From: Zhang Yi <yi.zhang@huaweicloud.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,
ritesh.list@gmail.com, yi.zhang@huawei.com,
yi.zhang@huaweicloud.com, chengzhihao1@huawei.com,
yukuai3@huawei.com
Subject: [PATCH v4 10/10] ext4: make ext4_da_map_blocks() buffer_head unaware
Date: Sat, 11 May 2024 19:26:19 +0800 [thread overview]
Message-ID: <20240511112619.3656450-11-yi.zhang@huaweicloud.com> (raw)
In-Reply-To: <20240511112619.3656450-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
After calling the ext4_da_map_blocks(), a delalloc extent state could
be identified through the EXT4_MAP_DELAYED flag in map. So factor out
buffer_head related handles in ext4_da_map_blocks(), make this function
buffer_head unaware and becomes a common helper, and also update the
stale function commtents, preparing for the iomap da write path in the
future.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/inode.c | 63 ++++++++++++++++++++++++-------------------------
1 file changed, 31 insertions(+), 32 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c56386d1b10d..1dba5337382a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1745,36 +1745,32 @@ static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk,
}
/*
- * This function is grabs code from the very beginning of
- * ext4_map_blocks, but assumes that the caller is from delayed write
- * time. This function looks up the requested blocks and sets the
- * buffer delay bit under the protection of i_data_sem.
+ * Looks up the requested blocks and sets the delalloc extent map.
+ * First try to look up for the extent entry that contains the requested
+ * blocks in the extent status tree without i_data_sem, then try to look
+ * up for the ondisk extent mapping with i_data_sem in read mode,
+ * finally hold i_data_sem in write mode, looks up again and add a
+ * delalloc extent entry if it still couldn't find any extent. Pass out
+ * the mapped extent through @map and return 0 on success.
*/
-static int ext4_da_map_blocks(struct inode *inode, 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, map->m_lblk, NULL, &es)) {
- retval = es.es_len - (map->m_lblk - es.es_lblk);
- if (retval > map->m_len)
- retval = map->m_len;
- map->m_len = retval;
+ map->m_len = min_t(unsigned int, map->m_len,
+ es.es_len - (map->m_lblk - es.es_lblk));
if (ext4_es_is_hole(&es))
goto add_delayed;
@@ -1784,10 +1780,8 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map,
* 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;
}
@@ -1802,7 +1796,7 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map,
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
#endif
- return retval;
+ return 0;
}
/*
@@ -1816,7 +1810,7 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map,
retval = ext4_map_query_blocks(NULL, inode, map);
up_read(&EXT4_I(inode)->i_data_sem);
if (retval)
- return retval;
+ return retval < 0 ? retval : 0;
add_delayed:
down_write(&EXT4_I(inode)->i_data_sem);
@@ -1828,10 +1822,8 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map,
* the extent status tree.
*/
if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
- retval = es.es_len - (map->m_lblk - es.es_lblk);
- if (retval > map->m_len)
- retval = map->m_len;
- map->m_len = retval;
+ map->m_len = min_t(unsigned int, map->m_len,
+ es.es_len - (map->m_lblk - es.es_lblk));
if (!ext4_es_is_hole(&es)) {
up_write(&EXT4_I(inode)->i_data_sem);
@@ -1841,18 +1833,14 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map,
retval = ext4_map_query_blocks(NULL, inode, map);
if (retval) {
up_write(&EXT4_I(inode)->i_data_sem);
- return retval;
+ return retval < 0 ? retval : 0;
}
}
+ 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;
}
@@ -1872,11 +1860,15 @@ 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;
@@ -1885,10 +1877,17 @@ 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, &map, bh);
- if (ret <= 0)
+ ret = ext4_da_map_blocks(inode, &map);
+ if (ret < 0)
return ret;
+ if (map.m_flags & EXT4_MAP_DELAYED) {
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ return 0;
+ }
+
map_bh(bh, inode->i_sb, map.m_pblk);
ext4_update_bh_state(bh, map.m_flags);
--
2.39.2
prev parent reply other threads:[~2024-05-11 11:37 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-11 11:26 [PATCH v4 00/10] ext4: support adding multi-delalloc blocks Zhang Yi
2024-05-11 11:26 ` [PATCH v4 01/10] ext4: factor out a common helper to query extent map Zhang Yi
2024-05-11 11:26 ` [PATCH v4 02/10] ext4: check the extent status again before inserting delalloc block Zhang Yi
2024-05-11 11:26 ` [PATCH v4 03/10] ext4: warn if delalloc counters are not zero on inactive Zhang Yi
2024-05-11 11:26 ` [PATCH v4 04/10] ext4: trim delalloc extent Zhang Yi
2024-05-11 11:26 ` [PATCH v4 05/10] ext4: drop iblock parameter Zhang Yi
2024-05-11 11:26 ` [PATCH v4 06/10] ext4: make ext4_es_insert_delayed_block() insert multi-blocks Zhang Yi
2024-05-11 11:26 ` [PATCH v4 07/10] ext4: make ext4_da_reserve_space() reserve multi-clusters Zhang Yi
2024-05-11 11:26 ` [PATCH v4 08/10] ext4: factor out check for whether a cluster is allocated Zhang Yi
2024-05-11 11:26 ` [PATCH v4 09/10] ext4: make ext4_insert_delayed_block() insert multi-blocks Zhang Yi
2024-05-11 11:26 ` Zhang Yi [this message]
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=20240511112619.3656450-11-yi.zhang@huaweicloud.com \
--to=yi.zhang@huaweicloud.com \
--cc=adilger.kernel@dilger.ca \
--cc=chengzhihao1@huawei.com \
--cc=jack@suse.cz \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ritesh.list@gmail.com \
--cc=tytso@mit.edu \
--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 read-only IMAP folder(s) and NNTP newsgroup(s).