drm/amdkfd: display debug capabilities

Expose debug capabilities in the KFD topology node's HSA capabilities and
debug properties flags.

Ensure correct capabilities are exposed based on firmware support.

Flag definitions can be referenced in uapi/linux/kfd_sysfs.h.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 96 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 8302d8967158..3def25b2bdbb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -535,6 +535,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 				      dev->gpu->kfd->mec_fw_version);
 		sysfs_show_32bit_prop(buffer, offs, "capability",
 				      dev->node_props.capability);
+		sysfs_show_64bit_prop(buffer, offs, "debug_prop",
+				      dev->node_props.debug_prop);
 		sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version",
 				      dev->gpu->kfd->sdma_fw_version);
 		sysfs_show_64bit_prop(buffer, offs, "unique_id",
@@ -1857,6 +1859,97 @@ err:
 	return res;
 }
 
+static void kfd_topology_set_dbg_firmware_support(struct kfd_topology_device *dev)
+{
+	bool firmware_supported = true;
+
+	if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(11, 0, 0) &&
+			KFD_GC_VERSION(dev->gpu) < IP_VERSION(12, 0, 0)) {
+		firmware_supported =
+			(dev->gpu->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 9;
+		goto out;
+	}
+
+	/*
+	 * Note: Any unlisted devices here are assumed to support exception handling.
+	 * Add additional checks here as needed.
+	 */
+	switch (KFD_GC_VERSION(dev->gpu)) {
+	case IP_VERSION(9, 0, 1):
+		firmware_supported = dev->gpu->kfd->mec_fw_version >= 459 + 32768;
+		break;
+	case IP_VERSION(9, 1, 0):
+	case IP_VERSION(9, 2, 1):
+	case IP_VERSION(9, 2, 2):
+	case IP_VERSION(9, 3, 0):
+	case IP_VERSION(9, 4, 0):
+		firmware_supported = dev->gpu->kfd->mec_fw_version >= 459;
+		break;
+	case IP_VERSION(9, 4, 1):
+		firmware_supported = dev->gpu->kfd->mec_fw_version >= 60;
+		break;
+	case IP_VERSION(9, 4, 2):
+		firmware_supported = dev->gpu->kfd->mec_fw_version >= 51;
+		break;
+	case IP_VERSION(10, 1, 10):
+	case IP_VERSION(10, 1, 2):
+	case IP_VERSION(10, 1, 1):
+		firmware_supported = dev->gpu->kfd->mec_fw_version >= 144;
+		break;
+	case IP_VERSION(10, 3, 0):
+	case IP_VERSION(10, 3, 2):
+	case IP_VERSION(10, 3, 1):
+	case IP_VERSION(10, 3, 4):
+	case IP_VERSION(10, 3, 5):
+		firmware_supported = dev->gpu->kfd->mec_fw_version >= 89;
+		break;
+	case IP_VERSION(10, 1, 3):
+	case IP_VERSION(10, 3, 3):
+		firmware_supported = false;
+		break;
+	default:
+		break;
+	}
+
+out:
+	if (firmware_supported)
+		dev->node_props.capability |= HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED;
+}
+
+static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
+{
+	dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 <<
+				HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
+				HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
+
+	dev->node_props.capability |= HSA_CAP_TRAP_DEBUG_SUPPORT |
+			HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_TRAP_OVERRIDE_SUPPORTED |
+			HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_MODE_SUPPORTED;
+
+	if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) {
+		dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX9 |
+						HSA_DBG_WATCH_ADDR_MASK_HI_BIT;
+
+		if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(9, 4, 2))
+			dev->node_props.debug_prop |=
+				HSA_DBG_DISPATCH_INFO_ALWAYS_VALID;
+		else
+			dev->node_props.capability |=
+				HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED;
+	} else {
+		dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 |
+					HSA_DBG_WATCH_ADDR_MASK_HI_BIT;
+
+		if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(11, 0, 0))
+			dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID;
+		else
+			dev->node_props.capability |=
+				HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED;
+	}
+
+	kfd_topology_set_dbg_firmware_support(dev);
+}
+
 int kfd_topology_add_device(struct kfd_node *gpu)
 {
 	uint32_t gpu_id;
@@ -1967,13 +2060,11 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
 		break;
 	default:
-		if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(9, 0, 1))
-			dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 <<
-				HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
-				HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
-		else
+		if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(9, 0, 1))
 			WARN(1, "Unexpected ASIC family %u",
 			     dev->gpu->adev->asic_type);
+		else
+			kfd_topology_set_capabilities(dev);
 	}
 
 	/*