From f2eeca099bbda45029da35abecb428a9084a5463 Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Tue, 24 Dec 2019 11:09:40 -0800 Subject: [PATCH 01/31] ext4: force buffer up-to-date while marking it dirty Writeback errors can leave buffer in not up-to-date state when there are errors during background writes. Force buffer up-to-date while marking it dirty. Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20191224190940.157952-1-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4_jbd2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 1f53d64e42a5..ee3755c3110a 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -332,6 +332,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, err); } } else { + set_buffer_uptodate(bh); if (inode) mark_buffer_dirty_inode(bh, inode); else From 72f9da1d5c8d03d6fb242d01aae66928b2b2e7a8 Mon Sep 17 00:00:00 2001 From: Xiaoguang Wang Date: Fri, 7 Feb 2020 20:07:58 +0800 Subject: [PATCH 02/31] ext4: start to support iopoll method Since commit "b1b4705d54ab ext4: introduce direct I/O read using iomap infrastructure", we can easily make ext4 support iopoll method, just use iomap_dio_iopoll(). Reviewed-by: Jan Kara Signed-off-by: Xiaoguang Wang Link: https://lore.kernel.org/r/20200207120758.2411-1-xiaoguang.wang@linux.alibaba.com Signed-off-by: Theodore Ts'o --- fs/ext4/file.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 5f225881176b..0d624250a62b 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -872,6 +872,7 @@ const struct file_operations ext4_file_operations = { .llseek = ext4_llseek, .read_iter = ext4_file_read_iter, .write_iter = ext4_file_write_iter, + .iopoll = iomap_dio_iopoll, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, From a08fe66e4a0e12a3df982b28059f3a90e0f1b31e Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Mon, 10 Feb 2020 16:24:45 +0800 Subject: [PATCH 03/31] ext4: code cleanup for ext4_statfs_project() Calling min_not_zero() to simplify complicated prjquota limit comparison in ext4_statfs_project(). Signed-off-by: Chengguang Xu Link: https://lore.kernel.org/r/20200210082445.2379-1-cgxu519@mykernel.net Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0c7c4adb664e..de5398c07161 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5622,10 +5622,8 @@ static int ext4_statfs_project(struct super_block *sb, return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); - limit = dquot->dq_dqb.dqb_bsoftlimit; - if (dquot->dq_dqb.dqb_bhardlimit && - (!limit || dquot->dq_dqb.dqb_bhardlimit < limit)) - limit = dquot->dq_dqb.dqb_bhardlimit; + limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, + dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; if (limit && buf->f_blocks > limit) { @@ -5637,11 +5635,8 @@ static int ext4_statfs_project(struct super_block *sb, (buf->f_blocks - curblock) : 0; } - limit = dquot->dq_dqb.dqb_isoftlimit; - if (dquot->dq_dqb.dqb_ihardlimit && - (!limit || dquot->dq_dqb.dqb_ihardlimit < limit)) - limit = dquot->dq_dqb.dqb_ihardlimit; - + limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, + dquot->dq_dqb.dqb_ihardlimit); if (limit && buf->f_files > limit) { buf->f_files = limit; buf->f_ffree = From 4337ecd1fe997d2b2135b4434caaccdb47c10c06 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Tue, 11 Feb 2020 16:02:16 -0500 Subject: [PATCH 04/31] ext4: remove EXT4_EOFBLOCKS_FL and associated code The EXT4_EOFBLOCKS_FL inode flag is used to indicate whether a file contains unwritten blocks past i_size. It's set when ext4_fallocate is called with the KEEP_SIZE flag to extend a file with an unwritten extent. However, this flag hasn't been useful functionally since March, 2012, when a decision was made to remove it from ext4. All traces of EXT4_EOFBLOCKS_FL were removed from e2fsprogs version 1.42.2 by commit 010dc7b90d97 ("e2fsck: remove EXT4_EOFBLOCKS_FL flag handling") at that time. Now that enough time has passed to make e2fsprogs versions containing this modification common, this patch now removes the code associated with EXT4_EOFBLOCKS_FL from the kernel as well. This change has two implications. First, because pre-1.42.2 e2fsck versions only look for a problem if EXT4_EOFBLOCKS_FL is set, and because that bit will never be set by newer kernels containing this patch, old versions of e2fsck won't have a compatibility problem with files created by newer kernels. Second, newer kernels will not clear EXT4_EOFBLOCKS_FL inode flag bits belonging to a file written by an older kernel. If set, it will remain in that state until the file is deleted. Because e2fsck versions since 1.42.2 don't check the flag at all, no adverse effect is expected. However, pre-1.42.2 e2fsck versions that do check the flag may report that it is set when it ought not to be after a file has been truncated or had its unwritten blocks written. In this case, the old version of e2fsck will offer to clear the flag. No adverse effect would then occur whether the user chooses to clear the flag or not. Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20200211210216.24960-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 5 ++- fs/ext4/extents.c | 92 ++++------------------------------------------- fs/ext4/inode.c | 2 -- fs/ext4/ioctl.c | 12 ------- 4 files changed, 9 insertions(+), 102 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 61b37a052052..54f0a003053b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -414,7 +414,7 @@ struct flex_groups { #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ #define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */ #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ -#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ +/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded file */ @@ -487,7 +487,7 @@ enum { EXT4_INODE_EXTENTS = 19, /* Inode uses extents */ EXT4_INODE_VERITY = 20, /* Verity protected inode */ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ - EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */ +/* 22 was formerly EXT4_INODE_EOFBLOCKS */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */ @@ -533,7 +533,6 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(EXTENTS); CHECK_FLAG_VALUE(VERITY); CHECK_FLAG_VALUE(EA_INODE); - CHECK_FLAG_VALUE(EOFBLOCKS); CHECK_FLAG_VALUE(INLINE_DATA); CHECK_FLAG_VALUE(PROJINHERIT); CHECK_FLAG_VALUE(RESERVED); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 954013d6076b..89aa9c7ae293 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3874,59 +3874,6 @@ out: return err; } -/* - * Handle EOFBLOCKS_FL flag, clearing it if necessary - */ -static int check_eofblocks_fl(handle_t *handle, struct inode *inode, - ext4_lblk_t lblk, - struct ext4_ext_path *path, - unsigned int len) -{ - int i, depth; - struct ext4_extent_header *eh; - struct ext4_extent *last_ex; - - if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)) - return 0; - - depth = ext_depth(inode); - eh = path[depth].p_hdr; - - /* - * We're going to remove EOFBLOCKS_FL entirely in future so we - * do not care for this case anymore. Simply remove the flag - * if there are no extents. - */ - if (unlikely(!eh->eh_entries)) - goto out; - last_ex = EXT_LAST_EXTENT(eh); - /* - * We should clear the EOFBLOCKS_FL flag if we are writing the - * last block in the last extent in the file. We test this by - * first checking to see if the caller to - * ext4_ext_get_blocks() was interested in the last block (or - * a block beyond the last block) in the current extent. If - * this turns out to be false, we can bail out from this - * function immediately. - */ - if (lblk + len < le32_to_cpu(last_ex->ee_block) + - ext4_ext_get_actual_len(last_ex)) - return 0; - /* - * If the caller does appear to be planning to write at or - * beyond the end of the current extent, we then test to see - * if the current extent is the last extent in the file, by - * checking to make sure it was reached via the rightmost node - * at each level of the tree. - */ - for (i = depth-1; i >= 0; i--) - if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr)) - return 0; -out: - ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); - return ext4_mark_inode_dirty(handle, inode); -} - static int convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -3991,9 +3938,7 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, ext4_ext_show_leaf(inode, path); ext4_update_inode_fsync_trans(handle, inode, 1); - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, map->m_len); - if (err) - return err; + map->m_flags |= EXT4_MAP_UNWRITTEN; if (allocated > map->m_len) allocated = map->m_len; @@ -4007,7 +3952,9 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, int flags, unsigned int allocated, ext4_fsblk_t newblock) { +#ifdef EXT_DEBUG struct ext4_ext_path *path = *ppath; +#endif int ret = 0; int err = 0; @@ -4047,11 +3994,9 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, } ret = ext4_convert_unwritten_extents_endio(handle, inode, map, ppath); - if (ret >= 0) { + if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); - err = check_eofblocks_fl(handle, inode, map->m_lblk, - path, map->m_len); - } else + else err = ret; map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = newblock; @@ -4100,12 +4045,6 @@ out: map_out: map->m_flags |= EXT4_MAP_MAPPED; - if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) { - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, - map->m_len); - if (err < 0) - goto out2; - } out1: if (allocated > map->m_len) allocated = map->m_len; @@ -4459,12 +4398,7 @@ got_allocated_blocks: } err = 0; - if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) - err = check_eofblocks_fl(handle, inode, map->m_lblk, - path, ar.len); - if (!err) - err = ext4_ext_insert_extent(handle, inode, &path, - &newex, flags); + err = ext4_ext_insert_extent(handle, inode, &path, &newex, flags); if (err && free_on_err) { int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ? @@ -4645,10 +4579,6 @@ retry: epos = new_size; if (ext4_update_inode_size(inode, epos) & 0x1) inode->i_mtime = inode->i_ctime; - } else { - if (epos > inode->i_size) - ext4_set_inode_flag(inode, - EXT4_INODE_EOFBLOCKS); } ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); @@ -4802,16 +4732,8 @@ static long ext4_zero_range(struct file *file, loff_t offset, } inode->i_mtime = inode->i_ctime = current_time(inode); - if (new_size) { + if (new_size) ext4_update_inode_size(inode, new_size); - } else { - /* - * Mark that we allocate beyond EOF so the subsequent truncate - * can proceed even if the new size is the same as i_size. - */ - if (offset + len > inode->i_size) - ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS); - } ext4_mark_inode_dirty(handle, inode); /* Zero out partial block at the edges of the range */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fa0ff78dc033..416aec6d6c65 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4144,8 +4144,6 @@ int ext4_truncate(struct inode *inode) if (!ext4_can_truncate(inode)) return 0; - ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); - if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a0ec750018dd..d0b00fab0531 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -327,18 +327,6 @@ static int ext4_ioctl_setflags(struct inode *inode, if ((flags ^ oldflags) & EXT4_EXTENTS_FL) migrate = 1; - if (flags & EXT4_EOFBLOCKS_FL) { - /* we don't support adding EOFBLOCKS flag */ - if (!(oldflags & EXT4_EOFBLOCKS_FL)) { - err = -EOPNOTSUPP; - goto flags_out; - } - } else if (oldflags & EXT4_EOFBLOCKS_FL) { - err = ext4_truncate(inode); - if (err) - goto flags_out; - } - if ((flags ^ oldflags) & EXT4_CASEFOLD_FL) { if (!ext4_has_feature_casefold(sb)) { err = -EOPNOTSUPP; From 765bfcd59a1ff799b1c71cb3be0c43b0775ec166 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Wed, 12 Feb 2020 11:21:41 -0500 Subject: [PATCH 05/31] ext4: delete declaration for ext4_split_extent() There are no forward references for ext4_split_extent() in extents.c, so delete its unnecessary declaration. Reviewed-by: Darrick J. Wong Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20200212162141.22381-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 89aa9c7ae293..a5338a8da2ab 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -83,13 +83,6 @@ static void ext4_extent_block_csum_set(struct inode *inode, et->et_checksum = ext4_extent_block_csum(inode, eh); } -static int ext4_split_extent(handle_t *handle, - struct inode *inode, - struct ext4_ext_path **ppath, - struct ext4_map_blocks *map, - int split_flag, - int flags); - static int ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, From 92e9c58c5629762001e7294afbdf1283d5c7d2ed Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Thu, 13 Feb 2020 20:55:58 +0530 Subject: [PATCH 06/31] ext4: use built-in RCU list checking in mballoc list_for_each_entry_rcu() has built-in RCU and lock checking. Pass cond argument to list_for_each_entry_rcu() to silence false lockdep warning when CONFIG_PROVE_RCU_LIST is enabled by default. Signed-off-by: Madhuparna Bhowmik Link: https://lore.kernel.org/r/20200213152558.7070-1-madhuparnabhowmik10@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 51a78eb65f3c..1027e01c9011 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4302,7 +4302,8 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], - pa_inode_list) { + pa_inode_list, + lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* @@ -4386,7 +4387,8 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) /* Add the prealloc space to lg */ spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order], - pa_inode_list) { + pa_inode_list, + lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted) { spin_unlock(&tmp_pa->pa_lock); From 6cfb061fe9e901dd0b6cfa3ed50bc39c81523532 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 13 Feb 2020 10:06:48 -0600 Subject: [PATCH 07/31] ext4: use flexible-array members in struct dx_node and struct dx_root The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200213160648.GA7054@embeddedor Signed-off-by: Theodore Ts'o --- fs/ext4/namei.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b05ea72f38fd..5f0a758956f6 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -233,13 +233,13 @@ struct dx_root u8 unused_flags; } info; - struct dx_entry entries[0]; + struct dx_entry entries[]; }; struct dx_node { struct fake_dirent fake; - struct dx_entry entries[0]; + struct dx_entry entries[]; }; From 780f66e59231fcf882f36c63f287252ee47cc75a Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Mon, 17 Feb 2020 19:27:06 +0800 Subject: [PATCH 08/31] jbd2: improve comments about freeing data buffers whose page mapping is NULL Improve comments in jbd2_journal_commit_transaction() to describe why we don't need to clear the buffer_mapped bit for freeing file mapping buffers whose page mapping is NULL. Link: https://lore.kernel.org/r/20200217112706.20085-1-yi.zhang@huawei.com Fixes: c96dceeabf76 ("jbd2: do not clear the BH_Mapped flag when forgetting a metadata buffer") Suggested-by: Jan Kara Reviewed-by: Jan Kara Signed-off-by: zhangyi (F) Signed-off-by: Theodore Ts'o --- fs/jbd2/commit.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 27373f5792a4..e855d8260433 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -997,9 +997,10 @@ restart_loop: * journalled data) we need to unmap buffer and clear * more bits. We also need to be careful about the check * because the data page mapping can get cleared under - * out hands, which alse need not to clear more bits - * because the page and buffers will be freed and can - * never be reused once we are done with them. + * our hands. Note that if mapping == NULL, we don't + * need to make buffer unmapped because the page is + * already detached from the mapping and buffers cannot + * get reused. */ mapping = READ_ONCE(bh->b_page->mapping); if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) { From f064a9d6e7dbd3473e9da0ffa1a91c08a032d747 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Tue, 18 Feb 2020 15:26:56 -0500 Subject: [PATCH 09/31] ext4: clean up error return for convert_initialized_extent() Although convert_initialized_extent() can potentially return an error code with a negative value, its returned value is assigned to an unsigned variable containing a block count in ext4_ext_map_blocks() and then returned to that function's caller. The code currently works, though the way this happens is obscure. The code would be more readable if it followed the error handling convention used elsewhere in ext4_ext_map_blocks(). This patch does not address any known test failure or bug report - it's simply a cleanup. It also addresses a nearby coding standard issue. Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20200218202656.21561-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index a5338a8da2ab..bc96529d1509 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3871,7 +3871,7 @@ static int convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, - unsigned int allocated) + unsigned int *allocated) { struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; @@ -3933,10 +3933,10 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, ext4_update_inode_fsync_trans(handle, inode, 1); map->m_flags |= EXT4_MAP_UNWRITTEN; - if (allocated > map->m_len) - allocated = map->m_len; - map->m_len = allocated; - return allocated; + if (*allocated > map->m_len) + *allocated = map->m_len; + map->m_len = *allocated; + return 0; } static int @@ -4240,12 +4240,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, */ if ((!ext4_ext_is_unwritten(ex)) && (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { - allocated = convert_initialized_extent( - handle, inode, map, &path, - allocated); + err = convert_initialized_extent(handle, + inode, map, &path, &allocated); goto out2; - } else if (!ext4_ext_is_unwritten(ex)) + } else if (!ext4_ext_is_unwritten(ex)) { goto out; + } ret = ext4_ext_handle_unwritten_extents( handle, inode, map, &path, flags, From 28936b62e71e41600bab319f262ea9f9b1027629 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 21 Feb 2020 23:32:58 -0500 Subject: [PATCH 10/31] ext4: fix a data race at inode->i_blocks inode->i_blocks could be accessed concurrently as noticed by KCSAN, BUG: KCSAN: data-race in ext4_do_update_inode [ext4] / inode_add_bytes write to 0xffff9a00d4b982d0 of 8 bytes by task 22100 on cpu 118: inode_add_bytes+0x65/0xf0 __inode_add_bytes at fs/stat.c:689 (inlined by) inode_add_bytes at fs/stat.c:702 ext4_mb_new_blocks+0x418/0xca0 [ext4] ext4_ext_map_blocks+0x1a6b/0x27b0 [ext4] ext4_map_blocks+0x1a9/0x950 [ext4] _ext4_get_block+0xfc/0x270 [ext4] ext4_get_block_unwritten+0x33/0x50 [ext4] __block_write_begin_int+0x22e/0xae0 __block_write_begin+0x39/0x50 ext4_write_begin+0x388/0xb50 [ext4] ext4_da_write_begin+0x35f/0x8f0 [ext4] generic_perform_write+0x15d/0x290 ext4_buffered_write_iter+0x11f/0x210 [ext4] ext4_file_write_iter+0xce/0x9e0 [ext4] new_sync_write+0x29c/0x3b0 __vfs_write+0x92/0xa0 vfs_write+0x103/0x260 ksys_write+0x9d/0x130 __x64_sys_write+0x4c/0x60 do_syscall_64+0x91/0xb05 entry_SYSCALL_64_after_hwframe+0x49/0xbe read to 0xffff9a00d4b982d0 of 8 bytes by task 8 on cpu 65: ext4_do_update_inode+0x4a0/0xf60 [ext4] ext4_inode_blocks_set at fs/ext4/inode.c:4815 ext4_mark_iloc_dirty+0xaf/0x160 [ext4] ext4_mark_inode_dirty+0x129/0x3e0 [ext4] ext4_convert_unwritten_extents+0x253/0x2d0 [ext4] ext4_convert_unwritten_io_end_vec+0xc5/0x150 [ext4] ext4_end_io_rsv_work+0x22c/0x350 [ext4] process_one_work+0x54f/0xb90 worker_thread+0x80/0x5f0 kthread+0x1cd/0x1f0 ret_from_fork+0x27/0x50 4 locks held by kworker/u256:0/8: #0: ffff9a025abc4328 ((wq_completion)ext4-rsv-conversion){+.+.}, at: process_one_work+0x443/0xb90 #1: ffffab5a862dbe20 ((work_completion)(&ei->i_rsv_conversion_work)){+.+.}, at: process_one_work+0x443/0xb90 #2: ffff9a025a9d0f58 (jbd2_handle){++++}, at: start_this_handle+0x1c1/0x9d0 [jbd2] #3: ffff9a00d4b985d8 (&(&ei->i_raw_lock)->rlock){+.+.}, at: ext4_do_update_inode+0xaa/0xf60 [ext4] irq event stamp: 3009267 hardirqs last enabled at (3009267): [] __find_get_block+0x107/0x790 hardirqs last disabled at (3009266): [] __find_get_block+0x49/0x790 softirqs last enabled at (3009230): [] __do_softirq+0x34c/0x57c softirqs last disabled at (3009223): [] irq_exit+0xa2/0xc0 Reported by Kernel Concurrency Sanitizer on: CPU: 65 PID: 8 Comm: kworker/u256:0 Tainted: G L 5.6.0-rc2-next-20200221+ #7 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 Workqueue: ext4-rsv-conversion ext4_end_io_rsv_work [ext4] The plain read is outside of inode->i_lock critical section which results in a data race. Fix it by adding READ_ONCE() there. Link: https://lore.kernel.org/r/20200222043258.2279-1-cai@lca.pw Signed-off-by: Qian Cai Signed-off-by: Theodore Ts'o Cc: stable@kernel.org --- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 416aec6d6c65..fa70ae21d032 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4810,7 +4810,7 @@ static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode_info *ei) { struct inode *inode = &(ei->vfs_inode); - u64 i_blocks = inode->i_blocks; + u64 i_blocks = READ_ONCE(inode->i_blocks); struct super_block *sb = inode->i_sb; if (i_blocks <= ~0U) { From dce8e237100f60c28cc66effb526ba65a01d8cb3 Mon Sep 17 00:00:00 2001 From: Qiujun Huang Date: Mon, 24 Feb 2020 23:02:46 +0800 Subject: [PATCH 11/31] ext4: fix a data race at inode->i_disksize KCSAN find inode->i_disksize could be accessed concurrently. BUG: KCSAN: data-race in ext4_mark_iloc_dirty / ext4_write_end write (marked) to 0xffff8b8932f40090 of 8 bytes by task 66792 on cpu 0: ext4_write_end+0x53f/0x5b0 ext4_da_write_end+0x237/0x510 generic_perform_write+0x1c4/0x2a0 ext4_buffered_write_iter+0x13a/0x210 ext4_file_write_iter+0xe2/0x9b0 new_sync_write+0x29c/0x3a0 __vfs_write+0x92/0xa0 vfs_write+0xfc/0x2a0 ksys_write+0xe8/0x140 __x64_sys_write+0x4c/0x60 do_syscall_64+0x8a/0x2a0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 read to 0xffff8b8932f40090 of 8 bytes by task 14414 on cpu 1: ext4_mark_iloc_dirty+0x716/0x1190 ext4_mark_inode_dirty+0xc9/0x360 ext4_convert_unwritten_extents+0x1bc/0x2a0 ext4_convert_unwritten_io_end_vec+0xc5/0x150 ext4_put_io_end+0x82/0x130 ext4_writepages+0xae7/0x16f0 do_writepages+0x64/0x120 __writeback_single_inode+0x7d/0x650 writeback_sb_inodes+0x3a4/0x860 __writeback_inodes_wb+0xc4/0x150 wb_writeback+0x43f/0x510 wb_workfn+0x3b2/0x8a0 process_one_work+0x39b/0x7e0 worker_thread+0x88/0x650 kthread+0x1d4/0x1f0 ret_from_fork+0x35/0x40 The plain read is outside of inode->i_data_sem critical section which results in a data race. Fix it by adding READ_ONCE(). Signed-off-by: Qiujun Huang Link: https://lore.kernel.org/r/1582556566-3909-1-git-send-email-hqjagain@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fa70ae21d032..27d009bf183f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4980,7 +4980,7 @@ 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 (ei->i_disksize != ext4_isize(inode->i_sb, raw_inode)) { + if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) { ext4_isize_set(raw_inode, ei->i_disksize); need_datasync = 1; } From 6386722a329824e005c3fd1b4a8cc37db367c76a Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 28 Feb 2020 14:56:54 +0530 Subject: [PATCH 12/31] ext4: add IOMAP_F_MERGED for non-extent based mapping IOMAP_F_MERGED needs to be set in case of non-extent based mapping. This is needed in later patches for conversion of ext4_fiemap to use iomap. Reviewed-by: Darrick J. Wong Reviewed-by: Jan Kara Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/a4764c91c08c16d4d4a4b36defb2a08625b0e9b3.1582880246.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 27d009bf183f..db3ba140351e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3333,6 +3333,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, iomap->offset = (u64) map->m_lblk << blkbits; iomap->length = (u64) map->m_len << blkbits; + if ((map->m_flags & EXT4_MAP_MAPPED) && + !ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + iomap->flags |= IOMAP_F_MERGED; + /* * Flags passed to ext4_map_blocks() for direct I/O writes can result * in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits From 2f424a5a09a506e1a6ad432e50bca3000a767d5a Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 28 Feb 2020 14:56:55 +0530 Subject: [PATCH 13/31] ext4: optimize ext4_ext_precache for 0 depth This patch avoids the memory alloc & free path when depth is 0, since anyway there is no extra caching done in that case. So on checking depth 0, simply return early. Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/93da0d0f073c73358e85bb9849d8a5378d1da539.1582880246.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index bc96529d1509..2ebc858fd392 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -549,6 +549,12 @@ int ext4_ext_precache(struct inode *inode) down_read(&ei->i_data_sem); depth = ext_depth(inode); + /* Don't cache anything if there are no external extent blocks */ + if (!depth) { + up_read(&ei->i_data_sem); + return ret; + } + path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS); if (path == NULL) { @@ -556,9 +562,6 @@ int ext4_ext_precache(struct inode *inode) return -ENOMEM; } - /* Don't cache anything if there are no external extent blocks */ - if (depth == 0) - goto out; path[0].p_hdr = ext_inode_hdr(inode); ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0); if (ret) From ac58e4fb03f9d111d733a4ad379d06eef3a24705 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 28 Feb 2020 14:56:56 +0530 Subject: [PATCH 14/31] ext4: move ext4 bmap to use iomap infrastructure ext4_iomap_begin is already implemented which provides ext4_map_blocks, so just move the API from generic_block_bmap to iomap_bmap for iomap conversion. Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/8bbd53bd719d5ccfecafcce93f2bf1d7955a44af.1582880246.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index db3ba140351e..07ca260b30ab 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3212,7 +3212,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) return 0; } - return generic_block_bmap(mapping, block, ext4_get_block); + return iomap_bmap(mapping, block, &ext4_iomap_ops); } static int ext4_readpage(struct file *file, struct page *page) From b2c5764262edded1b1cfff5a6ca82c3d61bb4a4a Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 28 Feb 2020 14:56:57 +0530 Subject: [PATCH 15/31] ext4: make ext4_ind_map_blocks work with fiemap For indirect block mapping if the i_block > max supported block in inode then ext4_ind_map_blocks() returns a -EIO error. But in case of fiemap this could be a valid query to ->iomap_begin call. So check if the offset >= s_bitmap_maxbytes in ext4_iomap_begin_report(), then simply skip calling ext4_map_blocks(). Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/87fa0ddc5967fa707656212a3b66a7233425325c.1582880246.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 07ca260b30ab..f6aebb792178 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3546,12 +3546,28 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits, EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1; + /* + * Fiemap callers may call for offset beyond s_bitmap_maxbytes. + * So handle it here itself instead of querying ext4_map_blocks(). + * Since ext4_map_blocks() will warn about it and will return + * -EIO error. + */ + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + + if (offset >= sbi->s_bitmap_maxbytes) { + map.m_flags = 0; + goto set_iomap; + } + } + ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; if (ret == 0) delalloc = ext4_iomap_is_delalloc(inode, &map); +set_iomap: ext4_set_iomap(inode, iomap, &map, offset, length); if (delalloc && iomap->type == IOMAP_HOLE) iomap->type = IOMAP_DELALLOC; From d3b6f23f71670007817a5d59f3fbafab2b794e8c Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 28 Feb 2020 14:56:58 +0530 Subject: [PATCH 16/31] ext4: move ext4_fiemap to use iomap framework This patch moves ext4_fiemap to use iomap framework. For xattr a new 'ext4_iomap_xattr_ops' is added. Reported-by: kbuild test robot Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/b9f45c885814fcdd0631747ff0fe08886270828c.1582880246.git.riteshh@linux.ibm.com Signed-off-by: Ritesh Harjani Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 292 ++++++++-------------------------------------- fs/ext4/inline.c | 41 ------- 2 files changed, 49 insertions(+), 284 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2ebc858fd392..5b2cac0208fe 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" @@ -90,9 +91,6 @@ static int ext4_split_extent_at(handle_t *handle, int split_flag, int flags); -static int ext4_find_delayed_extent(struct inode *inode, - struct extent_status *newes); - static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) { /* @@ -2130,155 +2128,6 @@ cleanup: return err; } -static int ext4_fill_fiemap_extents(struct inode *inode, - ext4_lblk_t block, ext4_lblk_t num, - struct fiemap_extent_info *fieinfo) -{ - struct ext4_ext_path *path = NULL; - struct ext4_extent *ex; - struct extent_status es; - ext4_lblk_t next, next_del, start = 0, end = 0; - ext4_lblk_t last = block + num; - int exists, depth = 0, err = 0; - unsigned int flags = 0; - unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; - - while (block < last && block != EXT_MAX_BLOCKS) { - num = last - block; - /* find extent for this block */ - down_read(&EXT4_I(inode)->i_data_sem); - - path = ext4_find_extent(inode, block, &path, 0); - if (IS_ERR(path)) { - up_read(&EXT4_I(inode)->i_data_sem); - err = PTR_ERR(path); - path = NULL; - break; - } - - depth = ext_depth(inode); - if (unlikely(path[depth].p_hdr == NULL)) { - up_read(&EXT4_I(inode)->i_data_sem); - EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); - err = -EFSCORRUPTED; - break; - } - ex = path[depth].p_ext; - next = ext4_ext_next_allocated_block(path); - - flags = 0; - exists = 0; - if (!ex) { - /* there is no extent yet, so try to allocate - * all requested space */ - start = block; - end = block + num; - } else if (le32_to_cpu(ex->ee_block) > block) { - /* need to allocate space before found extent */ - start = block; - end = le32_to_cpu(ex->ee_block); - if (block + num < end) - end = block + num; - } else if (block >= le32_to_cpu(ex->ee_block) - + ext4_ext_get_actual_len(ex)) { - /* need to allocate space after found extent */ - start = block; - end = block + num; - if (end >= next) - end = next; - } else if (block >= le32_to_cpu(ex->ee_block)) { - /* - * some part of requested space is covered - * by found extent - */ - start = block; - end = le32_to_cpu(ex->ee_block) - + ext4_ext_get_actual_len(ex); - if (block + num < end) - end = block + num; - exists = 1; - } else { - BUG(); - } - BUG_ON(end <= start); - - if (!exists) { - es.es_lblk = start; - es.es_len = end - start; - es.es_pblk = 0; - } else { - es.es_lblk = le32_to_cpu(ex->ee_block); - es.es_len = ext4_ext_get_actual_len(ex); - es.es_pblk = ext4_ext_pblock(ex); - if (ext4_ext_is_unwritten(ex)) - flags |= FIEMAP_EXTENT_UNWRITTEN; - } - - /* - * Find delayed extent and update es accordingly. We call - * it even in !exists case to find out whether es is the - * last existing extent or not. - */ - next_del = ext4_find_delayed_extent(inode, &es); - if (!exists && next_del) { - exists = 1; - flags |= (FIEMAP_EXTENT_DELALLOC | - FIEMAP_EXTENT_UNKNOWN); - } - up_read(&EXT4_I(inode)->i_data_sem); - - if (unlikely(es.es_len == 0)) { - EXT4_ERROR_INODE(inode, "es.es_len == 0"); - err = -EFSCORRUPTED; - break; - } - - /* - * This is possible iff next == next_del == EXT_MAX_BLOCKS. - * we need to check next == EXT_MAX_BLOCKS because it is - * possible that an extent is with unwritten and delayed - * status due to when an extent is delayed allocated and - * is allocated by fallocate status tree will track both of - * them in a extent. - * - * So we could return a unwritten and delayed extent, and - * its block is equal to 'next'. - */ - if (next == next_del && next == EXT_MAX_BLOCKS) { - flags |= FIEMAP_EXTENT_LAST; - if (unlikely(next_del != EXT_MAX_BLOCKS || - next != EXT_MAX_BLOCKS)) { - EXT4_ERROR_INODE(inode, - "next extent == %u, next " - "delalloc extent = %u", - next, next_del); - err = -EFSCORRUPTED; - break; - } - } - - if (exists) { - err = fiemap_fill_next_extent(fieinfo, - (__u64)es.es_lblk << blksize_bits, - (__u64)es.es_pblk << blksize_bits, - (__u64)es.es_len << blksize_bits, - flags); - if (err < 0) - break; - if (err == 1) { - err = 0; - break; - } - } - - block = es.es_lblk + es.es_len; - } - - ext4_ext_drop_refs(path); - kfree(path); - return err; -} - static int ext4_fill_es_cache_info(struct inode *inode, ext4_lblk_t block, ext4_lblk_t num, struct fiemap_extent_info *fieinfo) @@ -4927,64 +4776,13 @@ int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end) return ret < 0 ? ret : err; } -/* - * If newes is not existing extent (newes->ec_pblk equals zero) find - * delayed extent at start of newes and update newes accordingly and - * return start of the next delayed extent. - * - * If newes is existing extent (newes->ec_pblk is not equal zero) - * return start of next delayed extent or EXT_MAX_BLOCKS if no delayed - * extent found. Leave newes unmodified. - */ -static int ext4_find_delayed_extent(struct inode *inode, - struct extent_status *newes) -{ - struct extent_status es; - ext4_lblk_t block, next_del; - - if (newes->es_pblk == 0) { - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, - newes->es_lblk, - newes->es_lblk + newes->es_len - 1, - &es); - - /* - * No extent in extent-tree contains block @newes->es_pblk, - * then the block may stay in 1)a hole or 2)delayed-extent. - */ - if (es.es_len == 0) - /* A hole found. */ - return 0; - - if (es.es_lblk > newes->es_lblk) { - /* A hole found. */ - newes->es_len = min(es.es_lblk - newes->es_lblk, - newes->es_len); - return 0; - } - - newes->es_len = es.es_lblk + es.es_len - newes->es_lblk; - } - - block = newes->es_lblk + newes->es_len; - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, block, - EXT_MAX_BLOCKS, &es); - if (es.es_len == 0) - next_del = EXT_MAX_BLOCKS; - else - next_del = es.es_lblk; - - return next_del; -} - -static int ext4_xattr_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo) +static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap) { __u64 physical = 0; - __u64 length; - __u32 flags = FIEMAP_EXTENT_LAST; + __u64 length = 0; int blockbits = inode->i_sb->s_blocksize_bits; int error = 0; + u16 iomap_type; /* in-inode? */ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { @@ -4999,41 +4797,50 @@ static int ext4_xattr_fiemap(struct inode *inode, EXT4_I(inode)->i_extra_isize; physical += offset; length = EXT4_SB(inode->i_sb)->s_inode_size - offset; - flags |= FIEMAP_EXTENT_DATA_INLINE; brelse(iloc.bh); - } else { /* external block */ + iomap_type = IOMAP_INLINE; + } else if (EXT4_I(inode)->i_file_acl) { /* external block */ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits; length = inode->i_sb->s_blocksize; + iomap_type = IOMAP_MAPPED; + } else { + /* no in-inode or external block for xattr, so return -ENOENT */ + error = -ENOENT; + goto out; } - if (physical) - error = fiemap_fill_next_extent(fieinfo, 0, physical, - length, flags); - return (error < 0 ? error : 0); + iomap->addr = physical; + iomap->offset = 0; + iomap->length = length; + iomap->type = iomap_type; + iomap->flags = 0; +out: + return error; } -static int _ext4_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len, - int (*fill)(struct inode *, ext4_lblk_t, - ext4_lblk_t, - struct fiemap_extent_info *)) +static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset, + loff_t length, unsigned flags, + struct iomap *iomap, struct iomap *srcmap) +{ + int error; + + error = ext4_iomap_xattr_fiemap(inode, iomap); + if (error == 0 && (offset >= iomap->length)) + error = -ENOENT; + return error; +} + +static const struct iomap_ops ext4_iomap_xattr_ops = { + .iomap_begin = ext4_iomap_xattr_begin, +}; + +static int _ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len, bool from_es_cache) { ext4_lblk_t start_blk; - u32 ext4_fiemap_flags = FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR; - + u32 ext4_fiemap_flags = FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR; int error = 0; - if (ext4_has_inline_data(inode)) { - int has_inline = 1; - - error = ext4_inline_data_fiemap(inode, fieinfo, &has_inline, - start, len); - - if (has_inline) - return error; - } - if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) @@ -5041,19 +4848,19 @@ static int _ext4_fiemap(struct inode *inode, fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } - /* fallback to generic here if not in extents fmt */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) && - fill == ext4_fill_fiemap_extents) - return generic_block_fiemap(inode, fieinfo, start, len, - ext4_get_block); - - if (fill == ext4_fill_es_cache_info) + if (from_es_cache) ext4_fiemap_flags &= FIEMAP_FLAG_XATTR; + if (fiemap_check_flags(fieinfo, ext4_fiemap_flags)) return -EBADR; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { - error = ext4_xattr_fiemap(inode, fieinfo); + fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; + error = iomap_fiemap(inode, fieinfo, start, len, + &ext4_iomap_xattr_ops); + } else if (!from_es_cache) { + error = iomap_fiemap(inode, fieinfo, start, len, + &ext4_iomap_report_ops); } else { ext4_lblk_t len_blks; __u64 last_blk; @@ -5068,7 +4875,8 @@ static int _ext4_fiemap(struct inode *inode, * Walk the extent tree gathering extent information * and pushing extents back to the user. */ - error = fill(inode, start_blk, len_blks, fieinfo); + error = ext4_fill_es_cache_info(inode, start_blk, len_blks, + fieinfo); } return error; } @@ -5076,8 +4884,7 @@ static int _ext4_fiemap(struct inode *inode, int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { - return _ext4_fiemap(inode, fieinfo, start, len, - ext4_fill_fiemap_extents); + return _ext4_fiemap(inode, fieinfo, start, len, false); } int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, @@ -5093,8 +4900,7 @@ int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, return 0; } - return _ext4_fiemap(inode, fieinfo, start, len, - ext4_fill_es_cache_info); + return _ext4_fiemap(inode, fieinfo, start, len, true); } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index fad82d08fca5..e7db6ee23277 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1857,47 +1857,6 @@ out: return error; } -int ext4_inline_data_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, - int *has_inline, __u64 start, __u64 len) -{ - __u64 physical = 0; - __u64 inline_len; - __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED | - FIEMAP_EXTENT_LAST; - int error = 0; - struct ext4_iloc iloc; - - down_read(&EXT4_I(inode)->xattr_sem); - if (!ext4_has_inline_data(inode)) { - *has_inline = 0; - goto out; - } - inline_len = min_t(size_t, ext4_get_inline_size(inode), - i_size_read(inode)); - if (start >= inline_len) - goto out; - if (start + len < inline_len) - inline_len = start + len; - inline_len -= start; - - error = ext4_get_inode_loc(inode, &iloc); - if (error) - goto out; - - physical = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits; - physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; - physical += offsetof(struct ext4_inode, i_block); - - brelse(iloc.bh); -out: - up_read(&EXT4_I(inode)->xattr_sem); - if (physical) - error = fiemap_fill_next_extent(fieinfo, start, physical, - inline_len, flags); - return (error < 0 ? error : 0); -} - int ext4_inline_data_truncate(struct inode *inode, int *has_inline) { handle_t *handle; From 7af44c42df37094fd95897653fdaaa7b76c0539a Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 28 Feb 2020 14:56:59 +0530 Subject: [PATCH 17/31] Documentation: correct the description of FIEMAP_EXTENT_LAST Currently FIEMAP_EXTENT_LAST is not working consistently across different filesystem's fiemap implementations. So add more information about how else this flag could set in other implementation. Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/5a00e8d4283d6849e0b8f408c8365b31fbc1d153.1582880246.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- Documentation/filesystems/fiemap.txt | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt index f6d9c99103a4..ac87e6fda842 100644 --- a/Documentation/filesystems/fiemap.txt +++ b/Documentation/filesystems/fiemap.txt @@ -115,8 +115,10 @@ data. Note that the opposite is not true - it would be valid for FIEMAP_EXTENT_NOT_ALIGNED to appear alone. * FIEMAP_EXTENT_LAST -This is the last extent in the file. A mapping attempt past this -extent will return nothing. +This is generally the last extent in the file. A mapping attempt past +this extent may return nothing. Some implementations set this flag to +indicate this extent is the last one in the range queried by the user +(via fiemap->fm_length). * FIEMAP_EXTENT_UNKNOWN The location of this extent is currently unknown. This may indicate From e32ac2459cdac01f9b177eed526a3ffa1797039d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 9 Mar 2020 10:48:38 -0500 Subject: [PATCH 18/31] ext4: use flexible-array member in struct fname The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200309154838.GA31559@embeddedor Signed-off-by: Theodore Ts'o --- fs/ext4/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 9aa1f75409b0..c654205f648d 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -392,7 +392,7 @@ struct fname { __u32 inode; __u8 name_len; __u8 file_type; - char name[0]; + char name[]; }; /* From 47b1030612f4382a976be6aa2369cf5d973ca154 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 9 Mar 2020 13:08:13 -0500 Subject: [PATCH 19/31] ext4: use flexible-array member for xattr structs The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200309180813.GA3347@embeddedor Signed-off-by: Theodore Ts'o --- fs/ext4/xattr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index f39cad2abe2a..ffe21ac77f78 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -48,7 +48,7 @@ struct ext4_xattr_entry { __le32 e_value_inum; /* inode in which the value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ - char e_name[0]; /* attribute name */ + char e_name[]; /* attribute name */ }; #define EXT4_XATTR_PAD_BITS 2 @@ -118,7 +118,7 @@ struct ext4_xattr_ibody_find { struct ext4_xattr_inode_array { unsigned int count; /* # of used items in the array */ - struct inode *inodes[0]; + struct inode *inodes[]; }; extern const struct xattr_handler ext4_xattr_user_handler; From eb5760863fc28feab28b567ddcda7e667e638da0 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Tue, 10 Mar 2020 15:01:56 +0000 Subject: [PATCH 20/31] ext4: mark block bitmap corrupted when found instead of BUGON We already has similar code in ext4_mb_complex_scan_group(), but ext4_mb_simple_scan_group() still affected. Other reports: https://www.spinics.net/lists/linux-ext4/msg60231.html Reviewed-by: Andreas Dilger Signed-off-by: Dmitry Monakhov Link: https://lore.kernel.org/r/20200310150156.641-1-dmonakhov@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1027e01c9011..97cd1a2201a2 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1901,8 +1901,15 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, BUG_ON(buddy == NULL); k = mb_find_next_zero_bit(buddy, max, 0); - BUG_ON(k >= max); - + if (k >= max) { + ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, + "%d free clusters of order %d. But found 0", + grp->bb_counters[i], i); + ext4_mark_group_bitmap_corrupted(ac->ac_sb, + e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + break; + } ac->ac_found++; ac->ac_b_ex.fe_len = 1 << i; From 34990461342fc9aba806bd941653b72c89dd73a2 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Wed, 11 Mar 2020 16:50:33 -0400 Subject: [PATCH 21/31] ext4: clean up ext4_ext_insert_extent() call in ext4_ext_map_blocks() Now that the eofblocks code has been removed, we don't need to assign 0 to err before calling ext4_ext_insert_extent() since it will assign a return value to ret anyway. The variable free_on_err can be eliminated and replaced by a reference to allocated_clusters which clearly conveys the idea that newly allocated blocks should be freed when recovering from an extent insertion failure. The error handling code itself should be restructured so that it errors out immediately on an insertion failure in the case where no new blocks have been allocated (bigalloc) rather than proceeding further into the mapping code. The initializer for fb_flags can also be rearranged for improved readability. Finally, insert a missing space in nearby code. No known bugs are addressed by this patch - it's simply a cleanup. Reviewed-by: Ritesh Harjani Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20200311205033.25013-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5b2cac0208fe..a1342caad01d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4028,7 +4028,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_extent newex, *ex, *ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0; - int free_on_err = 0, err = 0, depth, ret; + int err = 0, depth, ret; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; @@ -4226,7 +4226,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, goto out2; ext_debug("allocate new block: goal %llu, found %llu/%u\n", ar.goal, newblock, allocated); - free_on_err = 1; allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; if (ar.len > allocated) @@ -4237,23 +4236,28 @@ got_allocated_blocks: ext4_ext_store_pblock(&newex, newblock + offset); newex.ee_len = cpu_to_le16(ar.len); /* Mark unwritten */ - if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){ + if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { ext4_ext_mark_unwritten(&newex); map->m_flags |= EXT4_MAP_UNWRITTEN; } - err = 0; err = ext4_ext_insert_extent(handle, inode, &path, &newex, flags); + if (err) { + if (allocated_clusters) { + int fb_flags = 0; - if (err && free_on_err) { - int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ? - EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0; - /* free data blocks we just allocated */ - /* not a good idea to call discard here directly, - * but otherwise we'd need to call it every free() */ - ext4_discard_preallocations(inode); - ext4_free_blocks(handle, inode, NULL, newblock, - EXT4_C2B(sbi, allocated_clusters), fb_flags); + /* + * free data blocks we just allocated. + * not a good idea to call discard here directly, + * but otherwise we'd need to call it every free(). + */ + ext4_discard_preallocations(inode); + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; + ext4_free_blocks(handle, inode, NULL, newblock, + EXT4_C2B(sbi, allocated_clusters), + fb_flags); + } goto out2; } From 2971148d0fecedcbd594ff2f2784496bdc7a7ffa Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Wed, 11 Mar 2020 16:51:25 -0400 Subject: [PATCH 22/31] ext4: remove map_from_cluster from ext4_ext_map_blocks We can use the variable allocated_clusters rather than map_from_clusters to control reserved block/cluster accounting in ext4_ext_map_blocks. This eliminates a variable and associated code and improves readability a little. Reviewed-by: Ritesh Harjani Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20200311205125.25061-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index a1342caad01d..0e86bc611f07 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4033,7 +4033,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; ext4_lblk_t cluster_offset; - bool map_from_cluster = false; ext_debug("blocks %u/%u requested for inode %lu\n", map->m_lblk, map->m_len, inode->i_ino); @@ -4148,7 +4147,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; - map_from_cluster = true; goto got_allocated_blocks; } @@ -4169,7 +4167,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; - map_from_cluster = true; goto got_allocated_blocks; } @@ -4274,7 +4271,7 @@ got_allocated_blocks: * clusters discovered to be delayed allocated. Once allocated, a * cluster is not included in the reserved count. */ - if (test_opt(inode->i_sb, DELALLOC) && !map_from_cluster) { + if (test_opt(inode->i_sb, DELALLOC) && allocated_clusters) { if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { /* * When allocating delayed allocated clusters, simply From f1eec3b0d0a849996ebee733b053efa71803dad5 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Mon, 16 Mar 2020 15:00:38 +0530 Subject: [PATCH 23/31] ext4: check for non-zero journal inum in ext4_calculate_overhead While calculating overhead for internal journal, also check that j_inum shouldn't be 0. Otherwise we get below error with xfstests generic/050 with external journal (XXX_LOGDEV config) enabled. It could be simply reproduced with loop device with an external journal and marking blockdev as RO before mounting. [ 3337.146838] EXT4-fs error (device pmem1p2): ext4_get_journal_inode:4634: comm mount: inode #0: comm mount: iget: illegal inode # ------------[ cut here ]------------ generic_make_request: Trying to write to read-only block-device pmem1p2 (partno 2) WARNING: CPU: 107 PID: 115347 at block/blk-core.c:788 generic_make_request_checks+0x6b4/0x7d0 CPU: 107 PID: 115347 Comm: mount Tainted: G L --------- -t - 4.18.0-167.el8.ppc64le #1 NIP: c0000000006f6d44 LR: c0000000006f6d40 CTR: 0000000030041dd4 <...> NIP [c0000000006f6d44] generic_make_request_checks+0x6b4/0x7d0 LR [c0000000006f6d40] generic_make_request_checks+0x6b0/0x7d0 <...> Call Trace: generic_make_request_checks+0x6b0/0x7d0 (unreliable) generic_make_request+0x3c/0x420 submit_bio+0xd8/0x200 submit_bh_wbc+0x1e8/0x250 __sync_dirty_buffer+0xd0/0x210 ext4_commit_super+0x310/0x420 [ext4] __ext4_error+0xa4/0x1e0 [ext4] __ext4_iget+0x388/0xe10 [ext4] ext4_get_journal_inode+0x40/0x150 [ext4] ext4_calculate_overhead+0x5a8/0x610 [ext4] ext4_fill_super+0x3188/0x3260 [ext4] mount_bdev+0x778/0x8f0 ext4_mount+0x28/0x50 [ext4] mount_fs+0x74/0x230 vfs_kern_mount.part.6+0x6c/0x250 do_mount+0x2fc/0x1280 sys_mount+0x158/0x180 system_call+0x5c/0x70 EXT4-fs (pmem1p2): no journal found EXT4-fs (pmem1p2): can't get journal size EXT4-fs (pmem1p2): mounted filesystem without journal. Opts: dax,norecovery Fixes: 3c816ded78bb ("ext4: use journal inode to determine journal overhead") Reported-by: Harish Sriram Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20200316093038.25485-1-riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index de5398c07161..5dc65b7583cb 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3609,7 +3609,8 @@ int ext4_calculate_overhead(struct super_block *sb) */ if (sbi->s_journal && !sbi->journal_bdev) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen); - else if (ext4_has_feature_journal(sb) && !sbi->s_journal) { + else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { + /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); if (j_inode) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits; From 5e47868fb94b63c7068dcfd2469d99fba06bae9d Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 18 Mar 2020 11:43:01 +0530 Subject: [PATCH 24/31] ext4: unregister sysfs path before destroying jbd2 journal Call ext4_unregister_sysfs(), before destroying jbd2 journal, since below might cause, NULL pointer dereference issue. This got reported with LTP tests. ext4_put_super() cat /sys/fs/ext4/loop2/journal_task | ext4_attr_show(); ext4_jbd2_journal_destroy(); | | journal_task_show() | | | task_pid_vnr(NULL); sbi->s_journal = NULL; Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20200318061301.4320-1-riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5dc65b7583cb..27ab130a40d1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1024,6 +1024,13 @@ static void ext4_put_super(struct super_block *sb) destroy_workqueue(sbi->rsv_conversion_wq); + /* + * Unregister sysfs before destroying jbd2 journal. + * Since we could still access attr_journal_task attribute via sysfs + * path which could have sbi->s_journal->j_task as NULL + */ + ext4_unregister_sysfs(sb); + if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); @@ -1034,7 +1041,6 @@ static void ext4_put_super(struct super_block *sb) } } - ext4_unregister_sysfs(sb); ext4_es_unregister_shrinker(sbi); del_timer_sync(&sbi->s_err_report); ext4_release_system_zone(sb); From d05466b27b19af8e148376590ed54d289b607f0a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 18 Mar 2020 13:13:17 +0100 Subject: [PATCH 25/31] ext4: avoid ENOSPC when avoiding to reuse recently deleted inodes When ext4 is running on a filesystem without a journal, it tries not to reuse recently deleted inodes to provide better chances for filesystem recovery in case of crash. However this logic forbids reuse of freed inodes for up to 5 minutes and especially for filesystems with smaller number of inodes can lead to ENOSPC errors returned when allocating new inodes. Fix the problem by allowing to reuse recently deleted inode if there's no other inode free in the scanned range. Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20200318121317.31941-1-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/ext4/ialloc.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f95ee99091e4..9652a0eadd1c 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -712,21 +712,34 @@ out: static int find_inode_bit(struct super_block *sb, ext4_group_t group, struct buffer_head *bitmap, unsigned long *ino) { + bool check_recently_deleted = EXT4_SB(sb)->s_journal == NULL; + unsigned long recently_deleted_ino = EXT4_INODES_PER_GROUP(sb); + next: *ino = ext4_find_next_zero_bit((unsigned long *) bitmap->b_data, EXT4_INODES_PER_GROUP(sb), *ino); if (*ino >= EXT4_INODES_PER_GROUP(sb)) - return 0; + goto not_found; - if ((EXT4_SB(sb)->s_journal == NULL) && - recently_deleted(sb, group, *ino)) { + if (check_recently_deleted && recently_deleted(sb, group, *ino)) { + recently_deleted_ino = *ino; *ino = *ino + 1; if (*ino < EXT4_INODES_PER_GROUP(sb)) goto next; - return 0; + goto not_found; } - + return 1; +not_found: + if (recently_deleted_ino >= EXT4_INODES_PER_GROUP(sb)) + return 0; + /* + * Not reusing recently deleted inodes is mostly a preference. We don't + * want to report ENOSPC or skew allocation patterns because of that. + * So return even recently deleted inode if we could find better in the + * given range. + */ + *ino = recently_deleted_ino; return 1; } From c96e2b8564adfb8ac14469ebc51ddc1bfecb3ae2 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 18 Mar 2020 14:19:38 -0500 Subject: [PATCH 26/31] ext4: do not commit super on read-only bdev Under some circumstances we may encounter a filesystem error on a read-only block device, and if we try to save the error info to the superblock and commit it, we'll wind up with a noisy error and backtrace, i.e.: [ 3337.146838] EXT4-fs error (device pmem1p2): ext4_get_journal_inode:4634: comm mount: inode #0: comm mount: iget: illegal inode # ------------[ cut here ]------------ generic_make_request: Trying to write to read-only block-device pmem1p2 (partno 2) WARNING: CPU: 107 PID: 115347 at block/blk-core.c:788 generic_make_request_checks+0x6b4/0x7d0 ... To avoid this, commit the error info in the superblock only if the block device is writable. Reported-by: Ritesh Harjani Signed-off-by: Eric Sandeen Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/4b6e774d-cc00-3469-7abb-108eb151071a@sandeen.net Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 27ab130a40d1..4d460747cca7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -372,7 +372,8 @@ static void save_error_info(struct super_block *sb, const char *func, unsigned int line) { __save_error_info(sb, func, line); - ext4_commit_super(sb, 1); + if (!bdev_read_only(sb->s_bdev)) + ext4_commit_super(sb, 1); } /* From c8980e1980ccdc2229aa2218d532ddc62e0aabe5 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Thu, 19 Mar 2020 11:00:28 -0400 Subject: [PATCH 27/31] ext4: disable dioread_nolock whenever delayed allocation is disabled The patch "ext4: make dioread_nolock the default" (244adf6426ee) causes generic/422 to fail when run in kvm-xfstests' ext3conv test case. This applies both the dioread_nolock and nodelalloc mount options, a combination not previously tested by kvm-xfstests. The failure occurs because the dioread_nolock code path splits a previously fallocated multiblock extent into a series of single block extents when overwriting a portion of that extent. That causes allocation of an extent tree leaf node and a reshuffling of extents. Once writeback is completed, the individual extents are recombined into a single extent, the extent is moved again, and the leaf node is deleted. The difference in block utilization before and after writeback due to the leaf node triggers the failure. The original reason for this behavior was to avoid ENOSPC when handling I/O completions during writeback in the dioread_nolock code paths when delayed allocation is disabled. It may no longer be necessary, because code was added in the past to reserve extra space to solve this problem when delayed allocation is enabled, and this code may also apply when delayed allocation is disabled. Until this can be verified, don't use the dioread_nolock code paths if delayed allocation is disabled. Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20200319150028.24592-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4_jbd2.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 7ea4f6fa173b..4b9002f0e84c 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -512,6 +512,9 @@ static inline int ext4_should_dioread_nolock(struct inode *inode) return 0; if (ext4_should_journal_data(inode)) return 0; + /* temporary fix to prevent generic/422 test failures */ + if (!test_opt(inode->i_sb, DELALLOC)) + return 0; return 1; } From 626b035b816b61a7a7b4d2205a6807e2f11a18c1 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 28 Mar 2020 01:37:44 +0530 Subject: [PATCH 28/31] ext4: don't set dioread_nolock by default for blocksize < pagesize Currently on calling echo 3 > drop_caches on host machine, we see FS corruption in the guest. This happens on Power machine where blocksize < pagesize. So as a temporary workaound don't enable dioread_nolock by default for blocksize < pagesize until we identify the root cause. Also emit a warning msg in case if this mount option is manually enabled for blocksize < pagesize. Reported-by: Aneesh Kumar K.V Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/20200327200744.12473-1-riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4d460747cca7..c5639c0ba2c5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2187,6 +2187,14 @@ static int parse_options(char *options, struct super_block *sb, } } #endif + if (test_opt(sb, DIOREAD_NOLOCK)) { + int blocksize = + BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); + if (blocksize < PAGE_SIZE) + ext4_msg(sb, KERN_WARNING, "Warning: mounting with an " + "experimental mount option 'dioread_nolock' " + "for blocksize < PAGE_SIZE"); + } return 1; } @@ -3793,7 +3801,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) set_opt(sb, NO_UID32); /* xattr user namespace & acls are now defaulted on */ set_opt(sb, XATTR_USER); - set_opt(sb, DIOREAD_NOLOCK); #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif @@ -3843,6 +3850,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + + if (blocksize == PAGE_SIZE) + set_opt(sb, DIOREAD_NOLOCK); + if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { ext4_msg(sb, KERN_ERR, From b9c538da4e52a7b79dfcf4cfa487c46125066dfb Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Sat, 28 Mar 2020 15:34:15 -0700 Subject: [PATCH 29/31] ext4: fix incorrect inodes per group in error message If ext4_fill_super detects an invalid number of inodes per group, the resulting error message printed the number of blocks per group, rather than the number of inodes per group. Fix it to print the correct value. Fixes: cd6bb35bf7f6d ("ext4: use more strict checks for inodes_per_block on mount") Link: https://lore.kernel.org/r/8be03355983a08e5d4eed480944613454d7e2550.1585434649.git.josh@joshtriplett.org Reviewed-by: Andreas Dilger Signed-off-by: Josh Triplett Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c5639c0ba2c5..2837f27947f9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4176,7 +4176,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > blocksize * 8) { ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", - sbi->s_blocks_per_group); + sbi->s_inodes_per_group); goto failed_mount; } sbi->s_itb_per_group = sbi->s_inodes_per_group / From df41460a21b06a76437af040d90ccee03888e8e5 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Sat, 28 Mar 2020 14:54:01 -0700 Subject: [PATCH 30/31] ext4: fix incorrect group count in ext4_fill_super error message ext4_fill_super doublechecks the number of groups before mounting; if that check fails, the resulting error message prints the group count from the ext4_sb_info sbi, which hasn't been set yet. Print the freshly computed group count instead (which at that point has just been computed in "blocks_count"). Signed-off-by: Josh Triplett Fixes: 4ec1102813798 ("ext4: Add sanity checks for the superblock before mounting the filesystem") Link: https://lore.kernel.org/r/8b957cd1513fcc4550fe675c10bcce2175c33a49.1585431964.git.josh@joshtriplett.org Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2837f27947f9..0153ae330c86 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4305,9 +4305,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { - ext4_msg(sb, KERN_WARNING, "groups count too large: %u " + ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " "(block count %llu, first data block %u, " - "blocks per group %lu)", sbi->s_groups_count, + "blocks per group %lu)", blocks_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); From 54d3adbc29f0c7c53890da1683e629cd220d7201 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 28 Mar 2020 19:33:43 -0400 Subject: [PATCH 31/31] ext4: save all error info in save_error_info() and drop ext4_set_errno() Using a separate function, ext4_set_errno() to set the errno is problematic because it doesn't do the right thing once s_last_error_errorcode is non-zero. It's also less racy to set all of the error information all at once. (Also, as a bonus, it shrinks code size slightly.) Link: https://lore.kernel.org/r/20200329020404.686965-1-tytso@mit.edu Fixes: 878520ac45f9 ("ext4: save the error code which triggered...") Signed-off-by: Theodore Ts'o --- fs/ext4/balloc.c | 7 +- fs/ext4/block_validity.c | 18 ++--- fs/ext4/ext4.h | 54 ++++++++----- fs/ext4/ext4_jbd2.c | 13 +-- fs/ext4/extents.c | 27 +++---- fs/ext4/ialloc.c | 13 ++- fs/ext4/indirect.c | 2 +- fs/ext4/inline.c | 13 ++- fs/ext4/inode.c | 29 +++---- fs/ext4/mballoc.c | 21 +++-- fs/ext4/mmp.c | 13 ++- fs/ext4/move_extent.c | 4 +- fs/ext4/namei.c | 24 +++--- fs/ext4/super.c | 166 ++++++++++++++++++--------------------- fs/ext4/xattr.c | 10 +-- 15 files changed, 199 insertions(+), 215 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 8fd0b3cdab4c..0e0a4d6209c7 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -516,10 +516,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, wait_on_buffer(bh); ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO); if (!buffer_uptodate(bh)) { - ext4_set_errno(sb, EIO); - ext4_error(sb, "Cannot read block bitmap - " - "block_group = %u, block_bitmap = %llu", - block_group, (unsigned long long) bh->b_blocknr); + ext4_error_err(sb, EIO, "Cannot read block bitmap - " + "block_group = %u, block_bitmap = %llu", + block_group, (unsigned long long) bh->b_blocknr); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EIO; diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 0a734ffb4310..16e9b2fda03a 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -166,10 +166,8 @@ static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || (start_blk + count < start_blk) || - (start_blk + count > ext4_blocks_count(sbi->s_es))) { - sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); + (start_blk + count > ext4_blocks_count(sbi->s_es))) return 0; - } if (system_blks == NULL) return 1; @@ -181,10 +179,8 @@ static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, n = n->rb_left; else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; - else { - sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); + else return 0; - } } return 1; } @@ -220,10 +216,12 @@ static int ext4_protect_reserved_inode(struct super_block *sb, } else { if (!ext4_data_block_valid_rcu(sbi, system_blks, map.m_pblk, n)) { - ext4_error(sb, "blocks %llu-%llu from inode %u " - "overlap system zone", map.m_pblk, - map.m_pblk + map.m_len - 1, ino); err = -EFSCORRUPTED; + __ext4_error(sb, __func__, __LINE__, -err, + map.m_pblk, "blocks %llu-%llu " + "from inode %u overlap system zone", + map.m_pblk, + map.m_pblk + map.m_len - 1, ino); break; } err = add_system_zone(system_blks, map.m_pblk, n); @@ -365,7 +363,6 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, int ext4_check_blockref(const char *function, unsigned int line, struct inode *inode, __le32 *p, unsigned int max) { - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; __le32 *bref = p; unsigned int blk; @@ -379,7 +376,6 @@ int ext4_check_blockref(const char *function, unsigned int line, if (blk && unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), blk, 1))) { - es->s_last_error_block = cpu_to_le64(blk); ext4_error_inode(inode, function, line, blk, "invalid block"); return -EFSCORRUPTED; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 54f0a003053b..91eb4381cae5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2770,21 +2770,20 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno, extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); -extern void ext4_set_errno(struct super_block *sb, int err); -extern __printf(4, 5) -void __ext4_error(struct super_block *, const char *, unsigned int, +extern __printf(6, 7) +void __ext4_error(struct super_block *, const char *, unsigned int, int, __u64, const char *, ...); -extern __printf(5, 6) -void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t, - const char *, ...); +extern __printf(6, 7) +void __ext4_error_inode(struct inode *, const char *, unsigned int, + ext4_fsblk_t, int, const char *, ...); extern __printf(5, 6) void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t, const char *, ...); extern void __ext4_std_error(struct super_block *, const char *, unsigned int, int); -extern __printf(4, 5) -void __ext4_abort(struct super_block *, const char *, unsigned int, +extern __printf(5, 6) +void __ext4_abort(struct super_block *, const char *, unsigned int, int, const char *, ...); extern __printf(4, 5) void __ext4_warning(struct super_block *, const char *, unsigned int, @@ -2805,8 +2804,12 @@ void __ext4_grp_locked_error(const char *, unsigned int, #define EXT4_ERROR_INODE(inode, fmt, a...) \ ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a) -#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...) \ - ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a) +#define EXT4_ERROR_INODE_ERR(inode, err, fmt, a...) \ + __ext4_error_inode((inode), __func__, __LINE__, 0, (err), (fmt), ## a) + +#define ext4_error_inode_block(inode, block, err, fmt, a...) \ + __ext4_error_inode((inode), __func__, __LINE__, (block), (err), \ + (fmt), ## a) #define EXT4_ERROR_FILE(file, block, fmt, a...) \ ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a) @@ -2814,13 +2817,18 @@ void __ext4_grp_locked_error(const char *, unsigned int, #ifdef CONFIG_PRINTK #define ext4_error_inode(inode, func, line, block, fmt, ...) \ - __ext4_error_inode(inode, func, line, block, fmt, ##__VA_ARGS__) + __ext4_error_inode(inode, func, line, block, 0, fmt, ##__VA_ARGS__) +#define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \ + __ext4_error_inode((inode), (func), (line), (block), \ + (err), (fmt), ##__VA_ARGS__) #define ext4_error_file(file, func, line, block, fmt, ...) \ __ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__) #define ext4_error(sb, fmt, ...) \ - __ext4_error(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) -#define ext4_abort(sb, fmt, ...) \ - __ext4_abort(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) + __ext4_error((sb), __func__, __LINE__, 0, 0, (fmt), ##__VA_ARGS__) +#define ext4_error_err(sb, err, fmt, ...) \ + __ext4_error((sb), __func__, __LINE__, (err), 0, (fmt), ##__VA_ARGS__) +#define ext4_abort(sb, err, fmt, ...) \ + __ext4_abort((sb), __func__, __LINE__, (err), (fmt), ##__VA_ARGS__) #define ext4_warning(sb, fmt, ...) \ __ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) #define ext4_warning_inode(inode, fmt, ...) \ @@ -2838,7 +2846,12 @@ void __ext4_grp_locked_error(const char *, unsigned int, #define ext4_error_inode(inode, func, line, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error_inode(inode, "", 0, block, " "); \ + __ext4_error_inode(inode, "", 0, block, 0, " "); \ +} while (0) +#define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \ +do { \ + no_printk(fmt, ##__VA_ARGS__); \ + __ext4_error_inode(inode, "", 0, block, err, " "); \ } while (0) #define ext4_error_file(file, func, line, block, fmt, ...) \ do { \ @@ -2848,12 +2861,17 @@ do { \ #define ext4_error(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error(sb, "", 0, " "); \ + __ext4_error(sb, "", 0, 0, 0, " "); \ } while (0) -#define ext4_abort(sb, fmt, ...) \ +#define ext4_error_err(sb, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_abort(sb, "", 0, " "); \ + __ext4_error(sb, "", 0, err, 0, " "); \ +} while (0) +#define ext4_abort(sb, err, fmt, ...) \ +do { \ + no_printk(fmt, ##__VA_ARGS__); \ + __ext4_abort(sb, "", 0, err, " "); \ } while (0) #define ext4_warning(sb, fmt, ...) \ do { \ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index ee3755c3110a..7f16e1af8d5c 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -80,8 +80,7 @@ static int ext4_journal_check_start(struct super_block *sb) * take the FS itself readonly cleanly. */ if (journal && is_journal_aborted(journal)) { - ext4_set_errno(sb, -journal->j_errno); - ext4_abort(sb, "Detected aborted journal"); + ext4_abort(sb, -journal->j_errno, "Detected aborted journal"); return -EROFS; } return 0; @@ -272,8 +271,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); - ext4_set_errno(inode->i_sb, -err); - __ext4_abort(inode->i_sb, where, line, + __ext4_abort(inode->i_sb, where, line, -err, "error %d when attempting revoke", err); } BUFFER_TRACE(bh, "exit"); @@ -343,11 +341,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, struct ext4_super_block *es; es = EXT4_SB(inode->i_sb)->s_es; - es->s_last_error_block = - cpu_to_le64(bh->b_blocknr); - ext4_set_errno(inode->i_sb, EIO); - ext4_error_inode(inode, where, line, - bh->b_blocknr, + ext4_error_inode_err(inode, where, line, + bh->b_blocknr, EIO, "IO error syncing itable block"); err = -EIO; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0e86bc611f07..031752cfb6f7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -349,8 +349,8 @@ static int ext4_valid_extent_idx(struct inode *inode, } static int ext4_valid_extent_entries(struct inode *inode, - struct ext4_extent_header *eh, - int depth) + struct ext4_extent_header *eh, + ext4_fsblk_t *pblk, int depth) { unsigned short entries; if (eh->eh_entries == 0) @@ -361,8 +361,6 @@ static int ext4_valid_extent_entries(struct inode *inode, if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; - ext4_fsblk_t pblock = 0; ext4_lblk_t lblock = 0; ext4_lblk_t prev = 0; int len = 0; @@ -374,8 +372,7 @@ static int ext4_valid_extent_entries(struct inode *inode, lblock = le32_to_cpu(ext->ee_block); len = ext4_ext_get_actual_len(ext); if ((lblock <= prev) && prev) { - pblock = ext4_ext_pblock(ext); - es->s_last_error_block = cpu_to_le64(pblock); + *pblk = ext4_ext_pblock(ext); return 0; } ext++; @@ -422,7 +419,7 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } - if (!ext4_valid_extent_entries(inode, eh, depth)) { + if (!ext4_valid_extent_entries(inode, eh, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } @@ -440,14 +437,14 @@ static int __ext4_ext_check(const char *function, unsigned int line, return 0; corrupted: - ext4_set_errno(inode->i_sb, -err); - ext4_error_inode(inode, function, line, 0, - "pblk %llu bad header/extent: %s - magic %x, " - "entries %u, max %u(%u), depth %u(%u)", - (unsigned long long) pblk, error_msg, - le16_to_cpu(eh->eh_magic), - le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), - max, le16_to_cpu(eh->eh_depth), depth); + ext4_error_inode_err(inode, function, line, 0, -err, + "pblk %llu bad header/extent: %s - magic %x, " + "entries %u, max %u(%u), depth %u(%u)", + (unsigned long long) pblk, error_msg, + le16_to_cpu(eh->eh_magic), + le16_to_cpu(eh->eh_entries), + le16_to_cpu(eh->eh_max), + max, le16_to_cpu(eh->eh_depth), depth); return err; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 9652a0eadd1c..b420c9dc444d 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -196,10 +196,9 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO); if (!buffer_uptodate(bh)) { put_bh(bh); - ext4_set_errno(sb, EIO); - ext4_error(sb, "Cannot read inode bitmap - " - "block_group = %u, inode_bitmap = %llu", - block_group, bitmap_blk); + ext4_error_err(sb, EIO, "Cannot read inode bitmap - " + "block_group = %u, inode_bitmap = %llu", + block_group, bitmap_blk); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); return ERR_PTR(-EIO); @@ -1244,9 +1243,9 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); - ext4_set_errno(sb, -err); - ext4_error(sb, "couldn't read orphan inode %lu (err %d)", - ino, err); + ext4_error_err(sb, -err, + "couldn't read orphan inode %lu (err %d)", + ino, err); return inode; } diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 569fc68e8975..107f0043f67f 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -1019,7 +1019,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, * (should be rare). */ if (!bh) { - EXT4_ERROR_INODE_BLOCK(inode, nr, + ext4_error_inode_block(inode, nr, EIO, "Read failure"); continue; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index e7db6ee23277..f35e289e17aa 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -98,10 +98,9 @@ int ext4_get_max_inline_size(struct inode *inode) error = ext4_get_inode_loc(inode, &iloc); if (error) { - ext4_set_errno(inode->i_sb, -error); - ext4_error_inode(inode, __func__, __LINE__, 0, - "can't get inode location %lu", - inode->i_ino); + ext4_error_inode_err(inode, __func__, __LINE__, 0, -error, + "can't get inode location %lu", + inode->i_ino); return 0; } @@ -1762,9 +1761,9 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) err = ext4_get_inode_loc(dir, &iloc); if (err) { - ext4_set_errno(dir->i_sb, -err); - EXT4_ERROR_INODE(dir, "error %d getting inode %lu block", - err, dir->i_ino); + EXT4_ERROR_INODE_ERR(dir, -err, + "error %d getting inode %lu block", + err, dir->i_ino); return true; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f6aebb792178..e416096fc081 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -269,10 +269,9 @@ void ext4_evict_inode(struct inode *inode) if (inode->i_blocks) { err = ext4_truncate(inode); if (err) { - ext4_set_errno(inode->i_sb, -err); - ext4_error(inode->i_sb, - "couldn't truncate inode %lu (err %d)", - inode->i_ino, err); + ext4_error_err(inode->i_sb, -err, + "couldn't truncate inode %lu (err %d)", + inode->i_ino, err); goto stop_handle; } } @@ -2478,10 +2477,9 @@ update_disksize: up_write(&EXT4_I(inode)->i_data_sem); err2 = ext4_mark_inode_dirty(handle, inode); if (err2) { - ext4_set_errno(inode->i_sb, -err2); - ext4_error(inode->i_sb, - "Failed to mark inode %lu dirty", - inode->i_ino); + ext4_error_err(inode->i_sb, -err2, + "Failed to mark inode %lu dirty", + inode->i_ino); } if (!err) err = err2; @@ -4382,8 +4380,7 @@ make_io: wait_on_buffer(bh); if (!buffer_uptodate(bh)) { simulate_eio: - ext4_set_errno(inode->i_sb, EIO); - EXT4_ERROR_INODE_BLOCK(inode, block, + ext4_error_inode_block(inode, block, EIO, "unable to read itable block"); brelse(bh); return -EIO; @@ -4535,7 +4532,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) { if (flags & EXT4_IGET_HANDLE) return ERR_PTR(-ESTALE); - __ext4_error(sb, function, line, + __ext4_error(sb, function, line, EFSCORRUPTED, 0, "inode #%lu: comm %s: iget: illegal inode #", ino, current->comm); return ERR_PTR(-EFSCORRUPTED); @@ -4598,9 +4595,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (!ext4_inode_csum_verify(inode, raw_inode, ei) || ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) { - ext4_set_errno(inode->i_sb, EFSBADCRC); - ext4_error_inode(inode, function, line, 0, - "iget: checksum invalid"); + ext4_error_inode_err(inode, function, line, 0, EFSBADCRC, + "iget: checksum invalid"); ret = -EFSBADCRC; goto bad_inode; } @@ -5149,9 +5145,8 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) sync_dirty_buffer(iloc.bh); if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) { - ext4_set_errno(inode->i_sb, EIO); - EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr, - "IO error syncing inode"); + ext4_error_inode_block(inode, iloc.bh->b_blocknr, EIO, + "IO error syncing inode"); err = -EIO; } brelse(iloc.bh); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 97cd1a2201a2..87c85be4c12e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3921,9 +3921,9 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); - ext4_set_errno(sb, -err); - ext4_error(sb, "Error %d reading block bitmap for %u", - err, group); + ext4_error_err(sb, -err, + "Error %d reading block bitmap for %u", + err, group); return 0; } @@ -4090,18 +4090,16 @@ repeat: err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { - ext4_set_errno(sb, -err); - ext4_error(sb, "Error %d loading buddy information for %u", - err, group); + ext4_error_err(sb, -err, "Error %d loading buddy information for %u", + err, group); continue; } bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); - ext4_set_errno(sb, -err); - ext4_error(sb, "Error %d reading block bitmap for %u", - err, group); + ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", + err, group); ext4_mb_unload_buddy(&e4b); continue; } @@ -4355,9 +4353,8 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { - ext4_set_errno(sb, -err); - ext4_error(sb, "Error %d loading buddy information for %u", - err, group); + ext4_error_err(sb, -err, "Error %d loading buddy information for %u", + err, group); continue; } ext4_lock_group(sb, group); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 87f7551c5132..d34cb8c46655 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -175,8 +175,8 @@ static int kmmpd(void *data) */ if (retval) { if ((failed_writes % 60) == 0) { - ext4_set_errno(sb, -retval); - ext4_error(sb, "Error writing to MMP block"); + ext4_error_err(sb, -retval, + "Error writing to MMP block"); } failed_writes++; } @@ -208,9 +208,9 @@ static int kmmpd(void *data) retval = read_mmp_block(sb, &bh_check, mmp_block); if (retval) { - ext4_set_errno(sb, -retval); - ext4_error(sb, "error reading MMP data: %d", - retval); + ext4_error_err(sb, -retval, + "error reading MMP data: %d", + retval); goto exit_thread; } @@ -222,8 +222,7 @@ static int kmmpd(void *data) "Error while updating MMP info. " "The filesystem seems to have been" " multiply mounted."); - ext4_set_errno(sb, EBUSY); - ext4_error(sb, "abort"); + ext4_error_err(sb, EBUSY, "abort"); put_bh(bh_check); retval = -EBUSY; goto exit_thread; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 30ce3dc69378..1ed86fb6c302 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -422,8 +422,8 @@ repair_branches: block_len_in_page, 0, &err2); ext4_double_up_write_data_sem(orig_inode, donor_inode); if (replaced_count != block_len_in_page) { - EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset), - "Unable to copy data block," + ext4_error_inode_block(orig_inode, (sector_t)(orig_blk_offset), + EIO, "Unable to copy data block," " data will be lost."); *err = -EIO; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5f0a758956f6..a8aca4772aaa 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -160,9 +160,9 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC)) set_buffer_verified(bh); else { - ext4_set_errno(inode->i_sb, EFSBADCRC); - ext4_error_inode(inode, func, line, block, - "Directory index failed checksum"); + ext4_error_inode_err(inode, func, line, block, + EFSBADCRC, + "Directory index failed checksum"); brelse(bh); return ERR_PTR(-EFSBADCRC); } @@ -172,9 +172,9 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC)) set_buffer_verified(bh); else { - ext4_set_errno(inode->i_sb, EFSBADCRC); - ext4_error_inode(inode, func, line, block, - "Directory block failed checksum"); + ext4_error_inode_err(inode, func, line, block, + EFSBADCRC, + "Directory block failed checksum"); brelse(bh); return ERR_PTR(-EFSBADCRC); } @@ -1532,9 +1532,9 @@ restart: goto next; wait_on_buffer(bh); if (!buffer_uptodate(bh)) { - ext4_set_errno(sb, EIO); - EXT4_ERROR_INODE(dir, "reading directory lblock %lu", - (unsigned long) block); + EXT4_ERROR_INODE_ERR(dir, EIO, + "reading directory lblock %lu", + (unsigned long) block); brelse(bh); ret = ERR_PTR(-EIO); goto cleanup_and_exit; @@ -1543,9 +1543,9 @@ restart: !is_dx_internal_node(dir, block, (struct ext4_dir_entry *)bh->b_data) && !ext4_dirblock_csum_verify(dir, bh)) { - ext4_set_errno(sb, EFSBADCRC); - EXT4_ERROR_INODE(dir, "checksumming directory " - "block %lu", (unsigned long)block); + EXT4_ERROR_INODE_ERR(dir, EFSBADCRC, + "checksumming directory " + "block %lu", (unsigned long)block); brelse(bh); ret = ERR_PTR(-EFSBADCRC); goto cleanup_and_exit; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0153ae330c86..1dc22825fdf7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -335,10 +335,12 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) -static void __save_error_info(struct super_block *sb, const char *func, - unsigned int line) +static void __save_error_info(struct super_block *sb, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; + int err; EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (bdev_read_only(sb->s_bdev)) @@ -347,8 +349,62 @@ static void __save_error_info(struct super_block *sb, const char *func, ext4_update_tstamp(es, s_last_error_time); strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); es->s_last_error_line = cpu_to_le32(line); - if (es->s_last_error_errcode == 0) - es->s_last_error_errcode = EXT4_ERR_EFSCORRUPTED; + es->s_last_error_ino = cpu_to_le32(ino); + es->s_last_error_block = cpu_to_le64(block); + switch (error) { + case EIO: + err = EXT4_ERR_EIO; + break; + case ENOMEM: + err = EXT4_ERR_ENOMEM; + break; + case EFSBADCRC: + err = EXT4_ERR_EFSBADCRC; + break; + case 0: + case EFSCORRUPTED: + err = EXT4_ERR_EFSCORRUPTED; + break; + case ENOSPC: + err = EXT4_ERR_ENOSPC; + break; + case ENOKEY: + err = EXT4_ERR_ENOKEY; + break; + case EROFS: + err = EXT4_ERR_EROFS; + break; + case EFBIG: + err = EXT4_ERR_EFBIG; + break; + case EEXIST: + err = EXT4_ERR_EEXIST; + break; + case ERANGE: + err = EXT4_ERR_ERANGE; + break; + case EOVERFLOW: + err = EXT4_ERR_EOVERFLOW; + break; + case EBUSY: + err = EXT4_ERR_EBUSY; + break; + case ENOTDIR: + err = EXT4_ERR_ENOTDIR; + break; + case ENOTEMPTY: + err = EXT4_ERR_ENOTEMPTY; + break; + case ESHUTDOWN: + err = EXT4_ERR_ESHUTDOWN; + break; + case EFAULT: + err = EXT4_ERR_EFAULT; + break; + default: + err = EXT4_ERR_UNKNOWN; + } + es->s_last_error_errcode = err; if (!es->s_first_error_time) { es->s_first_error_time = es->s_last_error_time; es->s_first_error_time_hi = es->s_last_error_time_hi; @@ -368,10 +424,11 @@ static void __save_error_info(struct super_block *sb, const char *func, le32_add_cpu(&es->s_error_count, 1); } -static void save_error_info(struct super_block *sb, const char *func, - unsigned int line) +static void save_error_info(struct super_block *sb, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { - __save_error_info(sb, func, line); + __save_error_info(sb, error, ino, block, func, line); if (!bdev_read_only(sb->s_bdev)) ext4_commit_super(sb, 1); } @@ -478,7 +535,8 @@ static void ext4_handle_error(struct super_block *sb) "EXT4-fs error") void __ext4_error(struct super_block *sb, const char *function, - unsigned int line, const char *fmt, ...) + unsigned int line, int error, __u64 block, + const char *fmt, ...) { struct va_format vaf; va_list args; @@ -496,24 +554,21 @@ void __ext4_error(struct super_block *sb, const char *function, sb->s_id, function, line, current->comm, &vaf); va_end(args); } - save_error_info(sb, function, line); + save_error_info(sb, error, 0, block, function, line); ext4_handle_error(sb); } void __ext4_error_inode(struct inode *inode, const char *function, - unsigned int line, ext4_fsblk_t block, + unsigned int line, ext4_fsblk_t block, int error, const char *fmt, ...) { va_list args; struct va_format vaf; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return; trace_ext4_error(inode->i_sb, function, line); - es->s_last_error_ino = cpu_to_le32(inode->i_ino); - es->s_last_error_block = cpu_to_le64(block); if (ext4_error_ratelimit(inode->i_sb)) { va_start(args, fmt); vaf.fmt = fmt; @@ -530,7 +585,8 @@ void __ext4_error_inode(struct inode *inode, const char *function, current->comm, &vaf); va_end(args); } - save_error_info(inode->i_sb, function, line); + save_error_info(inode->i_sb, error, inode->i_ino, block, + function, line); ext4_handle_error(inode->i_sb); } @@ -549,7 +605,6 @@ void __ext4_error_file(struct file *file, const char *function, trace_ext4_error(inode->i_sb, function, line); es = EXT4_SB(inode->i_sb)->s_es; - es->s_last_error_ino = cpu_to_le32(inode->i_ino); if (ext4_error_ratelimit(inode->i_sb)) { path = file_path(file, pathname, sizeof(pathname)); if (IS_ERR(path)) @@ -571,7 +626,8 @@ void __ext4_error_file(struct file *file, const char *function, current->comm, path, &vaf); va_end(args); } - save_error_info(inode->i_sb, function, line); + save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block, + function, line); ext4_handle_error(inode->i_sb); } @@ -615,66 +671,6 @@ const char *ext4_decode_error(struct super_block *sb, int errno, return errstr; } -void ext4_set_errno(struct super_block *sb, int err) -{ - if (err < 0) - err = -err; - - switch (err) { - case EIO: - err = EXT4_ERR_EIO; - break; - case ENOMEM: - err = EXT4_ERR_ENOMEM; - break; - case EFSBADCRC: - err = EXT4_ERR_EFSBADCRC; - break; - case EFSCORRUPTED: - err = EXT4_ERR_EFSCORRUPTED; - break; - case ENOSPC: - err = EXT4_ERR_ENOSPC; - break; - case ENOKEY: - err = EXT4_ERR_ENOKEY; - break; - case EROFS: - err = EXT4_ERR_EROFS; - break; - case EFBIG: - err = EXT4_ERR_EFBIG; - break; - case EEXIST: - err = EXT4_ERR_EEXIST; - break; - case ERANGE: - err = EXT4_ERR_ERANGE; - break; - case EOVERFLOW: - err = EXT4_ERR_EOVERFLOW; - break; - case EBUSY: - err = EXT4_ERR_EBUSY; - break; - case ENOTDIR: - err = EXT4_ERR_ENOTDIR; - break; - case ENOTEMPTY: - err = EXT4_ERR_ENOTEMPTY; - break; - case ESHUTDOWN: - err = EXT4_ERR_ESHUTDOWN; - break; - case EFAULT: - err = EXT4_ERR_EFAULT; - break; - default: - err = EXT4_ERR_UNKNOWN; - } - EXT4_SB(sb)->s_es->s_last_error_errcode = err; -} - /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ @@ -699,8 +695,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, sb->s_id, function, line, errstr); } - ext4_set_errno(sb, -errno); - save_error_info(sb, function, line); + save_error_info(sb, -errno, 0, 0, function, line); ext4_handle_error(sb); } @@ -715,7 +710,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, */ void __ext4_abort(struct super_block *sb, const char *function, - unsigned int line, const char *fmt, ...) + unsigned int line, int error, const char *fmt, ...) { struct va_format vaf; va_list args; @@ -723,7 +718,7 @@ void __ext4_abort(struct super_block *sb, const char *function, if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) return; - save_error_info(sb, function, line); + save_error_info(sb, error, 0, 0, function, line); va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; @@ -742,7 +737,6 @@ void __ext4_abort(struct super_block *sb, const char *function, sb->s_flags |= SB_RDONLY; if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); - save_error_info(sb, function, line); } if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { if (EXT4_SB(sb)->s_journal && @@ -816,15 +810,12 @@ __acquires(bitlock) { struct va_format vaf; va_list args; - struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) return; trace_ext4_error(sb, function, line); - es->s_last_error_ino = cpu_to_le32(ino); - es->s_last_error_block = cpu_to_le64(block); - __save_error_info(sb, function, line); + __save_error_info(sb, EFSCORRUPTED, ino, block, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); @@ -1037,8 +1028,7 @@ static void ext4_put_super(struct super_block *sb) err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; if ((err < 0) && !aborted) { - ext4_set_errno(sb, -err); - ext4_abort(sb, "Couldn't clean up the journal"); + ext4_abort(sb, -err, "Couldn't clean up the journal"); } } @@ -5452,7 +5442,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) - ext4_abort(sb, "Abort forced by user"); + ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 8cac7d95c3ad..21df43a25328 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -245,7 +245,7 @@ __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh, bh->b_data); errout: if (error) - __ext4_error_inode(inode, function, line, 0, + __ext4_error_inode(inode, function, line, 0, -error, "corrupted xattr block %llu", (unsigned long long) bh->b_blocknr); else @@ -269,7 +269,7 @@ __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header, error = ext4_xattr_check_entries(IFIRST(header), end, IFIRST(header)); errout: if (error) - __ext4_error_inode(inode, function, line, 0, + __ext4_error_inode(inode, function, line, 0, -error, "corrupted in-inode xattr"); return error; } @@ -2880,9 +2880,9 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, if (IS_ERR(bh)) { error = PTR_ERR(bh); if (error == -EIO) { - ext4_set_errno(inode->i_sb, EIO); - EXT4_ERROR_INODE(inode, "block %llu read error", - EXT4_I(inode)->i_file_acl); + EXT4_ERROR_INODE_ERR(inode, EIO, + "block %llu read error", + EXT4_I(inode)->i_file_acl); } bh = NULL; goto cleanup;