Merge tag 'xfs-alloc-perag-conversion' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs into xfs-6.3-merge-A

xfs: per-ag centric allocation alogrithms

This series continues the work towards making shrinking a filesystem
possible.  We need to be able to stop operations from taking place
on AGs that need to be removed by a shrink, so before shrink can be
implemented we need to have the infrastructure in place to prevent
incursion into AGs that are going to be, or are in the process, of
being removed from active duty.

The focus of this is making operations that depend on access to AGs
use the perag to access and pin the AG in active use, thereby
creating a barrier we can use to delay shrink until all active uses
of an AG have been drained and new uses are prevented.

This series starts by fixing some existing issues that are exposed
by changes later in the series. They stand alone, so can be picked
up independently of the rest of this patchset.

The most complex of these fixes is cleaning up the mess that is the
AGF deadlock avoidance algorithm. This algorithm stores the first
block that is allocated in a transaction in tp->t_firstblock, then
uses this to try to limit future allocations within the transaction
to AGs at or higher than the filesystem block stored in
tp->t_firstblock. This depends on one of the initial bug fixes in
the series to move the deadlock avoidance checks to
xfs_alloc_vextent(), and then builds on it to relax the constraints
of the avoidance algorithm to only be active when a deadlock is
possible.

We also update the algorithm to record allocations from higher AGs
that are allocated from, because we when we need to lock more than
two AGs we still have to ensure lock order is correct. Therefore we
can't lock AGs in the order 1, 3, 2, even though tp->t_firstblock
indicates that we've allocated from AG 1 and so AG is valid to lock.
It's not valid, because we already hold AG 3 locked, and so
tp->t-first_block should actually point at AG 3, not AG 1 in this
situation.

It should now be obvious that the deadlock avoidance algorithm
should record AGs, not filesystem blocks. So the series then changes
the transaction to store the highest AG we've allocated in rather
than a filesystem block we allocated.  This makes it obvious what
the constraints are, and trivial to update as we lock and allocate
from various AGs.

With all the bug fixes out of the way, the series then starts
converting the code to use active references. Active reference
counts are used by high level code that needs to prevent the AG from
being taken out from under it by a shrink operation. The high level
code needs to be able to handle not getting an active reference
gracefully, and the shrink code will need to wait for active
references to drain before continuing.

Active references are implemented just as reference counts right now
- an active reference is taken at perag init during mount, and all
other active references are dependent on the active reference count
being greater than zero. This gives us an initial method of stopping
new active references without needing other infrastructure; just
drop the reference taken at filesystem mount time and when the
refcount then falls to zero no new references can be taken.

In future, this will need to take into account AG control state
(e.g. offline, no alloc, etc) as well as the reference count, but
right now we can implement a basic barrier for shrink with just
reference count manipulations. As such, patches to convert the perag
state to atomic opstate fields similar to the xfs_mount and xlog
opstate fields follow the initial active perag reference counting
patches.

The first target for active reference conversion is the
for_each_perag*() iterators. This captures a lot of high level code
that should skip offline AGs, and introduces the ability to
differentiate between a lookup that didn't have an online AG and the
end of the AG iteration range.

From there, the inode allocation AG selection is converted to active
references, and the perag is driven deeper into the inode allocation
and btree code to replace the xfs_mount. Most of the inode
allocation code operates on a single AG once it is selected, hence
it should pass the perag as the primary referenced object around for
allocation, not the xfs_mount. There is a bit of churn here, but it
emphasises that inode allocation is inherently an allocation group
based operation.

Next the bmap/alloc interface undergoes a major untangling,
reworking xfs_bmap_btalloc() into separate allocation operations for
different contexts and failure handling behaviours. This then allows
us to completely remove the xfs_alloc_vextent() layer via
restructuring the xfs_alloc_vextent/xfs_alloc_ag_vextent() into a
set of realtively simple helper function that describe the
allocation that they are doing. e.g.  xfs_alloc_vextent_exact_bno().

This allows the requirements for accessing AGs to be allocation
context dependent. The allocations that require operation on a
single AG generally can't tolerate failure after the allocation
method and AG has been decided on, and hence the caller needs to
manage the active references to ensure the allocation does not race
with shrink removing the selected AG for the duration of the
operation that requires access to that allocation group.

Other allocations iterate AGs and so the first AG is just a hint -
these do not need to pin a perag first as they can tolerate not
being able to access an AG by simply skipping over it. These require
new perag iteration functions that can start at arbitrary AGs and
wrap around at arbitrary AGs, hence a new set for
for_each_perag_wrap*() helpers to do this.

Next is the rework of the filestreams allocator. This doesn't change
any functionality, but gets rid of the unnecessary multi-pass
selection algorithm when the selected AG is not available. It
currently does a lookup pass which might iterate all AGs to select
an AG, then checks if the AG is acceptible and if not does a "new
AG" pass that is essentially identical to the lookup pass. Both of
these scans also do the same "longest extent in AG" check before
selecting an AG as is done after the AG is selected.

IOWs, the filestreams algorithm can be greatly simplified into a
single new AG selection pass if the there is no current association
or the currently associated AG doesn't have enough contiguous free
space for the allocation to proceed.  With this simplification of
the filestreams allocator, it's then trivial to convert it to use
for_each_perag_wrap() for the AG scan algorithm.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>

* tag 'xfs-alloc-perag-conversion' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (42 commits)
  xfs: refactor the filestreams allocator pick functions
  xfs: return a referenced perag from filestreams allocator
  xfs: pass perag to filestreams tracing
  xfs: use for_each_perag_wrap in xfs_filestream_pick_ag
  xfs: track an active perag reference in filestreams
  xfs: factor out MRU hit case in xfs_filestream_select_ag
  xfs: remove xfs_filestream_select_ag() longest extent check
  xfs: merge new filestream AG selection into xfs_filestream_select_ag()
  xfs: merge filestream AG lookup into xfs_filestream_select_ag()
  xfs: move xfs_bmap_btalloc_filestreams() to xfs_filestreams.c
  xfs: use xfs_bmap_longest_free_extent() in filestreams
  xfs: get rid of notinit from xfs_bmap_longest_free_extent
  xfs: factor out filestreams from xfs_bmap_btalloc_nullfb
  xfs: convert trim to use for_each_perag_range
  xfs: convert xfs_alloc_vextent_iterate_ags() to use perag walker
  xfs: move the minimum agno checks into xfs_alloc_vextent_check_args
  xfs: fold xfs_alloc_ag_vextent() into callers
  xfs: move allocation accounting to xfs_alloc_vextent_set_fsbno()
  xfs: introduce xfs_alloc_vextent_prepare()
  xfs: introduce xfs_alloc_vextent_exact_bno()
  ...

36 files changed, 1534 insertions, 1243 deletions

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index bb0c700afe3c..86696a1c6891 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -44,16 +44,15 @@ xfs_perag_get(
 	xfs_agnumber_t		agno)
 {
 	struct xfs_perag	*pag;
-	int			ref = 0;
 
 	rcu_read_lock();
 	pag = radix_tree_lookup(&mp->m_perag_tree, agno);
 	if (pag) {
+		trace_xfs_perag_get(pag, _RET_IP_);
 		ASSERT(atomic_read(&pag->pag_ref) >= 0);
-		ref = atomic_inc_return(&pag->pag_ref);
+		atomic_inc(&pag->pag_ref);
 	}
 	rcu_read_unlock();
-	trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
 	return pag;
 }
 
@@ -68,7 +67,6 @@ xfs_perag_get_tag(
 {
 	struct xfs_perag	*pag;
 	int			found;
-	int			ref;
 
 	rcu_read_lock();
 	found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
@@ -77,9 +75,9 @@ xfs_perag_get_tag(
 		rcu_read_unlock();
 		return NULL;
 	}
-	ref = atomic_inc_return(&pag->pag_ref);
+	trace_xfs_perag_get_tag(pag, _RET_IP_);
+	atomic_inc(&pag->pag_ref);
 	rcu_read_unlock();
-	trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_);
 	return pag;
 }
 
@@ -87,11 +85,68 @@ void
 xfs_perag_put(
 	struct xfs_perag	*pag)
 {
-	int	ref;
-
+	trace_xfs_perag_put(pag, _RET_IP_);
 	ASSERT(atomic_read(&pag->pag_ref) > 0);
-	ref = atomic_dec_return(&pag->pag_ref);
-	trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
+	atomic_dec(&pag->pag_ref);
+}
+
+/*
+ * Active references for perag structures. This is for short term access to the
+ * per ag structures for walking trees or accessing state. If an AG is being
+ * shrunk or is offline, then this will fail to find that AG and return NULL
+ * instead.
+ */
+struct xfs_perag *
+xfs_perag_grab(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno)
+{
+	struct xfs_perag	*pag;
+
+	rcu_read_lock();
+	pag = radix_tree_lookup(&mp->m_perag_tree, agno);
+	if (pag) {
+		trace_xfs_perag_grab(pag, _RET_IP_);
+		if (!atomic_inc_not_zero(&pag->pag_active_ref))
+			pag = NULL;
+	}
+	rcu_read_unlock();
+	return pag;
+}
+
+/*
+ * search from @first to find the next perag with the given tag set.
+ */
+struct xfs_perag *
+xfs_perag_grab_tag(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		first,
+	int			tag)
+{
+	struct xfs_perag	*pag;
+	int			found;
+
+	rcu_read_lock();
+	found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
+					(void **)&pag, first, 1, tag);
+	if (found <= 0) {
+		rcu_read_unlock();
+		return NULL;
+	}
+	trace_xfs_perag_grab_tag(pag, _RET_IP_);
+	if (!atomic_inc_not_zero(&pag->pag_active_ref))
+		pag = NULL;
+	rcu_read_unlock();
+	return pag;
+}
+
+void
+xfs_perag_rele(
+	struct xfs_perag	*pag)
+{
+	trace_xfs_perag_rele(pag, _RET_IP_);
+	if (atomic_dec_and_test(&pag->pag_active_ref))
+		wake_up(&pag->pag_active_wq);
 }
 
 /*
@@ -196,6 +251,10 @@ xfs_free_perag(
 		cancel_delayed_work_sync(&pag->pag_blockgc_work);
 		xfs_buf_hash_destroy(pag);
 
+		/* drop the mount's active reference */
+		xfs_perag_rele(pag);
+		XFS_IS_CORRUPT(pag->pag_mount,
+				atomic_read(&pag->pag_active_ref) != 0);
 		call_rcu(&pag->rcu_head, __xfs_free_perag);
 	}
 }
@@ -314,6 +373,7 @@ xfs_initialize_perag(
 		INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
 		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
 		init_waitqueue_head(&pag->pagb_wait);
+		init_waitqueue_head(&pag->pag_active_wq);
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
 #endif /* __KERNEL__ */
@@ -322,6 +382,9 @@ xfs_initialize_perag(
 		if (error)
 			goto out_remove_pag;
 
+		/* Active ref owned by mount indicates AG is online. */
+		atomic_set(&pag->pag_active_ref, 1);
+
 		/* first new pag is fully initialized */
 		if (first_initialised == NULLAGNUMBER)
 			first_initialised = index;
@@ -824,7 +887,7 @@ xfs_ag_shrink_space(
 	struct xfs_alloc_arg	args = {
 		.tp	= *tpp,
 		.mp	= mp,
-		.type	= XFS_ALLOCTYPE_THIS_BNO,
+		.pag	= pag,
 		.minlen = delta,
 		.maxlen = delta,
 		.oinfo	= XFS_RMAP_OINFO_SKIP_UPDATE,
@@ -856,14 +919,11 @@ xfs_ag_shrink_space(
 	if (delta >= aglen)
 		return -EINVAL;
 
-	args.fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta);
-
 	/*
 	 * Make sure that the last inode cluster cannot overlap with the new
 	 * end of the AG, even if it's sparse.
 	 */
-	error = xfs_ialloc_check_shrink(*tpp, pag->pag_agno, agibp,
-			aglen - delta);
+	error = xfs_ialloc_check_shrink(pag, *tpp, agibp, aglen - delta);
 	if (error)
 		return error;
 
@@ -876,7 +936,8 @@ xfs_ag_shrink_space(
 		return error;
 
 	/* internal log shouldn't also show up in the free space btrees */
-	error = xfs_alloc_vextent(&args);
+	error = xfs_alloc_vextent_exact_bno(&args,
+			XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta));
 	if (!error && args.agbno == NULLAGBLOCK)
 		error = -ENOSPC;
 
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 191b22b9a35b..5e18536dfdce 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -32,14 +32,12 @@ struct xfs_ag_resv {
 struct xfs_perag {
 	struct xfs_mount *pag_mount;	/* owner filesystem */
 	xfs_agnumber_t	pag_agno;	/* AG this structure belongs to */
-	atomic_t	pag_ref;	/* perag reference count */
-	char		pagf_init;	/* this agf's entry is initialized */
-	char		pagi_init;	/* this agi's entry is initialized */
-	char		pagf_metadata;	/* the agf is preferred to be metadata */
-	char		pagi_inodeok;	/* The agi is ok for inodes */
+	atomic_t	pag_ref;	/* passive reference count */
+	atomic_t	pag_active_ref;	/* active reference count */
+	wait_queue_head_t pag_active_wq;/* woken active_ref falls to zero */
+	unsigned long	pag_opstate;
 	uint8_t		pagf_levels[XFS_BTNUM_AGF];
 					/* # of levels in bno & cnt btree */
-	bool		pagf_agflreset; /* agfl requires reset before use */
 	uint32_t	pagf_flcount;	/* count of blocks in freelist */
 	xfs_extlen_t	pagf_freeblks;	/* total free blocks */
 	xfs_extlen_t	pagf_longest;	/* longest free space */
@@ -106,16 +104,44 @@ struct xfs_perag {
 #endif /* __KERNEL__ */
 };
 
+/*
+ * Per-AG operational state. These are atomic flag bits.
+ */
+#define XFS_AGSTATE_AGF_INIT		0
+#define XFS_AGSTATE_AGI_INIT		1
+#define XFS_AGSTATE_PREFERS_METADATA	2
+#define XFS_AGSTATE_ALLOWS_INODES	3
+#define XFS_AGSTATE_AGFL_NEEDS_RESET	4
+
+#define __XFS_AG_OPSTATE(name, NAME) \
+static inline bool xfs_perag_ ## name (struct xfs_perag *pag) \
+{ \
+	return test_bit(XFS_AGSTATE_ ## NAME, &pag->pag_opstate); \
+}
+
+__XFS_AG_OPSTATE(initialised_agf, AGF_INIT)
+__XFS_AG_OPSTATE(initialised_agi, AGI_INIT)
+__XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
+__XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
+__XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
+
 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);
 void xfs_free_perag(struct xfs_mount *mp);
 
+/* Passive AG references */
 struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno);
 struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno,
 		unsigned int tag);
 void xfs_perag_put(struct xfs_perag *pag);
 
+/* Active AG references */
+struct xfs_perag *xfs_perag_grab(struct xfs_mount *, xfs_agnumber_t);
+struct xfs_perag *xfs_perag_grab_tag(struct xfs_mount *, xfs_agnumber_t,
+				   int tag);
+void xfs_perag_rele(struct xfs_perag *pag);
+
 /*
  * Per-ag geometry infomation and validation
  */
@@ -193,31 +219,86 @@ xfs_perag_next(
 	struct xfs_mount	*mp = pag->pag_mount;
 
 	*agno = pag->pag_agno + 1;
-	xfs_perag_put(pag);
-	if (*agno > end_agno)
-		return NULL;
-	return xfs_perag_get(mp, *agno);
+	xfs_perag_rele(pag);
+	while (*agno <= end_agno) {
+		pag = xfs_perag_grab(mp, *agno);
+		if (pag)
+			return pag;
+		(*agno)++;
+	}
+	return NULL;
 }
 
 #define for_each_perag_range(mp, agno, end_agno, pag) \
-	for ((pag) = xfs_perag_get((mp), (agno)); \
+	for ((pag) = xfs_perag_grab((mp), (agno)); \
 		(pag) != NULL; \
 		(pag) = xfs_perag_next((pag), &(agno), (end_agno)))
 
 #define for_each_perag_from(mp, agno, pag) \
 	for_each_perag_range((mp), (agno), (mp)->m_sb.sb_agcount - 1, (pag))
 
-
 #define for_each_perag(mp, agno, pag) \
 	(agno) = 0; \
 	for_each_perag_from((mp), (agno), (pag))
 
 #define for_each_perag_tag(mp, agno, pag, tag) \
-	for ((agno) = 0, (pag) = xfs_perag_get_tag((mp), 0, (tag)); \
+	for ((agno) = 0, (pag) = xfs_perag_grab_tag((mp), 0, (tag)); \
 		(pag) != NULL; \
 		(agno) = (pag)->pag_agno + 1, \
-		xfs_perag_put(pag), \
-		(pag) = xfs_perag_get_tag((mp), (agno), (tag)))
+		xfs_perag_rele(pag), \
+		(pag) = xfs_perag_grab_tag((mp), (agno), (tag)))
+
+static inline struct xfs_perag *
+xfs_perag_next_wrap(
+	struct xfs_perag	*pag,
+	xfs_agnumber_t		*agno,
+	xfs_agnumber_t		stop_agno,
+	xfs_agnumber_t		restart_agno,
+	xfs_agnumber_t		wrap_agno)
+{
+	struct xfs_mount	*mp = pag->pag_mount;
+
+	*agno = pag->pag_agno + 1;
+	xfs_perag_rele(pag);
+	while (*agno != stop_agno) {
+		if (*agno >= wrap_agno) {
+			if (restart_agno >= stop_agno)
+				break;
+			*agno = restart_agno;
+		}
+
+		pag = xfs_perag_grab(mp, *agno);
+		if (pag)
+			return pag;
+		(*agno)++;
+	}
+	return NULL;
+}
+
+/*
+ * Iterate all AGs from start_agno through wrap_agno, then restart_agno through
+ * (start_agno - 1).
+ */
+#define for_each_perag_wrap_range(mp, start_agno, restart_agno, wrap_agno, agno, pag) \
+	for ((agno) = (start_agno), (pag) = xfs_perag_grab((mp), (agno)); \
+		(pag) != NULL; \
+		(pag) = xfs_perag_next_wrap((pag), &(agno), (start_agno), \
+				(restart_agno), (wrap_agno)))
+/*
+ * Iterate all AGs from start_agno through wrap_agno, then 0 through
+ * (start_agno - 1).
+ */
+#define for_each_perag_wrap_at(mp, start_agno, wrap_agno, agno, pag) \
+	for_each_perag_wrap_range((mp), (start_agno), 0, (wrap_agno), (agno), (pag))
+
+/*
+ * Iterate all AGs from start_agno through to the end of the filesystem, then 0
+ * through (start_agno - 1).
+ */
+#define for_each_perag_wrap(mp, start_agno, agno, pag) \
+	for_each_perag_wrap_at((mp), (start_agno), (mp)->m_sb.sb_agcount, \
+				(agno), (pag))
+
 
 struct aghdr_init_data {
 	/* per ag data */
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 5af123d13a63..7fd1fea95552 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -264,7 +264,7 @@ xfs_ag_resv_init(
 		if (error)
 			goto out;
 
-		error = xfs_finobt_calc_reserves(mp, tp, pag, &ask, &used);
+		error = xfs_finobt_calc_reserves(pag, tp, &ask, &used);
 		if (error)
 			goto out;
 
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index f8ff81c3de76..6a037173d20d 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -36,10 +36,6 @@ struct workqueue_struct *xfs_alloc_wq;
 #define	XFSA_FIXUP_BNO_OK	1
 #define	XFSA_FIXUP_CNT_OK	2
 
-STATIC int xfs_alloc_ag_vextent_exact(xfs_alloc_arg_t *);
-STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *);
-STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *);
-
 /*
  * Size of the AGFL.  For CRC-enabled filesystes we steal a couple of slots in
  * the beginning of the block for a proper header with the location information
@@ -772,8 +768,6 @@ xfs_alloc_cur_setup(
 	int			error;
 	int			i;
 
-	ASSERT(args->alignment == 1 || args->type != XFS_ALLOCTYPE_THIS_BNO);
-
 	acur->cur_len = args->maxlen;
 	acur->rec_bno = 0;
 	acur->rec_len = 0;
@@ -887,7 +881,6 @@ xfs_alloc_cur_check(
 	 * We have an aligned record that satisfies minlen and beats or matches
 	 * the candidate extent size. Compare locality for near allocation mode.
 	 */
-	ASSERT(args->type == XFS_ALLOCTYPE_NEAR_BNO);
 	diff = xfs_alloc_compute_diff(args->agbno, args->len,
 				      args->alignment, args->datatype,
 				      bnoa, lena, &bnew);
@@ -1133,78 +1126,6 @@ error:
 }
 
 /*
- * Allocate a variable extent in the allocation group agno.
- * Type and bno are used to determine where in the allocation group the
- * extent will start.
- * Extent's length (returned in *len) will be between minlen and maxlen,
- * and of the form k * prod + mod unless there's nothing that large.
- * Return the starting a.g. block, or NULLAGBLOCK if we can't do it.
- */
-STATIC int			/* error */
-xfs_alloc_ag_vextent(
-	xfs_alloc_arg_t	*args)	/* argument structure for allocation */
-{
-	int		error=0;
-
-	ASSERT(args->minlen > 0);
-	ASSERT(args->maxlen > 0);
-	ASSERT(args->minlen <= args->maxlen);
-	ASSERT(args->mod < args->prod);
-	ASSERT(args->alignment > 0);
-
-	/*
-	 * Branch to correct routine based on the type.
-	 */
-	args->wasfromfl = 0;
-	switch (args->type) {
-	case XFS_ALLOCTYPE_THIS_AG:
-		error = xfs_alloc_ag_vextent_size(args);
-		break;
-	case XFS_ALLOCTYPE_NEAR_BNO:
-		error = xfs_alloc_ag_vextent_near(args);
-		break;
-	case XFS_ALLOCTYPE_THIS_BNO:
-		error = xfs_alloc_ag_vextent_exact(args);
-		break;
-	default:
-		ASSERT(0);
-		/* NOTREACHED */
-	}
-
-	if (error || args->agbno == NULLAGBLOCK)
-		return error;
-
-	ASSERT(args->len >= args->minlen);
-	ASSERT(args->len <= args->maxlen);
-	ASSERT(!args->wasfromfl || args->resv != XFS_AG_RESV_AGFL);
-	ASSERT(args->agbno % args->alignment == 0);
-
-	/* if not file data, insert new block into the reverse map btree */
-	if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) {
-		error = xfs_rmap_alloc(args->tp, args->agbp, args->pag,
-				       args->agbno, args->len, &args->oinfo);
-		if (error)
-			return error;
-	}
-
-	if (!args->wasfromfl) {
-		error = xfs_alloc_update_counters(args->tp, args->agbp,
-						  -((long)(args->len)));
-		if (error)
-			return error;
-
-		ASSERT(!xfs_extent_busy_search(args->mp, args->pag,
-					      args->agbno, args->len));
-	}
-
-	xfs_ag_resv_alloc_extent(args->pag, args->resv, args);
-
-	XFS_STATS_INC(args->mp, xs_allocx);
-	XFS_STATS_ADD(args->mp, xs_allocb, args->len);
-	return error;
-}
-
-/*
  * Allocate a variable extent at exactly agno/bno.
  * Extent's length (returned in *len) will be between minlen and maxlen,
  * and of the form k * prod + mod unless there's nothing that large.
@@ -1389,7 +1310,6 @@ xfs_alloc_ag_vextent_locality(
 	bool			fbinc;
 
 	ASSERT(acur->len == 0);
-	ASSERT(args->type == XFS_ALLOCTYPE_NEAR_BNO);
 
 	*stat = 0;
 
@@ -2435,7 +2355,7 @@ xfs_agfl_reset(
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_agf		*agf = agbp->b_addr;
 
-	ASSERT(pag->pagf_agflreset);
+	ASSERT(xfs_perag_agfl_needs_reset(pag));
 	trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_);
 
 	xfs_warn(mp,
@@ -2450,7 +2370,7 @@ xfs_agfl_reset(
 				    XFS_AGF_FLCOUNT);
 
 	pag->pagf_flcount = 0;
-	pag->pagf_agflreset = false;
+	clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
 }
 
 /*
@@ -2605,7 +2525,7 @@ xfs_alloc_fix_freelist(
 	/* deferred ops (AGFL block frees) require permanent transactions */
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 
-	if (!pag->pagf_init) {
+	if (!xfs_perag_initialised_agf(pag)) {
 		error = xfs_alloc_read_agf(pag, tp, flags, &agbp);
 		if (error) {
 			/* Couldn't lock the AGF so skip this AG. */
@@ -2620,7 +2540,8 @@ xfs_alloc_fix_freelist(
 	 * somewhere else if we are not being asked to try harder at this
 	 * point
 	 */
-	if (pag->pagf_metadata && (args->datatype & XFS_ALLOC_USERDATA) &&
+	if (xfs_perag_prefers_metadata(pag) &&
+	    (args->datatype & XFS_ALLOC_USERDATA) &&
 	    (flags & XFS_ALLOC_FLAG_TRYLOCK)) {
 		ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING));
 		goto out_agbp_relse;
@@ -2646,7 +2567,7 @@ xfs_alloc_fix_freelist(
 	}
 
 	/* reset a padding mismatched agfl before final free space check */
-	if (pag->pagf_agflreset)
+	if (xfs_perag_agfl_needs_reset(pag))
 		xfs_agfl_reset(tp, agbp, pag);
 
 	/* If there isn't enough total space or single-extent, reject it. */
@@ -2707,7 +2628,6 @@ xfs_alloc_fix_freelist(
 	targs.agbp = agbp;
 	targs.agno = args->agno;
 	targs.alignment = targs.minlen = targs.prod = 1;
-	targs.type = XFS_ALLOCTYPE_THIS_AG;
 	targs.pag = pag;
 	error = xfs_alloc_read_agfl(pag, tp, &agflbp);
 	if (error)
@@ -2720,7 +2640,7 @@ xfs_alloc_fix_freelist(
 		targs.resv = XFS_AG_RESV_AGFL;
 
 		/* Allocate as many blocks as possible at once. */
-		error = xfs_alloc_ag_vextent(&targs);
+		error = xfs_alloc_ag_vextent_size(&targs);
 		if (error)
 			goto out_agflbp_relse;
 
@@ -2734,6 +2654,18 @@ xfs_alloc_fix_freelist(
 				break;
 			goto out_agflbp_relse;
 		}
+
+		if (!xfs_rmap_should_skip_owner_update(&targs.oinfo)) {
+			error = xfs_rmap_alloc(tp, agbp, pag,
+				       targs.agbno, targs.len, &targs.oinfo);
+			if (error)
+				goto out_agflbp_relse;
+		}
+		error = xfs_alloc_update_counters(tp, agbp,
+						  -((long)(targs.len)));
+		if (error)
+			goto out_agflbp_relse;
+
 		/*
 		 * Put each allocated block on the list.
 		 */
@@ -2803,7 +2735,7 @@ xfs_alloc_get_freelist(
 	if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp))
 		agf->agf_flfirst = 0;
 
-	ASSERT(!pag->pagf_agflreset);
+	ASSERT(!xfs_perag_agfl_needs_reset(pag));
 	be32_add_cpu(&agf->agf_flcount, -1);
 	pag->pagf_flcount--;
 
@@ -2892,7 +2824,7 @@ xfs_alloc_put_freelist(
 	if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp))
 		agf->agf_fllast = 0;
 
-	ASSERT(!pag->pagf_agflreset);
+	ASSERT(!xfs_perag_agfl_needs_reset(pag));
 	be32_add_cpu(&agf->agf_flcount, 1);
 	pag->pagf_flcount++;
 
@@ -3099,7 +3031,7 @@ xfs_alloc_read_agf(
 		return error;
 
 	agf = agfbp->b_addr;
-	if (!pag->pagf_init) {
+	if (!xfs_perag_initialised_agf(pag)) {
 		pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
 		pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
 		pag->pagf_flcount = be32_to_cpu(agf->agf_flcount);
@@ -3111,8 +3043,8 @@ xfs_alloc_read_agf(
 		pag->pagf_levels[XFS_BTNUM_RMAPi] =
 			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
 		pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
-		pag->pagf_init = 1;
-		pag->pagf_agflreset = xfs_agfl_needs_reset(pag->pag_mount, agf);
+		if (xfs_agfl_needs_reset(pag->pag_mount, agf))
+			set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
 
 		/*
 		 * Update the in-core allocbt counter. Filter out the rmapbt
@@ -3127,6 +3059,8 @@ xfs_alloc_read_agf(
 		if (allocbt_blks > 0)
 			atomic64_add(allocbt_blks,
 					&pag->pag_mount->m_allocbt_blks);
+
+		set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
 	}
 #ifdef DEBUG
 	else if (!xfs_is_shutdown(pag->pag_mount)) {
@@ -3148,26 +3082,25 @@ xfs_alloc_read_agf(
 }
 
 /*
- * Allocate an extent (variable-size).
- * Depending on the allocation type, we either look in a single allocation
- * group or loop over the allocation groups to find the result.
+ * Pre-proces allocation arguments to set initial state that we don't require
+ * callers to set up correctly, as well as bounds check the allocation args
+ * that are set up.
  */
-int				/* error */
-xfs_alloc_vextent(
-	struct xfs_alloc_arg	*args)	/* allocation argument structure */
+static int
+xfs_alloc_vextent_check_args(
+	struct xfs_alloc_arg	*args,
+	xfs_fsblock_t		target,
+	xfs_agnumber_t		*minimum_agno)
 {
-	xfs_agblock_t		agsize;	/* allocation group size */
-	int			error;
-	int			flags;	/* XFS_ALLOC_FLAG_... locking flags */
-	struct xfs_mount	*mp;	/* mount structure pointer */
-	xfs_agnumber_t		sagno;	/* starting allocation group number */
-	xfs_alloctype_t		type;	/* input allocation type */
-	int			bump_rotor = 0;
-	xfs_agnumber_t		rotorstep = xfs_rotorstep; /* inode32 agf stepper */
-
-	mp = args->mp;
-	type = args->otype = args->type;
-	args->agbno = NULLAGBLOCK;
+	struct xfs_mount	*mp = args->mp;
+	xfs_agblock_t		agsize;
+
+	args->fsbno = NULLFSBLOCK;
+
+	*minimum_agno = 0;
+	if (args->tp->t_highest_agno != NULLAGNUMBER)
+		*minimum_agno = args->tp->t_highest_agno;
+
 	/*
 	 * Just fix this up, for the case where the last a.g. is shorter
 	 * (or there's only one a.g.) and the caller couldn't easily figure
@@ -3178,168 +3111,414 @@ xfs_alloc_vextent(
 		args->maxlen = agsize;
 	if (args->alignment == 0)
 		args->alignment = 1;
-	ASSERT(XFS_FSB_TO_AGNO(mp, args->fsbno) < mp->m_sb.sb_agcount);
-	ASSERT(XFS_FSB_TO_AGBNO(mp, args->fsbno) < agsize);
+
+	ASSERT(args->minlen > 0);
+	ASSERT(args->maxlen > 0);
+	ASSERT(args->alignment > 0);
+	ASSERT(args->resv != XFS_AG_RESV_AGFL);
+
+	ASSERT(XFS_FSB_TO_AGNO(mp, target) < mp->m_sb.sb_agcount);
+	ASSERT(XFS_FSB_TO_AGBNO(mp, target) < agsize);
 	ASSERT(args->minlen <= args->maxlen);
 	ASSERT(args->minlen <= agsize);
 	ASSERT(args->mod < args->prod);
-	if (XFS_FSB_TO_AGNO(mp, args->fsbno) >= mp->m_sb.sb_agcount ||
-	    XFS_FSB_TO_AGBNO(mp, args->fsbno) >= agsize ||
+
+	if (XFS_FSB_TO_AGNO(mp, target) >= mp->m_sb.sb_agcount ||
+	    XFS_FSB_TO_AGBNO(mp, target) >= agsize ||
 	    args->minlen > args->maxlen || args->minlen > agsize ||
 	    args->mod >= args->prod) {
-		args->fsbno = NULLFSBLOCK;
 		trace_xfs_alloc_vextent_badargs(args);
+		return -ENOSPC;
+	}
+
+	if (args->agno != NULLAGNUMBER && *minimum_agno > args->agno) {
+		trace_xfs_alloc_vextent_skip_deadlock(args);
+		return -ENOSPC;
+	}
+	return 0;
+
+}
+
+/*
+ * Prepare an AG for allocation. If the AG is not prepared to accept the
+ * allocation, return failure.
+ *
+ * XXX(dgc): The complexity of "need_pag" will go away as all caller paths are
+ * modified to hold their own perag references.
+ */
+static int
+xfs_alloc_vextent_prepare_ag(
+	struct xfs_alloc_arg	*args)
+{
+	bool			need_pag = !args->pag;
+	int			error;
+
+	if (need_pag)
+		args->pag = xfs_perag_get(args->mp, args->agno);
+
+	args->agbp = NULL;
+	error = xfs_alloc_fix_freelist(args, 0);
+	if (error) {
+		trace_xfs_alloc_vextent_nofix(args);
+		if (need_pag)
+			xfs_perag_put(args->pag);
+		args->agbno = NULLAGBLOCK;
+		return error;
+	}
+	if (!args->agbp) {
+		/* cannot allocate in this AG at all */
+		trace_xfs_alloc_vextent_noagbp(args);
+		args->agbno = NULLAGBLOCK;
 		return 0;
 	}
+	args->wasfromfl = 0;
+	return 0;
+}
 
-	switch (type) {
-	case XFS_ALLOCTYPE_THIS_AG:
-	case XFS_ALLOCTYPE_NEAR_BNO:
-	case XFS_ALLOCTYPE_THIS_BNO:
-		/*
-		 * These three force us into a single a.g.
-		 */
-		args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno);
-		args->pag = xfs_perag_get(mp, args->agno);
-		error = xfs_alloc_fix_freelist(args, 0);
-		if (error) {
-			trace_xfs_alloc_vextent_nofix(args);
-			goto error0;
-		}
-		if (!args->agbp) {
-			trace_xfs_alloc_vextent_noagbp(args);
+/*
+ * Post-process allocation results to account for the allocation if it succeed
+ * and set the allocated block number correctly for the caller.
+ *
+ * XXX: we should really be returning ENOSPC for ENOSPC, not
+ * hiding it behind a "successful" NULLFSBLOCK allocation.
+ */
+static int
+xfs_alloc_vextent_finish(
+	struct xfs_alloc_arg	*args,
+	xfs_agnumber_t		minimum_agno,
+	int			alloc_error,
+	bool			drop_perag)
+{
+	struct xfs_mount	*mp = args->mp;
+	int			error = 0;
+
+	/*
+	 * We can end up here with a locked AGF. If we failed, the caller is
+	 * likely going to try to allocate again with different parameters, and
+	 * that can widen the AGs that are searched for free space. If we have
+	 * to do BMBT block allocation, we have to do a new allocation.
+	 *
+	 * Hence leaving this function with the AGF locked opens up potential
+	 * ABBA AGF deadlocks because a future allocation attempt in this
+	 * transaction may attempt to lock a lower number AGF.
+	 *
+	 * We can't release the AGF until the transaction is commited, so at
+	 * this point we must update the "first allocation" tracker to point at
+	 * this AG if the tracker is empty or points to a lower AG. This allows
+	 * the next allocation attempt to be modified appropriately to avoid
+	 * deadlocks.
+	 */
+	if (args->agbp &&
+	    (args->tp->t_highest_agno == NULLAGNUMBER ||
+	     args->agno > minimum_agno))
+		args->tp->t_highest_agno = args->agno;
+
+	/*
+	 * If the allocation failed with an error or we had an ENOSPC result,
+	 * preserve the returned error whilst also marking the allocation result
+	 * as "no extent allocated". This ensures that callers that fail to
+	 * capture the error will still treat it as a failed allocation.
+	 */
+	if (alloc_error || args->agbno == NULLAGBLOCK) {
+		args->fsbno = NULLFSBLOCK;
+		error = alloc_error;
+		goto out_drop_perag;
+	}
+
+	args->fsbno = XFS_AGB_TO_FSB(mp, args->agno, args->agbno);
+
+	ASSERT(args->len >= args->minlen);
+	ASSERT(args->len <= args->maxlen);
+	ASSERT(args->agbno % args->alignment == 0);
+	XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno), args->len);
+
+	/* if not file data, insert new block into the reverse map btree */
+	if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) {
+		error = xfs_rmap_alloc(args->tp, args->agbp, args->pag,
+				       args->agbno, args->len, &args->oinfo);
+		if (error)
+			goto out_drop_perag;
+	}
+
+	if (!args->wasfromfl) {
+		error = xfs_alloc_update_counters(args->tp, args->agbp,
+						  -((long)(args->len)));
+		if (error)
+			goto out_drop_perag;
+
+		ASSERT(!xfs_extent_busy_search(mp, args->pag, args->agbno,
+				args->len));
+	}
+
+	xfs_ag_resv_alloc_extent(args->pag, args->resv, args);
+
+	XFS_STATS_INC(mp, xs_allocx);
+	XFS_STATS_ADD(mp, xs_allocb, args->len);
+
+out_drop_perag:
+	if (drop_perag && args->pag) {
+		xfs_perag_rele(args->pag);
+		args->pag = NULL;
+	}
+	return error;
+}
+
+/*
+ * Allocate within a single AG only. This uses a best-fit length algorithm so if
+ * you need an exact sized allocation without locality constraints, this is the
+ * fastest way to do it.
+ *
+ * Caller is expected to hold a perag reference in args->pag.
+ */
+int
+xfs_alloc_vextent_this_ag(
+	struct xfs_alloc_arg	*args,
+	xfs_agnumber_t		agno)
+{
+	struct xfs_mount	*mp = args->mp;
+	xfs_agnumber_t		minimum_agno;
+	int			error;
+
+	args->agno = agno;
+	args->agbno = 0;
+	error = xfs_alloc_vextent_check_args(args, XFS_AGB_TO_FSB(mp, agno, 0),
+			&minimum_agno);
+	if (error) {
+		if (error == -ENOSPC)
+			return 0;
+		return error;
+	}
+
+	error = xfs_alloc_vextent_prepare_ag(args);
+	if (!error && args->agbp)
+		error = xfs_alloc_ag_vextent_size(args);
+
+	return xfs_alloc_vextent_finish(args, minimum_agno, error, false);
+}
+
+/*
+ * Iterate all AGs trying to allocate an extent starting from @start_ag.
+ *
+ * If the incoming allocation type is XFS_ALLOCTYPE_NEAR_BNO, it means the
+ * allocation attempts in @start_agno have locality information. If we fail to
+ * allocate in that AG, then we revert to anywhere-in-AG for all the other AGs
+ * we attempt to allocation in as there is no locality optimisation possible for
+ * those allocations.
+ *
+ * On return, args->pag may be left referenced if we finish before the "all
+ * failed" return point. The allocation finish still needs the perag, and
+ * so the caller will release it once they've finished the allocation.
+ *
+ * When we wrap the AG iteration at the end of the filesystem, we have to be
+ * careful not to wrap into AGs below ones we already have locked in the
+ * transaction if we are doing a blocking iteration. This will result in an
+ * out-of-order locking of AGFs and hence can cause deadlocks.
+ */
+static int
+xfs_alloc_vextent_iterate_ags(
+	struct xfs_alloc_arg	*args,
+	xfs_agnumber_t		minimum_agno,
+	xfs_agnumber_t		start_agno,
+	xfs_agblock_t		target_agbno,
+	uint32_t		flags)
+{
+	struct xfs_mount	*mp = args->mp;
+	xfs_agnumber_t		agno;
+	int			error = 0;
+
+restart:
+	for_each_perag_wrap_range(mp, start_agno, minimum_agno,
+			mp->m_sb.sb_agcount, agno, args->pag) {
+		args->agno = agno;
+		error = xfs_alloc_vextent_prepare_ag(args);
+		if (error)
 			break;
+		if (!args->agbp) {
+			trace_xfs_alloc_vextent_loopfailed(args);
+			continue;
 		}
-		args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno);
-		if ((error = xfs_alloc_ag_vextent(args)))
-			goto error0;
-		break;
-	case XFS_ALLOCTYPE_START_BNO:
-		/*
-		 * Try near allocation first, then anywhere-in-ag after
-		 * the first a.g. fails.
-		 */
-		if ((args->datatype & XFS_ALLOC_INITIAL_USER_DATA) &&
-		    xfs_is_inode32(mp)) {
-			args->fsbno = XFS_AGB_TO_FSB(mp,
-					((mp->m_agfrotor / rotorstep) %
-					mp->m_sb.sb_agcount), 0);
-			bump_rotor = 1;
-		}
-		args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno);
-		args->type = XFS_ALLOCTYPE_NEAR_BNO;
-		fallthrough;
-	case XFS_ALLOCTYPE_FIRST_AG:
+
 		/*
-		 * Rotate through the allocation groups looking for a winner.
+		 * Allocation is supposed to succeed now, so break out of the
+		 * loop regardless of whether we succeed or not.
 		 */
-		if (type == XFS_ALLOCTYPE_FIRST_AG) {
-			/*
-			 * Start with allocation group given by bno.
-			 */
-			args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno);
-			args->type = XFS_ALLOCTYPE_THIS_AG;
-			sagno = 0;
-			flags = 0;
+		if (args->agno == start_agno && target_agbno) {
+			args->agbno = target_agbno;
+			error = xfs_alloc_ag_vextent_near(args);
 		} else {
-			/*
-			 * Start with the given allocation group.
-			 */
-			args->agno = sagno = XFS_FSB_TO_AGNO(mp, args->fsbno);
-			flags = XFS_ALLOC_FLAG_TRYLOCK;
-		}
-		/*
-		 * Loop over allocation groups twice; first time with
-		 * trylock set, second time without.
-		 */
-		for (;;) {
-			args->pag = xfs_perag_get(mp, args->agno);
-			error = xfs_alloc_fix_freelist(args, flags);
-			if (error) {
-				trace_xfs_alloc_vextent_nofix(args);
-				goto error0;
-			}
-			/*
-			 * If we get a buffer back then the allocation will fly.
-			 */
-			if (args->agbp) {
-				if ((error = xfs_alloc_ag_vextent(args)))
-					goto error0;
-				break;
-			}
-
-			trace_xfs_alloc_vextent_loopfailed(args);
-
-			/*
-			 * Didn't work, figure out the next iteration.
-			 */
-			if (args->agno == sagno &&
-			    type == XFS_ALLOCTYPE_START_BNO)
-				args->type = XFS_ALLOCTYPE_THIS_AG;
-			/*
-			* For the first allocation, we can try any AG to get
-			* space.  However, if we already have allocated a
-			* block, we don't want to try AGs whose number is below
-			* sagno. Otherwise, we may end up with out-of-order
-			* locking of AGF, which might cause deadlock.
-			*/
-			if (++(args->agno) == mp->m_sb.sb_agcount) {
-				if (args->tp->t_firstblock != NULLFSBLOCK)
-					args->agno = sagno;
-				else
-					args->agno = 0;
-			}
-			/*
-			 * Reached the starting a.g., must either be done
-			 * or switch to non-trylock mode.
-			 */
-			if (args->agno == sagno) {
-				if (flags == 0) {
-					args->agbno = NULLAGBLOCK;
-					trace_xfs_alloc_vextent_allfailed(args);
-					break;
-				}
-
-				flags = 0;
-				if (type == XFS_ALLOCTYPE_START_BNO) {
-					args->agbno = XFS_FSB_TO_AGBNO(mp,
-						args->fsbno);
-					args->type = XFS_ALLOCTYPE_NEAR_BNO;
-				}
-			}
-			xfs_perag_put(args->pag);
-		}
-		if (bump_rotor) {
-			if (args->agno == sagno)
-				mp->m_agfrotor = (mp->m_agfrotor + 1) %
-					(mp->m_sb.sb_agcount * rotorstep);
-			else
-				mp->m_agfrotor = (args->agno * rotorstep + 1) %
-					(mp->m_sb.sb_agcount * rotorstep);
+			args->agbno = 0;
+			error = xfs_alloc_ag_vextent_size(args);
 		}
 		break;
-	default:
-		ASSERT(0);
-		/* NOTREACHED */
 	}
-	if (args->agbno == NULLAGBLOCK)
-		args->fsbno = NULLFSBLOCK;
-	else {
-		args->fsbno = XFS_AGB_TO_FSB(mp, args->agno, args->agbno);
-#ifdef DEBUG
-		ASSERT(args->len >= args->minlen);
-		ASSERT(args->len <= args->maxlen);
-		ASSERT(args->agbno % args->alignment == 0);
-		XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno),
-			args->len);
-#endif
+	if (error) {
+		xfs_perag_rele(args->pag);
+		args->pag = NULL;
+		return error;
+	}
+	if (args->agbp)
+		return 0;
 
