] = space * (i + 1);
@@ -598,10 +598,10 @@ xfs_mount_reset_sbqflags(
 	return xfs_sync_sb(mp, false);
 }
 
-__uint64_t
+uint64_t
 xfs_default_resblks(xfs_mount_t *mp)
 {
-	__uint64_t resblks;
+	uint64_t resblks;
 
 	/*
 	 * We default to 5% or 8192 fsbs of space reserved, whichever is
@@ -612,7 +612,7 @@ xfs_default_resblks(xfs_mount_t *mp)
 	 */
 	resblks = mp->m_sb.sb_dblocks;
 	do_div(resblks, 20);
-	resblks = min_t(__uint64_t, resblks, 8192);
+	resblks = min_t(uint64_t, resblks, 8192);
 	return resblks;
 }
 
@@ -632,7 +632,7 @@ xfs_mountfs(
 {
 	struct xfs_sb		*sbp = &(mp->m_sb);
 	struct xfs_inode	*rip;
-	__uint64_t		resblks;
+	uint64_t		resblks;
 	uint			quotamount = 0;
 	uint			quotaflags = 0;
 	int			error = 0;
@@ -1060,7 +1060,7 @@ void
 xfs_unmountfs(
 	struct xfs_mount	*mp)
 {
-	__uint64_t		resblks;
+	uint64_t		resblks;
 	int			error;
 
 	cancel_delayed_work_sync(&mp->m_eofblocks_work);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 9fa312a41c93..305d95394e2d 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -108,10 +108,10 @@ typedef struct xfs_mount {
 	xfs_buftarg_t		*m_ddev_targp;	/* saves taking the address */
 	xfs_buftarg_t		*m_logdev_targp;/* ptr to log device */
 	xfs_buftarg_t		*m_rtdev_targp;	/* ptr to rt device */
-	__uint8_t		m_blkbit_log;	/* blocklog + NBBY */
-	__uint8_t		m_blkbb_log;	/* blocklog - BBSHIFT */
-	__uint8_t		m_agno_log;	/* log #ag's */
-	__uint8_t		m_agino_log;	/* #bits for agino in inum */
+	uint8_t			m_blkbit_log;	/* blocklog + NBBY */
+	uint8_t			m_blkbb_log;	/* blocklog - BBSHIFT */
+	uint8_t			m_agno_log;	/* log #ag's */
+	uint8_t			m_agino_log;	/* #bits for agino in inum */
 	uint			m_inode_cluster_size;/* min inode buf size */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
@@ -139,7 +139,7 @@ typedef struct xfs_mount {
 	struct mutex		m_growlock;	/* growfs mutex */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_dmevmask;	/* DMI events for this FS */
-	__uint64_t		m_flags;	/* global mount flags */
+	uint64_t		m_flags;	/* global mount flags */
 	bool			m_inotbt_nores; /* no per-AG finobt resv. */
 	int			m_ialloc_inos;	/* inodes in inode allocation */
 	int			m_ialloc_blks;	/* blocks in inode allocation */
@@ -148,14 +148,14 @@ typedef struct xfs_mount {
 	int			m_inoalign_mask;/* mask sb_inoalignmt if used */
 	uint			m_qflags;	/* quota status flags */
 	struct xfs_trans_resv	m_resv;		/* precomputed res values */
-	__uint64_t		m_maxicount;	/* maximum inode count */
-	__uint64_t		m_resblks;	/* total reserved blocks */
-	__uint64_t		m_resblks_avail;/* available reserved blocks */
-	__uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
+	uint64_t		m_maxicount;	/* maximum inode count */
+	uint64_t		m_resblks;	/* total reserved blocks */
+	uint64_t		m_resblks_avail;/* available reserved blocks */
+	uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
 	int			m_dalign;	/* stripe unit */
 	int			m_swidth;	/* stripe width */
 	int			m_sinoalign;	/* stripe unit inode alignment */
-	__uint8_t		m_sectbb_log;	/* sectlog - BBSHIFT */
+	uint8_t			m_sectbb_log;	/* sectlog - BBSHIFT */
 	const struct xfs_nameops *m_dirnameops;	/* vector of dir name ops */
 	const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */
 	const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */
@@ -194,7 +194,7 @@ typedef struct xfs_mount {
 	 * ever support shrinks it would have to be persisted in addition
 	 * to various other kinds of pain inflicted on the pNFS server.
 	 */
-	__uint32_t		m_generation;
+	uint32_t		m_generation;
 
 	bool			m_fail_unmount;
 #ifdef DEBUG
@@ -367,12 +367,12 @@ typedef struct xfs_perag {
 	char		pagi_init;	/* this agi's entry is initialized */
 	char		pagf_metadata;	/* the agf is preferred to be metadata */
 	char		pagi_inodeok;	/* The agi is ok for inodes */
-	__uint8_t	pagf_levels[XFS_BTNUM_AGF];
+	uint8_t		pagf_levels[XFS_BTNUM_AGF];
 					/* # of levels in bno & cnt btree */
-	__uint32_t	pagf_flcount;	/* count of blocks in freelist */
+	uint32_t	pagf_flcount;	/* count of blocks in freelist */
 	xfs_extlen_t	pagf_freeblks;	/* total free blocks */
 	xfs_extlen_t	pagf_longest;	/* longest free space */
-	__uint32_t	pagf_btreeblks;	/* # of blocks held in AGF btrees */
+	uint32_t	pagf_btreeblks;	/* # of blocks held in AGF btrees */
 	xfs_agino_t	pagi_freecount;	/* number of free inodes */
 	xfs_agino_t	pagi_count;	/* number of allocated inodes */
 
@@ -411,7 +411,7 @@ typedef struct xfs_perag {
 	struct xfs_ag_resv	pag_agfl_resv;
 
 	/* reference count */
-	__uint8_t		pagf_refcount_level;
+	uint8_t			pagf_refcount_level;
 } xfs_perag_t;
 
 static inline struct xfs_ag_resv *
@@ -434,7 +434,7 @@ void xfs_buf_hash_destroy(xfs_perag_t *pag);
 
 extern void	xfs_uuid_table_free(void);
 extern int	xfs_log_sbcount(xfs_mount_t *);
-extern __uint64_t xfs_default_resblks(xfs_mount_t *mp);
+extern uint64_t xfs_default_resblks(xfs_mount_t *mp);
 extern int	xfs_mountfs(xfs_mount_t *mp);
 extern int	xfs_initialize_perag(xfs_mount_t *mp, xfs_agnumber_t agcount,
 				     xfs_agnumber_t *maxagi);
@@ -450,7 +450,7 @@ extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
 extern int	xfs_readsb(xfs_mount_t *, int);
 extern void	xfs_freesb(xfs_mount_t *);
 extern bool	xfs_fs_writable(struct xfs_mount *mp, int level);
-extern int	xfs_sb_validate_fsb_count(struct xfs_sb *, __uint64_t);
+extern int	xfs_sb_validate_fsb_count(struct xfs_sb *, uint64_t);
 
 extern int	xfs_dev_is_read_only(struct xfs_mount *, char *);
 
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 3e52d5de7ae1..2be6d2735ca9 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -33,7 +33,7 @@ xfs_fill_statvfs_from_dquot(
 	struct kstatfs		*statp,
 	struct xfs_dquot	*dqp)
 {
-	__uint64_t		limit;
+	uint64_t		limit;
 
 	limit = dqp->q_core.d_blk_softlimit ?
 		be64_to_cpu(dqp->q_core.d_blk_softlimit) :
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index c57aa7f18087..91472193643b 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1256,13 +1256,13 @@ xfs_rtpick_extent(
 {
 	xfs_rtblock_t	b;		/* result block */
 	int		log2;		/* log of sequence number */
-	__uint64_t	resid;		/* residual after log removed */
-	__uint64_t	seq;		/* sequence number of file creation */
-	__uint64_t	*seqp;		/* pointer to seqno in inode */
+	uint64_t	resid;		/* residual after log removed */
+	uint64_t	seq;		/* sequence number of file creation */
+	uint64_t	*seqp;		/* pointer to seqno in inode */
 
 	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
-	seqp = (__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
+	seqp = (uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
 	if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
 		mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
 		*seqp = 0;
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index f11282c96887..056e12b421eb 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -33,9 +33,9 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 {
 	int		i, j;
 	int		len = 0;
-	__uint64_t	xs_xstrat_bytes = 0;
-	__uint64_t	xs_write_bytes = 0;
-	__uint64_t	xs_read_bytes = 0;
+	uint64_t	xs_xstrat_bytes = 0;
+	uint64_t	xs_write_bytes = 0;
+	uint64_t	xs_read_bytes = 0;
 
 	static const struct xstats_entry {
 		char	*desc;
@@ -100,7 +100,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 void xfs_stats_clearall(struct xfsstats __percpu *stats)
 {
 	int		c;
-	__uint32_t	vn_active;
+	uint32_t	vn_active;
 
 	xfs_notice(NULL, "Clearing xfsstats");
 	for_each_possible_cpu(c) {
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index 375840f5a99a..f64d0ae345c4 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -54,125 +54,125 @@ enum {
  */
 struct __xfsstats {
 # define XFSSTAT_END_EXTENT_ALLOC	4
-	__uint32_t		xs_allocx;
-	__uint32_t		xs_allocb;
-	__uint32_t		xs_freex;
-	__uint32_t		xs_freeb;
+	uint32_t		xs_allocx;
+	uint32_t		xs_allocb;
+	uint32_t		xs_freex;
+	uint32_t		xs_freeb;
 # define XFSSTAT_END_ALLOC_BTREE	(XFSSTAT_END_EXTENT_ALLOC+4)
-	__uint32_t		xs_abt_lookup;
-	__uint32_t		xs_abt_compare;
-	__uint32_t		xs_abt_insrec;
-	__uint32_t		xs_abt_delrec;
+	uint32_t		xs_abt_lookup;
+	uint32_t		xs_abt_compare;
+	uint32_t		xs_abt_insrec;
+	uint32_t		xs_abt_delrec;
 # define XFSSTAT_END_BLOCK_MAPPING	(XFSSTAT_END_ALLOC_BTREE+7)
-	__uint32_t		xs_blk_mapr;
-	__uint32_t		xs_blk_mapw;
-	__uint32_t		xs_blk_unmap;
-	__uint32_t		xs_add_exlist;
-	__uint32_t		xs_del_exlist;
-	__uint32_t		xs_look_exlist;
-	__uint32_t		xs_cmp_exlist;
+	uint32_t		xs_blk_mapr;
+	uint32_t		xs_blk_mapw;
+	uint32_t		xs_blk_unmap;
+	uint32_t		xs_add_exlist;
+	uint32_t		xs_del_exlist;
+	uint32_t		xs_look_exlist;
+	uint32_t		xs_cmp_exlist;
 # define XFSSTAT_END_BLOCK_MAP_BTREE	(XFSSTAT_END_BLOCK_MAPPING+4)
-	__uint32_t		xs_bmbt_lookup;
-	__uint32_t		xs_bmbt_compare;
-	__uint32_t		xs_bmbt_insrec;
-	__uint32_t		xs_bmbt_delrec;
+	uint32_t		xs_bmbt_lookup;
+	uint32_t		xs_bmbt_compare;
+	uint32_t		xs_bmbt_insrec;
+	uint32_t		xs_bmbt_delrec;
 # define XFSSTAT_END_DIRECTORY_OPS	(XFSSTAT_END_BLOCK_MAP_BTREE+4)
-	__uint32_t		xs_dir_lookup;
-	__uint32_t		xs_dir_create;
-	__uint32_t		xs_dir_remove;
-	__uint32_t		xs_dir_getdents;
+	uint32_t		xs_dir_lookup;
+	uint32_t		xs_dir_create;
+	uint32_t		xs_dir_remove;
+	uint32_t		xs_dir_getdents;
 # define XFSSTAT_END_TRANSACTIONS	(XFSSTAT_END_DIRECTORY_OPS+3)
-	__uint32_t		xs_trans_sync;
-	__uint32_t		xs_trans_async;
-	__uint32_t		xs_trans_empty;
+	uint32_t		xs_trans_sync;
+	uint32_t		xs_trans_async;
+	uint32_t		xs_trans_empty;
 # define XFSSTAT_END_INODE_OPS		(XFSSTAT_END_TRANSACTIONS+7)
-	__uint32_t		xs_ig_attempts;
-	__uint32_t		xs_ig_found;
-	__uint32_t		xs_ig_frecycle;
-	__uint32_t		xs_ig_missed;
-	__uint32_t		xs_ig_dup;
-	__uint32_t		xs_ig_reclaims;
-	__uint32_t		xs_ig_attrchg;
+	uint32_t		xs_ig_attempts;
+	uint32_t		xs_ig_found;
+	uint32_t		xs_ig_frecycle;
+	uint32_t		xs_ig_missed;
+	uint32_t		xs_ig_dup;
+	uint32_t		xs_ig_reclaims;
+	uint32_t		xs_ig_attrchg;
 # define XFSSTAT_END_LOG_OPS		(XFSSTAT_END_INODE_OPS+5)
-	__uint32_t		xs_log_writes;
-	__uint32_t		xs_log_blocks;
-	__uint32_t		xs_log_noiclogs;
-	__uint32_t		xs_log_force;
-	__uint32_t		xs_log_force_sleep;
+	uint32_t		xs_log_writes;
+	uint32_t		xs_log_blocks;
+	uint32_t		xs_log_noiclogs;
+	uint32_t		xs_log_force;
+	uint32_t		xs_log_force_sleep;
 # define XFSSTAT_END_TAIL_PUSHING	(XFSSTAT_END_LOG_OPS+10)
-	__uint32_t		xs_try_logspace;
-	__uint32_t		xs_sleep_logspace;
-	__uint32_t		xs_push_ail;
-	__uint32_t		xs_push_ail_success;
-	__uint32_t		xs_push_ail_pushbuf;
-	__uint32_t		xs_push_ail_pinned;
-	__uint32_t		xs_push_ail_locked;
-	__uint32_t		xs_push_ail_flushing;
-	__uint32_t		xs_push_ail_restarts;
-	__uint32_t		xs_push_ail_flush;
+	uint32_t		xs_try_logspace;
+	uint32_t		xs_sleep_logspace;
+	uint32_t		xs_push_ail;
+	uint32_t		xs_push_ail_success;
+	uint32_t		xs_push_ail_pushbuf;
+	uint32_t		xs_push_ail_pinned;
+	uint32_t		xs_push_ail_locked;
+	uint32_t		xs_push_ail_flushing;
+	uint32_t		xs_push_ail_restarts;
+	uint32_t		xs_push_ail_flush;
 # define XFSSTAT_END_WRITE_CONVERT	(XFSSTAT_END_TAIL_PUSHING+2)
-	__uint32_t		xs_xstrat_quick;
-	__uint32_t		xs_xstrat_split;
+	uint32_t		xs_xstrat_quick;
+	uint32_t		xs_xstrat_split;
 # define XFSSTAT_END_READ_WRITE_OPS	(XFSSTAT_END_WRITE_CONVERT+2)
-	__uint32_t		xs_write_calls;
-	__uint32_t		xs_read_calls;
+	uint32_t		xs_write_calls;
+	uint32_t		xs_read_calls;
 # define XFSSTAT_END_ATTRIBUTE_OPS	(XFSSTAT_END_READ_WRITE_OPS+4)
-	__uint32_t		xs_attr_get;
-	__uint32_t		xs_attr_set;
-	__uint32_t		xs_attr_remove;
-	__uint32_t		xs_attr_list;
+	uint32_t		xs_attr_get;
+	uint32_t		xs_attr_set;
+	uint32_t		xs_attr_remove;
+	uint32_t		xs_attr_list;
 # define XFSSTAT_END_INODE_CLUSTER	(XFSSTAT_END_ATTRIBUTE_OPS+3)
-	__uint32_t		xs_iflush_count;
-	__uint32_t		xs_icluster_flushcnt;
-	__uint32_t		xs_icluster_flushinode;
+	uint32_t		xs_iflush_count;
+	uint32_t		xs_icluster_flushcnt;
+	uint32_t		xs_icluster_flushinode;
 # define XFSSTAT_END_VNODE_OPS		(XFSSTAT_END_INODE_CLUSTER+8)
-	__uint32_t		vn_active;	/* # vnodes not on free lists */
-	__uint32_t		vn_alloc;	/* # times vn_alloc called */
-	__uint32_t		vn_get;		/* # times vn_get called */
-	__uint32_t		vn_hold;	/* # times vn_hold called */
-	__uint32_t		vn_rele;	/* # times vn_rele called */
-	__uint32_t		vn_reclaim;	/* # times vn_reclaim called */
-	__uint32_t		vn_remove;	/* # times vn_remove called */
-	__uint32_t		vn_free;	/* # times vn_free called */
+	uint32_t		vn_active;	/* # vnodes not on free lists */
+	uint32_t		vn_alloc;	/* # times vn_alloc called */
+	uint32_t		vn_get;		/* # times vn_get called */
+	uint32_t		vn_hold;	/* # times vn_hold called */
+	uint32_t		vn_rele;	/* # times vn_rele called */
+	uint32_t		vn_reclaim;	/* # times vn_reclaim called */
+	uint32_t		vn_remove;	/* # times vn_remove called */
+	uint32_t		vn_free;	/* # times vn_free called */
 #define XFSSTAT_END_BUF			(XFSSTAT_END_VNODE_OPS+9)
-	__uint32_t		xb_get;
-	__uint32_t		xb_create;
-	__uint32_t		xb_get_locked;
-	__uint32_t		xb_get_locked_waited;
-	__uint32_t		xb_busy_locked;
-	__uint32_t		xb_miss_locked;
-	__uint32_t		xb_page_retries;
-	__uint32_t		xb_page_found;
-	__uint32_t		xb_get_read;
+	uint32_t		xb_get;
+	uint32_t		xb_create;
+	uint32_t		xb_get_locked;
+	uint32_t		xb_get_locked_waited;
+	uint32_t		xb_busy_locked;
+	uint32_t		xb_miss_locked;
+	uint32_t		xb_page_retries;
+	uint32_t		xb_page_found;
+	uint32_t		xb_get_read;
 /* Version 2 btree counters */
 #define XFSSTAT_END_ABTB_V2		(XFSSTAT_END_BUF + __XBTS_MAX)
-	__uint32_t		xs_abtb_2[__XBTS_MAX];
+	uint32_t		xs_abtb_2[__XBTS_MAX];
 #define XFSSTAT_END_ABTC_V2		(XFSSTAT_END_ABTB_V2 + __XBTS_MAX)
-	__uint32_t		xs_abtc_2[__XBTS_MAX];
+	uint32_t		xs_abtc_2[__XBTS_MAX];
 #define XFSSTAT_END_BMBT_V2		(XFSSTAT_END_ABTC_V2 + __XBTS_MAX)
-	__uint32_t		xs_bmbt_2[__XBTS_MAX];
+	uint32_t		xs_bmbt_2[__XBTS_MAX];
 #define XFSSTAT_END_IBT_V2		(XFSSTAT_END_BMBT_V2 + __XBTS_MAX)
-	__uint32_t		xs_ibt_2[__XBTS_MAX];
+	uint32_t		xs_ibt_2[__XBTS_MAX];
 #define XFSSTAT_END_FIBT_V2		(XFSSTAT_END_IBT_V2 + __XBTS_MAX)
-	__uint32_t		xs_fibt_2[__XBTS_MAX];
+	uint32_t		xs_fibt_2[__XBTS_MAX];
 #define XFSSTAT_END_RMAP_V2		(XFSSTAT_END_FIBT_V2 + __XBTS_MAX)
-	__uint32_t		xs_rmap_2[__XBTS_MAX];
+	uint32_t		xs_rmap_2[__XBTS_MAX];
 #define XFSSTAT_END_REFCOUNT		(XFSSTAT_END_RMAP_V2 + __XBTS_MAX)
-	__uint32_t		xs_refcbt_2[__XBTS_MAX];
+	uint32_t		xs_refcbt_2[__XBTS_MAX];
 #define XFSSTAT_END_XQMSTAT		(XFSSTAT_END_REFCOUNT + 6)
-	__uint32_t		xs_qm_dqreclaims;
-	__uint32_t		xs_qm_dqreclaim_misses;
-	__uint32_t		xs_qm_dquot_dups;
-	__uint32_t		xs_qm_dqcachemisses;
-	__uint32_t		xs_qm_dqcachehits;
-	__uint32_t		xs_qm_dqwants;
+	uint32_t		xs_qm_dqreclaims;
+	uint32_t		xs_qm_dqreclaim_misses;
+	uint32_t		xs_qm_dquot_dups;
+	uint32_t		xs_qm_dqcachemisses;
+	uint32_t		xs_qm_dqcachehits;
+	uint32_t		xs_qm_dqwants;
 #define XFSSTAT_END_QM			(XFSSTAT_END_XQMSTAT+2)
-	__uint32_t		xs_qm_dquot;
-	__uint32_t		xs_qm_dquot_unused;
+	uint32_t		xs_qm_dquot;
+	uint32_t		xs_qm_dquot_unused;
 /* Extra precision counters */
-	__uint64_t		xs_xstrat_bytes;
-	__uint64_t		xs_write_bytes;
-	__uint64_t		xs_read_bytes;
+	uint64_t		xs_xstrat_bytes;
+	uint64_t		xs_write_bytes;
+	uint64_t		xs_read_bytes;
 };
 
 struct xfsstats {
@@ -186,7 +186,7 @@ struct xfsstats {
  * simple wrapper for getting the array index of s struct member offset
  */
 #define XFS_STATS_CALC_INDEX(member)	\
-	(offsetof(struct __xfsstats, member) / (int)sizeof(__uint32_t))
+	(offsetof(struct __xfsstats, member) / (int)sizeof(uint32_t))
 
 
 int xfs_stats_format(struct xfsstats __percpu *stats, char *buf);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 455a575f101d..a19aab897c9b 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -196,7 +196,7 @@ xfs_parseargs(
 	int			dsunit = 0;
 	int			dswidth = 0;
 	int			iosize = 0;
-	__uint8_t		iosizelog = 0;
+	uint8_t			iosizelog = 0;
 
