search for: nouveau_dmem_fence_don

...b/drivers/gpu/drm/nouveau/nouveau_dmem.c index d469bc334438..21052a4aaf69 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -133,6 +133,19 @@ static void nouveau_dmem_page_free(struct page *page) spin_unlock(&chunk->lock); } +static void nouveau_dmem_fence_done(struct nouveau_fence **fence) +{ + if (fence) { + nouveau_fence_wait(*fence, true, false); + nouveau_fence_unref(fence); + } else { + /* + * FIXME wait for channel to be IDLE before calling finalizing + * the hmem object. + */ + } +} + static void nouveau_dmem_fault_alloc_and_copy(struc...

...nouveau_dmem_fault { > - struct nouveau_drm *drm; > - struct nouveau_fence *fence; > - dma_addr_t *dma; > - unsigned long npages; > -}; > - > struct nouveau_migrate { > struct vm_area_struct *vma; > struct nouveau_drm *drm; > @@ -146,130 +139,57 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) > } > } > > -static void > -nouveau_dmem_fault_alloc_and_copy(struct vm_area_struct *vma, > - const unsigned long *src_pfns, > - unsigned long *dst_pfns, > - unsigned long start, > - unsigned long end, > -...

...eau_dmem.c @@ -209,8 +209,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) goto done; } - if (!nouveau_fence_new(&fence)) - nouveau_fence_emit(fence, dmem->migrate.chan); + nouveau_fence_new(&fence, dmem->migrate.chan); migrate_vma_pages(&args); nouveau_dmem_fence_done(&fence); dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); @@ -403,8 +402,7 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) } } - if (!nouveau_fence_new(&fence)) - nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan); + nouve...

...gt;pgmap, struct nouveau_dmem, pagemap); } -struct nouveau_dmem_fault { - struct nouveau_drm *drm; - struct nouveau_fence *fence; - dma_addr_t *dma; - unsigned long npages; -}; - struct nouveau_migrate { struct vm_area_struct *vma; struct nouveau_drm *drm; @@ -146,130 +139,57 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) } } -static void -nouveau_dmem_fault_alloc_and_copy(struct vm_area_struct *vma, - const unsigned long *src_pfns, - unsigned long *dst_pfns, - unsigned long start, - unsigned long end, - struct nouveau_dmem_fault *fault) +static vm_fault_t...

...gt;pgmap, struct nouveau_dmem, pagemap); } -struct nouveau_dmem_fault { - struct nouveau_drm *drm; - struct nouveau_fence *fence; - dma_addr_t *dma; - unsigned long npages; -}; - struct nouveau_migrate { struct vm_area_struct *vma; struct nouveau_drm *drm; @@ -146,130 +139,55 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) } } -static void -nouveau_dmem_fault_alloc_and_copy(struct vm_area_struct *vma, - const unsigned long *src_pfns, - unsigned long *dst_pfns, - unsigned long start, - unsigned long end, - struct nouveau_dmem_fault *fault) +static vm_fault_t...

...eau_dmem.c @@ -678,7 +678,7 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, } if (!nouveau_fence_new(&fence)) - nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan); + nouveau_fence_emit(fence, drm->dmem->migrate.chan); migrate_vma_pages(args); nouveau_dmem_fence_done(&fence); nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i); base-commit: 82d750e9d2f5d0594c8f7057ce59127e701af781 -- 2.41.0

Hi Jérôme, Ben and Jason, below is a series against the hmm tree which starts revamping the migrate_vma functionality. The prime idea is to export three slightly lower level functions and thus avoid the need for migrate_vma_ops callbacks. Diffstat: 5 files changed, 281 insertions(+), 607 deletions(-) A git tree is also available at: git://git.infradead.org/users/hch/misc.git

...kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, npages); @@ -406,11 +406,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) migrate_device_pages(src_pfns, dst_pfns, npages); nouveau_dmem_fence_done(&fence); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); for (i = 0; i < npages; i++) dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); - kfree(dma_addrs); + kv...

