search for: nouveau_pfnmap_arg

.../gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -70,6 +70,12 @@ struct nouveau_svm { #define SVM_DBG(s,f,a...) NV_DEBUG((s)->drm, "svm: "f"\n", ##a) #define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a) +struct nouveau_pfnmap_args { + struct nvif_ioctl_v0 i; + struct nvif_ioctl_mthd_v0 m; + struct nvif_vmm_pfnmap_v0 p; +}; + struct nouveau_ivmm { struct nouveau_svmm *svmm; u64 inst; @@ -782,6 +788,85 @@ nouveau_svm_fault(struct nvif_notify *notify) return NVIF_NOTIFY_KEEP; } +static inline struct nouveau_pfnmap_ar...

...dma tree since other HMM >> related changes were queued there. Now that those have been merged, this >> patch just contains changes to nouveau so it could go through any tree. >> I guess Ben Skeggs' tree would be appropriate. > > Yep > >> +static inline struct nouveau_pfnmap_args * >> +nouveau_pfns_to_args(void *pfns) > > don't use static inline inside C files OK. >> +{ >> + struct nvif_vmm_pfnmap_v0 *p = >> + container_of(pfns, struct nvif_vmm_pfnmap_v0, phys); >> + >> + return container_of(p, struct nouveau_pfnmap_args, p...

.../gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -70,6 +70,12 @@ struct nouveau_svm { #define SVM_DBG(s,f,a...) NV_DEBUG((s)->drm, "svm: "f"\n", ##a) #define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a) +struct nouveau_pfnmap_args { + struct nvif_ioctl_v0 i; + struct nvif_ioctl_mthd_v0 m; + struct nvif_vmm_pfnmap_v0 p; +}; + struct nouveau_ivmm { struct nouveau_svmm *svmm; u64 inst; @@ -734,6 +740,86 @@ nouveau_svm_fault(struct nvif_notify *notify) return NVIF_NOTIFY_KEEP; } +static inline struct nouveau_pfnmap_ar...

...> +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c > @@ -70,6 +70,12 @@ struct nouveau_svm { > #define SVM_DBG(s,f,a...) NV_DEBUG((s)->drm, "svm: "f"\n", ##a) > #define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a) > > +struct nouveau_pfnmap_args { > + struct nvif_ioctl_v0 i; > + struct nvif_ioctl_mthd_v0 m; > + struct nvif_vmm_pfnmap_v0 p; > +}; > + > struct nouveau_ivmm { > struct nouveau_svmm *svmm; > u64 inst; > @@ -734,6 +740,86 @@ nouveau_svm_fault(struct nvif_notify *notify) > return NVIF_NOTIFY_...

...was targeted for Jason's rdma tree since other HMM > related changes were queued there. Now that those have been merged, this > patch just contains changes to nouveau so it could go through any tree. > I guess Ben Skeggs' tree would be appropriate. Yep > +static inline struct nouveau_pfnmap_args * > +nouveau_pfns_to_args(void *pfns) don't use static inline inside C files > +{ > + struct nvif_vmm_pfnmap_v0 *p = > + container_of(pfns, struct nvif_vmm_pfnmap_v0, phys); > + > + return container_of(p, struct nouveau_pfnmap_args, p); And this should just be return...

Originally patch 4 was targeted for Jason's rdma tree since other HMM related changes were queued there. Now that those have been merged, these patches just contain changes to nouveau so they could go through any tree. I guess Ben Skeggs' tree would be appropriate. Changes since v2: Added patches 1-3 to fix some minor issues. Eliminated nouveau_find_svmm() since it is easily found.

.../nouveau_svm.c index a74ba8d84ba7..e072d610f2f9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -926,15 +926,14 @@ nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, unsigned long addr, u64 *pfns, unsigned long npages) { struct nouveau_pfnmap_args *args = nouveau_pfns_to_args(pfns); - int ret; args->p.addr = addr; args->p.size = npages << PAGE_SHIFT; mutex_lock(&svmm->mutex); - ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, - struct_size(args, p.phys, npages), NULL); + nvif_object_ioctl(&am...

hmm_range_fault() returns an array of page frame numbers and flags for how the pages are mapped in the requested process' page tables. The PFN can be used to get the struct page with hmm_pfn_to_page() and the page size order can be determined with compound_order(page) but if the page is larger than order 0 (PAGE_SIZE), there is no indication that the page is mapped using a larger page size. To

.../drivers/gpu/drm/nouveau/nouveau_svm.c @@ -514,38 +514,51 @@ static const struct mmu_interval_notifier_ops nouveau_svm_mni_ops = { }; static void nouveau_hmm_convert_pfn(struct nouveau_drm *drm, - struct hmm_range *range, u64 *ioctl_addr) + struct hmm_range *range, + struct nouveau_pfnmap_args *args) { struct page *page; /* - * The ioctl_addr prepared here is passed through nvif_object_ioctl() + * The address prepared here is passed through nvif_object_ioctl() * to an eventual DMA map in something like gp100_vmm_pgt_pfn() * * This is all just encoding the internal hmm...

...au/nouveau_svm.c index 2df1c0460559..7c95ffcbd18f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -815,7 +815,6 @@ nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, unsigned long addr, u64 *pfns, unsigned long npages) { struct nouveau_pfnmap_args *args = nouveau_pfns_to_args(pfns); - int ret; args->p.addr = addr; args->p.size = npages << PAGE_SHIFT; @@ -823,8 +822,8 @@ nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, mutex_lock(&svmm->mutex); svmm->vmm->vmm.object.client->super = tru...

