Skip to contentSkip to conversation

BPF for lightweight tunnel encapsulation

PATCH Superseded Thomas Graf 2 participants 14 messages Oct 30, 2016 – Oct 31, 2016

Subsystems (6)

v1 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

cover 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 sees an L3 skb as context. input is read-only, output can write, xmit can write, push headers, and redirect.

Motiviation for this work:
- Restricting outgoing routes beyond what the route tuple supports
- Per route accounting byond realms
- Fast attachment of L2 headers where header does not require resolving L2 addresses
- ILA like uses cases where L3 addresses are resolved and then routed in an async manner
- Fast encapsulation + redirect. For now limited to use cases where not setting inner and outer offset/protocol is OK.

A couple of samples on how to use it can be found in patch 04.

Thomas Graf (4):
route: Set orig_output when redirecting to lwt on locally generated
traffic
route: Set lwtstate for local traffic and cached input dsts
bpf: BPF for lightweight tunnel encapsulation
bpf: Add samples for LWT-BPF

 include/linux/filter.h        |   2 +-
 include/uapi/linux/bpf.h      |  31 +++-
 include/uapi/linux/lwtunnel.h |  21 +++
 kernel/bpf/verifier.c         |  16 +-
 net/core/Makefile             |   2 +-
 net/core/filter.c             | 148 ++++++++++++++++-
 net/core/lwt_bpf.c            | 365 ++++++++++++++++++++++++++++++++++++++++++
 net/core/lwtunnel.c           |   1 +
 net/ipv4/route.c              |  37 +++--
 samples/bpf/bpf_helpers.h     |   4 +
 samples/bpf/lwt_bpf.c         | 210 ++++++++++++++++++++++++
 samples/bpf/test_lwt_bpf.sh   | 337 ++++++++++++++++++++++++++++++++++++++
 12 files changed, 1156 insertions(+), 18 deletions(-)
 create mode 100644 net/core/lwt_bpf.c
 create mode 100644 samples/bpf/lwt_bpf.c
 create mode 100755 samples/bpf/test_lwt_bpf.sh
Signature · 1 line
2.7.4
#1 lore raw

PATCH 1/4 route: Set orig_output when redirecting to lwt on locally generated traffic

orig_output for IPv4 was only set for dsts which hit an input route. Set it consistently for locally generated traffic as well to allow lwt to continue the dst_output() path as configured by the nexthop.

Fixes 2536862311d ("lwt: Add support to redirect dst.input")
---
 net/ipv4/route.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
net/ipv4/route.c +3 -1
index 62d4d90..7da886e 100644
@@ -2138,8 +2138,10 @@ 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))
+	if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
+		rth->dst.lwtstate->orig_output = rth->dst.output;
 		rth->dst.output = lwtunnel_output;
+	}
 
 	return rth;
 }
Signature · 1 line
2.7.4
#2 lore raw

PATCH 2/4 route: Set lwtstate for local traffic and cached input dsts

In reply to Thomas Graf

A route on the output path hitting a RTN_LOCAL route will keep the dst associated on its way through the loopback device. On the receive path, the dst_input() call will thus invoke the input handler of the route created in the output path. Thus, lwt redirection for input must be done for dsts allocated in the otuput path as well.

Also, if a route is cached in the input path, the allocated dst should respect lwtunnel configuration on the nexthop as well.

---
 net/ipv4/route.c | 39 ++++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 13 deletions(-)
net/ipv4/route.c +26 -13
index 7da886e..44f5403 100644
@@ -1596,6 +1596,19 @@ 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,
@@ -1685,14 +1698,7 @@ 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;
@@ -1919,8 +1925,18 @@ 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);
 		}
@@ -2138,10 +2154,7 @@ 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.lwtstate->orig_output = rth->dst.output;
-		rth->dst.output = lwtunnel_output;
-	}
+	set_lwt_redirect(rth);
 
 	return rth;
 }
Signature · 1 line
2.7.4
#3 lore raw

PATCH 3/4 bpf: BPF for lightweight tunnel encapsulation

In reply to Thomas Graf

Register two new BPF prog types BPF_PROG_TYPE_LWT_IN and BPF_PROG_TYPE_LWT_OUT which are invoked if a route contains a LWT redirection of type LWTUNNEL_ENCAP_BPF.