+	/*
+	 * We didn't find an AG we can alloation from. If we were given
+	 * constraining flags by the caller, drop them and retry the allocation
+	 * without any constraints being set.
+	 */
+	if (flags) {
+		flags = 0;
+		goto restart;
 	}
-	xfs_perag_put(args->pag);
+
+	ASSERT(args->pag == NULL);
+	trace_xfs_alloc_vextent_allfailed(args);
 	return 0;
-error0:
-	xfs_perag_put(args->pag);
-	return error;
+}
+
+/*
+ * Iterate from the AGs from the start AG to the end of the filesystem, trying
+ * to allocate blocks. It starts with a near allocation attempt in the initial
+ * AG, then falls back to anywhere-in-ag after the first AG fails. It will wrap
+ * back to zero if allowed by previous allocations in this transaction,
+ * otherwise will wrap back to the start AG and run a second blocking pass to
+ * the end of the filesystem.
+ */
+int
+xfs_alloc_vextent_start_ag(
+	struct xfs_alloc_arg	*args,
+	xfs_fsblock_t		target)
+{
+	struct xfs_mount	*mp = args->mp;
+	xfs_agnumber_t		minimum_agno;
+	xfs_agnumber_t		start_agno;
+	xfs_agnumber_t		rotorstep = xfs_rotorstep;
+	bool			bump_rotor = false;
+	int			error;
+
+	args->agno = NULLAGNUMBER;
+	args->agbno = NULLAGBLOCK;
+	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
+	if (error) {
+		if (error == -ENOSPC)
+			return 0;
+		return error;
+	}
+
+	if ((args->datatype & XFS_ALLOC_INITIAL_USER_DATA) &&
+	    xfs_is_inode32(mp)) {
+		target = XFS_AGB_TO_FSB(mp,
+				((mp->m_agfrotor / rotorstep) %
+				mp->m_sb.sb_agcount), 0);
+		bump_rotor = 1;
+	}
+
+	start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
+	error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
+			XFS_FSB_TO_AGBNO(mp, target), XFS_ALLOC_FLAG_TRYLOCK);
+
+	if (bump_rotor) {
+		if (args->agno == start_agno)
+			mp->m_agfrotor = (mp->m_agfrotor + 1) %
+				(mp->m_sb.sb_agcount * rotorstep);
+		else
+			mp->m_agfrotor = (args->agno * rotorstep + 1) %
+				(mp->m_sb.sb_agcount * rotorstep);
+	}
+
+	return xfs_alloc_vextent_finish(args, minimum_agno, error, true);
+}
+
+/*
+ * Iterate from the agno indicated via @target through to the end of the
+ * filesystem attempting blocking allocation. This does not wrap or try a second
+ * pass, so will not recurse into AGs lower than indicated by the target.
+ */
+int
+xfs_alloc_vextent_first_ag(
+	struct xfs_alloc_arg	*args,
+	xfs_fsblock_t		target)
+ {
+	struct xfs_mount	*mp = args->mp;
+	xfs_agnumber_t		minimum_agno;
+	xfs_agnumber_t		start_agno;
+	int			error;
+
+	args->agno = NULLAGNUMBER;
+	args->agbno = NULLAGBLOCK;
+	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
+	if (error) {
+		if (error == -ENOSPC)
+			return 0;
+		return error;
+	}
+
+	start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
+	error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
+			XFS_FSB_TO_AGBNO(mp, target), 0);
+	return xfs_alloc_vextent_finish(args, minimum_agno, error, true);
+}
+
+/*
+ * Allocate at the exact block target or fail. Caller is expected to hold a
+ * perag reference in args->pag.
+ */
+int
+xfs_alloc_vextent_exact_bno(
+	struct xfs_alloc_arg	*args,
+	xfs_fsblock_t		target)
+{
+	struct xfs_mount	*mp = args->mp;
+	xfs_agnumber_t		minimum_agno;
+	int			error;
+
+	args->agno = XFS_FSB_TO_AGNO(mp, target);
+	args->agbno = XFS_FSB_TO_AGBNO(mp, target);
+	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
+	if (error) {
+		if (error == -ENOSPC)
+			return 0;
+		return error;
+	}
+
+	error = xfs_alloc_vextent_prepare_ag(args);
+	if (!error && args->agbp)
+		error = xfs_alloc_ag_vextent_exact(args);
+
+	return xfs_alloc_vextent_finish(args, minimum_agno, error, false);
+}
+
+/*
+ * Allocate an extent as close to the target as possible. If there are not
+ * viable candidates in the AG, then fail the allocation.
+ *
+ * Caller may or may not have a per-ag reference in args->pag.
+ */
+int
+xfs_alloc_vextent_near_bno(
+	struct xfs_alloc_arg	*args,
+	xfs_fsblock_t		target)
+{
+	struct xfs_mount	*mp = args->mp;
+	xfs_agnumber_t		minimum_agno;
+	bool			needs_perag = args->pag == NULL;
+	int			error;
+
+	args->agno = XFS_FSB_TO_AGNO(mp, target);
+	args->agbno = XFS_FSB_TO_AGBNO(mp, target);
+	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
+	if (error) {
+		if (error == -ENOSPC)
+			return 0;
+		return error;
+	}
+
+	if (needs_perag)
+		args->pag = xfs_perag_grab(mp, args->agno);
+
+	error = xfs_alloc_vextent_prepare_ag(args);
+	if (!error && args->agbp)
+		error = xfs_alloc_ag_vextent_near(args);
+
+	return xfs_alloc_vextent_finish(args, minimum_agno, error, needs_perag);
 }
 
 /* Ensure that the freelist is at full capacity. */
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 2c3f762dfb58..2b246d74c189 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -17,25 +17,6 @@ extern struct workqueue_struct *xfs_alloc_wq;
 unsigned int xfs_agfl_size(struct xfs_mount *mp);
 
 /*
- * Freespace allocation types.  Argument to xfs_alloc_[v]extent.
- */
-#define XFS_ALLOCTYPE_FIRST_AG	0x02	/* ... start at ag 0 */
-#define XFS_ALLOCTYPE_THIS_AG	0x08	/* anywhere in this a.g. */
-#define XFS_ALLOCTYPE_START_BNO	0x10	/* near this block else anywhere */
-#define XFS_ALLOCTYPE_NEAR_BNO	0x20	/* in this a.g. and near this block */
-#define XFS_ALLOCTYPE_THIS_BNO	0x40	/* at exactly this block */
-
-/* this should become an enum again when the tracing code is fixed */
-typedef unsigned int xfs_alloctype_t;
-
-#define XFS_ALLOC_TYPES \
-	{ XFS_ALLOCTYPE_FIRST_AG,	"FIRST_AG" }, \
-	{ XFS_ALLOCTYPE_THIS_AG,	"THIS_AG" }, \
-	{ XFS_ALLOCTYPE_START_BNO,	"START_BNO" }, \
-	{ XFS_ALLOCTYPE_NEAR_BNO,	"NEAR_BNO" }, \
-	{ XFS_ALLOCTYPE_THIS_BNO,	"THIS_BNO" }
-
-/*
  * Flags for xfs_alloc_fix_freelist.
  */
 #define	XFS_ALLOC_FLAG_TRYLOCK	0x00000001  /* use trylock for buffer locking */
@@ -68,8 +49,6 @@ typedef struct xfs_alloc_arg {
 	xfs_agblock_t	min_agbno;	/* set an agbno range for NEAR allocs */
 	xfs_agblock_t	max_agbno;	/* ... */
 	xfs_extlen_t	len;		/* output: actual size of extent */
-	xfs_alloctype_t	type;		/* allocation type XFS_ALLOCTYPE_... */
-	xfs_alloctype_t	otype;		/* original allocation type */
 	int		datatype;	/* mask defining data type treatment */
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
@@ -118,11 +97,43 @@ xfs_alloc_log_agf(
 	uint32_t	fields);/* mask of fields to be logged (XFS_AGF_...) */
 
 /*
- * Allocate an extent (variable-size).
+ * Allocate an extent anywhere in the specific AG given. If there is no
+ * space matching the requirements in that AG, then the allocation will fail.
  */
-int				/* error */
-xfs_alloc_vextent(
-	xfs_alloc_arg_t	*args);	/* allocation argument structure */
+int xfs_alloc_vextent_this_ag(struct xfs_alloc_arg *args, xfs_agnumber_t agno);
+
+/*
+ * Allocate an extent as close to the target as possible. If there are not
+ * viable candidates in the AG, then fail the allocation.
+ */
+int xfs_alloc_vextent_near_bno(struct xfs_alloc_arg *args,
+		xfs_fsblock_t target);
+
+/*
+ * Allocate an extent exactly at the target given. If this is not possible
+ * then the allocation fails.
+ */
+int xfs_alloc_vextent_exact_bno(struct xfs_alloc_arg *args,
+		xfs_fsblock_t target);
+
+/*
+ * Best effort full filesystem allocation scan.
+ *
+ * Locality aware allocation will be attempted in the initial AG, but on failure
+ * non-localised attempts will be made. The AGs are constrained by previous
+ * allocations in the current transaction. Two passes will be made - the first
+ * non-blocking, the second blocking.
+ */
+int xfs_alloc_vextent_start_ag(struct xfs_alloc_arg *args,
+		xfs_fsblock_t target);
+
+/*
+ * Iterate from the AG indicated from args->fsbno through to the end of the
+ * filesystem attempting blocking allocation. This is for use in last
+ * resort allocation attempts when everything else has failed.
+ */
+int xfs_alloc_vextent_first_ag(struct xfs_alloc_arg *args,
+		xfs_fsblock_t target);
 
 /*
  * Free an extent.
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 549a3cba0234..0f29c7b1b39f 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -315,7 +315,7 @@ xfs_allocbt_verify(
 	level = be16_to_cpu(block->bb_level);
 	if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC))
 		btnum = XFS_BTNUM_CNTi;
-	if (pag && pag->pagf_init) {
+	if (pag && xfs_perag_initialised_agf(pag)) {
 		if (level >= pag->pagf_levels[btnum])
 			return __this_address;
 	} else if (level >= mp->m_alloc_maxlevels)
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c8c65387136c..34de6e6898c4 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -645,34 +645,23 @@ xfs_bmap_extents_to_btree(
 	args.tp = tp;
 	args.mp = mp;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
-	if (tp->t_firstblock == NULLFSBLOCK) {
-		args.type = XFS_ALLOCTYPE_START_BNO;
-		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
-	} else if (tp->t_flags & XFS_TRANS_LOWMODE) {
-		args.type = XFS_ALLOCTYPE_START_BNO;
-		args.fsbno = tp->t_firstblock;
-	} else {
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		args.fsbno = tp->t_firstblock;
-	}
+
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = wasdel;
 	*logflagsp = 0;
-	error = xfs_alloc_vextent(&args);
+	error = xfs_alloc_vextent_start_ag(&args,
+				XFS_INO_TO_FSB(mp, ip->i_ino));
 	if (error)
 		goto out_root_realloc;
 
+	/*
+	 * Allocation can't fail, the space was reserved.
+	 */
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		error = -ENOSPC;
 		goto out_root_realloc;
 	}
 
-	/*
-	 * Allocation can't fail, the space was reserved.
-	 */
-	ASSERT(tp->t_firstblock == NULLFSBLOCK ||
-	       args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
-	tp->t_firstblock = args.fsbno;
 	cur->bc_ino.allocated++;
 	ip->i_nblocks++;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
@@ -799,28 +788,24 @@ xfs_bmap_local_to_extents(
 	memset(&args, 0, sizeof(args));
 	args.tp = tp;
 	args.mp = ip->i_mount;
+	args.total = total;
+	args.minlen = args.maxlen = args.prod = 1;
 	xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
+
 	/*
 	 * Allocate a block.  We know we need only one, since the
 	 * file currently fits in an inode.
 	 */
-	if (tp->t_firstblock == NULLFSBLOCK) {
-		args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
-		args.type = XFS_ALLOCTYPE_START_BNO;
-	} else {
-		args.fsbno = tp->t_firstblock;
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	}
 	args.total = total;
 	args.minlen = args.maxlen = args.prod = 1;
-	error = xfs_alloc_vextent(&args);
+	error = xfs_alloc_vextent_start_ag(&args,
+			XFS_INO_TO_FSB(args.mp, ip->i_ino));
 	if (error)
 		goto done;
 
 	/* Can't fail, the space was reserved. */
 	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(args.len == 1);
-	tp->t_firstblock = args.fsbno;
 	error = xfs_trans_get_buf(tp, args.mp->m_ddev_targp,
 			XFS_FSB_TO_DADDR(args.mp, args.fsbno),
 			args.mp->m_bsize, 0, &bp);
@@ -854,8 +839,7 @@ xfs_bmap_local_to_extents(
 
 	ifp->if_nextents = 1;
 	ip->i_nblocks = 1;
-	xfs_trans_mod_dquot_byino(tp, ip,
-		XFS_TRANS_DQ_BCOUNT, 1L);
+	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
 	flags |= xfs_ilog_fext(whichfork);
 
 done:
@@ -3025,9 +3009,7 @@ xfs_bmap_adjacent(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
 {
 	xfs_fsblock_t	adjust;		/* adjustment to block numbers */
-	xfs_agnumber_t	fb_agno;	/* ag number of ap->firstblock */
 	xfs_mount_t	*mp;		/* mount point structure */
-	int		nullfb;		/* true if ap->firstblock isn't set */
 	int		rt;		/* true if inode is realtime */
 
 #define	ISVALID(x,y)	\
@@ -3038,11 +3020,8 @@ xfs_bmap_adjacent(
 		XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks)
 
 	mp = ap->ip->i_mount;
-	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
 	rt = XFS_IS_REALTIME_INODE(ap->ip) &&
 		(ap->datatype & XFS_ALLOC_USERDATA);
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
-							ap->tp->t_firstblock);
 	/*
 	 * If allocating at eof, and there's a previous real block,
 	 * try to use its last block as our starting point.
@@ -3101,13 +3080,6 @@ xfs_bmap_adjacent(
 				prevbno += adjust;
 			else
 				prevdiff += adjust;
-			/*
-			 * If the firstblock forbids it, can't use it,
-			 * must use default.
-			 */
-			if (!rt && !nullfb &&
-			    XFS_FSB_TO_AGNO(mp, prevbno) != fb_agno)
-				prevbno = NULLFSBLOCK;
 		}
 		/*
 		 * No previous block or can't follow it, just default.
@@ -3143,13 +3115,6 @@ xfs_bmap_adjacent(
 				gotdiff += adjust - ap->length;
 			} else
 				gotdiff += adjust;
-			/*
-			 * If the firstblock forbids it, can't use it,
-			 * must use default.
-			 */
-			if (!rt && !nullfb &&
-			    XFS_FSB_TO_AGNO(mp, gotbno) != fb_agno)
-				gotbno = NULLFSBLOCK;
 		}
 		/*
 		 * No next block, just default.
@@ -3170,147 +3135,91 @@ xfs_bmap_adjacent(
 #undef ISVALID
 }
 
-static int
+int
 xfs_bmap_longest_free_extent(
+	struct xfs_perag	*pag,
 	struct xfs_trans	*tp,
-	xfs_agnumber_t		ag,
-	xfs_extlen_t		*blen,
-	int			*notinit)
+	xfs_extlen_t		*blen)
 {
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_perag	*pag;
 	xfs_extlen_t		longest;
 	int			error = 0;
 
-	pag = xfs_perag_get(mp, ag);
-	if (!pag->pagf_init) {
+	if (!xfs_perag_initialised_agf(pag)) {
 		error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_TRYLOCK,
 				NULL);
-		if (error) {
-			/* Couldn't lock the AGF, so skip this AG. */
-			if (error == -EAGAIN) {
-				*notinit = 1;
-				error = 0;
-			}
-			goto out;
-		}
+		if (error)
+			return error;
 	}
 
 	longest = xfs_alloc_longest_free_extent(pag,
-				xfs_alloc_min_freelist(mp, pag),
+				xfs_alloc_min_freelist(pag->pag_mount, pag),
 				xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE));
 	if (*blen < longest)
 		*blen = longest;
 
-out:
-	xfs_perag_put(pag);
-	return error;
+	return 0;
 }
 
-static void
+static xfs_extlen_t
 xfs_bmap_select_minlen(
 	struct xfs_bmalloca	*ap,
 	struct xfs_alloc_arg	*args,
-	xfs_extlen_t		*blen,
-	int			notinit)
+	xfs_extlen_t		blen)
 {
-	if (notinit || *blen < ap->minlen) {
-		/*
-		 * Since we did a BUF_TRYLOCK above, it is possible that
-		 * there is space for this request.
-		 */
-		args->minlen = ap->minlen;
-	} else if (*blen < args->maxlen) {
-		/*
-		 * If the best seen length is less than the request length,
-		 * use the best as the minimum.
-		 */
-		args->minlen = *blen;
-	} else {
-		/*
-		 * Otherwise we've seen an extent as big as maxlen, use that
-		 * as the minimum.
-		 */
-		args->minlen = args->maxlen;
-	}
-}
-
-STATIC int
-xfs_bmap_btalloc_nullfb(
-	struct xfs_bmalloca	*ap,
-	struct xfs_alloc_arg	*args,
-	xfs_extlen_t		*blen)
-{
-	struct xfs_mount	*mp = ap->ip->i_mount;
-	xfs_agnumber_t		ag, startag;
-	int			notinit = 0;
-	int			error;
 
-	args->type = XFS_ALLOCTYPE_START_BNO;
-	args->total = ap->total;
-
-	startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
-	if (startag == NULLAGNUMBER)
-		startag = ag = 0;
-
-	while (*blen < args->maxlen) {
-		error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
-						     &notinit);
-		if (error)
-			return error;
-
-		if (++ag == mp->m_sb.sb_agcount)
-			ag = 0;
-		if (ag == startag)
-			break;
-	}
+	/*
+	 * Since we used XFS_ALLOC_FLAG_TRYLOCK in _longest_free_extent(), it is
+	 * possible that there is enough contiguous free space for this request.
+	 */
+	if (blen < ap->minlen)
+		return ap->minlen;
 
-	xfs_bmap_select_minlen(ap, args, blen, notinit);
-	return 0;
+	/*
+	 * If the best seen length is less than the request length,
+	 * use the best as the minimum, otherwise we've got the maxlen we
+	 * were asked for.
+	 */
+	if (blen < args->maxlen)
+		return blen;
+	return args->maxlen;
 }
 
-STATIC int
-xfs_bmap_btalloc_filestreams(
+static int
+xfs_bmap_btalloc_select_lengths(
 	struct xfs_bmalloca	*ap,
 	struct xfs_alloc_arg	*args,
 	xfs_extlen_t		*blen)
 {
-	struct xfs_mount	*mp = ap->ip->i_mount;
-	xfs_agnumber_t		ag;
-	int			notinit = 0;
-	int			error;
-
-	args->type = XFS_ALLOCTYPE_NEAR_BNO;
-	args->total = ap->total;
-
-	ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
-	if (ag == NULLAGNUMBER)
-		ag = 0;
-
-	error = xfs_bmap_longest_free_extent(args->tp, ag, blen, &notinit);
-	if (error)
-		return error;
+	struct xfs_mount	*mp = args->mp;
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno, startag;
+	int			error = 0;
 
-	if (*blen < args->maxlen) {
-		error = xfs_filestream_new_ag(ap, &ag);
-		if (error)
-			return error;
+	if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
+		args->total = ap->minlen;
+		args->minlen = ap->minlen;
+		return 0;
+	}
 
-		error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
-						     &notinit);
-		if (error)
-			return error;
+	args->total = ap->total;
+	startag = XFS_FSB_TO_AGNO(mp, ap->blkno);
+	if (startag == NULLAGNUMBER)
+		startag = 0;
 
+	*blen = 0;
+	for_each_perag_wrap(mp, startag, agno, pag) {
+		error = xfs_bmap_longest_free_extent(pag, args->tp, blen);
+		if (error && error != -EAGAIN)
+			break;
+		error = 0;
+		if (*blen >= args->maxlen)
+			break;
 	}
+	if (pag)
+		xfs_perag_rele(pag);
 
-	xfs_bmap_select_minlen(ap, args, blen, notinit);
-
-	/*
-	 * Set the failure fallback case to look in the selected AG as stream
-	 * may have moved.
-	 */
-	ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
-	return 0;
+	args->minlen = xfs_bmap_select_minlen(ap, args, *blen);
+	return error;
 }
 
 /* Update all inode and quota accounting for the allocation we just did. */
@@ -3413,21 +3322,7 @@ xfs_bmap_process_allocated_extent(
 	xfs_fileoff_t		orig_offset,
 	xfs_extlen_t		orig_length)
 {
-	int			nullfb;
-
-	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
-
-	/*
-	 * check the allocation happened at the same or higher AG than
-	 * the first block that was allocated.
-	 */
-	ASSERT(nullfb ||
-		XFS_FSB_TO_AGNO(args->mp, ap->tp->t_firstblock) <=
-		XFS_FSB_TO_AGNO(args->mp, args->fsbno));
-
 	ap->blkno = args->fsbno;
-	if (nullfb)
-		ap->tp->t_firstblock = args->fsbno;
 	ap->length = args->len;
 	/*
 	 * If the extent size hint is active, we tried to round the
@@ -3474,23 +3369,17 @@ xfs_bmap_exact_minlen_extent_alloc(
 
 	xfs_bmap_compute_alignments(ap, &args);
 
