[PATCH 47/67] xfs: also use xfs_bmap_btalloc_accounting for RT allocations

[PATCH 47/67] xfs: also use xfs_bmap_btalloc_accounting for RT allocations

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 58643460546da1dc61593fc6fd78762798b4534f

Make xfs_bmap_btalloc_accounting more generic by handling the RT quota
reservations and then also use it from xfs_bmap_rtalloc instead of
open coding the accounting logic there.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 libxfs/libxfs_priv.h    |    5 ++++-
 libxfs/xfs_bmap.c       |   21 ++++++++++++++-------
 libxfs/xfs_bmap.h       |    2 ++
 libxfs/xfs_bmap_btree.c |    1 +
 4 files changed, 21 insertions(+), 8 deletions(-)


diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 30ff8dba9178..28ee192509c7 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -434,7 +434,10 @@ void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa);
 #define xfs_filestream_select_ag(...)		(-ENOSYS)
 
 /* quota bits */
-#define xfs_trans_mod_dquot_byino(t,i,f,d)		((void) 0)
+#define xfs_trans_mod_dquot_byino(t,i,f,d)		({ \
+	uint _f = (f); \
+	_f = _f; /* shut up gcc */ \
+})
 #define xfs_trans_reserve_quota_nblks(t,i,b,n,f)	(0)
 
 /* hack too silence gcc */
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index ad058bb126e2..4f6bd8dff47e 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -3257,10 +3257,14 @@ xfs_bmap_btalloc_select_lengths(
 }
 
 /* Update all inode and quota accounting for the allocation we just did. */
-static void
-xfs_bmap_btalloc_accounting(
+void
+xfs_bmap_alloc_account(
 	struct xfs_bmalloca	*ap)
 {
+	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
+					(ap->flags & XFS_BMAPI_ATTRFORK);
+	uint			fld;
+
 	if (ap->flags & XFS_BMAPI_COWFORK) {
 		/*
 		 * COW fork blocks are in-core only and thus are treated as
@@ -3285,7 +3289,8 @@ xfs_bmap_btalloc_accounting(
 		 * to that of a delalloc extent.
 		 */
 		ap->ip->i_delayed_blks += ap->length;
-		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS,
+		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, isrt ?
+				XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS,
 				-(long)ap->length);
 		return;
 	}
@@ -3296,10 +3301,12 @@ xfs_bmap_btalloc_accounting(
 	if (ap->wasdel) {
 		ap->ip->i_delayed_blks -= ap->length;
 		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+		fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT;
+	} else {
+		fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
 	}
-	xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
-		ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
-		ap->length);
+
+	xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length);
 }
 
 static int
@@ -3373,7 +3380,7 @@ xfs_bmap_process_allocated_extent(
 		ap->offset = orig_offset;
 	else if (ap->offset + ap->length < orig_offset + orig_length)
 		ap->offset = orig_offset + orig_length - ap->length;
-	xfs_bmap_btalloc_accounting(ap);
+	xfs_bmap_alloc_account(ap);
 }
 
 #ifdef DEBUG
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 4b83f6148e00..f6b73f1bad5f 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -116,6 +116,8 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
 	return XFS_DATA_FORK;
 }
 
+void xfs_bmap_alloc_account(struct xfs_bmalloca *ap);
+
 /*
  * Special values for xfs_bmbt_irec_t br_startblock field.
  */
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 73ba067df06e..887ba56f3b7b 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -21,6 +21,7 @@
 #include "xfs_trace.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_quota_defs.h"
 
 static struct kmem_cache	*xfs_bmbt_cur_cache;
 

[PATCH 47/67] xfs: also use xfs_bmap_btalloc_accounting for RT allocations

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 58643460546da1dc61593fc6fd78762798b4534f

Make xfs_bmap_btalloc_accounting more generic by handling the RT quota
reservations and then also use it from xfs_bmap_rtalloc instead of
open coding the accounting logic there.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Reviewed-by: Bill O'Donnell <bodonnel@redhat.com>
---
 libxfs/libxfs_priv.h    |    5 ++++-
 libxfs/xfs_bmap.c       |   21 ++++++++++++++-------
 libxfs/xfs_bmap.h       |    2 ++
 libxfs/xfs_bmap_btree.c |    1 +
 4 files changed, 21 insertions(+), 8 deletions(-)


diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 30ff8dba9178..28ee192509c7 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -434,7 +434,10 @@ void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa);
 #define xfs_filestream_select_ag(...)		(-ENOSYS)
 
 /* quota bits */
-#define xfs_trans_mod_dquot_byino(t,i,f,d)		((void) 0)
+#define xfs_trans_mod_dquot_byino(t,i,f,d)		({ \
+	uint _f = (f); \
+	_f = _f; /* shut up gcc */ \
+})
 #define xfs_trans_reserve_quota_nblks(t,i,b,n,f)	(0)
 
 /* hack too silence gcc */
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index ad058bb126e2..4f6bd8dff47e 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -3257,10 +3257,14 @@ xfs_bmap_btalloc_select_lengths(
 }
 
 /* Update all inode and quota accounting for the allocation we just did. */
-static void
-xfs_bmap_btalloc_accounting(
+void
+xfs_bmap_alloc_account(
 	struct xfs_bmalloca	*ap)
 {
+	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
+					(ap->flags & XFS_BMAPI_ATTRFORK);
+	uint			fld;
+
 	if (ap->flags & XFS_BMAPI_COWFORK) {
 		/*
 		 * COW fork blocks are in-core only and thus are treated as
@@ -3285,7 +3289,8 @@ xfs_bmap_btalloc_accounting(
 		 * to that of a delalloc extent.
 		 */
 		ap->ip->i_delayed_blks += ap->length;
-		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS,
+		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, isrt ?
+				XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS,
 				-(long)ap->length);
 		return;
 	}
@@ -3296,10 +3301,12 @@ xfs_bmap_btalloc_accounting(
 	if (ap->wasdel) {
 		ap->ip->i_delayed_blks -= ap->length;
 		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+		fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT;
+	} else {
+		fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
 	}
-	xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
-		ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
-		ap->length);
+
+	xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length);
 }
 
 static int
@@ -3373,7 +3380,7 @@ xfs_bmap_process_allocated_extent(
 		ap->offset = orig_offset;
 	else if (ap->offset + ap->length < orig_offset + orig_length)
 		ap->offset = orig_offset + orig_length - ap->length;
-	xfs_bmap_btalloc_accounting(ap);
+	xfs_bmap_alloc_account(ap);
 }
 
 #ifdef DEBUG
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 4b83f6148e00..f6b73f1bad5f 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -116,6 +116,8 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
 	return XFS_DATA_FORK;
 }
 
+void xfs_bmap_alloc_account(struct xfs_bmalloca *ap);
+
 /*
  * Special values for xfs_bmbt_irec_t br_startblock field.
  */
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 73ba067df06e..887ba56f3b7b 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -21,6 +21,7 @@
 #include "xfs_trace.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_quota_defs.h"
 
 static struct kmem_cache	*xfs_bmbt_cur_cache;
 

[PATCH 47/67] xfs: also use xfs_bmap_btalloc_accounting for RT allocations

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 58643460546da1dc61593fc6fd78762798b4534f

Make xfs_bmap_btalloc_accounting more generic by handling the RT quota
reservations and then also use it from xfs_bmap_rtalloc instead of
open coding the accounting logic there.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Reviewed-by: Bill O'Donnell <bodonnel@redhat.com>
---
 libxfs/libxfs_priv.h    |    5 ++++-
 libxfs/xfs_bmap.c       |   21 ++++++++++++++-------
 libxfs/xfs_bmap.h       |    2 ++
 libxfs/xfs_bmap_btree.c |    1 +
 4 files changed, 21 insertions(+), 8 deletions(-)


diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 30ff8dba9..28ee19250 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -434,7 +434,10 @@ void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa);
 #define xfs_filestream_select_ag(...)		(-ENOSYS)
 
 /* quota bits */
-#define xfs_trans_mod_dquot_byino(t,i,f,d)		((void) 0)
+#define xfs_trans_mod_dquot_byino(t,i,f,d)		({ \
+	uint _f = (f); \
+	_f = _f; /* shut up gcc */ \
+})
 #define xfs_trans_reserve_quota_nblks(t,i,b,n,f)	(0)
 
 /* hack too silence gcc */
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index ad058bb12..4f6bd8dff 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -3257,10 +3257,14 @@ xfs_bmap_btalloc_select_lengths(
 }
 
 /* Update all inode and quota accounting for the allocation we just did. */
-static void
-xfs_bmap_btalloc_accounting(
+void
+xfs_bmap_alloc_account(
 	struct xfs_bmalloca	*ap)
 {
+	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
+					(ap->flags & XFS_BMAPI_ATTRFORK);
+	uint			fld;
+
 	if (ap->flags & XFS_BMAPI_COWFORK) {
 		/*
 		 * COW fork blocks are in-core only and thus are treated as
@@ -3285,7 +3289,8 @@ xfs_bmap_btalloc_accounting(
 		 * to that of a delalloc extent.
 		 */
 		ap->ip->i_delayed_blks += ap->length;
-		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS,
+		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, isrt ?
+				XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS,
 				-(long)ap->length);
 		return;
 	}
@@ -3296,10 +3301,12 @@ xfs_bmap_btalloc_accounting(
 	if (ap->wasdel) {
 		ap->ip->i_delayed_blks -= ap->length;
 		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+		fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT;
+	} else {
+		fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
 	}
-	xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
-		ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
-		ap->length);
+
+	xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length);
 }
 
 static int
@@ -3373,7 +3380,7 @@ xfs_bmap_process_allocated_extent(
 		ap->offset = orig_offset;
 	else if (ap->offset + ap->length < orig_offset + orig_length)
 		ap->offset = orig_offset + orig_length - ap->length;
-	xfs_bmap_btalloc_accounting(ap);
+	xfs_bmap_alloc_account(ap);
 }
 
 #ifdef DEBUG
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 4b83f6148..f6b73f1ba 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -116,6 +116,8 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
 	return XFS_DATA_FORK;
 }
 
+void xfs_bmap_alloc_account(struct xfs_bmalloca *ap);
+
 /*
  * Special values for xfs_bmbt_irec_t br_startblock field.
  */
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 73ba067df..887ba56f3 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -21,6 +21,7 @@
 #include "xfs_trace.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_quota_defs.h"
 
 static struct kmem_cache	*xfs_bmbt_cur_cache;
 

[PATCH 00/67] libxfs: Sync to Linux 6.8

[cem]

Hi,

this is the libxfs sync for xfsprogs, I'm finishing testing it and I'll push it sometime this week.
I'll start to work on the patches already on the list and will push it all to for-next sometime this
week yet.

Some of the conflicts were fixed using Darrick's suggestions (thanks Darrick).

you can pull the series directly with

git pull https://git.kernel.org/pub/scm/linux/kernel/git/cem/xfsprogs-dev.git libxfs-sync-6.8

Any questions, let me know.

Cheers.
Carlos

[PATCH 01/67] xfs: use xfs_defer_pending objects to recover intent items

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 03f7767c9f6120ac933378fdec3bfd78bf07bc11

One thing I never quite got around to doing is porting the log intent
item recovery code to reconstruct the deferred pending work state.  As a
result, each intent item open codes xfs_defer_finish_one in its recovery
method, because that's what the EFI code did before xfs_defer.c even
existed.

This is a gross thing to have left unfixed -- if an EFI cannot proceed
due to busy extents, we end up creating separate new EFIs for each
unfinished work item, which is a change in behavior from what runtime
would have done.

Worse yet, Long Li pointed out that there's a UAF in the recovery code.
The ->commit_pass2 function adds the intent item to the AIL and drops
the refcount.  The one remaining refcount is now owned by the recovery
mechanism (aka the log intent items in the AIL) with the intent of
giving the refcount to the intent done item in the ->iop_recover
function.

However, if something fails later in recovery, xlog_recover_finish will
walk the recovered intent items in the AIL and release them.  If the CIL
hasn't been pushed before that point (which is possible since we don't
force the log until later) then the intent done release will try to free
its associated intent, which has already been freed.

This patch starts to address this mess by having the ->commit_pass2
functions recreate the xfs_defer_pending state.  The next few patches
will fix the recovery functions.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 105 +++++++++++++++++++++++++++++++++------------
 libxfs/xfs_defer.h |   5 +++
 2 files changed, 82 insertions(+), 28 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 7ff125c5f..bd6f14a2c 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -240,23 +240,53 @@ xfs_defer_create_intents(
 	return ret;
 }
 
-STATIC void
+static inline void
 xfs_defer_pending_abort(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+
+	trace_xfs_defer_pending_abort(mp, dfp);
+
+	if (dfp->dfp_intent && !dfp->dfp_done) {
+		ops->abort_intent(dfp->dfp_intent);
+		dfp->dfp_intent = NULL;
+	}
+}
+
+static inline void
+xfs_defer_pending_cancel_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+	struct list_head		*pwi;
+	struct list_head		*n;
+
+	trace_xfs_defer_cancel_list(mp, dfp);
+
+	list_del(&dfp->dfp_list);
+	list_for_each_safe(pwi, n, &dfp->dfp_work) {
+		list_del(pwi);
+		dfp->dfp_count--;
+		trace_xfs_defer_cancel_item(mp, dfp, pwi);
+		ops->cancel_item(pwi);
+	}
+	ASSERT(dfp->dfp_count == 0);
+	kmem_cache_free(xfs_defer_pending_cache, dfp);
+}
+
+STATIC void
+xfs_defer_pending_abort_list(
 	struct xfs_mount		*mp,
 	struct list_head		*dop_list)
 {
 	struct xfs_defer_pending	*dfp;
-	const struct xfs_defer_op_type	*ops;
 
 	/* Abort intent items that don't have a done item. */
-	list_for_each_entry(dfp, dop_list, dfp_list) {
-		ops = defer_op_types[dfp->dfp_type];
-		trace_xfs_defer_pending_abort(mp, dfp);
-		if (dfp->dfp_intent && !dfp->dfp_done) {
-			ops->abort_intent(dfp->dfp_intent);
-			dfp->dfp_intent = NULL;
-		}
-	}
+	list_for_each_entry(dfp, dop_list, dfp_list)
+		xfs_defer_pending_abort(mp, dfp);
 }
 
 /* Abort all the intents that were committed. */
@@ -266,7 +296,7 @@ xfs_defer_trans_abort(
 	struct list_head		*dop_pending)
 {
 	trace_xfs_defer_trans_abort(tp, _RET_IP_);
-	xfs_defer_pending_abort(tp->t_mountp, dop_pending);
+	xfs_defer_pending_abort_list(tp->t_mountp, dop_pending);
 }
 
 /*
@@ -384,27 +414,13 @@ xfs_defer_cancel_list(
 {
 	struct xfs_defer_pending	*dfp;
 	struct xfs_defer_pending	*pli;
-	struct list_head		*pwi;
-	struct list_head		*n;
-	const struct xfs_defer_op_type	*ops;
 
 	/*
 	 * Free the pending items.  Caller should already have arranged
 	 * for the intent items to be released.
 	 */
-	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) {
-		ops = defer_op_types[dfp->dfp_type];
-		trace_xfs_defer_cancel_list(mp, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			trace_xfs_defer_cancel_item(mp, dfp, pwi);
-			ops->cancel_item(pwi);
-		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_cache_free(xfs_defer_pending_cache, dfp);
-	}
+	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list)
+		xfs_defer_pending_cancel_work(mp, dfp);
 }
 
 /*
@@ -660,6 +676,39 @@ xfs_defer_add(
 	dfp->dfp_count++;
 }
 
+/*
+ * Create a pending deferred work item to replay the recovered intent item
+ * and add it to the list.
+ */
+void
+xfs_defer_start_recovery(
+	struct xfs_log_item		*lip,
+	enum xfs_defer_ops_type		dfp_type,
+	struct list_head		*r_dfops)
+{
+	struct xfs_defer_pending	*dfp;
+
+	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	dfp->dfp_type = dfp_type;
+	dfp->dfp_intent = lip;
+	INIT_LIST_HEAD(&dfp->dfp_work);
+	list_add_tail(&dfp->dfp_list, r_dfops);
+}
+
+/*
+ * Cancel a deferred work item created to recover a log intent item.  @dfp
+ * will be freed after this function returns.
+ */
+void
+xfs_defer_cancel_recovery(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	xfs_defer_pending_abort(mp, dfp);
+	xfs_defer_pending_cancel_work(mp, dfp);
+}
+
 /*
  * Move deferred ops from one transaction to another and reset the source to
  * initial state. This is primarily used to carry state forward across
@@ -764,7 +813,7 @@ xfs_defer_ops_capture_abort(
 {
 	unsigned short			i;
 
-	xfs_defer_pending_abort(mp, &dfc->dfc_dfops);
+	xfs_defer_pending_abort_list(mp, &dfc->dfc_dfops);
 	xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
 
 	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 8788ad5f6..5dce938ba 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -125,6 +125,11 @@ void xfs_defer_ops_capture_abort(struct xfs_mount *mp,
 		struct xfs_defer_capture *d);
 void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
 
+void xfs_defer_start_recovery(struct xfs_log_item *lip,
+		enum xfs_defer_ops_type dfp_type, struct list_head *r_dfops);
+void xfs_defer_cancel_recovery(struct xfs_mount *mp,
+		struct xfs_defer_pending *dfp);
+
 int __init xfs_defer_init_item_caches(void);
 void xfs_defer_destroy_item_caches(void);
 
-- 
2.44.0

[PATCH 02/67] xfs: recreate work items when recovering intent items

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: e70fb328d5277297ea2d9169a3a046de6412d777

Recreate work items for each xfs_defer_pending object when we are
recovering intent items.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 3 +--
 libxfs/xfs_defer.h | 9 +++++++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index bd6f14a2c..4900a7d62 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -671,9 +671,8 @@ xfs_defer_add(
 		list_add_tail(&dfp->dfp_list, &tp->t_dfops);
 	}
 
-	list_add_tail(li, &dfp->dfp_work);
+	xfs_defer_add_item(dfp, li);
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
-	dfp->dfp_count++;
 }
 
 /*
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 5dce938ba..bef5823f6 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -130,6 +130,15 @@ void xfs_defer_start_recovery(struct xfs_log_item *lip,
 void xfs_defer_cancel_recovery(struct xfs_mount *mp,
 		struct xfs_defer_pending *dfp);
 
+static inline void
+xfs_defer_add_item(
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*work)
+{
+	list_add_tail(work, &dfp->dfp_work);
+	dfp->dfp_count++;
+}
+
 int __init xfs_defer_init_item_caches(void);
 void xfs_defer_destroy_item_caches(void);
 
-- 
2.44.0

[PATCH 03/67] xfs: use xfs_defer_finish_one to finish recovered work items

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: e5f1a5146ec35f3ed5d7f5ac7807a10c0062b6b8

Get rid of the open-coded calls to xfs_defer_finish_one.  This also
means that the recovery transaction takes care of cleaning up the dfp,
and we have solved (I hope) all the ownership issues in recovery.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 2 +-
 libxfs/xfs_defer.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 4900a7d62..4ef9867cc 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -479,7 +479,7 @@ xfs_defer_relog(
  * Log an intent-done item for the first pending intent, and finish the work
  * items.
  */
-static int
+int
 xfs_defer_finish_one(
 	struct xfs_trans		*tp,
 	struct xfs_defer_pending	*dfp)
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index bef5823f6..c1a648e99 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -41,6 +41,7 @@ void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
 		struct list_head *h);
 int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
+int xfs_defer_finish_one(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
 void xfs_defer_cancel(struct xfs_trans *);
 void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
-- 
2.44.0

[PATCH 04/67] xfs: move ->iop_recover to xfs_defer_op_type

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: db7ccc0bac2add5a41b66578e376b49328fc99d0

Finish off the series by moving the intent item recovery function
pointer to the xfs_defer_op_type struct, since this is really a deferred
work function now.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 include/xfs_trace.h |  2 ++
 libxfs/xfs_defer.c  | 17 +++++++++++++++++
 libxfs/xfs_defer.h  |  4 ++++
 3 files changed, 23 insertions(+)

diff --git a/include/xfs_trace.h b/include/xfs_trace.h
index 7fd446ad4..c79a4bd74 100644
--- a/include/xfs_trace.h
+++ b/include/xfs_trace.h
@@ -336,4 +336,6 @@
 
 #define trace_xfs_fs_mark_healthy(a,b)		((void) 0)
 
+#define trace_xlog_intent_recovery_failed(...)	((void) 0)
+
 #endif /* __TRACE_H__ */
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 4ef9867cc..54865b73b 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -708,6 +708,23 @@ xfs_defer_cancel_recovery(
 	xfs_defer_pending_cancel_work(mp, dfp);
 }
 
+/* Replay the deferred work item created from a recovered log intent item. */
+int
+xfs_defer_finish_recovery(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*capture_list)
+{
+	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+	int				error;
+
+	error = ops->recover_work(dfp, capture_list);
+	if (error)
+		trace_xlog_intent_recovery_failed(mp, error,
+				ops->recover_work);
+	return error;
+}
+
 /*
  * Move deferred ops from one transaction to another and reset the source to
  * initial state. This is primarily used to carry state forward across
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index c1a648e99..ef86a7f9b 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -57,6 +57,8 @@ struct xfs_defer_op_type {
 	void (*finish_cleanup)(struct xfs_trans *tp,
 			struct xfs_btree_cur *state, int error);
 	void (*cancel_item)(struct list_head *item);
+	int (*recover_work)(struct xfs_defer_pending *dfp,
+			    struct list_head *capture_list);
 	unsigned int		max_items;
 };
 
@@ -130,6 +132,8 @@ void xfs_defer_start_recovery(struct xfs_log_item *lip,
 		enum xfs_defer_ops_type dfp_type, struct list_head *r_dfops);
 void xfs_defer_cancel_recovery(struct xfs_mount *mp,
 		struct xfs_defer_pending *dfp);
+int xfs_defer_finish_recovery(struct xfs_mount *mp,
+		struct xfs_defer_pending *dfp, struct list_head *capture_list);
 
 static inline void
 xfs_defer_add_item(
-- 
2.44.0

[PATCH 05/67] xfs: hoist intent done flag setting to ->finish_item callsite

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 3dd75c8db1c1675a26d3e228bab349c1fc065867

Each log intent item's ->finish_item call chain inevitably includes some
code to set the dirty flag of the transaction.  If there's an associated
log intent done item, it also sets the item's dirty flag and the
transaction's INTENT_DONE flag.  This is repeated throughout the
codebase.

Reduce the LOC by moving all that to xfs_defer_finish_one.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 54865b73b..6a9ce9241 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -186,6 +186,32 @@ static const struct xfs_defer_op_type *defer_op_types[] = {
 	[XFS_DEFER_OPS_TYPE_ATTR]	= &xfs_attr_defer_type,
 };
 
+/* Create a log intent done item for a log intent item. */
+static inline void
+xfs_defer_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+	struct xfs_log_item		*lip;
+
+	/*
+	 * Mark the transaction dirty, even on error. This ensures the
+	 * transaction is aborted, which:
+	 *
+	 * 1.) releases the log intent item and frees the log done item
+	 * 2.) shuts down the filesystem
+	 */
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	lip = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+	if (!lip)
+		return;
+
+	tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE;
+	set_bit(XFS_LI_DIRTY, &lip->li_flags);
+	dfp->dfp_done = lip;
+}
+
 /*
  * Ensure there's a log intent item associated with this deferred work item if
  * the operation must be restarted on crash.  Returns 1 if there's a log item;
@@ -491,7 +517,7 @@ xfs_defer_finish_one(
 
 	trace_xfs_defer_pending_finish(tp->t_mountp, dfp);
 
-	dfp->dfp_done = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+	xfs_defer_create_done(tp, dfp);
 	list_for_each_safe(li, n, &dfp->dfp_work) {
 		list_del(li);
 		dfp->dfp_count--;
-- 
2.44.0

[PATCH 06/67] xfs: hoist ->create_intent boilerplate to its callsite

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: f3fd7f6fce1cc9b8eb59705b27f823330207b7c9

Hoist the dirty flag setting code out of each ->create_intent
implementation up to the callsite to reduce boilerplate further.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 6a9ce9241..1be9554e1 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -235,6 +235,8 @@ xfs_defer_create_intent(
 	if (IS_ERR(lip))
 		return PTR_ERR(lip);
 
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	set_bit(XFS_LI_DIRTY, &lip->li_flags);
 	dfp->dfp_intent = lip;
 	return 1;
 }
-- 
2.44.0

[PATCH 07/67] xfs: use xfs_defer_create_done for the relogging operation

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: bd3a88f6b71c7509566b44b7021581191cc11ae3

Now that we have a helper to handle creating a log intent done item and
updating all the necessary state flags, use it to reduce boilerplate in
the ->iop_relog implementations.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 include/xfs_trans.h | 2 +-
 libxfs/xfs_defer.c  | 6 +++++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/xfs_trans.h b/include/xfs_trans.h
index 8371bc7e8..b39f0c22d 100644
--- a/include/xfs_trans.h
+++ b/include/xfs_trans.h
@@ -158,7 +158,7 @@ libxfs_trans_read_buf(
 }
 
 #define xfs_log_item_in_current_chkpt(lip)	(false)
-#define xfs_trans_item_relog(lip, tp)		(NULL)
+#define xfs_trans_item_relog(lip, dip, tp)	(NULL)
 
 /* Contorted mess to make gcc shut up about unused vars. */
 #define xlog_grant_push_threshold(log, need)    \
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 1be9554e1..43117099c 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -495,7 +495,11 @@ xfs_defer_relog(
 
 		trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp);
 		XFS_STATS_INC((*tpp)->t_mountp, defer_relog);
-		dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp);
+
+		xfs_defer_create_done(*tpp, dfp);
+		dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent,
+				dfp->dfp_done, *tpp);
+		dfp->dfp_done = NULL;
 	}
 
 	if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
-- 
2.44.0

[PATCH 08/67] xfs: clean out XFS_LI_DIRTY setting boilerplate from ->iop_relog

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 3e0958be2156d90ef908a1a547b4e27a3ec38da9

Hoist this dirty flag setting to the ->iop_relog callsite to reduce
boilerplate.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 43117099c..42e1c9c0c 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -469,6 +469,8 @@ xfs_defer_relog(
 	ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
 	list_for_each_entry(dfp, dfops, dfp_list) {
+		struct xfs_log_item	*lip;
+
 		/*
 		 * If the log intent item for this deferred op is not a part of
 		 * the current log checkpoint, relog the intent item to keep
@@ -497,9 +499,12 @@ xfs_defer_relog(
 		XFS_STATS_INC((*tpp)->t_mountp, defer_relog);
 
 		xfs_defer_create_done(*tpp, dfp);
-		dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent,
-				dfp->dfp_done, *tpp);
+		lip = xfs_trans_item_relog(dfp->dfp_intent, dfp->dfp_done,
+				*tpp);
+		if (lip)
+			set_bit(XFS_LI_DIRTY, &lip->li_flags);
 		dfp->dfp_done = NULL;
+		dfp->dfp_intent = lip;
 	}
 
 	if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
-- 
2.44.0

[PATCH 09/67] xfs: hoist xfs_trans_add_item calls to defer ops functions

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: b28852a5bd08654634e4e32eb072fba14c5fae26

Remove even more repeated boilerplate.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 42e1c9c0c..27f9938a0 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -208,6 +208,7 @@ xfs_defer_create_done(
 		return;
 
 	tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE;
+	xfs_trans_add_item(tp, lip);
 	set_bit(XFS_LI_DIRTY, &lip->li_flags);
 	dfp->dfp_done = lip;
 }
@@ -236,6 +237,7 @@ xfs_defer_create_intent(
 		return PTR_ERR(lip);
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
+	xfs_trans_add_item(tp, lip);
 	set_bit(XFS_LI_DIRTY, &lip->li_flags);
 	dfp->dfp_intent = lip;
 	return 1;
@@ -501,8 +503,10 @@ xfs_defer_relog(
 		xfs_defer_create_done(*tpp, dfp);
 		lip = xfs_trans_item_relog(dfp->dfp_intent, dfp->dfp_done,
 				*tpp);
-		if (lip)
+		if (lip) {
+			xfs_trans_add_item(*tpp, lip);
 			set_bit(XFS_LI_DIRTY, &lip->li_flags);
+		}
 		dfp->dfp_done = NULL;
 		dfp->dfp_intent = lip;
 	}
-- 
2.44.0

[PATCH 10/67] xfs: move ->iop_relog to struct xfs_defer_op_type

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: a49c708f9a445457f6a5905732081871234f61c6

The only log items that need relogging are the ones created for deferred
work operations, and the only part of the code base that relogs log
items is the deferred work machinery.  Move the function pointers.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 include/xfs_trans.h |  1 -
 libxfs/xfs_defer.c  | 31 ++++++++++++++++++++-----------
 libxfs/xfs_defer.h  |  3 +++
 3 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/include/xfs_trans.h b/include/xfs_trans.h
index b39f0c22d..ab298ccfe 100644
--- a/include/xfs_trans.h
+++ b/include/xfs_trans.h
@@ -158,7 +158,6 @@ libxfs_trans_read_buf(
 }
 
 #define xfs_log_item_in_current_chkpt(lip)	(false)
-#define xfs_trans_item_relog(lip, dip, tp)	(NULL)
 
 /* Contorted mess to make gcc shut up about unused vars. */
 #define xlog_grant_push_threshold(log, need)    \
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 27f9938a0..29ec0bd81 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -453,6 +453,25 @@ xfs_defer_cancel_list(
 		xfs_defer_pending_cancel_work(mp, dfp);
 }
 
+static inline void
+xfs_defer_relog_intent(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	struct xfs_log_item		*lip;
+	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+
+	xfs_defer_create_done(tp, dfp);
+
+	lip = ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done);
+	if (lip) {
+		xfs_trans_add_item(tp, lip);
+		set_bit(XFS_LI_DIRTY, &lip->li_flags);
+	}
+	dfp->dfp_done = NULL;
+	dfp->dfp_intent = lip;
+}
+
 /*
  * Prevent a log intent item from pinning the tail of the log by logging a
  * done item to release the intent item; and then log a new intent item.
@@ -471,8 +490,6 @@ xfs_defer_relog(
 	ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
 	list_for_each_entry(dfp, dfops, dfp_list) {
-		struct xfs_log_item	*lip;
-
 		/*
 		 * If the log intent item for this deferred op is not a part of
 		 * the current log checkpoint, relog the intent item to keep
@@ -500,15 +517,7 @@ xfs_defer_relog(
 		trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp);
 		XFS_STATS_INC((*tpp)->t_mountp, defer_relog);
 
-		xfs_defer_create_done(*tpp, dfp);
-		lip = xfs_trans_item_relog(dfp->dfp_intent, dfp->dfp_done,
-				*tpp);
-		if (lip) {
-			xfs_trans_add_item(*tpp, lip);
-			set_bit(XFS_LI_DIRTY, &lip->li_flags);
-		}
-		dfp->dfp_done = NULL;
-		dfp->dfp_intent = lip;
+		xfs_defer_relog_intent(*tpp, dfp);
 	}
 
 	if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index ef86a7f9b..78d6dcd1a 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -59,6 +59,9 @@ struct xfs_defer_op_type {
 	void (*cancel_item)(struct list_head *item);
 	int (*recover_work)(struct xfs_defer_pending *dfp,
 			    struct list_head *capture_list);
+	struct xfs_log_item *(*relog_intent)(struct xfs_trans *tp,
+			struct xfs_log_item *intent,
+			struct xfs_log_item *done_item);
 	unsigned int		max_items;
 };
 
-- 
2.44.0

[PATCH 11/67] xfs: make rextslog computation consistent with mkfs

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: a6a38f309afc4a7ede01242b603f36c433997780

There's a weird discrepancy in xfsprogs dating back to the creation of
the Linux port -- if there are zero rt extents, mkfs will set
sb_rextents and sb_rextslog both to zero:

sbp->sb_rextslog =
(uint8_t)(rtextents ?
libxfs_highbit32((unsigned int)rtextents) : 0);

However, that's not the check that xfs_repair uses for nonzero rtblocks:

if (sb->sb_rextslog !=
libxfs_highbit32((unsigned int)sb->sb_rextents))

The difference here is that xfs_highbit32 returns -1 if its argument is
zero.  Unfortunately, this means that in the weird corner case of a
realtime volume shorter than 1 rt extent, xfs_repair will immediately
flag a freshly formatted filesystem as corrupt.  Because mkfs has been
writing ondisk artifacts like this for decades, we have to accept that
as "correct".  TBH, zero rextslog for zero rtextents makes more sense to
me anyway.

Regrettably, the superblock verifier checks created in commit copied
xfs_repair even though mkfs has been writing out such filesystems for
ages.  Fix the superblock verifier to accept what mkfs spits out; the
userspace version of this patch will have to fix xfs_repair as well.

Note that the new helper leaves the zeroday bug where the upper 32 bits
of sb_rextents is ripped off and fed to highbit32.  This leads to a
seriously undersized rt summary file, which immediately breaks mkfs:

$ hugedisk.sh foo /dev/sdc $(( 0x100000080 * 4096))B
$ /sbin/mkfs.xfs -f /dev/sda -m rmapbt=0,reflink=0 -r rtdev=/dev/mapper/foo
meta-data=/dev/sda               isize=512    agcount=4, agsize=1298176 blks
=                       sectsz=512   attr=2, projid32bit=1
=                       crc=1        finobt=1, sparse=1, rmapbt=0
=                       reflink=0    bigtime=1 inobtcount=1 nrext64=1
data     =                       bsize=4096   blocks=5192704, imaxpct=25
=                       sunit=0      swidth=0 blks
naming   =version 2              bsize=4096   ascii-ci=0, ftype=1
log      =internal log           bsize=4096   blocks=16384, version=2
=                       sectsz=512   sunit=0 blks, lazy-count=1
realtime =/dev/mapper/foo        extsz=4096   blocks=4294967424, rtextents=4294967424
Discarding blocks...Done.
mkfs.xfs: Error initializing the realtime space [117 - Structure needs cleaning]

The next patch will drop support for rt volumes with fewer than 1 or
more than 2^32-1 rt extents, since they've clearly been broken forever.

Fixes: f8e566c0f5e1f ("xfs: validate the realtime geometry in xfs_validate_sb_common")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/libxfs_api_defs.h |  1 +
 libxfs/xfs_rtbitmap.c    | 12 ++++++++++++
 libxfs/xfs_rtbitmap.h    |  3 +++
 libxfs/xfs_sb.c          |  3 ++-
 mkfs/xfs_mkfs.c          |  3 +--
 repair/sb.c              |  3 +--
 6 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index a16efa007..836ace1ba 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -64,6 +64,7 @@
 #define xfs_bunmapi			libxfs_bunmapi
 #define xfs_bwrite			libxfs_bwrite
 #define xfs_calc_dquots_per_chunk	libxfs_calc_dquots_per_chunk
+#define xfs_compute_rextslog		libxfs_compute_rextslog
 #define xfs_da3_node_hdr_from_disk	libxfs_da3_node_hdr_from_disk
 #define xfs_da_get_buf			libxfs_da_get_buf
 #define xfs_da_hashname			libxfs_da_hashname
diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index fb0834990..90fe90288 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -1128,6 +1128,18 @@ xfs_rtbitmap_blockcount(
 	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
 }
 
+/*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs.  The use of highbit32 on a 64-bit quantity is a historic artifact that
+ * prohibits correct use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+	xfs_rtbxlen_t		rtextents)
+{
+	return rtextents ? xfs_highbit32(rtextents) : 0;
+}
+
 /*
  * Compute the number of rtbitmap words needed to populate every block of a
  * bitmap that is large enough to track the given number of rt extents.
diff --git a/libxfs/xfs_rtbitmap.h b/libxfs/xfs_rtbitmap.h
index c0637057d..6e5bae324 100644
--- a/libxfs/xfs_rtbitmap.h
+++ b/libxfs/xfs_rtbitmap.h
@@ -351,6 +351,8 @@ xfs_rtfree_extent(
 int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
 		xfs_filblks_t rtlen);
 
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -369,6 +371,7 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
 # define xfs_rtsummary_read_buf(a,b)			(-ENOSYS)
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
+# define xfs_compute_rextslog(rtx)			(0)
 static inline xfs_filblks_t
 xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
diff --git a/libxfs/xfs_sb.c b/libxfs/xfs_sb.c
index 1ebdb7ec4..95a29bf1f 100644
--- a/libxfs/xfs_sb.c
+++ b/libxfs/xfs_sb.c
@@ -23,6 +23,7 @@
 #include "xfs_da_format.h"
 #include "xfs_health.h"
 #include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -507,7 +508,7 @@ xfs_validate_sb_common(
 				       NBBY * sbp->sb_blocksize);
 
 		if (sbp->sb_rextents != rexts ||
-		    sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) ||
+		    sbp->sb_rextslog != xfs_compute_rextslog(rexts) ||
 		    sbp->sb_rbmblocks != rbmblocks) {
 			xfs_notice(mp,
 				"realtime geometry sanity check failed");
diff --git a/mkfs/xfs_mkfs.c b/mkfs/xfs_mkfs.c
index fcbf54132..e48624bbd 100644
--- a/mkfs/xfs_mkfs.c
+++ b/mkfs/xfs_mkfs.c
@@ -3693,8 +3693,7 @@ finish_superblock_setup(
 	sbp->sb_agcount = (xfs_agnumber_t)cfg->agcount;
 	sbp->sb_rbmblocks = cfg->rtbmblocks;
 	sbp->sb_logblocks = (xfs_extlen_t)cfg->logblocks;
-	sbp->sb_rextslog = (uint8_t)(cfg->rtextents ?
-			libxfs_highbit32((unsigned int)cfg->rtextents) : 0);
+	sbp->sb_rextslog = libxfs_compute_rextslog(cfg->rtextents);
 	sbp->sb_inprogress = 1;	/* mkfs is in progress */
 	sbp->sb_imax_pct = cfg->imaxpct;
 	sbp->sb_icount = 0;
diff --git a/repair/sb.c b/repair/sb.c
index dedac53af..384840db1 100644
--- a/repair/sb.c
+++ b/repair/sb.c
@@ -475,8 +475,7 @@ verify_sb(char *sb_buf, xfs_sb_t *sb, int is_primary_sb)
 		if (sb->sb_rblocks / sb->sb_rextsize != sb->sb_rextents)
 			return(XR_BAD_RT_GEO_DATA);
 
-		if (sb->sb_rextslog !=
-				libxfs_highbit32((unsigned int)sb->sb_rextents))
+		if (sb->sb_rextslog != libxfs_compute_rextslog(sb->sb_rextents))
 			return(XR_BAD_RT_GEO_DATA);
 
 		if (sb->sb_rbmblocks != (xfs_extlen_t) howmany(sb->sb_rextents,
-- 
2.44.0

[PATCH 12/67] xfs: fix 32-bit truncation in xfs_compute_rextslog

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: cf8f0e6c1429be7652869059ea44696b72d5b726

It's quite reasonable that some customer somewhere will want to
configure a realtime volume with more than 2^32 extents.  If they try to
do this, the highbit32() call will truncate the upper bits of the
xfs_rtbxlen_t and produce the wrong value for rextslog.  This in turn
causes the rsumlevels to be wrong, which results in a realtime summary
file that is the wrong length.  Fix that.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_rtbitmap.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index 90fe90288..726543abb 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -1130,14 +1130,16 @@ xfs_rtbitmap_blockcount(
 
 /*
  * Compute the maximum level number of the realtime summary file, as defined by
- * mkfs.  The use of highbit32 on a 64-bit quantity is a historic artifact that
- * prohibits correct use of rt volumes with more than 2^32 extents.
+ * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
  */
 uint8_t
 xfs_compute_rextslog(
 	xfs_rtbxlen_t		rtextents)
 {
-	return rtextents ? xfs_highbit32(rtextents) : 0;
+	if (!rtextents)
+		return 0;
+	return xfs_highbit64(rtextents);
 }
 
 /*
-- 
2.44.0

[PATCH 13/67] xfs: don't allow overly small or large realtime volumes

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: e14293803f4e84eb23a417b462b56251033b5a66

Don't allow realtime volumes that are less than one rt extent long.
This has been broken across 4 LTS kernels with nobody noticing, so let's
just disable it.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_rtbitmap.h | 13 +++++++++++++
 libxfs/xfs_sb.c       |  3 ++-
 mkfs/xfs_mkfs.c       |  6 ++++++
 repair/sb.c           |  3 +++
 4 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/libxfs/xfs_rtbitmap.h b/libxfs/xfs_rtbitmap.h
index 6e5bae324..1c84b52de 100644
--- a/libxfs/xfs_rtbitmap.h
+++ b/libxfs/xfs_rtbitmap.h
@@ -353,6 +353,18 @@ int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
 
 uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
 
+/* Do we support an rt volume having this number of rtextents? */
+static inline bool
+xfs_validate_rtextents(
+	xfs_rtbxlen_t		rtextents)
+{
+	/* No runt rt volumes */
+	if (rtextents == 0)
+		return false;
+
+	return true;
+}
+
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -372,6 +384,7 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
 # define xfs_compute_rextslog(rtx)			(0)
+# define xfs_validate_rtextents(rtx)			(false)
 static inline xfs_filblks_t
 xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
diff --git a/libxfs/xfs_sb.c b/libxfs/xfs_sb.c
index 95a29bf1f..7a72d5a17 100644
--- a/libxfs/xfs_sb.c
+++ b/libxfs/xfs_sb.c
@@ -507,7 +507,8 @@ xfs_validate_sb_common(
 		rbmblocks = howmany_64(sbp->sb_rextents,
 				       NBBY * sbp->sb_blocksize);
 
-		if (sbp->sb_rextents != rexts ||
+		if (!xfs_validate_rtextents(rexts) ||
+		    sbp->sb_rextents != rexts ||
 		    sbp->sb_rextslog != xfs_compute_rextslog(rexts) ||
 		    sbp->sb_rbmblocks != rbmblocks) {
 			xfs_notice(mp,
diff --git a/mkfs/xfs_mkfs.c b/mkfs/xfs_mkfs.c
index e48624bbd..d19f2a2fb 100644
--- a/mkfs/xfs_mkfs.c
+++ b/mkfs/xfs_mkfs.c
@@ -3025,6 +3025,12 @@ reported by the device (%u).\n"),
 	}
 
 	cfg->rtextents = cfg->rtblocks / cfg->rtextblocks;
+	if (cfg->rtextents == 0) {
+		fprintf(stderr,
+_("cannot have a rt subvolume with zero extents\n"));
+		usage();
+	}
+
 	cfg->rtbmblocks = (xfs_extlen_t)howmany(cfg->rtextents,
 						NBBY * cfg->blocksize);
 }
diff --git a/repair/sb.c b/repair/sb.c
index 384840db1..a26fc149f 100644
--- a/repair/sb.c
+++ b/repair/sb.c
@@ -475,6 +475,9 @@ verify_sb(char *sb_buf, xfs_sb_t *sb, int is_primary_sb)
 		if (sb->sb_rblocks / sb->sb_rextsize != sb->sb_rextents)
 			return(XR_BAD_RT_GEO_DATA);
 
+		if (sb->sb_rextents == 0)
+			return(XR_BAD_RT_GEO_DATA);
+
 		if (sb->sb_rextslog != libxfs_compute_rextslog(sb->sb_rextents))
 			return(XR_BAD_RT_GEO_DATA);
 
-- 
2.44.0

[PATCH 14/67] xfs: elide ->create_done calls for unlogged deferred work

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 9c07bca793b4ff9f0b7871e2a928a1b28b8fa4e3

Extended attribute updates use the deferred work machinery to manage
state across a chain of smaller transactions.  All previous deferred
work users have employed log intent items and log done items to manage
restarting of interrupted operations, which means that ->create_intent
sets dfp_intent to a log intent item and ->create_done uses that item to
create a log intent done item.

However, xattrs have used the INCOMPLETE flag to deal with the lack of
recovery support for an interrupted transaction chain.  Log items are
optional if the xattr update caller didn't set XFS_DA_OP_LOGGED to
require a restartable sequence.

In other words, ->create_intent can return NULL to say that there's no
log intent item.  If that's the case, no log intent done item should be
created.  Clean up xfs_defer_create_done not to do this, so that the
->create_done functions don't have to check for non-null dfp_intent
themselves.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 29ec0bd81..722ff6a77 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -195,6 +195,10 @@ xfs_defer_create_done(
 	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 	struct xfs_log_item		*lip;
 
+	/* If there is no log intent item, there can be no log done item. */
+	if (!dfp->dfp_intent)
+		return;
+
 	/*
 	 * Mark the transaction dirty, even on error. This ensures the
 	 * transaction is aborted, which:
-- 
2.44.0

[PATCH 15/67] xfs: don't append work items to logged xfs_defer_pending objects

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 6b126139401a2284402d7c38fe3168d5a26da41d

When someone tries to add a deferred work item to xfs_defer_add, it will
try to attach the work item to the most recently added xfs_defer_pending
object attached to the transaction.  However, it doesn't check if the
pending object has a log intent item attached to it.  This is incorrect
behavior because we cannot add more work to an object that has already
been committed to the ondisk log.

Therefore, change the behavior not to append to pending items with a non
null dfp_intent.  In practice this has not been an issue because the
only way xfs_defer_add gets called after log intent items have been
the @dop_pending isolation in xfs_defer_finish_noroll protects the
pending items that have already been logged.

However, the next patch will add the ability to pause a deferred extent
free object during online btree rebuilding, and any new extfree work
items need to have their own pending event.

While we're at it, hoist the predicate to its own static inline function
for readability.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 61 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 48 insertions(+), 13 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 722ff6a77..200d1b300 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -689,6 +689,51 @@ xfs_defer_cancel(
 	xfs_defer_cancel_list(mp, &tp->t_dfops);
 }
 
+/*
+ * Return the last pending work item attached to this transaction if it matches
+ * the deferred op type.
+ */
+static inline struct xfs_defer_pending *
+xfs_defer_find_last(
+	struct xfs_trans		*tp,
+	enum xfs_defer_ops_type		type,
+	const struct xfs_defer_op_type	*ops)
+{
+	struct xfs_defer_pending	*dfp = NULL;
+
+	/* No dfops at all? */
+	if (list_empty(&tp->t_dfops))
+		return NULL;
+
+	dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending,
+			dfp_list);
+
+	/* Wrong type? */
+	if (dfp->dfp_type != type)
+		return NULL;
+	return dfp;
+}
+
+/*
+ * Decide if we can add a deferred work item to the last dfops item attached
+ * to the transaction.
+ */
+static inline bool
+xfs_defer_can_append(
+	struct xfs_defer_pending	*dfp,
+	const struct xfs_defer_op_type	*ops)
+{
+	/* Already logged? */
+	if (dfp->dfp_intent)
+		return false;
+
+	/* Already full? */
+	if (ops->max_items && dfp->dfp_count >= ops->max_items)
+		return false;
+
+	return true;
+}
+
 /* Add an item for later deferred processing. */
 void
 xfs_defer_add(
@@ -702,19 +747,9 @@ xfs_defer_add(
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
 
-	/*
-	 * Add the item to a pending item at the end of the intake list.
-	 * If the last pending item has the same type, reuse it.  Else,
-	 * create a new pending item at the end of the intake list.
-	 */
-	if (!list_empty(&tp->t_dfops)) {
-		dfp = list_last_entry(&tp->t_dfops,
-				struct xfs_defer_pending, dfp_list);
-		if (dfp->dfp_type != type ||
-		    (ops->max_items && dfp->dfp_count >= ops->max_items))
-			dfp = NULL;
-	}
-	if (!dfp) {
+	dfp = xfs_defer_find_last(tp, type, ops);
+	if (!dfp || !xfs_defer_can_append(dfp, ops)) {
+		/* Create a new pending item at the end of the intake list. */
 		dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
 				GFP_NOFS | __GFP_NOFAIL);
 		dfp->dfp_type = type;
-- 
2.44.0

[PATCH 16/67] xfs: allow pausing of pending deferred work items

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 4dffb2cbb4839fd6f9bbac0b3fd06cc9015cbb9b

Traditionally, all pending deferred work attached to a transaction is
finished when one of the xfs_defer_finish* functions is called.
However, online repair wants to be able to allocate space for a new data
structure, format a new metadata structure into the allocated space, and

As a hedge against system crashes during repairs, we also want to log
some EFI items for the allocated space speculatively, and cancel them if
we elect to commit the new data structure.

Therefore, introduce the idea of pausing a pending deferred work item.
Log intent items are still created for paused items and relogged as
necessary.  However, paused items are pushed onto a side list before we
start calling ->finish_item, and the whole list is reattach to the
transaction afterwards.  New work items are never attached to paused
pending items.

Modify xfs_defer_cancel to clean up pending deferred work items holding
a log intent item but not a log intent done item, since that is now
possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 include/list.h      |  6 +++
 include/xfs_trace.h |  3 ++
 libxfs/xfs_defer.c  | 97 +++++++++++++++++++++++++++++++++++++++------
 libxfs/xfs_defer.h  | 17 +++++++-
 4 files changed, 109 insertions(+), 14 deletions(-)

diff --git a/include/list.h b/include/list.h
index e59cbd537..52b53c7a3 100644
--- a/include/list.h
+++ b/include/list.h
@@ -152,6 +152,12 @@ static inline void list_splice_init(struct list_head *list,
 #define list_first_entry(ptr, type, member) \
 	list_entry((ptr)->next, type, member)
 
+#define list_first_entry_or_null(ptr, type, member) ({ \
+	struct list_head *head__ = (ptr); \
+	struct list_head *pos__ = READ_ONCE(head__->next); \
+	pos__ != head__ ? list_entry(pos__, type, member) : NULL; \
+})
+
 #define container_of(ptr, type, member) ({			\
 	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
 	(type *)( (char *)__mptr - offsetof(type,member) );})
diff --git a/include/xfs_trace.h b/include/xfs_trace.h
index c79a4bd74..06d6aa950 100644
--- a/include/xfs_trace.h
+++ b/include/xfs_trace.h
@@ -337,5 +337,8 @@
 #define trace_xfs_fs_mark_healthy(a,b)		((void) 0)
 
 #define trace_xlog_intent_recovery_failed(...)	((void) 0)
+#define trace_xfs_defer_isolate_paused(...)	((void) 0)
+#define trace_xfs_defer_item_pause(...)		((void) 0)
+#define trace_xfs_defer_item_unpause(...)	((void) 0)
 
 #endif /* __TRACE_H__ */
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 200d1b300..58ad1881d 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -481,7 +481,7 @@ xfs_defer_relog_intent(
  * done item to release the intent item; and then log a new intent item.
  * The caller should provide a fresh transaction and roll it after we're done.
  */
-static int
+static void
 xfs_defer_relog(
 	struct xfs_trans		**tpp,
 	struct list_head		*dfops)
@@ -523,10 +523,6 @@ xfs_defer_relog(
 
 		xfs_defer_relog_intent(*tpp, dfp);
 	}
-
-	if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
-		return xfs_defer_trans_roll(tpp);
-	return 0;
 }
 
 /*
@@ -582,6 +578,24 @@ out:
 	return error;
 }
 
+/* Move all paused deferred work from @tp to @paused_list. */
+static void
+xfs_defer_isolate_paused(
+	struct xfs_trans		*tp,
+	struct list_head		*paused_list)
+{
+	struct xfs_defer_pending	*dfp;
+	struct xfs_defer_pending	*pli;
+
+	list_for_each_entry_safe(dfp, pli, &tp->t_dfops, dfp_list) {
+		if (!(dfp->dfp_flags & XFS_DEFER_PAUSED))
+			continue;
+
+		list_move_tail(&dfp->dfp_list, paused_list);
+		trace_xfs_defer_isolate_paused(tp->t_mountp, dfp);
+	}
+}
+
 /*
  * Finish all the pending work.  This involves logging intent items for
  * any work items that wandered in since the last transaction roll (if
@@ -597,6 +611,7 @@ xfs_defer_finish_noroll(
 	struct xfs_defer_pending	*dfp = NULL;
 	int				error = 0;
 	LIST_HEAD(dop_pending);
+	LIST_HEAD(dop_paused);
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
@@ -615,6 +630,8 @@ xfs_defer_finish_noroll(
 		 */
 		int has_intents = xfs_defer_create_intents(*tp);
 
+		xfs_defer_isolate_paused(*tp, &dop_paused);
+
 		list_splice_init(&(*tp)->t_dfops, &dop_pending);
 
 		if (has_intents < 0) {
@@ -627,22 +644,33 @@ xfs_defer_finish_noroll(
 				goto out_shutdown;
 
 			/* Relog intent items to keep the log moving. */
-			error = xfs_defer_relog(tp, &dop_pending);
-			if (error)
-				goto out_shutdown;
+			xfs_defer_relog(tp, &dop_pending);
+			xfs_defer_relog(tp, &dop_paused);
+
+			if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+				error = xfs_defer_trans_roll(tp);
+				if (error)
+					goto out_shutdown;
+			}
 		}
 
-		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
-				       dfp_list);
+		dfp = list_first_entry_or_null(&dop_pending,
+				struct xfs_defer_pending, dfp_list);
+		if (!dfp)
+			break;
 		error = xfs_defer_finish_one(*tp, dfp);
 		if (error && error != -EAGAIN)
 			goto out_shutdown;
 	}
 
+	/* Requeue the paused items in the outgoing transaction. */
+	list_splice_tail_init(&dop_paused, &(*tp)->t_dfops);
+
 	trace_xfs_defer_finish_done(*tp, _RET_IP_);
 	return 0;
 
 out_shutdown:
+	list_splice_tail_init(&dop_paused, &dop_pending);
 	xfs_defer_trans_abort(*tp, &dop_pending);
 	xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
 	trace_xfs_defer_finish_error(*tp, error);
@@ -655,6 +683,9 @@ int
 xfs_defer_finish(
 	struct xfs_trans	**tp)
 {
+#ifdef DEBUG
+	struct xfs_defer_pending *dfp;
+#endif
 	int			error;
 
 	/*
@@ -674,7 +705,10 @@ xfs_defer_finish(
 	}
 
 	/* Reset LOWMODE now that we've finished all the dfops. */
-	ASSERT(list_empty(&(*tp)->t_dfops));
+#ifdef DEBUG
+	list_for_each_entry(dfp, &(*tp)->t_dfops, dfp_list)
+		ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+#endif
 	(*tp)->t_flags &= ~XFS_TRANS_LOWMODE;
 	return 0;
 }
@@ -686,6 +720,7 @@ xfs_defer_cancel(
 	struct xfs_mount	*mp = tp->t_mountp;
 
 	trace_xfs_defer_cancel(tp, _RET_IP_);
+	xfs_defer_trans_abort(tp, &tp->t_dfops);
 	xfs_defer_cancel_list(mp, &tp->t_dfops);
 }
 
@@ -727,6 +762,10 @@ xfs_defer_can_append(
 	if (dfp->dfp_intent)
 		return false;
 
+	/* Paused items cannot absorb more work */
+	if (dfp->dfp_flags & XFS_DEFER_PAUSED)
+		return NULL;
+
 	/* Already full? */
 	if (ops->max_items && dfp->dfp_count >= ops->max_items)
 		return false;
@@ -735,7 +774,7 @@ xfs_defer_can_append(
 }
 
 /* Add an item for later deferred processing. */
-void
+struct xfs_defer_pending *
 xfs_defer_add(
 	struct xfs_trans		*tp,
 	enum xfs_defer_ops_type		type,
@@ -762,6 +801,7 @@ xfs_defer_add(
 
 	xfs_defer_add_item(dfp, li);
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
+	return dfp;
 }
 
 /*
@@ -1087,3 +1127,36 @@ xfs_defer_destroy_item_caches(void)
 	xfs_rmap_intent_destroy_cache();
 	xfs_defer_destroy_cache();
 }
+
+/*
+ * Mark a deferred work item so that it will be requeued indefinitely without
+ * being finished.  Caller must ensure there are no data dependencies on this
+ * work item in the meantime.
+ */
+void
+xfs_defer_item_pause(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	ASSERT(!(dfp->dfp_flags & XFS_DEFER_PAUSED));
+
+	dfp->dfp_flags |= XFS_DEFER_PAUSED;
+
+	trace_xfs_defer_item_pause(tp->t_mountp, dfp);
+}
+
+/*
+ * Release a paused deferred work item so that it will be finished during the
+ * next transaction roll.
+ */
+void
+xfs_defer_item_unpause(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+
+	dfp->dfp_flags &= ~XFS_DEFER_PAUSED;
+
+	trace_xfs_defer_item_unpause(tp->t_mountp, dfp);
+}
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 78d6dcd1a..b0284154f 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -34,11 +34,24 @@ struct xfs_defer_pending {
 	struct xfs_log_item		*dfp_intent;	/* log intent item */
 	struct xfs_log_item		*dfp_done;	/* log done item */
 	unsigned int			dfp_count;	/* # extent items */
+	unsigned int			dfp_flags;
 	enum xfs_defer_ops_type		dfp_type;
 };
 
-void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
-		struct list_head *h);
+/*
+ * Create a log intent item for this deferred item, but don't actually finish
+ * the work.  Caller must clear this before the final transaction commit.
+ */
+#define XFS_DEFER_PAUSED	(1U << 0)
+
+#define XFS_DEFER_PENDING_STRINGS \
+	{ XFS_DEFER_PAUSED,	"paused" }
+
+void xfs_defer_item_pause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
+void xfs_defer_item_unpause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
+
+struct xfs_defer_pending *xfs_defer_add(struct xfs_trans *tp,
+		enum xfs_defer_ops_type type, struct list_head *h);
 int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
 int xfs_defer_finish_one(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
-- 
2.44.0

[PATCH 17/67] xfs: remove __xfs_free_extent_later

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 4c88fef3af4a51c2cdba6a28237e98da4873e8dc

xfs_free_extent_later is a trivial helper, so remove it to reduce the
amount of thinking required to understand the deferred freeing
interface.  This will make it easier to introduce automatic reaping of
speculative allocations in the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_ag.c             |  2 +-
 libxfs/xfs_alloc.c          |  2 +-
 libxfs/xfs_alloc.h          | 14 +-------------
 libxfs/xfs_bmap.c           |  4 ++--
 libxfs/xfs_bmap_btree.c     |  2 +-
 libxfs/xfs_ialloc.c         |  5 +++--
 libxfs/xfs_ialloc_btree.c   |  2 +-
 libxfs/xfs_refcount.c       |  6 +++---
 libxfs/xfs_refcount_btree.c |  2 +-
 9 files changed, 14 insertions(+), 25 deletions(-)

diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index ac34a1c23..bdb8a08bb 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -982,7 +982,7 @@ xfs_ag_shrink_space(
 		if (err2 != -ENOSPC)
 			goto resv_err;
 
-		err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
+		err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
 				XFS_AG_RESV_NONE, true);
 		if (err2)
 			goto resv_err;
diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index 7ac7c2f6c..0a2404466 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -2519,7 +2519,7 @@ xfs_defer_agfl_block(
  * The list is maintained sorted (by block number).
  */
 int
-__xfs_free_extent_later(
+xfs_free_extent_later(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
diff --git a/libxfs/xfs_alloc.h b/libxfs/xfs_alloc.h
index 6bb8d295c..6b95d1d8a 100644
--- a/libxfs/xfs_alloc.h
+++ b/libxfs/xfs_alloc.h
@@ -231,7 +231,7 @@ xfs_buf_to_agfl_bno(
 	return bp->b_addr;
 }
 
-int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
+int xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
 		xfs_filblks_t len, const struct xfs_owner_info *oinfo,
 		enum xfs_ag_resv_type type, bool skip_discard);
 
@@ -256,18 +256,6 @@ void xfs_extent_free_get_group(struct xfs_mount *mp,
 #define XFS_EFI_ATTR_FORK	(1U << 1) /* freeing attr fork block */
 #define XFS_EFI_BMBT_BLOCK	(1U << 2) /* freeing bmap btree block */
 
-static inline int
-xfs_free_extent_later(
-	struct xfs_trans		*tp,
-	xfs_fsblock_t			bno,
-	xfs_filblks_t			len,
-	const struct xfs_owner_info	*oinfo,
-	enum xfs_ag_resv_type		type)
-{
-	return __xfs_free_extent_later(tp, bno, len, oinfo, type, false);
-}
-
-
 extern struct kmem_cache	*xfs_extfree_item_cache;
 
 int __init xfs_extfree_intent_init_cache(void);
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 8fde0dc25..8c553d22c 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -569,7 +569,7 @@ xfs_bmap_btree_to_extents(
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
 	error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo,
-			XFS_AG_RESV_NONE);
+			XFS_AG_RESV_NONE, false);
 	if (error)
 		return error;
 
@@ -5212,7 +5212,7 @@ xfs_bmap_del_extent_real(
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
 			xfs_refcount_decrease_extent(tp, del);
 		} else {
-			error = __xfs_free_extent_later(tp, del->br_startblock,
+			error = xfs_free_extent_later(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					XFS_AG_RESV_NONE,
 					((bflags & XFS_BMAPI_NODISCARD) ||
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 925cc153b..c4d5c8a64 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -270,7 +270,7 @@ xfs_bmbt_free_block(
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
 	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
-			XFS_AG_RESV_NONE);
+			XFS_AG_RESV_NONE, false);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index a95675b1d..14826280d 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -1849,7 +1849,7 @@ xfs_difree_inode_chunk(
 		return xfs_free_extent_later(tp,
 				XFS_AGB_TO_FSB(mp, agno, sagbno),
 				M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
-				XFS_AG_RESV_NONE);
+				XFS_AG_RESV_NONE, false);
 	}
 
 	/* holemask is only 16-bits (fits in an unsigned long) */
@@ -1895,7 +1895,8 @@ xfs_difree_inode_chunk(
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
 		error = xfs_free_extent_later(tp,
 				XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
-				&XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE);
+				&XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE,
+				false);
 		if (error)
 			return error;
 
diff --git a/libxfs/xfs_ialloc_btree.c b/libxfs/xfs_ialloc_btree.c
index 0c5d7ba1c..593cb1fcc 100644
--- a/libxfs/xfs_ialloc_btree.c
+++ b/libxfs/xfs_ialloc_btree.c
@@ -160,7 +160,7 @@ __xfs_inobt_free_block(
 	xfs_inobt_mod_blockcount(cur, -1);
 	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
 	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
-			&XFS_RMAP_OINFO_INOBT, resv);
+			&XFS_RMAP_OINFO_INOBT, resv, false);
 }
 
 STATIC int
diff --git a/libxfs/xfs_refcount.c b/libxfs/xfs_refcount.c
index ae72f2507..2284b45fb 100644
--- a/libxfs/xfs_refcount.c
+++ b/libxfs/xfs_refcount.c
@@ -1152,7 +1152,7 @@ xfs_refcount_adjust_extents(
 						tmp.rc_startblock);
 				error = xfs_free_extent_later(cur->bc_tp, fsbno,
 						  tmp.rc_blockcount, NULL,
-						  XFS_AG_RESV_NONE);
+						  XFS_AG_RESV_NONE, false);
 				if (error)
 					goto out_error;
 			}
@@ -1214,7 +1214,7 @@ xfs_refcount_adjust_extents(
 					ext.rc_startblock);
 			error = xfs_free_extent_later(cur->bc_tp, fsbno,
 					ext.rc_blockcount, NULL,
-					XFS_AG_RESV_NONE);
+					XFS_AG_RESV_NONE, false);
 			if (error)
 				goto out_error;
 		}
@@ -1984,7 +1984,7 @@ xfs_refcount_recover_cow_leftovers(
 		/* Free the block. */
 		error = xfs_free_extent_later(tp, fsb,
 				rr->rr_rrec.rc_blockcount, NULL,
-				XFS_AG_RESV_NONE);
+				XFS_AG_RESV_NONE, false);
 		if (error)
 			goto out_trans;
 
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index 67cb59e33..bc8bd867e 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -111,7 +111,7 @@ xfs_refcountbt_free_block(
 	be32_add_cpu(&agf->agf_refcount_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
 	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
-			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
+			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA, false);
 }
 
 STATIC int
-- 
2.44.0

[PATCH 18/67] xfs: automatic freeing of freshly allocated unwritten space

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: e3042be36c343207b7af249a09f50b4e37e9fda4

As mentioned in the previous commit, online repair wants to allocate
space to write out a new metadata structure, and it also wants to hedge
against system crashes during repairs by logging (and later cancelling)
EFIs to free the space if we crash before committing the new data
structure.

Therefore, create a trio of functions to schedule automatic reaping of
freshly allocated unwritten space.  xfs_alloc_schedule_autoreap creates
a paused EFI representing the space we just allocated.  Once the
allocations are made and the autoreaps scheduled, we can start writing
to disk.

If the writes succeed, xfs_alloc_cancel_autoreap marks the EFI work
items as stale and unpauses the pending deferred work item.  Assuming
that's done in the same transaction that commits the new structure into
the filesystem, we guarantee that either the new object is fully
visible, or that all the space gets reclaimed.

If the writes succeed but only part of an extent was used, repair must
call the same _cancel_autoreap function to kill the first EFI and then
log a new EFI to free the unused space.  The first EFI is already

For full extents that aren't used, xfs_alloc_commit_autoreap will
unpause the EFI, which results in the space being freed during the next
_defer_finish cycle.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/defer_item.c |  10 +++--
 libxfs/xfs_alloc.c  | 104 ++++++++++++++++++++++++++++++++++++++++++--
 libxfs/xfs_alloc.h  |  12 +++++
 3 files changed, 119 insertions(+), 7 deletions(-)

diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index 8731d1834..c4a16c7ce 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -101,7 +101,7 @@ xfs_extent_free_finish_item(
 	struct xfs_owner_info		oinfo = { };
 	struct xfs_extent_free_item	*xefi;
 	xfs_agblock_t			agbno;
-	int				error;
+	int				error = 0;
 
 	xefi = container_of(item, struct xfs_extent_free_item, xefi_list);
 
@@ -112,8 +112,12 @@ xfs_extent_free_finish_item(
 		oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
 
 	agbno = XFS_FSB_TO_AGBNO(tp->t_mountp, xefi->xefi_startblock);
-	error = xfs_free_extent(tp, xefi->xefi_pag, agbno,
-			xefi->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE);
+
+	if (!(xefi->xefi_flags & XFS_EFI_CANCELLED)) {
+		error = xfs_free_extent(tp, xefi->xefi_pag, agbno,
+			xefi->xefi_blockcount, &oinfo,
+			XFS_AG_RESV_NONE);
+	}
 
 	/*
 	 * Don't free the XEFI if we need a new transaction to complete
diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index 0a2404466..463381be7 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -2518,14 +2518,15 @@ xfs_defer_agfl_block(
  * Add the extent to the list of extents to be free at transaction end.
  * The list is maintained sorted (by block number).
  */
-int
-xfs_free_extent_later(
+static int
+xfs_defer_extent_free(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	const struct xfs_owner_info	*oinfo,
 	enum xfs_ag_resv_type		type,
-	bool				skip_discard)
+	bool				skip_discard,
+	struct xfs_defer_pending	**dfpp)
 {
 	struct xfs_extent_free_item	*xefi;
 	struct xfs_mount		*mp = tp->t_mountp;
@@ -2573,10 +2574,105 @@ xfs_free_extent_later(
 			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
 
 	xfs_extent_free_get_group(mp, xefi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
+	*dfpp = xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
+	return 0;
+}
+
+int
+xfs_free_extent_later(
+	struct xfs_trans		*tp,
+	xfs_fsblock_t			bno,
+	xfs_filblks_t			len,
+	const struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type		type,
+	bool				skip_discard)
+{
+	struct xfs_defer_pending	*dontcare = NULL;
+
+	return xfs_defer_extent_free(tp, bno, len, oinfo, type, skip_discard,
+			&dontcare);
+}
+
+/*
+ * Set up automatic freeing of unwritten space in the filesystem.
+ *
+ * This function attached a paused deferred extent free item to the
+ * transaction.  Pausing means that the EFI will be logged in the next
+ * transaction commit, but the pending EFI will not be finished until the
+ * pending item is unpaused.
+ *
+ * If the system goes down after the EFI has been persisted to the log but
+ * before the pending item is unpaused, log recovery will find the EFI, fail to
+ * find the EFD, and free the space.
+ *
+ * If the pending item is unpaused, the next transaction commit will log an EFD
+ * without freeing the space.
+ *
+ * Caller must ensure that the tp, fsbno, len, oinfo, and resv flags of the
+ * @args structure are set to the relevant values.
+ */
+int
+xfs_alloc_schedule_autoreap(
+	const struct xfs_alloc_arg	*args,
+	bool				skip_discard,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	int				error;
+
+	error = xfs_defer_extent_free(args->tp, args->fsbno, args->len,
+			&args->oinfo, args->resv, skip_discard, &aarp->dfp);
+	if (error)
+		return error;
+
+	xfs_defer_item_pause(args->tp, aarp->dfp);
 	return 0;
 }
 
+/*
+ * Cancel automatic freeing of unwritten space in the filesystem.
+ *
+ * Earlier, we created a paused deferred extent free item and attached it to
+ * this transaction so that we could automatically roll back a new space
+ * allocation if the system went down.  Now we want to cancel the paused work
+ * item by marking the EFI stale so we don't actually free the space, unpausing
+ * the pending item and logging an EFD.
+ *
+ * The caller generally should have already mapped the space into the ondisk
+ * filesystem.  If the reserved space was partially used, the caller must call
+ * xfs_free_extent_later to create a new EFI to free the unused space.
+ */
+void
+xfs_alloc_cancel_autoreap(
+	struct xfs_trans		*tp,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	struct xfs_defer_pending	*dfp = aarp->dfp;
+	struct xfs_extent_free_item	*xefi;
+
+	if (!dfp)
+		return;
+
+	list_for_each_entry(xefi, &dfp->dfp_work, xefi_list)
+		xefi->xefi_flags |= XFS_EFI_CANCELLED;
+
+	xfs_defer_item_unpause(tp, dfp);
+}
+
+/*
+ * Commit automatic freeing of unwritten space in the filesystem.
+ *
+ * This unpauses an earlier _schedule_autoreap and commits to freeing the
+ * allocated space.  Call this if none of the reserved space was used.
+ */
+void
+xfs_alloc_commit_autoreap(
+	struct xfs_trans		*tp,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	if (aarp->dfp)
+		xfs_defer_item_unpause(tp, aarp->dfp);
+}
+
 #ifdef DEBUG
 /*
  * Check if an AGF has a free extent record whose length is equal to
diff --git a/libxfs/xfs_alloc.h b/libxfs/xfs_alloc.h
index 6b95d1d8a..851cafbd6 100644
--- a/libxfs/xfs_alloc.h
+++ b/libxfs/xfs_alloc.h
@@ -255,6 +255,18 @@ void xfs_extent_free_get_group(struct xfs_mount *mp,
 #define XFS_EFI_SKIP_DISCARD	(1U << 0) /* don't issue discard */
 #define XFS_EFI_ATTR_FORK	(1U << 1) /* freeing attr fork block */
 #define XFS_EFI_BMBT_BLOCK	(1U << 2) /* freeing bmap btree block */
+#define XFS_EFI_CANCELLED	(1U << 3) /* dont actually free the space */
+
+struct xfs_alloc_autoreap {
+	struct xfs_defer_pending	*dfp;
+};
+
+int xfs_alloc_schedule_autoreap(const struct xfs_alloc_arg *args,
+		bool skip_discard, struct xfs_alloc_autoreap *aarp);
+void xfs_alloc_cancel_autoreap(struct xfs_trans *tp,
+		struct xfs_alloc_autoreap *aarp);
+void xfs_alloc_commit_autoreap(struct xfs_trans *tp,
+		struct xfs_alloc_autoreap *aarp);
 
 extern struct kmem_cache	*xfs_extfree_item_cache;
 
-- 
2.44.0

[PATCH 19/67] xfs: remove unused fields from struct xbtree_ifakeroot

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 4c8ecd1cfdd01fb727121035014d9f654a30bdf2

Remove these unused fields since nobody uses them.  They should have
been removed years ago in a different cleanup series from Christoph
Hellwig.

Fixes: daf83964a3681 ("xfs: move the per-fork nextents fields into struct xfs_ifork")
Fixes: f7e67b20ecbbc ("xfs: move the fork format fields into struct xfs_ifork")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_btree_staging.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/libxfs/xfs_btree_staging.h b/libxfs/xfs_btree_staging.h
index f0d297605..5f638f711 100644
--- a/libxfs/xfs_btree_staging.h
+++ b/libxfs/xfs_btree_staging.h
@@ -37,12 +37,6 @@ struct xbtree_ifakeroot {
 
 	/* Number of bytes available for this fork in the inode. */
 	unsigned int		if_fork_size;
-
-	/* Fork format. */
-	unsigned int		if_format;
-
-	/* Number of records. */
-	unsigned int		if_extents;
 };
 
 /* Cursor interactions with fake roots for inode-rooted btrees. */
-- 
2.44.0

[PATCH 20/67] xfs: force small EFIs for reaping btree extents

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 3f3cec031099c37513727efc978a12b6346e326d

Introduce the concept of a defer ops barrier to separate consecutively
queued pending work items of the same type.  With a barrier in place,
the two work items will be tracked separately, and receive separate log
intent items.  The goal here is to prevent reaping of old metadata
blocks from creating unnecessarily huge EFIs that could then run the
risk of overflowing the scrub transaction.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 107 ++++++++++++++++++++++++++++++++++++++++-----
 libxfs/xfs_defer.h |   3 ++
 2 files changed, 99 insertions(+), 11 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 58ad1881d..98f1cbe6a 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -176,6 +176,58 @@ static struct kmem_cache	*xfs_defer_pending_cache;
  * Note that the continuation requested between t2 and t3 is likely to
  * reoccur.
  */
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return NULL;
+}
+
+STATIC void
+xfs_defer_barrier_abort_intent(
+	struct xfs_log_item		*intent)
+{
+	/* empty */
+}
+
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	unsigned int			count)
+{
+	return NULL;
+}
+
+STATIC int
+xfs_defer_barrier_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*done,
+	struct list_head		*item,
+	struct xfs_btree_cur		**state)
+{
+	ASSERT(0);
+	return -EFSCORRUPTED;
+}
+
+STATIC void
+xfs_defer_barrier_cancel_item(
+	struct list_head		*item)
+{
+	ASSERT(0);
+}
+
+static const struct xfs_defer_op_type xfs_barrier_defer_type = {
+	.max_items	= 1,
+	.create_intent	= xfs_defer_barrier_create_intent,
+	.abort_intent	= xfs_defer_barrier_abort_intent,
+	.create_done	= xfs_defer_barrier_create_done,
+	.finish_item	= xfs_defer_barrier_finish_item,
+	.cancel_item	= xfs_defer_barrier_cancel_item,
+};
 
 static const struct xfs_defer_op_type *defer_op_types[] = {
 	[XFS_DEFER_OPS_TYPE_BMAP]	= &xfs_bmap_update_defer_type,
@@ -184,6 +236,7 @@ static const struct xfs_defer_op_type *defer_op_types[] = {
 	[XFS_DEFER_OPS_TYPE_FREE]	= &xfs_extent_free_defer_type,
 	[XFS_DEFER_OPS_TYPE_AGFL_FREE]	= &xfs_agfl_free_defer_type,
 	[XFS_DEFER_OPS_TYPE_ATTR]	= &xfs_attr_defer_type,
+	[XFS_DEFER_OPS_TYPE_BARRIER]	= &xfs_barrier_defer_type,
 };
 
 /* Create a log intent done item for a log intent item. */
@@ -773,6 +826,23 @@ xfs_defer_can_append(
 	return true;
 }
 
+/* Create a new pending item at the end of the transaction list. */
+static inline struct xfs_defer_pending *
+xfs_defer_alloc(
+	struct xfs_trans		*tp,
+	enum xfs_defer_ops_type		type)
+{
+	struct xfs_defer_pending	*dfp;
+
+	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	dfp->dfp_type = type;
+	INIT_LIST_HEAD(&dfp->dfp_work);
+	list_add_tail(&dfp->dfp_list, &tp->t_dfops);
+
+	return dfp;
+}
+
 /* Add an item for later deferred processing. */
 struct xfs_defer_pending *
 xfs_defer_add(
@@ -787,23 +857,38 @@ xfs_defer_add(
 	BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
 
 	dfp = xfs_defer_find_last(tp, type, ops);
-	if (!dfp || !xfs_defer_can_append(dfp, ops)) {
-		/* Create a new pending item at the end of the intake list. */
-		dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
-				GFP_NOFS | __GFP_NOFAIL);
-		dfp->dfp_type = type;
-		dfp->dfp_intent = NULL;
-		dfp->dfp_done = NULL;
-		dfp->dfp_count = 0;
-		INIT_LIST_HEAD(&dfp->dfp_work);
-		list_add_tail(&dfp->dfp_list, &tp->t_dfops);
-	}
+	if (!dfp || !xfs_defer_can_append(dfp, ops))
+		dfp = xfs_defer_alloc(tp, type);
 
 	xfs_defer_add_item(dfp, li);
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
 	return dfp;
 }
 
+/*
+ * Add a defer ops barrier to force two otherwise adjacent deferred work items
+ * to be tracked separately and have separate log items.
+ */
+void
+xfs_defer_add_barrier(
+	struct xfs_trans		*tp)
+{
+	struct xfs_defer_pending	*dfp;
+	const enum xfs_defer_ops_type	type = XFS_DEFER_OPS_TYPE_BARRIER;
+	const struct xfs_defer_op_type	*ops = defer_op_types[type];
+
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
+	/* If the last defer op added was a barrier, we're done. */
+	dfp = xfs_defer_find_last(tp, type, ops);
+	if (dfp)
+		return;
+
+	xfs_defer_alloc(tp, type);
+
+	trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
+}
+
 /*
  * Create a pending deferred work item to replay the recovered intent item
  * and add it to the list.
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index b0284154f..5b1990ef3 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -20,6 +20,7 @@ enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_FREE,
 	XFS_DEFER_OPS_TYPE_AGFL_FREE,
 	XFS_DEFER_OPS_TYPE_ATTR,
+	XFS_DEFER_OPS_TYPE_BARRIER,
 	XFS_DEFER_OPS_TYPE_MAX,
 };
 
@@ -163,4 +164,6 @@ xfs_defer_add_item(
 int __init xfs_defer_init_item_caches(void);
 void xfs_defer_destroy_item_caches(void);
 
+void xfs_defer_add_barrier(struct xfs_trans *tp);
+
 #endif /* __XFS_DEFER_H__ */
-- 
2.44.0

[PATCH 21/67] xfs: ensure logflagsp is initialized in xfs_bmap_del_extent_real

[cem]

From: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>

Source kernel commit: e6af9c98cbf0164a619d95572136bfb54d482dd6

In the case of returning -ENOSPC, ensure logflagsp is initialized by 0.
Otherwise the caller __xfs_bunmapi will set uninitialized illegal
tmp_logflags value into xfs log, which might cause unpredictable error
in the log recovery procedure.

Also, remove the flags variable and set the *logflagsp directly, so that
the code should be more robust in the long run.

