Merge git://oss.sgi.com:8090/xfs/xfs-2.6

* git://oss.sgi.com:8090/xfs/xfs-2.6:
  [XFS] Fix a bad pointer dereference in the quota statvfs handling.
  [XFS] Fix xfs_splice_write() so appended data gets to disk.
  [XFS] Fix ABBA deadlock between i_mutex and iolock. Avoid calling
  [XFS] Prevent free space oversubscription and xfssyncd looping.

7 files changed, 76 insertions, 42 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index c40f81ba9b1..34dcb43a783 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1390,11 +1390,19 @@ xfs_vm_direct_IO(
 
 	iocb->private = xfs_alloc_ioend(inode, IOMAP_UNWRITTEN);
 
-	ret = blockdev_direct_IO_own_locking(rw, iocb, inode,
-		iomap.iomap_target->bt_bdev,
-		iov, offset, nr_segs,
-		xfs_get_blocks_direct,
-		xfs_end_io_direct);
+	if (rw == WRITE) {
+		ret = blockdev_direct_IO_own_locking(rw, iocb, inode,
+			iomap.iomap_target->bt_bdev,
+			iov, offset, nr_segs,
+			xfs_get_blocks_direct,
+			xfs_end_io_direct);
+	} else {
+		ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
+			iomap.iomap_target->bt_bdev,
+			iov, offset, nr_segs,
+			xfs_get_blocks_direct,
+			xfs_end_io_direct);
+	}
 
 	if (unlikely(ret <= 0 && iocb->private))
 		xfs_destroy_ioend(iocb->private);
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 5d9cfd91ad0..ee788b1cb36 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -264,7 +264,9 @@ xfs_read(
 					dmflags, &locktype);
 		if (ret) {
 			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-			goto unlock_mutex;
+			if (unlikely(ioflags & IO_ISDIRECT))
+				mutex_unlock(&inode->i_mutex);
+			return ret;
 		}
 	}
 
@@ -272,6 +274,9 @@ xfs_read(
 		bhv_vop_flushinval_pages(vp, ctooff(offtoct(*offset)),
 						-1, FI_REMAPF_LOCKED);
 
+	if (unlikely(ioflags & IO_ISDIRECT))
+		mutex_unlock(&inode->i_mutex);
+
 	xfs_rw_enter_trace(XFS_READ_ENTER, &ip->i_iocore,
 				(void *)iovp, segs, *offset, ioflags);
 	ret = __generic_file_aio_read(iocb, iovp, segs, offset);
@@ -281,10 +286,6 @@ xfs_read(
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-
-unlock_mutex:
-	if (unlikely(ioflags & IO_ISDIRECT))
-		mutex_unlock(&inode->i_mutex);
 	return ret;
 }
 
@@ -390,6 +391,8 @@ xfs_splice_write(
 	xfs_inode_t		*ip = XFS_BHVTOI(bdp);
 	xfs_mount_t		*mp = ip->i_mount;
 	ssize_t			ret;
+	struct inode		*inode = outfilp->f_mapping->host;
+	xfs_fsize_t		isize;
 
 	XFS_STATS_INC(xs_write_calls);
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -416,6 +419,20 @@ xfs_splice_write(
 	if (ret > 0)
 		XFS_STATS_ADD(xs_write_bytes, ret);
 
+	isize = i_size_read(inode);
+	if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
+		*ppos = isize;
+
+	if (*ppos > ip->i_d.di_size) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		if (*ppos > ip->i_d.di_size) {
+			ip->i_d.di_size = *ppos;
+			i_size_write(inode, *ppos);
+			ip->i_update_core = 1;
+			ip->i_update_size = 1;
+		}
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	}
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	return ret;
 }
diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c
index f137856c326..db8872be8c8 100644
--- a/fs/xfs/quota/xfs_qm_bhv.c
+++ b/fs/xfs/quota/xfs_qm_bhv.c
@@ -203,7 +203,7 @@ xfs_qm_statvfs(
 	if (error || !vnode)
 		return error;
 
