@@ -3839,6 +3839,69 @@ union bpf_attr {
* Return
* A pointer to a struct socket on success or NULL if the file is
* not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ * Description
+
+ * Check ctx packet size against exceeding MTU of net device (based
+ * on *ifindex*). This helper will likely be used in combination
+ * with helpers that adjust/change the packet size.
+ *
+ * The argument *len_diff* can be used for querying with a planned
+ * size change. This allows to check MTU prior to changing packet
+ * ctx. Providing an *len_diff* adjustment that is larger than the
+ * actual packet size (resulting in negative packet size) will in
+ * principle not exceed the MTU, why it is not considered a
+ * failure. Other BPF-helpers are needed for performing the
+ * planned size change, why the responsability for catch a negative
+ * packet size belong in those helpers.
+ *
+ * Specifying *ifindex* zero means the MTU check is performed
+ * against the current net device. This is practical if this isn't
+ * used prior to redirect.
+ *
+ * The Linux kernel route table can configure MTUs on a more
+ * specific per route level, which is not provided by this helper.
+ * For route level MTU checks use the **bpf_fib_lookup**\ ()
+ * helper.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** for tc cls_act programs.
+ *
+ * The *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_MTU_CHK_SEGS**
+ * This flag will only works for *ctx* **struct sk_buff**.
+ * If packet context contains extra packet segment buffers
+ * (often knows as GSO skb), then MTU check is harder to
+ * check at this point, because in transmit path it is
+ * possible for the skb packet to get re-segmented
+ * (depending on net device features). This could still be
+ * a MTU violation, so this flag enables performing MTU
+ * check against segments, with a different violation
+ * return code to tell it apart. Check cannot use len_diff.
+ *
+ * On return *mtu_len* pointer contains the MTU value of the net
+ * device. Remember the net device configured MTU is the L3 size,
+ * which is returned here and XDP and TX length operate at L2.
+ * Helper take this into account for you, but remember when using
+ * MTU value in your BPF-code. On input *mtu_len* must be a valid
+ * pointer and be initialized (to zero), else verifier will reject
+ * BPF program.
+ *
+ * Return
+ * * 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ * * < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ * MTU violations return positive values, but also populate MTU
+ * value in *mtu_len* pointer, as this can be needed for
+ * implementing PMTU handing:
+ *
+ * * **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ * * **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -4004,6 +4067,7 @@ union bpf_attr {
FN(ktime_get_coarse_ns), \
FN(ima_inode_hash), \
FN(sock_from_file), \
+ FN(check_mtu), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5036,6 +5100,17 @@ struct bpf_redir_neigh {
};
};
+/* bpf_check_mtu flags*/
+enum bpf_check_mtu_flags {
+ BPF_MTU_CHK_SEGS = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+ BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */
+ BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */
+};
+
enum bpf_task_fd_type {
BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
BPF_FD_TYPE_TRACEPOINT, /* tp name */
@@ -5625,6 +5625,116 @@ static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
.arg4_type = ARG_ANYTHING,
};
+static struct net_device *__dev_via_ifindex(struct net_device *dev_curr,
+ u32 ifindex)
+{
+ struct net *netns = dev_net(dev_curr);
+
+ /* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */
+ if (ifindex == 0)
+ return dev_curr;
+
+ return dev_get_by_index_rcu(netns, ifindex);
+}
+
+BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
+ u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags)
+{
+ int ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+ struct net_device *dev = skb->dev;
+ int skb_len, dev_len;
+ int mtu;
+
+ if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
+ return -EINVAL;
+
+ if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+ return -EINVAL;
+
+ dev = __dev_via_ifindex(dev, ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ mtu = READ_ONCE(dev->mtu);
+
+ dev_len = mtu + dev->hard_header_len;
+ skb_len = skb->len + len_diff; /* minus result pass check */
+ if (skb_len <= dev_len) {
+ ret = BPF_MTU_CHK_RET_SUCCESS;
+ goto out;
+ }
+ /* At this point, skb->len exceed MTU, but as it include length of all
+ * segments, it can still be below MTU. The SKB can possibly get
+ * re-segmented in transmit path (see validate_xmit_skb). Thus, user
+ * must choose if segs are to be MTU checked.
+ */
+ if (skb_is_gso(skb)) {
+ ret = BPF_MTU_CHK_RET_SUCCESS;
+
+ if (flags & BPF_MTU_CHK_SEGS &&
+ !skb_gso_validate_network_len(skb, mtu))
+ ret = BPF_MTU_CHK_RET_SEGS_TOOBIG;
+ }
+out:
+ /* BPF verifier guarantees valid pointer */
+ *mtu_len = mtu;
+
+ return ret;
+}
+
+BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
+ u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags)
+{
+ struct net_device *dev = xdp->rxq->dev;
+ int xdp_len = xdp->data_end - xdp->data;
+ int ret = BPF_MTU_CHK_RET_SUCCESS;
+ int mtu, dev_len;
+
+ /* XDP variant doesn't support multi-buffer segment check (yet) */
+ if (unlikely(flags))
+ return -EINVAL;
+
+ dev = __dev_via_ifindex(dev, ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ mtu = READ_ONCE(dev->mtu);
+
+ /* Add L2-header as dev MTU is L3 size */
+ dev_len = mtu + dev->hard_header_len;
+
+ xdp_len += len_diff; /* minus result pass check */
+ if (xdp_len > dev_len)
+ ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+
+ /* BPF verifier guarantees valid pointer */
+ *mtu_len = mtu;
+
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
+ .func = bpf_skb_check_mtu,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_INT,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
+ .func = bpf_xdp_check_mtu,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_INT,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
{
@@ -7210,6 +7320,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_socket_uid_proto;
case BPF_FUNC_fib_lookup:
return &bpf_skb_fib_lookup_proto;
+ case BPF_FUNC_check_mtu:
+ return &bpf_skb_check_mtu_proto;
case BPF_FUNC_sk_fullsock:
return &bpf_sk_fullsock_proto;
case BPF_FUNC_sk_storage_get:
@@ -7279,6 +7391,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_xdp_adjust_tail_proto;
case BPF_FUNC_fib_lookup:
return &bpf_xdp_fib_lookup_proto;
+ case BPF_FUNC_check_mtu:
+ return &bpf_xdp_check_mtu_proto;
#ifdef CONFIG_INET
case BPF_FUNC_sk_lookup_udp:
return &bpf_xdp_sk_lookup_udp_proto;
@@ -3839,6 +3839,69 @@ union bpf_attr {
* Return
* A pointer to a struct socket on success or NULL if the file is
* not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ * Description
+
+ * Check ctx packet size against exceeding MTU of net device (based
+ * on *ifindex*). This helper will likely be used in combination
+ * with helpers that adjust/change the packet size.
+ *
+ * The argument *len_diff* can be used for querying with a planned
+ * size change. This allows to check MTU prior to changing packet
+ * ctx. Providing an *len_diff* adjustment that is larger than the
+ * actual packet size (resulting in negative packet size) will in
+ * principle not exceed the MTU, why it is not considered a
+ * failure. Other BPF-helpers are needed for performing the
+ * planned size change, why the responsability for catch a negative
+ * packet size belong in those helpers.
+ *
+ * Specifying *ifindex* zero means the MTU check is performed
+ * against the current net device. This is practical if this isn't
+ * used prior to redirect.
+ *
+ * The Linux kernel route table can configure MTUs on a more
+ * specific per route level, which is not provided by this helper.
+ * For route level MTU checks use the **bpf_fib_lookup**\ ()
+ * helper.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** for tc cls_act programs.
+ *
+ * The *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_MTU_CHK_SEGS**
+ * This flag will only works for *ctx* **struct sk_buff**.
+ * If packet context contains extra packet segment buffers
+ * (often knows as GSO skb), then MTU check is harder to
+ * check at this point, because in transmit path it is
+ * possible for the skb packet to get re-segmented
+ * (depending on net device features). This could still be
+ * a MTU violation, so this flag enables performing MTU
+ * check against segments, with a different violation
+ * return code to tell it apart. Check cannot use len_diff.
+ *
+ * On return *mtu_len* pointer contains the MTU value of the net
+ * device. Remember the net device configured MTU is the L3 size,
+ * which is returned here and XDP and TX length operate at L2.
+ * Helper take this into account for you, but remember when using
+ * MTU value in your BPF-code. On input *mtu_len* must be a valid
+ * pointer and be initialized (to zero), else verifier will reject
+ * BPF program.
+ *
+ * Return
+ * * 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ * * < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ * MTU violations return positive values, but also populate MTU
+ * value in *mtu_len* pointer, as this can be needed for
+ * implementing PMTU handing:
+ *
+ * * **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ * * **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -4004,6 +4067,7 @@ union bpf_attr {
FN(ktime_get_coarse_ns), \
FN(ima_inode_hash), \
FN(sock_from_file), \
+ FN(check_mtu), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5036,6 +5100,17 @@ struct bpf_redir_neigh {
};
};
+/* bpf_check_mtu flags*/
+enum bpf_check_mtu_flags {
+ BPF_MTU_CHK_SEGS = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+ BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */
+ BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */
+};
+
enum bpf_task_fd_type {
BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
BPF_FD_TYPE_TRACEPOINT, /* tp name */