scsi: scsi_debug: Improve command duration calculation

Previously the code did the work implied by the given SCSI command and
after that it waited for a timer based on the user specified command
duration to be exhausted before informing the mid-level that the command
was complete. For short command durations, the time to complete the work
implied by the SCSI command could be significant compared to the user
specified command duration.

For example a WRITE of 128 blocks (say 512 bytes each) on a machine that
can copy from main memory to main memory at a rate of 10 GB/sec will take
around 6.4 microseconds to do that copy.  If the user specified a command
duration of 5 microseconds (ndelay=5000), should the driver do a further
delay of 5 microseconds after the copy or return immediately because 6.4 >
5 ?

The action prior to this patch was to always do the timer based
delay. After this patch, for ndelay values less than 1 millisecond, this
driver will complete the command immediately.  And in the case where the
user specified delay was 7 microseconds, a timer delay of 600 nanoseconds
will be set ((7 - 6.4) * 1000).

Link: https://lore.kernel.org/r/20200421151424.32668-6-dgilbert@interlog.comSigned-off-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/scsi_debug.c

@@ -4402,6 +4402,8 @@ static void setup_inject(struct sdebug_queue *sqp,
 	sqcp->inj_cmd_abort = !!(SDEBUG_OPT_CMD_ABORT & sdebug_opts);
 }
 
+#define INCLUSIVE_TIMING_MAX_NS 1000000		/* 1 millisecond */
+
 /* Complete the processing of the thread that queued a SCSI command to this
  * driver. It either completes the command by calling cmnd_done() or
  * schedules a hr timer or work queue then returns 0. Returns
@@ -4413,8 +4415,10 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 				    struct sdebug_dev_info *),
 			 int delta_jiff, int ndelay)
 {
-	unsigned long iflags;
+	bool new_sd_dp;
 	int k, num_in_q, qdepth, inject;
+	unsigned long iflags;
+	u64 ns_from_boot = 0;
 	struct sdebug_queue *sqp;
 	struct sdebug_queued_cmd *sqcp;
 	struct scsi_device *sdp;
@@ -4430,7 +4434,6 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 	if (delta_jiff == 0)
 		goto respond_in_thread;
 
-	/* schedule the response at a later time if resources permit */
 	sqp = get_queue(cmnd);
 	spin_lock_irqsave(&sqp->qc_lock, iflags);
 	if (unlikely(atomic_read(&sqp->blocked))) {
@@ -4489,8 +4492,15 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 		sd_dp = kzalloc(sizeof(*sd_dp), GFP_ATOMIC);
 		if (sd_dp == NULL)
 			return SCSI_MLQUEUE_HOST_BUSY;
+		new_sd_dp = true;
+	} else {
+		new_sd_dp = false;
 	}
 
+	if (ndelay > 0 && ndelay < INCLUSIVE_TIMING_MAX_NS)
+		ns_from_boot = ktime_get_boottime_ns();
+
+	/* one of the resp_*() response functions is called here */
 	cmnd->result = pfp != NULL ? pfp(cmnd, devip) : 0;
 	if (cmnd->result & SDEG_RES_IMMED_MASK) {
 		cmnd->result &= ~SDEG_RES_IMMED_MASK;
@@ -4521,6 +4531,22 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 		} else {	/* ndelay has a 4.2 second max */
 			kt = sdebug_random ? prandom_u32_max((u32)ndelay) :
 					     (u32)ndelay;
+			if (ndelay < INCLUSIVE_TIMING_MAX_NS) {
+				u64 d = ktime_get_boottime_ns() - ns_from_boot;
+
+				if (kt <= d) {	/* elapsed duration >= kt */
+					sqcp->a_cmnd = NULL;
+					atomic_dec(&devip->num_in_q);
+					clear_bit(k, sqp->in_use_bm);
+					if (new_sd_dp)
+						kfree(sd_dp);
+					/* call scsi_done() from this thread */
+					cmnd->scsi_done(cmnd);
+					return 0;
+				}
+				/* otherwise reduce kt by elapsed time */
+				kt -= d;
+			}
 		}
 		if (!sd_dp->init_hrt) {
 			sd_dp->init_hrt = true;
@@ -4534,6 +4560,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 		if (sdebug_statistics)
 			sd_dp->issuing_cpu = raw_smp_processor_id();
 		sd_dp->defer_t = SDEB_DEFER_HRT;
+		/* schedule the invocation of scsi_done() for a later time */
 		hrtimer_start(&sd_dp->hrt, kt, HRTIMER_MODE_REL_PINNED);
 	} else {	/* jdelay < 0, use work queue */
 		if (!sd_dp->init_wq) {