search for: nvif_vmm_pfnmap_v0_vram

...eau_svm.c > +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c > @@ -367,7 +367,6 @@ static const u64 > nouveau_svm_pfn_flags[HMM_PFN_FLAG_MAX] = { > [HMM_PFN_VALID ] = NVIF_VMM_PFNMAP_V0_V, > [HMM_PFN_WRITE ] = NVIF_VMM_PFNMAP_V0_W, > - [HMM_PFN_DEVICE_PRIVATE] = NVIF_VMM_PFNMAP_V0_VRAM, > }; > > static const u64 > @@ -558,8 +557,6 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, > break; > } > > - nouveau_dmem_convert_pfn(drm, &range); > - > svmm->vmm->vmm.object.client->super = true; > ret = nvif_ob...

...ry !\n"); @@ -705,5 +705,6 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, addr = nouveau_dmem_page_addr(page); range->pfns[i] &= ((1UL << range->pfn_shift) - 1); range->pfns[i] |= (addr >> PAGE_SHIFT) << range->pfn_shift; + range->pfns[i] |= NVIF_VMM_PFNMAP_V0_VRAM; } } diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index df9bf1fd1bc0..39c731a99937 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -367,7 +367,6 @@ static const u64 nouveau_svm_pfn_flags[HMM_PFN_FLAG...

...} > + > dpage = nouveau_dmem_page_alloc_locked(drm); > if (!dpage) > goto out; > @@ -560,6 +566,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, > goto out_free_page; > } > > +done: > *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) > @@ -615,6 +622,7 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm, > struct migrate_vma args = { > .vma = vma, > .start = start, > + .src_owner...

...via clEnqueueSVMMigrateMem(). > > Also, Ben Skeggs has accepted a set of patches to map GPU memory after being > > migrated and this change would conflict with that. > > Can you explain me how we actually invoke this code? > > For that we'd need HMM_PFN_DEVICE_PRIVATE NVIF_VMM_PFNMAP_V0_VRAM > set in ->pfns before calling hmm_range_fault, which isn't happening. Oh, I got tripped on this too The logic is backwards from what you'd think.. If you *set* HMM_PFN_DEVICE_PRIVATE then this triggers: hmm_pte_need_fault(): if ((cpu_flags & range->flags[HMM_PFN_DEVICE_PRI...

...tl_addr[i] = 0; > continue; > + } Can't we rely on the caller pre-zeroing the array? > + 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; Now that this routine isn't really device memory specific any...

...) { - 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_addr[0] = 0; + return; } + + p...

...) { - 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_addr[0] = 0; + return; } + + p...

...5 +705,6 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, > addr = nouveau_dmem_page_addr(page); > range->pfns[i] &= ((1UL << range->pfn_shift) - 1); > range->pfns[i] |= (addr >> PAGE_SHIFT) << range->pfn_shift; > + range->pfns[i] |= NVIF_VMM_PFNMAP_V0_VRAM; > } > } > diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c > index df9bf1fd1bc0..39c731a99937 100644 > --- a/drivers/gpu/drm/nouveau/nouveau_svm.c > +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c > @@ -367,7 +367,6 @@ static const u6...

...and > device private memory via clEnqueueSVMMigrateMem(). > Also, Ben Skeggs has accepted a set of patches to map GPU memory after being > migrated and this change would conflict with that. Can you explain me how we actually invoke this code? For that we'd need HMM_PFN_DEVICE_PRIVATE NVIF_VMM_PFNMAP_V0_VRAM set in ->pfns before calling hmm_range_fault, which isn't happening.

...page); + *dma_addr = DMA_MAPPING_ERROR; + goto done; + } + dpage = nouveau_dmem_page_alloc_locked(drm); if (!dpage) goto out; @@ -560,6 +566,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, goto out_free_page; } +done: *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) @@ -615,6 +622,7 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm, struct migrate_vma args = { .vma = vma, .start = start, + .src_owner = drm->dev, }; unsigned long i;...

...rateMem(). >>> Also, Ben Skeggs has accepted a set of patches to map GPU memory after being >>> migrated and this change would conflict with that. >> >> Can you explain me how we actually invoke this code? >> >> For that we'd need HMM_PFN_DEVICE_PRIVATE NVIF_VMM_PFNMAP_V0_VRAM >> set in ->pfns before calling hmm_range_fault, which isn't happening. > > Oh, I got tripped on this too > > The logic is backwards from what you'd think.. If you *set* > HMM_PFN_DEVICE_PRIVATE then this triggers: > > hmm_pte_need_fault(): > if ((cpu_fl...

...this routine fully sets the output array and does not assume pre-initialize > > + 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; > > Now that this routine isn...

These are based on 5.8.0-rc2 and intended for Ben Skeggs' nouveau tree. I believe the changes can be queued for 5.8-rcX after being reviewed. These were part of a larger series but I'm resending them separately as suggested by Jason Gunthorpe. https://lore.kernel.org/linux-mm/20200619215649.32297-1-rcampbell at nvidia.com/ Note that in order to exercise/test patch 2 here, you will need a

When acting on device private mappings a driver needs to know if the device (or other entity in case of kvmppc) actually owns this private mapping. This series adds an owner field and converts the migrate_vma code over to check it. I looked into doing the same for hmm_range_fault, but as far as I can tell that code has never been wired up to actually work for device private memory, so instead of

When acting on device private mappings a driver needs to know if the device (or other entity in case of kvmppc) actually owns this private mapping. This series adds an owner field and converts the migrate_vma code over to check it. I looked into doing the same for hmm_range_fault, but as far as I can tell that code has never been wired up to actually work for device private memory, so instead of

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

...addr_t *dma_addr, u64 *pfn) { struct device *dev = drm->dev->dev; struct page *dpage, *spage; @@ -561,6 +568,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, goto out_free_page; } + dpage->zone_device_data = svmm; *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) @@ -584,8 +592,8 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, unsigned long addr = args->start, nr_dma = 0, i; for (i = 0; addr < args->end; i++) { - a...

...-- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -367,7 +367,6 @@ static const u64 nouveau_svm_pfn_flags[HMM_PFN_FLAG_MAX] = { [HMM_PFN_VALID ] = NVIF_VMM_PFNMAP_V0_V, [HMM_PFN_WRITE ] = NVIF_VMM_PFNMAP_V0_W, - [HMM_PFN_DEVICE_PRIVATE] = NVIF_VMM_PFNMAP_V0_VRAM, }; static const u64 @@ -558,8 +557,6 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, break; } - nouveau_dmem_convert_pfn(drm, &range); - svmm->vmm->vmm.object.client->super = true; ret = nvif_object_ioctl(&svmm->vmm->vmm.object, data, size, NULL);...

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

...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 nouveau_dmem_migrate_copy_one(st...