Merge tag 'amd-drm-next-5.12-2021-02-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.12-2021-02-18:

amdgpu:
- Prefer Bhawan's unused variable fix
- Fixes for high priority queues on gfx8,9
- swSMU fixes for sienna cichlid
- swSMU fixes for renoir
- mmhub client id fixes for arcturus
- SMUIO fixes for navi family
- swSMU fixes for vangogh
- GPU reset cleanup
- Display fixes
- GFX harvesting fix for sienna cichlid
- Fix reference clock on Renoir
- Misc fixes and cleanups

amdkfd:
- Fix for unique id query
- Fix recursive lock warnings

radeon:
- Remove confusing VCE messages on Oland

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210218221531.3870-1-alexander.deucher@amd.com

Author: airlied

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -171,7 +171,8 @@ amdgpu-y += \
 # add SMUIO block
 amdgpu-y += \
 	smuio_v9_0.o \
-	smuio_v11_0.o
+	smuio_v11_0.o \
+	smuio_v11_0_6.o
 
 # add amdkfd interfaces
 amdgpu-y += amdgpu_amdkfd.o

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

@@ -287,7 +287,7 @@ enum amdgpu_kiq_irq {
 
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
-#define MAX_KIQ_REG_TRY 80 /* 20 -> 80 */
+#define MAX_KIQ_REG_TRY 1000
 
 int amdgpu_device_ip_set_clockgating_state(void *dev,
 					   enum amd_ip_block_type block_type,
@@ -579,7 +579,8 @@ enum amd_reset_method {
 	AMD_RESET_METHOD_MODE0,
 	AMD_RESET_METHOD_MODE1,
 	AMD_RESET_METHOD_MODE2,
-	AMD_RESET_METHOD_BACO
+	AMD_RESET_METHOD_BACO,
+	AMD_RESET_METHOD_PCI,
 };
 
 /*
@@ -891,6 +892,7 @@ struct amdgpu_device {
 	/* For pre-DCE11. DCE11 and later are in "struct amdgpu_device->dm" */
 	struct work_struct		hotplug_work;
 	struct amdgpu_irq_src		crtc_irq;
+	struct amdgpu_irq_src		vline0_irq;
 	struct amdgpu_irq_src		vupdate_irq;
 	struct amdgpu_irq_src		pageflip_irq;
 	struct amdgpu_irq_src		hpd_irq;
@@ -1227,6 +1229,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);
 int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			      struct amdgpu_job* job);
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
+int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
 
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,

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

@@ -98,8 +98,7 @@ static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p,
 	return 0;
 
 error_free:
-	if (info)
-		kvfree(info);
+	kvfree(info);
 
 	return r;
 }

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

@@ -929,6 +929,18 @@ void amdgpu_device_pci_config_reset(struct amdgpu_device *adev)
 	pci_write_config_dword(adev->pdev, 0x7c, AMDGPU_ASIC_RESET_DATA);
 }
 
+/**
+ * amdgpu_device_pci_reset - reset the GPU using generic PCI means
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Resets the GPU using generic pci reset interfaces (FLR, SBR, etc.).
+ */
+int amdgpu_device_pci_reset(struct amdgpu_device *adev)
+{
+	return pci_reset_function(adev->pdev);
+}
+
 /*
  * GPU doorbell aperture helpers function.
  */
@@ -1433,10 +1445,8 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev,
 		amdgpu_device_resume(dev, true);
 
 		dev->switch_power_state = DRM_SWITCH_POWER_ON;
-		drm_kms_helper_poll_enable(dev);
 	} else {
 		pr_info("switched off\n");
-		drm_kms_helper_poll_disable(dev);
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 		amdgpu_device_suspend(dev, true);
 		amdgpu_device_cache_pci_state(pdev);
@@ -3724,7 +3734,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
 
-	amdgpu_amdkfd_suspend(adev, !fbcon);
+	amdgpu_amdkfd_suspend(adev, adev->in_runpm);
 
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
@@ -3808,7 +3818,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 			}
 		}
 	}
-	r = amdgpu_amdkfd_resume(adev, !fbcon);
+	r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
 	if (r)
 		return r;
 
@@ -4211,6 +4221,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 		case CHIP_NAVI12:
 		case CHIP_SIENNA_CICHLID:
 		case CHIP_NAVY_FLOUNDER:
+		case CHIP_DIMGREY_CAVEFISH:
 			break;
 		default:
 			goto disabled;

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

@@ -132,8 +132,12 @@ uint amdgpu_pg_mask = 0xffffffff;
 uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu = NULL;
 char *amdgpu_virtual_display = NULL;
-/* OverDrive(bit 14) disabled by default*/
-uint amdgpu_pp_feature_mask = 0xffffbfff;
+
+/*
+ * OverDrive(bit 14) disabled by default
+ * GFX DCS(bit 19) disabled by default
+ */
+uint amdgpu_pp_feature_mask = 0xfff7bfff;
 uint amdgpu_force_long_training;
 int amdgpu_job_hang_limit;
 int amdgpu_lbpw = -1;
@@ -789,9 +793,9 @@ module_param_named(tmz, amdgpu_tmz, int, 0444);
 
 /**
  * DOC: reset_method (int)
- * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)
+ * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco, 5 = pci)
  */
-MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco/bamaco)");
+MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco/bamaco, 5 = pci)");
 module_param_named(reset_method, amdgpu_reset_method, int, 0444);
 
 /**
@@ -1344,11 +1348,12 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 	adev->in_runpm = true;
 	if (amdgpu_device_supports_atpx(drm_dev))
 		drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-	drm_kms_helper_poll_disable(drm_dev);
 
 	ret = amdgpu_device_suspend(drm_dev, false);
-	if (ret)
+	if (ret) {
+		adev->in_runpm = false;
 		return ret;
+	}
 
 	if (amdgpu_device_supports_atpx(drm_dev)) {
 		/* Only need to handle PCI state in the driver for ATPX
@@ -1401,7 +1406,6 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 		amdgpu_device_baco_exit(drm_dev);
 	}
 	ret = amdgpu_device_resume(drm_dev, false);
-	drm_kms_helper_poll_enable(drm_dev);
 	if (amdgpu_device_supports_atpx(drm_dev))
 		drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
 	adev->in_runpm = false;

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

@@ -193,15 +193,16 @@ static bool amdgpu_gfx_is_multipipe_capable(struct amdgpu_device *adev)
 }
 
 bool amdgpu_gfx_is_high_priority_compute_queue(struct amdgpu_device *adev,
-					       int pipe, int queue)
+					       struct amdgpu_ring *ring)
 {
-	bool multipipe_policy = amdgpu_gfx_is_multipipe_capable(adev);
-	int cond;
-	/* Policy: alternate between normal and high priority */
-	cond = multipipe_policy ? pipe : queue;
-
-	return ((cond % 2) != 0);
+	/* Policy: use 1st queue as high priority compute queue if we
+	 * have more than one compute queue.
+	 */
+	if (adev->gfx.num_compute_rings > 1 &&
+	    ring == &adev->gfx.compute_ring[0])
+		return true;
 
+	return false;
 }
 
 void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)

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

@@ -380,7 +380,7 @@ void amdgpu_queue_mask_bit_to_mec_queue(struct amdgpu_device *adev, int bit,
 bool amdgpu_gfx_is_mec_queue_enabled(struct amdgpu_device *adev, int mec,
 				     int pipe, int queue);
 bool amdgpu_gfx_is_high_priority_compute_queue(struct amdgpu_device *adev,
-					       int pipe, int queue);
+					       struct amdgpu_ring *ring);
 int amdgpu_gfx_me_queue_to_bit(struct amdgpu_device *adev, int me,
 			       int pipe, int queue);
 void amdgpu_gfx_bit_to_me_queue(struct amdgpu_device *adev, int bit,

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

@@ -195,6 +195,10 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if ((ib->flags & AMDGPU_IB_FLAG_EMIT_MEM_SYNC) && ring->funcs->emit_mem_sync)
 		ring->funcs->emit_mem_sync(ring);
 
+	if (ring->funcs->emit_wave_limit &&
+	    ring->hw_prio == AMDGPU_GFX_PIPE_PRIO_HIGH)
+		ring->funcs->emit_wave_limit(ring, true);
+
 	if (ring->funcs->insert_start)
 		ring->funcs->insert_start(ring);
 
@@ -295,6 +299,11 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	ring->current_ctx = fence_ctx;
 	if (vm && ring->funcs->emit_switch_buffer)
 		amdgpu_ring_emit_switch_buffer(ring);
+
+	if (ring->funcs->emit_wave_limit &&
+	    ring->hw_prio == AMDGPU_GFX_PIPE_PRIO_HIGH)
+		ring->funcs->emit_wave_limit(ring, false);
+
 	amdgpu_ring_commit(ring);
 	return 0;
 }

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

@@ -88,6 +88,7 @@ struct amdgpu_nbio_funcs {
 	int (*ras_late_init)(struct amdgpu_device *adev);
 	void (*enable_aspm)(struct amdgpu_device *adev,
 			    bool enable);
+	void (*program_aspm)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_nbio {

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

@@ -166,7 +166,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		     unsigned int max_dw, struct amdgpu_irq_src *irq_src,
 		     unsigned int irq_type, unsigned int hw_prio)
 {
-	int r, i;
+	int r;
 	int sched_hw_submission = amdgpu_sched_hw_submission;
 	u32 *num_sched;
 	u32 hw_ip;
@@ -258,8 +258,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 	}
 
 	ring->max_dw = max_dw;
-	ring->priority = DRM_SCHED_PRIORITY_NORMAL;
-	mutex_init(&ring->priority_mutex);
+	ring->hw_prio = hw_prio;
 
 	if (!ring->no_scheduler) {
 		hw_ip = ring->funcs->type;
@@ -268,9 +267,6 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 			&ring->sched;
 	}
 
-	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; ++i)
-		atomic_set(&ring->num_jobs[i], 0);
-
 	return 0;
 }