From: Jan Kara <jack@suse.cz>
To: <linux-fsdevel@vger.kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>,
Dave Chinner <david@fromorbit.com>,
ceph-devel@vger.kernel.org, Chao Yu <yuchao0@huawei.com>,
Damien Le Moal <damien.lemoal@wdc.com>,
"Darrick J. Wong" <darrick.wong@oracle.com>,
Jaegeuk Kim <jaegeuk@kernel.org>,
Jeff Layton <jlayton@kernel.org>,
Johannes Thumshirn <jth@kernel.org>,
linux-cifs@vger.kernel.org, <linux-ext4@vger.kernel.org>,
linux-f2fs-devel@lists.sourceforge.net, <linux-mm@kvack.org>,
<linux-xfs@vger.kernel.org>, Miklos Szeredi <miklos@szeredi.hu>,
Steve French <sfrench@samba.org>, Ted Tso <tytso@mit.edu>,
Matthew Wilcox <willy@infradead.org>, Jan Kara <jack@suse.cz>
Subject: [PATCH 08/11] f2fs: Convert to using invalidate_lock
Date: Wed, 12 May 2021 15:46:16 +0200 [thread overview]
Message-ID: <20210512134631.4053-8-jack@suse.cz> (raw)
In-Reply-To: <20210512101639.22278-1-jack@suse.cz>
Use invalidate_lock instead of f2fs' private i_mmap_sem. The intended
purpose is exactly the same. By this conversion we fix a long standing
race between hole punching and read(2) / readahead(2) paths that can
lead to stale page cache contents.
CC: Jaegeuk Kim <jaegeuk@kernel.org>
CC: Chao Yu <yuchao0@huawei.com>
CC: linux-f2fs-devel@lists.sourceforge.net
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/f2fs/data.c | 4 ++--
fs/f2fs/f2fs.h | 1 -
fs/f2fs/file.c | 58 ++++++++++++++++++++++++-------------------------
fs/f2fs/super.c | 1 -
4 files changed, 30 insertions(+), 34 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 96f1a354f89f..f3177d03c28f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3165,12 +3165,12 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
/* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
if (to > i_size && !f2fs_verity_in_progress(inode)) {
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&mapping->invalidate_lock);
truncate_pagecache(inode, i_size);
f2fs_truncate_blocks(inode, i_size, true);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 044878866ca3..1f887c906aaf 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -748,7 +748,6 @@ struct f2fs_inode_info {
/* avoid racing between foreground op and gc */
struct rw_semaphore i_gc_rwsem[2];
- struct rw_semaphore i_mmap_sem;
struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
int i_extra_isize; /* size of extra space located in i_addr */
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 44a4650aea7b..6602f3c653c4 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -38,10 +38,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
struct inode *inode = file_inode(vmf->vma->vm_file);
vm_fault_t ret;
- down_read(&F2FS_I(inode)->i_mmap_sem);
ret = filemap_fault(vmf);
- up_read(&F2FS_I(inode)->i_mmap_sem);
-
if (!ret)
f2fs_update_iostat(F2FS_I_SB(inode), APP_MAPPED_READ_IO,
F2FS_BLKSIZE);
@@ -102,7 +99,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
file_update_time(vmf->vma->vm_file);
- down_read(&F2FS_I(inode)->i_mmap_sem);
+ down_read(&inode->i_mapping->invalidate_lock);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
@@ -161,7 +158,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
trace_f2fs_vm_page_mkwrite(page, DATA);
out_sem:
- up_read(&F2FS_I(inode)->i_mmap_sem);
+ up_read(&inode->i_mapping->invalidate_lock);
sb_end_pagefault(inode->i_sb);
err:
@@ -942,7 +939,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
}
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&inode->i_mapping->invalidate_lock);
truncate_setsize(inode, attr->ia_size);
@@ -952,7 +949,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
* do not trim all blocks after i_size if target size is
* larger than i_size.
