[PATCH] RDMA/core: Use flexible array for mad data

In preparation for FORTIFY_SOURCE performing compile-time and run-time
field bounds checking for memcpy(), memmove(), and memset(), avoid
intentionally read across neighboring array fields.

Without a flexible array, this looks like an attempt to perform a
memcpy() read beyond the end of the packet->mad.data array:

drivers/infiniband/core/user_mad.c:
	memcpy(packet->msg->mad, packet->mad.data, IB_MGMT_MAD_HDR);

Switch from [0] to [] to use the appropriately handled type for trailing
bytes.

Signed-off-by: Kees Cook <redacted>
---
 include/uapi/rdma/ib_user_mad.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/rdma/ib_user_mad.h b/include/uapi/rdma/ib_user_mad.h
index 90c0cf228020..10b5f6a4c677 100644
--- a/include/uapi/rdma/ib_user_mad.h
+++ b/include/uapi/rdma/ib_user_mad.h

@@ -143,7 +143,7 @@ struct ib_user_mad_hdr {
  */
 struct ib_user_mad {
 	struct ib_user_mad_hdr hdr;
-	__aligned_u64	data[0];
+	__aligned_u64	data[];
 };
 
 /*

-- 
2.25.1

On Wed, Jun 16, 2021 at 01:26:15PM -0700, Kees Cook wrote:

In preparation for FORTIFY_SOURCE performing compile-time and run-time
field bounds checking for memcpy(), memmove(), and memset(), avoid
intentionally read across neighboring array fields.

Without a flexible array, this looks like an attempt to perform a
memcpy() read beyond the end of the packet->mad.data array:

drivers/infiniband/core/user_mad.c:
	memcpy(packet->msg->mad, packet->mad.data, IB_MGMT_MAD_HDR);

Switch from [0] to [] to use the appropriately handled type for trailing
bytes.

Signed-off-by: Kees Cook <redacted>
---
 include/uapi/rdma/ib_user_mad.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Applied to for-next, thanks

Jason