-	if (ap->tp->t_firstblock == NULLFSBLOCK) {
-		/*
-		 * Unlike the longest extent available in an AG, we don't track
-		 * the length of an AG's shortest extent.
-		 * XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is a debug only knob and
-		 * hence we can afford to start traversing from the 0th AG since
-		 * we need not be concerned about a drop in performance in
-		 * "debug only" code paths.
-		 */
-		ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0);
-	} else {
-		ap->blkno = ap->tp->t_firstblock;
-	}
+	/*
+	 * Unlike the longest extent available in an AG, we don't track
+	 * the length of an AG's shortest extent.
+	 * XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is a debug only knob and
+	 * hence we can afford to start traversing from the 0th AG since
+	 * we need not be concerned about a drop in performance in
+	 * "debug only" code paths.
+	 */
+	ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0);
 
-	args.fsbno = ap->blkno;
 	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
-	args.type = XFS_ALLOCTYPE_FIRST_AG;
 	args.minlen = args.maxlen = ap->minlen;
 	args.total = ap->total;
 
@@ -3502,7 +3391,7 @@ xfs_bmap_exact_minlen_extent_alloc(
 	args.resv = XFS_AG_RESV_NONE;
 	args.datatype = ap->datatype;
 
-	error = xfs_alloc_vextent(&args);
+	error = xfs_alloc_vextent_first_ag(&args, ap->blkno);
 	if (error)
 		return error;
 
@@ -3522,193 +3411,270 @@ xfs_bmap_exact_minlen_extent_alloc(
 
 #endif
 
-STATIC int
-xfs_bmap_btalloc(
-	struct xfs_bmalloca	*ap)
+/*
+ * If we are not low on available data blocks and we are allocating at
+ * EOF, optimise allocation for contiguous file extension and/or stripe
+ * alignment of the new extent.
+ *
+ * NOTE: ap->aeof is only set if the allocation length is >= the
+ * stripe unit and the allocation offset is at the end of file.
+ */
+static int
+xfs_bmap_btalloc_at_eof(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_extlen_t		blen,
+	int			stripe_align,
+	bool			ag_only)
 {
-	struct xfs_mount	*mp = ap->ip->i_mount;
-	struct xfs_alloc_arg	args = { .tp = ap->tp, .mp = mp };
-	xfs_alloctype_t		atype = 0;
-	xfs_agnumber_t		fb_agno;	/* ag number of ap->firstblock */
-	xfs_agnumber_t		ag;
-	xfs_fileoff_t		orig_offset;
-	xfs_extlen_t		orig_length;
-	xfs_extlen_t		blen;
-	xfs_extlen_t		nextminlen = 0;
-	int			nullfb; /* true if ap->firstblock isn't set */
-	int			isaligned;
-	int			tryagain;
+	struct xfs_mount	*mp = args->mp;
+	struct xfs_perag	*caller_pag = args->pag;
 	int			error;
-	int			stripe_align;
-
-	ASSERT(ap->length);
-	orig_offset = ap->offset;
-	orig_length = ap->length;
-
-	stripe_align = xfs_bmap_compute_alignments(ap, &args);
-
-	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
-							ap->tp->t_firstblock);
-	if (nullfb) {
-		if ((ap->datatype & XFS_ALLOC_USERDATA) &&
-		    xfs_inode_is_filestream(ap->ip)) {
-			ag = xfs_filestream_lookup_ag(ap->ip);
-			ag = (ag != NULLAGNUMBER) ? ag : 0;
-			ap->blkno = XFS_AGB_TO_FSB(mp, ag, 0);
-		} else {
-			ap->blkno = XFS_INO_TO_FSB(mp, ap->ip->i_ino);
-		}
-	} else
-		ap->blkno = ap->tp->t_firstblock;
 
-	xfs_bmap_adjacent(ap);
-
-	/*
-	 * If allowed, use ap->blkno; otherwise must use firstblock since
-	 * it's in the right allocation group.
-	 */
-	if (nullfb || XFS_FSB_TO_AGNO(mp, ap->blkno) == fb_agno)
-		;
-	else
-		ap->blkno = ap->tp->t_firstblock;
 	/*
-	 * Normal allocation, done through xfs_alloc_vextent.
+	 * If there are already extents in the file, try an exact EOF block
+	 * allocation to extend the file as a contiguous extent. If that fails,
+	 * or it's the first allocation in a file, just try for a stripe aligned
+	 * allocation.
 	 */
-	tryagain = isaligned = 0;
-	args.fsbno = ap->blkno;
-	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
+	if (ap->offset) {
+		xfs_extlen_t	nextminlen = 0;
 
-	/* Trim the allocation back to the maximum an AG can fit. */
-	args.maxlen = min(ap->length, mp->m_ag_max_usable);
-	blen = 0;
-	if (nullfb) {
 		/*
-		 * Search for an allocation group with a single extent large
-		 * enough for the request.  If one isn't found, then adjust
-		 * the minimum allocation size to the largest space found.
+		 * Compute the minlen+alignment for the next case.  Set slop so
+		 * that the value of minlen+alignment+slop doesn't go up between
+		 * the calls.
 		 */
-		if ((ap->datatype & XFS_ALLOC_USERDATA) &&
-		    xfs_inode_is_filestream(ap->ip))
-			error = xfs_bmap_btalloc_filestreams(ap, &args, &blen);
+		args->alignment = 1;
+		if (blen > stripe_align && blen <= args->maxlen)
+			nextminlen = blen - stripe_align;
+		else
+			nextminlen = args->minlen;
+		if (nextminlen + stripe_align > args->minlen + 1)
+			args->minalignslop = nextminlen + stripe_align -
+					args->minlen - 1;
 		else
-			error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
+			args->minalignslop = 0;
+
+		if (!caller_pag)
+			args->pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ap->blkno));
+		error = xfs_alloc_vextent_exact_bno(args, ap->blkno);
+		if (!caller_pag)
+			xfs_perag_put(args->pag);
 		if (error)
 			return error;
-	} else if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
-		if (xfs_inode_is_filestream(ap->ip))
-			args.type = XFS_ALLOCTYPE_FIRST_AG;
-		else
-			args.type = XFS_ALLOCTYPE_START_BNO;
-		args.total = args.minlen = ap->minlen;
+
+		if (args->fsbno != NULLFSBLOCK)
+			return 0;
+		/*
+		 * Exact allocation failed. Reset to try an aligned allocation
+		 * according to the original allocation specification.
+		 */
+		args->pag = NULL;
+		args->alignment = stripe_align;
+		args->minlen = nextminlen;
+		args->minalignslop = 0;
 	} else {
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		args.total = ap->total;
-		args.minlen = ap->minlen;
+		/*
+		 * Adjust minlen to try and preserve alignment if we
+		 * can't guarantee an aligned maxlen extent.
+		 */
+		args->alignment = stripe_align;
+		if (blen > args->alignment &&
+		    blen <= args->maxlen + args->alignment)
+			args->minlen = blen - args->alignment;
+		args->minalignslop = 0;
 	}
 
-	/*
-	 * If we are not low on available data blocks, and the underlying
-	 * logical volume manager is a stripe, and the file offset is zero then
-	 * try to allocate data blocks on stripe unit boundary. NOTE: ap->aeof
-	 * is only set if the allocation length is >= the stripe unit and the
-	 * allocation offset is at the end of file.
-	 */
-	if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) {
-		if (!ap->offset) {
-			args.alignment = stripe_align;
-			atype = args.type;
-			isaligned = 1;
-			/*
-			 * Adjust minlen to try and preserve alignment if we
-			 * can't guarantee an aligned maxlen extent.
-			 */
-			if (blen > args.alignment &&
-			    blen <= args.maxlen + args.alignment)
-				args.minlen = blen - args.alignment;
-			args.minalignslop = 0;
-		} else {
-			/*
-			 * First try an exact bno allocation.
-			 * If it fails then do a near or start bno
-			 * allocation with alignment turned on.
-			 */
-			atype = args.type;
-			tryagain = 1;
-			args.type = XFS_ALLOCTYPE_THIS_BNO;
-			args.alignment = 1;
-			/*
-			 * Compute the minlen+alignment for the
-			 * next case.  Set slop so that the value
-			 * of minlen+alignment+slop doesn't go up
-			 * between the calls.
-			 */
-			if (blen > stripe_align && blen <= args.maxlen)
-				nextminlen = blen - stripe_align;
-			else
-				nextminlen = args.minlen;
-			if (nextminlen + stripe_align > args.minlen + 1)
-				args.minalignslop =
-					nextminlen + stripe_align -
-					args.minlen - 1;
-			else
-				args.minalignslop = 0;
-		}
+	if (ag_only) {
+		error = xfs_alloc_vextent_near_bno(args, ap->blkno);
 	} else {
-		args.alignment = 1;
-		args.minalignslop = 0;
+		args->pag = NULL;
+		error = xfs_alloc_vextent_start_ag(args, ap->blkno);
+		ASSERT(args->pag == NULL);
+		args->pag = caller_pag;
 	}
-	args.minleft = ap->minleft;
-	args.wasdel = ap->wasdel;
-	args.resv = XFS_AG_RESV_NONE;
-	args.datatype = ap->datatype;
-
-	error = xfs_alloc_vextent(&args);
 	if (error)
 		return error;
 
-	if (tryagain && args.fsbno == NULLFSBLOCK) {
-		/*
-		 * Exact allocation failed. Now try with alignment
-		 * turned on.
-		 */
-		args.type = atype;
-		args.fsbno = ap->blkno;
-		args.alignment = stripe_align;
-		args.minlen = nextminlen;
-		args.minalignslop = 0;
-		isaligned = 1;
-		if ((error = xfs_alloc_vextent(&args)))
-			return error;
-	}
-	if (isaligned && args.fsbno == NULLFSBLOCK) {
-		/*
-		 * allocation failed, so turn off alignment and
-		 * try again.
-		 */
-		args.type = atype;
-		args.fsbno = ap->blkno;
-		args.alignment = 0;
-		if ((error = xfs_alloc_vextent(&args)))
+	if (args->fsbno != NULLFSBLOCK)
+		return 0;
+
+	/*
+	 * Allocation failed, so turn return the allocation args to their
+	 * original non-aligned state so the caller can proceed on allocation
+	 * failure as if this function was never called.
+	 */
+	args->fsbno = ap->blkno;
+	args->alignment = 1;
+	return 0;
+}
+
+/*
+ * We have failed multiple allocation attempts so now are in a low space
+ * allocation situation. Try a locality first full filesystem minimum length
+ * allocation whilst still maintaining necessary total block reservation
+ * requirements.
+ *
+ * If that fails, we are now critically low on space, so perform a last resort
+ * allocation attempt: no reserve, no locality, blocking, minimum length, full
+ * filesystem free space scan. We also indicate to future allocations in this
+ * transaction that we are critically low on space so they don't waste time on
+ * allocation modes that are unlikely to succeed.
+ */
+int
+xfs_bmap_btalloc_low_space(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args)
+{
+	int			error;
+
+	if (args->minlen > ap->minlen) {
+		args->minlen = ap->minlen;
+		error = xfs_alloc_vextent_start_ag(args, ap->blkno);
+		if (error || args->fsbno != NULLFSBLOCK)
 			return error;
 	}
-	if (args.fsbno == NULLFSBLOCK && nullfb &&
-	    args.minlen > ap->minlen) {
-		args.minlen = ap->minlen;
-		args.type = XFS_ALLOCTYPE_START_BNO;
-		args.fsbno = ap->blkno;
-		if ((error = xfs_alloc_vextent(&args)))
-			return error;
+
+	/* Last ditch attempt before failure is declared. */
+	args->total = ap->minlen;
+	error = xfs_alloc_vextent_first_ag(args, 0);
+	if (error)
+		return error;
+	ap->tp->t_flags |= XFS_TRANS_LOWMODE;
+	return 0;
+}
+
+static int
+xfs_bmap_btalloc_filestreams(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	int			stripe_align)
+{
+	xfs_extlen_t		blen = 0;
+	int			error = 0;
+
+
+	error = xfs_filestream_select_ag(ap, args, &blen);
+	if (error)
+		return error;
+	ASSERT(args->pag);
+
+	/*
+	 * If we are in low space mode, then optimal allocation will fail so
+	 * prepare for minimal allocation and jump to the low space algorithm
+	 * immediately.
+	 */
+	if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
+		args->minlen = ap->minlen;
+		ASSERT(args->fsbno == NULLFSBLOCK);
+		goto out_low_space;
 	}
-	if (args.fsbno == NULLFSBLOCK && nullfb) {
-		args.fsbno = 0;
-		args.type = XFS_ALLOCTYPE_FIRST_AG;
-		args.total = ap->minlen;
-		if ((error = xfs_alloc_vextent(&args)))
+
+	args->minlen = xfs_bmap_select_minlen(ap, args, blen);
+	if (ap->aeof)
+		error = xfs_bmap_btalloc_at_eof(ap, args, blen, stripe_align,
+				true);
+
+	if (!error && args->fsbno == NULLFSBLOCK)
+		error = xfs_alloc_vextent_near_bno(args, ap->blkno);
+
+out_low_space:
+	/*
+	 * We are now done with the perag reference for the filestreams
+	 * association provided by xfs_filestream_select_ag(). Release it now as
+	 * we've either succeeded, had a fatal error or we are out of space and
+	 * need to do a full filesystem scan for free space which will take it's
+	 * own references.
+	 */
+	xfs_perag_rele(args->pag);
+	args->pag = NULL;
+	if (error || args->fsbno != NULLFSBLOCK)
+		return error;
+
+	return xfs_bmap_btalloc_low_space(ap, args);
+}
+
+static int
+xfs_bmap_btalloc_best_length(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	int			stripe_align)
+{
+	xfs_extlen_t		blen = 0;
+	int			error;
+
+	ap->blkno = XFS_INO_TO_FSB(args->mp, ap->ip->i_ino);
+	xfs_bmap_adjacent(ap);
+
+	/*
+	 * Search for an allocation group with a single extent large enough for
+	 * the request.  If one isn't found, then adjust the minimum allocation
+	 * size to the largest space found.
+	 */
+	error = xfs_bmap_btalloc_select_lengths(ap, args, &blen);
+	if (error)
+		return error;
+
+	/*
+	 * Don't attempt optimal EOF allocation if previous allocations barely
+	 * succeeded due to being near ENOSPC. It is highly unlikely we'll get
+	 * optimal or even aligned allocations in this case, so don't waste time
+	 * trying.
+	 */
+	if (ap->aeof && !(ap->tp->t_flags & XFS_TRANS_LOWMODE)) {
+		error = xfs_bmap_btalloc_at_eof(ap, args, blen, stripe_align,
+				false);
+		if (error || args->fsbno != NULLFSBLOCK)
 			return error;
-		ap->tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 
+	error = xfs_alloc_vextent_start_ag(args, ap->blkno);
+	if (error || args->fsbno != NULLFSBLOCK)
+		return error;
+
+	return xfs_bmap_btalloc_low_space(ap, args);
+}
+
+static int
+xfs_bmap_btalloc(
+	struct xfs_bmalloca	*ap)
+{
+	struct xfs_mount	*mp = ap->ip->i_mount;
+	struct xfs_alloc_arg	args = {
+		.tp		= ap->tp,
+		.mp		= mp,
+		.fsbno		= NULLFSBLOCK,
+		.oinfo		= XFS_RMAP_OINFO_SKIP_UPDATE,
+		.minleft	= ap->minleft,
+		.wasdel		= ap->wasdel,
+		.resv		= XFS_AG_RESV_NONE,
+		.datatype	= ap->datatype,
+		.alignment	= 1,
+		.minalignslop	= 0,
+	};
+	xfs_fileoff_t		orig_offset;
+	xfs_extlen_t		orig_length;
+	int			error;
+	int			stripe_align;
+
+	ASSERT(ap->length);
+	orig_offset = ap->offset;
+	orig_length = ap->length;
+
+	stripe_align = xfs_bmap_compute_alignments(ap, &args);
+
+	/* Trim the allocation back to the maximum an AG can fit. */
+	args.maxlen = min(ap->length, mp->m_ag_max_usable);
+
+	if ((ap->datatype & XFS_ALLOC_USERDATA) &&
+	    xfs_inode_is_filestream(ap->ip))
+		error = xfs_bmap_btalloc_filestreams(ap, &args, stripe_align);
+	else
+		error = xfs_bmap_btalloc_best_length(ap, &args, stripe_align);
+	if (error)
+		return error;
+
 	if (args.fsbno != NULLFSBLOCK) {
 		xfs_bmap_process_allocated_extent(ap, &args, orig_offset,
 			orig_length);
@@ -4256,7 +4222,7 @@ xfs_bmapi_convert_unwritten(
 	return 0;
 }
 
-static inline xfs_extlen_t
+xfs_extlen_t
 xfs_bmapi_minleft(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
@@ -4264,7 +4230,7 @@ xfs_bmapi_minleft(
 {
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, fork);
 
-	if (tp && tp->t_firstblock != NULLFSBLOCK)
+	if (tp && tp->t_highest_agno != NULLAGNUMBER)
 		return 0;
 	if (ifp->if_format != XFS_DINODE_FMT_BTREE)
 		return 1;
@@ -6151,7 +6117,7 @@ xfs_bmap_finish_one(
 	struct xfs_bmbt_irec		*bmap = &bi->bi_bmap;
 	int				error = 0;
 
-	ASSERT(tp->t_firstblock == NULLFSBLOCK);
+	ASSERT(tp->t_highest_agno == NULLAGNUMBER);
 
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 01c2df35c3e3..dd08361ca5a6 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -12,6 +12,7 @@ struct xfs_ifork;
 struct xfs_inode;
 struct xfs_mount;
 struct xfs_trans;
+struct xfs_alloc_arg;
 
 /*
  * Argument structure for xfs_bmap_alloc.
@@ -168,6 +169,8 @@ static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec)
 #define xfs_valid_startblock(ip, startblock) \
 	((startblock) != 0 || XFS_IS_REALTIME_INODE(ip))
 
+int	xfs_bmap_longest_free_extent(struct xfs_perag *pag,
+		struct xfs_trans *tp, xfs_extlen_t *blen);
 void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 		xfs_filblks_t len);
 unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
@@ -220,6 +223,10 @@ int	xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *icur, struct xfs_btree_cur **curp,
 		struct xfs_bmbt_irec *new, int *logflagsp);
+xfs_extlen_t xfs_bmapi_minleft(struct xfs_trans *tp, struct xfs_inode *ip,
+		int fork);
+int	xfs_bmap_btalloc_low_space(struct xfs_bmalloca *ap,
+		struct xfs_alloc_arg *args);
 
 enum xfs_bmap_intent_type {
 	XFS_BMAP_MAP = 1,
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index cfa052d40105..b8ad95050c9b 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -21,6 +21,7 @@
 #include "xfs_quota.h"
 #include "xfs_trace.h"
 #include "xfs_rmap.h"
+#include "xfs_ag.h"
 
 static struct kmem_cache	*xfs_bmbt_cur_cache;
 
@@ -184,11 +185,11 @@ xfs_bmbt_update_cursor(
 	struct xfs_btree_cur	*src,
 	struct xfs_btree_cur	*dst)
 {
-	ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) ||
+	ASSERT((dst->bc_tp->t_highest_agno != NULLAGNUMBER) ||
 	       (dst->bc_ino.ip->i_diflags & XFS_DIFLAG_REALTIME));
 
 	dst->bc_ino.allocated += src->bc_ino.allocated;
-	dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock;
+	dst->bc_tp->t_highest_agno = src->bc_tp->t_highest_agno;
 
 	src->bc_ino.allocated = 0;
 }
@@ -200,46 +201,32 @@ xfs_bmbt_alloc_block(
 	union xfs_btree_ptr		*new,
 	int				*stat)
 {
-	xfs_alloc_arg_t		args;		/* block allocation args */
-	int			error;		/* error return value */
+	struct xfs_alloc_arg	args;
+	int			error;
 
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
-	args.fsbno = cur->bc_tp->t_firstblock;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_ino.ip->i_ino,
 			cur->bc_ino.whichfork);
-
-	if (args.fsbno == NULLFSBLOCK) {
-		args.fsbno = be64_to_cpu(start->l);
-		args.type = XFS_ALLOCTYPE_START_BNO;
-		/*
-		 * Make sure there is sufficient room left in the AG to
-		 * complete a full tree split for an extent insert.  If
-		 * we are converting the middle part of an extent then
-		 * we may need space for two tree splits.
-		 *
-		 * We are relying on the caller to make the correct block
-		 * reservation for this operation to succeed.  If the
-		 * reservation amount is insufficient then we may fail a
-		 * block allocation here and corrupt the filesystem.
-		 */
-		args.minleft = args.tp->t_blk_res;
-	} else if (cur->bc_tp->t_flags & XFS_TRANS_LOWMODE) {
-		args.type = XFS_ALLOCTYPE_START_BNO;
-	} else {
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	}
-
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL;
-	if (!args.wasdel && args.tp->t_blk_res == 0) {
-		error = -ENOSPC;
-		goto error0;
-	}
-	error = xfs_alloc_vextent(&args);
+	if (!args.wasdel && args.tp->t_blk_res == 0)
+		return -ENOSPC;
+
+	/*
+	 * If we are coming here from something like unwritten extent
+	 * conversion, there has been no data extent allocation already done, so
+	 * we have to ensure that we attempt to locate the entire set of bmbt
+	 * allocations in the same AG, as xfs_bmapi_write() would have reserved.
+	 */
+	if (cur->bc_tp->t_highest_agno == NULLAGNUMBER)
+		args.minleft = xfs_bmapi_minleft(cur->bc_tp, cur->bc_ino.ip,
+					cur->bc_ino.whichfork);
+
+	error = xfs_alloc_vextent_start_ag(&args, be64_to_cpu(start->l));
 	if (error)
-		goto error0;
+		return error;
 
 	if (args.fsbno == NULLFSBLOCK && args.minleft) {
 		/*
@@ -247,11 +234,10 @@ xfs_bmbt_alloc_block(
 		 * a full btree split.  Try again and if
 		 * successful activate the lowspace algorithm.
 		 */
-		args.fsbno = 0;
-		args.type = XFS_ALLOCTYPE_FIRST_AG;
-		error = xfs_alloc_vextent(&args);
+		args.minleft = 0;
+		error = xfs_alloc_vextent_start_ag(&args, 0);
 		if (error)
-			goto error0;
+			return error;
 		cur->bc_tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
@@ -260,7 +246,6 @@ xfs_bmbt_alloc_block(
 	}
 
 	ASSERT(args.len == 1);
-	cur->bc_tp->t_firstblock = args.fsbno;
 	cur->bc_ino.allocated++;
 	cur->bc_ino.ip->i_nblocks++;
 	xfs_trans_log_inode(args.tp, cur->bc_ino.ip, XFS_ILOG_CORE);
@@ -271,9 +256,6 @@ xfs_bmbt_alloc_block(
 
 	*stat = 1;
 	return 0;
-
- error0:
-	return error;
 }
 
 STATIC int
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index da8c769887fd..c4649cc624e1 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2943,7 +2943,7 @@ xfs_btree_split(
 	DECLARE_COMPLETION_ONSTACK(done);
 
 	if (cur->bc_btnum != XFS_BTNUM_BMAP ||
-	    cur->bc_tp->t_firstblock == NULLFSBLOCK)
+	    cur->bc_tp->t_highest_agno == NULLAGNUMBER)
 		return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
 
 	args.cur = cur;
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 5118dedf9267..82ea6aa5af10 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -169,10 +169,9 @@ xfs_inobt_insert_rec(
  */
 STATIC int
 xfs_inobt_insert(
-	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
-	struct xfs_perag	*pag,
 	xfs_agino_t		newino,
 	xfs_agino_t		newlen,
 	xfs_btnum_t		btnum)
@@ -182,7 +181,7 @@ xfs_inobt_insert(
 	int			i;
 	int			error;
 
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, btnum);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp, btnum);
 
 	for (thisino = newino;
 	     thisino < newino + newlen;
@@ -514,20 +513,20 @@ __xfs_inobt_rec_merge(
  */
 STATIC int
 xfs_inobt_insert_sprec(
-	struct xfs_mount		*mp,
+	struct xfs_perag		*pag,
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
-	struct xfs_perag		*pag,
 	int				btnum,
 	struct xfs_inobt_rec_incore	*nrec,	/* in/out: new/merged rec. */
 	bool				merge)	/* merge or replace */
 {
+	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_btree_cur		*cur;
 	int				error;
 	int				i;
 	struct xfs_inobt_rec_incore	rec;
 
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, btnum);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp, btnum);
 
 	/* the new record is pre-aligned so we know where to look */
 	error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i);
@@ -609,9 +608,9 @@ error:
  */
 STATIC int
 xfs_ialloc_ag_alloc(
+	struct xfs_perag	*pag,
 	struct xfs_trans	*tp,
-	struct xfs_buf		*agbp,
-	struct xfs_perag	*pag)
+	struct xfs_buf		*agbp)
 {
 	struct xfs_agi		*agi;
 	struct xfs_alloc_arg	args;
@@ -631,6 +630,7 @@ xfs_ialloc_ag_alloc(
 	args.mp = tp->t_mountp;
 	args.fsbno = NULLFSBLOCK;
 	args.oinfo = XFS_RMAP_OINFO_INODES;
+	args.pag = pag;
 
 #ifdef DEBUG
 	/* randomly do sparse inode allocations */
@@ -662,8 +662,6 @@ xfs_ialloc_ag_alloc(
 		goto sparse_alloc;
 	if (likely(newino != NULLAGINO &&
 		  (args.agbno < be32_to_cpu(agi->agi_length)))) {
-		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
-		args.type = XFS_ALLOCTYPE_THIS_BNO;
 		args.prod = 1;
 
 		/*
@@ -684,7 +682,10 @@ xfs_ialloc_ag_alloc(
 
 		/* Allow space for the inode btree to split. */
 		args.minleft = igeo->inobt_maxlevels;
-		if ((error = xfs_alloc_vextent(&args)))
+		error = xfs_alloc_vextent_exact_bno(&args,
+				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
+						args.agbno));
+		if (error)
 			return error;
 
 		/*
@@ -717,22 +718,17 @@ xfs_ialloc_ag_alloc(
 		} else
 			args.alignment = igeo->cluster_align;
 		/*
-		 * Need to figure out where to allocate the inode blocks.
-		 * Ideally they should be spaced out through the a.g.
-		 * For now, just allocate blocks up front.
-		 */
-		args.agbno = be32_to_cpu(agi->agi_root);
-		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
-		/*
 		 * Allocate a fixed-size extent of inodes.
 		 */
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
 		args.prod = 1;
 		/*
 		 * Allow space for the inode btree to split.
 		 */
 		args.minleft = igeo->inobt_maxlevels;
-		if ((error = xfs_alloc_vextent(&args)))
+		error = xfs_alloc_vextent_near_bno(&args,
+				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
+						be32_to_cpu(agi->agi_root)));
+		if (error)
 			return error;
 	}
 
@@ -741,11 +737,11 @@ xfs_ialloc_ag_alloc(
 	 * alignment.
 	 */
 	if (isaligned && args.fsbno == NULLFSBLOCK) {
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		args.agbno = be32_to_cpu(agi->agi_root);
-		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
 		args.alignment = igeo->cluster_align;
-		if ((error = xfs_alloc_vextent(&args)))
+		error = xfs_alloc_vextent_near_bno(&args,
+				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
+						be32_to_cpu(agi->agi_root)));
+		if (error)
 			return error;
 	}
 
@@ -757,9 +753,6 @@ xfs_ialloc_ag_alloc(
 	    igeo->ialloc_min_blks < igeo->ialloc_blks &&
 	    args.fsbno == NULLFSBLOCK) {
 sparse_alloc:
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		args.agbno = be32_to_cpu(agi->agi_root);
-		args.fsbno = XFS_AGB_TO_FSB(args.mp, pag->pag_agno, args.agbno);
 		args.alignment = args.mp->m_sb.sb_spino_align;
 		args.prod = 1;
 
@@ -781,7 +774,9 @@ sparse_alloc:
 					    args.mp->m_sb.sb_inoalignmt) -
 				 igeo->ialloc_blks;
 
-		error = xfs_alloc_vextent(&args);
+		error = xfs_alloc_vextent_near_bno(&args,
+				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
+						be32_to_cpu(agi->agi_root)));
 		if (error)
 			return error;
 
@@ -831,7 +826,7 @@ sparse_alloc:
 		 * if necessary. If a merge does occur, rec is updated to the
 		 * merged record.
 		 */
-		error = xfs_inobt_insert_sprec(args.mp, tp, agbp, pag,
+		error = xfs_inobt_insert_sprec(pag, tp, agbp,
 				XFS_BTNUM_INO, &rec, true);
 		if (error == -EFSCORRUPTED) {
 			xfs_alert(args.mp,
@@ -856,20 +851,20 @@ sparse_alloc:
 		 * existing record with this one.
 		 */
 		if (xfs_has_finobt(args.mp)) {
-			error = xfs_inobt_insert_sprec(args.mp, tp, agbp, pag,
+			error = xfs_inobt_insert_sprec(pag, tp, agbp,
 				       XFS_BTNUM_FINO, &rec, false);
 			if (error)
 				return error;
 		}
 	} else {
 		/* full chunk - insert new records to both btrees */
-		error = xfs_inobt_insert(args.mp, tp, agbp, pag, newino, newlen,
+		error = xfs_inobt_insert(pag, tp, agbp, newino, newlen,
 					 XFS_BTNUM_INO);
 		if (error)
 			return error;
 
 		if (xfs_has_finobt(args.mp)) {
-			error = xfs_inobt_insert(args.mp, tp, agbp, pag, newino,
+			error = xfs_inobt_insert(pag, tp, agbp, newino,
 						 newlen, XFS_BTNUM_FINO);
 			if (error)
 				return error;
@@ -981,9 +976,9 @@ xfs_inobt_first_free_inode(
  */
 STATIC int
 xfs_dialloc_ag_inobt(
+	struct xfs_perag	*pag,
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
-	struct xfs_perag	*pag,
 	xfs_ino_t		parent,
 	xfs_ino_t		*inop)
 {
@@ -999,12 +994,12 @@ xfs_dialloc_ag_inobt(
 	int			i, j;
 	int			searchdistance = 10;
 
-	ASSERT(pag->pagi_init);
-	ASSERT(pag->pagi_inodeok);
+	ASSERT(xfs_perag_initialised_agi(pag));
+	ASSERT(xfs_perag_allows_inodes(pag));
 	ASSERT(pag->pagi_freecount > 0);
 
  restart_pagno:
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
 	 * This must work because we've just allocated some.
@@ -1429,9 +1424,9 @@ xfs_dialloc_ag_update_inobt(
  */
 static int
 xfs_dialloc_ag(
+	struct xfs_perag	*pag,
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
-	struct xfs_perag	*pag,
 	xfs_ino_t		parent,
 	xfs_ino_t		*inop)
 {
@@ -1448,7 +1443,7 @@ xfs_dialloc_ag(
 	int				i;
 
 	if (!xfs_has_finobt(mp))
-		return xfs_dialloc_ag_inobt(tp, agbp, pag, parent, inop);
+		return xfs_dialloc_ag_inobt(pag, tp, agbp, parent, inop);
 
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
@@ -1457,7 +1452,7 @@ xfs_dialloc_ag(
 	if (!pagino)
 		pagino = be32_to_cpu(agi->agi_newino);
 
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_FINO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_FINO);
 
 	error = xfs_check_agi_freecount(cur);
 	if (error)
@@ -1500,7 +1495,7 @@ xfs_dialloc_ag(
 	 * the original freecount. If all is well, make the equivalent update to
 	 * the inobt using the finobt record and offset information.
 	 */
-	icur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);
+	icur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
 
 	error = xfs_check_agi_freecount(icur);
 	if (error)
@@ -1577,25 +1572,10 @@ xfs_dialloc_roll(
 	return error;
 }
 
-static xfs_agnumber_t
-xfs_ialloc_next_ag(
-	xfs_mount_t	*mp)
-{
-	xfs_agnumber_t	agno;
-
-	spin_lock(&mp->m_agirotor_lock);
-	agno = mp->m_agirotor;
-	if (++mp->m_agirotor >= mp->m_maxagi)
-		mp->m_agirotor = 0;
-	spin_unlock(&mp->m_agirotor_lock);
-
-	return agno;
-}
-
 static bool
 xfs_dialloc_good_ag(
-	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
 	umode_t			mode,
 	int			flags,
 	bool			ok_alloc)
@@ -1606,10 +1586,12 @@ xfs_dialloc_good_ag(
 	int			needspace;
 	int			error;
 
-	if (!pag->pagi_inodeok)
+	if (!pag)
+		return false;
+	if (!xfs_perag_allows_inodes(pag))
 		return false;
 
-	if (!pag->pagi_init) {
+	if (!xfs_perag_initialised_agi(pag)) {
 		error = xfs_ialloc_read_agi(pag, tp, NULL);
 		if (error)
 			return false;
@@ -1620,7 +1602,7 @@ xfs_dialloc_good_ag(
 	if (!ok_alloc)
 		return false;
 
-	if (!pag->pagf_init) {
+	if (!xfs_perag_initialised_agf(pag)) {
 		error = xfs_alloc_read_agf(pag, tp, flags, NULL);
 		if (error)
 			return false;
@@ -1665,8 +1647,8 @@ xfs_dialloc_good_ag(
 
 static int
 xfs_dialloc_try_ag(
-	struct xfs_trans	**tpp,
 	struct xfs_perag	*pag,
+	struct xfs_trans	**tpp,
 	xfs_ino_t		parent,
 	xfs_ino_t		*new_ino,
 	bool			ok_alloc)
@@ -1689,7 +1671,7 @@ xfs_dialloc_try_ag(
 			goto out_release;
 		}
 
-		error = xfs_ialloc_ag_alloc(*tpp, agbp, pag);
+		error = xfs_ialloc_ag_alloc(pag, *tpp, agbp);
 		if (error < 0)
 			goto out_release;
 
@@ -1705,7 +1687,7 @@ xfs_dialloc_try_ag(
 	}
 
 	/* Allocate an inode in the found AG */
-	error = xfs_dialloc_ag(*tpp, agbp, pag, parent, &ino);
+	error = xfs_dialloc_ag(pag, *tpp, agbp, parent, &ino);
 	if (!error)
 		*new_ino = ino;
 	return error;
@@ -1737,8 +1719,9 @@ xfs_dialloc(
 	struct xfs_perag	*pag;
 	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
 	bool			ok_alloc = true;
+	bool			low_space = false;
 	int			flags;
-	xfs_ino_t		ino;
+	xfs_ino_t		ino = NULLFSINO;
 
 	/*
 	 * Directories, symlinks, and regular files frequently allocate at least
@@ -1746,7 +1729,7 @@ xfs_dialloc(
 	 * an AG has enough space for file creation.
 	 */
 	if (S_ISDIR(mode))
-		start_agno = xfs_ialloc_next_ag(mp);
+		start_agno = atomic_inc_return(&mp->m_agirotor) % mp->m_maxagi;
 	else {
 		start_agno = XFS_INO_TO_AGNO(mp, parent);
 		if (start_agno >= mp->m_maxagi)
@@ -1768,41 +1751,55 @@ xfs_dialloc(
 	}
 
 	/*
+	 * If we are near to ENOSPC, we want to prefer allocation from AGs that
+	 * have free inodes in them rather than use up free space allocating new
+	 * inode chunks. Hence we turn off allocation for the first non-blocking
+	 * pass through the AGs if we are near ENOSPC to consume free inodes
+	 * that we can immediately allocate, but then we allow allocation on the
+	 * second pass if we fail to find an AG with free inodes in it.
+	 */
+	if (percpu_counter_read_positive(&mp->m_fdblocks) <
+			mp->m_low_space[XFS_LOWSP_1_PCNT]) {
+		ok_alloc = false;
+		low_space = true;
+	}
+
+	/*
 	 * Loop until we find an allocation group that either has free inodes
 	 * or in which we can allocate some inodes.  Iterate through the
 	 * allocation groups upward, wrapping at the end.
 	 */
-	agno = start_agno;
 	flags = XFS_ALLOC_FLAG_TRYLOCK;
-	for (;;) {
-		pag = xfs_perag_get(mp, agno);
-		if (xfs_dialloc_good_ag(*tpp, pag, mode, flags, ok_alloc)) {
-			error = xfs_dialloc_try_ag(tpp, pag, parent,
+retry:
+	for_each_perag_wrap_at(mp, start_agno, mp->m_maxagi, agno, pag) {
+		if (xfs_dialloc_good_ag(pag, *tpp, mode, flags, ok_alloc)) {
+			error = xfs_dialloc_try_ag(pag, tpp, parent,
 					&ino, ok_alloc);
 			if (error != -EAGAIN)
 				break;
+			error = 0;
 		}
 
 		if (xfs_is_shutdown(mp)) {
 			error = -EFSCORRUPTED;
 			break;
 		}
-		if (++agno == mp->m_maxagi)
-			agno = 0;
-		if (agno == start_agno) {
-			if (!flags) {
-				error = -ENOSPC;
-				break;
-			}
+	}
+	if (pag)
+		xfs_perag_rele(pag);
+	if (error)
+		return error;
+	if (ino == NULLFSINO) {
+		if (flags) {
 			flags = 0;
+			if (low_space)
+				ok_alloc = true;
+			goto retry;
 		}
-		xfs_perag_put(pag);
+		return -ENOSPC;
 	}
-
-	if (!error)
-		*new_ino = ino;
-	xfs_perag_put(pag);
-	return error;
+	*new_ino = ino;
+	return 0;
 }
 
 /*
@@ -1885,14 +1882,14 @@ next:
 
 STATIC int
 xfs_difree_inobt(
-	struct xfs_mount		*mp,
+	struct xfs_perag		*pag,
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
-	struct xfs_perag		*pag,
 	xfs_agino_t			agino,
 	struct xfs_icluster		*xic,
 	struct xfs_inobt_rec_incore	*orec)
 {
+	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_agi			*agi = agbp->b_addr;
 	struct xfs_btree_cur		*cur;
 	struct xfs_inobt_rec_incore	rec;
@@ -1907,7 +1904,7 @@ xfs_difree_inobt(
 	/*
 	 * Initialize the cursor.
 	 */
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
 
 	error = xfs_check_agi_freecount(cur);
 	if (error)
@@ -2019,20 +2016,20 @@ error0:
  */
 STATIC int
 xfs_difree_finobt(
-	struct xfs_mount		*mp,
+	struct xfs_perag		*pag,
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
-	struct xfs_perag		*pag,
 	xfs_agino_t			agino,
 	struct xfs_inobt_rec_incore	*ibtrec) /* inobt record */
 {
+	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_btree_cur		*cur;
 	struct xfs_inobt_rec_incore	rec;
 	int				offset = agino - ibtrec->ir_startino;
 	int				error;
 	int				i;
 
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_FINO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_FINO);
 
 	error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
 	if (error)
@@ -2179,7 +2176,7 @@ xfs_difree(
 	/*
 	 * Fix up the inode allocation btree.
 	 */
-	error = xfs_difree_inobt(mp, tp, agbp, pag, agino, xic, &rec);
+	error = xfs_difree_inobt(pag, tp, agbp, agino, xic, &rec);
 	if (error)
 		goto error0;
 
@@ -2187,7 +2184,7 @@ xfs_difree(
 	 * Fix up the free inode btree.
 	 */
 	if (xfs_has_finobt(mp)) {
-		error = xfs_difree_finobt(mp, tp, agbp, pag, agino, &rec);
+		error = xfs_difree_finobt(pag, tp, agbp, agino, &rec);
 		if (error)
 			goto error0;
 	}
@@ -2200,15 +2197,15 @@ error0:
 
 STATIC int
 xfs_imap_lookup(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
 	xfs_agino_t		agino,
 	xfs_agblock_t		agbno,
 	xfs_agblock_t		*chunk_agbno,
 	xfs_agblock_t		*offset_agbno,
 	int			flags)
 {
+	struct xfs_mount	*mp = pag->pag_mount;
 	struct xfs_inobt_rec_incore rec;
 	struct xfs_btree_cur	*cur;
 	struct xfs_buf		*agbp;
@@ -2229,7 +2226,7 @@ xfs_imap_lookup(
 	 * we have a record, we need to ensure it contains the inode number
 	 * we are looking up.
 	 */
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
 	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
 	if (!error) {
 		if (i)
@@ -2263,12 +2260,13 @@ xfs_imap_lookup(
  */
 int
 xfs_imap(
-	struct xfs_mount	 *mp,	/* file system mount structure */
-	struct xfs_trans	 *tp,	/* transaction pointer */
+	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
 	xfs_ino_t		ino,	/* inode to locate */
 	struct xfs_imap		*imap,	/* location map structure */
 	uint			flags)	/* flags for inode btree lookup */
 {
+	struct xfs_mount	*mp = pag->pag_mount;
 	xfs_agblock_t		agbno;	/* block number of inode in the alloc group */
 	xfs_agino_t		agino;	/* inode number within alloc group */
 	xfs_agblock_t		chunk_agbno;	/* first block in inode chunk */
@@ -2276,17 +2274,15 @@ xfs_imap(
 	int			error;	/* error code */
 	int			offset;	/* index of inode in its buffer */
 	xfs_agblock_t		offset_agbno;	/* blks from chunk start to inode */
-	struct xfs_perag	*pag;
 
 	ASSERT(ino != NULLFSINO);
 
 	/*
 	 * Split up the inode number into its parts.
 	 */
-	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
 	agino = XFS_INO_TO_AGINO(mp, ino);
 	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
-	if (!pag || agbno >= mp->m_sb.sb_agblocks ||
+	if (agbno >= mp->m_sb.sb_agblocks ||
 	    ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
 		error = -EINVAL;
 #ifdef DEBUG
@@ -2295,20 +2291,14 @@ xfs_imap(
 		 * as they can be invalid without implying corruption.
 		 */
 		if (flags & XFS_IGET_UNTRUSTED)
-			goto out_drop;
-		if (!pag) {
-			xfs_alert(mp,
-				"%s: agno (%d) >= mp->m_sb.sb_agcount (%d)",
-				__func__, XFS_INO_TO_AGNO(mp, ino),
-				mp->m_sb.sb_agcount);
-		}
+			return error;
 		if (agbno >= mp->m_sb.sb_agblocks) {
 			xfs_alert(mp,
 		"%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)",
 				__func__, (unsigned long long)agbno,
 				(unsigned long)mp->m_sb.sb_agblocks);
 		}
-		if (pag && ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
+		if (ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
 			xfs_alert(mp,
 		"%s: ino (0x%llx) != XFS_AGINO_TO_INO() (0x%llx)",
 				__func__, ino,
@@ -2316,7 +2306,7 @@ xfs_imap(
 		}
 		xfs_stack_trace();
 #endif /* DEBUG */
-		goto out_drop;
+		return error;
 	}
 
 	/*
@@ -2327,10 +2317,10 @@ xfs_imap(
 	 * in all cases where an untrusted inode number is passed.
 	 */
 	if (flags & XFS_IGET_UNTRUSTED) {
-		error = xfs_imap_lookup(mp, tp, pag, agino, agbno,
+		error = xfs_imap_lookup(pag, tp, agino, agbno,
 					&chunk_agbno, &offset_agbno, flags);
 		if (error)
-			goto out_drop;
+			return error;
 		goto out_map;
 	}
 
@@ -2346,8 +2336,7 @@ xfs_imap(
 		imap->im_len = XFS_FSB_TO_BB(mp, 1);
 		imap->im_boffset = (unsigned short)(offset <<
 							mp->m_sb.sb_inodelog);
-		error = 0;
-		goto out_drop;
+		return 0;
 	}
 
