userfaultfd: wp: add the writeprotect API to userfaultfd ioctl

Introduce the new uffd-wp APIs for userspace.

Firstly, we'll allow to do UFFDIO_REGISTER with write protection tracking
using the new UFFDIO_REGISTER_MODE_WP flag.  Note that this flag can
co-exist with the existing UFFDIO_REGISTER_MODE_MISSING, in which case the
userspace program can not only resolve missing page faults, and at the
same time tracking page data changes along the way.

Secondly, we introduced the new UFFDIO_WRITEPROTECT API to do page level
write protection tracking.  Note that we will need to register the memory
region with UFFDIO_REGISTER_MODE_WP before that.

[[email protected]: write up the commit message]
[[email protected]: remove useless block, write commit message, check against
 VM_MAYWRITE rather than VM_WRITE when register]
Signed-off-by: Andrea Arcangeli <[email protected]>
Signed-off-by: Peter Xu <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Reviewed-by: Jerome Glisse <[email protected]>
Cc: Bobby Powers <[email protected]>
Cc: Brian Geffon <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Denis Plotnikov <[email protected]>
Cc: "Dr . David Alan Gilbert" <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: "Kirill A . Shutemov" <[email protected]>
Cc: Martin Cracauer <[email protected]>
Cc: Marty McFadden <[email protected]>
Cc: Maya Gokhale <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Pavel Emelyanov <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Shaohua Li <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 23 insertions, 0 deletions

diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 340f23bc251d..95c4a160e5f8 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -52,6 +52,7 @@
 #define _UFFDIO_WAKE			(0x02)
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_WRITEPROTECT		(0x06)
 #define _UFFDIO_API			(0x3F)
 
 /* userfaultfd ioctl ids */
@@ -68,6 +69,8 @@
 				      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 {
@@ -232,4 +235,24 @@ struct uffdio_zeropage {
 	__s64 zeropage;
 };
 
+struct uffdio_writeprotect {
+	struct uffdio_range range;
+/*
+ * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range,
+ * unset the flag to undo protection of a range which was previously
+ * write protected.
+ *
+ * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up
+ * any wait thread after the operation succeeds.
+ *
+ * NOTE: Write protecting a region (WP=1) is unrelated to page faults,
+ * therefore DONTWAKE flag is meaningless with WP=1.  Removing write
+ * protection (WP=0) in response to a page fault wakes the faulting
+ * task unless DONTWAKE is set.
+ */
+#define UFFDIO_WRITEPROTECT_MODE_WP		((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE	((__u64)1<<1)
+	__u64 mode;
+};
+
 #endif /* _LINUX_USERFAULTFD_H */