From: Zhang Yi yi.zhang@huawei.com

[ Upstream commit 982bf37da09d078570650b691d9084f43805a5de ]

The current implementation of ext4_punch_hole() contains complex position calculations and stale error tags. To improve the code's clarity and maintainability, it is essential to clean up the code and improve its readability, this can be achieved by: a) simplifying and renaming variables; b) eliminating unnecessary position calculations; c) writing back all data in data=journal mode, and drop page cache from the original offset to the end, rather than using aligned blocks, d) renaming the stale error tags.

Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Ojaswin Mujoo ojaswin@linux.ibm.com Link: https://patch.msgid.link/20241220011637.1157197-5-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu Stable-dep-of: 29ec9bed2395 ("ext4: fix incorrect punch max_end") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/ext4.h | 2 + fs/ext4/inode.c | 119 +++++++++++++++++++++--------------------------- 2 files changed, 55 insertions(+), 66 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e94df69ee2e0d..a95525bfb99cf 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -368,6 +368,8 @@ struct ext4_io_submit { #define EXT4_MAX_BLOCKS(size, offset, blkbits) \ ((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \ blkbits)) +#define EXT4_B_TO_LBLK(inode, offset) \ + (round_up((offset), i_blocksize(inode)) >> (inode)->i_blkbits)

/* Translate a block number to a cluster number */ #define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e4b6ab28d7055..bb68c851b33ad 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3991,13 +3991,13 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - ext4_lblk_t first_block, stop_block; + ext4_lblk_t start_lblk, end_lblk; struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset, max_length; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + loff_t max_end = EXT4_SB(sb)->s_bitmap_maxbytes - sb->s_blocksize; + loff_t end = offset + length; handle_t *handle; unsigned int credits; - int ret = 0, ret2 = 0; + int ret = 0;

trace_ext4_punch_hole(inode, offset, length, 0);

@@ -4005,36 +4005,27 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)

/* No need to punch hole beyond i_size */ if (offset >= inode->i_size) - goto out_mutex; + goto out;

/* - * If the hole extends beyond i_size, set the hole - * to end after the page that contains i_size + * If the hole extends beyond i_size, set the hole to end after + * the page that contains i_size, and also make sure that the hole + * within one block before last range. */ - if (offset + length > inode->i_size) { - length = inode->i_size + - PAGE_SIZE - (inode->i_size & (PAGE_SIZE - 1)) - - offset; - } + if (end > inode->i_size) + end = round_up(inode->i_size, PAGE_SIZE); + if (end > max_end) + end = max_end; + length = end - offset;

/* - * For punch hole the length + offset needs to be within one block - * before last range. Adjust the length if it goes beyond that limit. + * Attach jinode to inode for jbd2 if we do any zeroing of partial + * block. */ - max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize; - if (offset + length > max_length) - length = max_length - offset; - - if (offset & (sb->s_blocksize - 1) || - (offset + length) & (sb->s_blocksize - 1)) { - /* - * Attach jinode to inode for jbd2 if we do any zeroing of - * partial block - */ + if (!IS_ALIGNED(offset | end, sb->s_blocksize)) { ret = ext4_inode_attach_jinode(inode); if (ret < 0) - goto out_mutex; - + goto out; }

/* Wait all existing dio workers, newcomers will block on i_rwsem */ @@ -4042,7 +4033,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)

ret = file_modified(file); if (ret) - goto out_mutex; + goto out;

/* * Prevent page faults from reinstantiating pages we have released from @@ -4052,22 +4043,16 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)

ret = ext4_break_layouts(inode); if (ret) - goto out_dio; + goto out_invalidate_lock;

- first_block_offset = round_up(offset, sb->s_blocksize); - last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; + ret = ext4_update_disksize_before_punch(inode, offset, length); + if (ret) + goto out_invalidate_lock;

/* Now release the pages and zero block aligned part of pages*/ - if (last_block_offset > first_block_offset) { - ret = ext4_update_disksize_before_punch(inode, offset, length); - if (ret) - goto out_dio; - - ret = ext4_truncate_page_cache_block_range(inode, - first_block_offset, last_block_offset + 1); - if (ret) - goto out_dio; - } + ret = ext4_truncate_page_cache_block_range(inode, offset, end); + if (ret) + goto out_invalidate_lock;

if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); @@ -4077,52 +4062,54 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(sb, ret); - goto out_dio; + goto out_invalidate_lock; }

- ret = ext4_zero_partial_blocks(handle, inode, offset, - length); + ret = ext4_zero_partial_blocks(handle, inode, offset, length); if (ret) - goto out_stop; - - first_block = (offset + sb->s_blocksize - 1) >> - EXT4_BLOCK_SIZE_BITS(sb); - stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); + goto out_handle;

/* If there are blocks to remove, do it */ - if (stop_block > first_block) { - ext4_lblk_t hole_len = stop_block - first_block; + start_lblk = EXT4_B_TO_LBLK(inode, offset); + end_lblk = end >> inode->i_blkbits; + + if (end_lblk > start_lblk) { + ext4_lblk_t hole_len = end_lblk - start_lblk;

down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode);

- ext4_es_remove_extent(inode, first_block, hole_len); + ext4_es_remove_extent(inode, start_lblk, hole_len);

if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_remove_space(inode, first_block, - stop_block - 1); + ret = ext4_ext_remove_space(inode, start_lblk, + end_lblk - 1); else - ret = ext4_ind_remove_space(handle, inode, first_block, - stop_block); + ret = ext4_ind_remove_space(handle, inode, start_lblk, + end_lblk); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_handle; + }

- ext4_es_insert_extent(inode, first_block, hole_len, ~0, + ext4_es_insert_extent(inode, start_lblk, hole_len, ~0, EXTENT_STATUS_HOLE, 0); up_write(&EXT4_I(inode)->i_data_sem); } - ext4_fc_track_range(handle, inode, first_block, stop_block); + ext4_fc_track_range(handle, inode, start_lblk, end_lblk); + + ret = ext4_mark_inode_dirty(handle, inode); + if (unlikely(ret)) + goto out_handle; + + ext4_update_inode_fsync_trans(handle, inode, 1); if (IS_SYNC(inode)) ext4_handle_sync(handle); - - ret2 = ext4_mark_inode_dirty(handle, inode); - if (unlikely(ret2)) - ret = ret2; - if (ret >= 0) - ext4_update_inode_fsync_trans(handle, inode, 1); -out_stop: +out_handle: ext4_journal_stop(handle); -out_dio: +out_invalidate_lock: filemap_invalidate_unlock(mapping); -out_mutex: +out: inode_unlock(inode); return ret; }

From: Zhang Yi yi.zhang@huawei.com

[ Upstream commit 162e3c5ad1672ef41dccfb28ad198c704b8aa9e7 ]

Simplify ext4_collapse_range() and align its code style with that of ext4_zero_range() and ext4_punch_hole(). Refactor it by: a) renaming variables, b) removing redundant input parameter checks and moving the remaining checks under i_rwsem in preparation for future refactoring, and c) renaming the three stale error tags.

Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Ojaswin Mujoo ojaswin@linux.ibm.com Link: https://patch.msgid.link/20241220011637.1157197-7-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu Stable-dep-of: 29ec9bed2395 ("ext4: fix incorrect punch max_end") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/extents.c | 103 +++++++++++++++++++++------------------------- 1 file changed, 48 insertions(+), 55 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 00c7a03cc7c6e..54fbeba3a929d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5288,43 +5288,36 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; - ext4_lblk_t punch_start, punch_stop; + loff_t end = offset + len; + ext4_lblk_t start_lblk, end_lblk; handle_t *handle; unsigned int credits; - loff_t new_size, ioffset; + loff_t start, new_size; int ret;

- /* - * We need to test this early because xfstests assumes that a - * collapse range of (0, 1) will return EOPNOTSUPP if the file - * system does not support collapse range. - */ - if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - return -EOPNOTSUPP; + trace_ext4_collapse_range(inode, offset, len);

- /* Collapse range works only on fs cluster size aligned regions. */ - if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) - return -EINVAL; + inode_lock(inode);

- trace_ext4_collapse_range(inode, offset, len); + /* Currently just for extent based files */ + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + ret = -EOPNOTSUPP; + goto out; + }

- punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb); - punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb); + /* Collapse range works only on fs cluster size aligned regions. */ + if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) { + ret = -EINVAL; + goto out; + }

- inode_lock(inode); /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation */ - if (offset + len >= inode->i_size) { + if (end >= inode->i_size) { ret = -EINVAL; - goto out_mutex; - } - - /* Currently just for extent based files */ - if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - ret = -EOPNOTSUPP; - goto out_mutex; + goto out; }

/* Wait for existing dio to complete */ @@ -5332,7 +5325,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)

ret = file_modified(file); if (ret) - goto out_mutex; + goto out;

/* * Prevent page faults from reinstantiating pages we have released from @@ -5342,55 +5335,52 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)

ret = ext4_break_layouts(inode); if (ret) - goto out_mmap; + goto out_invalidate_lock;

/* + * Write tail of the last page before removed range and data that + * will be shifted since they will get removed from the page cache + * below. We are also protected from pages becoming dirty by + * i_rwsem and invalidate_lock. * Need to round down offset to be aligned with page size boundary * for page size > block size. */ - ioffset = round_down(offset, PAGE_SIZE); - /* - * Write tail of the last page before removed range since it will get - * removed from the page cache below. - */ - ret = filemap_write_and_wait_range(mapping, ioffset, offset); - if (ret) - goto out_mmap; - /* - * Write data that will be shifted to preserve them when discarding - * page cache below. We are also protected from pages becoming dirty - * by i_rwsem and invalidate_lock. - */ - ret = filemap_write_and_wait_range(mapping, offset + len, - LLONG_MAX); + start = round_down(offset, PAGE_SIZE); + ret = filemap_write_and_wait_range(mapping, start, offset); + if (!ret) + ret = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (ret) - goto out_mmap; - truncate_pagecache(inode, ioffset); + goto out_invalidate_lock; + + truncate_pagecache(inode, start);

credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_mmap; + goto out_invalidate_lock; } ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);

+ start_lblk = offset >> inode->i_blkbits; + end_lblk = (offset + len) >> inode->i_blkbits; + down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); - ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start); + ext4_es_remove_extent(inode, start_lblk, EXT_MAX_BLOCKS - start_lblk);

- ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1); + ret = ext4_ext_remove_space(inode, start_lblk, end_lblk - 1); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; + goto out_handle; } ext4_discard_preallocations(inode);

- ret = ext4_ext_shift_extents(inode, handle, punch_stop, - punch_stop - punch_start, SHIFT_LEFT); + ret = ext4_ext_shift_extents(inode, handle, end_lblk, + end_lblk - start_lblk, SHIFT_LEFT); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; + goto out_handle; }

new_size = inode->i_size - len; @@ -5398,16 +5388,19 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) EXT4_I(inode)->i_disksize = new_size;

up_write(&EXT4_I(inode)->i_data_sem); - if (IS_SYNC(inode)) - ext4_handle_sync(handle); ret = ext4_mark_inode_dirty(handle, inode); + if (ret) + goto out_handle; + ext4_update_inode_fsync_trans(handle, inode, 1); + if (IS_SYNC(inode)) + ext4_handle_sync(handle);

-out_stop: +out_handle: ext4_journal_stop(handle); -out_mmap: +out_invalidate_lock: filemap_invalidate_unlock(mapping); -out_mutex: +out: inode_unlock(inode); return ret; }

From: Zhang Yi yi.zhang@huawei.com

[ Upstream commit fd2f764826df5489b849a8937b5a093aae5b1816 ]

Now the real job of normal fallocate are open coded in ext4_fallocate(), factor out a new helper ext4_do_fallocate() to do the real job, like others functions (e.g. ext4_zero_range()) in ext4_fallocate() do, this can make the code more clear, no functional changes.

Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Ojaswin Mujoo ojaswin@linux.ibm.com Link: https://patch.msgid.link/20241220011637.1157197-9-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu Stable-dep-of: 29ec9bed2395 ("ext4: fix incorrect punch max_end") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/extents.c | 125 ++++++++++++++++++++++------------------------ 1 file changed, 60 insertions(+), 65 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 961e7b634401d..eb58f7a1ab5aa 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4690,6 +4690,58 @@ static long ext4_zero_range(struct file *file, loff_t offset, return ret; }

+static long ext4_do_fallocate(struct file *file, loff_t offset, + loff_t len, int mode) +{ + struct inode *inode = file_inode(file); + loff_t end = offset + len; + loff_t new_size = 0; + ext4_lblk_t start_lblk, len_lblk; + int ret; + + trace_ext4_fallocate_enter(inode, offset, len, mode); + + start_lblk = offset >> inode->i_blkbits; + len_lblk = EXT4_MAX_BLOCKS(len, offset, inode->i_blkbits); + + inode_lock(inode); + + /* We only support preallocation for extent-based files only. */ + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { + ret = -EOPNOTSUPP; + goto out; + } + + if (!(mode & FALLOC_FL_KEEP_SIZE) && + (end > inode->i_size || end > EXT4_I(inode)->i_disksize)) { + new_size = end; + ret = inode_newsize_ok(inode, new_size); + if (ret) + goto out; + } + + /* Wait all existing dio workers, newcomers will block on i_rwsem */ + inode_dio_wait(inode); + + ret = file_modified(file); + if (ret) + goto out; + + ret = ext4_alloc_file_blocks(file, start_lblk, len_lblk, new_size, + EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); + if (ret) + goto out; + + if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) { + ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, + EXT4_I(inode)->i_sync_tid); + } +out: + inode_unlock(inode); + trace_ext4_fallocate_exit(inode, offset, len_lblk, ret); + return ret; +} + /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. @@ -4700,12 +4752,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); - loff_t new_size = 0; - unsigned int max_blocks; - int ret = 0; - int flags; - ext4_lblk_t lblk; - unsigned int blkbits = inode->i_blkbits; + int ret;

/* * Encrypted inodes can't handle collapse range or insert @@ -4727,71 +4774,19 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) ret = ext4_convert_inline_data(inode); inode_unlock(inode); if (ret) - goto exit; + return ret;

- if (mode & FALLOC_FL_PUNCH_HOLE) { + if (mode & FALLOC_FL_PUNCH_HOLE) ret = ext4_punch_hole(file, offset, len); - goto exit; - } - - if (mode & FALLOC_FL_COLLAPSE_RANGE) { + else if (mode & FALLOC_FL_COLLAPSE_RANGE) ret = ext4_collapse_range(file, offset, len); - goto exit; - } - - if (mode & FALLOC_FL_INSERT_RANGE) { + else if (mode & FALLOC_FL_INSERT_RANGE) ret = ext4_insert_range(file, offset, len); - goto exit; - } - - if (mode & FALLOC_FL_ZERO_RANGE) { + else if (mode & FALLOC_FL_ZERO_RANGE) ret = ext4_zero_range(file, offset, len, mode); - goto exit; - } - trace_ext4_fallocate_enter(inode, offset, len, mode); - lblk = offset >> blkbits; - - max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); - flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; - - inode_lock(inode); - - /* - * We only support preallocation for extent-based files only - */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { - ret = -EOPNOTSUPP; - goto out; - } - - if (!(mode & FALLOC_FL_KEEP_SIZE) && - (offset + len > inode->i_size || - offset + len > EXT4_I(inode)->i_disksize)) { - new_size = offset + len; - ret = inode_newsize_ok(inode, new_size); - if (ret) - goto out; - } - - /* Wait all existing dio workers, newcomers will block on i_rwsem */ - inode_dio_wait(inode); - - ret = file_modified(file); - if (ret) - goto out; - - ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); - if (ret) - goto out; + else + ret = ext4_do_fallocate(file, offset, len, mode);

- if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) { - ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, - EXT4_I(inode)->i_sync_tid); - } -out: - inode_unlock(inode); - trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); -exit: return ret; }

From: Zhang Yi yi.zhang@huawei.com

[ Upstream commit 2890e5e0f49e10f3dadc5f7b7ea434e3e77e12a6 ]

Currently, all zeroing ranges, punch holes, collapse ranges, and insert ranges first wait for all existing direct I/O workers to complete, and then they acquire the mapping's invalidate lock before performing the actual work. These common components are nearly identical, so we can simplify the code by factoring them out into the ext4_fallocate().

Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Ojaswin Mujoo ojaswin@linux.ibm.com Link: https://patch.msgid.link/20241220011637.1157197-11-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu Stable-dep-of: 29ec9bed2395 ("ext4: fix incorrect punch max_end") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/extents.c | 124 ++++++++++++++++------------------------------ fs/ext4/inode.c | 25 ++-------- 2 files changed, 45 insertions(+), 104 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 30d412b62d9ed..51b9533416e04 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4569,7 +4569,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); - struct address_space *mapping = file->f_mapping; handle_t *handle = NULL; loff_t new_size = 0; loff_t end = offset + len; @@ -4593,23 +4592,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, return ret; }

- /* Wait all existing dio workers, newcomers will block on i_rwsem */ - inode_dio_wait(inode); - - ret = file_modified(file); - if (ret) - return ret; - - /* - * Prevent page faults from reinstantiating pages we have released - * from page cache. - */ - filemap_invalidate_lock(mapping); - - ret = ext4_break_layouts(inode); - if (ret) - goto out_invalidate_lock; - flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; /* Preallocate the range including the unaligned edges */ if (!IS_ALIGNED(offset | end, blocksize)) { @@ -4619,17 +4601,17 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = ext4_alloc_file_blocks(file, alloc_lblk, len_lblk, new_size, flags); if (ret) - goto out_invalidate_lock; + return ret; }

ret = ext4_update_disksize_before_punch(inode, offset, len); if (ret) - goto out_invalidate_lock; + return ret;

/* Now release the pages and zero block aligned part of pages */ ret = ext4_truncate_page_cache_block_range(inode, offset, end); if (ret) - goto out_invalidate_lock; + return ret;

/* Zero range excluding the unaligned edges */ start_lblk = EXT4_B_TO_LBLK(inode, offset); @@ -4641,11 +4623,11 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = ext4_alloc_file_blocks(file, start_lblk, zero_blks, new_size, flags); if (ret) - goto out_invalidate_lock; + return ret; } /* Finish zeroing out if it doesn't contain partial block */ if (IS_ALIGNED(offset | end, blocksize)) - goto out_invalidate_lock; + return ret;

/* * In worst case we have to writeout two nonadjacent unwritten @@ -4658,7 +4640,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(inode->i_sb, ret); - goto out_invalidate_lock; + return ret; }

/* Zero out partial block at the edges of the range */ @@ -4678,8 +4660,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,

out_handle: ext4_journal_stop(handle); -out_invalidate_lock: - filemap_invalidate_unlock(mapping); return ret; }

@@ -4712,13 +4692,6 @@ static long ext4_do_fallocate(struct file *file, loff_t offset, goto out; }

- /* Wait all existing dio workers, newcomers will block on i_rwsem */ - inode_dio_wait(inode); - - ret = file_modified(file); - if (ret) - goto out; - ret = ext4_alloc_file_blocks(file, start_lblk, len_lblk, new_size, EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); if (ret) @@ -4743,6 +4716,7 @@ static long ext4_do_fallocate(struct file *file, loff_t offset, long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); + struct address_space *mapping = file->f_mapping; int ret;

/* @@ -4766,6 +4740,29 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (ret) goto out_inode_lock;

+ /* Wait all existing dio workers, newcomers will block on i_rwsem */ + inode_dio_wait(inode); + + ret = file_modified(file); + if (ret) + return ret; + + if ((mode & FALLOC_FL_MODE_MASK) == FALLOC_FL_ALLOCATE_RANGE) { + ret = ext4_do_fallocate(file, offset, len, mode); + goto out_inode_lock; + } + + /* + * Follow-up operations will drop page cache, hold invalidate lock + * to prevent page faults from reinstantiating pages we have + * released from page cache. + */ + filemap_invalidate_lock(mapping); + + ret = ext4_break_layouts(inode); + if (ret) + goto out_invalidate_lock; + if (mode & FALLOC_FL_PUNCH_HOLE) ret = ext4_punch_hole(file, offset, len); else if (mode & FALLOC_FL_COLLAPSE_RANGE) @@ -4775,7 +4772,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) else if (mode & FALLOC_FL_ZERO_RANGE) ret = ext4_zero_range(file, offset, len, mode); else - ret = ext4_do_fallocate(file, offset, len, mode); + ret = -EOPNOTSUPP; + +out_invalidate_lock: + filemap_invalidate_unlock(mapping); out_inode_lock: inode_unlock(inode); return ret; @@ -5297,23 +5297,6 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) if (end >= inode->i_size) return -EINVAL;

- /* Wait for existing dio to complete */ - inode_dio_wait(inode); - - ret = file_modified(file); - if (ret) - return ret; - - /* - * Prevent page faults from reinstantiating pages we have released from - * page cache. - */ - filemap_invalidate_lock(mapping); - - ret = ext4_break_layouts(inode); - if (ret) - goto out_invalidate_lock; - /* * Write tail of the last page before removed range and data that * will be shifted since they will get removed from the page cache @@ -5327,16 +5310,15 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) if (!ret) ret = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (ret) - goto out_invalidate_lock; + return ret;

truncate_pagecache(inode, start);

credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out_invalidate_lock; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);

start_lblk = offset >> inode->i_blkbits; @@ -5375,8 +5357,6 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)

out_handle: ext4_journal_stop(handle); -out_invalidate_lock: - filemap_invalidate_unlock(mapping); return ret; }

@@ -5417,23 +5397,6 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) if (len > inode->i_sb->s_maxbytes - inode->i_size) return -EFBIG;

- /* Wait for existing dio to complete */ - inode_dio_wait(inode); - - ret = file_modified(file); - if (ret) - return ret; - - /* - * Prevent page faults from reinstantiating pages we have released from - * page cache. - */ - filemap_invalidate_lock(mapping); - - ret = ext4_break_layouts(inode); - if (ret) - goto out_invalidate_lock; - /* * Write out all dirty pages. Need to round down to align start offset * to page size boundary for page size > block size. @@ -5441,16 +5404,15 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) start = round_down(offset, PAGE_SIZE); ret = filemap_write_and_wait_range(mapping, start, LLONG_MAX); if (ret) - goto out_invalidate_lock; + return ret;

truncate_pagecache(inode, start);

credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out_invalidate_lock; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);

/* Expand file to avoid data loss if there is error while shifting */ @@ -5521,8 +5483,6 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)

out_handle: ext4_journal_stop(handle); -out_invalidate_lock: - filemap_invalidate_unlock(mapping); return ret; }

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6f0b1b0bd1af8..ca98f04fcf556 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3992,7 +3992,6 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t start_lblk, end_lblk; - struct address_space *mapping = inode->i_mapping; loff_t max_end = EXT4_SB(sb)->s_bitmap_maxbytes - sb->s_blocksize; loff_t end = offset + length; handle_t *handle; @@ -4027,31 +4026,15 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) return ret; }

- /* Wait all existing dio workers, newcomers will block on i_rwsem */ - inode_dio_wait(inode); - - ret = file_modified(file); - if (ret) - return ret; - - /* - * Prevent page faults from reinstantiating pages we have released from - * page cache. - */ - filemap_invalidate_lock(mapping); - - ret = ext4_break_layouts(inode); - if (ret) - goto out_invalidate_lock;

ret = ext4_update_disksize_before_punch(inode, offset, length); if (ret) - goto out_invalidate_lock; + return ret;

/* Now release the pages and zero block aligned part of pages*/ ret = ext4_truncate_page_cache_block_range(inode, offset, end); if (ret) - goto out_invalidate_lock; + return ret;

if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); @@ -4061,7 +4044,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(sb, ret); - goto out_invalidate_lock; + return ret; }

ret = ext4_zero_partial_blocks(handle, inode, offset, length); @@ -4106,8 +4089,6 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); -out_invalidate_lock: - filemap_invalidate_unlock(mapping); return ret; }

From: Zhang Yi yi.zhang@huawei.com

[ Upstream commit 129245cfbd6d79c6d603f357f428010ccc0f0ee7 ]

The error out label of file_modified() should be out_inode_lock in ext4_fallocate().

Fixes: 2890e5e0f49e ("ext4: move out common parts into ext4_fallocate()") Reported-by: Baokun Li libaokun1@huawei.com Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Baokun Li libaokun1@huawei.com Link: https://patch.msgid.link/20250319023557.2785018-1-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/extents.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 51b9533416e04..2f9c3cd4f26cc 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4745,7 +4745,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)

ret = file_modified(file); if (ret) - return ret; + goto out_inode_lock;

if ((mode & FALLOC_FL_MODE_MASK) == FALLOC_FL_ALLOCATE_RANGE) { ret = ext4_do_fallocate(file, offset, len, mode);