search for: nvif_vmm_pfnmap_v0

...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); > > And this should just be > > return container_of(pfns, struct nouveau_pfnmap_args, p.phys); Much simpler, thanks. >> +stati...

...or(dev, *dma_addr)) goto out_free_page; + paddr = nouveau_dmem_page_addr(dpage); if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_VRAM, - nouveau_dmem_page_addr(dpage), NOUVEAU_APER_HOST, - *dma_addr)) + paddr, NOUVEAU_APER_HOST, *dma_addr)) goto out_dma_unmap; + *pfn = NVIF_VMM_PFNMAP_V0_V | NVIF_VMM_PFNMAP_V0_VRAM | + ((paddr >> PAGE_SHIFT) << NVIF_VMM_PFNMAP_V0_ADDR_SHIFT); + if (src & MIGRATE_PFN_WRITE) + *pfn |= NVIF_VMM_PFNMAP_V0_W; return migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; out_dma_unmap: @@ -587,18 +594,19 @@ static unsigned long nouv...

...or(dev, *dma_addr)) goto out_free_page; + paddr = nouveau_dmem_page_addr(dpage); if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_VRAM, - nouveau_dmem_page_addr(dpage), NOUVEAU_APER_HOST, - *dma_addr)) + paddr, NOUVEAU_APER_HOST, *dma_addr)) goto out_dma_unmap; + *pfn = NVIF_VMM_PFNMAP_V0_V | NVIF_VMM_PFNMAP_V0_VRAM | + ((paddr >> PAGE_SHIFT) << NVIF_VMM_PFNMAP_V0_ADDR_SHIFT); + if (src & MIGRATE_PFN_WRITE) + *pfn |= NVIF_VMM_PFNMAP_V0_W; return migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; out_dma_unmap: @@ -590,18 +597,19 @@ static unsigned long nouv...

...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 container_of(pfns, struct nouveau_pfnmap_args, p.phys); > +static struct nouveau_svmm * > +nouveau_find_svmm(struct nouv...

...t; > + paddr = nouveau_dmem_page_addr(dpage); > if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_VRAM, > - nouveau_dmem_page_addr(dpage), NOUVEAU_APER_HOST, > - *dma_addr)) > + paddr, NOUVEAU_APER_HOST, *dma_addr)) > goto out_dma_unmap; > > + *pfn = NVIF_VMM_PFNMAP_V0_V | NVIF_VMM_PFNMAP_V0_VRAM | > + ((paddr >> PAGE_SHIFT) << NVIF_VMM_PFNMAP_V0_ADDR_SHIFT); > + if (src & MIGRATE_PFN_WRITE) > + *pfn |= NVIF_VMM_PFNMAP_V0_W; > return migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; > > out_dma_unmap: > @@ -590,18 +...

...or (i = 0; i < npages; ++i) { - struct page *page; - - if (!(range->hmm_pfns[i] & HMM_PFN_VALID)) { - ioctl_addr[i] = 0; - continue; - } - - page = hmm_pfn_to_page(range->hmm_pfns[i]); - if (is_device_private_page(page)) - ioctl_addr[i] = nouveau_dmem_page_addr(page) | - NVIF_VMM_PFNMAP_V0_V | - NVIF_VMM_PFNMAP_V0_VRAM; - else - ioctl_addr[i] = page_to_phys(page) | - NVIF_VMM_PFNMAP_V0_V | - NVIF_VMM_PFNMAP_V0_HOST; - if (range->hmm_pfns[i] & HMM_PFN_WRITE) - ioctl_addr[i] |= NVIF_VMM_PFNMAP_V0_W; + if (!(range->hmm_pfns[0] & HMM_PFN_VALID)) { + ioctl...

...or (i = 0; i < npages; ++i) { - struct page *page; - - if (!(range->hmm_pfns[i] & HMM_PFN_VALID)) { - ioctl_addr[i] = 0; - continue; - } - - page = hmm_pfn_to_page(range->hmm_pfns[i]); - if (is_device_private_page(page)) - ioctl_addr[i] = nouveau_dmem_page_addr(page) | - NVIF_VMM_PFNMAP_V0_V | - NVIF_VMM_PFNMAP_V0_VRAM; - else - ioctl_addr[i] = page_to_phys(page) | - NVIF_VMM_PFNMAP_V0_V | - NVIF_VMM_PFNMAP_V0_HOST; - if (range->hmm_pfns[i] & HMM_PFN_WRITE) - ioctl_addr[i] |= NVIF_VMM_PFNMAP_V0_W; + if (!(range->hmm_pfns[0] & HMM_PFN_VALID)) { + ioctl...

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.

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

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

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

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