Merge v6.18.39linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

17 files changed, 110 insertions, 39 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index b238d559ab03..e0c870beaf67 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -89,7 +89,7 @@ xfs_bmbt_key_addr(
 {
 	return (struct xfs_bmbt_key *)
 		((char *)block + xfs_bmbt_block_len(mp) +
-		 (index - 1) * sizeof(struct xfs_bmbt_key *));
+		 (index - 1) * sizeof(struct xfs_bmbt_key));
 }
 
 static inline xfs_bmbt_ptr_t *
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index e8db2f6149e0..43f352d89172 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -878,7 +878,7 @@ xfs_defer_add_barrier(
 	if (dfp)
 		return;
 
-	xfs_defer_alloc(&tp->t_dfops, &xfs_barrier_defer_type);
+	dfp = xfs_defer_alloc(&tp->t_dfops, &xfs_barrier_defer_type);
 
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
 }
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index dceef2abd4e2..785f422dfedb 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -436,17 +436,27 @@ xfs_dqinode_metadir_create(
 
 	error = xfs_metadir_create(&upd, S_IFREG);
 	if (error)
-		return error;
+		goto out_cancel;
 
 	xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE);
 
 	error = xfs_metadir_commit(&upd);
 	if (error)
-		return error;
+		goto out_irele;
 
 	xfs_finish_inode_setup(upd.ip);
 	*ipp = upd.ip;
 	return 0;
+
+out_cancel:
+	xfs_metadir_cancel(&upd, error);
+out_irele:
+	/* Have to finish setting up the inode to ensure it's deleted. */
+	if (upd.ip) {
+		xfs_finish_inode_setup(upd.ip);
+		xfs_irele(upd.ip);
+	}
+	return error;
 }
 
 #ifndef __KERNEL__
diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c
index 932ee4619e9e..f021fe3c9cb6 100644
--- a/fs/xfs/libxfs/xfs_exchmaps.c
+++ b/fs/xfs/libxfs/xfs_exchmaps.c
@@ -711,7 +711,7 @@ xfs_exchmaps_estimate_overhead(
 		return -ENOSPC;
 
 	/* Can't actually reserve more than UINT_MAX blocks. */
-	if (req->resblks > UINT_MAX)
+	if (resblks > UINT_MAX)
 		return -ENOSPC;
 
 	req->resblks = resblks;
diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c
index 3e0bbe75c44c..7301e9cbdab9 100644
--- a/fs/xfs/scrub/dirtree.c
+++ b/fs/xfs/scrub/dirtree.c
@@ -383,6 +383,14 @@ xchk_dirpath_step_up(
 		goto out_scanlock;
 	}
 
+	/* The handle encoded in the parent pointer must match. */
+	if (VFS_I(dp)->i_generation != be32_to_cpu(dl->pptr_rec.p_gen)) {
+		trace_xchk_dirpath_badgen(dl->sc, dp, path->path_nr,
+				path->nr_steps, &dl->xname, &dl->pptr_rec);
+		error = -EFSCORRUPTED;
+		goto out_scanlock;
+	}
+
 	/* We've reached the root directory; the path is ok. */
 	if (parent_ino == dl->root_ino) {
 		xchk_dirpath_set_outcome(dl, path, XCHK_DIRPATH_OK);
@@ -411,14 +419,6 @@ xchk_dirpath_step_up(
 		goto out_scanlock;
 	}
 
-	/* The handle encoded in the parent pointer must match. */
-	if (VFS_I(dp)->i_generation != be32_to_cpu(dl->pptr_rec.p_gen)) {
-		trace_xchk_dirpath_badgen(dl->sc, dp, path->path_nr,
-				path->nr_steps, &dl->xname, &dl->pptr_rec);
-		error = -EFSCORRUPTED;
-		goto out_scanlock;
-	}
-
 	/* Parent pointer must point up to a directory. */
 	if (!S_ISDIR(VFS_I(dp)->i_mode)) {
 		trace_xchk_dirpath_nondir_parent(dl->sc, dp, path->path_nr,
diff --git a/fs/xfs/scrub/dqiterate.c b/fs/xfs/scrub/dqiterate.c
index 20c4daedd48d..998b0d640d61 100644
--- a/fs/xfs/scrub/dqiterate.c
+++ b/fs/xfs/scrub/dqiterate.c
@@ -205,7 +205,7 @@ xchk_dquot_iter(
 	if (error)
 		return error;
 
