Merge tag 'amd-drm-next-6.1-2022-09-08' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.1-2022-09-08:

amdgpu:
- Mode2 reset for RDNA2
- Lots of new DC documentation
- Add documentation about different asic families
- DSC improvements
- Aldebaran fixes
- Misc spelling and grammar fixes
- GFXOFF stats support for vangogh
- DC frame size fixes
- NBIO 7.7 updates
- DCN 3.2 updates
- DCN 3.1.4 Updates
- SMU 13.x updates
- Misc bug fixes
- Rework DC register offset handling
- GC 11.x updates
- PSP 13.x updates
- SDMA 6.x updates
- GMC 11.x updates
- SR-IOV updates
- PSP fixes for TA unloading
- DSC passthrough support
- Misc code cleanups

amdkfd:
- ISA fixes for some GC 10.3 IPs
- Misc code cleanups

radeon:
- Delayed work flush fix
- Use time_after for some jiffies calculations

drm:
- DSC passthrough aux support

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220908155202.57862-1-alexander.deucher@amd.com

1 files changed, 20 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e8a0b19b7398..62b26f0e37b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2456,12 +2456,14 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			if (!hive->reset_domain ||
 			    !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
 				r = -ENOENT;
+				amdgpu_put_xgmi_hive(hive);
 				goto init_failed;
 			}
 
 			/* Drop the early temporary reset domain we created for device */
 			amdgpu_reset_put_reset_domain(adev->reset_domain);
 			adev->reset_domain = hive->reset_domain;
+			amdgpu_put_xgmi_hive(hive);
 		}
 	}
 
@@ -3577,6 +3579,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	INIT_WORK(&adev->xgmi_reset_work, amdgpu_device_xgmi_reset_func);
 
 	adev->gfx.gfx_off_req_count = 1;
+	adev->gfx.gfx_off_residency = 0;
+	adev->gfx.gfx_off_entrycount = 0;
 	adev->pm.ac_power = power_supply_is_system_supplied() > 0;
 
 	atomic_set(&adev->throttling_logging_enabled, 1);
@@ -3965,8 +3969,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 	amdgpu_gart_dummy_page_fini(adev);
 
-	if (drm_dev_is_unplugged(adev_to_drm(adev)))
-		amdgpu_device_unmap_mmio(adev);
+	amdgpu_device_unmap_mmio(adev);
 
 }
 
@@ -4413,8 +4416,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 retry:
 	amdgpu_amdkfd_pre_reset(adev);
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	if (from_hypervisor)
 		r = amdgpu_virt_request_full_gpu(adev, true);
 	else
@@ -4509,14 +4510,15 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
  */
 bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 {
-	if (!amdgpu_device_ip_check_soft_reset(adev)) {
-		dev_info(adev->dev, "Timeout, but no hardware hang detected.\n");
-		return false;
-	}
 
 	if (amdgpu_gpu_recovery == 0)
 		goto disabled;
 
+	if (!amdgpu_device_ip_check_soft_reset(adev)) {
+		dev_info(adev->dev,"Timeout, but no hardware hang detected.\n");
+		return false;
+	}
+
 	if (amdgpu_sriov_vf(adev))
 		return true;
 
@@ -4641,7 +4643,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 		if (!need_full_reset)
 			need_full_reset = amdgpu_device_ip_need_full_reset(adev);
 
-		if (!need_full_reset) {
+		if (!need_full_reset && amdgpu_gpu_recovery) {
 			amdgpu_device_ip_pre_soft_reset(adev);
 			r = amdgpu_device_ip_soft_reset(adev);
 			amdgpu_device_ip_post_soft_reset(adev);
@@ -5039,6 +5041,7 @@ static void amdgpu_device_recheck_guilty_jobs(
 
 			/* set guilty */
 			drm_sched_increase_karma(s_job);
+			amdgpu_reset_prepare_hwcontext(adev, reset_context);
 retry:
 			/* do hw reset */
 			if (amdgpu_sriov_vf(adev)) {
@@ -5148,6 +5151,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 	reset_context->job = job;
 	reset_context->hive = hive;
+
 	/*
 	 * Build list of devices to reset.
 	 * In case we are in XGMI hive mode, resort the device list
@@ -5267,8 +5271,11 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 			amdgpu_ras_resume(adev);
 	} else {
 		r = amdgpu_do_asic_reset(device_list_handle, reset_context);
-		if (r && r == -EAGAIN)
+		if (r && r == -EAGAIN) {
+			set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags);
+			adev->asic_reset_res = 0;
 			goto retry;
+		}
 	}
 
 skip_hw_reset:
@@ -5524,7 +5531,8 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 		~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
 	resource_size_t aper_limit =
 		adev->gmc.aper_base + adev->gmc.aper_size - 1;
-	bool p2p_access = !(pci_p2pdma_distance_many(adev->pdev,
+	bool p2p_access = !adev->gmc.xgmi.connected_to_cpu &&
+			  !(pci_p2pdma_distance_many(adev->pdev,
 					&peer_adev->dev, 1, true) < 0);
 
 	return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size &&
@@ -5699,6 +5707,7 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	reset_context.reset_req_dev = adev;
 	set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 	set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags);
+	set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
 
 	adev->no_hw_access = true;
 	r = amdgpu_device_pre_asic_reset(adev, &reset_context);