Junxiao Bi
2013-Jul-10 01:03 UTC
[Ocfs2-devel] [PATCH] ocfs2: update inode size after zeroed the hole
fs-writeback will release the dirty pages without page lock
whose offset are over inode size, the release happens at
block_write_full_page_endio(). If not update, dirty pages
in file holes may be released before flushed to the disk,
then file holes will contain some non-zero data, this will
cause sparse file cksum error.
Signed-off-by: Junxiao Bi <junxiao.bi at oracle.com>
---
fs/ocfs2/file.c | 25 ++++++++++++++++++++-----
1 file changed, 20 insertions(+), 5 deletions(-)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index ff54014..d1264ef 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -756,7 +756,7 @@ out:
* to be too fragile to do exactly what we need without us having to
* worry about recursive locking in ->write_begin() and ->write_end(). */
static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
- u64 abs_to)
+ u64 abs_to, struct buffer_head *di_bh)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
@@ -764,6 +764,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64
abs_from,
handle_t *handle = NULL;
int ret = 0;
unsigned zero_from, zero_to, block_start, block_end;
+ struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
BUG_ON(abs_from >= abs_to);
BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
@@ -823,8 +824,22 @@ static int ocfs2_write_zero_page(struct inode *inode, u64
abs_from,
ret = 0;
}
- if (handle)
+ if (handle) {
+ /*
+ * fs-writeback will release the dirty pages without page lock
+ * whose offset are over inode size, the release happens at
+ * block_write_full_page_endio().
+ */
+ i_size_write(inode, abs_to);
+ inode->i_blocks = ocfs2_inode_sector_count(inode);
+ di->i_size = cpu_to_le64((u64)i_size_read(inode));
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+ di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+ di->i_mtime_nsec = di->i_ctime_nsec;
+ ocfs2_journal_dirty(handle, di_bh);
ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+ }
out_unlock:
unlock_page(page);
@@ -920,7 +935,7 @@ out:
* has made sure that the entire range needs zeroing.
*/
static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
- u64 range_end)
+ u64 range_end, struct buffer_head *di_bh)
{
int rc = 0;
u64 next_pos;
@@ -936,7 +951,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64
range_start,
next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
if (next_pos > range_end)
next_pos = range_end;
- rc = ocfs2_write_zero_page(inode, zero_pos, next_pos);
+ rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
if (rc < 0) {
mlog_errno(rc);
break;
@@ -982,7 +997,7 @@ int ocfs2_zero_extend(struct inode *inode, struct
buffer_head *di_bh,
range_end = zero_to_size;
ret = ocfs2_zero_extend_range(inode, range_start,
- range_end);
+ range_end, di_bh);
if (ret) {
mlog_errno(ret);
break;
--
1.7.9.5
Junxiao Bi
2013-Jul-10 06:47 UTC
[Ocfs2-devel] [PATCH] ocfs2: update inode size after zeroed the hole
Sometimes, this patch will cause a call trace, see following, this code snippet is referenced from ocfs2_write_end(), I am not familiar with jbd, anybody know why? JBD: sda7-523: jh->b_next_transaction (58645, (null), 0) !transaction (ffff88014fa75ec0, 59276) ------------[ cut here ]------------ WARNING: at fs/jbd2/transaction.c:1237 jbd2_journal_dirty_metadata+0xf6/0x250() Modules linked in: ebtable_nat ebtables nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT iptable_filter ip_tables bridge stp llc autofs4 hidp rfcomm bluetooth rfkill lockd sunrpc cpufreq_ondemand ip6t_REJECT ip6table_filter ip6_tables be2iscsi iscsi_boot_sysfs ib_iser rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr iscsi_tcp bnx2i cnic uio ipv6 cxgb3i libcxgbi cxgb3 mdio libiscsi_tcp libiscsi scsi_transport_iscsi sbs sbshc hed acpi_pad acpi_ipmi ipmi_msghandler parport_pc lp parport i915 snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_seq_dummy snd_seq_oss drm_kms_helper snd_seq_midi_event drm snd_seq sg snd_seq_device snd_pcm_oss snd_mixer_oss e1000e iTCO_wdt snd_pcm iTCO_vendor_support i2c_algo_bit sr_mod cdrom snd_timer snd i2c_i801 ptp dcdbas soundcore pcspkr lpc_ich pps_core acpi_cpufreq serio_raw i2c_core video snd_page_alloc mfd_core freq_table mperf dm_snapshot(F) dm_zero(F) dm_mirror(F) dm_region_hash(F) dm_log(F) dm_mod(F) shpchp(F) ahci(F) libahci(F) sd_mod(F) crc_t10dif(F) ext3(F) jbd(F) mbcache(F) CPU: 2 PID: 6940 Comm: tar