Message-Id: <1d9d533b5d2640fe958d599ac0944132c3b7d61b.1524591163.git.m.xhonneux@gmail.com>
Date:   Tue, 24 Apr 2018 18:44:13 +0100
From:   Mathieu Xhonneux <m.xhonneux@...il.com>
To:     netdev@...r.kernel.org
Cc:     dlebrun@...gle.com, alexei.starovoitov@...il.com
Subject: [PATCH net-next v2 2/5] bpf: Add IPv6 Segment Routing helpers

The BPF seg6local hook should be powerful enough to enable users to
implement most of the use-cases one could think of. After some thinking,
we figured out that the following actions should be possible on a SRv6
packet, requiring 3 specific helpers :
    - bpf_lwt_seg6_store_bytes: Modify non-sensitive fields of the SRH
    - bpf_lwt_seg6_adjust_srh: Allow to grow or shrink a SRH
                               (to add/delete TLVs)
    - bpf_lwt_seg6_action: Apply some SRv6 network programming actions
                           (specifically End.X, End.T, End.B6 and
                            End.B6.Encap)

The specifications of these helpers are provided in the patch (see
include/uapi/linux/bpf.h).

The non-sensitive fields of the SRH are the following : flags, tag and
TLVs. The other fields can not be modified, to maintain the SRH
integrity. Flags, tag and TLVs can easily be modified as their validity
can be checked afterwards via seg6_validate_srh. It is not allowed to
modify the segments directly. If one wants to add segments on the path,
he should stack a new SRH using the End.B6 action via
bpf_lwt_seg6_action.

Growing, shrinking or editing TLVs via the helpers will flag the SRH as
invalid, and it will have to be re-validated before re-entering the IPv6
layer. This flag is stored in a per-CPU buffer, along with the current
header length in bytes.

Storing the SRH len in bytes in the control block is mandatory when using
bpf_lwt_seg6_adjust_srh. The Header Ext. Length field contains the SRH
len rounded to 8 bytes (a padding TLV can be inserted to ensure the 8-bytes
boundary). When adding/deleting TLVs within the BPF program, the SRH may
temporary be in an invalid state where its length cannot be rounded to 8
bytes without remainder, hence the need to store the length in bytes
separately. The caller of the BPF program can then ensure that the SRH's
final length is valid using this value. Again, a final SRH modified by a
BPF program which doesn’t respect the 8-bytes boundary will be discarded
as it will be considered as invalid.

Finally, a fourth helper is provided, bpf_lwt_push_encap, which is
available from the LWT BPF IN hook, but not from the seg6local BPF one.
This helper allows to encapsulate a Segment Routing Header (either with
a new outer IPv6 header, or by inlining it directly in the existing IPv6
header) into a non-SRv6 packet. This helper is required if we want to
offer the possibility to dynamically encapsulate a SRH for non-SRv6 packet,
as the BPF seg6local hook only works on traffic already containing a SRH.
This is the BPF equivalent of the seg6 LWT infrastructure, which achieves
the same purpose but with a static SRH per route.

Signed-off-by: Mathieu Xhonneux <m.xhonneux@...il.com>
Acked-by: David Lebrun <dlebrun@...gle.com>
---
 include/net/seg6_local.h |   8 ++
 include/uapi/linux/bpf.h |  57 +++++++++-
 net/core/filter.c        | 267 +++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 308 insertions(+), 24 deletions(-)

