[RFC 3/8] userfaultfd: expose writeprotect API to ioctl

[Shaohua Li <shli@fb.com>]

Add the writeprotect API to userfaultfd ioctl

Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 fs/userfaultfd.c                 | 45 ++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/userfaultfd.h | 10 +++++++++
 2 files changed, 55 insertions(+)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 5031170..eaa5086 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1122,6 +1122,49 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	return ret;
 }
 
+static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
+				    unsigned long arg)
+{
+	int ret;
+	struct uffdio_writeprotect uffdio_wp;
+	struct uffdio_writeprotect __user *user_uffdio_wp;
+	struct userfaultfd_wake_range range;
+
+	user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
+
+	if (copy_from_user(&uffdio_wp, user_uffdio_wp,
+			   sizeof(struct uffdio_writeprotect)))
+		return -EFAULT;
+
+	ret = validate_range(ctx->mm, uffdio_wp.range.start,
+			     uffdio_wp.range.len);
+	if (ret)
+		return ret;
+
+	if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
+			       UFFDIO_WRITEPROTECT_MODE_WP))
+		return -EINVAL;
+	if ((uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP) &&
+	     (uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE))
+		return -EINVAL;
+
+	if (uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP)
+		ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
+			uffdio_wp.range.len, true);
+	else
+		ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
+			uffdio_wp.range.len, false);
+	if (ret)
+		return ret;
+
+	if (!(uffdio_wp.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
+		range.start = uffdio_wp.range.start;
+		range.len = uffdio_wp.range.len;
+		wake_userfault(ctx, &range);
+	}
+	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
@@ -1186,6 +1229,8 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_ZEROPAGE:
 		ret = userfaultfd_zeropage(ctx, arg);
 		break;
+	case UFFDIO_WRITEPROTECT:
+		ret = userfaultfd_writeprotect(ctx, arg);
 	}
 	return ret;
 }
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 9057d7a..8898bd7 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -40,6 +40,7 @@
 #define _UFFDIO_WAKE			(0x02)
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_WRITEPROTECT		(0x05)
 #define _UFFDIO_API			(0x3F)
 
 /* userfaultfd ioctl ids */
@@ -56,6 +57,8 @@
 				      struct uffdio_copy)
 #define UFFDIO_ZEROPAGE		_IOWR(UFFDIO, _UFFDIO_ZEROPAGE,	\
 				      struct uffdio_zeropage)
+#define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
+				      struct uffdio_writeprotect)
 
 /* read() structure */
 struct uffd_msg {
@@ -164,4 +167,11 @@ struct uffdio_zeropage {
 	__s64 zeropage;
 };
 
+struct uffdio_writeprotect {
+	struct uffdio_range range;
+	/* !WP means undo writeprotect. DONTWAKE is valid only with !WP */
+#define UFFDIO_WRITEPROTECT_MODE_WP		((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE	((__u64)1<<1)
+	__u64 mode;
+};
 #endif /* _LINUX_USERFAULTFD_H */
-- 
2.4.6

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>