userfaultfd: UFFDIO_COPY and UFFDIO_ZEROPAGE

These two ioctl allows to either atomically copy or to map zeropages
into the virtual address space. This is used by the thread that opened
the userfaultfd to resolve the userfaults.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/userfaultfd.c

@@ -983,6 +983,96 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
 	return ret;
 }
 
+static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
+			    unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_copy uffdio_copy;
+	struct uffdio_copy __user *user_uffdio_copy;
+	struct userfaultfd_wake_range range;
+
+	user_uffdio_copy = (struct uffdio_copy __user *) arg;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
+			   /* don't copy "copy" last field */
+			   sizeof(uffdio_copy)-sizeof(__s64)))
+		goto out;
+
+	ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
+	if (ret)
+		goto out;
+	/*
+	 * double check for wraparound just in case. copy_from_user()
+	 * will later check uffdio_copy.src + uffdio_copy.len to fit
+	 * in the userland range.
+	 */
+	ret = -EINVAL;
+	if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
+		goto out;
+	if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
+		goto out;
+
+	ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
+			   uffdio_copy.len);
+	if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+	BUG_ON(!ret);
+	/* len == 0 would wake all */
+	range.len = ret;
+	if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
+		range.start = uffdio_copy.dst;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
+out:
+	return ret;
+}
+
+static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
+				unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_zeropage uffdio_zeropage;
+	struct uffdio_zeropage __user *user_uffdio_zeropage;
+	struct userfaultfd_wake_range range;
+
+	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
+			   /* don't copy "zeropage" last field */
+			   sizeof(uffdio_zeropage)-sizeof(__s64)))
+		goto out;
+
+	ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
+			     uffdio_zeropage.range.len);
+	if (ret)
+		goto out;
+	ret = -EINVAL;
+	if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
+		goto out;
+
+	ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
+			     uffdio_zeropage.range.len);
+	if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+	/* len == 0 would wake all */
+	BUG_ON(!ret);
+	range.len = ret;
+	if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
+		range.start = uffdio_zeropage.range.start;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
+out:
+	return ret;
+}
+
 /*
  * userland asks for a certain API version and we return which bits
  * and ioctl commands are implemented in this kernel for such API
@@ -1038,6 +1128,12 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_WAKE:
 		ret = userfaultfd_wake(ctx, arg);
 		break;
+	case UFFDIO_COPY:
+		ret = userfaultfd_copy(ctx, arg);
+		break;
+	case UFFDIO_ZEROPAGE:
+		ret = userfaultfd_zeropage(ctx, arg);
+		break;
 	}
 	return ret;
 }