[PATCH v3] f2fs: drop pending discard commands before reserving device alias

[Daeho Jeong]

From: Daeho Jeong <daehojeong@xxxxxxxxxx>

When reserving a device alias via f2fs_ioc_reserve_dev_alias(),
f2fs_reserve_device_alias() bulk-marks all blocks in the target device
range as valid in SIT.

However, if the device was previously in the released state, stale
pending discard commands covering that range may still exist in dcc->root.
When f2fs_issue_discard_thread later processes those commands,
__check_sit_bitmap() detects valid blocks in the discard range and
triggers a kernel BUG().

To fix this:
1. Introduce f2fs_drop_discard_cmd_range() to traverse the discard rbtree,
   drop all pending D_PREP discard commands in the range,
   and wait for any in-flight discard bios under dcc->cmd_lock.
2. Call f2fs_drop_discard_cmd_range() in f2fs_ioc_reserve_dev_alias()
   before f2fs_reserve_device_alias().

Reported-by: Wenjie Qi <qiwenjie@xxxxxxxxxx>
Fixes: eae3faf210bd ("f2fs: support dynamic reserve/release for device aliasing")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Daeho Jeong <daehojeong@xxxxxxxxxx>
---
v3: introduce cur to prevent 32-bit overflow.
v2: fix use-after-free and 32-bit overflow issues.
---
 fs/f2fs/f2fs.h    |  2 ++
 fs/f2fs/file.c    |  1 +
 fs/f2fs/segment.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 511286432483..ae109d3ae571 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4122,6 +4122,8 @@ void f2fs_reserve_device_alias(struct f2fs_sb_info *sbi, block_t addr,
 bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
 int f2fs_start_discard_thread(struct f2fs_sb_info *sbi);
 void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
+void f2fs_drop_discard_cmd_range(struct f2fs_sb_info *sbi,
+					block_t start, block_t len);
 void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
 bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi, bool need_check);
 void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 29cf82d02c77..0b2d173d9597 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -3855,6 +3855,7 @@ static int f2fs_ioc_reserve_dev_alias(struct file *filp)
 	write_unlock(&et->lock);
 	clear_inode_flag(inode, FI_NO_EXTENT);
 
+	f2fs_drop_discard_cmd_range(sbi, ei.blk, ei.len);
 	f2fs_reserve_device_alias(sbi, ei.blk, ei.len);
 
 	i_size_write(inode, (loff_t)ei.len << sbi->log_blocksize);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index ac0ed8609c1f..6826cb7ab34d 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1873,6 +1873,51 @@ static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
 	return discard_blks;
 }
 
+void f2fs_drop_discard_cmd_range(struct f2fs_sb_info *sbi,
+					block_t start, block_t len)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	struct discard_cmd *dc, *wait_dc;
+	u64 cur = start;
+	u64 end = (u64)start + len;
+
+	if (!f2fs_realtime_discard_enable(sbi))
+		return;
+
+next:
+	wait_dc = NULL;
+
+	mutex_lock(&dcc->cmd_lock);
+	while (cur < end) {
+		dc = __lookup_discard_cmd_ret(&dcc->root, cur,
+				&prev_dc, &next_dc, &insert_p, &insert_parent);
+		if (!dc)
+			dc = next_dc;
+
+		if (!dc || (u64)dc->di.lstart >= end)
+			break;
+
+		if (dc->state == D_PREP) {
+			cur = (u64)dc->di.lstart + dc->di.len;
+			__remove_discard_cmd(sbi, dc);
+			continue;
+		}
+
+		dc->ref++;
+		cur = (u64)dc->di.lstart + dc->di.len;
+		wait_dc = dc;
+		break;
+	}
+	mutex_unlock(&dcc->cmd_lock);
+
+	if (wait_dc) {
+		__wait_one_discard_bio(sbi, wait_dc);
+		goto next;
+	}
+}
+
 /* This should be covered by global mutex, &sit_i->sentry_lock */
 static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
-- 
2.55.0.966.g6673acef38-goog