Fixes: 1b24b633aafe ("xfs: move some more code into xfs_bmap_del_extent_real")
Signed-off-by: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_bmap.c | 73 ++++++++++++++++++++---------------------------
 1 file changed, 31 insertions(+), 42 deletions(-)

diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 8c553d22c..20ec22dfc 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -5004,7 +5004,6 @@ xfs_bmap_del_extent_real(
 	xfs_fileoff_t		del_endoff;	/* first offset past del */
 	int			do_fx;	/* free extent at end of routine */
 	int			error;	/* error return value */
-	int			flags = 0;/* inode logging flags */
 	struct xfs_bmbt_irec	got;	/* current extent entry */
 	xfs_fileoff_t		got_endoff;	/* first offset past got */
 	int			i;	/* temp state */
@@ -5017,6 +5016,8 @@ xfs_bmap_del_extent_real(
 	uint32_t		state = xfs_bmap_fork_to_state(whichfork);
 	struct xfs_bmbt_irec	old;
 
+	*logflagsp = 0;
+
 	mp = ip->i_mount;
 	XFS_STATS_INC(mp, xs_del_exlist);
 
@@ -5029,7 +5030,6 @@ xfs_bmap_del_extent_real(
 	ASSERT(got_endoff >= del_endoff);
 	ASSERT(!isnullstartblock(got.br_startblock));
 	qfield = 0;
-	error = 0;
 
 	/*
 	 * If it's the case where the directory code is running with no block
@@ -5045,13 +5045,13 @@ xfs_bmap_del_extent_real(
 	    del->br_startoff > got.br_startoff && del_endoff < got_endoff)
 		return -ENOSPC;
 
-	flags = XFS_ILOG_CORE;
+	*logflagsp = XFS_ILOG_CORE;
 	if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
 		if (!(bflags & XFS_BMAPI_REMAP)) {
 			error = xfs_rtfree_blocks(tp, del->br_startblock,
 					del->br_blockcount);
 			if (error)
-				goto done;
+				return error;
 		}
 
 		do_fx = 0;
@@ -5066,11 +5066,9 @@ xfs_bmap_del_extent_real(
 	if (cur) {
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
-			goto done;
-		if (XFS_IS_CORRUPT(mp, i != 1)) {
-			error = -EFSCORRUPTED;
-			goto done;
-		}
+			return error;
+		if (XFS_IS_CORRUPT(mp, i != 1))
+			return -EFSCORRUPTED;
 	}
 
 	if (got.br_startoff == del->br_startoff)
@@ -5087,17 +5085,15 @@ xfs_bmap_del_extent_real(
 		xfs_iext_prev(ifp, icur);
 		ifp->if_nextents--;
 
-		flags |= XFS_ILOG_CORE;
+		*logflagsp |= XFS_ILOG_CORE;
 		if (!cur) {
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 			break;
 		}
 		if ((error = xfs_btree_delete(cur, &i)))
-			goto done;
-		if (XFS_IS_CORRUPT(mp, i != 1)) {
-			error = -EFSCORRUPTED;
-			goto done;
-		}
+			return error;
+		if (XFS_IS_CORRUPT(mp, i != 1))
+			return -EFSCORRUPTED;
 		break;
 	case BMAP_LEFT_FILLING:
 		/*
@@ -5108,12 +5104,12 @@ xfs_bmap_del_extent_real(
 		got.br_blockcount -= del->br_blockcount;
 		xfs_iext_update_extent(ip, state, icur, &got);
 		if (!cur) {
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 			break;
 		}
 		error = xfs_bmbt_update(cur, &got);
 		if (error)
-			goto done;
+			return error;
 		break;
 	case BMAP_RIGHT_FILLING:
 		/*
@@ -5122,12 +5118,12 @@ xfs_bmap_del_extent_real(
 		got.br_blockcount -= del->br_blockcount;
 		xfs_iext_update_extent(ip, state, icur, &got);
 		if (!cur) {
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 			break;
 		}
 		error = xfs_bmbt_update(cur, &got);
 		if (error)
-			goto done;
+			return error;
 		break;
 	case 0:
 		/*
@@ -5144,18 +5140,18 @@ xfs_bmap_del_extent_real(
 		new.br_state = got.br_state;
 		new.br_startblock = del_endblock;
 
-		flags |= XFS_ILOG_CORE;
+		*logflagsp |= XFS_ILOG_CORE;
 		if (cur) {
 			error = xfs_bmbt_update(cur, &got);
 			if (error)
-				goto done;
+				return error;
 			error = xfs_btree_increment(cur, 0, &i);
 			if (error)
-				goto done;
+				return error;
 			cur->bc_rec.b = new;
 			error = xfs_btree_insert(cur, &i);
 			if (error && error != -ENOSPC)
-				goto done;
+				return error;
 			/*
 			 * If get no-space back from btree insert, it tried a
 			 * split, and we have a zero block reservation.  Fix up
@@ -5168,33 +5164,28 @@ xfs_bmap_del_extent_real(
 				 */
 				error = xfs_bmbt_lookup_eq(cur, &got, &i);
 				if (error)
-					goto done;
-				if (XFS_IS_CORRUPT(mp, i != 1)) {
-					error = -EFSCORRUPTED;
-					goto done;
-				}
+					return error;
+				if (XFS_IS_CORRUPT(mp, i != 1))
+					return -EFSCORRUPTED;
 				/*
 				 * Update the btree record back
 				 * to the original value.
 				 */
 				error = xfs_bmbt_update(cur, &old);
 				if (error)
-					goto done;
+					return error;
 				/*
 				 * Reset the extent record back
 				 * to the original value.
 				 */
 				xfs_iext_update_extent(ip, state, icur, &old);
-				flags = 0;
-				error = -ENOSPC;
-				goto done;
-			}
-			if (XFS_IS_CORRUPT(mp, i != 1)) {
-				error = -EFSCORRUPTED;
-				goto done;
+				*logflagsp = 0;
+				return -ENOSPC;
 			}
+			if (XFS_IS_CORRUPT(mp, i != 1))
+				return -EFSCORRUPTED;
 		} else
-			flags |= xfs_ilog_fext(whichfork);
+			*logflagsp |= xfs_ilog_fext(whichfork);
 
 		ifp->if_nextents++;
 		xfs_iext_next(ifp, icur);
@@ -5218,7 +5209,7 @@ xfs_bmap_del_extent_real(
 					((bflags & XFS_BMAPI_NODISCARD) ||
 					del->br_state == XFS_EXT_UNWRITTEN));
 			if (error)
-				goto done;
+				return error;
 		}
 	}
 
@@ -5233,9 +5224,7 @@ xfs_bmap_del_extent_real(
 	if (qfield && !(bflags & XFS_BMAPI_REMAP))
 		xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks);
 
-done:
-	*logflagsp = flags;
-	return error;
+	return 0;
 }
 
 /*
-- 
2.44.0

[PATCH 22/67] xfs: update dir3 leaf block metadata after swap

[cem]

From: Zhang Tianci <zhangtianci.1997@bytedance.com>

Source kernel commit: 5759aa4f956034b289b0ae2c99daddfc775442e1

xfs_da3_swap_lastblock() copy the last block content to the dead block,
but do not update the metadata in it. We need update some metadata
for some kinds of type block, such as dir3 leafn block records its
blkno, we shall update it to the dead block blkno. Otherwise,
before write the xfs_buf to disk, the verify_write() will fail in
blk_hdr->blkno != xfs_buf->b_bn, then xfs will be shutdown.

We will get this warning:

XFS (dm-0): Metadata corruption detected at xfs_dir3_leaf_verify+0xa8/0xe0 [xfs], xfs_dir3_leafn block 0x178
XFS (dm-0): Unmount and run xfs_repair
XFS (dm-0): First 128 bytes of corrupted metadata buffer:
00000000e80f1917: 00 80 00 0b 00 80 00 07 3d ff 00 00 00 00 00 00  ........=.......
000000009604c005: 00 00 00 00 00 00 01 a0 00 00 00 00 00 00 00 00  ................
000000006b6fb2bf: e4 44 e3 97 b5 64 44 41 8b 84 60 0e 50 43 d9 bf  .D...dDA..`.PC..
00000000678978a2: 00 00 00 00 00 00 00 83 01 73 00 93 00 00 00 00  .........s......
00000000b28b247c: 99 29 1d 38 00 00 00 00 99 29 1d 40 00 00 00 00  .).8.....).@....
000000002b2a662c: 99 29 1d 48 00 00 00 00 99 49 11 00 00 00 00 00  .).H.....I......
00000000ea2ffbb8: 99 49 11 08 00 00 45 25 99 49 11 10 00 00 48 fe  .I....E%.I....H.
0000000069e86440: 99 49 11 18 00 00 4c 6b 99 49 11 20 00 00 4d 97  .I....Lk.I. ..M.
XFS (dm-0): xfs_do_force_shutdown(0x8) called from line 1423 of file fs/xfs/xfs_buf.c.  Return address = 00000000c0ff63c1
XFS (dm-0): Corruption of in-memory data detected.  Shutting down filesystem
XFS (dm-0): Please umount the filesystem and rectify the problem(s)

>From the log above, we know xfs_buf->b_no is 0x178, but the block's hdr record
its blkno is 0x1a0.

Fixes: 24df33b45ecf ("xfs: add CRC checking to dir2 leaf blocks")
Signed-off-by: Zhang Tianci <zhangtianci.1997@bytedance.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_da_btree.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/libxfs/xfs_da_btree.c b/libxfs/xfs_da_btree.c
index a068a0164..3903486d1 100644
--- a/libxfs/xfs_da_btree.c
+++ b/libxfs/xfs_da_btree.c
@@ -2312,10 +2312,17 @@ xfs_da3_swap_lastblock(
 		return error;
 	/*
 	 * Copy the last block into the dead buffer and log it.
+	 * On CRC-enabled file systems, also update the stamped in blkno.
 	 */
 	memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize);
+	if (xfs_has_crc(mp)) {
+		struct xfs_da3_blkinfo *da3 = dead_buf->b_addr;
+
+		da3->blkno = cpu_to_be64(xfs_buf_daddr(dead_buf));
+	}
 	xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1);
 	dead_info = dead_buf->b_addr;
+
 	/*
 	 * Get values from the moved block.
 	 */
-- 
2.44.0

[PATCH 23/67] xfs: extract xfs_da_buf_copy() helper function

[cem]

From: Zhang Tianci <zhangtianci.1997@bytedance.com>

Source kernel commit: fd45ddb9dd606b3eaddf26e13f64340636955986

This patch does not modify logic.

xfs_da_buf_copy() will copy one block from src xfs_buf to
dst xfs_buf, and update the block metadata in dst directly.

Signed-off-by: Zhang Tianci <zhangtianci.1997@bytedance.com>
Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr_leaf.c | 12 +++----
 libxfs/xfs_da_btree.c  | 74 +++++++++++++++++-------------------------
 libxfs/xfs_da_btree.h  |  2 ++
 3 files changed, 36 insertions(+), 52 deletions(-)

diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index ed81471ce..baa168318 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -1241,14 +1241,10 @@ xfs_attr3_leaf_to_node(
 	if (error)
 		goto out;
 
-	/* copy leaf to new buffer, update identifiers */
-	xfs_trans_buf_set_type(args->trans, bp2, XFS_BLFT_ATTR_LEAF_BUF);
-	bp2->b_ops = bp1->b_ops;
-	memcpy(bp2->b_addr, bp1->b_addr, args->geo->blksize);
-	if (xfs_has_crc(mp)) {
-		struct xfs_da3_blkinfo *hdr3 = bp2->b_addr;
-		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp2));
-	}
+	/*
+	 * Copy leaf to new buffer and log it.
+	 */
+	xfs_da_buf_copy(bp2, bp1, args->geo->blksize);
 	xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1);
 
 	/*
diff --git a/libxfs/xfs_da_btree.c b/libxfs/xfs_da_btree.c
index 3903486d1..0779bb624 100644
--- a/libxfs/xfs_da_btree.c
+++ b/libxfs/xfs_da_btree.c
@@ -417,6 +417,25 @@ xfs_da3_node_read_mapped(
 	return xfs_da3_node_set_type(tp, *bpp);
 }
 
+/*
+ * Copy src directory/attr leaf/node buffer to the dst.
+ * For v5 file systems make sure the right blkno is stamped in.
+ */
+void
+xfs_da_buf_copy(
+	struct xfs_buf *dst,
+	struct xfs_buf *src,
+	size_t size)
+{
+	struct xfs_da3_blkinfo *da3 = dst->b_addr;
+
+	memcpy(dst->b_addr, src->b_addr, size);
+	dst->b_ops = src->b_ops;
+	xfs_trans_buf_copy_type(dst, src);
+	if (xfs_has_crc(dst->b_mount))
+		da3->blkno = cpu_to_be64(xfs_buf_daddr(dst));
+}
+
 /*========================================================================
  * Routines used for growing the Btree.
  *========================================================================*/
@@ -686,12 +705,6 @@ xfs_da3_root_split(
 		btree = icnodehdr.btree;
 		size = (int)((char *)&btree[icnodehdr.count] - (char *)oldroot);
 		level = icnodehdr.level;
-
-		/*
-		 * we are about to copy oldroot to bp, so set up the type
-		 * of bp while we know exactly what it will be.
-		 */
-		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DA_NODE_BUF);
 	} else {
 		struct xfs_dir3_icleaf_hdr leafhdr;
 
@@ -703,31 +716,17 @@ xfs_da3_root_split(
 		size = (int)((char *)&leafhdr.ents[leafhdr.count] -
 			(char *)leaf);
 		level = 0;
-
-		/*
-		 * we are about to copy oldroot to bp, so set up the type
-		 * of bp while we know exactly what it will be.
-		 */
-		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAFN_BUF);
 	}
 
 	/*
-	 * we can copy most of the information in the node from one block to
-	 * another, but for CRC enabled headers we have to make sure that the
-	 * block specific identifiers are kept intact. We update the buffer
-	 * directly for this.
+	 * Copy old root to new buffer and log it.
 	 */
-	memcpy(node, oldroot, size);
-	if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC) ||
-	    oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
-		struct xfs_da3_intnode *node3 = (struct xfs_da3_intnode *)node;
-
-		node3->hdr.info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-	}
+	xfs_da_buf_copy(bp, blk1->bp, size);
 	xfs_trans_log_buf(tp, bp, 0, size - 1);
 
-	bp->b_ops = blk1->bp->b_ops;
-	xfs_trans_buf_copy_type(bp, blk1->bp);
+	/*
+	 * Update blk1 to point to new buffer.
+	 */
 	blk1->bp = bp;
 	blk1->blkno = blkno;
 
@@ -1216,21 +1215,14 @@ xfs_da3_root_join(
 	xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level);
 
 	/*
-	 * This could be copying a leaf back into the root block in the case of
-	 * there only being a single leaf block left in the tree. Hence we have
-	 * to update the b_ops pointer as well to match the buffer type change
-	 * that could occur. For dir3 blocks we also need to update the block
-	 * number in the buffer header.
+	 * Copy child to root buffer and log it.
 	 */
-	memcpy(root_blk->bp->b_addr, bp->b_addr, args->geo->blksize);
-	root_blk->bp->b_ops = bp->b_ops;
-	xfs_trans_buf_copy_type(root_blk->bp, bp);
-	if (oldroothdr.magic == XFS_DA3_NODE_MAGIC) {
-		struct xfs_da3_blkinfo *da3 = root_blk->bp->b_addr;
-		da3->blkno = cpu_to_be64(xfs_buf_daddr(root_blk->bp));
-	}
+	xfs_da_buf_copy(root_blk->bp, bp, args->geo->blksize);
 	xfs_trans_log_buf(args->trans, root_blk->bp, 0,
 			  args->geo->blksize - 1);
+	/*
+	 * Now we can drop the child buffer.
+	 */
 	error = xfs_da_shrink_inode(args, child, bp);
 	return error;
 }
@@ -2312,14 +2304,8 @@ xfs_da3_swap_lastblock(
 		return error;
 	/*
 	 * Copy the last block into the dead buffer and log it.
-	 * On CRC-enabled file systems, also update the stamped in blkno.
 	 */
-	memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize);
-	if (xfs_has_crc(mp)) {
-		struct xfs_da3_blkinfo *da3 = dead_buf->b_addr;
-
-		da3->blkno = cpu_to_be64(xfs_buf_daddr(dead_buf));
-	}
+	xfs_da_buf_copy(dead_buf, last_buf, args->geo->blksize);
 	xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1);
 	dead_info = dead_buf->b_addr;
 
diff --git a/libxfs/xfs_da_btree.h b/libxfs/xfs_da_btree.h
index ffa3df5b2..706baf36e 100644
--- a/libxfs/xfs_da_btree.h
+++ b/libxfs/xfs_da_btree.h
@@ -219,6 +219,8 @@ int	xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
 		const struct xfs_buf_ops *ops);
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 					  struct xfs_buf *dead_buf);
+void	xfs_da_buf_copy(struct xfs_buf *dst, struct xfs_buf *src,
+			size_t size);
 
 uint xfs_da_hashname(const uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
-- 
2.44.0

[PATCH 24/67] xfs: move xfs_ondisk.h to libxfs/

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 18793e050504288345eb455a471677b57117bcc6

Move xfs_ondisk.h to libxfs so that we can do the struct sanity checks
in userspace libxfs as well.  This should allow us to retire the
somewhat fragile xfs/122 test on xfstests.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/init.c       |   6 ++
 libxfs/xfs_ondisk.h | 199 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 205 insertions(+)
 create mode 100644 libxfs/xfs_ondisk.h

diff --git a/libxfs/init.c b/libxfs/init.c
index 63c506a69..f7ba4d1b3 100644
--- a/libxfs/init.c
+++ b/libxfs/init.c
@@ -23,6 +23,11 @@
 #include "xfs_refcount_btree.h"
 #include "libfrog/platform.h"
 
+#include "xfs_format.h"
+#include "xfs_da_format.h"
+#include "xfs_log_format.h"
+#include "xfs_ondisk.h"
+
 #include "libxfs.h"		/* for now */
 
 #ifndef HAVE_LIBURCU_ATOMIC64
@@ -248,6 +253,7 @@ libxfs_close_devices(
 int
 libxfs_init(struct libxfs_init *a)
 {
+	xfs_check_ondisk_structs();
 	rcu_init();
 	rcu_register_thread();
 	radix_tree_init();
diff --git a/libxfs/xfs_ondisk.h b/libxfs/xfs_ondisk.h
new file mode 100644
index 000000000..d9c988c5a
--- /dev/null
+++ b/libxfs/xfs_ondisk.h
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016 Oracle.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_ONDISK_H
+#define __XFS_ONDISK_H
+
+#define XFS_CHECK_STRUCT_SIZE(structname, size) \
+	static_assert(sizeof(structname) == (size), \
+		"XFS: sizeof(" #structname ") is wrong, expected " #size)
+
+#define XFS_CHECK_OFFSET(structname, member, off) \
+	static_assert(offsetof(structname, member) == (off), \
+		"XFS: offsetof(" #structname ", " #member ") is wrong, " \
+		"expected " #off)
+
+#define XFS_CHECK_VALUE(value, expected) \
+	static_assert((value) == (expected), \
+		"XFS: value of " #value " is wrong, expected " #expected)
+
+static inline void __init
+xfs_check_ondisk_structs(void)
+{
+	/* ag/file structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_acl,			4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_acl_entry,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agf,			224);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agfl,			36);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agi,			344);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_shdr,	48);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_lhdr,	64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block,		72);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			264);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_key,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_rec,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_key,		20);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_rec,		24);
+	XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t,			8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp,	8);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t,			4);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_rec_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t,			4);
+	XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t,			4);
+
+	/* dir/attr trees */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr,	80);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leafblock,	80);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_rmt_hdr,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_blkinfo,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_intnode,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_node_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_blk_hdr,		48);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_data_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_hdr_t,		32);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_map_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_local_t,	4);
+
+	/* realtime structures */
+	XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw,		4);
+	XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw,		4);
+
+	/*
+	 * m68k has problems with xfs_attr_leaf_name_remote_t, but we pad it to
+	 * 4 bytes anyway so it's not obviously a problem.  Hence for the moment
+	 * we don't check this structure. This can be re-instated when the attr
+	 * definitions are updated to use c99 VLA definitions.
+	 *
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t,	12);
+	 */
+
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, valuelen,	0);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, namelen,	2);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, nameval,	3);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valueblk,	0);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valuelen,	4);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen,	8);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name,	9);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_shortform,	4);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.totsize, 0);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.count,	 2);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].namelen,	4);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].valuelen,	5);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].flags,	6);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].nameval,	7);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_node_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_free_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_hdr_t,		16);
+	XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, freetag,	0);
+	XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, length,	2);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_tail_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_entry_t,		3);
+	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, namelen,		0);
+	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, offset,		1);
+	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, name,		3);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t,		10);
+
+	/* log structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode,		176);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log,		28);
+	XFS_CHECK_STRUCT_SIZE(xfs_log_timestamp_t,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_log_legacy_timestamp,	8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32,	52);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format,	56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat,	20);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attri_log_format,	40);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrd_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_cui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_cud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_map_extent,		32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_phys_extent,		16);
+
+	XFS_CHECK_OFFSET(struct xfs_bui_log_format, bui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_cui_log_format, cui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_rui_log_format, rui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format, efi_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents,	16);
+
+	/*
+	 * The v5 superblock format extended several v4 header structures with
+	 * additional data. While new fields are only accessible on v5
+	 * superblocks, it's important that the v5 structures place original v4
+	 * fields/headers in the correct location on-disk. For example, we must
+	 * be able to find magic values at the same location in certain blocks
+	 * regardless of superblock version.
+	 *
+	 * The following checks ensure that various v5 data structures place the
+	 * subset of v4 metadata associated with the same type of block at the
+	 * start of the on-disk block. If there is no data structure definition
+	 * for certain types of v4 blocks, traverse down to the first field of
+	 * common metadata (e.g., magic value) and make sure it is at offset
+	 * zero.
+	 */
+	XFS_CHECK_OFFSET(struct xfs_dir3_leaf, hdr.info.hdr,	0);
+	XFS_CHECK_OFFSET(struct xfs_da3_intnode, hdr.info.hdr,	0);
+	XFS_CHECK_OFFSET(struct xfs_dir3_data_hdr, hdr.magic,	0);
+	XFS_CHECK_OFFSET(struct xfs_dir3_free, hdr.hdr.magic,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr3_leafblock, hdr.info.hdr, 0);
+
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat,		192);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers,		24);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req,		64);
+
+	/*
+	 * Make sure the incore inode timestamp range corresponds to hand
+	 * converted values based on the ondisk format specification.
+	 */
+	XFS_CHECK_VALUE(XFS_BIGTIME_TIME_MIN - XFS_BIGTIME_EPOCH_OFFSET,
+			XFS_LEGACY_TIME_MIN);
+	XFS_CHECK_VALUE(XFS_BIGTIME_TIME_MAX - XFS_BIGTIME_EPOCH_OFFSET,
+			16299260424LL);
+
+	/* Do the same with the incore quota expiration range. */
+	XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MIN << XFS_DQ_BIGTIME_SHIFT, 4);
+	XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MAX << XFS_DQ_BIGTIME_SHIFT,
+			16299260424LL);
+}
+
+#endif /* __XFS_ONDISK_H */
-- 
2.44.0

[PATCH 25/67] xfs: consolidate the xfs_attr_defer_* helpers

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: c00eebd09e95757c9c1d08f0a6bbc32c543daf90

Consolidate the xfs_attr_defer_* helpers into a single xfs_attr_defer_add
one that picks the right dela_state based on the passed in operation.
Also move to a single trace point as the actual operation is visible
through the flags in the delta_state passed to the trace point.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr.c | 90 +++++++++++------------------------------------
 1 file changed, 21 insertions(+), 69 deletions(-)

diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index 2103a06b9..550ca6b2e 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -878,11 +878,10 @@ xfs_attr_lookup(
 	return error;
 }
 
-static int
-xfs_attr_intent_init(
+static void
+xfs_attr_defer_add(
 	struct xfs_da_args	*args,
-	unsigned int		op_flags,	/* op flag (set or remove) */
-	struct xfs_attr_intent	**attr)		/* new xfs_attr_intent */
+	unsigned int		op_flags)
 {
 
 	struct xfs_attr_intent	*new;
@@ -891,66 +890,22 @@ xfs_attr_intent_init(
 	new->xattri_op_flags = op_flags;
 	new->xattri_da_args = args;
 
-	*attr = new;
-	return 0;
-}
-
-/* Sets an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_add(
-	struct xfs_da_args	*args)
-{
-	struct xfs_attr_intent	*new;
-	int			error = 0;
-
-	error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_SET, &new);
-	if (error)
-		return error;
+	switch (op_flags) {
+	case XFS_ATTRI_OP_FLAGS_SET:
+		new->xattri_dela_state = xfs_attr_init_add_state(args);
+		break;
+	case XFS_ATTRI_OP_FLAGS_REPLACE:
+		new->xattri_dela_state = xfs_attr_init_replace_state(args);
+		break;
+	case XFS_ATTRI_OP_FLAGS_REMOVE:
+		new->xattri_dela_state = xfs_attr_init_remove_state(args);
+		break;
+	default:
+		ASSERT(0);
+	}
 
-	new->xattri_dela_state = xfs_attr_init_add_state(args);
 	xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
 	trace_xfs_attr_defer_add(new->xattri_dela_state, args->dp);
-
-	return 0;
-}
-
-/* Sets an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_replace(
-	struct xfs_da_args	*args)
-{
-	struct xfs_attr_intent	*new;
-	int			error = 0;
-
-	error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REPLACE, &new);
-	if (error)
-		return error;
-
-	new->xattri_dela_state = xfs_attr_init_replace_state(args);
-	xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
-	trace_xfs_attr_defer_replace(new->xattri_dela_state, args->dp);
-
-	return 0;
-}
-
-/* Removes an attribute for an inode as a deferred operation */
-static int
-xfs_attr_defer_remove(
-	struct xfs_da_args	*args)
-{
-
-	struct xfs_attr_intent	*new;
-	int			error;
-
-	error  = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REMOVE, &new);
-	if (error)
-		return error;
-
-	new->xattri_dela_state = xfs_attr_init_remove_state(args);
-	xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
-	trace_xfs_attr_defer_remove(new->xattri_dela_state, args->dp);
-
-	return 0;
 }
 
 /*
@@ -1036,16 +991,16 @@ xfs_attr_set(
 	error = xfs_attr_lookup(args);
 	switch (error) {
 	case -EEXIST:
-		/* if no value, we are performing a remove operation */
 		if (!args->value) {
-			error = xfs_attr_defer_remove(args);
+			/* if no value, we are performing a remove operation */
+			xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REMOVE);
 			break;
 		}
+
 		/* Pure create fails if the attr already exists */
 		if (args->attr_flags & XATTR_CREATE)
 			goto out_trans_cancel;
-
-		error = xfs_attr_defer_replace(args);
+		xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_REPLACE);
 		break;
 	case -ENOATTR:
 		/* Can't remove what isn't there. */
@@ -1055,14 +1010,11 @@ xfs_attr_set(
 		/* Pure replace fails if no existing attr to replace. */
 		if (args->attr_flags & XATTR_REPLACE)
 			goto out_trans_cancel;
-
-		error = xfs_attr_defer_add(args);
+		xfs_attr_defer_add(args, XFS_ATTRI_OP_FLAGS_SET);
 		break;
 	default:
 		goto out_trans_cancel;
 	}
-	if (error)
-		goto out_trans_cancel;
 
 	/*
 	 * If this is a synchronous mount, make sure that the
-- 
2.44.0

[PATCH 26/67] xfs: store an ops pointer in struct xfs_defer_pending

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 7f2f7531e0d455f1abb9f48fbbe17c37e8742590

The dfp_type field in struct xfs_defer_pending is only used to either
look up the operations associated with the pending word or in trace
points.  Replace it with a direct pointer to the operations vector,
and store a pretty name in the vector for tracing.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/defer_item.c |  6 ++++++
 libxfs/xfs_defer.c  | 43 +++++++++++++++++--------------------------
 libxfs/xfs_defer.h  |  5 +++--
 3 files changed, 26 insertions(+), 28 deletions(-)

diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index c4a16c7ce..9e6899fea 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -152,6 +152,7 @@ xfs_extent_free_cancel_item(
 }
 
 const struct xfs_defer_op_type xfs_extent_free_defer_type = {
+	.name		= "extent_free",
 	.create_intent	= xfs_extent_free_create_intent,
 	.abort_intent	= xfs_extent_free_abort_intent,
 	.create_done	= xfs_extent_free_create_done,
@@ -195,6 +196,7 @@ xfs_agfl_free_finish_item(
 
 /* sub-type with special handling for AGFL deferred frees */
 const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
+	.name		= "agfl_free",
 	.create_intent	= xfs_extent_free_create_intent,
 	.abort_intent	= xfs_extent_free_abort_intent,
 	.create_done	= xfs_extent_free_create_done,
@@ -306,6 +308,7 @@ xfs_rmap_update_cancel_item(
 }
 
 const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
+	.name		= "rmap",
 	.create_intent	= xfs_rmap_update_create_intent,
 	.abort_intent	= xfs_rmap_update_abort_intent,
 	.create_done	= xfs_rmap_update_create_done,
@@ -424,6 +427,7 @@ xfs_refcount_update_cancel_item(
 }
 
 const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
+	.name		= "refcount",
 	.create_intent	= xfs_refcount_update_create_intent,
 	.abort_intent	= xfs_refcount_update_abort_intent,
 	.create_done	= xfs_refcount_update_create_done,
@@ -546,6 +550,7 @@ xfs_bmap_update_cancel_item(
 }
 
 const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
+	.name		= "bmap",
 	.create_intent	= xfs_bmap_update_create_intent,
 	.abort_intent	= xfs_bmap_update_abort_intent,
 	.create_done	= xfs_bmap_update_create_done,
@@ -641,6 +646,7 @@ xfs_attr_cancel_item(
 }
 
 const struct xfs_defer_op_type xfs_attr_defer_type = {
+	.name		= "attr",
 	.max_items	= 1,
 	.create_intent	= xfs_attr_create_intent,
 	.abort_intent	= xfs_attr_abort_intent,
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 98f1cbe6a..bb5411b84 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -245,7 +245,6 @@ xfs_defer_create_done(
 	struct xfs_trans		*tp,
 	struct xfs_defer_pending	*dfp)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 	struct xfs_log_item		*lip;
 
 	/* If there is no log intent item, there can be no log done item. */
@@ -260,7 +259,7 @@ xfs_defer_create_done(
 	 * 2.) shuts down the filesystem
 	 */
 	tp->t_flags |= XFS_TRANS_DIRTY;
-	lip = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+	lip = dfp->dfp_ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
 	if (!lip)
 		return;
 
@@ -281,13 +280,13 @@ xfs_defer_create_intent(
 	struct xfs_defer_pending	*dfp,
 	bool				sort)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 	struct xfs_log_item		*lip;
 
 	if (dfp->dfp_intent)
 		return 1;
 
-	lip = ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort);
+	lip = dfp->dfp_ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count,
+			sort);
 	if (!lip)
 		return 0;
 	if (IS_ERR(lip))
@@ -332,12 +331,10 @@ xfs_defer_pending_abort(
 	struct xfs_mount		*mp,
 	struct xfs_defer_pending	*dfp)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
-
 	trace_xfs_defer_pending_abort(mp, dfp);
 
 	if (dfp->dfp_intent && !dfp->dfp_done) {
-		ops->abort_intent(dfp->dfp_intent);
+		dfp->dfp_ops->abort_intent(dfp->dfp_intent);
 		dfp->dfp_intent = NULL;
 	}
 }
@@ -347,7 +344,6 @@ xfs_defer_pending_cancel_work(
 	struct xfs_mount		*mp,
 	struct xfs_defer_pending	*dfp)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 	struct list_head		*pwi;
 	struct list_head		*n;
 
@@ -358,7 +354,7 @@ xfs_defer_pending_cancel_work(
 		list_del(pwi);
 		dfp->dfp_count--;
 		trace_xfs_defer_cancel_item(mp, dfp, pwi);
-		ops->cancel_item(pwi);
+		dfp->dfp_ops->cancel_item(pwi);
 	}
 	ASSERT(dfp->dfp_count == 0);
 	kmem_cache_free(xfs_defer_pending_cache, dfp);
@@ -516,11 +512,10 @@ xfs_defer_relog_intent(
 	struct xfs_defer_pending	*dfp)
 {
 	struct xfs_log_item		*lip;
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 
 	xfs_defer_create_done(tp, dfp);
 
-	lip = ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done);
+	lip = dfp->dfp_ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done);
 	if (lip) {
 		xfs_trans_add_item(tp, lip);
 		set_bit(XFS_LI_DIRTY, &lip->li_flags);
@@ -587,7 +582,7 @@ xfs_defer_finish_one(
 	struct xfs_trans		*tp,
 	struct xfs_defer_pending	*dfp)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
 	struct xfs_btree_cur		*state = NULL;
 	struct list_head		*li, *n;
 	int				error;
@@ -784,7 +779,6 @@ xfs_defer_cancel(
 static inline struct xfs_defer_pending *
 xfs_defer_find_last(
 	struct xfs_trans		*tp,
-	enum xfs_defer_ops_type		type,
 	const struct xfs_defer_op_type	*ops)
 {
 	struct xfs_defer_pending	*dfp = NULL;
@@ -797,7 +791,7 @@ xfs_defer_find_last(
 			dfp_list);
 
 	/* Wrong type? */
-	if (dfp->dfp_type != type)
+	if (dfp->dfp_ops != ops)
 		return NULL;
 	return dfp;
 }
@@ -830,13 +824,13 @@ xfs_defer_can_append(
 static inline struct xfs_defer_pending *
 xfs_defer_alloc(
 	struct xfs_trans		*tp,
-	enum xfs_defer_ops_type		type)
+	const struct xfs_defer_op_type	*ops)
 {
 	struct xfs_defer_pending	*dfp;
 
 	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
 			GFP_NOFS | __GFP_NOFAIL);
-	dfp->dfp_type = type;
+	dfp->dfp_ops = ops;
 	INIT_LIST_HEAD(&dfp->dfp_work);
 	list_add_tail(&dfp->dfp_list, &tp->t_dfops);
 
@@ -856,9 +850,9 @@ xfs_defer_add(
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
 
-	dfp = xfs_defer_find_last(tp, type, ops);
+	dfp = xfs_defer_find_last(tp, ops);
 	if (!dfp || !xfs_defer_can_append(dfp, ops))
-		dfp = xfs_defer_alloc(tp, type);
+		dfp = xfs_defer_alloc(tp, ops);
 
 	xfs_defer_add_item(dfp, li);
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
@@ -874,17 +868,15 @@ xfs_defer_add_barrier(
 	struct xfs_trans		*tp)
 {
 	struct xfs_defer_pending	*dfp;
-	const enum xfs_defer_ops_type	type = XFS_DEFER_OPS_TYPE_BARRIER;
-	const struct xfs_defer_op_type	*ops = defer_op_types[type];
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 
 	/* If the last defer op added was a barrier, we're done. */
-	dfp = xfs_defer_find_last(tp, type, ops);
+	dfp = xfs_defer_find_last(tp, &xfs_barrier_defer_type);
 	if (dfp)
 		return;
 
-	xfs_defer_alloc(tp, type);
+	xfs_defer_alloc(tp, &xfs_barrier_defer_type);
 
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
 }
@@ -903,7 +895,7 @@ xfs_defer_start_recovery(
 
 	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
 			GFP_NOFS | __GFP_NOFAIL);
-	dfp->dfp_type = dfp_type;
+	dfp->dfp_ops = defer_op_types[dfp_type];
 	dfp->dfp_intent = lip;
 	INIT_LIST_HEAD(&dfp->dfp_work);
 	list_add_tail(&dfp->dfp_list, r_dfops);
@@ -929,13 +921,12 @@ xfs_defer_finish_recovery(
 	struct xfs_defer_pending	*dfp,
 	struct list_head		*capture_list)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 	int				error;
 
-	error = ops->recover_work(dfp, capture_list);
+	error = dfp->dfp_ops->recover_work(dfp, capture_list);
 	if (error)
 		trace_xlog_intent_recovery_failed(mp, error,
-				ops->recover_work);
+				dfp->dfp_ops->recover_work);
 	return error;
 }
 
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 5b1990ef3..957a06278 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -34,9 +34,9 @@ struct xfs_defer_pending {
 	struct list_head		dfp_work;	/* work items */
 	struct xfs_log_item		*dfp_intent;	/* log intent item */
 	struct xfs_log_item		*dfp_done;	/* log done item */
+	const struct xfs_defer_op_type	*dfp_ops;
 	unsigned int			dfp_count;	/* # extent items */
 	unsigned int			dfp_flags;
-	enum xfs_defer_ops_type		dfp_type;
 };
 
 /*
@@ -61,6 +61,8 @@ void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
 struct xfs_defer_op_type {
+	const char		*name;
+	unsigned int		max_items;
 	struct xfs_log_item *(*create_intent)(struct xfs_trans *tp,
 			struct list_head *items, unsigned int count, bool sort);
 	void (*abort_intent)(struct xfs_log_item *intent);
@@ -76,7 +78,6 @@ struct xfs_defer_op_type {
 	struct xfs_log_item *(*relog_intent)(struct xfs_trans *tp,
 			struct xfs_log_item *intent,
 			struct xfs_log_item *done_item);
-	unsigned int		max_items;
 };
 
 extern const struct xfs_defer_op_type xfs_bmap_update_defer_type;
-- 
2.44.0

[PATCH 27/67] xfs: pass the defer ops instead of type to xfs_defer_start_recovery

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: dc22af64368291a86fb6b7eb2adab21c815836b7

xfs_defer_start_recovery is only called from xlog_recover_intent_item,
and the callers of that all have the actual xfs_defer_ops_type operation
vector at hand.  Pass that directly instead of looking it up from the
defer_op_types table.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 6 +++---
 libxfs/xfs_defer.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index bb5411b84..033283017 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -888,14 +888,14 @@ xfs_defer_add_barrier(
 void
 xfs_defer_start_recovery(
 	struct xfs_log_item		*lip,
-	enum xfs_defer_ops_type		dfp_type,
-	struct list_head		*r_dfops)
+	struct list_head		*r_dfops,
+	const struct xfs_defer_op_type	*ops)
 {
 	struct xfs_defer_pending	*dfp;
 
 	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
 			GFP_NOFS | __GFP_NOFAIL);
-	dfp->dfp_ops = defer_op_types[dfp_type];
+	dfp->dfp_ops = ops;
 	dfp->dfp_intent = lip;
 	INIT_LIST_HEAD(&dfp->dfp_work);
 	list_add_tail(&dfp->dfp_list, r_dfops);
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 957a06278..60de91b66 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -147,7 +147,7 @@ void xfs_defer_ops_capture_abort(struct xfs_mount *mp,
 void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
 
 void xfs_defer_start_recovery(struct xfs_log_item *lip,
-		enum xfs_defer_ops_type dfp_type, struct list_head *r_dfops);
+		struct list_head *r_dfops, const struct xfs_defer_op_type *ops);
 void xfs_defer_cancel_recovery(struct xfs_mount *mp,
 		struct xfs_defer_pending *dfp);
 int xfs_defer_finish_recovery(struct xfs_mount *mp,
-- 
2.44.0

[PATCH 28/67] xfs: pass the defer ops directly to xfs_defer_add

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 603ce8ab12094a2d9483c79a7541335e258a5328

Pass a pointer to the xfs_defer_op_type structure to xfs_defer_add and
remove the indirection through the xfs_defer_ops_type enum and a global
table of all possible operations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_alloc.c    |  4 ++--
 libxfs/xfs_attr.c     |  2 +-
 libxfs/xfs_bmap.c     |  2 +-
 libxfs/xfs_defer.c    | 16 ++--------------
 libxfs/xfs_defer.h    | 18 ++----------------
 libxfs/xfs_refcount.c |  2 +-
 libxfs/xfs_rmap.c     |  2 +-
 7 files changed, 10 insertions(+), 36 deletions(-)

diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index 463381be7..aaa159615 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -2510,7 +2510,7 @@ xfs_defer_agfl_block(
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
 	xfs_extent_free_get_group(mp, xefi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list);
+	xfs_defer_add(tp, &xefi->xefi_list, &xfs_agfl_free_defer_type);
 	return 0;
 }
 
@@ -2574,7 +2574,7 @@ xfs_defer_extent_free(
 			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
 
 	xfs_extent_free_get_group(mp, xefi);
-	*dfpp = xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
+	*dfpp = xfs_defer_add(tp, &xefi->xefi_list, &xfs_extent_free_defer_type);
 	return 0;
 }
 
diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index 550ca6b2e..cb6c8d081 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -904,7 +904,7 @@ xfs_attr_defer_add(
 		ASSERT(0);
 	}
 
-	xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
+	xfs_defer_add(args->trans, &new->xattri_list, &xfs_attr_defer_type);
 	trace_xfs_attr_defer_add(new->xattri_dela_state, args->dp);
 }
 
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 20ec22dfc..6d23c5e3e 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -6085,7 +6085,7 @@ __xfs_bmap_add(
 	bi->bi_bmap = *bmap;
 
 	xfs_bmap_update_get_group(tp->t_mountp, bi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
+	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
 	return 0;
 }
 
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 033283017..077e99298 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -229,16 +229,6 @@ static const struct xfs_defer_op_type xfs_barrier_defer_type = {
 	.cancel_item	= xfs_defer_barrier_cancel_item,
 };
 
-static const struct xfs_defer_op_type *defer_op_types[] = {
-	[XFS_DEFER_OPS_TYPE_BMAP]	= &xfs_bmap_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_REFCOUNT]	= &xfs_refcount_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_RMAP]	= &xfs_rmap_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_FREE]	= &xfs_extent_free_defer_type,
-	[XFS_DEFER_OPS_TYPE_AGFL_FREE]	= &xfs_agfl_free_defer_type,
-	[XFS_DEFER_OPS_TYPE_ATTR]	= &xfs_attr_defer_type,
-	[XFS_DEFER_OPS_TYPE_BARRIER]	= &xfs_barrier_defer_type,
-};
-
 /* Create a log intent done item for a log intent item. */
 static inline void
 xfs_defer_create_done(
@@ -841,14 +831,12 @@ xfs_defer_alloc(
 struct xfs_defer_pending *
 xfs_defer_add(
 	struct xfs_trans		*tp,
-	enum xfs_defer_ops_type		type,
-	struct list_head		*li)
+	struct list_head		*li,
+	const struct xfs_defer_op_type	*ops)
 {
 	struct xfs_defer_pending	*dfp = NULL;
-	const struct xfs_defer_op_type	*ops = defer_op_types[type];
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
-	BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
 
 	dfp = xfs_defer_find_last(tp, ops);
 	if (!dfp || !xfs_defer_can_append(dfp, ops))
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 60de91b66..18a9fb92d 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -10,20 +10,6 @@ struct xfs_btree_cur;
 struct xfs_defer_op_type;
 struct xfs_defer_capture;
 
-/*
- * Header for deferred operation list.
- */
-enum xfs_defer_ops_type {
-	XFS_DEFER_OPS_TYPE_BMAP,
-	XFS_DEFER_OPS_TYPE_REFCOUNT,
-	XFS_DEFER_OPS_TYPE_RMAP,
-	XFS_DEFER_OPS_TYPE_FREE,
-	XFS_DEFER_OPS_TYPE_AGFL_FREE,
-	XFS_DEFER_OPS_TYPE_ATTR,
-	XFS_DEFER_OPS_TYPE_BARRIER,
-	XFS_DEFER_OPS_TYPE_MAX,
-};
-
 /*
  * Save a log intent item and a list of extents, so that we can replay
  * whatever action had to happen to the extent list and file the log done
@@ -51,8 +37,8 @@ struct xfs_defer_pending {
 void xfs_defer_item_pause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
 void xfs_defer_item_unpause(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
 
-struct xfs_defer_pending *xfs_defer_add(struct xfs_trans *tp,
-		enum xfs_defer_ops_type type, struct list_head *h);
+struct xfs_defer_pending *xfs_defer_add(struct xfs_trans *tp, struct list_head *h,
+		const struct xfs_defer_op_type *ops);
 int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
 int xfs_defer_finish_one(struct xfs_trans *tp, struct xfs_defer_pending *dfp);
diff --git a/libxfs/xfs_refcount.c b/libxfs/xfs_refcount.c
index 2284b45fb..45f8134e4 100644
--- a/libxfs/xfs_refcount.c
+++ b/libxfs/xfs_refcount.c
@@ -1457,7 +1457,7 @@ __xfs_refcount_add(
 	ri->ri_blockcount = blockcount;
 
 	xfs_refcount_update_get_group(tp->t_mountp, ri);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
+	xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type);
 }
 
 /*
diff --git a/libxfs/xfs_rmap.c b/libxfs/xfs_rmap.c
index 5ff6d7a32..4731e10d2 100644
--- a/libxfs/xfs_rmap.c
+++ b/libxfs/xfs_rmap.c
@@ -2566,7 +2566,7 @@ __xfs_rmap_add(
 	ri->ri_bmap = *bmap;
 
 	xfs_rmap_update_get_group(tp->t_mountp, ri);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
+	xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type);
 }
 
 /* Map an extent into a file. */
-- 
2.44.0

[PATCH 29/67] xfs: force all buffers to be written during btree bulk load

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 13ae04d8d45227c2ba51e188daf9fc13d08a1b12

While stress-testing online repair of btrees, I noticed periodic
assertion failures from the buffer cache about buffers with incorrect
DELWRI_Q state.  Looking further, I observed this race between the AIL
trying to write out a btree block and repair zapping a btree block after
the fact:

AIL:    Repair0:

pin buffer X
delwri_queue:
set DELWRI_Q
add to delwri list

stale buf X:
clear DELWRI_Q
does not clear b_list
free space X

delwri_submit   # oops

Worse yet, I discovered that running the same repair over and over in a
tight loop can result in a second race that cause data integrity
problems with the repair:

AIL:    Repair0:        Repair1:

pin buffer X
delwri_queue:
set DELWRI_Q
add to delwri list

stale buf X:
clear DELWRI_Q
does not clear b_list
free space X

find free space X
get buffer
rewrite buffer
delwri_queue:
set DELWRI_Q
already on a list, do not add

BAD: committed tree root before all blocks written

delwri_submit   # too late now

I traced this to my own misunderstanding of how the delwri lists work,
particularly with regards to the AIL's buffer list.  If a buffer is
logged and committed, the buffer can end up on that AIL buffer list.  If
btree repairs are run twice in rapid succession, it's possible that the
first repair will invalidate the buffer and free it before the next time
the AIL wakes up.  Marking the buffer stale clears DELWRI_Q from the
buffer state without removing the buffer from its delwri list.  The
buffer doesn't know which list it's on, so it cannot know which lock to
take to protect the list for a removal.

