Date:   Tue, 21 Mar 2023 09:12:51 +0900
From:   Yonggil Song <yonggil.song@...sung.com>
To:     "jaegeuk@...nel.org" <jaegeuk@...nel.org>,
        "chao@...nel.org" <chao@...nel.org>,
        "linux-f2fs-devel@...ts.sourceforge.net" 
        <linux-f2fs-devel@...ts.sourceforge.net>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: [PATCH v2] f2fs: Fix system crash due to lack of free space in LFS

When f2fs tries to checkpoint during foreground gc in LFS mode, system
crash occurs due to lack of free space if the amount of dirty node and
dentry pages generated by data migration exceeds free space.
The reproduction sequence is as follows.

 - 20GiB capacity block device (null_blk)
 - format and mount with LFS mode
 - create a file and write 20,000MiB
 - 4k random write on full range of the file

 RIP: 0010:new_curseg+0x48a/0x510 [f2fs]
 Code: 55 e7 f5 89 c0 48 0f af c3 48 8b 5d c0 48 c1 e8 20 83 c0 01 89 43 6c 48 83 c4 28 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc <0f> 0b f0 41 80 4f 48 04 45 85 f6 0f 84 ba fd ff ff e9 ef fe ff ff
 RSP: 0018:ffff977bc397b218 EFLAGS: 00010246
 RAX: 00000000000027b9 RBX: 0000000000000000 RCX: 00000000000027c0
 RDX: 0000000000000000 RSI: 00000000000027b9 RDI: ffff8c25ab4e74f8
 RBP: ffff977bc397b268 R08: 00000000000027b9 R09: ffff8c29e4a34b40
 R10: 0000000000000001 R11: ffff977bc397b0d8 R12: 0000000000000000
 R13: ffff8c25b4dd81a0 R14: 0000000000000000 R15: ffff8c2f667f9000
 FS: 0000000000000000(0000) GS:ffff8c344ec80000(0000) knlGS:0000000000000000
 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000c00055d000 CR3: 0000000e30810003 CR4: 00000000003706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
 <TASK>
 allocate_segment_by_default+0x9c/0x110 [f2fs]
 f2fs_allocate_data_block+0x243/0xa30 [f2fs]
 ? __mod_lruvec_page_state+0xa0/0x150
 do_write_page+0x80/0x160 [f2fs]
 f2fs_do_write_node_page+0x32/0x50 [f2fs]
 __write_node_page+0x339/0x730 [f2fs]
 f2fs_sync_node_pages+0x5a6/0x780 [f2fs]
 block_operations+0x257/0x340 [f2fs]
 f2fs_write_checkpoint+0x102/0x1050 [f2fs]
 f2fs_gc+0x27c/0x630 [f2fs]
 ? folio_mark_dirty+0x36/0x70
 f2fs_balance_fs+0x16f/0x180 [f2fs]

This patch adds checking whether free sections are enough before checkpoint
during gc.

Signed-off-by: Yonggil Song <yonggil.song@...sung.com>
---
 fs/f2fs/gc.c      | 10 ++++++++--
 fs/f2fs/gc.h      |  2 ++
 fs/f2fs/segment.h | 27 ++++++++++++++++++++++-----
 3 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 4546e01b2ee0..dd563866d3c9 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1773,6 +1773,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control)
 		.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
 	};
 	unsigned int skipped_round = 0, round = 0;
+	unsigned int need_lower = 0, need_upper = 0;
 
 	trace_f2fs_gc_begin(sbi->sb, gc_type, gc_control->no_bg_gc,
 				gc_control->nr_free_secs,
@@ -1858,8 +1859,13 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control)
 		}
 	}
 
-	/* Write checkpoint to reclaim prefree segments */
-	if (free_sections(sbi) < NR_CURSEG_PERSIST_TYPE &&
+	ret = get_need_secs(sbi, &need_lower, &need_upper);
+
+	/*
+	 * Write checkpoint to reclaim prefree segments.
+	 * We need more three extra sections for writer's data/node/dentry.
+	 */
+	if (free_sections(sbi) <= need_upper + NR_GC_CHECKPOINT_SECS &&
 				prefree_segments(sbi)) {
 		ret = f2fs_write_checkpoint(sbi, &cpc);
 		if (ret)
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 19b956c2d697..e81d22bf3772 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -30,6 +30,8 @@
 /* Search max. number of dirty segments to select a victim segment */
 #define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */
 
+#define NR_GC_CHECKPOINT_SECS (3)	/* data/node/dentry sections */
+
 struct f2fs_gc_kthread {
 	struct task_struct *f2fs_gc_task;
 	wait_queue_head_t gc_wait_queue_head;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index be8f2d7d007b..52a6d1ed4f24 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -605,8 +605,12 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
 	return true;
 }
 
-static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
-					int freed, int needed)
+/*
+ * calculate needed sections for dirty node/dentry
+ * and call has_curseg_enough_space
+ */
+static inline bool get_need_secs(struct f2fs_sb_info *sbi,
+				  unsigned int *lower, unsigned int *upper)
 {
 	unsigned int total_node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
 					get_pages(sbi, F2FS_DIRTY_DENTS) +
@@ -616,20 +620,33 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
 	unsigned int dent_secs = total_dent_blocks / CAP_BLKS_PER_SEC(sbi);
 	unsigned int node_blocks = total_node_blocks % CAP_BLKS_PER_SEC(sbi);
 	unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi);
+
+	*lower = node_secs + dent_secs;
+	*upper = *lower + (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0);
+
+	return !has_curseg_enough_space(sbi, node_blocks, dent_blocks);
+}
+
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
+					int freed, int needed)
+{
 	unsigned int free, need_lower, need_upper;
+	bool curseg_enough;
 
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
+	curseg_enough = get_need_secs(sbi, &need_lower, &need_upper);
+
 	free = free_sections(sbi) + freed;
-	need_lower = node_secs + dent_secs + reserved_sections(sbi) + needed;
-	need_upper = need_lower + (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0);
+	need_lower += (needed + reserved_sections(sbi));
+	need_upper += (needed + reserved_sections(sbi));
 
 	if (free > need_upper)
 		return false;
 	else if (free <= need_lower)
 		return true;
-	return !has_curseg_enough_space(sbi, node_blocks, dent_blocks);
+	return curseg_enough;
 }
 
 static inline bool f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
-- 
2.34.1

Powered by blists - more mailing lists