Merge branch 'bpf-ipv6-seg6-bpf-action'

Mathieu Xhonneux says:

====================
As of Linux 4.14, it is possible to define advanced local processing for
IPv6 packets with a Segment Routing Header through the seg6local LWT
infrastructure. This LWT implements the network programming principles
defined in the IETF "SRv6 Network Programming" draft.

The implemented operations are generic, and it would be very interesting to
be able to implement user-specific seg6local actions, without having to
modify the kernel directly. To do so, this patchset adds an End.BPF action
to seg6local, powered by some specific Segment Routing-related helpers,
which provide SR functionalities that can be applied on the packet. This
BPF hook would then allow to implement specific actions at native kernel
speed such as OAM features, advanced SR SDN policies, SRv6 actions like
Segment Routing Header (SRH) encapsulation depending on the content of
the packet, etc.

This patchset is divided in 6 patches, whose main features are :

- A new seg6local action End.BPF with the corresponding new BPF program
  type BPF_PROG_TYPE_LWT_SEG6LOCAL. Such attached BPF program can be
  passed to the LWT seg6local through netlink, the same way as the LWT
  BPF hook operates.
- 3 new BPF helpers for the seg6local BPF hook, allowing to edit/grow/
  shrink a SRH and apply on a packet some of the generic SRv6 actions.
- 1 new BPF helper for the LWT BPF IN hook, allowing to add a SRH through
  encapsulation (via IPv6 encapsulation or inlining if the packet contains
  already an IPv6 header).

As this patchset adds a new LWT BPF hook, I took into account the result
of the discussions when the LWT BPF infrastructure got merged. Hence, the
seg6local BPF hook doesn't allow write access to skb->data directly, only
the SRH can be modified through specific helpers, which ensures that the
integrity of the packet is maintained. More details are available in the
related patches messages.

The performances of this BPF hook have been assessed with the BPF JIT
enabled on an Intel Xeon X3440 processors with 4 cores and 8 threads
clocked at 2.53 GHz. No throughput losses are noted with the seg6local
BPF hook when the BPF program does nothing (440kpps). Adding a 8-bytes
TLV (1 call each to bpf_lwt_seg6_adjust_srh and bpf_lwt_seg6_store_bytes)
drops the throughput to 410kpps, and inlining a SRH via bpf_lwt_seg6_action
drops the throughput to 420kpps. All throughputs are stable.

Changelog:

v2: move the SRH integrity state from skb->cb to a per-cpu buffer
v3: - document helpers in man-page style
    - fix kbuild bugs
    - un-break BPF LWT out hook
    - bpf_push_seg6_encap is now static
    - preempt_enable is now called when the packet is dropped in
      input_action_end_bpf
v4: fix kbuild bugs when CONFIG_IPV6=m
v5: fix kbuild sparse warnings when CONFIG_IPV6=m
v6: fix skb pointers-related bugs in helpers
v7: - fix memory leak in error path of End.BPF setup
    - add freeing of BPF data in seg6_local_destroy_state
    - new enums SEG6_LOCAL_BPF_* instead of re-using ones of lwt bpf for
      netlink nested bpf attributes
    - SEG6_LOCAL_BPF_PROG attr now contains prog->aux->id when dumping
      state
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/linux/bpf_types.h

@@ -9,9 +9,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp)
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb)
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out)
 BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local)
 BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops)
 BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb)
 BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)

include/net/seg6.h

@@ -49,7 +49,11 @@ struct seg6_pernet_data {
 
 static inline struct seg6_pernet_data *seg6_pernet(struct net *net)
 {
+#if IS_ENABLED(CONFIG_IPV6)
 	return net->ipv6.seg6_data;
+#else
+	return NULL;
+#endif
 }
 
 extern int seg6_init(void);
@@ -63,5 +67,6 @@ extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len);
 extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
 			     int proto);
 extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh);
-
+extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
+			       u32 tbl_id);
 #endif

include/net/seg6_local.h

@@ -0,0 +1,32 @@
+/*
+ *  SR-IPv6 implementation
+ *
+ *  Authors:
+ *  David Lebrun <david.lebrun@uclouvain.be>
+ *  eBPF support: Mathieu Xhonneux <m.xhonneux@gmail.com>
+ *
+ *
+ *  This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _NET_SEG6_LOCAL_H
+#define _NET_SEG6_LOCAL_H
+
+#include <linux/percpu.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+
+extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
+			       u32 tbl_id);
+
+struct seg6_bpf_srh_state {
+	bool valid;
+	u16 hdrlen;
+};
+
+DECLARE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
+
+#endif

include/uapi/linux/bpf.h

@@ -141,6 +141,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_MSG,
 	BPF_PROG_TYPE_RAW_TRACEPOINT,
 	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+	BPF_PROG_TYPE_LWT_SEG6LOCAL,
 };
 
