1 files changed, 58 insertions, 30 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3987ecb24ef4..625424f3082b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -913,7 +913,10 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev)
 {
 	amdgpu_asic_pre_asic_init(adev);
 
-	return amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0))
+		return amdgpu_atomfirmware_asic_init(adev, true);
+	else
+		return amdgpu_atom_asic_init(adev->mode_info.atom_context);
 }
 
 /**
@@ -1041,19 +1044,25 @@ static int amdgpu_device_doorbell_init(struct amdgpu_device *adev)
 	adev->doorbell.base = pci_resource_start(adev->pdev, 2);
 	adev->doorbell.size = pci_resource_len(adev->pdev, 2);
 
-	adev->doorbell.num_doorbells = min_t(u32, adev->doorbell.size / sizeof(u32),
-					     adev->doorbell_index.max_assignment+1);
-	if (adev->doorbell.num_doorbells == 0)
-		return -EINVAL;
-
-	/* For Vega, reserve and map two pages on doorbell BAR since SDMA
-	 * paging queue doorbell use the second page. The
-	 * AMDGPU_DOORBELL64_MAX_ASSIGNMENT definition assumes all the
-	 * doorbells are in the first page. So with paging queue enabled,
-	 * the max num_doorbells should + 1 page (0x400 in dword)
-	 */
-	if (adev->asic_type >= CHIP_VEGA10)
-		adev->doorbell.num_doorbells += 0x400;
+	if (adev->enable_mes) {
+		adev->doorbell.num_doorbells =
+			adev->doorbell.size / sizeof(u32);
+	} else {
+		adev->doorbell.num_doorbells =
+			min_t(u32, adev->doorbell.size / sizeof(u32),
+			      adev->doorbell_index.max_assignment+1);
+		if (adev->doorbell.num_doorbells == 0)
+			return -EINVAL;
+
+		/* For Vega, reserve and map two pages on doorbell BAR since SDMA
+		 * paging queue doorbell use the second page. The
+		 * AMDGPU_DOORBELL64_MAX_ASSIGNMENT definition assumes all the
+		 * doorbells are in the first page. So with paging queue enabled,
+		 * the max num_doorbells should + 1 page (0x400 in dword)
+		 */
+		if (adev->asic_type >= CHIP_VEGA10)
+			adev->doorbell.num_doorbells += 0x400;
+	}
 
 	adev->doorbell.ptr = ioremap(adev->doorbell.base,
 				     adev->doorbell.num_doorbells *
@@ -1547,9 +1556,6 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
-	amdgpu_gmc_tmz_set(adev);
-
-
 	return 0;
 }
 
@@ -1703,7 +1709,7 @@ int amdgpu_device_ip_set_powergating_state(void *dev,
  * clockgating is enabled.
  */
 void amdgpu_device_ip_get_clockgating_state(struct amdgpu_device *adev,
-					    u32 *flags)
+					    u64 *flags)
 {
 	int i;
 
@@ -1926,11 +1932,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 	adev->firmware.gpu_info_fw = NULL;
 
 	if (adev->mman.discovery_bin) {
-		amdgpu_discovery_get_gfx_info(adev);
-
 		/*
 		 * FIXME: The bounding box is still needed by Navi12, so
-		 * temporarily read it from gpu_info firmware. Should be droped
+		 * temporarily read it from gpu_info firmware. Should be dropped
 		 * when DAL no longer needs it.
 		 */
 		if (adev->asic_type != CHIP_NAVI12)
@@ -3663,8 +3667,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (amdgpu_mcbp)
 		DRM_INFO("MCBP is enabled\n");
 
-	if (amdgpu_mes && adev->asic_type >= CHIP_NAVI10)
-		adev->enable_mes = true;
+	if (adev->asic_type >= CHIP_NAVI10) {
+		if (amdgpu_mes || amdgpu_mes_kiq)
+			adev->enable_mes = true;
+
+		if (amdgpu_mes_kiq)
+			adev->enable_mes_kiq = true;
+	}
 
 	/*
 	 * Reset domain needs to be present early, before XGMI hive discovered
@@ -3689,6 +3698,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	/* Enable TMZ based on IP_VERSION */
+	amdgpu_gmc_tmz_set(adev);
+
 	amdgpu_gmc_noretry_set(adev);
 	/* Need to get xgmi info early to decide the reset behavior*/
 	if (adev->gmc.xgmi.supported) {
@@ -3700,7 +3712,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	/* enable PCIE atomic ops */
 	if (amdgpu_sriov_vf(adev))
 		adev->have_atomics_support = ((struct amd_sriov_msg_pf2vf_info *)
-			adev->virt.fw_reserve.p_pf2vf)->pcie_atomic_ops_enabled_flags ==
+			adev->virt.fw_reserve.p_pf2vf)->pcie_atomic_ops_support_flags ==
 			(PCI_EXP_DEVCAP2_ATOMIC_COMP32 | PCI_EXP_DEVCAP2_ATOMIC_COMP64);
 	else
 		adev->have_atomics_support =
@@ -3857,6 +3869,14 @@ fence_driver_init:
 	} else
 		adev->ucode_sysfs_en = true;
 
+	r = amdgpu_psp_sysfs_init(adev);
+	if (r) {
+		adev->psp_sysfs_en = false;
+		if (!amdgpu_sriov_vf(adev))
+			DRM_ERROR("Creating psp sysfs failed\n");
+	} else
+		adev->psp_sysfs_en = true;
+
 	/*
 	 * Register gpu instance before amdgpu_device_enable_mgpu_fan_boost.
 	 * Otherwise the mgpu fan boost feature will be skipped due to the
@@ -3960,10 +3980,6 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 {
 	dev_info(adev->dev, "amdgpu: finishing device.\n");
 	flush_delayed_work(&adev->delayed_init_work);
-	if (adev->mman.initialized) {
-		flush_delayed_work(&adev->mman.bdev.wq);
-		ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
-	}
 	adev->shutdown = true;
 
 	/* make sure IB test finished before entering exclusive mode
@@ -3984,10 +4000,17 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	}
 	amdgpu_fence_driver_hw_fini(adev);
 
+	if (adev->mman.initialized) {
+		flush_delayed_work(&adev->mman.bdev.wq);
+		ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
+	}
+
 	if (adev->pm_sysfs_en)
 		amdgpu_pm_sysfs_fini(adev);
 	if (adev->ucode_sysfs_en)
 		amdgpu_ucode_sysfs_fini(adev);
+	if (adev->psp_sysfs_en)
+		amdgpu_psp_sysfs_fini(adev);
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
 
 	/* disable ras feature must before hw fini */
@@ -4486,6 +4509,7 @@ retry:
 	if (!r) {
 		amdgpu_irq_gpu_reset_resume_helper(adev);
 		r = amdgpu_ib_ring_tests(adev);
+
 		amdgpu_amdkfd_post_reset(adev);
 	}
 
@@ -5195,6 +5219,10 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		r = amdgpu_device_reset_sriov(adev, job ? false : true);
 		if (r)
 			adev->asic_reset_res = r;
+
+		/* Aldebaran supports ras in SRIOV, so need resume ras during reset */
+		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
+			amdgpu_ras_resume(adev);
 	} else {
 		r = amdgpu_do_asic_reset(device_list_handle, &reset_context);
 		if (r && r == -EAGAIN)
@@ -5733,7 +5761,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev,
 		struct amdgpu_ring *ring)
 {
 #ifdef CONFIG_X86_64
-	if (adev->flags & AMD_IS_APU)
+	if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev))
 		return;
 #endif
 	if (adev->gmc.xgmi.connected_to_cpu)
@@ -5749,7 +5777,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
 		struct amdgpu_ring *ring)
 {
 #ifdef CONFIG_X86_64
-	if (adev->flags & AMD_IS_APU)
+	if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev))
 		return;
 #endif
 	if (adev->gmc.xgmi.connected_to_cpu)