Merge tag 'xfs-5.13-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull more xfs updates from Darrick Wong:
 "Except for the timestamp struct renaming patches, everything else in
  here are bug fixes:

   - Rename the log timestamp struct.

   - Remove broken transaction counter debugging that wasn't working
     correctly on very old filesystems.

   - Various fixes to make pre-lazysbcount filesystems work properly
     again.

   - Fix a free space accounting problem where we neglected to consider
     free space btree blocks that track metadata reservation space when
     deciding whether or not to allow caller to reserve space for a
     metadata update.

   - Fix incorrect pagecache clearing behavior during FUNSHARE ops.

   - Don't allow log writes if the data device is readonly"

* tag 'xfs-5.13-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: don't allow log writes if the data device is readonly
  xfs: fix xfs_reflink_unshare usage of filemap_write_and_wait_range
  xfs: set aside allocation btree blocks from block reservation
  xfs: introduce in-core global counter of allocbt blocks
  xfs: unconditionally read all AGFs on mounts with perag reservation
  xfs: count free space btree blocks when scrubbing pre-lazysbcount fses
  xfs: update superblock counters correctly for !lazysbcount
  xfs: don't check agf_btreeblks on pre-lazysbcount filesystems
  xfs: remove obsolete AGF counter debugging
  xfs: rename struct xfs_legacy_ictimestamp
  xfs: rename xfs_ictimestamp_t

Author: torvalds

fs/xfs/libxfs/xfs_ag_resv.c

@@ -253,7 +253,8 @@ xfs_ag_resv_init(
 	xfs_agnumber_t			agno = pag->pag_agno;
 	xfs_extlen_t			ask;
 	xfs_extlen_t			used;
-	int				error = 0;
+	int				error = 0, error2;
+	bool				has_resv = false;
 
 	/* Create the metadata reservation. */
 	if (pag->pag_meta_resv.ar_asked == 0) {
@@ -291,6 +292,8 @@ xfs_ag_resv_init(
 			if (error)
 				goto out;
 		}
+		if (ask)
+			has_resv = true;
 	}
 
 	/* Create the RMAPBT metadata reservation */
@@ -304,19 +307,28 @@ xfs_ag_resv_init(
 		error = __xfs_ag_resv_init(pag, XFS_AG_RESV_RMAPBT, ask, used);
 		if (error)
 			goto out;
+		if (ask)
+			has_resv = true;
 	}
 
-#ifdef DEBUG
-	/* need to read in the AGF for the ASSERT below to work */
-	error = xfs_alloc_pagf_init(pag->pag_mount, tp, pag->pag_agno, 0);
-	if (error)
-		return error;
-
-	ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
-	       xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <=
-	       pag->pagf_freeblks + pag->pagf_flcount);
-#endif
 out:
+	/*
+	 * Initialize the pagf if we have at least one active reservation on the
+	 * AG. This may have occurred already via reservation calculation, but
+	 * fall back to an explicit init to ensure the in-core allocbt usage
+	 * counters are initialized as soon as possible. This is important
+	 * because filesystems with large perag reservations are susceptible to
+	 * free space reservation problems that the allocbt counter is used to
+	 * address.
+	 */
+	if (has_resv) {
+		error2 = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, 0);
+		if (error2)
+			return error2;
+		ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
+		       xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <=
+		       pag->pagf_freeblks + pag->pagf_flcount);
+	}
 	return error;
 }
 

fs/xfs/libxfs/xfs_alloc.c

@@ -718,7 +718,6 @@ xfs_alloc_update_counters(
 	agbp->b_pag->pagf_freeblks += len;
 	be32_add_cpu(&agf->agf_freeblks, len);
 
-	xfs_trans_agblocks_delta(tp, len);
 	if (unlikely(be32_to_cpu(agf->agf_freeblks) >
 		     be32_to_cpu(agf->agf_length))) {
 		xfs_buf_mark_corrupt(agbp);
@@ -2739,7 +2738,6 @@ xfs_alloc_get_freelist(
 	pag = agbp->b_pag;
 	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, -1);
-	xfs_trans_agflist_delta(tp, -1);
 	pag->pagf_flcount--;
 
 	logflags = XFS_AGF_FLFIRST | XFS_AGF_FLCOUNT;
@@ -2846,7 +2844,6 @@ xfs_alloc_put_freelist(
 	pag = agbp->b_pag;
 	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, 1);
-	xfs_trans_agflist_delta(tp, 1);
 	pag->pagf_flcount++;
 
 	logflags = XFS_AGF_FLLAST | XFS_AGF_FLCOUNT;
@@ -3036,6 +3033,7 @@ xfs_alloc_read_agf(
 	struct xfs_agf		*agf;		/* ag freelist header */
 	struct xfs_perag	*pag;		/* per allocation group data */
 	int			error;
+	int			allocbt_blks;
 
 	trace_xfs_alloc_read_agf(mp, agno);
 
