[PATCH 18/27] xfs: Convert to new freezing code

[PATCH 18/27] xfs: Convert to new freezing code

[Jan Kara]

Generic code now blocks all writers from standard write paths. So we add
blocking of all writers coming from ioctl (we get a protection of ioctl against
racing remount read-only as a bonus) and convert xfs_file_aio_write() to a
non-racy freeze protection. We also keep freeze protection on transaction
start to block internal filesystem writes such as removal of preallocated
blocks.

CC: Ben Myers <bpm@sgi.com>
CC: Alex Elder <elder@kernel.org>
CC: xfs@oss.sgi.com
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/xfs/xfs_file.c    |   10 ++++++--
 fs/xfs/xfs_ioctl.c   |   55 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/xfs/xfs_ioctl32.c |   12 ++++++++++
 fs/xfs/xfs_iomap.c   |    4 +-
 fs/xfs/xfs_mount.c   |    2 +-
 fs/xfs/xfs_mount.h   |    3 --
 fs/xfs/xfs_sync.c    |    2 +-
 fs/xfs/xfs_trans.c   |   17 ++++++++++++--
 fs/xfs/xfs_trans.h   |    2 +
 9 files changed, 91 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 54a67dd..7c4c471 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -822,10 +822,12 @@ xfs_file_aio_write(
 	if (ocount == 0)
 		return 0;
 
-	xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+		ret = -EIO;
+		goto out;
+	}
 
 	if (unlikely(file->f_flags & O_DIRECT))
 		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
@@ -844,6 +846,8 @@ xfs_file_aio_write(
 			ret = err;
 	}
 
+out:
+	sb_end_write(inode->i_sb);
 	return ret;
 }
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 91f8ff5..828b7cb 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -363,9 +363,15 @@ xfs_fssetdm_by_handle(
 	if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
 
+	error = mnt_want_write_file(parfilp);
+	if (error)
+		return error;
+
 	dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq);
-	if (IS_ERR(dentry))
+	if (IS_ERR(dentry)) {
+		mnt_drop_write_file(parfilp);
 		return PTR_ERR(dentry);
+	}
 
 	if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) {
 		error = -XFS_ERROR(EPERM);
@@ -381,6 +387,7 @@ xfs_fssetdm_by_handle(
 				 fsd.fsd_dmstate);
 
  out:
+	mnt_drop_write_file(parfilp);
 	dput(dentry);
 	return error;
 }
@@ -633,7 +640,11 @@ xfs_ioc_space(
 	if (ioflags & IO_INVIS)
 		attr_flags |= XFS_ATTR_DMI;
 
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
 	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
+	mnt_drop_write_file(filp);
 	return -error;
 }
 
@@ -1162,6 +1173,7 @@ xfs_ioc_fssetxattr(
 {
 	struct fsxattr		fa;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&fa, arg, sizeof(fa)))
 		return -EFAULT;
@@ -1170,7 +1182,12 @@ xfs_ioc_fssetxattr(
 	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
 		mask |= FSX_NONBLOCK;
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1195,6 +1212,7 @@ xfs_ioc_setxflags(
 	struct fsxattr		fa;
 	unsigned int		flags;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
 		return -EFAULT;
@@ -1209,7 +1227,12 @@ xfs_ioc_setxflags(
 		mask |= FSX_NONBLOCK;
 	fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1384,8 +1407,13 @@ xfs_file_ioctl(
 		if (copy_from_user(&dmi, arg, sizeof(dmi)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
 				dmi.fsd_dmstate);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1433,7 +1461,11 @@ xfs_file_ioctl(
 
 		if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1462,9 +1494,14 @@ xfs_file_ioctl(
 		if (copy_from_user(&inout, arg, sizeof(inout)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		/* input parameter is passed in resblks field of structure */
 		in = inout.resblks;
 		error = xfs_reserve_blocks(mp, &in, &inout);
+		mnt_drop_write_file(filp);
 		if (error)
 			return -error;
 
@@ -1495,7 +1532,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1505,7 +1546,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_log(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1515,7 +1560,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index a849a54..542ce93 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -602,7 +602,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_data_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSGROWFSRT_32: {
@@ -610,7 +614,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_rt_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 #endif
@@ -629,7 +637,11 @@ xfs_file_compat_ioctl(
 				   offsetof(struct xfs_swapext, sx_stat)) ||
 		    xfs_ioctl32_bstat_copyin(&sxp.sx_stat, &sxu->sx_stat))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSBULKSTAT_32:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 71a4645..dbcae37 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -681,9 +681,9 @@ xfs_iomap_write_unwritten(
 		 * the same inode that we complete here and might deadlock
 		 * on the iolock.
 		 */
-		xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
+		sb_start_intwrite(mp->m_super);
 		tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS);
-		tp->t_flags |= XFS_TRANS_RESERVE;
+		tp->t_flags |= XFS_TRANS_RESERVE | XFS_TRANS_FREEZE_PROT;
 		error = xfs_trans_reserve(tp, resblks,
 				XFS_WRITE_LOG_RES(mp), 0,
 				XFS_TRANS_PERM_LOG_RES,
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 1ffead4..5aa7444 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1543,7 +1543,7 @@ xfs_unmountfs(
 int
 xfs_fs_writable(xfs_mount_t *mp)
 {
-	return !(xfs_test_for_freeze(mp) || XFS_FORCED_SHUTDOWN(mp) ||
+	return !(mp->m_super->s_writers.frozen || XFS_FORCED_SHUTDOWN(mp) ||
 		(mp->m_flags & XFS_MOUNT_RDONLY));
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 9eba738..73f6c7a 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -313,9 +313,6 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 #define SHUTDOWN_REMOTE_REQ	0x0010	/* shutdown came from remote cell */
 #define SHUTDOWN_DEVICE_REQ	0x0020	/* failed all paths to the device */
 
-#define xfs_test_for_freeze(mp)		((mp)->m_super->s_frozen)
-#define xfs_wait_for_freeze(mp,l)	vfs_check_frozen((mp)->m_super, (l))
-
 /*
  * Flags for xfs_mountfs
  */
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 205ebcb..cb99ce0 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -462,7 +462,7 @@ xfs_sync_worker(
 
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
 		/* dgc: errors ignored here */
-		if (mp->m_super->s_frozen == SB_UNFROZEN &&
+		if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
 		    xfs_log_need_covered(mp))
 			error = xfs_fs_log_dummy(mp);
 		else
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 103b00c..d012dd2 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -577,8 +577,12 @@ xfs_trans_alloc(
 	xfs_mount_t	*mp,
 	uint		type)
 {
-	xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
-	return _xfs_trans_alloc(mp, type, KM_SLEEP);
+	xfs_trans_t     *tp;
+
+	sb_start_intwrite(mp->m_super);
+	tp = _xfs_trans_alloc(mp, type, KM_SLEEP);
+	tp->t_flags |= XFS_TRANS_FREEZE_PROT;
+	return tp;
 }
 
 xfs_trans_t *
@@ -589,6 +593,7 @@ _xfs_trans_alloc(
 {
 	xfs_trans_t	*tp;
 
+	WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
 	atomic_inc(&mp->m_active_trans);
 
 	tp = kmem_zone_zalloc(xfs_trans_zone, memflags);
@@ -612,6 +617,8 @@ xfs_trans_free(
 	xfs_alloc_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	atomic_dec(&tp->t_mountp->m_active_trans);
+	if (tp->t_flags & XFS_TRANS_FREEZE_PROT)
+		sb_end_intwrite(tp->t_mountp->m_super);
 	xfs_trans_free_dqinfo(tp);
 	kmem_zone_free(xfs_trans_zone, tp);
 }
@@ -644,7 +651,11 @@ xfs_trans_dup(
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
 
-	ntp->t_flags = XFS_TRANS_PERM_LOG_RES | (tp->t_flags & XFS_TRANS_RESERVE);
+	ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
+		       (tp->t_flags & XFS_TRANS_RESERVE) |
+		       (tp->t_flags & XFS_TRANS_FREEZE_PROT);
+	/* We gave our writer reference to the new transaction */
+	tp->t_flags &= ~XFS_TRANS_FREEZE_PROT;
 	ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
 	ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used;
 	tp->t_blk_res = tp->t_blk_res_used;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index f611870..e42d94e 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -179,6 +179,8 @@ struct xfs_log_item_desc {
 #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_FREEZE_PROT	0x40	/* Transaction has elevated writer
+					   count in superblock */
 
 /*
  * Values for call flags parameter.
-- 
1.7.1

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 18/27] xfs: Convert to new freezing code

[Jan Kara]

Generic code now blocks all writers from standard write paths. So we add
blocking of all writers coming from ioctl (we get a protection of ioctl against
racing remount read-only as a bonus) and convert xfs_file_aio_write() to a
non-racy freeze protection. We also keep freeze protection on transaction
start to block internal filesystem writes such as removal of preallocated
blocks.

CC: Ben Myers <bpm@sgi.com>
CC: Alex Elder <elder@kernel.org>
CC: xfs@oss.sgi.com
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/xfs/xfs_aops.c    |   18 ++++++++++++++++
 fs/xfs/xfs_file.c    |   10 ++++++--
 fs/xfs/xfs_ioctl.c   |   55 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/xfs/xfs_ioctl32.c |   12 ++++++++++
 fs/xfs/xfs_iomap.c   |    4 +-
 fs/xfs/xfs_mount.c   |    2 +-
 fs/xfs/xfs_mount.h   |    3 --
 fs/xfs/xfs_sync.c    |    2 +-
 fs/xfs/xfs_trans.c   |   17 ++++++++++++--
 fs/xfs/xfs_trans.h   |    2 +
 10 files changed, 109 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index ae31c31..4a001b8 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -124,6 +124,12 @@ xfs_setfilesize_trans_alloc(
 	ioend->io_append_trans = tp;
 
 	/*
+	 * We will pass freeze protection with a transaction.  So tell lockdep
+	 * we released it.
+	 */
+	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+		      1, _THIS_IP_);
+	/*
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
 	 */
@@ -199,6 +205,15 @@ xfs_end_io(
 	struct xfs_inode *ip = XFS_I(ioend->io_inode);
 	int		error = 0;
 
+	if (ioend->io_append_trans) {
+		/*
+		 * We've got freeze protection passed with the transaction.
+		 * Tell lockdep about it.
+		 */
+		rwsem_acquire_read(
+			&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+			0, 1, _THIS_IP_);
+	}
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		ioend->io_error = -EIO;
 		goto done;
@@ -1405,6 +1420,9 @@ out_trans_cancel:
 	if (ioend->io_append_trans) {
 		current_set_flags_nested(&ioend->io_append_trans->t_pflags,
 					 PF_FSTRANS);
+		rwsem_acquire_read(
+			&inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+			0, 1, _THIS_IP_);
 		xfs_trans_cancel(ioend->io_append_trans, 0);
 	}
 out_destroy_ioend:
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8d214b8..1e7bb9c 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -778,10 +778,12 @@ xfs_file_aio_write(
 	if (ocount == 0)
 		return 0;
 
-	xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+		ret = -EIO;
+		goto out;
+	}
 
 	if (unlikely(file->f_flags & O_DIRECT))
 		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
@@ -800,6 +802,8 @@ xfs_file_aio_write(
 			ret = err;
 	}
 
+out:
+	sb_end_write(inode->i_sb);
 	return ret;
 }
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 3a05a41..63624fb 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -361,9 +361,15 @@ xfs_fssetdm_by_handle(
 	if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
 
+	error = mnt_want_write_file(parfilp);
+	if (error)
+		return error;
+
 	dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq);
-	if (IS_ERR(dentry))
+	if (IS_ERR(dentry)) {
+		mnt_drop_write_file(parfilp);
 		return PTR_ERR(dentry);
+	}
 
 	if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) {
 		error = -XFS_ERROR(EPERM);
@@ -379,6 +385,7 @@ xfs_fssetdm_by_handle(
 				 fsd.fsd_dmstate);
 
  out:
+	mnt_drop_write_file(parfilp);
 	dput(dentry);
 	return error;
 }
@@ -631,7 +638,11 @@ xfs_ioc_space(
 	if (ioflags & IO_INVIS)
 		attr_flags |= XFS_ATTR_DMI;
 
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
 	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
+	mnt_drop_write_file(filp);
 	return -error;
 }
 
@@ -1160,6 +1171,7 @@ xfs_ioc_fssetxattr(
 {
 	struct fsxattr		fa;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&fa, arg, sizeof(fa)))
 		return -EFAULT;
@@ -1168,7 +1180,12 @@ xfs_ioc_fssetxattr(
 	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
 		mask |= FSX_NONBLOCK;
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1193,6 +1210,7 @@ xfs_ioc_setxflags(
 	struct fsxattr		fa;
 	unsigned int		flags;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
 		return -EFAULT;
@@ -1207,7 +1225,12 @@ xfs_ioc_setxflags(
 		mask |= FSX_NONBLOCK;
 	fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1382,8 +1405,13 @@ xfs_file_ioctl(
 		if (copy_from_user(&dmi, arg, sizeof(dmi)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
 				dmi.fsd_dmstate);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1431,7 +1459,11 @@ xfs_file_ioctl(
 
 		if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1460,9 +1492,14 @@ xfs_file_ioctl(
 		if (copy_from_user(&inout, arg, sizeof(inout)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		/* input parameter is passed in resblks field of structure */
 		in = inout.resblks;
 		error = xfs_reserve_blocks(mp, &in, &inout);
+		mnt_drop_write_file(filp);
 		if (error)
 			return -error;
 
@@ -1493,7 +1530,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1503,7 +1544,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_log(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1513,7 +1558,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c4f2da0..1244274 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -600,7 +600,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_data_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSGROWFSRT_32: {
@@ -608,7 +612,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_rt_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 #endif
@@ -627,7 +635,11 @@ xfs_file_compat_ioctl(
 				   offsetof(struct xfs_swapext, sx_stat)) ||
 		    xfs_ioctl32_bstat_copyin(&sxp.sx_stat, &sxu->sx_stat))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSBULKSTAT_32:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index aadfce6..b3b9b26 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -680,9 +680,9 @@ xfs_iomap_write_unwritten(
 		 * the same inode that we complete here and might deadlock
 		 * on the iolock.
 		 */
-		xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
+		sb_start_intwrite(mp->m_super);
 		tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS);
-		tp->t_flags |= XFS_TRANS_RESERVE;
+		tp->t_flags |= XFS_TRANS_RESERVE | XFS_TRANS_FREEZE_PROT;
 		error = xfs_trans_reserve(tp, resblks,
 				XFS_WRITE_LOG_RES(mp), 0,
 				XFS_TRANS_PERM_LOG_RES,
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 536021f..b09a4a7 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1544,7 +1544,7 @@ xfs_unmountfs(
 int
 xfs_fs_writable(xfs_mount_t *mp)
 {
-	return !(xfs_test_for_freeze(mp) || XFS_FORCED_SHUTDOWN(mp) ||
+	return !(mp->m_super->s_writers.frozen || XFS_FORCED_SHUTDOWN(mp) ||
 		(mp->m_flags & XFS_MOUNT_RDONLY));
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 8b89c5a..401ca2e 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -314,9 +314,6 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 #define SHUTDOWN_REMOTE_REQ	0x0010	/* shutdown came from remote cell */
 #define SHUTDOWN_DEVICE_REQ	0x0020	/* failed all paths to the device */
 
-#define xfs_test_for_freeze(mp)		((mp)->m_super->s_frozen)
-#define xfs_wait_for_freeze(mp,l)	vfs_check_frozen((mp)->m_super, (l))
-
 /*
  * Flags for xfs_mountfs
  */
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index c9d3409..9986c7a 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -392,7 +392,7 @@ xfs_sync_worker(
 	if (down_read_trylock(&mp->m_super->s_umount)) {
 		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
 			/* dgc: errors ignored here */
-			if (mp->m_super->s_frozen == SB_UNFROZEN &&
+			if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
 			    xfs_log_need_covered(mp))
 				error = xfs_fs_log_dummy(mp);
 			else
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index cdf896f..1639ac2 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -576,8 +576,12 @@ xfs_trans_alloc(
 	xfs_mount_t	*mp,
 	uint		type)
 {
-	xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
-	return _xfs_trans_alloc(mp, type, KM_SLEEP);
+	xfs_trans_t     *tp;
+
+	sb_start_intwrite(mp->m_super);
+	tp = _xfs_trans_alloc(mp, type, KM_SLEEP);
+	tp->t_flags |= XFS_TRANS_FREEZE_PROT;
+	return tp;
 }
 
 xfs_trans_t *
@@ -588,6 +592,7 @@ _xfs_trans_alloc(
 {
 	xfs_trans_t	*tp;
 
+	WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
 	atomic_inc(&mp->m_active_trans);
 
 	tp = kmem_zone_zalloc(xfs_trans_zone, memflags);
@@ -611,6 +616,8 @@ xfs_trans_free(
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	atomic_dec(&tp->t_mountp->m_active_trans);
+	if (tp->t_flags & XFS_TRANS_FREEZE_PROT)
+		sb_end_intwrite(tp->t_mountp->m_super);
 	xfs_trans_free_dqinfo(tp);
 	kmem_zone_free(xfs_trans_zone, tp);
 }
@@ -643,7 +650,11 @@ xfs_trans_dup(
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
 
-	ntp->t_flags = XFS_TRANS_PERM_LOG_RES | (tp->t_flags & XFS_TRANS_RESERVE);
+	ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
+		       (tp->t_flags & XFS_TRANS_RESERVE) |
+		       (tp->t_flags & XFS_TRANS_FREEZE_PROT);
+	/* We gave our writer reference to the new transaction */
+	tp->t_flags &= ~XFS_TRANS_FREEZE_PROT;
 	ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
 	ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used;
 	tp->t_blk_res = tp->t_blk_res_used;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 7ab99e1..a5d31d5 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -179,6 +179,8 @@ struct xfs_log_item_desc {
 #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_FREEZE_PROT	0x40	/* Transaction has elevated writer
+					   count in superblock */
 
 /*
  * Values for call flags parameter.
-- 
1.7.1

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 18/27] xfs: Convert to new freezing code

[Dave Chinner]

On Sat, Jun 02, 2012 at 12:30:32AM +0200, Jan Kara wrote:
> Generic code now blocks all writers from standard write paths. So we add
> blocking of all writers coming from ioctl (we get a protection of ioctl against
> racing remount read-only as a bonus) and convert xfs_file_aio_write() to a
> non-racy freeze protection. We also keep freeze protection on transaction
> start to block internal filesystem writes such as removal of preallocated
> blocks.

I don't think this will apply to a current TOT XFS - the end_io
context hunks look wrong. Perhaps your rebased this before the XFS
tree was merged?

> CC: Ben Myers <bpm@sgi.com>
> CC: Alex Elder <elder@kernel.org>
> CC: xfs@oss.sgi.com
> Signed-off-by: Jan Kara <jack@suse.cz>
> ---
>  fs/xfs/xfs_aops.c    |   18 ++++++++++++++++
>  fs/xfs/xfs_file.c    |   10 ++++++--
>  fs/xfs/xfs_ioctl.c   |   55 +++++++++++++++++++++++++++++++++++++++++++++++--
>  fs/xfs/xfs_ioctl32.c |   12 ++++++++++
>  fs/xfs/xfs_iomap.c   |    4 +-
>  fs/xfs/xfs_mount.c   |    2 +-
>  fs/xfs/xfs_mount.h   |    3 --
>  fs/xfs/xfs_sync.c    |    2 +-
>  fs/xfs/xfs_trans.c   |   17 ++++++++++++--
>  fs/xfs/xfs_trans.h   |    2 +
>  10 files changed, 109 insertions(+), 16 deletions(-)
> 
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index ae31c31..4a001b8 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -124,6 +124,12 @@ xfs_setfilesize_trans_alloc(
>  	ioend->io_append_trans = tp;
>  
>  	/*
> +	 * We will pass freeze protection with a transaction.  So tell lockdep
> +	 * we released it.
> +	 */
> +	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
> +		      1, _THIS_IP_);
> +	/*

Oh, that's rather ugly. If this is necessary where a transaction
handle is passed to another thread and completed there, then this
really needs to be wrapped in helper functions so it is always done
correctly when the PF_TRANS flag is also transferred. That can be
done later, though. It will also need to be done to the allocation
code which passes allocation off to a workqueue, but that is
currently synchronous so won't be a problem for this change right
now...