-	cursor->id = dq->q_id + 1;
+	cursor->id = (uint64_t)dq->q_id + 1;
 	*dqpp = dq;
 	return 1;
 }
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index a90a011c7e5f..5c45a68793d0 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -921,7 +921,7 @@ xrep_dinode_bad_bmbt_fork(
 
 	if (nrecs == 0 || xfs_bmdr_space_calc(nrecs) > dfork_size)
 		return true;
-	if (level == 0 || level >= XFS_BM_MAXLEVELS(sc->mp, whichfork))
+	if (level == 0 || level > XFS_BM_MAXLEVELS(sc->mp, whichfork))
 		return true;
 
 	dmxr = xfs_bmdr_maxrecs(dfork_size, 0);
@@ -1753,7 +1753,7 @@ xrep_clamp_timestamp(
 	struct xfs_inode	*ip,
 	struct timespec64	*ts)
 {
-	ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC);
+	ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC - 1);
 	*ts = timestamp_truncate(*ts, VFS_I(ip));
 }
 
diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c
index d189732d0e24..7b962890a894 100644
--- a/fs/xfs/scrub/rgsuper.c
+++ b/fs/xfs/scrub/rgsuper.c
@@ -23,6 +23,8 @@ int
 xchk_setup_rgsuperblock(
 	struct xfs_scrub	*sc)
 {
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
 	return xchk_trans_alloc(sc, 0);
 }
 
@@ -43,6 +45,7 @@ xchk_rgsuperblock(
 	struct xfs_scrub	*sc)
 {
 	xfs_rgnumber_t		rgno = sc->sm->sm_agno;
+	unsigned int		flags;
 	int			error;
 
 	/*
@@ -63,7 +66,12 @@ xchk_rgsuperblock(
 	if (!xchk_xref_process_error(sc, 0, 0, &error))
 		return error;
 
-	error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP_SHARED);
+	if (xfs_has_rtrmapbt(sc->mp))
+		flags = XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP;
+	else
+		flags = XFS_RTGLOCK_BITMAP_SHARED;
+
+	error = xchk_rtgroup_lock(sc, &sc->sr, flags);
 	if (error)
 		return error;
 
@@ -80,9 +88,13 @@ int
 xrep_rgsuperblock(
 	struct xfs_scrub	*sc)
 {
+	struct xfs_buf		*sb_bp;
+
 	ASSERT(rtg_rgno(sc->sr.rtg) == 0);
 
+	sb_bp = xfs_trans_getsb(sc->tp);
 	xfs_log_sb(sc->tp);
+	xfs_log_rtsb(sc->tp, sb_bp);
 	return 0;
 }
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index d5ff8609dbfb..8efde8c26e61 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -258,7 +258,7 @@ xchk_rtbitmap(
 	 * the last free extent we saw and the last possible extent in the rt
 	 * group.
 	 */
-	last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize - 1;
+	last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize;
 	if (rtb->next_free_rgbno < last_rgbno)
 		xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno,
 				last_rgbno - rtb->next_free_rgbno);
diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c
index 4c5dffc73641..24eb2a664aab 100644
--- a/fs/xfs/scrub/rtrefcount.c
+++ b/fs/xfs/scrub/rtrefcount.c
@@ -608,7 +608,7 @@ xchk_xref_is_rt_cow_staging(
 
 	/* CoW lookup returned a shared extent record? */
 	if (rc.rc_domain != XFS_REFC_DOMAIN_COW)
-		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0);
 
 	/* Must be at least as long as what was passed in */
 	if (rc.rc_blockcount < len)
diff --git a/fs/xfs/scrub/rtrmap.c b/fs/xfs/scrub/rtrmap.c
index 12989fe80e8b..e75fa9c095e0 100644
--- a/fs/xfs/scrub/rtrmap.c
+++ b/fs/xfs/scrub/rtrmap.c
@@ -87,6 +87,9 @@ xchk_rtrmapbt_is_shareable(
 		return false;
 	if (irec->rm_flags & XFS_RMAP_UNWRITTEN)
 		return false;
+	if (irec->rm_owner == XFS_RMAP_OWN_COW ||
+	    irec->rm_owner == XFS_RMAP_OWN_FS)
+		return false;
 	return true;
 }
 
