IB/hfi1: Turn off AOC TX after offline substates

Offline.quietDuration was added in the 8051 firmware, and the driver
only turns off the AOC transmitters when offline.quiet is reached.
However, the AOC transmitters need to be turned off at the new state.
Therefore, turn off the AOC transmitters at any offline substates
including offline.quiet and offline.quietDuration, then recheck we
reached offline.quiet to support backwards compatibility.
Reviewed-by: Jakub Byczkowski <jakub.byczkowski@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/chip.c

@@ -1066,6 +1066,8 @@ static int read_idle_sma(struct hfi1_devdata *dd, u64 *data);
 static int thermal_init(struct hfi1_devdata *dd);
 
 static void update_statusp(struct hfi1_pportdata *ppd, u32 state);
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs);
 static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 				  int msecs);
 static void log_state_transition(struct hfi1_pportdata *ppd, u32 state);
@@ -10305,6 +10307,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	u32 previous_state;
+	int offline_state_ret;
 	int ret;
 
 	update_lcb_cache(dd);
@@ -10326,13 +10329,36 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 		ppd->offline_disabled_reason =
 		HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT);
 
+	offline_state_ret = wait_phys_link_offline_substates(ppd, 10000);
+	if (offline_state_ret < 0)
+		return offline_state_ret;
+
+	/* Disabling AOC transmitters */
+	if (ppd->port_type == PORT_TYPE_QSFP &&
+	    ppd->qsfp_info.limiting_active &&
+	    qsfp_mod_present(ppd)) {
+		int ret;
+
+		ret = acquire_chip_resource(dd, qsfp_resource(dd), QSFP_WAIT);
+		if (ret == 0) {
+			set_qsfp_tx(ppd, 0);
+			release_chip_resource(dd, qsfp_resource(dd));
+		} else {
+			/* not fatal, but should warn */
+			dd_dev_err(dd,
+				   "Unable to acquire lock to turn off QSFP TX\n");
+		}
+	}
+
 	/*
-	 * Wait for offline transition. It can take a while for
-	 * the link to go down.
+	 * Wait for the offline.Quiet transition if it hasn't happened yet. It
+	 * can take a while for the link to go down.
 	 */
-	ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000);
+	if (offline_state_ret != PLS_OFFLINE_QUIET) {
+		ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000);
 		if (ret < 0)
 			return ret;
+	}
 
 	/*
 	 * Now in charge of LCB - must be after the physical state is
@@ -10348,22 +10374,6 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 
 	ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
 
-	if (ppd->port_type == PORT_TYPE_QSFP &&
-	    ppd->qsfp_info.limiting_active &&
-	    qsfp_mod_present(ppd)) {
-		int ret;
-
-		ret = acquire_chip_resource(dd, qsfp_resource(dd), QSFP_WAIT);
-		if (ret == 0) {
-			set_qsfp_tx(ppd, 0);
-			release_chip_resource(dd, qsfp_resource(dd));
-		} else {
-			/* not fatal, but should warn */
-			dd_dev_err(dd,
-				   "Unable to acquire lock to turn off QSFP TX\n");
-		}
-	}
-
 	/*
 	 * The LNI has a mandatory wait time after the physical state
 	 * moves to Offline.Quiet.  The wait time may be different
@@ -12804,6 +12814,39 @@ static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 	return 0;
 }
 
+/*
+ * wait_phys_link_offline_quiet_substates - wait for any offline substate
+ * @ppd: port device
+ * @msecs: the number of milliseconds to wait
+ *
+ * Wait up to msecs milliseconds for any offline physical link
+ * state change to occur.
+ * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT.
+ */
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs)
+{
+	u32 read_state;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(msecs);
+	while (1) {
+		read_state = read_physical_state(ppd->dd);
+		if ((read_state & 0xF0) == PLS_OFFLINE)
+			break;
+		if (time_after(jiffies, timeout)) {
+			dd_dev_err(ppd->dd,
+				   "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n",
+				   read_state, msecs);
+			return -ETIMEDOUT;
+		}
+		usleep_range(1950, 2050); /* sleep 2ms-ish */
+	}
+
+	log_state_transition(ppd, read_state);
+	return read_state;
+}
+
 #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
 (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)
 

drivers/infiniband/hw/hfi1/chip.h

@@ -204,6 +204,7 @@
 #define PLS_OFFLINE_READY_TO_QUIET_LT	   0x92
 #define PLS_OFFLINE_REPORT_FAILURE		   0x93
 #define PLS_OFFLINE_READY_TO_QUIET_BCC	   0x94
+#define PLS_OFFLINE_QUIET_DURATION	   0x95
 #define PLS_POLLING				   0x20
 #define PLS_POLLING_QUIET			   0x20
 #define PLS_POLLING_ACTIVE			   0x21