 	/*
 	 * set up the mount name first so all the errors will refer to the
@@ -556,7 +556,7 @@ xfs_showargs(
 
 	return 0;
 }
-static __uint64_t
+static uint64_t
 xfs_max_file_offset(
 	unsigned int		blockshift)
 {
@@ -587,7 +587,7 @@ xfs_max_file_offset(
 # endif
 #endif
 
-	return (((__uint64_t)pagefactor) << bitshift) - 1;
+	return (((uint64_t)pagefactor) << bitshift) - 1;
 }
 
 /*
@@ -622,7 +622,7 @@ xfs_set_inode_alloc(
 	 * the max inode percentage.  Used only for inode32.
 	 */
 	if (mp->m_maxicount) {
-		__uint64_t	icount;
+		uint64_t	icount;
 
 		icount = sbp->sb_dblocks * sbp->sb_imax_pct;
 		do_div(icount, 100);
@@ -1088,12 +1088,12 @@ xfs_fs_statfs(
 	struct xfs_mount	*mp = XFS_M(dentry->d_sb);
 	xfs_sb_t		*sbp = &mp->m_sb;
 	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
-	__uint64_t		fakeinos, id;
-	__uint64_t		icount;
-	__uint64_t		ifree;
-	__uint64_t		fdblocks;
+	uint64_t		fakeinos, id;
+	uint64_t		icount;
+	uint64_t		ifree;
+	uint64_t		fdblocks;
 	xfs_extlen_t		lsize;
-	__int64_t		ffree;
+	int64_t			ffree;
 
 	statp->f_type = XFS_SB_MAGIC;
 	statp->f_namelen = MAXNAMELEN - 1;
@@ -1116,7 +1116,7 @@ xfs_fs_statfs(
 	statp->f_bavail = statp->f_bfree;
 
 	fakeinos = statp->f_bfree << sbp->sb_inopblog;
-	statp->f_files = MIN(icount + fakeinos, (__uint64_t)XFS_MAXINUMBER);
+	statp->f_files = MIN(icount + fakeinos, (uint64_t)XFS_MAXINUMBER);
 	if (mp->m_maxicount)
 		statp->f_files = min_t(typeof(statp->f_files),
 					statp->f_files,
@@ -1129,7 +1129,7 @@ xfs_fs_statfs(
 
 	/* make sure statp->f_ffree does not underflow */
 	ffree = statp->f_files - (icount - ifree);
-	statp->f_ffree = max_t(__int64_t, ffree, 0);
+	statp->f_ffree = max_t(int64_t, ffree, 0);
 
 
 	if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
@@ -1142,7 +1142,7 @@ xfs_fs_statfs(
 STATIC void
 xfs_save_resvblks(struct xfs_mount *mp)
 {
-	__uint64_t resblks = 0;
+	uint64_t resblks = 0;
 
 	mp->m_resblks_save = mp->m_resblks;
 	xfs_reserve_blocks(mp, &resblks, NULL);
@@ -1151,7 +1151,7 @@ xfs_save_resvblks(struct xfs_mount *mp)
 STATIC void
 xfs_restore_resvblks(struct xfs_mount *mp)
 {
-	__uint64_t resblks;
+	uint64_t resblks;
 
 	if (mp->m_resblks_save) {
 		resblks = mp->m_resblks_save;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index a560bfd392c1..bcc3cdf8e1c5 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -251,7 +251,7 @@ TRACE_EVENT(xfs_iext_insert,
 		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
 		  (long)__entry->idx,
 		  __entry->startoff,
-		  (__int64_t)__entry->startblock,
+		  (int64_t)__entry->startblock,
 		  __entry->blockcount,
 		  __entry->state,
 		  (char *)__entry->caller_ip)
@@ -295,7 +295,7 @@ DECLARE_EVENT_CLASS(xfs_bmap_class,
 		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
 		  (long)__entry->idx,
 		  __entry->startoff,
-		  (__int64_t)__entry->startblock,
+		  (int64_t)__entry->startblock,
 		  __entry->blockcount,
 		  __entry->state,
 		  (char *)__entry->caller_ip)
@@ -1281,7 +1281,7 @@ DECLARE_EVENT_CLASS(xfs_imap_class,
 		  __entry->count,
 		  __print_symbolic(__entry->type, XFS_IO_TYPES),
 		  __entry->startoff,
-		  (__int64_t)__entry->startblock,
+		  (int64_t)__entry->startblock,
 		  __entry->blockcount)
 )
 
@@ -2039,7 +2039,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class,
 	TP_ARGS(log, buf_f),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(__int64_t, blkno)
+		__field(int64_t, blkno)
 		__field(unsigned short, len)
 		__field(unsigned short, flags)
 		__field(unsigned short, size)
@@ -2088,7 +2088,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class,
 		__field(int, fields)
 		__field(unsigned short, asize)
 		__field(unsigned short, dsize)
-		__field(__int64_t, blkno)
+		__field(int64_t, blkno)
 		__field(int, len)
 		__field(int, boffset)
 	),
@@ -3238,8 +3238,8 @@ DECLARE_EVENT_CLASS(xfs_fsmap_class,
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_fsblock_t, bno)
 		__field(xfs_filblks_t, len)
-		__field(__uint64_t, owner)
-		__field(__uint64_t, offset)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
@@ -3279,9 +3279,9 @@ DECLARE_EVENT_CLASS(xfs_getfsmap_class,
 		__field(dev_t, keydev)
 		__field(xfs_daddr_t, block)
 		__field(xfs_daddr_t, len)
-		__field(__uint64_t, owner)
-		__field(__uint64_t, offset)
-		__field(__uint64_t, flags)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(uint64_t, flags)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 82bb61e330d9..6bdad6f58934 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -245,7 +245,7 @@ struct xfs_rud_log_item *xfs_trans_get_rud(struct xfs_trans *tp,
 		struct xfs_rui_log_item *ruip);
 int xfs_trans_log_finish_rmap_update(struct xfs_trans *tp,
 		struct xfs_rud_log_item *rudp, enum xfs_rmap_intent_type type,
-		__uint64_t owner, int whichfork, xfs_fileoff_t startoff,
+		uint64_t owner, int whichfork, xfs_fileoff_t startoff,
 		xfs_fsblock_t startblock, xfs_filblks_t blockcount,
 		xfs_exntst_t state, struct xfs_btree_cur **pcur);
 
diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c
index 9ead064b5e90..9b577beb43d7 100644
--- a/fs/xfs/xfs_trans_rmap.c
+++ b/fs/xfs/xfs_trans_rmap.c
@@ -96,7 +96,7 @@ xfs_trans_log_finish_rmap_update(
 	struct xfs_trans		*tp,
 	struct xfs_rud_log_item		*rudp,
 	enum xfs_rmap_intent_type	type,
-	__uint64_t			owner,
+	uint64_t			owner,
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,

From 38dee376d67047e9877a34e408013852c9729eb8 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:06 -0700
Subject: [PATCH 16/48] xfs: always compile the btree inorder check functions

The btree record and key inorder check functions will be used by the
btree scrubber code, so make sure they're always built.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_alloc_btree.c    | 6 ------
 fs/xfs/libxfs/xfs_bmap_btree.c     | 4 ----
 fs/xfs/libxfs/xfs_btree.h          | 2 --
 fs/xfs/libxfs/xfs_ialloc_btree.c   | 6 ------
 fs/xfs/libxfs/xfs_refcount_btree.c | 4 ----
 fs/xfs/libxfs/xfs_rmap_btree.c     | 4 ----
 6 files changed, 26 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 5020cbc02db8..cfde0a0f9706 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -395,7 +395,6 @@ const struct xfs_buf_ops xfs_allocbt_buf_ops = {
 };
 
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_bnobt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -442,7 +441,6 @@ xfs_cntbt_recs_inorder(
 		 be32_to_cpu(r1->alloc.ar_startblock) <
 		 be32_to_cpu(r2->alloc.ar_startblock));
 }
-#endif /* DEBUG */
 
 static const struct xfs_btree_ops xfs_bnobt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
@@ -462,10 +460,8 @@ static const struct xfs_btree_ops xfs_bnobt_ops = {
 	.key_diff		= xfs_bnobt_key_diff,
 	.buf_ops		= &xfs_allocbt_buf_ops,
 	.diff_two_keys		= xfs_bnobt_diff_two_keys,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_bnobt_keys_inorder,
 	.recs_inorder		= xfs_bnobt_recs_inorder,
-#endif
 };
 
 static const struct xfs_btree_ops xfs_cntbt_ops = {
@@ -486,10 +482,8 @@ static const struct xfs_btree_ops xfs_cntbt_ops = {
 	.key_diff		= xfs_cntbt_key_diff,
 	.buf_ops		= &xfs_allocbt_buf_ops,
 	.diff_two_keys		= xfs_cntbt_diff_two_keys,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_cntbt_keys_inorder,
 	.recs_inorder		= xfs_cntbt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 5e2b3dc138ad..e23495e23620 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -687,7 +687,6 @@ const struct xfs_buf_ops xfs_bmbt_buf_ops = {
 };
 
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_bmbt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -708,7 +707,6 @@ xfs_bmbt_recs_inorder(
 		xfs_bmbt_disk_get_blockcount(&r1->bmbt) <=
 		xfs_bmbt_disk_get_startoff(&r2->bmbt);
 }
-#endif	/* DEBUG */
 
 static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
@@ -726,10 +724,8 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.init_ptr_from_cur	= xfs_bmbt_init_ptr_from_cur,
 	.key_diff		= xfs_bmbt_key_diff,
 	.buf_ops		= &xfs_bmbt_buf_ops,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_bmbt_keys_inorder,
 	.recs_inorder		= xfs_bmbt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 0a931f644103..177a364ce5cf 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -163,7 +163,6 @@ struct xfs_btree_ops {
 
 	const struct xfs_buf_ops	*buf_ops;
 
-#if defined(DEBUG) || defined(XFS_WARN)
 	/* check that k1 is lower than k2 */
 	int	(*keys_inorder)(struct xfs_btree_cur *cur,
 				union xfs_btree_key *k1,
@@ -173,7 +172,6 @@ struct xfs_btree_ops {
 	int	(*recs_inorder)(struct xfs_btree_cur *cur,
 				union xfs_btree_rec *r1,
 				union xfs_btree_rec *r2);
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index ed52d99732b8..6b1ddeb7e5c1 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -302,7 +302,6 @@ const struct xfs_buf_ops xfs_inobt_buf_ops = {
 	.verify_write = xfs_inobt_write_verify,
 };
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_inobt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -322,7 +321,6 @@ xfs_inobt_recs_inorder(
 	return be32_to_cpu(r1->inobt.ir_startino) + XFS_INODES_PER_CHUNK <=
 		be32_to_cpu(r2->inobt.ir_startino);
 }
-#endif	/* DEBUG */
 
 static const struct xfs_btree_ops xfs_inobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
@@ -339,10 +337,8 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 	.init_ptr_from_cur	= xfs_inobt_init_ptr_from_cur,
 	.key_diff		= xfs_inobt_key_diff,
 	.buf_ops		= &xfs_inobt_buf_ops,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
-#endif
 };
 
 static const struct xfs_btree_ops xfs_finobt_ops = {
@@ -360,10 +356,8 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
 	.init_ptr_from_cur	= xfs_finobt_init_ptr_from_cur,
 	.key_diff		= xfs_inobt_key_diff,
 	.buf_ops		= &xfs_inobt_buf_ops,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 65c222ae5b04..3c59dd3d58d7 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -285,7 +285,6 @@ const struct xfs_buf_ops xfs_refcountbt_buf_ops = {
 	.verify_write		= xfs_refcountbt_write_verify,
 };
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_refcountbt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -306,7 +305,6 @@ xfs_refcountbt_recs_inorder(
 		be32_to_cpu(r1->refc.rc_blockcount) <=
 		be32_to_cpu(r2->refc.rc_startblock);
 }
-#endif
 
 static const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.rec_len		= sizeof(struct xfs_refcount_rec),
@@ -325,10 +323,8 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.key_diff		= xfs_refcountbt_key_diff,
 	.buf_ops		= &xfs_refcountbt_buf_ops,
 	.diff_two_keys		= xfs_refcountbt_diff_two_keys,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_refcountbt_keys_inorder,
 	.recs_inorder		= xfs_refcountbt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index c5b4a1c862b0..9d9c9192584c 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -377,7 +377,6 @@ const struct xfs_buf_ops xfs_rmapbt_buf_ops = {
 	.verify_write		= xfs_rmapbt_write_verify,
 };
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_rmapbt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -437,7 +436,6 @@ xfs_rmapbt_recs_inorder(
 		return 1;
 	return 0;
 }
-#endif	/* DEBUG */
 
 static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
@@ -456,10 +454,8 @@ static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.key_diff		= xfs_rmapbt_key_diff,
 	.buf_ops		= &xfs_rmapbt_buf_ops,
 	.diff_two_keys		= xfs_rmapbt_diff_two_keys,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_rmapbt_keys_inorder,
 	.recs_inorder		= xfs_rmapbt_recs_inorder,
-#endif
 };
 
 /*

From 2678809799e6e37db0800725157f5ebfc03a9df7 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:07 -0700
Subject: [PATCH 17/48] xfs: export various function for the online scrubber

Export various internal functions so that the online scrubber can use
them to check the state of metadata.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_alloc.c     |  2 +-
 fs/xfs/libxfs/xfs_alloc.h     |  2 ++
 fs/xfs/libxfs/xfs_btree.c     | 12 ++++++------
 fs/xfs/libxfs/xfs_btree.h     | 13 +++++++++++++
 fs/xfs/libxfs/xfs_dir2_leaf.c |  2 +-
 fs/xfs/libxfs/xfs_dir2_priv.h |  2 ++
 fs/xfs/libxfs/xfs_inode_buf.c |  2 +-
 fs/xfs/libxfs/xfs_inode_buf.h |  3 +++
 fs/xfs/libxfs/xfs_rmap.c      |  3 ++-
 fs/xfs/libxfs/xfs_rmap.h      |  3 +++
 fs/xfs/libxfs/xfs_rtbitmap.c  |  2 +-
 fs/xfs/xfs_itable.c           |  2 +-
 fs/xfs/xfs_itable.h           |  2 ++
 fs/xfs/xfs_rtalloc.h          |  3 +++
 14 files changed, 41 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 7486401ccbd3..fefa8daa1c36 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -606,7 +606,7 @@ const struct xfs_buf_ops xfs_agfl_buf_ops = {
 /*
  * Read in the allocation group free block array.
  */
-STATIC int				/* error */
+int					/* error */
 xfs_alloc_read_agfl(
 	xfs_mount_t	*mp,		/* mount point structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 77d9c27330ab..ef26edc2e938 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -213,6 +213,8 @@ xfs_alloc_get_rec(
 
 int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
+int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp,
+			xfs_agnumber_t agno, struct xfs_buf **bpp);
 int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
 int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno,
 		struct xfs_buf **agbp);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 2aac3f499d97..2f8075aa8725 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -568,7 +568,7 @@ xfs_btree_ptr_offset(
 /*
  * Return a pointer to the n-th record in the btree block.
  */
-STATIC union xfs_btree_rec *
+union xfs_btree_rec *
 xfs_btree_rec_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -581,7 +581,7 @@ xfs_btree_rec_addr(
 /*
  * Return a pointer to the n-th key in the btree block.
  */
-STATIC union xfs_btree_key *
+union xfs_btree_key *
 xfs_btree_key_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -594,7 +594,7 @@ xfs_btree_key_addr(
 /*
  * Return a pointer to the n-th high key in the btree block.
  */
-STATIC union xfs_btree_key *
+union xfs_btree_key *
 xfs_btree_high_key_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -607,7 +607,7 @@ xfs_btree_high_key_addr(
 /*
  * Return a pointer to the n-th block pointer in the btree block.
  */
-STATIC union xfs_btree_ptr *
+union xfs_btree_ptr *
 xfs_btree_ptr_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -641,7 +641,7 @@ xfs_btree_get_iroot(
  * Retrieve the block pointer from the cursor at the given level.
  * This may be an inode btree root or from a buffer.
  */
-STATIC struct xfs_btree_block *		/* generic btree block pointer */
+struct xfs_btree_block *		/* generic btree block pointer */
 xfs_btree_get_block(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	int			level,	/* level in btree */
@@ -1756,7 +1756,7 @@ error0:
 	return error;
 }
 
-STATIC int
+int
 xfs_btree_lookup_get_block(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	int			level,	/* level in the btree */
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 177a364ce5cf..9c95e965cfe5 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -504,4 +504,17 @@ int xfs_btree_visit_blocks(struct xfs_btree_cur *cur,
 
 int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks);
 
+union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+union xfs_btree_key *xfs_btree_key_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+union xfs_btree_key *xfs_btree_high_key_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+union xfs_btree_ptr *xfs_btree_ptr_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+int xfs_btree_lookup_get_block(struct xfs_btree_cur *cur, int level,
+		union xfs_btree_ptr *pp, struct xfs_btree_block **blkp);
+struct xfs_btree_block *xfs_btree_get_block(struct xfs_btree_cur *cur,
+		int level, struct xfs_buf **bpp);
+
 #endif	/* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 68bf3e860a90..7002024a5d0d 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -256,7 +256,7 @@ const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = {
 	.verify_write = xfs_dir3_leafn_write_verify,
 };
 
-static int
+int
 xfs_dir3_leaf_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 011df4da6cc2..576f2d267fa7 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -58,6 +58,8 @@ extern int xfs_dir3_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
 		struct xfs_buf **bpp);
 
 /* xfs_dir2_leaf.c */
+extern int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
+		xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp);
 extern int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp,
 		xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp);
 extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d887af940f09..0c970cf7ab63 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -381,7 +381,7 @@ xfs_log_dinode_to_disk(
 	}
 }
 
-static bool
+bool
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino,
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 0827d7def1ce..a9c97a356c30 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -82,4 +82,7 @@ void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #define	xfs_inobp_check(mp, bp)
 #endif /* DEBUG */
 
+bool	xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
+			  struct xfs_dinode *dip);
+
 #endif	/* __XFS_INODE_BUF_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 1bcb41fe0156..eda275beebe0 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -179,7 +179,8 @@ done:
 	return error;
 }
 
-static int
+/* Convert an internal btree record to an rmap record. */
+int
 xfs_rmap_btrec_to_irec(
 	union xfs_btree_rec	*rec,
 	struct xfs_rmap_irec	*irec)
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 265116d044f4..466ede637080 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -216,5 +216,8 @@ int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		struct xfs_rmap_irec *irec, int	*stat);
 int xfs_rmap_compare(const struct xfs_rmap_irec *a,
 		const struct xfs_rmap_irec *b);
+union xfs_btree_rec;
+int xfs_rmap_btrec_to_irec(union xfs_btree_rec *rec,
+		struct xfs_rmap_irec *irec);
 
 #endif	/* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 26bba7f90fdf..5d4e43ef4eea 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -70,7 +70,7 @@ const struct xfs_buf_ops xfs_rtbuf_ops = {
  * Get a buffer for the bitmap or summary file block specified.
  * The buffer is returned read and locked.
  */
-static int
+int
 xfs_rtbuf_get(
 	xfs_mount_t	*mp,		/* file system mount structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 26d67ce3c18d..c393a2f6d8c3 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -31,7 +31,7 @@
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 
-STATIC int
+int
 xfs_internal_inum(
 	xfs_mount_t	*mp,
 	xfs_ino_t	ino)
diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
index 6ea8b3912fa4..17e86e0541af 100644
--- a/fs/xfs/xfs_itable.h
+++ b/fs/xfs/xfs_itable.h
@@ -96,4 +96,6 @@ xfs_inumbers(
 	void			__user *buffer, /* buffer with inode info */
 	inumbers_fmt_pf		formatter);
 
+int xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
+
 #endif	/* __XFS_ITABLE_H__ */
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index f13133e6f19f..79defa722bf1 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -107,6 +107,8 @@ xfs_growfs_rt(
 /*
  * From xfs_rtbitmap.c
  */
+int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp,
+		  xfs_rtblock_t block, int issum, struct xfs_buf **bpp);
 int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp,
 		      xfs_rtblock_t start, xfs_extlen_t len, int val,
 		      xfs_rtblock_t *new, int *stat);
@@ -143,6 +145,7 @@ int xfs_rtalloc_query_all(struct xfs_trans *tp,
 # define xfs_growfs_rt(mp,in)                           (ENOSYS)
 # define xfs_rtalloc_query_range(t,l,h,f,p)             (ENOSYS)
 # define xfs_rtalloc_query_all(t,f,p)                   (ENOSYS)
+# define xfs_rtbuf_get(m,t,b,i,p)                       (ENOSYS)
 static inline int		/* error */
 xfs_rtmount_init(
 	xfs_mount_t	*mp)	/* file system mount structure */

From 118bb47e281cde728608633f1a358fb9f2ac0adc Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:08 -0700
Subject: [PATCH 18/48] xfs: plumb in needed functions for range querying of
 various btrees

Plumb in the pieces (init_high_key, diff_two_keys) necessary to call
query_range on the inode space and block mapping btrees and to extract
raw btree records.  This will eventually be used by the inobt and bmbt
scrubbers.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_bmap_btree.c   | 22 ++++++++++++++++++++++
 fs/xfs/libxfs/xfs_ialloc_btree.c | 26 ++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index e23495e23620..85de22513014 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -572,6 +572,16 @@ xfs_bmbt_init_key_from_rec(
 		cpu_to_be64(xfs_bmbt_disk_get_startoff(&rec->bmbt));
 }
 
+STATIC void
+xfs_bmbt_init_high_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	key->bmbt.br_startoff = cpu_to_be64(
+			xfs_bmbt_disk_get_startoff(&rec->bmbt) +
+			xfs_bmbt_disk_get_blockcount(&rec->bmbt) - 1);
+}
+
 STATIC void
 xfs_bmbt_init_rec_from_cur(
 	struct xfs_btree_cur	*cur,
@@ -597,6 +607,16 @@ xfs_bmbt_key_diff(
 				      cur->bc_rec.b.br_startoff;
 }
 
+STATIC int64_t
+xfs_bmbt_diff_two_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return (int64_t)be64_to_cpu(k1->bmbt.br_startoff) -
+			  be64_to_cpu(k2->bmbt.br_startoff);
+}
+
 static bool
 xfs_bmbt_verify(
 	struct xfs_buf		*bp)
@@ -720,9 +740,11 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.get_minrecs		= xfs_bmbt_get_minrecs,
 	.get_dmaxrecs		= xfs_bmbt_get_dmaxrecs,
 	.init_key_from_rec	= xfs_bmbt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_bmbt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_bmbt_init_rec_from_cur,
 	.init_ptr_from_cur	= xfs_bmbt_init_ptr_from_cur,
 	.key_diff		= xfs_bmbt_key_diff,
+	.diff_two_keys		= xfs_bmbt_diff_two_keys,
 	.buf_ops		= &xfs_bmbt_buf_ops,
 	.keys_inorder		= xfs_bmbt_keys_inorder,
 	.recs_inorder		= xfs_bmbt_recs_inorder,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 6b1ddeb7e5c1..317caba9faa6 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -174,6 +174,18 @@ xfs_inobt_init_key_from_rec(
 	key->inobt.ir_startino = rec->inobt.ir_startino;
 }
 
+STATIC void
+xfs_inobt_init_high_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	__u32			x;
+
+	x = be32_to_cpu(rec->inobt.ir_startino);
+	x += XFS_INODES_PER_CHUNK - 1;
+	key->inobt.ir_startino = cpu_to_be32(x);
+}
+
 STATIC void
 xfs_inobt_init_rec_from_cur(
 	struct xfs_btree_cur	*cur,
@@ -228,6 +240,16 @@ xfs_inobt_key_diff(
 			  cur->bc_rec.i.ir_startino;
 }
 
+STATIC int64_t
+xfs_inobt_diff_two_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return (int64_t)be32_to_cpu(k1->inobt.ir_startino) -
+			  be32_to_cpu(k2->inobt.ir_startino);
+}
+
 static int
 xfs_inobt_verify(
 	struct xfs_buf		*bp)
@@ -333,10 +355,12 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 	.get_minrecs		= xfs_inobt_get_minrecs,
 	.get_maxrecs		= xfs_inobt_get_maxrecs,
 	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_inobt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
 	.init_ptr_from_cur	= xfs_inobt_init_ptr_from_cur,
 	.key_diff		= xfs_inobt_key_diff,
 	.buf_ops		= &xfs_inobt_buf_ops,
+	.diff_two_keys		= xfs_inobt_diff_two_keys,
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
 };
@@ -352,10 +376,12 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
 	.get_minrecs		= xfs_inobt_get_minrecs,
 	.get_maxrecs		= xfs_inobt_get_maxrecs,
 	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_inobt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
 	.init_ptr_from_cur	= xfs_finobt_init_ptr_from_cur,
 	.key_diff		= xfs_inobt_key_diff,
 	.buf_ops		= &xfs_inobt_buf_ops,
+	.diff_two_keys		= xfs_inobt_diff_two_keys,
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
 };

From e936945ee49693f40217db82a7db55c94e34ce4c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:08 -0700
Subject: [PATCH 19/48] xfs: export _inobt_btrec_to_irec and
 _ialloc_cluster_alignment for scrub

Create a function to extract an in-core inobt record from a generic
btree_rec union so that scrub will be able to check inobt records
and check inode block alignment.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_ialloc.c | 44 +++++++++++++++++++++++---------------
 fs/xfs/libxfs/xfs_ialloc.h |  5 +++++
 2 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 1e5ed940b84d..c514fe98bbab 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -46,7 +46,7 @@
 /*
  * Allocation group level functions.
  */
-static inline int
+int
 xfs_ialloc_cluster_alignment(
 	struct xfs_mount	*mp)
 {
@@ -98,24 +98,15 @@ xfs_inobt_update(
 	return xfs_btree_update(cur, &rec);
 }
 
-/*
- * Get the data from the pointed-to record.
- */
-int					/* error */
-xfs_inobt_get_rec(
-	struct xfs_btree_cur	*cur,	/* btree cursor */
-	xfs_inobt_rec_incore_t	*irec,	/* btree record */
-	int			*stat)	/* output: success/failure */
+/* Convert on-disk btree record to incore inobt record. */
+void
+xfs_inobt_btrec_to_irec(
+	struct xfs_mount		*mp,
+	union xfs_btree_rec		*rec,
+	struct xfs_inobt_rec_incore	*irec)
 {
-	union xfs_btree_rec	*rec;
-	int			error;
-
-	error = xfs_btree_get_rec(cur, &rec, stat);
-	if (error || *stat == 0)
-		return error;
-
 	irec->ir_startino = be32_to_cpu(rec->inobt.ir_startino);
-	if (xfs_sb_version_hassparseinodes(&cur->bc_mp->m_sb)) {
+	if (xfs_sb_version_hassparseinodes(&mp->m_sb)) {
 		irec->ir_holemask = be16_to_cpu(rec->inobt.ir_u.sp.ir_holemask);
 		irec->ir_count = rec->inobt.ir_u.sp.ir_count;
 		irec->ir_freecount = rec->inobt.ir_u.sp.ir_freecount;
@@ -130,6 +121,25 @@ xfs_inobt_get_rec(
 				be32_to_cpu(rec->inobt.ir_u.f.ir_freecount);
 	}
 	irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
+}
+
+/*
+ * Get the data from the pointed-to record.
+ */
+int
+xfs_inobt_get_rec(
+	struct xfs_btree_cur		*cur,
+	struct xfs_inobt_rec_incore	*irec,
+	int				*stat)
+{
+	union xfs_btree_rec		*rec;
+	int				error;
+
+	error = xfs_btree_get_rec(cur, &rec, stat);
+	if (error || *stat == 0)
+		return error;
+
+	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, irec);
 
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 0bb89669fc07..b32cfb5aeb5b 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -168,5 +168,10 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
 int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agnumber_t agno, struct xfs_buf **bpp);
 
+union xfs_btree_rec;
+void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, union xfs_btree_rec *rec,
+		struct xfs_inobt_rec_incore *irec);
+
+int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
 
 #endif	/* __XFS_IALLOC_H__ */

From 378f681c4b588c0432236e5517bf47b7e54ff2dc Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Mon, 19 Jun 2017 08:58:56 -0700
Subject: [PATCH 20/48] xfs: check if an inode is cached and allocated

Check the inode cache for a particular inode number.  If it's in the
cache, check that it's not currently being reclaimed.  If it's not being
reclaimed, return zero if the inode is allocated.  This function will be
used by various scrubbers to decide if the cache is more up to date
than the disk in terms of checking if an inode is allocated.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_icache.c | 52 +++++++++++++++++++++++++++++++++++++++++++--
 fs/xfs/xfs_icache.h |  4 ++++
 2 files changed, 54 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 990210fcb9c3..d78c853265d4 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -368,6 +368,11 @@ xfs_iget_cache_hit(
 	if (ip->i_flags & XFS_IRECLAIMABLE) {
 		trace_xfs_iget_reclaim(ip);
 
+		if (flags & XFS_IGET_INCORE) {
+			error = -EAGAIN;
+			goto out_error;
+		}
+
 		/*
 		 * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
 		 * from stomping over us while we recycle the inode.  We can't
@@ -432,7 +437,8 @@ xfs_iget_cache_hit(
 	if (lock_flags != 0)
 		xfs_ilock(ip, lock_flags);
 
-	xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
+	if (!(flags & XFS_IGET_INCORE))
+		xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
 	XFS_STATS_INC(mp, xs_ig_found);
 
 	return 0;
@@ -603,6 +609,10 @@ again:
 			goto out_error_or_again;
 	} else {
 		rcu_read_unlock();
+		if (flags & XFS_IGET_INCORE) {
+			error = -ENOENT;
+			goto out_error_or_again;
+		}
 		XFS_STATS_INC(mp, xs_ig_missed);
 
 		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
@@ -623,7 +633,7 @@ again:
 	return 0;
 
 out_error_or_again:
-	if (error == -EAGAIN) {
+	if (!(flags & XFS_IGET_INCORE) && error == -EAGAIN) {
 		delay(1);
 		goto again;
 	}
@@ -631,6 +641,44 @@ out_error_or_again:
 	return error;
 }
 
+/*
+ * "Is this a cached inode that's also allocated?"
+ *
+ * Look up an inode by number in the given file system.  If the inode is
+ * in cache and isn't in purgatory, return 1 if the inode is allocated
+ * and 0 if it is not.  For all other cases (not in cache, being torn
+ * down, etc.), return a negative error code.
+ *
+ * The caller has to prevent inode allocation and freeing activity,
+ * presumably by locking the AGI buffer.   This is to ensure that an
+ * inode cannot transition from allocated to freed until the caller is
+ * ready to allow that.  If the inode is in an intermediate state (new,
+ * reclaimable, or being reclaimed), -EAGAIN will be returned; if the
+ * inode is not in the cache, -ENOENT will be returned.  The caller must
+ * deal with these scenarios appropriately.
+ *
+ * This is a specialized use case for the online scrubber; if you're
+ * reading this, you probably want xfs_iget.
+ */
+int
+xfs_icache_inode_is_allocated(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_ino_t		ino,
+	bool			*inuse)
+{
+	struct xfs_inode	*ip;
+	int			error;
+
+	error = xfs_iget(mp, tp, ino, XFS_IGET_INCORE, 0, &ip);
+	if (error)
+		return error;
+
+	*inuse = !!(VFS_I(ip)->i_mode);
+	IRELE(ip);
+	return 0;
+}
+
 /*
  * The inode lookup is done in batches to keep the amount of lock traffic and
  * radix tree lookups to a minimum. The batch size is a trade off between
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 9183f77958ef..bff4d85e5498 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -47,6 +47,7 @@ struct xfs_eofblocks {
 #define XFS_IGET_CREATE		0x1
 #define XFS_IGET_UNTRUSTED	0x2
 #define XFS_IGET_DONTCACHE	0x4
+#define XFS_IGET_INCORE		0x8	/* don't read from disk or reinit */
 
 /*
  * flags for AG inode iterator
@@ -126,4 +127,7 @@ xfs_fs_eofblocks_from_user(
 	return 0;
 }
 
+int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp,
+				  xfs_ino_t ino, bool *inuse);
+
 #endif

From 92ff7285f1df5590d53ab7031f0b86552b59121d Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:10 -0700
Subject: [PATCH 21/48] xfs: reflink find shared should take a transaction

Adapt _reflink_find_shared to take an optional transaction pointer.  The
inode scrubber code will need to decide (within transaction context) if
a file has shared blocks.  To avoid buffer deadlocks, we must pass the
tp through to this function's utility calls.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_bmap_util.c |  4 ++--
 fs/xfs/xfs_reflink.c   | 15 ++++++++-------
 fs/xfs/xfs_reflink.h   |  6 +++---
 3 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 0ea70a44c1a7..863180c41858 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -455,8 +455,8 @@ xfs_getbmap_adjust_shared(
 
 	agno = XFS_FSB_TO_AGNO(mp, map->br_startblock);
 	agbno = XFS_FSB_TO_AGBNO(mp, map->br_startblock);
-	error = xfs_reflink_find_shared(mp, agno, agbno, map->br_blockcount,
-			&ebno, &elen, true);
+	error = xfs_reflink_find_shared(mp, NULL, agno, agbno,
+			map->br_blockcount, &ebno, &elen, true);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index ffe6fe7a7eb5..e25c9953a7c9 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -155,6 +155,7 @@
 int
 xfs_reflink_find_shared(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		agbno,
 	xfs_extlen_t		aglen,
@@ -166,18 +167,18 @@ xfs_reflink_find_shared(
 	struct xfs_btree_cur	*cur;
 	int			error;
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
-	cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
 	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
 			find_end_of_shared);
 
 	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
 
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 	return error;
 }
 
@@ -217,7 +218,7 @@ xfs_reflink_trim_around_shared(
 	agbno = XFS_FSB_TO_AGBNO(ip->i_mount, irec->br_startblock);
 	aglen = irec->br_blockcount;
 
-	error = xfs_reflink_find_shared(ip->i_mount, agno, agbno,
+	error = xfs_reflink_find_shared(ip->i_mount, NULL, agno, agbno,
 			aglen, &fbno, &flen, true);
 	if (error)
 		return error;
@@ -1373,8 +1374,8 @@ xfs_reflink_dirty_extents(
 			agbno = XFS_FSB_TO_AGBNO(mp, map[1].br_startblock);
 			aglen = map[1].br_blockcount;
 
-			error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
-					&rbno, &rlen, true);
+			error = xfs_reflink_find_shared(mp, NULL, agno, agbno,
+					aglen, &rbno, &rlen, true);
 			if (error)
 				goto out;
 			if (rbno == NULLAGBLOCK)
@@ -1445,7 +1446,7 @@ xfs_reflink_clear_inode_flag(
 		agbno = XFS_FSB_TO_AGBNO(mp, map.br_startblock);
 		aglen = map.br_blockcount;
 
-		error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
+		error = xfs_reflink_find_shared(mp, *tpp, agno, agbno, aglen,
 				&rbno, &rlen, false);
 		if (error)
 			return error;
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index d29a7967f029..b8cc5c3e2724 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -20,9 +20,9 @@
 #ifndef __XFS_REFLINK_H
 #define __XFS_REFLINK_H 1
 
-extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
-		xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno,
-		xfs_extlen_t *flen, bool find_maximal);
+extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp,
+		xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen,
+		xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal);
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
 

From ea7cdd7b7baffc40d1e60de7c93e5b1aabb3d081 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:11 -0700
Subject: [PATCH 22/48] xfs: separate function to check if inode shares extents

Separate the "clear reflink flag" function into one function that checks
if the flag is needed, and a second function that checks and clears the
flag.  The inode scrub code will want to check the necessity of the flag
without clearing it.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_reflink.c | 96 ++++++++++++++++++++++++++------------------
 fs/xfs/xfs_reflink.h |  2 +
 2 files changed, 58 insertions(+), 40 deletions(-)

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index e25c9953a7c9..ab2270a87196 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1406,56 +1406,72 @@ out:
 	return error;
 }
 
+/* Does this inode need the reflink flag? */
+int
+xfs_reflink_inode_has_shared_extents(
+	struct xfs_trans		*tp,
+	struct xfs_inode		*ip,
+	bool				*has_shared)
+{
+	struct xfs_bmbt_irec		got;
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_ifork		*ifp;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
+	xfs_extlen_t			aglen;
+	xfs_agblock_t			rbno;
+	xfs_extlen_t			rlen;
+	xfs_extnum_t			idx;
+	bool				found;
+	int				error;
+
+	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
+		if (error)
+			return error;
+	}
+
+	*has_shared = false;
+	found = xfs_iext_lookup_extent(ip, ifp, 0, &idx, &got);
+	while (found) {
+		if (isnullstartblock(got.br_startblock) ||
+		    got.br_state != XFS_EXT_NORM)
+			goto next;
+		agno = XFS_FSB_TO_AGNO(mp, got.br_startblock);
+		agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock);
+		aglen = got.br_blockcount;
+
+		error = xfs_reflink_find_shared(mp, tp, agno, agbno, aglen,
+				&rbno, &rlen, false);
+		if (error)
+			return error;
+		/* Is there still a shared block here? */
+		if (rbno != NULLAGBLOCK) {
+			*has_shared = true;
+			return 0;
+		}
+next:
+		found = xfs_iext_get_extent(ifp, ++idx, &got);
+	}
+
+	return 0;
+}
+
 /* Clear the inode reflink flag if there are no shared extents. */
 int
 xfs_reflink_clear_inode_flag(
 	struct xfs_inode	*ip,
 	struct xfs_trans	**tpp)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		fbno;
-	xfs_filblks_t		end;
-	xfs_agnumber_t		agno;
-	xfs_agblock_t		agbno;
-	xfs_extlen_t		aglen;
-	xfs_agblock_t		rbno;
-	xfs_extlen_t		rlen;
-	struct xfs_bmbt_irec	map;
-	int			nmaps;
+	bool			needs_flag;
 	int			error = 0;
 
 	ASSERT(xfs_is_reflink_inode(ip));
 
-	fbno = 0;
-	end = XFS_B_TO_FSB(mp, i_size_read(VFS_I(ip)));
-	while (end - fbno > 0) {
-		nmaps = 1;
-		/*
-		 * Look for extents in the file.  Skip holes, delalloc, or
-		 * unwritten extents; they can't be reflinked.
-		 */
-		error = xfs_bmapi_read(ip, fbno, end - fbno, &map, &nmaps, 0);
-		if (error)
-			return error;
-		if (nmaps == 0)
-			break;
-		if (!xfs_bmap_is_real_extent(&map))
-			goto next;
-
-		agno = XFS_FSB_TO_AGNO(mp, map.br_startblock);
-		agbno = XFS_FSB_TO_AGBNO(mp, map.br_startblock);
-		aglen = map.br_blockcount;
-
-		error = xfs_reflink_find_shared(mp, *tpp, agno, agbno, aglen,
-				&rbno, &rlen, false);
-		if (error)
-			return error;
-		/* Is there still a shared block here? */
-		if (rbno != NULLAGBLOCK)
-			return 0;
-next:
-		fbno = map.br_startoff + map.br_blockcount;
-	}
+	error = xfs_reflink_inode_has_shared_extents(*tpp, ip, &needs_flag);
+	if (error || needs_flag)
+		return error;
 
 	/*
 	 * We didn't find any shared blocks so turn off the reflink flag.
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index b8cc5c3e2724..701487bab468 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -47,6 +47,8 @@ extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
 extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
 		struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
+extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp,
+		struct xfs_inode *ip, bool *has_shared);
 extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
 		struct xfs_trans **tpp);
 extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,

From d29cb3e45e923715f74d8a08d5c1ea996dce5a59 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:12 -0700
Subject: [PATCH 23/48] xfs: make _bmap_count_blocks consistent wrt delalloc
 extent behavior

There is an inconsistency in the way that _bmap_count_blocks deals with
delalloc reservations -- if the specified fork is in extents format,
*count is set to the total number of blocks referenced by the in-core
fork, including delalloc extents.  However, if the fork is in btree
format, *count is set to the number of blocks referenced by the on-disk
fork, which does /not/ include delalloc extents.

For the lone existing caller of _bmap_count_blocks this hasn't been an
issue because the function is only used to count xattr fork blocks
(where there aren't any delalloc reservations).  However, when scrub
comes along it will use this same function to check di_nblocks against
both on-disk extent maps, so we need this behavior to be consistent.

Therefore, fix _bmap_count_leaves not to include delalloc extents and
remove unnecessary parameters.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_bmap_util.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 863180c41858..424e3bd12700 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -219,20 +219,22 @@ xfs_bmap_eof(
  */
 
 /*
- * Count leaf blocks given a range of extent records.
+ * Count leaf blocks given a range of extent records.  Delayed allocation
+ * extents are not counted towards the totals.
  */
 STATIC void
 xfs_bmap_count_leaves(
-	xfs_ifork_t		*ifp,
-	xfs_extnum_t		idx,
-	int			numrecs,
+	struct xfs_ifork	*ifp,
 	int			*count)
 {
-	int		b;
+	xfs_extnum_t		i;
+	xfs_extnum_t		nr_exts = xfs_iext_count(ifp);
 
-	for (b = 0; b < numrecs; b++) {
-		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b);
-		*count += xfs_bmbt_get_blockcount(frp);
+	for (i = 0; i < nr_exts; i++) {
+		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, i);
+		if (!isnullstartblock(xfs_bmbt_get_startblock(frp))) {
+			*count += xfs_bmbt_get_blockcount(frp);
+		}
 	}
 }
 
@@ -334,7 +336,8 @@ xfs_bmap_count_tree(
 }
 
 /*
- * Count fsblocks of the given fork.
+ * Count fsblocks of the given fork.  Delayed allocation extents are
+ * not counted towards the totals.
  */
 static int					/* error */
 xfs_bmap_count_blocks(
@@ -354,7 +357,7 @@ xfs_bmap_count_blocks(
 	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
-		xfs_bmap_count_leaves(ifp, 0, xfs_iext_count(ifp), count);
+		xfs_bmap_count_leaves(ifp, count);
 		return 0;
 	}
 

From e7f5d5ca36e29fa3c9702f236b0ab73f63336080 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:12 -0700
Subject: [PATCH 24/48] xfs: refactor the ifork block counting function

Refactor the inode fork block counting function to count extents for us
at the same time.  This will be used by the bmbt scrubber function.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_bmap_util.c | 111 +++++++++++++++++++++++++----------------
 fs/xfs/xfs_bmap_util.h |   4 ++
 2 files changed, 71 insertions(+), 44 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 424e3bd12700..93e955262d07 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -225,7 +225,8 @@ xfs_bmap_eof(
 STATIC void
 xfs_bmap_count_leaves(
 	struct xfs_ifork	*ifp,
-	int			*count)
+	xfs_extnum_t		*numrecs,
+	xfs_filblks_t		*count)
 {
 	xfs_extnum_t		i;
 	xfs_extnum_t		nr_exts = xfs_iext_count(ifp);
@@ -233,6 +234,7 @@ xfs_bmap_count_leaves(
 	for (i = 0; i < nr_exts; i++) {
 		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, i);
 		if (!isnullstartblock(xfs_bmbt_get_startblock(frp))) {
+			(*numrecs)++;
 			*count += xfs_bmbt_get_blockcount(frp);
 		}
 	}
@@ -247,7 +249,7 @@ xfs_bmap_disk_count_leaves(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*block,
 	int			numrecs,
-	int			*count)
+	xfs_filblks_t		*count)
 {
 	int		b;
 	xfs_bmbt_rec_t	*frp;
@@ -262,17 +264,18 @@ xfs_bmap_disk_count_leaves(
  * Recursively walks each level of a btree
  * to count total fsblocks in use.
  */
-STATIC int                                     /* error */
+STATIC int
 xfs_bmap_count_tree(
-	xfs_mount_t     *mp,            /* file system mount point */
-	xfs_trans_t     *tp,            /* transaction pointer */
-	xfs_ifork_t	*ifp,		/* inode fork pointer */
-	xfs_fsblock_t   blockno,	/* file system block number */
-	int             levelin,	/* level in btree */
-	int		*count)		/* Count of blocks */
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_ifork	*ifp,
+	xfs_fsblock_t		blockno,
+	int			levelin,
+	xfs_extnum_t		*nextents,
+	xfs_filblks_t		*count)
 {
 	int			error;
-	xfs_buf_t		*bp, *nbp;
+	struct xfs_buf		*bp, *nbp;
 	int			level = levelin;
 	__be64			*pp;
 	xfs_fsblock_t           bno = blockno;
@@ -305,8 +308,9 @@ xfs_bmap_count_tree(
 		/* Dive to the next level */
 		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
-		if (unlikely((error =
-		     xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
+		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level, nextents,
+				count);
+		if (error) {
 			xfs_trans_brelse(tp, bp);
 			XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
 					 XFS_ERRLEVEL_LOW, mp);
@@ -318,6 +322,7 @@ xfs_bmap_count_tree(
 		for (;;) {
 			nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
 			numrecs = be16_to_cpu(block->bb_numrecs);
+			(*nextents) += numrecs;
 			xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
 			xfs_trans_brelse(tp, bp);
 			if (nextbno == NULLFSBLOCK)
@@ -339,44 +344,61 @@ xfs_bmap_count_tree(
  * Count fsblocks of the given fork.  Delayed allocation extents are
  * not counted towards the totals.
  */
-static int					/* error */
+int
 xfs_bmap_count_blocks(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode */
-	int			whichfork,	/* data or attr fork */
-	int			*count)		/* out: count of blocks */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			whichfork,
+	xfs_extnum_t		*nextents,
+	xfs_filblks_t		*count)
 {
-	struct xfs_btree_block	*block;	/* current btree block */
-	xfs_fsblock_t		bno;	/* block # of "block" */
-	xfs_ifork_t		*ifp;	/* fork structure */
-	int			level;	/* btree level, for checking */
-	xfs_mount_t		*mp;	/* file system mount structure */
+	struct xfs_mount	*mp;	/* file system mount structure */
 	__be64			*pp;	/* pointer to block address */
+	struct xfs_btree_block	*block;	/* current btree block */
+	struct xfs_ifork	*ifp;	/* fork structure */
+	xfs_fsblock_t		bno;	/* block # of "block" */
+	int			level;	/* btree level, for checking */
+	int			error;
 
 	bno = NULLFSBLOCK;
 	mp = ip->i_mount;
+	*nextents = 0;
+	*count = 0;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
-		xfs_bmap_count_leaves(ifp, count);
+	if (!ifp)
 		return 0;
-	}
 
-	/*
-	 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
-	 */
-	block = ifp->if_broot;
-	level = be16_to_cpu(block->bb_level);
-	ASSERT(level > 0);
-	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
-	bno = be64_to_cpu(*pp);
-	ASSERT(bno != NULLFSBLOCK);
-	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
-	ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
+	case XFS_DINODE_FMT_EXTENTS:
+		xfs_bmap_count_leaves(ifp, nextents, count);
+		return 0;
+	case XFS_DINODE_FMT_BTREE:
+		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+			error = xfs_iread_extents(tp, ip, whichfork);
+			if (error)
+				return error;
+		}
 
-	if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
-		XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
-				 mp);
-		return -EFSCORRUPTED;
+		/*
+		 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
+		 */
+		block = ifp->if_broot;
+		level = be16_to_cpu(block->bb_level);
+		ASSERT(level > 0);
+		pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
+		bno = be64_to_cpu(*pp);
+		ASSERT(bno != NULLFSBLOCK);
+		ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
+		ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+
+		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level,
+				nextents, count);
+		if (error) {
+			XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)",
+					XFS_ERRLEVEL_LOW, mp);
+			return -EFSCORRUPTED;
+		}
+		return 0;
 	}
 
 	return 0;
@@ -1792,8 +1814,9 @@ xfs_swap_extent_forks(
 	int			*target_log_flags)
 {
 	struct xfs_ifork	tempifp, *ifp, *tifp;
-	int			aforkblks = 0;
-	int			taforkblks = 0;
+	xfs_filblks_t		aforkblks = 0;
+	xfs_filblks_t		taforkblks = 0;
+	xfs_extnum_t		junk;
 	xfs_extnum_t		nextents;
 	uint64_t		tmp;
 	int			error;
@@ -1803,14 +1826,14 @@ xfs_swap_extent_forks(
 	 */
 	if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
 	     (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
-		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK,
+		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk,
 				&aforkblks);
 		if (error)
 			return error;
 	}
 	if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
 	     (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
-		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
+		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk,
 				&taforkblks);
 		if (error)
 			return error;
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 135d8267e284..0cede1043571 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -70,4 +70,8 @@ int	xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
 
 xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
 
+int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
+			  int whichfork, xfs_extnum_t *nextents,
+			  xfs_filblks_t *count);
+
 #endif	/* __XFS_BMAP_UTIL_H__ */

From 8e8877e6edf2b593fe488b6efa8b3b7cfba96738 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:13 -0700
Subject: [PATCH 25/48] xfs: return the hash value of a leaf1 directory block

Modify the existing dir leafn lasthash function to enable us to
calculate the highest hash value of a leaf1 block.  This will be used by
the directory scrubbing code to check the sanity of hashes in leaf1
directory blocks.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_da_btree.c  | 10 +++++-----
 fs/xfs/libxfs/xfs_dir2_node.c | 10 ++++++----
 fs/xfs/libxfs/xfs_dir2_priv.h |  2 +-
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 48f1136b80bf..356f21d5cd35 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -1282,7 +1282,7 @@ xfs_da3_fixhashpath(
 			return;
 		break;
 	case XFS_DIR2_LEAFN_MAGIC:
-		lasthash = xfs_dir2_leafn_lasthash(dp, blk->bp, &count);
+		lasthash = xfs_dir2_leaf_lasthash(dp, blk->bp, &count);
 		if (count == 0)
 			return;
 		break;
@@ -1502,8 +1502,8 @@ xfs_da3_node_lookup_int(
 		if (blk->magic == XFS_DIR2_LEAFN_MAGIC ||
 		    blk->magic == XFS_DIR3_LEAFN_MAGIC) {
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
-			blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
-							       blk->bp, NULL);
+			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
+							      blk->bp, NULL);
 			break;
 		}
 
@@ -1929,8 +1929,8 @@ xfs_da3_path_shift(
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
-			blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
-							       blk->bp, NULL);
+			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
+							      blk->bp, NULL);
 			break;
 		default:
 			ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index bbd1238852b3..682e2bf370c7 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -528,7 +528,7 @@ xfs_dir2_free_hdr_check(
  * Stale entries are ok.
  */
 xfs_dahash_t					/* hash value */
-xfs_dir2_leafn_lasthash(
+xfs_dir2_leaf_lasthash(
 	struct xfs_inode *dp,
 	struct xfs_buf	*bp,			/* leaf buffer */
 	int		*count)			/* count of entries in leaf */
@@ -540,7 +540,9 @@ xfs_dir2_leafn_lasthash(
 	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
-	       leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
+	       leafhdr.magic == XFS_DIR3_LEAFN_MAGIC ||
+	       leafhdr.magic == XFS_DIR2_LEAF1_MAGIC ||
+	       leafhdr.magic == XFS_DIR3_LEAF1_MAGIC);
 
 	if (count)
 		*count = leafhdr.count;
@@ -1405,8 +1407,8 @@ xfs_dir2_leafn_split(
 	/*
 	 * Update last hashval in each block since we added the name.
 	 */
-	oldblk->hashval = xfs_dir2_leafn_lasthash(dp, oldblk->bp, NULL);
-	newblk->hashval = xfs_dir2_leafn_lasthash(dp, newblk->bp, NULL);
+	oldblk->hashval = xfs_dir2_leaf_lasthash(dp, oldblk->bp, NULL);
+	newblk->hashval = xfs_dir2_leaf_lasthash(dp, newblk->bp, NULL);
 	xfs_dir3_leaf_check(dp, oldblk->bp);
 	xfs_dir3_leaf_check(dp, newblk->bp);
 	return error;
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 576f2d267fa7..6d2420974d4f 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -95,7 +95,7 @@ extern bool xfs_dir3_leaf_check_int(struct xfs_mount *mp, struct xfs_inode *dp,
 /* xfs_dir2_node.c */
 extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args,
 		struct xfs_buf *lbp);
-extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_inode *dp,
+extern xfs_dahash_t xfs_dir2_leaf_lasthash(struct xfs_inode *dp,
 		struct xfs_buf *bp, int *count);
 extern int xfs_dir2_leafn_lookup_int(struct xfs_buf *bp,
 		struct xfs_da_args *args, int *indexp,

From acb9553cab552cf17154814f079f54401eefa474 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:14 -0700
Subject: [PATCH 26/48] xfs: pass along transaction context when reading
 directory block buffers

Teach the directory reading functions to pass along a transaction context
if one was supplied.  The directory scrub code will use transactions to
lock buffers and avoid deadlocking with itself in the case of loops.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_dir2_priv.h |  4 ++--
 fs/xfs/xfs_dir2_readdir.c     | 15 +++++++++++----
 fs/xfs/xfs_file.c             |  2 +-
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 6d2420974d4f..4badd26c47e6 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -130,7 +130,7 @@ extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
 extern int xfs_dir2_sf_verify(struct xfs_inode *ip);
 
 /* xfs_dir2_readdir.c */
-extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
-		       size_t bufsize);
+extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp,
+		       struct dir_context *ctx, size_t bufsize);
 
 #endif /* __XFS_DIR2_PRIV_H__ */
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index ede4790753bc..ba2638d37031 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -170,7 +170,7 @@ xfs_dir2_block_getdents(
 		return 0;
 
 	lock_mode = xfs_ilock_data_map_shared(dp);
-	error = xfs_dir3_block_read(NULL, dp, &bp);
+	error = xfs_dir3_block_read(args->trans, dp, &bp);
 	xfs_iunlock(dp, lock_mode);
 	if (error)
 		return error;
@@ -228,7 +228,7 @@ xfs_dir2_block_getdents(
 		if (!dir_emit(ctx, (char *)dep->name, dep->namelen,
 			    be64_to_cpu(dep->inumber),
 			    xfs_dir3_get_dtype(dp->i_mount, filetype))) {
-			xfs_trans_brelse(NULL, bp);
+			xfs_trans_brelse(args->trans, bp);
 			return 0;
 		}
 	}
@@ -239,7 +239,7 @@ xfs_dir2_block_getdents(
 	 */
 	ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) &
 								0x7fffffff;
-	xfs_trans_brelse(NULL, bp);
+	xfs_trans_brelse(args->trans, bp);
 	return 0;
 }
 
@@ -495,15 +495,21 @@ xfs_dir2_leaf_getdents(
 	else
 		ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
 	if (bp)
-		xfs_trans_brelse(NULL, bp);
+		xfs_trans_brelse(args->trans, bp);
 	return error;
 }
 
 /*
  * Read a directory.
+ *
+ * If supplied, the transaction collects locked dir buffers to avoid
+ * nested buffer deadlocks.  This function does not dirty the
+ * transaction.  The caller should ensure that the inode is locked
+ * before calling this function.
  */
 int
 xfs_readdir(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
 	struct dir_context	*ctx,
 	size_t			bufsize)
@@ -522,6 +528,7 @@ xfs_readdir(
 
 	args.dp = dp;
 	args.geo = dp->i_mount->m_dir_geo;
+	args.trans = tp;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
 		rval = xfs_dir2_sf_getdents(&args, ctx);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5fb5a0958a14..36c129303fcf 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -950,7 +950,7 @@ xfs_file_readdir(
 	 */
 	bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size);
 
-	return xfs_readdir(ip, ctx, bufsize);
+	return xfs_readdir(NULL, ip, ctx, bufsize);
 }
 
 /*

From ad017f6537dee30a67b89f937a16e2f6c82e3774 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:14 -0700
Subject: [PATCH 27/48] xfs: pass along transaction context when reading xattr
 block buffers

Teach the extended attribute reading functions to pass along a
transaction context if one was supplied.  The extended attribute scrub
code will use transactions to lock buffers and avoid deadlocking with
itself in the case of loops; since it will already have the inode
locked, also create xattr get/list helpers that don't take locks.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 26 ++++++++++-----
 fs/xfs/libxfs/xfs_attr_remote.c |  5 +--
 fs/xfs/xfs_attr.h               |  3 ++
 fs/xfs/xfs_attr_list.c          | 59 ++++++++++++++++++---------------
 4 files changed, 57 insertions(+), 36 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 6622d46ddec3..ef8a1c75a467 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -114,6 +114,23 @@ xfs_inode_hasattr(
  * Overall external interface routines.
  *========================================================================*/
 
+/* Retrieve an extended attribute and its value.  Must have iolock. */
+int
+xfs_attr_get_ilocked(
+	struct xfs_inode	*ip,
+	struct xfs_da_args	*args)
+{
+	if (!xfs_inode_hasattr(ip))
+		return -ENOATTR;
+	else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
+		return xfs_attr_shortform_getvalue(args);
+	else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
+		return xfs_attr_leaf_get(args);
+	else
+		return xfs_attr_node_get(args);
+}
+
+/* Retrieve an extended attribute by name, and its value. */
 int
 xfs_attr_get(
 	struct xfs_inode	*ip,
@@ -141,14 +158,7 @@ xfs_attr_get(
 	args.op_flags = XFS_DA_OP_OKNOENT;
 
 	lock_mode = xfs_ilock_attr_map_shared(ip);
-	if (!xfs_inode_hasattr(ip))
-		error = -ENOATTR;
-	else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
-		error = xfs_attr_shortform_getvalue(&args);
-	else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
-		error = xfs_attr_leaf_get(&args);
-	else
-		error = xfs_attr_node_get(&args);
+	error = xfs_attr_get_ilocked(ip, &args);
 	xfs_iunlock(ip, lock_mode);
 
 	*valuelenp = args.valuelen;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index da72b16bef8e..5236d8e45146 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -386,7 +386,8 @@ xfs_attr_rmtval_get(
 			       (map[i].br_startblock != HOLESTARTBLOCK));
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
-			error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
+			error = xfs_trans_read_buf(mp, args->trans,
+						   mp->m_ddev_targp,
 						   dblkno, dblkcnt, 0, &bp,
 						   &xfs_attr3_rmt_buf_ops);
 			if (error)
@@ -395,7 +396,7 @@ xfs_attr_rmtval_get(
 			error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
 							&offset, &valuelen,
 							&dst);
-			xfs_buf_relse(bp);
+			xfs_trans_brelse(args->trans, bp);
 			if (error)
 				return error;
 
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index d14691aa02b4..5d5a5e277f35 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -117,6 +117,7 @@ typedef void (*put_listent_func_t)(struct xfs_attr_list_context *, int,
 			      unsigned char *, int, int);
 
 typedef struct xfs_attr_list_context {
+	struct xfs_trans		*tp;
 	struct xfs_inode		*dp;		/* inode */
 	struct attrlist_cursor_kern	*cursor;	/* position in list */
 	char				*alist;		/* output buffer */
@@ -140,8 +141,10 @@ typedef struct xfs_attr_list_context {
  * Overall external interface routines.
  */
 int xfs_attr_inactive(struct xfs_inode *dp);
+int xfs_attr_list_int_ilocked(struct xfs_attr_list_context *);
 int xfs_attr_list_int(struct xfs_attr_list_context *);
 int xfs_inode_hasattr(struct xfs_inode *ip);
+int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args);
 int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
 		 unsigned char *value, int *valuelenp, int flags);
 int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 9bc1e1217989..545eca508d42 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -230,7 +230,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	 */
 	bp = NULL;
 	if (cursor->blkno > 0) {
-		error = xfs_da3_node_read(NULL, dp, cursor->blkno, -1,
+		error = xfs_da3_node_read(context->tp, dp, cursor->blkno, -1,
 					      &bp, XFS_ATTR_FORK);
 		if ((error != 0) && (error != -EFSCORRUPTED))
 			return error;
@@ -242,7 +242,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 			case XFS_DA_NODE_MAGIC:
 			case XFS_DA3_NODE_MAGIC:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				bp = NULL;
 				break;
 			case XFS_ATTR_LEAF_MAGIC:
@@ -254,18 +254,18 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				if (cursor->hashval > be32_to_cpu(
 						entries[leafhdr.count - 1].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_trans_brelse(NULL, bp);
+					xfs_trans_brelse(context->tp, bp);
 					bp = NULL;
 				} else if (cursor->hashval <= be32_to_cpu(
 						entries[0].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_trans_brelse(NULL, bp);
+					xfs_trans_brelse(context->tp, bp);
 					bp = NULL;
 				}
 				break;
 			default:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				bp = NULL;
 			}
 		}
@@ -281,7 +281,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 		for (;;) {
 			uint16_t magic;
 
-			error = xfs_da3_node_read(NULL, dp,
+			error = xfs_da3_node_read(context->tp, dp,
 						      cursor->blkno, -1, &bp,
 						      XFS_ATTR_FORK);
 			if (error)
@@ -297,7 +297,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						     XFS_ERRLEVEL_LOW,
 						     context->dp->i_mount,
 						     node);
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				return -EFSCORRUPTED;
 			}
 
@@ -313,10 +313,10 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				}
 			}
 			if (i == nodehdr.count) {
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				return 0;
 			}
-			xfs_trans_brelse(NULL, bp);
+			xfs_trans_brelse(context->tp, bp);
 		}
 	}
 	ASSERT(bp != NULL);
@@ -333,12 +333,12 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 		if (context->seen_enough || leafhdr.forw == 0)
 			break;
 		cursor->blkno = leafhdr.forw;
-		xfs_trans_brelse(NULL, bp);
-		error = xfs_attr3_leaf_read(NULL, dp, cursor->blkno, -1, &bp);
+		xfs_trans_brelse(context->tp, bp);
+		error = xfs_attr3_leaf_read(context->tp, dp, cursor->blkno, -1, &bp);
 		if (error)
 			return error;
 	}
-	xfs_trans_brelse(NULL, bp);
+	xfs_trans_brelse(context->tp, bp);
 	return 0;
 }
 
@@ -448,15 +448,33 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context)
 	trace_xfs_attr_leaf_list(context);
 
 	context->cursor->blkno = 0;
-	error = xfs_attr3_leaf_read(NULL, context->dp, 0, -1, &bp);
+	error = xfs_attr3_leaf_read(context->tp, context->dp, 0, -1, &bp);
 	if (error)
 		return error;
 
 	xfs_attr3_leaf_list_int(bp, context);
-	xfs_trans_brelse(NULL, bp);
+	xfs_trans_brelse(context->tp, bp);
 	return 0;
 }
 
+int
+xfs_attr_list_int_ilocked(
+	struct xfs_attr_list_context	*context)
+{
+	struct xfs_inode		*dp = context->dp;
+
+	/*
+	 * Decide on what work routines to call based on the inode size.
+	 */
+	if (!xfs_inode_hasattr(dp))
+		return 0;
+	else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
+		return xfs_attr_shortform_list(context);
+	else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+		return xfs_attr_leaf_list(context);
+	return xfs_attr_node_list(context);
+}
+
 int
 xfs_attr_list_int(
 	xfs_attr_list_context_t *context)
@@ -470,19 +488,8 @@ xfs_attr_list_int(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	/*
-	 * Decide on what work routines to call based on the inode size.
-	 */
 	lock_mode = xfs_ilock_attr_map_shared(dp);
-	if (!xfs_inode_hasattr(dp)) {
-		error = 0;
-	} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-		error = xfs_attr_shortform_list(context);
-	} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
-		error = xfs_attr_leaf_list(context);
-	} else {
-		error = xfs_attr_node_list(context);
-	}
+	error = xfs_attr_list_int_ilocked(context);
 	xfs_iunlock(dp, lock_mode);
 	return error;
 }

From 5da8f2f8908aabcfa4113d37d470039c79962ba9 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 16 Jun 2017 11:00:15 -0700
Subject: [PATCH 28/48] xfs: allow reading of already-locked remote symbolic
 link

Expose the readlink variant that doesn't take the inode lock so that
the scrubber can inspect symlink contents.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/xfs_symlink.c | 6 +++---
 fs/xfs/xfs_symlink.h | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index f2cb45ed1d54..493804857d67 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -43,8 +43,8 @@
 #include "xfs_log.h"
 
 /* ----- Kernel only functions below ----- */
-STATIC int
-xfs_readlink_bmap(
+int
+xfs_readlink_bmap_ilocked(
 	struct xfs_inode	*ip,
 	char			*link)
 {
@@ -153,7 +153,7 @@ xfs_readlink(
 	}
 
 
-	error = xfs_readlink_bmap(ip, link);
+	error = xfs_readlink_bmap_ilocked(ip, link);
 
  out:
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_symlink.h b/fs/xfs/xfs_symlink.h
index e75245d09116..aeaee8923617 100644
--- a/fs/xfs/xfs_symlink.h
+++ b/fs/xfs/xfs_symlink.h
@@ -21,6 +21,7 @@
 
 int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
 		const char *target_path, umode_t mode, struct xfs_inode **ipp);
+int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link);
 int xfs_readlink(struct xfs_inode *ip, char *link);
 int xfs_inactive_symlink(struct xfs_inode *ip);
 

From 61d819e7bcb7f33da710bf3f5dcb2bcf1e48203c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Mon, 19 Jun 2017 13:19:08 -0700
Subject: [PATCH 29/48] xfs: don't allow bmap on rt files

bmap returns a dumb LBA address but not the block device that goes with
that LBA.  Swapfiles don't care about this and will blindly assume that
the data volume is the correct blockdev, which is totally bogus for
files on the rt subvolume.  This results in the swap code doing IOs to
arbitrary locations on the data device(!) if the passed in mapping is a
realtime file, so just turn off bmap for rt files.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_aops.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 6bab8c449b81..716b5eeeed94 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1316,9 +1316,12 @@ xfs_vm_bmap(
 	 * The swap code (ab-)uses ->bmap to get a block mapping and then
 	 * bypasseѕ the file system for actual I/O.  We really can't allow
 	 * that on reflinks inodes, so we have to skip out here.  And yes,
-	 * 0 is the magic code for a bmap error..
+	 * 0 is the magic code for a bmap error.
+	 *
+	 * Since we don't pass back blockdev info, we can't return bmap
+	 * information for rt files either.
 	 */
-	if (xfs_is_reflink_inode(ip))
+	if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip))
 		return 0;
 
 	filemap_write_and_wait(mapping);

From 39775431f82f890f4aaa08860a30883d081bffc7 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Sat, 24 Jun 2017 10:11:41 -0700
Subject: [PATCH 30/48] xfs: free uncommitted transactions during log recovery

Log recovery allocates in-core transaction and member item data
structures on-demand as it processes the on-disk log. Transactions
are allocated on first encounter on-disk and stored in a hash table
structure where they are easily accessible for subsequent lookups.
Transaction items are also allocated on demand and are attached to
the associated transactions.

