Merge tag 'amd-drm-fixes-5.17-2022-01-19' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-fixes-5.17-2022-01-19:

amdgpu:
- SR-IOV fix
- VCN harvest fix
- Suspend/resume fixes
- Tahiti fix
- Enable GPU recovery on yellow carp

radeon:
- Fix error handling regression in radeon_driver_open_kms

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220120013547.5649-1-alexander.deucher@amd.com

15 files changed, 75 insertions, 139 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index cf7fad88c138..ed077de426d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2354,7 +2354,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_exchange_data(adev);
+		amdgpu_virt_init_data_exchange(adev);
 
 	r = amdgpu_ib_pool_init(adev);
 	if (r) {
@@ -4450,33 +4450,24 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 
 	if (amdgpu_gpu_recovery == -1) {
 		switch (adev->asic_type) {
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_TOPAZ:
-		case CHIP_TONGA:
-		case CHIP_FIJI:
-		case CHIP_POLARIS10:
-		case CHIP_POLARIS11:
-		case CHIP_POLARIS12:
-		case CHIP_VEGAM:
-		case CHIP_VEGA20:
-		case CHIP_VEGA10:
-		case CHIP_VEGA12:
-		case CHIP_RAVEN:
-		case CHIP_ARCTURUS:
-		case CHIP_RENOIR:
-		case CHIP_NAVI10:
-		case CHIP_NAVI14:
-		case CHIP_NAVI12:
-		case CHIP_SIENNA_CICHLID:
-		case CHIP_NAVY_FLOUNDER:
-		case CHIP_DIMGREY_CAVEFISH:
-		case CHIP_BEIGE_GOBY:
-		case CHIP_VANGOGH:
-		case CHIP_ALDEBARAN:
-			break;
-		default:
+#ifdef CONFIG_DRM_AMDGPU_SI
+		case CHIP_VERDE:
+		case CHIP_TAHITI:
+		case CHIP_PITCAIRN:
+		case CHIP_OLAND:
+		case CHIP_HAINAN:
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+		case CHIP_KAVERI:
+		case CHIP_KABINI:
+		case CHIP_MULLINS:
+#endif
+		case CHIP_CARRIZO:
+		case CHIP_STONEY:
+		case CHIP_CYAN_SKILLFISH:
 			goto disabled;
+		default:
+			break;
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index be45650250fa..81bfee978b74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -243,6 +243,30 @@ static inline bool amdgpu_discovery_verify_binary_signature(uint8_t *binary)
 	return (le32_to_cpu(bhdr->binary_signature) == BINARY_SIGNATURE);
 }
 
+static void amdgpu_discovery_harvest_config_quirk(struct amdgpu_device *adev)
+{
+	/*
+	 * So far, apply this quirk only on those Navy Flounder boards which
+	 * have a bad harvest table of VCN config.
+	 */
+	if ((adev->ip_versions[UVD_HWIP][1] == IP_VERSION(3, 0, 1)) &&
+		(adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 2))) {
+		switch (adev->pdev->revision) {
+		case 0xC1:
+		case 0xC2:
+		case 0xC3:
+		case 0xC5:
+		case 0xC7:
+		case 0xCF:
+		case 0xDF:
+			adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN1;
+			break;
+		default:
+			break;
+		}
+	}
+}
+
 static int amdgpu_discovery_init(struct amdgpu_device *adev)
 {
 	struct table_info *info;
@@ -548,11 +572,9 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 			break;
 		}
 	}
-	/* some IP discovery tables on Navy Flounder don't have this set correctly */
-	if ((adev->ip_versions[UVD_HWIP][1] == IP_VERSION(3, 0, 1)) &&
-	    (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 2)) &&
-	    (adev->pdev->revision != 0xFF))
-		adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN1;
+
+	amdgpu_discovery_harvest_config_quirk(adev);
+
 	if (vcn_harvest_count == adev->vcn.num_vcn_inst) {
 		adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK;
 		adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 366e475056bd..2a4bb032a7e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1907,11 +1907,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 			return -ENODEV;
 	}
 
-	if (flags == 0) {
-		DRM_INFO("Unsupported asic.  Remove me when IP discovery init is in place.\n");
-		return -ENODEV;
-	}
-
 	if (amdgpu_virtual_display ||
 	    amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK))
 		supports_atomic = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 894444ab0032..07bc0f504713 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -625,20 +625,20 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 	adev->virt.fw_reserve.p_vf2pf = NULL;
 	adev->virt.vf2pf_update_interval_ms = 0;
 
-	if (adev->bios != NULL) {
-		adev->virt.vf2pf_update_interval_ms = 2000;
+	if (adev->mman.fw_vram_usage_va != NULL) {
+		/* go through this logic in ip_init and reset to init workqueue*/
+		amdgpu_virt_exchange_data(adev);
 
