bfq_setup_cooperator() uses bfqd->in_serv_last_pos so detect whether it
makes sense to merge current bfq queue with the in-service queue.
However if the in-service queue is freshly scheduled and didn't dispatch
any requests yet, bfqd->in_serv_last_pos is stale and contains value
from the previously scheduled bfq queue which can thus result in a bogus
decision that the two queues should be merged. This bug can be observed
for example with the following fio jobfile:

[global]
direct=0
ioengine=sync
invalidate=1
size=1g
rw=read

[reader]
numjobs=4
directory=/mnt

where the 4 processes will end up in the one shared bfq queue although
they do IO to physically very distant files (for some reason I was able to
observe this only with slice_idle=1ms setting).

Fix the problem by invalidating bfqd->in_serv_last_pos when switching
in-service queue.

Fixes: 058fdecc6de7 ("block, bfq: fix in-service-queue check for queue merging")
CC: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 block/bfq-iosched.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 3d411716d7ee..50017275915f 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c

@@ -2937,6 +2937,7 @@ static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
 	}
 
 	bfqd->in_service_queue = bfqq;
+	bfqd->in_serv_last_pos = 0;
 }
 
 /*

-- 
2.16.4