If the second repair allocates the same block, it will then recycle the
buffer to start writing the new btree block.  Meanwhile, if the AIL
wakes up and walks the buffer list, it will ignore the buffer because it
can't lock it, and go back to sleep.

When the second repair calls delwri_queue to put the buffer on the
list of buffers to write before committing the new btree, it will set
DELWRI_Q again, but since the buffer hasn't been removed from the AIL's
buffer list, it won't add it to the bulkload buffer's list.

This is incorrect, because the bulkload caller relies on delwri_submit
to ensure that all the buffers have been sent to disk /before/
required for data consistency.

Worse, the AIL won't clear DELWRI_Q from the buffer when it does finally
drop it, so the next thread to walk through the btree will trip over a
debug assertion on that flag.

To fix this, create a new function that waits for the buffer to be
removed from any other delwri lists before adding the buffer to the
caller's delwri list.  By waiting for the buffer to clear both the
delwri list and any potential delwri wait list, we can be sure that
repair will initiate writes of all buffers and report all write errors
back to userspace instead of committing the new structure.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/libxfs_io.h         | 11 +++++++++++
 libxfs/xfs_btree_staging.c |  4 +---
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/libxfs/libxfs_io.h b/libxfs/libxfs_io.h
index 267ea9796..259c6a7cf 100644
--- a/libxfs/libxfs_io.h
+++ b/libxfs/libxfs_io.h
@@ -244,6 +244,17 @@ xfs_buf_delwri_queue(struct xfs_buf *bp, struct list_head *buffer_list)
 	return true;
 }
 
+static inline void
+xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *buffer_list)
+{
+	ASSERT(list_empty(&bp->b_list));
+
+	/* This buffer is uptodate; don't let it get reread. */
+	libxfs_buf_mark_dirty(bp);
+
+	xfs_buf_delwri_queue(bp, buffer_list);
+}
+
 int xfs_buf_delwri_submit(struct list_head *buffer_list);
 void xfs_buf_delwri_cancel(struct list_head *list);
 
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index a6a907916..baf7f4226 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -342,9 +342,7 @@ xfs_btree_bload_drop_buf(
 	if (*bpp == NULL)
 		return;
 
-	if (!xfs_buf_delwri_queue(*bpp, buffers_list))
-		ASSERT(0);
-
+	xfs_buf_delwri_queue_here(*bpp, buffers_list);
 	xfs_buf_relse(*bpp);
 	*bpp = NULL;
 }
-- 
2.44.0

[PATCH 30/67] xfs: set XBF_DONE on newly formatted btree block that are ready for writing

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: c1e0f8e6fb060b23b6f1b82eb4265983f7d271f8

The btree bulkloading code calls xfs_buf_delwri_queue_here when it has
finished formatting a new btree block and wants to queue it to be
written to disk.  Once the new btree root has been committed, the blocks
(and hence the buffers) will be accessible to the rest of the
filesystem.  Mark each new buffer as DONE when adding it to the delwri
list so that the next btree traversal can skip reloading the contents
from disk.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_btree_staging.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index baf7f4226..ae2d9c63f 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -342,6 +342,12 @@ xfs_btree_bload_drop_buf(
 	if (*bpp == NULL)
 		return;
 
+	/*
+	 * Mark this buffer XBF_DONE (i.e. uptodate) so that a subsequent
+	 * xfs_buf_read will not pointlessly reread the contents from the disk.
+	 */
+	(*bpp)->b_flags |= XBF_DONE;
+
 	xfs_buf_delwri_queue_here(*bpp, buffers_list);
 	xfs_buf_relse(*bpp);
 	*bpp = NULL;
-- 
2.44.0

[PATCH 31/67] xfs: read leaf blocks when computing keys for bulkloading into node blocks

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 26de64629d8b439a03bce243f14a46f7440729f3

When constructing a new btree, xfs_btree_bload_node needs to read the
btree blocks for level N to compute the keyptrs for the blocks that will
be loaded into level N+1.  The level N blocks must be formatted at that
point.

A subsequent patch will change the btree bulkloader to write new btree
blocks in 256K chunks to moderate memory consumption if the new btree is
very large.  As a consequence of that, it's possible that the buffers
for lower level blocks might have been reclaimed by the time the node
builder comes back to the block.

Therefore, change xfs_btree_bload_node to read the lower level blocks
to handle the reclaimed buffer case.  As a side effect, the read will
increase the LRU refs, which will bias towards keeping new btree buffers
in memory after the new btree commits.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_btree.c         | 2 +-
 libxfs/xfs_btree.h         | 3 +++
 libxfs/xfs_btree_staging.c | 7 ++++++-
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 85f8bef06..97962fc16 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -1327,7 +1327,7 @@ xfs_btree_get_buf_block(
  * Read in the buffer at the given ptr and return the buffer and
  * the block pointer within the buffer.
  */
-STATIC int
+int
 xfs_btree_read_buf_block(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_ptr	*ptr,
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index 4d68a58be..e0875cec4 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -700,6 +700,9 @@ void xfs_btree_set_ptr_null(struct xfs_btree_cur *cur,
 int xfs_btree_get_buf_block(struct xfs_btree_cur *cur,
 		const union xfs_btree_ptr *ptr, struct xfs_btree_block **block,
 		struct xfs_buf **bpp);
+int xfs_btree_read_buf_block(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int flags,
+		struct xfs_btree_block **block, struct xfs_buf **bpp);
 void xfs_btree_set_sibling(struct xfs_btree_cur *cur,
 		struct xfs_btree_block *block, const union xfs_btree_ptr *ptr,
 		int lr);
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index ae2d9c63f..be0b43e45 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -489,7 +489,12 @@ xfs_btree_bload_node(
 
 		ASSERT(!xfs_btree_ptr_is_null(cur, child_ptr));
 
-		ret = xfs_btree_get_buf_block(cur, child_ptr, &child_block,
+		/*
+		 * Read the lower-level block in case the buffer for it has
+		 * been reclaimed.  LRU refs will be set on the block, which is
+		 * desirable if the new btree commits.
+		 */
+		ret = xfs_btree_read_buf_block(cur, child_ptr, 0, &child_block,
 				&child_bp);
 		if (ret)
 			return ret;
-- 
2.44.0

[PATCH 32/67] xfs: move btree bulkload record initialization to ->get_record implementations

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 6dfeb0c2ecde71d61af77f65eabbdd6ca9315161

When we're performing a bulk load of a btree, move the code that
actually stores the btree record in the new btree block out of the
generic code and into the individual ->get_record implementations.
This is preparation for being able to store multiple records with a
single indirect call.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/libxfs_api_defs.h   |  1 +
 libxfs/xfs_btree_staging.c | 17 +++++-------
 libxfs/xfs_btree_staging.h | 15 ++++++----
 repair/agbtree.c           | 56 ++++++++++++++++++++++++++++----------
 4 files changed, 60 insertions(+), 29 deletions(-)

diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 836ace1ba..4edc8a7e1 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -53,6 +53,7 @@
 #define xfs_btree_bload_compute_geometry libxfs_btree_bload_compute_geometry
 #define xfs_btree_del_cursor		libxfs_btree_del_cursor
 #define xfs_btree_init_block		libxfs_btree_init_block
+#define xfs_btree_rec_addr		libxfs_btree_rec_addr
 #define xfs_buf_delwri_submit		libxfs_buf_delwri_submit
 #define xfs_buf_get			libxfs_buf_get
 #define xfs_buf_get_uncached		libxfs_buf_get_uncached
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index be0b43e45..a6f0d7d3b 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -440,22 +440,19 @@ STATIC int
 xfs_btree_bload_leaf(
 	struct xfs_btree_cur		*cur,
 	unsigned int			recs_this_block,
-	xfs_btree_bload_get_record_fn	get_record,
+	xfs_btree_bload_get_records_fn	get_records,
 	struct xfs_btree_block		*block,
 	void				*priv)
 {
-	unsigned int			j;
+	unsigned int			j = 1;
 	int				ret;
 
 	/* Fill the leaf block with records. */
-	for (j = 1; j <= recs_this_block; j++) {
-		union xfs_btree_rec	*block_rec;
-
-		ret = get_record(cur, priv);
-		if (ret)
+	while (j <= recs_this_block) {
+		ret = get_records(cur, j, block, recs_this_block - j + 1, priv);
+		if (ret < 0)
 			return ret;
-		block_rec = xfs_btree_rec_addr(cur, j, block);
-		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+		j += ret;
 	}
 
 	return 0;
@@ -798,7 +795,7 @@ xfs_btree_bload(
 		trace_xfs_btree_bload_block(cur, level, i, blocks, &ptr,
 				nr_this_block);
 
-		ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_record,
+		ret = xfs_btree_bload_leaf(cur, nr_this_block, bbl->get_records,
 				block, priv);
 		if (ret)
 			goto out;
diff --git a/libxfs/xfs_btree_staging.h b/libxfs/xfs_btree_staging.h
index 5f638f711..bd5b3f004 100644
--- a/libxfs/xfs_btree_staging.h
+++ b/libxfs/xfs_btree_staging.h
@@ -47,7 +47,9 @@ void xfs_btree_commit_ifakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp,
 		int whichfork, const struct xfs_btree_ops *ops);
 
 /* Bulk loading of staged btrees. */
-typedef int (*xfs_btree_bload_get_record_fn)(struct xfs_btree_cur *cur, void *priv);
+typedef int (*xfs_btree_bload_get_records_fn)(struct xfs_btree_cur *cur,
+		unsigned int idx, struct xfs_btree_block *block,
+		unsigned int nr_wanted, void *priv);
 typedef int (*xfs_btree_bload_claim_block_fn)(struct xfs_btree_cur *cur,
 		union xfs_btree_ptr *ptr, void *priv);
 typedef size_t (*xfs_btree_bload_iroot_size_fn)(struct xfs_btree_cur *cur,
@@ -55,11 +57,14 @@ typedef size_t (*xfs_btree_bload_iroot_size_fn)(struct xfs_btree_cur *cur,
 
 struct xfs_btree_bload {
 	/*
-	 * This function will be called nr_records times to load records into
-	 * the btree.  The function does this by setting the cursor's bc_rec
-	 * field in in-core format.  Records must be returned in sort order.
+	 * This function will be called to load @nr_wanted records into the
+	 * btree.  The implementation does this by setting the cursor's bc_rec
+	 * field in in-core format and using init_rec_from_cur to set the
+	 * records in the btree block.  Records must be returned in sort order.
+	 * The function must return the number of records loaded or the usual
+	 * negative errno.
 	 */
-	xfs_btree_bload_get_record_fn	get_record;
+	xfs_btree_bload_get_records_fn	get_records;
 
 	/*
 	 * This function will be called nr_blocks times to obtain a pointer
diff --git a/repair/agbtree.c b/repair/agbtree.c
index 7211765d3..10a0c7e48 100644
--- a/repair/agbtree.c
+++ b/repair/agbtree.c
@@ -209,18 +209,25 @@ get_bno_rec(
 
 /* Grab one bnobt record and put it in the btree cursor. */
 static int
-get_bnobt_record(
+get_bnobt_records(
 	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
 	void				*priv)
 {
 	struct bt_rebuild		*btr = priv;
 	struct xfs_alloc_rec_incore	*arec = &cur->bc_rec.a;
+	union xfs_btree_rec		*block_rec;
 
 	btr->bno_rec = get_bno_rec(cur, btr->bno_rec);
 	arec->ar_startblock = btr->bno_rec->ex_startblock;
 	arec->ar_blockcount = btr->bno_rec->ex_blockcount;
 	btr->freeblks += btr->bno_rec->ex_blockcount;
-	return 0;
+
+	block_rec = libxfs_btree_rec_addr(cur, idx, block);
+	cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	return 1;
 }
 
 void
@@ -247,10 +254,10 @@ init_freespace_cursors(
 	btr_cnt->cur = libxfs_allocbt_stage_cursor(sc->mp,
 			&btr_cnt->newbt.afake, pag, XFS_BTNUM_CNT);
 
-	btr_bno->bload.get_record = get_bnobt_record;
+	btr_bno->bload.get_records = get_bnobt_records;
 	btr_bno->bload.claim_block = rebuild_claim_block;
 
-	btr_cnt->bload.get_record = get_bnobt_record;
+	btr_cnt->bload.get_records = get_bnobt_records;
 	btr_cnt->bload.claim_block = rebuild_claim_block;
 
 	/*
@@ -371,13 +378,17 @@ get_ino_rec(
 
 /* Grab one inobt record. */
 static int
-get_inobt_record(
+get_inobt_records(
 	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
 	void				*priv)
 {
 	struct bt_rebuild		*btr = priv;
 	struct xfs_inobt_rec_incore	*irec = &cur->bc_rec.i;
 	struct ino_tree_node		*ino_rec;
+	union xfs_btree_rec		*block_rec;
 	int				inocnt = 0;
 	int				finocnt = 0;
 	int				k;
@@ -431,7 +442,10 @@ get_inobt_record(
 		btr->first_agino = ino_rec->ino_startnum;
 	btr->freecount += finocnt;
 	btr->count += inocnt;
-	return 0;
+
+	block_rec = libxfs_btree_rec_addr(cur, idx, block);
+	cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	return 1;
 }
 
 /* Initialize both inode btree cursors as needed. */
@@ -490,7 +504,7 @@ init_ino_cursors(
 	btr_ino->cur = libxfs_inobt_stage_cursor(pag, &btr_ino->newbt.afake,
 			XFS_BTNUM_INO);
 
-	btr_ino->bload.get_record = get_inobt_record;
+	btr_ino->bload.get_records = get_inobt_records;
 	btr_ino->bload.claim_block = rebuild_claim_block;
 	btr_ino->first_agino = NULLAGINO;
 
@@ -510,7 +524,7 @@ _("Unable to compute inode btree geometry, error %d.\n"), error);
 	btr_fino->cur = libxfs_inobt_stage_cursor(pag,
 			&btr_fino->newbt.afake, XFS_BTNUM_FINO);
 
-	btr_fino->bload.get_record = get_inobt_record;
+	btr_fino->bload.get_records = get_inobt_records;
 	btr_fino->bload.claim_block = rebuild_claim_block;
 	btr_fino->first_agino = NULLAGINO;
 
@@ -560,16 +574,23 @@ _("Error %d while creating finobt btree for AG %u.\n"), error, agno);
 
 /* Grab one rmap record. */
 static int
-get_rmapbt_record(
+get_rmapbt_records(
 	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
 	void				*priv)
 {
 	struct xfs_rmap_irec		*rec;
 	struct bt_rebuild		*btr = priv;
+	union xfs_btree_rec		*block_rec;
 
 	rec = pop_slab_cursor(btr->slab_cursor);
 	memcpy(&cur->bc_rec.r, rec, sizeof(struct xfs_rmap_irec));
-	return 0;
+
+	block_rec = libxfs_btree_rec_addr(cur, idx, block);
+	cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	return 1;
 }
 
 /* Set up the rmap rebuild parameters. */
@@ -589,7 +610,7 @@ init_rmapbt_cursor(
 	init_rebuild(sc, &XFS_RMAP_OINFO_AG, est_agfreeblocks, btr);
 	btr->cur = libxfs_rmapbt_stage_cursor(sc->mp, &btr->newbt.afake, pag);
 
-	btr->bload.get_record = get_rmapbt_record;
+	btr->bload.get_records = get_rmapbt_records;
 	btr->bload.claim_block = rebuild_claim_block;
 
 	/* Compute how many blocks we'll need. */
@@ -631,16 +652,23 @@ _("Error %d while creating rmap btree for AG %u.\n"), error, agno);
 
 /* Grab one refcount record. */
 static int
-get_refcountbt_record(
+get_refcountbt_records(
 	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
 	void				*priv)
 {
 	struct xfs_refcount_irec	*rec;
 	struct bt_rebuild		*btr = priv;
+	union xfs_btree_rec		*block_rec;
 
 	rec = pop_slab_cursor(btr->slab_cursor);
 	memcpy(&cur->bc_rec.rc, rec, sizeof(struct xfs_refcount_irec));
-	return 0;
+
+	block_rec = libxfs_btree_rec_addr(cur, idx, block);
+	cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	return 1;
 }
 
 /* Set up the refcount rebuild parameters. */
@@ -661,7 +689,7 @@ init_refc_cursor(
 	btr->cur = libxfs_refcountbt_stage_cursor(sc->mp, &btr->newbt.afake,
 			pag);
 
-	btr->bload.get_record = get_refcountbt_record;
+	btr->bload.get_records = get_refcountbt_records;
 	btr->bload.claim_block = rebuild_claim_block;
 
 	/* Compute how many blocks we'll need. */
-- 
2.44.0

[PATCH 33/67] xfs: constrain dirty buffers while formatting a staged btree

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: e069d549705e49841247acf9b3176744e27d5425

Constrain the number of dirty buffers that are locked by the btree
staging code at any given time by establishing a threshold at which we
put them all on the delwri queue and push them to disk.  This limits
memory consumption while writing out new btrees.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_btree_staging.c | 50 +++++++++++++++++++++++++++++---------
 libxfs/xfs_btree_staging.h | 10 ++++++++
 repair/agbtree.c           |  1 +
 3 files changed, 50 insertions(+), 11 deletions(-)

diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index a6f0d7d3b..d4164e37b 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -333,24 +333,41 @@ xfs_btree_commit_ifakeroot(
 /*
  * Put a btree block that we're loading onto the ordered list and release it.
  * The btree blocks will be written to disk when bulk loading is finished.
+ * If we reach the dirty buffer threshold, flush them to disk before
+ * continuing.
  */
-static void
+static int
 xfs_btree_bload_drop_buf(
-	struct list_head	*buffers_list,
-	struct xfs_buf		**bpp)
+	struct xfs_btree_bload		*bbl,
+	struct list_head		*buffers_list,
+	struct xfs_buf			**bpp)
 {
-	if (*bpp == NULL)
-		return;
+	struct xfs_buf			*bp = *bpp;
+	int				error;
+
+	if (!bp)
+		return 0;
 
 	/*
 	 * Mark this buffer XBF_DONE (i.e. uptodate) so that a subsequent
 	 * xfs_buf_read will not pointlessly reread the contents from the disk.
 	 */
-	(*bpp)->b_flags |= XBF_DONE;
+	bp->b_flags |= XBF_DONE;
 
-	xfs_buf_delwri_queue_here(*bpp, buffers_list);
-	xfs_buf_relse(*bpp);
+	xfs_buf_delwri_queue_here(bp, buffers_list);
+	xfs_buf_relse(bp);
 	*bpp = NULL;
+	bbl->nr_dirty++;
+
+	if (!bbl->max_dirty || bbl->nr_dirty < bbl->max_dirty)
+		return 0;
+
+	error = xfs_buf_delwri_submit(buffers_list);
+	if (error)
+		return error;
+
+	bbl->nr_dirty = 0;
+	return 0;
 }
 
 /*
@@ -422,7 +439,10 @@ xfs_btree_bload_prep_block(
 	 */
 	if (*blockp)
 		xfs_btree_set_sibling(cur, *blockp, &new_ptr, XFS_BB_RIGHTSIB);
-	xfs_btree_bload_drop_buf(buffers_list, bpp);
+
+	ret = xfs_btree_bload_drop_buf(bbl, buffers_list, bpp);
+	if (ret)
+		return ret;
 
 	/* Initialize the new btree block. */
 	xfs_btree_init_block_cur(cur, new_bp, level, nr_this_block);
@@ -770,6 +790,7 @@ xfs_btree_bload(
 	cur->bc_nlevels = bbl->btree_height;
 	xfs_btree_set_ptr_null(cur, &child_ptr);
 	xfs_btree_set_ptr_null(cur, &ptr);
+	bbl->nr_dirty = 0;
 
 	xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level,
 			&avg_per_block, &blocks, &blocks_with_extra);
@@ -808,7 +829,10 @@ xfs_btree_bload(
 			xfs_btree_copy_ptrs(cur, &child_ptr, &ptr, 1);
 	}
 	total_blocks += blocks;
-	xfs_btree_bload_drop_buf(&buffers_list, &bp);
+
+	ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp);
+	if (ret)
+		goto out;
 
 	/* Populate the internal btree nodes. */
 	for (level = 1; level < cur->bc_nlevels; level++) {
@@ -850,7 +874,11 @@ xfs_btree_bload(
 				xfs_btree_copy_ptrs(cur, &first_ptr, &ptr, 1);
 		}
 		total_blocks += blocks;
-		xfs_btree_bload_drop_buf(&buffers_list, &bp);
+
+		ret = xfs_btree_bload_drop_buf(bbl, &buffers_list, &bp);
+		if (ret)
+			goto out;
+
 		xfs_btree_copy_ptrs(cur, &child_ptr, &first_ptr, 1);
 	}
 
diff --git a/libxfs/xfs_btree_staging.h b/libxfs/xfs_btree_staging.h
index bd5b3f004..f0a500728 100644
--- a/libxfs/xfs_btree_staging.h
+++ b/libxfs/xfs_btree_staging.h
@@ -112,6 +112,16 @@ struct xfs_btree_bload {
 	 * height of the new btree.
 	 */
 	unsigned int			btree_height;
+
+	/*
+	 * Flush the new btree block buffer list to disk after this many blocks
+	 * have been formatted.  Zero prohibits writing any buffers until all
+	 * blocks have been formatted.
+	 */
+	uint16_t			max_dirty;
+
+	/* Number of dirty buffers. */
+	uint16_t			nr_dirty;
 };
 
 int xfs_btree_bload_compute_geometry(struct xfs_btree_cur *cur,
diff --git a/repair/agbtree.c b/repair/agbtree.c
index 10a0c7e48..981d8e340 100644
--- a/repair/agbtree.c
+++ b/repair/agbtree.c
@@ -23,6 +23,7 @@ init_rebuild(
 	memset(btr, 0, sizeof(struct bt_rebuild));
 
 	bulkload_init_ag(&btr->newbt, sc, oinfo);
+	btr->bload.max_dirty = XFS_B_TO_FSBT(sc->mp, 256U << 10); /* 256K */
 	bulkload_estimate_ag_slack(sc, &btr->bload, est_agfreeblocks);
 }
 
-- 
2.44.0

[PATCH 34/67] xfs: repair free space btrees

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 4bdfd7d15747b170ce93a06fafccaf20544b6684

Rebuild the free space btrees from the gaps in the rmap btree.  Refer to
the case study in Documentation/filesystems/xfs-online-fsck-design.rst
for more details.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_ag.h          |  9 +++++++++
 libxfs/xfs_ag_resv.c     |  2 ++
 libxfs/xfs_alloc.c       | 10 ++++------
 libxfs/xfs_alloc.h       |  2 +-
 libxfs/xfs_alloc_btree.c | 13 ++++++++++++-
 libxfs/xfs_types.h       |  7 +++++++
 6 files changed, 35 insertions(+), 8 deletions(-)

diff --git a/libxfs/xfs_ag.h b/libxfs/xfs_ag.h
index 2e0aef87d..f16cb7a17 100644
--- a/libxfs/xfs_ag.h
+++ b/libxfs/xfs_ag.h
@@ -80,6 +80,15 @@ struct xfs_perag {
 	 */
 	uint16_t	pag_checked;
 	uint16_t	pag_sick;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+	/*
+	 * Alternate btree heights so that online repair won't trip the write
+	 * verifiers while rebuilding the AG btrees.
+	 */
+	uint8_t		pagf_repair_levels[XFS_BTNUM_AGF];
+#endif
+
 	spinlock_t	pag_state_lock;
 
 	spinlock_t	pagb_lock;	/* lock for pagb_tree */
diff --git a/libxfs/xfs_ag_resv.c b/libxfs/xfs_ag_resv.c
index 29bbcb55d..3a80b1613 100644
--- a/libxfs/xfs_ag_resv.c
+++ b/libxfs/xfs_ag_resv.c
@@ -410,6 +410,8 @@ xfs_ag_resv_free_extent(
 		fallthrough;
 	case XFS_AG_RESV_NONE:
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (int64_t)len);
+		fallthrough;
+	case XFS_AG_RESV_IGNORE:
 		return;
 	}
 
diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index aaa159615..352efbeca 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -242,11 +242,9 @@ xfs_alloc_btrec_to_irec(
 /* Simple checks for free space records. */
 xfs_failaddr_t
 xfs_alloc_check_irec(
-	struct xfs_btree_cur		*cur,
-	const struct xfs_alloc_rec_incore *irec)
+	struct xfs_perag			*pag,
+	const struct xfs_alloc_rec_incore	*irec)
 {
-	struct xfs_perag		*pag = cur->bc_ag.pag;
-
 	if (irec->ar_blockcount == 0)
 		return __this_address;
 
@@ -295,7 +293,7 @@ xfs_alloc_get_rec(
 		return error;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur, &irec);
+	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
@@ -3940,7 +3938,7 @@ xfs_alloc_query_range_helper(
 	xfs_failaddr_t				fa;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur, &irec);
+	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
diff --git a/libxfs/xfs_alloc.h b/libxfs/xfs_alloc.h
index 851cafbd6..0b956f8b9 100644
--- a/libxfs/xfs_alloc.h
+++ b/libxfs/xfs_alloc.h
@@ -185,7 +185,7 @@ xfs_alloc_get_rec(
 union xfs_btree_rec;
 void xfs_alloc_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_alloc_rec_incore *irec);
-xfs_failaddr_t xfs_alloc_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_alloc_check_irec(struct xfs_perag *pag,
 		const struct xfs_alloc_rec_incore *irec);
 
 int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
diff --git a/libxfs/xfs_alloc_btree.c b/libxfs/xfs_alloc_btree.c
index 5ec14288d..a472ec6d2 100644
--- a/libxfs/xfs_alloc_btree.c
+++ b/libxfs/xfs_alloc_btree.c
@@ -321,7 +321,18 @@ xfs_allocbt_verify(
 	if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC))
 		btnum = XFS_BTNUM_CNTi;
 	if (pag && xfs_perag_initialised_agf(pag)) {
-		if (level >= pag->pagf_levels[btnum])
+		unsigned int	maxlevel = pag->pagf_levels[btnum];
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+		/*
+		 * Online repair could be rewriting the free space btrees, so
+		 * we'll validate against the larger of either tree while this
+		 * is going on.
+		 */
+		maxlevel = max_t(unsigned int, maxlevel,
+				 pag->pagf_repair_levels[btnum]);
+#endif
+		if (level >= maxlevel)
 			return __this_address;
 	} else if (level >= mp->m_alloc_maxlevels)
 		return __this_address;
diff --git a/libxfs/xfs_types.h b/libxfs/xfs_types.h
index 533200c4c..035bf703d 100644
--- a/libxfs/xfs_types.h
+++ b/libxfs/xfs_types.h
@@ -208,6 +208,13 @@ enum xfs_ag_resv_type {
 	XFS_AG_RESV_AGFL,
 	XFS_AG_RESV_METADATA,
 	XFS_AG_RESV_RMAPBT,
+
+	/*
+	 * Don't increase fdblocks when freeing extent.  This is a pony for
+	 * the bnobt repair functions to re-free the free space without
+	 * altering fdblocks.  If you think you need this you're wrong.
+	 */
+	XFS_AG_RESV_IGNORE,
 };
 
 /* Results of scanning a btree keyspace to check occupancy. */
-- 
2.44.0

[PATCH 35/67] xfs: repair inode btrees

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: dbfbf3bdf639a20da7d5fb390cd2e197d25aa418

Use the rmapbt to find inode chunks, query the chunks to compute hole
and free masks, and with that information rebuild the inobt and finobt.
Refer to the case study in
Documentation/filesystems/xfs-online-fsck-design.rst for more details.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_ialloc.c | 31 ++++++++++++++++++-------------
 libxfs/xfs_ialloc.h |  3 ++-
 2 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index 14826280d..5ff09c8c9 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -90,18 +90,28 @@ xfs_inobt_btrec_to_irec(
 	irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
 }
 
+/* Compute the freecount of an incore inode record. */
+uint8_t
+xfs_inobt_rec_freecount(
+	const struct xfs_inobt_rec_incore	*irec)
+{
+	uint64_t				realfree = irec->ir_free;
+
+	if (xfs_inobt_issparse(irec->ir_holemask))
+		realfree &= xfs_inobt_irec_to_allocmask(irec);
+	return hweight64(realfree);
+}
+
 /* Simple checks for inode records. */
 xfs_failaddr_t
 xfs_inobt_check_irec(
-	struct xfs_btree_cur			*cur,
+	struct xfs_perag			*pag,
 	const struct xfs_inobt_rec_incore	*irec)
 {
-	uint64_t			realfree;
-
 	/* Record has to be properly aligned within the AG. */
-	if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino))
+	if (!xfs_verify_agino(pag, irec->ir_startino))
 		return __this_address;
-	if (!xfs_verify_agino(cur->bc_ag.pag,
+	if (!xfs_verify_agino(pag,
 				irec->ir_startino + XFS_INODES_PER_CHUNK - 1))
 		return __this_address;
 	if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT ||
@@ -110,12 +120,7 @@ xfs_inobt_check_irec(
 	if (irec->ir_freecount > XFS_INODES_PER_CHUNK)
 		return __this_address;
 
-	/* if there are no holes, return the first available offset */
-	if (!xfs_inobt_issparse(irec->ir_holemask))
-		realfree = irec->ir_free;
-	else
-		realfree = irec->ir_free & xfs_inobt_irec_to_allocmask(irec);
-	if (hweight64(realfree) != irec->ir_freecount)
+	if (xfs_inobt_rec_freecount(irec) != irec->ir_freecount)
 		return __this_address;
 
 	return NULL;
@@ -159,7 +164,7 @@ xfs_inobt_get_rec(
 		return error;
 
 	xfs_inobt_btrec_to_irec(mp, rec, irec);
-	fa = xfs_inobt_check_irec(cur, irec);
+	fa = xfs_inobt_check_irec(cur->bc_ag.pag, irec);
 	if (fa)
 		return xfs_inobt_complain_bad_rec(cur, fa, irec);
 
@@ -2735,7 +2740,7 @@ xfs_ialloc_count_inodes_rec(
 	xfs_failaddr_t			fa;
 
 	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
-	fa = xfs_inobt_check_irec(cur, &irec);
+	fa = xfs_inobt_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_inobt_complain_bad_rec(cur, fa, &irec);
 
diff --git a/libxfs/xfs_ialloc.h b/libxfs/xfs_ialloc.h
index fe824bb04..f1412183b 100644
--- a/libxfs/xfs_ialloc.h
+++ b/libxfs/xfs_ialloc.h
@@ -79,6 +79,7 @@ int xfs_inobt_lookup(struct xfs_btree_cur *cur, xfs_agino_t ino,
  */
 int xfs_inobt_get_rec(struct xfs_btree_cur *cur,
 		xfs_inobt_rec_incore_t *rec, int *stat);
+uint8_t xfs_inobt_rec_freecount(const struct xfs_inobt_rec_incore *irec);
 
 /*
  * Inode chunk initialisation routine
@@ -93,7 +94,7 @@ union xfs_btree_rec;
 void xfs_inobt_btrec_to_irec(struct xfs_mount *mp,
 		const union xfs_btree_rec *rec,
 		struct xfs_inobt_rec_incore *irec);
-xfs_failaddr_t xfs_inobt_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_inobt_check_irec(struct xfs_perag *pag,
 		const struct xfs_inobt_rec_incore *irec);
 int xfs_ialloc_has_inodes_at_extent(struct xfs_btree_cur *cur,
 		xfs_agblock_t bno, xfs_extlen_t len,
-- 
2.44.0

[PATCH 36/67] xfs: repair refcount btrees

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 9099cd38002f8029c9a1da08e6832d1cd18e8451

Reconstruct the refcount data from the rmap btree.

Link: https://docs.kernel.org/filesystems/xfs-online-fsck-design.html#case-study-rebuilding-the-space-reference-counts
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_ag.h             |  1 +
 libxfs/xfs_btree.c          | 26 ++++++++++++++++++++++++++
 libxfs/xfs_btree.h          |  2 ++
 libxfs/xfs_refcount.c       |  8 +++-----
 libxfs/xfs_refcount.h       |  2 +-
 libxfs/xfs_refcount_btree.c | 13 ++++++++++++-
 6 files changed, 45 insertions(+), 7 deletions(-)

diff --git a/libxfs/xfs_ag.h b/libxfs/xfs_ag.h
index f16cb7a17..67c3260ee 100644
--- a/libxfs/xfs_ag.h
+++ b/libxfs/xfs_ag.h
@@ -87,6 +87,7 @@ struct xfs_perag {
 	 * verifiers while rebuilding the AG btrees.
 	 */
 	uint8_t		pagf_repair_levels[XFS_BTNUM_AGF];
+	uint8_t		pagf_repair_refcount_level;
 #endif
 
 	spinlock_t	pag_state_lock;
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 97962fc16..0022bb641 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -5209,3 +5209,29 @@ xfs_btree_destroy_cur_caches(void)
 	xfs_rmapbt_destroy_cur_cache();
 	xfs_refcountbt_destroy_cur_cache();
 }
+
+/* Move the btree cursor before the first record. */
+int
+xfs_btree_goto_left_edge(
+	struct xfs_btree_cur	*cur)
+{
+	int			stat = 0;
+	int			error;
+
+	memset(&cur->bc_rec, 0, sizeof(cur->bc_rec));
+	error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, &stat);
+	if (error)
+		return error;
+	if (!stat)
+		return 0;
+
+	error = xfs_btree_decrement(cur, 0, &stat);
+	if (error)
+		return error;
+	if (stat != 0) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index e0875cec4..d906324e2 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -738,4 +738,6 @@ xfs_btree_alloc_cursor(
 int __init xfs_btree_init_cur_caches(void);
 void xfs_btree_destroy_cur_caches(void);
 
+int xfs_btree_goto_left_edge(struct xfs_btree_cur *cur);
+
 #endif	/* __XFS_BTREE_H__ */
diff --git a/libxfs/xfs_refcount.c b/libxfs/xfs_refcount.c
index 45f8134e4..3377fac12 100644
--- a/libxfs/xfs_refcount.c
+++ b/libxfs/xfs_refcount.c
@@ -122,11 +122,9 @@ xfs_refcount_btrec_to_irec(
 /* Simple checks for refcount records. */
 xfs_failaddr_t
 xfs_refcount_check_irec(
-	struct xfs_btree_cur		*cur,
+	struct xfs_perag		*pag,
 	const struct xfs_refcount_irec	*irec)
 {
-	struct xfs_perag		*pag = cur->bc_ag.pag;
-
 	if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
 		return __this_address;
 
@@ -178,7 +176,7 @@ xfs_refcount_get_rec(
 		return error;
 
 	xfs_refcount_btrec_to_irec(rec, irec);
-	fa = xfs_refcount_check_irec(cur, irec);
+	fa = xfs_refcount_check_irec(cur->bc_ag.pag, irec);
 	if (fa)
 		return xfs_refcount_complain_bad_rec(cur, fa, irec);
 
@@ -1898,7 +1896,7 @@ xfs_refcount_recover_extent(
 	INIT_LIST_HEAD(&rr->rr_list);
 	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
 
-	if (xfs_refcount_check_irec(cur, &rr->rr_rrec) != NULL ||
+	if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
 	    XFS_IS_CORRUPT(cur->bc_mp,
 			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
 		kfree(rr);
diff --git a/libxfs/xfs_refcount.h b/libxfs/xfs_refcount.h
index 783cd89ca..5c207f1c6 100644
--- a/libxfs/xfs_refcount.h
+++ b/libxfs/xfs_refcount.h
@@ -117,7 +117,7 @@ extern int xfs_refcount_has_records(struct xfs_btree_cur *cur,
 union xfs_btree_rec;
 extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_refcount_irec *irec);
-xfs_failaddr_t xfs_refcount_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag,
 		const struct xfs_refcount_irec *irec);
 extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
 		struct xfs_refcount_irec *irec, int *stat);
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index bc8bd867e..ac1c3ab86 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -225,7 +225,18 @@ xfs_refcountbt_verify(
 
 	level = be16_to_cpu(block->bb_level);
 	if (pag && xfs_perag_initialised_agf(pag)) {
-		if (level >= pag->pagf_refcount_level)
+		unsigned int	maxlevel = pag->pagf_refcount_level;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+		/*
+		 * Online repair could be rewriting the refcount btree, so
+		 * we'll validate against the larger of either tree while this
+		 * is going on.
+		 */
+		maxlevel = max_t(unsigned int, maxlevel,
+				pag->pagf_repair_refcount_level);
+#endif
+		if (level >= maxlevel)
 			return __this_address;
 	} else if (level >= mp->m_refc_maxlevels)
 		return __this_address;
-- 
2.44.0

[PATCH 37/67] xfs: dont cast to char * for XFS_DFORK_*PTR macros

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 6b5d917780219d0d8f8e2cefefcb6f50987d0fa3

Code in the next patch will assign the return value of XFS_DFORK_*PTR
macros to a struct pointer.  gcc complains about casting char* strings
to struct pointers, so let's fix the macro's cast to void* to shut up
the warnings.

While we're at it, fix one of the scrub tests that uses PTR to use BOFF
instead for a simpler integer comparison, since other linters whine
about char* and void* comparisons.

Can't satisfy all these dman bots.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_format.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index 9a88aba15..f16974126 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -1008,7 +1008,7 @@ enum xfs_dinode_fmt {
  * Return pointers to the data or attribute forks.
  */
 #define XFS_DFORK_DPTR(dip) \
-	((char *)dip + xfs_dinode_size(dip->di_version))
+	((void *)dip + xfs_dinode_size(dip->di_version))
 #define XFS_DFORK_APTR(dip)	\
 	(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
 #define XFS_DFORK_PTR(dip,w)	\
-- 
2.44.0

[PATCH 38/67] xfs: set inode sick state flags when we zap either ondisk fork

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: d9041681dd2f5334529a68868c9266631c384de4

In a few patches, we'll add some online repair code that tries to
massage the ondisk inode record just enough to get it to pass the inode
verifiers so that we can continue with more file repairs.  Part of that
massaging can include zapping the ondisk forks to clear errors.  After
that point, the bmap fork repair functions will rebuild the zapped
forks.

Christoph asked for stronger protections against online repair zapping a
fork to get the inode to load vs. other threads trying to access the
partially repaired file.  Do this by adding a special "[DA]FORK_ZAPPED"
inode health flag whenever repair zaps a fork, and sprinkling checks for
that flag into the various file operations for things that don't like
handling an unexpected zero-extents fork.

In practice xfs_scrub will scrub and fix the forks almost immediately
after zapping them, so the window is very small.  However, if a crash or
unmount should occur, we can still detect these zapped inode forks by
looking for a zero-extents fork when data was expected.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_health.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 99e796256..6296993ff 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -68,6 +68,11 @@ struct xfs_fsop_geom;
 #define XFS_SICK_INO_SYMLINK	(1 << 6)  /* symbolic link remote target */
 #define XFS_SICK_INO_PARENT	(1 << 7)  /* parent pointers */
 
+#define XFS_SICK_INO_BMBTD_ZAPPED	(1 << 8)  /* data fork erased */
+#define XFS_SICK_INO_BMBTA_ZAPPED	(1 << 9)  /* attr fork erased */
+#define XFS_SICK_INO_DIR_ZAPPED		(1 << 10) /* directory erased */
+#define XFS_SICK_INO_SYMLINK_ZAPPED	(1 << 11) /* symlink erased */
+
 /* Primary evidence of health problems in a given group. */
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \
 				 XFS_SICK_FS_UQUOTA | \
@@ -97,6 +102,11 @@ struct xfs_fsop_geom;
 				 XFS_SICK_INO_SYMLINK | \
 				 XFS_SICK_INO_PARENT)
 
+#define XFS_SICK_INO_ZAPPED	(XFS_SICK_INO_BMBTD_ZAPPED | \
+				 XFS_SICK_INO_BMBTA_ZAPPED | \
+				 XFS_SICK_INO_DIR_ZAPPED | \
+				 XFS_SICK_INO_SYMLINK_ZAPPED)
+
 /* These functions must be provided by the xfs implementation. */
 
 void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask);
-- 
2.44.0

[PATCH 39/67] xfs: zap broken inode forks

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: e744cef206055954517648070d2b3aaa3d2515ba

Determine if inode fork damage is responsible for the inode being unable
to pass the ifork verifiers in xfs_iget and zap the fork contents if
this is true.  Once this is done the fork will be empty but we'll be
able to construct an in-core inode, and a subsequent call to the inode
fork repair ioctl will search the rmapbt to rebuild the records that
were in the fork.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr_leaf.c      | 13 +++----------
 libxfs/xfs_attr_leaf.h      |  3 ++-
 libxfs/xfs_bmap.c           | 22 ++++++++++++++++------
 libxfs/xfs_bmap.h           |  2 ++
 libxfs/xfs_dir2_priv.h      |  3 ++-
 libxfs/xfs_dir2_sf.c        | 13 +++----------
 libxfs/xfs_inode_fork.c     | 33 ++++++++++++++++++++++++++-------
 libxfs/xfs_shared.h         |  2 +-
 libxfs/xfs_symlink_remote.c |  8 ++------
 9 files changed, 57 insertions(+), 42 deletions(-)

diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index baa168318..8329348eb 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -1037,23 +1037,16 @@ xfs_attr_shortform_allfit(
 	return xfs_attr_shortform_bytesfit(dp, bytes);
 }
 
-/* Verify the consistency of an inline attribute fork. */
+/* Verify the consistency of a raw inline attribute fork. */
 xfs_failaddr_t
 xfs_attr_shortform_verify(
-	struct xfs_inode		*ip)
+	struct xfs_attr_shortform	*sfp,
+	size_t				size)
 {
-	struct xfs_attr_shortform	*sfp;
 	struct xfs_attr_sf_entry	*sfep;
 	struct xfs_attr_sf_entry	*next_sfep;
 	char				*endp;
-	struct xfs_ifork		*ifp;
 	int				i;
-	int64_t				size;
-
-	ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL);
-	ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
-	sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	size = ifp->if_bytes;
 
 	/*
 	 * Give up if the attribute is way too short.
diff --git a/libxfs/xfs_attr_leaf.h b/libxfs/xfs_attr_leaf.h
index 368f4d9fa..ce6743463 100644
--- a/libxfs/xfs_attr_leaf.h
+++ b/libxfs/xfs_attr_leaf.h
@@ -56,7 +56,8 @@ int	xfs_attr_sf_findname(struct xfs_da_args *args,
 			     unsigned int *basep);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
-xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_shortform *sfp,
+		size_t size);
 void	xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
 
 /*
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 6d23c5e3e..534a516b5 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -6162,19 +6162,18 @@ xfs_bmap_finish_one(
 	return error;
 }
 
-/* Check that an inode's extent does not have invalid flags or bad ranges. */
+/* Check that an extent does not have invalid flags or bad ranges. */
 xfs_failaddr_t
-xfs_bmap_validate_extent(
-	struct xfs_inode	*ip,
+xfs_bmap_validate_extent_raw(
+	struct xfs_mount	*mp,
+	bool			rtfile,
 	int			whichfork,
 	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-
 	if (!xfs_verify_fileext(mp, irec->br_startoff, irec->br_blockcount))
 		return __this_address;
 
-	if (XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK) {
+	if (rtfile && whichfork == XFS_DATA_FORK) {
 		if (!xfs_verify_rtbext(mp, irec->br_startblock,
 					   irec->br_blockcount))
 			return __this_address;
@@ -6204,3 +6203,14 @@ xfs_bmap_intent_destroy_cache(void)
 	kmem_cache_destroy(xfs_bmap_intent_cache);
 	xfs_bmap_intent_cache = NULL;
 }
+
+/* Check that an inode's extent does not have invalid flags or bad ranges. */
+xfs_failaddr_t
+xfs_bmap_validate_extent(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	struct xfs_bmbt_irec	*irec)
+{
+	return xfs_bmap_validate_extent_raw(ip->i_mount,
+			XFS_IS_REALTIME_INODE(ip), whichfork, irec);
+}
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index e33470e39..8518324db 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -263,6 +263,8 @@ static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
 	}
 }
 
+xfs_failaddr_t xfs_bmap_validate_extent_raw(struct xfs_mount *mp, bool rtfile,
+		int whichfork, struct xfs_bmbt_irec *irec);
 xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *irec);
 int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork,
diff --git a/libxfs/xfs_dir2_priv.h b/libxfs/xfs_dir2_priv.h
index 7404a9ff1..1db2e60ba 100644
--- a/libxfs/xfs_dir2_priv.h
+++ b/libxfs/xfs_dir2_priv.h
@@ -175,7 +175,8 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
 extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
-extern xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_mount *mp,
+		struct xfs_dir2_sf_hdr *sfp, int64_t size);
 int xfs_dir2_sf_entsize(struct xfs_mount *mp,
 		struct xfs_dir2_sf_hdr *hdr, int len);
 void xfs_dir2_sf_put_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr,
diff --git a/libxfs/xfs_dir2_sf.c b/libxfs/xfs_dir2_sf.c
index 08b36c95c..260eccacf 100644
--- a/libxfs/xfs_dir2_sf.c
+++ b/libxfs/xfs_dir2_sf.c
@@ -707,11 +707,10 @@ xfs_dir2_sf_check(
 /* Verify the consistency of an inline directory. */
 xfs_failaddr_t
 xfs_dir2_sf_verify(
-	struct xfs_inode		*ip)
+	struct xfs_mount		*mp,
+	struct xfs_dir2_sf_hdr		*sfp,
+	int64_t				size)
 {
-	struct xfs_mount		*mp = ip->i_mount;
-	struct xfs_ifork		*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
-	struct xfs_dir2_sf_hdr		*sfp;
 	struct xfs_dir2_sf_entry	*sfep;
 	struct xfs_dir2_sf_entry	*next_sfep;
 	char				*endp;
@@ -719,15 +718,9 @@ xfs_dir2_sf_verify(
 	int				i;
 	int				i8count;
 	int				offset;
-	int64_t				size;
 	int				error;
 	uint8_t				filetype;
 
-	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
-	sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
-	size = ifp->if_bytes;
-
 	/*
 	 * Give up if the directory is way too short.
 	 */
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index 5cc056ff7..3e2d7882a 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -700,12 +700,22 @@ xfs_ifork_verify_local_data(
 	xfs_failaddr_t		fa = NULL;
 
 	switch (VFS_I(ip)->i_mode & S_IFMT) {
-	case S_IFDIR:
-		fa = xfs_dir2_sf_verify(ip);
+	case S_IFDIR: {
+		struct xfs_mount	*mp = ip->i_mount;
+		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+		struct xfs_dir2_sf_hdr	*sfp;
+
+		sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+		fa = xfs_dir2_sf_verify(mp, sfp, ifp->if_bytes);
 		break;
-	case S_IFLNK:
-		fa = xfs_symlink_shortform_verify(ip);
+	}
+	case S_IFLNK: {
+		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+
+		fa = xfs_symlink_shortform_verify(ifp->if_u1.if_data,
+				ifp->if_bytes);
 		break;
+	}
 	default:
 		break;
 	}
@@ -727,11 +737,20 @@ xfs_ifork_verify_local_attr(
 	struct xfs_ifork	*ifp = &ip->i_af;
 	xfs_failaddr_t		fa;
 
-	if (!xfs_inode_has_attr_fork(ip))
+	if (!xfs_inode_has_attr_fork(ip)) {
 		fa = __this_address;
-	else
-		fa = xfs_attr_shortform_verify(ip);
+	} else {
+		struct xfs_attr_shortform	*sfp;
+		struct xfs_ifork		*ifp;
+		int64_t				size;
 
+		ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL);
+		ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
+		sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
+		size = ifp->if_bytes;
+
+		fa = xfs_attr_shortform_verify(sfp, size);
+	}
 	if (fa) {
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
 				ifp->if_u1.if_data, ifp->if_bytes, fa);
diff --git a/libxfs/xfs_shared.h b/libxfs/xfs_shared.h
index c4381388c..4220d3584 100644
--- a/libxfs/xfs_shared.h
+++ b/libxfs/xfs_shared.h
@@ -139,7 +139,7 @@ bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
 			uint32_t size, struct xfs_buf *bp);
 void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
 				 struct xfs_inode *ip, struct xfs_ifork *ifp);
-xfs_failaddr_t xfs_symlink_shortform_verify(struct xfs_inode *ip);
+xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
 
 /* Computed inode geometry for the filesystem. */
 struct xfs_ino_geometry {
diff --git a/libxfs/xfs_symlink_remote.c b/libxfs/xfs_symlink_remote.c
index 29c9f1cc1..cf894b527 100644
--- a/libxfs/xfs_symlink_remote.c
+++ b/libxfs/xfs_symlink_remote.c
@@ -199,15 +199,11 @@ xfs_symlink_local_to_remote(
  */
 xfs_failaddr_t
 xfs_symlink_shortform_verify(
-	struct xfs_inode	*ip)
+	void			*sfp,
+	int64_t			size)
 {
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
-	char			*sfp = (char *)ifp->if_u1.if_data;
-	int			size = ifp->if_bytes;
 	char			*endp = sfp + size;
 
-	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-
 	/*
 	 * Zero length symlinks should never occur in memory as they are
 	 * never allowed to exist on disk.
-- 
2.44.0

[PATCH 40/67] xfs: repair inode fork block mapping data structures

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 8f71bede8efd820627ac05c19eac2758214bc896

Use the reverse-mapping btree information to rebuild an inode block map.
Update the btree bulk loading code as necessary to support inode rooted
btrees and fix some bitrot problems.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_bmap_btree.c    | 121 +++++++++++++++++++++++++++++++------
 libxfs/xfs_bmap_btree.h    |   5 ++
 libxfs/xfs_btree_staging.c |  11 +++-
 libxfs/xfs_btree_staging.h |   2 +-
 libxfs/xfs_iext_tree.c     |  23 ++++---
 libxfs/xfs_inode_fork.c    |   1 +
 libxfs/xfs_inode_fork.h    |   3 +
 7 files changed, 136 insertions(+), 30 deletions(-)

diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index c4d5c8a64..73ba067df 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -15,6 +15,7 @@
 #include "xfs_trans.h"
 #include "xfs_alloc.h"
 #include "xfs_btree.h"
+#include "xfs_btree_staging.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
 #include "xfs_trace.h"
@@ -286,10 +287,7 @@ xfs_bmbt_get_minrecs(
 	int			level)
 {
 	if (level == cur->bc_nlevels - 1) {
-		struct xfs_ifork	*ifp;
-
-		ifp = xfs_ifork_ptr(cur->bc_ino.ip,
-				    cur->bc_ino.whichfork);
+		struct xfs_ifork	*ifp = xfs_btree_ifork_ptr(cur);
 
 		return xfs_bmbt_maxrecs(cur->bc_mp,
 					ifp->if_broot_bytes, level == 0) / 2;
@@ -304,10 +302,7 @@ xfs_bmbt_get_maxrecs(
 	int			level)
 {
 	if (level == cur->bc_nlevels - 1) {
-		struct xfs_ifork	*ifp;
-
-		ifp = xfs_ifork_ptr(cur->bc_ino.ip,
-				    cur->bc_ino.whichfork);
+		struct xfs_ifork	*ifp = xfs_btree_ifork_ptr(cur);
 
 		return xfs_bmbt_maxrecs(cur->bc_mp,
 					ifp->if_broot_bytes, level == 0);
@@ -541,23 +536,19 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.keys_contiguous	= xfs_bmbt_keys_contiguous,
 };
 
-/*
- * Allocate a new bmap btree cursor.
- */
-struct xfs_btree_cur *				/* new bmap btree cursor */
-xfs_bmbt_init_cursor(
-	struct xfs_mount	*mp,		/* file system mount point */
-	struct xfs_trans	*tp,		/* transaction pointer */
-	struct xfs_inode	*ip,		/* inode owning the btree */
-	int			whichfork)	/* data or attr fork */
+static struct xfs_btree_cur *
+xfs_bmbt_init_common(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			whichfork)
 {
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 	struct xfs_btree_cur	*cur;
+
 	ASSERT(whichfork != XFS_COW_FORK);
 
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
 			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
-	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
 	cur->bc_ops = &xfs_bmbt_ops;
@@ -565,10 +556,30 @@ xfs_bmbt_init_cursor(
 	if (xfs_has_crc(mp))
 		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
-	cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
 	cur->bc_ino.ip = ip;
 	cur->bc_ino.allocated = 0;
 	cur->bc_ino.flags = 0;
+
+	return cur;
+}
+
+/*
+ * Allocate a new bmap btree cursor.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_init_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
+	struct xfs_btree_cur	*cur;
+
+	cur = xfs_bmbt_init_common(mp, tp, ip, whichfork);
+
+	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+	cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
 	cur->bc_ino.whichfork = whichfork;
 
 	return cur;
@@ -585,6 +596,76 @@ xfs_bmbt_block_maxrecs(
 	return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
 }
 
+/*
+ * Allocate a new bmap btree cursor for reloading an inode block mapping data
+ * structure.  Note that callers can use the staged cursor to reload extents
+ * format inode forks if they rebuild the iext tree and commit the staged
+ * cursor immediately.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_stage_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_inode	*ip,
+	struct xbtree_ifakeroot	*ifake)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_btree_ops	*ops;
+
+	/* data fork always has larger maxheight */
+	cur = xfs_bmbt_init_common(mp, NULL, ip, XFS_DATA_FORK);
+	cur->bc_nlevels = ifake->if_levels;
+	cur->bc_ino.forksize = ifake->if_fork_size;
+
+	/* Don't let anyone think we're attached to the real fork yet. */
+	cur->bc_ino.whichfork = -1;
+	xfs_btree_stage_ifakeroot(cur, ifake, &ops);
+	ops->update_cursor = NULL;
+	return cur;
+}
+
+/*
+ * Swap in the new inode fork root.  Once we pass this point the newly rebuilt
+ * mappings are in place and we have to kill off any old btree blocks.
+ */
+void
+xfs_bmbt_commit_staged_btree(
+	struct xfs_btree_cur	*cur,
+	struct xfs_trans	*tp,
+	int			whichfork)
+{
+	struct xbtree_ifakeroot	*ifake = cur->bc_ino.ifake;
+	struct xfs_ifork	*ifp;
+	static const short	brootflag[2] = {XFS_ILOG_DBROOT, XFS_ILOG_ABROOT};
+	static const short	extflag[2] = {XFS_ILOG_DEXT, XFS_ILOG_AEXT};
+	int			flags = XFS_ILOG_CORE;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
+	ASSERT(whichfork != XFS_COW_FORK);
+
+	/*
+	 * Free any resources hanging off the real fork, then shallow-copy the
+	 * staging fork's contents into the real fork to transfer everything
+	 * we just built.
+	 */
+	ifp = xfs_ifork_ptr(cur->bc_ino.ip, whichfork);
+	xfs_idestroy_fork(ifp);
+	memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork));
+
+	switch (ifp->if_format) {
+	case XFS_DINODE_FMT_EXTENTS:
+		flags |= extflag[whichfork];
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		flags |= brootflag[whichfork];
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+	xfs_trans_log_inode(tp, cur->bc_ino.ip, flags);
+	xfs_btree_commit_ifakeroot(cur, tp, whichfork, &xfs_bmbt_ops);
+}
+
 /*
  * Calculate number of records in a bmap btree block.
  */
diff --git a/libxfs/xfs_bmap_btree.h b/libxfs/xfs_bmap_btree.h
index 3e7a40a83..151b8491f 100644
--- a/libxfs/xfs_bmap_btree.h
+++ b/libxfs/xfs_bmap_btree.h
@@ -11,6 +11,7 @@ struct xfs_btree_block;
 struct xfs_mount;
 struct xfs_inode;
 struct xfs_trans;
+struct xbtree_ifakeroot;
 
 /*
  * Btree block header size depends on a superblock flag.
@@ -106,6 +107,10 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
 
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
+struct xfs_btree_cur *xfs_bmbt_stage_cursor(struct xfs_mount *mp,
+		struct xfs_inode *ip, struct xbtree_ifakeroot *ifake);
+void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur,
+		struct xfs_trans *tp, int whichfork);
 
 extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index d4164e37b..0ea44dcf1 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -405,7 +405,7 @@ xfs_btree_bload_prep_block(
 		ASSERT(*bpp == NULL);
 
 		/* Allocate a new incore btree root block. */
-		new_size = bbl->iroot_size(cur, nr_this_block, priv);
+		new_size = bbl->iroot_size(cur, level, nr_this_block, priv);
 		ifp->if_broot = kmem_zalloc(new_size, 0);
 		ifp->if_broot_bytes = (int)new_size;
 
@@ -596,7 +596,14 @@ xfs_btree_bload_level_geometry(
 	unsigned int		desired_npb;
 	unsigned int		maxnr;
 
-	maxnr = cur->bc_ops->get_maxrecs(cur, level);
+	/*
+	 * Compute the absolute maximum number of records that we can store in
+	 * the ondisk block or inode root.
+	 */
+	if (cur->bc_ops->get_dmaxrecs)
+		maxnr = cur->bc_ops->get_dmaxrecs(cur, level);
+	else
+		maxnr = cur->bc_ops->get_maxrecs(cur, level);
 
 	/*
 	 * Compute the number of blocks we need to fill each block with the
diff --git a/libxfs/xfs_btree_staging.h b/libxfs/xfs_btree_staging.h
index f0a500728..055ea43b1 100644
--- a/libxfs/xfs_btree_staging.h
+++ b/libxfs/xfs_btree_staging.h
@@ -53,7 +53,7 @@ typedef int (*xfs_btree_bload_get_records_fn)(struct xfs_btree_cur *cur,
 typedef int (*xfs_btree_bload_claim_block_fn)(struct xfs_btree_cur *cur,
 		union xfs_btree_ptr *ptr, void *priv);
 typedef size_t (*xfs_btree_bload_iroot_size_fn)(struct xfs_btree_cur *cur,
-		unsigned int nr_this_level, void *priv);
+		unsigned int level, unsigned int nr_this_level, void *priv);
 
 struct xfs_btree_bload {
 	/*
diff --git a/libxfs/xfs_iext_tree.c b/libxfs/xfs_iext_tree.c
index 7f5c4f403..5d0be2dc8 100644
--- a/libxfs/xfs_iext_tree.c
+++ b/libxfs/xfs_iext_tree.c
@@ -622,13 +622,11 @@ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp)
 }
 
 void
-xfs_iext_insert(
-	struct xfs_inode	*ip,
+xfs_iext_insert_raw(
+	struct xfs_ifork	*ifp,
 	struct xfs_iext_cursor	*cur,
-	struct xfs_bmbt_irec	*irec,
-	int			state)
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
 	xfs_fileoff_t		offset = irec->br_startoff;
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
@@ -662,12 +660,23 @@ xfs_iext_insert(
 	xfs_iext_set(cur_rec(cur), irec);
 	ifp->if_bytes += sizeof(struct xfs_iext_rec);
 
-	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
-
 	if (new)
 		xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2);
 }
 
+void
+xfs_iext_insert(
+	struct xfs_inode	*ip,
+	struct xfs_iext_cursor	*cur,
+	struct xfs_bmbt_irec	*irec,
+	int			state)
+{
+	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
+
+	xfs_iext_insert_raw(ifp, cur, irec);
+	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
+}
+
 static struct xfs_iext_node *
 xfs_iext_rebalance_node(
 	struct xfs_iext_node	*parent,
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index 3e2d7882a..80f4215d2 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -518,6 +518,7 @@ xfs_idata_realloc(
 	ifp->if_bytes = new_size;
 }
 
+/* Free all memory and reset a fork back to its initial state. */
 void
 xfs_idestroy_fork(
 	struct xfs_ifork	*ifp)
diff --git a/libxfs/xfs_inode_fork.h b/libxfs/xfs_inode_fork.h
index 96d307784..535be5c03 100644
--- a/libxfs/xfs_inode_fork.h
+++ b/libxfs/xfs_inode_fork.h
@@ -180,6 +180,9 @@ void		xfs_init_local_fork(struct xfs_inode *ip, int whichfork,
 				const void *data, int64_t size);
 
 xfs_extnum_t	xfs_iext_count(struct xfs_ifork *ifp);
+void		xfs_iext_insert_raw(struct xfs_ifork *ifp,
+			struct xfs_iext_cursor *cur,
+			struct xfs_bmbt_irec *irec);
 void		xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur,
 			struct xfs_bmbt_irec *, int);
 void		xfs_iext_remove(struct xfs_inode *, struct xfs_iext_cursor *,
-- 
2.44.0

[PATCH 41/67] xfs: create a ranged query function for refcount btrees

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: d12bf8bac87a0d93e6e5fab67f399d1e3d3d5767

Implement ranged queries for refcount records.  The next patch will use
this to scan refcount data.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_refcount.c | 41 +++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_refcount.h | 10 ++++++++++
 2 files changed, 51 insertions(+)

diff --git a/libxfs/xfs_refcount.c b/libxfs/xfs_refcount.c
index 3377fac12..de321ab9d 100644
--- a/libxfs/xfs_refcount.c
+++ b/libxfs/xfs_refcount.c
@@ -2030,6 +2030,47 @@ xfs_refcount_has_records(
 	return xfs_btree_has_records(cur, &low, &high, NULL, outcome);
 }
 
+struct xfs_refcount_query_range_info {
+	xfs_refcount_query_range_fn	fn;
+	void				*priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_refcount_query_range_helper(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*rec,
+	void				*priv)
+{
+	struct xfs_refcount_query_range_info	*query = priv;
+	struct xfs_refcount_irec	irec;
+	xfs_failaddr_t			fa;
+
+	xfs_refcount_btrec_to_irec(rec, &irec);
+	fa = xfs_refcount_check_irec(cur->bc_ag.pag, &irec);
+	if (fa)
+		return xfs_refcount_complain_bad_rec(cur, fa, &irec);
+
+	return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all refcount records between two keys. */
+int
+xfs_refcount_query_range(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*low_rec,
+	const struct xfs_refcount_irec	*high_rec,
+	xfs_refcount_query_range_fn	fn,
+	void				*priv)
+{
+	union xfs_btree_irec		low_brec = { .rc = *low_rec };
+	union xfs_btree_irec		high_brec = { .rc = *high_rec };
+	struct xfs_refcount_query_range_info query = { .priv = priv, .fn = fn };
+
+	return xfs_btree_query_range(cur, &low_brec, &high_brec,
+			xfs_refcount_query_range_helper, &query);
+}
+
 int __init
 xfs_refcount_intent_init_cache(void)
 {
diff --git a/libxfs/xfs_refcount.h b/libxfs/xfs_refcount.h
index 5c207f1c6..9b56768a5 100644
--- a/libxfs/xfs_refcount.h
+++ b/libxfs/xfs_refcount.h
@@ -127,4 +127,14 @@ extern struct kmem_cache	*xfs_refcount_intent_cache;
 int __init xfs_refcount_intent_init_cache(void);
 void xfs_refcount_intent_destroy_cache(void);
 
+typedef int (*xfs_refcount_query_range_fn)(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*rec,
+	void				*priv);
+
+int xfs_refcount_query_range(struct xfs_btree_cur *cur,
+		const struct xfs_refcount_irec *low_rec,
+		const struct xfs_refcount_irec *high_rec,
+		xfs_refcount_query_range_fn fn, void *priv);
+
 #endif	/* __XFS_REFCOUNT_H__ */
-- 
2.44.0

[PATCH 42/67] xfs: create a new inode fork block unmap helper

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: a59eb5fc21b2a6dc160ee6cdf77f20bc186a88fd

Create a new helper to unmap blocks from an inode's fork.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_bmap.c | 41 ++++++++++++++++++++++++++++++++++++++++-
 libxfs/xfs_bmap.h |  5 ++---
 2 files changed, 42 insertions(+), 4 deletions(-)

diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 534a516b5..3520235b5 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -5233,7 +5233,7 @@ xfs_bmap_del_extent_real(
  * that value.  If not all extents in the block range can be removed then
  * *done is set.
  */
-int						/* error */
+static int
 __xfs_bunmapi(
 	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode */
@@ -6214,3 +6214,42 @@ xfs_bmap_validate_extent(
 	return xfs_bmap_validate_extent_raw(ip->i_mount,
 			XFS_IS_REALTIME_INODE(ip), whichfork, irec);
 }
+
+/*
+ * Used in xfs_itruncate_extents().  This is the maximum number of extents
+ * freed from a file in a single transaction.
+ */
+#define	XFS_ITRUNC_MAX_EXTENTS	2
+
+/*
+ * Unmap every extent in part of an inode's fork.  We don't do any higher level
+ * invalidation work at all.
+ */
+int
+xfs_bunmapi_range(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	uint32_t		flags,
+	xfs_fileoff_t		startoff,
+	xfs_fileoff_t		endoff)
+{
+	xfs_filblks_t		unmap_len = endoff - startoff + 1;
+	int			error = 0;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	while (unmap_len > 0) {
+		ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER);
+		error = __xfs_bunmapi(*tpp, ip, startoff, &unmap_len, flags,
+				XFS_ITRUNC_MAX_EXTENTS);
+		if (error)
+			goto out;
+
+		/* free the just unmapped extents */
+		error = xfs_defer_finish(tpp);
+		if (error)
+			goto out;
+	}
+out:
+	return error;
+}
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 8518324db..4b83f6148 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -190,9 +190,6 @@ int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
 		xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
-int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
-		xfs_fileoff_t bno, xfs_filblks_t *rlen, uint32_t flags,
-		xfs_extnum_t nexts);
 int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
 		xfs_extnum_t nexts, int *done);
@@ -273,6 +270,8 @@ int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork,
 int	xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
 		uint32_t flags);
+int	xfs_bunmapi_range(struct xfs_trans **tpp, struct xfs_inode *ip,
+		uint32_t flags, xfs_fileoff_t startoff, xfs_fileoff_t endoff);
 
 extern struct kmem_cache	*xfs_bmap_intent_cache;
 
-- 
2.44.0

[PATCH 43/67] xfs: improve dquot iteration for scrub

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 21d7500929c8a0b10e22a6755850c6f9a9280284

Upon a closer inspection of the quota record scrubber, I noticed that
dqiterate wasn't actually walking all possible dquots for the mapped
blocks in the quota file.  This is due to xfs_qm_dqget_next skipping all
XFS_IS_DQUOT_UNINITIALIZED dquots.

For a fsck program, we really want to look at all the dquots, even if
all counters and limits in the dquot record are zero.  Rewrite the
implementation to do this, as well as switching to an iterator paradigm
to reduce the number of indirect calls.

This enables removal of the old broken dqiterate code from xfs_dquot.c.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_format.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index f16974126..e6ca188e2 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -1272,6 +1272,9 @@ static inline time64_t xfs_dq_bigtime_to_unix(uint32_t ondisk_seconds)
 #define XFS_DQ_GRACE_MIN		((int64_t)0)
 #define XFS_DQ_GRACE_MAX		((int64_t)U32_MAX)
 
+/* Maximum id value for a quota record */
+#define XFS_DQ_ID_MAX			(U32_MAX)
+
 /*
  * This is the main portion of the on-disk representation of quota information
  * for a user.  We pad this with some more expansion room to construct the on
-- 
2.44.0

[PATCH 44/67] xfs: add lock protection when remove perag from radix tree

[cem]

From: Long Li <leo.lilong@huawei.com>

Source kernel commit: 07afd3173d0c6d24a47441839a835955ec6cf0d4

Take mp->m_perag_lock for deletions from the perag radix tree in
xfs_initialize_perag to prevent racing with tagging operations.
Lookups are fine - they are RCU protected so already deal with the
tree changing shape underneath the lookup - but tagging operations
require the tree to be stable while the tags are propagated back up
to the root.

Right now there's nothing stopping radix tree tagging from operating
while a growfs operation is progress and adding/removing new entries
into the radix tree.

Hence we can have traversals that require a stable tree occurring at
the same time we are removing unused entries from the radix tree which
causes the shape of the tree to change.

Likely this hasn't caused a problem in the past because we are only
doing append addition and removal so the active AG part of the tree
is not changing shape, but that doesn't mean it is safe. Just making
the radix tree modifications serialise against each other is obviously
correct.

Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_ag.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index bdb8a08bb..1dbc01b97 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -422,13 +422,17 @@ xfs_initialize_perag(
 
 out_remove_pag:
 	xfs_defer_drain_free(&pag->pag_intents_drain);
+	spin_lock(&mp->m_perag_lock);
 	radix_tree_delete(&mp->m_perag_tree, index);
+	spin_unlock(&mp->m_perag_lock);
 out_free_pag:
 	kmem_free(pag);
 out_unwind_new_pags:
 	/* unwind any prior newly initialized pags */
 	for (index = first_initialised; index < agcount; index++) {
+		spin_lock(&mp->m_perag_lock);
 		pag = radix_tree_delete(&mp->m_perag_tree, index);
+		spin_unlock(&mp->m_perag_lock);
 		if (!pag)
 			break;
 		xfs_buf_hash_destroy(pag);
-- 
2.44.0

[PATCH 45/67] xfs: fix perag leak when growfs fails

[cem]

From: Long Li <leo.lilong@huawei.com>

Source kernel commit: 7823921887750b39d02e6b44faafdd1cc617c651

During growfs, if new ag in memory has been initialized, however
sb_agcount has not been updated, if an error occurs at this time it
will cause perag leaks as follows, these new AGs will not been freed
during umount , because of these new AGs are not visible(that is
included in mp->m_sb.sb_agcount).

unreferenced object 0xffff88810be40200 (size 512):
comm "xfs_growfs", pid 857, jiffies 4294909093
hex dump (first 32 bytes):
00 c0 c1 05 81 88 ff ff 04 00 00 00 00 00 00 00  ................
01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
backtrace (crc 381741e2):
[<ffffffff8191aef6>] __kmalloc+0x386/0x4f0
[<ffffffff82553e65>] kmem_alloc+0xb5/0x2f0
[<ffffffff8238dac5>] xfs_initialize_perag+0xc5/0x810
[<ffffffff824f679c>] xfs_growfs_data+0x9bc/0xbc0
[<ffffffff8250b90e>] xfs_file_ioctl+0x5fe/0x14d0
[<ffffffff81aa5194>] __x64_sys_ioctl+0x144/0x1c0
[<ffffffff83c3d81f>] do_syscall_64+0x3f/0xe0
[<ffffffff83e00087>] entry_SYSCALL_64_after_hwframe+0x62/0x6a
unreferenced object 0xffff88810be40800 (size 512):
comm "xfs_growfs", pid 857, jiffies 4294909093
hex dump (first 32 bytes):
20 00 00 00 00 00 00 00 57 ef be dc 00 00 00 00   .......W.......
10 08 e4 0b 81 88 ff ff 10 08 e4 0b 81 88 ff ff  ................
backtrace (crc bde50e2d):
[<ffffffff8191b43a>] __kmalloc_node+0x3da/0x540
[<ffffffff81814489>] kvmalloc_node+0x99/0x160
[<ffffffff8286acff>] bucket_table_alloc.isra.0+0x5f/0x400
[<ffffffff8286bdc5>] rhashtable_init+0x405/0x760
[<ffffffff8238dda3>] xfs_initialize_perag+0x3a3/0x810
[<ffffffff824f679c>] xfs_growfs_data+0x9bc/0xbc0
[<ffffffff8250b90e>] xfs_file_ioctl+0x5fe/0x14d0
[<ffffffff81aa5194>] __x64_sys_ioctl+0x144/0x1c0
[<ffffffff83c3d81f>] do_syscall_64+0x3f/0xe0
[<ffffffff83e00087>] entry_SYSCALL_64_after_hwframe+0x62/0x6a

Factor out xfs_free_unused_perag_range() from xfs_initialize_perag(),
used for freeing unused perag within a specified range in error handling,
included in the error path of the growfs failure.

Fixes: 1c1c6ebcf528 ("xfs: Replace per-ag array with a radix tree")
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_ag.c | 36 ++++++++++++++++++++++++++----------
 libxfs/xfs_ag.h |  2 ++
 2 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index 1dbc01b97..0556d5547 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -330,6 +330,31 @@ xfs_agino_range(
 	return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
 }
 
+/*
+ * Free perag within the specified AG range, it is only used to free unused
+ * perags under the error handling path.
+ */
+void
+xfs_free_unused_perag_range(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agstart,
+	xfs_agnumber_t		agend)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		index;
+
+	for (index = agstart; index < agend; index++) {
+		spin_lock(&mp->m_perag_lock);
+		pag = radix_tree_delete(&mp->m_perag_tree, index);
+		spin_unlock(&mp->m_perag_lock);
+		if (!pag)
+			break;
+		xfs_buf_hash_destroy(pag);
+		xfs_defer_drain_free(&pag->pag_intents_drain);
+		kmem_free(pag);
+	}
+}
+
 int
 xfs_initialize_perag(
 	struct xfs_mount	*mp,
@@ -429,16 +454,7 @@ out_free_pag:
 	kmem_free(pag);
 out_unwind_new_pags:
 	/* unwind any prior newly initialized pags */
-	for (index = first_initialised; index < agcount; index++) {
-		spin_lock(&mp->m_perag_lock);
-		pag = radix_tree_delete(&mp->m_perag_tree, index);
-		spin_unlock(&mp->m_perag_lock);
-		if (!pag)
-			break;
-		xfs_buf_hash_destroy(pag);
-		xfs_defer_drain_free(&pag->pag_intents_drain);
-		kmem_free(pag);
-	}
+	xfs_free_unused_perag_range(mp, first_initialised, agcount);
 	return error;
 }
 
diff --git a/libxfs/xfs_ag.h b/libxfs/xfs_ag.h
index 67c3260ee..4b343c4fa 100644
--- a/libxfs/xfs_ag.h
+++ b/libxfs/xfs_ag.h
@@ -143,6 +143,8 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
 __XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
 __XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
 
+void xfs_free_unused_perag_range(struct xfs_mount *mp, xfs_agnumber_t agstart,
+			xfs_agnumber_t agend);
 int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
 			xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi);
 int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
-- 
2.44.0

[PATCH 46/67] xfs: remove the xfs_alloc_arg argument to xfs_bmap_btalloc_accounting

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: eef519d746bbfb90cbad4077c2d39d7a359c3282

xfs_bmap_btalloc_accounting only uses the len field from args, but that
has just been propagated to ap->length field by the caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_bmap.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 3520235b5..ad058bb12 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -3259,8 +3259,7 @@ xfs_bmap_btalloc_select_lengths(
 /* Update all inode and quota accounting for the allocation we just did. */
 static void
 xfs_bmap_btalloc_accounting(
-	struct xfs_bmalloca	*ap,
-	struct xfs_alloc_arg	*args)
+	struct xfs_bmalloca	*ap)
 {
 	if (ap->flags & XFS_BMAPI_COWFORK) {
 		/*
@@ -3273,7 +3272,7 @@ xfs_bmap_btalloc_accounting(
 		 * yet.
 		 */
 		if (ap->wasdel) {
-			xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
+			xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
 			return;
 		}
 
@@ -3285,22 +3284,22 @@ xfs_bmap_btalloc_accounting(
 		 * This essentially transfers the transaction quota reservation
 		 * to that of a delalloc extent.
 		 */
-		ap->ip->i_delayed_blks += args->len;
+		ap->ip->i_delayed_blks += ap->length;
 		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS,
-				-(long)args->len);
+				-(long)ap->length);
 		return;
 	}
 
 	/* data/attr fork only */
-	ap->ip->i_nblocks += args->len;
+	ap->ip->i_nblocks += ap->length;
 	xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
 	if (ap->wasdel) {
-		ap->ip->i_delayed_blks -= args->len;
-		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)args->len);
+		ap->ip->i_delayed_blks -= ap->length;
+		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
 	}
 	xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
 		ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
-		args->len);
+		ap->length);
 }
 
 static int
@@ -3374,7 +3373,7 @@ xfs_bmap_process_allocated_extent(
 		ap->offset = orig_offset;
 	else if (ap->offset + ap->length < orig_offset + orig_length)
 		ap->offset = orig_offset + orig_length - ap->length;
-	xfs_bmap_btalloc_accounting(ap, args);
+	xfs_bmap_btalloc_accounting(ap);
 }
 
 #ifdef DEBUG
-- 
2.44.0

[PATCH 47/67] xfs: also use xfs_bmap_btalloc_accounting for RT allocations

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 58643460546da1dc61593fc6fd78762798b4534f

Make xfs_bmap_btalloc_accounting more generic by handling the RT quota
reservations and then also use it from xfs_bmap_rtalloc instead of
open coding the accounting logic there.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/libxfs_priv.h    |  8 +++++++-
 libxfs/xfs_bmap.c       | 21 ++++++++++++++-------
 libxfs/xfs_bmap.h       |  2 ++
 libxfs/xfs_bmap_btree.c |  1 +
 4 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 30ff8dba9..3ba6b0e55 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -434,7 +434,13 @@ void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa);
 #define xfs_filestream_select_ag(...)		(-ENOSYS)
 
 /* quota bits */
-#define xfs_trans_mod_dquot_byino(t,i,f,d)		((void) 0)
+
+/* Silence GCC unused variable warning on xfs_bmap.c */
+#define xfs_trans_mod_dquot_byino(t,i,f,d)	({ \
+	uint _f = (f);				   \
+	_f = _f;				   \
+})
+
 #define xfs_trans_reserve_quota_nblks(t,i,b,n,f)	(0)
 
 /* hack too silence gcc */
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index ad058bb12..4f6bd8dff 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -3257,10 +3257,14 @@ xfs_bmap_btalloc_select_lengths(
 }
 
 /* Update all inode and quota accounting for the allocation we just did. */
-static void
-xfs_bmap_btalloc_accounting(
+void
+xfs_bmap_alloc_account(
 	struct xfs_bmalloca	*ap)
 {
+	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
+					(ap->flags & XFS_BMAPI_ATTRFORK);
+	uint			fld;
+
 	if (ap->flags & XFS_BMAPI_COWFORK) {
 		/*
 		 * COW fork blocks are in-core only and thus are treated as
@@ -3285,7 +3289,8 @@ xfs_bmap_btalloc_accounting(
 		 * to that of a delalloc extent.
 		 */
 		ap->ip->i_delayed_blks += ap->length;
-		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, XFS_TRANS_DQ_RES_BLKS,
+		xfs_trans_mod_dquot_byino(ap->tp, ap->ip, isrt ?
+				XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS,
 				-(long)ap->length);
 		return;
 	}
@@ -3296,10 +3301,12 @@ xfs_bmap_btalloc_accounting(
 	if (ap->wasdel) {
 		ap->ip->i_delayed_blks -= ap->length;
 		xfs_mod_delalloc(ap->ip->i_mount, -(int64_t)ap->length);
+		fld = isrt ? XFS_TRANS_DQ_DELRTBCOUNT : XFS_TRANS_DQ_DELBCOUNT;
+	} else {
+		fld = isrt ? XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
 	}
-	xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
-		ap->wasdel ? XFS_TRANS_DQ_DELBCOUNT : XFS_TRANS_DQ_BCOUNT,
-		ap->length);
+
+	xfs_trans_mod_dquot_byino(ap->tp, ap->ip, fld, ap->length);
 }
 
 static int
@@ -3373,7 +3380,7 @@ xfs_bmap_process_allocated_extent(
 		ap->offset = orig_offset;
 	else if (ap->offset + ap->length < orig_offset + orig_length)
 		ap->offset = orig_offset + orig_length - ap->length;
-	xfs_bmap_btalloc_accounting(ap);
+	xfs_bmap_alloc_account(ap);
 }
 
 #ifdef DEBUG
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 4b83f6148..f6b73f1ba 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -116,6 +116,8 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
 	return XFS_DATA_FORK;
 }
 
+void xfs_bmap_alloc_account(struct xfs_bmalloca *ap);
+
 /*
  * Special values for xfs_bmbt_irec_t br_startblock field.
  */
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 73ba067df..887ba56f3 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -21,6 +21,7 @@
 #include "xfs_trace.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_quota_defs.h"
 
 static struct kmem_cache	*xfs_bmbt_cur_cache;
 
-- 
2.44.0

[PATCH 48/67] xfs: return -ENOSPC from xfs_rtallocate_*

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: ce42b5d37527b282d38413c1b5f7283253f6562d

Just return -ENOSPC instead of returning 0 and setting the return rt
extent number to NULLRTEXTNO.  This is turn removes all users of
NULLRTEXTNO, so remove that as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_types.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/libxfs/xfs_types.h b/libxfs/xfs_types.h
index 035bf703d..20b5375f2 100644
--- a/libxfs/xfs_types.h
+++ b/libxfs/xfs_types.h
@@ -51,7 +51,6 @@ typedef void *		xfs_failaddr_t;
 #define	NULLRFSBLOCK	((xfs_rfsblock_t)-1)
 #define	NULLRTBLOCK	((xfs_rtblock_t)-1)
 #define	NULLFILEOFF	((xfs_fileoff_t)-1)
-#define	NULLRTEXTNO	((xfs_rtxnum_t)-1)
 
 #define	NULLAGBLOCK	((xfs_agblock_t)-1)
 #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
-- 
2.44.0

[PATCH 49/67] xfs: indicate if xfs_bmap_adjacent changed ap->blkno

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 676544c27e710aee7f8357f57abd348d98b1ccd4

Add a return value to xfs_bmap_adjacent to indicate if it did change
ap->blkno or not.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/libxfs_priv.h |  2 +-
 libxfs/xfs_bmap.c    | 19 ++++++++++++++-----
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 3ba6b0e55..ae01b076c 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -568,7 +568,7 @@ int xfs_bmap_extsize_align(struct xfs_mount *mp, struct xfs_bmbt_irec *gotp,
 			   struct xfs_bmbt_irec *prevp, xfs_extlen_t extsz,
 			   int rt, int eof, int delay, int convert,
 			   xfs_fileoff_t *offp, xfs_extlen_t *lenp);
-void xfs_bmap_adjacent(struct xfs_bmalloca *ap);
+bool xfs_bmap_adjacent(struct xfs_bmalloca *ap);
 int xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 			 int whichfork, struct xfs_bmbt_irec *rec,
 			 int *is_empty);
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 4f6bd8dff..b977032d8 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -3038,7 +3038,8 @@ xfs_bmap_extsize_align(
 
 #define XFS_ALLOC_GAP_UNITS	4
 
-void
+/* returns true if ap->blkno was modified */
+bool
 xfs_bmap_adjacent(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
 {
@@ -3073,13 +3074,14 @@ xfs_bmap_adjacent(
 		if (adjust &&
 		    ISVALID(ap->blkno + adjust, ap->prev.br_startblock))
 			ap->blkno += adjust;
+		return true;
 	}
 	/*
 	 * If not at eof, then compare the two neighbor blocks.
 	 * Figure out whether either one gives us a good starting point,
 	 * and pick the better one.
 	 */
-	else if (!ap->eof) {
+	if (!ap->eof) {
 		xfs_fsblock_t	gotbno;		/* right side block number */
 		xfs_fsblock_t	gotdiff=0;	/* right side difference */
 		xfs_fsblock_t	prevbno;	/* left side block number */
@@ -3159,14 +3161,21 @@ xfs_bmap_adjacent(
 		 * If both valid, pick the better one, else the only good
 		 * one, else ap->blkno is already set (to 0 or the inode block).
 		 */
-		if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK)
+		if (prevbno != NULLFSBLOCK && gotbno != NULLFSBLOCK) {
 			ap->blkno = prevdiff <= gotdiff ? prevbno : gotbno;
-		else if (prevbno != NULLFSBLOCK)
+			return true;
+		}
+		if (prevbno != NULLFSBLOCK) {
 			ap->blkno = prevbno;
-		else if (gotbno != NULLFSBLOCK)
+			return true;
+		}
+		if (gotbno != NULLFSBLOCK) {
 			ap->blkno = gotbno;
+			return true;
+		}
 	}
 #undef ISVALID
+	return false;
 }
 
 int
-- 
2.44.0

[PATCH 50/67] xfs: move xfs_rtget_summary to xfs_rtbitmap.c

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: c2adcfa31ff606264fab6e69129d6d45c9ddb7cb

xfs_rtmodify_summary_int is only used inside xfs_rtbitmap.c and to
implement xfs_rtget_summary.  Move xfs_rtget_summary to xfs_rtbitmap.c
as the exported API and mark xfs_rtmodify_summary_int static.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_rtbitmap.c | 14 ++++++++++++++
 libxfs/xfs_rtbitmap.h |  4 ++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index 726543abb..adeaffed7 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -517,6 +517,20 @@ xfs_rtmodify_summary(
 	return xfs_rtmodify_summary_int(args, log, bbno, delta, NULL);
 }
 
+/*
+ * Read and return the summary information for a given extent size, bitmap block
+ * combination.
+ */
+int
+xfs_rtget_summary(
+	struct xfs_rtalloc_args	*args,
+	int			log,	/* log2 of extent size */
+	xfs_fileoff_t		bbno,	/* bitmap block number */
+	xfs_suminfo_t		*sum)	/* out: summary info for this block */
+{
+	return xfs_rtmodify_summary_int(args, log, bbno, 0, sum);
+}
+
 /* Log rtbitmap block from the word @from to the byte before @next. */
 static inline void
 xfs_trans_log_rtbitmap(
diff --git a/libxfs/xfs_rtbitmap.h b/libxfs/xfs_rtbitmap.h
index 1c84b52de..274dc7dae 100644
--- a/libxfs/xfs_rtbitmap.h
+++ b/libxfs/xfs_rtbitmap.h
@@ -321,8 +321,8 @@ int xfs_rtfind_forw(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
 		xfs_rtxnum_t limit, xfs_rtxnum_t *rtblock);
 int xfs_rtmodify_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
 		xfs_rtxlen_t len, int val);
-int xfs_rtmodify_summary_int(struct xfs_rtalloc_args *args, int log,
-		xfs_fileoff_t bbno, int delta, xfs_suminfo_t *sum);
+int xfs_rtget_summary(struct xfs_rtalloc_args *args, int log,
+		xfs_fileoff_t bbno, xfs_suminfo_t *sum);
 int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log,
 		xfs_fileoff_t bbno, int delta);
 int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
-- 
2.44.0

[PATCH 51/67] xfs: split xfs_rtmodify_summary_int

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: b271b314119eca1fb98a2c4e15304ce562802f0c

Inline the logic of xfs_rtmodify_summary_int into xfs_rtmodify_summary
and xfs_rtget_summary instead of having a somewhat awkward helper to
share a little bit of code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_rtbitmap.c | 76 ++++++++++++++-----------------------------
 1 file changed, 25 insertions(+), 51 deletions(-)

diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index adeaffed7..bbf955be8 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -450,71 +450,38 @@ xfs_trans_log_rtsummary(
 }
 
 /*
- * Read and/or modify the summary information for a given extent size,
- * bitmap block combination.
- * Keeps track of a current summary block, so we don't keep reading
- * it from the buffer cache.
- *
- * Summary information is returned in *sum if specified.
- * If no delta is specified, returns summary only.
+ * Modify the summary information for a given extent size, bitmap block
+ * combination.
  */
 int
-xfs_rtmodify_summary_int(
+xfs_rtmodify_summary(
 	struct xfs_rtalloc_args	*args,
 	int			log,	/* log2 of extent size */
 	xfs_fileoff_t		bbno,	/* bitmap block number */
-	int			delta,	/* change to make to summary info */
-	xfs_suminfo_t		*sum)	/* out: summary info for this block */
+	int			delta)	/* in/out: summary block number */
 {
 	struct xfs_mount	*mp = args->mp;
-	int			error;
-	xfs_fileoff_t		sb;	/* summary fsblock */
-	xfs_rtsumoff_t		so;	/* index into the summary file */
+	xfs_rtsumoff_t		so = xfs_rtsumoffs(mp, log, bbno);
 	unsigned int		infoword;
+	xfs_suminfo_t		val;
+	int			error;
 
-	/*
-	 * Compute entry number in the summary file.
-	 */
-	so = xfs_rtsumoffs(mp, log, bbno);
-	/*
-	 * Compute the block number in the summary file.
-	 */
-	sb = xfs_rtsumoffs_to_block(mp, so);
-
-	error = xfs_rtsummary_read_buf(args, sb);
+	error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so));
 	if (error)
 		return error;
 
-	/*
-	 * Point to the summary information, modify/log it, and/or copy it out.
-	 */
 	infoword = xfs_rtsumoffs_to_infoword(mp, so);
-	if (delta) {
-		xfs_suminfo_t	val = xfs_suminfo_add(args, infoword, delta);
-
-		if (mp->m_rsum_cache) {
-			if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
-				mp->m_rsum_cache[bbno] = log;
-			if (val != 0 && log >= mp->m_rsum_cache[bbno])
-				mp->m_rsum_cache[bbno] = log + 1;
-		}
-		xfs_trans_log_rtsummary(args, infoword);
-		if (sum)
-			*sum = val;
-	} else if (sum) {
-		*sum = xfs_suminfo_get(args, infoword);
+	val = xfs_suminfo_add(args, infoword, delta);
+
+	if (mp->m_rsum_cache) {
+		if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
+			mp->m_rsum_cache[bbno] = log;
+		if (val != 0 && log >= mp->m_rsum_cache[bbno])
+			mp->m_rsum_cache[bbno] = log + 1;
 	}
-	return 0;
-}
 
-int
-xfs_rtmodify_summary(
-	struct xfs_rtalloc_args	*args,
-	int			log,	/* log2 of extent size */
-	xfs_fileoff_t		bbno,	/* bitmap block number */
-	int			delta)	/* in/out: summary block number */
-{
-	return xfs_rtmodify_summary_int(args, log, bbno, delta, NULL);
+	xfs_trans_log_rtsummary(args, infoword);
+	return 0;
 }
 
 /*
@@ -528,7 +495,14 @@ xfs_rtget_summary(
 	xfs_fileoff_t		bbno,	/* bitmap block number */
 	xfs_suminfo_t		*sum)	/* out: summary info for this block */
 {
-	return xfs_rtmodify_summary_int(args, log, bbno, 0, sum);
+	struct xfs_mount	*mp = args->mp;
+	xfs_rtsumoff_t		so = xfs_rtsumoffs(mp, log, bbno);
+	int			error;
+
+	error = xfs_rtsummary_read_buf(args, xfs_rtsumoffs_to_block(mp, so));
+	if (!error)
+		*sum = xfs_suminfo_get(args, xfs_rtsumoffs_to_infoword(mp, so));
+	return error;
 }
 
 /* Log rtbitmap block from the word @from to the byte before @next. */
-- 
2.44.0

[PATCH 52/67] xfs: remove rt-wrappers from xfs_format.h

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 3abfe6c2759e2e3000b13f8ce8a1a325e80987a1

xfs_format.h has a bunch odd wrappers for helper functions and mount
structure access using RT* prefixes.  Replace them with their open coded
versions (for those that weren't entirely unused) and remove the wrappers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 db/check.c            |  4 ++--
 libxfs/xfs_format.h   |  8 --------
 libxfs/xfs_rtbitmap.c | 24 ++++++++++++------------
 repair/rt.c           |  6 ++----
 4 files changed, 16 insertions(+), 26 deletions(-)

diff --git a/db/check.c b/db/check.c
index a47a5d9cb..36d82af0a 100644
--- a/db/check.c
+++ b/db/check.c
@@ -3647,7 +3647,7 @@ process_rtbitmap(
 			} else if (prevbit == 1) {
 				len = ((int)bmbno - start_bmbno) *
 					bitsperblock + (bit - start_bit);
-				log = XFS_RTBLOCKLOG(len);
+				log = xfs_highbit64(len);
 				offs = xfs_rtsumoffs(mp, log, start_bmbno);
 				sumcompute[offs]++;
 				prevbit = 0;
@@ -3660,7 +3660,7 @@ process_rtbitmap(
 	if (prevbit == 1) {
 		len = ((int)bmbno - start_bmbno) * bitsperblock +
 			(bit - start_bit);
-		log = XFS_RTBLOCKLOG(len);
+		log = xfs_highbit64(len);
 		offs = xfs_rtsumoffs(mp, log, start_bmbno);
 		sumcompute[offs]++;
 	}
diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index e6ca188e2..7d2873a79 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -1156,20 +1156,12 @@ static inline bool xfs_dinode_has_large_extent_counts(
 #define	XFS_DFL_RTEXTSIZE	(64 * 1024)	        /* 64kB */
 #define	XFS_MIN_RTEXTSIZE	(4 * 1024)		/* 4kB */
 
-#define	XFS_BLOCKSIZE(mp)	((mp)->m_sb.sb_blocksize)
-#define	XFS_BLOCKMASK(mp)	((mp)->m_blockmask)
-
 /*
  * RT bit manipulation macros.
  */
 #define	XFS_RTMIN(a,b)	((a) < (b) ? (a) : (b))
 #define	XFS_RTMAX(a,b)	((a) > (b) ? (a) : (b))
 
-#define	XFS_RTLOBIT(w)	xfs_lowbit32(w)
-#define	XFS_RTHIBIT(w)	xfs_highbit32(w)
-
-#define	XFS_RTBLOCKLOG(b)	xfs_highbit64(b)
-
 /*
  * Dquot and dquot block format definitions
  */
diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index bbf955be8..eefc45c64 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -193,7 +193,7 @@ xfs_rtfind_back(
 			/*
 			 * Different.  Mark where we are and return.
 			 */
-			i = bit - XFS_RTHIBIT(wdiff);
+			i = bit - xfs_highbit32(wdiff);
 			*rtx = start - i + 1;
 			return 0;
 		}
@@ -231,7 +231,7 @@ xfs_rtfind_back(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+			i += XFS_NBWORD - 1 - xfs_highbit32(wdiff);
 			*rtx = start - i + 1;
 			return 0;
 		}
@@ -270,7 +270,7 @@ xfs_rtfind_back(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_NBWORD - 1 - XFS_RTHIBIT(wdiff);
+			i += XFS_NBWORD - 1 - xfs_highbit32(wdiff);
 			*rtx = start - i + 1;
 			return 0;
 		} else
@@ -346,7 +346,7 @@ xfs_rtfind_forw(
 			/*
 			 * Different.  Mark where we are and return.
 			 */
-			i = XFS_RTLOBIT(wdiff) - bit;
+			i = xfs_lowbit32(wdiff) - bit;
 			*rtx = start + i - 1;
 			return 0;
 		}
@@ -384,7 +384,7 @@ xfs_rtfind_forw(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*rtx = start + i - 1;
 			return 0;
 		}
@@ -421,7 +421,7 @@ xfs_rtfind_forw(
 			/*
 			 * Different, mark where we are and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*rtx = start + i - 1;
 			return 0;
 		} else
@@ -706,7 +706,7 @@ xfs_rtfree_range(
 	 */
 	if (preblock < start) {
 		error = xfs_rtmodify_summary(args,
-				XFS_RTBLOCKLOG(start - preblock),
+				xfs_highbit64(start - preblock),
 				xfs_rtx_to_rbmblock(mp, preblock), -1);
 		if (error) {
 			return error;
@@ -718,7 +718,7 @@ xfs_rtfree_range(
 	 */
 	if (postblock > end) {
 		error = xfs_rtmodify_summary(args,
-				XFS_RTBLOCKLOG(postblock - end),
+				xfs_highbit64(postblock - end),
 				xfs_rtx_to_rbmblock(mp, end + 1), -1);
 		if (error) {
 			return error;
@@ -729,7 +729,7 @@ xfs_rtfree_range(
 	 * (new) free extent.
 	 */
 	return xfs_rtmodify_summary(args,
-			XFS_RTBLOCKLOG(postblock + 1 - preblock),
+			xfs_highbit64(postblock + 1 - preblock),
 			xfs_rtx_to_rbmblock(mp, preblock), 1);
 }
 
@@ -798,7 +798,7 @@ xfs_rtcheck_range(
 			/*
 			 * Different, compute first wrong bit and return.
 			 */
-			i = XFS_RTLOBIT(wdiff) - bit;
+			i = xfs_lowbit32(wdiff) - bit;
 			*new = start + i;
 			*stat = 0;
 			return 0;
@@ -837,7 +837,7 @@ xfs_rtcheck_range(
 			/*
 			 * Different, compute first wrong bit and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*new = start + i;
 			*stat = 0;
 			return 0;
@@ -875,7 +875,7 @@ xfs_rtcheck_range(
 			/*
 			 * Different, compute first wrong bit and return.
 			 */
-			i += XFS_RTLOBIT(wdiff);
+			i += xfs_lowbit32(wdiff);
 			*new = start + i;
 			*stat = 0;
 			return 0;
diff --git a/repair/rt.c b/repair/rt.c
index 9f3bc8d53..d5283c57f 100644
--- a/repair/rt.c
+++ b/repair/rt.c
@@ -14,8 +14,6 @@
 #include "err_protos.h"
 #include "rt.h"
 
-#define xfs_highbit64 libxfs_highbit64	/* for XFS_RTBLOCKLOG macro */
-
 void
 rtinit(xfs_mount_t *mp)
 {
@@ -90,7 +88,7 @@ generate_rtinfo(xfs_mount_t	*mp,
 				}
 			} else if (in_extent == 1) {
 				len = (int) (extno - start_ext);
-				log = XFS_RTBLOCKLOG(len);
+				log = libxfs_highbit64(len);
 				offs = xfs_rtsumoffs(mp, log, start_bmbno);
 				sumcompute[offs]++;
 				in_extent = 0;
@@ -106,7 +104,7 @@ generate_rtinfo(xfs_mount_t	*mp,
 	}
 	if (in_extent == 1) {
 		len = (int) (extno - start_ext);
-		log = XFS_RTBLOCKLOG(len);
+		log = libxfs_highbit64(len);
 		offs = xfs_rtsumoffs(mp, log, start_bmbno);
 		sumcompute[offs]++;
 	}
-- 
2.44.0

[PATCH 53/67] xfs: remove XFS_RTMIN/XFS_RTMAX

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: a39f5ccc30d5a00b7e6d921aa387ad17d1e6d168

Use the kernel min/max helpers instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_format.h   | 6 ------
 libxfs/xfs_rtbitmap.c | 8 ++++----
 mkfs/proto.c          | 3 +--
 3 files changed, 5 insertions(+), 12 deletions(-)

diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index 7d2873a79..382ab1e71 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -1156,12 +1156,6 @@ static inline bool xfs_dinode_has_large_extent_counts(
 #define	XFS_DFL_RTEXTSIZE	(64 * 1024)	        /* 64kB */
 #define	XFS_MIN_RTEXTSIZE	(4 * 1024)		/* 4kB */
 
-/*
- * RT bit manipulation macros.
- */
-#define	XFS_RTMIN(a,b)	((a) < (b) ? (a) : (b))
-#define	XFS_RTMAX(a,b)	((a) > (b) ? (a) : (b))
-
 /*
  * Dquot and dquot block format definitions
  */
diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index eefc45c64..79af7cda3 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -182,7 +182,7 @@ xfs_rtfind_back(
 		 * Calculate first (leftmost) bit number to look at,
 		 * and mask for all the relevant bits in this word.
 		 */
-		firstbit = XFS_RTMAX((xfs_srtblock_t)(bit - len + 1), 0);
+		firstbit = max_t(xfs_srtblock_t, bit - len + 1, 0);
 		mask = (((xfs_rtword_t)1 << (bit - firstbit + 1)) - 1) <<
 			firstbit;
 		/*
@@ -336,7 +336,7 @@ xfs_rtfind_forw(
 		 * Calculate last (rightmost) bit number to look at,
 		 * and mask for all the relevant bits in this word.
 		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		lastbit = min(bit + len, XFS_NBWORD);
 		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
 		/*
 		 * Calculate the difference between the value there
@@ -571,7 +571,7 @@ xfs_rtmodify_range(
 		/*
 		 * Compute first bit not changed and mask of relevant bits.
 		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		lastbit = min(bit + len, XFS_NBWORD);
 		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
 		/*
 		 * Set/clear the active bits.
@@ -785,7 +785,7 @@ xfs_rtcheck_range(
 		/*
 		 * Compute first bit not examined.
 		 */
-		lastbit = XFS_RTMIN(bit + len, XFS_NBWORD);
+		lastbit = min(bit + len, XFS_NBWORD);
 		/*
 		 * Mask of relevant bits.
 		 */
diff --git a/mkfs/proto.c b/mkfs/proto.c
index e9c633ed3..ec28728d4 100644
--- a/mkfs/proto.c
+++ b/mkfs/proto.c
@@ -780,8 +780,7 @@ rtinit(
 		if (i)
 			res_failed(i);
 		libxfs_trans_ijoin(tp, rbmip, 0);
-		ebno = XFS_RTMIN(mp->m_sb.sb_rextents,
-			bno + NBBY * mp->m_sb.sb_blocksize);
+		ebno = min(mp->m_sb.sb_rextents, bno + NBBY * mp->m_sb.sb_blocksize);
 		error = -libxfs_rtfree_extent(tp, bno, (xfs_extlen_t)(ebno-bno));
 		if (error) {
 			fail(_("Error initializing the realtime space"),
-- 
2.44.0

[PATCH 54/67] xfs: make if_data a void pointer

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 6e145f943bd86be47e54101fa5939f9ed0cb73e5

The xfs_ifork structure currently has a union of the if_root void pointer
and the if_data char pointer.  In either case it is an opaque pointer
that depends on the fork format.  Replace the union with a single if_data
void pointer as that is what almost all callers want.  Only the symlink
NULL termination code in xfs_init_local_fork actually needs a new local
variable now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 db/namei.c                  |  3 +-
 libxfs/util.c               |  2 +-
 libxfs/xfs_attr.c           |  3 +-
 libxfs/xfs_attr_leaf.c      | 62 ++++++++++++++-----------------------
 libxfs/xfs_bmap.c           |  4 +--
 libxfs/xfs_dir2.c           |  2 +-
 libxfs/xfs_dir2_block.c     |  6 ++--
 libxfs/xfs_dir2_sf.c        | 61 ++++++++++++++----------------------
 libxfs/xfs_iext_tree.c      | 36 ++++++++++-----------
 libxfs/xfs_inode_fork.c     | 53 ++++++++++++++-----------------
 libxfs/xfs_inode_fork.h     |  8 ++---
 libxfs/xfs_symlink_remote.c |  4 +--
 repair/phase6.c             |  9 +++---
 13 files changed, 107 insertions(+), 146 deletions(-)

diff --git a/db/namei.c b/db/namei.c
index 063721ca9..80252b902 100644
--- a/db/namei.c
+++ b/db/namei.c
@@ -290,13 +290,12 @@ list_sfdir(
 	struct xfs_mount		*mp = dp->i_mount;
 	struct xfs_da_geometry		*geo = args->geo;
 	struct xfs_dir2_sf_entry	*sfep;
-	struct xfs_dir2_sf_hdr		*sfp;
+	struct xfs_dir2_sf_hdr		*sfp = dp->i_df.if_data;
 	xfs_ino_t			ino;
 	xfs_dir2_dataptr_t		off;
 	unsigned int			i;
 	uint8_t				filetype;
 
-	sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data;
 
 	/* . and .. entries */
 	off = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
diff --git a/libxfs/util.c b/libxfs/util.c
index 8517bfb64..8cea0c150 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -316,7 +316,7 @@ libxfs_init_new_inode(
 	case S_IFLNK:
 		ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
 		ip->i_df.if_bytes = 0;
-		ip->i_df.if_u1.if_root = NULL;
+		ip->i_df.if_data = NULL;
 		break;
 	default:
 		ASSERT(0);
diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index cb6c8d081..d7512efd4 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -1047,9 +1047,8 @@ out_trans_cancel:
 
 static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
 {
-	struct xfs_attr_shortform *sf;
+	struct xfs_attr_shortform *sf = dp->i_af.if_data;
 
-	sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
 	return be16_to_cpu(sf->hdr.totsize);
 }
 
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 8329348eb..5ab52bf1a 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -688,7 +688,7 @@ xfs_attr_shortform_create(
 	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS)
 		ifp->if_format = XFS_DINODE_FMT_LOCAL;
 	xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
-	hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+	hdr = ifp->if_data;
 	memset(hdr, 0, sizeof(*hdr));
 	hdr->totsize = cpu_to_be16(sizeof(*hdr));
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
@@ -709,14 +709,13 @@ xfs_attr_sf_findname(
 	struct xfs_attr_sf_entry **sfep,
 	unsigned int		 *basep)
 {
-	struct xfs_attr_shortform *sf;
+	struct xfs_attr_shortform *sf = args->dp->i_af.if_data;
 	struct xfs_attr_sf_entry *sfe;
 	unsigned int		base = sizeof(struct xfs_attr_sf_hdr);
 	int			size = 0;
 	int			end;
 	int			i;
 
-	sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
 	sfe = &sf->list[0];
 	end = sf->hdr.count;
 	for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe),
@@ -748,29 +747,25 @@ xfs_attr_shortform_add(
 	struct xfs_da_args		*args,
 	int				forkoff)
 {
-	struct xfs_attr_shortform	*sf;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_mount		*mp = dp->i_mount;
+	struct xfs_ifork		*ifp = &dp->i_af;
+	struct xfs_attr_shortform	*sf = ifp->if_data;
 	struct xfs_attr_sf_entry	*sfe;
 	int				offset, size;
-	struct xfs_mount		*mp;
-	struct xfs_inode		*dp;
-	struct xfs_ifork		*ifp;
 
 	trace_xfs_attr_sf_add(args);
 
-	dp = args->dp;
-	mp = dp->i_mount;
 	dp->i_forkoff = forkoff;
 
-	ifp = &dp->i_af;
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
 		ASSERT(0);
 
 	offset = (char *)sfe - (char *)sf;
 	size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen);
 	xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
+	sf = ifp->if_data;
 	sfe = (struct xfs_attr_sf_entry *)((char *)sf + offset);
 
 	sfe->namelen = args->namelen;
@@ -808,20 +803,16 @@ int
 xfs_attr_sf_removename(
 	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform	*sf;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_mount		*mp = dp->i_mount;
+	struct xfs_attr_shortform	*sf = dp->i_af.if_data;
 	struct xfs_attr_sf_entry	*sfe;
 	int				size = 0, end, totsize;
 	unsigned int			base;
-	struct xfs_mount		*mp;
-	struct xfs_inode		*dp;
 	int				error;
 
 	trace_xfs_attr_sf_remove(args);
 
-	dp = args->dp;
-	mp = dp->i_mount;
-	sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
-
 	error = xfs_attr_sf_findname(args, &sfe, &base);
 
 	/*
@@ -875,18 +866,17 @@ xfs_attr_sf_removename(
  */
 /*ARGSUSED*/
 int
-xfs_attr_shortform_lookup(xfs_da_args_t *args)
+xfs_attr_shortform_lookup(
+	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform *sf;
-	struct xfs_attr_sf_entry *sfe;
-	int i;
-	struct xfs_ifork *ifp;
+	struct xfs_ifork		*ifp = &args->dp->i_af;
+	struct xfs_attr_shortform	*sf = ifp->if_data;
+	struct xfs_attr_sf_entry	*sfe;
+	int				i;
 
 	trace_xfs_attr_sf_lookup(args);
 
-	ifp = &args->dp->i_af;
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
 				sfe = xfs_attr_sf_nextentry(sfe), i++) {
@@ -906,14 +896,13 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
  */
 int
 xfs_attr_shortform_getvalue(
-	struct xfs_da_args	*args)
+	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform *sf;
-	struct xfs_attr_sf_entry *sfe;
-	int			i;
+	struct xfs_attr_shortform	*sf = args->dp->i_af.if_data;
+	struct xfs_attr_sf_entry	*sfe;
+	int				i;
 
 	ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL);
-	sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
 				sfe = xfs_attr_sf_nextentry(sfe), i++) {
@@ -930,25 +919,22 @@ int
 xfs_attr_shortform_to_leaf(
 	struct xfs_da_args		*args)
 {
-	struct xfs_inode		*dp;
-	struct xfs_attr_shortform	*sf;
+	struct xfs_inode		*dp = args->dp;
+	struct xfs_ifork		*ifp = &dp->i_af;
+	struct xfs_attr_shortform	*sf = ifp->if_data;
 	struct xfs_attr_sf_entry	*sfe;
 	struct xfs_da_args		nargs;
 	char				*tmpbuffer;
 	int				error, i, size;
 	xfs_dablk_t			blkno;
 	struct xfs_buf			*bp;
-	struct xfs_ifork		*ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
 
-	dp = args->dp;
-	ifp = &dp->i_af;
-	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	size = be16_to_cpu(sf->hdr.totsize);
 	tmpbuffer = kmem_alloc(size, 0);
 	ASSERT(tmpbuffer != NULL);
-	memcpy(tmpbuffer, ifp->if_u1.if_data, size);
+	memcpy(tmpbuffer, ifp->if_data, size);
 	sf = (struct xfs_attr_shortform *)tmpbuffer;
 
 	xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index b977032d8..5e6a5e1f3 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -741,7 +741,7 @@ xfs_bmap_local_to_extents_empty(
 	ASSERT(ifp->if_nextents == 0);
 
 	xfs_bmap_forkoff_reset(ip, whichfork);
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 	ifp->if_format = XFS_DINODE_FMT_EXTENTS;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -826,7 +826,7 @@ xfs_bmap_local_to_extents(
 	xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
 	flags |= XFS_ILOG_CORE;
 
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 
 	rec.br_startoff = 0;
diff --git a/libxfs/xfs_dir2.c b/libxfs/xfs_dir2.c
index c19684b34..a781520c8 100644
--- a/libxfs/xfs_dir2.c
+++ b/libxfs/xfs_dir2.c
@@ -195,7 +195,7 @@ xfs_dir_isempty(
 		return 1;
 	if (dp->i_disk_size > xfs_inode_data_fork_size(dp))
 		return 0;
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	return !sfp->count;
 }
 
diff --git a/libxfs/xfs_dir2_block.c b/libxfs/xfs_dir2_block.c
index bb9301b76..bf950c700 100644
--- a/libxfs/xfs_dir2_block.c
+++ b/libxfs/xfs_dir2_block.c
@@ -1086,7 +1086,7 @@ xfs_dir2_sf_to_block(
 	int			newoffset;	/* offset from current entry */
 	unsigned int		offset = geo->data_entry_offset;
 	xfs_dir2_sf_entry_t	*sfep;		/* sf entry pointer */
-	xfs_dir2_sf_hdr_t	*oldsfp;	/* old shortform header  */
+	struct xfs_dir2_sf_hdr	*oldsfp = ifp->if_data;
 	xfs_dir2_sf_hdr_t	*sfp;		/* shortform header  */
 	__be16			*tagp;		/* end of data entry */
 	struct xfs_name		name;
@@ -1096,10 +1096,8 @@ xfs_dir2_sf_to_block(
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 
-	oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
-
 	ASSERT(ifp->if_bytes == dp->i_disk_size);
-	ASSERT(ifp->if_u1.if_data != NULL);
+	ASSERT(oldsfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
 	ASSERT(dp->i_df.if_nextents == 0);
 
diff --git a/libxfs/xfs_dir2_sf.c b/libxfs/xfs_dir2_sf.c
index 260eccacf..b2b43e937 100644
--- a/libxfs/xfs_dir2_sf.c
+++ b/libxfs/xfs_dir2_sf.c
@@ -364,25 +364,23 @@ int						/* error */
 xfs_dir2_sf_addname(
 	xfs_da_args_t		*args)		/* operation arguments */
 {
-	xfs_inode_t		*dp;		/* incore directory inode */
+	struct xfs_inode	*dp = args->dp;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			error;		/* error return value */
 	int			incr_isize;	/* total change in size */
 	int			new_isize;	/* size after adding name */
 	int			objchange;	/* changing to 8-byte inodes */
 	xfs_dir2_data_aoff_t	offset = 0;	/* offset for new entry */
 	int			pick;		/* which algorithm to use */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 	xfs_dir2_sf_entry_t	*sfep = NULL;	/* shortform entry */
 
 	trace_xfs_dir2_sf_addname(args);
 
 	ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT);
-	dp = args->dp;
 	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Compute entry (and change in) size.
@@ -462,11 +460,9 @@ xfs_dir2_sf_addname_easy(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
-	int			byteoff;	/* byte offset in sf dir */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
+	int			byteoff = (int)((char *)sfep - (char *)sfp);
 
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	byteoff = (int)((char *)sfep - (char *)sfp);
 	/*
 	 * Grow the in-inode space.
 	 */
@@ -475,7 +471,7 @@ xfs_dir2_sf_addname_easy(
 	/*
 	 * Need to set up again due to realloc of the inode data.
 	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff);
 	/*
 	 * Fill in the new entry.
@@ -528,11 +524,10 @@ xfs_dir2_sf_addname_hard(
 	/*
 	 * Copy the old directory to the stack buffer.
 	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	old_isize = (int)dp->i_disk_size;
 	buf = kmem_alloc(old_isize, 0);
 	oldsfp = (xfs_dir2_sf_hdr_t *)buf;
-	memcpy(oldsfp, sfp, old_isize);
+	memcpy(oldsfp, dp->i_df.if_data, old_isize);
 	/*
 	 * Loop over the old directory finding the place we're going
 	 * to insert the new entry.
@@ -560,7 +555,7 @@ xfs_dir2_sf_addname_hard(
 	/*
 	 * Reset the pointer since the buffer was reallocated.
 	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	/*
 	 * Copy the first part of the directory, including the header.
 	 */
@@ -610,11 +605,10 @@ xfs_dir2_sf_addname_pick(
 	int			i;		/* entry number */
 	xfs_dir2_data_aoff_t	offset;		/* data block offset */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			size;		/* entry's data size */
 	int			used;		/* data bytes used */
 
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	size = xfs_dir2_data_entsize(mp, args->namelen);
 	offset = args->geo->data_first_offset;
 	sfep = xfs_dir2_sf_firstentry(sfp);
@@ -673,14 +667,13 @@ xfs_dir2_sf_check(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			i;		/* entry number */
 	int			i8count;	/* number of big inode#s */
 	xfs_ino_t		ino;		/* entry inode number */
 	int			offset;		/* data offset */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform dir entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	offset = args->geo->data_first_offset;
 	ino = xfs_dir2_sf_get_parent_ino(sfp);
 	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
@@ -834,7 +827,7 @@ xfs_dir2_sf_create(
 	/*
 	 * Fill in the header,
 	 */
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	sfp->i8count = i8count;
 	/*
 	 * Now can put in the inode number, since i8count is set.
@@ -857,9 +850,9 @@ xfs_dir2_sf_lookup(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			i;		/* entry index */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 	enum xfs_dacmp		cmp;		/* comparison result */
 	xfs_dir2_sf_entry_t	*ci_sfep;	/* case-insens. entry */
 
@@ -870,8 +863,7 @@ xfs_dir2_sf_lookup(
 	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Special case for .
@@ -933,13 +925,13 @@ xfs_dir2_sf_removename(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			byteoff;	/* offset of removed entry */
 	int			entsize;	/* this entry's size */
 	int			i;		/* shortform entry index */
 	int			newsize;	/* new inode size */
 	int			oldsize;	/* old inode size */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 
 	trace_xfs_dir2_sf_removename(args);
 
@@ -947,8 +939,7 @@ xfs_dir2_sf_removename(
 	oldsize = (int)dp->i_disk_size;
 	ASSERT(oldsize >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == oldsize);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Loop over the old directory entries.
@@ -989,7 +980,7 @@ xfs_dir2_sf_removename(
 	 * Reallocate, making it smaller.
 	 */
 	xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	/*
 	 * Are we changing inode number size?
 	 */
@@ -1012,13 +1003,12 @@ xfs_dir2_sf_replace_needblock(
 	struct xfs_inode	*dp,
 	xfs_ino_t		inum)
 {
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			newsize;
-	struct xfs_dir2_sf_hdr	*sfp;
 
 	if (dp->i_df.if_format != XFS_DINODE_FMT_LOCAL)
 		return false;
 
