Hello
On Thu, 20 Jun 2019 10:19:53 +0800 Peter Xu <peterx@xxxxxxxxxx> wrote:
> From: Andrea Arcangeli <aarcange@xxxxxxxxxx>
>
> This allows UFFDIO_COPY to map pages write-protected.
>
> Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> [peterx: switch to VM_WARN_ON_ONCE in mfill_atomic_pte; add brackets
> around "dst_vma->vm_flags & VM_WRITE"; fix wordings in comments and
> commit messages]
> Reviewed-by: Jerome Glisse <jglisse@xxxxxxxxxx>
> Reviewed-by: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
> Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
> ---
> fs/userfaultfd.c | 5 +++--
> include/linux/userfaultfd_k.h | 2 +-
> include/uapi/linux/userfaultfd.h | 11 +++++-----
> mm/userfaultfd.c | 36 ++++++++++++++++++++++----------
> 4 files changed, 35 insertions(+), 19 deletions(-)
>
> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
> index 5dbef45ecbf5..c594945ad5bf 100644
> --- a/fs/userfaultfd.c
> +++ b/fs/userfaultfd.c
> @@ -1694,11 +1694,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
> ret = -EINVAL;
> if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
> goto out;
> - if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
> + if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
> goto out;
> if (mmget_not_zero(ctx->mm)) {
> ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
> - uffdio_copy.len, &ctx->mmap_changing);
> + uffdio_copy.len, &ctx->mmap_changing,
> + uffdio_copy.mode);
> mmput(ctx->mm);
> } else {
> return -ESRCH;
> diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> index 7b91b76aac58..dcd33172b728 100644
> --- a/include/linux/userfaultfd_k.h
> +++ b/include/linux/userfaultfd_k.h
> @@ -36,7 +36,7 @@ extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
>
> extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
> unsigned long src_start, unsigned long len,
> - bool *mmap_changing);
> + bool *mmap_changing, __u64 mode);
> extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
> unsigned long dst_start,
> unsigned long len,
> diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
> index 48f1a7c2f1f0..340f23bc251d 100644
> --- a/include/uapi/linux/userfaultfd.h
> +++ b/include/uapi/linux/userfaultfd.h
> @@ -203,13 +203,14 @@ struct uffdio_copy {
> __u64 dst;
> __u64 src;
> __u64 len;
> +#define UFFDIO_COPY_MODE_DONTWAKE ((__u64)1<<0)
> /*
> - * There will be a wrprotection flag later that allows to map
> - * pages wrprotected on the fly. And such a flag will be
> - * available if the wrprotection ioctl are implemented for the
> - * range according to the uffdio_register.ioctls.
> + * UFFDIO_COPY_MODE_WP will map the page write protected on
> + * the fly. UFFDIO_COPY_MODE_WP is available only if the
> + * write protected ioctl is implemented for the range
> + * according to the uffdio_register.ioctls.
> */
> -#define UFFDIO_COPY_MODE_DONTWAKE ((__u64)1<<0)
> +#define UFFDIO_COPY_MODE_WP ((__u64)1<<1)
> __u64 mode;
>
> /*
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index 9932d5755e4c..c8e7846e9b7e 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -25,7 +25,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
> struct vm_area_struct *dst_vma,
> unsigned long dst_addr,
> unsigned long src_addr,
> - struct page **pagep)
> + struct page **pagep,
> + bool wp_copy)
> {
> struct mem_cgroup *memcg;
> pte_t _dst_pte, *dst_pte;
> @@ -71,9 +72,9 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
> if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
> goto out_release;
>
> - _dst_pte = mk_pte(page, dst_vma->vm_page_prot);
> - if (dst_vma->vm_flags & VM_WRITE)
> - _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
> + _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot));
Make a dirty pte if the memory region is writable, imho.
> + if ((dst_vma->vm_flags & VM_WRITE) && !wp_copy)
> + _dst_pte = pte_mkwrite(_dst_pte);
>
> dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
> if (dst_vma->vm_file) {
> @@ -398,7 +399,8 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
> unsigned long dst_addr,
> unsigned long src_addr,
> struct page **page,
> - bool zeropage)
> + bool zeropage,
> + bool wp_copy)
> {
> ssize_t err;
>
> @@ -415,11 +417,13 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
> if (!(dst_vma->vm_flags & VM_SHARED)) {
> if (!zeropage)
> err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
> - dst_addr, src_addr, page);
> + dst_addr, src_addr, page,
> + wp_copy);
> else
> err = mfill_zeropage_pte(dst_mm, dst_pmd,
> dst_vma, dst_addr);
> } else {
> + VM_WARN_ON_ONCE(wp_copy);
> if (!zeropage)
> err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
> dst_vma, dst_addr,
> @@ -437,7 +441,8 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
> unsigned long src_start,
> unsigned long len,
> bool zeropage,
> - bool *mmap_changing)
> + bool *mmap_changing,
> + __u64 mode)
> {
> struct vm_area_struct *dst_vma;
> ssize_t err;
> @@ -445,6 +450,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
> unsigned long src_addr, dst_addr;
> long copied;
> struct page *page;
> + bool wp_copy;
>
> /*
> * Sanitize the command parameters:
> @@ -501,6 +507,14 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
> dst_vma->vm_flags & VM_SHARED))
> goto out_unlock;
>
> + /*
> + * validate 'mode' now that we know the dst_vma: don't allow
> + * a wrprotect copy if the userfaultfd didn't register as WP.
> + */
> + wp_copy = mode & UFFDIO_COPY_MODE_WP;
> + if (wp_copy && !(dst_vma->vm_flags & VM_UFFD_WP))
> + goto out_unlock;
> +
> /*
> * If this is a HUGETLB vma, pass off to appropriate routine
> */
> @@ -556,7 +570,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
> BUG_ON(pmd_trans_huge(*dst_pmd));
>
> err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
> - src_addr, &page, zeropage);
> + src_addr, &page, zeropage, wp_copy);
> cond_resched();
>
> if (unlikely(err == -ENOENT)) {
> @@ -603,14 +617,14 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
>
> ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
> unsigned long src_start, unsigned long len,
> - bool *mmap_changing)
> + bool *mmap_changing, __u64 mode)
> {
> return __mcopy_atomic(dst_mm, dst_start, src_start, len, false,
> - mmap_changing);
> + mmap_changing, mode);
> }
>
> ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
> unsigned long len, bool *mmap_changing)
> {
> - return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing);
> + return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing, 0);
> }
> --
> 2.21.0
>
>
Hillf
