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, 194 insertions, 76 deletions

diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 386b672c5058..27a4472402ba 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -13,6 +13,8 @@
 #include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
 #include "xfs_trans.h"
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
@@ -69,7 +71,7 @@ xfs_rtbuf_cache_relse(
  * Get a buffer for the bitmap or summary file block specified.
  * The buffer is returned read and locked.
  */
-int
+static int
 xfs_rtbuf_get(
 	struct xfs_rtalloc_args	*args,
 	xfs_fileoff_t		block,	/* block number in bitmap or summary */
@@ -138,15 +140,43 @@ xfs_rtbuf_get(
 	return 0;
 }
 
+int
+xfs_rtbitmap_read_buf(
+	struct xfs_rtalloc_args		*args,
+	xfs_fileoff_t			block)
+{
+	struct xfs_mount		*mp = args->mp;
+
+	if (XFS_IS_CORRUPT(mp, block >= mp->m_sb.sb_rbmblocks)) {
+		xfs_rt_mark_sick(mp, XFS_SICK_RT_BITMAP);
+		return -EFSCORRUPTED;
+	}
+
+	return xfs_rtbuf_get(args, block, 0);
+}
+
+int
+xfs_rtsummary_read_buf(
+	struct xfs_rtalloc_args		*args,
+	xfs_fileoff_t			block)
+{
+	struct xfs_mount		*mp = args->mp;
+
+	if (XFS_IS_CORRUPT(mp, block >= mp->m_rsumblocks)) {
+		xfs_rt_mark_sick(args->mp, XFS_SICK_RT_SUMMARY);
+		return -EFSCORRUPTED;
+	}
+	return xfs_rtbuf_get(args, block, 1);
+}
+
 /*
- * Searching backward from start to limit, find the first block whose
- * allocated/free state is different from start's.
+ * Searching backward from start find the first block whose allocated/free state
+ * is different from start's.
  */
 int
 xfs_rtfind_back(
 	struct xfs_rtalloc_args	*args,
 	xfs_rtxnum_t		start,	/* starting rtext to look at */
-	xfs_rtxnum_t		limit,	/* last rtext to look at */
 	xfs_rtxnum_t		*rtx)	/* out: start rtext found */
 {
 	struct xfs_mount	*mp = args->mp;
@@ -175,7 +205,7 @@ xfs_rtfind_back(
 	 */
 	word = xfs_rtx_to_rbmword(mp, start);
 	bit = (int)(start & (XFS_NBWORD - 1));
-	len = start - limit + 1;
+	len = start + 1;
 	/*
 	 * Compute match value, based on the bit at start: if 1 (free)
 	 * then all-ones, else all-zeroes.
@@ -316,6 +346,8 @@ xfs_rtfind_forw(
 	xfs_rtword_t		incore;
 	unsigned int		word;	/* word number in the buffer */
 
+	ASSERT(start <= limit);
+
 	/*
 	 * Compute and read in starting bitmap block for starting block.
 	 */
@@ -698,7 +730,7 @@ xfs_rtfree_range(
 	 * We need to find the beginning and end of the extent so we can
 	 * properly update the summary.
 	 */
-	error = xfs_rtfind_back(args, start, 0, &preblock);
+	error = xfs_rtfind_back(args, start, &preblock);
 	if (error) {
 		return error;
 	}
@@ -990,25 +1022,24 @@ xfs_rtfree_blocks(
 	xfs_filblks_t		rtlen)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
-	xfs_rtxnum_t		start;
-	xfs_filblks_t		len;
 	xfs_extlen_t		mod;
 
 	ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
 
-	len = xfs_rtb_to_rtxrem(mp, rtlen, &mod);
+	mod = xfs_rtb_to_rtxoff(mp, rtlen);
 	if (mod) {
 		ASSERT(mod == 0);
 		return -EIO;
 	}
 
-	start = xfs_rtb_to_rtxrem(mp, rtbno, &mod);
+	mod = xfs_rtb_to_rtxoff(mp, rtbno);
 	if (mod) {
 		ASSERT(mod == 0);
 		return -EIO;
 	}
 
-	return xfs_rtfree_extent(tp, start, len);
+	return xfs_rtfree_extent(tp, xfs_rtb_to_rtx(mp, rtbno),
+			xfs_rtb_to_rtx(mp, rtlen));
 }
 
 /* Find all the free records within a given range. */
@@ -1016,8 +1047,8 @@ int
 xfs_rtalloc_query_range(
 	struct xfs_mount		*mp,
 	struct xfs_trans		*tp,
-	const struct xfs_rtalloc_rec	*low_rec,
-	const struct xfs_rtalloc_rec	*high_rec,
+	xfs_rtxnum_t			start,
+	xfs_rtxnum_t			end,
 	xfs_rtalloc_query_range_fn	fn,
 	void				*priv)
 {
@@ -1025,45 +1056,42 @@ xfs_rtalloc_query_range(
 		.mp			= mp,
 		.tp			= tp,
 	};
-	struct xfs_rtalloc_rec		rec;
-	xfs_rtxnum_t			rtstart;
-	xfs_rtxnum_t			rtend;
-	xfs_rtxnum_t			high_key;
-	int				is_free;
 	int				error = 0;
 
-	if (low_rec->ar_startext > high_rec->ar_startext)
+	if (start > end)
 		return -EINVAL;
-	if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
-	    low_rec->ar_startext == high_rec->ar_startext)
+	if (start == end || start >= mp->m_sb.sb_rextents)
 		return 0;
 
-	high_key = min(high_rec->ar_startext, mp->m_sb.sb_rextents - 1);
+	end = min(end, mp->m_sb.sb_rextents - 1);
 
 	/* Iterate the bitmap, looking for discrepancies. */
-	rtstart = low_rec->ar_startext;
-	while (rtstart <= high_key) {
+	while (start <= end) {
+		struct xfs_rtalloc_rec	rec;
+		int			is_free;
+		xfs_rtxnum_t		rtend;
+
 		/* Is the first block free? */
-		error = xfs_rtcheck_range(&args, rtstart, 1, 1, &rtend,
+		error = xfs_rtcheck_range(&args, start, 1, 1, &rtend,
 				&is_free);
 		if (error)
 			break;
 
 		/* How long does the extent go for? */
-		error = xfs_rtfind_forw(&args, rtstart, high_key, &rtend);
+		error = xfs_rtfind_forw(&args, start, end, &rtend);
 		if (error)
 			break;
 
 		if (is_free) {
-			rec.ar_startext = rtstart;
-			rec.ar_extcount = rtend - rtstart + 1;
+			rec.ar_startext = start;
+			rec.ar_extcount = rtend - start + 1;
 
 			error = fn(mp, tp, &rec, priv);
 			if (error)
 				break;
 		}
 
-		rtstart = rtend + 1;
+		start = rtend + 1;
 	}
 
 	xfs_rtbuf_cache_relse(&args);
@@ -1078,13 +1106,8 @@ xfs_rtalloc_query_all(
 	xfs_rtalloc_query_range_fn	fn,
 	void				*priv)
 {
-	struct xfs_rtalloc_rec		keys[2];
-
-	keys[0].ar_startext = 0;
-	keys[1].ar_startext = mp->m_sb.sb_rextents - 1;
-	keys[0].ar_extcount = keys[1].ar_extcount = 0;
-
-	return xfs_rtalloc_query_range(mp, tp, &keys[0], &keys[1], fn, priv);
+	return xfs_rtalloc_query_range(mp, tp, 0, mp->m_sb.sb_rextents - 1, fn,
+			priv);
 }
 
 /* Is the given extent all free? */
@@ -1125,21 +1148,6 @@ xfs_rtbitmap_blockcount(
 	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
 }
 
-/*
- * Compute the number of rtbitmap words needed to populate every block of a
- * bitmap that is large enough to track the given number of rt extents.
- */
-unsigned long long
-xfs_rtbitmap_wordcount(
-	struct xfs_mount	*mp,
-	xfs_rtbxlen_t		rtextents)
-{
-	xfs_filblks_t		blocks;
-
-	blocks = xfs_rtbitmap_blockcount(mp, rtextents);
-	return XFS_FSB_TO_B(mp, blocks) >> XFS_WORDLOG;
-}
-
 /* Compute the number of rtsummary blocks needed to track the given rt space. */
 xfs_filblks_t
 xfs_rtsummary_blockcount(
@@ -1153,39 +1161,25 @@ xfs_rtsummary_blockcount(
 	return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
 }
 
-/*
- * Compute the number of rtsummary info words needed to populate every block of
- * a summary file that is large enough to track the given rt space.
- */
-unsigned long long
-xfs_rtsummary_wordcount(
-	struct xfs_mount	*mp,
-	unsigned int		rsumlevels,
-	xfs_extlen_t		rbmblocks)
+/* Lock both realtime free space metadata inodes for a freespace update. */
+void
+xfs_rtbitmap_lock(
+	struct xfs_mount	*mp)
 {
-	xfs_filblks_t		blocks;
-
-	blocks = xfs_rtsummary_blockcount(mp, rsumlevels, rbmblocks);
-	return XFS_FSB_TO_B(mp, blocks) >> XFS_WORDLOG;
+	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
+	xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
 }
 
 /*
- * Lock both realtime free space metadata inodes for a freespace update.  If a
- * transaction is given, the inodes will be joined to the transaction and the
+ * Join both realtime free space metadata inodes to the transaction.  The
  * ILOCKs will be released on transaction commit.
  */
 void
-xfs_rtbitmap_lock(
-	struct xfs_trans	*tp,
-	struct xfs_mount	*mp)
+xfs_rtbitmap_trans_join(
+	struct xfs_trans	*tp)
 {
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
-	if (tp)
-		xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
-
-	xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
-	if (tp)
-		xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, tp->t_mountp->m_rbmip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, tp->t_mountp->m_rsumip, XFS_ILOCK_EXCL);
 }
 
 /* Unlock both realtime free space metadata inodes after a freespace update. */
@@ -1225,3 +1219,127 @@ xfs_rtbitmap_unlock_shared(
 	if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
 		xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 }
+
+static int
+xfs_rtfile_alloc_blocks(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		offset_fsb,
+	xfs_filblks_t		count_fsb,
+	struct xfs_bmbt_irec	*map)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			nmap = 1;
+	int			error;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtalloc,
+			XFS_GROWFSRT_SPACE_RES(mp, count_fsb), 0, 0, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
+				XFS_IEXT_ADD_NOSPLIT_CNT);
+	if (error)
+		goto out_trans_cancel;
+
+	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
+			XFS_BMAPI_METADATA, 0, map, &nmap);
+	if (error)
+		goto out_trans_cancel;
+
+	return xfs_trans_commit(tp);
+
+out_trans_cancel:
+	xfs_trans_cancel(tp);
+	return error;
+}
+
+/* Get a buffer for the block. */
+static int
+xfs_rtfile_initialize_block(
+	struct xfs_inode	*ip,
+	xfs_fsblock_t		fsbno,
+	void			*data)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	struct xfs_buf		*bp;
+	const size_t		copylen = mp->m_blockwsize << XFS_WORDLOG;
+	enum xfs_blft		buf_type;
+	int			error;
+
+	if (ip == mp->m_rsumip)
+		buf_type = XFS_BLFT_RTSUMMARY_BUF;
+	else
+		buf_type = XFS_BLFT_RTBITMAP_BUF;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtzero, 0, 0, 0, &tp);
+	if (error)
+		return error;
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
+			XFS_FSB_TO_DADDR(mp, fsbno), mp->m_bsize, 0, &bp);
+	if (error) {
+		xfs_trans_cancel(tp);
+		return error;
+	}
+
+	xfs_trans_buf_set_type(tp, bp, buf_type);
+	bp->b_ops = &xfs_rtbuf_ops;
+	if (data)
+		memcpy(bp->b_addr, data, copylen);
+	else
+		memset(bp->b_addr, 0, copylen);
+	xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
+	return xfs_trans_commit(tp);
+}
+
+/*
+ * Allocate space to the bitmap or summary file, and zero it, for growfs.
+ * @data must be a contiguous buffer large enough to fill all blocks in the
+ * file; or NULL to initialize the contents to zeroes.
+ */
+int
+xfs_rtfile_initialize_blocks(
+	struct xfs_inode	*ip,		/* inode (bitmap/summary) */
+	xfs_fileoff_t		offset_fsb,	/* offset to start from */
+	xfs_fileoff_t		end_fsb,	/* offset to allocate to */
+	void			*data)		/* data to fill the blocks */
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	const size_t		copylen = mp->m_blockwsize << XFS_WORDLOG;
+
+	while (offset_fsb < end_fsb) {
+		struct xfs_bmbt_irec	map;
+		xfs_filblks_t		i;
+		int			error;
+
+		error = xfs_rtfile_alloc_blocks(ip, offset_fsb,
+				end_fsb - offset_fsb, &map);
+		if (error)
+			return error;
+
+		/*
+		 * Now we need to clear the allocated blocks.
+		 *
+		 * Do this one block per transaction, to keep it simple.
+		 */
+		for (i = 0; i < map.br_blockcount; i++) {
+			error = xfs_rtfile_initialize_block(ip,
+					map.br_startblock + i, data);
+			if (error)
+				return error;
+			if (data)
+				data += copylen;
+		}
+
+		offset_fsb = map.br_startoff + map.br_blockcount;
+	}
+
+	return 0;
+}