habanalabs: add uapi to retrieve aggregate H/W events

Add a new opcode to INFO IOCTL to retrieve aggregate H/W events. i.e. the
events counters are NOT cleared upon device reset, but count from the
loading of the driver.

Add the code to support it in the device event handling function.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>

drivers/misc/habanalabs/goya/goya.c

@@ -4469,6 +4469,7 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
 	struct goya_device *goya = hdev->asic_specific;
 
 	goya->events_stat[event_type]++;
+	goya->events_stat_aggregate[event_type]++;
 
 	switch (event_type) {
 	case GOYA_ASYNC_EVENT_ID_PCIE_IF:
@@ -4550,12 +4551,16 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
 	}
 }
 
-void *goya_get_events_stat(struct hl_device *hdev, u32 *size)
+void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size)
 {
 	struct goya_device *goya = hdev->asic_specific;
 
-	*size = (u32) sizeof(goya->events_stat);
+	if (aggregate) {
+		*size = (u32) sizeof(goya->events_stat_aggregate);
+		return goya->events_stat_aggregate;
+	}
 
+	*size = (u32) sizeof(goya->events_stat);
 	return goya->events_stat;
 }
 

drivers/misc/habanalabs/goya/goyaP.h

@@ -162,6 +162,7 @@ struct goya_device {
 
 	u64		ddr_bar_cur_addr;
 	u32		events_stat[GOYA_ASYNC_EVENT_ID_SIZE];
+	u32		events_stat_aggregate[GOYA_ASYNC_EVENT_ID_SIZE];
 	u32		hw_cap_initialized;
 	u8		device_cpu_mmu_mappings_done;
 };
@@ -215,7 +216,7 @@ int goya_suspend(struct hl_device *hdev);
 int goya_resume(struct hl_device *hdev);
 
 void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry);
-void *goya_get_events_stat(struct hl_device *hdev, u32 *size);
+void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size);
 
 void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
 				u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec);

drivers/misc/habanalabs/habanalabs.h

@@ -558,7 +558,8 @@ struct hl_asic_funcs {
 				struct hl_eq_entry *eq_entry);
 	void (*set_pll_profile)(struct hl_device *hdev,
 			enum hl_pll_frequency freq);
-	void* (*get_events_stat)(struct hl_device *hdev, u32 *size);
+	void* (*get_events_stat)(struct hl_device *hdev, bool aggregate,
+				u32 *size);
 	u64 (*read_pte)(struct hl_device *hdev, u64 addr);
 	void (*write_pte)(struct hl_device *hdev, u64 addr, u64 val);
 	void (*mmu_invalidate_cache)(struct hl_device *hdev, bool is_hard);

drivers/misc/habanalabs/habanalabs_ioctl.c

@@ -75,7 +75,8 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
 		min((size_t)size, sizeof(hw_ip))) ? -EFAULT : 0;
 }
 
-static int hw_events_info(struct hl_device *hdev, struct hl_info_args *args)
+static int hw_events_info(struct hl_device *hdev, bool aggregate,
+			struct hl_info_args *args)
 {
 	u32 size, max_size = args->return_size;
 	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
@@ -84,7 +85,7 @@ static int hw_events_info(struct hl_device *hdev, struct hl_info_args *args)
 	if ((!max_size) || (!out))
 		return -EINVAL;
 
-	arr = hdev->asic_funcs->get_events_stat(hdev, &size);
+	arr = hdev->asic_funcs->get_events_stat(hdev, aggregate, &size);
 
 	return copy_to_user(out, arr, min(max_size, size)) ? -EFAULT : 0;
 }
@@ -251,7 +252,7 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 
 	switch (args->op) {
 	case HL_INFO_HW_EVENTS:
-		rc = hw_events_info(hdev, args);
+		rc = hw_events_info(hdev, false, args);
 		break;
 
 	case HL_INFO_DRAM_USAGE:
@@ -266,6 +267,10 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 		rc = device_utilization(hdev, args);
 		break;
 
+	case HL_INFO_HW_EVENTS_AGGREGATE:
+		rc = hw_events_info(hdev, true, args);
+		break;
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -ENOTTY;

include/uapi/misc/habanalabs.h

@@ -93,6 +93,8 @@ enum hl_device_status {
  *                              The period can be between 100ms to 1s, in
  *                              resolution of 100ms. The return value is a
  *                              percentage of the utilization rate.
+ * HL_INFO_HW_EVENTS_AGGREGATE - Receive an array describing how many times each
+ *                               event occurred since the driver was loaded.
  */
 #define HL_INFO_HW_IP_INFO		0
 #define HL_INFO_HW_EVENTS		1
@@ -100,6 +102,7 @@ enum hl_device_status {
 #define HL_INFO_HW_IDLE			3
 #define HL_INFO_DEVICE_STATUS		4
 #define HL_INFO_DEVICE_UTILIZATION	6
+#define HL_INFO_HW_EVENTS_AGGREGATE	7
 
 #define HL_INFO_VERSION_MAX_LEN	128