habanalabs: Add busy engines bitmask to HW idle IOCTL

The information which is currently provided as a response to the
"HL_INFO_HW_IDLE" IOCTL is merely a general boolean value.
This patch extends it and provides also a bitmask that indicates which
of the device engines are busy.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

drivers/misc/habanalabs/debugfs.c

@@ -506,7 +506,7 @@ static int engines_show(struct seq_file *s, void *data)
 	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
 	struct hl_device *hdev = dev_entry->hdev;
 
-	hdev->asic_funcs->is_device_idle(hdev, s);
+	hdev->asic_funcs->is_device_idle(hdev, NULL, s);
 
 	return 0;
 }

drivers/misc/habanalabs/goya/goya.c

@@ -2828,7 +2828,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job)
 	else
 		timeout = HL_DEVICE_TIMEOUT_USEC;
 
-	if (!hdev->asic_funcs->is_device_idle(hdev, NULL)) {
+	if (!hdev->asic_funcs->is_device_idle(hdev, NULL, NULL)) {
 		dev_err_ratelimited(hdev->dev,
 			"Can't send KMD job on QMAN0 because the device is not idle\n");
 		return -EBUSY;
@@ -4914,7 +4914,8 @@ int goya_armcp_info_get(struct hl_device *hdev)
 	return 0;
 }
 
-static bool goya_is_device_idle(struct hl_device *hdev, struct seq_file *s)
+static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask,
+				struct seq_file *s)
 {
 	const char *fmt = "%-5d%-9s%#-14x%#-16x%#x\n";
 	const char *dma_fmt = "%-5d%-9s%#-14x%#x\n";
@@ -4937,6 +4938,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, struct seq_file *s)
 				IS_DMA_IDLE(dma_core_sts0);
 		is_idle &= is_eng_idle;
 
+		if (mask)
+			*mask |= !is_eng_idle << (GOYA_ENGINE_ID_DMA_0 + i);
 		if (s)
 			seq_printf(s, dma_fmt, i, is_eng_idle ? "Y" : "N",
 					qm_glbl_sts0, dma_core_sts0);
@@ -4958,6 +4961,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, struct seq_file *s)
 				IS_TPC_IDLE(tpc_cfg_sts);
 		is_idle &= is_eng_idle;
 
+		if (mask)
+			*mask |= !is_eng_idle << (GOYA_ENGINE_ID_TPC_0 + i);
 		if (s)
 			seq_printf(s, fmt, i, is_eng_idle ? "Y" : "N",
 				qm_glbl_sts0, cmdq_glbl_sts0, tpc_cfg_sts);
@@ -4976,6 +4981,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, struct seq_file *s)
 			IS_MME_IDLE(mme_arch_sts);
 	is_idle &= is_eng_idle;
 
+	if (mask)
+		*mask |= !is_eng_idle << GOYA_ENGINE_ID_MME_0;
 	if (s) {
 		seq_printf(s, fmt, 0, is_eng_idle ? "Y" : "N", qm_glbl_sts0,
 				cmdq_glbl_sts0, mme_arch_sts);

drivers/misc/habanalabs/habanalabs.h

@@ -557,7 +557,8 @@ struct hl_asic_funcs {
 			u32 asid, u64 va, u64 size);
 	int (*send_heartbeat)(struct hl_device *hdev);
 	int (*debug_coresight)(struct hl_device *hdev, void *data);
-	bool (*is_device_idle)(struct hl_device *hdev, struct seq_file *s);
+	bool (*is_device_idle)(struct hl_device *hdev, u32 *mask,
+				struct seq_file *s);
 	int (*soft_reset_late_init)(struct hl_device *hdev);
 	void (*hw_queues_lock)(struct hl_device *hdev);
 	void (*hw_queues_unlock)(struct hl_device *hdev);

drivers/misc/habanalabs/habanalabs_ioctl.c

@@ -119,7 +119,8 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
 	if ((!max_size) || (!out))
 		return -EINVAL;
 
-	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev, NULL);
+	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
+					&hw_idle.busy_engines_mask, NULL);
 
 	return copy_to_user(out, &hw_idle,
 		min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;

include/uapi/misc/habanalabs.h

@@ -45,6 +45,30 @@ enum goya_queue_id {
 	GOYA_QUEUE_ID_SIZE
 };
 
+/*
+ * Engine Numbering
+ *
+ * Used in the "busy_engines_mask" field in `struct hl_info_hw_idle'
+ */
+
+enum goya_engine_id {
+	GOYA_ENGINE_ID_DMA_0 = 0,
+	GOYA_ENGINE_ID_DMA_1,
+	GOYA_ENGINE_ID_DMA_2,
+	GOYA_ENGINE_ID_DMA_3,
+	GOYA_ENGINE_ID_DMA_4,
+	GOYA_ENGINE_ID_MME_0,
+	GOYA_ENGINE_ID_TPC_0,
+	GOYA_ENGINE_ID_TPC_1,
+	GOYA_ENGINE_ID_TPC_2,
+	GOYA_ENGINE_ID_TPC_3,
+	GOYA_ENGINE_ID_TPC_4,
+	GOYA_ENGINE_ID_TPC_5,
+	GOYA_ENGINE_ID_TPC_6,
+	GOYA_ENGINE_ID_TPC_7,
+	GOYA_ENGINE_ID_SIZE
+};
+
 enum hl_device_status {
 	HL_DEVICE_STATUS_OPERATIONAL,
 	HL_DEVICE_STATUS_IN_RESET,
@@ -86,7 +110,11 @@ struct hl_info_dram_usage {
 
 struct hl_info_hw_idle {
 	__u32 is_idle;
-	__u32 pad;
+	/*
+	 * Bitmask of busy engines.
+	 * Bits definition is according to `enum <chip>_enging_id'.
+	 */
+	__u32 busy_engines_mask;
 };
 
 struct hl_info_device_status {