-	sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data;
 	newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF;
 
 	return inum > XFS_DIR2_MAX_SHORT_INUM &&
@@ -1034,19 +1024,18 @@ xfs_dir2_sf_replace(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*sfp = dp->i_df.if_data;
 	int			i;		/* entry index */
 	xfs_ino_t		ino=0;		/* entry old inode number */
 	int			i8elevated;	/* sf_toino8 set i8count=1 */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
-	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 
 	trace_xfs_dir2_sf_replace(args);
 
 	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	ASSERT(sfp != NULL);
 	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 
 	/*
@@ -1069,7 +1058,7 @@ xfs_dir2_sf_replace(
 		 */
 		xfs_dir2_sf_toino8(args);
 		i8elevated = 1;
-		sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+		sfp = dp->i_df.if_data;
 	} else
 		i8elevated = 0;
 
@@ -1150,11 +1139,11 @@ xfs_dir2_sf_toino4(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*oldsfp = dp->i_df.if_data;
 	char			*buf;		/* old dir's buffer */
 	int			i;		/* entry index */
 	int			newsize;	/* new inode size */
 	xfs_dir2_sf_entry_t	*oldsfep;	/* old sf entry */
-	xfs_dir2_sf_hdr_t	*oldsfp;	/* old sf directory */
 	int			oldsize;	/* old inode size */
 	xfs_dir2_sf_entry_t	*sfep;		/* new sf entry */
 	xfs_dir2_sf_hdr_t	*sfp;		/* new sf directory */
@@ -1168,7 +1157,6 @@ xfs_dir2_sf_toino4(
 	 */
 	oldsize = dp->i_df.if_bytes;
 	buf = kmem_alloc(oldsize, 0);
-	oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	ASSERT(oldsfp->i8count == 1);
 	memcpy(buf, oldsfp, oldsize);
 	/*
@@ -1181,7 +1169,7 @@ xfs_dir2_sf_toino4(
 	 * Reset our pointers, the data has moved.
 	 */
 	oldsfp = (xfs_dir2_sf_hdr_t *)buf;
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	/*
 	 * Fill in the new header.
 	 */
@@ -1223,11 +1211,11 @@ xfs_dir2_sf_toino8(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir2_sf_hdr	*oldsfp = dp->i_df.if_data;
 	char			*buf;		/* old dir's buffer */
 	int			i;		/* entry index */
 	int			newsize;	/* new inode size */
 	xfs_dir2_sf_entry_t	*oldsfep;	/* old sf entry */
-	xfs_dir2_sf_hdr_t	*oldsfp;	/* old sf directory */
 	int			oldsize;	/* old inode size */
 	xfs_dir2_sf_entry_t	*sfep;		/* new sf entry */
 	xfs_dir2_sf_hdr_t	*sfp;		/* new sf directory */
@@ -1241,7 +1229,6 @@ xfs_dir2_sf_toino8(
 	 */
 	oldsize = dp->i_df.if_bytes;
 	buf = kmem_alloc(oldsize, 0);
-	oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	ASSERT(oldsfp->i8count == 0);
 	memcpy(buf, oldsfp, oldsize);
 	/*
@@ -1254,7 +1241,7 @@ xfs_dir2_sf_toino8(
 	 * Reset our pointers, the data has moved.
 	 */
 	oldsfp = (xfs_dir2_sf_hdr_t *)buf;
-	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	sfp = dp->i_df.if_data;
 	/*
 	 * Fill in the new header.
 	 */
diff --git a/libxfs/xfs_iext_tree.c b/libxfs/xfs_iext_tree.c
index 5d0be2dc8..24124039f 100644
--- a/libxfs/xfs_iext_tree.c
+++ b/libxfs/xfs_iext_tree.c
@@ -158,7 +158,7 @@ static void *
 xfs_iext_find_first_leaf(
 	struct xfs_ifork	*ifp)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height;
 
 	if (!ifp->if_height)
@@ -176,7 +176,7 @@ static void *
 xfs_iext_find_last_leaf(
 	struct xfs_ifork	*ifp)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height, i;
 
 	if (!ifp->if_height)
@@ -306,7 +306,7 @@ xfs_iext_find_level(
 	xfs_fileoff_t		offset,
 	int			level)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height, i;
 
 	if (!ifp->if_height)
@@ -402,12 +402,12 @@ xfs_iext_grow(
 	int			i;
 
 	if (ifp->if_height == 1) {
-		struct xfs_iext_leaf *prev = ifp->if_u1.if_root;
+		struct xfs_iext_leaf *prev = ifp->if_data;
 
 		node->keys[0] = xfs_iext_leaf_key(prev, 0);
 		node->ptrs[0] = prev;
 	} else  {
-		struct xfs_iext_node *prev = ifp->if_u1.if_root;
+		struct xfs_iext_node *prev = ifp->if_data;
 
 		ASSERT(ifp->if_height > 1);
 
@@ -418,7 +418,7 @@ xfs_iext_grow(
 	for (i = 1; i < KEYS_PER_NODE; i++)
 		node->keys[i] = XFS_IEXT_KEY_INVALID;
 
-	ifp->if_u1.if_root = node;
+	ifp->if_data = node;
 	ifp->if_height++;
 }
 
@@ -430,7 +430,7 @@ xfs_iext_update_node(
 	int			level,
 	void			*ptr)
 {
-	struct xfs_iext_node	*node = ifp->if_u1.if_root;
+	struct xfs_iext_node	*node = ifp->if_data;
 	int			height, i;
 
 	for (height = ifp->if_height; height > level; height--) {
@@ -583,11 +583,11 @@ xfs_iext_alloc_root(
 {
 	ASSERT(ifp->if_bytes == 0);
 
-	ifp->if_u1.if_root = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS);
+	ifp->if_data = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS);
 	ifp->if_height = 1;
 
 	/* now that we have a node step into it */
-	cur->leaf = ifp->if_u1.if_root;
+	cur->leaf = ifp->if_data;
 	cur->pos = 0;
 }
 
@@ -603,9 +603,9 @@ xfs_iext_realloc_root(
 	if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF)
 		new_size = NODE_SIZE;
 
-	new = krealloc(ifp->if_u1.if_root, new_size, GFP_NOFS | __GFP_NOFAIL);
+	new = krealloc(ifp->if_data, new_size, GFP_NOFS | __GFP_NOFAIL);
 	memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes);
-	ifp->if_u1.if_root = new;
+	ifp->if_data = new;
 	cur->leaf = new;
 }
 
@@ -786,8 +786,8 @@ again:
 		 * If we are at the root and only one entry is left we can just
 		 * free this node and update the root pointer.
 		 */
-		ASSERT(node == ifp->if_u1.if_root);
-		ifp->if_u1.if_root = node->ptrs[0];
+		ASSERT(node == ifp->if_data);
+		ifp->if_data = node->ptrs[0];
 		ifp->if_height--;
 		kmem_free(node);
 	}
@@ -863,8 +863,8 @@ xfs_iext_free_last_leaf(
 	struct xfs_ifork	*ifp)
 {
 	ifp->if_height--;
-	kmem_free(ifp->if_u1.if_root);
-	ifp->if_u1.if_root = NULL;
+	kmem_free(ifp->if_data);
+	ifp->if_data = NULL;
 }
 
 void
@@ -881,7 +881,7 @@ xfs_iext_remove(
 	trace_xfs_iext_remove(ip, cur, state, _RET_IP_);
 
 	ASSERT(ifp->if_height > 0);
-	ASSERT(ifp->if_u1.if_root != NULL);
+	ASSERT(ifp->if_data != NULL);
 	ASSERT(xfs_iext_valid(ifp, cur));
 
 	xfs_iext_inc_seq(ifp);
@@ -1051,9 +1051,9 @@ void
 xfs_iext_destroy(
 	struct xfs_ifork	*ifp)
 {
-	xfs_iext_destroy_node(ifp->if_u1.if_root, ifp->if_height);
+	xfs_iext_destroy_node(ifp->if_data, ifp->if_height);
 
 	ifp->if_bytes = 0;
 	ifp->if_height = 0;
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 }
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index 80f4215d2..fbcda5f54 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -48,12 +48,15 @@ xfs_init_local_fork(
 		mem_size++;
 
 	if (size) {
-		ifp->if_u1.if_data = kmem_alloc(mem_size, KM_NOFS);
-		memcpy(ifp->if_u1.if_data, data, size);
+		char *new_data = kmem_alloc(mem_size, KM_NOFS);
+
+		memcpy(new_data, data, size);
 		if (zero_terminate)
-			ifp->if_u1.if_data[size] = '\0';
+			new_data[size] = '\0';
+
+		ifp->if_data = new_data;
 	} else {
-		ifp->if_u1.if_data = NULL;
+		ifp->if_data = NULL;
 	}
 
 	ifp->if_bytes = size;
@@ -123,7 +126,7 @@ xfs_iformat_extents(
 	}
 
 	ifp->if_bytes = 0;
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 	if (size) {
 		dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
@@ -210,7 +213,7 @@ xfs_iformat_btree(
 			 ifp->if_broot, size);
 
 	ifp->if_bytes = 0;
-	ifp->if_u1.if_root = NULL;
+	ifp->if_data = NULL;
 	ifp->if_height = 0;
 	return 0;
 }
@@ -507,14 +510,14 @@ xfs_idata_realloc(
 		return;
 
 	if (new_size == 0) {
-		kmem_free(ifp->if_u1.if_data);
-		ifp->if_u1.if_data = NULL;
+		kmem_free(ifp->if_data);
+		ifp->if_data = NULL;
 		ifp->if_bytes = 0;
 		return;
 	}
 
-	ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, new_size,
-				      GFP_NOFS | __GFP_NOFAIL);
+	ifp->if_data = krealloc(ifp->if_data, new_size,
+			GFP_NOFS | __GFP_NOFAIL);
 	ifp->if_bytes = new_size;
 }
 
@@ -530,8 +533,8 @@ xfs_idestroy_fork(
 
 	switch (ifp->if_format) {
 	case XFS_DINODE_FMT_LOCAL:
-		kmem_free(ifp->if_u1.if_data);
-		ifp->if_u1.if_data = NULL;
+		kmem_free(ifp->if_data);
+		ifp->if_data = NULL;
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
 	case XFS_DINODE_FMT_BTREE:
@@ -624,9 +627,9 @@ xfs_iflush_fork(
 	case XFS_DINODE_FMT_LOCAL:
 		if ((iip->ili_fields & dataflag[whichfork]) &&
 		    (ifp->if_bytes > 0)) {
-			ASSERT(ifp->if_u1.if_data != NULL);
+			ASSERT(ifp->if_data != NULL);
 			ASSERT(ifp->if_bytes <= xfs_inode_fork_size(ip, whichfork));
-			memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes);
+			memcpy(cp, ifp->if_data, ifp->if_bytes);
 		}
 		break;
 
@@ -704,17 +707,15 @@ xfs_ifork_verify_local_data(
 	case S_IFDIR: {
 		struct xfs_mount	*mp = ip->i_mount;
 		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
-		struct xfs_dir2_sf_hdr	*sfp;
+		struct xfs_dir2_sf_hdr	*sfp = ifp->if_data;
 
-		sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
 		fa = xfs_dir2_sf_verify(mp, sfp, ifp->if_bytes);
 		break;
 	}
 	case S_IFLNK: {
 		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
 
-		fa = xfs_symlink_shortform_verify(ifp->if_u1.if_data,
-				ifp->if_bytes);
+		fa = xfs_symlink_shortform_verify(ifp->if_data, ifp->if_bytes);
 		break;
 	}
 	default:
@@ -723,7 +724,7 @@ xfs_ifork_verify_local_data(
 
 	if (fa) {
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork",
-				ip->i_df.if_u1.if_data, ip->i_df.if_bytes, fa);
+				ip->i_df.if_data, ip->i_df.if_bytes, fa);
 		return -EFSCORRUPTED;
 	}
 
@@ -741,20 +742,14 @@ xfs_ifork_verify_local_attr(
 	if (!xfs_inode_has_attr_fork(ip)) {
 		fa = __this_address;
 	} else {
-		struct xfs_attr_shortform	*sfp;
-		struct xfs_ifork		*ifp;
-		int64_t				size;
-
-		ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL);
-		ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
-		sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-		size = ifp->if_bytes;
+		struct xfs_ifork		*ifp = &ip->i_af;
 
-		fa = xfs_attr_shortform_verify(sfp, size);
+		ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+		fa = xfs_attr_shortform_verify(ifp->if_data, ifp->if_bytes);
 	}
 	if (fa) {
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
-				ifp->if_u1.if_data, ifp->if_bytes, fa);
+				ifp->if_data, ifp->if_bytes, fa);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/libxfs/xfs_inode_fork.h b/libxfs/xfs_inode_fork.h
index 535be5c03..7edcf0e8c 100644
--- a/libxfs/xfs_inode_fork.h
+++ b/libxfs/xfs_inode_fork.h
@@ -13,14 +13,12 @@ struct xfs_dinode;
  * File incore extent information, present for each of data & attr forks.
  */
 struct xfs_ifork {
-	int64_t			if_bytes;	/* bytes in if_u1 */
+	int64_t			if_bytes;	/* bytes in if_data */
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	unsigned int		if_seq;		/* fork mod counter */
 	int			if_height;	/* height of the extent tree */
-	union {
-		void		*if_root;	/* extent tree root */
-		char		*if_data;	/* inline file data */
-	} if_u1;
+	void			*if_data;	/* extent tree root or
+						   inline data */
 	xfs_extnum_t		if_nextents;	/* # of extents in this fork */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	int8_t			if_format;	/* format of this fork */
diff --git a/libxfs/xfs_symlink_remote.c b/libxfs/xfs_symlink_remote.c
index cf894b527..fa90b1793 100644
--- a/libxfs/xfs_symlink_remote.c
+++ b/libxfs/xfs_symlink_remote.c
@@ -172,7 +172,7 @@ xfs_symlink_local_to_remote(
 
 	if (!xfs_has_crc(mp)) {
 		bp->b_ops = NULL;
-		memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
+		memcpy(bp->b_addr, ifp->if_data, ifp->if_bytes);
 		xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
 		return;
 	}
@@ -188,7 +188,7 @@ xfs_symlink_local_to_remote(
 
 	buf = bp->b_addr;
 	buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp);
-	memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes);
+	memcpy(buf, ifp->if_data, ifp->if_bytes);
 	xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) +
 					ifp->if_bytes - 1);
 }
diff --git a/repair/phase6.c b/repair/phase6.c
index 3870c5c93..1b4ec6f90 100644
--- a/repair/phase6.c
+++ b/repair/phase6.c
@@ -515,7 +515,7 @@ mk_rbmino(xfs_mount_t *mp)
 	 * now the ifork
 	 */
 	ip->i_df.if_bytes = 0;
-	ip->i_df.if_u1.if_root = NULL;
+	ip->i_df.if_data = NULL;
 
 	ip->i_disk_size = mp->m_sb.sb_rbmblocks * mp->m_sb.sb_blocksize;
 
@@ -754,7 +754,7 @@ mk_rsumino(xfs_mount_t *mp)
 	 * now the ifork
 	 */
 	ip->i_df.if_bytes = 0;
-	ip->i_df.if_u1.if_root = NULL;
+	ip->i_df.if_data = NULL;
 
 	ip->i_disk_size = mp->m_rsumsize;
 
@@ -854,7 +854,7 @@ mk_root_dir(xfs_mount_t *mp)
 	 * now the ifork
 	 */
 	ip->i_df.if_bytes = 0;
-	ip->i_df.if_u1.if_root = NULL;
+	ip->i_df.if_data = NULL;
 
 	/*
 	 * initialize the directory
@@ -2456,7 +2456,7 @@ shortform_dir2_entry_check(
 {
 	xfs_ino_t		lino;
 	xfs_ino_t		parent;
-	struct xfs_dir2_sf_hdr	*sfp;
+	struct xfs_dir2_sf_hdr	*sfp = ip->i_df.if_data;
 	struct xfs_dir2_sf_entry *sfep;
 	struct xfs_dir2_sf_entry *next_sfep;
 	struct xfs_ifork	*ifp;
@@ -2471,7 +2471,6 @@ shortform_dir2_entry_check(
 	int			i8;
 
 	ifp = &ip->i_df;
-	sfp = (struct xfs_dir2_sf_hdr *) ifp->if_u1.if_data;
 	*ino_dirty = 0;
 	bytes_deleted = 0;
 
-- 
2.44.0

[PATCH 55/67] xfs: return if_data from xfs_idata_realloc

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 45c76a2add55b332d965c901e14004ae0134a67e

Many of the xfs_idata_realloc callers need to set a local pointer to the
just reallocated if_data memory.  Return the pointer to simplify them a
bit and use the opportunity to re-use krealloc for freeing if_data if the
size hits 0.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr_leaf.c  |  7 +++----
 libxfs/xfs_dir2_sf.c    | 25 ++++++++++---------------
 libxfs/xfs_inode_fork.c | 20 ++++++++------------
 libxfs/xfs_inode_fork.h |  2 +-
 4 files changed, 22 insertions(+), 32 deletions(-)

diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 5ab52bf1a..a21740a87 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -687,8 +687,8 @@ xfs_attr_shortform_create(
 	ASSERT(ifp->if_bytes == 0);
 	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS)
 		ifp->if_format = XFS_DINODE_FMT_LOCAL;
-	xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
-	hdr = ifp->if_data;
+
+	hdr = xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
 	memset(hdr, 0, sizeof(*hdr));
 	hdr->totsize = cpu_to_be16(sizeof(*hdr));
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
@@ -764,8 +764,7 @@ xfs_attr_shortform_add(
 
 	offset = (char *)sfe - (char *)sf;
 	size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen);
-	xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
-	sf = ifp->if_data;
+	sf = xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
 	sfe = (struct xfs_attr_sf_entry *)((char *)sf + offset);
 
 	sfe->namelen = args->namelen;
diff --git a/libxfs/xfs_dir2_sf.c b/libxfs/xfs_dir2_sf.c
index b2b43e937..37c7e1d5c 100644
--- a/libxfs/xfs_dir2_sf.c
+++ b/libxfs/xfs_dir2_sf.c
@@ -466,12 +466,11 @@ xfs_dir2_sf_addname_easy(
 	/*
 	 * Grow the in-inode space.
 	 */
-	xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen),
+	sfp = xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen),
 			  XFS_DATA_FORK);
 	/*
 	 * Need to set up again due to realloc of the inode data.
 	 */
-	sfp = dp->i_df.if_data;
 	sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff);
 	/*
 	 * Fill in the new entry.
@@ -551,11 +550,8 @@ xfs_dir2_sf_addname_hard(
 	 * the data.
 	 */
 	xfs_idata_realloc(dp, -old_isize, XFS_DATA_FORK);
-	xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK);
-	/*
-	 * Reset the pointer since the buffer was reallocated.
-	 */
-	sfp = dp->i_df.if_data;
+	sfp = xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK);
+
 	/*
 	 * Copy the first part of the directory, including the header.
 	 */
@@ -820,15 +816,13 @@ xfs_dir2_sf_create(
 	ASSERT(dp->i_df.if_bytes == 0);
 	i8count = pino > XFS_DIR2_MAX_SHORT_INUM;
 	size = xfs_dir2_sf_hdr_size(i8count);
+
 	/*
-	 * Make a buffer for the data.
-	 */
-	xfs_idata_realloc(dp, size, XFS_DATA_FORK);
-	/*
-	 * Fill in the header,
+	 * Make a buffer for the data and fill in the header.
 	 */
-	sfp = dp->i_df.if_data;
+	sfp = xfs_idata_realloc(dp, size, XFS_DATA_FORK);
 	sfp->i8count = i8count;
+
 	/*
 	 * Now can put in the inode number, since i8count is set.
 	 */
@@ -976,11 +970,12 @@ xfs_dir2_sf_removename(
 	 */
 	sfp->count--;
 	dp->i_disk_size = newsize;
+
 	/*
 	 * Reallocate, making it smaller.
 	 */
-	xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK);
-	sfp = dp->i_df.if_data;
+	sfp = xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK);
+
 	/*
 	 * Are we changing inode number size?
 	 */
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index fbcda5f54..c95abd43a 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -494,7 +494,7 @@ xfs_iroot_realloc(
  * byte_diff -- the change in the number of bytes, positive or negative,
  *	 requested for the if_data array.
  */
-void
+void *
 xfs_idata_realloc(
 	struct xfs_inode	*ip,
 	int64_t			byte_diff,
@@ -506,19 +506,15 @@ xfs_idata_realloc(
 	ASSERT(new_size >= 0);
 	ASSERT(new_size <= xfs_inode_fork_size(ip, whichfork));
 
-	if (byte_diff == 0)
-		return;
-
-	if (new_size == 0) {
-		kmem_free(ifp->if_data);
-		ifp->if_data = NULL;
-		ifp->if_bytes = 0;
-		return;
+	if (byte_diff) {
+		ifp->if_data = krealloc(ifp->if_data, new_size,
+					GFP_NOFS | __GFP_NOFAIL);
+		if (new_size == 0)
+			ifp->if_data = NULL;
+		ifp->if_bytes = new_size;
 	}
 
-	ifp->if_data = krealloc(ifp->if_data, new_size,
-			GFP_NOFS | __GFP_NOFAIL);
-	ifp->if_bytes = new_size;
+	return ifp->if_data;
 }
 
 /* Free all memory and reset a fork back to its initial state. */
diff --git a/libxfs/xfs_inode_fork.h b/libxfs/xfs_inode_fork.h
index 7edcf0e8c..96303249d 100644
--- a/libxfs/xfs_inode_fork.h
+++ b/libxfs/xfs_inode_fork.h
@@ -168,7 +168,7 @@ int		xfs_iformat_attr_fork(struct xfs_inode *, struct xfs_dinode *);
 void		xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
 				struct xfs_inode_log_item *, int);
 void		xfs_idestroy_fork(struct xfs_ifork *ifp);
-void		xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff,
+void *		xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff,
 				int whichfork);
 void		xfs_iroot_realloc(struct xfs_inode *, int, int);
 int		xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int);
-- 
2.44.0

[PATCH 56/67] xfs: move the xfs_attr_sf_lookup tracepoint

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 14f2e4ab5d0310c2bb231941d9884fa5bae47fab

trace_xfs_attr_sf_lookup is currently only called by
xfs_attr_shortform_lookup, which despit it's name is a simple helper for
xfs_attr_shortform_addname, which has it's own tracing.  Move the
callsite to xfs_attr_shortform_getvalue, which is the closest thing to
a high level lookup we have for the Linux xattr API.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr_leaf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index a21740a87..10ed518f3 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -873,8 +873,6 @@ xfs_attr_shortform_lookup(
 	struct xfs_attr_sf_entry	*sfe;
 	int				i;
 
-	trace_xfs_attr_sf_lookup(args);
-
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
@@ -902,6 +900,9 @@ xfs_attr_shortform_getvalue(
 	int				i;
 
 	ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL);
+
+	trace_xfs_attr_sf_lookup(args);
+
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
 				sfe = xfs_attr_sf_nextentry(sfe), i++) {
-- 
2.44.0

[PATCH 57/67] xfs: simplify xfs_attr_sf_findname

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 6c8d169bbd51fc10d1d0029d495962881315b4c2

xfs_attr_sf_findname has the simple job of finding a xfs_attr_sf_entry in
the attr fork, but the convoluted calling convention obfuscates that.

Return the found entry as the return value instead of an pointer
argument, as the -ENOATTR/-EEXIST can be trivally derived from that, and
remove the basep argument, as it is equivalent of the offset of sfe in
the data for if an sfe was found, or an offset of totsize if not was
found.  To simplify the totsize computation add a xfs_attr_sf_endptr
helper that returns the imaginative xfs_attr_sf_entry at the end of
the current attrs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr.c      |  7 ++-
 libxfs/xfs_attr_leaf.c | 96 +++++++++++++++---------------------------
 libxfs/xfs_attr_leaf.h |  4 +-
 libxfs/xfs_attr_sf.h   |  7 +++
 4 files changed, 48 insertions(+), 66 deletions(-)

diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index d7512efd4..d5a5ae6e2 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -860,8 +860,11 @@ xfs_attr_lookup(
 	if (!xfs_inode_hasattr(dp))
 		return -ENOATTR;
 
-	if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL)
-		return xfs_attr_sf_findname(args, NULL, NULL);
+	if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) {
+		if (xfs_attr_sf_findname(args))
+			return -EEXIST;
+		return -ENOATTR;
+	}
 
 	if (xfs_attr_is_leaf(dp)) {
 		error = xfs_attr_leaf_hasname(args, &bp);
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 10ed518f3..6ea364059 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -695,47 +695,24 @@ xfs_attr_shortform_create(
 }
 
 /*
- * Return -EEXIST if attr is found, or -ENOATTR if not
- * args:  args containing attribute name and namelen
- * sfep:  If not null, pointer will be set to the last attr entry found on
-	  -EEXIST.  On -ENOATTR pointer is left at the last entry in the list
- * basep: If not null, pointer is set to the byte offset of the entry in the
- *	  list on -EEXIST.  On -ENOATTR, pointer is left at the byte offset of
- *	  the last entry in the list
+ * Return the entry if the attr in args is found, or NULL if not.
  */
-int
+struct xfs_attr_sf_entry *
 xfs_attr_sf_findname(
-	struct xfs_da_args	 *args,
-	struct xfs_attr_sf_entry **sfep,
-	unsigned int		 *basep)
+	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform *sf = args->dp->i_af.if_data;
-	struct xfs_attr_sf_entry *sfe;
-	unsigned int		base = sizeof(struct xfs_attr_sf_hdr);
-	int			size = 0;
-	int			end;
-	int			i;
+	struct xfs_attr_shortform	*sf = args->dp->i_af.if_data;
+	struct xfs_attr_sf_entry	*sfe;
 
-	sfe = &sf->list[0];
-	end = sf->hdr.count;
-	for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe),
-			     base += size, i++) {
-		size = xfs_attr_sf_entsize(sfe);
-		if (!xfs_attr_match(args, sfe->namelen, sfe->nameval,
-				    sfe->flags))
-			continue;
-		break;
+	for (sfe = &sf->list[0];
+	     sfe < xfs_attr_sf_endptr(sf);
+	     sfe = xfs_attr_sf_nextentry(sfe)) {
+		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
+				sfe->flags))
+			return sfe;
 	}
 
-	if (sfep != NULL)
-		*sfep = sfe;
-
-	if (basep != NULL)
-		*basep = base;
-
-	if (i == end)
-		return -ENOATTR;
-	return -EEXIST;
+	return NULL;
 }
 
 /*
@@ -752,21 +729,19 @@ xfs_attr_shortform_add(
 	struct xfs_ifork		*ifp = &dp->i_af;
 	struct xfs_attr_shortform	*sf = ifp->if_data;
 	struct xfs_attr_sf_entry	*sfe;
-	int				offset, size;
+	int				size;
 
 	trace_xfs_attr_sf_add(args);
 
 	dp->i_forkoff = forkoff;
 
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-	if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
-		ASSERT(0);
+	ASSERT(!xfs_attr_sf_findname(args));
 
-	offset = (char *)sfe - (char *)sf;
 	size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen);
 	sf = xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
-	sfe = (struct xfs_attr_sf_entry *)((char *)sf + offset);
 
+	sfe = xfs_attr_sf_endptr(sf);
 	sfe->namelen = args->namelen;
 	sfe->valuelen = args->valuelen;
 	sfe->flags = args->attr_filter;
@@ -806,39 +781,38 @@ xfs_attr_sf_removename(
 	struct xfs_mount		*mp = dp->i_mount;
 	struct xfs_attr_shortform	*sf = dp->i_af.if_data;
 	struct xfs_attr_sf_entry	*sfe;
-	int				size = 0, end, totsize;
-	unsigned int			base;
-	int				error;
+	uint16_t			totsize = be16_to_cpu(sf->hdr.totsize);
+	void				*next, *end;
+	int				size = 0;
 
 	trace_xfs_attr_sf_remove(args);
 
-	error = xfs_attr_sf_findname(args, &sfe, &base);
-
-	/*
-	 * If we are recovering an operation, finding nothing to
-	 * remove is not an error - it just means there was nothing
-	 * to clean up.
-	 */
-	if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY))
-		return 0;
-	if (error != -EEXIST)
-		return error;
-	size = xfs_attr_sf_entsize(sfe);
+	sfe = xfs_attr_sf_findname(args);
+	if (!sfe) {
+		/*
+		 * If we are recovering an operation, finding nothing to remove
+		 * is not an error, it just means there was nothing to clean up.
+		 */
+		if (args->op_flags & XFS_DA_OP_RECOVERY)
+			return 0;
+		return -ENOATTR;
+	}
 
 	/*
 	 * Fix up the attribute fork data, covering the hole
 	 */
-	end = base + size;
-	totsize = be16_to_cpu(sf->hdr.totsize);
-	if (end != totsize)
-		memmove(&((char *)sf)[base], &((char *)sf)[end], totsize - end);
+	size = xfs_attr_sf_entsize(sfe);
+	next = xfs_attr_sf_nextentry(sfe);
+	end = xfs_attr_sf_endptr(sf);
+	if (next < end)
+		memmove(sfe, next, end - next);
 	sf->hdr.count--;
-	be16_add_cpu(&sf->hdr.totsize, -size);
+	totsize -= size;
+	sf->hdr.totsize = cpu_to_be16(totsize);
 
 	/*
 	 * Fix up the start offset of the attribute fork
 	 */
-	totsize -= size;
 	if (totsize == sizeof(xfs_attr_sf_hdr_t) && xfs_has_attr2(mp) &&
 	    (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) &&
 	    !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE))) {
diff --git a/libxfs/xfs_attr_leaf.h b/libxfs/xfs_attr_leaf.h
index ce6743463..56fcd689e 100644
--- a/libxfs/xfs_attr_leaf.h
+++ b/libxfs/xfs_attr_leaf.h
@@ -51,9 +51,7 @@ int	xfs_attr_shortform_lookup(struct xfs_da_args *args);
 int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
 int	xfs_attr_sf_removename(struct xfs_da_args *args);
-int	xfs_attr_sf_findname(struct xfs_da_args *args,
-			     struct xfs_attr_sf_entry **sfep,
-			     unsigned int *basep);
+struct xfs_attr_sf_entry *xfs_attr_sf_findname(struct xfs_da_args *args);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
 xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_shortform *sfp,
diff --git a/libxfs/xfs_attr_sf.h b/libxfs/xfs_attr_sf.h
index 37578b369..a774d4d87 100644
--- a/libxfs/xfs_attr_sf.h
+++ b/libxfs/xfs_attr_sf.h
@@ -48,4 +48,11 @@ xfs_attr_sf_nextentry(struct xfs_attr_sf_entry *sfep)
 	return (void *)sfep + xfs_attr_sf_entsize(sfep);
 }
 
+/* pointer to the space after the last entry, e.g. for adding a new one */
+static inline struct xfs_attr_sf_entry *
+xfs_attr_sf_endptr(struct xfs_attr_shortform *sf)
+{
+	return (void *)sf + be16_to_cpu(sf->hdr.totsize);
+}
+
 #endif	/* __XFS_ATTR_SF_H__ */
-- 
2.44.0

[PATCH 58/67] xfs: remove xfs_attr_shortform_lookup

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 22b7b1f597a6a21fb7b3791a55f3a7ae54d2dfe4

xfs_attr_shortform_lookup is only used by xfs_attr_shortform_addname,
which is much better served by calling xfs_attr_sf_findname.  Switch
it over and remove xfs_attr_shortform_lookup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr.c      | 21 +++++++--------------
 libxfs/xfs_attr_leaf.c | 24 ------------------------
 libxfs/xfs_attr_leaf.h |  1 -
 3 files changed, 7 insertions(+), 39 deletions(-)

diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index d5a5ae6e2..a383024db 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -1064,19 +1064,14 @@ xfs_attr_shortform_addname(
 	struct xfs_da_args	*args)
 {
 	int			newsize, forkoff;
-	int			error;
 
 	trace_xfs_attr_sf_addname(args);
 
-	error = xfs_attr_shortform_lookup(args);
-	switch (error) {
-	case -ENOATTR:
-		if (args->op_flags & XFS_DA_OP_REPLACE)
-			return error;
-		break;
-	case -EEXIST:
+	if (xfs_attr_sf_findname(args)) {
+		int		error;
+
 		if (!(args->op_flags & XFS_DA_OP_REPLACE))
-			return error;
+			return -EEXIST;
 
 		error = xfs_attr_sf_removename(args);
 		if (error)
@@ -1089,11 +1084,9 @@ xfs_attr_shortform_addname(
 		 * around.
 		 */
 		args->op_flags &= ~XFS_DA_OP_REPLACE;
-		break;
-	case 0:
-		break;
-	default:
-		return error;
+	} else {
+		if (args->op_flags & XFS_DA_OP_REPLACE)
+			return -ENOATTR;
 	}
 
 	if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 6ea364059..8f1678d29 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -834,30 +834,6 @@ xfs_attr_sf_removename(
 	return 0;
 }
 
-/*
- * Look up a name in a shortform attribute list structure.
- */
-/*ARGSUSED*/
-int
-xfs_attr_shortform_lookup(
-	struct xfs_da_args		*args)
-{
-	struct xfs_ifork		*ifp = &args->dp->i_af;
-	struct xfs_attr_shortform	*sf = ifp->if_data;
-	struct xfs_attr_sf_entry	*sfe;
-	int				i;
-
-	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
-	sfe = &sf->list[0];
-	for (i = 0; i < sf->hdr.count;
-				sfe = xfs_attr_sf_nextentry(sfe), i++) {
-		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
-				sfe->flags))
-			return -EEXIST;
-	}
-	return -ENOATTR;
-}
-
 /*
  * Retrieve the attribute value and length.
  *
diff --git a/libxfs/xfs_attr_leaf.h b/libxfs/xfs_attr_leaf.h
index 56fcd689e..35e668ae7 100644
--- a/libxfs/xfs_attr_leaf.h
+++ b/libxfs/xfs_attr_leaf.h
@@ -47,7 +47,6 @@ struct xfs_attr3_icleaf_hdr {
  */
 void	xfs_attr_shortform_create(struct xfs_da_args *args);
 void	xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff);
-int	xfs_attr_shortform_lookup(struct xfs_da_args *args);
 int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
 int	xfs_attr_sf_removename(struct xfs_da_args *args);
-- 
2.44.0

[PATCH 59/67] xfs: use xfs_attr_sf_findname in xfs_attr_shortform_getvalue

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 1fb4b0def7b5a5bf91ad62a112d8d3f6dc76585f

xfs_attr_shortform_getvalue duplicates the logic in xfs_attr_sf_findname.
Use the helper instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr_leaf.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 8f1678d29..9b6dcff34 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -845,23 +845,17 @@ int
 xfs_attr_shortform_getvalue(
 	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform	*sf = args->dp->i_af.if_data;
 	struct xfs_attr_sf_entry	*sfe;
-	int				i;
 
 	ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL);
 
 	trace_xfs_attr_sf_lookup(args);
 
-	sfe = &sf->list[0];
-	for (i = 0; i < sf->hdr.count;
-				sfe = xfs_attr_sf_nextentry(sfe), i++) {
-		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
-				sfe->flags))
-			return xfs_attr_copy_value(args,
-				&sfe->nameval[args->namelen], sfe->valuelen);
-	}
-	return -ENOATTR;
+	sfe = xfs_attr_sf_findname(args);
+	if (!sfe)
+		return -ENOATTR;
+	return xfs_attr_copy_value(args, &sfe->nameval[args->namelen],
+			sfe->valuelen);
 }
 
 /* Convert from using the shortform to the leaf format. */
-- 
2.44.0

[PATCH 60/67] xfs: remove struct xfs_attr_shortform

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 414147225400a0c4562ebfb0fdd40f065099ede4

sparse complains about struct xfs_attr_shortform because it embeds a
structure with a variable sized array in a variable sized array.

Given that xfs_attr_shortform is not a very useful structure, and the
dir2 equivalent has been removed a long time ago, remove it as well.

