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()
  ...

Author: torvalds

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,
@@ -77,21 +75,78 @@ 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;
 }
 
 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;