* [PATCH] drm/amdgpu: ensure no_hw_access is visible before MMIO
@ 2026-01-28 6:23 Perry Yuan
2026-01-28 13:57 ` Lazar, Lijo
0 siblings, 1 reply; 3+ messages in thread
From: Perry Yuan @ 2026-01-28 6:23 UTC (permalink / raw)
To: alexander.deucher, amd-gfx
Add a full memory barrier after clearing no_hw_access in
amdgpu_device_mode1_reset() so subsequent PCI state restore
access cannot observe stale state on other CPUs.
Fixes: 91ae0045130b ("drm/amd/pm: Disable MMIO access during SMU Mode 1 reset")
Signed-off-by: Perry Yuan <perry.yuan@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b2deb6a74eb2..e69ab8a923e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5735,6 +5735,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
/* enable mmio access after mode 1 reset completed */
adev->no_hw_access = false;
+ /* ensure no_hw_access is updated before we access hw */
+ smp_mb();
+
amdgpu_device_load_pci_state(adev->pdev);
ret = amdgpu_psp_wait_for_bootloader(adev);
if (ret)
--
2.34.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] drm/amdgpu: ensure no_hw_access is visible before MMIO
2026-01-28 6:23 [PATCH] drm/amdgpu: ensure no_hw_access is visible before MMIO Perry Yuan
@ 2026-01-28 13:57 ` Lazar, Lijo
2026-01-28 14:40 ` Christian König
0 siblings, 1 reply; 3+ messages in thread
From: Lazar, Lijo @ 2026-01-28 13:57 UTC (permalink / raw)
To: Perry Yuan, alexander.deucher, amd-gfx
On 28-Jan-26 11:53 AM, Perry Yuan wrote:
> Add a full memory barrier after clearing no_hw_access in
> amdgpu_device_mode1_reset() so subsequent PCI state restore
> access cannot observe stale state on other CPUs.
>
Just want to reiterate that this approach masks the original logical
errors within amdgpu.
For ex: this is one such which would not have been caught in the first
place with shortcuts like these.
12caf3b76150 drm/amdkfd: Handle GPU reset and drain retry fault race
Thanks,
Lijo
> Fixes: 91ae0045130b ("drm/amd/pm: Disable MMIO access during SMU Mode 1 reset")
> Signed-off-by: Perry Yuan <perry.yuan@amd.com>
> Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index b2deb6a74eb2..e69ab8a923e3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -5735,6 +5735,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
> /* enable mmio access after mode 1 reset completed */
> adev->no_hw_access = false;
>
> + /* ensure no_hw_access is updated before we access hw */
> + smp_mb();
> +
> amdgpu_device_load_pci_state(adev->pdev);
> ret = amdgpu_psp_wait_for_bootloader(adev);
> if (ret)
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] drm/amdgpu: ensure no_hw_access is visible before MMIO
2026-01-28 13:57 ` Lazar, Lijo
@ 2026-01-28 14:40 ` Christian König
0 siblings, 0 replies; 3+ messages in thread
From: Christian König @ 2026-01-28 14:40 UTC (permalink / raw)
To: Lazar, Lijo, Perry Yuan, alexander.deucher, amd-gfx
On 1/28/26 14:57, Lazar, Lijo wrote:
> On 28-Jan-26 11:53 AM, Perry Yuan wrote:
>> Add a full memory barrier after clearing no_hw_access in
>> amdgpu_device_mode1_reset() so subsequent PCI state restore
>> access cannot observe stale state on other CPUs.
>>
>
> Just want to reiterate that this approach masks the original logical errors within amdgpu.
Yeah, completely agree. A single smp_mb() is actually forbidden by upstreaming rules.
So absolutely clear NAK from my side to this patch here.
Regards,
Christian.
>
> For ex: this is one such which would not have been caught in the first place with shortcuts like these.
>
> 12caf3b76150 drm/amdkfd: Handle GPU reset and drain retry fault race
>
> Thanks,
> Lijo
>
>> Fixes: 91ae0045130b ("drm/amd/pm: Disable MMIO access during SMU Mode 1 reset")
>> Signed-off-by: Perry Yuan <perry.yuan@amd.com>
>> Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++
>> 1 file changed, 3 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> index b2deb6a74eb2..e69ab8a923e3 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> @@ -5735,6 +5735,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
>> /* enable mmio access after mode 1 reset completed */
>> adev->no_hw_access = false;
>> + /* ensure no_hw_access is updated before we access hw */
>> + smp_mb();
>> +
>> amdgpu_device_load_pci_state(adev->pdev);
>> ret = amdgpu_psp_wait_for_bootloader(adev);
>> if (ret)
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-01-28 14:40 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-01-28 6:23 [PATCH] drm/amdgpu: ensure no_hw_access is visible before MMIO Perry Yuan
2026-01-28 13:57 ` Lazar, Lijo
2026-01-28 14:40 ` Christian König
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox