| Message ID | 59EF3614.6050008@huawei.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 17/10/24 20:46, alex chen wrote: > The ip_alloc_sem should be taken in ocfs2_get_block() when reading file > in DIRECT mode to prevent concurrent access to extent tree with > ocfs2_dio_end_io_write(), which may cause BUGON in the following situation: > > read file 'A' end_io of writing file 'A' > vfs_read > __vfs_read > ocfs2_file_read_iter > generic_file_read_iter > ocfs2_direct_IO > __blockdev_direct_IO > do_blockdev_direct_IO > do_direct_IO > get_more_blocks > ocfs2_get_block > ocfs2_extent_map_get_blocks > ocfs2_get_clusters > ocfs2_get_clusters_nocache() > ocfs2_search_extent_list > return the index of record which > contains the v_cluster, that is > v_cluster > rec[i]->e_cpos. > ocfs2_dio_end_io > ocfs2_dio_end_io_write > down_write(&oi->ip_alloc_sem); > ocfs2_mark_extent_written > ocfs2_change_extent_flag > ocfs2_split_extent > ... > --> modify the rec[i]->e_cpos, resulting > in v_cluster < rec[i]->e_cpos. > BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos)) > > Fixes: c15471f79506 ("ocfs2: fix sparse file & data ordering issue in direct io") > > Signed-off-by: Alex Chen <alex.chen@huawei.com> > Reviewed-by: Jun Piao <piaojun@huawei.com> > Acked-by: Changwei Ge <ge.changwei@h3c.com>> I don't think we have to rename ocfs2_dio_get_block. Anyway it doesn't matter. Reviewed-by: Joseph Qi <jiangqi903@gmail.com> > --- > fs/ocfs2/aops.c | 26 ++++++++++++++++++-------- > 1 file changed, 18 insertions(+), 8 deletions(-) > > diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c > index 88a31e9..d151632 100644 > --- a/fs/ocfs2/aops.c > +++ b/fs/ocfs2/aops.c > @@ -134,6 +134,19 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock, > return err; > } > > +static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock, > + struct buffer_head *bh_result, int create) > +{ > + int ret = 0; > + struct ocfs2_inode_info *oi = OCFS2_I(inode); > + > + down_read(&oi->ip_alloc_sem); > + ret = ocfs2_get_block(inode, iblock, bh_result, create); > + up_read(&oi->ip_alloc_sem); > + > + return ret; > +} > + > int ocfs2_get_block(struct inode *inode, sector_t iblock, > struct buffer_head *bh_result, int create) > { > @@ -2128,7 +2141,7 @@ static void ocfs2_dio_free_write_ctx(struct inode *inode, > * called like this: dio->get_blocks(dio->inode, fs_startblk, > * fs_count, map_bh, dio->rw == WRITE); > */ > -static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, > +static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, > struct buffer_head *bh_result, int create) > { > struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); > @@ -2154,12 +2167,9 @@ static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, > * while file size will be changed. > */ > if (pos + total_len <= i_size_read(inode)) { > - down_read(&oi->ip_alloc_sem); > - /* This is the fast path for re-write. */ > - ret = ocfs2_get_block(inode, iblock, bh_result, create); > - > - up_read(&oi->ip_alloc_sem); > > + /* This is the fast path for re-write. */ > + ret = ocfs2_lock_get_block(inode, iblock, bh_result, create); > if (buffer_mapped(bh_result) && > !buffer_new(bh_result) && > ret == 0) > @@ -2424,9 +2434,9 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) > return 0; > > if (iov_iter_rw(iter) == READ) > - get_block = ocfs2_get_block; > + get_block = ocfs2_lock_get_block; > else > - get_block = ocfs2_dio_get_block; > + get_block = ocfs2_dio_wr_get_block; > > return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, > iter, get_block, >
>>> > The ip_alloc_sem should be taken in ocfs2_get_block() when reading file > in DIRECT mode to prevent concurrent access to extent tree with > ocfs2_dio_end_io_write(), which may cause BUGON in the following situation: > > read file 'A' end_io of writing file 'A' > vfs_read > __vfs_read > ocfs2_file_read_iter > generic_file_read_iter > ocfs2_direct_IO > __blockdev_direct_IO > do_blockdev_direct_IO > do_direct_IO > get_more_blocks > ocfs2_get_block > ocfs2_extent_map_get_blocks > ocfs2_get_clusters > ocfs2_get_clusters_nocache() > ocfs2_search_extent_list > return the index of record which > contains the v_cluster, that is > v_cluster > rec[i]->e_cpos. > ocfs2_dio_end_io > ocfs2_dio_end_io_write > > down_write(&oi->ip_alloc_sem); > ocfs2_mark_extent_written > ocfs2_change_extent_flag > ocfs2_split_extent > ... > --> modify the rec[i]->e_cpos, > resulting > in v_cluster < > rec[i]->e_cpos. > BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos)) > > Fixes: c15471f79506 ("ocfs2: fix sparse file & data ordering issue in direct > io") > > Signed-off-by: Alex Chen <alex.chen@huawei.com> > Reviewed-by: Jun Piao <piaojun@huawei.com> > Acked-by: Changwei Ge <ge.changwei@h3c.com> Reviewed-by: Gang He <ghe@suse.com> > > --- > fs/ocfs2/aops.c | 26 ++++++++++++++++++-------- > 1 file changed, 18 insertions(+), 8 deletions(-) > > diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c > index 88a31e9..d151632 100644 > --- a/fs/ocfs2/aops.c > +++ b/fs/ocfs2/aops.c > @@ -134,6 +134,19 @@ static int ocfs2_symlink_get_block(struct inode *inode, > sector_t iblock, > return err; > } > > +static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock, > + struct buffer_head *bh_result, int create) > +{ > + int ret = 0; > + struct ocfs2_inode_info *oi = OCFS2_I(inode); > + > + down_read(&oi->ip_alloc_sem); > + ret = ocfs2_get_block(inode, iblock, bh_result, create); > + up_read(&oi->ip_alloc_sem); > + > + return ret; > +} > + > int ocfs2_get_block(struct inode *inode, sector_t iblock, > struct buffer_head *bh_result, int create) > { > @@ -2128,7 +2141,7 @@ static void ocfs2_dio_free_write_ctx(struct inode > *inode, > * called like this: dio->get_blocks(dio->inode, fs_startblk, > * fs_count, map_bh, dio->rw == WRITE); > */ > -static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, > +static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, > struct buffer_head *bh_result, int create) > { > struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); > @@ -2154,12 +2167,9 @@ static int ocfs2_dio_get_block(struct inode *inode, > sector_t iblock, > * while file size will be changed. > */ > if (pos + total_len <= i_size_read(inode)) { > - down_read(&oi->ip_alloc_sem); > - /* This is the fast path for re-write. */ > - ret = ocfs2_get_block(inode, iblock, bh_result, create); > - > - up_read(&oi->ip_alloc_sem); > > + /* This is the fast path for re-write. */ > + ret = ocfs2_lock_get_block(inode, iblock, bh_result, create); > if (buffer_mapped(bh_result) && > !buffer_new(bh_result) && > ret == 0) > @@ -2424,9 +2434,9 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, > struct iov_iter *iter) > return 0; > > if (iov_iter_rw(iter) == READ) > - get_block = ocfs2_get_block; > + get_block = ocfs2_lock_get_block; > else > - get_block = ocfs2_dio_get_block; > + get_block = ocfs2_dio_wr_get_block; > > return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, > iter, get_block, > -- > 1.9.5.msysgit.1
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 88a31e9..d151632 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -134,6 +134,19 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock, return err; } +static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + int ret = 0; + struct ocfs2_inode_info *oi = OCFS2_I(inode); + + down_read(&oi->ip_alloc_sem); + ret = ocfs2_get_block(inode, iblock, bh_result, create); + up_read(&oi->ip_alloc_sem); + + return ret; +} + int ocfs2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -2128,7 +2141,7 @@ static void ocfs2_dio_free_write_ctx(struct inode *inode, * called like this: dio->get_blocks(dio->inode, fs_startblk, * fs_count, map_bh, dio->rw == WRITE); */ -static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, +static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); @@ -2154,12 +2167,9 @@ static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, * while file size will be changed. */ if (pos + total_len <= i_size_read(inode)) { - down_read(&oi->ip_alloc_sem); - /* This is the fast path for re-write. */ - ret = ocfs2_get_block(inode, iblock, bh_result, create); - - up_read(&oi->ip_alloc_sem); + /* This is the fast path for re-write. */ + ret = ocfs2_lock_get_block(inode, iblock, bh_result, create); if (buffer_mapped(bh_result) && !buffer_new(bh_result) && ret == 0) @@ -2424,9 +2434,9 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return 0; if (iov_iter_rw(iter) == READ) - get_block = ocfs2_get_block; + get_block = ocfs2_lock_get_block; else - get_block = ocfs2_dio_get_block; + get_block = ocfs2_dio_wr_get_block; return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block,
The ip_alloc_sem should be taken in ocfs2_get_block() when reading file in DIRECT mode to prevent concurrent access to extent tree with ocfs2_dio_end_io_write(), which may cause BUGON in the following situation: read file 'A' end_io of writing file 'A' vfs_read __vfs_read ocfs2_file_read_iter generic_file_read_iter ocfs2_direct_IO __blockdev_direct_IO do_blockdev_direct_IO do_direct_IO get_more_blocks ocfs2_get_block ocfs2_extent_map_get_blocks ocfs2_get_clusters ocfs2_get_clusters_nocache() ocfs2_search_extent_list return the index of record which contains the v_cluster, that is v_cluster > rec[i]->e_cpos. ocfs2_dio_end_io ocfs2_dio_end_io_write down_write(&oi->ip_alloc_sem); ocfs2_mark_extent_written ocfs2_change_extent_flag ocfs2_split_extent ... --> modify the rec[i]->e_cpos, resulting in v_cluster < rec[i]->e_cpos. BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos)) Fixes: c15471f79506 ("ocfs2: fix sparse file & data ordering issue in direct io") Signed-off-by: Alex Chen <alex.chen@huawei.com> Reviewed-by: Jun Piao <piaojun@huawei.com> Acked-by: Changwei Ge <ge.changwei@h3c.com> --- fs/ocfs2/aops.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-)