linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zhang Yi <yi.zhang@huaweicloud.com>
To: linux-ext4@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org, tytso@mit.edu,
	adilger.kernel@dilger.ca, jack@suse.cz, ritesh.list@gmail.com,
	hch@infradead.org, djwong@kernel.org, willy@infradead.org,
	yi.zhang@huawei.com, yi.zhang@huaweicloud.com,
	chengzhihao1@huawei.com, yukuai3@huawei.com,
	wangkefeng.wang@huawei.com
Subject: [RFC PATCH v2 12/25] ext4: factor out bh handles to ext4_da_get_block_prep()
Date: Tue,  2 Jan 2024 20:39:05 +0800	[thread overview]
Message-ID: <20240102123918.799062-13-yi.zhang@huaweicloud.com> (raw)
In-Reply-To: <20240102123918.799062-1-yi.zhang@huaweicloud.com>

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

Factor buffer_head related handles out from ext4_da_map_blocks() to
ext4_da_get_block_prep(), and make ext4_da_map_blocks() always return 0
if success, we can distinguish delalloc map through EXT4_MAP_DELAYED
flag.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
 fs/ext4/inode.c | 75 ++++++++++++++++++++++++-------------------------
 1 file changed, 36 insertions(+), 39 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9ac9bb548a4c..9f9b1fce8da8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1690,48 +1690,37 @@ static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk,
  * time. This function looks up the requested blocks and sets the
  * buffer delay bit under the protection of i_data_sem.
  */
-static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
-			      struct ext4_map_blocks *map,
-			      struct buffer_head *bh)
+static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map)
 {
 	struct extent_status es;
 	int retval;
-	sector_t invalid_block = ~((sector_t) 0xffff);
 #ifdef ES_AGGRESSIVE_TEST
 	struct ext4_map_blocks orig_map;
 
 	memcpy(&orig_map, map, sizeof(*map));
 #endif
 
-	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
-		invalid_block = ~0;
-
 	map->m_flags = 0;
 	ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
 		  (unsigned long) map->m_lblk);
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
-		retval = es.es_len - (iblock - es.es_lblk);
-		if (retval > map->m_len)
-			retval = map->m_len;
-		map->m_len = retval;
-
-		if (ext4_es_is_hole(&es))
-			goto add_delayed;
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+		retval = es.es_len - (map->m_lblk - es.es_lblk);
+		map->m_len = min_t(unsigned int, map->m_len, retval);
 
 		/*
 		 * Delayed extent could be allocated by fallocate.
 		 * So we need to check it.
 		 */
-		if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
-			map_bh(bh, inode->i_sb, invalid_block);
-			set_buffer_new(bh);
-			set_buffer_delay(bh);
+		if (ext4_es_is_delonly(&es)) {
+			map->m_flags |= EXT4_MAP_DELAYED;
 			return 0;
 		}
+		if (ext4_es_is_hole(&es))
+			goto add_delayed;
 
-		map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
+		map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk;
 		if (ext4_es_is_written(&es))
 			map->m_flags |= EXT4_MAP_MAPPED;
 		else if (ext4_es_is_unwritten(&es))
@@ -1743,7 +1732,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
 #endif
 		if (ext4_es_is_delayed(&es) || ext4_es_is_written(&es))
-			return retval;
+			return 0;
 
 		down_read(&EXT4_I(inode)->i_data_sem);
 		goto insert_extent;
@@ -1775,6 +1764,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 			WARN_ON(1);
 		}
 insert_extent:
+		retval = 0;
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		if (status == EXTENT_STATUS_UNWRITTEN)
@@ -1788,14 +1778,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 
 add_delayed:
 	down_write(&EXT4_I(inode)->i_data_sem);
+	map->m_flags |= EXT4_MAP_DELAYED;
 	retval = ext4_insert_delayed_blocks(inode, map->m_lblk, map->m_len);
 	up_write(&EXT4_I(inode)->i_data_sem);
-	if (retval)
-		return retval;
 
-	map_bh(bh, inode->i_sb, invalid_block);
-	set_buffer_new(bh);
-	set_buffer_delay(bh);
 	return retval;
 }
 
@@ -1815,11 +1801,15 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int create)
 {
 	struct ext4_map_blocks map;
+	sector_t invalid_block = ~((sector_t) 0xffff);
 	int ret = 0;
 
 	BUG_ON(create == 0);
 	BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
 
+	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+		invalid_block = ~0;
+
 	map.m_lblk = iblock;
 	map.m_len = 1;
 
@@ -1828,22 +1818,29 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 	 * preallocated blocks are unmapped but should treated
 	 * the same as allocated blocks.
 	 */
-	ret = ext4_da_map_blocks(inode, iblock, &map, bh);
-	if (ret <= 0)
+	ret = ext4_da_map_blocks(inode, &map);
+	if (ret < 0)
 		return ret;
 