diff --git a/include/net/seg6_local.h b/include/net/seg6_local.h
index 57498b23085d..661fd5b4d3e0 100644
--- a/include/net/seg6_local.h
+++ b/include/net/seg6_local.h
@@ -15,10 +15,18 @@
 #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
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c8383a289f7b..23421dbc29a7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -774,6 +774,51 @@ union bpf_attr {
  *     @xdp_md: pointer to xdp_md
  *     @delta: A negative integer to be added to xdp_md.data_end
  *     Return: 0 on success or negative on error
+ *
+ * int lwt_push_encap(skb, type, hdr, len)
+ *     Push an encapsulation header on top of current packet.
+ *     @type: type of header to push :
+ *          - BPF_LWT_ENCAP_SEG6 (push an IPv6 Segment Routing Header, struct
+ *                    ipv6_sr_hdr, the helper will add the outer IPv6 header)
+ *          - BPF_LWT_ENCAP_SEG6_INLINE (push an IPv6 Segment Routing Header,
+ *                       struct ipv6_sr_hdr, inside the existing IPv6 header)
+ *     @hdr: pointer where to copy the header from
+ *     @len: size of hdr in bytes
+ *     Return: 0 on success or negative error
+ *
+ * int lwt_seg6_store_bytes(skb, offset, from, len)
+ *     Store bytes into the outermost Segment Routing header of an IPv6 header.
+ *     Only the flags, tag and TLVs can be modified.
+ *     @skb: pointer to skb
+ *     @offset: offset within packet from skb->data
+ *     @from: pointer where to copy bytes from
+ *     @len: number of bytes to store into packet
+ *     Return: 0 on success or negative error
+ *
+ * int lwt_seg6_adjust_srh(skb, offset, delta)
+ *     Adjust the size allocated to TLVs in the outermost IPv6 Segment Routing
+ *     Header (grow if delta > 0, else shrink)
+ *     @skb: pointer to skb
+ *     @offset: offset within packet from skb->data where SRH will grow/shrink,
+ *              only offsets after the segments are accepted
+ *     @delta: a positive/negative integer
+ *     Return: 0 on success or negative on error
+ *
+ * int lwt_seg6_action(skb, action, param, param_len)
+ *     Apply a IPv6 Segment Routing action on a packet with an IPv6 Segment
+ *     Routing Header.
+ *     @action:
+ *              - End.X: SEG6_LOCAL_ACTION_END_X
+ *                                           (type of param: struct in6_addr)
+ *              - End.T: SEG6_LOCAL_ACTION_END_T
+ *                                           (type of param: int)
+ *              - End.B6: SEG6_LOCAL_ACTION_END_B6
+ *                                           (type of param: struct ipv6_sr_hdr)
+ *              - End.B6.Encap: SEG6_LOCAL_ACTION_END_B6_ENCAP
+ *                                           (type of param: struct ipv6_sr_hdr)
+ *     @param: pointer to the parameter required by the action
+ *     @param_len: length of param in bytes
+ *     Return: 0 on success or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -841,7 +886,11 @@ union bpf_attr {
 	FN(msg_cork_bytes),		\
 	FN(msg_pull_data),		\
 	FN(bind),			\
-	FN(xdp_adjust_tail),
+	FN(xdp_adjust_tail),		\
+	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
@@ -899,6 +948,12 @@ enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_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
  */
diff --git a/net/core/filter.c b/net/core/filter.c
index e25bc4a3aa1a..8e67c423db35 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -58,6 +58,10 @@
 #include <net/busy_poll.h>
 #include <net/tcp.h>
 #include <linux/bpf_trace.h>
+#include <net/ipv6.h>
+#include <linux/seg6_local.h>
+#include <net/seg6.h>
+#include <net/seg6_local.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -3077,28 +3081,6 @@ static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
 	.arg3_type      = ARG_ANYTHING,
 };
 
-bool bpf_helper_changes_pkt_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_adjust_room ||
-	    func == bpf_skb_pull_data ||
-	    func == bpf_clone_redirect ||
-	    func == bpf_l3_csum_replace ||
-	    func == bpf_l4_csum_replace ||
-	    func == bpf_xdp_adjust_head ||
-	    func == bpf_xdp_adjust_meta ||
-	    func == bpf_msg_pull_data ||
-	    func == bpf_xdp_adjust_tail)
-		return true;
-
-	return false;
-}
-
 static unsigned long bpf_skb_copy(void *dst_buff, const void *skb,
 				  unsigned long off, unsigned long len)
 {
@@ -3743,6 +3725,246 @@ static const struct bpf_func_proto bpf_bind_proto = {
 	.arg3_type	= ARG_CONST_SIZE,
 };
 
