[PATCH] drm/amdgpu: add vm fault information to devcoredump

[Christian König]

Am 06.03.24 um 19:19 schrieb Sunil Khatri:
> Add page fault information to the devcoredump.
>
> Output of devcoredump:
> **** AMDGPU Device Coredump ****
> version: 1
> kernel: 6.7.0-amd-staging-drm-next
> module: amdgpu
> time: 29.725011811
> process_name: soft_recovery_p PID: 1720
>
> Ring timed out details
> IP Type: 0 Ring Name: gfx_0.0.0
>
> [gfxhub] Page fault observed for GPU family:143
> Faulty page starting at address 0x0000000000000000
> Protection fault status register:0x301031
>
> VRAM is lost due to GPU reset!
>
> Signed-off-by: Sunil Khatri <sunil.khatri at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c | 15 ++++++++++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h |  1 +
>   2 files changed, 15 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> index 147100c27c2d..d7fea6cdf2f9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> @@ -203,8 +203,20 @@ amdgpu_devcoredump_read(char *buffer, loff_t offset, size_t count,
>   			   coredump->ring->name);
>   	}
>   
> +	if (coredump->fault_info.status) {
> +		struct amdgpu_vm_fault_info *fault_info = &coredump->fault_info;
> +
> +		drm_printf(&p, "\n[%s] Page fault observed for GPU family:%d\n",
> +			   fault_info->vmhub ? "mmhub" : "gfxhub",
> +			   coredump->adev->family);
> +		drm_printf(&p, "Faulty page starting at address 0x%016llx\n",
> +			   fault_info->addr);
> +		drm_printf(&p, "Protection fault status register:0x%x\n",
> +			   fault_info->status);
> +	}
> +
>   	if (coredump->reset_vram_lost)
> -		drm_printf(&p, "VRAM is lost due to GPU reset!\n");
> +		drm_printf(&p, "\nVRAM is lost due to GPU reset!\n");
>   	if (coredump->adev->reset_info.num_regs) {
>   		drm_printf(&p, "AMDGPU register dumps:\nOffset:     Value:\n");
>   
> @@ -253,6 +265,7 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
>   	if (job) {
>   		s_job = &job->base;
>   		coredump->ring = to_amdgpu_ring(s_job->sched);
> +		coredump->fault_info = job->vm->fault_info;

That's illegal. The VM pointer might already be stale at this point.

I think you need to add the fault info of the last fault globally in the 
VRAM manager or move this to the process info Shashank is working on.

Regards,
Christian.

>   	}
>   
>   	coredump->adev = adev;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
> index 60522963aaca..3197955264f9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
> @@ -98,6 +98,7 @@ struct amdgpu_coredump_info {
>   	struct timespec64               reset_time;
>   	bool                            reset_vram_lost;
>   	struct amdgpu_ring			*ring;
> +	struct amdgpu_vm_fault_info	fault_info;
>   };
>   #endif
>