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>
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ba35caf..14f9228 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1487,6 +1487,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
+ /* CONTINUE ioctl is only supported for MINOR ranges. */
+ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR))
+ ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE);
+
/*
* Now that we scanned all vmas we can already tell
* userland which ioctls methods are guaranteed to
@@ -1840,6 +1844,66 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
return ret;
}
+static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
+{
+ __s64 ret;
+ struct uffdio_continue uffdio_continue;
+ struct uffdio_continue __user *user_uffdio_continue;
+ struct userfaultfd_wake_range range;
+
+ user_uffdio_continue = (struct uffdio_continue __user *)arg;
+
+ ret = -EAGAIN;
+ if (READ_ONCE(ctx->mmap_changing))
+ goto out;
+
+ ret = -EFAULT;
+ if (copy_from_user(&uffdio_continue, user_uffdio_continue,
+ /* don't copy the output fields */
+ sizeof(uffdio_continue) - (sizeof(__s64))))
+ goto out;
+
+ ret = validate_range(ctx->mm, &uffdio_continue.range.start,
+ uffdio_continue.range.len);
+ if (ret)
+ goto out;
+
+ ret = -EINVAL;
+ /* double check for wraparound just in case. */
+ if (uffdio_continue.range.start + uffdio_continue.range.len <=
+ uffdio_continue.range.start) {
+ goto out;
+ }
+ if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE)
+ goto out;
+
+ if (mmget_not_zero(ctx->mm)) {
+ ret = mcopy_continue(ctx->mm, uffdio_continue.range.start,
+ uffdio_continue.range.len,
+ &ctx->mmap_changing);
+ mmput(ctx->mm);
+ } else {
+ return -ESRCH;
+ }
+
+ if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+ return -EFAULT;
+ if (ret < 0)
+ goto out;
+
+ /* len == 0 would wake all */
+ BUG_ON(!ret);
+ range.len = ret;
+ if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) {
+ range.start = uffdio_continue.range.start;
+ wake_userfault(ctx, &range);
+ }
+ ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN;
+
+out:
+ return ret;
+}
+
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
@@ -1927,6 +1991,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
case UFFDIO_WRITEPROTECT:
ret = userfaultfd_writeprotect(ctx, arg);
break;
+ case UFFDIO_CONTINUE:
+ ret = userfaultfd_continue(ctx, arg);
+ break;
}
return ret;
}