When queue is in PREEMPT_ONLY mode, only REQ_PREEMPT request
can be allocated and dispatched, other requests won't be allowed
to enter I/O path.
This is useful for supporting safe SCSI quiesce.
Part of this patch is from Bart's '[PATCH v4 4∕7] block: Add the
QUEUE_FLAG_PREEMPT_ONLY
request queue flag'.
Tested-by: Oleksandr Natalenko <oleksa...@natalenko.name>
Tested-by: Martin Steigerwald <mar...@lichtvoll.de>
Cc: Bart Van Assche <bart.vanass...@wdc.com>
Signed-off-by: Ming Lei <ming....@redhat.com>
---
block/blk-core.c | 44 +++++++++++++++++++++++++++++++++++++++++---
include/linux/blkdev.h | 5 +++++
2 files changed, 46 insertions(+), 3 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 1bb566245d37..7849cc1687bc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -346,6 +346,34 @@ void blk_sync_queue(struct request_queue *q)
}
EXPORT_SYMBOL(blk_sync_queue);
+void blk_set_preempt_only(struct request_queue *q, bool preempt_only)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ if (preempt_only)
+ queue_flag_set(QUEUE_FLAG_PREEMPT_ONLY, q);
+ else
+ queue_flag_clear(QUEUE_FLAG_PREEMPT_ONLY, q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ /*
+ * The synchronize_rcu() implicied in blk_mq_freeze_queue()
+ * or the explicit one will make sure the above write on
+ * PREEMPT_ONLY is observed in blk_queue_enter() before
+ * running blk_mq_unfreeze_queue().
+ *
+ * blk_mq_freeze_queue() also drains up any request in queue,
+ * so blk_queue_enter() will see the above updated value of
+ * PREEMPT flag before any new allocation.
+ */
+ if (!blk_mq_freeze_queue(q))
+ synchronize_rcu();
+
+ blk_mq_unfreeze_queue(q);
+}
+EXPORT_SYMBOL(blk_set_preempt_only);
+
/**
* __blk_run_queue_uncond - run a queue whether or not it has been stopped
* @q: The queue to run
@@ -771,8 +799,16 @@ int blk_queue_enter(struct request_queue *q, unsigned int
op)
while (true) {
int ret;
- if (percpu_ref_tryget_live(&q->q_usage_counter))
- return 0;
+ rcu_read_lock_sched();
+ if (__percpu_ref_tryget_live(&q->q_usage_counter)) {
+ if (likely((op & REQ_PREEMPT) ||
+ !blk_queue_preempt_only(q))) {
+ rcu_read_unlock_sched();
+ return 0;
+ } else
+ percpu_ref_put(&q->q_usage_counter);
+ }
+ rcu_read_unlock_sched();
if (op & REQ_NOWAIT)
return -EBUSY;
@@ -787,7 +823,9 @@ int blk_queue_enter(struct request_queue *q, unsigned int
op)
smp_rmb();
ret = wait_event_interruptible(q->mq_freeze_wq,
- !atomic_read(&q->mq_freeze_depth) ||
+ (!atomic_read(&q->mq_freeze_depth) &&
+ ((op & REQ_PREEMPT) ||
+ !blk_queue_preempt_only(q))) ||
blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4c688385d866..66d46d9eac29 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -628,6 +628,7 @@ struct request_queue {
#define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk
*/
#define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */
#define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */
+#define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT
requests */
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_STACKABLE) | \
@@ -732,6 +733,10 @@ static inline void queue_flag_clear(unsigned int flag,
struct request_queue *q)
((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
REQ_FAILFAST_DRIVER))
#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
+#define blk_queue_preempt_only(q) \
+ test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags)
+
+extern void blk_set_preempt_only(struct request_queue *q, bool preempt_only);
static inline bool blk_account_rq(struct request *rq)
{
--
2.9.5
