Received-SPF: pass (google.com: domain of linux-kernel+bounces-40995-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Zhang Yi <yi.zhang@huaweicloud.com>
To: linux-ext4@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org,
	linux-mm@kvack.org,
	linux-kernel@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,
	zokeefe@google.com,
	yi.zhang@huawei.com,
	yi.zhang@huaweicloud.com,
	chengzhihao1@huawei.com,
	yukuai3@huawei.com,
	wangkefeng.wang@huawei.com
Subject: [RFC PATCH v3 15/26] ext4: introduce seq counter for extent entry
Date: Sat, 27 Jan 2024 09:58:14 +0800
Message-Id: <20240127015825.1608160-16-yi.zhang@huaweicloud.com>
In-Reply-To: <20240127015825.1608160-1-yi.zhang@huaweicloud.com>
References: <20240127015825.1608160-1-yi.zhang@huaweicloud.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

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

Add a modify counter for extents to indicate the version of one inode's
extent status, increase it once extent changes, it will be used for
converting regular file's buffered write path to iomap.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
 fs/ext4/ext4.h              |  1 +
 fs/ext4/extents_status.c    | 13 ++++++++++++-
 fs/ext4/super.c             |  1 +
 include/trace/events/ext4.h | 19 +++++++++++++------
 4 files changed, 27 insertions(+), 7 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 55195909d32f..287284a3f128 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1115,6 +1115,7 @@ struct ext4_inode_info {
 	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
 					   extents to shrink. Protected by
 					   i_es_lock  */
+	unsigned int i_es_seq;		/* modify counter for extents */
 
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 324a6b0a6283..b0a4aa60b311 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -204,6 +204,13 @@ static inline ext4_lblk_t ext4_es_end(struct extent_status *es)
 	return es->es_lblk + es->es_len - 1;
 }
 
+static inline void ext4_es_inc_seq(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	WRITE_ONCE(ei->i_es_seq, READ_ONCE(ei->i_es_seq) + 1);
+}
+
 /*
  * search through the tree for an delayed extent with a given offset.  If
  * it can't be found, try to find next extent.
@@ -876,6 +883,7 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 		WARN_ON(1);
 	}
 
+	ext4_es_inc_seq(inode);
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, pblk, status);
@@ -1503,13 +1511,15 @@ void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
 
-	trace_ext4_es_remove_extent(inode, lblk, len);
 	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
 		 lblk, len, inode->i_ino);
 
 	if (!len)
 		return;
 
+	ext4_es_inc_seq(inode);
+	trace_ext4_es_remove_extent(inode, lblk, len);
+
 	end = lblk + len - 1;
 	BUG_ON(end < lblk);
 
@@ -2080,6 +2090,7 @@ void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
 	if (!len)
 		return;
 
+	ext4_es_inc_seq(inode);
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c5fcf377ab1f..d4afaae8ab38 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1421,6 +1421,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_es_all_nr = 0;
 	ei->i_es_shk_nr = 0;
 	ei->i_es_shrink_lblk = 0;
+	ei->i_es_seq = 0;
 	ei->i_reserved_data_blocks = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
 	ext4_init_pending_tree(&ei->i_pending_tree);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 53aa7a7fb3be..6ae504c43de7 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -2186,6 +2186,7 @@ DECLARE_EVENT_CLASS(ext4__es_extent,
 		__field(	ext4_lblk_t,	len		)
 		__field(	ext4_fsblk_t,	pblk		)
 		__field(	char, status	)
+		__field(	unsigned int,	seq		)
 	),
 
 	TP_fast_assign(
@@ -2195,13 +2196,15 @@ DECLARE_EVENT_CLASS(ext4__es_extent,
 		__entry->len	= es->es_len;
 		__entry->pblk	= ext4_es_show_pblock(es);
 		__entry->status	= ext4_es_status(es);
+		__entry->seq	= EXT4_I(inode)->i_es_seq;
 	),
 
-	TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s",
+	TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s seq %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->lblk, __entry->len,
-		  __entry->pblk, show_extent_status(__entry->status))
+		  __entry->pblk, show_extent_status(__entry->status),
+		  __entry->seq)
 );
 
 DEFINE_EVENT(ext4__es_extent, ext4_es_insert_extent,
@@ -2226,6 +2229,7 @@ TRACE_EVENT(ext4_es_remove_extent,
 		__field(	ino_t,	ino			)
 		__field(	loff_t,	lblk			)
 		__field(	loff_t,	len			)
+		__field(	unsigned int, seq		)
 	),
 
 	TP_fast_assign(
@@ -2233,12 +2237,13 @@ TRACE_EVENT(ext4_es_remove_extent,
 		__entry->ino	= inode->i_ino;
 		__entry->lblk	= lblk;
 		__entry->len	= len;
+		__entry->seq	= EXT4_I(inode)->i_es_seq;
 	),
 
-	TP_printk("dev %d,%d ino %lu es [%lld/%lld)",
+	TP_printk("dev %d,%d ino %lu es [%lld/%lld) seq %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->lblk, __entry->len)
+		  __entry->lblk, __entry->len, __entry->seq)
 );
 
 TRACE_EVENT(ext4_es_find_extent_range_enter,
@@ -2497,6 +2502,7 @@ TRACE_EVENT(ext4_es_insert_delayed_extent,
 		__field(	ext4_fsblk_t,	pblk		)
 		__field(	char,		status		)
 		__field(	bool,		allocated	)
+		__field(	unsigned int,	seq		)
 	),
 
 	TP_fast_assign(
@@ -2507,15 +2513,16 @@ TRACE_EVENT(ext4_es_insert_delayed_extent,
 		__entry->pblk		= ext4_es_show_pblock(es);
 		__entry->status		= ext4_es_status(es);
 		__entry->allocated	= allocated;
+		__entry->seq		= EXT4_I(inode)->i_es_seq;
 	),
 
 	TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s "
-		  "allocated %d",
+		  "allocated %d seq %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->lblk, __entry->len,
 		  __entry->pblk, show_extent_status(__entry->status),
-		  __entry->allocated)
+		  __entry->allocated, __entry->seq)
 );
 
 /* fsmap traces */
-- 
2.39.2