From 5839d27d5b2dad160e402bfac16ab61b481c47f3 Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Mon, 19 Aug 2024 13:23:42 +0530 Subject: drm/amdgpu: Use init level for pending_reset flag Drop pending_reset flag in gmc block. Instead use init level to determine which type of init is preferred - in this case MINIMAL. Signed-off-by: Lijo Lazar Acked-by: Rajneesh Bhardwaj Tested-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index db0763ffeff7..69fa3c87dbe1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2512,7 +2512,6 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) for (i = 0; i < mgpu_info.num_dgpu; i++) { adev = mgpu_info.gpu_ins[i].adev; flush_work(&adev->xgmi_reset_work); - adev->gmc.xgmi.pending_reset = false; } /* reset function will rebuild the xgmi hive info , clear it now */ -- cgit v1.2.3 From 2accf9d6831054429a365d1c259859f048f289ce Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Mon, 2 Sep 2024 11:52:26 +0530 Subject: drm/amdgpu: Drop delayed reset work handler Drop delayed reset work handler as it is no longer used. Signed-off-by: Lijo Lazar Reviewed-by: Feifei Xu Reviewed-by: Alex Deucher Acked-by: Rajneesh Bhardwaj Tested-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 80 --------------------------------- 1 file changed, 80 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 69fa3c87dbe1..b997843354b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -231,8 +231,6 @@ int amdgpu_wbrf = -1; int amdgpu_damage_clips = -1; /* auto */ int amdgpu_umsch_mm_fwlog; -static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); - DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", "DRM_UT_DRIVER", @@ -247,9 +245,6 @@ DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), - .delayed_reset_work = __DELAYED_WORK_INITIALIZER( - mgpu_info.delayed_reset_work, - amdgpu_drv_delayed_reset_work_handler, 0), }; int amdgpu_ras_enable = -1; uint amdgpu_ras_mask = 0xffffffff; @@ -2472,81 +2467,6 @@ amdgpu_pci_shutdown(struct pci_dev *pdev) adev->mp1_state = PP_MP1_STATE_NONE; } -/** - * amdgpu_drv_delayed_reset_work_handler - work handler for reset - * - * @work: work_struct. - */ -static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) -{ - struct list_head device_list; - struct amdgpu_device *adev; - int i, r; - struct amdgpu_reset_context reset_context; - - memset(&reset_context, 0, sizeof(reset_context)); - - mutex_lock(&mgpu_info.mutex); - if (mgpu_info.pending_reset == true) { - mutex_unlock(&mgpu_info.mutex); - return; - } - mgpu_info.pending_reset = true; - mutex_unlock(&mgpu_info.mutex); - - /* Use a common context, just need to make sure full reset is done */ - reset_context.method = AMD_RESET_METHOD_NONE; - set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); - - for (i = 0; i < mgpu_info.num_dgpu; i++) { - adev = mgpu_info.gpu_ins[i].adev; - reset_context.reset_req_dev = adev; - r = amdgpu_device_pre_asic_reset(adev, &reset_context); - if (r) { - dev_err(adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ", - r, adev_to_drm(adev)->unique); - } - if (!queue_work(system_unbound_wq, &adev->xgmi_reset_work)) - r = -EALREADY; - } - for (i = 0; i < mgpu_info.num_dgpu; i++) { - adev = mgpu_info.gpu_ins[i].adev; - flush_work(&adev->xgmi_reset_work); - } - - /* reset function will rebuild the xgmi hive info , clear it now */ - for (i = 0; i < mgpu_info.num_dgpu; i++) - amdgpu_xgmi_remove_device(mgpu_info.gpu_ins[i].adev); - - INIT_LIST_HEAD(&device_list); - - for (i = 0; i < mgpu_info.num_dgpu; i++) - list_add_tail(&mgpu_info.gpu_ins[i].adev->reset_list, &device_list); - - /* unregister the GPU first, reset function will add them back */ - list_for_each_entry(adev, &device_list, reset_list) - amdgpu_unregister_gpu_instance(adev); - - /* Use a common context, just need to make sure full reset is done */ - set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags); - set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags); - r = amdgpu_do_asic_reset(&device_list, &reset_context); - - if (r) { - DRM_ERROR("reinit gpus failure"); - return; - } - for (i = 0; i < mgpu_info.num_dgpu; i++) { - adev = mgpu_info.gpu_ins[i].adev; - if (!adev->kfd.init_complete) { - kgd2kfd_init_zone_device(adev); - amdgpu_amdkfd_device_init(adev); - amdgpu_amdkfd_drm_client_create(adev); - } - amdgpu_ttm_set_buffer_funcs_status(adev, true); - } -} - static