6.12-stable review patch. If anyone has any objections, please let me know. ------------------ From: David Francis [ Upstream commit 47ea05f246bebc81c7796f56265cffd812cf0601 ] 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. Reviewed-by: David Yat Sin Signed-off-by: David Francis Signed-off-by: Alex Deucher (cherry picked from commit f19d8086f6644083c913d70bfdeee20e1b6f46a5) Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin --- .../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 d03160a463d0f..8a6c59af4a4ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -3575,6 +3575,12 @@ 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 09ab36f8e8c69..c03b6e6fb3688 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -327,6 +327,8 @@ int debug_refresh_runlist(struct device_queue_manager *dqm); bool kfd_dqm_is_queue_in_process(struct device_queue_manager *dqm, struct qcm_process_device *qpd, int doorbell_off, u32 *queue_format); +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 8f7e44afba635..939a6c92351b6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -440,7 +440,8 @@ enum kfd_queue_type { KFD_QUEUE_TYPE_HIQ, KFD_QUEUE_TYPE_DIQ, 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 be3f821dfd566..bf3c7d055fc33 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -1015,6 +1015,23 @@ 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; @@ -1037,13 +1054,6 @@ 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, ctl_stack */ mqd = q_extra_data; ctl_stack = mqd + q_data->mqd_size; -- 2.53.0