linux-kernel - [RFC PATCH 2/2] ext4: add FALLOC_FL_FORCE

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] [day] [month] [year] [list]

Message-Id: <20241228014522.2395187-3-yi.zhang@huaweicloud.com>
Date: Sat, 28 Dec 2024 09:45:22 +0800
From: Zhang Yi <yi.zhang@...weicloud.com>
To: linux-fsdevel@...r.kernel.org,
	linux-ext4@...r.kernel.org
Cc: linux-kernel@...r.kernel.org,
	viro@...iv.linux.org.uk,
	brauner@...nel.org,
	jack@...e.cz,
	tytso@....edu,
	djwong@...nel.org,
	adilger.kernel@...ger.ca,
	yi.zhang@...wei.com,
	yi.zhang@...weicloud.com,
	chengzhihao1@...wei.com,
	yukuai3@...wei.com,
	yangerkun@...wei.com
Subject: [RFC PATCH 2/2] ext4: add FALLOC_FL_FORCE_ZERO support

From: Zhang Yi <yi.zhang@...wei.com>

Add support for FALLOC_FL_FORCE_ZERO. This first allocates blocks as
unwritten, then issues a zero command outside of the running journal
handle, and finally converts them to a written state.

Signed-off-by: Zhang Yi <yi.zhang@...wei.com>
---
 fs/ext4/extents.c           | 42 +++++++++++++++++++++++++++++++------
 include/trace/events/ext4.h |  3 ++-
 2 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 1b028be19193..dcb3ef4ca1d4 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4483,6 +4483,8 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	struct ext4_map_blocks map;
 	unsigned int credits;
 	loff_t epos, old_size = i_size_read(inode);
+	unsigned int blkbits = inode->i_blkbits;
+	bool alloc_zero = false;
 
 	BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS));
 	map.m_lblk = offset;
@@ -4495,6 +4497,17 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	if (len <= EXT_UNWRITTEN_MAX_LEN)
 		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
+	/*
+	 * Do the actual write zero during a running journal transaction
+	 * costs a lot. First allocate an unwritten extent and then
+	 * convert it to written after zeroing it out.
+	 */
+	if (flags & EXT4_GET_BLOCKS_ZERO) {
+		flags &= ~EXT4_GET_BLOCKS_ZERO;
+		flags |= EXT4_GET_BLOCKS_UNWRIT_EXT;
+		alloc_zero = true;
+	}
+
 	/*
 	 * credits to insert 1 extent into extent tree
 	 */
@@ -4531,9 +4544,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 		 * allow a full retry cycle for any remaining allocations
 		 */
 		retries = 0;
-		map.m_lblk += ret;
-		map.m_len = len = len - ret;
-		epos = (loff_t)map.m_lblk << inode->i_blkbits;
+		epos = (loff_t)(map.m_lblk + ret) << blkbits;
 		inode_set_ctime_current(inode);
 		if (new_size) {
 			if (epos > new_size)
@@ -4553,6 +4564,21 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 		ret2 = ret3 ? ret3 : ret2;
 		if (unlikely(ret2))
 			break;
+
+		if (alloc_zero &&
+		    (map.m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN))) {
+			ret2 = ext4_issue_zeroout(inode, map.m_lblk, map.m_pblk,
+						  map.m_len);
+			if (likely(!ret2))
+				ret2 = ext4_convert_unwritten_extents(NULL,
+					inode, (loff_t)map.m_lblk << blkbits,
+					(loff_t)map.m_len << blkbits);
+			if (ret2)
+				break;
+		}
+
+		map.m_lblk += ret;
+		map.m_len = len = len - ret;
 	}
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
@@ -4618,7 +4644,11 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	if (end_lblk > start_lblk) {
 		ext4_lblk_t zero_blks = end_lblk - start_lblk;
 
-		flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE);
+		if (mode & FALLOC_FL_FORCE_ZERO)
+			flags = EXT4_GET_BLOCKS_CREATE_ZERO | EXT4_EX_NOCACHE;
+		else
+			flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
+				  EXT4_EX_NOCACHE);
 		ret = ext4_alloc_file_blocks(file, start_lblk, zero_blks,
 					     new_size, flags);
 		if (ret)
@@ -4730,8 +4760,8 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 
 	/* Return error if mode is not supported */
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
-		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
-		     FALLOC_FL_INSERT_RANGE))
+		     FALLOC_FL_ZERO_RANGE | FALLOC_FL_FORCE_ZERO |
+		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
 
 	inode_lock(inode);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 156908641e68..1ac29dc637a9 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -92,7 +92,8 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 	{ FALLOC_FL_KEEP_SIZE,		"KEEP_SIZE"},		\
 	{ FALLOC_FL_PUNCH_HOLE,		"PUNCH_HOLE"},		\
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
-	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
+	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"},		\
+	{ FALLOC_FL_FORCE_ZERO,		"FORCE_ZERO"})
 
 TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR);
 TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME);
-- 
2.39.2