...target value < GPU_VRAM */ target = args->header >> NOUVEAU_SVM_BIND_TARGET_SHIFT; target &= NOUVEAU_SVM_BIND_TARGET_MASK; @@ -926,15 +923,14 @@ nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, unsigned long addr, u64 *pfns, unsigned long npages) { struct nouveau_pfnmap_args *args = nouveau_pfns_to_args(pfns); - int ret; args->p.addr = addr; args->p.size = npages << PAGE_SHIFT; mutex_lock(&svmm->mutex); - ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, - struct_size(args, p.phys, npages), NULL); + nvif_object_ioctl(&am...

...args->src[i], &dma_addrs[nr_dma]); > + args->src[i], &dma_addrs[nr_dma], &pfns[i]); Nit: I find the &pfns[i] way to pass the argument a little weird to read. Why not "pfns + i"? > +u64 * > +nouveau_pfns_alloc(unsigned long npages) > +{ > + struct nouveau_pfnmap_args *args; > + > + args = kzalloc(sizeof(*args) + npages * sizeof(args->p.phys[0]), Can we use struct_size here? > + int ret; > + > + if (!svm) > + return; > + > + mutex_lock(&svm->mutex); > + svmm = nouveau_find_svmm(svm, mm); > + if (!svmm) { > + mutex_...

...au/nouveau_svm.c index 2df1c0460559..01583e9954a2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -815,7 +815,6 @@ nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, unsigned long addr, u64 *pfns, unsigned long npages) { struct nouveau_pfnmap_args *args = nouveau_pfns_to_args(pfns); - int ret; args->p.addr = addr; args->p.size = npages << PAGE_SHIFT; @@ -823,7 +822,7 @@ nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, mutex_lock(&svmm->mutex); svmm->vmm->vmm.object.client->super = tru...

The goal for this series is to introduce the hmm_range_fault() output array flags HMM_PFN_PMD and HMM_PFN_PUD. This allows a device driver to know that a given 4K PFN is actually mapped by the CPU using either a PMD sized or PUD sized CPU page table entry and therefore the device driver can safely map system memory using larger device MMU PTEs. The series is based on 5.8.0-rc3 and is intended for

...; > > Nit: I find the &pfns[i] way to pass the argument a little weird to read. > Why not "pfns + i"? OK, will do in v2. Should I convert to "dma_addrs + nr_dma" too? >> +u64 * >> +nouveau_pfns_alloc(unsigned long npages) >> +{ >> + struct nouveau_pfnmap_args *args; >> + >> + args = kzalloc(sizeof(*args) + npages * sizeof(args->p.phys[0]), > > Can we use struct_size here? Yes, good suggestion. > >> + int ret; >> + >> + if (!svm) >> + return; >> + >> + mutex_lock(&svm->mutex); >&...

The goal for this series is to introduce the hmm_pfn_to_map_order() function. This allows a device driver to know that a given 4K PFN is actually mapped by the CPU using a larger sized CPU page table entry and therefore the device driver can safely map system memory using larger device MMU PTEs. The series is based on 5.8.0-rc3 and is intended for Jason Gunthorpe's hmm tree. These were

...ouveau_svm_fault(struct nvif_notify *notify) struct nvif_object *device = &svm->drm->client.device.object; struct nouveau_svmm *svmm; struct { - struct { - struct nvif_ioctl_v0 i; - struct nvif_ioctl_mthd_v0 m; - struct nvif_vmm_pfnmap_v0 p; - } i; - u64 phys[16]; + struct nouveau_pfnmap_args i; + u64 phys[1]; } args; - unsigned long hmm_pfns[ARRAY_SIZE(args.phys)]; - struct vm_area_struct *vma; + unsigned long hmm_flags; u64 inst, start, limit; - int fi, fn, pi, fill; + int fi, fn; int replay = 0, ret; /* Parse available fault buffer entries into a cache, and update @@ -691...

...ouveau_svm_fault(struct nvif_notify *notify) struct nvif_object *device = &svm->drm->client.device.object; struct nouveau_svmm *svmm; struct { - struct { - struct nvif_ioctl_v0 i; - struct nvif_ioctl_mthd_v0 m; - struct nvif_vmm_pfnmap_v0 p; - } i; - u64 phys[16]; + struct nouveau_pfnmap_args i; + u64 phys[1]; } args; - unsigned long hmm_pfns[ARRAY_SIZE(args.phys)]; - struct vm_area_struct *vma; + unsigned long hmm_flags; u64 inst, start, limit; - int fi, fn, pi, fill; + int fi, fn; int replay = 0, ret; /* Parse available fault buffer entries into a cache, and update @@ -691...

These patches apply to linux-5.8.0-rc1. Patches 1-3 should probably go into 5.8, the others can be queued for 5.9. Patches 4-6 improve the HMM self tests. Patch 7-8 prepare nouveau for the meat of this series which adds support and testing for compound page mapping of system memory (patches 9-11) and compound page migration to device private memory (patches 12-16). Since these changes are split

This series adds support for transparent huge page migration to migrate_vma_*() and adds nouveau SVM and HMM selftests as consumers. Earlier versions were posted previously [1] and [2]. The patches apply cleanly to the linux-mm 5.10.0-rc2 tree. There are a lot of other THP patches being posted. I don't think there are any semantic conflicts but there may be some merge conflicts depending on