mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Zhang Yi <yi.zhang@huawei.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,
	ojaswin@linux.ibm.com, ritesh.list@gmail.com, hch@infradead.org,
	djwong@kernel.org, yi.zhang@huawei.com, yi.zhang@huaweicloud.com,
	yizhang089@gmail.com, libaokun1@huawei.com, yangerkun@huawei.com,
	yukuai@fnnas.com
Subject: [PATCH -next v2 17/22] ext4: implement partial block zero range iomap path
Date: Tue,  3 Feb 2026 14:25:17 +0800	[thread overview]
Message-ID: <20260203062523.3869120-18-yi.zhang@huawei.com> (raw)
In-Reply-To: <20260203062523.3869120-1-yi.zhang@huawei.com>

Introduce a new iomap_ops instance, ext4_iomap_zero_ops, along with
ext4_iomap_block_zero_range() to implement the iomap block zeroing range
for ext4. ext4_iomap_block_zero_range() invokes iomap_zero_range() and
passes ext4_iomap_zero_begin() to locate and zero out a mapped partial
block or a dirty, unwritten partial block.

Note that zeroing out under an active handle can cause deadlock since
the order of acquiring the folio lock and starting a handle is
inconsistent with the iomap iteration procedure. Therefore,
ext4_iomap_block_zero_range() cannot be called under an active handle.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
 fs/ext4/inode.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 85 insertions(+)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0d2852159fa3..c59f3adba0f3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4107,6 +4107,50 @@ static int ext4_iomap_buffered_da_write_end(struct inode *inode, loff_t offset,
 	return 0;
 }
 
+static int ext4_iomap_zero_begin(struct inode *inode,
+		loff_t offset, loff_t length, unsigned int flags,
+		struct iomap *iomap, struct iomap *srcmap)
+{
+	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
+	struct ext4_map_blocks map;
+	u8 blkbits = inode->i_blkbits;
+	unsigned int iomap_flags = 0;
+	int ret;
+
+	ret = ext4_emergency_state(inode->i_sb);
+	if (unlikely(ret))
+		return ret;
+
+	if (WARN_ON_ONCE(!(flags & IOMAP_ZERO)))
+		return -EINVAL;
+
+	ret = ext4_iomap_map_blocks(inode, offset, length, NULL, &map);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Look up dirty folios for unwritten mappings within EOF. Providing
+	 * this bypasses the flush iomap uses to trigger extent conversion
+	 * when unwritten mappings have dirty pagecache in need of zeroing.
+	 */
+	if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+		loff_t offset = ((loff_t)map.m_lblk) << blkbits;
+		loff_t end = ((loff_t)map.m_lblk + map.m_len) << blkbits;
+
+		iomap_fill_dirty_folios(iter, &offset, end, &iomap_flags);
+		if ((offset >> blkbits) < map.m_lblk + map.m_len)
+			map.m_len = (offset >> blkbits) - map.m_lblk;
+	}
+
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
+	iomap->flags |= iomap_flags;
+
+	return 0;
+}
+
+const struct iomap_ops ext4_iomap_zero_ops = {
+	.iomap_begin = ext4_iomap_zero_begin,
+};
 
 const struct iomap_ops ext4_iomap_buffered_write_ops = {
 	.iomap_begin = ext4_iomap_buffered_write_begin,
@@ -4622,6 +4666,32 @@ static int ext4_journalled_block_zero_range(struct inode *inode, loff_t from,
 	return err;
 }
 
+static int ext4_iomap_block_zero_range(struct inode *inode, loff_t from,
+				       loff_t length, bool *did_zero)
+{
+	/*
+	 * Zeroing out under an active handle can cause deadlock since
+	 * the order of acquiring the folio lock and starting a handle is
+	 * inconsistent with the iomap writeback procedure.
+	 */
+	if (WARN_ON_ONCE(ext4_handle_valid(journal_current_handle())))
+		return -EINVAL;
+
+	/* The zeroing scope should not extend across a block. */
+	if (WARN_ON_ONCE((from >> inode->i_blkbits) !=
+			 ((from + length - 1) >> inode->i_blkbits)))
+		return -EINVAL;
+
+	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS) &&
+	    !(inode_state_read_once(inode) & (I_NEW | I_FREEING)))
+		WARN_ON_ONCE(!inode_is_locked(inode) &&
+			!rwsem_is_locked(&inode->i_mapping->invalidate_lock));
+
+	return iomap_zero_range(inode, from, length, did_zero,
+				&ext4_iomap_zero_ops,
+				&ext4_iomap_write_ops, NULL);
+}
+
 /*
  * ext4_block_zero_page_range() zeros out a mapping of length 'length'
  * starting from file offset 'from'.  The range to be zero'd must
@@ -4650,6 +4720,9 @@ static int ext4_block_zero_page_range(struct address_space *mapping,
 	} else if (ext4_should_journal_data(inode)) {
 		return ext4_journalled_block_zero_range(inode, from,
 							length, did_zero);
+	} else if (ext4_inode_buffered_iomap(inode)) {
+		return ext4_iomap_block_zero_range(inode, from, length,
+						   did_zero);
 	}
 	return ext4_block_zero_range(inode, from, length, did_zero);
 }
@@ -5063,6 +5136,18 @@ int ext4_truncate(struct inode *inode)
 			err = zero_len;
 			goto out_trace;
 		}
+		/*
+		 * inodes using the iomap buffered I/O path do not use the
+		 * ordered data mode, it is necessary to write out zeroed data
+		 * before the updating i_disksize transaction is committed.
+		 */
+		if (zero_len > 0 && ext4_inode_buffered_iomap(inode)) {
+			err = filemap_write_and_wait_range(mapping,
+					inode->i_size,
+					inode->i_size + zero_len - 1);
+			if (err)
+				return err;
+		}
 	}
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-- 
2.52.0