 	/*
@@ -2359,10 +2348,10 @@ xfs_imap(
 		offset_agbno = agbno & M_IGEO(mp)->inoalign_mask;
 		chunk_agbno = agbno - offset_agbno;
 	} else {
-		error = xfs_imap_lookup(mp, tp, pag, agino, agbno,
+		error = xfs_imap_lookup(pag, tp, agino, agbno,
 					&chunk_agbno, &offset_agbno, flags);
 		if (error)
-			goto out_drop;
+			return error;
 	}
 
 out_map:
@@ -2390,14 +2379,9 @@ out_map:
 			__func__, (unsigned long long) imap->im_blkno,
 			(unsigned long long) imap->im_len,
 			XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
-		error = -EINVAL;
-		goto out_drop;
+		return -EINVAL;
 	}
-	error = 0;
-out_drop:
-	if (pag)
-		xfs_perag_put(pag);
-	return error;
+	return 0;
 }
 
 /*
@@ -2613,10 +2597,10 @@ xfs_ialloc_read_agi(
 		return error;
 
 	agi = agibp->b_addr;
-	if (!pag->pagi_init) {
+	if (!xfs_perag_initialised_agi(pag)) {
 		pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
 		pag->pagi_count = be32_to_cpu(agi->agi_count);
-		pag->pagi_init = 1;
+		set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
 	}
 
 	/*
@@ -2924,26 +2908,24 @@ xfs_ialloc_calc_rootino(
  */
 int
 xfs_ialloc_check_shrink(
+	struct xfs_perag	*pag,
 	struct xfs_trans	*tp,
-	xfs_agnumber_t		agno,
 	struct xfs_buf		*agibp,
 	xfs_agblock_t		new_length)
 {
 	struct xfs_inobt_rec_incore rec;
 	struct xfs_btree_cur	*cur;
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_perag	*pag;
-	xfs_agino_t		agino = XFS_AGB_TO_AGINO(mp, new_length);
+	xfs_agino_t		agino;
 	int			has;
 	int			error;
 
-	if (!xfs_has_sparseinodes(mp))
+	if (!xfs_has_sparseinodes(pag->pag_mount))
 		return 0;
 
-	pag = xfs_perag_get(mp, agno);
-	cur = xfs_inobt_init_cursor(mp, tp, agibp, pag, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agibp, XFS_BTNUM_INO);
 
 	/* Look up the inobt record that would correspond to the new EOFS. */
+	agino = XFS_AGB_TO_AGINO(pag->pag_mount, new_length);
 	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has);
 	if (error || !has)
 		goto out;
@@ -2964,6 +2946,5 @@ xfs_ialloc_check_shrink(
 	}
 out:
 	xfs_btree_del_cursor(cur, error);
-	xfs_perag_put(pag);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 9bbbca6ac4ed..ab8c30b4ec22 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -12,6 +12,7 @@ struct xfs_imap;
 struct xfs_mount;
 struct xfs_trans;
 struct xfs_btree_cur;
+struct xfs_perag;
 
 /* Move inodes in clusters of this size */
 #define	XFS_INODE_BIG_CLUSTER_SIZE	8192
@@ -47,7 +48,7 @@ int xfs_difree(struct xfs_trans *tp, struct xfs_perag *pag,
  */
 int
 xfs_imap(
-	struct xfs_mount *mp,		/* file system mount structure */
+	struct xfs_perag *pag,
 	struct xfs_trans *tp,		/* transaction pointer */
 	xfs_ino_t	ino,		/* inode to locate */
 	struct xfs_imap	*imap,		/* location map structure */
@@ -106,7 +107,7 @@ int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
 void xfs_ialloc_setup_geometry(struct xfs_mount *mp);
 xfs_ino_t xfs_ialloc_calc_rootino(struct xfs_mount *mp, int sunit);
 
-int xfs_ialloc_check_shrink(struct xfs_trans *tp, xfs_agnumber_t agno,
+int xfs_ialloc_check_shrink(struct xfs_perag *pag, struct xfs_trans *tp,
 		struct xfs_buf *agibp, xfs_agblock_t new_length);
 
 #endif	/* __XFS_IALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 8c83e265770c..9b28211d5a4c 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -36,8 +36,8 @@ STATIC struct xfs_btree_cur *
 xfs_inobt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
-	return xfs_inobt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_ag.agbp, cur->bc_ag.pag, cur->bc_btnum);
+	return xfs_inobt_init_cursor(cur->bc_ag.pag, cur->bc_tp,
+			cur->bc_ag.agbp, cur->bc_btnum);
 }
 
 STATIC void
@@ -103,15 +103,15 @@ __xfs_inobt_alloc_block(
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
+	args.pag = cur->bc_ag.pag;
 	args.oinfo = XFS_RMAP_OINFO_INOBT;
-	args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_ag.pag->pag_agno, sbno);
 	args.minlen = 1;
 	args.maxlen = 1;
 	args.prod = 1;
-	args.type = XFS_ALLOCTYPE_NEAR_BNO;
 	args.resv = resv;
 
-	error = xfs_alloc_vextent(&args);
+	error = xfs_alloc_vextent_near_bno(&args,
+			XFS_AGB_TO_FSB(args.mp, args.pag->pag_agno, sbno));
 	if (error)
 		return error;
 
@@ -291,8 +291,8 @@ xfs_inobt_verify(
 	 * Similarly, during log recovery we will have a perag structure
 	 * attached, but the agi information will not yet have been initialised
 	 * from the on disk AGI. We don't currently use any of this information,
-	 * but beware of the landmine (i.e. need to check pag->pagi_init) if we
-	 * ever do.
+	 * but beware of the landmine (i.e. need to check
+	 * xfs_perag_initialised_agi(pag)) if we ever do.
 	 */
 	if (xfs_has_crc(mp)) {
 		fa = xfs_btree_sblock_v5hdr_verify(bp);
@@ -427,11 +427,11 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
  */
 static struct xfs_btree_cur *
 xfs_inobt_init_common(
-	struct xfs_mount	*mp,		/* file system mount point */
-	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,		/* transaction pointer */
 	xfs_btnum_t		btnum)		/* ialloc or free ino btree */
 {
+	struct xfs_mount	*mp = pag->pag_mount;
 	struct xfs_btree_cur	*cur;
 
 	cur = xfs_btree_alloc_cursor(mp, tp, btnum,
@@ -456,16 +456,15 @@ xfs_inobt_init_common(
 /* Create an inode btree cursor. */
 struct xfs_btree_cur *
 xfs_inobt_init_cursor(
-	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
-	struct xfs_perag	*pag,
 	xfs_btnum_t		btnum)
 {
 	struct xfs_btree_cur	*cur;
 	struct xfs_agi		*agi = agbp->b_addr;
 
-	cur = xfs_inobt_init_common(mp, tp, pag, btnum);
+	cur = xfs_inobt_init_common(pag, tp, btnum);
 	if (btnum == XFS_BTNUM_INO)
 		cur->bc_nlevels = be32_to_cpu(agi->agi_level);
 	else
@@ -477,14 +476,13 @@ xfs_inobt_init_cursor(
 /* Create an inode btree cursor with a fake root for staging. */
 struct xfs_btree_cur *
 xfs_inobt_stage_cursor(
-	struct xfs_mount	*mp,
-	struct xbtree_afakeroot	*afake,
 	struct xfs_perag	*pag,
+	struct xbtree_afakeroot	*afake,
 	xfs_btnum_t		btnum)
 {
 	struct xfs_btree_cur	*cur;
 
-	cur = xfs_inobt_init_common(mp, NULL, pag, btnum);
+	cur = xfs_inobt_init_common(pag, NULL, btnum);
 	xfs_btree_stage_afakeroot(cur, afake);
 	return cur;
 }
@@ -708,9 +706,8 @@ xfs_inobt_max_size(
 /* Read AGI and create inobt cursor. */
 int
 xfs_inobt_cur(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
 	xfs_btnum_t		which,
 	struct xfs_btree_cur	**curpp,
 	struct xfs_buf		**agi_bpp)
@@ -725,16 +722,15 @@ xfs_inobt_cur(
 	if (error)
 		return error;
 
-	cur = xfs_inobt_init_cursor(mp, tp, *agi_bpp, pag, which);
+	cur = xfs_inobt_init_cursor(pag, tp, *agi_bpp, which);
 	*curpp = cur;
 	return 0;
 }
 
 static int
 xfs_inobt_count_blocks(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
 	xfs_btnum_t		btnum,
 	xfs_extlen_t		*tree_blocks)
 {
@@ -742,7 +738,7 @@ xfs_inobt_count_blocks(
 	struct xfs_btree_cur	*cur = NULL;
 	int			error;
 
-	error = xfs_inobt_cur(mp, tp, pag, btnum, &cur, &agbp);
+	error = xfs_inobt_cur(pag, tp, btnum, &cur, &agbp);
 	if (error)
 		return error;
 
@@ -779,22 +775,21 @@ xfs_finobt_read_blocks(
  */
 int
 xfs_finobt_calc_reserves(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
 {
 	xfs_extlen_t		tree_len = 0;
 	int			error;
 
-	if (!xfs_has_finobt(mp))
+	if (!xfs_has_finobt(pag->pag_mount))
 		return 0;
 
-	if (xfs_has_inobtcounts(mp))
+	if (xfs_has_inobtcounts(pag->pag_mount))
 		error = xfs_finobt_read_blocks(pag, tp, &tree_len);
 	else
-		error = xfs_inobt_count_blocks(mp, tp, pag, XFS_BTNUM_FINO,
+		error = xfs_inobt_count_blocks(pag, tp, XFS_BTNUM_FINO,
 				&tree_len);
 	if (error)
 		return error;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index 26451cb76b98..e859a6e05230 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -46,12 +46,10 @@ struct xfs_perag;
 		 (maxrecs) * sizeof(xfs_inobt_key_t) + \
 		 ((index) - 1) * sizeof(xfs_inobt_ptr_t)))
 
-extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *mp,
-		struct xfs_trans *tp, struct xfs_buf *agbp,
-		struct xfs_perag *pag, xfs_btnum_t btnum);
-struct xfs_btree_cur *xfs_inobt_stage_cursor(struct xfs_mount *mp,
-		struct xbtree_afakeroot *afake, struct xfs_perag *pag,
-		xfs_btnum_t btnum);
+extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_perag *pag,
+		struct xfs_trans *tp, struct xfs_buf *agbp, xfs_btnum_t btnum);
+struct xfs_btree_cur *xfs_inobt_stage_cursor(struct xfs_perag *pag,
+		struct xbtree_afakeroot *afake, xfs_btnum_t btnum);
 extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
 
 /* ir_holemask to inode allocation bitmap conversion */
@@ -64,13 +62,13 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 #define xfs_inobt_rec_check_count(mp, rec)	0
 #endif	/* DEBUG */
 
-int xfs_finobt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
-		struct xfs_perag *pag, xfs_extlen_t *ask, xfs_extlen_t *used);
+int xfs_finobt_calc_reserves(struct xfs_perag *perag, struct xfs_trans *tp,
+		xfs_extlen_t *ask, xfs_extlen_t *used);
 extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
-int xfs_inobt_cur(struct xfs_mount *mp, struct xfs_trans *tp,
-		struct xfs_perag *pag, xfs_btnum_t btnum,
-		struct xfs_btree_cur **curpp, struct xfs_buf **agi_bpp);
+int xfs_inobt_cur(struct xfs_perag *pag, struct xfs_trans *tp,
+		xfs_btnum_t btnum, struct xfs_btree_cur **curpp,
+		struct xfs_buf **agi_bpp);
 
 void xfs_inobt_commit_staged_btree(struct xfs_btree_cur *cur,
 		struct xfs_trans *tp, struct xfs_buf *agbp);
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index e1f789866683..f3b860970b26 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -67,14 +67,14 @@ xfs_refcountbt_alloc_block(
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
-	args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno,
-			xfs_refc_block(args.mp));
+	args.pag = cur->bc_ag.pag;
 	args.oinfo = XFS_RMAP_OINFO_REFC;
 	args.minlen = args.maxlen = args.prod = 1;
 	args.resv = XFS_AG_RESV_METADATA;
 
-	error = xfs_alloc_vextent(&args);
+	error = xfs_alloc_vextent_near_bno(&args,
+			XFS_AGB_TO_FSB(args.mp, args.pag->pag_agno,
+					xfs_refc_block(args.mp)));
 	if (error)
 		goto out_error;
 	trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
@@ -227,7 +227,7 @@ xfs_refcountbt_verify(
 		return fa;
 
 	level = be16_to_cpu(block->bb_level);
-	if (pag && pag->pagf_init) {
+	if (pag && xfs_perag_initialised_agf(pag)) {
 		if (level >= pag->pagf_refcount_level)
 			return __this_address;
 	} else if (level >= mp->m_refc_maxlevels)
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 7f83f62e51e0..d3285684bb5e 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -313,7 +313,7 @@ xfs_rmapbt_verify(
 		return fa;
 
 	level = be16_to_cpu(block->bb_level);
-	if (pag && pag->pagf_init) {
+	if (pag && xfs_perag_initialised_agf(pag)) {
 		if (level >= pag->pagf_levels[XFS_BTNUM_RMAPi])
 			return __this_address;
 	} else if (level >= mp->m_rmap_maxlevels)
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 1eeecf2eb2a7..99cc03a298e2 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -909,7 +909,8 @@ xfs_sb_mount_common(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
-	mp->m_agfrotor = mp->m_agirotor = 0;
+	mp->m_agfrotor = 0;
+	atomic_set(&mp->m_agirotor, 0);
 	mp->m_maxagi = mp->m_sb.sb_agcount;
 	mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG;
 	mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT;
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index d75d82151eeb..c37e6d72760b 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -191,14 +191,15 @@ xrep_agf_init_header(
 	struct xfs_agf		*old_agf)
 {
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_perag	*pag = sc->sa.pag;
 	struct xfs_agf		*agf = agf_bp->b_addr;
 
 	memcpy(old_agf, agf, sizeof(*old_agf));
 	memset(agf, 0, BBTOB(agf_bp->b_length));
 	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
 	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
-	agf->agf_seqno = cpu_to_be32(sc->sa.pag->pag_agno);
-	agf->agf_length = cpu_to_be32(sc->sa.pag->block_count);
+	agf->agf_seqno = cpu_to_be32(pag->pag_agno);
+	agf->agf_length = cpu_to_be32(pag->block_count);
 	agf->agf_flfirst = old_agf->agf_flfirst;
 	agf->agf_fllast = old_agf->agf_fllast;
 	agf->agf_flcount = old_agf->agf_flcount;
@@ -206,8 +207,8 @@ xrep_agf_init_header(
 		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
 
 	/* Mark the incore AGF data stale until we're done fixing things. */
-	ASSERT(sc->sa.pag->pagf_init);
-	sc->sa.pag->pagf_init = 0;
+	ASSERT(xfs_perag_initialised_agf(pag));
+	clear_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
 }
 
 /* Set btree root information in an AGF. */
@@ -333,7 +334,7 @@ xrep_agf_commit_new(
 	pag->pagf_levels[XFS_BTNUM_RMAPi] =
 			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
 	pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
-	pag->pagf_init = 1;
+	set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
 
 	return 0;
 }
@@ -434,7 +435,7 @@ xrep_agf(
 
 out_revert:
 	/* Mark the incore AGF state stale and revert the AGF. */
-	sc->sa.pag->pagf_init = 0;
+	clear_bit(XFS_AGSTATE_AGF_INIT, &sc->sa.pag->pag_opstate);
 	memcpy(agf, &old_agf, sizeof(old_agf));
 	return error;
 }
@@ -618,7 +619,7 @@ xrep_agfl_update_agf(
 	xfs_force_summary_recalc(sc->mp);
 
 	/* Update the AGF counters. */
-	if (sc->sa.pag->pagf_init)
+	if (xfs_perag_initialised_agf(sc->sa.pag))
 		sc->sa.pag->pagf_flcount = flcount;
 	agf->agf_flfirst = cpu_to_be32(0);
 	agf->agf_flcount = cpu_to_be32(flcount);
@@ -822,14 +823,15 @@ xrep_agi_init_header(
 	struct xfs_agi		*old_agi)
 {
 	struct xfs_agi		*agi = agi_bp->b_addr;
+	struct xfs_perag	*pag = sc->sa.pag;
 	struct xfs_mount	*mp = sc->mp;
 
 	memcpy(old_agi, agi, sizeof(*old_agi));
 	memset(agi, 0, BBTOB(agi_bp->b_length));
 	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
 	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
-	agi->agi_seqno = cpu_to_be32(sc->sa.pag->pag_agno);
-	agi->agi_length = cpu_to_be32(sc->sa.pag->block_count);
+	agi->agi_seqno = cpu_to_be32(pag->pag_agno);
+	agi->agi_length = cpu_to_be32(pag->block_count);
 	agi->agi_newino = cpu_to_be32(NULLAGINO);
 	agi->agi_dirino = cpu_to_be32(NULLAGINO);
 	if (xfs_has_crc(mp))
@@ -840,8 +842,8 @@ xrep_agi_init_header(
 			sizeof(agi->agi_unlinked));
 
 	/* Mark the incore AGF data stale until we're done fixing things. */
-	ASSERT(sc->sa.pag->pagi_init);
-	sc->sa.pag->pagi_init = 0;
+	ASSERT(xfs_perag_initialised_agi(pag));
+	clear_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
 }
 
 /* Set btree root information in an AGI. */
@@ -873,8 +875,7 @@ xrep_agi_calc_from_btrees(
 	xfs_agino_t		freecount;
 	int			error;
 
-	cur = xfs_inobt_init_cursor(mp, sc->tp, agi_bp,
-			sc->sa.pag, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp, agi_bp, XFS_BTNUM_INO);
 	error = xfs_ialloc_count_inodes(cur, &count, &freecount);
 	if (error)
 		goto err;
@@ -894,8 +895,8 @@ xrep_agi_calc_from_btrees(
 	if (xfs_has_finobt(mp) && xfs_has_inobtcounts(mp)) {
 		xfs_agblock_t	blocks;
 
-		cur = xfs_inobt_init_cursor(mp, sc->tp, agi_bp,
-				sc->sa.pag, XFS_BTNUM_FINO);
+		cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp, agi_bp,
+				XFS_BTNUM_FINO);
 		error = xfs_btree_count_blocks(cur, &blocks);
 		if (error)
 			goto err;
@@ -929,7 +930,7 @@ xrep_agi_commit_new(
 	pag = sc->sa.pag;
 	pag->pagi_count = be32_to_cpu(agi->agi_count);
 	pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
-	pag->pagi_init = 1;
+	set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
 
 	return 0;
 }
@@ -994,7 +995,7 @@ xrep_agi(
 
 out_revert:
 	/* Mark the incore AGI state stale and revert the AGI. */
-	sc->sa.pag->pagi_init = 0;
+	clear_bit(XFS_AGSTATE_AGI_INIT, &sc->sa.pag->pag_opstate);
 	memcpy(agi, &old_agi, sizeof(old_agi));
 	return error;
 }
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index d50d0eab196a..dbbc7037074c 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -662,7 +662,7 @@ xchk_bmap_check_rmaps(
 		error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag);
 		if (error ||
 		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
-			xfs_perag_put(pag);
+			xfs_perag_rele(pag);
 			return error;
 		}
 	}
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 613260b04a3d..848a8e32e56f 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -478,15 +478,15 @@ xchk_ag_btcur_init(
 	/* Set up a inobt cursor for cross-referencing. */
 	if (sa->agi_bp &&
 	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_INO)) {
-		sa->ino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp,
-				sa->pag, XFS_BTNUM_INO);
+		sa->ino_cur = xfs_inobt_init_cursor(sa->pag, sc->tp, sa->agi_bp,
+				XFS_BTNUM_INO);
 	}
 
 	/* Set up a finobt cursor for cross-referencing. */
 	if (sa->agi_bp && xfs_has_finobt(mp) &&
 	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_FINO)) {
-		sa->fino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp,
-				sa->pag, XFS_BTNUM_FINO);
+		sa->fino_cur = xfs_inobt_init_cursor(sa->pag, sc->tp, sa->agi_bp,
+				XFS_BTNUM_FINO);
 	}
 
 	/* Set up a rmapbt cursor for cross-referencing. */
@@ -636,6 +636,7 @@ xchk_get_inode(
 {
 	struct xfs_imap		imap;
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_perag	*pag;
 	struct xfs_inode	*ip_in = XFS_I(file_inode(sc->file));
 	struct xfs_inode	*ip = NULL;
 	int			error;
@@ -671,10 +672,14 @@ xchk_get_inode(
 		 * Otherwise, we really couldn't find it so tell userspace
 		 * that it no longer exists.
 		 */
-		error = xfs_imap(sc->mp, sc->tp, sc->sm->sm_ino, &imap,
-				XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE);
-		if (error)
-			return -ENOENT;
+		pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, sc->sm->sm_ino));
+		if (pag) {
+			error = xfs_imap(pag, sc->tp, sc->sm->sm_ino, &imap,
+					XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE);
+			xfs_perag_put(pag);
+			if (error)
+				return -ENOENT;
+		}
 		error = -EFSCORRUPTED;
 		fallthrough;
 	default:
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 4777e7b89fdc..f0c7f41897b9 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -86,7 +86,8 @@ xchk_fscount_warmup(
 	for_each_perag(mp, agno, pag) {
 		if (xchk_should_terminate(sc, &error))
 			break;
-		if (pag->pagi_init && pag->pagf_init)
+		if (xfs_perag_initialised_agi(pag) &&
+		    xfs_perag_initialised_agf(pag))
 			continue;
 
 		/* Lock both AG headers. */
@@ -101,7 +102,8 @@ xchk_fscount_warmup(
 		 * These are supposed to be initialized by the header read
 		 * function.
 		 */
-		if (!pag->pagi_init || !pag->pagf_init) {
+		if (!xfs_perag_initialised_agi(pag) ||
+		    !xfs_perag_initialised_agf(pag)) {
 			error = -EFSCORRUPTED;
 			break;
 		}
@@ -117,7 +119,7 @@ xchk_fscount_warmup(
 	if (agi_bp)
 		xfs_buf_relse(agi_bp);
 	if (pag)
-		xfs_perag_put(pag);
+		xfs_perag_rele(pag);
 	return error;
 }
 
