bfq: Split shared queues on move between cgroups

When bfqq is shared by multiple processes it can happen that one of the
processes gets moved to a different cgroup (or just starts submitting IO
for different cgroup). In case that happens we need to split the merged
bfqq as otherwise we will have IO for multiple cgroups in one bfqq and
we will just account IO time to wrong entities etc.

Similarly if the bfqq is scheduled to merge with another bfqq but the
merge didn't happen yet, cancel the merge as it need not be valid
anymore.

CC: stable@vger.kernel.org
Fixes: e6c0e1d5b810 ("block, bfq: add full hierarchical scheduling and cgroups support")
Tested-by: "yukuai (C)" <yukuai3@huawei.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220401102752.8599-3-jack@suse.cz
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 420eda2589c0ec99ea4647233fdd85a32b6b63e8..9352f3cc2377b5e38e827da4e3442a350f72c494 100644 (file)
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -743,9 +743,39 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
        }
 
        if (sync_bfqq) {
-               entity = &sync_bfqq->entity;
-               if (entity->sched_data != &bfqg->sched_data)
-                       bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+               if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) {
+                       /* We are the only user of this bfqq, just move it */
+                       if (sync_bfqq->entity.sched_data != &bfqg->sched_data)
+                               bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+               } else {
+                       struct bfq_queue *bfqq;
+
+                       /*
+                        * The queue was merged to a different queue. Check
+                        * that the merge chain still belongs to the same
+                        * cgroup.
+                        */
+                       for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq)
+                               if (bfqq->entity.sched_data !=
+                                   &bfqg->sched_data)
+                                       break;
+                       if (bfqq) {
+                               /*
+                                * Some queue changed cgroup so the merge is
+                                * not valid anymore. We cannot easily just
+                                * cancel the merge (by clearing new_bfqq) as
+                                * there may be other processes using this
+                                * queue and holding refs to all queues below
+                                * sync_bfqq->new_bfqq. Similarly if the merge
+                                * already happened, we need to detach from
+                                * bfqq now so that we cannot merge bio to a
+                                * request from the old cgroup.
+                                */
+                               bfq_put_cooperator(sync_bfqq);
+                               bfq_release_process_ref(bfqd, sync_bfqq);
+                               bic_set_bfqq(bic, NULL, 1);
+                       }
+               }
        }
 
        return bfqg;

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 7d00b21ebe5db1b0b28e04a19642ff5a8454cf35..89fe3f85eb3c9db02b20748590bfdd6c2d084db4 100644 (file)
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5315,7 +5315,7 @@ static void bfq_put_stable_ref(struct bfq_queue *bfqq)
        bfq_put_queue(bfqq);
 }
 
-static void bfq_put_cooperator(struct bfq_queue *bfqq)
+void bfq_put_cooperator(struct bfq_queue *bfqq)
 {
        struct bfq_queue *__bfqq, *next;
 

diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 3b83e3d1c2e5879af814292ba3d095f1ef3f926b..a56763045d19713220a3700362304ac068b0f05c 100644 (file)
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -979,6 +979,7 @@ void bfq_weights_tree_remove(struct bfq_data *bfqd,
 void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
                     bool compensate, enum bfqq_expiration reason);
 void bfq_put_queue(struct bfq_queue *bfqq);
+void bfq_put_cooperator(struct bfq_queue *bfqq);
 void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
 void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_schedule_dispatch(struct bfq_data *bfqd);