Merge tag 'xfs-6.12-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Chandan Babu:
 "New code:

   - Introduce new ioctls to exchange contents of two files.

     The first ioctl does the preparation work to exchange the contents
     of two files while the second ioctl performs the actual exchange if
     the target file has not been changed since a given sampling point.

  Fixes:

   - Fix bugs associated with calculating the maximum range of realtime
     extents to scan for free space.

   - Copy keys instead of records when resizing the incore BMBT root
     block.

   - Do not report FITRIMming more bytes than possibly exist in the
     filesystem.

   - Modify xfs_fs.h to prevent C++ compilation errors.

   - Do not over eagerly free post-EOF speculative preallocation.

   - Ensure st_blocks never goes to zero during COW writes

  Cleanups/refactors:

   - Use Xarray to hold per-AG data instead of a Radix tree.

   - Cleanups to:
      - realtime bitmap
      - inode allocator
      - quota
      - inode rooted btree code"

* tag 'xfs-6.12-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (61 commits)
  xfs: ensure st_blocks never goes to zero during COW writes
  xfs: use xas_for_each_marked in xfs_reclaim_inodes_count
  xfs: convert perag lookup to xarray
  xfs: simplify tagged perag iteration
  xfs: move the tagged perag lookup helpers to xfs_icache.c
  xfs: use kfree_rcu_mightsleep to free the perag structures
  xfs: use LIST_HEAD() to simplify code
  xfs: Remove duplicate xfs_trans_priv.h header
  xfs: remove unnecessary check
  xfs: Use xfs set and clear mp state helpers
  xfs: reclaim speculative preallocations for append only files
  xfs: simplify extent lookup in xfs_can_free_eofblocks
  xfs: check XFS_EOFBLOCKS_RELEASED earlier in xfs_release_eofblocks
  xfs: only free posteof blocks on first close
  xfs: don't free post-EOF blocks on read close
  xfs: skip all of xfs_file_release when shut down
  xfs: don't bother returning errors from xfs_file_release
  xfs: refactor f_op->release handling
  xfs: remove the i_mode check in xfs_release
  xfs: standardize the btree maxrecs function parameters
  ...

1 files changed, 61 insertions, 28 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index cf629302d48e..20d9924f28c2 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -65,6 +65,18 @@ static int xfs_icwalk_ag(struct xfs_perag *pag,
 					 XFS_ICWALK_FLAG_RECLAIM_SICK | \
 					 XFS_ICWALK_FLAG_UNION)
 
+/* Marks for the perag xarray */
+#define XFS_PERAG_RECLAIM_MARK	XA_MARK_0
+#define XFS_PERAG_BLOCKGC_MARK	XA_MARK_1
+
+static inline xa_mark_t ici_tag_to_mark(unsigned int tag)
+{
+	if (tag == XFS_ICI_RECLAIM_TAG)
+		return XFS_PERAG_RECLAIM_MARK;
+	ASSERT(tag == XFS_ICI_BLOCKGC_TAG);
+	return XFS_PERAG_BLOCKGC_MARK;
+}
+
 /*
  * Allocate and initialise an xfs_inode.
  */
@@ -191,7 +203,7 @@ xfs_reclaim_work_queue(
 {
 
 	rcu_read_lock();
-	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
+	if (xa_marked(&mp->m_perags, XFS_PERAG_RECLAIM_MARK)) {
 		queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
 			msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
 	}
@@ -241,9 +253,7 @@ xfs_perag_set_inode_tag(
 		return;
 
 	/* propagate the tag up into the perag radix tree */
-	spin_lock(&mp->m_perag_lock);
-	radix_tree_tag_set(&mp->m_perag_tree, pag->pag_agno, tag);
-	spin_unlock(&mp->m_perag_lock);
+	xa_set_mark(&mp->m_perags, pag->pag_agno, ici_tag_to_mark(tag));
 
 	/* start background work */
 	switch (tag) {
@@ -285,14 +295,39 @@ xfs_perag_clear_inode_tag(
 		return;
 