> @@ -631,7 +638,11 @@ xfs_ioc_space(
>  	if (ioflags & IO_INVIS)
>  		attr_flags |= XFS_ATTR_DMI;
>  
> +	error = mnt_want_write_file(filp);
> +	if (error)
> +		return error;
>  	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
> +	mnt_drop_write_file(filp);
>  	return -error;

Those positive/negative error conversions are starting to get
confusing and difficult to get right. I'm going to have to convert
XFS at some point to return negative errors everywhere so we can get
rid of that problem once and for all...

Otherwise, this looks OK. I'll need to pull this in and test it, but
the I was using the previous version of the patch series for almost
the entire 3.4-rc cycle and didn't come across any problems with
it....

Cheers,

Dave.
-- 
Dave Chinner
dchinner@redhat.com

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 18/27] xfs: Convert to new freezing code

[Jan Kara]

On Tue 05-06-12 14:15:46, Dave Chinner wrote:
> On Sat, Jun 02, 2012 at 12:30:32AM +0200, Jan Kara wrote:
> > Generic code now blocks all writers from standard write paths. So we add
> > blocking of all writers coming from ioctl (we get a protection of ioctl against
> > racing remount read-only as a bonus) and convert xfs_file_aio_write() to a
> > non-racy freeze protection. We also keep freeze protection on transaction
> > start to block internal filesystem writes such as removal of preallocated
> > blocks.
> 
> I don't think this will apply to a current TOT XFS - the end_io
> context hunks look wrong. Perhaps your rebased this before the XFS
> tree was merged?
  Umm, doesn't look like that. I've based my patches on top of
51eab603f5c86dd1eae4c525df3e7f7eeab401d6 which is after XFS merge. 

> > CC: Ben Myers <bpm@sgi.com>
> > CC: Alex Elder <elder@kernel.org>
> > CC: xfs@oss.sgi.com
> > Signed-off-by: Jan Kara <jack@suse.cz>
> > ---
> >  fs/xfs/xfs_aops.c    |   18 ++++++++++++++++
> >  fs/xfs/xfs_file.c    |   10 ++++++--
> >  fs/xfs/xfs_ioctl.c   |   55 +++++++++++++++++++++++++++++++++++++++++++++++--
> >  fs/xfs/xfs_ioctl32.c |   12 ++++++++++
> >  fs/xfs/xfs_iomap.c   |    4 +-
> >  fs/xfs/xfs_mount.c   |    2 +-
> >  fs/xfs/xfs_mount.h   |    3 --
> >  fs/xfs/xfs_sync.c    |    2 +-
> >  fs/xfs/xfs_trans.c   |   17 ++++++++++++--
> >  fs/xfs/xfs_trans.h   |    2 +
> >  10 files changed, 109 insertions(+), 16 deletions(-)
> > 
> > diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> > index ae31c31..4a001b8 100644
> > --- a/fs/xfs/xfs_aops.c
> > +++ b/fs/xfs/xfs_aops.c
> > @@ -124,6 +124,12 @@ xfs_setfilesize_trans_alloc(
> >  	ioend->io_append_trans = tp;
> >  
> >  	/*
> > +	 * We will pass freeze protection with a transaction.  So tell lockdep
> > +	 * we released it.
> > +	 */
> > +	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
> > +		      1, _THIS_IP_);
> > +	/*
> 
> Oh, that's rather ugly. If this is necessary where a transaction
> handle is passed to another thread and completed there, then this
> really needs to be wrapped in helper functions so it is always done
> correctly when the PF_TRANS flag is also transferred. That can be
> done later, though. It will also need to be done to the allocation
> code which passes allocation off to a workqueue, but that is
> currently synchronous so won't be a problem for this change right
> now...
  This lockdep magic is necessary because lockdep freaks out if you acquire
lock in one process and release it in another one. But wrapping that inside a
function is a good idea.

> > @@ -631,7 +638,11 @@ xfs_ioc_space(
> >  	if (ioflags & IO_INVIS)
> >  		attr_flags |= XFS_ATTR_DMI;
> >  
> > +	error = mnt_want_write_file(filp);
> > +	if (error)
> > +		return error;
> >  	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
> > +	mnt_drop_write_file(filp);
> >  	return -error;
> 
> Those positive/negative error conversions are starting to get
> confusing and difficult to get right. I'm going to have to convert
> XFS at some point to return negative errors everywhere so we can get
> rid of that problem once and for all...
  Yeah, it's a bit messy.

> Otherwise, this looks OK. I'll need to pull this in and test it, but
> the I was using the previous version of the patch series for almost
> the entire 3.4-rc cycle and didn't come across any problems with
> it....
  Thanks!

								Honza
-- 
Jan Kara <jack@suse.cz>
SUSE Labs, CR

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 00/27 v7] Fix filesystem freezing deadlocks

[Jan Kara]

  Hello,

  here is the seventh iteration of my patches to improve filesystem freezing.
I've rebased patches on top of 3.5-rc2 as Al requested. Otherwise I've just
fixed some outdated text in the introduction below and added one ack.

Introductory text to first time readers:

Filesystem freezing is currently racy and thus we can end up with dirty data on
frozen filesystem (see changelog patch 13 for detailed race description). This
patch series aims at fixing this.

To be able to block all places where inodes get dirtied, I've moved filesystem
file_update_time() call to ->page_mkwrite callback (patches 01-07) and put
freeze handling in mnt_want_write() / mnt_drop_write(). That however required
some code shuffling and changes to kern_path_create() (see patches 09-12). I
think the result is OK but opinions may differ ;). The advantage of this change
also is that all filesystems get freeze protection almost for free - even ext2
can handle freezing well now.

I'm not able to hit any deadlocks, lockdep warnings, or dirty data on frozen
filesystem despite beating it with fsstress, bash-shared-mapping, and
aio-stress while freezing and unfreezing for several hours (using ext4 and xfs)
so I'm reasonably confident this could finally be the right solution.

Changes since v6:
  * rebased on 3.5-rc2
  * added ack

Changes since v5:
  * handle unlinked & open files on frozen filesystem
  * lockdep keys for freeze protection are now per filesystem type
  * taught lockdep that freeze protection at lower level does not create
    dependency when we already hold freeze protection at higher level 
  * rebased on 3.5-rc1-ish

Changes since v4:
  * added a couple of Acked-by's
  * added some comments & doc update
  * added patches from series "Push file_update_time() into .page_mkwrite"
    since it doesn't make much sense to keep them separate anymore
  * rebased on top of 3.4-rc2

Changes since v3:
  * added third level of freezing for fs internal purposes - hooked some
    filesystems to use it (XFS, nilfs2)
  * removed racy i_size check from filemap_mkwrite()

Changes since v2:
  * completely rewritten
  * freezing is now blocked at VFS entry points
  * two stage freezing to handle both mmapped writes and other IO

The biggest changes since v1:
  * have two counters to provide safe state transitions for SB_FREEZE_WRITE
    and SB_FREEZE_TRANS states
  * use percpu counters instead of own percpu structure
  * added documentation fixes from the old fs freezing series
  * converted XFS to use SB_FREEZE_TRANS counter instead of its private
    m_active_trans counter

								Honza

CC: Alex Elder <elder@kernel.org>
CC: Anton Altaparmakov <anton@tuxera.com>
CC: Ben Myers <bpm@sgi.com>
CC: Chris Mason <chris.mason@oracle.com>
CC: cluster-devel@redhat.com
CC: "David S. Miller" <davem@davemloft.net>
CC: fuse-devel@lists.sourceforge.net
CC: "J. Bruce Fields" <bfields@fieldses.org>
CC: Joel Becker <jlbec@evilplan.org>
CC: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp>
CC: linux-btrfs@vger.kernel.org
CC: linux-ext4@vger.kernel.org
CC: linux-nfs@vger.kernel.org
CC: linux-nilfs@vger.kernel.org
CC: linux-ntfs-dev@lists.sourceforge.net
CC: Mark Fasheh <mfasheh@suse.com>
CC: Miklos Szeredi <miklos@szeredi.hu>
CC: ocfs2-devel@oss.oracle.com
CC: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
CC: Steven Whitehouse <swhiteho@redhat.com>
CC: "Theodore Ts'o" <tytso@mit.edu>
CC: xfs@oss.sgi.com

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 18/27] xfs: Convert to new freezing code

[Jan Kara]

Generic code now blocks all writers from standard write paths. So we add
blocking of all writers coming from ioctl (we get a protection of ioctl against
racing remount read-only as a bonus) and convert xfs_file_aio_write() to a
non-racy freeze protection. We also keep freeze protection on transaction
start to block internal filesystem writes such as removal of preallocated
blocks.

CC: Ben Myers <bpm@sgi.com>
CC: Alex Elder <elder@kernel.org>
CC: xfs@oss.sgi.com
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/xfs/xfs_aops.c    |   18 ++++++++++++++++
 fs/xfs/xfs_file.c    |   10 ++++++--
 fs/xfs/xfs_ioctl.c   |   55 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/xfs/xfs_ioctl32.c |   12 ++++++++++
 fs/xfs/xfs_iomap.c   |    4 +-
 fs/xfs/xfs_mount.c   |    2 +-
 fs/xfs/xfs_mount.h   |    3 --
 fs/xfs/xfs_sync.c    |    2 +-
 fs/xfs/xfs_trans.c   |   17 ++++++++++++--
 fs/xfs/xfs_trans.h   |    2 +
 10 files changed, 109 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index ae31c31..4a001b8 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -124,6 +124,12 @@ xfs_setfilesize_trans_alloc(
 	ioend->io_append_trans = tp;
 
 	/*
+	 * We will pass freeze protection with a transaction.  So tell lockdep
+	 * we released it.
+	 */
+	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+		      1, _THIS_IP_);
+	/*
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
 	 */
@@ -199,6 +205,15 @@ xfs_end_io(
 	struct xfs_inode *ip = XFS_I(ioend->io_inode);
 	int		error = 0;
 
+	if (ioend->io_append_trans) {
+		/*
+		 * We've got freeze protection passed with the transaction.
+		 * Tell lockdep about it.
+		 */
+		rwsem_acquire_read(
+			&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+			0, 1, _THIS_IP_);
+	}
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		ioend->io_error = -EIO;
 		goto done;
@@ -1405,6 +1420,9 @@ out_trans_cancel:
 	if (ioend->io_append_trans) {
 		current_set_flags_nested(&ioend->io_append_trans->t_pflags,
 					 PF_FSTRANS);
+		rwsem_acquire_read(
+			&inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+			0, 1, _THIS_IP_);
 		xfs_trans_cancel(ioend->io_append_trans, 0);
 	}
 out_destroy_ioend:
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 9f7ec15..f0081f2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -781,10 +781,12 @@ xfs_file_aio_write(
 	if (ocount == 0)
 		return 0;
 
-	xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+		ret = -EIO;
+		goto out;
+	}
 
 	if (unlikely(file->f_flags & O_DIRECT))
 		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
@@ -803,6 +805,8 @@ xfs_file_aio_write(
 			ret = err;
 	}
 
+out:
+	sb_end_write(inode->i_sb);
 	return ret;
 }
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 3a05a41..63624fb 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -361,9 +361,15 @@ xfs_fssetdm_by_handle(
 	if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
 
+	error = mnt_want_write_file(parfilp);
+	if (error)
+		return error;
+
 	dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq);
-	if (IS_ERR(dentry))
+	if (IS_ERR(dentry)) {
+		mnt_drop_write_file(parfilp);
 		return PTR_ERR(dentry);
+	}
 
 	if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) {
 		error = -XFS_ERROR(EPERM);
@@ -379,6 +385,7 @@ xfs_fssetdm_by_handle(
 				 fsd.fsd_dmstate);
 
  out:
+	mnt_drop_write_file(parfilp);
 	dput(dentry);
 	return error;
 }
@@ -631,7 +638,11 @@ xfs_ioc_space(
 	if (ioflags & IO_INVIS)
 		attr_flags |= XFS_ATTR_DMI;
 
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
 	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
+	mnt_drop_write_file(filp);
 	return -error;
 }
 
@@ -1160,6 +1171,7 @@ xfs_ioc_fssetxattr(
 {
 	struct fsxattr		fa;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&fa, arg, sizeof(fa)))
 		return -EFAULT;
@@ -1168,7 +1180,12 @@ xfs_ioc_fssetxattr(
 	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
 		mask |= FSX_NONBLOCK;
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1193,6 +1210,7 @@ xfs_ioc_setxflags(
 	struct fsxattr		fa;
 	unsigned int		flags;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
 		return -EFAULT;
@@ -1207,7 +1225,12 @@ xfs_ioc_setxflags(
 		mask |= FSX_NONBLOCK;
 	fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1382,8 +1405,13 @@ xfs_file_ioctl(
 		if (copy_from_user(&dmi, arg, sizeof(dmi)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
 				dmi.fsd_dmstate);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1431,7 +1459,11 @@ xfs_file_ioctl(
 
 		if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1460,9 +1492,14 @@ xfs_file_ioctl(
 		if (copy_from_user(&inout, arg, sizeof(inout)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		/* input parameter is passed in resblks field of structure */
 		in = inout.resblks;
 		error = xfs_reserve_blocks(mp, &in, &inout);
+		mnt_drop_write_file(filp);
 		if (error)
 			return -error;
 
