[pull] master from torvalds:master

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

@@ -3166,6 +3166,12 @@ static void amdgpu_device_detect_sriov_bios(struct amdgpu_device *adev)
 bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 {
 	switch (asic_type) {
+#ifdef CONFIG_DRM_AMDGPU_SI
+	case CHIP_HAINAN:
+#endif
+	case CHIP_TOPAZ:
+		/* chips with no display hardware */
+		return false;
 #if defined(CONFIG_DRM_AMD_DC)
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
@@ -4461,7 +4467,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 				 struct amdgpu_reset_context *reset_context)
 {
-	int i, j, r = 0;
+	int i, r = 0;
 	struct amdgpu_job *job = NULL;
 	bool need_full_reset =
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
@@ -4483,15 +4489,8 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 
 		/*clear job fence from fence drv to avoid force_completion
 		 *leave NULL and vm flush fence in fence drv */
-		for (j = 0; j <= ring->fence_drv.num_fences_mask; j++) {
-			struct dma_fence *old, **ptr;
+		amdgpu_fence_driver_clear_job_fences(ring);
 
-			ptr = &ring->fence_drv.fences[j];
-			old = rcu_dereference_protected(*ptr, 1);
-			if (old && test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &old->flags)) {
-				RCU_INIT_POINTER(*ptr, NULL);
-			}
-		}
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
 	}

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

@@ -526,39 +526,71 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 	}
 }
 
+union gc_info {
+	struct gc_info_v1_0 v1;
+	struct gc_info_v2_0 v2;
+};
+
 int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
 {
 	struct binary_header *bhdr;
-	struct gc_info_v1_0 *gc_info;
+	union gc_info *gc_info;
 
 	if (!adev->mman.discovery_bin) {
 		DRM_ERROR("ip discovery uninitialized\n");
 		return -EINVAL;
 	}
 
 	bhdr = (struct binary_header *)adev->mman.discovery_bin;
-	gc_info = (struct gc_info_v1_0 *)(adev->mman.discovery_bin +
+	gc_info = (union gc_info *)(adev->mman.discovery_bin +
 			le16_to_cpu(bhdr->table_list[GC].offset));
-
-	adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se);
-	adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->gc_num_wgp0_per_sa) +
-					      le32_to_cpu(gc_info->gc_num_wgp1_per_sa));
-	adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->gc_num_sa_per_se);
-	adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->gc_num_rb_per_se);
-	adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->gc_num_gl2c);
-	adev->gfx.config.max_gprs = le32_to_cpu(gc_info->gc_num_gprs);
-	adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->gc_num_max_gs_thds);
-	adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->gc_gs_table_depth);
-	adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->gc_gsprim_buff_depth);
-	adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->gc_double_offchip_lds_buffer);
-	adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->gc_wave_size);
-	adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->gc_max_waves_per_simd);
-	adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->gc_max_scratch_slots_per_cu);
-	adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->gc_lds_size);
-	adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->gc_num_sc_per_se) /
-					 le32_to_cpu(gc_info->gc_num_sa_per_se);
-	adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->gc_num_packer_per_sc);
-
+	switch (gc_info->v1.header.version_major) {
+	case 1:
+		adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v1.gc_num_se);
+		adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->v1.gc_num_wgp0_per_sa) +
+						      le32_to_cpu(gc_info->v1.gc_num_wgp1_per_sa));
+		adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+		adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v1.gc_num_rb_per_se);
+		adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v1.gc_num_gl2c);
+		adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v1.gc_num_gprs);
+		adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v1.gc_num_max_gs_thds);
+		adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v1.gc_gs_table_depth);
+		adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v1.gc_gsprim_buff_depth);
+		adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v1.gc_double_offchip_lds_buffer);
+		adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v1.gc_wave_size);
+		adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v1.gc_max_waves_per_simd);
+		adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v1.gc_max_scratch_slots_per_cu);
+		adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v1.gc_lds_size);
+		adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v1.gc_num_sc_per_se) /
+			le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+		adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v1.gc_num_packer_per_sc);
+		break;
+	case 2:
+		adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v2.gc_num_se);
+		adev->gfx.config.max_cu_per_sh = le32_to_cpu(gc_info->v2.gc_num_cu_per_sh);
+		adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+		adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v2.gc_num_rb_per_se);
+		adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v2.gc_num_tccs);
+		adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v2.gc_num_gprs);
+		adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v2.gc_num_max_gs_thds);
+		adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v2.gc_gs_table_depth);
+		adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v2.gc_gsprim_buff_depth);
+		adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v2.gc_double_offchip_lds_buffer);
+		adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v2.gc_wave_size);
+		adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v2.gc_max_waves_per_simd);
+		adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v2.gc_max_scratch_slots_per_cu);
+		adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v2.gc_lds_size);
+		adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) /
+			le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+		adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc);
+		break;
+	default:
+		dev_err(adev->dev,
+			"Unhandled GC info table %d.%d\n",
+			gc_info->v1.header.version_major,
+			gc_info->v1.header.version_minor);
+		return -EINVAL;
+	}
 	return 0;
 }
 

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

@@ -384,7 +384,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach)
 	struct amdgpu_vm_bo_base *bo_base;
 	int r;
 
-	if (bo->tbo.resource->mem_type == TTM_PL_SYSTEM)
+	if (!bo->tbo.resource || bo->tbo.resource->mem_type == TTM_PL_SYSTEM)
 		return;
 
 	r = ttm_bo_validate(&bo->tbo, &placement, &ctx);

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

@@ -328,10 +328,11 @@ module_param_named(aspm, amdgpu_aspm, int, 0444);
 
 /**
  * DOC: runpm (int)
- * Override for runtime power management control for dGPUs in PX/HG laptops. The amdgpu driver can dynamically power down
- * the dGPU on PX/HG laptops when it is idle. The default is -1 (auto enable). Setting the value to 0 disables this functionality.
+ * Override for runtime power management control for dGPUs. The amdgpu driver can dynamically power down
+ * the dGPUs when they are idle if supported. The default is -1 (auto enable).
+ * Setting the value to 0 disables this functionality.
  */
-MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = PX only default)");
+MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = auto)");
 module_param_named(runpm, amdgpu_runtime_pm, int, 0444);
 
 /**
@@ -2153,7 +2154,10 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	adev->in_s3 = true;
 	r = amdgpu_device_suspend(drm_dev, true);
 	adev->in_s3 = false;
-
+	if (r)
+		return r;
+	if (!adev->in_s0ix)
+		r = amdgpu_asic_reset(adev);
 	return r;
 }
 
@@ -2234,12 +2238,27 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 	if (amdgpu_device_supports_px(drm_dev))
 		drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
+	/*
+	 * By setting mp1_state as PP_MP1_STATE_UNLOAD, MP1 will do some
+	 * proper cleanups and put itself into a state ready for PNP. That
+	 * can address some random resuming failure observed on BOCO capable
+	 * platforms.
+	 * TODO: this may be also needed for PX capable platform.
+	 */
+	if (amdgpu_device_supports_boco(drm_dev))
+		adev->mp1_state = PP_MP1_STATE_UNLOAD;
+
 	ret = amdgpu_device_suspend(drm_dev, false);
 	if (ret) {
 		adev->in_runpm = false;
+		if (amdgpu_device_supports_boco(drm_dev))
+			adev->mp1_state = PP_MP1_STATE_NONE;
 		return ret;
 	}
 
+	if (amdgpu_device_supports_boco(drm_dev))
+		adev->mp1_state = PP_MP1_STATE_NONE;
+
 	if (amdgpu_device_supports_px(drm_dev)) {
 		/* Only need to handle PCI state in the driver for ATPX
 		 * PCI core handles it for _PR3.

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

@@ -77,11 +77,13 @@ void amdgpu_fence_slab_fini(void)
  * Cast helper
  */
 static const struct dma_fence_ops amdgpu_fence_ops;
+static const struct dma_fence_ops amdgpu_job_fence_ops;
 static inline struct amdgpu_fence *to_amdgpu_fence(struct dma_fence *f)
 {
 	struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base);
 
-	if (__f->base.ops == &amdgpu_fence_ops)
+	if (__f->base.ops == &amdgpu_fence_ops ||
+	    __f->base.ops == &amdgpu_job_fence_ops)
 		return __f;
 
 	return NULL;
@@ -158,19 +160,18 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 	}
 
 	seq = ++ring->fence_drv.sync_seq;
-	if (job != NULL && job->job_run_counter) {
+	if (job && job->job_run_counter) {
 		/* reinit seq for resubmitted jobs */
 		fence->seqno = seq;
 	} else {
-		dma_fence_init(fence, &amdgpu_fence_ops,
-				&ring->fence_drv.lock,
-				adev->fence_context + ring->idx,
-				seq);
-	}
-
-	if (job != NULL) {
-		/* mark this fence has a parent job */
-		set_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &fence->flags);
+		if (job)
+			dma_fence_init(fence, &amdgpu_job_fence_ops,
+				       &ring->fence_drv.lock,
+				       adev->fence_context + ring->idx, seq);
+		else
+			dma_fence_init(fence, &amdgpu_fence_ops,
+				       &ring->fence_drv.lock,
+				       adev->fence_context + ring->idx, seq);
 	}
 
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
@@ -620,6 +621,25 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 	}
 }
 
+/**
+ * amdgpu_fence_driver_clear_job_fences - clear job embedded fences of ring
+ *
+ * @ring: fence of the ring to be cleared
+ *
+ */
+void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
+{
+	int i;
+	struct dma_fence *old, **ptr;
+
+	for (i = 0; i <= ring->fence_drv.num_fences_mask; i++) {
+		ptr = &ring->fence_drv.fences[i];
+		old = rcu_dereference_protected(*ptr, 1);
+		if (old && old->ops == &amdgpu_job_fence_ops)
+			RCU_INIT_POINTER(*ptr, NULL);
+	}
+}
+
 /**
  * amdgpu_fence_driver_force_completion - force signal latest fence of ring
  *
@@ -643,16 +663,14 @@ static const char *amdgpu_fence_get_driver_name(struct dma_fence *fence)
 
 static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
 {
-	struct amdgpu_ring *ring;
+	return (const char *)to_amdgpu_fence(f)->ring->name;
+}
 
-	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
-		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f)
+{
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
 
-		ring = to_amdgpu_ring(job->base.sched);
-	} else {
-		ring = to_amdgpu_fence(f)->ring;
-	}
-	return (const char *)ring->name;
+	return (const char *)to_amdgpu_ring(job->base.sched)->name;
 }
 
 /**
@@ -665,18 +683,25 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
  */
 static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
 {
-	struct amdgpu_ring *ring;
+	if (!timer_pending(&to_amdgpu_fence(f)->ring->fence_drv.fallback_timer))
+		amdgpu_fence_schedule_fallback(to_amdgpu_fence(f)->ring);
 
-	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
-		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+	return true;
+}
 
-		ring = to_amdgpu_ring(job->base.sched);
-	} else {
-		ring = to_amdgpu_fence(f)->ring;
-	}
+/**
+ * amdgpu_job_fence_enable_signaling - enable signalling on job fence
+ * @f: fence
+ *
+ * This is the simliar function with amdgpu_fence_enable_signaling above, it
+ * only handles the job embedded fence.
+ */
+static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f)
+{
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
 
-	if (!timer_pending(&ring->fence_drv.fallback_timer))
-		amdgpu_fence_schedule_fallback(ring);
+	if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer))
+		amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched));
 
 	return true;
 }
@@ -692,19 +717,23 @@ static void amdgpu_fence_free(struct rcu_head *rcu)
 {
 	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
 
-	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
-	/* free job if fence has a parent job */
-		struct amdgpu_job *job;
-
-		job = container_of(f, struct amdgpu_job, hw_fence);
-		kfree(job);
-	} else {
 	/* free fence_slab if it's separated fence*/
-		struct amdgpu_fence *fence;
+	kmem_cache_free(amdgpu_fence_slab, to_amdgpu_fence(f));
+}
 
-		fence = to_amdgpu_fence(f);
-		kmem_cache_free(amdgpu_fence_slab, fence);
-	}
+/**
+ * amdgpu_job_fence_free - free up the job with embedded fence
+ *
+ * @rcu: RCU callback head
+ *
+ * Free up the job with embedded fence after the RCU grace period.
+ */
+static void amdgpu_job_fence_free(struct rcu_head *rcu)
+{
+	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
+
+	/* free job if fence has a parent job */
+	kfree(container_of(f, struct amdgpu_job, hw_fence));
 }
 
 /**
@@ -720,13 +749,32 @@ static void amdgpu_fence_release(struct dma_fence *f)
 	call_rcu(&f->rcu, amdgpu_fence_free);
 }
 
+/**
+ * amdgpu_job_fence_release - callback that job embedded fence can be freed
+ *
+ * @f: fence
+ *
+ * This is the simliar function with amdgpu_fence_release above, it
+ * only handles the job embedded fence.
+ */
+static void amdgpu_job_fence_release(struct dma_fence *f)
+{
+	call_rcu(&f->rcu, amdgpu_job_fence_free);
+}
+
 static const struct dma_fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
 	.enable_signaling = amdgpu_fence_enable_signaling,
 	.release = amdgpu_fence_release,
 };
 
+static const struct dma_fence_ops amdgpu_job_fence_ops = {
+	.get_driver_name = amdgpu_fence_get_driver_name,
+	.get_timeline_name = amdgpu_job_fence_get_timeline_name,
+	.enable_signaling = amdgpu_job_fence_enable_signaling,
+	.release = amdgpu_job_fence_release,
+};
 
 /*
  * Fence debugfs