Merge tag 'xfs-5.3-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "In this release there are a significant amounts of consolidations and
  cleanups in the log code; restructuring of the log to issue struct
  bios directly; new bulkstat ioctls to return v5 fs inode information
  (and fix all the padding problems of the old ioctl); the beginnings of
  multithreaded inode walks (e.g. quotacheck); and a reduction in memory
  usage in the online scrub code leading to reduced runtimes.

   - Refactor inode geometry calculation into a single structure instead
     of open-coding pieces everywhere.

   - Add online repair to build options.

   - Remove unnecessary function call flags and functions.

   - Claim maintainership of various loose xfs documentation and header
     files.

   - Use struct bio directly for log buffer IOs instead of struct
     xfs_buf.

   - Reduce log item boilerplate code requirements.

   - Merge log item code spread across too many files.

   - Further distinguish between log item commits and cancellations.

   - Various small cleanups to the ag small allocator.

   - Support cgroup-aware writeback

   - libxfs refactoring for mkfs cleanup

   - Remove unneeded #includes

   - Fix a memory allocation miscalculation in the new log bio code

   - Fix bisection problems

   - Fix a crash in ioend processing caused by tripping over freeing of
     preallocated transactions

   - Split out a generic inode walk mechanism from the bulkstat code,
     hook up all the internal users to use the walking code, then clean
     up bulkstat to serve only the bulkstat ioctls.

   - Add a multithreaded iwalk implementation to speed up quotacheck on
     fast storage with many CPUs.

   - Remove unnecessary return values in logging teardown functions.

   - Supplement the bstat and inogrp structures with new bulkstat and
     inumbers structures that have all the fields we need for v5
     filesystem features and none of the padding problems of their
     predecessors.

   - Wire up new ioctls that use the new structures with a much simpler
     bulk_ireq structure at the head instead of the pointerhappy mess we
     had before.

   - Enable userspace to constrain bulkstat returns to a single AG or a
     single special inode so that we can phase out a lot of geometry
     guesswork in userspace.

   - Reduce memory consumption and zeroing overhead in extended
     attribute scrub code.

   - Fix some behavioral regressions in the new bulkstat backend code.

   - Fix some behavioral regressions in the new log bio code"

* tag 'xfs-5.3-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (100 commits)
  xfs: chain bios the right way around in xfs_rw_bdev
  xfs: bump INUMBERS cursor correctly in xfs_inumbers_walk
  xfs: don't update lastino for FSBULKSTAT_SINGLE
  xfs: online scrub needn't bother zeroing its temporary buffer
  xfs: only allocate memory for scrubbing attributes when we need it
  xfs: refactor attr scrub memory allocation function
  xfs: refactor extended attribute buffer pointer functions
  xfs: attribute scrub should use seen_enough to pass error values
  xfs: allow single bulkstat of special inodes
  xfs: specify AG in bulk req
  xfs: wire up the v5 inumbers ioctl
  xfs: wire up new v5 bulkstat ioctls
  xfs: introduce v5 inode group structure
  xfs: introduce new v5 bulkstat structure
  xfs: rename bulkstat functions
  xfs: remove various bulk request typedef usage
  fs: xfs: xfs_log: Change return type from int to void
  xfs: poll waiting for quotacheck
  xfs: multithreaded iwalk implementation
  xfs: refactor INUMBERS to use iwalk functions
  ...

1 files changed, 109 insertions, 118 deletions

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index a9ff3cf82cce..372ad55631fc 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -13,7 +13,6 @@
 #include "xfs_sb.h"
 #include "xfs_mount.h"
 #include "xfs_defer.h"
-#include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_alloc_btree.h"
@@ -21,7 +20,6 @@
 #include "xfs_extent_busy.h"
 #include "xfs_errortag.h"
 #include "xfs_error.h"
-#include "xfs_cksum.h"
 #include "xfs_trace.h"
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
@@ -41,8 +39,6 @@ struct workqueue_struct *xfs_alloc_wq;
 STATIC int xfs_alloc_ag_vextent_exact(xfs_alloc_arg_t *);
 STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *);
 STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *);
-STATIC int xfs_alloc_ag_vextent_small(xfs_alloc_arg_t *,
-		xfs_btree_cur_t *, xfs_agblock_t *, xfs_extlen_t *, int *);
 
 /*
  * Size of the AGFL.  For CRC-enabled filesystes we steal a couple of slots in
@@ -555,7 +551,7 @@ static xfs_failaddr_t
 xfs_agfl_verify(
 	struct xfs_buf	*bp)
 {
-	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_mount *mp = bp->b_mount;
 	struct xfs_agfl	*agfl = XFS_BUF_TO_AGFL(bp);
 	int		i;
 