 	/* clear the tag from the perag radix tree */
-	spin_lock(&mp->m_perag_lock);
-	radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno, tag);
-	spin_unlock(&mp->m_perag_lock);
+	xa_clear_mark(&mp->m_perags, pag->pag_agno, ici_tag_to_mark(tag));
 
 	trace_xfs_perag_clear_inode_tag(pag, _RET_IP_);
 }
 
 /*
+ * Find the next AG after @pag, or the first AG if @pag is NULL.
+ */
+static struct xfs_perag *
+xfs_perag_grab_next_tag(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	int			tag)
+{
+	unsigned long		index = 0;
+
+	if (pag) {
+		index = pag->pag_agno + 1;
+		xfs_perag_rele(pag);
+	}
+
+	rcu_read_lock();
+	pag = xa_find(&mp->m_perags, &index, ULONG_MAX, ici_tag_to_mark(tag));
+	if (pag) {
+		trace_xfs_perag_grab_next_tag(pag, _RET_IP_);
+		if (!atomic_inc_not_zero(&pag->pag_active_ref))
+			pag = NULL;
+	}
+	rcu_read_unlock();
+	return pag;
+}
+
+/*
  * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
  * part of the structure. This is made more complex by the fact we store
  * information about the on-disk values in the VFS inode and so we can't just
@@ -755,7 +790,7 @@ xfs_iget(
 	ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);
 
 	/* reject inode numbers outside existing AGs */
-	if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
+	if (!xfs_verify_ino(mp, ino))
 		return -EINVAL;
 
 	XFS_STATS_INC(mp, xs_ig_attempts);
@@ -977,7 +1012,7 @@ xfs_reclaim_inodes(
 	if (xfs_want_reclaim_sick(mp))
 		icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK;
 
-	while (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
+	while (xa_marked(&mp->m_perags, XFS_PERAG_RECLAIM_MARK)) {
 		xfs_ail_push_all_sync(mp->m_ail);
 		xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw);
 	}
@@ -1019,15 +1054,17 @@ long
 xfs_reclaim_inodes_count(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		ag = 0;
+	XA_STATE		(xas, &mp->m_perags, 0);
 	long			reclaimable = 0;
+	struct xfs_perag	*pag;
 
-	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
-		ag = pag->pag_agno + 1;
+	rcu_read_lock();
+	xas_for_each_marked(&xas, pag, ULONG_MAX, XFS_PERAG_RECLAIM_MARK) {
+		trace_xfs_reclaim_inodes_count(pag, _THIS_IP_);
 		reclaimable += pag->pag_ici_reclaimable;
-		xfs_perag_put(pag);
 	}
+	rcu_read_unlock();
+
 	return reclaimable;
 }
 
@@ -1159,7 +1196,7 @@ xfs_inode_free_eofblocks(
 	if (xfs_can_free_eofblocks(ip))
 		return xfs_free_eofblocks(ip);
 
-	/* inode could be preallocated or append-only */
+	/* inode could be preallocated */
 	trace_xfs_inode_free_eofblocks_invalid(ip);
 	xfs_inode_clear_eofblocks_tag(ip);
 	return 0;
@@ -1369,14 +1406,13 @@ void
 xfs_blockgc_start(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 
 	if (xfs_set_blockgc_enabled(mp))
 		return;
 
 	trace_xfs_blockgc_start(mp, __return_address);
-	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+	while ((pag = xfs_perag_grab_next_tag(mp, pag, XFS_ICI_BLOCKGC_TAG)))
 		xfs_blockgc_queue(pag);
 }
 
@@ -1492,21 +1528,19 @@ int
 xfs_blockgc_flush_all(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 
 	trace_xfs_blockgc_flush_all(mp, __return_address);
 
 	/*
-	 * For each blockgc worker, move its queue time up to now.  If it
-	 * wasn't queued, it will not be requeued.  Then flush whatever's
-	 * left.
+	 * For each blockgc worker, move its queue time up to now.  If it wasn't
+	 * queued, it will not be requeued.  Then flush whatever is left.
 	 */
-	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+	while ((pag = xfs_perag_grab_next_tag(mp, pag, XFS_ICI_BLOCKGC_TAG)))
 		mod_delayed_work(pag->pag_mount->m_blockgc_wq,
 				&pag->pag_blockgc_work, 0);
 
-	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+	while ((pag = xfs_perag_grab_next_tag(mp, pag, XFS_ICI_BLOCKGC_TAG)))
 		flush_delayed_work(&pag->pag_blockgc_work);
 
 	return xfs_inodegc_flush(mp);
@@ -1752,12 +1786,11 @@ xfs_icwalk(
 	enum xfs_icwalk_goal	goal,
 	struct xfs_icwalk	*icw)
 {
-	struct xfs_perag	*pag;
+	struct xfs_perag	*pag = NULL;
 	int			error = 0;
 	int			last_error = 0;
-	xfs_agnumber_t		agno;
 
-	for_each_perag_tag(mp, agno, pag, goal) {
+	while ((pag = xfs_perag_grab_next_tag(mp, pag, goal))) {
 		error = xfs_icwalk_ag(pag, goal, icw);
 		if (error) {
 			last_error = error;