From: Zhang Yi yi.zhang@huawei.com
hulk inclusion category: bugfix bugzilla: 174653, https://gitee.com/openeuler/kernel/issues/I476C7 CVE: NA ---------------------------
No EIO simulation is required if the buffer is uptodate, so move the simulation behind read bio completeion just like inode/block bitmap simulation does.
Link: https://lore.kernel.org/linux-ext4/20210821065450.1397451-2-yi.zhang@huawei.... Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Yang Erkun yangerkun@huawei.com Reviewed-by: Xie Miao miaoxie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/ext4/inode.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 800e6e3de40aa..1b2ccf61354f3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4635,8 +4635,6 @@ static int __ext4_get_inode_loc(struct inode *inode, bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; - if (ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO)) - goto simulate_eio; if (!buffer_uptodate(bh)) { lock_buffer(bh);
@@ -4721,8 +4719,8 @@ static int __ext4_get_inode_loc(struct inode *inode, trace_ext4_load_inode(inode); ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL); wait_on_buffer(bh); + ext4_simulate_fail_bh(sb, bh, EXT4_SIM_INODE_EIO); if (!buffer_uptodate(bh)) { - simulate_eio: ext4_error_inode_block(inode, block, EIO, "unable to read itable block"); brelse(bh);
From: Zhang Yi yi.zhang@huawei.com
hulk inclusion category: bugfix bugzilla: 174653, https://gitee.com/openeuler/kernel/issues/I476C7 CVE: NA ---------------------------
Now that ext4_do_update_inode() return error before filling the whole inode data if we fail to set inode blocks in ext4_inode_blocks_set(). This error should never happen in theory since sb->s_maxbytes should not have allowed this, we have already init sb->s_maxbytes according to this feature in ext4_fill_super(). So even through that could only happen due to the filesystem corruption, we'd better to return after we finish updating the inode because it may left an uninitialized buffer and we could read this buffer later in "errors=continue" mode.
This patch make the updating inode data procedure atomic, call EXT4_ERROR_INODE() after we dropping i_raw_lock after something bad happened, make sure that the inode is integrated, and also drop a BUG_ON and do some small cleanups.
Link: https://lore.kernel.org/linux-ext4/20210821065450.1397451-4-yi.zhang@huawei.... Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Yang Erkun yangerkun@huawei.com Reviewed-by: Xie Miao miaoxie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/ext4/inode.c | 44 ++++++++++++++++++++++++++++---------------- 1 file changed, 28 insertions(+), 16 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1b2ccf61354f3..8b01b73367a2b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5171,8 +5171,14 @@ static int ext4_inode_blocks_set(handle_t *handle, ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); return 0; } + + /* + * This should never happen since sb->s_maxbytes should not have + * allowed this, sb->s_maxbytes was set according to the huge_file + * feature in ext4_fill_super(). + */ if (!ext4_has_feature_huge_file(sb)) - return -EFBIG; + return -EFSCORRUPTED;
if (i_blocks <= 0xffffffffffffULL) { /* @@ -5279,16 +5285,14 @@ static int ext4_do_update_inode(handle_t *handle,
spin_lock(&ei->i_raw_lock);
- /* For fields not tracked in the in-memory inode, - * initialise them to zero for new inodes. */ + /* + * For fields not tracked in the in-memory inode, initialise them + * to zero for new inodes. + */ if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
err = ext4_inode_blocks_set(handle, raw_inode, ei); - if (err) { - spin_unlock(&ei->i_raw_lock); - goto out_brelse; - }
raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); @@ -5297,10 +5301,11 @@ static int ext4_do_update_inode(handle_t *handle, if (!(test_opt(inode->i_sb, NO_UID32))) { raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); -/* - * Fix up interoperability with old kernels. Otherwise, old inodes get - * re-used with the upper 16 bits of the uid/gid intact - */ + /* + * Fix up interoperability with old kernels. Otherwise, + * old inodes get re-used with the upper 16 bits of the + * uid/gid intact. + */ if (ei->i_dtime && list_empty(&ei->i_orphan)) { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; @@ -5369,8 +5374,9 @@ static int ext4_do_update_inode(handle_t *handle, } }