@@ -3066,6 +3064,19 @@ xfs_alloc_read_agf(
 		pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
 		pag->pagf_init = 1;
 		pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
+
+		/*
+		 * Update the in-core allocbt counter. Filter out the rmapbt
+		 * subset of the btreeblks counter because the rmapbt is managed
+		 * by perag reservation. Subtract one for the rmapbt root block
+		 * because the rmap counter includes it while the btreeblks
+		 * counter only tracks non-root blocks.
+		 */
+		allocbt_blks = pag->pagf_btreeblks;
+		if (xfs_sb_version_hasrmapbt(&mp->m_sb))
+			allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1;
+		if (allocbt_blks > 0)
+			atomic64_add(allocbt_blks, &mp->m_allocbt_blks);
 	}
 #ifdef DEBUG
 	else if (!XFS_FORCED_SHUTDOWN(mp)) {

fs/xfs/libxfs/xfs_alloc_btree.c

@@ -71,9 +71,9 @@ xfs_allocbt_alloc_block(
 		return 0;
 	}
 
+	atomic64_inc(&cur->bc_mp->m_allocbt_blks);
 	xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agno, bno, 1, false);
 
-	xfs_trans_agbtree_delta(cur->bc_tp, 1);
 	new->s = cpu_to_be32(bno);
 
 	*stat = 1;
@@ -95,9 +95,9 @@ xfs_allocbt_free_block(
 	if (error)
 		return error;
 
+	atomic64_dec(&cur->bc_mp->m_allocbt_blks);
 	xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
-	xfs_trans_agbtree_delta(cur->bc_tp, -1);
 	return 0;
 }
 

fs/xfs/libxfs/xfs_log_format.h

@@ -368,10 +368,10 @@ static inline int xfs_ilog_fdata(int w)
  * directly mirrors the xfs_dinode structure as it must contain all the same
  * information.
  */
-typedef uint64_t xfs_ictimestamp_t;
+typedef uint64_t xfs_log_timestamp_t;
 
 /* Legacy timestamp encoding format. */
-struct xfs_legacy_ictimestamp {
+struct xfs_log_legacy_timestamp {
 	int32_t		t_sec;		/* timestamp seconds */
 	int32_t		t_nsec;		/* timestamp nanoseconds */
 };
@@ -393,9 +393,9 @@ struct xfs_log_dinode {
 	uint16_t	di_projid_hi;	/* higher part of owner's project id */
 	uint8_t		di_pad[6];	/* unused, zeroed space */
 	uint16_t	di_flushiter;	/* incremented on flush */
-	xfs_ictimestamp_t di_atime;	/* time last accessed */
-	xfs_ictimestamp_t di_mtime;	/* time last modified */
-	xfs_ictimestamp_t di_ctime;	/* time created/inode modified */
+	xfs_log_timestamp_t di_atime;	/* time last accessed */
+	xfs_log_timestamp_t di_mtime;	/* time last modified */
+	xfs_log_timestamp_t di_ctime;	/* time created/inode modified */
 	xfs_fsize_t	di_size;	/* number of bytes in file */
 	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
@@ -420,7 +420,7 @@ struct xfs_log_dinode {
 	uint8_t		di_pad2[12];	/* more padding for future expansion */
 
 	/* fields only written to during inode creation */
-	xfs_ictimestamp_t di_crtime;	/* time created */
+	xfs_log_timestamp_t di_crtime;	/* time created */
 	xfs_ino_t	di_ino;		/* inode number */
 	uuid_t		di_uuid;	/* UUID of the filesystem */
 

fs/xfs/libxfs/xfs_rmap_btree.c

@@ -103,7 +103,6 @@ xfs_rmapbt_alloc_block(
 	xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agno, bno, 1,
 			false);
 
-	xfs_trans_agbtree_delta(cur->bc_tp, 1);
 	new->s = cpu_to_be32(bno);
 	be32_add_cpu(&agf->agf_rmap_blocks, 1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
@@ -136,7 +135,6 @@ xfs_rmapbt_free_block(
 
 	xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
-	xfs_trans_agbtree_delta(cur->bc_tp, -1);
 
 	pag = cur->bc_ag.agbp->b_pag;
 	xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);

fs/xfs/libxfs/xfs_sb.c

@@ -926,9 +926,19 @@ xfs_log_sb(
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*bp = xfs_trans_getsb(tp);
 
-	mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
-	mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
-	mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+	/*
+	 * Lazy sb counters don't update the in-core superblock so do that now.
+	 * If this is at unmount, the counters will be exactly correct, but at
+	 * any other time they will only be ballpark correct because of
+	 * reservations that have been taken out percpu counters. If we have an
+	 * unclean shutdown, this will be corrected by log recovery rebuilding
+	 * the counters from the AGF block counts.
+	 */
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb)) {
+		mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+		mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
+		mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+	}
 
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);

fs/xfs/scrub/agheader.c

@@ -416,6 +416,10 @@ xchk_agf_xref_btreeblks(
 	xfs_agblock_t		btreeblks;
 	int			error;
 
+	/* agf_btreeblks didn't exist before lazysbcount */
+	if (!xfs_sb_version_haslazysbcount(&sc->mp->m_sb))
+		return;
+
 	/* Check agf_rmap_blocks; set up for agf_btreeblks check */
 	if (sc->sa.rmap_cur) {
 		error = xfs_btree_count_blocks(sc->sa.rmap_cur, &blocks);
@@ -581,7 +585,8 @@ xchk_agf(
 		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	if (pag->pagf_flcount != be32_to_cpu(agf->agf_flcount))
 		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
-	if (pag->pagf_btreeblks != be32_to_cpu(agf->agf_btreeblks))
+	if (xfs_sb_version_haslazysbcount(&sc->mp->m_sb) &&
+	    pag->pagf_btreeblks != be32_to_cpu(agf->agf_btreeblks))
 		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	xfs_perag_put(pag);
 

fs/xfs/scrub/fscounters.c

@@ -13,6 +13,7 @@
 #include "xfs_alloc.h"
 #include "xfs_ialloc.h"
 #include "xfs_health.h"
+#include "xfs_btree.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -143,6 +144,35 @@ xchk_setup_fscounters(
 	return xchk_trans_alloc(sc, 0);
 }
 
+/* Count free space btree blocks manually for pre-lazysbcount filesystems. */
+static int
+xchk_fscount_btreeblks(
+	struct xfs_scrub	*sc,
+	struct xchk_fscounters	*fsc,
+	xfs_agnumber_t		agno)
+{
+	xfs_extlen_t		blocks;
+	int			error;
+
+	error = xchk_ag_init(sc, agno, &sc->sa);
+	if (error)
+		return error;
+
+	error = xfs_btree_count_blocks(sc->sa.bno_cur, &blocks);
+	if (error)
+		goto out_free;
+	fsc->fdblocks += blocks - 1;
+
+	error = xfs_btree_count_blocks(sc->sa.cnt_cur, &blocks);
+	if (error)
+		goto out_free;
+	fsc->fdblocks += blocks - 1;
+
+out_free:
+	xchk_ag_free(sc, &sc->sa);
+	return error;
+}
+
 /*
  * Calculate what the global in-core counters ought to be from the incore
  * per-AG structure.  Callers can compare this to the actual in-core counters
@@ -182,7 +212,15 @@ xchk_fscount_aggregate_agcounts(
 		/* Add up the free/freelist/bnobt/cntbt blocks */
 		fsc->fdblocks += pag->pagf_freeblks;
 		fsc->fdblocks += pag->pagf_flcount;
-		fsc->fdblocks += pag->pagf_btreeblks;
+		if (xfs_sb_version_haslazysbcount(&sc->mp->m_sb)) {
+			fsc->fdblocks += pag->pagf_btreeblks;
+		} else {
+			error = xchk_fscount_btreeblks(sc, fsc, agno);
+			if (error) {
+				xfs_perag_put(pag);
+				break;
+			}
+		}
 
 		/*
 		 * Per-AG reservations are taken out of the incore counters,

fs/xfs/xfs_fsops.c

@@ -69,8 +69,6 @@ xfs_resizefs_init_new_ags(
 	if (error)
 		return error;
 
-	xfs_trans_agblocks_delta(tp, id->nfree);
-
 	if (delta) {
 		*lastag_extended = true;
 		error = xfs_ag_extend_space(mp, tp, id, delta);

fs/xfs/xfs_inode_item.c

@@ -299,18 +299,18 @@ xfs_inode_item_format_attr_fork(
  * Convert an incore timestamp to a log timestamp.  Note that the log format
  * specifies host endian format!
  */
-static inline xfs_ictimestamp_t
+static inline xfs_log_timestamp_t
 xfs_inode_to_log_dinode_ts(
 	struct xfs_inode		*ip,
 	const struct timespec64		tv)
 {
-	struct xfs_legacy_ictimestamp	*lits;
-	xfs_ictimestamp_t		its;
+	struct xfs_log_legacy_timestamp	*lits;
+	xfs_log_timestamp_t		its;
 
 	if (xfs_inode_has_bigtime(ip))
 		return xfs_inode_encode_bigtime(tv);
 
-	lits = (struct xfs_legacy_ictimestamp *)&its;
+	lits = (struct xfs_log_legacy_timestamp *)&its;
 	lits->t_sec = tv.tv_sec;
 	lits->t_nsec = tv.tv_nsec;