Merge tag 'amd-drm-next-6.12-2024-08-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.12-2024-08-26:

amdgpu:
- SDMA devcoredump support
- DCN 4.0.1 updates
- DC SUBVP fixes
- Refactor OPP in DC
- Refactor MMHUBBUB in DC
- DC DML 2.1 updates
- DC FAMS2 updates
- RAS updates
- GFX12 updates
- VCN 4.0.3 updates
- JPEG 4.0.3 updates
- Enable wave kill (soft recovery) for compute queues
- Clean up CP error interrupt handling
- Enable CP bad opcode interrupts
- VCN 4.x fixes
- VCN 5.x fixes
- GPU reset fixes
- Fix vbios embedded EDID size handling
- SMU 14.x updates
- Misc code cleanups and spelling fixes
- VCN devcoredump support
- ISP MFD i2c support
- DC vblank fixes
- GFX 12 fixes
- PSR fixes
- Convert vbios embedded EDID to drm_edid
- DCN 3.5 updates
- DMCUB updates
- Cursor fixes
- Overdrive support for SMU 14.x
- GFX CP padding optimizations
- DCC fixes
- DSC fixes
- Preliminary per queue reset infrastructure
- Initial per queue reset support for GFX 9
- Initial per queue reset support for GFX 7, 8
- DCN 3.2 fixes
- DP MST fixes
- SR-IOV fixes
- GFX 9.4.3/4 devcoredump support
- Add process isolation framework
- Enable process isolation support for GFX 9.4.3/4
- Take IOMMU remapping into account for P2P DMA checks

amdkfd:
- CRIU fixes
- Improved input validation for user queues
- HMM fix
- Enable process isolation support for GFX 9.4.3/4
- Initial per queue reset support for GFX 9
- Allow users to target recommended SDMA engines

radeon:
- remove .load and drm_dev_alloc
- Fix vbios embedded EDID size handling
- Convert vbios embedded EDID to drm_edid
- Use GEM references instead of TTM
- r100 cp init cleanup
- Fix potential overflows in evergreen CS offset tracking

UAPI:
- KFD support for targetting queues on recommended SDMA engines
  Proposed userspace:
  https://github.com/ROCm/ROCR-Runtime/commit/2f588a24065f41c208c3701945e20be746d8faf7
  https://github.com/ROCm/ROCR-Runtime/commit/eb30a5bbc7719c6ffcf2d2dd2878bc53a47b3f30

drm/buddy:
- Add start address support for trim function

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240826201528.55307-1-alexander.deucher@amd.com

1 files changed, 105 insertions, 35 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 1cb1ec7beefe..44c74a08987d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -501,60 +501,50 @@ int amdgpu_mes_remove_gang(struct amdgpu_device *adev, int gang_id)
 
 int amdgpu_mes_suspend(struct amdgpu_device *adev)
 {
-	struct idr *idp;
-	struct amdgpu_mes_process *process;
-	struct amdgpu_mes_gang *gang;
 	struct mes_suspend_gang_input input;
-	int r, pasid;
+	int r;
+
+	if (!amdgpu_mes_suspend_resume_all_supported(adev))
+		return 0;
+
+	memset(&input, 0x0, sizeof(struct mes_suspend_gang_input));
+	input.suspend_all_gangs = 1;
 
 	/*
 	 * Avoid taking any other locks under MES lock to avoid circular
 	 * lock dependencies.
 	 */
 	amdgpu_mes_lock(&adev->mes);
-
-	idp = &adev->mes.pasid_idr;
-
-	idr_for_each_entry(idp, process, pasid) {
-		list_for_each_entry(gang, &process->gang_list, list) {
-			r = adev->mes.funcs->suspend_gang(&adev->mes, &input);
-			if (r)
-				DRM_ERROR("failed to suspend pasid %d gangid %d",
-					 pasid, gang->gang_id);
-		}
-	}
-
+	r = adev->mes.funcs->suspend_gang(&adev->mes, &input);
 	amdgpu_mes_unlock(&adev->mes);
-	return 0;
+	if (r)
+		DRM_ERROR("failed to suspend all gangs");
+
+	return r;
 }
 
 int amdgpu_mes_resume(struct amdgpu_device *adev)
 {
-	struct idr *idp;
-	struct amdgpu_mes_process *process;
-	struct amdgpu_mes_gang *gang;
 	struct mes_resume_gang_input input;
-	int r, pasid;
+	int r;
+
+	if (!amdgpu_mes_suspend_resume_all_supported(adev))
+		return 0;
+
+	memset(&input, 0x0, sizeof(struct mes_resume_gang_input));
+	input.resume_all_gangs = 1;
 
 	/*
 	 * Avoid taking any other locks under MES lock to avoid circular
 	 * lock dependencies.
 	 */
 	amdgpu_mes_lock(&adev->mes);
-
-	idp = &adev->mes.pasid_idr;
-
-	idr_for_each_entry(idp, process, pasid) {
-		list_for_each_entry(gang, &process->gang_list, list) {
-			r = adev->mes.funcs->resume_gang(&adev->mes, &input);
-			if (r)
-				DRM_ERROR("failed to resume pasid %d gangid %d",
-					 pasid, gang->gang_id);
-		}
-	}
-
+	r = adev->mes.funcs->resume_gang(&adev->mes, &input);
 	amdgpu_mes_unlock(&adev->mes);
-	return 0;
+	if (r)
+		DRM_ERROR("failed to resume all gangs");
+
+	return r;
 }
 
 static int amdgpu_mes_queue_alloc_mqd(struct amdgpu_device *adev,
@@ -793,6 +783,49 @@ int amdgpu_mes_remove_hw_queue(struct amdgpu_device *adev, int queue_id)
 	return 0;
 }
 
+int amdgpu_mes_reset_hw_queue(struct amdgpu_device *adev, int queue_id)
+{
+	unsigned long flags;
+	struct amdgpu_mes_queue *queue;
+	struct amdgpu_mes_gang *gang;
+	struct mes_reset_queue_input queue_input;
+	int r;
+
+	/*
+	 * Avoid taking any other locks under MES lock to avoid circular
+	 * lock dependencies.
+	 */
+	amdgpu_mes_lock(&adev->mes);
+
+	/* remove the mes gang from idr list */
+	spin_lock_irqsave(&adev->mes.queue_id_lock, flags);
+
+	queue = idr_find(&adev->mes.queue_id_idr, queue_id);
+	if (!queue) {
+		spin_unlock_irqrestore(&adev->mes.queue_id_lock, flags);
+		amdgpu_mes_unlock(&adev->mes);
+		DRM_ERROR("queue id %d doesn't exist\n", queue_id);
+		return -EINVAL;
+	}
+	spin_unlock_irqrestore(&adev->mes.queue_id_lock, flags);
+
+	DRM_DEBUG("try to reset queue, doorbell off = 0x%llx\n",
+		  queue->doorbell_off);
+
+	gang = queue->gang;
+	queue_input.doorbell_offset = queue->doorbell_off;
+	queue_input.gang_context_addr = gang->gang_ctx_gpu_addr;
+
+	r = adev->mes.funcs->reset_hw_queue(&adev->mes, &queue_input);
+	if (r)
+		DRM_ERROR("failed to reset hardware queue, queue id = %d\n",
+			  queue_id);
+
+	amdgpu_mes_unlock(&adev->mes);
+
+	return 0;
+}
+
 int amdgpu_mes_map_legacy_queue(struct amdgpu_device *adev,
 				struct amdgpu_ring *ring)
 {
@@ -838,6 +871,30 @@ int amdgpu_mes_unmap_legacy_queue(struct amdgpu_device *adev,
 	return r;
 }
 
+int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev,
+				  struct amdgpu_ring *ring,
+				  unsigned int vmid)
+{
+	struct mes_reset_legacy_queue_input queue_input;
+	int r;
+
+	memset(&queue_input, 0, sizeof(queue_input));
+
+	queue_input.queue_type = ring->funcs->type;
+	queue_input.doorbell_offset = ring->doorbell_index;
+	queue_input.pipe_id = ring->pipe;
+	queue_input.queue_id = ring->queue;
+	queue_input.mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
+	queue_input.wptr_addr = ring->wptr_gpu_addr;
+	queue_input.vmid = vmid;
+
+	r = adev->mes.funcs->reset_legacy_queue(&adev->mes, &queue_input);
+	if (r)
+		DRM_ERROR("failed to reset legacy queue\n");
+
+	return r;
+}
+
 uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg)
 {
 	struct mes_misc_op_input op_input;
@@ -1533,7 +1590,7 @@ int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe)
 			 pipe == AMDGPU_MES_SCHED_PIPE ? "" : "1");
 	}
 
-	r = amdgpu_ucode_request(adev, &adev->mes.fw[pipe], fw_name);
+	r = amdgpu_ucode_request(adev, &adev->mes.fw[pipe], "%s", fw_name);
 	if (r && need_retry && pipe == AMDGPU_MES_SCHED_PIPE) {
 		dev_info(adev->dev, "try to fall back to %s_mes.bin\n", ucode_prefix);
 		r = amdgpu_ucode_request(adev, &adev->mes.fw[pipe],
@@ -1584,6 +1641,19 @@ out:
 	return r;
 }
 
+bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev)
+{
+	uint32_t mes_rev = adev->mes.sched_version & AMDGPU_MES_VERSION_MASK;
+	bool is_supported = false;
+
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0) &&
+	    amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(12, 0, 0) &&
+	    mes_rev >= 0x63)
+		is_supported = true;
+
+	return is_supported;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)