drm/amdgpu: handle mp1 state properly on suspend or device removal
Subsystems (2)
PATCH 1/2 drm/amdgpu: handle mp1 state properly on suspend or device removal
Set mp1 state properly for non gpu reset cases.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 16 ++++++++++++++-- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 13 +++++++++++++ 3 files changed, 30 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3 -0
@@ -1089,6 +1089,7 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)static void amdgpu_switcheroo_set_state (struct pci_dev *pdev,enum vga_switcheroo_state state) {struct drm_device *dev =pci_get_drvdata (pdev); +struct amdgpu_device *adev = dev->dev_private;int r;if (amdgpu_device_supports_boco (dev) && state ==VGA_SWITCHEROO_OFF )
@@ -1112,7 +1113,9 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheropr_info ("amdgpu: switched off\n" );drm_kms_helper_poll_disable (dev); dev->switch_power_state =DRM_SWITCH_POWER_CHANGING ; + adev->mp1_state =PP_MP1_STATE_SHUTDOWN ;amdgpu_device_suspend (dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ;pci_save_state (dev->pdev);/* Shut down the device */ pci_disable_device (dev->pdev);
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +14 -2
@@ -1157,8 +1157,14 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)static int amdgpu_pmops_suspend (struct device *dev) {struct drm_device *drm_dev =dev_get_drvdata (dev); +struct amdgpu_device *adev = drm_dev->dev_private; +int r; + + adev->mp1_state =PP_MP1_STATE_SHUTDOWN ; + r =amdgpu_device_suspend (drm_dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ; -return amdgpu_device_suspend (drm_dev, true); +return r; }static int amdgpu_pmops_resume (struct device *dev)
@@ -1198,8 +1204,14 @@ static int amdgpu_pmops_thaw(struct device *dev)static int amdgpu_pmops_poweroff (struct device *dev) {struct drm_device *drm_dev =dev_get_drvdata (dev); +struct amdgpu_device *adev = drm_dev->dev_private; +int r; + + adev->mp1_state =PP_MP1_STATE_SHUTDOWN ; + r =amdgpu_device_suspend (drm_dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ; -return amdgpu_device_suspend (drm_dev, true); +return r; }static int amdgpu_pmops_restore (struct device *dev)
drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +13 -0
@@ -1370,6 +1370,18 @@ int smu_reset(struct smu_context *smu)return ret; } +void smu_late_fini (void *handle) +{ +struct amdgpu_device *adev = (struct amdgpu_device *)handle; +struct smu_context *smu = &adev->smu; + +/* +* Put the mp1 in the right state. +* This gets called on driver unloading. +*/ +smu_send_smc_msg (smu, SMU_MSG_PrepareMp1ForShutdown); +} +static int smu_suspend (void *handle) {int ret;
@@ -1931,6 +1943,7 @@ const struct amd_ip_funcs smu_ip_funcs = { .sw_fini = smu_sw_fini, .hw_init = smu_hw_init, .hw_fini = smu_hw_fini, + .late_fini = smu_late_fini, .suspend = smu_suspend, .resume = smu_resume, .is_idle = NULL,
Signature · 6 lines
2.24.0 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 2/2 drm/amdgpu: avoid unnecessary SMC firmware reloading
E.g. During non-RAS baco reset, the SMC is still alive. Thus there is no need to reload the SMC firmware.