When a commit record is encountered in the log, the transaction is
committed to the fs and the in-core structures are freed. If a
filesystem crashes or shuts down before all in-core log buffers are
flushed to the log, however, not all transactions may have commit
records in the log. As expected, the modifications in such an
incomplete transaction are not replayed to the fs. The in-core data
structures for the partial transaction are never freed, however,
resulting in a memory leak.

Update xlog_do_recovery_pass() to first correctly initialize the
hash table array so empty lists can be distinguished from populated
lists on function exit. Update xlog_recover_free_trans() to always
remove the transaction from the list prior to freeing the associated
memory. Finally, walk the hash table of transaction lists as the
last step before it goes out of scope and free any transactions that
may remain on the lists. This prevents a memory leak of partial
transactions in the log.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log_recover.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index e19b20c87f35..b6a40bd50099 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4152,7 +4152,7 @@ xlog_recover_commit_trans(
 
 	#define XLOG_RECOVER_COMMIT_QUEUE_MAX 100
 
-	hlist_del(&trans->r_list);
+	hlist_del_init(&trans->r_list);
 
 	error = xlog_recover_reorder_trans(log, trans, pass);
 	if (error)
@@ -4354,6 +4354,8 @@ xlog_recover_free_trans(
 	xlog_recover_item_t	*item, *n;
 	int			i;
 
+	hlist_del_init(&trans->r_list);
+
 	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
 		/* Free the regions in the item. */
 		list_del(&item->ri_list);
@@ -5224,12 +5226,16 @@ xlog_do_recovery_pass(
 	int			error2 = 0;
 	int			bblks, split_bblks;
 	int			hblks, split_hblks, wrapped_hblks;
+	int			i;
 	struct hlist_head	rhash[XLOG_RHASH_SIZE];
 	LIST_HEAD		(buffer_list);
 
 	ASSERT(head_blk != tail_blk);
 	rhead_blk = 0;
 
+	for (i = 0; i < XLOG_RHASH_SIZE; i++)
+		INIT_HLIST_HEAD(&rhash[i]);
+
 	/*
 	 * Read the header of the tail block and get the iclog buffer size from
 	 * h_size.  Use this to tell how many sectors make up the log header.
@@ -5466,6 +5472,19 @@ xlog_do_recovery_pass(
 	if (error && first_bad)
 		*first_bad = rhead_blk;
 
+	/*
+	 * Transactions are freed at commit time but transactions without commit
+	 * records on disk are never committed. Free any that may be left in the
+	 * hash table.
+	 */
+	for (i = 0; i < XLOG_RHASH_SIZE; i++) {
+		struct hlist_node	*tmp;
+		struct xlog_recover	*trans;
+
+		hlist_for_each_entry_safe(trans, tmp, &rhash[i], r_list)
+			xlog_recover_free_trans(trans);
+	}
+
 	return error ? error : error2;
 }
 

From 31965ef34802f49903bba06dd7c3b96a2e2ed4e4 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 20 Jun 2017 17:54:46 -0700
Subject: [PATCH 31/48] xfs: make errortag a per-mountpoint structure

Remove the xfs_etest structure in favor of a per-mountpoint structure.
This will give us the flexibility to set as many error injection points
as we want, and later enable us to set up sysfs knobs to set the trigger
frequency as we wish.  This comes at a cost of higher memory use, but
unti we hit 1024 injection points (we're at 29) or a lot of mounts this
shouldn't be a huge issue.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_error.c | 156 +++++++++++++++++++++++----------------------
 fs/xfs/xfs_error.h |  25 ++++----
 fs/xfs/xfs_ioctl.c |   4 +-
 fs/xfs/xfs_mount.c |  10 ++-
 fs/xfs/xfs_mount.h |   7 ++
 5 files changed, 112 insertions(+), 90 deletions(-)

diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index ed7ee4e8af73..52f75bc1abac 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -25,100 +25,106 @@
 
 #ifdef DEBUG
 
-int	xfs_etest[XFS_NUM_INJECT_ERROR];
-int64_t	xfs_etest_fsid[XFS_NUM_INJECT_ERROR];
-char *	xfs_etest_fsname[XFS_NUM_INJECT_ERROR];
-int	xfs_error_test_active;
+static unsigned int xfs_errortag_random_default[] = {
+	XFS_RANDOM_DEFAULT,
+	XFS_RANDOM_IFLUSH_1,
+	XFS_RANDOM_IFLUSH_2,
+	XFS_RANDOM_IFLUSH_3,
+	XFS_RANDOM_IFLUSH_4,
+	XFS_RANDOM_IFLUSH_5,
+	XFS_RANDOM_IFLUSH_6,
+	XFS_RANDOM_DA_READ_BUF,
+	XFS_RANDOM_BTREE_CHECK_LBLOCK,
+	XFS_RANDOM_BTREE_CHECK_SBLOCK,
+	XFS_RANDOM_ALLOC_READ_AGF,
+	XFS_RANDOM_IALLOC_READ_AGI,
+	XFS_RANDOM_ITOBP_INOTOBP,
+	XFS_RANDOM_IUNLINK,
+	XFS_RANDOM_IUNLINK_REMOVE,
+	XFS_RANDOM_DIR_INO_VALIDATE,
+	XFS_RANDOM_BULKSTAT_READ_CHUNK,
+	XFS_RANDOM_IODONE_IOERR,
+	XFS_RANDOM_STRATREAD_IOERR,
+	XFS_RANDOM_STRATCMPL_IOERR,
+	XFS_RANDOM_DIOWRITE_IOERR,
+	XFS_RANDOM_BMAPIFORMAT,
+	XFS_RANDOM_FREE_EXTENT,
+	XFS_RANDOM_RMAP_FINISH_ONE,
+	XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE,
+	XFS_RANDOM_REFCOUNT_FINISH_ONE,
+	XFS_RANDOM_BMAP_FINISH_ONE,
+	XFS_RANDOM_AG_RESV_CRITICAL,
+};
 
 int
-xfs_error_test(int error_tag, int *fsidp, char *expression,
-	       int line, char *file, unsigned long randfactor)
+xfs_errortag_init(
+	struct xfs_mount	*mp)
 {
-	int i;
-	int64_t fsid;
+	mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX,
+			KM_SLEEP | KM_MAYFAIL);
+	if (!mp->m_errortag)
+		return -ENOMEM;
+	return 0;
+}
 
-	if (prandom_u32() % randfactor)
-		return 0;
+void
+xfs_errortag_del(
+	struct xfs_mount	*mp)
+{
+	kmem_free(mp->m_errortag);
+}
 
-	memcpy(&fsid, fsidp, sizeof(xfs_fsid_t));
+bool
+xfs_errortag_test(
+	struct xfs_mount	*mp,
+	const char		*expression,
+	const char		*file,
+	int			line,
+	unsigned int		error_tag)
+{
+	unsigned int		randfactor;
 
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
-		if (xfs_etest[i] == error_tag && xfs_etest_fsid[i] == fsid) {
-			xfs_warn(NULL,
-	"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
-				expression, file, line, xfs_etest_fsname[i]);
-			return 1;
-		}
-	}
+	ASSERT(error_tag < XFS_ERRTAG_MAX);
+	randfactor = mp->m_errortag[error_tag];
+	if (!randfactor || prandom_u32() % randfactor)
+		return false;
 
+	xfs_warn_ratelimited(mp,
+"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
+			expression, file, line, mp->m_fsname);
+	return true;
+}
+
+int
+xfs_errortag_set(
+	struct xfs_mount	*mp,
+	unsigned int		error_tag,
+	unsigned int		tag_value)
+{
+	if (error_tag >= XFS_ERRTAG_MAX)
+		return -EINVAL;
+
+	mp->m_errortag[error_tag] = tag_value;
 	return 0;
 }
 
 int
-xfs_errortag_add(unsigned int error_tag, xfs_mount_t *mp)
+xfs_errortag_add(
+	struct xfs_mount	*mp,
+	unsigned int		error_tag)
 {
-	int i;
-	int len;
-	int64_t fsid;
-
 	if (error_tag >= XFS_ERRTAG_MAX)
 		return -EINVAL;
 
-	memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
-
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
-		if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) {
-			xfs_warn(mp, "error tag #%d on", error_tag);
-			return 0;
-		}
-	}
-
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
-		if (xfs_etest[i] == 0) {
-			xfs_warn(mp, "Turned on XFS error tag #%d",
-				error_tag);
-			xfs_etest[i] = error_tag;
-			xfs_etest_fsid[i] = fsid;
-			len = strlen(mp->m_fsname);
-			xfs_etest_fsname[i] = kmem_alloc(len + 1, KM_SLEEP);
-			strcpy(xfs_etest_fsname[i], mp->m_fsname);
-			xfs_error_test_active++;
-			return 0;
-		}
-	}
-
-	xfs_warn(mp, "error tag overflow, too many turned on");
-
-	return 1;
+	return xfs_errortag_set(mp, error_tag,
+			xfs_errortag_random_default[error_tag]);
 }
 
 int
-xfs_errortag_clearall(xfs_mount_t *mp, int loud)
+xfs_errortag_clearall(
+	struct xfs_mount	*mp)
 {
-	int64_t fsid;
-	int cleared = 0;
-	int i;
-
-	memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
-
-
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
-		if ((fsid == 0LL || xfs_etest_fsid[i] == fsid) &&
-		     xfs_etest[i] != 0) {
-			cleared = 1;
-			xfs_warn(mp, "Clearing XFS error tag #%d",
-				xfs_etest[i]);
-			xfs_etest[i] = 0;
-			xfs_etest_fsid[i] = 0LL;
-			kmem_free(xfs_etest_fsname[i]);
-			xfs_etest_fsname[i] = NULL;
-			xfs_error_test_active--;
-		}
-	}
-
-	if (loud || cleared)
-		xfs_warn(mp, "Cleared all XFS error tags for filesystem");
-
+	memset(mp->m_errortag, 0, sizeof(unsigned int) * XFS_ERRTAG_MAX);
 	return 0;
 }
 #endif /* DEBUG */
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 05f8666733a0..b4316d39e1ca 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -131,21 +131,24 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
 #define XFS_RANDOM_AG_RESV_CRITICAL			4
 
 #ifdef DEBUG
-extern int xfs_error_test_active;
-extern int xfs_error_test(int, int *, char *, int, char *, unsigned long);
-
-#define	XFS_NUM_INJECT_ERROR				10
+extern int xfs_errortag_init(struct xfs_mount *mp);
+extern void xfs_errortag_del(struct xfs_mount *mp);
+extern bool xfs_errortag_test(struct xfs_mount *mp, const char *expression,
+		const char *file, int line, unsigned int error_tag);
 #define XFS_TEST_ERROR(expr, mp, tag, rf)		\
-	((expr) || (xfs_error_test_active && \
-	 xfs_error_test((tag), (mp)->m_fixedfsid, "expr", __LINE__, __FILE__, \
-			(rf))))
+	((expr) || xfs_errortag_test((mp), #expr, __FILE__, __LINE__, (tag)))
 
-extern int xfs_errortag_add(unsigned int error_tag, struct xfs_mount *mp);
-extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud);
+extern int xfs_errortag_set(struct xfs_mount *mp, unsigned int error_tag,
+		unsigned int tag_value);
+extern int xfs_errortag_add(struct xfs_mount *mp, unsigned int error_tag);
+extern int xfs_errortag_clearall(struct xfs_mount *mp);
 #else
+#define xfs_errortag_init(mp)			(0)
+#define xfs_errortag_del(mp)
 #define XFS_TEST_ERROR(expr, mp, tag, rf)	(expr)
-#define xfs_errortag_add(tag, mp)		(ENOSYS)
-#define xfs_errortag_clearall(mp, loud)		(ENOSYS)
+#define xfs_errortag_set(mp, tag, val)		(ENOSYS)
+#define xfs_errortag_add(mp, tag)		(ENOSYS)
+#define xfs_errortag_clearall(mp)		(ENOSYS)
 #endif /* DEBUG */
 
 /*
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 8ffe4eac0b48..9c0c7a920304 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -2037,14 +2037,14 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -EFAULT;
 
-		return xfs_errortag_add(in.errtag, mp);
+		return xfs_errortag_add(mp, in.errtag);
 	}
 
 	case XFS_IOC_ERROR_CLEARALL:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		return xfs_errortag_clearall(mp, 1);
+		return xfs_errortag_clearall(mp);
 
 	case XFS_IOC_FREE_EOFBLOCKS: {
 		struct xfs_fs_eofblocks eofb;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index cc6789d35232..1a98c35e1ccf 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -720,10 +720,13 @@ xfs_mountfs(
 	if (error)
 		goto out_del_stats;
 
+	error = xfs_errortag_init(mp);
+	if (error)
+		goto out_remove_error_sysfs;
 
 	error = xfs_uuid_mount(mp);
 	if (error)
-		goto out_remove_error_sysfs;
+		goto out_remove_errortag;
 
 	/*
 	 * Set the minimum read and write sizes
@@ -1042,6 +1045,8 @@ xfs_mountfs(
 	xfs_da_unmount(mp);
  out_remove_uuid:
 	xfs_uuid_unmount(mp);
+ out_remove_errortag:
+	xfs_errortag_del(mp);
  out_remove_error_sysfs:
 	xfs_error_sysfs_del(mp);
  out_del_stats:
@@ -1145,10 +1150,11 @@ xfs_unmountfs(
 	xfs_uuid_unmount(mp);
 
 #if defined(DEBUG)
-	xfs_errortag_clearall(mp, 0);
+	xfs_errortag_clearall(mp);
 #endif
 	xfs_free_perag(mp);
 
+	xfs_errortag_del(mp);
 	xfs_error_sysfs_del(mp);
 	xfs_sysfs_del(&mp->m_stats.xs_kobj);
 	xfs_sysfs_del(&mp->m_kobj);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 305d95394e2d..e002ac52a4e6 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -198,6 +198,13 @@ typedef struct xfs_mount {
 
 	bool			m_fail_unmount;
 #ifdef DEBUG
+	/*
+	 * Frequency with which errors are injected.  Replaces xfs_etest; the
+	 * value stored in here is the inverse of the frequency with which the
+	 * error triggers.  1 = always, 2 = half the time, etc.
+	 */
+	unsigned int		*m_errortag;
+
 	/*
 	 * DEBUG mode instrumentation to test and/or trigger delayed allocation
 	 * block killing in the event of failed writes. When enabled, all

From c684010115221978b17968dbddc8e31a09da85e7 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 20 Jun 2017 17:54:47 -0700
Subject: [PATCH 32/48] xfs: expose errortag knobs via sysfs

Creates a /sys/fs/xfs/$dev/errortag/ directory to control the errortag
values directly.  This enables us to control the randomness values,
rather than having to accept the defaults.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_error.c | 156 ++++++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/xfs_error.h |   1 +
 fs/xfs/xfs_mount.h |   1 +
 3 files changed, 157 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 52f75bc1abac..e2278af6aed1 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -22,6 +22,7 @@
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_error.h"
+#include "xfs_sysfs.h"
 
 #ifdef DEBUG
 
@@ -56,6 +57,145 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_AG_RESV_CRITICAL,
 };
 
+struct xfs_errortag_attr {
+	struct attribute	attr;
+	unsigned int		tag;
+};
+
+static inline struct xfs_errortag_attr *
+to_attr(struct attribute *attr)
+{
+	return container_of(attr, struct xfs_errortag_attr, attr);
+}
+
+static inline struct xfs_mount *
+to_mp(struct kobject *kobject)
+{
+	struct xfs_kobj *kobj = to_kobj(kobject);
+
+	return container_of(kobj, struct xfs_mount, m_errortag_kobj);
+}
+
+STATIC ssize_t
+xfs_errortag_attr_store(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+	struct xfs_errortag_attr *xfs_attr = to_attr(attr);
+	int			ret;
+	unsigned int		val;
+
+	if (strcmp(buf, "default") == 0) {
+		val = xfs_errortag_random_default[xfs_attr->tag];
+	} else {
+		ret = kstrtouint(buf, 0, &val);
+		if (ret)
+			return ret;
+	}
+
+	ret = xfs_errortag_set(mp, xfs_attr->tag, val);
+	if (ret)
+		return ret;
+	return count;
+}
+
+STATIC ssize_t
+xfs_errortag_attr_show(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	char			*buf)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+	struct xfs_errortag_attr *xfs_attr = to_attr(attr);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+			xfs_errortag_get(mp, xfs_attr->tag));
+}
+
+static const struct sysfs_ops xfs_errortag_sysfs_ops = {
+	.show = xfs_errortag_attr_show,
+	.store = xfs_errortag_attr_store,
+};
+
+#define XFS_ERRORTAG_ATTR_RW(_name, _tag) \
+static struct xfs_errortag_attr xfs_errortag_attr_##_name = {		\
+	.attr = {.name = __stringify(_name),				\
+		 .mode = VERIFY_OCTAL_PERMISSIONS(S_IWUSR | S_IRUGO) },	\
+	.tag	= (_tag),						\
+}
+
+#define XFS_ERRORTAG_ATTR_LIST(_name) &xfs_errortag_attr_##_name.attr
+
+XFS_ERRORTAG_ATTR_RW(noerror,		XFS_ERRTAG_NOERROR);
+XFS_ERRORTAG_ATTR_RW(iflush1,		XFS_ERRTAG_IFLUSH_1);
+XFS_ERRORTAG_ATTR_RW(iflush2,		XFS_ERRTAG_IFLUSH_2);
+XFS_ERRORTAG_ATTR_RW(iflush3,		XFS_ERRTAG_IFLUSH_3);
+XFS_ERRORTAG_ATTR_RW(iflush4,		XFS_ERRTAG_IFLUSH_4);
+XFS_ERRORTAG_ATTR_RW(iflush5,		XFS_ERRTAG_IFLUSH_5);
+XFS_ERRORTAG_ATTR_RW(iflush6,		XFS_ERRTAG_IFLUSH_6);
+XFS_ERRORTAG_ATTR_RW(dareadbuf,		XFS_ERRTAG_DA_READ_BUF);
+XFS_ERRORTAG_ATTR_RW(btree_chk_lblk,	XFS_ERRTAG_BTREE_CHECK_LBLOCK);
+XFS_ERRORTAG_ATTR_RW(btree_chk_sblk,	XFS_ERRTAG_BTREE_CHECK_SBLOCK);
+XFS_ERRORTAG_ATTR_RW(readagf,		XFS_ERRTAG_ALLOC_READ_AGF);
+XFS_ERRORTAG_ATTR_RW(readagi,		XFS_ERRTAG_IALLOC_READ_AGI);
+XFS_ERRORTAG_ATTR_RW(itobp,		XFS_ERRTAG_ITOBP_INOTOBP);
+XFS_ERRORTAG_ATTR_RW(iunlink,		XFS_ERRTAG_IUNLINK);
+XFS_ERRORTAG_ATTR_RW(iunlinkrm,		XFS_ERRTAG_IUNLINK_REMOVE);
+XFS_ERRORTAG_ATTR_RW(dirinovalid,	XFS_ERRTAG_DIR_INO_VALIDATE);
+XFS_ERRORTAG_ATTR_RW(bulkstat,		XFS_ERRTAG_BULKSTAT_READ_CHUNK);
+XFS_ERRORTAG_ATTR_RW(logiodone,		XFS_ERRTAG_IODONE_IOERR);
+XFS_ERRORTAG_ATTR_RW(stratread,		XFS_ERRTAG_STRATREAD_IOERR);
+XFS_ERRORTAG_ATTR_RW(stratcmpl,		XFS_ERRTAG_STRATCMPL_IOERR);
+XFS_ERRORTAG_ATTR_RW(diowrite,		XFS_ERRTAG_DIOWRITE_IOERR);
+XFS_ERRORTAG_ATTR_RW(bmapifmt,		XFS_ERRTAG_BMAPIFORMAT);
+XFS_ERRORTAG_ATTR_RW(free_extent,	XFS_ERRTAG_FREE_EXTENT);
+XFS_ERRORTAG_ATTR_RW(rmap_finish_one,	XFS_ERRTAG_RMAP_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(refcount_continue_update,	XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE);
+XFS_ERRORTAG_ATTR_RW(refcount_finish_one,	XFS_ERRTAG_REFCOUNT_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(bmap_finish_one,	XFS_ERRTAG_BMAP_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(ag_resv_critical,	XFS_ERRTAG_AG_RESV_CRITICAL);
+
+static struct attribute *xfs_errortag_attrs[] = {
+	XFS_ERRORTAG_ATTR_LIST(noerror),
+	XFS_ERRORTAG_ATTR_LIST(iflush1),
+	XFS_ERRORTAG_ATTR_LIST(iflush2),
+	XFS_ERRORTAG_ATTR_LIST(iflush3),
+	XFS_ERRORTAG_ATTR_LIST(iflush4),
+	XFS_ERRORTAG_ATTR_LIST(iflush5),
+	XFS_ERRORTAG_ATTR_LIST(iflush6),
+	XFS_ERRORTAG_ATTR_LIST(dareadbuf),
+	XFS_ERRORTAG_ATTR_LIST(btree_chk_lblk),
+	XFS_ERRORTAG_ATTR_LIST(btree_chk_sblk),
+	XFS_ERRORTAG_ATTR_LIST(readagf),
+	XFS_ERRORTAG_ATTR_LIST(readagi),
+	XFS_ERRORTAG_ATTR_LIST(itobp),
+	XFS_ERRORTAG_ATTR_LIST(iunlink),
+	XFS_ERRORTAG_ATTR_LIST(iunlinkrm),
+	XFS_ERRORTAG_ATTR_LIST(dirinovalid),
+	XFS_ERRORTAG_ATTR_LIST(bulkstat),
+	XFS_ERRORTAG_ATTR_LIST(logiodone),
+	XFS_ERRORTAG_ATTR_LIST(stratread),
+	XFS_ERRORTAG_ATTR_LIST(stratcmpl),
+	XFS_ERRORTAG_ATTR_LIST(diowrite),
+	XFS_ERRORTAG_ATTR_LIST(bmapifmt),
+	XFS_ERRORTAG_ATTR_LIST(free_extent),
+	XFS_ERRORTAG_ATTR_LIST(rmap_finish_one),
+	XFS_ERRORTAG_ATTR_LIST(refcount_continue_update),
+	XFS_ERRORTAG_ATTR_LIST(refcount_finish_one),
+	XFS_ERRORTAG_ATTR_LIST(bmap_finish_one),
+	XFS_ERRORTAG_ATTR_LIST(ag_resv_critical),
+	NULL,
+};
+
+struct kobj_type xfs_errortag_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_errortag_sysfs_ops,
+	.default_attrs = xfs_errortag_attrs,
+};
+
 int
 xfs_errortag_init(
 	struct xfs_mount	*mp)
@@ -64,13 +204,16 @@ xfs_errortag_init(
 			KM_SLEEP | KM_MAYFAIL);
 	if (!mp->m_errortag)
 		return -ENOMEM;
-	return 0;
+
+	return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype,
+			       &mp->m_kobj, "errortag");
 }
 
 void
 xfs_errortag_del(
 	struct xfs_mount	*mp)
 {
+	xfs_sysfs_del(&mp->m_errortag_kobj);
 	kmem_free(mp->m_errortag);
 }
 
@@ -95,6 +238,17 @@ xfs_errortag_test(
 	return true;
 }
 
+int
+xfs_errortag_get(
+	struct xfs_mount	*mp,
+	unsigned int		error_tag)
+{
+	if (error_tag >= XFS_ERRTAG_MAX)
+		return -EINVAL;
+
+	return mp->m_errortag[error_tag];
+}
+
 int
 xfs_errortag_set(
 	struct xfs_mount	*mp,
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index b4316d39e1ca..8915bdeb6128 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -138,6 +138,7 @@ extern bool xfs_errortag_test(struct xfs_mount *mp, const char *expression,
 #define XFS_TEST_ERROR(expr, mp, tag, rf)		\
 	((expr) || xfs_errortag_test((mp), #expr, __FILE__, __LINE__, (tag)))
 
+extern int xfs_errortag_get(struct xfs_mount *mp, unsigned int error_tag);
 extern int xfs_errortag_set(struct xfs_mount *mp, unsigned int error_tag,
 		unsigned int tag_value);
 extern int xfs_errortag_add(struct xfs_mount *mp, unsigned int error_tag);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index e002ac52a4e6..931e9fc21a1c 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -204,6 +204,7 @@ typedef struct xfs_mount {
 	 * error triggers.  1 = always, 2 = half the time, etc.
 	 */
 	unsigned int		*m_errortag;
+	struct xfs_kobj		m_errortag_kobj;
 
 	/*
 	 * DEBUG mode instrumentation to test and/or trigger delayed allocation

From 9e24cfd044853e0e46e7149b91b7bb09effb0a79 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 20 Jun 2017 17:54:47 -0700
Subject: [PATCH 33/48] xfs: remove unneeded parameter from XFS_TEST_ERROR

Since we moved the injected error frequency controls to the mountpoint,
we can get rid of the last argument to XFS_TEST_ERROR.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/libxfs/xfs_ag_resv.c   |  3 +--
 fs/xfs/libxfs/xfs_alloc.c     |  6 ++----
 fs/xfs/libxfs/xfs_bmap.c      | 13 ++++++-------
 fs/xfs/libxfs/xfs_btree.c     |  6 ++----
 fs/xfs/libxfs/xfs_dir2.c      |  3 +--
 fs/xfs/libxfs/xfs_ialloc.c    |  3 +--
 fs/xfs/libxfs/xfs_inode_buf.c |  3 +--
 fs/xfs/libxfs/xfs_refcount.c  |  6 ++----
 fs/xfs/libxfs/xfs_rmap.c      |  3 +--
 fs/xfs/xfs_error.h            |  4 ++--
 fs/xfs/xfs_inode.c            | 11 +++++------
 fs/xfs/xfs_iomap.c            |  2 +-
 fs/xfs/xfs_log.c              |  3 +--
 13 files changed, 26 insertions(+), 40 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 33db69be4832..b008ff3250eb 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -111,8 +111,7 @@ xfs_ag_resv_critical(
 
 	/* Critically low if less than 10% or max btree height remains. */
 	return XFS_TEST_ERROR(avail < orig / 10 || avail < XFS_BTREE_MAXLEVELS,
-			pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL,
-			XFS_RANDOM_AG_RESV_CRITICAL);
+			pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index fefa8daa1c36..744dcaec34cc 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2454,8 +2454,7 @@ xfs_agf_read_verify(
 	    !xfs_buf_verify_cksum(bp, XFS_AGF_CRC_OFF))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
 	else if (XFS_TEST_ERROR(!xfs_agf_verify(mp, bp), mp,
-				XFS_ERRTAG_ALLOC_READ_AGF,
-				XFS_RANDOM_ALLOC_READ_AGF))
+				XFS_ERRTAG_ALLOC_READ_AGF))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
@@ -2842,8 +2841,7 @@ xfs_free_extent(
 	ASSERT(type != XFS_AG_RESV_AGFL);
 
 	if (XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_FREE_EXTENT,
-			XFS_RANDOM_FREE_EXTENT))
+			XFS_ERRTAG_FREE_EXTENT))
 		return -EIO;
 
 	error = xfs_free_extent_fix_freelist(tp, agno, &agbp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 19480ed231a4..0a9880777c9c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3992,7 +3992,7 @@ xfs_bmapi_read(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmapi_read", XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
 	}
@@ -4473,7 +4473,7 @@ xfs_bmapi_write(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmapi_write", XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
 	}
@@ -4694,7 +4694,7 @@ xfs_bmapi_remap(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmapi_remap", XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
 	}
@@ -6098,7 +6098,7 @@ xfs_bmap_shift_extents(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmap_shift_extents",
 				 XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
@@ -6250,7 +6250,7 @@ xfs_bmap_split_extent_at(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmap_split_extent_at",
 				 XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
@@ -6508,8 +6508,7 @@ xfs_bmap_finish_one(
 		return -EFSCORRUPTED;
 
 	if (XFS_TEST_ERROR(false, tp->t_mountp,
-			XFS_ERRTAG_BMAP_FINISH_ONE,
-			XFS_RANDOM_BMAP_FINISH_ONE))
+			XFS_ERRTAG_BMAP_FINISH_ONE))
 		return -EIO;
 
 	switch (type) {
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 2f8075aa8725..4da85fff69ad 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -101,8 +101,7 @@ xfs_btree_check_lblock(
 			be64_to_cpu(block->bb_u.l.bb_rightsib)));
 
 	if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp,
-			XFS_ERRTAG_BTREE_CHECK_LBLOCK,
-			XFS_RANDOM_BTREE_CHECK_LBLOCK))) {
+			XFS_ERRTAG_BTREE_CHECK_LBLOCK))) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
@@ -153,8 +152,7 @@ xfs_btree_check_sblock(
 		block->bb_u.s.bb_rightsib;
 
 	if (unlikely(XFS_TEST_ERROR(!sblock_ok, mp,
-			XFS_ERRTAG_BTREE_CHECK_SBLOCK,
-			XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
+			XFS_ERRTAG_BTREE_CHECK_SBLOCK))) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 2f389d366e93..ccf9783fd3f0 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -218,8 +218,7 @@ xfs_dir_ino_validate(
 		agblkno != 0 &&
 		ioff < (1 << mp->m_sb.sb_inopblog) &&
 		XFS_AGINO_TO_INO(mp, agno, agino) == ino;
-	if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE,
-			XFS_RANDOM_DIR_INO_VALIDATE))) {
+	if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE))) {
 		xfs_warn(mp, "Invalid inode number 0x%Lx",
 				(unsigned long long) ino);
 		XFS_ERROR_REPORT("xfs_dir_ino_validate", XFS_ERRLEVEL_LOW, mp);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index c514fe98bbab..ffd5a15d1bb6 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2552,8 +2552,7 @@ xfs_agi_read_verify(
 	    !xfs_buf_verify_cksum(bp, XFS_AGI_CRC_OFF))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
 	else if (XFS_TEST_ERROR(!xfs_agi_verify(bp), mp,
-				XFS_ERRTAG_IALLOC_READ_AGI,
-				XFS_RANDOM_IALLOC_READ_AGI))
+				XFS_ERRTAG_IALLOC_READ_AGI))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 0c970cf7ab63..378f8fbc91a7 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -105,8 +105,7 @@ xfs_inode_buf_verify(
 		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
 			xfs_dinode_good_version(mp, dip->di_version);
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
-						XFS_ERRTAG_ITOBP_INOTOBP,
-						XFS_RANDOM_ITOBP_INOTOBP))) {
+						XFS_ERRTAG_ITOBP_INOTOBP))) {
 			if (readahead) {
 				bp->b_flags &= ~XBF_DONE;
 				xfs_buf_ioerror(bp, -EIO);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index e17016163542..900ea231f9a3 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -805,8 +805,7 @@ xfs_refcount_still_have_space(
 	 */
 	if (cur->bc_private.a.priv.refc.nr_ops > 2 &&
 	    XFS_TEST_ERROR(false, cur->bc_mp,
-			XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE,
-			XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE))
+			XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE))
 		return false;
 
 	if (cur->bc_private.a.priv.refc.nr_ops == 0)
@@ -1068,8 +1067,7 @@ xfs_refcount_finish_one(
 			blockcount);
 
 	if (XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_REFCOUNT_FINISH_ONE,
-			XFS_RANDOM_REFCOUNT_FINISH_ONE))
+			XFS_ERRTAG_REFCOUNT_FINISH_ONE))
 		return -EIO;
 
 	/*
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index eda275beebe0..55c88a732690 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2087,8 +2087,7 @@ xfs_rmap_finish_one(
 			startoff, blockcount, state);
 
 	if (XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_RMAP_FINISH_ONE,
-			XFS_RANDOM_RMAP_FINISH_ONE))
+			XFS_ERRTAG_RMAP_FINISH_ONE))
 		return -EIO;
 
 	/*
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 8915bdeb6128..ae8935b90a93 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -135,7 +135,7 @@ extern int xfs_errortag_init(struct xfs_mount *mp);
 extern void xfs_errortag_del(struct xfs_mount *mp);
 extern bool xfs_errortag_test(struct xfs_mount *mp, const char *expression,
 		const char *file, int line, unsigned int error_tag);
-#define XFS_TEST_ERROR(expr, mp, tag, rf)		\
+#define XFS_TEST_ERROR(expr, mp, tag)		\
 	((expr) || xfs_errortag_test((mp), #expr, __FILE__, __LINE__, (tag)))
 
 extern int xfs_errortag_get(struct xfs_mount *mp, unsigned int error_tag);
@@ -146,7 +146,7 @@ extern int xfs_errortag_clearall(struct xfs_mount *mp);
 #else
 #define xfs_errortag_init(mp)			(0)
 #define xfs_errortag_del(mp)
-#define XFS_TEST_ERROR(expr, mp, tag, rf)	(expr)
+#define XFS_TEST_ERROR(expr, mp, tag)		(expr)
 #define xfs_errortag_set(mp, tag, val)		(ENOSYS)
 #define xfs_errortag_add(mp, tag)		(ENOSYS)
 #define xfs_errortag_clearall(mp)		(ENOSYS)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ffbfe7d8bc6d..67bd5631166e 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3489,7 +3489,7 @@ xfs_iflush_int(
 	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
 	if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC),
-			       mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
+			       mp, XFS_ERRTAG_IFLUSH_1)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 			"%s: Bad inode %Lu magic number 0x%x, ptr 0x%p",
 			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
@@ -3499,7 +3499,7 @@ xfs_iflush_int(
 		if (XFS_TEST_ERROR(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
-		    mp, XFS_ERRTAG_IFLUSH_3, XFS_RANDOM_IFLUSH_3)) {
+		    mp, XFS_ERRTAG_IFLUSH_3)) {
 			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 				"%s: Bad regular inode %Lu, ptr 0x%p",
 				__func__, ip->i_ino, ip);
@@ -3510,7 +3510,7 @@ xfs_iflush_int(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL),
-		    mp, XFS_ERRTAG_IFLUSH_4, XFS_RANDOM_IFLUSH_4)) {
+		    mp, XFS_ERRTAG_IFLUSH_4)) {
 			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 				"%s: Bad directory inode %Lu, ptr 0x%p",
 				__func__, ip->i_ino, ip);
@@ -3518,8 +3518,7 @@ xfs_iflush_int(
 		}
 	}
 	if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents >
-				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5,
-				XFS_RANDOM_IFLUSH_5)) {
+				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 			"%s: detected corrupt incore inode %Lu, "
 			"total extents = %d, nblocks = %Ld, ptr 0x%p",
@@ -3529,7 +3528,7 @@ xfs_iflush_int(
 		goto corrupt_out;
 	}
 	if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
-				mp, XFS_ERRTAG_IFLUSH_6, XFS_RANDOM_IFLUSH_6)) {
+				mp, XFS_ERRTAG_IFLUSH_6)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 			"%s: bad inode %Lu, forkoff 0x%x, ptr 0x%p",
 			__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 94e5bdf7304c..304b79d681e4 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -543,7 +543,7 @@ xfs_file_iomap_begin_delay(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
 		error = -EFSCORRUPTED;
 		goto out_unlock;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 98b39cbae42d..2d1112ee1f86 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1189,8 +1189,7 @@ xlog_iodone(xfs_buf_t *bp)
 	 * IOABORT state. The IOABORT state is only set in DEBUG mode to inject
 	 * CRC errors into log recovery.
 	 */
-	if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR,
-			   XFS_RANDOM_IODONE_IOERR) ||
+	if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR) ||
 	    iclog->ic_state & XLOG_STATE_IOABORT) {
 		if (iclog->ic_state & XLOG_STATE_IOABORT)
 			iclog->ic_state &= ~XLOG_STATE_IOABORT;

From f8c47250ba46eb221d1ac537266ac65bcf2866d5 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 20 Jun 2017 17:54:48 -0700
Subject: [PATCH 34/48] xfs: convert drop_writes to use the errortag mechanism

We now have enhanced error injection that can control the frequency
with which errors happen, so convert drop_writes to use this.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_error.c |  3 +++
 fs/xfs/xfs_error.h | 12 +++++++++++-
 fs/xfs/xfs_iomap.c |  2 +-
 fs/xfs/xfs_mount.h | 24 ------------------------
 fs/xfs/xfs_sysfs.c | 42 ------------------------------------------
 5 files changed, 15 insertions(+), 68 deletions(-)

diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index e2278af6aed1..a2f23d2bab16 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -55,6 +55,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_REFCOUNT_FINISH_ONE,
 	XFS_RANDOM_BMAP_FINISH_ONE,
 	XFS_RANDOM_AG_RESV_CRITICAL,
+	XFS_RANDOM_DROP_WRITES,
 };
 
 struct xfs_errortag_attr {
@@ -157,6 +158,7 @@ XFS_ERRORTAG_ATTR_RW(refcount_continue_update,	XFS_ERRTAG_REFCOUNT_CONTINUE_UPDA
 XFS_ERRORTAG_ATTR_RW(refcount_finish_one,	XFS_ERRTAG_REFCOUNT_FINISH_ONE);
 XFS_ERRORTAG_ATTR_RW(bmap_finish_one,	XFS_ERRTAG_BMAP_FINISH_ONE);
 XFS_ERRORTAG_ATTR_RW(ag_resv_critical,	XFS_ERRTAG_AG_RESV_CRITICAL);
+XFS_ERRORTAG_ATTR_RW(drop_writes,	XFS_ERRTAG_DROP_WRITES);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -187,6 +189,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(refcount_finish_one),
 	XFS_ERRORTAG_ATTR_LIST(bmap_finish_one),
 	XFS_ERRORTAG_ATTR_LIST(ag_resv_critical),
+	XFS_ERRORTAG_ATTR_LIST(drop_writes),
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index ae8935b90a93..e0e4cf776fac 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -96,7 +96,16 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
 #define XFS_ERRTAG_REFCOUNT_FINISH_ONE			25
 #define XFS_ERRTAG_BMAP_FINISH_ONE			26
 #define XFS_ERRTAG_AG_RESV_CRITICAL			27
-#define XFS_ERRTAG_MAX					28
+/*
+ * DEBUG mode instrumentation to test and/or trigger delayed allocation
+ * block killing in the event of failed writes. When enabled, all
+ * buffered writes are silenty dropped and handled as if they failed.
+ * All delalloc blocks in the range of the write (including pre-existing
+ * delalloc blocks!) are tossed as part of the write failure error
+ * handling sequence.
+ */
+#define XFS_ERRTAG_DROP_WRITES				28
+#define XFS_ERRTAG_MAX					29
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -129,6 +138,7 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
 #define XFS_RANDOM_REFCOUNT_FINISH_ONE			1
 #define XFS_RANDOM_BMAP_FINISH_ONE			1
 #define XFS_RANDOM_AG_RESV_CRITICAL			4
+#define XFS_RANDOM_DROP_WRITES				1
 
 #ifdef DEBUG
 extern int xfs_errortag_init(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 304b79d681e4..86f1a9fa46d2 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1097,7 +1097,7 @@ xfs_file_iomap_end_delalloc(
 	 * Behave as if the write failed if drop writes is enabled. Set the NEW
 	 * flag to force delalloc cleanup.
 	 */
-	if (xfs_mp_drop_writes(mp)) {
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) {
 		iomap->flags |= IOMAP_F_NEW;
 		written = 0;
 	}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 931e9fc21a1c..e0792d036be2 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -205,16 +205,6 @@ typedef struct xfs_mount {
 	 */
 	unsigned int		*m_errortag;
 	struct xfs_kobj		m_errortag_kobj;
-
-	/*
-	 * DEBUG mode instrumentation to test and/or trigger delayed allocation
-	 * block killing in the event of failed writes. When enabled, all
-	 * buffered writes are silenty dropped and handled as if they failed.
-	 * All delalloc blocks in the range of the write (including pre-existing
-	 * delalloc blocks!) are tossed as part of the write failure error
-	 * handling sequence.
-	 */
-	bool			m_drop_writes;
 #endif
 } xfs_mount_t;
 
@@ -333,20 +323,6 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 	return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks);
 }
 
-#ifdef DEBUG
-static inline bool
-xfs_mp_drop_writes(struct xfs_mount *mp)
-{
-	return mp->m_drop_writes;
-}
-#else
-static inline bool
-xfs_mp_drop_writes(struct xfs_mount *mp)
-{
-	return 0;
-}
-#endif
-
 /* per-AG block reservation data structures*/
 enum xfs_ag_resv_type {
 	XFS_AG_RESV_NONE = 0,
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index ec6e0e2f95d6..56610a973593 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -90,49 +90,7 @@ to_mp(struct kobject *kobject)
 	return container_of(kobj, struct xfs_mount, m_kobj);
 }
 
-#ifdef DEBUG
-
-STATIC ssize_t
-drop_writes_store(
-	struct kobject		*kobject,
-	const char		*buf,
-	size_t			count)
-{
-	struct xfs_mount	*mp = to_mp(kobject);
-	int			ret;
-	int			val;
-
-	ret = kstrtoint(buf, 0, &val);
-	if (ret)
-		return ret;
-
-	if (val == 1)
-		mp->m_drop_writes = true;
-	else if (val == 0)
-		mp->m_drop_writes = false;
-	else
-		return -EINVAL;
-
-	return count;
-}
-
-STATIC ssize_t
-drop_writes_show(
-	struct kobject		*kobject,
-	char			*buf)
-{
-	struct xfs_mount	*mp = to_mp(kobject);
-
-	return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_drop_writes ? 1 : 0);
-}
-XFS_SYSFS_ATTR_RW(drop_writes);
-
-#endif /* DEBUG */
-
 static struct attribute *xfs_mp_attrs[] = {
-#ifdef DEBUG
-	ATTR_LIST(drop_writes),
-#endif
 	NULL,
 };
 

From 3e88a0078ba8ef61816c85d33131827b4a307852 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 27 Jun 2017 09:52:32 -0700
Subject: [PATCH 35/48] xfs: replace log_badcrc_factor knob with error
 injection tag

Now that error injection tags support dynamic frequency adjustment,
replace the debug mode sysfs knob that controls log record CRC error
injection with an error injection tag.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_error.c |  3 +++
 fs/xfs/xfs_error.h |  4 +++-
 fs/xfs/xfs_log.c   |  5 +----
 fs/xfs/xfs_sysfs.c | 36 ------------------------------------
 4 files changed, 7 insertions(+), 41 deletions(-)

diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index a2f23d2bab16..26c32bc5cd34 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -56,6 +56,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_BMAP_FINISH_ONE,
 	XFS_RANDOM_AG_RESV_CRITICAL,
 	XFS_RANDOM_DROP_WRITES,
+	XFS_RANDOM_LOG_BAD_CRC,
 };
 
 struct xfs_errortag_attr {
@@ -159,6 +160,7 @@ XFS_ERRORTAG_ATTR_RW(refcount_finish_one,	XFS_ERRTAG_REFCOUNT_FINISH_ONE);
 XFS_ERRORTAG_ATTR_RW(bmap_finish_one,	XFS_ERRTAG_BMAP_FINISH_ONE);
 XFS_ERRORTAG_ATTR_RW(ag_resv_critical,	XFS_ERRTAG_AG_RESV_CRITICAL);
 XFS_ERRORTAG_ATTR_RW(drop_writes,	XFS_ERRTAG_DROP_WRITES);
+XFS_ERRORTAG_ATTR_RW(log_bad_crc,	XFS_ERRTAG_LOG_BAD_CRC);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -190,6 +192,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(bmap_finish_one),
 	XFS_ERRORTAG_ATTR_LIST(ag_resv_critical),
 	XFS_ERRORTAG_ATTR_LIST(drop_writes),
+	XFS_ERRORTAG_ATTR_LIST(log_bad_crc),
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index e0e4cf776fac..7577be5f09bc 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -105,7 +105,8 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
  * handling sequence.
  */
 #define XFS_ERRTAG_DROP_WRITES				28
-#define XFS_ERRTAG_MAX					29
+#define XFS_ERRTAG_LOG_BAD_CRC				29
+#define XFS_ERRTAG_MAX					30
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -139,6 +140,7 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
 #define XFS_RANDOM_BMAP_FINISH_ONE			1
 #define XFS_RANDOM_AG_RESV_CRITICAL			4
 #define XFS_RANDOM_DROP_WRITES				1
+#define XFS_RANDOM_LOG_BAD_CRC				1
 
 #ifdef DEBUG
 extern int xfs_errortag_init(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 2d1112ee1f86..31f11be42f01 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1841,7 +1841,6 @@ xlog_sync(
 	/* calculcate the checksum */
 	iclog->ic_header.h_crc = xlog_cksum(log, &iclog->ic_header,
 					    iclog->ic_datap, size);
-#ifdef DEBUG
 	/*
 	 * Intentionally corrupt the log record CRC based on the error injection
 	 * frequency, if defined. This facilitates testing log recovery in the
@@ -1849,15 +1848,13 @@ xlog_sync(
 	 * write on I/O completion and shutdown the fs. The subsequent mount
 	 * detects the bad CRC and attempts to recover.
 	 */
-	if (log->l_badcrc_factor &&
-	    (prandom_u32() % log->l_badcrc_factor == 0)) {
+	if (XFS_TEST_ERROR(false, log->l_mp, XFS_ERRTAG_LOG_BAD_CRC)) {
 		iclog->ic_header.h_crc &= cpu_to_le32(0xAAAAAAAA);
 		iclog->ic_state |= XLOG_STATE_IOABORT;
 		xfs_warn(log->l_mp,
 	"Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.",
 			 be64_to_cpu(iclog->ic_header.h_lsn));
 	}
-#endif
 
 	bp->b_io_length = BTOBB(count);
 	bp->b_fspriv = iclog;
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 56610a973593..8b2ccc234f36 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -305,47 +305,11 @@ write_grant_head_show(
 }
 XFS_SYSFS_ATTR_RO(write_grant_head);
 
-#ifdef DEBUG
-STATIC ssize_t
-log_badcrc_factor_store(
-	struct kobject	*kobject,
-	const char	*buf,
-	size_t		count)
-{
-	struct xlog	*log = to_xlog(kobject);
-	int		ret;
-	uint32_t	val;
-
-	ret = kstrtouint(buf, 0, &val);
-	if (ret)
-		return ret;
-
-	log->l_badcrc_factor = val;
-
-	return count;
-}
-
-STATIC ssize_t
-log_badcrc_factor_show(
-	struct kobject	*kobject,
-	char		*buf)
-{
-	struct xlog	*log = to_xlog(kobject);
-
-	return snprintf(buf, PAGE_SIZE, "%d\n", log->l_badcrc_factor);
-}
-
-XFS_SYSFS_ATTR_RW(log_badcrc_factor);
-#endif	/* DEBUG */
-
 static struct attribute *xfs_log_attrs[] = {
 	ATTR_LIST(log_head_lsn),
 	ATTR_LIST(log_tail_lsn),
 	ATTR_LIST(reserve_grant_head),
 	ATTR_LIST(write_grant_head),
-#ifdef DEBUG
-	ATTR_LIST(log_badcrc_factor),
-#endif
 	NULL,
 };
 

From cf2cb7845d6e101cb17bd62f8aa08cd514fc8988 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 20 Jun 2017 14:36:19 -0700
Subject: [PATCH 36/48] xfs: free cowblocks and retry on buffered write ENOSPC

XFS runs an eofblocks reclaim scan before returning an ENOSPC error to
userspace for buffered writes. This facilitates aggressive speculative
preallocation without causing user visible side effects such as
premature ENOSPC.

Run a cowblocks scan in the same situation to reclaim lingering COW fork
preallocation throughout the filesystem.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_file.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 36c129303fcf..8f9a491b2551 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -660,6 +660,7 @@ write_retry:
 		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);
 		goto write_retry;
 	}
 

From 8ba358756aa08414fa9e65a1a41d28304ed6fd7f Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 26 Jun 2017 08:48:18 -0700
Subject: [PATCH 37/48] xfs: Don't clear SGID when inheriting ACLs

When new directory 'DIR1' is created in a directory 'DIR0' with SGID bit
set, DIR1 is expected to have SGID bit set (and owning group equal to
the owning group of 'DIR0'). However when 'DIR0' also has some default
ACLs that 'DIR1' inherits, setting these ACLs will result in SGID bit on
'DIR1' to get cleared if user is not member of the owning group.

Fix the problem by calling __xfs_set_acl() instead of xfs_set_acl() when
setting up inode in xfs_generic_create(). That prevents SGID bit
clearing and mode is properly set by posix_acl_create() anyway. We also
reorder arguments of __xfs_set_acl() to match the ordering of
xfs_set_acl() to make things consistent.

Fixes: 073931017b49d9458aa351605b43a7e34598caef
CC: stable@vger.kernel.org
CC: Darrick J. Wong <darrick.wong@oracle.com>
CC: linux-xfs@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_acl.c  | 6 +++---
 fs/xfs/xfs_acl.h  | 1 +
 fs/xfs/xfs_iops.c | 4 ++--
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index b468e041f207..7034e17535de 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -170,8 +170,8 @@ xfs_get_acl(struct inode *inode, int type)
 	return acl;
 }
 
-STATIC int
-__xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
+int
+__xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	struct xfs_inode *ip = XFS_I(inode);
 	unsigned char *ea_name;
@@ -268,5 +268,5 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	}
 
  set_acl:
-	return __xfs_set_acl(inode, type, acl);
+	return __xfs_set_acl(inode, acl, type);
 }
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 286fa89217f5..04327318ef67 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -24,6 +24,7 @@ struct posix_acl;
 #ifdef CONFIG_XFS_POSIX_ACL
 extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
 extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 #else
 static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type)
 {
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ebfc13350f9a..077e2b2ac773 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -190,12 +190,12 @@ xfs_generic_create(
 
 #ifdef CONFIG_XFS_POSIX_ACL
 	if (default_acl) {
-		error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		error = __xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		if (error)
 			goto out_cleanup_inode;
 	}
 	if (acl) {
-		error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
+		error = __xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
 		if (error)
 			goto out_cleanup_inode;
 	}

From 244e3dea58818e9520bf3dbaf4404a60b105bfb1 Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Mon, 26 Jun 2017 08:54:16 -0700
Subject: [PATCH 38/48] xfs: fix semicolon.cocci warnings

fs/xfs/xfs_log.c:2092:38-39: Unneeded semicolon


 Remove unneeded semicolon.

Generated by: scripts/coccinelle/misc/semicolon.cocci

Fixes: d4ca1d550d05 ("xfs: dump transaction usage details on log reservation overrun")
CC: Brian Foster <bfoster@redhat.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 31f11be42f01..0053bcf2b10a 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2085,7 +2085,7 @@ xlog_print_trans(
 			xfs_warn(mp, "    type	= 0x%x", vec->i_type);
 			xfs_warn(mp, "    len	= %d", vec->i_len);
 			xfs_warn(mp, "    first %d bytes of iovec[%d]:", dumplen, i);
-			xfs_hex_dump(vec->i_addr, dumplen);;
+			xfs_hex_dump(vec->i_addr, dumplen);
 
 			vec++;
 		}

From 50e0bdbe9f48f98bb02eac7030d682f4716884ae Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 27 Jun 2017 10:19:45 -0700
Subject: [PATCH 39/48] xfs: grab dquots without taking the ilock

Add a new dqget flag that grabs the dquot without taking the ilock.
This will be used by the scrubber (which will have already grabbed
the ilock) to perform basic sanity checking of the quota data.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_quota_defs.h |  2 ++
 fs/xfs/xfs_dquot.c             | 14 ++++++++++----
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index d69c772271cb..2834574cb6e7 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -136,6 +136,8 @@ typedef uint16_t	xfs_qwarncnt_t;
  */
 #define XFS_QMOPT_INHERIT	0x1000000
 
+#define XFS_QMOPT_NOLOCK	0x2000000 /* don't ilock during dqget */
+
 /*
  * flags to xfs_trans_mod_dquot.
  */
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index e57c6cce91aa..79668142afc1 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -472,18 +472,23 @@ xfs_qm_dqtobp(
 	struct xfs_mount	*mp = dqp->q_mount;
 	xfs_dqid_t		id = be32_to_cpu(dqp->q_core.d_id);
 	struct xfs_trans	*tp = (tpp ? *tpp : NULL);
-	uint			lock_mode;
+	uint			lock_mode = 0;
 
 	quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags);
 	dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
 
-	lock_mode = xfs_ilock_data_map_shared(quotip);
+	ASSERT(!(flags & XFS_QMOPT_NOLOCK) ||
+		xfs_isilocked(quotip, XFS_ILOCK_SHARED) ||
+		xfs_isilocked(quotip, XFS_ILOCK_EXCL));
+	if (!(flags & XFS_QMOPT_NOLOCK))
+		lock_mode = xfs_ilock_data_map_shared(quotip);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
 		/*
 		 * Return if this type of quotas is turned off while we
 		 * didn't have the quota inode lock.
 		 */
-		xfs_iunlock(quotip, lock_mode);
+		if (lock_mode)
+			xfs_iunlock(quotip, lock_mode);
 		return -ESRCH;
 	}
 
@@ -493,7 +498,8 @@ xfs_qm_dqtobp(
 	error = xfs_bmapi_read(quotip, dqp->q_fileoffset,
 			       XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0);
 
-	xfs_iunlock(quotip, lock_mode);
+	if (lock_mode)
+		xfs_iunlock(quotip, lock_mode);
 	if (error)
 		return error;
 

From d04c241c669209667dd8f44335591246e601139a Mon Sep 17 00:00:00 2001
From: Carlos Maiolino <cmaiolino@redhat.com>
Date: Fri, 30 Jun 2017 09:46:07 -0700
Subject: [PATCH 40/48] xfs: Check for m_errortag initialization in
 xfs_errortag_test

While adding error injection into IO completion, I notice the lack of
initialization check in xfs_errortag_test(), make the error injection
mechanism unable to be used there.

IO completion is executed a few times before the error injection
mechanism is initialized, so to be safer, make xfs_errortag_test() check
if the errortag is properly initialized.

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_error.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 26c32bc5cd34..2f4feb959bfb 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -233,6 +233,17 @@ xfs_errortag_test(
 {
 	unsigned int		randfactor;
 
+	/*
+	 * To be able to use error injection anywhere, we need to ensure error
+	 * injection mechanism is already initialized.
+	 *
+	 * Code paths like I/O completion can be called before the
+	 * initialization is complete, but be able to inject errors in such
+	 * places is still useful.
+	 */
+	if (!mp->m_errortag)
+		return false;
+
 	ASSERT(error_tag < XFS_ERRTAG_MAX);
 	randfactor = mp->m_errortag[error_tag];
 	if (!randfactor || prandom_u32() % randfactor)

From bda250dbaf39f67f8910e183853e4e6a9e5ce899 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 29 Jun 2017 12:28:36 -0700
Subject: [PATCH 41/48] xfs: rewrite xfs_dq_get_next_id using
 xfs_iext_lookup_extent

This goes straight to a single lookup in the extent list and avoids a
roundtrip through two layers that don't add any value for the simple
quoata file that just has data or holes and no page cache, delayed
allocation, unwritten extent or COW fork (which btw, doesn't seem to
be handled by the existing SEEK HOLE/DATA code).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_dquot.c | 66 ++++++++++++++++------------------------------
 1 file changed, 22 insertions(+), 44 deletions(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 79668142afc1..8848b397e7a8 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -701,21 +701,18 @@ error0:
  */
 static int
 xfs_dq_get_next_id(
-	xfs_mount_t		*mp,
+	struct xfs_mount	*mp,
 	uint			type,
-	xfs_dqid_t		*id,
-	loff_t			eof)
+	xfs_dqid_t		*id)
 {
-	struct xfs_inode	*quotip;
+	struct xfs_inode	*quotip = xfs_quota_inode(mp, type);
+	xfs_dqid_t		next_id = *id + 1; /* simple advance */
+	uint			lock_flags;
+	struct xfs_bmbt_irec	got;
+	xfs_extnum_t		idx;
 	xfs_fsblock_t		start;
-	loff_t			offset;
-	uint			lock;
-	xfs_dqid_t		next_id;
 	int			error = 0;
 
-	/* Simple advance */
-	next_id = *id + 1;
-
 	/* If we'd wrap past the max ID, stop */
 	if (next_id < *id)
 		return -ENOENT;
@@ -729,23 +726,20 @@ xfs_dq_get_next_id(
 	/* Nope, next_id is now past the current chunk, so find the next one */
 	start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk;
 
-	quotip = xfs_quota_inode(mp, type);
-	lock = xfs_ilock_data_map_shared(quotip);
+	lock_flags = xfs_ilock_data_map_shared(quotip);
+	if (!(quotip->i_df.if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK);
+		if (error)
+			return error;
+	}
 
-	offset = __xfs_seek_hole_data(VFS_I(quotip), XFS_FSB_TO_B(mp, start),
-				      eof, SEEK_DATA);
-	if (offset < 0)
-		error = offset;
+	if (xfs_iext_lookup_extent(quotip, &quotip->i_df, start, &idx, &got))
+		*id = got.br_startoff * mp->m_quotainfo->qi_dqperchunk;
+	else
+		error = -ENOENT;
+	xfs_iunlock(quotip, lock_flags);
 
-	xfs_iunlock(quotip, lock);
-
-	/* -ENXIO is essentially "no more data" */
-	if (error)
-		return (error == -ENXIO ? -ENOENT: error);
-
-	/* Convert next data offset back to a quota id */
-	*id = XFS_B_TO_FSB(mp, offset) * mp->m_quotainfo->qi_dqperchunk;
-	return 0;
+	return error;
 }
 
 /*
@@ -768,7 +762,6 @@ xfs_qm_dqget(
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
 	struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
 	struct xfs_dquot	*dqp;
-	loff_t			eof = 0;
 	int			error;
 
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
@@ -796,21 +789,6 @@ xfs_qm_dqget(
 	}
 #endif
 
-	/* Get the end of the quota file if we need it */
-	if (flags & XFS_QMOPT_DQNEXT) {
-		struct xfs_inode	*quotip;
-		xfs_fileoff_t		last;
-		uint			lock_mode;
-
-		quotip = xfs_quota_inode(mp, type);
-		lock_mode = xfs_ilock_data_map_shared(quotip);
-		error = xfs_bmap_last_offset(quotip, &last, XFS_DATA_FORK);
-		xfs_iunlock(quotip, lock_mode);
-		if (error)
-			return error;
-		eof = XFS_FSB_TO_B(mp, last);
-	}
-
 restart:
 	mutex_lock(&qi->qi_tree_lock);
 	dqp = radix_tree_lookup(tree, id);
@@ -829,7 +807,7 @@ restart:
 			if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
 				xfs_dqunlock(dqp);
 				mutex_unlock(&qi->qi_tree_lock);
-				error = xfs_dq_get_next_id(mp, type, &id, eof);
+				error = xfs_dq_get_next_id(mp, type, &id);
 				if (error)
 					return error;
 				goto restart;
@@ -864,7 +842,7 @@ restart:
 
 	/* If we are asked to find next active id, keep looking */
 	if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) {
-		error = xfs_dq_get_next_id(mp, type, &id, eof);
+		error = xfs_dq_get_next_id(mp, type, &id);
 		if (!error)
 			goto restart;
 	}
@@ -923,7 +901,7 @@ restart:
 	if (flags & XFS_QMOPT_DQNEXT) {
 		if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
 			xfs_qm_dqput(dqp);
-			error = xfs_dq_get_next_id(mp, type, &id, eof);
+			error = xfs_dq_get_next_id(mp, type, &id);
 			if (error)
 				return error;
 			goto restart;

From 7175a11214f02e6184690c17cf5366012b667531 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 29 Jun 2017 11:43:19 -0700
Subject: [PATCH 42/48] xfs: remove a whitespace-only line from
 xfs_fs_get_nextdqblk

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_quotaops.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index f82d79a8c694..de9493253edf 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -269,7 +269,6 @@ xfs_fs_get_nextdqblk(
 	/* ID may be different, so convert back what we got */
 	*qid = make_kqid(current_user_ns(), qid->type, id);
 	return 0;
-	
 }
 
 STATIC int

From 334fd34d76f237c0ee58dfc400d2c4e34d660544 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 29 Jun 2017 11:43:20 -0700
Subject: [PATCH 43/48] vfs: Add page_cache_seek_hole_data helper

Both ext4 and xfs implement seeking for the next hole or piece of data
in unwritten extents by scanning the page cache, and both versions share
the same bug when iterating the buffers of a page: the start offset into
the page isn't taken into account, so when a page fits more than two
filesystem blocks, things will go wrong.  For example, on a filesystem
with a block size of 1k, the following command will fail:

  xfs_io -f -c "falloc 0 4k" \
            -c "pwrite 1k 1k" \
            -c "pwrite 3k 1k" \
            -c "seek -a -r 0" foo

In this example, neither lseek(fd, 1024, SEEK_HOLE) nor lseek(fd, 2048,
SEEK_DATA) will return the correct result.

Introduce a generic vfs helper for seeking in the page cache that gets
this right.  The next commits will replace the filesystem specific
implementations.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
[hch: dropped the export]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/buffer.c                 | 124 ++++++++++++++++++++++++++++++++++++
 include/linux/buffer_head.h |   2 +
 2 files changed, 126 insertions(+)

diff --git a/fs/buffer.c b/fs/buffer.c
index 161be58c5cb0..b3674eb7c9c0 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3492,6 +3492,130 @@ int bh_submit_read(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(bh_submit_read);
 
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
+ *
+ * Returns the offset within the file on success, and -ENOENT otherwise.
+ */
+static loff_t
+page_seek_hole_data(struct page *page, loff_t lastoff, int whence)
+{
+	loff_t offset = page_offset(page);
+	struct buffer_head *bh, *head;
+	bool seek_data = whence == SEEK_DATA;
+
+	if (lastoff < offset)
+		lastoff = offset;
+
+	bh = head = page_buffers(page);
+	do {
+		offset += bh->b_size;
+		if (lastoff >= offset)
+			continue;
+
+		/*
+		 * Unwritten extents that have data in the page cache covering
+		 * them can be identified by the BH_Unwritten state flag.
+		 * Pages with multiple buffers might have a mix of holes, data
+		 * and unwritten extents - any buffer with valid data in it
+		 * should have BH_Uptodate flag set on it.
+		 */
+
+		if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data)
+			return lastoff;
+
+		lastoff = offset;
+	} while ((bh = bh->b_this_page) != head);
+	return -ENOENT;
+}
+
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
+ *
+ * Within unwritten extents, the page cache determines which parts are holes
+ * and which are data: unwritten and uptodate buffer heads count as data;
+ * everything else counts as a hole.
+ *
+ * Returns the resulting offset on successs, and -ENOENT otherwise.
+ */
+loff_t
+page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
+			  int whence)
+{
+	pgoff_t index = offset >> PAGE_SHIFT;
+	pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
+	loff_t lastoff = offset;
+	struct pagevec pvec;
+
+	if (length <= 0)
+		return -ENOENT;
+
+	pagevec_init(&pvec, 0);
+
+	do {
+		unsigned want, nr_pages, i;
+
+		want = min_t(unsigned, end - index, PAGEVEC_SIZE);
+		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/*
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping.  However, page->index will not change
+			 * because we have a reference on the page.
+                         *
+			 * If current page offset is beyond where we've ended,
+			 * we've found a hole.
+                         */
+			if (whence == SEEK_HOLE &&
+			    lastoff < page_offset(page))
+				goto check_range;
+
+			/* Searching done if the page index is out of range. */
+			if (page->index >= end)
+				goto not_found;
+
+			lock_page(page);
+			if (likely(page->mapping == inode->i_mapping) &&
+			    page_has_buffers(page)) {
+				lastoff = page_seek_hole_data(page, lastoff, whence);
+				if (lastoff >= 0) {
+					unlock_page(page);
+					goto check_range;
+				}
+			}
+			unlock_page(page);
+			lastoff = page_offset(page) + PAGE_SIZE;
+		}
+
+		/* Searching done if fewer pages returned than wanted. */
+		if (nr_pages < want)
+			break;
+
+		index = pvec.pages[i - 1]->index + 1;
+		pagevec_release(&pvec);
+	} while (index < end);
+
+	/* When no page at lastoff and we are not done, we found a hole. */
+	if (whence != SEEK_HOLE)
+		goto not_found;
+
+check_range:
+	if (lastoff < offset + length)
+		goto out;
+not_found:
+	lastoff = -ENOENT;
+out:
+	pagevec_release(&pvec);
+	return lastoff;
+}
+
 void __init buffer_init(void)
 {
 	unsigned long nrpages;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index bd029e52ef5e..ad4e024ce17e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -201,6 +201,8 @@ void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize);
 int bh_uptodate_or_lock(struct buffer_head *bh);
 int bh_submit_read(struct buffer_head *bh);
+loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset,
+				 loff_t length, int whence);
 
 extern int buffer_heads_over_limit;
 

From 0ed3b0d45fd39142e418220f518c8959c1a5f596 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 29 Jun 2017 11:43:21 -0700
Subject: [PATCH 44/48] vfs: Add iomap_seek_hole and iomap_seek_data helpers

Filesystems can use this for implementing lseek SEEK_HOLE / SEEK_DATA
support via iomap.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
[hch: split functions, coding style cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c            | 94 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/iomap.h |  4 ++
 2 files changed, 98 insertions(+)

diff --git a/fs/iomap.c b/fs/iomap.c
index 4b10892967a5..432eed8f091f 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -584,6 +584,100 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 }
 EXPORT_SYMBOL_GPL(iomap_fiemap);
 
+static loff_t
+iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
+		      void *data, struct iomap *iomap)
+{
+	switch (iomap->type) {
+	case IOMAP_UNWRITTEN:
+		offset = page_cache_seek_hole_data(inode, offset, length,
+						   SEEK_HOLE);
+		if (offset < 0)
+			return length;
+		/* fall through */
+	case IOMAP_HOLE:
+		*(loff_t *)data = offset;
+		return 0;
+	default:
+		return length;
+	}
+}
+
+loff_t
+iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	loff_t length = size - offset;
+	loff_t ret;
+
+	/* Nothing to be found beyond the end of the file. */
+	if (offset >= size)
+		return -ENXIO;
+
+	while (length > 0) {
+		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
+				  &offset, iomap_seek_hole_actor);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			break;
+
+		offset += ret;
+		length -= ret;
+	}
+
+	return offset;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_hole);
+
+static loff_t
+iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
+		      void *data, struct iomap *iomap)
+{
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		return length;
+	case IOMAP_UNWRITTEN:
+		offset = page_cache_seek_hole_data(inode, offset, length,
+						   SEEK_DATA);
+		if (offset < 0)
+			return length;
+		/*FALLTHRU*/
+	default:
+		*(loff_t *)data = offset;
+		return 0;
+	}
+}
+
+loff_t
+iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	loff_t length = size - offset;
+	loff_t ret;
+
+	/* Nothing to be found beyond the end of the file. */
+	if (offset >= size)
+		return -ENXIO;
+
+	while (length > 0) {
+		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
+				  &offset, iomap_seek_data_actor);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			break;
+
+		offset += ret;
+		length -= ret;
+	}
+
+	if (length <= 0)
+		return -ENXIO;
+	return offset;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_data);
+
 /*
  * Private flags for iomap_dio, must not overlap with the public ones in
  * iomap.h:
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index f753e788da31..8a03f5dcd89b 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -83,6 +83,10 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops);
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		loff_t start, loff_t len, const struct iomap_ops *ops);
+loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
+		const struct iomap_ops *ops);
+loff_t iomap_seek_data(struct inode *inode, loff_t offset,
+		const struct iomap_ops *ops);
 
 /*
  * Flags for direct I/O ->end_io:

From 9b2970aacfd9aa5d9bad377a554a002b398f882e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 29 Jun 2017 11:43:21 -0700
Subject: [PATCH 45/48] xfs: Switch to iomap for SEEK_HOLE / SEEK_DATA

Switch to the iomap_seek_hole and iomap_seek_data helpers for
implementing lseek SEEK_HOLE / SEEK_DATA, and remove all the
code that isn't needed any more.

