[PATCH v3 12/13] epoll: support mapping for epfd when polled from userspace

[Roman Penyaev <rpenyaev@suse.de>]

User has to mmap user_header and user_index vmalloce'd pointers in order
to consume events from userspace.  Also we do not let any copies of vma
on fork().

Signed-off-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 20c94587488f..9ff666ce7cb5 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1276,11 +1276,47 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f)
 }
 #endif
 
+static int ep_eventpoll_mmap(struct file *filep, struct vm_area_struct *vma)
+{
+	struct eventpoll *ep = vma->vm_file->private_data;
+	size_t size;
+	int rc;
+
+	if (!ep_polled_by_user(ep))
+		return -ENOTSUPP;
+
+	size = vma->vm_end - vma->vm_start;
+	if (!vma->vm_pgoff && size > ep->header_length)
+		return -ENXIO;
+	if (vma->vm_pgoff && ep->header_length != (vma->vm_pgoff << PAGE_SHIFT))
+		/* Index ring starts exactly after the header */
+		return -ENXIO;
+	if (vma->vm_pgoff && size > ep->index_length)
+		return -ENXIO;
+
+	/*
+	 * vm_pgoff is used *only* for indication, what is mapped: user header
+	 * or user index ring.  Sizes are checked above.
+	 */
+	if (!vma->vm_pgoff)
+		rc = remap_vmalloc_range_partial(vma, vma->vm_start,
+						 ep->user_header, size);
+	else
+		rc = remap_vmalloc_range_partial(vma, vma->vm_start,
+						 ep->user_index, size);
+	if (likely(!rc))
+		/* No copies for forks(), please */
+		vma->vm_flags |= VM_DONTCOPY;
+
+	return rc;
+}
+
 /* File callbacks that implement the eventpoll file behaviour */
 static const struct file_operations eventpoll_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= ep_show_fdinfo,
 #endif
+	.mmap		= ep_eventpoll_mmap,
 	.release	= ep_eventpoll_release,
 	.poll		= ep_eventpoll_poll,
 	.llseek		= noop_llseek,
-- 
2.21.0