Provide a xfs_attr_sf_firstentry helper that returns the first
xfs_attr_sf_entry behind a xfs_attr_sf_hdr to replace the structure
dereference.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 db/attrshort.c           | 33 +++++++++++++++---------------
 db/check.c               |  8 ++++----
 db/inode.c               |  6 +++---
 db/metadump.c            | 16 +++++++--------
 libxfs/libxfs_api_defs.h |  1 +
 libxfs/xfs_attr.c        |  4 ++--
 libxfs/xfs_attr_leaf.c   | 37 +++++++++++++++++-----------------
 libxfs/xfs_attr_leaf.h   |  2 +-
 libxfs/xfs_attr_sf.h     | 13 +++++++++---
 libxfs/xfs_da_format.h   | 33 +++++++++++++++++-------------
 libxfs/xfs_inode_fork.c  |  5 ++---
 libxfs/xfs_ondisk.h      | 14 ++++++-------
 repair/attr_repair.c     | 43 ++++++++++++++++++++--------------------
 repair/dinode.c          | 21 ++++++++++----------
 14 files changed, 121 insertions(+), 115 deletions(-)

diff --git a/db/attrshort.c b/db/attrshort.c
index e234fbd83..c98b90be3 100644
--- a/db/attrshort.c
+++ b/db/attrshort.c
@@ -18,9 +18,8 @@ static int	attr_sf_entry_value_offset(void *obj, int startoff, int idx);
 static int	attr_shortform_list_count(void *obj, int startoff);
 static int	attr_shortform_list_offset(void *obj, int startoff, int idx);
 
-#define	OFF(f)	bitize(offsetof(struct xfs_attr_shortform, f))
 const field_t	attr_shortform_flds[] = {
-	{ "hdr", FLDT_ATTR_SF_HDR, OI(OFF(hdr)), C1, 0, TYP_NONE },
+	{ "hdr", FLDT_ATTR_SF_HDR, OI(0), C1, 0, TYP_NONE },
 	{ "list", FLDT_ATTR_SF_ENTRY, attr_shortform_list_offset,
 	  attr_shortform_list_count, FLD_ARRAY|FLD_COUNT|FLD_OFFSET, TYP_NONE },
 	{ NULL }
@@ -71,11 +70,11 @@ attr_sf_entry_size(
 {
 	struct xfs_attr_sf_entry	*e;
 	int				i;
-	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_hdr		*hdr;
 
 	ASSERT(bitoffs(startoff) == 0);
-	sf = (struct xfs_attr_shortform *)((char *)obj + byteize(startoff));
-	e = &sf->list[0];
+	hdr = (struct xfs_attr_sf_hdr *)((char *)obj + byteize(startoff));
+	e = libxfs_attr_sf_firstentry(hdr);
 	for (i = 0; i < idx; i++)
 		e = xfs_attr_sf_nextentry(e);
 	return bitize((int)xfs_attr_sf_entsize(e));
@@ -113,11 +112,11 @@ attr_shortform_list_count(
 	void				*obj,
 	int				startoff)
 {
-	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_hdr		*hdr;
 
 	ASSERT(bitoffs(startoff) == 0);
-	sf = (struct xfs_attr_shortform *)((char *)obj + byteize(startoff));
-	return sf->hdr.count;
+	hdr = (struct xfs_attr_sf_hdr *)((char *)obj + byteize(startoff));
+	return hdr->count;
 }
 
 static int
@@ -128,14 +127,14 @@ attr_shortform_list_offset(
 {
 	struct xfs_attr_sf_entry	*e;
 	int				i;
-	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_hdr		*hdr;
 
 	ASSERT(bitoffs(startoff) == 0);
-	sf = (struct xfs_attr_shortform *)((char *)obj + byteize(startoff));
-	e = &sf->list[0];
+	hdr = (struct xfs_attr_sf_hdr *)((char *)obj + byteize(startoff));
+	e = libxfs_attr_sf_firstentry(hdr);
 	for (i = 0; i < idx; i++)
 		e = xfs_attr_sf_nextentry(e);
-	return bitize((int)((char *)e - (char *)sf));
+	return bitize((int)((char *)e - (char *)hdr));
 }
 
 /*ARGSUSED*/
@@ -147,13 +146,13 @@ attrshort_size(
 {
 	struct xfs_attr_sf_entry	*e;
 	int				i;
-	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_hdr		*hdr;
 
 	ASSERT(bitoffs(startoff) == 0);
 	ASSERT(idx == 0);
-	sf = (struct xfs_attr_shortform *)((char *)obj + byteize(startoff));
-	e = &sf->list[0];
-	for (i = 0; i < sf->hdr.count; i++)
+	hdr = (struct xfs_attr_sf_hdr *)((char *)obj + byteize(startoff));
+	e = libxfs_attr_sf_firstentry(hdr);
+	for (i = 0; i < hdr->count; i++)
 		e = xfs_attr_sf_nextentry(e);
-	return bitize((int)((char *)e - (char *)sf));
+	return bitize((int)((char *)e - (char *)hdr));
 }
diff --git a/db/check.c b/db/check.c
index 36d82af0a..c29c661b7 100644
--- a/db/check.c
+++ b/db/check.c
@@ -3055,7 +3055,7 @@ process_lclinode(
 	blkmap_t			**blkmapp,
 	int				whichfork)
 {
-	struct xfs_attr_shortform	*asf;
+	struct xfs_attr_sf_hdr		*hdr;
 	xfs_fsblock_t			bno;
 
 	bno = XFS_INO_TO_FSB(mp, id->ino);
@@ -3068,12 +3068,12 @@ process_lclinode(
 		error++;
 	}
 	else if (whichfork == XFS_ATTR_FORK) {
-		asf = (struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
-		if (be16_to_cpu(asf->hdr.totsize) > XFS_DFORK_ASIZE(dip, mp)) {
+		hdr = XFS_DFORK_APTR(dip);
+		if (be16_to_cpu(hdr->totsize) > XFS_DFORK_ASIZE(dip, mp)) {
 			if (!sflag || id->ilist || CHECK_BLIST(bno))
 				dbprintf(_("local inode %lld attr is too large "
 					 "(size %d)\n"),
-					id->ino, be16_to_cpu(asf->hdr.totsize));
+					id->ino, be16_to_cpu(hdr->totsize));
 			error++;
 		}
 	}
diff --git a/db/inode.c b/db/inode.c
index c9b506b90..d5e4be0ad 100644
--- a/db/inode.c
+++ b/db/inode.c
@@ -356,7 +356,7 @@ inode_a_size(
 	int				startoff,
 	int				idx)
 {
-	struct xfs_attr_shortform	*asf;
+	struct xfs_attr_sf_hdr		*hdr;
 	struct xfs_dinode		*dip;
 
 	ASSERT(startoff == 0);
@@ -364,8 +364,8 @@ inode_a_size(
 	dip = obj;
 	switch (dip->di_aformat) {
 	case XFS_DINODE_FMT_LOCAL:
-		asf = (struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
-		return bitize(be16_to_cpu(asf->hdr.totsize));
+		hdr = (struct xfs_attr_sf_hdr *)XFS_DFORK_APTR(dip);
+		return bitize(be16_to_cpu(hdr->totsize));
 	case XFS_DINODE_FMT_EXTENTS:
 		return (int)xfs_dfork_attr_extents(dip) * bitsz(xfs_bmbt_rec_t);
 	case XFS_DINODE_FMT_BTREE:
diff --git a/db/metadump.c b/db/metadump.c
index bac35b9cc..536d089fb 100644
--- a/db/metadump.c
+++ b/db/metadump.c
@@ -1035,16 +1035,15 @@ process_sf_attr(
 	 * values with 'v' (to see a valid string length, as opposed to NULLs)
 	 */
 
-	struct xfs_attr_shortform	*asfp;
-	struct xfs_attr_sf_entry	*asfep;
+	struct xfs_attr_sf_hdr		*hdr = XFS_DFORK_APTR(dip);
+	struct xfs_attr_sf_entry	*asfep = libxfs_attr_sf_firstentry(hdr);
 	int				ino_attr_size;
 	int				i;
 
-	asfp = (struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
-	if (asfp->hdr.count == 0)
+	if (hdr->count == 0)
 		return;
 
-	ino_attr_size = be16_to_cpu(asfp->hdr.totsize);
+	ino_attr_size = be16_to_cpu(hdr->totsize);
 	if (ino_attr_size > XFS_DFORK_ASIZE(dip, mp)) {
 		ino_attr_size = XFS_DFORK_ASIZE(dip, mp);
 		if (metadump.show_warnings)
@@ -1052,9 +1051,8 @@ process_sf_attr(
 					(long long)metadump.cur_ino);
 	}
 
-	asfep = &asfp->list[0];
-	for (i = 0; (i < asfp->hdr.count) &&
-			((char *)asfep - (char *)asfp < ino_attr_size); i++) {
+	for (i = 0; (i < hdr->count) &&
+			((char *)asfep - (char *)hdr < ino_attr_size); i++) {
 
 		int	namelen = asfep->namelen;
 
@@ -1063,7 +1061,7 @@ process_sf_attr(
 				print_warning("zero length attr entry in inode "
 					"%llu", (long long)metadump.cur_ino);
 			break;
-		} else if ((char *)asfep - (char *)asfp +
+		} else if ((char *)asfep - (char *)hdr +
 				xfs_attr_sf_entsize(asfep) > ino_attr_size) {
 			if (metadump.show_warnings)
 				print_warning("attr entry length in inode %llu "
diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 4edc8a7e1..c38ccc5f8 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -40,6 +40,7 @@
 #define xfs_attr_leaf_newentsize	libxfs_attr_leaf_newentsize
 #define xfs_attr_namecheck		libxfs_attr_namecheck
 #define xfs_attr_set			libxfs_attr_set
+#define xfs_attr_sf_firstentry		libxfs_attr_sf_firstentry
 
 #define __xfs_bmap_add_free		__libxfs_bmap_add_free
 #define xfs_bmapi_read			libxfs_bmapi_read
diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index a383024db..055d20410 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -1050,9 +1050,9 @@ out_trans_cancel:
 
 static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
 {
-	struct xfs_attr_shortform *sf = dp->i_af.if_data;
+	struct xfs_attr_sf_hdr *sf = dp->i_af.if_data;
 
-	return be16_to_cpu(sf->hdr.totsize);
+	return be16_to_cpu(sf->totsize);
 }
 
 /*
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 9b6dcff34..cf172b6ea 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -701,10 +701,10 @@ struct xfs_attr_sf_entry *
 xfs_attr_sf_findname(
 	struct xfs_da_args		*args)
 {
-	struct xfs_attr_shortform	*sf = args->dp->i_af.if_data;
+	struct xfs_attr_sf_hdr		*sf = args->dp->i_af.if_data;
 	struct xfs_attr_sf_entry	*sfe;
 
-	for (sfe = &sf->list[0];
+	for (sfe = xfs_attr_sf_firstentry(sf);
 	     sfe < xfs_attr_sf_endptr(sf);
 	     sfe = xfs_attr_sf_nextentry(sfe)) {
 		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
@@ -727,7 +727,7 @@ xfs_attr_shortform_add(
 	struct xfs_inode		*dp = args->dp;
 	struct xfs_mount		*mp = dp->i_mount;
 	struct xfs_ifork		*ifp = &dp->i_af;
-	struct xfs_attr_shortform	*sf = ifp->if_data;
+	struct xfs_attr_sf_hdr		*sf = ifp->if_data;
 	struct xfs_attr_sf_entry	*sfe;
 	int				size;
 
@@ -747,8 +747,8 @@ xfs_attr_shortform_add(
 	sfe->flags = args->attr_filter;
 	memcpy(sfe->nameval, args->name, args->namelen);
 	memcpy(&sfe->nameval[args->namelen], args->value, args->valuelen);
-	sf->hdr.count++;
-	be16_add_cpu(&sf->hdr.totsize, size);
+	sf->count++;
+	be16_add_cpu(&sf->totsize, size);
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
 
 	xfs_sbversion_add_attr2(mp, args->trans);
@@ -779,9 +779,9 @@ xfs_attr_sf_removename(
 {
 	struct xfs_inode		*dp = args->dp;
 	struct xfs_mount		*mp = dp->i_mount;
-	struct xfs_attr_shortform	*sf = dp->i_af.if_data;
+	struct xfs_attr_sf_hdr		*sf = dp->i_af.if_data;
 	struct xfs_attr_sf_entry	*sfe;
-	uint16_t			totsize = be16_to_cpu(sf->hdr.totsize);
+	uint16_t			totsize = be16_to_cpu(sf->totsize);
 	void				*next, *end;
 	int				size = 0;
 
@@ -806,9 +806,9 @@ xfs_attr_sf_removename(
 	end = xfs_attr_sf_endptr(sf);
 	if (next < end)
 		memmove(sfe, next, end - next);
-	sf->hdr.count--;
+	sf->count--;
 	totsize -= size;
-	sf->hdr.totsize = cpu_to_be16(totsize);
+	sf->totsize = cpu_to_be16(totsize);
 
 	/*
 	 * Fix up the start offset of the attribute fork
@@ -865,21 +865,21 @@ xfs_attr_shortform_to_leaf(
 {
 	struct xfs_inode		*dp = args->dp;
 	struct xfs_ifork		*ifp = &dp->i_af;
-	struct xfs_attr_shortform	*sf = ifp->if_data;
+	struct xfs_attr_sf_hdr		*sf = ifp->if_data;
 	struct xfs_attr_sf_entry	*sfe;
+	int				size = be16_to_cpu(sf->totsize);
 	struct xfs_da_args		nargs;
 	char				*tmpbuffer;
-	int				error, i, size;
+	int				error, i;
 	xfs_dablk_t			blkno;
 	struct xfs_buf			*bp;
 
 	trace_xfs_attr_sf_to_leaf(args);
 
-	size = be16_to_cpu(sf->hdr.totsize);
 	tmpbuffer = kmem_alloc(size, 0);
 	ASSERT(tmpbuffer != NULL);
 	memcpy(tmpbuffer, ifp->if_data, size);
-	sf = (struct xfs_attr_shortform *)tmpbuffer;
+	sf = (struct xfs_attr_sf_hdr *)tmpbuffer;
 
 	xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 	xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK);
@@ -902,8 +902,8 @@ xfs_attr_shortform_to_leaf(
 	nargs.trans = args->trans;
 	nargs.op_flags = XFS_DA_OP_OKNOENT;
 
-	sfe = &sf->list[0];
-	for (i = 0; i < sf->hdr.count; i++) {
+	sfe = xfs_attr_sf_firstentry(sf);
+	for (i = 0; i < sf->count; i++) {
 		nargs.name = sfe->nameval;
 		nargs.namelen = sfe->namelen;
 		nargs.value = &sfe->nameval[nargs.namelen];
@@ -970,10 +970,10 @@ xfs_attr_shortform_allfit(
 /* Verify the consistency of a raw inline attribute fork. */
 xfs_failaddr_t
 xfs_attr_shortform_verify(
-	struct xfs_attr_shortform	*sfp,
+	struct xfs_attr_sf_hdr		*sfp,
 	size_t				size)
 {
-	struct xfs_attr_sf_entry	*sfep;
+	struct xfs_attr_sf_entry	*sfep = xfs_attr_sf_firstentry(sfp);
 	struct xfs_attr_sf_entry	*next_sfep;
 	char				*endp;
 	int				i;
@@ -987,8 +987,7 @@ xfs_attr_shortform_verify(
 	endp = (char *)sfp + size;
 
 	/* Check all reported entries */
-	sfep = &sfp->list[0];
-	for (i = 0; i < sfp->hdr.count; i++) {
+	for (i = 0; i < sfp->count; i++) {
 		/*
 		 * struct xfs_attr_sf_entry has a variable length.
 		 * Check the fixed-offset parts of the structure are
diff --git a/libxfs/xfs_attr_leaf.h b/libxfs/xfs_attr_leaf.h
index 35e668ae7..9b9948639 100644
--- a/libxfs/xfs_attr_leaf.h
+++ b/libxfs/xfs_attr_leaf.h
@@ -53,7 +53,7 @@ int	xfs_attr_sf_removename(struct xfs_da_args *args);
 struct xfs_attr_sf_entry *xfs_attr_sf_findname(struct xfs_da_args *args);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
-xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_shortform *sfp,
+xfs_failaddr_t xfs_attr_shortform_verify(struct xfs_attr_sf_hdr *sfp,
 		size_t size);
 void	xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
 
diff --git a/libxfs/xfs_attr_sf.h b/libxfs/xfs_attr_sf.h
index a774d4d87..9abf7de95 100644
--- a/libxfs/xfs_attr_sf.h
+++ b/libxfs/xfs_attr_sf.h
@@ -41,7 +41,14 @@ static inline int xfs_attr_sf_entsize(struct xfs_attr_sf_entry *sfep)
 	return struct_size(sfep, nameval, sfep->namelen + sfep->valuelen);
 }
 
-/* next entry in struct */
+/* first entry in the SF attr fork */
+static inline struct xfs_attr_sf_entry *
+xfs_attr_sf_firstentry(struct xfs_attr_sf_hdr *hdr)
+{
+	return (struct xfs_attr_sf_entry *)(hdr + 1);
+}
+
+/* next entry after sfep */
 static inline struct xfs_attr_sf_entry *
 xfs_attr_sf_nextentry(struct xfs_attr_sf_entry *sfep)
 {
@@ -50,9 +57,9 @@ xfs_attr_sf_nextentry(struct xfs_attr_sf_entry *sfep)
 
 /* pointer to the space after the last entry, e.g. for adding a new one */
 static inline struct xfs_attr_sf_entry *
-xfs_attr_sf_endptr(struct xfs_attr_shortform *sf)
+xfs_attr_sf_endptr(struct xfs_attr_sf_hdr *sf)
 {
-	return (void *)sf + be16_to_cpu(sf->hdr.totsize);
+	return (void *)sf + be16_to_cpu(sf->totsize);
 }
 
 #endif	/* __XFS_ATTR_SF_H__ */
diff --git a/libxfs/xfs_da_format.h b/libxfs/xfs_da_format.h
index f9015f88e..24f9d1461 100644
--- a/libxfs/xfs_da_format.h
+++ b/libxfs/xfs_da_format.h
@@ -578,20 +578,25 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
 #define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
 
 /*
- * Entries are packed toward the top as tight as possible.
- */
-struct xfs_attr_shortform {
-	struct xfs_attr_sf_hdr {	/* constant-structure header block */
-		__be16	totsize;	/* total bytes in shortform list */
-		__u8	count;	/* count of active entries */
-		__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[];	/* name & value bytes concatenated */
-	} list[];			/* variable sized array */
+ * Attribute storage when stored inside the inode.
+ *
+ * Small attribute lists are packed as tightly as possible so as to fit into the
+ * literal area of the inode.
+ *
+ * These "shortform" attribute forks consist of a single xfs_attr_sf_hdr header
+ * followed by zero or more xfs_attr_sf_entry structures.
+ */
+struct xfs_attr_sf_hdr {	/* constant-structure header block */
+	__be16	totsize;	/* total bytes in shortform list */
+	__u8	count;		/* count of active entries */
+	__u8	padding;
+};
+
+struct xfs_attr_sf_entry {
+	__u8	namelen;	/* actual length of name (no NULL) */
+	__u8	valuelen;	/* actual length of value (no NULL) */
+	__u8	flags;		/* flags bits (XFS_ATTR_*) */
+	__u8	nameval[];	/* name & value bytes concatenated */
 };
 
 typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index c95abd43a..208b283ba 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -277,10 +277,9 @@ static uint16_t
 xfs_dfork_attr_shortform_size(
 	struct xfs_dinode		*dip)
 {
-	struct xfs_attr_shortform	*atp =
-		(struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
+	struct xfs_attr_sf_hdr		*sf = XFS_DFORK_APTR(dip);
 
-	return be16_to_cpu(atp->hdr.totsize);
+	return be16_to_cpu(sf->totsize);
 }
 
 void
diff --git a/libxfs/xfs_ondisk.h b/libxfs/xfs_ondisk.h
index d9c988c5a..81885a6a0 100644
--- a/libxfs/xfs_ondisk.h
+++ b/libxfs/xfs_ondisk.h
@@ -93,13 +93,13 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen,	8);
 	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name,	9);
 	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		32);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_shortform,	4);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.totsize, 0);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.count,	 2);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].namelen,	4);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].valuelen,	5);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].flags,	6);
-	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].nameval,	7);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_hdr,		4);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, totsize,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, count,		2);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, namelen,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, valuelen,	1);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, flags,	2);
+	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, nameval,	3);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
diff --git a/repair/attr_repair.c b/repair/attr_repair.c
index c3a6d5026..b65b28a20 100644
--- a/repair/attr_repair.c
+++ b/repair/attr_repair.c
@@ -210,27 +210,27 @@ process_shortform_attr(
 	struct xfs_dinode		*dip,
 	int				*repair)
 {
-	struct xfs_attr_shortform	*asf;
+	struct xfs_attr_sf_hdr		*hdr;
 	struct xfs_attr_sf_entry	*currententry, *nextentry, *tempentry;
 	int				i, junkit;
 	int				currentsize, remainingspace;
 
 	*repair = 0;
 
-	asf = (struct xfs_attr_shortform *) XFS_DFORK_APTR(dip);
+	hdr = XFS_DFORK_APTR(dip);
 
 	/* Assumption: hdr.totsize is less than a leaf block and was checked
 	 * by lclinode for valid sizes. Check the count though.
 	*/
-	if (asf->hdr.count == 0)
+	if (hdr->count == 0)
 		/* then the total size should just be the header length */
-		if (be16_to_cpu(asf->hdr.totsize) != sizeof(xfs_attr_sf_hdr_t)) {
+		if (be16_to_cpu(hdr->totsize) != sizeof(xfs_attr_sf_hdr_t)) {
 			/* whoops there's a discrepancy. Clear the hdr */
 			if (!no_modify) {
 				do_warn(
 	_("there are no attributes in the fork for inode %" PRIu64 "\n"),
 					ino);
-				asf->hdr.totsize =
+				hdr->totsize =
 					cpu_to_be16(sizeof(xfs_attr_sf_hdr_t));
 				*repair = 1;
 				return(1);
@@ -243,15 +243,15 @@ process_shortform_attr(
 		}
 
 	currentsize = sizeof(xfs_attr_sf_hdr_t);
-	remainingspace = be16_to_cpu(asf->hdr.totsize) - currentsize;
-	nextentry = &asf->list[0];
-	for (i = 0; i < asf->hdr.count; i++)  {
+	remainingspace = be16_to_cpu(hdr->totsize) - currentsize;
+	nextentry = libxfs_attr_sf_firstentry(hdr);
+	for (i = 0; i < hdr->count; i++)  {
 		currententry = nextentry;
 		junkit = 0;
 
 		/* don't go off the end if the hdr.count was off */
 		if ((currentsize + (sizeof(struct xfs_attr_sf_entry) - 1)) >
-						be16_to_cpu(asf->hdr.totsize))
+						be16_to_cpu(hdr->totsize))
 			break; /* get out and reset count and totSize */
 
 		/* if the namelen is 0, can't get to the rest of the entries */
@@ -326,7 +326,7 @@ process_shortform_attr(
 					((intptr_t) currententry +
 					 xfs_attr_sf_entsize(currententry));
 				memmove(currententry,tempentry,remainingspace);
-				asf->hdr.count -= 1;
+				hdr->count -= 1;
 				i--; /* no worries, it will wrap back to 0 */
 				*repair = 1;
 				continue; /* go back up now */
@@ -344,33 +344,33 @@ process_shortform_attr(
 
 	} /* end the loop */
 
-	if (asf->hdr.count != i)  {
+	if (hdr->count != i)  {
 		if (no_modify)  {
 			do_warn(
 	_("would have corrected attribute entry count in inode %" PRIu64 " from %d to %d\n"),
-				ino, asf->hdr.count, i);
+				ino, hdr->count, i);
 		} else  {
 			do_warn(
 	_("corrected attribute entry count in inode %" PRIu64 ", was %d, now %d\n"),
-				ino, asf->hdr.count, i);
-			asf->hdr.count = i;
+				ino, hdr->count, i);
+			hdr->count = i;
 			*repair = 1;
 		}
 	}
 
 	/* ASSUMPTION: currentsize <= totsize */
-	if (be16_to_cpu(asf->hdr.totsize) != currentsize)  {
+	if (be16_to_cpu(hdr->totsize) != currentsize)  {
 		if (no_modify)  {
 			do_warn(
 	_("would have corrected attribute totsize in inode %" PRIu64 " from %d to %d\n"),
-				ino, be16_to_cpu(asf->hdr.totsize),
+				ino, be16_to_cpu(hdr->totsize),
 				currentsize);
 		} else  {
 			do_warn(
 	_("corrected attribute entry totsize in inode %" PRIu64 ", was %d, now %d\n"),
-				ino, be16_to_cpu(asf->hdr.totsize),
+				ino, be16_to_cpu(hdr->totsize),
 				currentsize);
-			asf->hdr.totsize = cpu_to_be16(currentsize);
+			hdr->totsize = cpu_to_be16(currentsize);
 			*repair = 1;
 		}
 	}
@@ -1232,14 +1232,13 @@ process_attributes(
 	int			err;
 	__u8			aformat = dip->di_aformat;
 #ifdef DEBUG
-	struct xfs_attr_shortform *asf;
+	struct xfs_attr_sf_hdr *hdr;
 
-	asf = (struct xfs_attr_shortform *) XFS_DFORK_APTR(dip);
+	hdr = XFS_DFORK_APTR(dip);
 #endif
 
 	if (aformat == XFS_DINODE_FMT_LOCAL) {
-		ASSERT(be16_to_cpu(asf->hdr.totsize) <=
-			XFS_DFORK_ASIZE(dip, mp));
+		ASSERT(be16_to_cpu(hdr->totsize) <= XFS_DFORK_ASIZE(dip, mp));
 		err = process_shortform_attr(mp, ino, dip, repair);
 	} else if (aformat == XFS_DINODE_FMT_EXTENTS ||
 					aformat == XFS_DINODE_FMT_BTREE)  {
diff --git a/repair/dinode.c b/repair/dinode.c
index c10dd1fa3..f4398c0df 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -99,11 +99,10 @@ _("would have cleared inode %" PRIu64 " attributes\n"), ino_num);
 	 */
 
 	if (!no_modify) {
-		struct xfs_attr_shortform *asf = (struct xfs_attr_shortform *)
-				XFS_DFORK_APTR(dino);
-		asf->hdr.totsize = cpu_to_be16(sizeof(xfs_attr_sf_hdr_t));
-		asf->hdr.count = 0;
-		dino->di_forkoff = 0;  /* got to do this after asf is set */
+		struct xfs_attr_sf_hdr *hdr = XFS_DFORK_APTR(dino);
+		hdr->totsize = cpu_to_be16(sizeof(xfs_attr_sf_hdr_t));
+		hdr->count = 0;
+		dino->di_forkoff = 0;  /* got to do this after hdr is set */
 	}
 
 	/*
@@ -990,7 +989,7 @@ process_lclinode(
 	struct xfs_dinode		*dip,
 	int				whichfork)
 {
-	struct xfs_attr_shortform	*asf;
+	struct xfs_attr_sf_hdr		*hdr;
 	xfs_ino_t			lino;
 
 	lino = XFS_AGINO_TO_INO(mp, agno, ino);
@@ -1002,18 +1001,18 @@ process_lclinode(
 			XFS_DFORK_DSIZE(dip, mp));
 		return(1);
 	} else if (whichfork == XFS_ATTR_FORK) {
-		asf = (struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
-		if (be16_to_cpu(asf->hdr.totsize) > XFS_DFORK_ASIZE(dip, mp)) {
+		hdr = XFS_DFORK_APTR(dip);
+		if (be16_to_cpu(hdr->totsize) > XFS_DFORK_ASIZE(dip, mp)) {
 			do_warn(
 	_("local inode %" PRIu64 " attr fork too large (size %d, max = %zu)\n"),
-				lino, be16_to_cpu(asf->hdr.totsize),
+				lino, be16_to_cpu(hdr->totsize),
 				XFS_DFORK_ASIZE(dip, mp));
 			return(1);
 		}
-		if (be16_to_cpu(asf->hdr.totsize) < sizeof(xfs_attr_sf_hdr_t)) {
+		if (be16_to_cpu(hdr->totsize) < sizeof(xfs_attr_sf_hdr_t)) {
 			do_warn(
 	_("local inode %" PRIu64 " attr too small (size = %d, min size = %zd)\n"),
-				lino, be16_to_cpu(asf->hdr.totsize),
+				lino, be16_to_cpu(hdr->totsize),
 				sizeof(xfs_attr_sf_hdr_t));
 			return(1);
 		}
-- 
2.44.0

[PATCH 61/67] xfs: remove xfs_attr_sf_hdr_t

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 074aea4be1a4074be49a7ec41c674cc02b52fd60

Remove the last two users of the typedef.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 db/attrshort.c         | 2 +-
 libxfs/xfs_attr_leaf.c | 4 ++--
 libxfs/xfs_attr_sf.h   | 8 --------
 repair/attr_repair.c   | 6 +++---
 repair/dinode.c        | 6 +++---
 5 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/db/attrshort.c b/db/attrshort.c
index c98b90be3..7c386d46f 100644
--- a/db/attrshort.c
+++ b/db/attrshort.c
@@ -25,7 +25,7 @@ const field_t	attr_shortform_flds[] = {
 	{ NULL }
 };
 
-#define	HOFF(f)	bitize(offsetof(xfs_attr_sf_hdr_t, f))
+#define	HOFF(f)	bitize(offsetof(struct xfs_attr_sf_hdr, f))
 const field_t	attr_sf_hdr_flds[] = {
 	{ "totsize", FLDT_UINT16D, OI(HOFF(totsize)), C1, 0, TYP_NONE },
 	{ "count", FLDT_UINT8D, OI(HOFF(count)), C1, 0, TYP_NONE },
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index cf172b6ea..e3f8f67b5 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -813,7 +813,7 @@ xfs_attr_sf_removename(
 	/*
 	 * Fix up the start offset of the attribute fork
 	 */
-	if (totsize == sizeof(xfs_attr_sf_hdr_t) && xfs_has_attr2(mp) &&
+	if (totsize == sizeof(struct xfs_attr_sf_hdr) && xfs_has_attr2(mp) &&
 	    (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) &&
 	    !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE))) {
 		xfs_attr_fork_remove(dp, args->trans);
@@ -821,7 +821,7 @@ xfs_attr_sf_removename(
 		xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 		dp->i_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
 		ASSERT(dp->i_forkoff);
-		ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) ||
+		ASSERT(totsize > sizeof(struct xfs_attr_sf_hdr) ||
 				(args->op_flags & XFS_DA_OP_ADDNAME) ||
 				!xfs_has_attr2(mp) ||
 				dp->i_df.if_format == XFS_DINODE_FMT_BTREE);
diff --git a/libxfs/xfs_attr_sf.h b/libxfs/xfs_attr_sf.h
index 9abf7de95..bc4422223 100644
--- a/libxfs/xfs_attr_sf.h
+++ b/libxfs/xfs_attr_sf.h
@@ -6,14 +6,6 @@
 #ifndef __XFS_ATTR_SF_H__
 #define	__XFS_ATTR_SF_H__
 
-/*
- * Attribute storage when stored inside the inode.
- *
- * Small attribute lists are packed as tightly as possible so as
- * to fit into the literal area of the inode.
- */
-typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t;
-
 /*
  * We generate this then sort it, attr_list() must return things in hash-order.
  */
diff --git a/repair/attr_repair.c b/repair/attr_repair.c
index b65b28a20..0d22feb4f 100644
--- a/repair/attr_repair.c
+++ b/repair/attr_repair.c
@@ -224,14 +224,14 @@ process_shortform_attr(
 	*/
 	if (hdr->count == 0)
 		/* then the total size should just be the header length */
-		if (be16_to_cpu(hdr->totsize) != sizeof(xfs_attr_sf_hdr_t)) {
+		if (be16_to_cpu(hdr->totsize) != sizeof(struct xfs_attr_sf_hdr)) {
 			/* whoops there's a discrepancy. Clear the hdr */
 			if (!no_modify) {
 				do_warn(
 	_("there are no attributes in the fork for inode %" PRIu64 "\n"),
 					ino);
 				hdr->totsize =
-					cpu_to_be16(sizeof(xfs_attr_sf_hdr_t));
+					cpu_to_be16(sizeof(struct xfs_attr_sf_hdr));
 				*repair = 1;
 				return(1);
 			} else {
@@ -242,7 +242,7 @@ process_shortform_attr(
 			}
 		}
 
-	currentsize = sizeof(xfs_attr_sf_hdr_t);
+	currentsize = sizeof(struct xfs_attr_sf_hdr);
 	remainingspace = be16_to_cpu(hdr->totsize) - currentsize;
 	nextentry = libxfs_attr_sf_firstentry(hdr);
 	for (i = 0; i < hdr->count; i++)  {
diff --git a/repair/dinode.c b/repair/dinode.c
index f4398c0df..cc3f07dda 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -100,7 +100,7 @@ _("would have cleared inode %" PRIu64 " attributes\n"), ino_num);
 
 	if (!no_modify) {
 		struct xfs_attr_sf_hdr *hdr = XFS_DFORK_APTR(dino);
-		hdr->totsize = cpu_to_be16(sizeof(xfs_attr_sf_hdr_t));
+		hdr->totsize = cpu_to_be16(sizeof(struct xfs_attr_sf_hdr));
 		hdr->count = 0;
 		dino->di_forkoff = 0;  /* got to do this after hdr is set */
 	}
@@ -1009,11 +1009,11 @@ process_lclinode(
 				XFS_DFORK_ASIZE(dip, mp));
 			return(1);
 		}
-		if (be16_to_cpu(hdr->totsize) < sizeof(xfs_attr_sf_hdr_t)) {
+		if (be16_to_cpu(hdr->totsize) < sizeof(struct xfs_attr_sf_hdr)) {
 			do_warn(
 	_("local inode %" PRIu64 " attr too small (size = %d, min size = %zd)\n"),
 				lino, be16_to_cpu(hdr->totsize),
-				sizeof(xfs_attr_sf_hdr_t));
+				sizeof(struct xfs_attr_sf_hdr));
 			return(1);
 		}
 	}
-- 
2.44.0

[PATCH 62/67] xfs: turn the XFS_DA_OP_REPLACE checks in xfs_attr_shortform_addname into asserts

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 378b6aef9de0f7c3d0de309ecc61c11eb29e57da

Since commit deed9512872d ("xfs: Check for -ENOATTR or -EEXIST"), the
high-level attr code does a lookup for any attr we're trying to set,
and does the checks to handle the create vs replace cases, which thus
never hit the low-level attr code.

Turn the checks in xfs_attr_shortform_addname as they must never trip.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index 055d20410..1419846bd 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -1070,8 +1070,7 @@ xfs_attr_shortform_addname(
 	if (xfs_attr_sf_findname(args)) {
 		int		error;
 
-		if (!(args->op_flags & XFS_DA_OP_REPLACE))
-			return -EEXIST;
+		ASSERT(args->op_flags & XFS_DA_OP_REPLACE);
 
 		error = xfs_attr_sf_removename(args);
 		if (error)
@@ -1085,8 +1084,7 @@ xfs_attr_shortform_addname(
 		 */
 		args->op_flags &= ~XFS_DA_OP_REPLACE;
 	} else {
-		if (args->op_flags & XFS_DA_OP_REPLACE)
-			return -ENOATTR;
+		ASSERT(!(args->op_flags & XFS_DA_OP_REPLACE));
 	}
 
 	if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
-- 
2.44.0

[PATCH 63/67] xfs: fix a use after free in xfs_defer_finish_recovery

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: 4f6ac47b55e3ce6e982807928d6074ec105ab66e

dfp will be freed by ->recover_work and thus the tracepoint in case
of an error can lead to a use after free.

Store the defer ops in a local variable to avoid that.

Fixes: 7f2f7531e0d4 ("xfs: store an ops pointer in struct xfs_defer_pending")
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 077e99298..5bdc8f5a2 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -909,12 +909,14 @@ xfs_defer_finish_recovery(
 	struct xfs_defer_pending	*dfp,
 	struct list_head		*capture_list)
 {
+	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
 	int				error;
 
-	error = dfp->dfp_ops->recover_work(dfp, capture_list);
+	/* dfp is freed by recover_work and must not be accessed afterwards */
+	error = ops->recover_work(dfp, capture_list);
 	if (error)
 		trace_xlog_intent_recovery_failed(mp, error,
-				dfp->dfp_ops->recover_work);
+				ops->recover_work);
 	return error;
 }
 
-- 
2.44.0

[PATCH 64/67] xfs: use the op name in trace_xlog_intent_recovery_failed

[cem]

From: Christoph Hellwig <hch@lst.de>

Source kernel commit: bcdfae6ee520b665385020fa3e47633a8af84f12

Instead of tracing the address of the recovery handler, use the name
in the defer op, similar to other defer ops related tracepoints.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_defer.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 5bdc8f5a2..bf1d1e06a 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -915,8 +915,7 @@ xfs_defer_finish_recovery(
 	/* dfp is freed by recover_work and must not be accessed afterwards */
 	error = ops->recover_work(dfp, capture_list);
 	if (error)
-		trace_xlog_intent_recovery_failed(mp, error,
-				ops->recover_work);
+		trace_xlog_intent_recovery_failed(mp, ops, error);
 	return error;
 }
 
-- 
2.44.0

[PATCH 65/67] xfs: fix backwards logic in xfs_bmap_alloc_account

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: d61b40bf15ce453f3aa71f6b423938e239e7f8f8

We're only allocating from the realtime device if the inode is marked
for realtime and we're /not/ allocating into the attr fork.

Fixes: 58643460546d ("xfs: also use xfs_bmap_btalloc_accounting for RT allocations")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_bmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 5e6a5e1f3..494994d36 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -3271,7 +3271,7 @@ xfs_bmap_alloc_account(
 	struct xfs_bmalloca	*ap)
 {
 	bool			isrt = XFS_IS_REALTIME_INODE(ap->ip) &&
-					(ap->flags & XFS_BMAPI_ATTRFORK);
+					!(ap->flags & XFS_BMAPI_ATTRFORK);
 	uint			fld;
 
 	if (ap->flags & XFS_BMAPI_COWFORK) {
-- 
2.44.0

[PATCH 66/67] xfs: reset XFS_ATTR_INCOMPLETE filter on node removal

[cem]

From: Andrey Albershteyn <aalbersh@redhat.com>

Source kernel commit: 82ef1a5356572219f41f9123ca047259a77bd67b

In XFS_DAS_NODE_REMOVE_ATTR case, xfs_attr_mode_remove_attr() sets
filter to XFS_ATTR_INCOMPLETE. The filter is then reset in
xfs_attr_complete_op() if XFS_DA_OP_REPLACE operation is performed.

The filter is not reset though if XFS just removes the attribute
(args->value == NULL) with xfs_attr_defer_remove(). attr code goes
to XFS_DAS_DONE state.

Fix this by always resetting XFS_ATTR_INCOMPLETE filter. The replace
operation already resets this filter in anyway and others are
completed at this step hence don't need it.

Fixes: fdaf1bb3cafc ("xfs: ATTR_REPLACE algorithm with LARP enabled needs rework")
Signed-off-by: Andrey Albershteyn <aalbersh@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_attr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index 1419846bd..630065f1a 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -419,10 +419,10 @@ xfs_attr_complete_op(
 	bool			do_replace = args->op_flags & XFS_DA_OP_REPLACE;
 
 	args->op_flags &= ~XFS_DA_OP_REPLACE;
-	if (do_replace) {
-		args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	if (do_replace)
 		return replace_state;
-	}
+
 	return XFS_DAS_DONE;
 }
 
-- 
2.44.0

[PATCH 67/67] xfs: remove conditional building of rt geometry validator functions

[cem]

From: "Darrick J. Wong" <djwong@kernel.org>

Source kernel commit: 881f78f472556ed05588172d5b5676b48dc48240

I mistakenly turned off CONFIG_XFS_RT in the Kconfig file for arm64
variant of the djwong-wtf git branch.  Unfortunately, it took me a good
hour to figure out that RT wasn't built because this is what got printed
to dmesg:

XFS (sda2): realtime geometry sanity check failed
XFS (sda2): Metadata corruption detected at xfs_sb_read_verify+0x170/0x190 [xfs], xfs_sb block 0x0

Whereas I would have expected:

XFS (sda2): Not built with CONFIG_XFS_RT
XFS (sda2): RT mount failed

The root cause of these problems is the conditional compilation of the
new functions xfs_validate_rtextents and xfs_compute_rextslog that I
introduced in the two commits listed below.  The !RT versions of these
functions return false and 0, respectively, which causes primary
superblock validation to fail, which explains the first message.

Move the two functions to other parts of libxfs that are not
conditionally defined by CONFIG_XFS_RT and remove the broken stubs so
that validation works again.

Fixes: e14293803f4e ("xfs: don't allow overly small or large realtime volumes")
Fixes: a6a38f309afc ("xfs: make rextslog computation consistent with mkfs")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 libxfs/xfs_rtbitmap.c | 14 --------------
 libxfs/xfs_rtbitmap.h | 16 ----------------
 libxfs/xfs_sb.c       | 14 ++++++++++++++
 libxfs/xfs_sb.h       |  2 ++
 libxfs/xfs_types.h    | 12 ++++++++++++
 5 files changed, 28 insertions(+), 30 deletions(-)

diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index 79af7cda3..08a4128fc 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -1116,20 +1116,6 @@ xfs_rtbitmap_blockcount(
 	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
 }
 
-/*
- * Compute the maximum level number of the realtime summary file, as defined by
- * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
- * use of rt volumes with more than 2^32 extents.
- */
-uint8_t
-xfs_compute_rextslog(
-	xfs_rtbxlen_t		rtextents)
-{
-	if (!rtextents)
-		return 0;
-	return xfs_highbit64(rtextents);
-}
-
 /*
  * Compute the number of rtbitmap words needed to populate every block of a
  * bitmap that is large enough to track the given number of rt extents.
diff --git a/libxfs/xfs_rtbitmap.h b/libxfs/xfs_rtbitmap.h
index 274dc7dae..152a66750 100644
--- a/libxfs/xfs_rtbitmap.h
+++ b/libxfs/xfs_rtbitmap.h
@@ -351,20 +351,6 @@ xfs_rtfree_extent(
 int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
 		xfs_filblks_t rtlen);
 
-uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
-
-/* Do we support an rt volume having this number of rtextents? */
-static inline bool
-xfs_validate_rtextents(
-	xfs_rtbxlen_t		rtextents)
-{
-	/* No runt rt volumes */
-	if (rtextents == 0)
-		return false;
-
-	return true;
-}
-
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -383,8 +369,6 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
 # define xfs_rtsummary_read_buf(a,b)			(-ENOSYS)
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
-# define xfs_compute_rextslog(rtx)			(0)
-# define xfs_validate_rtextents(rtx)			(false)
 static inline xfs_filblks_t
 xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
diff --git a/libxfs/xfs_sb.c b/libxfs/xfs_sb.c
index 7a72d5a17..402f03a55 100644
--- a/libxfs/xfs_sb.c
+++ b/libxfs/xfs_sb.c
@@ -1375,3 +1375,17 @@ xfs_validate_stripe_geometry(
 	}
 	return true;
 }
+
+/*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+	xfs_rtbxlen_t		rtextents)
+{
+	if (!rtextents)
+		return 0;
+	return xfs_highbit64(rtextents);
+}
diff --git a/libxfs/xfs_sb.h b/libxfs/xfs_sb.h
index 19134b23c..2e8e8d63d 100644
--- a/libxfs/xfs_sb.h
+++ b/libxfs/xfs_sb.h
@@ -38,4 +38,6 @@ extern int	xfs_sb_get_secondary(struct xfs_mount *mp,
 extern bool	xfs_validate_stripe_geometry(struct xfs_mount *mp,
 		__s64 sunit, __s64 swidth, int sectorsize, bool silent);
 
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
 #endif	/* __XFS_SB_H__ */
diff --git a/libxfs/xfs_types.h b/libxfs/xfs_types.h
index 20b5375f2..62e02d538 100644
--- a/libxfs/xfs_types.h
+++ b/libxfs/xfs_types.h
@@ -251,4 +251,16 @@ bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off);
 bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off,
 		xfs_fileoff_t len);
 
+/* Do we support an rt volume having this number of rtextents? */
+static inline bool
+xfs_validate_rtextents(
+	xfs_rtbxlen_t		rtextents)
+{
+	/* No runt rt volumes */
+	if (rtextents == 0)
+		return false;
+
+	return true;
+}
+
 #endif	/* __XFS_TYPES_H__ */
-- 
2.44.0