Merge tag 'amd-drm-fixes-6.7-2023-11-30' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.7-2023-11-30:

amdgpu:
- DMUB fix
- DCN 3.5 fixes
- XGMI fix
- DCN 3.2 fixes
- Vangogh suspend fix
- NBIO 7.9 fix
- GFX11 golden register fix
- Backlight fix
- NBIO 7.11 fix
- IB test overflow fix
- DCN 3.1.4 fixes
- fix a runtime pm ref count
- Retimer fix
- ABM fix
- DCN 3.1.5 fix
- Fix AGP addressing
- Fix possible memory leak in SMU error path
- Make sure PME is enabled in D3
- Fix possible NULL pointer dereference in debugfs
- EEPROM fix
- GC 9.4.3 fix

amdkfd:
- IP version check fix
- Fix memory leak in pqm_uninit()

drm:
- Revert unexport of prime helpers for fd/handle conversion

Signed-off-by: Dave Airlie <[email protected]>

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

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

@@ -547,7 +547,7 @@ int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
 	struct amdgpu_device *adev = dst, *peer_adev;
 	int num_links;
 
-	if (adev->asic_type != CHIP_ALDEBARAN)
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2))
 		return 0;
 
 	if (src)

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

@@ -638,6 +638,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_rreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -694,6 +697,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_wreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);

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

@@ -4538,6 +4538,10 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
+	r = amdgpu_dpm_notify_rlc_state(adev, false);
+	if (r)
+		return r;
+
 	return 0;
 }
 

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

@@ -340,14 +340,11 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set,
 		adev->have_disp_power_ref = true;
 		return ret;
 	}
-	/* if we have no active crtcs, then drop the power ref
-	 * we got before
+	/* if we have no active crtcs, then go to
+	 * drop the power ref we got before
 	 */
-	if (!active && adev->have_disp_power_ref) {
-		pm_runtime_put_autosuspend(dev->dev);
+	if (!active && adev->have_disp_power_ref)
 		adev->have_disp_power_ref = false;
-	}
-
 out:
 	/* drop the power reference we got coming in here */
 	pm_runtime_put_autosuspend(dev->dev);

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

@@ -2263,6 +2263,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		pm_runtime_mark_last_busy(ddev->dev);
 		pm_runtime_put_autosuspend(ddev->dev);
 
+		pci_wake_from_d3(pdev, TRUE);
+
 		/*
 		 * For runpm implemented via BACO, PMFW will handle the
 		 * timing for BACO in and out:

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

@@ -181,6 +181,9 @@ uint64_t amdgpu_gmc_agp_addr(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 
+	if (!bo->ttm)
+		return AMDGPU_BO_INVALID_OFFSET;
+
 	if (bo->ttm->num_pages != 1 || bo->ttm->caching == ttm_cached)
 		return AMDGPU_BO_INVALID_OFFSET;
 

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

@@ -1527,10 +1527,14 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	uint64_t offset;
+	uint64_t offset = AMDGPU_BO_INVALID_OFFSET;
 
-	offset = (bo->tbo.resource->start << PAGE_SHIFT) +
-		 amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
+	if (bo->tbo.resource->mem_type == TTM_PL_TT)
+		offset = amdgpu_gmc_agp_addr(&bo->tbo);
+
+	if (offset == AMDGPU_BO_INVALID_OFFSET)
+		offset = (bo->tbo.resource->start << PAGE_SHIFT) +
+			amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
 
 	return amdgpu_gmc_sign_extend(offset);
 }

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

@@ -214,6 +214,12 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 			control->i2c_address = EEPROM_I2C_MADDR_0;
 		return true;
 	case IP_VERSION(13, 0, 0):
+		if (strnstr(atom_ctx->vbios_pn, "D707",
+			    sizeof(atom_ctx->vbios_pn)))
+			control->i2c_address = EEPROM_I2C_MADDR_0;
+		else
+			control->i2c_address = EEPROM_I2C_MADDR_4;
+		return true;
 	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
 		control->i2c_address = EEPROM_I2C_MADDR_4;

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

@@ -959,10 +959,8 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 		return 0;
 
 	addr = amdgpu_gmc_agp_addr(bo);
-	if (addr != AMDGPU_BO_INVALID_OFFSET) {
-		bo->resource->start = addr >> PAGE_SHIFT;
+	if (addr != AMDGPU_BO_INVALID_OFFSET)
 		return 0;
-	}
 
 	/* allocate GART space */
 	placement.num_placement = 1;

drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c

@@ -89,6 +89,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_5_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_rlc.bin");
 
+static const struct soc15_reg_golden golden_settings_gc_11_0[] = {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL, 0x20000000, 0x20000000)
+};
+
 static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regCGTT_GS_NGG_CLK_CTRL, 0x9fff8fff, 0x00000010),
@@ -304,6 +308,10 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 	default:
 		break;
 	}
+	soc15_program_register_sequence(adev,
+					golden_settings_gc_11_0,
+					(const u32)ARRAY_SIZE(golden_settings_gc_11_0));
+
 }
 
 static void gfx_v11_0_write_data_to_reg(struct amdgpu_ring *ring, int eng_sel,
@@ -419,7 +427,7 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 		cpu_ptr = &adev->wb.wb[index];
 
-		r = amdgpu_ib_get(adev, NULL, 16, AMDGPU_IB_POOL_DIRECT, &ib);
+		r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 		if (r) {
 			DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 			goto err1;