@@ -596,7 +592,7 @@ static void
 xfs_agfl_read_verify(
 	struct xfs_buf	*bp)
 {
-	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_mount *mp = bp->b_mount;
 	xfs_failaddr_t	fa;
 
 	/*
@@ -621,7 +617,7 @@ static void
 xfs_agfl_write_verify(
 	struct xfs_buf	*bp)
 {
-	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	xfs_failaddr_t		fa;
 
@@ -700,6 +696,107 @@ xfs_alloc_update_counters(
  */
 
 /*
+ * Deal with the case where only small freespaces remain. Either return the
+ * contents of the last freespace record, or allocate space from the freelist if
+ * there is nothing in the tree.
+ */
+STATIC int			/* error */
+xfs_alloc_ag_vextent_small(
+	struct xfs_alloc_arg	*args,	/* allocation argument structure */
+	struct xfs_btree_cur	*ccur,	/* optional by-size cursor */
+	xfs_agblock_t		*fbnop,	/* result block number */
+	xfs_extlen_t		*flenp,	/* result length */
+	int			*stat)	/* status: 0-freelist, 1-normal/none */
+{
+	int			error = 0;
+	xfs_agblock_t		fbno = NULLAGBLOCK;
+	xfs_extlen_t		flen = 0;
+	int			i = 0;
+
+	/*
+	 * If a cntbt cursor is provided, try to allocate the largest record in
+	 * the tree. Try the AGFL if the cntbt is empty, otherwise fail the
+	 * allocation. Make sure to respect minleft even when pulling from the
+	 * freelist.
+	 */
+	if (ccur)
+		error = xfs_btree_decrement(ccur, 0, &i);
+	if (error)
+		goto error;
+	if (i) {
+		error = xfs_alloc_get_rec(ccur, &fbno, &flen, &i);
+		if (error)
+			goto error;
+		XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error);
+		goto out;
+	}
+
+	if (args->minlen != 1 || args->alignment != 1 ||
+	    args->resv == XFS_AG_RESV_AGFL ||
+	    (be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_flcount) <=
+	     args->minleft))
+		goto out;
+
+	error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno, 0);
+	if (error)
+		goto error;
+	if (fbno == NULLAGBLOCK)
+		goto out;
+
+	xfs_extent_busy_reuse(args->mp, args->agno, fbno, 1,
+			      xfs_alloc_allow_busy_reuse(args->datatype));
+
+	if (xfs_alloc_is_userdata(args->datatype)) {
+		struct xfs_buf	*bp;
+
+		bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno);
+		if (!bp) {
+			error = -EFSCORRUPTED;
+			goto error;
+		}
+		xfs_trans_binval(args->tp, bp);
+	}
+	*fbnop = args->agbno = fbno;
+	*flenp = args->len = 1;
+	XFS_WANT_CORRUPTED_GOTO(args->mp,
+		fbno < be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length),
+		error);
+	args->wasfromfl = 1;
+	trace_xfs_alloc_small_freelist(args);
+
+	/*
+	 * If we're feeding an AGFL block to something that doesn't live in the
+	 * free space, we need to clear out the OWN_AG rmap.
+	 */
+	error = xfs_rmap_free(args->tp, args->agbp, args->agno, fbno, 1,
+			      &XFS_RMAP_OINFO_AG);
+	if (error)
+		goto error;
+
+	*stat = 0;
+	return 0;
+
+out:
+	/*
+	 * Can't do the allocation, give up.
+	 */
+	if (flen < args->minlen) {
+		args->agbno = NULLAGBLOCK;
+		trace_xfs_alloc_small_notenough(args);
+		flen = 0;
+	}
+	*fbnop = fbno;
+	*flenp = flen;
+	*stat = 1;
+	trace_xfs_alloc_small_done(args);
+	return 0;
+
+error:
+	trace_xfs_alloc_small_error(args);
+	return error;
+}
+
+/*
  * Allocate a variable extent in the allocation group agno.
  * Type and bno are used to determine where in the allocation group the
  * extent will start.
@@ -1583,112 +1680,6 @@ out_nominleft:
 }
 
 /*
- * Deal with the case where only small freespaces remain.
- * Either return the contents of the last freespace record,
- * or allocate space from the freelist if there is nothing in the tree.
- */
-STATIC int			/* error */
-xfs_alloc_ag_vextent_small(
-	xfs_alloc_arg_t	*args,	/* allocation argument structure */
-	xfs_btree_cur_t	*ccur,	/* by-size cursor */
-	xfs_agblock_t	*fbnop,	/* result block number */
-	xfs_extlen_t	*flenp,	/* result length */
-	int		*stat)	/* status: 0-freelist, 1-normal/none */
-{
-	int		error;
-	xfs_agblock_t	fbno;
-	xfs_extlen_t	flen;
-	int		i;
-
-	if ((error = xfs_btree_decrement(ccur, 0, &i)))
-		goto error0;
-	if (i) {
-		if ((error = xfs_alloc_get_rec(ccur, &fbno, &flen, &i)))
-			goto error0;
-		XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
-	}
-	/*
-	 * Nothing in the btree, try the freelist.  Make sure
-	 * to respect minleft even when pulling from the
-	 * freelist.
-	 */
-	else if (args->minlen == 1 && args->alignment == 1 &&
-		 args->resv != XFS_AG_RESV_AGFL &&
-		 (be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_flcount)
-		  > args->minleft)) {
-		error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno, 0);
-		if (error)
-			goto error0;
-		if (fbno != NULLAGBLOCK) {
-			xfs_extent_busy_reuse(args->mp, args->agno, fbno, 1,
-			      xfs_alloc_allow_busy_reuse(args->datatype));
-
-			if (xfs_alloc_is_userdata(args->datatype)) {
-				xfs_buf_t	*bp;
-
-				bp = xfs_btree_get_bufs(args->mp, args->tp,
-					args->agno, fbno, 0);
-				if (!bp) {
-					error = -EFSCORRUPTED;
-					goto error0;
-				}
-				xfs_trans_binval(args->tp, bp);
-			}
-			args->len = 1;
-			args->agbno = fbno;
-			XFS_WANT_CORRUPTED_GOTO(args->mp,
-				args->agbno + args->len <=
-				be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length),
-				error0);
-			args->wasfromfl = 1;
-			trace_xfs_alloc_small_freelist(args);
-
-			/*
-			 * If we're feeding an AGFL block to something that
-			 * doesn't live in the free space, we need to clear
-			 * out the OWN_AG rmap.
-			 */
-			error = xfs_rmap_free(args->tp, args->agbp, args->agno,
-					fbno, 1, &XFS_RMAP_OINFO_AG);
-			if (error)
-				goto error0;
-
-			*stat = 0;
-			return 0;
-		}
-		/*
-		 * Nothing in the freelist.
-		 */
-		else
-			flen = 0;
-	}
-	/*
-	 * Can't allocate from the freelist for some reason.
-	 */
-	else {
-		fbno = NULLAGBLOCK;
-		flen = 0;
-	}
-	/*
-	 * Can't do the allocation, give up.
-	 */
-	if (flen < args->minlen) {
-		args->agbno = NULLAGBLOCK;
-		trace_xfs_alloc_small_notenough(args);
-		flen = 0;
-	}
-	*fbnop = fbno;
-	*flenp = flen;
-	*stat = 1;
-	trace_xfs_alloc_small_done(args);
-	return 0;
-
-error0:
-	trace_xfs_alloc_small_error(args);
-	return error;
-}
-
-/*
  * Free the extent starting at agno/bno for length.
  */
 STATIC int
@@ -2095,7 +2086,7 @@ xfs_free_agfl_block(
 	if (error)
 		return error;
 
-	bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno, 0);
+	bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno);
 	if (!bp)
 		return -EFSCORRUPTED;
 	xfs_trans_binval(tp, bp);
@@ -2586,7 +2577,7 @@ static xfs_failaddr_t
 xfs_agf_verify(
 	struct xfs_buf		*bp)
 {
-	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_agf		*agf = XFS_BUF_TO_AGF(bp);
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
@@ -2644,7 +2635,7 @@ static void
 xfs_agf_read_verify(
 	struct xfs_buf	*bp)
 {
-	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_mount *mp = bp->b_mount;
 	xfs_failaddr_t	fa;
 
 	if (xfs_sb_version_hascrc(&mp->m_sb) &&
@@ -2661,7 +2652,7 @@ static void
 xfs_agf_write_verify(
 	struct xfs_buf	*bp)
 {
-	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	xfs_failaddr_t		fa;
 
@@ -3146,7 +3137,7 @@ xfs_alloc_has_record(
 
 /*
  * Walk all the blocks in the AGFL.  The @walk_fn can return any negative
- * error code or XFS_BTREE_QUERY_RANGE_ABORT.
+ * error code or XFS_ITER_*.
  */
 int
 xfs_agfl_walk(