@@ -220,7 +222,8 @@ retry:
 			break;
 
 		/* This somehow got unset since the warmup? */
-		if (!pag->pagi_init || !pag->pagf_init) {
+		if (!xfs_perag_initialised_agi(pag) ||
+		    !xfs_perag_initialised_agf(pag)) {
 			error = -EFSCORRUPTED;
 			break;
 		}
@@ -249,7 +252,7 @@ retry:
 
 	}
 	if (pag)
-		xfs_perag_put(pag);
+		xfs_perag_rele(pag);
 	if (error) {
 		xchk_set_incomplete(sc);
 		return error;
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 4b92f9253ccd..1b71174ec0d6 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -206,7 +206,7 @@ xrep_calc_ag_resblks(
 		return 0;
 
 	pag = xfs_perag_get(mp, sm->sm_agno);
-	if (pag->pagi_init) {
+	if (xfs_perag_initialised_agi(pag)) {
 		/* Use in-core icount if possible. */
 		icount = pag->pagi_count;
 	} else {
@@ -326,15 +326,14 @@ xrep_alloc_ag_block(
 
 	args.tp = sc->tp;
 	args.mp = sc->mp;
+	args.pag = sc->sa.pag;
 	args.oinfo = *oinfo;
-	args.fsbno = XFS_AGB_TO_FSB(args.mp, sc->sa.pag->pag_agno, 0);
 	args.minlen = 1;
 	args.maxlen = 1;
 	args.prod = 1;
-	args.type = XFS_ALLOCTYPE_THIS_AG;
 	args.resv = resv;
 
-	error = xfs_alloc_vextent(&args);
+	error = xfs_alloc_vextent_this_ag(&args, sc->sa.pag->pag_agno);
 	if (error)
 		return error;
 	if (args.fsbno == NULLFSBLOCK)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 867645b74d88..a09dd2606479 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1410,7 +1410,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			ASSERT(tp->t_firstblock == NULLFSBLOCK);
+			ASSERT(tp->t_highest_agno == NULLAGNUMBER);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index bfc829c07f03..afc4c78b9eed 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -21,23 +21,20 @@
 
 STATIC int
 xfs_trim_extents(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno,
+	struct xfs_perag	*pag,
 	xfs_daddr_t		start,
 	xfs_daddr_t		end,
 	xfs_daddr_t		minlen,
 	uint64_t		*blocks_trimmed)
 {
+	struct xfs_mount	*mp = pag->pag_mount;
 	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;
 	struct xfs_btree_cur	*cur;
 	struct xfs_buf		*agbp;
 	struct xfs_agf		*agf;
-	struct xfs_perag	*pag;
 	int			error;
 	int			i;
 
-	pag = xfs_perag_get(mp, agno);
-
 	/*
 	 * Force out the log.  This means any transactions that might have freed
 	 * space before we take the AGF buffer lock are now on disk, and the
@@ -47,7 +44,7 @@ xfs_trim_extents(
 
 	error = xfs_alloc_read_agf(pag, NULL, 0, &agbp);
 	if (error)
-		goto out_put_perag;
+		return error;
 	agf = agbp->b_addr;
 
 	cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_CNT);
@@ -71,10 +68,10 @@ xfs_trim_extents(
 
 		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
 		if (error)
-			goto out_del_cursor;
+			break;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
 			error = -EFSCORRUPTED;
-			goto out_del_cursor;
+			break;
 		}
 		ASSERT(flen <= be32_to_cpu(agf->agf_longest));
 
@@ -83,15 +80,15 @@ xfs_trim_extents(
 		 * the format the range/len variables are supplied in by
 		 * userspace.
 		 */
-		dbno = XFS_AGB_TO_DADDR(mp, agno, fbno);
+		dbno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, fbno);
 		dlen = XFS_FSB_TO_BB(mp, flen);
 
 		/*
 		 * Too small?  Give up.
 		 */
 		if (dlen < minlen) {
-			trace_xfs_discard_toosmall(mp, agno, fbno, flen);
-			goto out_del_cursor;
+			trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
+			break;
 		}
 
 		/*
@@ -100,7 +97,7 @@ xfs_trim_extents(
 		 * down partially overlapping ranges for now.
 		 */
 		if (dbno + dlen < start || dbno > end) {
-			trace_xfs_discard_exclude(mp, agno, fbno, flen);
+			trace_xfs_discard_exclude(mp, pag->pag_agno, fbno, flen);
 			goto next_extent;
 		}
 
@@ -109,32 +106,30 @@ xfs_trim_extents(
 		 * discard and try again the next time.
 		 */
 		if (xfs_extent_busy_search(mp, pag, fbno, flen)) {
-			trace_xfs_discard_busy(mp, agno, fbno, flen);
+			trace_xfs_discard_busy(mp, pag->pag_agno, fbno, flen);
 			goto next_extent;
 		}
 
-		trace_xfs_discard_extent(mp, agno, fbno, flen);
+		trace_xfs_discard_extent(mp, pag->pag_agno, fbno, flen);
 		error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS);
 		if (error)
-			goto out_del_cursor;
+			break;
 		*blocks_trimmed += flen;
 
 next_extent:
 		error = xfs_btree_decrement(cur, 0, &i);
 		if (error)
-			goto out_del_cursor;
+			break;
 
 		if (fatal_signal_pending(current)) {
 			error = -ERESTARTSYS;
-			goto out_del_cursor;
+			break;
 		}
 	}
 
 out_del_cursor:
 	xfs_btree_del_cursor(cur, error);
 	xfs_buf_relse(agbp);
-out_put_perag:
-	xfs_perag_put(pag);
 	return error;
 }
 
@@ -152,11 +147,12 @@ xfs_ioc_trim(
 	struct xfs_mount		*mp,
 	struct fstrim_range __user	*urange)
 {
+	struct xfs_perag	*pag;
 	unsigned int		granularity =
 		bdev_discard_granularity(mp->m_ddev_targp->bt_bdev);
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end, minlen;
-	xfs_agnumber_t		start_agno, end_agno, agno;
+	xfs_agnumber_t		agno;
 	uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;
 
@@ -193,18 +189,18 @@ xfs_ioc_trim(
 	end = start + BTOBBT(range.len) - 1;
 
 	if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
-		end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;
-
-	start_agno = xfs_daddr_to_agno(mp, start);
-	end_agno = xfs_daddr_to_agno(mp, end);
+		end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1;
 
-	for (agno = start_agno; agno <= end_agno; agno++) {
-		error = xfs_trim_extents(mp, agno, start, end, minlen,
+	agno = xfs_daddr_to_agno(mp, start);
+	for_each_perag_range(mp, agno, xfs_daddr_to_agno(mp, end), pag) {
+		error = xfs_trim_extents(pag, start, end, minlen,
 					  &blocks_trimmed);
 		if (error) {
 			last_error = error;
-			if (error == -ERESTARTSYS)
+			if (error == -ERESTARTSYS) {
+				xfs_perag_rele(pag);
 				break;
+			}
 		}
 	}
 
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 34b21a29c39b..22c13933c8f8 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -12,6 +12,7 @@
 #include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
 #include "xfs_alloc.h"
 #include "xfs_mru_cache.h"
 #include "xfs_trace.h"
@@ -22,7 +23,7 @@
 
 struct xfs_fstrm_item {
 	struct xfs_mru_cache_elem	mru;
-	xfs_agnumber_t			ag; /* AG in use for this directory */
+	struct xfs_perag		*pag; /* AG in use for this directory */
 };
 
 enum xfs_fstrm_alloc {
@@ -30,117 +31,68 @@ enum xfs_fstrm_alloc {
 	XFS_PICK_LOWSPACE = 2,
 };
 
-/*
- * Allocation group filestream associations are tracked with per-ag atomic
- * counters.  These counters allow xfs_filestream_pick_ag() to tell whether a
- * particular AG already has active filestreams associated with it.
- */
-int
-xfs_filestream_peek_ag(
-	xfs_mount_t	*mp,
-	xfs_agnumber_t	agno)
-{
-	struct xfs_perag *pag;
-	int		ret;
-
-	pag = xfs_perag_get(mp, agno);
-	ret = atomic_read(&pag->pagf_fstrms);
-	xfs_perag_put(pag);
-	return ret;
-}
-
-static int
-xfs_filestream_get_ag(
-	xfs_mount_t	*mp,
-	xfs_agnumber_t	agno)
-{
-	struct xfs_perag *pag;
-	int		ret;
-
-	pag = xfs_perag_get(mp, agno);
-	ret = atomic_inc_return(&pag->pagf_fstrms);
-	xfs_perag_put(pag);
-	return ret;
-}
-
-static void
-xfs_filestream_put_ag(
-	xfs_mount_t	*mp,
-	xfs_agnumber_t	agno)
-{
-	struct xfs_perag *pag;
-
-	pag = xfs_perag_get(mp, agno);
-	atomic_dec(&pag->pagf_fstrms);
-	xfs_perag_put(pag);
-}
-
 static void
 xfs_fstrm_free_func(
 	void			*data,
 	struct xfs_mru_cache_elem *mru)
 {
-	struct xfs_mount	*mp = data;
 	struct xfs_fstrm_item	*item =
 		container_of(mru, struct xfs_fstrm_item, mru);
+	struct xfs_perag	*pag = item->pag;
 
-	xfs_filestream_put_ag(mp, item->ag);
-	trace_xfs_filestream_free(mp, mru->key, item->ag);
+	trace_xfs_filestream_free(pag, mru->key);
+	atomic_dec(&pag->pagf_fstrms);
+	xfs_perag_rele(pag);
 
 	kmem_free(item);
 }
 
 /*
- * Scan the AGs starting at startag looking for an AG that isn't in use and has
- * at least minlen blocks free.
+ * Scan the AGs starting at start_agno looking for an AG that isn't in use and
+ * has at least minlen blocks free. If no AG is found to match the allocation
+ * requirements, pick the AG with the most free space in it.
  */
 static int
 xfs_filestream_pick_ag(
-	struct xfs_inode	*ip,
-	xfs_agnumber_t		startag,
-	xfs_agnumber_t		*agp,
+	struct xfs_alloc_arg	*args,
+	xfs_ino_t		pino,
+	xfs_agnumber_t		start_agno,
 	int			flags,
-	xfs_extlen_t		minlen)
+	xfs_extlen_t		*longest)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_fstrm_item	*item;
+	struct xfs_mount	*mp = args->mp;
 	struct xfs_perag	*pag;
-	xfs_extlen_t		longest, free = 0, minfree, maxfree = 0;
-	xfs_agnumber_t		ag, max_ag = NULLAGNUMBER;
-	int			err, trylock, nscan;
-
-	ASSERT(S_ISDIR(VFS_I(ip)->i_mode));
+	struct xfs_perag	*max_pag = NULL;
+	xfs_extlen_t		minlen = *longest;
+	xfs_extlen_t		free = 0, minfree, maxfree = 0;
+	xfs_agnumber_t		agno;
+	bool			first_pass = true;
+	int			err;
 
 	/* 2% of an AG's blocks must be free for it to be chosen. */
 	minfree = mp->m_sb.sb_agblocks / 50;
 
-	ag = startag;
-	*agp = NULLAGNUMBER;
-
-	/* For the first pass, don't sleep trying to init the per-AG. */
-	trylock = XFS_ALLOC_FLAG_TRYLOCK;
-
-	for (nscan = 0; 1; nscan++) {
-		trace_xfs_filestream_scan(mp, ip->i_ino, ag);
-
-		pag = xfs_perag_get(mp, ag);
-
-		if (!pag->pagf_init) {
-			err = xfs_alloc_read_agf(pag, NULL, trylock, NULL);
-			if (err) {
-				if (err != -EAGAIN) {
-					xfs_perag_put(pag);
-					return err;
-				}
-				/* Couldn't lock the AGF, skip this AG. */
-				goto next_ag;
-			}
+restart:
+	for_each_perag_wrap(mp, start_agno, agno, pag) {
+		trace_xfs_filestream_scan(pag, pino);
+		*longest = 0;
+		err = xfs_bmap_longest_free_extent(pag, NULL, longest);
+		if (err) {
+			xfs_perag_rele(pag);
+			if (err != -EAGAIN)
+				break;
+			/* Couldn't lock the AGF, skip this AG. */
+			err = 0;
+			continue;
 		}
 
 		/* Keep track of the AG with the most free blocks. */
 		if (pag->pagf_freeblks > maxfree) {
 			maxfree = pag->pagf_freeblks;
-			max_ag = ag;
+			if (max_pag)
+				xfs_perag_rele(max_pag);
+			atomic_inc(&pag->pag_active_ref);
+			max_pag = pag;
 		}
 
 		/*
@@ -149,93 +101,73 @@ xfs_filestream_pick_ag(
 		 * loop, and it guards against two filestreams being established
 		 * in the same AG as each other.
 		 */
-		if (xfs_filestream_get_ag(mp, ag) > 1) {
-			xfs_filestream_put_ag(mp, ag);
-			goto next_ag;
-		}
-
-		longest = xfs_alloc_longest_free_extent(pag,
-				xfs_alloc_min_freelist(mp, pag),
-				xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE));
-		if (((minlen && longest >= minlen) ||
-		     (!minlen && pag->pagf_freeblks >= minfree)) &&
-		    (!pag->pagf_metadata || !(flags & XFS_PICK_USERDATA) ||
-		     (flags & XFS_PICK_LOWSPACE))) {
-
-			/* Break out, retaining the reference on the AG. */
-			free = pag->pagf_freeblks;
-			xfs_perag_put(pag);
-			*agp = ag;
-			break;
+		if (atomic_inc_return(&pag->pagf_fstrms) <= 1) {
+			if (((minlen && *longest >= minlen) ||
+			     (!minlen && pag->pagf_freeblks >= minfree)) &&
+			    (!xfs_perag_prefers_metadata(pag) ||
+			     !(flags & XFS_PICK_USERDATA) ||
+			     (flags & XFS_PICK_LOWSPACE))) {
+				/* Break out, retaining the reference on the AG. */
+				free = pag->pagf_freeblks;
+				break;
+			}
 		}
 
 		/* Drop the reference on this AG, it's not usable. */
-		xfs_filestream_put_ag(mp, ag);
-next_ag:
-		xfs_perag_put(pag);
-		/* Move to the next AG, wrapping to AG 0 if necessary. */
-		if (++ag >= mp->m_sb.sb_agcount)
-			ag = 0;
-
-		/* If a full pass of the AGs hasn't been done yet, continue. */
-		if (ag != startag)
-			continue;
+		atomic_dec(&pag->pagf_fstrms);
+	}
 
-		/* Allow sleeping in xfs_alloc_read_agf() on the 2nd pass. */
-		if (trylock != 0) {
-			trylock = 0;
-			continue;
+	if (err) {
+		xfs_perag_rele(pag);
+		if (max_pag)
+			xfs_perag_rele(max_pag);
+		return err;
+	}
+
+	if (!pag) {
+		/*
+		 * Allow a second pass to give xfs_bmap_longest_free_extent()
+		 * another attempt at locking AGFs that it might have skipped
+		 * over before we fail.
+		 */
+		if (first_pass) {
+			first_pass = false;
+			goto restart;
 		}
 
-		/* Finally, if lowspace wasn't set, set it for the 3rd pass. */
+		/*
+		 * We must be low on data space, so run a final lowspace
+		 * optimised selection pass if we haven't already.
+		 */
 		if (!(flags & XFS_PICK_LOWSPACE)) {
 			flags |= XFS_PICK_LOWSPACE;
-			continue;
+			goto restart;
 		}
 
 		/*
-		 * Take the AG with the most free space, regardless of whether
-		 * it's already in use by another filestream.
+		 * No unassociated AGs are available, so select the AG with the
+		 * most free space, regardless of whether it's already in use by
+		 * another filestream. It none suit, just use whatever AG we can
+		 * grab.
 		 */
-		if (max_ag != NULLAGNUMBER) {
-			xfs_filestream_get_ag(mp, max_ag);
+		if (!max_pag) {
+			for_each_perag_wrap(args->mp, 0, start_agno, args->pag)
+				break;
+			atomic_inc(&args->pag->pagf_fstrms);
+			*longest = 0;
+		} else {
+			pag = max_pag;
 			free = maxfree;
-			*agp = max_ag;
-			break;
+			atomic_inc(&pag->pagf_fstrms);
 		}
-
-		/* take AG 0 if none matched */
-		trace_xfs_filestream_pick(ip, *agp, free, nscan);
-		*agp = 0;
-		return 0;
-	}
-
-	trace_xfs_filestream_pick(ip, *agp, free, nscan);
-
-	if (*agp == NULLAGNUMBER)
-		return 0;
-
-	err = -ENOMEM;
-	item = kmem_alloc(sizeof(*item), KM_MAYFAIL);
-	if (!item)
-		goto out_put_ag;
-
-	item->ag = *agp;
-
-	err = xfs_mru_cache_insert(mp->m_filestream, ip->i_ino, &item->mru);
-	if (err) {
-		if (err == -EEXIST)
-			err = 0;
-		goto out_free_item;
+	} else if (max_pag) {
+		xfs_perag_rele(max_pag);
 	}
 
+	trace_xfs_filestream_pick(pag, pino, free);
+	args->pag = pag;
 	return 0;
 
-out_free_item:
-	kmem_free(item);
-out_put_ag:
-	xfs_filestream_put_ag(mp, *agp);
-	return err;
 }
 
 static struct xfs_inode *
@@ -263,104 +195,187 @@ out:
 }
 
 /*
- * Find the right allocation group for a file, either by finding an
- * existing file stream or creating a new one.
+ * Lookup the mru cache for an existing association. If one exists and we can
+ * use it, return with an active perag reference indicating that the allocation
+ * will proceed with that association.
  *
- * Returns NULLAGNUMBER in case of an error.
+ * If we have no association, or we cannot use the current one and have to
+ * destroy it, return with longest = 0 to tell the caller to create a new
+ * association.
  */
-xfs_agnumber_t
-xfs_filestream_lookup_ag(
-	struct xfs_inode	*ip)
+static int
+xfs_filestream_lookup_association(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_ino_t		pino,
+	xfs_extlen_t		*longest)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_inode	*pip = NULL;
-	xfs_agnumber_t		startag, ag = NULLAGNUMBER;
+	struct xfs_mount	*mp = args->mp;
+	struct xfs_perag	*pag;
 	struct xfs_mru_cache_elem *mru;
+	int			error = 0;
 
-	ASSERT(S_ISREG(VFS_I(ip)->i_mode));
-
-	pip = xfs_filestream_get_parent(ip);
-	if (!pip)
-		return NULLAGNUMBER;
+	*longest = 0;
+	mru = xfs_mru_cache_lookup(mp->m_filestream, pino);
+	if (!mru)
+		return 0;
+	/*
+	 * Grab the pag and take an extra active reference for the caller whilst
+	 * the mru item cannot go away. This means we'll pin the perag with
+	 * the reference we get here even if the filestreams association is torn
+	 * down immediately after we mark the lookup as done.
+	 */
+	pag = container_of(mru, struct xfs_fstrm_item, mru)->pag;
+	atomic_inc(&pag->pag_active_ref);
+	xfs_mru_cache_done(mp->m_filestream);
 
-	mru = xfs_mru_cache_lookup(mp->m_filestream, pip->i_ino);
-	if (mru) {
-		ag = container_of(mru, struct xfs_fstrm_item, mru)->ag;
-		xfs_mru_cache_done(mp->m_filestream);
+	trace_xfs_filestream_lookup(pag, ap->ip->i_ino);
 
-		trace_xfs_filestream_lookup(mp, ip->i_ino, ag);
-		goto out;
-	}
+	ap->blkno = XFS_AGB_TO_FSB(args->mp, pag->pag_agno, 0);
+	xfs_bmap_adjacent(ap);
 
 	/*
-	 * Set the starting AG using the rotor for inode32, otherwise
-	 * use the directory inode's AG.
+	 * If there is very little free space before we start a filestreams
+	 * allocation, we're almost guaranteed to fail to find a large enough
+	 * free space available so just use the cached AG.
 	 */
-	if (xfs_is_inode32(mp)) {
-		xfs_agnumber_t	 rotorstep = xfs_rotorstep;
-		startag = (mp->m_agfrotor / rotorstep) % mp->m_sb.sb_agcount;
-		mp->m_agfrotor = (mp->m_agfrotor + 1) %
-		                 (mp->m_sb.sb_agcount * rotorstep);
-	} else
-		startag = XFS_INO_TO_AGNO(mp, pip->i_ino);
+	if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
+		*longest = 1;
+		goto out_done;
+	}
 
-	if (xfs_filestream_pick_ag(pip, startag, &ag, 0, 0))
-		ag = NULLAGNUMBER;
-out:
-	xfs_irele(pip);
-	return ag;
+	error = xfs_bmap_longest_free_extent(pag, args->tp, longest);
+	if (error == -EAGAIN)
+		error = 0;
+	if (error || *longest < args->maxlen) {
+		/* We aren't going to use this perag */
+		*longest = 0;
+		xfs_perag_rele(pag);
+		return error;
+	}
+
+out_done:
+	args->pag = pag;
+	return 0;
 }
 
-/*
- * Pick a new allocation group for the current file and its file stream.
- *
- * This is called when the allocator can't find a suitable extent in the
- * current AG, and we have to move the stream into a new AG with more space.
- */
-int
-xfs_filestream_new_ag(
+static int
+xfs_filestream_create_association(
 	struct xfs_bmalloca	*ap,
-	xfs_agnumber_t		*agp)
+	struct xfs_alloc_arg	*args,
+	xfs_ino_t		pino,
+	xfs_extlen_t		*longest)
 {
-	struct xfs_inode	*ip = ap->ip, *pip;
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_extlen_t		minlen = ap->length;
-	xfs_agnumber_t		startag = 0;
-	int			flags = 0;
-	int			err = 0;
+	struct xfs_mount	*mp = args->mp;
 	struct xfs_mru_cache_elem *mru;
+	struct xfs_fstrm_item	*item;
+	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, pino);
+	int			flags = 0;
+	int			error;
 
