| Message ID | 20180416020227.18528-1-wqu@suse.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 04/16/2018 10:02 AM, Qu Wenruo wrote: > There are already 2 reports about strangely corrupted super blocks, > where csum type and incompat flags get some obvious garbage, but csum > still matches and all other vitals are correct. > > This normally means some kernel memory corruption happens, although the > cause is unknown, at least detect it and prevent further corruption. > > Signed-off-by: Qu Wenruo <wqu@suse.com> > --- Can you help point those 2 cases here? Thanks, Anand > fs/btrfs/disk-io.c | 24 ++++++++++++++++++++---- > 1 file changed, 20 insertions(+), 4 deletions(-) > > diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c > index 23803102aa0d..10d814f03f13 100644 > --- a/fs/btrfs/disk-io.c > +++ b/fs/btrfs/disk-io.c > @@ -68,7 +68,8 @@ > static const struct extent_io_ops btree_extent_io_ops; > static void end_workqueue_fn(struct btrfs_work *work); > static void free_fs_root(struct btrfs_root *root); > -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info); > +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, > + struct btrfs_super_block *sb); > static void btrfs_destroy_ordered_extents(struct btrfs_root *root); > static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, > struct btrfs_fs_info *fs_info); > @@ -2680,7 +2681,7 @@ int open_ctree(struct super_block *sb, > > memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE); > > - ret = btrfs_check_super_valid(fs_info); > + ret = btrfs_check_super_valid(fs_info, fs_info->super_copy); > if (ret) { > btrfs_err(fs_info, "superblock contains fatal errors"); > err = -EINVAL; > @@ -3575,6 +3576,21 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) > sb = fs_info->super_for_commit; > dev_item = &sb->dev_item; > > + /* Do extra check on the sb to be written */ > + ret = btrfs_check_super_valid(fs_info, sb); > + if (ret) { > + btrfs_err(fs_info, "fatal superblock corrupted detected"); > + return -EUCLEAN; > + } > + /* > + * Unknown incompat flags can't be mounted, so newly developed flags > + * means corruption > + */ > + if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) { > + btrfs_err(fs_info, "fatal superblock corrupted detected"); > + return -EUCLEAN; > + } > + > mutex_lock(&fs_info->fs_devices->device_list_mutex); > head = &fs_info->fs_devices->devices; > max_errors = btrfs_super_num_devices(fs_info->super_copy) - 1; > @@ -3985,9 +4001,9 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, > level, first_key); > } > > -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) > +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, > + struct btrfs_super_block *sb) > { > - struct btrfs_super_block *sb = fs_info->super_copy; > u64 nodesize = btrfs_super_nodesize(sb); > u64 sectorsize = btrfs_super_sectorsize(sb); > int ret = 0; > -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 2018年04月16日 20:55, Anand Jain wrote: > > > On 04/16/2018 10:02 AM, Qu Wenruo wrote: >> There are already 2 reports about strangely corrupted super blocks, >> where csum type and incompat flags get some obvious garbage, but csum >> still matches and all other vitals are correct. >> >> This normally means some kernel memory corruption happens, although the >> cause is unknown, at least detect it and prevent further corruption. >> >> Signed-off-by: Qu Wenruo <wqu@suse.com> >> --- > > Can you help point those 2 cases here? Did you mean the reported-by tags? If so, no problem. Thanks, Qu > > Thanks, Anand > > >> fs/btrfs/disk-io.c | 24 ++++++++++++++++++++---- >> 1 file changed, 20 insertions(+), 4 deletions(-) >> >> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c >> index 23803102aa0d..10d814f03f13 100644 >> --- a/fs/btrfs/disk-io.c >> +++ b/fs/btrfs/disk-io.c >> @@ -68,7 +68,8 @@ >> static const struct extent_io_ops btree_extent_io_ops; >> static void end_workqueue_fn(struct btrfs_work *work); >> static void free_fs_root(struct btrfs_root *root); >> -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info); >> +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, >> + struct btrfs_super_block *sb); >> static void btrfs_destroy_ordered_extents(struct btrfs_root *root); >> static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, >> struct btrfs_fs_info *fs_info); >> @@ -2680,7 +2681,7 @@ int open_ctree(struct super_block *sb, >> memcpy(fs_info->fsid, fs_info->super_copy->fsid, >> BTRFS_FSID_SIZE); >> - ret = btrfs_check_super_valid(fs_info); >> + ret = btrfs_check_super_valid(fs_info, fs_info->super_copy); >> if (ret) { >> btrfs_err(fs_info, "superblock contains fatal errors"); >> err = -EINVAL; >> @@ -3575,6 +3576,21 @@ int write_all_supers(struct btrfs_fs_info >> *fs_info, int max_mirrors) >> sb = fs_info->super_for_commit; >> dev_item = &sb->dev_item; >> + /* Do extra check on the sb to be written */ >> + ret = btrfs_check_super_valid(fs_info, sb); >> + if (ret) { >> + btrfs_err(fs_info, "fatal superblock corrupted detected"); >> + return -EUCLEAN; >> + } >> + /* >> + * Unknown incompat flags can't be mounted, so newly developed flags >> + * means corruption >> + */ >> + if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) { >> + btrfs_err(fs_info, "fatal superblock corrupted detected"); >> + return -EUCLEAN; >> + } >> + >> mutex_lock(&fs_info->fs_devices->device_list_mutex); >> head = &fs_info->fs_devices->devices; >> max_errors = btrfs_super_num_devices(fs_info->super_copy) - 1; >> @@ -3985,9 +4001,9 @@ int btrfs_read_buffer(struct extent_buffer *buf, >> u64 parent_transid, int level, >> level, first_key); >> } >> -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) >> +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, >> + struct btrfs_super_block *sb) >> { >> - struct btrfs_super_block *sb = fs_info->super_copy; >> u64 nodesize = btrfs_super_nodesize(sb); >> u64 sectorsize = btrfs_super_sectorsize(sb); >> int ret = 0; >> > -- > To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Apr 16, 2018 at 10:02:27AM +0800, Qu Wenruo wrote: > There are already 2 reports about strangely corrupted super blocks, > where csum type and incompat flags get some obvious garbage, but csum > still matches and all other vitals are correct. > > This normally means some kernel memory corruption happens, although the > cause is unknown, at least detect it and prevent further corruption. > > Signed-off-by: Qu Wenruo <wqu@suse.com> > --- > fs/btrfs/disk-io.c | 24 ++++++++++++++++++++---- > 1 file changed, 20 insertions(+), 4 deletions(-) > > diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c > index 23803102aa0d..10d814f03f13 100644 > --- a/fs/btrfs/disk-io.c > +++ b/fs/btrfs/disk-io.c > @@ -68,7 +68,8 @@ > static const struct extent_io_ops btree_extent_io_ops; > static void end_workqueue_fn(struct btrfs_work *work); > static void free_fs_root(struct btrfs_root *root); > -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info); > +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, > + struct btrfs_super_block *sb); > static void btrfs_destroy_ordered_extents(struct btrfs_root *root); > static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, > struct btrfs_fs_info *fs_info); > @@ -2680,7 +2681,7 @@ int open_ctree(struct super_block *sb, > > memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE); > > - ret = btrfs_check_super_valid(fs_info); > + ret = btrfs_check_super_valid(fs_info, fs_info->super_copy); > if (ret) { > btrfs_err(fs_info, "superblock contains fatal errors"); > err = -EINVAL; > @@ -3575,6 +3576,21 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) > sb = fs_info->super_for_commit; > dev_item = &sb->dev_item; > > + /* Do extra check on the sb to be written */ > + ret = btrfs_check_super_valid(fs_info, sb); > + if (ret) { > + btrfs_err(fs_info, "fatal superblock corrupted detected"); > + return -EUCLEAN; > + } > + /* > + * Unknown incompat flags can't be mounted, so newly developed flags > + * means corruption > + */ > + if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) { > + btrfs_err(fs_info, "fatal