-	mp = XFS_BHVTOM(bhv);
+	mp = xfs_vfstom(bhvtovfs(bhv));
 	ip = xfs_vtoi(vnode);
 
 	if (!(ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT))
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 650591f999a..5a4256120cc 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -44,6 +44,26 @@ typedef enum xfs_alloctype
 #define	XFS_ALLOC_FLAG_FREEING	0x00000002  /* indicate caller is freeing extents*/
 
 /*
+ * In order to avoid ENOSPC-related deadlock caused by
+ * out-of-order locking of AGF buffer (PV 947395), we place
+ * constraints on the relationship among actual allocations for
+ * data blocks, freelist blocks, and potential file data bmap
+ * btree blocks. However, these restrictions may result in no
+ * actual space allocated for a delayed extent, for example, a data
+ * block in a certain AG is allocated but there is no additional
+ * block for the additional bmap btree block due to a split of the
+ * bmap btree of the file. The result of this may lead to an
+ * infinite loop in xfssyncd when the file gets flushed to disk and
+ * all delayed extents need to be actually allocated. To get around
+ * this, we explicitly set aside a few blocks which will not be
+ * reserved in delayed allocation. Considering the minimum number of
+ * needed freelist blocks is 4 fsbs _per AG_, a potential split of file's bmap
+ * btree requires 1 fsb, so we set the number of set-aside blocks
+ * to 4 + 4*agcount.
+ */
+#define XFS_ALLOC_SET_ASIDE(mp)  (4 + ((mp)->m_sb.sb_agcount * 4))
+
+/*
  * Argument structure for xfs_alloc routines.
  * This is turned into a structure to avoid having 20 arguments passed
  * down several levels of the stack.
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 077629bab53..c064e72ada9 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -462,7 +462,7 @@ xfs_fs_counts(
 
 	xfs_icsb_sync_counters_lazy(mp);
 	s = XFS_SB_LOCK(mp);
-	cnt->freedata = mp->m_sb.sb_fdblocks;
+	cnt->freedata = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 	cnt->freertx = mp->m_sb.sb_frextents;
 	cnt->freeino = mp->m_sb.sb_ifree;
 	cnt->allocino = mp->m_sb.sb_icount;
@@ -519,15 +519,19 @@ xfs_reserve_blocks(
 		}
 		mp->m_resblks = request;
 	} else {
+		__int64_t	free;
+
+		free =  mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 		delta = request - mp->m_resblks;
-		lcounter = mp->m_sb.sb_fdblocks - delta;
+		lcounter = free - delta;
 		if (lcounter < 0) {
 			/* We can't satisfy the request, just get what we can */
-			mp->m_resblks += mp->m_sb.sb_fdblocks;
-			mp->m_resblks_avail += mp->m_sb.sb_fdblocks;
-			mp->m_sb.sb_fdblocks = 0;
+			mp->m_resblks += free;
+			mp->m_resblks_avail += free;
+			mp->m_sb.sb_fdblocks = XFS_ALLOC_SET_ASIDE(mp);
 		} else {
-			mp->m_sb.sb_fdblocks = lcounter;
+			mp->m_sb.sb_fdblocks =
+				lcounter + XFS_ALLOC_SET_ASIDE(mp);
 			mp->m_resblks = request;
 			mp->m_resblks_avail += delta;
 		}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 4be5c0b2d29..9dfae18d995 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1243,24 +1243,6 @@ xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
 	xfs_trans_log_buf(tp, bp, first, last);
 }
 
-/*
- * In order to avoid ENOSPC-related deadlock caused by
- * out-of-order locking of AGF buffer (PV 947395), we place
- * constraints on the relationship among actual allocations for
- * data blocks, freelist blocks, and potential file data bmap
- * btree blocks. However, these restrictions may result in no
- * actual space allocated for a delayed extent, for example, a data
- * block in a certain AG is allocated but there is no additional
- * block for the additional bmap btree block due to a split of the
- * bmap btree of the file. The result of this may lead to an
- * infinite loop in xfssyncd when the file gets flushed to disk and
- * all delayed extents need to be actually allocated. To get around
- * this, we explicitly set aside a few blocks which will not be
- * reserved in delayed allocation. Considering the minimum number of
- * needed freelist blocks is 4 fsbs, a potential split of file's bmap
- * btree requires 1 fsb, so we set the number of set-aside blocks to 8.
-*/
-#define SET_ASIDE_BLOCKS 8
 
 /*
  * xfs_mod_incore_sb_unlocked() is a utility routine common used to apply
@@ -1306,7 +1288,8 @@ xfs_mod_incore_sb_unlocked(xfs_mount_t *mp, xfs_sb_field_t field,
 		return 0;
 	case XFS_SBS_FDBLOCKS:
 
-		lcounter = (long long)mp->m_sb.sb_fdblocks - SET_ASIDE_BLOCKS;
+		lcounter = (long long)
+			mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);
 
 		if (delta > 0) {		/* Putting blocks back */
@@ -1340,7 +1323,7 @@ xfs_mod_incore_sb_unlocked(xfs_mount_t *mp, xfs_sb_field_t field,
 			}
 		}
 
-		mp->m_sb.sb_fdblocks = lcounter + SET_ASIDE_BLOCKS;
+		mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
 		return 0;
 	case XFS_SBS_FREXTENTS:
 		lcounter = (long long)mp->m_sb.sb_frextents;
@@ -2021,7 +2004,8 @@ xfs_icsb_sync_counters_lazy(
  * when we get near ENOSPC.
  */
 #define XFS_ICSB_INO_CNTR_REENABLE	64
-#define XFS_ICSB_FDBLK_CNTR_REENABLE	512
+#define XFS_ICSB_FDBLK_CNTR_REENABLE(mp) \
+		(512 + XFS_ALLOC_SET_ASIDE(mp))
 STATIC void
 xfs_icsb_balance_counter(
 	xfs_mount_t	*mp,
@@ -2055,7 +2039,7 @@ xfs_icsb_balance_counter(
 	case XFS_SBS_FDBLOCKS:
 		count = mp->m_sb.sb_fdblocks;
 		resid = do_div(count, weight);
-		if (count < XFS_ICSB_FDBLK_CNTR_REENABLE)
+		if (count < XFS_ICSB_FDBLK_CNTR_REENABLE(mp))
 			goto out;
 		break;
 	default:
@@ -2110,11 +2094,11 @@ again:
 	case XFS_SBS_FDBLOCKS:
 		BUG_ON((mp->m_resblks - mp->m_resblks_avail) != 0);
 
-		lcounter = icsbp->icsb_fdblocks;
+		lcounter = icsbp->icsb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 		lcounter += delta;
 		if (unlikely(lcounter < 0))
 			goto slow_path;
-		icsbp->icsb_fdblocks = lcounter;
+		icsbp->icsb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
 		break;
 	default:
 		BUG();
diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
index b427d220a16..a34796e57af 100644
--- a/fs/xfs/xfs_vfsops.c
+++ b/fs/xfs/xfs_vfsops.c
@@ -811,7 +811,8 @@ xfs_statvfs(
 	statp->f_bsize = sbp->sb_blocksize;
 	lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;
 	statp->f_blocks = sbp->sb_dblocks - lsize;
-	statp->f_bfree = statp->f_bavail = sbp->sb_fdblocks;
+	statp->f_bfree = statp->f_bavail =
+				sbp->sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 	fakeinos = statp->f_bfree << sbp->sb_inopblog;
 #if XFS_BIG_INUMS
 	fakeinos += mp->m_inoadd;