iov_iter: add copy_page_to_iter_nofault()

Provide a means to copy a page to user space from an iterator, aborting if
a page fault would occur.  This supports compound pages, but may be passed
a tail page with an offset extending further into the compound page, so we
cannot pass a folio.

This allows for this function to be called from atomic context and _try_
to user pages if they are faulted in, aborting if not.

The function does not use _copy_to_iter() in order to not specify
might_fault(), this is similar to copy_page_from_iter_atomic().

This is being added in order that an iteratable form of vread() can be
implemented while holding spinlocks.

Link: https://lkml.kernel.org/r/19734729defb0f498a76bdec1bef3ac48a3af3e8.1679511146.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/uio.h

@@ -173,6 +173,8 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset,
 {
 	return copy_page_to_iter(&folio->page, offset, bytes, i);
 }
+size_t copy_page_to_iter_nofault(struct page *page, unsigned offset,
+				 size_t bytes, struct iov_iter *i);
 
 static __always_inline __must_check
 size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)

lib/iov_iter.c

@@ -172,6 +172,18 @@ static int copyout(void __user *to, const void *from, size_t n)
 	return n;
 }
 
+static int copyout_nofault(void __user *to, const void *from, size_t n)
+{
+	long res;
+
+	if (should_fail_usercopy())
+		return n;
+
+	res = copy_to_user_nofault(to, from, n);
+
+	return res < 0 ? n : res;
+}
+
 static int copyin(void *to, const void __user *from, size_t n)
 {
 	size_t res = n;
@@ -734,6 +746,42 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 }
 EXPORT_SYMBOL(copy_page_to_iter);
 
+size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes,
+				 struct iov_iter *i)
+{
+	size_t res = 0;
+
+	if (!page_copy_sane(page, offset, bytes))
+		return 0;
+	if (WARN_ON_ONCE(i->data_source))
+		return 0;
+	if (unlikely(iov_iter_is_pipe(i)))
+		return copy_page_to_iter_pipe(page, offset, bytes, i);
+	page += offset / PAGE_SIZE; // first subpage
+	offset %= PAGE_SIZE;
+	while (1) {
+		void *kaddr = kmap_local_page(page);
+		size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
+
+		iterate_and_advance(i, n, base, len, off,
+			copyout_nofault(base, kaddr + offset + off, len),
+			memcpy(base, kaddr + offset + off, len)
+		)
+		kunmap_local(kaddr);
+		res += n;
+		bytes -= n;
+		if (!bytes || !n)
+			break;
+		offset += n;
+		if (offset == PAGE_SIZE) {
+			page++;
+			offset = 0;
+		}
+	}
+	return res;
+}
+EXPORT_SYMBOL(copy_page_to_iter_nofault);
+
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {