Date:   Fri, 23 Mar 2018 10:16:03 +0000
From:   Mathieu Xhonneux <m.xhonneux@...il.com>
To:     netdev@...r.kernel.org
Cc:     dlebrun@...gle.com
Subject: [PATCH net-next RFC 4/5] ipv6: sr: Add seg6local action End.BPF

This patch adds the End.BPF action to the LWT seg6local infrastructure.
This action works like any other seg6local End action, meaning that an IPv6
header with SRH is needed, whose DA has to be equal to the SID of the
action. It will also advance the SRH to the next segment, the BPF program
doesn’t have to take care of this.

Since the BPF program may not be a source of instability in the kernel, it
is important to ensure that the integrity of the packet is maintained
before yielding it back to the IPv6 layer. The hook hence keeps track if
the SRH has been altered through the helpers, and re-validates its
content if needed with seg6_validate_srh. The state kept for validation is
stored in skb->cb, read and write access to it from the BPF program is
prohibited. The BPF program is not allowed to directly write into the
packet, and only some fields of the SRH can be altered through the helper
bpf_lwt_seg6_store_bytes.

Performances profiling has shown that the SRH re-validation doesn’t induce
a significant overhead. If the altered SRH is deemed as invalid, the packet
is dropped.

This validation is also done before executing any action through
bpf_lwt_seg6_action, and won’t be performed again if the SRH isn’t modified
after calling the action.

The BPF program may return 3 types of return codes :
    - BPF_OK: the End.BPF action will look up the next destination through
             seg6_lookup_nexthop.
    - BPF_REDIRECT: if an action has been executed through the
          bpf_lwt_seg6_action helper, the BPF program should return this
          value, as the skb destination is already set and the default
          lookup shouldn’t be performed.
    - BPF_DROP : the packet will be dropped.

Signed-off-by: Mathieu Xhonneux <m.xhonneux@...il.com>
Acked-by: David Lebrun <dlebrun@...gle.com>
---
 include/linux/bpf_types.h       |   1 +
 include/uapi/linux/bpf.h        |   1 +
 include/uapi/linux/seg6_local.h |   3 +
 kernel/bpf/verifier.c           |   1 +
 net/core/filter.c               |  37 ++++++++++
 net/ipv6/seg6_local.c           | 150 +++++++++++++++++++++++++++++++++++++++-
 6 files changed, 190 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 0f8f2525da9b..92bc613a3b59 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -11,6 +11,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
 BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in)
 BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out)
 BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local)
 BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops)
 BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb)
 BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f2679c29e353..2eeea4c4cc7f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -134,6 +134,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_SKB,
 	BPF_PROG_TYPE_CGROUP_DEVICE,
 	BPF_PROG_TYPE_SK_MSG,
+	BPF_PROG_TYPE_LWT_SEG6LOCAL,
 };
 
 enum bpf_attach_type {
diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h
index ef2d8c3e76c1..aadcc11fb918 100644
--- a/include/uapi/linux/seg6_local.h
+++ b/include/uapi/linux/seg6_local.h
@@ -25,6 +25,7 @@ enum {
 	SEG6_LOCAL_NH6,
 	SEG6_LOCAL_IIF,
 	SEG6_LOCAL_OIF,
+	SEG6_LOCAL_BPF,
 	__SEG6_LOCAL_MAX,
 };
 #define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1)
@@ -59,6 +60,8 @@ enum {
 	SEG6_LOCAL_ACTION_END_AS	= 13,
 	/* forward to SR-unaware VNF with masquerading */
 	SEG6_LOCAL_ACTION_END_AM	= 14,
+	/* custom BPF action */
+	SEG6_LOCAL_ACTION_END_BPF	= 15,
 
 	__SEG6_LOCAL_ACTION_MAX,
 };
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e9f7c20691c1..3c645ad33ac7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1239,6 +1239,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 	switch (env->prog->type) {
 	case BPF_PROG_TYPE_LWT_IN:
 	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
 		/* dst_input() and dst_output() can't write for now */
 		if (t == BPF_WRITE)
 			return false;
diff --git a/net/core/filter.c b/net/core/filter.c
index 741dd352937d..4b46d09dcddc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4094,6 +4094,19 @@ lwt_xmit_func_proto(enum bpf_func_id func_id)
 		return lwt_out_func_proto(func_id);
 	}
 }
+
+static const struct bpf_func_proto *
+lwt_seg6local_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_lwt_seg6_store_bytes:
+		return &bpf_lwt_seg6_store_bytes_proto;
+	case BPF_FUNC_lwt_seg6_action:
+		return &bpf_lwt_seg6_action_proto;
+	case BPF_FUNC_lwt_seg6_adjust_srh:
+		return &bpf_lwt_seg6_adjust_srh_proto;
+	default:
+		return lwt_out_func_proto(func_id);
 	}
 }
 
@@ -4198,6 +4211,20 @@ static bool lwt_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, info);
 }
 
+static bool lwt_seg6local_is_valid_access(int off, int size,
+					  enum bpf_access_type type,
+					  struct bpf_insn_access_aux *info)
+{
+	switch (off) {
+	case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
+		return false;
+	default:
+		break;
+	}
+
+	return lwt_is_valid_access(off, size, type, info);
+}
+
 static bool sock_filter_is_valid_access(int off, int size,
 					enum bpf_access_type type,
 					struct bpf_insn_access_aux *info)
@@ -5346,6 +5373,16 @@ const struct bpf_prog_ops lwt_xmit_prog_ops = {
 	.test_run		= bpf_prog_test_run_skb,
 };
 
+const struct bpf_verifier_ops lwt_seg6local_verifier_ops = {
+	.get_func_proto		= lwt_seg6local_func_proto,
+	.is_valid_access	= lwt_seg6local_is_valid_access,
+	.convert_ctx_access	= bpf_convert_ctx_access,
+};
+
+const struct bpf_prog_ops lwt_seg6local_prog_ops = {
+	.test_run		= bpf_prog_test_run_skb,
+};
+
 const struct bpf_verifier_ops cg_sock_verifier_ops = {
 	.get_func_proto		= sock_filter_func_proto,
 	.is_valid_access	= sock_filter_is_valid_access,
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index e9b23fb924ad..4805b7d404ed 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -1,8 +1,9 @@
 /*
  *  SR-IPv6 implementation
  *
- *  Author:
+ *  Authors:
  *  David Lebrun <david.lebrun@...ouvain.be>
+ *  eBPF support: Mathieu Xhonneux <m.xhonneux@...il.com>
  *
  *
  *  This program is free software; you can redistribute it and/or
@@ -32,6 +33,7 @@
 #endif
 #include <net/seg6_local.h>
 #include <linux/etherdevice.h>
+#include <linux/bpf.h>
 
 struct seg6_local_lwt;
 
@@ -42,6 +44,11 @@ struct seg6_action_desc {
 	int static_headroom;
 };
 
+struct bpf_lwt_prog {
+	struct bpf_prog *prog;
+	char *name;
+};
+
 struct seg6_local_lwt {
 	int action;
 	struct ipv6_sr_hdr *srh;
@@ -50,6 +57,7 @@ struct seg6_local_lwt {
 	struct in6_addr nh6;
 	int iif;
 	int oif;
+	struct bpf_lwt_prog bpf;
 
 	int headroom;
 	struct seg6_action_desc *desc;
@@ -449,6 +457,61 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
 	return err;
 }
 
+static int input_action_end_bpf(struct sk_buff *skb,
+				struct seg6_local_lwt *slwt)
+{
+	struct seg6_bpf_srh_state *srh_state = (struct seg6_bpf_srh_state *)
+					       &skb->cb;
+	struct ipv6_sr_hdr *srh;
+	int srhoff = 0;
+	int ret;
+
+	srh = get_and_validate_srh(skb);
+	if (!srh)
+		goto drop;
+
+	advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
+	srh_state->hdrlen = srh->hdrlen << 3;
+	srh_state->valid = 1;
+
+	rcu_read_lock();
+	bpf_compute_data_pointers(skb);
+	ret = bpf_prog_run_save_cb(slwt->bpf.prog, skb);
+	rcu_read_unlock();
+
+	switch (ret) {
+	case BPF_OK:
+	case BPF_REDIRECT:
+		break;
+	case BPF_DROP:
+		goto drop;
+	default:
+		pr_warn_once("bpf-seg6local: Illegal return value %u\n", ret);
+		goto drop;
+	}
+
+	if (unlikely((srh_state->hdrlen & 7) != 0))
+		goto drop;
+
+	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+		goto drop;
+	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
+	srh->hdrlen = (u8)(srh_state->hdrlen >> 3);
+
+	if (!srh_state->valid &&
+	    unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3)))
+		goto drop;
+
+	if (ret != BPF_REDIRECT)
+		seg6_lookup_nexthop(skb, NULL, 0);
+
+	return dst_input(skb);
+
+drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
 static struct seg6_action_desc seg6_action_table[] = {
 	{
 		.action		= SEG6_LOCAL_ACTION_END,
@@ -495,7 +558,13 @@ static struct seg6_action_desc seg6_action_table[] = {
 		.attrs		= (1 << SEG6_LOCAL_SRH),
 		.input		= input_action_end_b6_encap,
 		.static_headroom	= sizeof(struct ipv6hdr),
-	}
+	},
+	{
+		.action		= SEG6_LOCAL_ACTION_END_BPF,
+		.attrs		= (1 << SEG6_LOCAL_BPF),
+		.input		= input_action_end_bpf,
+	},
+
 };
 
 static struct seg6_action_desc *__get_action_desc(int action)
@@ -540,6 +609,7 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
 				    .len = sizeof(struct in6_addr) },
 	[SEG6_LOCAL_IIF]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_OIF]	= { .type = NLA_U32 },
+	[SEG6_LOCAL_BPF]	= { .type = NLA_NESTED },
 };
 
 static int parse_nla_srh(struct nlattr **attrs, struct seg6_local_lwt *slwt)
@@ -717,6 +787,71 @@ static int cmp_nla_oif(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
 	return 0;
 }
 
+#define MAX_PROG_NAME 256
+static const struct nla_policy bpf_prog_policy[LWT_BPF_PROG_MAX + 1] = {
+	[LWT_BPF_PROG_FD]   = { .type = NLA_U32, },
+	[LWT_BPF_PROG_NAME] = { .type = NLA_NUL_STRING,
+				.len = MAX_PROG_NAME },
+};
+
+static int parse_nla_bpf(struct nlattr **attrs, struct seg6_local_lwt *slwt)
+{
+	struct nlattr *tb[LWT_BPF_PROG_MAX + 1];
+	struct bpf_prog *p;
+	int ret;
+	u32 fd;
+
+	ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attrs[SEG6_LOCAL_BPF],
+			       bpf_prog_policy, NULL);
+	if (ret < 0)
+		return ret;
+
+	if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME])
+		return -EINVAL;
+
+	slwt->bpf.name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL);
+	if (!slwt->bpf.name)
+		return -ENOMEM;
+
+	fd = nla_get_u32(tb[LWT_BPF_PROG_FD]);
+	p = bpf_prog_get_type(fd, BPF_PROG_TYPE_LWT_SEG6LOCAL);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	slwt->bpf.prog = p;
+
+	return 0;
+}
+
+static int put_nla_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt)
+{
+	struct nlattr *nest;
+
+	if (!slwt->bpf.prog)
+		return 0;
+
+	nest = nla_nest_start(skb, SEG6_LOCAL_BPF);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (slwt->bpf.name &&
+	    nla_put_string(skb, LWT_BPF_PROG_NAME, slwt->bpf.name))
+		return -EMSGSIZE;
+
+	return nla_nest_end(skb, nest);
+}
+
+static int cmp_nla_bpf(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
+{
+	if (!a->bpf.name && !b->bpf.name)
+		return 0;
+
+	if (!a->bpf.name || !b->bpf.name)
+		return 1;
+
+	return strcmp(a->bpf.name, b->bpf.name);
+}
+
 struct seg6_action_param {
 	int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt);
 	int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
@@ -747,6 +882,11 @@ static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {
 	[SEG6_LOCAL_OIF]	= { .parse = parse_nla_oif,
 				    .put = put_nla_oif,
 				    .cmp = cmp_nla_oif },
+
+	[SEG6_LOCAL_BPF]	= { .parse = parse_nla_bpf,
+				    .put = put_nla_bpf,
+				    .cmp = cmp_nla_bpf },
+
 };
 
 static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
@@ -795,7 +935,6 @@ static int seg6_local_build_state(struct nlattr *nla, unsigned int family,
 
 	err = nla_parse_nested(tb, SEG6_LOCAL_MAX, nla, seg6_local_policy,
 			       extack);
-
 	if (err < 0)
 		return err;
 
@@ -884,6 +1023,11 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt)
 	if (attrs & (1 << SEG6_LOCAL_OIF))
 		nlsize += nla_total_size(4);
 
+	if (attrs & (1 << SEG6_LOCAL_BPF))
+		nlsize += nla_total_size(sizeof(struct nlattr)) +
+		       nla_total_size(MAX_PROG_NAME) +
+		       nla_total_size(4);
+
 	return nlsize;
 }
 
-- 
2.16.1

Powered by blists - more mailing lists