dm cache: fix race when issuing a POLICY_REPLACE operation
There is a race between a policy deciding to replace a cache entry,
the core target writing back any dirty data from this block, and other
IO threads doing IO to the same block.
This sort of problem is avoided most of the time by the core target
grabbing a bio prison cell before making the request to the policy.
But for a demotion the core target doesn't know which block will be
demoted, so can't do this in advance.
Fix this demotion race by introducing a callback to the policy interface
that allows the policy to grab the cell on behalf of the core target.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index 3ddd116..515d44b 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -693,9 +693,10 @@
* - set the hit count to a hard coded value other than 1, eg, is it better
* if it goes in at level 2?
*/
-static int demote_cblock(struct mq_policy *mq, dm_oblock_t *oblock)
+static int demote_cblock(struct mq_policy *mq,
+ struct policy_locker *locker, dm_oblock_t *oblock)
{
- struct entry *demoted = pop(mq, &mq->cache_clean);
+ struct entry *demoted = peek(&mq->cache_clean);
if (!demoted)
/*
@@ -707,6 +708,13 @@
*/
return -ENOSPC;
+ if (locker->fn(locker, demoted->oblock))
+ /*
+ * We couldn't lock the demoted block.
+ */
+ return -EBUSY;
+
+ del(mq, demoted);
*oblock = demoted->oblock;
free_entry(&mq->cache_pool, demoted);
@@ -795,6 +803,7 @@
* finding which cache block to use.
*/
static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e,
+ struct policy_locker *locker,
struct policy_result *result)
{
int r;
@@ -803,11 +812,12 @@
/* Ensure there's a free cblock in the cache */
if (epool_empty(&mq->cache_pool)) {
result->op = POLICY_REPLACE;
- r = demote_cblock(mq, &result->old_oblock);
+ r = demote_cblock(mq, locker, &result->old_oblock);
if (r) {
result->op = POLICY_MISS;
return 0;
}
+
} else
result->op = POLICY_NEW;
@@ -829,7 +839,8 @@
static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e,
bool can_migrate, bool discarded_oblock,
- int data_dir, struct policy_result *result)
+ int data_dir, struct policy_locker *locker,
+ struct policy_result *result)
{
int r = 0;
@@ -842,7 +853,7 @@
else {
requeue(mq, e);
- r = pre_cache_to_cache(mq, e, result);
+ r = pre_cache_to_cache(mq, e, locker, result);
}
return r;
@@ -872,6 +883,7 @@
}
static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock,
+ struct policy_locker *locker,
struct policy_result *result)
{
int r;
@@ -879,7 +891,7 @@
if (epool_empty(&mq->cache_pool)) {
result->op = POLICY_REPLACE;
- r = demote_cblock(mq, &result->old_oblock);
+ r = demote_cblock(mq, locker, &result->old_oblock);
if (unlikely(r)) {
result->op = POLICY_MISS;
insert_in_pre_cache(mq, oblock);
@@ -907,11 +919,12 @@
static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock,
bool can_migrate, bool discarded_oblock,
- int data_dir, struct policy_result *result)
+ int data_dir, struct policy_locker *locker,
+ struct policy_result *result)
{
if (adjusted_promote_threshold(mq, discarded_oblock, data_dir) <= 1) {
if (can_migrate)
- insert_in_cache(mq, oblock, result);
+ insert_in_cache(mq, oblock, locker, result);
else
return -EWOULDBLOCK;
} else {
@@ -928,7 +941,8 @@
*/
static int map(struct mq_policy *mq, dm_oblock_t oblock,
bool can_migrate, bool discarded_oblock,
- int data_dir, struct policy_result *result)
+ int data_dir, struct policy_locker *locker,
+ struct policy_result *result)
{
int r = 0;
struct entry *e = hash_lookup(mq, oblock);
@@ -942,11 +956,11 @@
else if (e)
r = pre_cache_entry_found(mq, e, can_migrate, discarded_oblock,
- data_dir, result);
+ data_dir, locker, result);
else
r = no_entry_found(mq, oblock, can_migrate, discarded_oblock,
- data_dir, result);
+ data_dir, locker, result);
if (r == -EWOULDBLOCK)
result->op = POLICY_MISS;
@@ -1012,7 +1026,8 @@
static int mq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
bool can_block, bool can_migrate, bool discarded_oblock,
- struct bio *bio, struct policy_result *result)
+ struct bio *bio, struct policy_locker *locker,
+ struct policy_result *result)
{
int r;
struct mq_policy *mq = to_mq_policy(p);
@@ -1028,7 +1043,7 @@
iot_examine_bio(&mq->tracker, bio);
r = map(mq, oblock, can_migrate, discarded_oblock,
- bio_data_dir(bio), result);
+ bio_data_dir(bio), locker, result);
mutex_unlock(&mq->lock);