| 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
| ||
|
Message-ID: <20250604020850.1304633-11-yi.zhang@huaweicloud.com>
Date: Wed, 4 Jun 2025 10:08:50 +0800
From: Zhang Yi <yi.zhang@...weicloud.com>
To: linux-fsdevel@...r.kernel.org,
linux-ext4@...r.kernel.org,
linux-block@...r.kernel.org,
dm-devel@...ts.linux.dev,
linux-nvme@...ts.infradead.org,
linux-scsi@...r.kernel.org
Cc: linux-xfs@...r.kernel.org,
linux-kernel@...r.kernel.org,
hch@....de,
tytso@....edu,
djwong@...nel.org,
john.g.garry@...cle.com,
bmarzins@...hat.com,
chaitanyak@...dia.com,
shinichiro.kawasaki@....com,
brauner@...nel.org,
martin.petersen@...cle.com,
yi.zhang@...wei.com,
yi.zhang@...weicloud.com,
chengzhihao1@...wei.com,
yukuai3@...wei.com,
yangerkun@...wei.com
Subject: [PATCH 10/10] ext4: add FALLOC_FL_WRITE_ZEROES support
From: Zhang Yi <yi.zhang@...wei.com>
Add support for FALLOC_FL_WRITE_ZEROES if the underlying device enable
the unmap write zeroes operation. 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 | 66 ++++++++++++++++++++++++++++++-------
include/trace/events/ext4.h | 3 +-
2 files changed, 57 insertions(+), 12 deletions(-)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index b543a46fc809..29ce9f6287d0 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4501,6 +4501,8 @@ 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;
@@ -4513,6 +4515,17 @@ 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
*/
@@ -4549,9 +4562,7 @@ 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)
@@ -4571,6 +4582,21 @@ 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;
@@ -4636,7 +4662,11 @@ 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_WRITE_ZEROES)
+ 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)
@@ -4745,11 +4775,18 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (IS_ENCRYPTED(inode) &&
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
+ /*
+ * Don't allow writing zeroes if the underlying device does not
+ * enable the unmap write zeroes operation.
+ */
+ if (!bdev_write_zeroes_unmap(inode->i_sb->s_bdev) &&
+ (mode & FALLOC_FL_WRITE_ZEROES))
+ return -EOPNOTSUPP;
/* 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_COLLAPSE_RANGE |
+ FALLOC_FL_INSERT_RANGE | FALLOC_FL_WRITE_ZEROES))
return -EOPNOTSUPP;
inode_lock(inode);
@@ -4780,16 +4817,23 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (ret)
goto out_invalidate_lock;
- if (mode & FALLOC_FL_PUNCH_HOLE)
+ switch (mode & FALLOC_FL_MODE_MASK) {
+ case FALLOC_FL_PUNCH_HOLE:
ret = ext4_punch_hole(file, offset, len);
- else if (mode & FALLOC_FL_COLLAPSE_RANGE)
+ break;
+ case FALLOC_FL_COLLAPSE_RANGE:
ret = ext4_collapse_range(file, offset, len);
- else if (mode & FALLOC_FL_INSERT_RANGE)
+ break;
+ case FALLOC_FL_INSERT_RANGE:
ret = ext4_insert_range(file, offset, len);
- else if (mode & FALLOC_FL_ZERO_RANGE)
+ break;
+ case FALLOC_FL_ZERO_RANGE:
+ case FALLOC_FL_WRITE_ZEROES:
ret = ext4_zero_range(file, offset, len, mode);
- else
+ break;
+ default:
ret = -EOPNOTSUPP;
+ }
out_invalidate_lock:
filemap_invalidate_unlock(mapping);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 156908641e68..6f9cf2811733 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_WRITE_ZEROES, "WRITE_ZEROES"})
TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR);
TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME);
--
2.46.1
Powered by blists - more mailing lists