-	map_bh(bh, inode->i_sb, map.m_pblk);
-	ext4_update_bh_state(bh, map.m_flags);
-
-	if (buffer_unwritten(bh)) {
-		/* A delayed write to unwritten bh should be marked
-		 * new and mapped.  Mapped ensures that we don't do
-		 * get_block multiple times when we write to the same
-		 * offset and new ensures that we do proper zero out
-		 * for partial write.
-		 */
+	if (map.m_flags & EXT4_MAP_DELAYED) {
+		map_bh(bh, inode->i_sb, invalid_block);
 		set_buffer_new(bh);
-		set_buffer_mapped(bh);
+		set_buffer_delay(bh);
+	} else {
+		map_bh(bh, inode->i_sb, map.m_pblk);
+		ext4_update_bh_state(bh, map.m_flags);
+
+		if (buffer_unwritten(bh)) {
+			/*
+			 * A delayed write to unwritten bh should be marked
+			 * new and mapped.  Mapped ensures that we don't do
+			 * get_block multiple times when we write to the same
+			 * offset and new ensures that we do proper zero out
+			 * for partial write.
+			 */
+			set_buffer_new(bh);
+			set_buffer_mapped(bh);
+		}
 	}
 	return 0;
 }
-- 
2.39.2


  parent reply	other threads:[~2024-01-02 12:42 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-02 12:38 [RFC PATCH v2 00/25] ext4: use iomap for regular file's buffered IO path and enable large foilo Zhang Yi
2024-01-02 12:38 ` [RFC PATCH v2 01/25] ext4: refactor ext4_da_map_blocks() Zhang Yi
2024-01-03  9:56   ` Jan Kara
2024-01-02 12:38 ` [RFC PATCH v2 02/25] ext4: convert to exclusive lock while inserting delalloc extents Zhang Yi
2024-01-03 10:03   ` Jan Kara
2024-01-02 12:38 ` [RFC PATCH v2 03/25] ext4: correct the hole length returned by ext4_map_blocks() Zhang Yi
2024-01-03 11:02   ` Jan Kara
2024-01-02 12:38 ` [RFC PATCH v2 04/25] ext4: add a hole extent entry in cache after punch Zhang Yi
2024-01-03 11:04   ` Jan Kara
2024-01-02 12:38 ` [RFC PATCH v2 05/25] ext4: make ext4_map_blocks() distinguish delalloc only extent Zhang Yi
2024-01-03 11:31   ` Jan Kara
2024-01-03 13:20     ` Zhang Yi
2024-01-02 12:38 ` [RFC PATCH v2 06/25] ext4: make ext4_set_iomap() recognize IOMAP_DELALLOC map type Zhang Yi
2024-01-03 11:35   ` Jan Kara
2024-01-02 12:39 ` [RFC PATCH v2 07/25] iomap: don't increase i_size if it's not a write operation Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 08/25] iomap: add pos and dirty_len into trace_iomap_writepage_map Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 09/25] ext4: allow inserting delalloc extents with multi-blocks Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 10/25] ext4: correct delalloc extent length Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 11/25] ext4: also mark extent as delalloc if it's been unwritten Zhang Yi
2024-01-02 12:39 ` Zhang Yi [this message]
2024-01-02 12:39 ` [RFC PATCH v2 13/25] ext4: use reserved metadata blocks when splitting extent in endio Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 14/25] ext4: introduce seq counter for extent entry Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 15/25] ext4: add a new iomap aops for regular file's buffered IO path Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 16/25] ext4: implement buffered read iomap path Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 17/25] ext4: implement buffered write " Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 18/25] ext4: implement writeback " Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 19/25] ext4: implement mmap " Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 20/25] ext4: implement zero_range " Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 21/25] ext4: writeback partial blocks before zero range Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 22/25] ext4: fall back to buffer_head path for defrag Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 23/25] ext4: partially enable iomap for regular file's buffered IO path Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 24/25] filemap: support disable large folios on active inode Zhang Yi
2024-01-02 12:39 ` [RFC PATCH v2 25/25] ext4: enable large folio for regular file with iomap buffered IO path Zhang Yi

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=20240102123918.799062-13-yi.zhang@huaweicloud.com \
    --to=yi.zhang@huaweicloud.com \
    --cc=adilger.kernel@dilger.ca \
    --cc=chengzhihao1@huawei.com \
    --cc=djwong@kernel.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=ritesh.list@gmail.com \
    --cc=tytso@mit.edu \
    --cc=wangkefeng.wang@huawei.com \
    --cc=willy@infradead.org \
    --cc=yi.zhang@huawei.com \
    --cc=yukuai3@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).