1 files changed, 88 insertions, 82 deletions

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);