+		INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
+		schedule_delayed_work(&(adev->virt.vf2pf_work), msecs_to_jiffies(adev->virt.vf2pf_update_interval_ms));
+	} else if (adev->bios != NULL) {
+		/* got through this logic in early init stage to get necessary flags, e.g. rlcg_acc related*/
 		adev->virt.fw_reserve.p_pf2vf =
 			(struct amd_sriov_msg_pf2vf_info_header *)
 			(adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
 
 		amdgpu_virt_read_pf2vf_data(adev);
 	}
-
-	if (adev->virt.vf2pf_update_interval_ms != 0) {
-		INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
-		schedule_delayed_work(&(adev->virt.vf2pf_work), msecs_to_jiffies(adev->virt.vf2pf_update_interval_ms));
-	}
 }
 
 
@@ -674,12 +674,6 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 				if (adev->virt.ras_init_done)
 					amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size);
 			}
-	} else if (adev->bios != NULL) {
-		adev->virt.fw_reserve.p_pf2vf =
-			(struct amd_sriov_msg_pf2vf_info_header *)
-			(adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
-
-		amdgpu_virt_read_pf2vf_data(adev);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 54f28c075f21..f10ce740a29c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1428,6 +1428,10 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 {
 	int r;
 
+	/* APUs don't have full asic reset */
+	if (adev->flags & AMD_IS_APU)
+		return 0;
+
 	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		dev_info(adev->dev, "BACO reset\n");
 		r = amdgpu_dpm_baco_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index fe9a7cc8d9eb..6645ebbd2696 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -956,6 +956,10 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 {
 	int r;
 
+	/* APUs don't have full asic reset */
+	if (adev->flags & AMD_IS_APU)
+		return 0;
+
 	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		dev_info(adev->dev, "BACO reset\n");
 		r = amdgpu_dpm_baco_reset(adev);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 9f35f2e8f971..cac80ba69072 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -38,7 +38,6 @@
 #include "clk/clk_11_0_0_offset.h"
 #include "clk/clk_11_0_0_sh_mask.h"
 
-#include "irq/dcn20/irq_service_dcn20.h"
 
 #undef FN
 #define FN(reg_name, field_name) \
@@ -223,8 +222,6 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 	bool force_reset = false;
 	bool p_state_change_support;
 	int total_plane_count;
-	int irq_src;
-	uint32_t hpd_state;
 
 	if (dc->work_arounds.skip_clock_update)
 		return;
@@ -242,13 +239,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->res_pool->pp_smu)
 		pp_smu = &dc->res_pool->pp_smu->nv_funcs;
 
-	for (irq_src = DC_IRQ_SOURCE_HPD1; irq_src <= DC_IRQ_SOURCE_HPD6; irq_src++) {
-		hpd_state = dc_get_hpd_state_dcn20(dc->res_pool->irqs, irq_src);
-		if (hpd_state)
-			break;
-	}
-
-	if (display_count == 0 && !hpd_state)
+	if (display_count == 0)
 		enter_display_off = true;
 
 	if (enter_display_off == safe_to_lower) {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index fbda42313bfe..f4dee0e48a67 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -42,7 +42,6 @@
 #include "clk/clk_10_0_2_sh_mask.h"
 #include "renoir_ip_offset.h"
 
-#include "irq/dcn21/irq_service_dcn21.h"
 
 /* Constants */
 
@@ -129,11 +128,9 @@ static void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 	struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk;
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int display_count;
-	int irq_src;
 	bool update_dppclk = false;
 	bool update_dispclk = false;
 	bool dpp_clock_lowered = false;
-	uint32_t hpd_state;
 
 	struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
 
@@ -150,14 +147,8 @@ static void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 
 			display_count = rn_get_active_display_cnt_wa(dc, context);
 
-			for (irq_src = DC_IRQ_SOURCE_HPD1; irq_src <= DC_IRQ_SOURCE_HPD5; irq_src++) {
-				hpd_state = dc_get_hpd_state_dcn21(dc->res_pool->irqs, irq_src);
-				if (hpd_state)
-					break;
-			}
-
 			/* if we can go lower, go lower */
-			if (display_count == 0 && !hpd_state) {
+			if (display_count == 0) {
 				rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER);
 				/* update power state */
 				clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER;
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
index 9ccafe007b23..c4b067d01895 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
@@ -132,31 +132,6 @@ enum dc_irq_source to_dal_irq_source_dcn20(
 	}
 }
 