Based on patches from Andreas Gruenbacher <agruenba@redhat.com>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_file.c  | 375 ++-------------------------------------------
 fs/xfs/xfs_inode.h |   3 -
 2 files changed, 14 insertions(+), 364 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8f9a491b2551..5b95e58c5bf2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -954,378 +954,31 @@ xfs_file_readdir(
 	return xfs_readdir(NULL, ip, ctx, bufsize);
 }
 
-/*
- * This type is designed to indicate the type of offset we would like
- * to search from page cache for xfs_seek_hole_data().
- */
-enum {
-	HOLE_OFF = 0,
-	DATA_OFF,
-};
-
-/*
- * Lookup the desired type of offset from the given page.
- *
- * On success, return true and the offset argument will point to the
- * start of the region that was found.  Otherwise this function will
- * return false and keep the offset argument unchanged.
- */
-STATIC bool
-xfs_lookup_buffer_offset(
-	struct page		*page,
-	loff_t			*offset,
-	unsigned int		type)
-{
-	loff_t			lastoff = page_offset(page);
-	bool			found = false;
-	struct buffer_head	*bh, *head;
-
-	bh = head = page_buffers(page);
-	do {
-		/*
-		 * Unwritten extents that have data in the page
-		 * cache covering them can be identified by the
-		 * BH_Unwritten state flag.  Pages with multiple
-		 * buffers might have a mix of holes, data and
-		 * unwritten extents - any buffer with valid
-		 * data in it should have BH_Uptodate flag set
-		 * on it.
-		 */
-		if (buffer_unwritten(bh) ||
-		    buffer_uptodate(bh)) {
-			if (type == DATA_OFF)
-				found = true;
-		} else {
-			if (type == HOLE_OFF)
-				found = true;
-		}
-
-		if (found) {
-			*offset = lastoff;
-			break;
-		}
-		lastoff += bh->b_size;
-	} while ((bh = bh->b_this_page) != head);
-
-	return found;
-}
-
-/*
- * This routine is called to find out and return a data or hole offset
- * from the page cache for unwritten extents according to the desired
- * type for xfs_seek_hole_data().
- *
- * The argument offset is used to tell where we start to search from the
- * page cache.  Map is used to figure out the end points of the range to
- * lookup pages.
- *
- * Return true if the desired type of offset was found, and the argument
- * offset is filled with that address.  Otherwise, return false and keep
- * offset unchanged.
- */
-STATIC bool
-xfs_find_get_desired_pgoff(
-	struct inode		*inode,
-	struct xfs_bmbt_irec	*map,
-	unsigned int		type,
-	loff_t			*offset)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	struct pagevec		pvec;
-	pgoff_t			index;
-	pgoff_t			end;
-	loff_t			endoff;
-	loff_t			startoff = *offset;
-	loff_t			lastoff = startoff;
-	bool			found = false;
-
-	pagevec_init(&pvec, 0);
-
-	index = startoff >> PAGE_SHIFT;
-	endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount);
-	end = (endoff - 1) >> PAGE_SHIFT;
-	do {
-		int		want;
-		unsigned	nr_pages;
-		unsigned int	i;
-
-		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
-		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
-					  want);
-		if (nr_pages == 0)
-			break;
-
-		for (i = 0; i < nr_pages; i++) {
-			struct page	*page = pvec.pages[i];
-			loff_t		b_offset;
-
-			/*
-			 * At this point, the page may be truncated or
-			 * invalidated (changing page->mapping to NULL),
-			 * or even swizzled back from swapper_space to tmpfs
-			 * file mapping. However, page->index will not change
-			 * because we have a reference on the page.
-			 *
-			 * If current page offset is beyond where we've ended,
-			 * we've found a hole.
-			 */
-			if (type == HOLE_OFF && lastoff < endoff &&
-			    lastoff < page_offset(pvec.pages[i])) {
-				found = true;
-				*offset = lastoff;
-				goto out;
-			}
-			/* Searching done if the page index is out of range. */
-			if (page->index > end)
-				goto out;
-
-			lock_page(page);
-			/*
-			 * Page truncated or invalidated(page->mapping == NULL).
-			 * We can freely skip it and proceed to check the next
-			 * page.
-			 */
-			if (unlikely(page->mapping != inode->i_mapping)) {
-				unlock_page(page);
-				continue;
-			}
-
-			if (!page_has_buffers(page)) {
-				unlock_page(page);
-				continue;
-			}
-
-			found = xfs_lookup_buffer_offset(page, &b_offset, type);
-			if (found) {
-				/*
-				 * The found offset may be less than the start
-				 * point to search if this is the first time to
-				 * come here.
-				 */
-				*offset = max_t(loff_t, startoff, b_offset);
-				unlock_page(page);
-				goto out;
-			}
-
-			/*
-			 * We either searching data but nothing was found, or
-			 * searching hole but found a data buffer.  In either
-			 * case, probably the next page contains the desired
-			 * things, update the last offset to it so.
-			 */
-			lastoff = page_offset(page) + PAGE_SIZE;
-			unlock_page(page);
-		}
-
-		/*
-		 * The number of returned pages less than our desired, search
-		 * done.
-		 */
-		if (nr_pages < want)
-			break;
-
-		index = pvec.pages[i - 1]->index + 1;
-		pagevec_release(&pvec);
-	} while (index <= end);
-
-	/* No page at lastoff and we are not done - we found a hole. */
-	if (type == HOLE_OFF && lastoff < endoff) {
-		*offset = lastoff;
-		found = true;
-	}
-out:
-	pagevec_release(&pvec);
-	return found;
-}
-
-/*
- * caller must lock inode with xfs_ilock_data_map_shared,
- * can we craft an appropriate ASSERT?
- *
- * end is because the VFS-level lseek interface is defined such that any
- * offset past i_size shall return -ENXIO, but we use this for quota code
- * which does not maintain i_size, and we want to SEEK_DATA past i_size.
- */
-loff_t
-__xfs_seek_hole_data(
-	struct inode		*inode,
-	loff_t			start,
-	loff_t			end,
-	int			whence)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	loff_t			uninitialized_var(offset);
-	xfs_fileoff_t		fsbno;
-	xfs_filblks_t		lastbno;
-	int			error;
-
-	if (start >= end) {
-		error = -ENXIO;
-		goto out_error;
-	}
-
-	/*
-	 * Try to read extents from the first block indicated
-	 * by fsbno to the end block of the file.
-	 */
-	fsbno = XFS_B_TO_FSBT(mp, start);
-	lastbno = XFS_B_TO_FSB(mp, end);
-
-	for (;;) {
-		struct xfs_bmbt_irec	map[2];
-		int			nmap = 2;
-		unsigned int		i;
-
-		error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap,
-				       XFS_BMAPI_ENTIRE);
-		if (error)
-			goto out_error;
-
-		/* No extents at given offset, must be beyond EOF */
-		if (nmap == 0) {
-			error = -ENXIO;
-			goto out_error;
-		}
-
-		for (i = 0; i < nmap; i++) {
-			offset = max_t(loff_t, start,
-				       XFS_FSB_TO_B(mp, map[i].br_startoff));
-
-			/* Landed in the hole we wanted? */
-			if (whence == SEEK_HOLE &&
-			    map[i].br_startblock == HOLESTARTBLOCK)
-				goto out;
-
-			/* Landed in the data extent we wanted? */
-			if (whence == SEEK_DATA &&
-			    (map[i].br_startblock == DELAYSTARTBLOCK ||
-			     (map[i].br_state == XFS_EXT_NORM &&
-			      !isnullstartblock(map[i].br_startblock))))
-				goto out;
-
-			/*
-			 * Landed in an unwritten extent, try to search
-			 * for hole or data from page cache.
-			 */
-			if (map[i].br_state == XFS_EXT_UNWRITTEN) {
-				if (xfs_find_get_desired_pgoff(inode, &map[i],
-				      whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF,
-							&offset))
-					goto out;
-			}
-		}
-
-		/*
-		 * We only received one extent out of the two requested. This
-		 * means we've hit EOF and didn't find what we are looking for.
-		 */
-		if (nmap == 1) {
-			/*
-			 * If we were looking for a hole, set offset to
-			 * the end of the file (i.e., there is an implicit
-			 * hole at the end of any file).
-		 	 */
-			if (whence == SEEK_HOLE) {
-				offset = end;
-				break;
-			}
-			/*
-			 * If we were looking for data, it's nowhere to be found
-			 */
-			ASSERT(whence == SEEK_DATA);
-			error = -ENXIO;
-			goto out_error;
-		}
-
-		ASSERT(i > 1);
-
-		/*
-		 * Nothing was found, proceed to the next round of search
-		 * if the next reading offset is not at or beyond EOF.
-		 */
-		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
-		start = XFS_FSB_TO_B(mp, fsbno);
-		if (start >= end) {
-			if (whence == SEEK_HOLE) {
-				offset = end;
-				break;
-			}
-			ASSERT(whence == SEEK_DATA);
-			error = -ENXIO;
-			goto out_error;
-		}
-	}
-
-out:
-	/*
-	 * If at this point we have found the hole we wanted, the returned
-	 * offset may be bigger than the file size as it may be aligned to
-	 * page boundary for unwritten extents.  We need to deal with this
-	 * situation in particular.
-	 */
-	if (whence == SEEK_HOLE)
-		offset = min_t(loff_t, offset, end);
-
-	return offset;
-
-out_error:
-	return error;
-}
-
-STATIC loff_t
-xfs_seek_hole_data(
-	struct file		*file,
-	loff_t			start,
-	int			whence)
-{
-	struct inode		*inode = file->f_mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	uint			lock;
-	loff_t			offset, end;
-	int			error = 0;
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	lock = xfs_ilock_data_map_shared(ip);
-
-	end = i_size_read(inode);
-	offset = __xfs_seek_hole_data(inode, start, end, whence);
-	if (offset < 0) {
-		error = offset;
-		goto out_unlock;
-	}
-
-	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
-
-out_unlock:
-	xfs_iunlock(ip, lock);
-
-	if (error)
-		return error;
-	return offset;
-}
-
 STATIC loff_t
 xfs_file_llseek(
 	struct file	*file,
 	loff_t		offset,
 	int		whence)
 {
+	struct inode		*inode = file->f_mapping->host;
+
+	if (XFS_FORCED_SHUTDOWN(XFS_I(inode)->i_mount))
+		return -EIO;
+
 	switch (whence) {
-	case SEEK_END:
-	case SEEK_CUR:
-	case SEEK_SET:
+	default:
 		return generic_file_llseek(file, offset, whence);
 	case SEEK_HOLE:
+		offset = iomap_seek_hole(inode, offset, &xfs_iomap_ops);
+		break;
 	case SEEK_DATA:
-		return xfs_seek_hole_data(file, offset, whence);
-	default:
-		return -EINVAL;
+		offset = iomap_seek_data(inode, offset, &xfs_iomap_ops);
+		break;
 	}
+
+	if (offset < 0)
+		return offset;
+	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
 /*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 677d0bfe1c2d..0ee453de239a 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -445,9 +445,6 @@ int	xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
 		     xfs_fsize_t isize, bool *did_zeroing);
 int	xfs_zero_range(struct xfs_inode *ip, xfs_off_t pos, xfs_off_t count,
 		bool *did_zero);
-loff_t	__xfs_seek_hole_data(struct inode *inode, loff_t start,
-			     loff_t eof, int whence);
-
 
 /* from xfs_iops.c */
 extern void xfs_setup_inode(struct xfs_inode *ip);

From 2192b0baea395274ffcd38ec70e284389e3c243d Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 5 Jul 2017 12:07:52 -0700
Subject: [PATCH 46/48] xfs: fix contiguous dquot chunk iteration livelock

The patch below updated xfs_dq_get_next_id() to use the XFS iext
lookup helpers to locate the next quota id rather than to seek for
data in the quota file. The updated code fails to correctly handle
the case where the quota inode might have contiguous chunks part of
the same extent. In this case, the start block offset is calculated
based on the next expected id but the extent lookup returns the same
start offset as for the previous chunk. This causes the returned id
to go backwards and livelocks the quota iteration. This problem is
reproduced intermittently by generic/232.

To handle this case, check whether the startoff from the extent
lookup is behind the startoff calculated from the next quota id. If
so, bump up got.br_startoff to the specific file offset that is
expected to hold the next dquot chunk.

Fixes: bda250dbaf39 ("xfs: rewrite xfs_dq_get_next_id using xfs_iext_lookup_extent")
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_dquot.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 8848b397e7a8..f89f7b5241e6 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -733,10 +733,15 @@ xfs_dq_get_next_id(
 			return error;
 	}
 
-	if (xfs_iext_lookup_extent(quotip, &quotip->i_df, start, &idx, &got))
+	if (xfs_iext_lookup_extent(quotip, &quotip->i_df, start, &idx, &got)) {
+		/* contiguous chunk, bump startoff for the id calculation */
+		if (got.br_startoff < start)
+			got.br_startoff = start;
 		*id = got.br_startoff * mp->m_quotainfo->qi_dqperchunk;
-	else
+	} else {
 		error = -ENOENT;
+	}
+
 	xfs_iunlock(quotip, lock_flags);
 
 	return error;

From 6eb0b8df9f74f33d1a69100117630a7a87a9cc96 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 7 Jul 2017 08:37:26 -0700
Subject: [PATCH 47/48] xfs: rename MAXPATHLEN to XFS_SYMLINK_MAXLEN

XFS has a maximum symlink target length of 1024 bytes; this is a
holdover from the Irix days.  Unfortunately, the constant establishing
this is 'MAXPATHLEN' and is /not/ the same as the Linux MAXPATHLEN,
which is 4096.

The kernel enforces its 1024 byte MAXPATHLEN on symlink targets, but
xfsprogs picks up the (Linux) system 4096 byte MAXPATHLEN, which means
that xfs_repair doesn't complain about oversized symlinks.

Since this is an on-disk format constraint, put the define in the XFS
namespace and move everything over to use the new name.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_format.h         | 1 +
 fs/xfs/libxfs/xfs_symlink_remote.c | 2 +-
 fs/xfs/libxfs/xfs_trans_resv.c     | 4 ++--
 fs/xfs/xfs_iops.c                  | 2 +-
 fs/xfs/xfs_linux.h                 | 1 -
 fs/xfs/xfs_symlink.c               | 6 +++---
 6 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index e204a942e5bf..23229f0c5b15 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1211,6 +1211,7 @@ struct xfs_dsymlink_hdr {
 
 #define XFS_SYMLINK_CRC_OFF	offsetof(struct xfs_dsymlink_hdr, sl_crc)
 
+#define XFS_SYMLINK_MAXLEN	1024
 /*
  * The maximum pathlen is 1024 bytes. Since the minimum file system
  * blocksize is 512 bytes, we can get a max of 3 extents back from
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 2e2c6716b623..c484877129a0 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -114,7 +114,7 @@ xfs_symlink_verify(
 	if (bp->b_bn != be64_to_cpu(dsl->sl_blkno))
 		return false;
 	if (be32_to_cpu(dsl->sl_offset) +
-				be32_to_cpu(dsl->sl_bytes) >= MAXPATHLEN)
+				be32_to_cpu(dsl->sl_bytes) >= XFS_SYMLINK_MAXLEN)
 		return false;
 	if (dsl->sl_owner == 0)
 		return false;
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index b456cca1bfb2..6bd916bd35e2 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -477,14 +477,14 @@ xfs_calc_mkdir_reservation(
 /*
  * Making a new symplink is the same as creating a new file, but
  * with the added blocks for remote symlink data which can be up to 1kB in
- * length (MAXPATHLEN).
+ * length (XFS_SYMLINK_MAXLEN).
  */
 STATIC uint
 xfs_calc_symlink_reservation(
 	struct xfs_mount	*mp)
 {
 	return xfs_calc_create_reservation(mp) +
-	       xfs_calc_buf_res(1, MAXPATHLEN);
+	       xfs_calc_buf_res(1, XFS_SYMLINK_MAXLEN);
 }
 
 /*
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 077e2b2ac773..469c9fa4c178 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -460,7 +460,7 @@ xfs_vn_get_link(
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
 
-	link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
+	link = kmalloc(XFS_SYMLINK_MAXLEN+1, GFP_KERNEL);
 	if (!link)
 		goto out_err;
 
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index ecdae42267d3..44abaecd1481 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -143,7 +143,6 @@ typedef __u32			xfs_nlink_t;
 #define __return_address __builtin_return_address(0)
 
 #define XFS_PROJID_DEFAULT	0
-#define MAXPATHLEN	1024
 
 #define MIN(a,b)	(min(a,b))
 #define MAX(a,b)	(max(a,b))
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 493804857d67..12cd9cf7de41 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -143,7 +143,7 @@ xfs_readlink(
 	if (!pathlen)
 		goto out;
 
-	if (pathlen < 0 || pathlen > MAXPATHLEN) {
+	if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
 		xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)",
 			 __func__, (unsigned long long) ip->i_ino,
 			 (long long) pathlen);
@@ -202,7 +202,7 @@ xfs_symlink(
 	 * Check component lengths of the target path name.
 	 */
 	pathlen = strlen(target_path);
-	if (pathlen >= MAXPATHLEN)      /* total string too long */
+	if (pathlen >= XFS_SYMLINK_MAXLEN)      /* total string too long */
 		return -ENAMETOOLONG;
 
 	udqp = gdqp = NULL;
@@ -559,7 +559,7 @@ xfs_inactive_symlink(
 		return 0;
 	}
 
-	if (pathlen < 0 || pathlen > MAXPATHLEN) {
+	if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
 		xfs_alert(mp, "%s: inode (0x%llx) bad symlink length (%d)",
 			 __func__, (unsigned long long)ip->i_ino, pathlen);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);

From cd87d867920155911d0d2e6485b769d853547750 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 7 Jul 2017 18:55:17 -0700
Subject: [PATCH 48/48] xfs: don't crash on unexpected holes in dir/attr btrees

In quite a few places we call xfs_da_read_buf with a mappedbno that we
don't control, then assume that the function passes back either an error
code or a buffer pointer.  Unfortunately, if mappedbno == -2 and bno
maps to a hole, we get a return code of zero and a NULL buffer, which
means that we crash if we actually try to use that buffer pointer.  This
happens immediately when we set the buffer type for transaction context.

Therefore, check that we have no error code and a non-NULL bp before
trying to use bp.  This patch is a follow-up to an incomplete fix in
96a3aefb8ffde231 ("xfs: don't crash if reading a directory results in an
unexpected hole").

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c  | 2 +-
 fs/xfs/libxfs/xfs_da_btree.c   | 2 +-
 fs/xfs/libxfs/xfs_dir2_block.c | 2 +-
 fs/xfs/libxfs/xfs_dir2_leaf.c  | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 2852521fc8ec..c6c15e5717e4 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -351,7 +351,7 @@ xfs_attr3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 				XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
 	return err;
 }
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 356f21d5cd35..6d4335815c3f 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -263,7 +263,7 @@ xfs_da3_node_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 					which_fork, &xfs_da3_node_buf_ops);
-	if (!err && tp) {
+	if (!err && tp && *bpp) {
 		struct xfs_da_blkinfo	*info = (*bpp)->b_addr;
 		int			type;
 
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index aa17cb788946..43c902f7a68d 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -139,7 +139,7 @@ xfs_dir3_block_read(
 
 	err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp,
 				XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF);
 	return err;
 }
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 7002024a5d0d..27297a689d9c 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -268,7 +268,7 @@ xfs_dir3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
 	return err;
 }
@@ -285,7 +285,7 @@ xfs_dir3_leafn_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
 	return err;
 }