AMD General

Reviewed-by: "David Yat Sin <[email protected]>"


> -----Original Message-----
> From: amd-gfx <[email protected]> On Behalf Of David
> Francis
> Sent: Monday, July 6, 2026 2:15 PM
> To: [email protected]
> Cc: Francis, David <[email protected]>
> Subject: [PATCH] drm/amdkfd: Check bounds on CRIU restore queue type and mqd
> size
>
> We weren't checking whether the values provided in the private data in kfd 
> CRIU
> restore were within bounds.
>
> For queue type, add a KFD_QUEUE_TYPE_MAX and ensure the provided type is
> less than it.
>
> For mqd_size, add new function mqd_size_from_queue_type and confirm that the
> provided mqd_size matches expectations.
>
> Signed-off-by: David Francis <[email protected]>
> ---
>  .../drm/amd/amdkfd/kfd_device_queue_manager.c |  6 +++++
> .../drm/amd/amdkfd/kfd_device_queue_manager.h |  2 ++
>  drivers/gpu/drm/amd/amdkfd/kfd_priv.h         |  3 ++-
>  .../amd/amdkfd/kfd_process_queue_manager.c    | 24 +++++++++++++------
>  4 files changed, 27 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> index f6a749fbdd8e..0419fe869d4b 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> @@ -3777,6 +3777,12 @@ bool kfd_dqm_is_queue_in_process(struct
> device_queue_manager *dqm,
>       dqm_unlock(dqm);
>       return r;
>  }
> +
> +size_t mqd_size_from_queue_type(struct device_queue_manager *dqm, enum
> +kfd_queue_type type) {
> +     return dqm->mqd_mgrs[get_mqd_type_from_queue_type(type)]->mqd_size;
> +}
> +
>  #if defined(CONFIG_DEBUG_FS)
>
>  static void seq_reg_dump(struct seq_file *m, diff --git
> a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
> b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
> index 2229f8b2f446..c9f9f7a87111 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
> @@ -335,6 +335,8 @@ bool kfd_dqm_is_queue_in_process(struct
> device_queue_manager *dqm,
>                                int doorbell_off, u32 *queue_format);  int
> kfd_reset_queue_mes(struct device_queue_manager *dqm, int queue_type,
>                       int pipe, int queue, unsigned int db);
> +size_t mqd_size_from_queue_type(struct device_queue_manager *dqm,
> +                             enum kfd_queue_type type);
>
>  static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device 
> *pdd)
> { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> index 6e559aab4009..6c1b8255435f 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> @@ -441,7 +441,8 @@ enum kfd_queue_type  {
>       KFD_QUEUE_TYPE_SDMA,
>       KFD_QUEUE_TYPE_HIQ,
>       KFD_QUEUE_TYPE_SDMA_XGMI,
> -     KFD_QUEUE_TYPE_SDMA_BY_ENG_ID
> +     KFD_QUEUE_TYPE_SDMA_BY_ENG_ID,
> +     KFD_QUEUE_TYPE_MAX,
>  };
>
>  enum kfd_queue_format {
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> index 0a7276eadf79..3131f1e46d50 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> @@ -1003,6 +1003,23 @@ int kfd_criu_restore_queue(struct kfd_process *p,
>               goto exit;
>       }
>
> +     pdd = kfd_process_device_data_by_id(p, q_data->gpu_id);
> +     if (!pdd) {
> +             pr_err("Failed to get pdd\n");
> +             ret = -EINVAL;
> +             goto exit;
> +     }
> +
> +     if (q_data->type >= KFD_QUEUE_TYPE_MAX) {
> +             ret = -EINVAL;
> +             goto exit;
> +     }
> +
> +     if (q_data->mqd_size != mqd_size_from_queue_type(pdd->dev->dqm,
> q_data->type)) {
> +             ret = -EINVAL;
> +             goto exit;
> +     }
> +
>       *priv_data_offset += sizeof(*q_data);
>       q_extra_data_size = (uint64_t)q_data->ctl_stack_size + q_data->mqd_size;
>
> @@ -1025,13 +1042,6 @@ int kfd_criu_restore_queue(struct kfd_process *p,
>
>       *priv_data_offset += q_extra_data_size;
>
> -     pdd = kfd_process_device_data_by_id(p, q_data->gpu_id);
> -     if (!pdd) {
> -             pr_err("Failed to get pdd\n");
> -             ret = -EINVAL;
> -             goto exit;
> -     }
> -
>       /*
>        * data stored in this order:
>        * mqd[xcc0], mqd[xcc1],..., ctl_stack[xcc0], ctl_stack[xcc1]...
> --
> 2.34.1

Reply via email to