+int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
+{
+	int err;
+	struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)hdr;
+
+	if (!seg6_validate_srh(srh, len))
+		return -EINVAL;
+
+	switch (type) {
+	case BPF_LWT_ENCAP_SEG6_INLINE:
+		if (skb->protocol != htons(ETH_P_IPV6))
+			return -EBADMSG;
+
+		err = seg6_do_srh_inline(skb, srh);
+		break;
+	case BPF_LWT_ENCAP_SEG6:
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
+		err = seg6_do_srh_encap(skb, srh, IPPROTO_IPV6);
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (err)
+		return err;
+
+	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+
+	return seg6_lookup_nexthop(skb, NULL, 0);
+}
+
+BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr,
+	   u32, len)
+{
+	switch (type) {
+	case BPF_LWT_ENCAP_SEG6:
+	case BPF_LWT_ENCAP_SEG6_INLINE:
+		return bpf_push_seg6_encap(skb, type, hdr, len);
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct bpf_func_proto bpf_lwt_push_encap_proto = {
+	.func		= bpf_lwt_push_encap,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE
+};
+
+DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
+
+BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
+	   const void *, from, u32, len)
+{
+	struct seg6_bpf_srh_state *srh_state =
+		this_cpu_ptr(&seg6_bpf_srh_states);
+	void *srh_tlvs, *srh_end, *ptr;
+	struct ipv6_sr_hdr *srh;
+	int srhoff = 0;
+
+	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+		return -EINVAL;
+
+	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
+	srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4));
+	srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen);
+
+	ptr = skb->data + offset;
+	if (ptr >= srh_tlvs && ptr + len <= srh_end)
+		srh_state->valid = 0;
+	else if (ptr < (void *)&srh->flags ||
+		 ptr + len > (void *)&srh->segments)
+		return -EFAULT;
+
+	if (unlikely(bpf_try_make_writable(skb, offset + len)))
+		return -EFAULT;
+
+	memcpy(ptr, from, len);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
+	.func		= bpf_lwt_seg6_store_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE
+};
+
+BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
+	   u32, action, void *, param, u32, param_len)
+{
+	struct seg6_bpf_srh_state *srh_state =
+		this_cpu_ptr(&seg6_bpf_srh_states);
+	struct ipv6_sr_hdr *srh;
+	int srhoff = 0;
+	int err;
+
+	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+		return -EINVAL;
+	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
+
+	if (!srh_state->valid) {
+		if (unlikely((srh_state->hdrlen & 7) != 0))
+			return -EBADMSG;
+
+		srh->hdrlen = (u8)(srh_state->hdrlen >> 3);
+		if (unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3)))
+			return -EBADMSG;
+
+		srh_state->valid = 1;
+	}
+
+	switch (action) {
+	case SEG6_LOCAL_ACTION_END_X:
+		if (param_len != sizeof(struct in6_addr))
+			return -EINVAL;
+		return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0);
+	case SEG6_LOCAL_ACTION_END_T:
+		if (param_len != sizeof(int))
+			return -EINVAL;
+		return seg6_lookup_nexthop(skb, NULL, *(int *)param);
+	case SEG6_LOCAL_ACTION_END_B6:
+		err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE,
+					  param, param_len);
+		if (!err)
+			srh_state->hdrlen =
+				((struct ipv6_sr_hdr *)param)->hdrlen << 3;
+		return err;
+	case SEG6_LOCAL_ACTION_END_B6_ENCAP:
+		err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6,
+					  param, param_len);
+		if (!err)
+			srh_state->hdrlen =
+				((struct ipv6_sr_hdr *)param)->hdrlen << 3;
+		return err;
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
+	.func		= bpf_lwt_seg6_action,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE
+};
+
+BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
+	   s32, len)
+{
+	struct seg6_bpf_srh_state *srh_state =
+		this_cpu_ptr(&seg6_bpf_srh_states);
+	void *srh_end, *srh_tlvs, *ptr;
+	struct ipv6_sr_hdr *srh;
+	struct ipv6hdr *hdr;
+	int srhoff = 0;
+	int ret;
+
+	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+		return -EINVAL;
+	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
+
+	srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) +
+			((srh->first_segment + 1) << 4));
+	srh_end = (void *)((unsigned char *)srh + sizeof(*srh) +
+			srh_state->hdrlen);
+	ptr = skb->data + offset;
+
+	if (unlikely(ptr < srh_tlvs || ptr > srh_end))
+		return -EFAULT;
+	if (unlikely(len < 0 && (void *)((char *)ptr - len) > srh_end))
+		return -EFAULT;
+
+	if (len > 0) {
+		ret = skb_cow_head(skb, len);
+		if (unlikely(ret < 0))
+			return ret;
+
+		ret = bpf_skb_net_hdr_push(skb, offset, len);
+	} else {
+		ret = bpf_skb_net_hdr_pop(skb, offset, -1 * len);
+	}
+	if (unlikely(ret < 0))
+		return ret;
+
+	hdr = (struct ipv6hdr *)skb->data;
+	hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
+	bpf_compute_data_pointers(skb);
+	srh_state->hdrlen += len;
+	srh_state->valid = 0;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
+	.func		= bpf_lwt_seg6_adjust_srh,
+	.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_pkt_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_adjust_room ||
+	    func == bpf_skb_pull_data ||
+	    func == bpf_clone_redirect ||
+	    func == bpf_l3_csum_replace ||
+	    func == bpf_l4_csum_replace ||
+	    func == bpf_xdp_adjust_head ||
+	    func == bpf_xdp_adjust_meta ||
+	    func == bpf_msg_pull_data ||
+	    func == bpf_xdp_adjust_tail ||
+	    func == bpf_lwt_push_encap ||
+	    func == bpf_lwt_seg6_store_bytes ||
+	    func == bpf_lwt_seg6_adjust_srh
+	    )
+		return true;
+
+	return false;
+}
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -4139,7 +4361,6 @@ static bool lwt_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, prog, info);
 }
 
-
 /* Attach type specific accesses */
 static bool __sock_filter_check_attach_type(int off,
 					    enum bpf_access_type access_type,
-- 
2.16.1

Powered by blists - more mailing lists