diff options
| author | Felix Kuehling <Felix.Kuehling@amd.com> | 2018-03-15 17:27:46 -0400 |
|---|---|---|
| committer | Oded Gabbay <oded.gabbay@gmail.com> | 2018-03-15 17:27:46 -0400 |
| commit | c7bcbfa4f8d1e0e1078adfe959d4b65542bccf66 (patch) | |
| tree | bf626611a9648da7268e682253df552d6b1eea4b /include | |
| parent | 7c9b717196b1afd368436c258994ed6054717c7a (diff) | |
| download | linux-stable-c7bcbfa4f8d1e0e1078adfe959d4b65542bccf66.tar.gz linux-stable-c7bcbfa4f8d1e0e1078adfe959d4b65542bccf66.tar.bz2 linux-stable-c7bcbfa4f8d1e0e1078adfe959d4b65542bccf66.zip | |
drm/amdkfd: Remove limit on number of GPUs
Currently the number of GPUs is limited by aperture placement options
available on GFX7 and GFX8 hardware. This limitation is not necessary.
Scratch and LDS represent per-work-item and per-work-group storage
respectively. Different work-items and work-groups use the same virtual
address to access their own data. Work running on different GPUs is by
definition in different work-groups (different dispatches, in fact).
That means the same virtual addresses can be used for these apertures
on different GPUs.
Add a new AMDKFD_IOC_GET_PROCESS_APERTURES_NEW ioctl that removes the
artificial limitation on the number of GPUs that can be supported. The
new ioctl allows user mode to query the number of GPUs to allocate
enough memory for all GPUs to be reported.
This deprecates AMDKFD_IOC_GET_PROCESS_APERTURES.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Diffstat (limited to 'include')
| -rw-r--r-- | include/uapi/linux/kfd_ioctl.h | 27 |
1 files changed, 24 insertions, 3 deletions
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 111d73ba2d96..52014370e2e5 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -107,8 +107,6 @@ struct kfd_ioctl_get_clock_counters_args { __u32 pad; }; -#define NUM_OF_SUPPORTED_GPUS 7 - struct kfd_process_device_apertures { __u64 lds_base; /* from KFD */ __u64 lds_limit; /* from KFD */ @@ -120,6 +118,12 @@ struct kfd_process_device_apertures { __u32 pad; }; +/* + * AMDKFD_IOC_GET_PROCESS_APERTURES is deprecated. Use + * AMDKFD_IOC_GET_PROCESS_APERTURES_NEW instead, which supports an + * unlimited number of GPUs. + */ +#define NUM_OF_SUPPORTED_GPUS 7 struct kfd_ioctl_get_process_apertures_args { struct kfd_process_device_apertures process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */ @@ -129,6 +133,19 @@ struct kfd_ioctl_get_process_apertures_args { __u32 pad; }; +struct kfd_ioctl_get_process_apertures_new_args { + /* User allocated. Pointer to struct kfd_process_device_apertures + * filled in by Kernel + */ + __u64 kfd_process_device_apertures_ptr; + /* to KFD - indicates amount of memory present in + * kfd_process_device_apertures_ptr + * from KFD - Number of entries filled by KFD. + */ + __u32 num_of_nodes; + __u32 pad; +}; + #define MAX_ALLOWED_NUM_POINTS 100 #define MAX_ALLOWED_AW_BUFF_SIZE 4096 #define MAX_ALLOWED_WAC_BUFF_SIZE 128 @@ -332,7 +349,11 @@ struct kfd_ioctl_set_trap_handler_args { #define AMDKFD_IOC_SET_TRAP_HANDLER \ AMDKFD_IOW(0x13, struct kfd_ioctl_set_trap_handler_args) +#define AMDKFD_IOC_GET_PROCESS_APERTURES_NEW \ + AMDKFD_IOWR(0x14, \ + struct kfd_ioctl_get_process_apertures_new_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x14 +#define AMDKFD_COMMAND_END 0x15 #endif |