@@ -1493,7 +1530,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1503,7 +1544,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_log(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1513,7 +1558,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c4f2da0..1244274 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -600,7 +600,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_data_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSGROWFSRT_32: {
@@ -608,7 +612,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_rt_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 #endif
@@ -627,7 +635,11 @@ xfs_file_compat_ioctl(
 				   offsetof(struct xfs_swapext, sx_stat)) ||
 		    xfs_ioctl32_bstat_copyin(&sxp.sx_stat, &sxu->sx_stat))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSBULKSTAT_32:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index aadfce6..b3b9b26 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -680,9 +680,9 @@ xfs_iomap_write_unwritten(
 		 * the same inode that we complete here and might deadlock
 		 * on the iolock.
 		 */
-		xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
+		sb_start_intwrite(mp->m_super);
 		tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS);
-		tp->t_flags |= XFS_TRANS_RESERVE;
+		tp->t_flags |= XFS_TRANS_RESERVE | XFS_TRANS_FREEZE_PROT;
 		error = xfs_trans_reserve(tp, resblks,
 				XFS_WRITE_LOG_RES(mp), 0,
 				XFS_TRANS_PERM_LOG_RES,
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 536021f..b09a4a7 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1544,7 +1544,7 @@ xfs_unmountfs(
 int
 xfs_fs_writable(xfs_mount_t *mp)
 {
-	return !(xfs_test_for_freeze(mp) || XFS_FORCED_SHUTDOWN(mp) ||
+	return !(mp->m_super->s_writers.frozen || XFS_FORCED_SHUTDOWN(mp) ||
 		(mp->m_flags & XFS_MOUNT_RDONLY));
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 8b89c5a..401ca2e 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -314,9 +314,6 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 #define SHUTDOWN_REMOTE_REQ	0x0010	/* shutdown came from remote cell */
 #define SHUTDOWN_DEVICE_REQ	0x0020	/* failed all paths to the device */
 
-#define xfs_test_for_freeze(mp)		((mp)->m_super->s_frozen)
-#define xfs_wait_for_freeze(mp,l)	vfs_check_frozen((mp)->m_super, (l))
-
 /*
  * Flags for xfs_mountfs
  */
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index c9d3409..9986c7a 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -392,7 +392,7 @@ xfs_sync_worker(
 	if (down_read_trylock(&mp->m_super->s_umount)) {
 		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
 			/* dgc: errors ignored here */
-			if (mp->m_super->s_frozen == SB_UNFROZEN &&
+			if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
 			    xfs_log_need_covered(mp))
 				error = xfs_fs_log_dummy(mp);
 			else
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index fdf3245..06ed520 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -576,8 +576,12 @@ xfs_trans_alloc(
 	xfs_mount_t	*mp,
 	uint		type)
 {
-	xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
-	return _xfs_trans_alloc(mp, type, KM_SLEEP);
+	xfs_trans_t     *tp;
+
+	sb_start_intwrite(mp->m_super);
+	tp = _xfs_trans_alloc(mp, type, KM_SLEEP);
+	tp->t_flags |= XFS_TRANS_FREEZE_PROT;
+	return tp;
 }
 
 xfs_trans_t *
@@ -588,6 +592,7 @@ _xfs_trans_alloc(
 {
 	xfs_trans_t	*tp;
 
+	WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
 	atomic_inc(&mp->m_active_trans);
 
 	tp = kmem_zone_zalloc(xfs_trans_zone, memflags);
@@ -611,6 +616,8 @@ xfs_trans_free(
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	atomic_dec(&tp->t_mountp->m_active_trans);
+	if (tp->t_flags & XFS_TRANS_FREEZE_PROT)
+		sb_end_intwrite(tp->t_mountp->m_super);
 	xfs_trans_free_dqinfo(tp);
 	kmem_zone_free(xfs_trans_zone, tp);
 }
@@ -643,7 +650,11 @@ xfs_trans_dup(
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
 
-	ntp->t_flags = XFS_TRANS_PERM_LOG_RES | (tp->t_flags & XFS_TRANS_RESERVE);
+	ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
+		       (tp->t_flags & XFS_TRANS_RESERVE) |
+		       (tp->t_flags & XFS_TRANS_FREEZE_PROT);
+	/* We gave our writer reference to the new transaction */
+	tp->t_flags &= ~XFS_TRANS_FREEZE_PROT;
 	ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
 	ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used;
 	tp->t_blk_res = tp->t_blk_res_used;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 7c37b53..19c1742 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -179,6 +179,8 @@ struct xfs_log_item_desc {
 #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_FREEZE_PROT	0x40	/* Transaction has elevated writer
+					   count in superblock */
 
 /*
  * Values for call flags parameter.
-- 
1.7.1

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 18/27] xfs: Convert to new freezing code

[Christoph Hellwig]

> +	 * We will pass freeze protection with a transaction.  So tell lockdep
> +	 * we released it.
> +	 */
> +	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
> +		      1, _THIS_IP_);

I'll need some time to get through the whole series, but repeated use
of constructs like this really screams for a helper abstracting it out
and documenting it.

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

Re: [PATCH 18/27] xfs: Convert to new freezing code

[Jan Kara]

On Tue 12-06-12 10:23:47, Christoph Hellwig wrote:
> > +	 * We will pass freeze protection with a transaction.  So tell lockdep
> > +	 * we released it.
> > +	 */
> > +	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
> > +		      1, _THIS_IP_);
> 
> I'll need some time to get through the whole series, but repeated use
> of constructs like this really screams for a helper abstracting it out
> and documenting it.
  It's there twice and only in XFS because XFS needs to pass the freeze
protection (along with a transaction) to a worker thread. I'm not against a
helper but then it should probably be in a form to allow easy
instrumentation of lockdep that we are passing a state of lock together
with a work struct?

								Honza
-- 
Jan Kara <jack@suse.cz>
SUSE Labs, CR

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs