[net-next PATCH] bpf: reserve xdp_frame size in xdp headroom

[net-next PATCH] bpf: reserve xdp_frame size in xdp headroom

[Jesper Dangaard Brouer]

Commit 6dfb970d3dbd ("xdp: avoid leaking info stored in frame data on
page reuse") tried to allow user/bpf_prog to (re)use area used by
xdp_frame (stored in frame headroom), by memset clearing area when
bpf_xdp_adjust_head give bpf_prog access to headroom area.

The mentioned commit had two bugs. (1) Didn't take bpf_xdp_adjust_meta
into account. (2) a combination of bpf_xdp_adjust_head calls, where
xdp->data is moved into xdp_frame section, can cause clearing
xdp_frame area again for area previously granted to bpf_prog.

After discussions with Daniel, we choose to implement a simpler
solution to the problem, which is to reserve the headroom used by
xdp_frame info.

This also avoids the situation where bpf_prog is allowed to adjust/add
headers, and then XDP_REDIRECT later drops the packet due to lack of
headroom for the xdp_frame.  This would likely confuse the end-user.

Fixes: 6dfb970d3dbd ("xdp: avoid leaking info stored in frame data on page reuse")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 net/core/filter.c |   12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index a374b8560bc4..6398d2443f9f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2694,20 +2694,13 @@ BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
 {
 	void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame);
 	unsigned long metalen = xdp_get_metalen(xdp);
-	void *data_start = xdp->data_hard_start + metalen;
+	void *data_start = xdp_frame_end + metalen;
 	void *data = xdp->data + offset;
 
 	if (unlikely(data < data_start ||
 		     data > xdp->data_end - ETH_HLEN))
 		return -EINVAL;
 
-	/* Avoid info leak, when reusing area prev used by xdp_frame */
-	if (data < xdp_frame_end) {
-		unsigned long clearlen = xdp_frame_end - data;
-
-		memset(data, 0, clearlen);
-	}
-
 	if (metalen)
 		memmove(xdp->data_meta + offset,
 			xdp->data_meta, metalen);
@@ -2727,12 +2720,13 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 
 BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset)
 {
+	void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame);
 	void *meta = xdp->data_meta + offset;
 	unsigned long metalen = xdp->data - meta;
 
 	if (xdp_data_meta_unsupported(xdp))
 		return -ENOTSUPP;
-	if (unlikely(meta < xdp->data_hard_start ||
+	if (unlikely(meta < xdp_frame_end ||
 		     meta > xdp->data))
 		return -EINVAL;
 	if (unlikely((metalen & (sizeof(__u32) - 1)) ||

Re: [net-next PATCH] bpf: reserve xdp_frame size in xdp headroom

[Daniel Borkmann]

On 04/19/2018 04:17 PM, Jesper Dangaard Brouer wrote:
> Commit 6dfb970d3dbd ("xdp: avoid leaking info stored in frame data on
> page reuse") tried to allow user/bpf_prog to (re)use area used by
> xdp_frame (stored in frame headroom), by memset clearing area when
> bpf_xdp_adjust_head give bpf_prog access to headroom area.
> 
> The mentioned commit had two bugs. (1) Didn't take bpf_xdp_adjust_meta
> into account. (2) a combination of bpf_xdp_adjust_head calls, where
> xdp->data is moved into xdp_frame section, can cause clearing
> xdp_frame area again for area previously granted to bpf_prog.
> 
> After discussions with Daniel, we choose to implement a simpler
> solution to the problem, which is to reserve the headroom used by
> xdp_frame info.
> 
> This also avoids the situation where bpf_prog is allowed to adjust/add
> headers, and then XDP_REDIRECT later drops the packet due to lack of
> headroom for the xdp_frame.  This would likely confuse the end-user.
> 
> Fixes: 6dfb970d3dbd ("xdp: avoid leaking info stored in frame data on page reuse")
> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>

Applied to bpf-next, thanks Jesper!