The separate program types are required because manipulation of packet data is only allowed on the output and transmit path as the subsequent dst_input() call path assumes an IP header validated by ip_rcv(). The BPF programs will be handed an skb with the L3 header attached and may return one of the following return codes:

BPF_OK - Continue routing as per nexthop
BPF_DROP - Drop skb and return EPERM
BPF_REDIRECT - Redirect skb to device as per redirect() helper.
(Only valid on lwtunnel_xmit() hook)

The return codes are binary compatible with their TC_ACT_ relatives to ease compatibility.

A new helper bpf_skb_push() is added which allows to preprend an L2 header in front of the skb, extend the existing L3 header, or both. This allows to address a wide range of issues:
- Optimize L2 header construction when L2 information is always static to avoid ARP/NDisc lookup.
- Extend IP header to add additional IP options.
- Perform simple encapsulation where offload is of no concern. (The existing funtionality to attach a tunnel key to the skb and redirect to a tunnel net_device to allow for offload continues to work obviously).

---
 include/linux/filter.h        |   2 +-
 include/uapi/linux/bpf.h      |  31 +++-
 include/uapi/linux/lwtunnel.h |  21 +++
 kernel/bpf/verifier.c         |  16 +-
 net/core/Makefile             |   2 +-
 net/core/filter.c             | 148 ++++++++++++++++-
 net/core/lwt_bpf.c            | 365 ++++++++++++++++++++++++++++++++++++++++++
 net/core/lwtunnel.c           |   1 +
 8 files changed, 579 insertions(+), 7 deletions(-)
 create mode 100644 net/core/lwt_bpf.c
include/linux/filter.h +1 -1
index 1f09c52..aad7f81 100644
@@ -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 +30 -1
index e2f38e0..2ebaa3c 100644
@@ -96,6 +96,9 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_TRACEPOINT,
 	BPF_PROG_TYPE_XDP,
 	BPF_PROG_TYPE_PERF_EVENT,
+	BPF_PROG_TYPE_LWT_IN,
+	BPF_PROG_TYPE_LWT_OUT,
+	BPF_PROG_TYPE_LWT_XMIT,
 };
 
 #define BPF_PSEUDO_MAP_FD	1
@@ -383,6 +386,16 @@ union bpf_attr {
  *
  * int bpf_get_numa_node_id()
  *     Return: Id of current NUMA node.
+ *
+ * int bpf_skb_push()
+ *     Add room to beginning of skb and adjusts MAC header offset accordingly.
+ *     Extends/reallocaes for needed skb headeroom automatically.
+ *     May change skb data pointer and will thus invalidate any check done
+ *     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),			\
@@ -427,7 +440,8 @@ 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_push),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -511,6 +525,21 @@ 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,
+};
+
 /* 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 +21 -0
index a478fe8..9354d997 100644
@@ -9,6 +9,7 @@ enum lwtunnel_encap_types {
 	LWTUNNEL_ENCAP_IP,
 	LWTUNNEL_ENCAP_ILA,
 	LWTUNNEL_ENCAP_IP6,
+	LWTUNNEL_ENCAP_BPF,
 	__LWTUNNEL_ENCAP_MAX,
 };
 
@@ -42,4 +43,24 @@ 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_MAX,
+};
+
+#define LWT_BPF_MAX (__LWT_BPF_MAX - 1)
+
+
 #endif /* _UAPI_LWTUNNEL_H_ */
kernel/bpf/verifier.c +13 -3
index 9002575..519b58e 100644
@@ -633,12 +633,21 @@ 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:
+		/* dst_input() can't write for now, orig_input may depend on
+		 * IP header parsed by ip_rcv().
+		 */
+		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_OUT:
+	case BPF_PROG_TYPE_LWT_XMIT:
 		if (meta)
 			return meta->pkt_access;
 