superblock corrupted detected"); The error messages could state that the corruption is detected at the pre-commit time. Otherwise it's a good idea to do the checks, they're lighweight. > + return -EUCLEAN; > + } > + > mutex_lock(&fs_info->fs_devices->device_list_mutex); > head = &fs_info->fs_devices->devices; > max_errors = btrfs_super_num_devices(fs_info->super_copy) - 1; > @@ -3985,9 +4001,9 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, > level, first_key); > } > > -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) > +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, > + struct btrfs_super_block *sb) > { > - struct btrfs_super_block *sb = fs_info->super_copy; > u64 nodesize = btrfs_super_nodesize(sb); > u64 sectorsize = btrfs_super_sectorsize(sb); > int ret = 0; > -- > 2.17.0 > > -- > To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Apr 16, 2018 at 09:00:38PM +0800, Qu Wenruo wrote: > > > On 2018年04月16日 20:55, Anand Jain wrote: > > > > > > On 04/16/2018 10:02 AM, Qu Wenruo wrote: > >> There are already 2 reports about strangely corrupted super blocks, > >> where csum type and incompat flags get some obvious garbage, but csum > >> still matches and all other vitals are correct. > >> > >> This normally means some kernel memory corruption happens, although the > >> cause is unknown, at least detect it and prevent further corruption. > >> > >> Signed-off-by: Qu Wenruo <wqu@suse.com> > >> --- > > > > Can you help point those 2 cases here? > > Did you mean the reported-by tags? > If so, no problem. Yes please, also describe what got corrupted in the changelog, besides the links to the bugreports. -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 23803102aa0d..10d814f03f13 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -68,7 +68,8 @@ static const struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); static void free_fs_root(struct btrfs_root *root); -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info); +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, + struct btrfs_super_block *sb); static void btrfs_destroy_ordered_extents(struct btrfs_root *root); static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info); @@ -2680,7 +2681,7 @@ int open_ctree(struct super_block *sb, memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE); - ret = btrfs_check_super_valid(fs_info); + ret = btrfs_check_super_valid(fs_info, fs_info->super_copy); if (ret) { btrfs_err(fs_info, "superblock contains fatal errors"); err = -EINVAL; @@ -3575,6 +3576,21 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) sb = fs_info->super_for_commit; dev_item = &sb->dev_item; + /* Do extra check on the sb to be written */ + ret = btrfs_check_super_valid(fs_info, sb); + if (ret) { + btrfs_err(fs_info, "fatal superblock corrupted detected"); + return -EUCLEAN; + } + /* + * Unknown incompat flags can't be mounted, so newly developed flags + * means corruption + */ + if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) { + btrfs_err(fs_info, "fatal superblock corrupted detected"); + return -EUCLEAN; + } + mutex_lock(&fs_info->fs_devices->device_list_mutex); head = &fs_info->fs_devices->devices; max_errors = btrfs_super_num_devices(fs_info->super_copy) - 1; @@ -3985,9 +4001,9 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, level, first_key); } -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, + struct btrfs_super_block *sb) { - struct btrfs_super_block *sb = fs_info->super_copy; u64 nodesize = btrfs_super_nodesize(sb); u64 sectorsize = btrfs_super_sectorsize(sb); int ret = 0;
There are already 2 reports about strangely corrupted super blocks, where csum type and incompat flags get some obvious garbage, but csum still matches and all other vitals are correct. This normally means some kernel memory corruption happens, although the cause is unknown, at least detect it and prevent further corruption. Signed-off-by: Qu Wenruo <wqu@suse.com> --- fs/btrfs/disk-io.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-)