- BUG_ON(!ext4_has_feature_project(inode->i_sb) && - i_projid != EXT4_DEF_PROJID); + if (i_projid != EXT4_DEF_PROJID && + !ext4_has_feature_project(inode->i_sb)) + err = err ?: -EFSCORRUPTED;
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) @@ -5378,6 +5384,11 @@ static int ext4_do_update_inode(handle_t *handle,
ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); + if (err) { + EXT4_ERROR_INODE(inode, "corrupted inode contents"); + goto out_brelse; + } + if (inode->i_sb->s_flags & SB_LAZYTIME) ext4_update_other_inodes_time(inode->i_sb, inode->i_ino, bh->b_data); @@ -5385,13 +5396,13 @@ static int ext4_do_update_inode(handle_t *handle, BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) - goto out_brelse; + goto out_error; ext4_clear_inode_state(inode, EXT4_STATE_NEW); if (set_large_file) { BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access"); err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) - goto out_brelse; + goto out_error; lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_large_file(sb); ext4_superblock_csum_set(sb); @@ -5401,9 +5412,10 @@ static int ext4_do_update_inode(handle_t *handle, EXT4_SB(sb)->s_sbh); } ext4_update_inode_fsync_trans(handle, inode, need_datasync); +out_error: + ext4_std_error(inode->i_sb, err); out_brelse: brelse(bh); - ext4_std_error(inode->i_sb, err); return err; }
From: Zhang Yi yi.zhang@huawei.com
hulk inclusion category: bugfix bugzilla: 174653, https://gitee.com/openeuler/kernel/issues/I476C7 CVE: NA ---------------------------
Factor out ext4_fill_raw_inode() from ext4_do_update_inode(), which is use to fill the in-mem inode contents into the inode table buffer, in preparation for initializing the exclusive inode buffer without reading the block in __ext4_get_inode_loc().
Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com Reviewed-by: Xie Miao miaoxie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/ext4/inode.c | 85 +++++++++++++++++++++++++++---------------------- 1 file changed, 47 insertions(+), 38 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8b01b73367a2b..fb54a7e75acfa 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5153,9 +5153,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, return ERR_PTR(ret); }
-static int ext4_inode_blocks_set(handle_t *handle, - struct ext4_inode *raw_inode, - struct ext4_inode_info *ei) +static int ext4_inode_blocks_set(struct ext4_inode *raw_inode, + struct ext4_inode_info *ei) { struct inode *inode = &(ei->vfs_inode); u64 i_blocks = READ_ONCE(inode->i_blocks); @@ -5262,37 +5261,16 @@ static void ext4_update_other_inodes_time(struct super_block *sb, } }
-/* - * Post the struct inode info into an on-disk inode location in the - * buffer-cache. This gobbles the caller's reference to the - * buffer_head in the inode location struct. - * - * The caller must have write access to iloc->bh. - */ -static int ext4_do_update_inode(handle_t *handle, - struct inode *inode, - struct ext4_iloc *iloc) +static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode) { - struct ext4_inode *raw_inode = ext4_raw_inode(iloc); struct ext4_inode_info *ei = EXT4_I(inode); - struct buffer_head *bh = iloc->bh; - struct super_block *sb = inode->i_sb; - int err = 0, block; - int need_datasync = 0, set_large_file = 0; uid_t i_uid; gid_t i_gid; projid_t i_projid; + int block; + int err;
- spin_lock(&ei->i_raw_lock); - - /* - * For fields not tracked in the in-memory inode, initialise them - * to zero for new inodes. - */ - if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) - memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); - - err = ext4_inode_blocks_set(handle, raw_inode, ei); + err = ext4_inode_blocks_set(raw_inode, ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); @@ -5334,16 +5312,8 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) { - ext4_isize_set(raw_inode, ei->i_disksize); - need_datasync = 1; - } - if (ei->i_disksize > 0x7fffffffULL) { - if (!ext4_has_feature_large_file(sb) || - EXT4_SB(sb)->s_es->s_rev_level == - cpu_to_le32(EXT4_GOOD_OLD_REV)) - set_large_file = 1; - } + ext4_isize_set(raw_inode, ei->i_disksize); + raw_inode->i_generation = cpu_to_le32(inode->i_generation); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { if (old_valid_dev(inode->i_rdev)) { @@ -5383,6 +5353,45 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_projid = cpu_to_le32(i_projid);
