linux-kernel - [PATCH -next v2 21/22] ext4: partially enable iomap for the buffered I/O path of regular files

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20260203062523.3869120-22-yi.zhang@huawei.com>
Date: Tue,  3 Feb 2026 14:25:21 +0800
From: Zhang Yi <yi.zhang@...wei.com>
To: linux-ext4@...r.kernel.org
Cc: linux-fsdevel@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	tytso@....edu,
	adilger.kernel@...ger.ca,
	jack@...e.cz,
	ojaswin@...ux.ibm.com,
	ritesh.list@...il.com,
	hch@...radead.org,
	djwong@...nel.org,
	yi.zhang@...wei.com,
	yi.zhang@...weicloud.com,
	yizhang089@...il.com,
	libaokun1@...wei.com,
	yangerkun@...wei.com,
	yukuai@...as.com
Subject: [PATCH -next v2 21/22] ext4: partially enable iomap for the buffered I/O path of regular files

Partially enable iomap for the buffered I/O path of regular files. We
now support default filesystem features, mount options, and the bigalloc
feature. However, inline data, fs_verity, fs_crypt, online
defragmentation, and data=journal mode are not yet supported. Some of
these features are expected to be gradually supported in the future. The
filesystem will automatically fall back to the original buffered_head
path if these mount options or features are enabled.

Signed-off-by: Zhang Yi <yi.zhang@...wei.com>
---
 fs/ext4/ext4.h      |  1 +
 fs/ext4/ext4_jbd2.c |  1 +
 fs/ext4/ialloc.c    |  1 +
 fs/ext4/inode.c     | 36 ++++++++++++++++++++++++++++++++++++
 4 files changed, 39 insertions(+)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 520f6d5dcdab..259c6e780e65 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3064,6 +3064,7 @@ int ext4_walk_page_buffers(handle_t *handle,
 int do_journal_get_write_access(handle_t *handle, struct inode *inode,
 				struct buffer_head *bh);
 void ext4_set_inode_mapping_order(struct inode *inode);
+void ext4_enable_buffered_iomap(struct inode *inode);
 int ext4_nonda_switch(struct super_block *sb);
 #define FALL_BACK_TO_NONDELALLOC 1
 #define CONVERT_INLINE_DATA	 2
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 05e5946ed9b3..f587bfbe8423 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -16,6 +16,7 @@ int ext4_inode_journal_mode(struct inode *inode)
 	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
 	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
 	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !ext4_inode_buffered_iomap(inode) &&
 	    !test_opt(inode->i_sb, DELALLOC))) {
 		/* We do not support data journalling for encrypted data */
 		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index b20a1bf866ab..dfa6f60f67b3 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1334,6 +1334,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 		}
 	}
 
+	ext4_enable_buffered_iomap(inode);
 	ext4_set_inode_mapping_order(inode);
 
 	ext4_update_inode_fsync_trans(handle, inode, 1);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 77dcca584153..bbdd0bb3bc8b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -903,6 +903,9 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 	if (ext4_has_inline_data(inode))
 		return -ERANGE;
+	/* inodes using the iomap buffered I/O path should not go here. */
+	if (WARN_ON_ONCE(ext4_inode_buffered_iomap(inode)))
+		return -EINVAL;
 
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
@@ -2771,6 +2774,12 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
 	if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		goto out_writepages;
 
+	/* inodes using the iomap buffered I/O path should not go here. */
+	if (WARN_ON_ONCE(ext4_inode_buffered_iomap(inode))) {
+		ret = -EINVAL;
+		goto out_writepages;
+	}
+
 	/*
 	 * If the filesystem has aborted, it is read-only, so return
 	 * right away instead of dumping stack traces later on that
@@ -5730,6 +5739,31 @@ static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
 	return -EFSCORRUPTED;
 }
 
+void ext4_enable_buffered_iomap(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
+		return;
+
+	/* Unsupported Features */
+	if (ext4_has_feature_inline_data(sb))
+		return;
+	if (ext4_has_feature_verity(sb))
+		return;
+	if (ext4_has_feature_encrypt(sb))
+		return;
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
+		return;
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return;
+
+	ext4_set_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+}
+
 void ext4_set_inode_mapping_order(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
@@ -6015,6 +6049,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	if (ret)
 		goto bad_inode;
 
+	ext4_enable_buffered_iomap(inode);
+
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
 		inode->i_fop = &ext4_file_operations;
-- 
2.52.0