-	*agp = NULLAGNUMBER;
-
-	pip = xfs_filestream_get_parent(ip);
-	if (!pip)
-		goto exit;
-
-	mru = xfs_mru_cache_remove(mp->m_filestream, pip->i_ino);
+	/* Changing parent AG association now, so remove the existing one. */
+	mru = xfs_mru_cache_remove(mp->m_filestream, pino);
 	if (mru) {
 		struct xfs_fstrm_item *item =
 			container_of(mru, struct xfs_fstrm_item, mru);
-		startag = (item->ag + 1) % mp->m_sb.sb_agcount;
+
+		agno = (item->pag->pag_agno + 1) % mp->m_sb.sb_agcount;
+		xfs_fstrm_free_func(mp, mru);
+	} else if (xfs_is_inode32(mp)) {
+		xfs_agnumber_t	 rotorstep = xfs_rotorstep;
+
+		agno = (mp->m_agfrotor / rotorstep) % mp->m_sb.sb_agcount;
+		mp->m_agfrotor = (mp->m_agfrotor + 1) %
+				 (mp->m_sb.sb_agcount * rotorstep);
 	}
 
+	ap->blkno = XFS_AGB_TO_FSB(args->mp, agno, 0);
+	xfs_bmap_adjacent(ap);
+
 	if (ap->datatype & XFS_ALLOC_USERDATA)
 		flags |= XFS_PICK_USERDATA;
 	if (ap->tp->t_flags & XFS_TRANS_LOWMODE)
 		flags |= XFS_PICK_LOWSPACE;
 
-	err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);
+	*longest = ap->length;
+	error = xfs_filestream_pick_ag(args, pino, agno, flags, longest);
+	if (error)
+		return error;
 
 	/*
-	 * Only free the item here so we skip over the old AG earlier.
+	 * We are going to use this perag now, so create an assoication for it.
+	 * xfs_filestream_pick_ag() has already bumped the perag fstrms counter
+	 * for us, so all we need to do here is take another active reference to
+	 * the perag for the cached association.
+	 *
+	 * If we fail to store the association, we need to drop the fstrms
+	 * counter as well as drop the perag reference we take here for the
+	 * item. We do not need to return an error for this failure - as long as
+	 * we return a referenced AG, the allocation can still go ahead just
+	 * fine.
 	 */
-	if (mru)
-		xfs_fstrm_free_func(mp, mru);
+	item = kmem_alloc(sizeof(*item), KM_MAYFAIL);
+	if (!item)
+		goto out_put_fstrms;
+
+	atomic_inc(&args->pag->pag_active_ref);
+	item->pag = args->pag;
+	error = xfs_mru_cache_insert(mp->m_filestream, pino, &item->mru);
+	if (error)
+		goto out_free_item;
+	return 0;
+
+out_free_item:
+	xfs_perag_rele(item->pag);
+	kmem_free(item);
+out_put_fstrms:
+	atomic_dec(&args->pag->pagf_fstrms);
+	return 0;
+}
+
+/*
+ * Search for an allocation group with a single extent large enough for
+ * the request. First we look for an existing association and use that if it
+ * is found. Otherwise, we create a new association by selecting an AG that fits
+ * the allocation criteria.
+ *
+ * We return with a referenced perag in args->pag to indicate which AG we are
+ * allocating into or an error with no references held.
+ */
+int
+xfs_filestream_select_ag(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_extlen_t		*longest)
+{
+	struct xfs_mount	*mp = args->mp;
+	struct xfs_inode	*pip;
+	xfs_ino_t		ino = 0;
+	int			error = 0;
+
+	*longest = 0;
+	args->total = ap->total;
+	pip = xfs_filestream_get_parent(ap->ip);
+	if (pip) {
+		ino = pip->i_ino;
+		error = xfs_filestream_lookup_association(ap, args, ino,
+				longest);
+		xfs_irele(pip);
+		if (error)
+			return error;
+		if (*longest >= args->maxlen)
+			goto out_select;
+		if (ap->tp->t_flags & XFS_TRANS_LOWMODE)
+			goto out_select;
+	}
+
+	error = xfs_filestream_create_association(ap, args, ino, longest);
+	if (error)
+		return error;
 
-	xfs_irele(pip);
-exit:
-	if (*agp == NULLAGNUMBER)
-		*agp = 0;
-	return err;
+out_select:
+	ap->blkno = XFS_AGB_TO_FSB(mp, args->pag->pag_agno, 0);
+	return 0;
 }
 
 void
diff --git a/fs/xfs/xfs_filestream.h b/fs/xfs/xfs_filestream.h
index 403226ebb80b..84149ed0e340 100644
--- a/fs/xfs/xfs_filestream.h
+++ b/fs/xfs/xfs_filestream.h
@@ -9,13 +9,13 @@
 struct xfs_mount;
 struct xfs_inode;
 struct xfs_bmalloca;
+struct xfs_alloc_arg;
 
 int xfs_filestream_mount(struct xfs_mount *mp);
 void xfs_filestream_unmount(struct xfs_mount *mp);
 void xfs_filestream_deassociate(struct xfs_inode *ip);
-xfs_agnumber_t xfs_filestream_lookup_ag(struct xfs_inode *ip);
-int xfs_filestream_new_ag(struct xfs_bmalloca *ap, xfs_agnumber_t *agp);
-int xfs_filestream_peek_ag(struct xfs_mount *mp, xfs_agnumber_t agno);
+int xfs_filestream_select_ag(struct xfs_bmalloca *ap,
+		struct xfs_alloc_arg *args, xfs_extlen_t *blen);
 
 static inline int
 xfs_inode_is_filestream(
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 88a88506ffff..120d284a03fe 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -688,11 +688,11 @@ __xfs_getfsmap_datadev(
 		info->agf_bp = NULL;
 	}
 	if (info->pag) {
-		xfs_perag_put(info->pag);
+		xfs_perag_rele(info->pag);
 		info->pag = NULL;
 	} else if (pag) {
 		/* loop termination case */
-		xfs_perag_put(pag);
+		xfs_perag_rele(pag);
 	}
 
 	return error;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index ddeaccc04aec..c9a7e270a428 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -255,7 +255,7 @@ xfs_perag_set_inode_tag(
 		break;
 	}
 
-	trace_xfs_perag_set_inode_tag(mp, pag->pag_agno, tag, _RET_IP_);
+	trace_xfs_perag_set_inode_tag(pag, _RET_IP_);
 }
 
 /* Clear a tag on both the AG incore inode tree and the AG radix tree. */
@@ -289,7 +289,7 @@ xfs_perag_clear_inode_tag(
 	radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno, tag);
 	spin_unlock(&mp->m_perag_lock);
 
-	trace_xfs_perag_clear_inode_tag(mp, pag->pag_agno, tag, _RET_IP_);
+	trace_xfs_perag_clear_inode_tag(pag, _RET_IP_);
 }
 
 /*
@@ -586,7 +586,7 @@ xfs_iget_cache_miss(
 	if (!ip)
 		return -ENOMEM;
 
-	error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, flags);
+	error = xfs_imap(pag, tp, ip->i_ino, &ip->i_imap, flags);
 	if (error)
 		goto out_destroy;
 
@@ -1767,7 +1767,7 @@ xfs_icwalk(
 		if (error) {
 			last_error = error;
 			if (error == -EFSCORRUPTED) {
-				xfs_perag_put(pag);
+				xfs_perag_rele(pag);
 				break;
 			}
 		}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index d354ea2b74f9..dbe274b8065d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1367,7 +1367,7 @@ xfs_itruncate_extents_flags(
 
 	unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
 	while (unmap_len > 0) {
-		ASSERT(tp->t_firstblock == NULLFSBLOCK);
+		ASSERT(tp->t_highest_agno == NULLAGNUMBER);
 		error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
 				flags, XFS_ITRUNC_MAX_EXTENTS);
 		if (error)
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index 7558486f4937..21be93bf006d 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -275,7 +275,7 @@ xfs_iwalk_ag_start(
 
 	/* Set up a fresh cursor and empty the inobt cache. */
 	iwag->nr_recs = 0;
-	error = xfs_inobt_cur(mp, tp, pag, XFS_BTNUM_INO, curpp, agi_bpp);
+	error = xfs_inobt_cur(pag, tp, XFS_BTNUM_INO, curpp, agi_bpp);
 	if (error)
 		return error;
 
@@ -390,7 +390,7 @@ xfs_iwalk_run_callbacks(
 	}
 
 	/* ...and recreate the cursor just past where we left off. */
-	error = xfs_inobt_cur(mp, iwag->tp, iwag->pag, XFS_BTNUM_INO, curpp,
+	error = xfs_inobt_cur(iwag->pag, iwag->tp, XFS_BTNUM_INO, curpp,
 			agi_bpp);
 	if (error)
 		return error;
@@ -591,7 +591,7 @@ xfs_iwalk(
 	}
 
 	if (iwag.pag)
-		xfs_perag_put(pag);
+		xfs_perag_rele(pag);
 	xfs_iwalk_free(&iwag);
 	return error;
 }
@@ -683,7 +683,7 @@ xfs_iwalk_threaded(
 			break;
 	}
 	if (pag)
-		xfs_perag_put(pag);
+		xfs_perag_rele(pag);
 	if (polled)
 		xfs_pwork_poll(&pctl);
 	return xfs_pwork_destroy(&pctl);
@@ -776,7 +776,7 @@ xfs_inobt_walk(
 	}
 
 	if (iwag.pag)
-		xfs_perag_put(pag);
+		xfs_perag_rele(pag);
 	xfs_iwalk_free(&iwag);
 	return error;
 }
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 8aca2cc173ac..f3269c0626f0 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -210,8 +210,7 @@ typedef struct xfs_mount {
 	struct xfs_error_cfg	m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX];
 	struct xstats		m_stats;	/* per-fs stats */
 	xfs_agnumber_t		m_agfrotor;	/* last ag where space found */
-	xfs_agnumber_t		m_agirotor;	/* last ag dir inode alloced */
-	spinlock_t		m_agirotor_lock;/* .. and lock protecting it */
+	atomic_t		m_agirotor;	/* last ag dir inode alloced */
 
 	/* Memory shrinker to throttle and reprioritize inodegc */
 	struct shrinker		m_inodegc_shrinker;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 5535778a98f9..f5dc46ce9803 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -610,7 +610,7 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
+			ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER);
 
 			/* Free the CoW orphan record. */
 			xfs_refcount_free_cow_extent(*tpp, del.br_startblock,
@@ -927,7 +927,7 @@ xfs_reflink_recover_cow(
 	for_each_perag(mp, agno, pag) {
 		error = xfs_refcount_recover_cow_leftovers(mp, pag);
 		if (error) {
-			xfs_perag_put(pag);
+			xfs_perag_rele(pag);
 			break;
 		}
 	}
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 0c4b73e9b29d..2479b5cbd75e 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -247,6 +247,32 @@ xfs_fs_show_options(
 	return 0;
 }
 
+static bool
+xfs_set_inode_alloc_perag(
+	struct xfs_perag	*pag,
+	xfs_ino_t		ino,
+	xfs_agnumber_t		max_metadata)
+{
+	if (!xfs_is_inode32(pag->pag_mount)) {
+		set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
+		clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
+		return false;
+	}
+
+	if (ino > XFS_MAXINUMBER_32) {
+		clear_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
+		clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
+		return false;
+	}
+
+	set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
+	if (pag->pag_agno < max_metadata)
+		set_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
+	else
+		clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
+	return true;
+}
+
 /*
  * Set parameters for inode allocation heuristics, taking into account
  * filesystem size and inode32/inode64 mount options; i.e. specifically
@@ -310,24 +336,8 @@ xfs_set_inode_alloc(
 		ino = XFS_AGINO_TO_INO(mp, index, agino);
 
 		pag = xfs_perag_get(mp, index);
-
-		if (xfs_is_inode32(mp)) {
-			if (ino > XFS_MAXINUMBER_32) {
-				pag->pagi_inodeok = 0;
-				pag->pagf_metadata = 0;
-			} else {
-				pag->pagi_inodeok = 1;
-				maxagi++;
-				if (index < max_metadata)
-					pag->pagf_metadata = 1;
-				else
-					pag->pagf_metadata = 0;
-			}
-		} else {
-			pag->pagi_inodeok = 1;
-			pag->pagf_metadata = 0;
-		}
-
+		if (xfs_set_inode_alloc_perag(pag, ino, max_metadata))
+			maxagi++;
 		xfs_perag_put(pag);
 	}
 
@@ -1922,7 +1932,6 @@ static int xfs_init_fs_context(
 		return -ENOMEM;
 
 	spin_lock_init(&mp->m_sb_lock);
-	spin_lock_init(&mp->m_agirotor_lock);
 	INIT_RADIX_TREE(&mp->m_perag_tree, GFP_ATOMIC);
 	spin_lock_init(&mp->m_perag_lock);
 	mutex_init(&mp->m_growlock);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 6b0e9ae7c513..7dc0fd6a6504 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -74,6 +74,7 @@ struct xfs_inobt_rec_incore;
 union xfs_btree_ptr;
 struct xfs_dqtrx;
 struct xfs_icwalk;
+struct xfs_perag;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -159,36 +160,40 @@ TRACE_EVENT(xlog_intent_recovery_failed,
 );
 
 DECLARE_EVENT_CLASS(xfs_perag_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int refcount,
-		 unsigned long caller_ip),
-	TP_ARGS(mp, agno, refcount, caller_ip),
+	TP_PROTO(struct xfs_perag *pag, unsigned long caller_ip),
+	TP_ARGS(pag, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
 		__field(int, refcount)
+		__field(int, active_refcount)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->refcount = refcount;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->refcount = atomic_read(&pag->pag_ref);
+		__entry->active_refcount = atomic_read(&pag->pag_active_ref);
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d agno 0x%x refcount %d caller %pS",
+	TP_printk("dev %d:%d agno 0x%x passive refs %d active refs %d caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->refcount,
+		  __entry->active_refcount,
 		  (char *)__entry->caller_ip)
 );
 
 #define DEFINE_PERAG_REF_EVENT(name)	\
 DEFINE_EVENT(xfs_perag_class, name,	\
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int refcount,	\
-		 unsigned long caller_ip),					\
-	TP_ARGS(mp, agno, refcount, caller_ip))
+	TP_PROTO(struct xfs_perag *pag, unsigned long caller_ip), \
+	TP_ARGS(pag, caller_ip))
 DEFINE_PERAG_REF_EVENT(xfs_perag_get);
 DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag);
 DEFINE_PERAG_REF_EVENT(xfs_perag_put);
+DEFINE_PERAG_REF_EVENT(xfs_perag_grab);
+DEFINE_PERAG_REF_EVENT(xfs_perag_grab_tag);
+DEFINE_PERAG_REF_EVENT(xfs_perag_rele);
 DEFINE_PERAG_REF_EVENT(xfs_perag_set_inode_tag);
 DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
 
@@ -634,8 +639,8 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
 
 DECLARE_EVENT_CLASS(xfs_filestream_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino, xfs_agnumber_t agno),
-	TP_ARGS(mp, ino, agno),
+	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino),
+	TP_ARGS(pag, ino),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_ino_t, ino)
@@ -643,10 +648,10 @@ DECLARE_EVENT_CLASS(xfs_filestream_class,
 		__field(int, streams)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
 		__entry->ino = ino;
-		__entry->agno = agno;
-		__entry->streams = xfs_filestream_peek_ag(mp, agno);
+		__entry->agno = pag->pag_agno;
+		__entry->streams = atomic_read(&pag->pagf_fstrms);
 	),
 	TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -656,39 +661,40 @@ DECLARE_EVENT_CLASS(xfs_filestream_class,
 )
 #define DEFINE_FILESTREAM_EVENT(name) \
 DEFINE_EVENT(xfs_filestream_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino, xfs_agnumber_t agno), \
-	TP_ARGS(mp, ino, agno))
+	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino), \
+	TP_ARGS(pag, ino))
 DEFINE_FILESTREAM_EVENT(xfs_filestream_free);
 DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup);
 DEFINE_FILESTREAM_EVENT(xfs_filestream_scan);
 
 TRACE_EVENT(xfs_filestream_pick,
-	TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno,
-		 xfs_extlen_t free, int nscan),
-	TP_ARGS(ip, agno, free, nscan),
+	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino, xfs_extlen_t free),
+	TP_ARGS(pag, ino, free),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_ino_t, ino)
 		__field(xfs_agnumber_t, agno)
 		__field(int, streams)
 		__field(xfs_extlen_t, free)
-		__field(int, nscan)
 	),
 	TP_fast_assign(
-		__entry->dev = VFS_I(ip)->i_sb->s_dev;
-		__entry->ino = ip->i_ino;
-		__entry->agno = agno;
-		__entry->streams = xfs_filestream_peek_ag(ip->i_mount, agno);
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->ino = ino;
+		if (pag) {
+			__entry->agno = pag->pag_agno;
+			__entry->streams = atomic_read(&pag->pagf_fstrms);
+		} else {
+			__entry->agno = NULLAGNUMBER;
+			__entry->streams = 0;
+		}
 		__entry->free = free;
-		__entry->nscan = nscan;
 	),
-	TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d free %d nscan %d",
+	TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d free %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->agno,
 		  __entry->streams,
-		  __entry->free,
-		  __entry->nscan)
+		  __entry->free)
 );
 
 DECLARE_EVENT_CLASS(xfs_lock_class,
@@ -1795,13 +1801,11 @@ DECLARE_EVENT_CLASS(xfs_alloc_class,
 		__field(xfs_extlen_t, alignment)
 		__field(xfs_extlen_t, minalignslop)
 		__field(xfs_extlen_t, len)
-		__field(short, type)
-		__field(short, otype)
 		__field(char, wasdel)
 		__field(char, wasfromfl)
 		__field(int, resv)
 		__field(int, datatype)
-		__field(xfs_fsblock_t, firstblock)
+		__field(xfs_agnumber_t, highest_agno)
 	),
 	TP_fast_assign(
 		__entry->dev = args->mp->m_super->s_dev;
@@ -1816,18 +1820,16 @@ DECLARE_EVENT_CLASS(xfs_alloc_class,
 		__entry->alignment = args->alignment;
 		__entry->minalignslop = args->minalignslop;
 		__entry->len = args->len;
-		__entry->type = args->type;
-		__entry->otype = args->otype;
 		__entry->wasdel = args->wasdel;
 		__entry->wasfromfl = args->wasfromfl;
 		__entry->resv = args->resv;
 		__entry->datatype = args->datatype;
-		__entry->firstblock = args->tp->t_firstblock;
+		__entry->highest_agno = args->tp->t_highest_agno;
 	),
 	TP_printk("dev %d:%d agno 0x%x agbno 0x%x minlen %u maxlen %u mod %u "
 		  "prod %u minleft %u total %u alignment %u minalignslop %u "
-		  "len %u type %s otype %s wasdel %d wasfromfl %d resv %d "
-		  "datatype 0x%x firstblock 0x%llx",
+		  "len %u wasdel %d wasfromfl %d resv %d "
+		  "datatype 0x%x highest_agno 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->agbno,
@@ -1840,13 +1842,11 @@ DECLARE_EVENT_CLASS(xfs_alloc_class,
 		  __entry->alignment,
 		  __entry->minalignslop,
 		  __entry->len,
-		  __print_symbolic(__entry->type, XFS_ALLOC_TYPES),
-		  __print_symbolic(__entry->otype, XFS_ALLOC_TYPES),
 		  __entry->wasdel,
 		  __entry->wasfromfl,
 		  __entry->resv,
 		  __entry->datatype,
-		  (unsigned long long)__entry->firstblock)
+		  __entry->highest_agno)
 )
 
 #define DEFINE_ALLOC_EVENT(name) \
@@ -1877,6 +1877,7 @@ DEFINE_ALLOC_EVENT(xfs_alloc_small_notenough);
 DEFINE_ALLOC_EVENT(xfs_alloc_small_done);
 DEFINE_ALLOC_EVENT(xfs_alloc_small_error);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_badargs);
+DEFINE_ALLOC_EVENT(xfs_alloc_vextent_skip_deadlock);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_nofix);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_noagbp);
 DEFINE_ALLOC_EVENT(xfs_alloc_vextent_loopfailed);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 7bd16fbff534..8afc0c080861 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -102,7 +102,7 @@ xfs_trans_dup(
 	INIT_LIST_HEAD(&ntp->t_items);
 	INIT_LIST_HEAD(&ntp->t_busy);
 	INIT_LIST_HEAD(&ntp->t_dfops);
-	ntp->t_firstblock = NULLFSBLOCK;
+	ntp->t_highest_agno = NULLAGNUMBER;
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
@@ -278,7 +278,7 @@ retry:
 	INIT_LIST_HEAD(&tp->t_items);
 	INIT_LIST_HEAD(&tp->t_busy);
 	INIT_LIST_HEAD(&tp->t_dfops);
-	tp->t_firstblock = NULLFSBLOCK;
+	tp->t_highest_agno = NULLAGNUMBER;
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error == -ENOSPC && want_retry) {
@@ -1078,10 +1078,10 @@ xfs_trans_cancel(
 	/*
 	 * It's never valid to cancel a transaction with deferred ops attached,
 	 * because the transaction is effectively dirty.  Complain about this
-	 * loudly before freeing the in-memory defer items.
+	 * loudly before freeing the in-memory defer items and shutting down the
+	 * filesystem.
 	 */
 	if (!list_empty(&tp->t_dfops)) {
-		ASSERT(xfs_is_shutdown(mp) || list_empty(&tp->t_dfops));
 		ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 		dirty = true;
 		xfs_defer_cancel(tp);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 55819785941c..6e3646d524ce 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -132,7 +132,7 @@ typedef struct xfs_trans {
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
 	unsigned int		t_flags;	/* misc flags */
-	xfs_fsblock_t		t_firstblock;	/* first block allocated */
+	xfs_agnumber_t		t_highest_agno;	/* highest AGF locked */
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */