19 files changed, 299 insertions, 217 deletions
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 852b536551b5..7cb9f064ac64 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -690,9 +690,9 @@ xfs_alloc_read_agfl(
 	xfs_mount_t	*mp,		/* mount point structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_agnumber_t	agno,		/* allocation group number */
-	xfs_buf_t	**bpp)		/* buffer for the ag free block array */
+	struct xfs_buf	**bpp)		/* buffer for the ag free block array */
 {
-	xfs_buf_t	*bp;		/* return value */
+	struct xfs_buf	*bp;		/* return value */
 	int		error;
 
 	ASSERT(agno != NULLAGNUMBER);
@@ -2467,6 +2467,7 @@ xfs_defer_agfl_block(
 	new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
 	new->xefi_blockcount = 1;
 	new->xefi_oinfo = *oinfo;
+	new->xefi_skip_discard = false;
 
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
@@ -2646,12 +2647,12 @@ out_no_agbp:
 int				/* error */
 xfs_alloc_get_freelist(
 	xfs_trans_t	*tp,	/* transaction pointer */
-	xfs_buf_t	*agbp,	/* buffer containing the agf structure */
+	struct xfs_buf	*agbp,	/* buffer containing the agf structure */
 	xfs_agblock_t	*bnop,	/* block address retrieved from freelist */
 	int		btreeblk) /* destination is a AGF btree */
 {
 	struct xfs_agf	*agf = agbp->b_addr;
-	xfs_buf_t	*agflbp;/* buffer for a.g. freelist structure */
+	struct xfs_buf	*agflbp;/* buffer for a.g. freelist structure */
 	xfs_agblock_t	bno;	/* block number returned */
 	__be32		*agfl_bno;
 	int		error;
@@ -2710,7 +2711,7 @@ xfs_alloc_get_freelist(
 void
 xfs_alloc_log_agf(
 	xfs_trans_t	*tp,	/* transaction pointer */
-	xfs_buf_t	*bp,	/* buffer for a.g. freelist header */
+	struct xfs_buf	*bp,	/* buffer for a.g. freelist header */
 	int		fields)	/* mask of fields to be logged (XFS_AGF_...) */
 {
 	int	first;		/* first byte offset */
@@ -2756,7 +2757,7 @@ xfs_alloc_pagf_init(
 	xfs_agnumber_t		agno,	/* allocation group number */
 	int			flags)	/* XFS_ALLOC_FLAGS_... */
 {
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
 	int			error;
 
 	error = xfs_alloc_read_agf(mp, tp, agno, flags, &bp);
@@ -2771,8 +2772,8 @@ xfs_alloc_pagf_init(
 int					/* error */
 xfs_alloc_put_freelist(
 	xfs_trans_t		*tp,	/* transaction pointer */
-	xfs_buf_t		*agbp,	/* buffer for a.g. freelist header */
-	xfs_buf_t		*agflbp,/* buffer for a.g. free block array */
+	struct xfs_buf		*agbp,	/* buffer for a.g. freelist header */
+	struct xfs_buf		*agflbp,/* buffer for a.g. free block array */
 	xfs_agblock_t		bno,	/* block being freed */
 	int			btreeblk) /* block came from a AGF btree */
 {
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index bb128db220ac..d6ef69ab1c67 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -515,7 +515,7 @@ xfs_attr_copy_value(
  *========================================================================*/
 
 /*
- * Query whether the requested number of additional bytes of extended
+ * Query whether the total requested number of attr fork bytes of extended
  * attribute space will be able to fit inline.
  *
  * Returns zero if not, else the di_forkoff fork offset to be used in the
@@ -535,6 +535,12 @@ xfs_attr_shortform_bytesfit(
 	int			maxforkoff;
 	int			offset;
 
+	/*
+	 * Check if the new size could fit at all first:
+	 */
+	if (bytes > XFS_LITINO(mp))
+		return 0;
+
 	/* rounded down */
 	offset = (XFS_LITINO(mp) - bytes) >> 3;
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index d9a692484eae..bc446418e227 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -321,7 +321,7 @@ xfs_bmap_check_leaf_extents(
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	struct xfs_btree_block	*block;	/* current btree block */
 	xfs_fsblock_t		bno;	/* block # of "block" */
-	xfs_buf_t		*bp;	/* buffer for "block" */
+	struct xfs_buf		*bp;	/* buffer for "block" */
 	int			error;	/* error return value */
 	xfs_extnum_t		i=0, j;	/* index into the extents list */
 	int			level;	/* btree level, for checking */
@@ -592,7 +592,7 @@ xfs_bmap_btree_to_extents(
 	struct xfs_btree_block	*rblock = ifp->if_broot;
 	struct xfs_btree_block	*cblock;/* child btree block */
 	xfs_fsblock_t		cbno;	/* child block number */
-	xfs_buf_t		*cbp;	/* child block's buffer */
+	struct xfs_buf		*cbp;	/* child block's buffer */
 	int			error;	/* error return value */
 	__be64			*pp;	/* ptr to block address */
 	struct xfs_owner_info	oinfo;
@@ -830,7 +830,7 @@ xfs_bmap_local_to_extents(
 	int		flags;		/* logging flags returned */
 	struct xfs_ifork *ifp;		/* inode fork pointer */
 	xfs_alloc_arg_t	args;		/* allocation arguments */
-	xfs_buf_t	*bp;		/* buffer for extent block */
+	struct xfs_buf	*bp;		/* buffer for extent block */
 	struct xfs_bmbt_irec rec;
 	struct xfs_iext_cursor icur;
 
@@ -6226,23 +6226,17 @@ xfs_bmap_validate_extent(
 	struct xfs_bmbt_irec	*irec)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fsblock_t		endfsb;
-	bool			isrt;
 
-	isrt = XFS_IS_REALTIME_INODE(ip);
-	endfsb = irec->br_startblock + irec->br_blockcount - 1;
-	if (isrt && whichfork == XFS_DATA_FORK) {
-		if (!xfs_verify_rtbno(mp, irec->br_startblock))
-			return __this_address;
-		if (!xfs_verify_rtbno(mp, endfsb))
+	if (!xfs_verify_fileext(mp, irec->br_startoff, irec->br_blockcount))
+		return __this_address;
+
+	if (XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK) {
+		if (!xfs_verify_rtext(mp, irec->br_startblock,
+					  irec->br_blockcount))
 			return __this_address;
 	} else {
-		if (!xfs_verify_fsbno(mp, irec->br_startblock))
-			return __this_address;
-		if (!xfs_verify_fsbno(mp, endfsb))
-			return __this_address;
-		if (XFS_FSB_TO_AGNO(mp, irec->br_startblock) !=
-		    XFS_FSB_TO_AGNO(mp, endfsb))
+		if (!xfs_verify_fsbext(mp, irec->br_startblock,
+					   irec->br_blockcount))
 			return __this_address;
 	}
 	if (irec->br_state != XFS_EXT_NORM && whichfork != XFS_DATA_FORK)
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e1bd484e5548..6747e97a7949 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -52,9 +52,9 @@ struct xfs_extent_free_item
 {
 	xfs_fsblock_t		xefi_startblock;/* starting fs block number */
 	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */
+	bool			xefi_skip_discard;
 	struct list_head	xefi_list;
 	struct xfs_owner_info	xefi_oinfo;	/* extent owner */
-	bool			xefi_skip_discard;
 };
 
 #define	XFS_BMAP_MAX_NMAP	4
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index ecec604e6e4d..976659190d27 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -639,8 +639,6 @@ xfs_bmbt_change_owner(
 	ASSERT(XFS_IFORK_PTR(ip, whichfork)->if_format == XFS_DINODE_FMT_BTREE);
 
 	cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
-	if (!cur)
-		return -ENOMEM;
 	cur->bc_ino.flags |= XFS_BTCUR_BMBT_INVALID_OWNER;
 
 	error = xfs_btree_change_owner(cur, new_owner, buffer_list);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 2d25bab68764..c4d7a9241dc3 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -397,7 +397,7 @@ xfs_btree_dup_cursor(
 	xfs_btree_cur_t	*cur,		/* input cursor */
 	xfs_btree_cur_t	**ncur)		/* output cursor */
 {
-	xfs_buf_t	*bp;		/* btree block's buffer pointer */
+	struct xfs_buf	*bp;		/* btree block's buffer pointer */
 	int		error;		/* error return value */
 	int		i;		/* level number of btree block */
 	xfs_mount_t	*mp;		/* mount structure for filesystem */
@@ -701,7 +701,7 @@ xfs_btree_firstrec(
 	int			level)	/* level to change */
 {
 	struct xfs_btree_block	*block;	/* generic btree block pointer */
-	xfs_buf_t		*bp;	/* buffer containing block */
+	struct xfs_buf		*bp;	/* buffer containing block */
 
 	/*
 	 * Get the block pointer for this level.
@@ -731,7 +731,7 @@ xfs_btree_lastrec(
 	int			level)	/* level to change */
 {
 	struct xfs_btree_block	*block;	/* generic btree block pointer */
-	xfs_buf_t		*bp;	/* buffer containing block */
+	struct xfs_buf		*bp;	/* buffer containing block */
 
 	/*
 	 * Get the block pointer for this level.
@@ -993,7 +993,7 @@ STATIC void
 xfs_btree_setbuf(
 	xfs_btree_cur_t		*cur,	/* btree cursor */
 	int			lev,	/* level in btree */
-	xfs_buf_t		*bp)	/* new buffer to set */
+	struct xfs_buf		*bp)	/* new buffer to set */
 {
 	struct xfs_btree_block	*b;	/* btree block */
 
@@ -1636,7 +1636,7 @@ xfs_btree_decrement(
 	int			*stat)		/* success/failure */
 {
 	struct xfs_btree_block	*block;
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
 	int			error;		/* error return value */
 	int			lev;
 	union xfs_btree_ptr	ptr;
@@ -4070,7 +4070,7 @@ xfs_btree_delrec(
 	 * surviving block, and log it.
 	 */
 	xfs_btree_set_numrecs(left, lrecs + rrecs);
-	xfs_btree_get_sibling(cur, right, &cptr, XFS_BB_RIGHTSIB),
+	xfs_btree_get_sibling(cur, right, &cptr, XFS_BB_RIGHTSIB);
 	xfs_btree_set_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB);
 	xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
 
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index dd764da08f6f..630388b72dbe 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -468,11 +468,13 @@ xfs_sb_has_ro_compat_feature(
 #define XFS_SB_FEAT_INCOMPAT_SPINODES	(1 << 1)	/* sparse inode chunks */
 #define XFS_SB_FEAT_INCOMPAT_META_UUID	(1 << 2)	/* metadata UUID */
 #define XFS_SB_FEAT_INCOMPAT_BIGTIME	(1 << 3)	/* large timestamps */
+#define XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR (1 << 4)	/* needs xfs_repair */
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE|	\
 		 XFS_SB_FEAT_INCOMPAT_SPINODES|	\
 		 XFS_SB_FEAT_INCOMPAT_META_UUID| \
-		 XFS_SB_FEAT_INCOMPAT_BIGTIME)
+		 XFS_SB_FEAT_INCOMPAT_BIGTIME| \
+		 XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR)
 
 #define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
 static inline bool
@@ -584,6 +586,12 @@ static inline bool xfs_sb_version_hasinobtcounts(struct xfs_sb *sbp)
 		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT);
 }
 
+static inline bool xfs_sb_version_needsrepair(struct xfs_sb *sbp)
+{
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+		(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR);
+}
+
 /*
  * end of superblock version macros
  */
@@ -625,7 +633,6 @@ xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
 #define XFS_B_TO_FSB(mp,b)	\
 	((((uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog)
 #define XFS_B_TO_FSBT(mp,b)	(((uint64_t)(b)) >> (mp)->m_sb.sb_blocklog)
-#define XFS_B_FSB_OFFSET(mp,b)	((b) & (mp)->m_blockmask)
 
 /*
  * Allocation group header
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 974e71bc4a3a..69b228fce81a 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -607,13 +607,13 @@ error:
 
 /*
  * Allocate new inodes in the allocation group specified by agbp.
- * Return 0 for success, else error code.
+ * Returns 0 if inodes were allocated in this AG; 1 if there was no space
+ * in this AG; or the usual negative error code.
  */
 STATIC int
 xfs_ialloc_ag_alloc(
 	struct xfs_trans	*tp,
-	struct xfs_buf		*agbp,
-	int			*alloc)
+	struct xfs_buf		*agbp)
 {
 	struct xfs_agi		*agi;
 	struct xfs_alloc_arg	args;
@@ -795,10 +795,9 @@ sparse_alloc:
 		allocmask = (1 << (newlen / XFS_INODES_PER_HOLEMASK_BIT)) - 1;
 	}
 
-	if (args.fsbno == NULLFSBLOCK) {
-		*alloc = 0;
-		return 0;
-	}
+	if (args.fsbno == NULLFSBLOCK)
+		return 1;
+
 	ASSERT(args.len == args.minlen);
 
 	/*
@@ -903,7 +902,6 @@ sparse_alloc:
 	 */
 	xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, (long)newlen);
 	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, (long)newlen);
-	*alloc = 1;
 	return 0;
 }
 
@@ -1570,7 +1568,7 @@ xfs_dialloc_ag_update_inobt(
  * The caller selected an AG for us, and made sure that free inodes are
  * available.
  */
-STATIC int
+int
 xfs_dialloc_ag(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
@@ -1682,65 +1680,78 @@ error_cur:
 	return error;
 }
 
+static int
+xfs_dialloc_roll(
+	struct xfs_trans	**tpp,
+	struct xfs_buf		*agibp)
+{
+	struct xfs_trans	*tp = *tpp;
+	struct xfs_dquot_acct	*dqinfo;
+	int			error;
+
+	/*
+	 * Hold to on to the agibp across the commit so no other allocation can
+	 * come in and take the free inodes we just allocated for our caller.
+	 */
+	xfs_trans_bhold(tp, agibp);
+
+	/*
+	 * We want the quota changes to be associated with the next transaction,
+	 * NOT this one. So, detach the dqinfo from this and attach it to the
+	 * next transaction.
+	 */
+	dqinfo = tp->t_dqinfo;
+	tp->t_dqinfo = NULL;
+
+	error = xfs_trans_roll(&tp);
+
+	/* Re-attach the quota info that we detached from prev trx. */
+	tp->t_dqinfo = dqinfo;
+
+	*tpp = tp;
+	if (error)
+		return error;
+	xfs_trans_bjoin(tp, agibp);
+	return 0;
+}
+
 /*
- * Allocate an inode on disk.
- *
- * Mode is used to tell whether the new inode will need space, and whether it
- * is a directory.
+ * Select and prepare an AG for inode allocation.
  *
- * This function is designed to be called twice if it has to do an allocation
- * to make more free inodes.  On the first call, *IO_agbp should be set to NULL.
- * If an inode is available without having to performn an allocation, an inode
- * number is returned.  In this case, *IO_agbp is set to NULL.  If an allocation
- * needs to be done, xfs_dialloc returns the current AGI buffer in *IO_agbp.
- * The caller should then commit the current transaction, allocate a
- * new transaction, and call xfs_dialloc() again, passing in the previous value
- * of *IO_agbp.  IO_agbp should be held across the transactions. Since the AGI
- * buffer is locked across the two calls, the second call is guaranteed to have
- * a free inode available.
+ * Mode is used to tell whether the new inode is a directory and hence where to
+ * locate it.
  *
- * Once we successfully pick an inode its number is returned and the on-disk
- * data structures are updated.  The inode itself is not read in, since doing so
- * would break ordering constraints with xfs_reclaim.
+ * This function will ensure that the selected AG has free inodes available to
+ * allocate from. The selected AGI will be returned locked to the caller, and it
+ * will allocate more free inodes if required. If no free inodes are found or
+ * can be allocated, no AGI will be returned.
  */
 int
-xfs_dialloc(
-	struct xfs_trans	*tp,
+xfs_dialloc_select_ag(
+	struct xfs_trans	**tpp,
 	xfs_ino_t		parent,
 	umode_t			mode,
-	struct xfs_buf		**IO_agbp,
-	xfs_ino_t		*inop)
+	struct xfs_buf		**IO_agbp)
 {
-	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_mount	*mp = (*tpp)->t_mountp;
 	struct xfs_buf		*agbp;
 	xfs_agnumber_t		agno;
 	int			error;
-	int			ialloced;
-	int			noroom = 0;
+	bool			noroom = false;
 	xfs_agnumber_t		start_agno;
 	struct xfs_perag	*pag;
 	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
-	int			okalloc = 1;
+	bool			okalloc = true;
 
-	if (*IO_agbp) {
-		/*
-		 * If the caller passes in a pointer to the AGI buffer,
-		 * continue where we left off before.  In this case, we
-		 * know that the allocation group has free inodes.
-		 */
-		agbp = *IO_agbp;
-		goto out_alloc;
-	}
+	*IO_agbp = NULL;
 
 	/*
 	 * We do not have an agbp, so select an initial allocation
 	 * group for inode allocation.
 	 */
-	start_agno = xfs_ialloc_ag_select(tp, parent, mode);
-	if (start_agno == NULLAGNUMBER) {
-		*inop = NULLFSINO;
+	start_agno = xfs_ialloc_ag_select(*tpp, parent, mode);
+	if (start_agno == NULLAGNUMBER)
 		return 0;
-	}
 
 	/*
 	 * If we have already hit the ceiling of inode blocks then clear
@@ -1753,8 +1764,8 @@ xfs_dialloc(
 	if (igeo->maxicount &&
 	    percpu_counter_read_positive(&mp->m_icount) + igeo->ialloc_inos
 							> igeo->maxicount) {
-		noroom = 1;
-		okalloc = 0;
+		noroom = true;
+		okalloc = false;
 	}
 
 	/*
@@ -1771,9 +1782,9 @@ xfs_dialloc(
 		}
 
 		if (!pag->pagi_init) {
-			error = xfs_ialloc_pagi_init(mp, tp, agno);
+			error = xfs_ialloc_pagi_init(mp, *tpp, agno);
 			if (error)
-				goto out_error;
+				break;
 		}
 
 		/*
@@ -1786,64 +1797,59 @@ xfs_dialloc(
 		 * Then read in the AGI buffer and recheck with the AGI buffer
 		 * lock held.
 		 */
-		error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+		error = xfs_ialloc_read_agi(mp, *tpp, agno, &agbp);
 		if (error)
-			goto out_error;
+			break;
 
 		if (pag->pagi_freecount) {
 			xfs_perag_put(pag);
-			goto out_alloc;
+			goto found_ag;
 		}
 
 		if (!okalloc)
 			goto nextag_relse_buffer;
 
+		error = xfs_ialloc_ag_alloc(*tpp, agbp);
+		if (error < 0) {
+			xfs_trans_brelse(*tpp, agbp);
 
-		error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced);
-		if (error) {
-			xfs_trans_brelse(tp, agbp);
-
-			if (error != -ENOSPC)
-				goto out_error;
-
-			xfs_perag_put(pag);
-			*inop = NULLFSINO;
-			return 0;
+			if (error == -ENOSPC)
+				error = 0;
+			break;
 		}
 
-		if (ialloced) {
+		if (error == 0) {
 			/*
-			 * We successfully allocated some inodes, return
-			 * the current context to the caller so that it
-			 * can commit the current transaction and call
-			 * us again where we left off.
+			 * We successfully allocated space for an inode cluster
+			 * in this AG.  Roll the transaction so that we can
+			 * allocate one of the new inodes.
 			 */
 			ASSERT(pag->pagi_freecount > 0);
 			xfs_perag_put(pag);
 
-			*IO_agbp = agbp;
-			*inop = NULLFSINO;
-			return 0;
+			error = xfs_dialloc_roll(tpp, agbp);
+			if (error) {
+				xfs_buf_relse(agbp);
+				return error;
+			}
+			goto found_ag;
 		}
 
 nextag_relse_buffer:
-		xfs_trans_brelse(tp, agbp);
+		xfs_trans_brelse(*tpp, agbp);
 nextag:
 		xfs_perag_put(pag);
 		if (++agno == mp->m_sb.sb_agcount)
 			agno = 0;
-		if (agno == start_agno) {
-			*inop = NULLFSINO;
+		if (agno == start_agno)
 			return noroom ? -ENOSPC : 0;
-		}
 	}
 
-out_alloc:
-	*IO_agbp = NULL;
-	return xfs_dialloc_ag(tp, agbp, parent, inop);
-out_error:
 	xfs_perag_put(pag);
 	return error;
+found_ag:
+	*IO_agbp = agbp;
+	return 0;
 }
 
 /*
@@ -2453,7 +2459,7 @@ out_map:
 void
 xfs_ialloc_log_agi(
 	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_buf_t	*bp,		/* allocation group header buffer */
+	struct xfs_buf	*bp,		/* allocation group header buffer */
 	int		fields)		/* bitmask of fields to log */
 {
 	int			first;		/* first byte number */
@@ -2674,7 +2680,7 @@ xfs_ialloc_pagi_init(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_agnumber_t	agno)		/* allocation group number */
 {
-	xfs_buf_t	*bp = NULL;
+	struct xfs_buf	*bp = NULL;
 	int		error;
 
 	error = xfs_ialloc_read_agi(mp, tp, agno, &bp);
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 72b3468b97b1..3511086a7ae1 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -37,30 +37,26 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o)
  * Mode is used to tell whether the new inode will need space, and whether
  * it is a directory.
  *
- * To work within the constraint of one allocation per transaction,
- * xfs_dialloc() is designed to be called twice if it has to do an
- * allocation to make more free inodes.  If an inode is
- * available without an allocation, agbp would be set to the current
- * agbp and alloc_done set to false.
- * If an allocation needed to be done, agbp would be set to the
- * inode header of the allocation group and alloc_done set to true.
- * The caller should then commit the current transaction and allocate a new
- * transaction.  xfs_dialloc() should then be called again with
- * the agbp value returned from the previous call.
- *
- * Once we successfully pick an inode its number is returned and the
- * on-disk data structures are updated.  The inode itself is not read
- * in, since doing so would break ordering constraints with xfs_reclaim.
- *
- * *agbp should be set to NULL on the first call, *alloc_done set to FALSE.
+ * There are two phases to inode allocation: selecting an AG and ensuring
+ * that it contains free inodes, followed by allocating one of the free
+ * inodes. xfs_dialloc_select_ag() does the former and returns a locked AGI
+ * to the caller, ensuring that followup call to xfs_dialloc_ag() will
+ * have free inodes to allocate from. xfs_dialloc_ag() will return the inode
+ * number of the free inode we allocated.
  */
 int					/* error */
-xfs_dialloc(
-	struct xfs_trans *tp,		/* transaction pointer */
+xfs_dialloc_select_ag(
+	struct xfs_trans **tpp,		/* double pointer of transaction */
 	xfs_ino_t	parent,		/* parent inode (directory) */
 	umode_t		mode,		/* mode bits for new inode */
-	struct xfs_buf	**agbp,		/* buf for a.g. inode header */
-	xfs_ino_t	*inop);		/* inode number allocated */
+	struct xfs_buf	**IO_agbp);
+
+int
+xfs_dialloc_ag(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	xfs_ino_t		parent,
+	xfs_ino_t		*inop);
 
 /*
  * Free disk inode.  Carefully avoids touching the incore inode, all
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index cc919a2ee870..4c5831646bd9 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -672,11 +672,6 @@ xfs_inobt_cur(
 		return error;
 
 	cur = xfs_inobt_init_cursor(mp, tp, *agi_bpp, agno, which);
-	if (!cur) {
-		xfs_trans_brelse(tp, *agi_bpp);
-		*agi_bpp = NULL;
-		return -ENOMEM;
-	}
 	*curpp = cur;
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index c667c63f2cb0..4d7410e49db4 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -547,10 +547,6 @@ xfs_dinode_verify(
 	if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME))
 		return __this_address;
 
-	/* don't let reflink and dax mix */
-	if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags2 & XFS_DIFLAG2_DAX))
-		return __this_address;
-
 	/* COW extent size hint validation */
 	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
 			mode, flags, flags2);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 2076627243b0..2037b9f23069 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1179,10 +1179,6 @@ xfs_refcount_finish_one(
 			return error;
 
 		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
-		if (!rcur) {
-			error = -ENOMEM;
-			goto out_cur;
-		}
 		rcur->bc_ag.refc.nr_ops = nr_ops;
 		rcur->bc_ag.refc.shape_changes = shape_changes;
 	}
@@ -1217,11 +1213,6 @@ xfs_refcount_finish_one(
 		trace_xfs_refcount_finish_one_leftover(mp, agno, type,
 				bno, blockcount, new_agbno, *new_len);
 	return error;
-
-out_cur:
-	xfs_trans_brelse(tp, agbp);
-
-	return error;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 340c83f76c80..10e0cf9949a2 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -1514,7 +1514,7 @@ xfs_rmap_convert_shared(
 	 * record for our insertion point. This will also give us the record for
 	 * start block contiguity tests.
 	 */
-	error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags,
+	error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext,
 			&PREV, &i);
 	if (error)
 		goto done;
@@ -2404,10 +2404,6 @@ xfs_rmap_finish_one(
 			return -EFSCORRUPTED;
 
 		rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
-		if (!rcur) {
-			error = -ENOMEM;
-			goto out_cur;
-		}
 	}
 	*pcur = rcur;
 
@@ -2446,11 +2442,6 @@ xfs_rmap_finish_one(
 		error = -EFSCORRUPTED;
 	}
 	return error;
-
-out_cur:
-	xfs_trans_brelse(tp, agbp);
-
-	return error;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 6c1aba16113c..fe3a49575ff3 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -56,9 +56,9 @@ xfs_rtbuf_get(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_rtblock_t	block,		/* block number in bitmap or summary */
 	int		issum,		/* is summary not bitmap */
-	xfs_buf_t	**bpp)		/* output: buffer for the block */
+	struct xfs_buf	**bpp)		/* output: buffer for the block */
 {
-	xfs_buf_t	*bp;		/* block buffer, result */
+	struct xfs_buf	*bp;		/* block buffer, result */
 	xfs_inode_t	*ip;		/* bitmap or summary inode */
 	xfs_bmbt_irec_t	map;
 	int		nmap = 1;
@@ -101,7 +101,7 @@ xfs_rtfind_back(
 	xfs_rtword_t	*b;		/* current word in buffer */
 	int		bit;		/* bit number in the word */
 	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
+	struct xfs_buf	*bp;		/* buf for the block */
 	xfs_rtword_t	*bufp;		/* starting word in buffer */
 	int		error;		/* error value */
 	xfs_rtblock_t	firstbit;	/* first useful bit in the word */
@@ -276,7 +276,7 @@ xfs_rtfind_forw(
 	xfs_rtword_t	*b;		/* current word in buffer */
 	int		bit;		/* bit number in the word */
 	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
+	struct xfs_buf	*bp;		/* buf for the block */
 	xfs_rtword_t	*bufp;		/* starting word in buffer */
 	int		error;		/* error value */
 	xfs_rtblock_t	i;		/* current bit number rel. to start */
@@ -447,11 +447,11 @@ xfs_rtmodify_summary_int(
 	int		log,		/* log2 of extent size */
 	xfs_rtblock_t	bbno,		/* bitmap block number */
 	int		delta,		/* change to make to summary info */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	struct xfs_buf	**rbpp,		/* in/out: summary block buffer */
 	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
 	xfs_suminfo_t	*sum)		/* out: summary info for this block */
 {
-	xfs_buf_t	*bp;		/* buffer for the summary block */
+	struct xfs_buf	*bp;		/* buffer for the summary block */
 	int		error;		/* error value */
 	xfs_fsblock_t	sb;		/* summary fsblock */
 	int		so;		/* index into the summary file */
@@ -517,7 +517,7 @@ xfs_rtmodify_summary(
 	int		log,		/* log2 of extent size */
 	xfs_rtblock_t	bbno,		/* bitmap block number */
 	int		delta,		/* change to make to summary info */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	struct xfs_buf	**rbpp,		/* in/out: summary block buffer */
 	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
 {
 	return xfs_rtmodify_summary_int(mp, tp, log, bbno,
@@ -539,7 +539,7 @@ xfs_rtmodify_range(
 	xfs_rtword_t	*b;		/* current word in buffer */
 	int		bit;		/* bit number in the word */
 	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
+	struct xfs_buf	*bp;		/* buf for the block */
 	xfs_rtword_t	*bufp;		/* starting word in buffer */
 	int		error;		/* error value */
 	xfs_rtword_t	*first;		/* first used word in the buffer */
@@ -690,7 +690,7 @@ xfs_rtfree_range(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_rtblock_t	start,		/* starting block to free */
 	xfs_extlen_t	len,		/* length to free */
-	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	struct xfs_buf	**rbpp,		/* in/out: summary block buffer */
 	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
 {
 	xfs_rtblock_t	end;		/* end of the freed extent */
@@ -773,7 +773,7 @@ xfs_rtcheck_range(
 	xfs_rtword_t	*b;		/* current word in buffer */
 	int		bit;		/* bit number in the word */
 	xfs_rtblock_t	block;		/* bitmap block number */
-	xfs_buf_t	*bp;		/* buf for the block */
+	struct xfs_buf	*bp;		/* buf for the block */
 	xfs_rtword_t	*bufp;		/* starting word in buffer */
 	int		error;		/* error value */
 	xfs_rtblock_t	i;		/* current bit number rel. to start */
@@ -969,7 +969,7 @@ xfs_rtfree_extent(
 	int		error;		/* error value */
 	xfs_mount_t	*mp;		/* file system mount structure */
 	xfs_fsblock_t	sb;		/* summary file block number */
-	xfs_buf_t	*sumbp = NULL;	/* summary file block buffer */
+	struct xfs_buf	*sumbp = NULL;	/* summary file block buffer */
 
 	mp = tp->t_mountp;
 
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 5aeafa59ed27..bbda117e5d85 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -360,21 +360,18 @@ xfs_validate_sb_common(
 		}
 	}
 
-	if (sbp->sb_unit) {
-		if (!xfs_sb_version_hasdalign(sbp) ||
-		    sbp->sb_unit > sbp->sb_width ||
-		    (sbp->sb_width % sbp->sb_unit) != 0) {
-			xfs_notice(mp, "SB stripe unit sanity check failed");
-			return -EFSCORRUPTED;
-		}
-	} else if (xfs_sb_version_hasdalign(sbp)) {
+	/*
+	 * Either (sb_unit and !hasdalign) or (!sb_unit and hasdalign)
+	 * would imply the image is corrupted.
+	 */
+	if (!!sbp->sb_unit ^ xfs_sb_version_hasdalign(sbp)) {
 		xfs_notice(mp, "SB stripe alignment sanity check failed");
 		return -EFSCORRUPTED;
-	} else if (sbp->sb_width) {
-		xfs_notice(mp, "SB stripe width sanity check failed");
-		return -EFSCORRUPTED;
 	}
 
+	if (!xfs_validate_stripe_geometry(mp, XFS_FSB_TO_B(mp, sbp->sb_unit),
+			XFS_FSB_TO_B(mp, sbp->sb_width), 0, false))
+		return -EFSCORRUPTED;
 
 	if (xfs_sb_version_hascrc(&mp->m_sb) &&
 	    sbp->sb_blocksize < XFS_MIN_CRC_BLOCKSIZE) {
@@ -383,17 +380,6 @@ xfs_validate_sb_common(
 	}
 
 	/*
-	 * Until this is fixed only page-sized or smaller data blocks work.
-	 */
-	if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
-		xfs_warn(mp,
-		"File system with blocksize %d bytes. "
-		"Only pagesize (%ld) or less will currently work.",
-				sbp->sb_blocksize, PAGE_SIZE);
-		return -ENOSYS;
-	}
-
-	/*
 	 * Currently only very few inode sizes are supported.
 	 */
 	switch (sbp->sb_inodesize) {
@@ -408,22 +394,6 @@ xfs_validate_sb_common(
 		return -ENOSYS;
 	}
 
-	if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
-	    xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
-		xfs_warn(mp,
-		"file system too large to be mounted on this system.");
-		return -EFBIG;
-	}
-
-	/*
-	 * Don't touch the filesystem if a user tool thinks it owns the primary
-	 * superblock.  mkfs doesn't clear the flag from secondary supers, so
-	 * we don't check them at all.
-	 */
-	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && sbp->sb_inprogress) {
-		xfs_warn(mp, "Offline file system operation in progress!");
-		return -EFSCORRUPTED;
-	}
 	return 0;
 }
 
@@ -1233,3 +1203,61 @@ xfs_sb_get_secondary(
 	*bpp = bp;
 	return 0;
 }
+
+/*
+ * sunit, swidth, sectorsize(optional with 0) should be all in bytes,
+ * so users won't be confused by values in error messages.
+ */
+bool
+xfs_validate_stripe_geometry(
+	struct xfs_mount	*mp,
+	__s64			sunit,
+	__s64			swidth,
+	int			sectorsize,
+	bool			silent)
+{
+	if (swidth > INT_MAX) {
+		if (!silent)
+			xfs_notice(mp,
+"stripe width (%lld) is too large", swidth);
+		return false;
+	}
+
+	if (sunit > swidth) {
+		if (!silent)
+			xfs_notice(mp,
+"stripe unit (%lld) is larger than the stripe width (%lld)", sunit, swidth);
+		return false;
+	}
+
+	if (sectorsize && (int)sunit % sectorsize) {
+		if (!silent)
+			xfs_notice(mp,
+"stripe unit (%lld) must be a multiple of the sector size (%d)",
+				   sunit, sectorsize);
+		return false;
+	}
+
+	if (sunit && !swidth) {
+		if (!silent)
+			xfs_notice(mp,
+"invalid stripe unit (%lld) and stripe width of 0", sunit);
+		return false;
+	}
+
+	if (!sunit && swidth) {
+		if (!silent)
+			xfs_notice(mp,
+"invalid stripe width (%lld) and stripe unit of 0", swidth);
+		return false;
+	}
+
+	if (sunit && (int)swidth % (int)sunit) {
+		if (!silent)
+			xfs_notice(mp,
+"stripe width (%lld) must be a multiple of the stripe unit (%lld)",
+				   swidth, sunit);
+		return false;
+	}
+	return true;
+}
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 92465a9a5162..f79f9dc632b6 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -42,4 +42,7 @@ extern int	xfs_sb_get_secondary(struct xfs_mount *mp,
 				struct xfs_trans *tp, xfs_agnumber_t agno,
 				struct xfs_buf **bpp);
 
