7 files changed, 116 insertions, 39 deletions

diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 84db76e0e3e3..fecd187fcf2c 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -157,6 +157,7 @@ __xfs_ag_resv_free(
 	error = xfs_mod_fdblocks(pag->pag_mount, oldresv, true);
 	resv->ar_reserved = 0;
 	resv->ar_asked = 0;
+	resv->ar_orig_reserved = 0;
 
 	if (error)
 		trace_xfs_ag_resv_free_error(pag->pag_mount, pag->pag_agno,
@@ -189,13 +190,34 @@ __xfs_ag_resv_init(
 	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_ag_resv		*resv;
 	int				error;
-	xfs_extlen_t			reserved;
+	xfs_extlen_t			hidden_space;
 
 	if (used > ask)
 		ask = used;
-	reserved = ask - used;
 
-	error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+	switch (type) {
+	case XFS_AG_RESV_RMAPBT:
+		/*
+		 * Space taken by the rmapbt is not subtracted from fdblocks
+		 * because the rmapbt lives in the free space.  Here we must
+		 * subtract the entire reservation from fdblocks so that we
+		 * always have blocks available for rmapbt expansion.
+		 */
+		hidden_space = ask;
+		break;
+	case XFS_AG_RESV_METADATA:
+		/*
+		 * Space taken by all other metadata btrees are accounted
+		 * on-disk as used space.  We therefore only hide the space
+		 * that is reserved but not used by the trees.
+		 */
+		hidden_space = ask - used;
+		break;
+	default:
+		ASSERT(0);
+		return -EINVAL;
+	}
+	error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
 	if (error) {
 		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
 				error, _RET_IP_);
@@ -216,7 +238,8 @@ __xfs_ag_resv_init(
 
 	resv = xfs_perag_resv(pag, type);
 	resv->ar_asked = ask;
-	resv->ar_reserved = resv->ar_orig_reserved = reserved;
+	resv->ar_orig_reserved = hidden_space;
+	resv->ar_reserved = ask - used;
 
 	trace_xfs_ag_resv_init(pag, type, ask);
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index eef466260d43..75dbdc14c45f 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -223,12 +223,13 @@ xfs_alloc_get_rec(
 	error = xfs_btree_get_rec(cur, &rec, stat);
 	if (error || !(*stat))
 		return error;
-	if (rec->alloc.ar_blockcount == 0)
-		goto out_bad_rec;
 
 	*bno = be32_to_cpu(rec->alloc.ar_startblock);
 	*len = be32_to_cpu(rec->alloc.ar_blockcount);
 
+	if (*len == 0)
+		goto out_bad_rec;
+
 	/* check for valid extent range, including overflow */
 	if (!xfs_verify_agbno(mp, agno, *bno))
 		goto out_bad_rec;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 01628f0c9a0c..7205268b30bc 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5780,6 +5780,32 @@ del_cursor:
 	return error;
 }
 
+/* Make sure we won't be right-shifting an extent past the maximum bound. */
+int
+xfs_bmap_can_insert_extents(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		off,
+	xfs_fileoff_t		shift)
+{
+	struct xfs_bmbt_irec	got;
+	int			is_empty;
+	int			error = 0;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmap_last_extent(NULL, ip, XFS_DATA_FORK, &got, &is_empty);
+	if (!error && !is_empty && got.br_startoff >= off &&
+	    ((got.br_startoff + shift) & BMBT_STARTOFF_MASK) < got.br_startoff)
+		error = -EINVAL;
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	return error;
+}
+
 int
 xfs_bmap_insert_extents(
 	struct xfs_trans	*tp,
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 99dddbd0fcc6..9b49ddf99c41 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -227,6 +227,8 @@ int	xfs_bmap_collapse_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
 		bool *done, xfs_fsblock_t *firstblock,
 		struct xfs_defer_ops *dfops);
+int	xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
+		xfs_fileoff_t shift);
 int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
 		bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 1c5a8aaf2bfc..059bc44c27e8 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -962,6 +962,9 @@ typedef enum xfs_dinode_fmt {
 		XFS_DFORK_DSIZE(dip, mp) : \
 		XFS_DFORK_ASIZE(dip, mp))
 
+#define XFS_DFORK_MAXEXT(dip, mp, w) \
+	(XFS_DFORK_SIZE(dip, mp, w) / sizeof(struct xfs_bmbt_rec))
+
 /*
  * Return pointers to the data or attribute forks.
  */
@@ -1526,6 +1529,8 @@ typedef struct xfs_bmdr_block {
 #define BMBT_STARTBLOCK_BITLEN	52
 #define BMBT_BLOCKCOUNT_BITLEN	21
 
+#define BMBT_STARTOFF_MASK	((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+
 typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;
 } xfs_bmbt_rec_t;
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d38d724534c4..30d1d60f1d46 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -374,6 +374,47 @@ xfs_log_dinode_to_disk(
 	}
 }
 
+static xfs_failaddr_t
+xfs_dinode_verify_fork(
+	struct xfs_dinode	*dip,
+	struct xfs_mount	*mp,
+	int			whichfork)
+{
+	uint32_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+
+	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+	case XFS_DINODE_FMT_LOCAL:
+		/*
+		 * no local regular files yet
+		 */
+		if (whichfork == XFS_DATA_FORK) {
+			if (S_ISREG(be16_to_cpu(dip->di_mode)))
+				return __this_address;
+			if (be64_to_cpu(dip->di_size) >
+					XFS_DFORK_SIZE(dip, mp, whichfork))
+				return __this_address;
+		}
+		if (di_nextents)
+			return __this_address;
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+		if (di_nextents > XFS_DFORK_MAXEXT(dip, mp, whichfork))
+			return __this_address;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		if (whichfork == XFS_ATTR_FORK) {
+			if (di_nextents > MAXAEXTNUM)
+				return __this_address;
+		} else if (di_nextents > MAXEXTNUM) {
+			return __this_address;
+		}
+		break;
+	default:
+		return __this_address;
+	}
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -441,24 +482,9 @@ xfs_dinode_verify(
 	case S_IFREG:
 	case S_IFLNK:
 	case S_IFDIR:
-		switch (dip->di_format) {
-		case XFS_DINODE_FMT_LOCAL:
-			/*
-			 * no local regular files yet
-			 */
-			if (S_ISREG(mode))
-				return __this_address;
-			if (di_size > XFS_DFORK_DSIZE(dip, mp))
-				return __this_address;
-			if (dip->di_nextents)
-				return __this_address;
-			/* fall through */
-		case XFS_DINODE_FMT_EXTENTS:
-		case XFS_DINODE_FMT_BTREE:
-			break;
-		default:
-			return __this_address;
-		}
+		fa = xfs_dinode_verify_fork(dip, mp, XFS_DATA_FORK);
+		if (fa)
+			return fa;
 		break;
 	case 0:
 		/* Uninitialized inode ok. */
@@ -468,17 +494,9 @@ xfs_dinode_verify(
 	}
 
 	if (XFS_DFORK_Q(dip)) {
-		switch (dip->di_aformat) {
-		case XFS_DINODE_FMT_LOCAL:
-			if (dip->di_anextents)
-				return __this_address;
-		/* fall through */
-		case XFS_DINODE_FMT_EXTENTS:
-		case XFS_DINODE_FMT_BTREE:
-			break;
-		default:
-			return __this_address;
-		}
+		fa = xfs_dinode_verify_fork(dip, mp, XFS_ATTR_FORK);
+		if (fa)
+			return fa;
 	} else {
 		/*
 		 * If there is no fork offset, this may be a freshly-made inode
@@ -713,7 +731,8 @@ xfs_inode_validate_extsize(
 	if ((hint_flag || inherit_flag) && extsize == 0)
 		return __this_address;
 
-	if (!(hint_flag || inherit_flag) && extsize != 0)
+	/* free inodes get flags set to zero but extsize remains */
+	if (mode && !(hint_flag || inherit_flag) && extsize != 0)
 		return __this_address;
 
 	if (extsize_bytes % blocksize_bytes)
@@ -759,7 +778,8 @@ xfs_inode_validate_cowextsize(
 	if (hint_flag && cowextsize == 0)
 		return __this_address;
 
-	if (!hint_flag && cowextsize != 0)
+	/* free inodes get flags set to zero but cowextsize remains */
+	if (mode && !hint_flag && cowextsize != 0)
 		return __this_address;
 
 	if (hint_flag && rt_flag)
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 65fc4ed2e9a1..b228c821bae6 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1029,8 +1029,8 @@ xfs_rtalloc_query_range(
 	if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
 	    low_rec->ar_startext == high_rec->ar_startext)
 		return 0;
-	if (high_rec->ar_startext >= mp->m_sb.sb_rextents)
-		high_rec->ar_startext = mp->m_sb.sb_rextents - 1;
+	if (high_rec->ar_startext > mp->m_sb.sb_rextents)
+		high_rec->ar_startext = mp->m_sb.sb_rextents;
 
 	/* Iterate the bitmap, looking for discrepancies. */
 	rtstart = low_rec->ar_startext;