@@ -837,7 +846,7 @@ 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 +979,8 @@ 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/core/Makefile +1 -1
index d6508c2..a675fd3 100644
@@ -23,7 +23,7 @@ obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
 obj-$(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) += lwtunnel.o 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 +147 -1

184 lines not on this page · raw message

net/core/lwt_bpf.c new file +365 -0

365 lines not on this page · raw message

net/core/lwtunnel.c +1 -0
index 88fd642..554d901 100644
@@ -39,6 +39,7 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
 		return "MPLS";
 	case LWTUNNEL_ENCAP_ILA:
 		return "ILA";
+	case LWTUNNEL_ENCAP_BPF:
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
 	case LWTUNNEL_ENCAP_NONE:
Signature · 1 line
2.7.4
#4 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 538 lines · Thomas Graf

Register two new BPF prog types BPF_PROG_TYPE_LWT_IN and BPF_PROG_TYPE_LWT_OUT which are invoked if a route contains a LWT redirection of type LWTUNNEL_ENCAP_BPF.

The separate program types are required because manipulation of packet data is only allowed on the output and transmit path as the subsequent dst_input() call path assumes an IP header validated by ip_rcv(). The BPF programs will be handed an skb with the L3 header attached and may return one of the following return codes:

BPF_OK - Continue routing as per nexthop
BPF_DROP - Drop skb and return EPERM
BPF_REDIRECT - Redirect skb to device as per redirect() helper.
(Only valid on lwtunnel_xmit() hook)

The return codes are binary compatible with their TC_ACT_ relatives to ease compatibility.

A new helper bpf_skb_push() is added which allows to preprend an L2 header in front of the skb, extend the existing L3 header, or both. This allows to address a wide range of issues:
- Optimize L2 header construction when L2 information is always static to avoid ARP/NDisc lookup.
- Extend IP header to add additional IP options.
- Perform simple encapsulation where offload is of no concern. (The existing funtionality to attach a tunnel key to the skb and redirect to a tunnel net_device to allow for offload continues to work obviously).

---
 include/linux/filter.h        |   2 +-
 include/uapi/linux/bpf.h      |  31 +++-
 include/uapi/linux/lwtunnel.h |  21 +++
 kernel/bpf/verifier.c         |  16 +-
 net/core/Makefile             |   2 +-
 net/core/filter.c             | 148 ++++++++++++++++-
 net/core/lwt_bpf.c            | 365 ++++++++++++++++++++++++++++++++++++++++++
 net/core/lwtunnel.c           |   1 +
 8 files changed, 579 insertions(+), 7 deletions(-)
 create mode 100644 net/core/lwt_bpf.c
include/linux/filter.h +1 -1
index 1f09c52..aad7f81 100644
@@ -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 +30 -1
index e2f38e0..2ebaa3c 100644
@@ -96,6 +96,9 @@ enum bpf_prog_type {
        BPF_PROG_TYPE_TRACEPOINT,
        BPF_PROG_TYPE_XDP,
        BPF_PROG_TYPE_PERF_EVENT,
+       BPF_PROG_TYPE_LWT_IN,
+       BPF_PROG_TYPE_LWT_OUT,
+       BPF_PROG_TYPE_LWT_XMIT,
 };
 