--- drivers/gpu/drm/amd/amdgpu/psp_v11_0.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)
drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +14 -0
@@ -676,6 +676,19 @@ static bool psp_v11_0_compare_sram_data(struct psp_context *psp,return true; } +/* +* Check whether SMU is still alive. If that's true +* (e.g. for non-RAS baco reset), we need to skip SMC firmware reloading. +*/ +static bool psp_v11_0_smu_reload_quirk (struct psp_context *psp) +{ +struct amdgpu_device *adev = psp->adev; +uint32_t reg; + + reg =RREG32_PCIE (smnMP1_FIRMWARE_FLAGS |0x03b00000 ); +return (reg &MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK ) ? true : false; +} +static int psp_v11_0_mode1_reset (struct psp_context *psp) {int ret;
@@ -1070,6 +1083,7 @@ static const struct psp_funcs psp_v11_0_funcs = { .ring_stop = psp_v11_0_ring_stop, .ring_destroy = psp_v11_0_ring_destroy, .compare_sram_data = psp_v11_0_compare_sram_data, + .smu_reload_quirk = psp_v11_0_smu_reload_quirk, .mode1_reset = psp_v11_0_mode1_reset, .xgmi_get_topology_info = psp_v11_0_xgmi_get_topology_info, .xgmi_set_topology_info = psp_v11_0_xgmi_set_topology_info,
Signature · 6 lines
2.24.0 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
RE: [PATCH 2/2] drm/amdgpu: avoid unnecessary SMC firmware reloading
[AMD Public Use]
Quoted 9 lines
-----Original Message-----
From: Quan, Evan <[email protected]>
Sent: Thursday, December 26, 2019 3:11 AM
To: [email protected]
Cc: Deucher, Alexander <[email protected]>; Quan, Evan <[email protected]>
Subject: [PATCH 2/2] drm/amdgpu: avoid unnecessary SMC firmware reloading
Quoted 5 lines
E.g. During non-RAS baco reset, the SMC is still alive. Thus there is no need to reload the SMC firmware.
Change-Id I73f6284541d0ca0e82761380a27e32484fb0061cSigned-off-by Evan Quan <[email protected]>
Quoted 38 lines
--- drivers/gpu/drm/amd/amdgpu/psp_v11_0.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +10
-0@@ -676,6 +676,19 @@ static bool psp_v11_0_compare_sram_data(structpsp_context *psp, return true; } +/* +* Check whether SMU is still alive. If that's true +* (e.g. for non-RAS baco reset), we need to skip SMC firmware reloading. +*/ +static bool psp_v11_0_smu_reload_quirk (struct psp_context *psp) { +struct amdgpu_device *adev = psp->adev; +uint32_t reg; + + reg =RREG32_PCIE (smnMP1_FIRMWARE_FLAGS |0x03b00000 ); + return (reg &
MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) ? true :drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +3
-1+false; } +static int psp_v11_0_mode1_reset (struct psp_context *psp) {int ret;@@ -1070,6 +1083,7 @@ static const struct psp_funcs psp_v11_0_funcs = { .ring_stop = psp_v11_0_ring_stop, .ring_destroy = psp_v11_0_ring_destroy, .compare_sram_data = psp_v11_0_compare_sram_data, + .smu_reload_quirk = psp_v11_0_smu_reload_quirk, .mode1_reset = psp_v11_0_mode1_reset, .xgmi_get_topology_info = psp_v11_0_xgmi_get_topology_info, .xgmi_set_topology_info = psp_v11_0_xgmi_set_topology_info, --
Quoted 1 line
2.24.0
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Deucher, Alexander
maintainer[AMD Public Use]
Quoted 66 lines
-----Original Message-----
From: Quan, Evan <[email protected]>
Sent: Thursday, December 26, 2019 3:11 AM
To: [email protected]
Cc: Deucher, Alexander <[email protected]>; Quan, Evan <[email protected]>
Subject: [PATCH 1/2] drm/amdgpu: handle mp1 state properly on suspend or device removalSet mp1 state properly for non gpu reset cases.
