Current journal_max_cmp() and journal_min_cmp() assume that smaller fifo
index indicating elder journal entries, but this is only true when fifo
index is not swapped.
Fifo structure journal.pin is implemented by a cycle buffer, if the head
index reaches highest location of the cycle buffer, it will be swapped
to 0. Once the swapping happens, it means a smaller fifo index might be
associated to a newer journal entry. So the btree node with oldest
journal entry won't be selected by btree_flush_write() to flush out to
cache device. The result is, the oldest journal entries may always has
no chance to be written into cache device, and after a reboot
bch_journal_replay() may complain some journal entries are missing.
This patch handles the fifo index swapping conditions properly, then in
btree_flush_write() the btree node with oldest journal entry can be
slected from c->flush_btree correctly.
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Coly Li <colyli@xxxxxxx>
---
drivers/md/bcache/journal.c | 47 +++++++++++++++++++++++++++++++++++++++------
1 file changed, 41 insertions(+), 6 deletions(-)
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index bdb6f9cefe48..bc0e01151155 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -464,12 +464,47 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list)
}
/* Journalling */
-#define journal_max_cmp(l, r) \
- (fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
- fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
-#define journal_min_cmp(l, r) \
- (fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
- fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
+#define journal_max_cmp(l, r) \
+({ \
+ int l_idx, r_idx, f_idx, b_idx; \
+ bool _ret = true; \
+ \
+ l_idx = fifo_idx(&c->journal.pin, btree_current_write(l)->journal); \
+ r_idx = fifo_idx(&c->journal.pin, btree_current_write(r)->journal); \
+ f_idx = c->journal.pin.front; \
+ b_idx = c->journal.pin.back; \
+ \
+ _ret = (l_idx < r_idx); \
+ /* in case fifo back pointer is swapped */ \
+ if (b_idx < f_idx) { \
+ if (l_idx <= b_idx && r_idx >= f_idx) \
+ _ret = false; \
+ else if (l_idx >= f_idx && r_idx <= b_idx) \
+ _ret = true; \
+ } \
+ _ret; \
+})
+
+#define journal_min_cmp(l, r) \
+({ \
+ int l_idx, r_idx, f_idx, b_idx; \
+ bool _ret = true; \
+ \
+ l_idx = fifo_idx(&c->journal.pin, btree_current_write(l)->journal); \
+ r_idx = fifo_idx(&c->journal.pin, btree_current_write(r)->journal); \
+ f_idx = c->journal.pin.front; \
+ b_idx = c->journal.pin.back; \
+ \
+ _ret = (l_idx > r_idx); \
+ /* in case fifo back pointer is swapped */ \
+ if (b_idx < f_idx) { \
+ if (l_idx <= b_idx && r_idx >= f_idx) \
+ _ret = true; \
+ else if (l_idx >= f_idx && r_idx <= b_idx) \
+ _ret = false; \
+ } \
+ _ret; \
+})
static void btree_flush_write(struct cache_set *c)
{
--
2.16.4
