Instead of allowing requests that are not power management requests
to enter the queue in runtime suspended status (RPM_SUSPENDED), make
the blk_get_request() caller block. This change fixes a starvation
issue: it is now guaranteed that power management requests will be
executed no matter how many blk_get_request() callers are waiting.
Instead of maintaining the q->nr_pending counter, rely on
q->q_usage_counter. Call pm_runtime_mark_last_busy() every time a
request finishes instead of only if the queue depth drops to zero.
Use RQF_PREEMPT to mark power management requests instead of RQF_PM.
This is safe because the power management core serializes system-wide
suspend/resume and runtime power management state changes.
Signed-off-by: Bart Van Assche <bart.vanassche@xxxxxxx>
Cc: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Ming Lei <ming.lei@xxxxxxxxxx>
Cc: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>
Cc: Johannes Thumshirn <jthumshirn@xxxxxxx>
---
block/blk-core.c | 49 +++++++++++++++------------------------
block/blk-mq-debugfs.c | 1 -
block/blk-pm.c | 19 +++++++++++++--
block/elevator.c | 11 +--------
drivers/scsi/sd.c | 4 ++--
drivers/scsi/ufs/ufshcd.c | 10 ++++----
include/linux/blkdev.h | 7 ++----
7 files changed, 46 insertions(+), 55 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index feac2b4d3b90..195a99de7c7e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -689,6 +689,16 @@ void blk_set_queue_dying(struct request_queue *q)
{
blk_queue_flag_set(QUEUE_FLAG_DYING, q);
+#ifdef CONFIG_PM
+ /*
+ * Avoid that runtime power management tries to modify the state of
+ * q->q_usage_counter after that counter has been transitioned to the
+ * "dead" state.
+ */
+ if (q->dev)
+ pm_runtime_dont_use_autosuspend(q->dev);
+#endif
+
/*
* When queue DYING flag is set, we need to block new req
* entering queue, so we call blk_freeze_queue_start() to
@@ -1728,7 +1738,7 @@ EXPORT_SYMBOL_GPL(part_round_stats);
#ifdef CONFIG_PM
static void blk_pm_put_request(struct request *rq)
{
- if (rq->q->dev && !(rq->rq_flags & RQF_PM) && !--rq->q->nr_pending)
+ if (rq->q->dev && !(rq->rq_flags & RQF_PREEMPT))
pm_runtime_mark_last_busy(rq->q->dev);
}
#else
@@ -2745,30 +2755,6 @@ void blk_account_io_done(struct request *req, u64 now)
}
}
-#ifdef CONFIG_PM
-/*
- * Don't process normal requests when queue is suspended
- * or in the process of suspending/resuming
- */
-static bool blk_pm_allow_request(struct request *rq)
-{
- switch (rq->q->rpm_status) {
- case RPM_RESUMING:
- case RPM_SUSPENDING:
- return rq->rq_flags & RQF_PM;
- case RPM_SUSPENDED:
- return false;
- default:
- return true;
- }
-}
-#else
-static bool blk_pm_allow_request(struct request *rq)
-{
- return true;
-}
-#endif
-
void blk_account_io_start(struct request *rq, bool new_io)
{
struct hd_struct *part;
@@ -2814,11 +2800,14 @@ static struct request *elv_next_request(struct request_queue *q)
while (1) {
list_for_each_entry(rq, &q->queue_head, queuelist) {
- if (blk_pm_allow_request(rq))
- return rq;
-
- if (rq->rq_flags & RQF_SOFTBARRIER)
- break;
+#ifdef CONFIG_PM
+ /*
+ * If a request gets queued in state RPM_SUSPENDED
+ * then that's a kernel bug.
+ */
+ WARN_ON_ONCE(q->rpm_status == RPM_SUSPENDED);
+#endif
+ return rq;
}
/*
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index cb1e6cf7ac48..994bdd41feb2 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -324,7 +324,6 @@ static const char *const rqf_name[] = {
RQF_NAME(ELVPRIV),
RQF_NAME(IO_STAT),
RQF_NAME(ALLOCED),
- RQF_NAME(PM),
RQF_NAME(HASHED),
RQF_NAME(STATS),
RQF_NAME(SPECIAL_PAYLOAD),
diff --git a/block/blk-pm.c b/block/blk-pm.c
index 7dc9375a2f46..9f1130381322 100644
--- a/block/blk-pm.c
+++ b/block/blk-pm.c
@@ -73,6 +73,13 @@ void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
}
EXPORT_SYMBOL(blk_pm_runtime_init);
+static void blk_unprepare_runtime_suspend(struct request_queue *q)
+{
+ blk_queue_flag_clear(QUEUE_FLAG_PREEMPT_ONLY, q);
+ /* Because QUEUE_FLAG_PREEMPT_ONLY has been cleared. */
+ wake_up_all(&q->mq_freeze_wq);
+}
+
/**
* blk_pre_runtime_suspend - Pre runtime suspend check
* @q: the queue of the device
@@ -102,9 +109,11 @@ int blk_pre_runtime_suspend(struct request_queue *q)
return ret;
blk_pm_runtime_lock(q);
+ blk_set_preempt_only(q);
+ percpu_ref_switch_to_atomic_sync(&q->q_usage_counter);
spin_lock_irq(q->queue_lock);
- if (q->nr_pending) {
+ if (!percpu_ref_is_zero(&q->q_usage_counter)) {
ret = -EBUSY;
pm_runtime_mark_last_busy(q->dev);
} else {
@@ -112,6 +121,7 @@ int blk_pre_runtime_suspend(struct request_queue *q)
}
spin_unlock_irq(q->queue_lock);
+ percpu_ref_switch_to_percpu(&q->q_usage_counter);
blk_pm_runtime_unlock(q);
return ret;
@@ -144,6 +154,9 @@ void blk_post_runtime_suspend(struct request_queue *q, int err)
pm_runtime_mark_last_busy(q->dev);
}
spin_unlock_irq(q->queue_lock);
+
+ if (err)
+ blk_unprepare_runtime_suspend(q);
}
EXPORT_SYMBOL(blk_post_runtime_suspend);
@@ -191,13 +204,15 @@ void blk_post_runtime_resume(struct request_queue *q, int err)
spin_lock_irq(q->queue_lock);
if (!err) {
q->rpm_status = RPM_ACTIVE;
- __blk_run_queue(q);
pm_runtime_mark_last_busy(q->dev);
pm_request_autosuspend(q->dev);
} else {
q->rpm_status = RPM_SUSPENDED;
}
spin_unlock_irq(q->queue_lock);
+
+ if (!err)
+ blk_unprepare_runtime_suspend(q);
}
EXPORT_SYMBOL(blk_post_runtime_resume);
diff --git a/block/elevator.c b/block/elevator.c
index fa828b5bfd4b..68174953e730 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -558,20 +558,13 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
}
#ifdef CONFIG_PM
-static void blk_pm_requeue_request(struct request *rq)
-{
- if (rq->q->dev && !(rq->rq_flags & RQF_PM))
- rq->q->nr_pending--;
-}
-
static void blk_pm_add_request(struct request_queue *q, struct request *rq)
{
- if (q->dev && !(rq->rq_flags & RQF_PM) && q->nr_pending++ == 0 &&
+ if (q->dev && !(rq->rq_flags & RQF_PREEMPT) &&
(q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
pm_request_resume(q->dev);
}
#else
-static inline void blk_pm_requeue_request(struct request *rq) {}
static inline void blk_pm_add_request(struct request_queue *q,
struct request *rq)
{
@@ -592,8 +585,6 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
rq->rq_flags &= ~RQF_STARTED;
- blk_pm_requeue_request(rq);
-
__elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE);
}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index e60cd8480a03..876401f4764e 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1628,7 +1628,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
* flush everything.
*/
res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, sshdr,
- timeout, SD_MAX_RETRIES, 0, RQF_PM, NULL);
+ timeout, SD_MAX_RETRIES, 0, RQF_PREEMPT, NULL);
if (res == 0)
break;
}
@@ -3488,7 +3488,7 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
return -ENODEV;
res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
- SD_TIMEOUT, SD_MAX_RETRIES, 0, RQF_PM, NULL);
+ SD_TIMEOUT, SD_MAX_RETRIES, 0, RQF_PREEMPT, NULL);
if (res) {
sd_print_result(sdkp, "Start/Stop Unit failed", res);
if (driver_byte(res) & DRIVER_SENSE)
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 397081d320b1..4a16d6e90e65 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -7219,7 +7219,7 @@ ufshcd_send_request_sense(struct ufs_hba *hba, struct scsi_device *sdp)
ret = scsi_execute(sdp, cmd, DMA_FROM_DEVICE, buffer,
UFSHCD_REQ_SENSE_SIZE, NULL, NULL,
- msecs_to_jiffies(1000), 3, 0, RQF_PM, NULL);
+ msecs_to_jiffies(1000), 3, 0, RQF_PREEMPT, NULL);
if (ret)
pr_err("%s: failed with err %d\n", __func__, ret);
@@ -7280,12 +7280,12 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
cmd[4] = pwr_mode << 4;
/*
- * Current function would be generally called from the power management
- * callbacks hence set the RQF_PM flag so that it doesn't resume the
- * already suspended childs.
+ * Current function would be generally called from the power
+ * management callbacks hence set the RQF_PREEMPT flag so that it
+ * doesn't resume the already suspended childs.
*/
ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
- START_STOP_TIMEOUT, 0, 0, RQF_PM, NULL);
+ START_STOP_TIMEOUT, 0, 0, RQF_PREEMPT, NULL);
if (ret) {
sdev_printk(KERN_WARNING, sdp,
"START_STOP failed for power mode: %d, result %x\n",
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3a8c20eafe58..4cee277fd1af 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -99,8 +99,8 @@ typedef __u32 __bitwise req_flags_t;
#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6))
/* don't call prep for this one */
#define RQF_DONTPREP ((__force req_flags_t)(1 << 7))
-/* set for "ide_preempt" requests and also for requests for which the SCSI
- "quiesce" state must be ignored. */
+/* set for requests that must be processed even if QUEUE_FLAG_PREEMPT_ONLY has
+ been set, e.g. power management requests and "ide_preempt" requests. */
#define RQF_PREEMPT ((__force req_flags_t)(1 << 8))
/* contains copies of user pages */
#define RQF_COPY_USER ((__force req_flags_t)(1 << 9))
@@ -114,8 +114,6 @@ typedef __u32 __bitwise req_flags_t;
#define RQF_IO_STAT ((__force req_flags_t)(1 << 13))
/* request came from our alloc pool */
#define RQF_ALLOCED ((__force req_flags_t)(1 << 14))
-/* runtime pm request */
-#define RQF_PM ((__force req_flags_t)(1 << 15))
/* on IO scheduler merge hash */
#define RQF_HASHED ((__force req_flags_t)(1 << 16))
/* IO stats tracking on */
@@ -543,7 +541,6 @@ struct request_queue {
#ifdef CONFIG_PM
struct device *dev;
int rpm_status;
- unsigned int nr_pending;
spinlock_t rpm_lock;
wait_queue_head_t rpm_wq;
struct task_struct *rpm_owner;
--
2.18.0