@@ -146,6 +149,9 @@ xchk_rtrmap_mergeable(
 		return false;
 	if (r1->rm_flags != r2->rm_flags)
 		return false;
+	if (r1->rm_owner == XFS_RMAP_OWN_COW ||
+	    r1->rm_owner == XFS_RMAP_OWN_FS)
+		return true;
 	return r1->rm_offset + r1->rm_blockcount == r2->rm_offset;
 }
 
@@ -209,7 +215,7 @@ xchk_rtrmapbt_xref(
 			xfs_rgbno_to_rtb(sc->sr.rtg, irec->rm_startblock),
 			irec->rm_blockcount);
 	if (irec->rm_owner == XFS_RMAP_OWN_COW)
-		xchk_xref_is_cow_staging(sc, irec->rm_startblock,
+		xchk_xref_is_rt_cow_staging(sc, irec->rm_startblock,
 				irec->rm_blockcount);
 	else
 		xchk_rtrmapbt_xref_rtrefc(sc, irec);
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index a3f1abc91390..6d7d3523b71f 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -11,7 +11,7 @@ struct xfs_scrub;
 struct xchk_relax {
 	unsigned long	next_resched;
 	unsigned int	resched_nr;
-	bool		interruptible;
+	bool		killable;
 };
 
 /* Yield to the scheduler at most 10x per second. */
@@ -21,7 +21,7 @@ struct xchk_relax {
 	(struct xchk_relax){ \
 		.next_resched	= XCHK_RELAX_NEXT, \
 		.resched_nr	= 0, \
-		.interruptible	= true, \
+		.killable	= true, \
 	}
 
 /*
@@ -45,7 +45,7 @@ static inline int xchk_maybe_relax(struct xchk_relax *widget)
 		widget->next_resched = XCHK_RELAX_NEXT;
 	}
 
-	if (widget->interruptible && fatal_signal_pending(current))
+	if (widget->killable && fatal_signal_pending(current))
 		return -EINTR;
 
 	return 0;
diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c
index cdd13ed9c569..a3ad0b323576 100644
--- a/fs/xfs/scrub/xfarray.c
+++ b/fs/xfs/scrub/xfarray.c
@@ -487,8 +487,7 @@ xfarray_sortinfo_alloc(
 	xfarray_sortinfo_lo(si)[0] = 0;
 	xfarray_sortinfo_hi(si)[0] = array->nr - 1;
 	si->relax = INIT_XCHK_RELAX;
-	if (flags & XFARRAY_SORT_KILLABLE)
-		si->relax.interruptible = false;
+	si->relax.killable = !!(flags & XFARRAY_SORT_KILLABLE);
 
 	trace_xfarray_sort(si, nr_bytes);
 	*infop = si;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 92a8863bee36..896ff8080b75 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1241,6 +1241,14 @@ xfs_qm_dqflush_check(
 	    type != XFS_DQTYPE_PROJ)
 		return __this_address;
 
+	/* bigtime flag should never be set on root dquots */
+	if (dqp->q_type & XFS_DQTYPE_BIGTIME) {
+		if (!xfs_has_bigtime(dqp->q_mount))
+			return __this_address;
+		if (dqp->q_id == 0)
+			return __this_address;
+	}
+
 	if (dqp->q_id == 0)
 		return NULL;
 
@@ -1256,14 +1264,6 @@ xfs_qm_dqflush_check(
 	    !dqp->q_rtb.timer)
 		return __this_address;
 
-	/* bigtime flag should never be set on root dquots */
-	if (dqp->q_type & XFS_DQTYPE_BIGTIME) {
-		if (!xfs_has_bigtime(dqp->q_mount))
-			return __this_address;
-		if (dqp->q_id == 0)
-			return __this_address;
-	}
-
 	return NULL;
 }
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 549d60959aee..33cf2a31780c 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1028,7 +1028,7 @@ xlog_verify_head(
 {
 	struct xlog_rec_header	*tmp_rhead;
 	char			*tmp_buffer;
-	xfs_daddr_t		first_bad;
+	xfs_daddr_t		first_bad = XFS_BUF_DADDR_NULL;
 	xfs_daddr_t		tmp_rhead_blk;
 	int			found;
 	int			error;
@@ -1057,7 +1057,8 @@ xlog_verify_head(
 	 */
 	error = xlog_do_recovery_pass(log, *head_blk, tmp_rhead_blk,
 				      XLOG_RECOVER_CRCPASS, &first_bad);
-	if ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) {
+	if ((error == -EFSBADCRC || error == -EFSCORRUPTED) &&
+	    first_bad != XFS_BUF_DADDR_NULL) {
 		/*
 		 * We've hit a potential torn write. Reset the error and warn
 		 * about it.
@@ -1906,6 +1907,15 @@ xlog_recover_reorder_trans(
 	list_for_each_entry_safe(item, n, &sort_list, ri_list) {
 		enum xlog_recover_reorder	fate = XLOG_REORDER_ITEM_LIST;
 
+		/* a committed item with no regions has a NULL ri_buf[0] */
+		if (!item->ri_cnt || !item->ri_buf) {
+			xfs_warn(log->l_mp,
+				"%s: committed log item has no regions",
+				__func__);
+			error = -EFSCORRUPTED;
+			break;
+		}
+
 		item->ri_ops = xlog_find_item_ops(item);
 		if (!item->ri_ops) {
 			xfs_warn(log->l_mp,
@@ -3582,4 +3592,3 @@ xlog_recover_cancel(
 	if (xlog_recovery_needed(log))
 		xlog_recover_cancel_intents(log);
 }
-
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 18a19947bbdb..48a5a294f0a1 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -163,10 +163,9 @@ xfs_qm_dqpurge(
 		 * does it on success.
 		 */
 		error = xfs_qm_dqflush(dqp, bp);
-		if (!error) {
+		if (!error)
 			error = xfs_bwrite(bp);
-			xfs_buf_relse(bp);
-		}
+		xfs_buf_relse(bp);
 		xfs_dqflock(dqp);
 	}
 	xfs_dquot_detach_buf(dqp);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 3f177b4ec131..d6cd7c1f00ff 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -440,6 +440,7 @@ xfs_reflink_fill_cow_hole(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	xfs_filblks_t		resaligned;
+	unsigned int		seq_before = READ_ONCE(ip->i_df.if_seq);
 	unsigned int		dblocks = 0, rblocks = 0;
 	int			nimaps;
 	int			error;
@@ -465,6 +466,22 @@ xfs_reflink_fill_cow_hole(
 
 	*lockmode = XFS_ILOCK_EXCL;
 
+	/*
+	 * The data fork mapping may have changed while we dropped the ILOCK
+	 * (a racing O_DIRECT writer under IOLOCK_SHARED can complete a full
+	 * CoW cycle including xfs_reflink_end_cow(), which remaps this offset
+	 * and drops the refcount of the old shared block).  Re-read it so the
+	 * shared-status recheck below and the caller's in-place iomap both
+	 * operate on the current mapping rather than a stale physical block.
+	 */
+	if (seq_before != READ_ONCE(ip->i_df.if_seq)) {
+		nimaps = 1;
+		error = xfs_bmapi_read(ip, imap->br_startoff,
+				imap->br_blockcount, imap, &nimaps, 0);
+		if (error)
+			goto out_trans_cancel;
+	}
+
 	error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found);
 	if (error || !*shared)
 		goto out_trans_cancel;
@@ -511,6 +528,8 @@ xfs_reflink_fill_delalloc(
 	bool			found;
 
 	do {
+		unsigned int	seq_before = READ_ONCE(ip->i_df.if_seq);
+
 		xfs_iunlock(ip, *lockmode);
 		*lockmode = 0;
 
@@ -521,6 +540,23 @@ xfs_reflink_fill_delalloc(
 
 		*lockmode = XFS_ILOCK_EXCL;
 
+		/*
+		 * The data fork mapping may have changed while we dropped the
+		 * ILOCK (a racing O_DIRECT writer under IOLOCK_SHARED can
+		 * complete a full CoW cycle including xfs_reflink_end_cow(),
+		 * which remaps this offset and drops the refcount of the old
+		 * shared block).  Re-read it so the shared-status recheck
+		 * below and the caller's in-place iomap both operate on the
+		 * current mapping rather than a stale physical block.
+		 */
+		if (seq_before != READ_ONCE(ip->i_df.if_seq)) {
+			nimaps = 1;
+			error = xfs_bmapi_read(ip, imap->br_startoff,
+					imap->br_blockcount, imap, &nimaps, 0);
+			if (error)
+				goto out_trans_cancel;
+		}
+
 		error = xfs_find_trim_cow_extent(ip, imap, cmap, shared,
 				&found);
 		if (error || !*shared)