From 121a2bc6ae786f59c7327a2b54c8bed5779e67e6 Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Fri, 18 Oct 2019 16:15:04 -0400 Subject: [PATCH] drm/amdgpu: Move amdgpu_ras_recovery_init to after SMU ready. For Arcturus the I2C traffic is done through SMU tables and so we must postpone RAS recovery init to after they are ready which is in amdgpu_device_ip_hw_init_phase2. Signed-off-by: Andrey Grodzovsky Reviewed-by: Alex Deucher Reviewed-by: Evan Quan Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 11 ----------- 2 files changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 46218b36dc9e..83d80070f0e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1877,6 +1877,19 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (r) goto init_failed; + /* + * retired pages will be loaded from eeprom and reserved here, + * it should be called after amdgpu_device_ip_hw_init_phase2 since + * for some ASICs the RAS EEPROM code relies on SMU fully functioning + * for I2C communication which only true at this point. + * recovery_init may fail, but it can free all resources allocated by + * itself and its failure should not stop amdgpu init process. + * + * Note: theoretically, this should be called before all vram allocations + * to protect retired page from abusing + */ + amdgpu_ras_recovery_init(adev); + if (adev->gmc.xgmi.num_physical_nodes > 1) amdgpu_xgmi_add_device(adev); amdgpu_amdkfd_device_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 69e54308f080..41eb2af59445 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1802,17 +1802,6 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) adev->gmc.visible_vram_size); #endif - /* - * retired pages will be loaded from eeprom and reserved here, - * it should be called after ttm init since new bo may be created, - * recovery_init may fail, but it can free all resources allocated by - * itself and its failure should not stop amdgpu init process. - * - * Note: theoretically, this should be called before all vram allocations - * to protect retired page from abusing - */ - amdgpu_ras_recovery_init(adev); - /* *The reserved vram for firmware must be pinned to the specified *place on the VRAM, so reserve it early. -- 2.45.2