summaryrefslogtreecommitdiff
path: root/include/uapi
diff options
context:
space:
mode:
authorAxel Rasmussen <axelrasmussen@google.com>2021-05-05 04:35:49 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-05-05 21:27:22 +0300
commitf619147104c8ea71e120e4936d2b68ec11a1e527 (patch)
tree66c3491aa51468f682aecc0115a3285b1daa3777 /include/uapi
parent714c189108244f1df579689061db1d785d92e7e2 (diff)
downloadlinux-f619147104c8ea71e120e4936d2b68ec11a1e527.tar.xz
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/20210301222728.176417-5-axelrasmussen@google.com Signed-off-by: Axel Rasmussen <axelrasmussen@google.com> Reviewed-by: Peter Xu <peterx@redhat.com> Cc: Adam Ruprecht <ruprecht@google.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Cannon Matthews <cannonmatthews@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chinwen Chang <chinwen.chang@mediatek.com> Cc: David Rientjes <rientjes@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Michal Koutn" <mkoutny@suse.com> Cc: Michel Lespinasse <walken@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shawn Anastasio <shawn@anastas.io> Cc: Steven Price <steven.price@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/uapi')
-rw-r--r--include/uapi/linux/userfaultfd.h21
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.
*/