*/
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&inode->i_mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (err)
return err;
@@ -1097,7 +1094,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
blk_end = (loff_t)pg_end << PAGE_SHIFT;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&mapping->invalidate_lock);
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
@@ -1106,7 +1103,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
ret = f2fs_truncate_hole(inode, pg_start, pg_end);
f2fs_unlock_op(sbi);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
@@ -1341,7 +1338,7 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
/* avoid gc operation during block exchange */
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&inode->i_mapping->invalidate_lock);
f2fs_lock_op(sbi);
f2fs_drop_extent_tree(inode);
@@ -1349,7 +1346,7 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
f2fs_unlock_op(sbi);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&inode->i_mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
return ret;
}
@@ -1380,13 +1377,13 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
return ret;
/* write out all moved pages, if possible */
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&inode->i_mapping->invalidate_lock);
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
new_size = i_size_read(inode) - len;
ret = f2fs_truncate_blocks(inode, new_size, true);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&inode->i_mapping->invalidate_lock);
if (!ret)
f2fs_i_size_write(inode, new_size);
return ret;
@@ -1486,7 +1483,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
pgoff_t end;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&mapping->invalidate_lock);
truncate_pagecache_range(inode,
(loff_t)index << PAGE_SHIFT,
@@ -1498,7 +1495,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
if (ret) {
f2fs_unlock_op(sbi);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
goto out;
}
@@ -1510,7 +1507,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
f2fs_balance_fs(sbi, dn.node_changed);
@@ -1545,6 +1542,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct address_space *mapping = inode->i_mapping;
pgoff_t nr, pg_start, pg_end, delta, idx;
loff_t new_size;
int ret = 0;
@@ -1567,14 +1565,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
f2fs_balance_fs(sbi, true);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&mapping->invalidate_lock);
ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
if (ret)
return ret;
/* write out all dirty pages from offset */
- ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
if (ret)
return ret;
@@ -1585,7 +1583,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
/* avoid gc operation during block exchange */
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&mapping->invalidate_lock);
truncate_pagecache(inode, offset);
while (!ret && idx > pg_start) {
@@ -1601,14 +1599,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
idx + delta, nr, false);
f2fs_unlock_op(sbi);
}
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
/* write out all moved pages, if possible */
- down_write(&F2FS_I(inode)->i_mmap_sem);
- filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ down_write(&mapping->invalidate_lock);
+ filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
if (!ret)
f2fs_i_size_write(inode, new_size);
@@ -3442,7 +3440,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
goto out;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&inode->i_mapping->invalidate_lock);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
@@ -3478,7 +3476,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
}
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&inode->i_mapping->invalidate_lock);
out:
inode_unlock(inode);
@@ -3595,7 +3593,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
}
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&inode->i_mapping->invalidate_lock);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
@@ -3631,7 +3629,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
}
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&inode->i_mapping->invalidate_lock);
if (ret >= 0) {
F2FS_I(inode)->i_flags &= ~F2FS_IMMUTABLE_FL;
@@ -3751,7 +3749,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
goto err;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- down_write(&F2FS_I(inode)->i_mmap_sem);
+ down_write(&mapping->invalidate_lock);
ret = filemap_write_and_wait_range(mapping, range.start,
to_end ? LLONG_MAX : end_addr - 1);
@@ -3838,7 +3836,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
prev_block, len, range.flags);
out:
- up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&mapping->invalidate_lock);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
err:
inode_unlock(inode);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 7d325bfaf65a..22e942aac7ad 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1187,7 +1187,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
mutex_init(&fi->inmem_lock);
init_rwsem(&fi->i_gc_rwsem[READ]);
init_rwsem(&fi->i_gc_rwsem[WRITE]);
- init_rwsem(&fi->i_mmap_sem);
init_rwsem(&fi->i_xattr_sem);
/* Will be used by directory only */
--
2.26.2
next prev parent reply other threads:[~2021-05-12 13:46 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-12 13:46 [PATCH 0/11 v5] fs: Hole punch vs page cache filling races Jan Kara
2021-05-12 13:46 ` [PATCH 01/11] mm: Fix comments mentioning i_mutex Jan Kara
2021-05-12 13:46 ` [PATCH 02/11] documentation: Sync file_operations members with reality Jan Kara
2021-05-12 13:46 ` [PATCH 03/11] mm: Protect operations adding pages to page cache with invalidate_lock Jan Kara
2021-05-12 14:20 ` Matthew Wilcox
2021-05-13 17:49 ` Jan Kara
2021-05-12 14:40 ` Matthew Wilcox
2021-05-13 19:01 ` Jan Kara
2021-05-13 19:38 ` Matthew Wilcox
2021-05-14 11:07 ` Jan Kara
2021-05-12 15:23 ` Darrick J. Wong
2021-05-13 17:44 ` Jan Kara
2021-05-13 18:52 ` Darrick J. Wong
2021-05-13 23:19 ` Dave Chinner
2021-05-14 16:17 ` Darrick J. Wong
2021-05-17 11:21 ` Jan Kara
2021-05-18 22:36 ` Dave Chinner
2021-05-19 10:57 ` Jan Kara
2021-05-12 13:46 ` [PATCH 04/11] ext4: Convert to use mapping->invalidate_lock Jan Kara
2021-05-12 13:46 ` [PATCH 05/11] ext2: Convert to using invalidate_lock Jan Kara
2021-05-12 13:46 ` [PATCH 06/11] xfs: Convert to use invalidate_lock Jan Kara
2021-05-12 13:46 ` [PATCH 07/11] zonefs: Convert to using invalidate_lock Jan Kara
2021-05-13 0:34 ` Damien Le Moal
2021-05-12 13:46 ` Jan Kara [this message]
2021-05-12 13:46 ` [PATCH 09/11] fuse: " Jan Kara
2021-05-12 13:46 ` [PATCH 10/11] ceph: Fix race between hole punch and page fault Jan Kara
2021-05-12 15:19 ` Jeff Layton
2021-05-12 13:46 ` [PATCH 11/11] cifs: " Jan Kara
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=20210512134631.4053-8-jack@suse.cz \
--to=jack@suse.cz \
--cc=ceph-devel@vger.kernel.org \
--cc=damien.lemoal@wdc.com \
--cc=darrick.wong@oracle.com \
--cc=david@fromorbit.com \
--cc=hch@infradead.org \
--cc=jaegeuk@kernel.org \
--cc=jlayton@kernel.org \
--cc=jth@kernel.org \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=sfrench@samba.org \
--cc=tytso@mit.edu \
--cc=willy@infradead.org \
--cc=yuchao0@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).