 enum bpf_attach_type {
@@ -1902,6 +1903,90 @@ union bpf_attr {
  *		egress otherwise). This is the only flag supported for now.
  *	Return
  *		**SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
+ *	Description
+ *		Encapsulate the packet associated to *skb* within a Layer 3
+ *		protocol header. This header is provided in the buffer at
+ *		address *hdr*, with *len* its size in bytes. *type* indicates
+ *		the protocol of the header and can be one of:
+ *
+ *		**BPF_LWT_ENCAP_SEG6**
+ *			IPv6 encapsulation with Segment Routing Header
+ *			(**struct ipv6_sr_hdr**). *hdr* only contains the SRH,
+ *			the IPv6 header is computed by the kernel.
+ *		**BPF_LWT_ENCAP_SEG6_INLINE**
+ *			Only works if *skb* contains an IPv6 packet. Insert a
+ *			Segment Routing Header (**struct ipv6_sr_hdr**) inside
+ *			the IPv6 header.
+ *
+ * 		A call to this helper is susceptible to change the underlaying
+ * 		packet buffer. Therefore, at load time, all checks on pointers
+ * 		previously done by the verifier are invalidated and must be
+ * 		performed again, if the helper is used in combination with
+ * 		direct packet access.
+ *	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len)
+ *	Description
+ *		Store *len* bytes from address *from* into the packet
+ *		associated to *skb*, at *offset*. Only the flags, tag and TLVs
+ *		inside the outermost IPv6 Segment Routing Header can be
+ *		modified through this helper.
+ *
+ * 		A call to this helper is susceptible to change the underlaying
+ * 		packet buffer. Therefore, at load time, all checks on pointers
+ * 		previously done by the verifier are invalidated and must be
+ * 		performed again, if the helper is used in combination with
+ * 		direct packet access.
+ *	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta)
+ *	Description
+ *		Adjust the size allocated to TLVs in the outermost IPv6
+ *		Segment Routing Header contained in the packet associated to
+ *		*skb*, at position *offset* by *delta* bytes. Only offsets
+ *		after the segments are accepted. *delta* can be as well
+ *		positive (growing) as negative (shrinking).
+ *
+ * 		A call to this helper is susceptible to change the underlaying
+ * 		packet buffer. Therefore, at load time, all checks on pointers
+ * 		previously done by the verifier are invalidated and must be
+ * 		performed again, if the helper is used in combination with
+ * 		direct packet access.
+ *	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len)
+ *	Description
+ *		Apply an IPv6 Segment Routing action of type *action* to the
+ *		packet associated to *skb*. Each action takes a parameter
+ *		contained at address *param*, and of length *param_len* bytes.
+ *		*action* can be one of:
+ *
+ *		**SEG6_LOCAL_ACTION_END_X**
+ *			End.X action: Endpoint with Layer-3 cross-connect.
+ *			Type of *param*: **struct in6_addr**.
+ *		**SEG6_LOCAL_ACTION_END_T**
+ *			End.T action: Endpoint with specific IPv6 table lookup.
+ *			Type of *param*: **int**.
+ *		**SEG6_LOCAL_ACTION_END_B6**
+ *			End.B6 action: Endpoint bound to an SRv6 policy.
+ *			Type of param: **struct ipv6_sr_hdr**.
+ *		**SEG6_LOCAL_ACTION_END_B6_ENCAP**
+ *			End.B6.Encap action: Endpoint bound to an SRv6
+ *			encapsulation policy.
+ *			Type of param: **struct ipv6_sr_hdr**.
+ *
+ * 		A call to this helper is susceptible to change the underlaying
+ * 		packet buffer. Therefore, at load time, all checks on pointers
+ * 		previously done by the verifier are invalidated and must be
+ * 		performed again, if the helper is used in combination with
+ * 		direct packet access.
+ *	Return
+ * 		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1976,7 +2061,11 @@ union bpf_attr {
 	FN(fib_lookup),			\
 	FN(sock_hash_update),		\
 	FN(msg_redirect_hash),		\
-	FN(sk_redirect_hash),
+	FN(sk_redirect_hash),		\
+	FN(lwt_push_encap),		\
+	FN(lwt_seg6_store_bytes),	\
+	FN(lwt_seg6_adjust_srh),	\
+	FN(lwt_seg6_action),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2043,6 +2132,12 @@ enum bpf_hdr_start_off {
 	BPF_HDR_START_NET,
 };
 
+/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
+enum bpf_lwt_encap_mode {
+	BPF_LWT_ENCAP_SEG6,
+	BPF_LWT_ENCAP_SEG6_INLINE
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */

include/uapi/linux/seg6_local.h

@@ -25,6 +25,7 @@ enum {
 	SEG6_LOCAL_NH6,
 	SEG6_LOCAL_IIF,
 	SEG6_LOCAL_OIF,
+	SEG6_LOCAL_BPF,
 	__SEG6_LOCAL_MAX,
 };
 #define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1)
@@ -59,10 +60,21 @@ enum {
 	SEG6_LOCAL_ACTION_END_AS	= 13,
 	/* forward to SR-unaware VNF with masquerading */
 	SEG6_LOCAL_ACTION_END_AM	= 14,
+	/* custom BPF action */
+	SEG6_LOCAL_ACTION_END_BPF	= 15,
 
 	__SEG6_LOCAL_ACTION_MAX,
 };
 
 #define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1)
 
+enum {
+	SEG6_LOCAL_BPF_PROG_UNSPEC,
+	SEG6_LOCAL_BPF_PROG,
+	SEG6_LOCAL_BPF_PROG_NAME,
+	__SEG6_LOCAL_BPF_PROG_MAX,
+};
+
+#define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1)
+
 #endif

kernel/bpf/verifier.c

@@ -1262,6 +1262,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 	switch (env->prog->type) {
 	case BPF_PROG_TYPE_LWT_IN:
 	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
 		/* dst_input() and dst_output() can't write for now */
 		if (t == BPF_WRITE)
 			return false;