From: Zhang Yi <yi.zhang@huaweicloud.com>
To: linux-ext4@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
tytso@mit.edu, adilger.kernel@dilger.ca, jack@suse.cz,
yi.zhang@huawei.com, yi.zhang@huaweicloud.com,
chengzhihao1@huawei.com, yukuai3@huawei.com,
yangerkun@huawei.com
Subject: [PATCH v4 10/10] ext4: move out common parts into ext4_fallocate()
Date: Mon, 16 Dec 2024 09:39:15 +0800 [thread overview]
Message-ID: <20241216013915.3392419-11-yi.zhang@huaweicloud.com> (raw)
In-Reply-To: <20241216013915.3392419-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
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>
---
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 85f0de1abe78..1b028be19193 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4568,7 +4568,6 @@ 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;
@@ -4592,23 +4591,6 @@ 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)) {
@@ -4618,17 +4600,17 @@ 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);
@@ -4640,11 +4622,11 @@ 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
@@ -4657,7 +4639,7 @@ 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 */
@@ -4677,8 +4659,6 @@ 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;
}
@@ -4711,13 +4691,6 @@ 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)
@@ -4742,6 +4715,7 @@ 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;
/*
@@ -4765,6 +4739,29 @@ 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)
@@ -4774,7 +4771,10 @@ 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;
@@ -5301,23 +5301,6 @@ 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
@@ -5331,16 +5314,15 @@ 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;
@@ -5379,8 +5361,6 @@ 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;
}
@@ -5421,23 +5401,6 @@ 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.
@@ -5445,16 +5408,15 @@ 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 */
@@ -5525,8 +5487,6 @@ 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 2e1f070ab449..2677a2cace58 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4009,7 +4009,6 @@ 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;
@@ -4044,31 +4043,15 @@ 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);
@@ -4078,7 +4061,7 @@ 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);
@@ -4123,8 +4106,6 @@ 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;
}
--
2.46.1
next prev parent reply other threads:[~2024-12-16 1:42 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-16 1:39 [PATCH v4 00/10] ext4: clean up and refactor fallocate Zhang Yi
2024-12-16 1:39 ` [PATCH v4 01/10] ext4: remove writable userspace mappings before truncating page cache Zhang Yi
2024-12-16 15:00 ` Jan Kara
2024-12-17 7:05 ` Zhang Yi
2024-12-16 15:15 ` Matthew Wilcox
2024-12-17 7:38 ` Zhang Yi
2024-12-18 9:56 ` Ojaswin Mujoo
2024-12-18 13:02 ` Zhang Yi
2024-12-19 7:19 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 02/10] ext4: don't explicit update times in ext4_fallocate() Zhang Yi
2024-12-18 9:58 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 03/10] ext4: don't write back data before punch hole in nojournal mode Zhang Yi
2024-12-16 15:02 ` Jan Kara
2024-12-17 14:31 ` Ojaswin Mujoo
2024-12-17 14:50 ` Ojaswin Mujoo
2024-12-18 7:10 ` Zhang Yi
2024-12-18 10:13 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 04/10] ext4: refactor ext4_punch_hole() Zhang Yi
2024-12-16 15:07 ` Jan Kara
2024-12-18 10:17 ` Ojaswin Mujoo
2024-12-18 13:13 ` Zhang Yi
2024-12-19 7:11 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 05/10] ext4: refactor ext4_zero_range() Zhang Yi
2024-12-16 15:24 ` Jan Kara
2024-12-19 7:12 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 06/10] ext4: refactor ext4_collapse_range() Zhang Yi
2024-12-18 10:18 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 07/10] ext4: refactor ext4_insert_range() Zhang Yi
2024-12-18 10:18 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 08/10] ext4: factor out ext4_do_fallocate() Zhang Yi
2024-12-18 10:18 ` Ojaswin Mujoo
2024-12-16 1:39 ` [PATCH v4 09/10] ext4: move out inode_lock into ext4_fallocate() Zhang Yi
2024-12-18 10:19 ` Ojaswin Mujoo
2024-12-16 1:39 ` Zhang Yi [this message]
2024-12-18 10:20 ` [PATCH v4 10/10] ext4: move out common parts " Ojaswin Mujoo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241216013915.3392419-11-yi.zhang@huaweicloud.com \
--to=yi.zhang@huaweicloud.com \
--cc=adilger.kernel@dilger.ca \
--cc=chengzhihao1@huawei.com \
--cc=jack@suse.cz \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tytso@mit.edu \
--cc=yangerkun@huawei.com \
--cc=yi.zhang@huawei.com \
--cc=yukuai3@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).