iov_iter: Introduce fault_in_iov_iter_writeable

Introduce a new fault_in_iov_iter_writeable helper for safely faulting
in an iterator for writing.  Uses get_user_pages() to fault in the pages
without actually writing to them, which would be destructive.

We'll use fault_in_iov_iter_writeable in gfs2 once we've determined that
the iterator passed to .read_iter isn't in memory.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

1 files changed, 63 insertions, 0 deletions

diff --git a/mm/gup.c b/mm/gup.c
index a7efb027d6cf..795f15c410cc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1691,6 +1691,69 @@ out:
 }
 EXPORT_SYMBOL(fault_in_writeable);
 
+/*
+ * fault_in_safe_writeable - fault in an address range for writing
+ * @uaddr: start of address range
+ * @size: length of address range
+ *
+ * Faults in an address range using get_user_pages, i.e., without triggering
+ * hardware page faults.  This is primarily useful when we already know that
+ * some or all of the pages in the address range aren't in memory.
+ *
+ * Other than fault_in_writeable(), this function is non-destructive.
+ *
+ * Note that we don't pin or otherwise hold the pages referenced that we fault
+ * in.  There's no guarantee that they'll stay in memory for any duration of
+ * time.
+ *
+ * Returns the number of bytes not faulted in, like copy_to_user() and
+ * copy_from_user().
+ */
+size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
+{
+	unsigned long start = (unsigned long)untagged_addr(uaddr);
+	unsigned long end, nstart, nend;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma = NULL;
+	int locked = 0;
+
+	nstart = start & PAGE_MASK;
+	end = PAGE_ALIGN(start + size);
+	if (end < nstart)
+		end = 0;
+	for (; nstart != end; nstart = nend) {
+		unsigned long nr_pages;
+		long ret;
+
+		if (!locked) {
+			locked = 1;
+			mmap_read_lock(mm);
+			vma = find_vma(mm, nstart);
+		} else if (nstart >= vma->vm_end)
+			vma = vma->vm_next;
+		if (!vma || vma->vm_start >= end)
+			break;
+		nend = end ? min(end, vma->vm_end) : vma->vm_end;
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+			continue;
+		if (nstart < vma->vm_start)
+			nstart = vma->vm_start;
+		nr_pages = (nend - nstart) / PAGE_SIZE;
+		ret = __get_user_pages_locked(mm, nstart, nr_pages,
+					      NULL, NULL, &locked,
+					      FOLL_TOUCH | FOLL_WRITE);
+		if (ret <= 0)
+			break;
+		nend = nstart + ret * PAGE_SIZE;
+	}
+	if (locked)
+		mmap_read_unlock(mm);
+	if (nstart == end)
+		return 0;
+	return size - min_t(size_t, nstart - start, size);
+}
+EXPORT_SYMBOL(fault_in_safe_writeable);
+
 /**
  * fault_in_readable - fault in userspace address range for reading
  * @uaddr: start of user address range