blkcg: add generic throttling mechanism

Since IO can be issued from literally anywhere it's almost impossible to
do throttling without having some sort of adverse effect somewhere else
in the system because of locking or other dependencies.  The best way to
solve this is to do the throttling when we know we aren't holding any
other kernel resources.  Do this by tracking throttling in a per-blkg
basis, and if we require throttling flag the task that it needs to check
before it returns to user space and possibly sleep there.

This is to address the case where a process is doing work that is
generating IO that can't be throttled, whether that is directly with a
lot of REQ_META IO, or indirectly by allocating so much memory that it
is swamping the disk with REQ_SWAP.  We can't use task_add_work as we
don't want to induce a memory allocation in the IO path, so simply
saving the request queue in the task and flagging it to do the
notify_resume thing achieves the same result without the overhead of a
memory allocation.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 8 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 43731fe51c97..c2e993de67ec 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -734,6 +734,10 @@ struct task_struct {
 	/* disallow userland-initiated cgroup migration */
 	unsigned			no_cgroup_migration:1;
 #endif
+#ifdef CONFIG_BLK_CGROUP
+	/* to be used once the psi infrastructure lands upstream. */
+	unsigned			use_memdelay:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -1151,6 +1155,10 @@ struct task_struct {
 	unsigned int			memcg_nr_pages_over_high;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	struct request_queue		*throttle_queue;
+#endif
+
 #ifdef CONFIG_UPROBES
 	struct uprobe_task		*utask;
 #endif