 #define BPF_PSEUDO_MAP_FD      1
@@ -383,6 +386,16 @@ union bpf_attr {
  *
  * int bpf_get_numa_node_id()
  *     Return: Id of current NUMA node.
+ *
+ * int bpf_skb_push()
+ *     Add room to beginning of skb and adjusts MAC header offset accordingly.
+ *     Extends/reallocaes for needed skb headeroom automatically.
+ *     May change skb data pointer and will thus invalidate any check done
+ *     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),                     \
@@ -427,7 +440,8 @@ 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_push),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -511,6 +525,21 @@ 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,
+};
+
 /* 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 +21 -0
index a478fe8..9354d997 100644
@@ -9,6 +9,7 @@ enum lwtunnel_encap_types {
        LWTUNNEL_ENCAP_IP,
        LWTUNNEL_ENCAP_ILA,
        LWTUNNEL_ENCAP_IP6,
+       LWTUNNEL_ENCAP_BPF,
        __LWTUNNEL_ENCAP_MAX,
 };
 
@@ -42,4 +43,24 @@ 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_MAX,
+};
+
+#define LWT_BPF_MAX (__LWT_BPF_MAX - 1)
+
+
 #endif /* _UAPI_LWTUNNEL_H_ */
kernel/bpf/verifier.c +13 -3
index 9002575..519b58e 100644
@@ -633,12 +633,21 @@ 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:
+               /* dst_input() can't write for now, orig_input may depend on
+                * IP header parsed by ip_rcv().
+                */
+               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_OUT:
+       case BPF_PROG_TYPE_LWT_XMIT:
                if (meta)
                        return meta->pkt_access;
 
@@ -837,7 +846,7 @@ 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 +979,8 @@ 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/core/Makefile +1 -1
index d6508c2..a675fd3 100644
@@ -23,7 +23,7 @@ obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
 obj-$(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) += lwtunnel.o 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 +147 -1
index cd9e2ba..325a9d8 100644
@@ -2138,6 +2138,43 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = {
        .arg3_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_skb_push, struct sk_buff *, skb, __u32, len, u64, flags)
+{
+       u32 new_len = skb->len + len;
+
+       /* restrict max skb size and check for overflow */
+       if (new_len > __bpf_skb_max_len(skb) || new_len < skb->len)
+               return -ERANGE;
+
+       if (flags)
+               return -EINVAL;
+
+       if (len > 0) {
+               int ret;
+
+               ret = skb_cow(skb, len);
+               if (unlikely(ret < 0))
+                       return ret;
+
+               __skb_push(skb, len);
+               memset(skb->data, 0, len);
+       }
+
+       skb_reset_mac_header(skb);
+
+       bpf_compute_data_end(skb);
+       return 0;
+}
+
+static const struct bpf_func_proto bpf_skb_push_proto = {
+       .func           = bpf_skb_push,
+       .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 ||
@@ -2147,7 +2184,8 @@ bool bpf_helper_changes_skb_data(void *func)
            func == bpf_skb_change_tail ||
            func == bpf_skb_pull_data ||
            func == bpf_l3_csum_replace ||
-           func == bpf_l4_csum_replace)
+           func == bpf_l4_csum_replace ||
+           func == bpf_skb_push)
                return true;
 
        return false;
@@ -2578,6 +2616,75 @@ xdp_func_proto(enum bpf_func_id func_id)
        }
 }
 
+static const struct bpf_func_proto *
+lwt_in_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_out_func_proto(enum bpf_func_id func_id)
+{
+       switch (func_id) {
+       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_in_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_skb_change_tail:
+               return &bpf_skb_change_tail_proto;
+       case BPF_FUNC_skb_push:
+               return &bpf_skb_push_proto;
+       default:
+               return lwt_out_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))
@@ -2940,6 +3047,27 @@ static const struct bpf_verifier_ops xdp_ops = {
        .convert_ctx_access     = xdp_convert_ctx_access,
 };
 
