From: chong li <chongli2@amd.com>
Date: Fri, 7 Nov 2025 03:59:28 +0000 (+0800)
Subject: drm/amdgpu: reduce the full gpu access time in amdgpu_device_init.
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c71980a3fc1dd7bf2f3c10b113d917e9f3cd10ae;p=thirdparty%2Fkernel%2Flinux.git

drm/amdgpu: reduce the full gpu access time in amdgpu_device_init.

[Why]
function "devm_memremap_pages" in function "kgd2kfd_init_zone_device",
sometimes cost too much time.

[How]
move the function "kgd2kfd_init_zone_device"
after release full gpu access(amdgpu_virt_release_full_gpu).

v2:
improve the coding style.

Signed-off-by: chong li <chongli2@amd.com>
Reviewed-by: Emily Deng <Emily.Deng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 8bdfcde2029b..335d733751cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -37,7 +37,7 @@
 #include "amdgpu_sync.h"
 #include "amdgpu_vm.h"
 #include "amdgpu_xcp.h"
-
+#include "kfd_topology.h"
 extern uint64_t amdgpu_amdkfd_total_mem_size;
 
 enum TLB_FLUSH_TYPE {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6fb82d6c9a1a..06f4cdcccb4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3317,7 +3317,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 
 	/* Don't init kfd if whole hive need to be reset during init */
 	if (adev->init_lvl->level != AMDGPU_INIT_LEVEL_MINIMAL_XGMI) {
-		kgd2kfd_init_zone_device(adev);
 		amdgpu_amdkfd_device_init(adev);
 	}
 
@@ -4934,6 +4933,13 @@ fence_driver_init:
 
 	if (adev->init_lvl->level == AMDGPU_INIT_LEVEL_MINIMAL_XGMI)
 		amdgpu_xgmi_reset_on_init(adev);
+
+	/* Don't init kfd if whole hive need to be reset during init */
+	if (adev->init_lvl->level != AMDGPU_INIT_LEVEL_MINIMAL_XGMI) {
+		kgd2kfd_init_zone_device(adev);
+		kfd_update_svm_support_properties(adev);
+	}
+
 	/*
 	 * Place those sysfs registering after `late_init`. As some of those
 	 * operations performed in `late_init` might affect the sysfs
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 811636af14ea..9c3e8f946a3d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -2404,3 +2404,26 @@ int kfd_debugfs_rls_by_device(struct seq_file *m, void *data)
 }
 
 #endif
+
+void kfd_update_svm_support_properties(struct amdgpu_device *adev)
+{
+	struct kfd_topology_device *dev;
+	int ret;
+
+	down_write(&topology_lock);
+	list_for_each_entry(dev, &topology_device_list, list) {
+		if (!dev->gpu || dev->gpu->adev != adev)
+			continue;
+
+		if (KFD_IS_SVM_API_SUPPORTED(adev)) {
+			dev->node_props.capability |= HSA_CAP_SVMAPI_SUPPORTED;
+			ret = kfd_topology_update_sysfs();
+			if (!ret)
+				sys_props.generation_count++;
+			else
+				dev_err(adev->dev, "Failed to update SVM support properties. ret=%d\n", ret);
+		} else
+			dev->node_props.capability &= ~HSA_CAP_SVMAPI_SUPPORTED;
+	}
+	up_write(&topology_lock);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index 3de8ec0043bb..ad63ba67b577 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -201,4 +201,10 @@ struct kfd_topology_device *kfd_create_topology_device(
 		struct list_head *device_list);
 void kfd_release_topology_device_list(struct list_head *device_list);
 
+#if IS_ENABLED(CONFIG_HSA_AMD)
+void kfd_update_svm_support_properties(struct amdgpu_device *adev);
+#else
+static inline void kfd_update_svm_support_properties(struct amdgpu_device *adev) {}
+#endif
+
 #endif /* __KFD_TOPOLOGY_H__ */