userfaultfd: wp: add UFFDIO_COPY_MODE_WP

This allows UFFDIO_COPY to map pages write-protected.

[peterx@redhat.com: 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]
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Bobby Powers <bobbypowers@gmail.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Denis Plotnikov <dplotnikov@virtuozzo.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Martin Cracauer <cracauer@cons.org>
Cc: Marty McFadden <mcfadden8@llnl.gov>
Cc: Maya Gokhale <gokhale2@llnl.gov>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Link: http://lkml.kernel.org/r/20200220163112.11409-6-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 35 insertions, 19 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 703c1c3faa6e..c49bef505775 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1724,11 +1724,12 @@ 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 bd96855f3961..05dbbcafdcc0 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -53,7 +53,8 @@ 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;
@@ -99,9 +100,9 @@ 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));
+	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) {
@@ -415,7 +416,8 @@ 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;
 
@@ -432,11 +434,13 @@ 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,
@@ -454,7 +458,8 @@ 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;
@@ -462,6 +467,7 @@ 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:
@@ -508,6 +514,14 @@ retry:
 		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
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
@@ -562,7 +576,7 @@ retry:
 		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)) {
@@ -609,14 +623,14 @@ out:
 
 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);
 }