+static const struct bpf_verifier_ops lwt_in_ops = {
+       .get_func_proto         = lwt_in_func_proto,
+       .is_valid_access        = tc_cls_act_is_valid_access,
+       .convert_ctx_access     = sk_filter_convert_ctx_access,
+       .gen_prologue           = tc_cls_act_prologue,
+};
+
+static const struct bpf_verifier_ops lwt_out_ops = {
+       .get_func_proto         = lwt_out_func_proto,
+       .is_valid_access        = tc_cls_act_is_valid_access,
+       .convert_ctx_access     = sk_filter_convert_ctx_access,
+       .gen_prologue           = tc_cls_act_prologue,
+};
+
+static const struct bpf_verifier_ops lwt_xmit_ops = {
+       .get_func_proto         = lwt_xmit_func_proto,
+       .is_valid_access        = tc_cls_act_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,
@@ -2960,12 +3088,30 @@ static struct bpf_prog_type_list xdp_type __read_mostly = {
        .type   = BPF_PROG_TYPE_XDP,
 };
 
+static struct bpf_prog_type_list lwt_in_type __read_mostly = {
+       .ops    = &lwt_in_ops,
+       .type   = BPF_PROG_TYPE_LWT_IN,
+};
+
+static struct bpf_prog_type_list lwt_out_type __read_mostly = {
+       .ops    = &lwt_out_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);
        bpf_register_prog_type(&sched_cls_type);
        bpf_register_prog_type(&sched_act_type);
        bpf_register_prog_type(&xdp_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 new file +124 -0
new file mode 100644
index 0000000..8404ac6
@@ -0,0 +1,365 @@
+/* Copyright (c) 2016 Thomas Graf <[email protected]>
+ *
+ * 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;
+};
+
+#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(lwt->prog, skb);
+       rcu_read_unlock();
+
+       switch (ret) {
+       case BPF_OK:
+               break;
+
+       case BPF_REDIRECT:
+               if (!can_redirect) {
+                       WARN_ONCE(1, "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:
+               WARN_ONCE(1, "Illegal LWT BPF 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)) {
+               WARN_ONCE(1, "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;

net/core/lwt_bpf.c line 134

Quoted 10 lines
net/core/lwt_bpf.c new file +10 -0
+       }
+
+       if (unlikely(!dst->lwtstate->orig_output)) {
+               WARN_ONCE(1, "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);

Thomas,

The BPF program may have changed the destination address so continuing with original route in skb may not be appropriate here. This was fixed in ila_lwt by calling ip6_route_output and we were able to dst cache facility to cache the route to avoid cost of looking it up on every packet. Since the kernel has no insight into what the BPF program does to the packet I'd suggest 1) checking if destination address changed by BPF and if it did then call route_output to get new route
2) If the LWT destination is a host route then try to keep a dst cache. This would entail checking destination address on return that it is the same one as kept in the dst cache.

Tom

Quoted 246 lines
net/core/lwt_bpf.c new file +231 -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:
+                       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, },
+};
+
+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;
+
+       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]) {
+               ret = bpf_parse_prog(tb[LWT_BPF_IN], &bpf->in,
+                                    BPF_PROG_TYPE_LWT_IN);
+               if (ret  < 0) {
+                       kfree(newts);
+                       return ret;
+               }
+
+               newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT;
+       }
+
+       if (tb[LWT_BPF_OUT]) {
+               ret = bpf_parse_prog(tb[LWT_BPF_OUT], &bpf->out,
+                                    BPF_PROG_TYPE_LWT_OUT);
+               if (ret < 0) {
+                       bpf_destroy_state(newts);
+                       kfree(newts);
+                       return ret;
+               }
+
+               newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT;
+       }
+
+       if (tb[LWT_BPF_XMIT]) {
+               ret = bpf_parse_prog(tb[LWT_BPF_XMIT], &bpf->xmit,
+                                    BPF_PROG_TYPE_LWT_XMIT);
+               if (ret < 0) {
+                       bpf_destroy_state(newts);
+                       kfree(newts);
+                       return ret;
+               }
+
+               newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT;
+       }
+
+       *ts = newts;
+
+       return 0;
+}
+
+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 +1 -1
index 88fd642..554d901 100644
@@ -39,6 +39,7 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
                return "MPLS";
        case LWTUNNEL_ENCAP_ILA:
                return "ILA";
+       case LWTUNNEL_ENCAP_BPF:
        case LWTUNNEL_ENCAP_IP6:
        case LWTUNNEL_ENCAP_IP:
        case LWTUNNEL_ENCAP_NONE:
--

2.7.4

#5 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 10 lines · Tom Herbert

net/core/lwt_bpf.c line 134

Quoted 8 lines · Thomas Graf
net/core/lwt_bpf.c new file +8 -0
+       if (unlikely(!dst->lwtstate->orig_output)) {
+               WARN_ONCE(1, "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);
Quoted 10 lines

The BPF program may have changed the destination address so continuing with original route in skb may not be appropriate here. This was fixed in ila_lwt by calling ip6_route_output and we were able to dst cache facility to cache the route to avoid cost of looking it up on every packet. Since the kernel has no insight into what the BPF program does to the packet I'd suggest 1) checking if destination address changed by BPF and if it did then call route_output to get new route
2) If the LWT destination is a host route then try to keep a dst cache. This would entail checking destination address on return that it is the same one as kept in the dst cache.

Instead of building complex logic, we can allow the program to return a code to indicate when to perform another route lookup just as we do for the redirect case. Just because the destination address has changed may not require another lookup in all cases. A typical example would be a program rewriting addresses for the default route to other address which are always handled by the default route as well. An unconditional lookup would hurt performance in many cases.

#6 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 22 lines · Thomas Graf
Quoted 10 lines · Tom Herbert

net/core/lwt_bpf.c line 134

Quoted 8 lines · Thomas Graf
net/core/lwt_bpf.c new file +8 -0
+       if (unlikely(!dst->lwtstate->orig_output)) {
+               WARN_ONCE(1, "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);
Quoted 10 lines

The BPF program may have changed the destination address so continuing with original route in skb may not be appropriate here. This was fixed in ila_lwt by calling ip6_route_output and we were able to dst cache facility to cache the route to avoid cost of looking it up on every packet. Since the kernel has no insight into what the BPF program does to the packet I'd suggest 1) checking if destination address changed by BPF and if it did then call route_output to get new route
2) If the LWT destination is a host route then try to keep a dst cache. This would entail checking destination address on return that it is the same one as kept in the dst cache.

Quoted 7 lines

Instead of building complex logic, we can allow the program to return a code to indicate when to perform another route lookup just as we do for the redirect case. Just because the destination address has changed may not require another lookup in all cases. A typical example would be a program rewriting addresses for the default route to other address which are always handled by the default route as well. An unconditional lookup would hurt performance in many cases.

Right, that's why we rely on a dst cache. Any use of LWT that encapsulates or tunnels to a fixed destination (ILA, VXLAN, IPIP, etc.) would want to use the dst cache optimization to avoid the second lookup. The ILA LWT code used to call orig output and that worked as long as we could set the default router as the gateway "via". It was something we were able to deploy, but not a general solution. Integrating properly with routing gives a much better solution IMO. Note that David Lebrun's latest LWT Segment Routing patch does the second lookup with the dst cache to try to avoid it.

Thanks,
Tom

#7 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 9 lines · Tom Herbert
Quoted 7 lines · Thomas Graf

Instead of building complex logic, we can allow the program to return a code to indicate when to perform another route lookup just as we do for the redirect case. Just because the destination address has changed may not require another lookup in all cases. A typical example would be a program rewriting addresses for the default route to other address which are always handled by the default route as well. An unconditional lookup would hurt performance in many cases.

Quoted 9 lines

Right, that's why we rely on a dst cache. Any use of LWT that encapsulates or tunnels to a fixed destination (ILA, VXLAN, IPIP, etc.) would want to use the dst cache optimization to avoid the second lookup. The ILA LWT code used to call orig output and that worked as long as we could set the default router as the gateway "via". It was something we were able to deploy, but not a general solution. Integrating properly with routing gives a much better solution IMO. Note that David Lebrun's latest LWT Segment Routing patch does the second lookup with the dst cache to try to avoid it.

Yes, I saw both ILA and SR dst_cache. I was planning on addressing the conditional reroute in a second step but it looks fairly simple actually so I'm fine adding this in a v2 based on a return code. I will limit lwt-bpf to AF_INET && AF_INET6 though.

#8 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

In reply to Tom Herbert
Quoted 9 lines · Tom Herbert

Right, that's why we rely on a dst cache. Any use of LWT that encapsulates or tunnels to a fixed destination (ILA, VXLAN, IPIP, etc.) would want to use the dst cache optimization to avoid the second lookup. The ILA LWT code used to call orig output and that worked as long as we could set the default router as the gateway "via". It was something we were able to deploy, but not a general solution. Integrating properly with routing gives a much better solution IMO. Note that David Lebrun's latest LWT Segment Routing patch does the second lookup with the dst cache to try to avoid it.

Noticed while implementing this: How does ILA ensure that dst_output() is not invoked in a circular manner?

dstA->output() -> dstB->otuput() -> dstA->output() -> ...

#9 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 11 lines · Thomas Graf
Quoted 9 lines · Tom Herbert

Right, that's why we rely on a dst cache. Any use of LWT that encapsulates or tunnels to a fixed destination (ILA, VXLAN, IPIP, etc.) would want to use the dst cache optimization to avoid the second lookup. The ILA LWT code used to call orig output and that worked as long as we could set the default router as the gateway "via". It was something we were able to deploy, but not a general solution. Integrating properly with routing gives a much better solution IMO. Note that David Lebrun's latest LWT Segment Routing patch does the second lookup with the dst cache to try to avoid it.

Quoted 4 lines

Noticed while implementing this: How does ILA ensure that dst_output() is not invoked in a circular manner?

dstA->output() -> dstB->otuput() -> dstA->output() -> ...

It doesn't. We'll need to add a check for that. Maybe the rule should be that an skbuff is only allowed to hit one LWT route?

Another scenario to consider: Suppose someone is doing protocol translation like in RFC7915. This is one of operations we'd need with ILA or GRE to implement an IPv4 overlay network over IPv6. Would this be allowed/supported in LWT BPF?

Tom

#10 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 8 lines · Tom Herbert
Quoted 4 lines · Thomas Graf

Noticed while implementing this: How does ILA ensure that dst_output() is not invoked in a circular manner?

dstA->output() -> dstB->otuput() -> dstA->output() -> ...

It doesn't. We'll need to add a check for that. Maybe the rule should be that an skbuff is only allowed to hit one LWT route?

I'll add a per cpu variable to do a recursion limit for dst_output() which callers to possibly recurse can use. ILA can use that as well.

Quoted 4 lines

Another scenario to consider: Suppose someone is doing protocol translation like in RFC7915. This is one of operations we'd need with ILA or GRE to implement an IPv4 overlay network over IPv6. Would this be allowed/supported in LWT BPF?

In lwtunnel_xmit() yes, input and output would not support this right now. It will need some logic as the orig_input and orig_output would obviously be expecting the same protocol. This is the reason why the xmit prog type currently has a wider set of allowed helpers.

#11 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 18 lines · Thomas Graf
Quoted 8 lines · Tom Herbert
Quoted 4 lines · Thomas Graf

Noticed while implementing this: How does ILA ensure that dst_output() is not invoked in a circular manner?

dstA->output() -> dstB->otuput() -> dstA->output() -> ...

It doesn't. We'll need to add a check for that. Maybe the rule should be that an skbuff is only allowed to hit one LWT route?

I'll add a per cpu variable to do a recursion limit for dst_output() which callers to possibly recurse can use. ILA can use that as well.