ext4_inode_csum_set(inode, raw_inode, ei); + return err; +} + +/* + * Post the struct inode info into an on-disk inode location in the + * buffer-cache. This gobbles the caller's reference to the + * buffer_head in the inode location struct. + * + * The caller must have write access to iloc->bh. + */ +static int ext4_do_update_inode(handle_t *handle, + struct inode *inode, + struct ext4_iloc *iloc) +{ + struct ext4_inode *raw_inode = ext4_raw_inode(iloc); + struct ext4_inode_info *ei = EXT4_I(inode); + struct buffer_head *bh = iloc->bh; + struct super_block *sb = inode->i_sb; + int err; + int need_datasync = 0, set_large_file = 0; + + spin_lock(&ei->i_raw_lock); + + /* + * For fields not tracked in the in-memory inode, initialise them + * to zero for new inodes. + */ + if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) + memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); + + if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) + need_datasync = 1; + if (ei->i_disksize > 0x7fffffffULL) { + if (!ext4_has_feature_large_file(sb) || + EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV)) + set_large_file = 1; + } + + err = ext4_fill_raw_inode(inode, raw_inode); spin_unlock(&ei->i_raw_lock); if (err) { EXT4_ERROR_INODE(inode, "corrupted inode contents");
From: Zhang Yi yi.zhang@huawei.com
hulk inclusion category: bugfix bugzilla: 174653, https://gitee.com/openeuler/kernel/issues/I476C7 CVE: NA ---------------------------
In preparation for calling ext4_fill_raw_inode() in __ext4_get_inode_loc(), move three related functions before __ext4_get_inode_loc(), no logical change.
Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com Reviewed-by: Xie Miao miaoxie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/ext4/inode.c | 293 ++++++++++++++++++++++++------------------------ 1 file changed, 147 insertions(+), 146 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fb54a7e75acfa..8c20b4d6da9be 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4598,6 +4598,153 @@ int ext4_truncate(struct inode *inode) return err; }
+static inline u64 ext4_inode_peek_iversion(const struct inode *inode) +{ + if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return inode_peek_iversion_raw(inode); + else + return inode_peek_iversion(inode); +} + +static int ext4_inode_blocks_set(struct ext4_inode *raw_inode, + struct ext4_inode_info *ei) +{ + struct inode *inode = &(ei->vfs_inode); + u64 i_blocks = READ_ONCE(inode->i_blocks); + struct super_block *sb = inode->i_sb; + + if (i_blocks <= ~0U) { + /* + * i_blocks can be represented in a 32 bit variable + * as multiple of 512 bytes + */ + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = 0; + ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); + return 0; + } + + /* + * This should never happen since sb->s_maxbytes should not have + * allowed this, sb->s_maxbytes was set according to the huge_file + * feature in ext4_fill_super(). + */ + if (!ext4_has_feature_huge_file(sb)) + return -EFSCORRUPTED; + + if (i_blocks <= 0xffffffffffffULL) { + /* + * i_blocks can be represented in a 48 bit variable + * as multiple of 512 bytes + */ + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); + ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); + } else { + ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); + /* i_block is stored in file system block size */ + i_blocks = i_blocks >> (inode->i_blkbits - 9); + raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); + raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); + } + return 0; +} + +static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + uid_t i_uid; + gid_t i_gid; + projid_t i_projid; + int block; + int err; + + err = ext4_inode_blocks_set(raw_inode, ei); + + raw_inode->i_mode = cpu_to_le16(inode->i_mode); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); + i_projid = from_kprojid(&init_user_ns, ei->i_projid); + if (!(test_opt(inode->i_sb, NO_UID32))) { + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); + /* + * Fix up interoperability with old kernels. Otherwise, + * old inodes get re-used with the upper 16 bits of the + * uid/gid intact. + */ + if (ei->i_dtime && list_empty(&ei->i_orphan)) { + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } else { + raw_inode->i_uid_high = + cpu_to_le16(high_16_bits(i_uid)); + raw_inode->i_gid_high = + cpu_to_le16(high_16_bits(i_gid)); + } + } else { + raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } + raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); + + EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode); + EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); + EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); + EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); + + raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); + raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); + if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) + raw_inode->i_file_acl_high = + cpu_to_le16(ei->i_file_acl >> 32); + raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); + ext4_isize_set(raw_inode, ei->i_disksize); + + raw_inode->i_generation = cpu_to_le32(inode->i_generation); + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { + if (old_valid_dev(inode->i_rdev)) { + raw_inode->i_block[0] = + cpu_to_le32(old_encode_dev(inode->i_rdev)); + raw_inode->i_block[1] = 0; + } else { + raw_inode->i_block[0] = 0; + raw_inode->i_block[1] = + cpu_to_le32(new_encode_dev(inode->i_rdev)); + raw_inode->i_block[2] = 0; + } + } else if (!ext4_has_inline_data(inode)) { + for (block = 0; block < EXT4_N_BLOCKS; block++) + raw_inode->i_block[block] = ei->i_data[block]; + } + + if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { + u64 ivers = ext4_inode_peek_iversion(inode); + + raw_inode->i_disk_version = cpu_to_le32(ivers); + if (ei->i_extra_isize) { + if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) + raw_inode->i_version_hi = + cpu_to_le32(ivers >> 32); + raw_inode->i_extra_isize = + cpu_to_le16(ei->i_extra_isize); + } + } + + if (i_projid != EXT4_DEF_PROJID && + !ext4_has_feature_project(inode->i_sb)) + err = err ?: -EFSCORRUPTED; + + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + raw_inode->i_projid = cpu_to_le32(i_projid); + + ext4_inode_csum_set(inode, raw_inode, ei); + return err; +} + /* * ext4_get_inode_loc returns with an extra refcount against the inode's * underlying buffer_head on success. If 'in_mem' is true, we have all @@ -4837,13 +4984,6 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) else inode_set_iversion_queried(inode, val); } -static inline u64 ext4_inode_peek_iversion(const struct inode *inode) -{ - if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) - return inode_peek_iversion_raw(inode); - else - return inode_peek_iversion(inode); -}
struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, @@ -5153,50 +5293,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, return ERR_PTR(ret); }
-static int ext4_inode_blocks_set(struct ext4_inode *raw_inode, - struct ext4_inode_info *ei) -{ - struct inode *inode = &(ei->vfs_inode); - u64 i_blocks = READ_ONCE(inode->i_blocks); - struct super_block *sb = inode->i_sb; - - if (i_blocks <= ~0U) { - /* - * i_blocks can be represented in a 32 bit variable - * as multiple of 512 bytes - */ - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = 0; - ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); - return 0; - } - - /* - * This should never happen since sb->s_maxbytes should not have - * allowed this, sb->s_maxbytes was set according to the huge_file - * feature in ext4_fill_super(). - */ - if (!ext4_has_feature_huge_file(sb)) - return -EFSCORRUPTED; - - if (i_blocks <= 0xffffffffffffULL) { - /* - * i_blocks can be represented in a 48 bit variable - * as multiple of 512 bytes - */ - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); - ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); - } else { - ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); - /* i_block is stored in file system block size */ - i_blocks = i_blocks >> (inode->i_blkbits - 9); - raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); - raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); - } - return 0; -} - struct other_inode { unsigned long orig_ino; struct ext4_inode *raw_inode; @@ -5261,101 +5357,6 @@ static void ext4_update_other_inodes_time(struct super_block *sb, } }
