1 files changed, 26 insertions, 22 deletions

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 68eebed3b050..999c92d7036e 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -1066,28 +1066,11 @@ static bool is_pci_link_healthy(struct hl_device *hdev)
 	return (device_id == hdev->pdev->device);
 }
 
-static void stringify_time_of_last_heartbeat(struct hl_device *hdev, char *time_str, size_t size,
-						bool is_pq_hb)
-{
-	time64_t seconds = is_pq_hb ? hdev->heartbeat_debug_info.last_pq_heartbeat_ts
-					: hdev->heartbeat_debug_info.last_eq_heartbeat_ts;
-	struct tm tm;
-
-	if (!seconds)
-		return;
-
-	time64_to_tm(seconds, 0, &tm);
-
-	snprintf(time_str, size, "%ld-%02d-%02d %02d:%02d:%02d (UTC)",
-		tm.tm_year + 1900, tm.tm_mon, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec);
-}
-
 static bool hl_device_eq_heartbeat_received(struct hl_device *hdev)
 {
 	struct eq_heartbeat_debug_info *heartbeat_debug_info = &hdev->heartbeat_debug_info;
 	u32 cpu_q_id = heartbeat_debug_info->cpu_queue_id, pq_pi_mask = (HL_QUEUE_LENGTH << 1) - 1;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	char pq_time_str[64] = "N/A", eq_time_str[64] = "N/A";
 
 	if (!prop->cpucp_info.eq_health_check_supported)
 		return true;
@@ -1095,17 +1078,15 @@ static bool hl_device_eq_heartbeat_received(struct hl_device *hdev)
 	if (!hdev->eq_heartbeat_received) {
 		dev_err(hdev->dev, "EQ heartbeat event was not received!\n");
 
-		stringify_time_of_last_heartbeat(hdev, pq_time_str, sizeof(pq_time_str), true);
-		stringify_time_of_last_heartbeat(hdev, eq_time_str, sizeof(eq_time_str), false);
 		dev_err(hdev->dev,
-			"EQ: {CI %u, HB counter %u, last HB time: %s}, PQ: {PI: %u, CI: %u (%u), last HB time: %s}\n",
+			"EQ: {CI %u, HB counter %u, last HB time: %ptTs}, PQ: {PI: %u, CI: %u (%u), last HB time: %ptTs}\n",
 			hdev->event_queue.ci,
 			heartbeat_debug_info->heartbeat_event_counter,
-			eq_time_str,
+			&hdev->heartbeat_debug_info.last_eq_heartbeat_ts,
 			hdev->kernel_queues[cpu_q_id].pi,
 			atomic_read(&hdev->kernel_queues[cpu_q_id].ci),
 			atomic_read(&hdev->kernel_queues[cpu_q_id].ci) & pq_pi_mask,
-			pq_time_str);
+			&hdev->heartbeat_debug_info.last_pq_heartbeat_ts);
 
 		hl_eq_dump(hdev, &hdev->event_queue);
 
@@ -1649,6 +1630,11 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
 	from_watchdog_thread = !!(flags & HL_DRV_RESET_FROM_WD_THR);
 	reset_upon_device_release = hdev->reset_upon_device_release && from_dev_release;
 
+	if (hdev->cpld_shutdown) {
+		dev_err(hdev->dev, "Cannot reset device, cpld is shutdown! Device is NOT usable\n");
+		return -EIO;
+	}
+
 	if (!hard_reset && (hl_device_status(hdev) == HL_DEVICE_STATUS_MALFUNCTION)) {
 		dev_dbg(hdev->dev, "soft-reset isn't supported on a malfunctioning device\n");
 		return 0;
@@ -2595,6 +2581,14 @@ void hl_device_fini(struct hl_device *hdev)
 	if (rc)
 		dev_err(hdev->dev, "hw_fini failed in device fini while removing device %d\n", rc);
 
+	/* Reset the H/W (if it accessible). It will be in idle state after this returns */
+	if (!hdev->cpld_shutdown) {
+		rc = hdev->asic_funcs->hw_fini(hdev, true, false);
+		if (rc)
+			dev_err(hdev->dev,
+				"hw_fini failed in device fini while removing device %d\n", rc);
+	}
+
 	hdev->fw_loader.fw_comp_loaded = FW_TYPE_NONE;
 
 	/* Release kernel context */
@@ -2962,3 +2956,13 @@ void hl_handle_clk_change_event(struct hl_device *hdev, u16 event_type, u64 *eve
 
 	mutex_unlock(&clk_throttle->lock);
 }
+
+void hl_eq_cpld_shutdown_event_handle(struct hl_device *hdev, u16 event_id, u64 *event_mask)
+{
+	hl_handle_critical_hw_err(hdev, event_id, event_mask);
+	*event_mask |= HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE;
+
+	/* Avoid any new accesses to the H/W */
+	hdev->disabled = true;
+	hdev->cpld_shutdown = true;
+}