Merge tag 'xfs-6.3-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull moar xfs updates from Darrick Wong:
 "This contains a fix for a deadlock in the allocator. It continues the
  slow march towards being able to offline AGs, and it refactors the
  interface to the xfs allocator to be less indirection happy.

  Summary:

   - Fix a deadlock in the free space allocator due to the AG-walking
     algorithm forgetting to follow AG-order locking rules

   - Make the inode allocator prefer existing free inodes instead of
     failing to allocate new inode chunks when free space is low

   - Set minleft correctly when setting allocator parameters for bmap
     changes

   - Fix uninitialized variable access in the getfsmap code

   - Make a distinction between active and passive per-AG structure
     references. For now, active references are taken to perform some
     work in an AG on behalf of a high level operation; passive
     references are used by lower level code to finish operations
     started by other threads. Eventually this will become part of
     online shrink

   - Split out all the different allocator strategies into separate
     functions to move us away from design antipattern of filling out a
     huge structure for various differentish things and issuing a single
     function multiplexing call

   - Various cleanups in the filestreams allocator code, which we might
     very well want to deprecate instead of continuing

   - Fix a bug with the agi rotor code that was introduced earlier in
     this series"

* tag 'xfs-6.3-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (44 commits)
  xfs: restore old agirotor behavior
  xfs: fix uninitialized variable access
  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()
  ...

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;
 

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 */

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;
 

fs/xfs/libxfs/xfs_alloc.h

@@ -16,25 +16,6 @@ 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.
  */
@@ -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.

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)

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,

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

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;

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__ */

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;

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);

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)

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)

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;

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;
 }

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;
 		}
 	}

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:

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 @@ xchk_fscount_aggregate_agcounts(
 			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 @@ xchk_fscount_aggregate_agcounts(
 
 	}
 	if (pag)
-		xfs_perag_put(pag);
+		xfs_perag_rele(pag);
 	if (error) {
 		xchk_set_incomplete(sc);
 		return error;

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)

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 */

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;
+			}
 		}
 	}
 

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(

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;
@@ -761,6 +761,7 @@ xfs_getfsmap_datadev_bnobt(
 {
 	struct xfs_alloc_rec_incore	akeys[2];
 
+	memset(akeys, 0, sizeof(akeys));
 	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
 	return __xfs_getfsmap_datadev(tp, keys, info,
 			xfs_getfsmap_datadev_bnobt_query, &akeys[0]);

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;
 			}
 		}

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)

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;
 }

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;

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;
 		}
 	}

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);

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);

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 @@ xfs_trans_alloc(
 	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);

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 */