Merge tag 'amd-drm-next-6.8-2023-12-01' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.8-2023-12-01:

amdgpu:
- Add new 64 bit sequence number infrastructure.
  This will ultimately be used for user queue synchronization.
- GPUVM updates
- Misc code cleanups
- RAS updates
- DCN 3.5 updates
- Rework PCIe link speed handling
- Document GPU reset types
- DMUB fixes
- eDP fixes
- NBIO 7.9 updates
- NBIO 7.11 updates
- SubVP updates
- DCN 3.1.4 fixes
- ABM fixes
- AGP aperture fix
- DCN 3.1.5 fix
- Fix some potential error path memory leaks
- Enable PCIe PMEs
- Add XGMI, PCIe state dumping for aqua vanjaram
- GFX11 golden register updates
- Misc display fixes

amdkfd:
- Migrate TLB flushing logic to amdgpu
- Trap handler fixes
- Fix restore workers handling on suspend and reset
- Fix possible memory leak in pqm_uninit()

radeon:
- Fix some possible overflows in command buffer checking
- Check for errors in ring_lock

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231201181743.5313-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 114 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2a6684a38714..6c0cf64d465a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -162,6 +162,65 @@ static ssize_t amdgpu_device_get_pcie_replay_count(struct device *dev,
 static DEVICE_ATTR(pcie_replay_count, 0444,
 		amdgpu_device_get_pcie_replay_count, NULL);
 
+static ssize_t amdgpu_sysfs_reg_state_get(struct file *f, struct kobject *kobj,
+					  struct bin_attribute *attr, char *buf,
+					  loff_t ppos, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	ssize_t bytes_read;
+
+	switch (ppos) {
+	case AMDGPU_SYS_REG_STATE_XGMI:
+		bytes_read = amdgpu_asic_get_reg_state(
+			adev, AMDGPU_REG_STATE_TYPE_XGMI, buf, count);
+		break;
+	case AMDGPU_SYS_REG_STATE_WAFL:
+		bytes_read = amdgpu_asic_get_reg_state(
+			adev, AMDGPU_REG_STATE_TYPE_WAFL, buf, count);
+		break;
+	case AMDGPU_SYS_REG_STATE_PCIE:
+		bytes_read = amdgpu_asic_get_reg_state(
+			adev, AMDGPU_REG_STATE_TYPE_PCIE, buf, count);
+		break;
+	case AMDGPU_SYS_REG_STATE_USR:
+		bytes_read = amdgpu_asic_get_reg_state(
+			adev, AMDGPU_REG_STATE_TYPE_USR, buf, count);
+		break;
+	case AMDGPU_SYS_REG_STATE_USR_1:
+		bytes_read = amdgpu_asic_get_reg_state(
+			adev, AMDGPU_REG_STATE_TYPE_USR_1, buf, count);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return bytes_read;
+}
+
+BIN_ATTR(reg_state, 0444, amdgpu_sysfs_reg_state_get, NULL,
+	 AMDGPU_SYS_REG_STATE_END);
+
+int amdgpu_reg_state_sysfs_init(struct amdgpu_device *adev)
+{
+	int ret;
+
+	if (!amdgpu_asic_get_reg_state_supported(adev))
+		return 0;
+
+	ret = sysfs_create_bin_file(&adev->dev->kobj, &bin_attr_reg_state);
+
+	return ret;
+}
+
+void amdgpu_reg_state_sysfs_fini(struct amdgpu_device *adev)
+{
+	if (!amdgpu_asic_get_reg_state_supported(adev))
+		return;
+	sysfs_remove_bin_file(&adev->dev->kobj, &bin_attr_reg_state);
+}
+
 /**
  * DOC: board_info
  *
@@ -1551,11 +1610,15 @@ bool amdgpu_device_seamless_boot_supported(struct amdgpu_device *adev)
  * https://edc.intel.com/content/www/us/en/design/products/platforms/details/raptor-lake-s/13th-generation-core-processors-datasheet-volume-1-of-2/005/pci-express-support/
  * https://gitlab.freedesktop.org/drm/amd/-/issues/2663
  */
-static bool amdgpu_device_pcie_dynamic_switching_supported(void)
+static bool amdgpu_device_pcie_dynamic_switching_supported(struct amdgpu_device *adev)
 {
 #if IS_ENABLED(CONFIG_X86)
 	struct cpuinfo_x86 *c = &cpu_data(0);
 
+	/* eGPU change speeds based on USB4 fabric conditions */
+	if (dev_is_removable(adev->dev))
+		return true;
+
 	if (c->x86_vendor == X86_VENDOR_INTEL)
 		return false;
 #endif
@@ -2395,7 +2458,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 	if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)
 		adev->pm.pp_feature &= ~PP_OVERDRIVE_MASK;
-	if (!amdgpu_device_pcie_dynamic_switching_supported())
+	if (!amdgpu_device_pcie_dynamic_switching_supported(adev))
 		adev->pm.pp_feature &= ~PP_PCIE_DPM_MASK;
 
 	total = true;
@@ -2676,6 +2739,12 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 					goto init_failed;
 				}
 			}
+
+			r = amdgpu_seq64_init(adev);
+			if (r) {
+				DRM_ERROR("allocate seq64 failed %d\n", r);
+				goto init_failed;
+			}
 		}
 	}
 
@@ -3138,6 +3207,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 			amdgpu_device_wb_fini(adev);
 			amdgpu_device_mem_scratch_fini(adev);
 			amdgpu_ib_pool_fini(adev);
+			amdgpu_seq64_fini(adev);
 		}
 
 		r = adev->ip_blocks[i].version->funcs->sw_fini((void *)adev);
@@ -4222,6 +4292,7 @@ fence_driver_init:
 			"Could not create amdgpu board attributes\n");
 
 	amdgpu_fru_sysfs_init(adev);
+	amdgpu_reg_state_sysfs_init(adev);
 
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		r = amdgpu_pmu_init(adev);
@@ -4344,6 +4415,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
 	amdgpu_fru_sysfs_fini(adev);
 
+	amdgpu_reg_state_sysfs_fini(adev);
+
 	/* disable ras feature must before hw fini */
 	amdgpu_ras_pre_fini(adev);
 
@@ -4538,6 +4611,10 @@ 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;
 }
 
@@ -5731,6 +5808,39 @@ recover_end:
 }
 
 /**
+ * amdgpu_device_partner_bandwidth - find the bandwidth of appropriate partner
+ *
+ * @adev: amdgpu_device pointer
+ * @speed: pointer to the speed of the link
+ * @width: pointer to the width of the link
+ *
+ * Evaluate the hierarchy to find the speed and bandwidth capabilities of the
+ * first physical partner to an AMD dGPU.
+ * This will exclude any virtual switches and links.
+ */
+static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev,
+					    enum pci_bus_speed *speed,
+					    enum pcie_link_width *width)
+{
+	struct pci_dev *parent = adev->pdev;
+
+	if (!speed || !width)
+		return;
+
+	*speed = PCI_SPEED_UNKNOWN;
+	*width = PCIE_LNK_WIDTH_UNKNOWN;
+
+	while ((parent = pci_upstream_bridge(parent))) {
+		/* skip upstream/downstream switches internal to dGPU*/
+		if (parent->vendor == PCI_VENDOR_ID_ATI)
+			continue;
+		*speed = pcie_get_speed_cap(parent);
+		*width = pcie_get_width_cap(parent);
+		break;
+	}
+}
+
+/**
  * amdgpu_device_get_pcie_info - fence pcie info about the PCIE slot
  *
  * @adev: amdgpu_device pointer
@@ -5763,8 +5873,8 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 	if (adev->pm.pcie_gen_mask && adev->pm.pcie_mlw_mask)
 		return;
 
-	pcie_bandwidth_available(adev->pdev, NULL,
-				 &platform_speed_cap, &platform_link_width);
+	amdgpu_device_partner_bandwidth(adev, &platform_speed_cap,
+					&platform_link_width);
 
 	if (adev->pm.pcie_gen_mask == 0) {
 		/* asic caps */