Merge tag 'amd-drm-fixes-6.2-2023-01-11' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.2-2023-01-11:

amdgpu:
- SMU13 fan speed fix
- SMU13 fix power cap handling
- SMU13 BACO fix
- Fix a possible segfault in bo validation error case
- Delay removal of firmware framebuffer
- Fix error when unloading

amdkfd:
- SVM fix when clearing vram
- GC11 fix for multi-GPU

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230112033004.8184-1-alexander.deucher@amd.com

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

@@ -2099,7 +2099,7 @@ int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_b
 	}
 
 	amdgpu_amdkfd_remove_eviction_fence(
-		bo, bo->kfd_bo->process_info->eviction_fence);
+		bo, bo->vm_bo->vm->process_info->eviction_fence);
 
 	amdgpu_bo_unreserve(bo);
 

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

@@ -36,6 +36,7 @@
 #include <generated/utsrelease.h>
 #include <linux/pci-p2pdma.h>
 
+#include <drm/drm_aperture.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_probe_helper.h>
@@ -90,6 +91,8 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
 #define AMDGPU_MAX_RETRY_LIMIT		2
 #define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL)
 
+static const struct drm_driver amdgpu_kms_driver;
+
 const char *amdgpu_asic_name[] = {
 	"TAHITI",
 	"PITCAIRN",
@@ -3687,6 +3690,11 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	/* Get rid of things like offb */
+	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
+	if (r)
+		return r;
+
 	/* Enable TMZ based on IP_VERSION */
 	amdgpu_gmc_tmz_set(adev);
 

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

@@ -23,7 +23,6 @@
  */
 
 #include <drm/amdgpu_drm.h>
-#include <drm/drm_aperture.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fbdev_generic.h>
 #include <drm/drm_gem.h>
@@ -2122,11 +2121,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	}
 #endif
 
-	/* Get rid of things like offb */
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
-	if (ret)
-		return ret;
-
 	adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev);
 	if (IS_ERR(adev))
 		return PTR_ERR(adev);

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

@@ -470,8 +470,9 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev,
 	return true;
 
 fail:
-	DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
-		  man->size);
+	if (man)
+		DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
+			  man->size);
 	return false;
 }
 

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

@@ -882,7 +882,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 		kfree(rsv);
 
 	list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
-		drm_buddy_free_list(&mgr->mm, &rsv->blocks);
+		drm_buddy_free_list(&mgr->mm, &rsv->allocated);
 		kfree(rsv);
 	}
 	drm_buddy_fini(&mgr->mm);

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -200,7 +200,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
 
 	if (q->wptr_bo) {
-		wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va;
+		wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1);
 		queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off;
 	}
 

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

@@ -570,6 +570,15 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange,
 		goto reserve_bo_failed;
 	}
 
+	if (clear) {
+		r = amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false);
+		if (r) {
+			pr_debug("failed %d to sync bo\n", r);
+			amdgpu_bo_unreserve(bo);
+			goto reserve_bo_failed;
+		}
+	}
+
 	r = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
 	if (r) {
 		pr_debug("failed %d to reserve bo\n", r);

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c

@@ -1261,7 +1261,8 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu,
 				uint32_t speed)
 {
 	struct amdgpu_device *adev = smu->adev;
-	uint32_t tach_period, crystal_clock_freq;
+	uint32_t crystal_clock_freq = 2500;
+	uint32_t tach_period;
 	int ret;
 
 	if (!speed)
@@ -1271,7 +1272,6 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu,
 	if (ret)
 		return ret;
 
-	crystal_clock_freq = amdgpu_asic_get_xclk(adev);
 	tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
 	WREG32_SOC15(THM, 0, regCG_TACH_CTRL,
 		     REG_SET_FIELD(RREG32_SOC15(THM, 0, regCG_TACH_CTRL),
@@ -2298,6 +2298,10 @@ bool smu_v13_0_baco_is_support(struct smu_context *smu)
 	    !smu_baco->platform_support)
 		return false;
 
+	/* return true if ASIC is in BACO state already */
+	if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER)
+		return true;
+
 	if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) &&
 	    !smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
 		return false;

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c

@@ -213,6 +213,7 @@ static struct cmn2asic_mapping smu_v13_0_0_feature_mask_map[SMU_FEATURE_COUNT] =
 	FEA_MAP(SOC_PCC),
 	[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
 	[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+	[SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
 };
 
 static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = {

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c

@@ -192,6 +192,7 @@ static struct cmn2asic_mapping smu_v13_0_7_feature_mask_map[SMU_FEATURE_COUNT] =
 	FEA_MAP(SOC_PCC),
 	[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
 	[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+	[SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
 };
 
 static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = {