[PATCH 18/27] xfs: Convert to new freezing code
From: Jan Kara
Date: Tue Jun 12 2012 - 10:25:10 EST
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@xxxxxxx>
CC: Alex Elder <elder@xxxxxxxxxx>
CC: xfs@xxxxxxxxxxx
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
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
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/