scsi: lpfc: Adjust CMF total bytes and rxmonitor

Calculate any extra bytes needed to account for timer accuracy. If we are
less than LPFC_CMF_INTERVAL, then calculate the adjustment needed for total
to reflect a full LPFC_CMF_INTERVAL.

Add additional info to rxmonitor, and adjust some log formatting.

Link: https://lore.kernel.org/r/20211204002644.116455-7-jsmart2021@gmail.comCo-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/lpfc/lpfc.h

@@ -1602,6 +1602,7 @@ struct lpfc_hba {
 #define LPFC_MAX_RXMONITOR_ENTRY	800
 #define LPFC_MAX_RXMONITOR_DUMP		32
 struct rxtable_entry {
+	uint64_t cmf_bytes;	/* Total no of read bytes for CMF_SYNC_WQE */
 	uint64_t total_bytes;   /* Total no of read bytes requested */
 	uint64_t rcv_bytes;     /* Total no of read bytes completed */
 	uint64_t avg_io_size;

drivers/scsi/lpfc/lpfc_debugfs.c

@@ -5561,22 +5561,24 @@ lpfc_rx_monitor_read(struct file *file, char __user *buf, size_t nbytes,
 	start = tail;
 
 	len += scnprintf(buffer + len, MAX_DEBUGFS_RX_TABLE_SIZE - len,
-			"        MaxBPI\t Total Data Cmd  Total Data Cmpl "
-			"  Latency(us)    Avg IO Size\tMax IO Size   IO cnt "
-			"Info BWutil(ms)\n");
+			"        MaxBPI    Tot_Data_CMF Tot_Data_Cmd "
+			"Tot_Data_Cmpl  Lat(us)  Avg_IO  Max_IO "
+			"Bsy IO_cnt Info BWutil(ms)\n");
 get_table:
 	for (i = start; i < last; i++) {
 		entry = &phba->rxtable[i];
 		len += scnprintf(buffer + len, MAX_DEBUGFS_RX_TABLE_SIZE - len,
-				"%3d:%12lld  %12lld\t%12lld\t"
-				"%8lldus\t%8lld\t%10lld "
-				"%8d   %2d %2d(%2d)\n",
+				"%3d:%12lld %12lld %12lld %12lld "
+				"%7lldus %8lld %7lld "
+				"%2d   %4d   %2d   %2d(%2d)\n",
 				i, entry->max_bytes_per_interval,
+				entry->cmf_bytes,
 				entry->total_bytes,
 				entry->rcv_bytes,
 				entry->avg_io_latency,
 				entry->avg_io_size,
 				entry->max_read_cnt,
+				entry->cmf_busy,
 				entry->io_cnt,
 				entry->cmf_info,
 				entry->timer_utilization,

drivers/scsi/lpfc/lpfc_debugfs.h

@@ -282,7 +282,7 @@ struct lpfc_idiag {
 	void *ptr_private;
 };
 
-#define MAX_DEBUGFS_RX_TABLE_SIZE	(100 * LPFC_MAX_RXMONITOR_ENTRY)
+#define MAX_DEBUGFS_RX_TABLE_SIZE	(128 * LPFC_MAX_RXMONITOR_ENTRY)
 struct lpfc_rx_monitor_debug {
 	char *i_private;
 	char *buffer;

drivers/scsi/lpfc/lpfc_init.c

@@ -5927,7 +5927,7 @@ lpfc_cmf_timer(struct hrtimer *timer)
 	uint32_t io_cnt;
 	uint32_t head, tail;
 	uint32_t busy, max_read;
-	uint64_t total, rcv, lat, mbpi, extra;
+	uint64_t total, rcv, lat, mbpi, extra, cnt;
 	int timer_interval = LPFC_CMF_INTERVAL;
 	uint32_t ms;
 	struct lpfc_cgn_stat *cgs;
@@ -5998,20 +5998,23 @@ lpfc_cmf_timer(struct hrtimer *timer)
 
 		/* Calculate any extra bytes needed to account for the
 		 * timer accuracy. If we are less than LPFC_CMF_INTERVAL
-		 * add an extra 3% slop factor, equal to LPFC_CMF_INTERVAL
-		 * add an extra 2%. The goal is to equalize total with a
-		 * time > LPFC_CMF_INTERVAL or <= LPFC_CMF_INTERVAL + 1
+		 * calculate the adjustment needed for total to reflect
+		 * a full LPFC_CMF_INTERVAL.
 		 */
-		if (ms == LPFC_CMF_INTERVAL)
-			extra = div_u64(total, 50);
-		else if (ms < LPFC_CMF_INTERVAL)
-			extra = div_u64(total, 33);
+		if (ms && ms < LPFC_CMF_INTERVAL) {
+			cnt = div_u64(total, ms); /* bytes per ms */
+			cnt *= LPFC_CMF_INTERVAL; /* what total should be */
+			if (cnt > mbpi)
+				cnt = mbpi;
+			extra = cnt - total;
+		}
 		lpfc_issue_cmf_sync_wqe(phba, LPFC_CMF_INTERVAL, total + extra);
 	} else {
 		/* For Monitor mode or link down we want mbpi
 		 * to be the full link speed
 		 */
 		mbpi = phba->cmf_link_byte_count;
+		extra = 0;
 	}
 	phba->cmf_timer_cnt++;
 
@@ -6042,6 +6045,7 @@ lpfc_cmf_timer(struct hrtimer *timer)
 				   LPFC_RXMONITOR_TABLE_IN_USE);
 		entry = &phba->rxtable[head];
 		entry->total_bytes = total;
+		entry->cmf_bytes = total + extra;
 		entry->rcv_bytes = rcv;
 		entry->cmf_busy = busy;
 		entry->cmf_info = phba->cmf_active_info;