cfq-iosched: temporarily boost queue priority for idle classes

If we're queuing REQ_PRIO IO and the task is running at an idle IO
class, then temporarily boost the priority. This prevents livelocks
due to priority inversion, when a low priority task is holding file
system resources while attempting to do IO.

An example of that is shown below. An ioniced idle task is holding
the directory mutex, while a normal priority task is trying to do
a directory lookup.

[478381.198925] ------------[ cut here ]------------
[478381.200315] INFO: task ionice:1168369 blocked for more than 120 seconds.
[478381.201324]       Not tainted 4.0.9-38_fbk5_hotfix1_2936_g85409c6 #1
[478381.202278] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[478381.203462] ionice          D ffff8803692736a8     0 1168369      1 0x00000080
[478381.203466]  ffff8803692736a8 ffff880399c21300 ffff880276adcc00 ffff880369273698
[478381.204589]  ffff880369273fd8 0000000000000000 7fffffffffffffff 0000000000000002
[478381.205752]  ffffffff8177d5e0 ffff8803692736c8 ffffffff8177cea7 0000000000000000
[478381.206874] Call Trace:
[478381.207253]  [<ffffffff8177d5e0>] ? bit_wait_io_timeout+0x80/0x80
[478381.208175]  [<ffffffff8177cea7>] schedule+0x37/0x90
[478381.208932]  [<ffffffff8177f5fc>] schedule_timeout+0x1dc/0x250
[478381.209805]  [<ffffffff81421c17>] ? __blk_run_queue+0x37/0x50
[478381.210706]  [<ffffffff810ca1c5>] ? ktime_get+0x45/0xb0
[478381.211489]  [<ffffffff8177c407>] io_schedule_timeout+0xa7/0x110
[478381.212402]  [<ffffffff810a8c2b>] ? prepare_to_wait+0x5b/0x90
[478381.213280]  [<ffffffff8177d616>] bit_wait_io+0x36/0x50
[478381.214063]  [<ffffffff8177d325>] __wait_on_bit+0x65/0x90
[478381.214961]  [<ffffffff8177d5e0>] ? bit_wait_io_timeout+0x80/0x80
[478381.215872]  [<ffffffff8177d47c>] out_of_line_wait_on_bit+0x7c/0x90
[478381.216806]  [<ffffffff810a89f0>] ? wake_atomic_t_function+0x40/0x40
[478381.217773]  [<ffffffff811f03aa>] __wait_on_buffer+0x2a/0x30
[478381.218641]  [<ffffffff8123c557>] ext4_bread+0x57/0x70
[478381.219425]  [<ffffffff8124498c>] __ext4_read_dirblock+0x3c/0x380
[478381.220467]  [<ffffffff8124665d>] ext4_dx_find_entry+0x7d/0x170
[478381.221357]  [<ffffffff8114c49e>] ? find_get_entry+0x1e/0xa0
[478381.222208]  [<ffffffff81246bd4>] ext4_find_entry+0x484/0x510
[478381.223090]  [<ffffffff812471a2>] ext4_lookup+0x52/0x160
[478381.223882]  [<ffffffff811c401d>] lookup_real+0x1d/0x60
[478381.224675]  [<ffffffff811c4698>] __lookup_hash+0x38/0x50
[478381.225697]  [<ffffffff817745bd>] lookup_slow+0x45/0xab
[478381.226941]  [<ffffffff811c690e>] link_path_walk+0x7ae/0x820
[478381.227880]  [<ffffffff811c6a42>] path_init+0xc2/0x430
[478381.228677]  [<ffffffff813e6e26>] ? security_file_alloc+0x16/0x20
[478381.229776]  [<ffffffff811c8c57>] path_openat+0x77/0x620
[478381.230767]  [<ffffffff81185c6e>] ? page_add_file_rmap+0x2e/0x70
[478381.232019]  [<ffffffff811cb253>] do_filp_open+0x43/0xa0
[478381.233016]  [<ffffffff8108c4a9>] ? creds_are_invalid+0x29/0x70
[478381.234072]  [<ffffffff811c0cb0>] do_open_execat+0x70/0x170
[478381.235039]  [<ffffffff811c1bf8>] do_execveat_common.isra.36+0x1b8/0x6e0
[478381.236051]  [<ffffffff811c214c>] do_execve+0x2c/0x30
[478381.236809]  [<ffffffff811ca392>] ? getname+0x12/0x20
[478381.237564]  [<ffffffff811c23be>] SyS_execve+0x2e/0x40
[478381.238338]  [<ffffffff81780a1d>] stub_execve+0x6d/0xa0
[478381.239126] ------------[ cut here ]------------
[478381.239915] ------------[ cut here ]------------
[478381.240606] INFO: task python2.7:1168375 blocked for more than 120 seconds.
[478381.242673]       Not tainted 4.0.9-38_fbk5_hotfix1_2936_g85409c6 #1
[478381.243653] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[478381.244902] python2.7       D ffff88005cf8fb98     0 1168375 1168248 0x00000080
[478381.244904]  ffff88005cf8fb98 ffff88016c1f0980 ffffffff81c134c0 ffff88016c1f11a0
[478381.246023]  ffff88005cf8ffd8 ffff880466cd0cbc ffff88016c1f0980 00000000ffffffff
[478381.247138]  ffff880466cd0cc0 ffff88005cf8fbb8 ffffffff8177cea7 ffff88005cf8fcc8
[478381.248252] Call Trace:
[478381.248630]  [<ffffffff8177cea7>] schedule+0x37/0x90
[478381.249382]  [<ffffffff8177d08e>] schedule_preempt_disabled+0xe/0x10
[478381.250465]  [<ffffffff8177e892>] __mutex_lock_slowpath+0x92/0x100
[478381.251409]  [<ffffffff8177e91b>] mutex_lock+0x1b/0x2f
[478381.252199]  [<ffffffff817745ae>] lookup_slow+0x36/0xab
[478381.253023]  [<ffffffff811c690e>] link_path_walk+0x7ae/0x820
[478381.253877]  [<ffffffff811aeb41>] ? try_charge+0xc1/0x700
[478381.254690]  [<ffffffff811c6a42>] path_init+0xc2/0x430
[478381.255525]  [<ffffffff813e6e26>] ? security_file_alloc+0x16/0x20
[478381.256450]  [<ffffffff811c8c57>] path_openat+0x77/0x620
[478381.257256]  [<ffffffff8115b2fb>] ? lru_cache_add_active_or_unevictable+0x2b/0xa0
[478381.258390]  [<ffffffff8117b623>] ? handle_mm_fault+0x13f3/0x1720
[478381.259309]  [<ffffffff811cb253>] do_filp_open+0x43/0xa0
[478381.260139]  [<ffffffff811d7ae2>] ? __alloc_fd+0x42/0x120
[478381.260962]  [<ffffffff811b95ac>] do_sys_open+0x13c/0x230
[478381.261779]  [<ffffffff81011393>] ? syscall_trace_enter_phase1+0x113/0x170
[478381.262851]  [<ffffffff811b96c2>] SyS_open+0x22/0x30
[478381.263598]  [<ffffffff81780532>] system_call_fastpath+0x12/0x17
[478381.264551] ------------[ cut here ]------------
[478381.265377] ------------[ cut here ]------------

Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>

2 files changed, 26 insertions, 1 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 32a283eb7274c..3cfd67d006fb4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1781,6 +1781,11 @@ get_rq:
 		rw_flags |= REQ_SYNC;
 
 	/*
+	 * Add in META/PRIO flags, if set, before we get to the IO scheduler
+	 */
+	rw_flags |= (bio->bi_rw & (REQ_META | REQ_PRIO));
+
+	/*
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 4e5978426ee79..d227ad6332426 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -141,7 +141,7 @@ struct cfq_queue {
 
 	/* io prio of this group */
 	unsigned short ioprio, org_ioprio;
-	unsigned short ioprio_class;
+	unsigned short ioprio_class, org_ioprio_class;
 
 	pid_t pid;
 
@@ -3700,6 +3700,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
 	 * elevate the priority of this queue
 	 */
 	cfqq->org_ioprio = cfqq->ioprio;
+	cfqq->org_ioprio_class = cfqq->ioprio_class;
 	cfq_clear_cfqq_prio_changed(cfqq);
 }
 
@@ -4295,6 +4296,24 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		cfq_schedule_dispatch(cfqd);
 }
 
+static void cfqq_boost_on_prio(struct cfq_queue *cfqq, int op_flags)
+{
+	/*
+	 * If REQ_PRIO is set, boost class and prio level, if it's below
+	 * BE/NORM. If prio is not set, restore the potentially boosted
+	 * class/prio level.
+	 */
+	if (!(op_flags & REQ_PRIO)) {
+		cfqq->ioprio_class = cfqq->org_ioprio_class;
+		cfqq->ioprio = cfqq->org_ioprio;
+	} else {
+		if (cfq_class_idle(cfqq))
+			cfqq->ioprio_class = IOPRIO_CLASS_BE;
+		if (cfqq->ioprio > IOPRIO_NORM)
+			cfqq->ioprio = IOPRIO_NORM;
+	}
+}
+
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
@@ -4325,6 +4344,7 @@ static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
 	cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic);
+		cfqq_boost_on_prio(cfqq, op_flags);
 
 		return __cfq_may_queue(cfqq);
 	}