AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-28 03:35:27 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
9726920b7e
linux_dsm_epyc7002/drivers/gpu/drm/nouveau/nouveau_svm.h

49 lines
1.5 KiB
C
Raw Normal View History

drm/nouveau/svm: initial support for shared virtual memory This uses HMM to mirror a process' CPU page tables into a channel's page tables, and keep them synchronised so that both the CPU and GPU are able to access the same memory at the same virtual address. While this code also supports Volta/Turing, it's only enabled for Pascal GPUs currently due to channel recovery being unreliable right now on the later GPUs. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2018-07-05 09:57:12 +07:00
#ifndef __NOUVEAU_SVM_H__
#define __NOUVEAU_SVM_H__
#include <nvif/os.h>
struct drm_device;
struct drm_file;
struct nouveau_drm;
struct nouveau_svmm;
#if IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM)
void nouveau_svm_init(struct nouveau_drm *);
void nouveau_svm_fini(struct nouveau_drm *);
void nouveau_svm_suspend(struct nouveau_drm *);
void nouveau_svm_resume(struct nouveau_drm *);
int nouveau_svmm_init(struct drm_device *, void *, struct drm_file *);
void nouveau_svmm_fini(struct nouveau_svmm **);
int nouveau_svmm_join(struct nouveau_svmm *, u64 inst);
void nouveau_svmm_part(struct nouveau_svmm *, u64 inst);
drm/nouveau/svm: new ioctl to migrate process memory to GPU memory This add an ioctl to migrate a range of process address space to the device memory. On platform without cache coherent bus (x86, ARM, ...) this means that CPU can not access that range directly, instead CPU will fault which will migrate the memory back to system memory. This is behind a staging flag so that we can evolve the API. Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
2018-08-08 03:13:16 +07:00
int nouveau_svmm_bind(struct drm_device *, void *, struct drm_file *);
drm/nouveau/svm: initial support for shared virtual memory This uses HMM to mirror a process' CPU page tables into a channel's page tables, and keep them synchronised so that both the CPU and GPU are able to access the same memory at the same virtual address. While this code also supports Volta/Turing, it's only enabled for Pascal GPUs currently due to channel recovery being unreliable right now on the later GPUs. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2018-07-05 09:57:12 +07:00
#else /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */
static inline void nouveau_svm_init(struct nouveau_drm *drm) {}
static inline void nouveau_svm_fini(struct nouveau_drm *drm) {}
static inline void nouveau_svm_suspend(struct nouveau_drm *drm) {}
static inline void nouveau_svm_resume(struct nouveau_drm *drm) {}
static inline int nouveau_svmm_init(struct drm_device *device, void *p,
struct drm_file *file)
{
return -ENOSYS;
}
static inline void nouveau_svmm_fini(struct nouveau_svmm **svmmp) {}
static inline int nouveau_svmm_join(struct nouveau_svmm *svmm, u64 inst)
{
return 0;
}
static inline void nouveau_svmm_part(struct nouveau_svmm *svmm, u64 inst) {}
drm/nouveau/svm: new ioctl to migrate process memory to GPU memory This add an ioctl to migrate a range of process address space to the device memory. On platform without cache coherent bus (x86, ARM, ...) this means that CPU can not access that range directly, instead CPU will fault which will migrate the memory back to system memory. This is behind a staging flag so that we can evolve the API. Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
2018-08-08 03:13:16 +07:00
static inline int nouveau_svmm_bind(struct drm_device *device, void *p,
struct drm_file *file)
{
return -ENOSYS;
}
drm/nouveau/svm: initial support for shared virtual memory This uses HMM to mirror a process' CPU page tables into a channel's page tables, and keep them synchronised so that both the CPU and GPU are able to access the same memory at the same virtual address. While this code also supports Volta/Turing, it's only enabled for Pascal GPUs currently due to channel recovery being unreliable right now on the later GPUs. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2018-07-05 09:57:12 +07:00
#endif /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */
#endif
Reference in New Issue Copy Permalink