-uint32_t dc_get_hpd_state_dcn20(struct irq_service *irq_service, enum dc_irq_source source)
-{
-	const struct irq_source_info *info;
-	uint32_t addr;
-	uint32_t value;
-	uint32_t current_status;
-
-	info = find_irq_source_info(irq_service, source);
-	if (!info)
-		return 0;
-
-	addr = info->status_reg;
-	if (!addr)
-		return 0;
-
-	value = dm_read_reg(irq_service->ctx, addr);
-	current_status =
-		get_reg_field_value(
-			value,
-			HPD0_DC_HPD_INT_STATUS,
-			DC_HPD_SENSE);
-
-	return current_status;
-}
-
 static bool hpd_ack(
 	struct irq_service *irq_service,
 	const struct irq_source_info *info)
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h
index 4d69ab24ca25..aee4b37999f1 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.h
@@ -31,6 +31,4 @@
 struct irq_service *dal_irq_service_dcn20_create(
 	struct irq_service_init_data *init_data);
 
-uint32_t dc_get_hpd_state_dcn20(struct irq_service *irq_service, enum dc_irq_source source);
-
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
index 235294534c43..0f15bcada4e9 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
@@ -134,31 +134,6 @@ static enum dc_irq_source to_dal_irq_source_dcn21(struct irq_service *irq_servic
 	return DC_IRQ_SOURCE_INVALID;
 }
 
-uint32_t dc_get_hpd_state_dcn21(struct irq_service *irq_service, enum dc_irq_source source)
-{
-	const struct irq_source_info *info;
-	uint32_t addr;
-	uint32_t value;
-	uint32_t current_status;
-
-	info = find_irq_source_info(irq_service, source);
-	if (!info)
-		return 0;
-
-	addr = info->status_reg;
-	if (!addr)
-		return 0;
-
-	value = dm_read_reg(irq_service->ctx, addr);
-	current_status =
-		get_reg_field_value(
-			value,
-			HPD0_DC_HPD_INT_STATUS,
-			DC_HPD_SENSE);
-
-	return current_status;
-}
-
 static bool hpd_ack(
 	struct irq_service *irq_service,
 	const struct irq_source_info *info)
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
index 616470e32380..da2bd0e93d7a 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
@@ -31,6 +31,4 @@
 struct irq_service *dal_irq_service_dcn21_create(
 	struct irq_service_init_data *init_data);
 
-uint32_t dc_get_hpd_state_dcn21(struct irq_service *irq_service, enum dc_irq_source source);
-
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index 4db1133e4466..a2a4fbeb83f8 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -79,7 +79,7 @@ void dal_irq_service_destroy(struct irq_service **irq_service)
 	*irq_service = NULL;
 }
 
-const struct irq_source_info *find_irq_source_info(
+static const struct irq_source_info *find_irq_source_info(
 	struct irq_service *irq_service,
 	enum dc_irq_source source)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.h b/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
index e60b82480093..dbfcb096eedd 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
@@ -69,10 +69,6 @@ struct irq_service {
 	const struct irq_service_funcs *funcs;
 };
 
-const struct irq_source_info *find_irq_source_info(
-	struct irq_service *irq_service,
-	enum dc_irq_source source);
-
 void dal_irq_service_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data);
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index e2488559cc9f..11ad210919c8 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -666,18 +666,18 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 		fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL);
 		if (unlikely(!fpriv)) {
 			r = -ENOMEM;
-			goto out_suspend;
+			goto err_suspend;
 		}
 
 		if (rdev->accel_working) {
 			vm = &fpriv->vm;
 			r = radeon_vm_init(rdev, vm);
 			if (r)
-				goto out_fpriv;
+				goto err_fpriv;
 
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (r)
-				goto out_vm_fini;
+				goto err_vm_fini;
 
 			/* map the ib pool buffer read only into
 			 * virtual address space */
@@ -685,7 +685,7 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 							rdev->ring_tmp_bo.bo);
 			if (!vm->ib_bo_va) {
 				r = -ENOMEM;
-				goto out_vm_fini;
+				goto err_vm_fini;
 			}
 
 			r = radeon_vm_bo_set_addr(rdev, vm->ib_bo_va,
@@ -693,19 +693,21 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 						  RADEON_VM_PAGE_READABLE |
 						  RADEON_VM_PAGE_SNOOPED);
 			if (r)
-				goto out_vm_fini;
+				goto err_vm_fini;
 		}
 		file_priv->driver_priv = fpriv;
 	}
 
-	if (!r)
-		goto out_suspend;
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+	return 0;
 
-out_vm_fini:
+err_vm_fini:
 	radeon_vm_fini(rdev, vm);
-out_fpriv:
+err_fpriv:
 	kfree(fpriv);
-out_suspend:
+
+err_suspend:
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
 	return r;