scsi: ufs: Fix imprecise load calculation in devfreq window

The UFS load calculation is based on "total_time" and "busy_time" in a
devfreq window.  However, the source of time is different for both
parameters: "busy_time" is assigned from "jiffies" thus has different
accuracy from "total_time" which is assigned from ktime_get().

In addition, the time of window boundary is not exactly the same as the
starting busy time in this window if UFS is actually busy in the beginning
of the window. A similar accuracy error may also happen for the end of busy
time in current window.

To guarantee the precision of load calculation, we need to

1. Align time accuracy of both devfreq_dev_status.total_time and
   devfreq_dev_status.busy_time. For example, use "ktime_get()" directly.

2. Align the following timelines:
   - The beginning time of devfreq windows
   - The beginning of busy time in a new window
   - The end of busy time in the current window

Link: https://lore.kernel.org/r/20200611101043.6379-1-stanley.chu@mediatek.com
Fixes: a3cd5ec5 ("scsi: ufs: add load based scaling of UFS gear")
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/ufs/ufshcd.c

@@ -1312,6 +1312,7 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev,
 	unsigned long flags;
 	struct list_head *clk_list = &hba->clk_list_head;
 	struct ufs_clk_info *clki;
+	ktime_t curr_t;
 
 	if (!ufshcd_is_clkscaling_supported(hba))
 		return -EINVAL;
@@ -1319,6 +1320,7 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev,
 	memset(stat, 0, sizeof(*stat));
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
+	curr_t = ktime_get();
 	if (!scaling->window_start_t)
 		goto start_window;
 
@@ -1330,18 +1332,17 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev,
 	 */
 	stat->current_frequency = clki->curr_freq;
 	if (scaling->is_busy_started)
-		scaling->tot_busy_t += ktime_to_us(ktime_sub(ktime_get(),
-					scaling->busy_start_t));
+		scaling->tot_busy_t += ktime_us_delta(curr_t,
+				scaling->busy_start_t);
 
-	stat->total_time = jiffies_to_usecs((long)jiffies -
-				(long)scaling->window_start_t);
+	stat->total_time = ktime_us_delta(curr_t, scaling->window_start_t);
 	stat->busy_time = scaling->tot_busy_t;
 start_window:
-	scaling->window_start_t = jiffies;
+	scaling->window_start_t = curr_t;
 	scaling->tot_busy_t = 0;
 
 	if (hba->outstanding_reqs) {
-		scaling->busy_start_t = ktime_get();
+		scaling->busy_start_t = curr_t;
 		scaling->is_busy_started = true;
 	} else {
 		scaling->busy_start_t = 0;
@@ -1875,6 +1876,7 @@ static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
 static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba)
 {
 	bool queue_resume_work = false;
+	ktime_t curr_t = ktime_get();
 
 	if (!ufshcd_is_clkscaling_supported(hba))
 		return;
@@ -1890,13 +1892,13 @@ static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba)
 			   &hba->clk_scaling.resume_work);
 
 	if (!hba->clk_scaling.window_start_t) {
-		hba->clk_scaling.window_start_t = jiffies;
+		hba->clk_scaling.window_start_t = curr_t;
 		hba->clk_scaling.tot_busy_t = 0;
 		hba->clk_scaling.is_busy_started = false;
 	}
 
 	if (!hba->clk_scaling.is_busy_started) {
-		hba->clk_scaling.busy_start_t = ktime_get();
+		hba->clk_scaling.busy_start_t = curr_t;
 		hba->clk_scaling.is_busy_started = true;
 	}
 }

drivers/scsi/ufs/ufshcd.h

@@ -372,7 +372,7 @@ struct ufs_saved_pwr_info {
 struct ufs_clk_scaling {
 	int active_reqs;
 	unsigned long tot_busy_t;
-	unsigned long window_start_t;
+	ktime_t window_start_t;
 	ktime_t busy_start_t;
 	struct device_attribute enable_attr;
 	struct ufs_saved_pwr_info saved_pwr_info;