xdp: Add xdp_txq_info to xdp_buff

Add xdp_txq_info as the Tx counterpart to xdp_rxq_info. At the
moment only the device is added. Other fields (queue_index)
can be added as use cases arise.

>From a UAPI perspective, add egress_ifindex to xdp context for
bpf programs to see the Tx device.

Update the verifier to only allow accesses to egress_ifindex by
XDP programs with BPF_XDP_DEVMAP expected attach type.

Signed-off-by: David Ahern <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: dsahern

include/net/xdp.h

@@ -61,12 +61,17 @@ struct xdp_rxq_info {
 	struct xdp_mem_info mem;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 
+struct xdp_txq_info {
+	struct net_device *dev;
+};
+
 struct xdp_buff {
 	void *data;
 	void *data_end;
 	void *data_meta;
 	void *data_hard_start;
 	struct xdp_rxq_info *rxq;
+	struct xdp_txq_info *txq;
 	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
 };
 

include/uapi/linux/bpf.h

@@ -3707,6 +3707,8 @@ struct xdp_md {
 	/* Below access go through struct xdp_rxq_info */
 	__u32 ingress_ifindex; /* rxq->dev->ifindex */
 	__u32 rx_queue_index;  /* rxq->queue_index  */
+
+	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
 enum sk_action {

kernel/bpf/devmap.c

@@ -476,8 +476,11 @@ static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
 					 struct xdp_buff *xdp,
 					 struct bpf_prog *xdp_prog)
 {
+	struct xdp_txq_info txq = { .dev = dev };
 	u32 act;
 
+	xdp->txq = &txq;
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:

net/core/filter.c

@@ -7015,6 +7015,13 @@ static bool xdp_is_valid_access(int off, int size,
 				const struct bpf_prog *prog,
 				struct bpf_insn_access_aux *info)
 {
+	if (prog->expected_attach_type != BPF_XDP_DEVMAP) {
+		switch (off) {
+		case offsetof(struct xdp_md, egress_ifindex):
+			return false;
+		}
+	}
+
 	if (type == BPF_WRITE) {
 		if (bpf_prog_is_dev_bound(prog->aux)) {
 			switch (off) {
@@ -7985,6 +7992,16 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(struct xdp_rxq_info,
 					       queue_index));
 		break;
+	case offsetof(struct xdp_md, egress_ifindex):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, txq));
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct xdp_txq_info, dev));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct net_device, ifindex));
+		break;
 	}
 
 	return insn - insn_buf;

tools/include/uapi/linux/bpf.h

@@ -3706,6 +3706,8 @@ struct xdp_md {
 	/* Below access go through struct xdp_rxq_info */
 	__u32 ingress_ifindex; /* rxq->dev->ifindex */
 	__u32 rx_queue_index;  /* rxq->queue_index  */
+
+	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
 enum sk_action {