drm/amdgpu: Add sysfs interface for sdma reset mask

Add the sysfs interface for sdma:
sdma_reset_mask

The interface is read-only and show the resets supported by the IP.
For example, full adapter reset (mode1/mode2/BACO/etc),
soft reset, queue reset, and pipe reset.

V2: the sysfs node returns a text string instead of some flags (Christian)
v3: add a generic helper which takes the ring as parameter
   and print the strings in the order they are applied (Christian)

   check amdgpu_gpu_recovery  before creating sysfs file itself,
   and initialize supported_reset_types in IP version files (Lijo)

Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Tim Huang <tim.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c

@@ -413,3 +413,44 @@ void amdgpu_debugfs_sdma_sched_mask_init(struct amdgpu_device *adev)
 			    &amdgpu_debugfs_sdma_sched_mask_fops);
 #endif
 }
+
+static ssize_t amdgpu_get_sdma_reset_mask(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (!adev)
+		return -ENODEV;
+
+	return amdgpu_show_reset_mask(buf, adev->sdma.supported_reset);
+}
+
+static DEVICE_ATTR(sdma_reset_mask, 0444,
+		   amdgpu_get_sdma_reset_mask, NULL);
+
+int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (!amdgpu_gpu_recovery)
+		return r;
+
+	if (adev->sdma.num_instances) {
+		r = device_create_file(adev->dev, &dev_attr_sdma_reset_mask);
+		if (r)
+			return r;
+	}
+
+	return r;
+}
+
+void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev)
+{
+	if (!amdgpu_gpu_recovery)
+		return;
+
+	if (adev->sdma.num_instances)
+		device_remove_file(adev->dev, &dev_attr_sdma_reset_mask);
+}

drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h

@@ -116,6 +116,7 @@ struct amdgpu_sdma {
 	struct ras_common_if	*ras_if;
 	struct amdgpu_sdma_ras	*ras;
 	uint32_t		*ip_dump;
+	uint32_t 		supported_reset;
 };
 
 /*
@@ -176,4 +177,6 @@ void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev,
         bool duplicate);
 int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_sdma_sched_mask_init(struct amdgpu_device *adev);
+int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev);
+void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev);
 #endif

drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c

@@ -1430,6 +1430,10 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+
 	if (amdgpu_sdma_ras_sw_init(adev)) {
 		dev_err(adev->dev, "fail to initialize sdma ras block\n");
 		return -EINVAL;
@@ -1442,6 +1446,10 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1456,6 +1464,7 @@ static int sdma_v4_4_2_sw_fini(struct amdgpu_ip_block *ip_block)
 			amdgpu_ring_fini(&adev->sdma.instance[i].page);
 	}
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 2) ||
 	    amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 5))
 		amdgpu_sdma_destroy_inst_ctx(adev, true);

drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c

@@ -1452,6 +1452,19 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(5, 0, 0):
+	case IP_VERSION(5, 0, 2):
+	case IP_VERSION(5, 0, 5):
+		if (adev->sdma.instance[0].fw_version >= 35)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	default:
+		break;
+	}
+
 	/* Allocate memory for SDMA IP Dump buffer */
 	ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL);
 	if (ptr)
@@ -1459,6 +1472,10 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1470,6 +1487,7 @@ static int sdma_v5_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	amdgpu_sdma_destroy_inst_ctx(adev, false);
 
 	kfree(adev->sdma.ip_dump);

drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c

@@ -1357,6 +1357,24 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(5, 2, 0):
+	case IP_VERSION(5, 2, 2):
+	case IP_VERSION(5, 2, 3):
+	case IP_VERSION(5, 2, 4):
+		if (adev->sdma.instance[0].fw_version >= 76)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	case IP_VERSION(5, 2, 5):
+		if (adev->sdma.instance[0].fw_version >= 34)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	default:
+		break;
+	}
+
 	/* Allocate memory for SDMA IP Dump buffer */
 	ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL);
 	if (ptr)
@@ -1364,6 +1382,10 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1375,6 +1397,7 @@ static int sdma_v5_2_sw_fini(struct amdgpu_ip_block *ip_block)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	amdgpu_sdma_destroy_inst_ctx(adev, true);
 
 	kfree(adev->sdma.ip_dump);

drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c

@@ -1350,6 +1350,19 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(6, 0, 0):
+	case IP_VERSION(6, 0, 2):
+	case IP_VERSION(6, 0, 3):
+		if (adev->sdma.instance[0].fw_version >= 21)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	default:
+		break;
+	}
+
 	if (amdgpu_sdma_ras_sw_init(adev)) {
 		dev_err(adev->dev, "Failed to initialize sdma ras block!\n");
 		return -EINVAL;
@@ -1362,6 +1375,10 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1373,6 +1390,7 @@ static int sdma_v6_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	amdgpu_sdma_destroy_inst_ctx(adev, true);
 
 	kfree(adev->sdma.ip_dump);