block, scsi: Make SCSI quiesce and resume work reliably

The contexts from which a SCSI device can be quiesced or resumed are:
* Writing into /sys/class/scsi_device/*/device/state.
* SCSI parallel (SPI) domain validation.
* The SCSI device power management methods. See also scsi_bus_pm_ops.

It is essential during suspend and resume that neither the filesystem
state nor the filesystem metadata in RAM changes. This is why while
the hibernation image is being written or restored that SCSI devices
are quiesced. The SCSI core quiesces devices through scsi_device_quiesce()
and scsi_device_resume(). In the SDEV_QUIESCE state execution of
non-preempt requests is deferred. This is realized by returning
BLKPREP_DEFER from inside scsi_prep_state_check() for quiesced SCSI
devices. Avoid that a full queue prevents power management requests
to be submitted by deferring allocation of non-preempt requests for
devices in the quiesced state. This patch has been tested by running
the following commands and by verifying that after each resume the
fio job was still running:

for ((i=0; i<10; i++)); do
  (
    cd /sys/block/md0/md &&
    while true; do
      [ "$(<sync_action)" = "idle" ] && echo check > sync_action
      sleep 1
    done
  ) &
  pids=($!)
  for d in /sys/class/block/sd*[a-z]; do
    bdev=${d#/sys/class/block/}
    hcil=$(readlink "$d/device")
    hcil=${hcil#../../../}
    echo 4 > "$d/queue/nr_requests"
    echo 1 > "/sys/class/scsi_device/$hcil/device/queue_depth"
    fio --name="$bdev" --filename="/dev/$bdev" --buffered=0 --bs=512 \
      --rw=randread --ioengine=libaio --numjobs=4 --iodepth=16       \
      --iodepth_batch=1 --thread --loops=$((2**31)) &
    pids+=($!)
  done
  sleep 1
  echo "$(date) Hibernating ..." >>hibernate-test-log.txt
  systemctl hibernate
  sleep 10
  kill "${pids[@]}"
  echo idle > /sys/block/md0/md/sync_action
  wait
  echo "$(date) Done." >>hibernate-test-log.txt
done

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
References: "I/O hangs after resuming from suspend-to-ram" (https://marc.info/?l=linux-block&m=150340235201348).
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 34 insertions, 8 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index edc276899116..29b08428ae45 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -374,6 +374,7 @@ void blk_clear_preempt_only(struct request_queue *q)
 
 	spin_lock_irqsave(q->queue_lock, flags);
 	queue_flag_clear(QUEUE_FLAG_PREEMPT_ONLY, q);
+	wake_up_all(&q->mq_freeze_wq);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL_GPL(blk_clear_preempt_only);
@@ -795,15 +796,38 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_alloc_queue);
 
-int blk_queue_enter(struct request_queue *q, bool nowait)
+/**
+ * blk_queue_enter() - try to increase q->q_usage_counter
+ * @q: request queue pointer
+ * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT
+ */
+int blk_queue_enter(struct request_queue *q, unsigned int flags)
 {
+	const bool preempt = flags & BLK_MQ_REQ_PREEMPT;
+
 	while (true) {
+		bool success = false;
 		int ret;
 
-		if (percpu_ref_tryget_live(&q->q_usage_counter))
+		rcu_read_lock_sched();
+		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
+			/*
+			 * The code that sets the PREEMPT_ONLY flag is
+			 * responsible for ensuring that that flag is globally
+			 * visible before the queue is unfrozen.
+			 */
+			if (preempt || !blk_queue_preempt_only(q)) {
+				success = true;
+			} else {
+				percpu_ref_put(&q->q_usage_counter);
+			}
+		}
+		rcu_read_unlock_sched();
+
+		if (success)
 			return 0;
 
-		if (nowait)
+		if (flags & BLK_MQ_REQ_NOWAIT)
 			return -EBUSY;
 
 		/*
@@ -816,7 +840,8 @@ int blk_queue_enter(struct request_queue *q, bool nowait)
 		smp_rmb();
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
-				!atomic_read(&q->mq_freeze_depth) ||
+				(atomic_read(&q->mq_freeze_depth) == 0 &&
+				 (preempt || !blk_queue_preempt_only(q))) ||
 				blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
@@ -1445,8 +1470,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
 	/* create ioc upfront */
 	create_io_context(gfp_mask, q->node);
 
-	ret = blk_queue_enter(q, !(gfp_mask & __GFP_DIRECT_RECLAIM) ||
-			      (op & REQ_NOWAIT));
+	ret = blk_queue_enter(q, flags);
 	if (ret)
 		return ERR_PTR(ret);
 	spin_lock_irq(q->queue_lock);
@@ -2267,8 +2291,10 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bio->bi_disk->queue;
+		unsigned int flags = bio->bi_opf & REQ_NOWAIT ?
+			BLK_MQ_REQ_NOWAIT : 0;
 
-		if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
+		if (likely(blk_queue_enter(q, flags) == 0)) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -2327,7 +2353,7 @@ blk_qc_t direct_make_request(struct bio *bio)
 	if (!generic_make_request_checks(bio))
 		return BLK_QC_T_NONE;
 
-	if (unlikely(blk_queue_enter(q, nowait))) {
+	if (unlikely(blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0))) {
 		if (nowait && !blk_queue_dying(q))
 			bio->bi_status = BLK_STS_AGAIN;
 		else