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 <dsahern@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20200529220716.75383-4-dsahern@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 90f11760bd122c5b93f94d917f2d12a937a34c9c..d540229594910294e8e8a539659e2d6089ca8bfe 100644 (file)
--- a/include/net/xdp.h
+++ b/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*/
 };
 

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f1e364d69007bf16eef09086f151db883178ee7b..f862a58fb567302f84fd782b1e581f8a2fbfc94d 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/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 {

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 0089d56617ecb32894abcb42fccb63400e06774b..c04fb1c72f5e8bb9333af337ae1f41208f79b0cc 100644 (file)
--- a/kernel/bpf/devmap.c
+++ b/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:

diff --git a/net/core/filter.c b/net/core/filter.c
index 0008b029d6446c35ab1cf9a4e23542147adabb99..85ff827aab73b15b230bc969031d3bee51bbaeca 100644 (file)
--- a/net/core/filter.c
+++ b/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;

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 65d7717bce2f4ddebc47a305a4c6783add204387..f74bc4a2385e0d908440f8664da9300a28cc87f6 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/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 {