Quoted 4 lines

Another scenario to consider: Suppose someone is doing protocol translation like in RFC7915. This is one of operations we'd need with ILA or GRE to implement an IPv4 overlay network over IPv6. Would this be allowed/supported in LWT BPF?

Quoted 4 lines

In lwtunnel_xmit() yes, input and output would not support this right now. It will need some logic as the orig_input and orig_output would obviously be expecting the same protocol. This is the reason why the xmit prog type currently has a wider set of allowed helpers.

I guess this leads to a more general question I have about the effects of allowing userspace to insert code in the kernel that modifies packets. If we allow BPF programs to arbitrarily modify packets in LWT, how do we ensure that there are no insidious effects later in the path? For instance, what someone uses BPF to convert an IPv6 packet to IPv4, or maybe convert packet to something that isn't even IP, or what if someone just decides to overwrite every byte in a packet with 0xff? Are these thing allowed, and if so what is the effect? I would assume a policy that these can't cause any insidious effects to unrelated traffic or the rest of the system, in particular such things should not cause the kernel to crash (based on the principle that user space code should never cause kernel to crash). I think XDP might be okay since the path is straightforward and only deals with raw packets, but LWT is much higher in that stack.

Thanks,
Tom

#12 lore raw

Re: [PATCH net-next 3/4] bpf: BPF for lightweight tunnel encapsulation

Quoted 8 lines · Tom Herbert

I guess this leads to a more general question I have about the effects of allowing userspace to insert code in the kernel that modifies packets. If we allow BPF programs to arbitrarily modify packets in LWT, how do we ensure that there are no insidious effects later in the path? For instance, what someone uses BPF to convert an IPv6 packet to IPv4, or maybe convert packet to something that isn't even IP, or what if someone just decides to overwrite every byte in a packet with 0xff?

This is why modifying packets is not allowed on input at all as it would invalidate the IP parsing that has already been done.

Writing is allowed for dst_output() on the basis that it is the equivalent of a raw socket with header inclusion. If you look at rawv6_send_hdrinc(), it does not perform any validation and calls into dst_output() directly. I agree though that this must be made water proof.

Pushing additional headers is only allowed at xmit, this is the equivalent LWT MPLS.

Quoted 5 lines

Are these thing allowed, and if so what is the effect? I would assume a policy that these can't cause any insidious effects to unrelated traffic or the rest of the system, in particular such things should not cause the kernel to crash (based on the principle that user space code should never cause kernel to crash). I think XDP might

Agreed. Although it's already possible to hook a kernel module at LWT or Netfilter to do arbitrary packet modifications, BPF must be held at a higher standard even in privileged mode.

#13 lore raw

PATCH 4/4 bpf: Add samples for LWT-BPF

In reply to Thomas Graf

This adds a set of samples demonstrating the use of lwt-bpf combined with a shell script which allows running the samples in the form of a basic selftest.

The samples include:
- Allowing all packets
- Dropping all packets
- Printing context information
- Access packet data
- IPv4 daddr rewrite in dst_output()
- L2 MAC header push + redirect in lwt xmit

---
 samples/bpf/bpf_helpers.h   |   4 +
 samples/bpf/lwt_bpf.c       | 210 +++++++++++++++++++++++++++
 samples/bpf/test_lwt_bpf.sh | 337 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 551 insertions(+)
 create mode 100644 samples/bpf/lwt_bpf.c
 create mode 100755 samples/bpf/test_lwt_bpf.sh
samples/bpf/bpf_helpers.h +4 -0
index 90f44bd..f34e417 100644
@@ -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_push)(void *, int len, int flags) =
+	(void *) BPF_FUNC_skb_push;
 
 #if defined(__x86_64__)
 
samples/bpf/lwt_bpf.c new file +210 -0

210 lines not on this page · raw message

samples/bpf/test_lwt_bpf.sh new file +337 -0

337 lines not on this page · raw message

Signature · 1 line
2.7.4