...uct nouveau_dmem_fault { > - struct nouveau_drm *drm; > - struct nouveau_fence *fence; > - dma_addr_t *dma; > - unsigned long npages; > -}; > - > struct nouveau_migrate { > struct vm_area_struct *vma; > struct nouveau_drm *drm; > @@ -146,130 +139,55 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) > } > } > > -static void > -nouveau_dmem_fault_alloc_and_copy(struct vm_area_struct *vma, > - const unsigned long *src_pfns, > - unsigned long *dst_pfns, > - unsigned long start, > - unsigned long end, > - st...

...*fence; + unsigned long addr = args->start, nr_dma = 0, i; + + for (i = 0; addr < args->end; i++) { + args->dst[i] = nouveau_dmem_migrate_copy_one(drm, args->vma, + addr, args->src[i], &dma_addrs[nr_dma]); + if (args->dst[i]) + nr_dma++; + addr += PAGE_SIZE; + } - nouveau_dmem_fence_done(&migrate->fence); + nouveau_fence_new(drm->dmem->migrate.chan, false, &fence); + migrate_vma_pages(args); + nouveau_dmem_fence_done(&fence); - while (migrate->dma_nr--) { - dma_unmap_page(drm->dev->dev, migrate->dma[migrate->dma_nr], - PAGE_SIZE, PCI...

Hi Jérôme, Ben and Jason, below is a series against the hmm tree which starts revamping the migrate_vma functionality. The prime idea is to export three slightly lower level functions and thus avoid the need for migrate_vma_ops callbacks. Diffstat: 4 files changed, 285 insertions(+), 602 deletions(-) A git tree is also available at: git://git.infradead.org/users/hch/misc.git

...), GFP_KERNEL | __GFP_NOFAIL); > > migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, > npages); > @@ -406,11 +406,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) > migrate_device_pages(src_pfns, dst_pfns, npages); > nouveau_dmem_fence_done(&fence); > migrate_device_finalize(src_pfns, dst_pfns, npages); > - kfree(src_pfns); > - kfree(dst_pfns); > + kvfree(src_pfns); > + kvfree(dst_pfns); > for (i = 0; i < npages; i++) > dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BI...

...s); + memset(dst_pfns, 0, npages); + memset(dma_addrs, 0, npages); migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, npages); @@ -406,11 +406,8 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) migrate_device_pages(src_pfns, dst_pfns, npages); nouveau_dmem_fence_done(&fence); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); for (i = 0; i < npages; i++) dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); - kfree(dma_addrs); } void -- 2.17.1

Hi Jérôme, Ben and Jason, below is a series against the hmm tree which starts revamping the migrate_vma functionality. The prime idea is to export three slightly lower level functions and thus avoid the need for migrate_vma_ops callbacks. Diffstat: 7 files changed, 282 insertions(+), 614 deletions(-) A git tree is also available at: git://git.infradead.org/users/hch/misc.git

..._addrs + nr_dma); + dma_addrs + nr_dma, pfns + i); if (args->dst[i]) nr_dma++; addr += PAGE_SIZE; @@ -607,15 +615,12 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, nouveau_fence_new(drm->dmem->migrate.chan, false, &fence); migrate_vma_pages(args); nouveau_dmem_fence_done(&fence); + nouveau_pfns_map(drm, args->vma->vm_mm, args->start, pfns, i); while (nr_dma--) { dma_unmap_page(drm->dev->dev, dma_addrs[nr_dma], PAGE_SIZE, DMA_BIDIRECTIONAL); } - /* - * FIXME optimization: update GPU page table to point to newly migrated - * memory...

...RN_ON(!chunk->callocated); chunk->callocated--; /* * FIXME when chunk->callocated reach 0 we should add the chunk to * a reclaim list so that it can be freed in case of memory pressure. */ - spin_unlock(&chunk->lock); + spin_unlock(&dmem->lock); } static void nouveau_dmem_fence_done(struct nouveau_fence **fence) @@ -167,8 +167,8 @@ static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) { - struct nouveau_dmem *dmem = page_to_dmem(vmf->page); - struct nouveau_drm *drm = dmem->drm; + s...

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.

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

This series adds support for transparent huge page migration to migrate_vma_*() and adds nouveau SVM and HMM selftests as consumers. An earlier version was posted previously [1]. This version now supports splitting a THP midway in the migration process which led to a number of changes. The patches apply cleanly to the current linux-mm tree. Since there are a couple of patches in linux-mm from Dan

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