+extern bool	xfs_validate_stripe_geometry(struct xfs_mount *mp,
+		__s64 sunit, __s64 swidth, int sectorsize, bool silent);
+
 #endif	/* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index c795ae47b3c9..8c61a461bf7b 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -62,7 +62,6 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define	XFS_TRANS_SB_DIRTY	0x02	/* superblock is modified */
 #define	XFS_TRANS_PERM_LOG_RES	0x04	/* xact took a permanent log res */
 #define	XFS_TRANS_SYNC		0x08	/* make commit synchronous */
-#define XFS_TRANS_DQ_DIRTY	0x10	/* at least one dquot in trx dirty */
 #define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
 #define XFS_TRANS_NO_WRITECOUNT 0x40	/* do not elevate SB writecount */
 #define XFS_TRANS_RES_FDBLKS	0x80	/* reserve newly freed blocks */
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index 4f595546a639..b254fbeaaa50 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -61,6 +61,29 @@ xfs_verify_fsbno(
 	return xfs_verify_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno));
 }
 
+/*
+ * Verify that a data device extent is fully contained inside the filesystem,
+ * does not cross an AG boundary, and does not point at static metadata.
+ */
+bool
+xfs_verify_fsbext(
+	struct xfs_mount	*mp,
+	xfs_fsblock_t		fsbno,
+	xfs_fsblock_t		len)
+{
+	if (fsbno + len <= fsbno)
+		return false;
+
+	if (!xfs_verify_fsbno(mp, fsbno))
+		return false;
+
+	if (!xfs_verify_fsbno(mp, fsbno + len - 1))
+		return false;
+
+	return  XFS_FSB_TO_AGNO(mp, fsbno) ==
+		XFS_FSB_TO_AGNO(mp, fsbno + len - 1);
+}
+
 /* Calculate the first and last possible inode number in an AG. */
 void
 xfs_agino_range(
@@ -175,6 +198,22 @@ xfs_verify_rtbno(
 	return rtbno < mp->m_sb.sb_rblocks;
 }
 
+/* Verify that a realtime device extent is fully contained inside the volume. */
+bool
+xfs_verify_rtext(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno,
+	xfs_rtblock_t		len)
+{
+	if (rtbno + len <= rtbno)
+		return false;
+
+	if (!xfs_verify_rtbno(mp, rtbno))
+		return false;
+
+	return xfs_verify_rtbno(mp, rtbno + len - 1);
+}
+
 /* Calculate the range of valid icount values. */
 void
 xfs_icount_range(
@@ -219,3 +258,28 @@ xfs_verify_dablk(
 
 	return dabno <= max_dablk;
 }
+
+/* Check that a file block offset does not exceed the maximum. */
+bool
+xfs_verify_fileoff(
+	struct xfs_mount	*mp,
+	xfs_fileoff_t		off)
+{
+	return off <= XFS_MAX_FILEOFF;
+}
+
+/* Check that a range of file block offsets do not exceed the maximum. */
+bool
+xfs_verify_fileext(
+	struct xfs_mount	*mp,
+	xfs_fileoff_t		off,
+	xfs_fileoff_t		len)
+{
+	if (off + len <= off)
+		return false;
+
+	if (!xfs_verify_fileoff(mp, off))
+		return false;
+
+	return xfs_verify_fileoff(mp, off + len - 1);
+}
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 397d94775440..064bd6e8c922 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -184,6 +184,8 @@ xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno);
 bool xfs_verify_agbno(struct xfs_mount *mp, xfs_agnumber_t agno,
 		xfs_agblock_t agbno);
 bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno);
+bool xfs_verify_fsbext(struct xfs_mount *mp, xfs_fsblock_t fsbno,
+		xfs_fsblock_t len);
 
 void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
 		xfs_agino_t *first, xfs_agino_t *last);
@@ -195,9 +197,14 @@ bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
+bool xfs_verify_rtext(struct xfs_mount *mp, xfs_rtblock_t rtbno,
+		xfs_rtblock_t len);
 bool xfs_verify_icount(struct xfs_mount *mp, unsigned long long icount);
 bool xfs_verify_dablk(struct xfs_mount *mp, xfs_fileoff_t off);
 void xfs_icount_range(struct xfs_mount *mp, unsigned long long *min,
 		unsigned long long *max);
+bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off);
+bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off,
+		xfs_fileoff_t len);
 
 #endif	/* __XFS_TYPES_H__ */