userfaultfd: add UFFDIO_CONTINUE ioctl

This ioctl is how userspace ought to resolve "minor" userfaults.  The
idea is, userspace is notified that a minor fault has occurred.  It
might change the contents of the page using its second non-UFFD mapping,
or not.  Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".

Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs.  ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.

It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`.  We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case.  (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Axel Rasmussen <[email protected]>
Reviewed-by: Peter Xu <[email protected]>
Cc: Adam Ruprecht <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: Alexey Dobriyan <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Anshuman Khandual <[email protected]>
Cc: Cannon Matthews <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Chinwen Chang <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: "Dr . David Alan Gilbert" <[email protected]>
Cc: Huang Ying <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Jerome Glisse <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Lokesh Gidra <[email protected]>
Cc: "Matthew Wilcox (Oracle)" <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: "Michal Koutn" <[email protected]>
Cc: Michel Lespinasse <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Mina Almasry <[email protected]>
Cc: Nicholas Piggin <[email protected]>
Cc: Oliver Upton <[email protected]>
Cc: Shaohua Li <[email protected]>
Cc: Shawn Anastasio <[email protected]>
Cc: Steven Price <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 19 insertions, 2 deletions

diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index f24dd4fcbad9..bafbeb1a2624 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -40,10 +40,12 @@
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
 	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
-	 (__u64)1 << _UFFDIO_WRITEPROTECT)
+	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
+	 (__u64)1 << _UFFDIO_CONTINUE)
 #define UFFD_API_RANGE_IOCTLS_BASIC		\
 	((__u64)1 << _UFFDIO_WAKE |		\
-	 (__u64)1 << _UFFDIO_COPY)
+	 (__u64)1 << _UFFDIO_COPY |		\
+	 (__u64)1 << _UFFDIO_CONTINUE)
 
 /*
  * Valid ioctl command number range with this API is from 0x00 to
@@ -59,6 +61,7 @@
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
 #define _UFFDIO_WRITEPROTECT		(0x06)
+#define _UFFDIO_CONTINUE		(0x07)
 #define _UFFDIO_API			(0x3F)
 
 /* userfaultfd ioctl ids */
@@ -77,6 +80,8 @@
 				      struct uffdio_zeropage)
 #define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
 				      struct uffdio_writeprotect)
+#define UFFDIO_CONTINUE		_IOR(UFFDIO, _UFFDIO_CONTINUE,	\
+				     struct uffdio_continue)
 
 /* read() structure */
 struct uffd_msg {
@@ -268,6 +273,18 @@ struct uffdio_writeprotect {
 	__u64 mode;
 };
 
+struct uffdio_continue {
+	struct uffdio_range range;
+#define UFFDIO_CONTINUE_MODE_DONTWAKE		((__u64)1<<0)
+	__u64 mode;
+
+	/*
+	 * Fields below here are written by the ioctl and must be at the end:
+	 * the copy_from_user will not read past here.
+	 */
+	__s64 mapped;
+};
+
 /*
  * Flags for the userfaultfd(2) system call itself.
  */