diff options
| -rw-r--r-- | drivers/vfio/vfio_iommu_type1.c | 135 |
1 files changed, 89 insertions, 46 deletions
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 1c86375aca2d..4bb162c1d649 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -107,6 +107,8 @@ struct vfio_batch { struct page **pages; /* for pin_user_pages_remote */ struct page *fallback_page; /* if pages alloc fails */ int capacity; /* length of pages array */ + int size; /* of batch currently */ + int offset; /* of next entry in pages */ }; struct vfio_group { @@ -469,6 +471,9 @@ static int put_pfn(unsigned long pfn, int prot) static void vfio_batch_init(struct vfio_batch *batch) { + batch->size = 0; + batch->offset = 0; + if (unlikely(disable_hugepages)) goto fallback; @@ -484,6 +489,17 @@ fallback: batch->capacity = 1; } +static void vfio_batch_unpin(struct vfio_batch *batch, struct vfio_dma *dma) +{ + while (batch->size) { + unsigned long pfn = page_to_pfn(batch->pages[batch->offset]); + + put_pfn(pfn, dma->prot); + batch->offset++; + batch->size--; + } +} + static void vfio_batch_fini(struct vfio_batch *batch) { if (batch->capacity == VFIO_BATCH_MAX_CAPACITY) @@ -635,65 +651,88 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr, long npage, unsigned long *pfn_base, unsigned long limit, struct vfio_batch *batch) { - unsigned long pfn = 0; + unsigned long pfn; + struct mm_struct *mm = current->mm; long ret, pinned = 0, lock_acct = 0; bool rsvd; dma_addr_t iova = vaddr - dma->vaddr + dma->iova; /* This code path is only user initiated */ - if (!current->mm) + if (!mm) return -ENODEV; - ret = vaddr_get_pfns(current->mm, vaddr, 1, dma->prot, pfn_base, - batch->pages); - if (ret < 0) - return ret; - - pinned++; - rsvd = is_invalid_reserved_pfn(*pfn_base); - - /* - * Reserved pages aren't counted against the user, externally pinned - * pages are already counted against the user. - */ - if (!rsvd && !vfio_find_vpfn(dma, iova)) { - if (!dma->lock_cap && current->mm->locked_vm + 1 > limit) { - put_pfn(*pfn_base, dma->prot); - pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__, - limit << PAGE_SHIFT); - return -ENOMEM; - } - lock_acct++; + if (batch->size) { + /* Leftover pages in batch from an earlier call. */ + *pfn_base = page_to_pfn(batch->pages[batch->offset]); + pfn = *pfn_base; + rsvd = is_invalid_reserved_pfn(*pfn_base); + } else { + *pfn_base = 0; } - if (unlikely(disable_hugepages)) - goto out; + while (npage) { + if (!batch->size) { + /* Empty batch, so refill it. */ + long req_pages = min_t(long, npage, batch->capacity); - /* Lock all the consecutive pages from pfn_base */ - for (vaddr += PAGE_SIZE, iova += PAGE_SIZE; pinned < npage; - pinned++, vaddr += PAGE_SIZE, iova += PAGE_SIZE) { - ret = vaddr_get_pfns(current->mm, vaddr, 1, dma->prot, &pfn, - batch->pages); - if (ret < 0) - break; + ret = vaddr_get_pfns(mm, vaddr, req_pages, dma->prot, + &pfn, batch->pages); + if (ret < 0) + goto unpin_out; - if (pfn != *pfn_base + pinned || - rsvd != is_invalid_reserved_pfn(pfn)) { - put_pfn(pfn, dma->prot); - break; + batch->size = ret; + batch->offset = 0; + + if (!*pfn_base) { + *pfn_base = pfn; + rsvd = is_invalid_reserved_pfn(*pfn_base); + } } - if (!rsvd && !vfio_find_vpfn(dma, iova)) { - if (!dma->lock_cap && - current->mm->locked_vm + lock_acct + 1 > limit) { - put_pfn(pfn, dma->prot); - pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", - __func__, limit << PAGE_SHIFT); - ret = -ENOMEM; - goto unpin_out; + /* + * pfn is preset for the first iteration of this inner loop and + * updated at the end to handle a VM_PFNMAP pfn. In that case, + * batch->pages isn't valid (there's no struct page), so allow + * batch->pages to be touched only when there's more than one + * pfn to check, which guarantees the pfns are from a + * !VM_PFNMAP vma. + */ + while (true) { + if (pfn != *pfn_base + pinned || + rsvd != is_invalid_reserved_pfn(pfn)) + goto out; + + /* + * Reserved pages aren't counted against the user, + * externally pinned pages are already counted against + * the user. + */ + if (!rsvd && !vfio_find_vpfn(dma, iova)) { + if (!dma->lock_cap && + mm->locked_vm + lock_acct + 1 > limit) { + pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", + __func__, limit << PAGE_SHIFT); + ret = -ENOMEM; + goto unpin_out; + } + lock_acct++; } - lock_acct++; + + pinned++; + npage--; + vaddr += PAGE_SIZE; + iova += PAGE_SIZE; + batch->offset++; + batch->size--; + + if (!batch->size) + break; + + pfn = page_to_pfn(batch->pages[batch->offset]); } + + if (unlikely(disable_hugepages)) + break; } out: @@ -701,10 +740,11 @@ out: unpin_out: if (ret < 0) { - if (!rsvd) { + if (pinned && !rsvd) { for (pfn = *pfn_base ; pinned ; pfn++, pinned--) put_pfn(pfn, dma->prot); } + vfio_batch_unpin(batch, dma); return ret; } @@ -1463,6 +1503,7 @@ static int vfio_pin_map_dma(struct vfio_iommu *iommu, struct vfio_dma *dma, if (ret) { vfio_unpin_pages_remote(dma, iova + dma->size, pfn, npage, true); + vfio_batch_unpin(&batch, dma); break; } @@ -1726,11 +1767,13 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, ret = iommu_map(domain->domain, iova, phys, size, dma->prot | domain->prot); if (ret) { - if (!dma->iommu_mapped) + if (!dma->iommu_mapped) { vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT, size >> PAGE_SHIFT, true); + vfio_batch_unpin(&batch, dma); + } goto unwind; } |