IB/hfi1: Convert PortXmitWait/PortVLXmitWait counters to flit times

HFI's counters SendWaitCnt and SendWaitVlCnt are in units
of TXE cycle time (at 805MHz). OPA counters PortXmitWait and
PortVLXmtWait are in units of flit times.
Convert the counter values to flit units using following
conversion formula:

PortXmitWait =
	SendWaitCnt * 2 * (4 /link_width) * (25 Gbps /link_speed)
PortVLXmitWait =
	SendWaitVLCnt * 2 * (4 /link_width) * (25 Gbps /link_speed)

At link up or downgrade events, the link width can change. To ensure
accurate counter calculations, sample the counters after the events,
during counter requests, and then aggregate the OPA counters.

Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Kamenee Arumugam <kamenee.arumugam@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 58 insertions, 6 deletions

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 57f0df2f84f2..e6a60fa59f2b 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1083,6 +1083,7 @@ static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
 static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
 static int wait_link_transfer_active(struct hfi1_devdata *dd, int wait_ms);
 static void clear_rsm_rule(struct hfi1_devdata *dd, u8 rule_index);
+static void update_xmit_counters(struct hfi1_pportdata *ppd, u16 link_width);
 
 /*
  * Error interrupt table entry.  This is used as input to the interrupt
@@ -6905,6 +6906,32 @@ void handle_freeze(struct work_struct *work)
 	/* no longer frozen */
 }
 
+/**
+ * update_xmit_counters - update PortXmitWait/PortVlXmitWait
+ * counters.
+ * @ppd: info of physical Hfi port
+ * @link_width: new link width after link up or downgrade
+ *
+ * Update the PortXmitWait and PortVlXmitWait counters after
+ * a link up or downgrade event to reflect a link width change.
+ */
+static void update_xmit_counters(struct hfi1_pportdata *ppd, u16 link_width)
+{
+	int i;
+	u16 tx_width;
+	u16 link_speed;
+
+	tx_width = tx_link_width(link_width);
+	link_speed = get_link_speed(ppd->link_speed_active);
+
+	/*
+	 * There are C_VL_COUNT number of PortVLXmitWait counters.
+	 * Adding 1 to C_VL_COUNT to include the PortXmitWait counter.
+	 */
+	for (i = 0; i < C_VL_COUNT + 1; i++)
+		get_xmit_wait_counters(ppd, tx_width, link_speed, i);
+}
+
 /*
  * Handle a link up interrupt from the 8051.
  *
@@ -7526,18 +7553,29 @@ void handle_verify_cap(struct work_struct *work)
 	set_link_state(ppd, HLS_GOING_UP);
 }
 
-/*
- * Apply the link width downgrade enabled policy against the current active
- * link widths.
+/**
+ * apply_link_downgrade_policy - Apply the link width downgrade enabled
+ * policy against the current active link widths.
+ * @ppd: info of physical Hfi port
+ * @refresh_widths: True indicates link downgrade event
+ * @return: True indicates a successful link downgrade. False indicates
+ *	    link downgrade event failed and the link will bounce back to
+ *	    default link width.
  *
- * Called when the enabled policy changes or the active link widths change.
+ * Called when the enabled policy changes or the active link widths
+ * change.
+ * Refresh_widths indicates that a link downgrade occurred. The
+ * link_downgraded variable is set by refresh_widths and
+ * determines the success/failure of the policy application.
  */
-void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
+bool apply_link_downgrade_policy(struct hfi1_pportdata *ppd,
+				 bool refresh_widths)
 {
 	int do_bounce = 0;
 	int tries;
 	u16 lwde;
 	u16 tx, rx;
+	bool link_downgraded = refresh_widths;
 
 	/* use the hls lock to avoid a race with actual link up */
 	tries = 0;
@@ -7571,6 +7609,7 @@ retry:
 	    ppd->link_width_downgrade_rx_active == 0) {
 		/* the 8051 reported a dead link as a downgrade */
 		dd_dev_err(ppd->dd, "Link downgrade is really a link down, ignoring\n");
+		link_downgraded = false;
 	} else if (lwde == 0) {
 		/* downgrade is disabled */
 
@@ -7587,6 +7626,7 @@ retry:
 				   ppd->link_width_downgrade_tx_active,
 				   ppd->link_width_downgrade_rx_active);
 			do_bounce = 1;
+			link_downgraded = false;
 		}
 	} else if ((lwde & ppd->link_width_downgrade_tx_active) == 0 ||
 		   (lwde & ppd->link_width_downgrade_rx_active) == 0) {
@@ -7598,6 +7638,7 @@ retry:
 			   lwde, ppd->link_width_downgrade_tx_active,
 			   ppd->link_width_downgrade_rx_active);
 		do_bounce = 1;
+		link_downgraded = false;
 	}
 
 done:
@@ -7609,6 +7650,8 @@ done:
 		set_link_state(ppd, HLS_DN_OFFLINE);
 		start_link(ppd);
 	}
+
+	return link_downgraded;
 }
 
 /*
@@ -7622,7 +7665,8 @@ void handle_link_downgrade(struct work_struct *work)
 							link_downgrade_work);
 
 	dd_dev_info(ppd->dd, "8051: Link width downgrade\n");
-	apply_link_downgrade_policy(ppd, 1);
+	if (apply_link_downgrade_policy(ppd, true))
+		update_xmit_counters(ppd, ppd->link_width_downgrade_tx_active);
 }
 
 static char *dcc_err_string(char *buf, int buf_len, u64 flags)
@@ -10597,6 +10641,14 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 		add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
 
 		handle_linkup_change(dd, 1);
+
+		/*
+		 * After link up, a new link width will have been set.
+		 * Update the xmit counters with regards to the new
+		 * link width.
+		 */
+		update_xmit_counters(ppd, ppd->link_width_active);
+
 		ppd->host_link_state = HLS_UP_INIT;
 		update_statusp(ppd, IB_PORT_INIT);
 		break;