[PATCH] drm/amdkfd: fixed page fault when enable MES shader debugger

[Li, Yunxiang (Teddy)]

[Public]

> From: Jesse.zhang at amd.com <jesse.zhang at amd.com>
> Sent: Wednesday, December 18, 2024 6:26 PM
> Subject: [PATCH] drm/amdkfd: fixed page fault when enable MES shader debugger
>
> Initialize the process context address before setting the shader debugger.

I think it would make sense to pull this into it's own function if it's duplicated at multiple places. Also, may need to add a check before amdgpu_mes_flush_shader_debugger as well? Seems like in that case it would be enough to just skip the call if gpu_addr is null.

Regards,
Teddy

> [  260.781212] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:32
> vmid:0 pasid:0)
> [  260.781236] amdgpu 0000:03:00.0: amdgpu:   in page starting at address
> 0x0000000000000000 from client 10
> [  260.781255] amdgpu 0000:03:00.0: amdgpu:
> GCVM_L2_PROTECTION_FAULT_STATUS:0x00040A40
> [  260.781270] amdgpu 0000:03:00.0: amdgpu:      Faulty UTCL2 client ID: CPC
> (0x5)
> [  260.781284] amdgpu 0000:03:00.0: amdgpu:      MORE_FAULTS: 0x0
> [  260.781296] amdgpu 0000:03:00.0: amdgpu:      WALKER_ERROR: 0x0
> [  260.781308] amdgpu 0000:03:00.0: amdgpu:      PERMISSION_FAULTS: 0x4
> [  260.781320] amdgpu 0000:03:00.0: amdgpu:      MAPPING_ERROR: 0x0
> [  260.781332] amdgpu 0000:03:00.0: amdgpu:      RW: 0x1
> [  260.782017] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:32
> vmid:0 pasid:0)
> [  260.782039] amdgpu 0000:03:00.0: amdgpu:   in page starting at address
> 0x0000000000000000 from client 10
> [  260.782058] amdgpu 0000:03:00.0: amdgpu:
> GCVM_L2_PROTECTION_FAULT_STATUS:0x00040A41
> [  260.782073] amdgpu 0000:03:00.0: amdgpu:      Faulty UTCL2 client ID: CPC
> (0x5)
> [  260.782087] amdgpu 0000:03:00.0: amdgpu:      MORE_FAULTS: 0x1
> [  260.782098] amdgpu 0000:03:00.0: amdgpu:      WALKER_ERROR: 0x0
> [  260.782110] amdgpu 0000:03:00.0: amdgpu:      PERMISSION_FAULTS: 0x4
> [  260.782122] amdgpu 0000:03:00.0: amdgpu:      MAPPING_ERROR: 0x0
> [  260.782137] amdgpu 0000:03:00.0: amdgpu:      RW: 0x1
> [  260.782155] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:32
> vmid:0 pasid:0)
> [  260.782166] amdgpu 0000:03:00.0: amdgpu:   in page starting at address
> 0x0000000000000000 from client 10
>
> Signed-off-by: Jesse Zhang <jesse.zhang at amd.com>
> ---
>  drivers/gpu/drm/amd/amdkfd/kfd_debug.c | 17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
> b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
> index 312dfa84f29f..a8abc3091801 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
> @@ -350,10 +350,27 @@ int kfd_dbg_set_mes_debug_mode(struct
> kfd_process_device *pdd, bool sq_trap_en)  {
>         uint32_t spi_dbg_cntl = pdd->spi_dbg_override | pdd->spi_dbg_launch_mode;
>         uint32_t flags = pdd->process->dbg_flags;
> +       struct amdgpu_device *adev = pdd->dev->adev;
> +       int r;
>
>         if (!kfd_dbg_is_per_vmid_supported(pdd->dev))
>                 return 0;
>
> +       if (!pdd->proc_ctx_cpu_ptr) {
> +                       r = amdgpu_amdkfd_alloc_gtt_mem(adev,
> +                               AMDGPU_MES_PROC_CTX_SIZE,
> +                               &pdd->proc_ctx_bo,
> +                               &pdd->proc_ctx_gpu_addr,
> +                               &pdd->proc_ctx_cpu_ptr,
> +                               false);
> +               if (r) {
> +                       dev_err(adev->dev,
> +                       "failed to allocate process context bo\n");
> +                       return r;
> +               }
> +               memset(pdd->proc_ctx_cpu_ptr, 0,
> AMDGPU_MES_PROC_CTX_SIZE);
> +       }
> +
>         return amdgpu_mes_set_shader_debugger(pdd->dev->adev, pdd-
> >proc_ctx_gpu_addr, spi_dbg_cntl,
>                                                 pdd->watch_points, flags, sq_trap_en);  }
> --
> 2.25.1
>