accel/ivpu: Add FW state dump on TDR

[ Upstream commit 5e162f8 ]

Send JSM state dump message at the beginning of TDR handler. This allows
FW to collect debug info in the FW log before the state of the NPU is
lost allowing to analyze the cause of a TDR.

Wait a predefined timeout (10 ms) so the FW has a chance to write debug
logs. We cannot wait for JSM response at this point because IRQs are
already disabled before TDR handler is invoked.

Signed-off-by: Tomasz Rusinowicz <tomasz.rusinowicz@intel.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240930195322.461209-9-jacek.lawrynowicz@linux.intel.com
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Stable-dep-of: 41a2d82 ("accel/ivpu: Fix error handling in recovery/reset")
Signed-off-by: Sasha Levin <sashal@kernel.org>

Author: trusinowicz

drivers/accel/ivpu/ivpu_drv.h

@@ -152,6 +152,7 @@ struct ivpu_device {
 		int tdr;
 		int autosuspend;
 		int d0i3_entry_msg;
+		int state_dump_msg;
 	} timeout;
 };
 

drivers/accel/ivpu/ivpu_hw.c

@@ -89,12 +89,14 @@ static void timeouts_init(struct ivpu_device *vdev)
 		vdev->timeout.tdr = 2000000;
 		vdev->timeout.autosuspend = -1;
 		vdev->timeout.d0i3_entry_msg = 500;
+		vdev->timeout.state_dump_msg = 10;
 	} else if (ivpu_is_simics(vdev)) {
 		vdev->timeout.boot = 50;
 		vdev->timeout.jsm = 500;
 		vdev->timeout.tdr = 10000;
 		vdev->timeout.autosuspend = -1;
 		vdev->timeout.d0i3_entry_msg = 100;
+		vdev->timeout.state_dump_msg = 10;
 	} else {
 		vdev->timeout.boot = 1000;
 		vdev->timeout.jsm = 500;
@@ -104,6 +106,7 @@ static void timeouts_init(struct ivpu_device *vdev)
 		else
 			vdev->timeout.autosuspend = 100;
 		vdev->timeout.d0i3_entry_msg = 5;
+		vdev->timeout.state_dump_msg = 10;
 	}
 }
 

drivers/accel/ivpu/ivpu_ipc.c

@@ -353,6 +353,32 @@ int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
 	return ret;
 }
 
+int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+			   u32 channel, unsigned long timeout_ms)
+{
+	struct ivpu_ipc_consumer cons;
+	int ret;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	ivpu_ipc_consumer_add(vdev, &cons, channel, NULL);
+
+	ret = ivpu_ipc_send(vdev, &cons, req);
+	if (ret) {
+		ivpu_warn_ratelimited(vdev, "IPC send failed: %d\n", ret);
+		goto consumer_del;
+	}
+
+	msleep(timeout_ms);
+
+consumer_del:
+	ivpu_ipc_consumer_del(vdev, &cons);
+	ivpu_rpm_put(vdev);
+	return ret;
+}
+
 static bool
 ivpu_ipc_match_consumer(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 			struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg)

drivers/accel/ivpu/ivpu_ipc.h

@@ -107,5 +107,7 @@ int ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg
 int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
 			  enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
 			  u32 channel, unsigned long timeout_ms);
+int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+			   u32 channel, unsigned long timeout_ms);
 
 #endif /* __IVPU_IPC_H__ */

drivers/accel/ivpu/ivpu_jsm_msg.c

@@ -555,3 +555,11 @@ int ivpu_jsm_dct_disable(struct ivpu_device *vdev)
 	return ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_DCT_DISABLE_DONE, &resp,
 					      VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
 }
+
+int ivpu_jsm_state_dump(struct ivpu_device *vdev)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_STATE_DUMP };
+
+	return ivpu_ipc_send_and_wait(vdev, &req, VPU_IPC_CHAN_ASYNC_CMD,
+				      vdev->timeout.state_dump_msg);
+}

drivers/accel/ivpu/ivpu_jsm_msg.h

@@ -43,4 +43,6 @@ int ivpu_jsm_metric_streamer_info(struct ivpu_device *vdev, u64 metric_group_mas
 				  u64 buffer_size, u32 *sample_size, u64 *info_size);
 int ivpu_jsm_dct_enable(struct ivpu_device *vdev, u32 active_us, u32 inactive_us);
 int ivpu_jsm_dct_disable(struct ivpu_device *vdev);
+int ivpu_jsm_state_dump(struct ivpu_device *vdev);
+
 #endif

drivers/accel/ivpu/ivpu_pm.c

@@ -124,6 +124,7 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
 	if (ret)
 		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
 
+	ivpu_jsm_state_dump(vdev);
 	ivpu_dev_coredump(vdev);
 
 	atomic_inc(&vdev->pm->reset_counter);