-static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode) -{ - struct ext4_inode_info *ei = EXT4_I(inode); - uid_t i_uid; - gid_t i_gid; - projid_t i_projid; - int block; - int err; - - err = ext4_inode_blocks_set(raw_inode, ei); - - raw_inode->i_mode = cpu_to_le16(inode->i_mode); - i_uid = i_uid_read(inode); - i_gid = i_gid_read(inode); - i_projid = from_kprojid(&init_user_ns, ei->i_projid); - if (!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); - /* - * Fix up interoperability with old kernels. Otherwise, - * old inodes get re-used with the upper 16 bits of the - * uid/gid intact. - */ - if (ei->i_dtime && list_empty(&ei->i_orphan)) { - raw_inode->i_uid_high = 0; - raw_inode->i_gid_high = 0; - } else { - raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(i_uid)); - raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(i_gid)); - } - } else { - raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); - raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); - raw_inode->i_uid_high = 0; - raw_inode->i_gid_high = 0; - } - raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); - - EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); - EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); - - raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); - raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); - if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) - raw_inode->i_file_acl_high = - cpu_to_le16(ei->i_file_acl >> 32); - raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - ext4_isize_set(raw_inode, ei->i_disksize); - - raw_inode->i_generation = cpu_to_le32(inode->i_generation); - if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { - if (old_valid_dev(inode->i_rdev)) { - raw_inode->i_block[0] = - cpu_to_le32(old_encode_dev(inode->i_rdev)); - raw_inode->i_block[1] = 0; - } else { - raw_inode->i_block[0] = 0; - raw_inode->i_block[1] = - cpu_to_le32(new_encode_dev(inode->i_rdev)); - raw_inode->i_block[2] = 0; - } - } else if (!ext4_has_inline_data(inode)) { - for (block = 0; block < EXT4_N_BLOCKS; block++) - raw_inode->i_block[block] = ei->i_data[block]; - } - - if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { - u64 ivers = ext4_inode_peek_iversion(inode); - - raw_inode->i_disk_version = cpu_to_le32(ivers); - if (ei->i_extra_isize) { - if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) - raw_inode->i_version_hi = - cpu_to_le32(ivers >> 32); - raw_inode->i_extra_isize = - cpu_to_le16(ei->i_extra_isize); - } - } - - if (i_projid != EXT4_DEF_PROJID && - !ext4_has_feature_project(inode->i_sb)) - err = err ?: -EFSCORRUPTED; - - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && - EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) - raw_inode->i_projid = cpu_to_le32(i_projid); - - ext4_inode_csum_set(inode, raw_inode, ei); - return err; -} - /* * Post the struct inode info into an on-disk inode location in the * buffer-cache. This gobbles the caller's reference to the
From: Zhang Yi yi.zhang@huawei.com
hulk inclusion category: bugfix bugzilla: 174653, https://gitee.com/openeuler/kernel/issues/I476C7 CVE: NA ---------------------------
In ext4_get_inode_loc(), we may skip IO and get an zero && uptodate inode buffer when the inode monopolize an inode block for performance reason. For most cases, ext4_mark_iloc_dirty() will fill the inode buffer to make it fine, but we could miss this call if something bad happened. Finally, __ext4_get_inode_loc_noinmem() may probably get an empty inode buffer and trigger ext4 error.
For example, if we remove a nonexistent xattr on inode A, ext4_xattr_set_handle() will return ENODATA before invoking ext4_mark_iloc_dirty(), it will left an uptodate but zero buffer. We will get checksum error message in ext4_iget() when getting inode again.
EXT4-fs error (device sda): ext4_lookup:1784: inode #131074: comm cat: iget: checksum invalid
Even worse, if we allocate another inode B at the same inode block, it will corrupt the inode A on disk when write back inode B.
So this patch initialize the inode buffer by filling the in-mem inode contents if we skip read I/O, ensure that the buffer is really uptodate.
Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com Reviewed-by: Xie Miao miaoxie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/ext4/inode.c | 5 +++++ 1 file changed, 5 insertions(+)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8c20b4d6da9be..b1bede3c489e7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4824,8 +4824,13 @@ static int __ext4_get_inode_loc(struct inode *inode, } brelse(bitmap_bh); if (i == start + inodes_per_block) { + struct ext4_inode *raw_inode = + (struct ext4_inode *) (bh->b_data + iloc->offset); + /* all other inodes are free, so skip I/O */ memset(bh->b_data, 0, bh->b_size); + if (!ext4_test_inode_state(inode, EXT4_STATE_NEW)) + ext4_fill_raw_inode(inode, raw_inode); set_buffer_uptodate(bh); unlock_buffer(bh); goto has_buffer;
-
Yang Yingliang