drm/amdgpu: fix MGPU fan boost enablement for XGMI reset
Subsystems (2)
PATCH 1/1 drm/amdgpu: fix MGPU fan boost enablement for XGMI reset
MGPU fan boost feature should not be enabled until all the devices from the same hive are all back from reset.
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 4 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 4 ++-- 3 files changed, 19 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +4 -0
@@ -1219,6 +1219,10 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev );static inline int amdgpu_dm_display_resume (struct amdgpu_device *adev) {return 0 ; }#endif + +void amdgpu_register_gpu_instance (struct amdgpu_device *adev); +void amdgpu_unregister_gpu_instance (struct amdgpu_device *adev); +#include "amdgpu_object.h" /* used by df_v3_6.c and amdgpu_pmu.c */
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +13 -0
@@ -3558,6 +3558,12 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,if (vram_lost)amdgpu_device_fill_reset_magic (tmp_adev); +/* +* Add this ASIC as tracked as reset was already +* complete successfully. +*/ +amdgpu_register_gpu_instance (tmp_adev); + r =amdgpu_device_ip_late_init (tmp_adev);if (r) goto out;
@@ -3692,6 +3698,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, device_list_handle = &device_list; } +/* +* Mark these ASICs to be reseted as untracked first +* And add them back after reset completed +*/ +list_for_each_entry (tmp_adev, device_list_handle, gmc.xgmi.head) +amdgpu_unregister_gpu_instance (tmp_adev); +/* block all schedulers and reset given job's ring */ list_for_each_entry (tmp_adev, device_list_handle, gmc.xgmi.head) {for (i =0 ; i <AMDGPU_MAX_RINGS ; ++i) {
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +2 -2
@@ -41,7 +41,7 @@#include "amdgpu_display.h" #include "amdgpu_ras.h" -static void amdgpu_unregister_gpu_instance (struct amdgpu_device *adev) +void amdgpu_unregister_gpu_instance (struct amdgpu_device *adev) {struct amdgpu_gpu_instance *gpu_instance;int i;
@@ -102,7 +102,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev) dev->dev_private =NULL ; } -static void amdgpu_register_gpu_instance (struct amdgpu_device *adev) +void amdgpu_register_gpu_instance (struct amdgpu_device *adev) {struct amdgpu_gpu_instance *gpu_instance;
Signature · 6 lines
2.21.0 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): [email protected]
Deucher, Alexander
Reviewed-by________________________________
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> on behalf of Evan Quan <[email protected]>
Sent: Thursday, June 27, 2019 11:31 PM
To: [email protected]
Cc: Quan, Evan
Subject: [PATCH] drm/amdgpu: fix MGPU fan boost enablement for XGMI reset
MGPU fan boost feature should not be enabled until all the devices from the same hive are all back from reset.
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 4 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 4 ++-- 3 files changed, 19 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +4 -0
@@ -1219,6 +1219,10 @@ int amdgpu_dm_display_resume(struct amdgpu_device *adev );static inline int amdgpu_dm_display_resume (struct amdgpu_device *adev) {return 0 ; }#endif + +void amdgpu_register_gpu_instance (struct amdgpu_device *adev); +void amdgpu_unregister_gpu_instance (struct amdgpu_device *adev); +#include "amdgpu_object.h" /* used by df_v3_6.c and amdgpu_pmu.c */
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +13 -0
@@ -3558,6 +3558,12 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,if (vram_lost)amdgpu_device_fill_reset_magic (tmp_adev); +/* +* Add this ASIC as tracked as reset was already +* complete successfully. +*/ +amdgpu_register_gpu_instance (tmp_adev); + r =amdgpu_device_ip_late_init (tmp_adev);if (r) goto out;
@@ -3692,6 +3698,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, device_list_handle = &device_list; } +/* +* Mark these ASICs to be reseted as untracked first +* And add them back after reset completed +*/ +list_for_each_entry (tmp_adev, device_list_handle, gmc.xgmi.head) +amdgpu_unregister_gpu_instance (tmp_adev); +/* block all schedulers and reset given job's ring */ list_for_each_entry (tmp_adev, device_list_handle, gmc.xgmi.head) {for (i =0 ; i <AMDGPU_MAX_RINGS ; ++i) {
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +2 -2
@@ -41,7 +41,7 @@#include "amdgpu_display.h" #include "amdgpu_ras.h" -static void amdgpu_unregister_gpu_instance (struct amdgpu_device *adev) +void amdgpu_unregister_gpu_instance (struct amdgpu_device *adev) {struct amdgpu_gpu_instance *gpu_instance;int i;
@@ -102,7 +102,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev) dev->dev_private =NULL ; } -static void amdgpu_register_gpu_instance (struct amdgpu_device *adev) +void amdgpu_register_gpu_instance (struct amdgpu_device *adev) {struct amdgpu_gpu_instance *gpu_instance;
--
2.21.0
_______________________________________________
amd-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx