From 6fe1010d6d9c02cf3556ab076585104551a6ee7e Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 6 Feb 2015 10:58:56 -0700 Subject: [PATCH] vfio/type1: DMA unmap chunking When unmapping DMA entries we try to rely on the IOMMU API behavior that allows the IOMMU to unmap a larger area than requested, up to the size of the original mapping. This works great when the IOMMU supports superpages *and* they're in use. Otherwise, each PAGE_SIZE increment is unmapped separately, resulting in poor performance. Instead we can use the IOVA-to-physical-address translation provided by the IOMMU API and unmap using the largest contiguous physical memory chunk available, which is also how vfio/type1 would have mapped the region. For a synthetic 1TB guest VM mapping and shutdown test on Intel VT-d (2M IOMMU pagesize support), this achieves about a 30% overall improvement mapping standard 4K pages, regardless of IOMMU superpage enabling, and about a 40% improvement mapping 2M hugetlbfs pages when IOMMU superpages are not available. Hugetlbfs with IOMMU superpages enabled is effectively unchanged. Unfortunately the same algorithm does not work well on IOMMUs with fine-grained superpages, like AMD-Vi, costing about 25% extra since the IOMMU will automatically unmap any power-of-two contiguous mapping we've provided it. We add a routine and a domain flag to detect this feature, leaving AMD-Vi unaffected by this unmap optimization. Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 54 +++++++++++++++++++++++++++++++-- 1 file changed, 51 insertions(+), 3 deletions(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 4a9d666f1e91..e6e7f155bdd9 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -66,6 +66,7 @@ struct vfio_domain { struct list_head next; struct list_head group_list; int prot; /* IOMMU_CACHE */ + bool fgsp; /* Fine-grained super pages */ }; struct vfio_dma { @@ -350,8 +351,8 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma) iommu_unmap(d->domain, dma->iova, dma->size); while (iova < end) { - size_t unmapped; - phys_addr_t phys; + size_t unmapped, len; + phys_addr_t phys, next; phys = iommu_iova_to_phys(domain->domain, iova); if (WARN_ON(!phys)) { @@ -359,7 +360,19 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma) continue; } - unmapped = iommu_unmap(domain->domain, iova, PAGE_SIZE); + /* + * To optimize for fewer iommu_unmap() calls, each of which + * may require hardware cache flushing, try to find the + * largest contiguous physical memory chunk to unmap. + */ + for (len = PAGE_SIZE; + !domain->fgsp && iova + len < end; len += PAGE_SIZE) { + next = iommu_iova_to_phys(domain->domain, iova + len); + if (next != phys + len) + break; + } + + unmapped = iommu_unmap(domain->domain, iova, len); if (WARN_ON(!unmapped)) break; @@ -665,6 +678,39 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, return 0; } +/* + * We change our unmap behavior slightly depending on whether the IOMMU + * supports fine-grained superpages. IOMMUs like AMD-Vi will use a superpage + * for practically any contiguous power-of-two mapping we give it. This means + * we don't need to look for contiguous chunks ourselves to make unmapping + * more efficient. On IOMMUs with coarse-grained super pages, like Intel VT-d + * with discrete 2M/1G/512G/1T superpages, identifying contiguous chunks + * significantly boosts non-hugetlbfs mappings and doesn't seem to hurt when + * hugetlbfs is in use. + */ +static void vfio_test_domain_fgsp(struct vfio_domain *domain) +{ + struct page *pages; + int ret, order = get_order(PAGE_SIZE * 2); + + pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); + if (!pages) + return; + + ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2, + IOMMU_READ | IOMMU_WRITE | domain->prot); + if (!ret) { + size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE); + + if (unmapped == PAGE_SIZE) + iommu_unmap(domain->domain, PAGE_SIZE, PAGE_SIZE); + else + domain->fgsp = true; + } + + __free_pages(pages, order); +} + static int vfio_iommu_type1_attach_group(void *iommu_data, struct iommu_group *iommu_group) { @@ -758,6 +804,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, } } + vfio_test_domain_fgsp(domain); + /* replay mappings on new domains */ ret = vfio_iommu_replay(iommu, domain); if (ret)