Commit a6395256 authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'amd-drm-fixes-6.8-2024-02-01' of... 

Merge tag 'amd-drm-fixes-6.8-2024-02-01' of https://gitlab.freedesktop.org/agd5f/linux

 into drm-fixes

amd-drm-fixes-6.8-2024-02-01:

amdgpu:
- Fix reboot issue seen on some 7000 series dGPUs
- Fix client init order for KFD
- Misc display fixes
- USB-C fix
- DCN 3.5 fixes
- Fix issues with GPU scheduler and GPU reset
- GPU firmware loading fix
- Misc fixes
- GC 11.5 fix
- VCN 4.0.5 fix
- IH overflow fix

amdkfd:
- SVM fixes
- Trap handler fix
- Fix device permission lookup
- Properly reserve BO before validating it

Signed-off-by: default avatarDave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240201184108.4923-1-alexander.deucher@amd.com
parents 111a3f0a 6813cdca

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

+21 −11
Original line number Diff line number Diff line
@@ -141,11 +141,31 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work) 
static const struct drm_client_funcs kfd_client_funcs = {

	.unregister	= drm_client_release,

};



int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev)

{

	int ret;



	if (!adev->kfd.init_complete)

		return 0;



	ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",

			      &kfd_client_funcs);

	if (ret) {

		dev_err(adev->dev, "Failed to init DRM client: %d\n",

			ret);

		return ret;

	}



	drm_client_register(&adev->kfd.client);



	return 0;

}



void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)

{

	int i;

	int last_valid_bit;

	int ret;



	amdgpu_amdkfd_gpuvm_init_mem_limits();
@@ -164,12 +184,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) 
			.enable_mes = adev->enable_mes,

		};



		ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs);

		if (ret) {

			dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);

			return;

		}



		/* this is going to have a few of the MSBs set that we need to

		 * clear

		 */
@@ -208,10 +222,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) 


		adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,

							&gpu_resources);

		if (adev->kfd.init_complete)

			drm_client_register(&adev->kfd.client);

		else

			drm_client_release(&adev->kfd.client);



		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;

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

+3 −1
Original line number Diff line number Diff line
@@ -182,6 +182,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev, 
struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,

				struct mm_struct *mm,

				struct svm_range_bo *svm_bo);



int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev);

#if defined(CONFIG_DEBUG_FS)

int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data);

#endif
@@ -301,7 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev, 
					  struct kgd_mem *mem, void *drm_priv);

int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(

		struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv);

void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);

int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);

int amdgpu_amdkfd_gpuvm_sync_memory(

		struct amdgpu_device *adev, struct kgd_mem *mem, bool intr);

int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,

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

+1 −1
Original line number Diff line number Diff line
@@ -290,7 +290,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus 
	for (i = 0; i < adev->gfx.num_compute_rings; i++) {

		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];



		if (!(ring && drm_sched_wqueue_ready(&ring->sched)))

		if (!amdgpu_ring_sched_ready(ring))

			continue;



		/* stop secheduler and drain ring. */

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

+17 −3
Original line number Diff line number Diff line
@@ -2085,21 +2085,35 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( 
	return ret;

}



void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)

int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)

{

	struct kfd_mem_attachment *entry;

	struct amdgpu_vm *vm;

	int ret;



	vm = drm_priv_to_vm(drm_priv);



	mutex_lock(&mem->lock);



	ret = amdgpu_bo_reserve(mem->bo, true);

	if (ret)

		goto out;



	list_for_each_entry(entry, &mem->attachments, list) {

		if (entry->bo_va->base.vm == vm)

		if (entry->bo_va->base.vm != vm)

			continue;

		if (entry->bo_va->base.bo->tbo.ttm &&

		    !entry->bo_va->base.bo->tbo.ttm->sg)

			continue;



		kfd_mem_dmaunmap_attachment(mem, entry);

	}



	amdgpu_bo_unreserve(mem->bo);

out:

	mutex_unlock(&mem->lock);



	return ret;

}



int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(

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

+4 −4
Original line number Diff line number Diff line
@@ -1678,7 +1678,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused) 
	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {

		struct amdgpu_ring *ring = adev->rings[i];



		if (!ring || !drm_sched_wqueue_ready(&ring->sched))

		if (!amdgpu_ring_sched_ready(ring))

			continue;

		drm_sched_wqueue_stop(&ring->sched);

	}
@@ -1694,7 +1694,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused) 
	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {

		struct amdgpu_ring *ring = adev->rings[i];



		if (!ring || !drm_sched_wqueue_ready(&ring->sched))

		if (!amdgpu_ring_sched_ready(ring))

			continue;

		drm_sched_wqueue_start(&ring->sched);

	}
@@ -1916,8 +1916,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val) 


	ring = adev->rings[val];



	if (!ring || !ring->funcs->preempt_ib ||

	    !drm_sched_wqueue_ready(&ring->sched))

	if (!amdgpu_ring_sched_ready(ring) ||

	    !ring->funcs->preempt_ib)

		return -EINVAL;



	/* the last preemption failed */