Change-Id I2a007910da6b5e2d1f8915d17827621ebd2e8c59Signed-off-by Evan Quan <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 16 ++++++++++++++-- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 13 +++++++++++++ 3 files changed, 30 insertions(+), 2 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -1089,6 +1089,7 @@ static int amdgpu_device_check_arguments(struct
amdgpu_device*adev) static voidamdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state){drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0struct drm_device *dev =pci_get_drvdata (pdev); +struct amdgpu_device *adev = dev->dev_private;int r; if (amdgpu_device_supports_boco(dev) && state ==
VGA_SWITCHEROO_OFF) @@ -1112,7 +1113,9 @@ static void amdgpu_switcheroo_set_state(structpci_dev*pdev, enumvga_switcherodrivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0pr_info ("amdgpu: switched off\n" );drm_kms_helper_poll_disable (dev); dev->switch_power_state =
DRM_SWITCH_POWER_CHANGING;drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2
-0+ adev->mp1_state =PP_MP1_STATE_SHUTDOWN ;amdgpu_device_suspend (dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ;pci_save_state (dev->pdev);/* Shut down the device */ pci_disable_device (dev->pdev);drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +7
-1@@ -1157,8 +1157,14 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)static int amdgpu_pmops_suspend (struct device *dev) {struct drm_device *drm_dev =dev_get_drvdata (dev); +struct amdgpu_device *adev = drm_dev->dev_private; +int r; + + adev->mp1_state =PP_MP1_STATE_SHUTDOWN ; + r =amdgpu_device_suspend (drm_dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ; -return amdgpu_device_suspend (drm_dev, true); +return r; } static int amdgpu_pmops_resume(struct device *dev) @@ -1198,8 +1204,14@@ static int
amdgpu_pmops_thaw(struct device *dev)static intamdgpu_pmops_poweroff(struct device *dev){
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c amdgpu_pci_shutdown(struct pci_dev *pdev) · line 1163
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +4
-0struct drm_device *drm_dev =dev_get_drvdata (dev); +struct amdgpu_device *adev = drm_dev->dev_private; +int r; + + adev->mp1_state =PP_MP1_STATE_SHUTDOWN ;
Should this be STATE_UNLOAD for poweroff?
Quoted 18 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +3
-1+ r =amdgpu_device_suspend (drm_dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ; -return amdgpu_device_suspend (drm_dev, true); +return r; } static int amdgpu_pmops_restore(struct device *dev) diff --git
a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.cb/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
indexd07c4f2ccee7..4a7fb6b15635100644drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +1
-0@@ -1370,6 +1370,18 @@ int smu_reset(struct smu_context *smu)return ret; } +void smu_late_fini (void *handle)
drivers/gpu/drm/amd/powerplay/amdgpu_smu.c int smu_reset(struct smu_context *smu) · line 1383
Quoted 10 lines
drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +10
-0+{ +struct amdgpu_device *adev = (struct amdgpu_device *)handle; +struct smu_context *smu = &adev->smu; + +/* +* Put the mp1 in the right state. +* This gets called on driver unloading. +*/ +smu_send_smc_msg (smu, SMU_MSG_PrepareMp1ForShutdown); } +
Do we need something similar for the powerplay code? E.g., pp_late_fini()? Also shouldn't this be adev->mp1_state or prepare for unload rather than hardcoding it to prepare for shutdown?
Alex
Quoted 12 lines
drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +1
-1static int smu_suspend (void *handle) {int ret;@@ -1931,6 +1943,7 @@ const struct amd_ip_funcs smu_ip_funcs = { .sw_fini = smu_sw_fini, .hw_init = smu_hw_init, .hw_fini = smu_hw_fini, + .late_fini = smu_late_fini, .suspend = smu_suspend, .resume = smu_resume, .is_idle = NULL, --
Quoted 1 line
2.24.0
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Quoted 74 lines
-----Original Message-----
From: Deucher, Alexander <[email protected]>
Sent: Sunday, December 29, 2019 2:43 PM
To: Quan, Evan <[email protected]>; [email protected]
Subject: RE: [PATCH 1/2] drm/amdgpu: handle mp1 state properly on suspend or device removal[AMD Public Use]
Quoted 63 lines
-----Original Message-----
From: Quan, Evan <[email protected]>
Sent: Thursday, December 26, 2019 3:11 AM
To: [email protected]
Cc: Deucher, Alexander <[email protected]>; Quan, Evan <[email protected]>
Subject: [PATCH 1/2] drm/amdgpu: handle mp1 state properly on suspend or device removalSet mp1 state properly for non gpu reset cases.
