Merge tag 'amd-drm-next-6.10-2024-04-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.10-2024-04-26:

amdgpu:
- Misc code cleanups and refactors
- Support setting reset method at runtime
- Report OD status
- SMU 14.0.1 fixes
- SDMA 4.4.2 fixes
- VPE fixes
- MES fixes
- Update BO eviction priorities
- UMSCH fixes
- Reset fixes
- Freesync fixes
- GFXIP 9.4.3 fixes
- SDMA 5.2 fixes
- MES UAF fix
- RAS updates
- Devcoredump updates for dumping IP state
- DSC fixes
- JPEG fix
- Fix VRAM memory accounting
- VCN 5.0 fixes
- MES fixes
- UMC 12.0 updates
- Modify contiguous flags handling
- Initial support for mapping kernel queues via MES

amdkfd:
- Fix rescheduling of restore worker
- VRAM accounting for SVM migrations
- mGPU fix
- Enable SQ watchpoint for gfx10

Signed-off-by: Dave Airlie <[email protected]>

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

4 files changed, 11 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 55aa74cbc532..6b713fb0b818 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -371,6 +371,11 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 			err = -EINVAL;
 			goto err_wptr_map_gart;
 		}
+		if (dev->adev != amdgpu_ttm_adev(wptr_bo->tbo.bdev)) {
+			pr_err("Queue memory allocated to wrong device\n");
+			err = -EINVAL;
+			goto err_wptr_map_gart;
+		}
 
 		err = amdgpu_amdkfd_map_gtt_bo_to_gart(wptr_bo);
 		if (err) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 719d6d365e15..9596bca57212 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -435,12 +435,12 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 
 	if (!f2g) {
 		if (amdgpu_ip_version(adev, GC_HWIP, 0))
-			dev_err(kfd_device,
+			dev_info(kfd_device,
 				"GC IP %06x %s not supported in kfd\n",
 				amdgpu_ip_version(adev, GC_HWIP, 0),
 				vf ? "VF" : "");
 		else
-			dev_err(kfd_device, "%s %s not supported in kfd\n",
+			dev_info(kfd_device, "%s %s not supported in kfd\n",
 				amdgpu_asic_name[adev->asic_type], vf ? "VF" : "");
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index c3beb872adf8..e1c21d250611 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -190,7 +190,8 @@ static void event_interrupt_poison_consumption_v9(struct kfd_node *dev,
 	dev_warn(dev->adev->dev,
 		 "poison is consumed by client %d, kick off gpu reset flow\n", client_id);
 
-	amdgpu_amdkfd_ras_poison_consumption_handler(dev->adev, block, reset);
+	amdgpu_amdkfd_ras_pasid_poison_consumption_handler(dev->adev,
+		block, pasid, NULL, NULL, reset);
 }
 
 static bool context_id_expected(struct kfd_dev *dev)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 5c8d81bfce7a..4bcfbeac48fb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -77,7 +77,7 @@ svm_migrate_gart_map(struct amdgpu_ring *ring, uint64_t npages,
 
 	dst_addr = amdgpu_bo_gpu_offset(adev->gart.bo);
 	amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_addr,
-				dst_addr, num_bytes, false);
+				dst_addr, num_bytes, 0);
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
@@ -153,7 +153,7 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
 		}
 
 		r = amdgpu_copy_buffer(ring, gart_s, gart_d, size * PAGE_SIZE,
-				       NULL, &next, false, true, false);
+				       NULL, &next, false, true, 0);
 		if (r) {
 			dev_err(adev->dev, "fail %d to copy memory\n", r);
 			goto out_unlock;