Received-SPF: pass (google.com: domain of linux-kernel+bounces-140071-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: Chao Yu <chao@kernel.org>
To: jaegeuk@kernel.org
Cc: linux-f2fs-devel@lists.sourceforge.net,
	linux-kernel@vger.kernel.org,
	Chao Yu <chao@kernel.org>
Subject: [PATCH v2 2/2] f2fs: introduce written_map to indicate written datas
Date: Thu, 11 Apr 2024 16:23:54 +0800
Message-Id: <20240411082354.1691820-2-chao@kernel.org>
In-Reply-To: <20240411082354.1691820-1-chao@kernel.org>
References: <20240411082354.1691820-1-chao@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Currently, __exchange_data_block() will check checkpointed state of data,
if it is not checkpointed, it will try to exchange blkaddrs directly in
dnode.

However, after commit 899fee36fac0 ("f2fs: fix to avoid data corruption
by forbidding SSR overwrite"), in order to disallow SSR allocator to
reuse all written data/node type blocks, all written blocks were set as
checkpointed.

In order to reenable metadata exchange functionality, let's introduce
written_map to indicate all written blocks including checkpointed one,
or newly written and invalidated one, and use it for SSR allocation,
and then ckpt_valid_bitmap can indicate real checkpointed status, and
we can use it correctly in __exchange_data_block().

[testcase]
xfs_io -f /mnt/f2fs/src -c "pwrite 0 2m"
xfs_io -f /mnt/f2fs/dst -c "pwrite 0 2m"
xfs_io /mnt/f2fs/src -c "fiemap -v"
xfs_io /mnt/f2fs/dst -c "fiemap -v"
f2fs_io move_range /mnt/f2fs/src /mnt/f2fs/dst 0 0 2097152
xfs_io /mnt/f2fs/src -c "fiemap -v"
xfs_io /mnt/f2fs/dst -c "fiemap -v"

[before]
/mnt/f2fs/src:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..4095]:       8445952..8450047  4096 0x1001
/mnt/f2fs/dst:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..4095]:       143360..147455    4096 0x1001

/mnt/f2fs/src:
/mnt/f2fs/dst:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..4095]:       4284416..4288511  4096 0x1001

[after]
/mnt/f2fs/src:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..4095]:       147456..151551    4096 0x1001
/mnt/f2fs/dst:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..4095]:       151552..155647    4096 0x1001

/mnt/f2fs/src:
/mnt/f2fs/dst:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..4095]:       147456..151551    4096 0x1001

Signed-off-by: Chao Yu <chao@kernel.org>
---
v2:
- introduce written_blocks in struct seg_entry for
ssr allocator.
 fs/f2fs/gc.c      |  2 +-
 fs/f2fs/segment.c | 22 ++++++++++++----------
 fs/f2fs/segment.h | 19 ++++++++++++++-----
 3 files changed, 27 insertions(+), 16 deletions(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 8852814dab7f..ea7b5ca6f09b 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -366,7 +366,7 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct victim_sel_policy *p)
 {
 	if (p->alloc_mode == SSR)
-		return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+		return get_seg_entry(sbi, segno)->written_blocks;
 
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index af716925db19..0d110908e383 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2456,12 +2456,13 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 			sbi->discard_blks--;
 
 		/*
-		 * SSR should never reuse block which is checkpointed
-		 * or newly invalidated.
+		 * if CP disabling is enable, it allows SSR to reuse newly
+		 * invalidated block, otherwise forbidding it to pretect fsyned
+		 * datas.
 		 */
 		if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
-			if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
-				se->ckpt_valid_blocks++;
+			if (!f2fs_test_and_set_bit(offset, se->written_map))
+				se->written_blocks++;
 		}
 	} else {
 		exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
@@ -2498,8 +2499,6 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 			f2fs_test_and_clear_bit(offset, se->discard_map))
 			sbi->discard_blks++;
 	}
-	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
-		se->ckpt_valid_blocks += del;
 
 	__mark_sit_entry_dirty(sbi, segno);
 
@@ -2847,11 +2846,11 @@ static void __get_segment_bitmap(struct f2fs_sb_info *sbi,
 	struct seg_entry *se = get_seg_entry(sbi, segno);
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
-	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
+	unsigned long *written_map = (unsigned long *)se->written_map;
 	int i;
 
 	for (i = 0; i < entries; i++)
-		target_map[i] = ckpt_map[i] | cur_map[i];
+		target_map[i] = ckpt_map[i] | written_map[i];
 }
 
 static int __next_free_blkoff(struct f2fs_sb_info *sbi, unsigned long *bitmap,
@@ -4512,9 +4511,9 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 #ifdef CONFIG_F2FS_CHECK_FS
-	bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * (3 + discard_map);
+	bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * (4 + discard_map);
 #else
-	bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * (2 + discard_map);
+	bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * (3 + discard_map);
 #endif
 	sit_i->bitmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL);
 	if (!sit_i->bitmap)
@@ -4529,6 +4528,9 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 		sit_i->sentries[start].ckpt_valid_map = bitmap;
 		bitmap += SIT_VBLOCK_MAP_SIZE;
 
+		sit_i->sentries[start].written_map = bitmap;
+		bitmap += SIT_VBLOCK_MAP_SIZE;
+
 #ifdef CONFIG_F2FS_CHECK_FS
 		sit_i->sentries[start].cur_valid_map_mir = bitmap;
 		bitmap += SIT_VBLOCK_MAP_SIZE;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 10f3e44f036f..71131a0b00d7 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -191,10 +191,11 @@ struct victim_sel_policy {
 };
 
 struct seg_entry {
-	unsigned int type:6;		/* segment type like CURSEG_XXX_TYPE */
-	unsigned int valid_blocks:10;	/* # of valid blocks */
-	unsigned int ckpt_valid_blocks:10;	/* # of valid blocks last cp */
-	unsigned int padding:6;		/* padding */
+	unsigned long long type:6;		/* segment type like CURSEG_XXX_TYPE */
+	unsigned long long valid_blocks:10;	/* # of valid blocks */
+	unsigned long long ckpt_valid_blocks:10;/* # of valid blocks last cp */
+	unsigned long long written_blocks:10;	/* # of written blocks */
+	unsigned long long padding:28;		/* padding */
 	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
 #ifdef CONFIG_F2FS_CHECK_FS
 	unsigned char *cur_valid_map_mir;	/* mirror of current valid bitmap */
@@ -204,6 +205,10 @@ struct seg_entry {
 	 * checkpoint pack. This information is used by the SSR mode.
 	 */
 	unsigned char *ckpt_valid_map;	/* validity bitmap of blocks last cp */
+	unsigned char *written_map;	/*
+					 * blocks were written, including newly
+					 * invalidated data
+					 */
 	unsigned char *discard_map;
 	unsigned long long mtime;	/* modification time of the segment */
 };
@@ -366,9 +371,11 @@ static inline void seg_info_from_raw_sit(struct seg_entry *se,
 					struct f2fs_sit_entry *rs)
 {
 	se->valid_blocks = GET_SIT_VBLOCKS(rs);
-	se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
+	se->ckpt_valid_blocks = se->valid_blocks;
+	se->written_blocks = se->valid_blocks;
 	memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	memcpy(se->written_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 #ifdef CONFIG_F2FS_CHECK_FS
 	memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 #endif
@@ -411,7 +418,9 @@ static inline void seg_info_to_raw_sit(struct seg_entry *se,
 	__seg_info_to_raw_sit(se, rs);
 
 	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	memcpy(se->written_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 	se->ckpt_valid_blocks = se->valid_blocks;
+	se->written_blocks = se->valid_blocks;
 }
 
 static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
-- 
2.40.1