Change-Id I2a007910da6b5e2d1f8915d17827621ebd2e8c59Signed-off-by Evan Quan <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 16 ++++++++++++++-- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 13 +++++++++++++ 3 files changed, 30 insertions(+), 2 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -1089,6 +1089,7 @@ static int amdgpu_device_check_arguments(struct
amdgpu_device*adev) static voidamdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state){drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0struct drm_device *dev =pci_get_drvdata (pdev); +struct amdgpu_device *adev = dev->dev_private;int r; if (amdgpu_device_supports_boco(dev) && state ==
VGA_SWITCHEROO_OFF) @@ -1112,7 +1113,9 @@ static void amdgpu_switcheroo_set_state(structpci_dev*pdev, enumvga_switcherodrivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0pr_info ("amdgpu: switched off\n" );drm_kms_helper_poll_disable (dev); dev->switch_power_state =
DRM_SWITCH_POWER_CHANGING;drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2
-0+ adev->mp1_state =PP_MP1_STATE_SHUTDOWN ;amdgpu_device_suspend (dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ;pci_save_state (dev->pdev);/* Shut down the device */ pci_disable_device (dev->pdev);drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +7
-1@@ -1157,8 +1157,14 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)static int amdgpu_pmops_suspend (struct device *dev) {struct drm_device *drm_dev =dev_get_drvdata (dev); +struct amdgpu_device *adev = drm_dev->dev_private; +int r; + + adev->mp1_state =PP_MP1_STATE_SHUTDOWN ; + r =amdgpu_device_suspend (drm_dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ; -return amdgpu_device_suspend (drm_dev, true); +return r; }
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c amdgpu_pci_shutdown(struct pci_dev *pdev) · line 1163
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +0
-0static int amdgpu_pmops_resume(struct device *dev) @@ -1198,8 +1204,14@@ static int
amdgpu_pmops_thaw(struct device *dev)static intamdgpu_pmops_poweroff(struct device *dev){drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +4
-0struct drm_device *drm_dev =dev_get_drvdata (dev); +struct amdgpu_device *adev = drm_dev->dev_private; +int r; + + adev->mp1_state =PP_MP1_STATE_SHUTDOWN ;Should this be
STATE_UNLOADfor poweroff?
[Quan, Evan] "PrepareMp1ForUnload is for PnP cases, where ASIC is not reset. If the whole ASIC is reset or need to shutdown, then we can simply use PrepareMp1ForShutdown." - a quote from a SMC firmware developer. According to that, I think PrepareMp1ForShutdown is more proper. How do you think?
Quoted 18 lines
Quoted 18 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +3
-1+ r =amdgpu_device_suspend (drm_dev, true); + adev->mp1_state =PP_MP1_STATE_NONE ; -return amdgpu_device_suspend (drm_dev, true); +return r; } static int amdgpu_pmops_restore(struct device *dev) diff --git
a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.cb/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
indexd07c4f2ccee7..4a7fb6b15635100644drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +0
-0@@ -1370,6 +1370,18 @@ int smu_reset(struct smu_context *smu)return ret; }
Quoted 15 lines
drivers/gpu/drm/amd/powerplay/amdgpu_smu.c int smu_reset(struct smu_context *smu) · line 1384
Quoted 11 lines
drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +11
-0+void smu_late_fini (void *handle) +{ +struct amdgpu_device *adev = (struct amdgpu_device *)handle; +struct smu_context *smu = &adev->smu; + +/* +* Put the mp1 in the right state. +* This gets called on driver unloading. +*/ +smu_send_smc_msg (smu, SMU_MSG_PrepareMp1ForShutdown); } +Do we need something similar for the powerplay code? E.g.,
pp_late_fini()? Also shouldn't this beadev->mp1_stateor prepare for unload rather than hardcoding it to prepare for shutdown?
[Quan, Evan] This is specifically for the amdgpu_driver_unload_kms() use case.
For that, the call path is amdgpu_driver_unload_kms() -> amdgpu_device_fini() -> amdgpu_device_ip_fini() -> hw_fini(). And the suspend routines are not on the call path. So, the adev->mp1_state way is not workable.
Yes, I think powerplay code needs this also.
Maybe we can use prepareMp1forunload. Considering amdgpu_driver_unload_kms() may be called on runtime driver/module unloading and the ASIC needs no power down or reset for that.
Quoted 16 lines
Alex
Quoted 12 lines
drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +1
-1static int smu_suspend (void *handle) {int ret;@@ -1931,6 +1943,7 @@ const struct amd_ip_funcs smu_ip_funcs = { .sw_fini = smu_sw_fini, .hw_init = smu_hw_init, .hw_fini = smu_hw_fini, + .late_fini = smu_late_fini, .suspend = smu_suspend, .resume = smu_resume, .is_idle = NULL, --Quoted 1 line
2.24.0
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx