Merge branch 'lwt-bpf'

Thomas Graf says:

====================
bpf: BPF for lightweight tunnel encapsulation

This series implements BPF program invocation from dst entries via the
lightweight tunnels infrastructure. The BPF program can be attached to
lwtunnel_input(), lwtunnel_output() or lwtunnel_xmit() and see an L3
skb as context. Programs attached to input and output are read-only.
Programs attached to lwtunnel_xmit() can modify and redirect, push headers
and redirect packets.

The facility can be used to:
 - Collect statistics and generate sampling data for a subset of traffic
   based on the dst utilized by the packet thus allowing to extend the
   existing realms.
 - Apply additional per route/dst filters to prohibit certain outgoing
   or incoming packets based on BPF filters. In particular, this allows
   to maintain per dst custom state across multiple packets in BPF maps
   and apply filters based on statistics and behaviour observed over time.
 - Attachment of L2 headers at transmit where resolving the L2 address
   is not required.
 - Possibly many more.

v3 -> v4:
 - Bumped LWT_BPF_MAX_HEADROOM from 128 to 256 (Alexei)
 - Renamed bpf_skb_push() helper to bpf_skb_change_head() to relate to
   existing bpf_skb_change_tail() helper (Alexei/Daniel)
 - Added check in __bpf_redirect_common() to verify that program added a
   link header before redirecting to a l2 device. Adding the check to
   lwt-bpf code was considered but dropped due to massive code required
   due to retrieval of net_device via per-cpu redirect buffer. A test
   case was added to cover the scenario when a program directs to an l2
   device without adding an appropriate l2 header.
   (Alexei)
 - Prohibited access to tc_classid (Daniel)
 - Collapsed bpf_verifier_ops instance for lwt in/out as they are
   identical (Daniel)
 - Some cosmetic changes

v2 -> v3:
 - Added real world sample lwt_len_hist_kern.c which demonstrates how to
   collect a histogram on packet sizes for all packets flowing through
   a number of routes.
 - Restricted output to be read-only. Since the header can no longer
   be modified, the rerouting functionality has been removed again.
 - Added test case which cover destructive modification of packet data.

v1 -> v2:
 - Added new BPF_LWT_REROUTE return code for program to indicate
   that new route lookup should be performed. Suggested by Tom.
 - New sample to illustrate rerouting
 - New patch 05: Recursion limit for lwtunnel_output for the case
   when user creates circular dst redirection. Also resolves the
   issue for ILA.
 - Fix to ensure headroom for potential future L2 header is still
   guaranteed
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/linux/filter.h

@@ -438,7 +438,7 @@ struct xdp_buff {
 };
 
 /* compute the linear packet data range [data, data_end) which
- * will be accessed by cls_bpf and act_bpf programs
+ * will be accessed by cls_bpf, act_bpf and lwt programs
  */
 static inline void bpf_compute_data_end(struct sk_buff *skb)
 {

include/uapi/linux/bpf.h

@@ -101,6 +101,9 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_XDP,
 	BPF_PROG_TYPE_PERF_EVENT,
 	BPF_PROG_TYPE_CGROUP_SKB,
+	BPF_PROG_TYPE_LWT_IN,
+	BPF_PROG_TYPE_LWT_OUT,
+	BPF_PROG_TYPE_LWT_XMIT,
 };
 
 enum bpf_attach_type {
@@ -409,6 +412,16 @@ union bpf_attr {
  *
  * int bpf_get_numa_node_id()
  *     Return: Id of current NUMA node.
+ *
+ * int bpf_skb_change_head()
+ *     Grows headroom of skb and adjusts MAC header offset accordingly.
+ *     Will extends/reallocae as required automatically.
+ *     May change skb data pointer and will thus invalidate any check
+ *     performed for direct packet access.
+ *     @skb: pointer to skb
+ *     @len: length of header to be pushed in front
+ *     @flags: Flags (unused for now)
+ *     Return: 0 on success or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -453,7 +466,8 @@ union bpf_attr {
 	FN(skb_pull_data),		\
 	FN(csum_update),		\
 	FN(set_hash_invalid),		\
-	FN(get_numa_node_id),
+	FN(get_numa_node_id),		\
+	FN(skb_change_head),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -537,6 +551,22 @@ struct bpf_tunnel_key {
 	__u32 tunnel_label;
 };
 
+/* Generic BPF return codes which all BPF program types may support.
+ * The values are binary compatible with their TC_ACT_* counter-part to
+ * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
+ * programs.
+ *
+ * XDP is handled seprately, see XDP_*.
+ */
+enum bpf_ret_code {
+	BPF_OK = 0,
+	/* 1 reserved */
+	BPF_DROP = 2,
+	/* 3-6 reserved */
+	BPF_REDIRECT = 7,
+	/* >127 are reserved for prog type specific return codes */
+};
+
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
  * return codes are reserved for future use. Unknown return codes will result

include/uapi/linux/lwtunnel.h

@@ -10,6 +10,7 @@ enum lwtunnel_encap_types {
 	LWTUNNEL_ENCAP_ILA,
 	LWTUNNEL_ENCAP_IP6,
 	LWTUNNEL_ENCAP_SEG6,
+	LWTUNNEL_ENCAP_BPF,
 	__LWTUNNEL_ENCAP_MAX,
 };
 
@@ -43,4 +44,26 @@ enum lwtunnel_ip6_t {
 
 #define LWTUNNEL_IP6_MAX (__LWTUNNEL_IP6_MAX - 1)
 
+enum {
+	LWT_BPF_PROG_UNSPEC,
+	LWT_BPF_PROG_FD,
+	LWT_BPF_PROG_NAME,
+	__LWT_BPF_PROG_MAX,
+};
+
+#define LWT_BPF_PROG_MAX (__LWT_BPF_PROG_MAX - 1)
+
+enum {
+	LWT_BPF_UNSPEC,
+	LWT_BPF_IN,
+	LWT_BPF_OUT,
+	LWT_BPF_XMIT,
+	LWT_BPF_XMIT_HEADROOM,
+	__LWT_BPF_MAX,
+};
+
+#define LWT_BPF_MAX (__LWT_BPF_MAX - 1)
+
+#define LWT_BPF_MAX_HEADROOM 256
+
 #endif /* _UAPI_LWTUNNEL_H_ */

kernel/bpf/verifier.c

@@ -633,12 +633,19 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 #define MAX_PACKET_OFF 0xffff
 
 static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
-				       const struct bpf_call_arg_meta *meta)
+				       const struct bpf_call_arg_meta *meta,
+				       enum bpf_access_type t)
 {
 	switch (env->prog->type) {
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_OUT:
+		/* dst_input() and dst_output() can't write for now */
+		if (t == BPF_WRITE)
+			return false;
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
 	case BPF_PROG_TYPE_XDP:
+	case BPF_PROG_TYPE_LWT_XMIT:
 		if (meta)
 			return meta->pkt_access;
 
@@ -837,7 +844,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 			err = check_stack_read(state, off, size, value_regno);
 		}
 	} else if (state->regs[regno].type == PTR_TO_PACKET) {
-		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL)) {
+		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
 			verbose("cannot write into packet\n");
 			return -EACCES;
 		}
@@ -970,7 +977,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		return 0;
 	}
 
-	if (type == PTR_TO_PACKET && !may_access_direct_pkt_data(env, meta)) {
+	if (type == PTR_TO_PACKET &&
+	    !may_access_direct_pkt_data(env, meta, BPF_READ)) {
 		verbose("helper access to the packet is not allowed\n");
 		return -EACCES;
 	}

net/Kconfig

@@ -402,6 +402,14 @@ config LWTUNNEL
 	  weight tunnel endpoint. Tunnel encapsulation parameters are stored
 	  with light weight tunnel state associated with fib routes.
 
+config LWTUNNEL_BPF
+	bool "Execute BPF program as route nexthop action"
+	depends on LWTUNNEL
+	default y if LWTUNNEL=y
+	---help---
+	  Allows to run BPF programs as a nexthop action following a route
+	  lookup for incoming and outgoing packets.
+
 config DST_CACHE
 	bool
 	default n

net/core/Makefile

@@ -24,6 +24,7 @@ obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
 obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
 obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
 obj-$(CONFIG_LWTUNNEL) += lwtunnel.o
+obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o
 obj-$(CONFIG_DST_CACHE) += dst_cache.o
 obj-$(CONFIG_HWBM) += hwbm.o
 obj-$(CONFIG_NET_DEVLINK) += devlink.o

net/core/filter.c

@@ -1689,6 +1689,12 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
 static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
 				 u32 flags)
 {
+	/* Verify that a link layer header is carried */
+	if (unlikely(skb->mac_header >= skb->network_header)) {
+		kfree_skb(skb);
+		return -ERANGE;
+	}
+
 	bpf_push_mac_rcsum(skb);
 	return flags & BPF_F_INGRESS ?
 	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
@@ -2188,12 +2194,53 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+	   u64, flags)
+{
+	u32 max_len = __bpf_skb_max_len(skb);
+	u32 new_len = skb->len + head_room;
+	int ret;
+
+	if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) ||
+		     new_len < skb->len))
+		return -EINVAL;
+
+	ret = skb_cow(skb, head_room);
+	if (likely(!ret)) {
+		/* Idea for this helper is that we currently only
+		 * allow to expand on mac header. This means that
+		 * skb->protocol network header, etc, stay as is.
+		 * Compared to bpf_skb_change_tail(), we're more
+		 * flexible due to not needing to linearize or
+		 * reset GSO. Intention for this helper is to be
+		 * used by an L3 skb that needs to push mac header
+		 * for redirection into L2 device.
+		 */
+		__skb_push(skb, head_room);
+		memset(skb->data, 0, head_room);
+		skb_reset_mac_header(skb);
+	}
+
+	bpf_compute_data_end(skb);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_skb_change_head_proto = {
+	.func		= bpf_skb_change_head,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 bool bpf_helper_changes_skb_data(void *func)
 {
 	if (func == bpf_skb_vlan_push ||
 	    func == bpf_skb_vlan_pop ||
 	    func == bpf_skb_store_bytes ||
 	    func == bpf_skb_change_proto ||
+	    func == bpf_skb_change_head ||
 	    func == bpf_skb_change_tail ||
 	    func == bpf_skb_pull_data ||
 	    func == bpf_l3_csum_replace ||
@@ -2639,6 +2686,68 @@ cg_skb_func_proto(enum bpf_func_id func_id)
 	}
 }
 
+static const struct bpf_func_proto *
+lwt_inout_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_skb_load_bytes:
+		return &bpf_skb_load_bytes_proto;
+	case BPF_FUNC_skb_pull_data:
+		return &bpf_skb_pull_data_proto;
+	case BPF_FUNC_csum_diff:
+		return &bpf_csum_diff_proto;
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_proto;
+	case BPF_FUNC_get_route_realm:
+		return &bpf_get_route_realm_proto;
+	case BPF_FUNC_get_hash_recalc:
+		return &bpf_get_hash_recalc_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_skb_event_output_proto;
+	case BPF_FUNC_get_smp_processor_id:
+		return &bpf_get_smp_processor_id_proto;
+	case BPF_FUNC_skb_under_cgroup:
+		return &bpf_skb_under_cgroup_proto;
+	default:
+		return sk_filter_func_proto(func_id);
+	}
+}
+
+static const struct bpf_func_proto *
+lwt_xmit_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_skb_get_tunnel_key:
+		return &bpf_skb_get_tunnel_key_proto;
+	case BPF_FUNC_skb_set_tunnel_key:
+		return bpf_get_skb_set_tunnel_proto(func_id);
+	case BPF_FUNC_skb_get_tunnel_opt:
+		return &bpf_skb_get_tunnel_opt_proto;
+	case BPF_FUNC_skb_set_tunnel_opt:
+		return bpf_get_skb_set_tunnel_proto(func_id);
+	case BPF_FUNC_redirect:
+		return &bpf_redirect_proto;
+	case BPF_FUNC_clone_redirect:
+		return &bpf_clone_redirect_proto;
+	case BPF_FUNC_skb_change_tail:
+		return &bpf_skb_change_tail_proto;
+	case BPF_FUNC_skb_change_head:
+		return &bpf_skb_change_head_proto;
+	case BPF_FUNC_skb_store_bytes:
+		return &bpf_skb_store_bytes_proto;
+	case BPF_FUNC_csum_update:
+		return &bpf_csum_update_proto;
+	case BPF_FUNC_l3_csum_replace:
+		return &bpf_l3_csum_replace_proto;
+	case BPF_FUNC_l4_csum_replace:
+		return &bpf_l4_csum_replace_proto;
+	case BPF_FUNC_set_hash_invalid:
+		return &bpf_set_hash_invalid_proto;
+	default:
+		return lwt_inout_func_proto(func_id);
+	}
+}
+
 static bool __is_valid_access(int off, int size, enum bpf_access_type type)
 {
 	if (off < 0 || off >= sizeof(struct __sk_buff))
@@ -2676,6 +2785,39 @@ static bool sk_filter_is_valid_access(int off, int size,
 	return __is_valid_access(off, size, type);
 }
 
+static bool lwt_is_valid_access(int off, int size,
+				enum bpf_access_type type,
+				enum bpf_reg_type *reg_type)
+{
+	switch (off) {
+	case offsetof(struct __sk_buff, tc_classid):
+		return false;
+	}
+
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case offsetof(struct __sk_buff, mark):
+		case offsetof(struct __sk_buff, priority):
+		case offsetof(struct __sk_buff, cb[0]) ...
+		     offsetof(struct __sk_buff, cb[4]):
+			break;
+		default:
+			return false;
+		}
+	}
+
+	switch (off) {
+	case offsetof(struct __sk_buff, data):
+		*reg_type = PTR_TO_PACKET;
+		break;
+	case offsetof(struct __sk_buff, data_end):
+		*reg_type = PTR_TO_PACKET_END;
+		break;
+	}
+
+	return __is_valid_access(off, size, type);
+}
+
 static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
 			       const struct bpf_prog *prog)
 {
@@ -3007,6 +3149,19 @@ static const struct bpf_verifier_ops cg_skb_ops = {
 	.convert_ctx_access	= sk_filter_convert_ctx_access,
 };
 
+static const struct bpf_verifier_ops lwt_inout_ops = {
+	.get_func_proto		= lwt_inout_func_proto,
+	.is_valid_access	= lwt_is_valid_access,
+	.convert_ctx_access	= sk_filter_convert_ctx_access,
+};
+
+static const struct bpf_verifier_ops lwt_xmit_ops = {
+	.get_func_proto		= lwt_xmit_func_proto,
+	.is_valid_access	= lwt_is_valid_access,
+	.convert_ctx_access	= sk_filter_convert_ctx_access,
+	.gen_prologue		= tc_cls_act_prologue,
+};
+
 static struct bpf_prog_type_list sk_filter_type __read_mostly = {
 	.ops	= &sk_filter_ops,
 	.type	= BPF_PROG_TYPE_SOCKET_FILTER,
@@ -3032,6 +3187,21 @@ static struct bpf_prog_type_list cg_skb_type __read_mostly = {
 	.type	= BPF_PROG_TYPE_CGROUP_SKB,
 };
 
+static struct bpf_prog_type_list lwt_in_type __read_mostly = {
+	.ops	= &lwt_inout_ops,
+	.type	= BPF_PROG_TYPE_LWT_IN,
+};
+
+static struct bpf_prog_type_list lwt_out_type __read_mostly = {
+	.ops	= &lwt_inout_ops,
+	.type	= BPF_PROG_TYPE_LWT_OUT,
+};
+
+static struct bpf_prog_type_list lwt_xmit_type __read_mostly = {
+	.ops	= &lwt_xmit_ops,
+	.type	= BPF_PROG_TYPE_LWT_XMIT,
+};
+
 static int __init register_sk_filter_ops(void)
 {
 	bpf_register_prog_type(&sk_filter_type);
@@ -3039,6 +3209,9 @@ static int __init register_sk_filter_ops(void)
 	bpf_register_prog_type(&sched_act_type);
 	bpf_register_prog_type(&xdp_type);
 	bpf_register_prog_type(&cg_skb_type);
+	bpf_register_prog_type(&lwt_in_type);
+	bpf_register_prog_type(&lwt_out_type);
+	bpf_register_prog_type(&lwt_xmit_type);
 
 	return 0;
 }

net/core/lwt_bpf.c

+/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <net/lwtunnel.h>
+
+struct bpf_lwt_prog {
+	struct bpf_prog *prog;
+	char *name;
+};
+
+struct bpf_lwt {
+	struct bpf_lwt_prog in;
+	struct bpf_lwt_prog out;
+	struct bpf_lwt_prog xmit;
+	int family;
+};
+
+#define MAX_PROG_NAME 256
+
+static inline struct bpf_lwt *bpf_lwt_lwtunnel(struct lwtunnel_state *lwt)
+{
+	return (struct bpf_lwt *)lwt->data;
+}
+
+#define NO_REDIRECT false
+#define CAN_REDIRECT true
+
+static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
+		       struct dst_entry *dst, bool can_redirect)
+{
+	int ret;
+
+	/* Preempt disable is needed to protect per-cpu redirect_info between
+	 * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and
+	 * access to maps strictly require a rcu_read_lock() for protection,
+	 * mixing with BH RCU lock doesn't work.
+	 */
+	preempt_disable();
+	rcu_read_lock();
+	bpf_compute_data_end(skb);
+	ret = bpf_prog_run_save_cb(lwt->prog, skb);
+	rcu_read_unlock();
+
+	switch (ret) {
+	case BPF_OK:
+		break;
+
+	case BPF_REDIRECT:
+		if (unlikely(!can_redirect)) {
+			pr_warn_once("Illegal redirect return code in prog %s\n",
+				     lwt->name ? : "<unknown>");
+			ret = BPF_OK;
+		} else {
+			ret = skb_do_redirect(skb);
+			if (ret == 0)
+				ret = BPF_REDIRECT;
+		}
+		break;
+
+	case BPF_DROP:
+		kfree_skb(skb);
+		ret = -EPERM;
+		break;
+
+	default:
+		pr_warn_once("bpf-lwt: Illegal return value %u, expect packet loss\n", ret);
+		kfree_skb(skb);
+		ret = -EINVAL;
+		break;
+	}
+
+	preempt_enable();
+
+	return ret;
+}
+
+static int bpf_input(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct bpf_lwt *bpf;
+	int ret;
+
+	bpf = bpf_lwt_lwtunnel(dst->lwtstate);
+	if (bpf->in.prog) {
+		ret = run_lwt_bpf(skb, &bpf->in, dst, NO_REDIRECT);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (unlikely(!dst->lwtstate->orig_input)) {
+		pr_warn_once("orig_input not set on dst for prog %s\n",
+			     bpf->out.name);
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	return dst->lwtstate->orig_input(skb);
+}
+
+static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct bpf_lwt *bpf;
+	int ret;
+
+	bpf = bpf_lwt_lwtunnel(dst->lwtstate);
+	if (bpf->out.prog) {
+		ret = run_lwt_bpf(skb, &bpf->out, dst, NO_REDIRECT);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (unlikely(!dst->lwtstate->orig_output)) {
+		pr_warn_once("orig_output not set on dst for prog %s\n",
+			     bpf->out.name);
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	return dst->lwtstate->orig_output(net, sk, skb);
+}
+
+static int xmit_check_hhlen(struct sk_buff *skb)
+{
+	int hh_len = skb_dst(skb)->dev->hard_header_len;
+
+	if (skb_headroom(skb) < hh_len) {
+		int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
+
+		if (pskb_expand_head(skb, nhead, 0, GFP_ATOMIC))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int bpf_xmit(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct bpf_lwt *bpf;
+
+	bpf = bpf_lwt_lwtunnel(dst->lwtstate);
+	if (bpf->xmit.prog) {
+		int ret;
+
+		ret = run_lwt_bpf(skb, &bpf->xmit, dst, CAN_REDIRECT);
+		switch (ret) {
+		case BPF_OK:
+			/* If the header was expanded, headroom might be too
+			 * small for L2 header to come, expand as needed.
+			 */
+			ret = xmit_check_hhlen(skb);
+			if (unlikely(ret))
+				return ret;
+
+			return LWTUNNEL_XMIT_CONTINUE;
+		case BPF_REDIRECT:
+			return LWTUNNEL_XMIT_DONE;
+		default:
+			return ret;
+		}
+	}
+
+	return LWTUNNEL_XMIT_CONTINUE;
+}
+
+static void bpf_lwt_prog_destroy(struct bpf_lwt_prog *prog)
+{
+	if (prog->prog)
+		bpf_prog_put(prog->prog);
+
+	kfree(prog->name);
+}
+
+static void bpf_destroy_state(struct lwtunnel_state *lwt)
+{
+	struct bpf_lwt *bpf = bpf_lwt_lwtunnel(lwt);
+
+	bpf_lwt_prog_destroy(&bpf->in);
+	bpf_lwt_prog_destroy(&bpf->out);
+	bpf_lwt_prog_destroy(&bpf->xmit);
+}
+
+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 bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
+			  enum bpf_prog_type type)
+{
+	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, attr, bpf_prog_policy);
+	if (ret < 0)
+		return ret;
+
+	if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME])
+		return -EINVAL;
+
+	prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL);
+	if (!prog->name)
+		return -ENOMEM;
+
+	fd = nla_get_u32(tb[LWT_BPF_PROG_FD]);
+	p = bpf_prog_get_type(fd, type);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	prog->prog = p;
+
+	return 0;
+}
+
+static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = {
+	[LWT_BPF_IN]		= { .type = NLA_NESTED, },
+	[LWT_BPF_OUT]		= { .type = NLA_NESTED, },
+	[LWT_BPF_XMIT]		= { .type = NLA_NESTED, },
+	[LWT_BPF_XMIT_HEADROOM]	= { .type = NLA_U32 },
+};
+
+static int bpf_build_state(struct net_device *dev, struct nlattr *nla,
+			   unsigned int family, const void *cfg,
+			   struct lwtunnel_state **ts)
+{
+	struct nlattr *tb[LWT_BPF_MAX + 1];
+	struct lwtunnel_state *newts;
+	struct bpf_lwt *bpf;
+	int ret;
+
+	if (family != AF_INET && family != AF_INET6)
+		return -EAFNOSUPPORT;
+
+	ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy);
+	if (ret < 0)
+		return ret;
+
+	if (!tb[LWT_BPF_IN] && !tb[LWT_BPF_OUT] && !tb[LWT_BPF_XMIT])
+		return -EINVAL;
+
+	newts = lwtunnel_state_alloc(sizeof(*bpf));
+	if (!newts)
+		return -ENOMEM;
+
+	newts->type = LWTUNNEL_ENCAP_BPF;
+	bpf = bpf_lwt_lwtunnel(newts);
+
+	if (tb[LWT_BPF_IN]) {
+		newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT;
+		ret = bpf_parse_prog(tb[LWT_BPF_IN], &bpf->in,
+				     BPF_PROG_TYPE_LWT_IN);
+		if (ret  < 0)
+			goto errout;
+	}
+
+	if (tb[LWT_BPF_OUT]) {
+		newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT;
+		ret = bpf_parse_prog(tb[LWT_BPF_OUT], &bpf->out,
+				     BPF_PROG_TYPE_LWT_OUT);
+		if (ret < 0)
+			goto errout;
+	}
+
+	if (tb[LWT_BPF_XMIT]) {
+		newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT;
+		ret = bpf_parse_prog(tb[LWT_BPF_XMIT], &bpf->xmit,
+				     BPF_PROG_TYPE_LWT_XMIT);
+		if (ret < 0)
+			goto errout;
+	}
+
+	if (tb[LWT_BPF_XMIT_HEADROOM]) {
+		u32 headroom = nla_get_u32(tb[LWT_BPF_XMIT_HEADROOM]);
+
+		if (headroom > LWT_BPF_MAX_HEADROOM) {
+			ret = -ERANGE;
+			goto errout;
+		}
+
+		newts->headroom = headroom;
+	}
+
+	bpf->family = family;
+	*ts = newts;
+
+	return 0;
+
+errout:
+	bpf_destroy_state(newts);
+	kfree(newts);
+	return ret;
+}
+
+static int bpf_fill_lwt_prog(struct sk_buff *skb, int attr,
+			     struct bpf_lwt_prog *prog)
+{
+	struct nlattr *nest;
+
+	if (!prog->prog)
+		return 0;
+
+	nest = nla_nest_start(skb, attr);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (prog->name &&
+	    nla_put_string(skb, LWT_BPF_PROG_NAME, prog->name))
+		return -EMSGSIZE;
+
+	return nla_nest_end(skb, nest);
+}
+
+static int bpf_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwt)
+{
+	struct bpf_lwt *bpf = bpf_lwt_lwtunnel(lwt);
+
+	if (bpf_fill_lwt_prog(skb, LWT_BPF_IN, &bpf->in) < 0 ||
+	    bpf_fill_lwt_prog(skb, LWT_BPF_OUT, &bpf->out) < 0 ||
+	    bpf_fill_lwt_prog(skb, LWT_BPF_XMIT, &bpf->xmit) < 0)
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int bpf_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+	int nest_len = nla_total_size(sizeof(struct nlattr)) +
+		       nla_total_size(MAX_PROG_NAME) + /* LWT_BPF_PROG_NAME */
+		       0;
+
+	return nest_len + /* LWT_BPF_IN */
+	       nest_len + /* LWT_BPF_OUT */
+	       nest_len + /* LWT_BPF_XMIT */
+	       0;
+}
+
+int bpf_lwt_prog_cmp(struct bpf_lwt_prog *a, struct bpf_lwt_prog *b)
+{
+	/* FIXME:
+	 * The LWT state is currently rebuilt for delete requests which
+	 * results in a new bpf_prog instance. Comparing names for now.
+	 */
+	if (!a->name && !b->name)
+		return 0;
+
+	if (!a->name || !b->name)
+		return 1;
+
+	return strcmp(a->name, b->name);
+}
+
+static int bpf_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+	struct bpf_lwt *a_bpf = bpf_lwt_lwtunnel(a);
+	struct bpf_lwt *b_bpf = bpf_lwt_lwtunnel(b);
+
+	return bpf_lwt_prog_cmp(&a_bpf->in, &b_bpf->in) ||
+	       bpf_lwt_prog_cmp(&a_bpf->out, &b_bpf->out) ||
+	       bpf_lwt_prog_cmp(&a_bpf->xmit, &b_bpf->xmit);
+}
+
+static const struct lwtunnel_encap_ops bpf_encap_ops = {
+	.build_state	= bpf_build_state,
+	.destroy_state	= bpf_destroy_state,
+	.input		= bpf_input,
+	.output		= bpf_output,
+	.xmit		= bpf_xmit,
+	.fill_encap	= bpf_fill_encap_info,
+	.get_encap_size = bpf_encap_nlsize,
+	.cmp_encap	= bpf_encap_cmp,
+};
+
+static int __init bpf_lwt_init(void)
+{
+	return lwtunnel_encap_add_ops(&bpf_encap_ops, LWTUNNEL_ENCAP_BPF);
+}
+
+subsys_initcall(bpf_lwt_init)

net/core/lwtunnel.c

@@ -41,6 +41,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
 		return "ILA";
 	case LWTUNNEL_ENCAP_SEG6:
 		return "SEG6";
+	case LWTUNNEL_ENCAP_BPF:
+		return "BPF";
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
 	case LWTUNNEL_ENCAP_NONE:

net/ipv4/route.c

@@ -1603,6 +1603,19 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 	spin_unlock_bh(&fnhe_lock);
 }
 
+static void set_lwt_redirect(struct rtable *rth)
+{
+	if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
+		rth->dst.lwtstate->orig_output = rth->dst.output;
+		rth->dst.output = lwtunnel_output;
+	}
+
+	if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
+		rth->dst.lwtstate->orig_input = rth->dst.input;
+		rth->dst.input = lwtunnel_input;
+	}
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1692,14 +1705,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->dst.input = ip_forward;
 
 	rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
-	if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
-		rth->dst.lwtstate->orig_output = rth->dst.output;
-		rth->dst.output = lwtunnel_output;
-	}
-	if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
-		rth->dst.lwtstate->orig_input = rth->dst.input;
-		rth->dst.input = lwtunnel_input;
-	}
+	set_lwt_redirect(rth);
 	skb_dst_set(skb, &rth->dst);
 out:
 	err = 0;
@@ -1926,8 +1932,18 @@ out:	return err;
 		rth->dst.error= -err;
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
+
 	if (do_cache) {
-		if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+		struct fib_nh *nh = &FIB_RES_NH(res);
+
+		rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate);
+		if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
+			WARN_ON(rth->dst.input == lwtunnel_input);
+			rth->dst.lwtstate->orig_input = rth->dst.input;
+			rth->dst.input = lwtunnel_input;
+		}
+
+		if (unlikely(!rt_cache_route(nh, rth))) {
 			rth->dst.flags |= DST_NOCACHE;
 			rt_add_uncached_list(rth);
 		}
@@ -2155,8 +2171,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	}
 
 	rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0);
-	if (lwtunnel_output_redirect(rth->dst.lwtstate))
-		rth->dst.output = lwtunnel_output;
+	set_lwt_redirect(rth);
 
 	return rth;
 }

samples/bpf/Makefile

@@ -29,6 +29,7 @@ hostprogs-y += test_current_task_under_cgroup
 hostprogs-y += trace_event
 hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
+hostprogs-y += lwt_len_hist
 
 test_lru_dist-objs := test_lru_dist.o libbpf.o
 sock_example-objs := sock_example.o libbpf.o
@@ -59,6 +60,7 @@ test_current_task_under_cgroup-objs := bpf_load.o libbpf.o \
 trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
 sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
 tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o
+lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -89,6 +91,7 @@ always += xdp2_kern.o
 always += test_current_task_under_cgroup_kern.o
 always += trace_event_kern.o
 always += sampleip_kern.o
+always += lwt_len_hist_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
@@ -117,6 +120,7 @@ HOSTLOADLIBES_test_current_task_under_cgroup += -lelf
 HOSTLOADLIBES_trace_event += -lelf
 HOSTLOADLIBES_sampleip += -lelf
 HOSTLOADLIBES_tc_l2_redirect += -l elf
+HOSTLOADLIBES_lwt_len_hist += -l elf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang

samples/bpf/bpf_helpers.h

@@ -80,6 +80,8 @@ struct bpf_map_def {
 	unsigned int map_flags;
 };
 
+static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
+	(void *) BPF_FUNC_skb_load_bytes;
 static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
 	(void *) BPF_FUNC_skb_store_bytes;
 static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
@@ -88,6 +90,8 @@ static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flag
 	(void *) BPF_FUNC_l4_csum_replace;
 static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
 	(void *) BPF_FUNC_skb_under_cgroup;
+static int (*bpf_skb_change_head)(void *, int len, int flags) =
+	(void *) BPF_FUNC_skb_change_head;
 
 #if defined(__x86_64__)
 

samples/bpf/lwt_len_hist.sh

+#!/bin/bash
+
+NS1=lwt_ns1
+VETH0=tst_lwt1a
+VETH1=tst_lwt1b
+
+TRACE_ROOT=/sys/kernel/debug/tracing
+
+function cleanup {
+	ip route del 192.168.253.2/32 dev $VETH0 2> /dev/null
+	ip link del $VETH0 2> /dev/null
+	ip link del $VETH1 2> /dev/null
+	ip netns exec $NS1 killall netserver
+	ip netns delete $NS1 2> /dev/null
+}
+
+cleanup
+
+ip netns add $NS1
+ip link add $VETH0 type veth peer name $VETH1
+ip link set dev $VETH0 up
+ip addr add 192.168.253.1/24 dev $VETH0
+ip link set $VETH1 netns $NS1
+ip netns exec $NS1 ip link set dev $VETH1 up
+ip netns exec $NS1 ip addr add 192.168.253.2/24 dev $VETH1
+ip netns exec $NS1 netserver
+
+echo 1 > ${TRACE_ROOT}/tracing_on
+cp /dev/null ${TRACE_ROOT}/trace
+ip route add 192.168.253.2/32 encap bpf out obj lwt_len_hist_kern.o section len_hist dev $VETH0
+netperf -H 192.168.253.2 -t TCP_STREAM
+cat ${TRACE_ROOT}/trace | grep -v '^#'
+./lwt_len_hist
+cleanup
+echo 0 > ${TRACE_ROOT}/tracing_on
+
+exit 0

samples/bpf/lwt_len_hist_kern.c

+/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/in.h>
+#include "bpf_helpers.h"
+
+# define printk(fmt, ...)						\
+		({							\
+			char ____fmt[] = fmt;				\
+			bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				     ##__VA_ARGS__);			\
+		})
+
+struct bpf_elf_map {
+	__u32 type;
+	__u32 size_key;
+	__u32 size_value;
+	__u32 max_elem;
+	__u32 flags;
+	__u32 id;
+	__u32 pinning;
+};
+
+struct bpf_elf_map SEC("maps") lwt_len_hist_map = {
+	.type = BPF_MAP_TYPE_PERCPU_HASH,
+	.size_key = sizeof(__u64),
+	.size_value = sizeof(__u64),
+	.pinning = 2,
+	.max_elem = 1024,
+};
+
+static unsigned int log2(unsigned int v)
+{
+	unsigned int r;
+	unsigned int shift;
+
+	r = (v > 0xFFFF) << 4; v >>= r;
+	shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
+	shift = (v > 0xF) << 2; v >>= shift; r |= shift;
+	shift = (v > 0x3) << 1; v >>= shift; r |= shift;
+	r |= (v >> 1);
+	return r;
+}
+
+static unsigned int log2l(unsigned long v)
+{
+	unsigned int hi = v >> 32;
+	if (hi)
+		return log2(hi) + 32;
+	else
+		return log2(v);
+}
+
+SEC("len_hist")
+int do_len_hist(struct __sk_buff *skb)
+{
+	__u64 *value, key, init_val = 1;
+
+	key = log2l(skb->len);
+
+	value = bpf_map_lookup_elem(&lwt_len_hist_map, &key);
+	if (value)
+		__sync_fetch_and_add(value, 1);
+	else
+		bpf_map_update_elem(&lwt_len_hist_map, &key, &init_val, BPF_ANY);
+
+	return BPF_OK;
+}
+
+char _license[] SEC("license") = "GPL";

samples/bpf/lwt_len_hist_user.c

+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <arpa/inet.h>
+
+#include "libbpf.h"
+#include "bpf_util.h"
+
+#define MAX_INDEX 64
+#define MAX_STARS 38
+
+static void stars(char *str, long val, long max, int width)
+{
+	int i;
+
+	for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++)
+		str[i] = '*';
+	if (val > max)
+		str[i - 1] = '+';
+	str[i] = '\0';
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	const char *map_filename = "/sys/fs/bpf/tc/globals/lwt_len_hist_map";
+	uint64_t values[nr_cpus], sum, max_value = 0, data[MAX_INDEX] = {};
+	uint64_t key = 0, next_key, max_key = 0;
+	char starstr[MAX_STARS];
+	int i, map_fd;
+
+	map_fd = bpf_obj_get(map_filename);
+	if (map_fd < 0) {
+		fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
+			map_filename, strerror(errno), errno);
+		return -1;
+	}
+
+	while (bpf_get_next_key(map_fd, &key, &next_key) == 0) {
+		if (next_key >= MAX_INDEX) {
+			fprintf(stderr, "Key %lu out of bounds\n", next_key);
+			continue;
+		}
+
+		bpf_lookup_elem(map_fd, &next_key, values);
+
+		sum = 0;
+		for (i = 0; i < nr_cpus; i++)
+			sum += values[i];
+
+		data[next_key] = sum;
+		if (sum && next_key > max_key)
+			max_key = next_key;
+
+		if (sum > max_value)
+			max_value = sum;
+
+		key = next_key;
+	}
+
+	for (i = 1; i <= max_key + 1; i++) {
+		stars(starstr, data[i - 1], max_value, MAX_STARS);
+		printf("%8ld -> %-8ld : %-8ld |%-*s|\n",
+		       (1l << i) >> 1, (1l << i) - 1, data[i - 1],
+		       MAX_STARS, starstr);
+	}
+
+	close(map_fd);
+
+	return 0;
+}

samples/bpf/test_lwt_bpf.c

+/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <stdint.h>
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/icmpv6.h>
+#include <linux/if_ether.h>
+#include "bpf_helpers.h"
+#include <string.h>
+
+# define printk(fmt, ...)						\
+		({							\
+			char ____fmt[] = fmt;				\
+			bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				     ##__VA_ARGS__);			\
+		})
+
+#define CB_MAGIC 1234
+
+/* Test: Pass all packets through */
+SEC("nop")
+int do_nop(struct __sk_buff *skb)
+{
+	return BPF_OK;
+}
+
+/* Test: Verify context information can be accessed */
+SEC("test_ctx")
+int do_test_ctx(struct __sk_buff *skb)
+{
+	skb->cb[0] = CB_MAGIC;
+	printk("len %d hash %d protocol %d\n", skb->len, skb->hash,
+	       skb->protocol);
+	printk("cb %d ingress_ifindex %d ifindex %d\n", skb->cb[0],
+	       skb->ingress_ifindex, skb->ifindex);
+
+	return BPF_OK;
+}
+
+/* Test: Ensure skb->cb[] buffer is cleared */
+SEC("test_cb")
+int do_test_cb(struct __sk_buff *skb)
+{
+	printk("cb0: %x cb1: %x cb2: %x\n", skb->cb[0], skb->cb[1],
+	       skb->cb[2]);
+	printk("cb3: %x cb4: %x\n", skb->cb[3], skb->cb[4]);
+
+	return BPF_OK;
+}
+
+/* Test: Verify skb data can be read */
+SEC("test_data")
+int do_test_data(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	void *data_end = (void *)(long)skb->data_end;
+	struct iphdr *iph = data;
+
+	if (data + sizeof(*iph) > data_end) {
+		printk("packet truncated\n");
+		return BPF_DROP;
+	}
+
+	printk("src: %x dst: %x\n", iph->saddr, iph->daddr);
+
+	return BPF_OK;
+}
+
+#define IP_CSUM_OFF offsetof(struct iphdr, check)
+#define IP_DST_OFF offsetof(struct iphdr, daddr)
+#define IP_SRC_OFF offsetof(struct iphdr, saddr)
+#define IP_PROTO_OFF offsetof(struct iphdr, protocol)
+#define TCP_CSUM_OFF offsetof(struct tcphdr, check)
+#define UDP_CSUM_OFF offsetof(struct udphdr, check)
+#define IS_PSEUDO 0x10
+
+static inline int rewrite(struct __sk_buff *skb, uint32_t old_ip,
+			  uint32_t new_ip, int rw_daddr)
+{
+	int ret, off = 0, flags = IS_PSEUDO;
+	uint8_t proto;
+
+	ret = bpf_skb_load_bytes(skb, IP_PROTO_OFF, &proto, 1);
+	if (ret < 0) {
+		printk("bpf_l4_csum_replace failed: %d\n", ret);
+		return BPF_DROP;
+	}
+
+	switch (proto) {
+	case IPPROTO_TCP:
+		off = TCP_CSUM_OFF;
+		break;
+
+	case IPPROTO_UDP:
+		off = UDP_CSUM_OFF;
+		flags |= BPF_F_MARK_MANGLED_0;
+		break;
+
+	case IPPROTO_ICMPV6:
+		off = offsetof(struct icmp6hdr, icmp6_cksum);
+		break;
+	}
+
+	if (off) {
+		ret = bpf_l4_csum_replace(skb, off, old_ip, new_ip,
+					  flags | sizeof(new_ip));
+		if (ret < 0) {
+			printk("bpf_l4_csum_replace failed: %d\n");
+			return BPF_DROP;
+		}
+	}
+
+	ret = bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip));
+	if (ret < 0) {
+		printk("bpf_l3_csum_replace failed: %d\n", ret);
+		return BPF_DROP;
+	}
+
+	if (rw_daddr)
+		ret = bpf_skb_store_bytes(skb, IP_DST_OFF, &new_ip, sizeof(new_ip), 0);
+	else
+		ret = bpf_skb_store_bytes(skb, IP_SRC_OFF, &new_ip, sizeof(new_ip), 0);
+
+	if (ret < 0) {
+		printk("bpf_skb_store_bytes() failed: %d\n", ret);
+		return BPF_DROP;
+	}
+
+	return BPF_OK;
+}
+
+/* Test: Verify skb data can be modified */
+SEC("test_rewrite")
+int do_test_rewrite(struct __sk_buff *skb)
+{
+	uint32_t old_ip, new_ip = 0x3fea8c0;
+	int ret;
+
+	ret = bpf_skb_load_bytes(skb, IP_DST_OFF, &old_ip, 4);
+	if (ret < 0) {
+		printk("bpf_skb_load_bytes failed: %d\n", ret);
+		return BPF_DROP;
+	}
+
+	if (old_ip == 0x2fea8c0) {
+		printk("out: rewriting from %x to %x\n", old_ip, new_ip);
+		return rewrite(skb, old_ip, new_ip, 1);
+	}
+
+	return BPF_OK;
+}
+
+static inline int __do_push_ll_and_redirect(struct __sk_buff *skb)
+{
+	uint64_t smac = SRC_MAC, dmac = DST_MAC;
+	int ret, ifindex = DST_IFINDEX;
+	struct ethhdr ehdr;
+
+	ret = bpf_skb_change_head(skb, 14, 0);
+	if (ret < 0) {
+		printk("skb_change_head() failed: %d\n", ret);
+	}
+
+	ehdr.h_proto = __constant_htons(ETH_P_IP);
+	memcpy(&ehdr.h_source, &smac, 6);
+	memcpy(&ehdr.h_dest, &dmac, 6);
+
+	ret = bpf_skb_store_bytes(skb, 0, &ehdr, sizeof(ehdr), 0);
+	if (ret < 0) {
+		printk("skb_store_bytes() failed: %d\n", ret);
+		return BPF_DROP;
+	}
+
+	return bpf_redirect(ifindex, 0);
+}
+
+SEC("push_ll_and_redirect_silent")
+int do_push_ll_and_redirect_silent(struct __sk_buff *skb)
+{
+	return __do_push_ll_and_redirect(skb);
+}
+
+SEC("push_ll_and_redirect")
+int do_push_ll_and_redirect(struct __sk_buff *skb)
+{
+	int ret, ifindex = DST_IFINDEX;
+
+	ret = __do_push_ll_and_redirect(skb);
+	if (ret >= 0)
+		printk("redirected to %d\n", ifindex);
+
+	return ret;
+}
+
+static inline void __fill_garbage(struct __sk_buff *skb)
+{
+	uint64_t f = 0xFFFFFFFFFFFFFFFF;
+
+	bpf_skb_store_bytes(skb, 0, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 8, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 16, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 24, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 32, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 40, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 48, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 56, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 64, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 72, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 80, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 88, &f, sizeof(f), 0);
+}
+
+SEC("fill_garbage")
+int do_fill_garbage(struct __sk_buff *skb)
+{
+	__fill_garbage(skb);
+	printk("Set initial 96 bytes of header to FF\n");
+	return BPF_OK;
+}
+
+SEC("fill_garbage_and_redirect")
+int do_fill_garbage_and_redirect(struct __sk_buff *skb)
+{
+	int ifindex = DST_IFINDEX;
+	__fill_garbage(skb);
+	printk("redirected to %d\n", ifindex);
+	return bpf_redirect(ifindex, 0);
+}
+
+/* Drop all packets */
+SEC("drop_all")
+int do_drop_all(struct __sk_buff *skb)
+{
+	printk("dropping with: %d\n", BPF_DROP);
+	return BPF_DROP;
+}
+
+char _license[] SEC("license") = "GPL";

samples/bpf/test_lwt_bpf.sh

+#!/bin/bash
+
+# Uncomment to see generated bytecode
+#VERBOSE=verbose
+
+NS1=lwt_ns1
+NS2=lwt_ns2
+VETH0=tst_lwt1a
+VETH1=tst_lwt1b
+VETH2=tst_lwt2a
+VETH3=tst_lwt2b
+IPVETH0="192.168.254.1"
+IPVETH1="192.168.254.2"
+IPVETH1b="192.168.254.3"
+
+IPVETH2="192.168.111.1"
+IPVETH3="192.168.111.2"
+
+IP_LOCAL="192.168.99.1"
+
+TRACE_ROOT=/sys/kernel/debug/tracing
+
+function lookup_mac()
+{
+	set +x
+	if [ ! -z "$2" ]; then
+		MAC=$(ip netns exec $2 ip link show $1 | grep ether | awk '{print $2}')
+	else
+		MAC=$(ip link show $1 | grep ether | awk '{print $2}')
+	fi
+	MAC="${MAC//:/}"
+	echo "0x${MAC:10:2}${MAC:8:2}${MAC:6:2}${MAC:4:2}${MAC:2:2}${MAC:0:2}"
+	set -x
+}
+
+function cleanup {
+	set +ex
+	rm test_lwt_bpf.o 2> /dev/null
+	ip link del $VETH0 2> /dev/null
+	ip link del $VETH1 2> /dev/null
+	ip link del $VETH2 2> /dev/null
+	ip link del $VETH3 2> /dev/null
+	ip netns exec $NS1 killall netserver
+	ip netns delete $NS1 2> /dev/null
+	ip netns delete $NS2 2> /dev/null
+	set -ex
+}
+
+function setup_one_veth {
+	ip netns add $1
+	ip link add $2 type veth peer name $3
+	ip link set dev $2 up
+	ip addr add $4/24 dev $2
+	ip link set $3 netns $1
+	ip netns exec $1 ip link set dev $3 up
+	ip netns exec $1 ip addr add $5/24 dev $3
+
+	if [ "$6" ]; then
+		ip netns exec $1 ip addr add $6/32 dev $3
+	fi
+}
+
+function get_trace {
+	set +x
+	cat ${TRACE_ROOT}/trace | grep -v '^#'
+	set -x
+}
+
+function cleanup_routes {
+	ip route del ${IPVETH1}/32 dev $VETH0 2> /dev/null || true
+	ip route del table local local ${IP_LOCAL}/32 dev lo 2> /dev/null || true
+}
+
+function install_test {
+	cleanup_routes
+	cp /dev/null ${TRACE_ROOT}/trace
+
+	OPTS="encap bpf headroom 14 $1 obj test_lwt_bpf.o section $2 $VERBOSE"
+
+	if [ "$1" == "in" ];  then
+		ip route add table local local ${IP_LOCAL}/32 $OPTS dev lo
+	else
+		ip route add ${IPVETH1}/32 $OPTS dev $VETH0
+	fi
+}
+
+function remove_prog {
+	if [ "$1" == "in" ];  then
+		ip route del table local local ${IP_LOCAL}/32 dev lo
+	else
+		ip route del ${IPVETH1}/32 dev $VETH0
+	fi
+}
+
+function filter_trace {
+	# Add newline to allow starting EXPECT= variables on newline
+	NL=$'\n'
+	echo "${NL}$*" | sed -e 's/^.*: : //g'
+}
+
+function expect_fail {
+	set +x
+	echo "FAIL:"
+	echo "Expected: $1"
+	echo "Got: $2"
+	set -x
+	exit 1
+}
+
+function match_trace {
+	set +x
+	RET=0
+	TRACE=$1
+	EXPECT=$2
+	GOT="$(filter_trace "$TRACE")"
+
+	[ "$GOT" != "$EXPECT" ] && {
+		expect_fail "$EXPECT" "$GOT"
+		RET=1
+	}
+	set -x
+	return $RET
+}
+
+function test_start {
+	set +x
+	echo "----------------------------------------------------------------"
+	echo "Starting test: $*"
+	echo "----------------------------------------------------------------"
+	set -x
+}
+
+function failure {
+	get_trace
+	echo "FAIL: $*"
+	exit 1
+}
+
+function test_ctx_xmit {
+	test_start "test_ctx on lwt xmit"
+	install_test xmit test_ctx
+	ping -c 3 $IPVETH1 || {
+		failure "test_ctx xmit: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX" || exit 1
+	remove_prog xmit
+}
+
+function test_ctx_out {
+	test_start "test_ctx on lwt out"
+	install_test out test_ctx
+	ping -c 3 $IPVETH1 || {
+		failure "test_ctx out: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+len 84 hash 0 protocol 0
+cb 1234 ingress_ifindex 0 ifindex 0
+len 84 hash 0 protocol 0
+cb 1234 ingress_ifindex 0 ifindex 0
+len 84 hash 0 protocol 0
+cb 1234 ingress_ifindex 0 ifindex 0" || exit 1
+	remove_prog out
+}
+
+function test_ctx_in {
+	test_start "test_ctx on lwt in"
+	install_test in test_ctx
+	ping -c 3 $IP_LOCAL || {
+		failure "test_ctx out: packets are dropped"
+	}
+	# We will both request & reply packets as the packets will
+	# be from $IP_LOCAL => $IP_LOCAL
+	match_trace "$(get_trace)" "
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1" || exit 1
+	remove_prog in
+}
+
+function test_data {
+	test_start "test_data on lwt $1"
+	install_test $1 test_data
+	ping -c 3 $IPVETH1 || {
+		failure "test_data ${1}: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+src: 1fea8c0 dst: 2fea8c0
+src: 1fea8c0 dst: 2fea8c0
+src: 1fea8c0 dst: 2fea8c0" || exit 1
+	remove_prog $1
+}
+
+function test_data_in {
+	test_start "test_data on lwt in"
+	install_test in test_data
+	ping -c 3 $IP_LOCAL || {
+		failure "test_data in: packets are dropped"
+	}
+	# We will both request & reply packets as the packets will
+	# be from $IP_LOCAL => $IP_LOCAL
+	match_trace "$(get_trace)" "
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0" || exit 1
+	remove_prog in
+}
+
+function test_cb {
+	test_start "test_cb on lwt $1"
+	install_test $1 test_cb
+	ping -c 3 $IPVETH1 || {
+		failure "test_cb ${1}: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0" || exit 1
+	remove_prog $1
+}
+
+function test_cb_in {
+	test_start "test_cb on lwt in"
+	install_test in test_cb
+	ping -c 3 $IP_LOCAL || {
+		failure "test_cb in: packets are dropped"
+	}
+	# We will both request & reply packets as the packets will
+	# be from $IP_LOCAL => $IP_LOCAL
+	match_trace "$(get_trace)" "
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0" || exit 1
+	remove_prog in
+}
+
+function test_drop_all {
+	test_start "test_drop_all on lwt $1"
+	install_test $1 drop_all
+	ping -c 3 $IPVETH1 && {
+		failure "test_drop_all ${1}: Unexpected success of ping"
+	}
+	match_trace "$(get_trace)" "
+dropping with: 2
+dropping with: 2
+dropping with: 2" || exit 1
+	remove_prog $1
+}
+
+function test_drop_all_in {
+	test_start "test_drop_all on lwt in"
+	install_test in drop_all
+	ping -c 3 $IP_LOCAL && {
+		failure "test_drop_all in: Unexpected success of ping"
+	}
+	match_trace "$(get_trace)" "
+dropping with: 2
+dropping with: 2
+dropping with: 2" || exit 1
+	remove_prog in
+}
+
+function test_push_ll_and_redirect {
+	test_start "test_push_ll_and_redirect on lwt xmit"
+	install_test xmit push_ll_and_redirect
+	ping -c 3 $IPVETH1 || {
+		failure "Redirected packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" "
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX" || exit 1
+	remove_prog xmit
+}
+
+function test_no_l2_and_redirect {
+	test_start "test_no_l2_and_redirect on lwt xmit"
+	install_test xmit fill_garbage_and_redirect
+	ping -c 3 $IPVETH1 && {
+		failure "Unexpected success despite lack of L2 header"
+	}
+	match_trace "$(get_trace)" "
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX" || exit 1
+	remove_prog xmit
+}
+
+function test_rewrite {
+	test_start "test_rewrite on lwt xmit"
+	install_test xmit test_rewrite
+	ping -c 3 $IPVETH1 || {
+		failure "Rewritten packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" "
+out: rewriting from 2fea8c0 to 3fea8c0
+out: rewriting from 2fea8c0 to 3fea8c0
+out: rewriting from 2fea8c0 to 3fea8c0" || exit 1
+	remove_prog out
+}
+
+function test_fill_garbage {
+	test_start "test_fill_garbage on lwt xmit"
+	install_test xmit fill_garbage
+	ping -c 3 $IPVETH1 && {
+		failure "test_drop_all ${1}: Unexpected success of ping"
+	}
+	match_trace "$(get_trace)" "
+Set initial 96 bytes of header to FF
+Set initial 96 bytes of header to FF
+Set initial 96 bytes of header to FF" || exit 1
+	remove_prog xmit
+}
+
+function test_netperf_nop {
+	test_start "test_netperf_nop on lwt xmit"
+	install_test xmit nop
+	netperf -H $IPVETH1 -t TCP_STREAM || {
+		failure "packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" ""|| exit 1
+	remove_prog xmit
+}
+
+function test_netperf_redirect {
+	test_start "test_netperf_redirect on lwt xmit"
+	install_test xmit push_ll_and_redirect_silent
+	netperf -H $IPVETH1 -t TCP_STREAM || {
+		failure "Rewritten packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" ""|| exit 1
+	remove_prog xmit
+}
+
+cleanup
+setup_one_veth $NS1 $VETH0 $VETH1 $IPVETH0 $IPVETH1 $IPVETH1b
+setup_one_veth $NS2 $VETH2 $VETH3 $IPVETH2 $IPVETH3
+ip netns exec $NS1 netserver
+echo 1 > ${TRACE_ROOT}/tracing_on
+
+DST_MAC=$(lookup_mac $VETH1 $NS1)
+SRC_MAC=$(lookup_mac $VETH0)
+DST_IFINDEX=$(cat /sys/class/net/$VETH0/ifindex)
+
+CLANG_OPTS="-O2 -target bpf -I ../include/"
+CLANG_OPTS+=" -DSRC_MAC=$SRC_MAC -DDST_MAC=$DST_MAC -DDST_IFINDEX=$DST_IFINDEX"
+clang $CLANG_OPTS -c test_lwt_bpf.c -o test_lwt_bpf.o
+
+test_ctx_xmit
+test_ctx_out
+test_ctx_in
+test_data "xmit"
+test_data "out"
+test_data_in
+test_cb "xmit"
+test_cb "out"
+test_cb_in
+test_drop_all "xmit"
+test_drop_all "out"
+test_drop_all_in
+test_rewrite
+test_push_ll_and_redirect
+test_no_l2_and_redirect
+test_fill_garbage
+test_netperf_nop
+test_netperf_redirect
+
+cleanup
+echo 0 > ${TRACE_ROOT}/tracing_on
+exit 0