int amdgpu_pmops_prepare(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); -- cgit v1.2.3 From b472b8d829c1562c5597c1f212957b6b2696d40e Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 25 Sep 2024 15:05:07 -0500 Subject: drm/amd: Taint the kernel when enabling overdrive Some distributions have been patching amdgpu to enable overdrive by default which may compromise stability. Furthermore when bug reports are brought upstream it's not obvious that the system has been tampered with. When overdrive is enabled taint the kernel and leave a critical message in the logs for users so that it's obvious in a bug report it's been tampered with. Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b997843354b0..68f9c17a17eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2986,6 +2986,12 @@ static int __init amdgpu_init(void) /* Ignore KFD init failures. Normal when CONFIG_HSA_AMD is not set. */ amdgpu_amdkfd_init(); + if (amdgpu_pp_feature_mask & PP_OVERDRIVE_MASK) { + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + pr_crit("Overdrive is enabled, please disable it before " + "reporting any bugs unrelated to overdrive.\n"); + } + /* let modprobe override vga console setting */ return pci_register_driver(&amdgpu_kms_pci_driver); -- cgit v1.2.3 From ee52489d1210dbb894fda71957e1e9832126efda Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Fri, 20 Sep 2024 13:14:40 +0530 Subject: drm/amdgpu: Place NPS mode request on unload If a user has requested NPS mode switch, place the request through PSP during unload of the driver. For devices which are part of a hive, all requests are placed together. If one of them fails, revert back to the current NPS mode. Signed-off-by: Lijo Lazar Signed-off-by: Rajneesh Bhardwaj Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 68f9c17a17eb..46f756513948 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2429,6 +2429,7 @@ amdgpu_pci_remove(struct pci_dev *pdev) struct amdgpu_device *adev = drm_to_adev(dev); amdgpu_xcp_dev_unplug(adev); + amdgpu_gmc_prepare_nps_mode_change(adev); drm_dev_unplug(dev); if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) { -- cgit v1.2.3 From d5e3d8a2a6cb8b8c8678e60ae8067c18ffbc2da2 Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Mon, 14 Oct 2024 15:25:35 +0800 Subject: drm/amdgpu: clean up the suspend_complete To check the status of S3 suspend completion, use the PM core pm_suspend_global_flags bit(1) to detect S3 abort events. Therefore, clean up the AMDGPU driver's private flag suspend_complete. Signed-off-by: Prike Liang Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 46f756513948..ff3ac30744dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2500,7 +2500,6 @@ static int amdgpu_pmops_suspend(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - adev->suspend_complete = false; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else if (amdgpu_acpi_is_s3_active(adev)) @@ -2515,7 +2514,6 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - adev->suspend_complete = true; if (amdgpu_acpi_should_gpu_reset(adev)) return amdgpu_asic_reset(adev); -- cgit v1.2.3 From 0174c0791c042a357e54f91c68f58142e69c3584 Mon Sep 17 00:00:00 2001 From: "jeffbai@aosc.io" Date: Thu, 24 Oct 2024 21:07:18 +0800 Subject: drm/amdgpu: fix comment about amdgpu.abmlevel defaults Since 040fdcde288a ("drm/amdgpu: respect the abmlevel module parameter value if it is set"), the default value for amdgpu.abmlevel was set to -1, or auto. However, the comment explaining the default value was not updated to reflect the change (-1, or auto; not -1, or disabled). Clarify that the default value (-1) means auto. Fixes: 040fdcde288a ("drm/amdgpu: respect the abmlevel module parameter value if it is set") Reported-by: Ruikai Liu Signed-off-by: Mingcong Bai Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index ff3ac30744dc..054d1837e566 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -887,7 +887,7 @@ module_param_named(visualconfirm, amdgpu_dc_visual_confirm, uint, 0444); * the ABM algorithm, with 1 being the least reduction and 4 being the most * reduction. * - * Defaults to -1, or disabled. Userspace can only override this level after + * Defaults to -1, or auto. Userspace can only override this level after * boot if it's set to auto. */ int amdgpu_dm_abm_level = -1; -- cgit v1.2.3