Tainted: PF 3.10.0-rc6 #2 Hardware name: Dell Inc. OptiPlex 790/0PG55N, BIOS A11 12/30/2011 ffffffff8184f02f ffff880214c29808 ffffffff8132e369 ffff880214c29848 ffffffff81041e10 0000000000001000 ffff88014f8ff600 00000000ffffffea ffff88014fa75ec0 ffff88021e275000 ffff88020a0b4338 ffff880214c29858 Call Trace: [<ffffffff8132e369>] dump_stack+0x19/0x20 [<ffffffff81041e10>] warn_slowpath_common+0x70/0xa0 [<ffffffff81041e5a>] warn_slowpath_null+0x1a/0x20 [<ffffffff811e0eb6>] jbd2_journal_dirty_metadata+0xf6/0x250 [<ffffffff812304ef>] ocfs2_journal_dirty+0x2f/0x70 [<ffffffff81224571>] ocfs2_write_zero_page+0x301/0x3e0 [<ffffffff812246e8>] ocfs2_zero_extend_range+0x98/0x160 [<ffffffff81224872>] ocfs2_zero_extend+0xc2/0x220 [<ffffffff812049cc>] ocfs2_zero_tail+0x2c/0x40 [<ffffffff81207fbb>] ocfs2_write_begin_nolock+0xfb/0xc80 [<ffffffff81229220>] ? ocfs2_read_inode_block+0x10/0x20 [<ffffffff81217d8a>] ? ocfs2_assign_bh+0x2a/0xb0 [<ffffffff8121c5a9>] ? ocfs2_inode_lock_full_nested+0xa9/0x470 [<ffffffff81208c76>] ocfs2_write_begin+0x136/0x200 [<ffffffff8110c444>] generic_perform_write+0xd4/0x1e0 [<ffffffff8110c5b5>] generic_file_buffered_write+0x65/0xa0 [<ffffffff812266b1>] ocfs2_file_aio_write+0x691/0x7b0 [<ffffffff81163ea7>] do_sync_write+0x97/0xe0 [<ffffffff811647a5>] vfs_write+0xe5/0x1e0 [<ffffffff81164ae1>] SyS_write+0x61/0xa0 [<ffffffff81604cc2>] system_call_fastpath+0x16/0x1b ---[ end trace edb3aa856f6f3cde ]--- On 07/10/2013 09:03 AM, Junxiao Bi wrote:> fs-writeback will release the dirty pages without page lock > whose offset are over inode size, the release happens at > block_write_full_page_endio(). If not update, dirty pages > in file holes may be released before flushed to the disk, > then file holes will contain some non-zero data, this will > cause sparse file cksum error. > > Signed-off-by: Junxiao Bi <junxiao.bi at oracle.com> > --- > fs/ocfs2/file.c | 25 ++++++++++++++++++++----- > 1 file changed, 20 insertions(+), 5 deletions(-) > > diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c > index ff54014..d1264ef 100644 > --- a/fs/ocfs2/file.c > +++ b/fs/ocfs2/file.c > @@ -756,7 +756,7 @@ out: > * to be too fragile to do exactly what we need without us having to > * worry about recursive locking in ->write_begin() and ->write_end(). */ > static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, > - u64 abs_to) > + u64 abs_to, struct buffer_head *di_bh) > { > struct address_space *mapping = inode->i_mapping; > struct page *page; > @@ -764,6 +764,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, > handle_t *handle = NULL; > int ret = 0; > unsigned zero_from, zero_to, block_start, block_end; > + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; > > BUG_ON(abs_from >= abs_to); > BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT)); > @@ -823,8 +824,22 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, > ret = 0; > } > > - if (handle) > + if (handle) { > + /* > + * fs-writeback will release the dirty pages without page lock > + * whose offset are over inode size, the release happens at > + * block_write_full_page_endio(). > + */ > + i_size_write(inode, abs_to); > + inode->i_blocks = ocfs2_inode_sector_count(inode); > + di->i_size = cpu_to_le64((u64)i_size_read(inode)); > + inode->i_mtime = inode->i_ctime = CURRENT_TIME; > + di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); > + di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); > + di->i_mtime_nsec = di->i_ctime_nsec; > + ocfs2_journal_dirty(handle, di_bh); > ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); > + } > > out_unlock: > unlock_page(page); > @@ -920,7 +935,7 @@ out: > * has made sure that the entire range needs zeroing. > */ > static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, > - u64 range_end) > + u64 range_end, struct buffer_head *di_bh) > { > int rc = 0; > u64 next_pos; > @@ -936,7 +951,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, > next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE; > if (next_pos > range_end) > next_pos = range_end; > - rc = ocfs2_write_zero_page(inode, zero_pos, next_pos); > + rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh); > if (rc < 0) { > mlog_errno(rc); > break; > @@ -982,7 +997,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, > range_end = zero_to_size; > > ret = ocfs2_zero_extend_range(inode, range_start, > - range_end); > + range_end, di_bh); > if (ret) { > mlog_errno(ret); > break;