scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler

Inside scsi_eh_wakeup(), scsi_host_busy() is called & checked with host
lock every time for deciding if error handler kthread needs to be waken up.

This can be too heavy in case of recovery, such as:

 - N hardware queues

 - queue depth is M for each hardware queue

 - each scsi_host_busy() iterates over (N * M) tag/requests

If recovery is triggered in case that all requests are in-flight, each
scsi_eh_wakeup() is strictly serialized, when scsi_eh_wakeup() is called
for the last in-flight request, scsi_host_busy() has been run for (N * M -
1) times, and request has been iterated for (N*M - 1) * (N * M) times.

If both N and M are big enough, hard lockup can be triggered on acquiring
host lock, and it is observed on mpi3mr(128 hw queues, queue depth 8169).

Fix the issue by calling scsi_host_busy() outside the host lock. We don't
need the host lock for getting busy count because host the lock never
covers that.

[mkp: Drop unnecessary 'busy' variables pointed out by Bart]

Cc: Ewan Milne <[email protected]>
Fixes: 6eb045e ("scsi: core: avoid host-wide host_busy counter for scsi_mq")
Signed-off-by: Ming Lei <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Reviewed-by: Ewan D. Milne <[email protected]>
Reviewed-by: Sathya Prakash Veerichetty <[email protected]>
Tested-by: Sathya Prakash Veerichetty <[email protected]>
Reviewed-by: Bart Van Assche <[email protected]>
Signed-off-by: Martin K. Petersen <[email protected]>

Author: Ming Lei

drivers/scsi/scsi_error.c

@@ -61,11 +61,11 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd);
 static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *,
 						   struct scsi_cmnd *);
 
-void scsi_eh_wakeup(struct Scsi_Host *shost)
+void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy)
 {
 	lockdep_assert_held(shost->host_lock);
 
-	if (scsi_host_busy(shost) == shost->host_failed) {
+	if (busy == shost->host_failed) {
 		trace_scsi_eh_wakeup(shost);
 		wake_up_process(shost->ehandler);
 		SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
@@ -88,7 +88,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost)
 	if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 ||
 	    scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) {
 		shost->host_eh_scheduled++;
-		scsi_eh_wakeup(shost);
+		scsi_eh_wakeup(shost, scsi_host_busy(shost));
 	}
 
 	spin_unlock_irqrestore(shost->host_lock, flags);
@@ -286,7 +286,7 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head)
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	shost->host_failed++;
-	scsi_eh_wakeup(shost);
+	scsi_eh_wakeup(shost, scsi_host_busy(shost));
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 

drivers/scsi/scsi_lib.c

@@ -280,7 +280,7 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 	if (unlikely(scsi_host_in_recovery(shost))) {
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
-			scsi_eh_wakeup(shost);
+			scsi_eh_wakeup(shost, scsi_host_busy(shost));
 		spin_unlock_irqrestore(shost->host_lock, flags);
 	}
 	rcu_read_unlock();

drivers/scsi/scsi_priv.h

@@ -92,7 +92,7 @@ extern void scmd_eh_abort_handler(struct work_struct *work);
 extern enum blk_eh_timer_return scsi_timeout(struct request *req);
 extern int scsi_error_handler(void *host);
 extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd);
-extern void scsi_eh_wakeup(struct Scsi_Host *shost);
+extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy);
 extern void scsi_eh_scmd_add(struct scsi_cmnd *);
 void scsi_eh_ready_devs(struct Scsi_Host *shost,
 			struct list_head *work_q,