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, 69 insertions, 3 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f6e4912769a0..e97d789495a5 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1238,12 +1238,78 @@ xfs_dir_open(
 	return error;
 }
 
+/*
+ * Don't bother propagating errors.  We're just doing cleanup, and the caller
+ * ignores the return value anyway.
+ */
 STATIC int
 xfs_file_release(
-	struct inode	*inode,
-	struct file	*filp)
+	struct inode		*inode,
+	struct file		*file)
 {
-	return xfs_release(XFS_I(inode));
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+
+	/*
+	 * If this is a read-only mount or the file system has been shut down,
+	 * don't generate I/O.
+	 */
+	if (xfs_is_readonly(mp) || xfs_is_shutdown(mp))
+		return 0;
+
+	/*
+	 * If we previously truncated this file and removed old data in the
+	 * process, we want to initiate "early" writeout on the last close.
+	 * This is an attempt to combat the notorious NULL files problem which
+	 * is particularly noticeable from a truncate down, buffered (re-)write
+	 * (delalloc), followed by a crash.  What we are effectively doing here
+	 * is significantly reducing the time window where we'd otherwise be
+	 * exposed to that problem.
+	 */
+	if (xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED)) {
+		xfs_iflags_clear(ip, XFS_EOFBLOCKS_RELEASED);
+		if (ip->i_delayed_blks > 0)
+			filemap_flush(inode->i_mapping);
+	}
+
+	/*
+	 * XFS aggressively preallocates post-EOF space to generate contiguous
+	 * allocations for writers that append to the end of the file.
+	 *
+	 * To support workloads that close and reopen the file frequently, these
+	 * preallocations usually persist after a close unless it is the first
+	 * close for the inode.  This is a tradeoff to generate tightly packed
+	 * data layouts for unpacking tarballs or similar archives that write
+	 * one file after another without going back to it while keeping the
+	 * preallocation for files that have recurring open/write/close cycles.
+	 *
+	 * This heuristic is skipped for inodes with the append-only flag as
+	 * that flag is rather pointless for inodes written only once.
+	 *
+	 * There is no point in freeing blocks here for open but unlinked files
+	 * as they will be taken care of by the inactivation path soon.
+	 *
+	 * When releasing a read-only context, don't flush data or trim post-EOF
+	 * blocks.  This avoids open/read/close workloads from removing EOF
+	 * blocks that other writers depend upon to reduce fragmentation.
+	 *
+	 * If we can't get the iolock just skip truncating the blocks past EOF
+	 * because we could deadlock with the mmap_lock otherwise. We'll get
+	 * another chance to drop them once the last reference to the inode is
+	 * dropped, so we'll never leak blocks permanently.
+	 */
+	if (inode->i_nlink &&
+	    (file->f_mode & FMODE_WRITE) &&
+	    !(ip->i_diflags & XFS_DIFLAG_APPEND) &&
+	    !xfs_iflags_test(ip, XFS_EOFBLOCKS_RELEASED) &&
+	    xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+		if (xfs_can_free_eofblocks(ip) &&
+		    !xfs_iflags_test_and_set(ip, XFS_EOFBLOCKS_RELEASED))
+			xfs_free_eofblocks(ip);
+		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	}
+
+	return 0;
 }
 
 STATIC int