[PATCH] drm/amdkfd: range check cp bad op exception interrupts

[Felix Kuehling]

On 2024-03-13 10:21, Jonathan Kim wrote:
> Due to a CP interrupt bug, bad packet garbage exception codes are raised.
> Do a range check so that the debugger and runtime do not receive garbage
> codes.
> Update the user api to guard exception code type checking as well.
>
> Signed-off-by: Jonathan Kim <jonathan.kim at amd.com>
> Tested-by: Jesse Zhang <jesse.zhang at amd.com>

Reviewed-by: Felix Kuehling <felix.kuehling at amd.com>


> ---
>   .../gpu/drm/amd/amdkfd/kfd_int_process_v10.c    |  3 ++-
>   .../gpu/drm/amd/amdkfd/kfd_int_process_v11.c    |  3 ++-
>   drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c |  3 ++-
>   include/uapi/linux/kfd_ioctl.h                  | 17 ++++++++++++++---
>   4 files changed, 20 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
> index a8e76287dde0..013d0a073b9b 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
> @@ -339,7 +339,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev,
>   				break;
>   			}
>   			kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23);
> -		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
> +		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
> +			   KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
>   			kfd_set_dbg_ev_from_interrupt(dev, pasid,
>   				KFD_DEBUG_DOORBELL_ID(context_id0),
>   				KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
> index 7e2859736a55..fe2ad0c0de95 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
> @@ -328,7 +328,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev,
>   		/* CP */
>   		if (source_id == SOC15_INTSRC_CP_END_OF_PIPE)
>   			kfd_signal_event_interrupt(pasid, context_id0, 32);
> -		else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
> +		else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
> +			 KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)))
>   			kfd_set_dbg_ev_from_interrupt(dev, pasid,
>   				KFD_CTXID0_DOORBELL_ID(context_id0),
>   				KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)),
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
> index ff7392336795..5483211c5d3d 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
> @@ -388,7 +388,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev,
>   				break;
>   			}
>   			kfd_signal_event_interrupt(pasid, sq_int_data, 24);
> -		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
> +		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
> +			   KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
>   			kfd_set_dbg_ev_from_interrupt(dev, pasid,
>   				KFD_DEBUG_DOORBELL_ID(context_id0),
>   				KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
> diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
> index 9ce46edc62a5..2040a470ddb4 100644
> --- a/include/uapi/linux/kfd_ioctl.h
> +++ b/include/uapi/linux/kfd_ioctl.h
> @@ -913,14 +913,25 @@ enum kfd_dbg_trap_exception_code {
>   				 KFD_EC_MASK(EC_DEVICE_NEW))
>   #define KFD_EC_MASK_PROCESS	(KFD_EC_MASK(EC_PROCESS_RUNTIME) |	\
>   				 KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE))
> +#define KFD_EC_MASK_PACKET	(KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) |	\
> +				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) |	\
> +				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) |	\
> +				 KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) |	\
> +				 KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) |	\
> +				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) |	\
> +				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) |	\
> +				 KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED))
>   
>   /* Checks for exception code types for KFD search */
> +#define KFD_DBG_EC_IS_VALID(ecode) (ecode > EC_NONE && ecode < EC_MAX)
>   #define KFD_DBG_EC_TYPE_IS_QUEUE(ecode)					\
> -			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE))
> +			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE))
>   #define KFD_DBG_EC_TYPE_IS_DEVICE(ecode)				\
> -			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE))
> +			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE))
>   #define KFD_DBG_EC_TYPE_IS_PROCESS(ecode)				\
> -			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS))
> +			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS))
> +#define KFD_DBG_EC_TYPE_IS_PACKET(ecode)				\
> +			(KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PACKET))
>   
>   
>   /* Runtime enable states */