  parent reply	other threads:[~2026-02-03  6:30 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-03  6:25 [PATCH -next v2 00/22] ext4: use iomap for regular file's buffered I/O path Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 01/22] ext4: make ext4_block_zero_page_range() pass out did_zero Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 02/22] ext4: make ext4_block_truncate_page() return zeroed length Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 03/22] ext4: only order data when partially block truncating down Zhang Yi
2026-02-03  9:59   ` Jan Kara
2026-02-04  6:42     ` Zhang Yi
2026-02-04 14:18       ` Jan Kara
2026-02-05  3:27         ` Baokun Li
2026-02-05 14:07           ` Jan Kara
2026-02-06  1:14             ` Baokun Li
2026-02-05  7:50         ` Zhang Yi
2026-02-05 15:05           ` Jan Kara
2026-02-06 11:09             ` Zhang Yi
2026-02-06 15:35               ` Jan Kara
2026-02-09  8:28                 ` Zhang Yi
2026-02-10 12:02                   ` Zhang Yi
2026-02-10 14:07                     ` Jan Kara
2026-02-10 16:11                       ` Zhang Yi
2026-02-11 11:42                         ` Jan Kara
2026-02-11 13:38                           ` Zhang Yi
2026-02-04  4:21   ` kernel test robot
2026-02-10  7:05   ` Ojaswin Mujoo
2026-02-10 15:57     ` Zhang Yi
2026-02-11 15:23       ` Ojaswin Mujoo
2026-02-03  6:25 ` [PATCH -next v2 04/22] ext4: factor out journalled block zeroing range Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 05/22] ext4: stop passing handle to ext4_journalled_block_zero_range() Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 06/22] ext4: don't zero partial block under an active handle when truncating down Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 07/22] ext4: move ext4_block_zero_page_range() out of an active handle Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 08/22] ext4: zero post EOF partial block before appending write Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 09/22] ext4: add a new iomap aops for regular file's buffered IO path Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 10/22] ext4: implement buffered read iomap path Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 11/22] ext4: pass out extent seq counter when mapping da blocks Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 12/22] ext4: implement buffered write iomap path Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 13/22] ext4: implement writeback " Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 14/22] ext4: implement mmap " Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 15/22] iomap: correct the range of a partial dirty clear Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 16/22] iomap: support invalidating partial folios Zhang Yi
2026-02-03  6:25 ` Zhang Yi [this message]
2026-02-04  0:21   ` [PATCH -next v2 17/22] ext4: implement partial block zero range iomap path kernel test robot
2026-02-03  6:25 ` [PATCH -next v2 18/22] ext4: do not order data for inodes using buffered " Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 19/22] ext4: add block mapping tracepoints for iomap buffered I/O path Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 20/22] ext4: disable online defrag when inode using " Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 21/22] ext4: partially enable iomap for the buffered I/O path of regular files Zhang Yi
2026-02-03  6:25 ` [PATCH -next v2 22/22] ext4: introduce a mount option for iomap buffered I/O path Zhang Yi
2026-02-03  6:43 ` [PATCH -next v2 00/22] ext4: use iomap for regular file's " Christoph Hellwig
2026-02-03  9:18   ` Zhang Yi
2026-02-03 13:14     ` Theodore Tso
2026-02-04  1:33       ` Zhang Yi
2026-02-04  1:59       ` Baokun Li
2026-02-04 14:23         ` Jan Kara
2026-02-05  2:06           ` Zhang Yi
2026-02-05  3:04             ` Baokun Li
2026-02-05 12:58             ` Jan Kara
2026-02-06  2:15               ` Zhang Yi
2026-02-05  2:55           ` Baokun Li
2026-02-05 12:46             ` 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=20260203062523.3869120-18-yi.zhang@huawei.com \
    --to=yi.zhang@huawei.com \
    --cc=adilger.kernel@dilger.ca \
    --cc=djwong@kernel.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=libaokun1@huawei.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ojaswin@linux.ibm.com \
    --cc=ritesh.list@gmail.com \
    --cc=tytso@mit.edu \
    --cc=yangerkun@huawei.com \
    --cc=yi.zhang@huaweicloud.com \
    --cc=yizhang089@gmail.com \
    --cc=yukuai@fnnas.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

all inboxes | Powered by JetHome®