linux/net/ipv6/seg6_local.c

1111 lines
23 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* SR-IPv6 implementation
*
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
* Authors:
* David Lebrun <david.lebrun@uclouvain.be>
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
* eBPF support: Mathieu Xhonneux <m.xhonneux@gmail.com>
*/
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/net.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
#include <net/ip6_fib.h>
#include <net/route.h>
#include <net/seg6.h>
#include <linux/seg6.h>
#include <linux/seg6_local.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/dst_cache.h>
#ifdef CONFIG_IPV6_SEG6_HMAC
#include <net/seg6_hmac.h>
#endif
#include <net/seg6_local.h>
#include <linux/etherdevice.h>
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
#include <linux/bpf.h>
struct seg6_local_lwt;
struct seg6_action_desc {
int action;
unsigned long attrs;
int (*input)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
int static_headroom;
};
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
struct bpf_lwt_prog {
struct bpf_prog *prog;
char *name;
};
struct seg6_local_lwt {
int action;
struct ipv6_sr_hdr *srh;
int table;
struct in_addr nh4;
struct in6_addr nh6;
int iif;
int oif;
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
struct bpf_lwt_prog bpf;
int headroom;
struct seg6_action_desc *desc;
};
static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt)
{
return (struct seg6_local_lwt *)lwt->data;
}
static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb)
{
struct ipv6_sr_hdr *srh;
int len, srhoff = 0;
if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
return NULL;
if (!pskb_may_pull(skb, srhoff + sizeof(*srh)))
return NULL;
srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
len = (srh->hdrlen + 1) << 3;
if (!pskb_may_pull(skb, srhoff + len))
return NULL;
if (!seg6_validate_srh(srh, len))
return NULL;
return srh;
}
static struct ipv6_sr_hdr *get_and_validate_srh(struct sk_buff *skb)
{
struct ipv6_sr_hdr *srh;
srh = get_srh(skb);
if (!srh)
return NULL;
if (srh->segments_left == 0)
return NULL;
#ifdef CONFIG_IPV6_SEG6_HMAC
if (!seg6_hmac_validate_skb(skb))
return NULL;
#endif
return srh;
}
static bool decap_and_validate(struct sk_buff *skb, int proto)
{
struct ipv6_sr_hdr *srh;
unsigned int off = 0;
srh = get_srh(skb);
if (srh && srh->segments_left > 0)
return false;
#ifdef CONFIG_IPV6_SEG6_HMAC
if (srh && !seg6_hmac_validate_skb(skb))
return false;
#endif
if (ipv6_find_hdr(skb, &off, proto, NULL, NULL) < 0)
return false;
if (!pskb_pull(skb, off))
return false;
skb_postpull_rcsum(skb, skb_network_header(skb), off);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
skb->encapsulation = 0;
return true;
}
static void advance_nextseg(struct ipv6_sr_hdr *srh, struct in6_addr *daddr)
{
struct in6_addr *addr;
srh->segments_left--;
addr = srh->segments + srh->segments_left;
*daddr = *addr;
}
int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
u32 tbl_id)
{
struct net *net = dev_net(skb->dev);
struct ipv6hdr *hdr = ipv6_hdr(skb);
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct dst_entry *dst = NULL;
struct rt6_info *rt;
struct flowi6 fl6;
fl6.flowi6_iif = skb->dev->ifindex;
fl6.daddr = nhaddr ? *nhaddr : hdr->daddr;
fl6.saddr = hdr->saddr;
fl6.flowlabel = ip6_flowinfo(hdr);
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = hdr->nexthdr;
if (nhaddr)
fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
if (!tbl_id) {
dst = ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags);
} else {
struct fib6_table *table;
table = fib6_get_table(net, tbl_id);
if (!table)
goto out;
rt = ip6_pol_route(net, table, 0, &fl6, skb, flags);
dst = &rt->dst;
}
if (dst && dst->dev->flags & IFF_LOOPBACK && !dst->error) {
dst_release(dst);
dst = NULL;
}
out:
if (!dst) {
rt = net->ipv6.ip6_blk_hole_entry;
dst = &rt->dst;
dst_hold(dst);
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
return dst->error;
}
/* regular endpoint function */
static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
/* regular endpoint, and forward to specified nexthop */
static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
seg6_lookup_nexthop(skb, &slwt->nh6, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int input_action_end_t(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
seg6_lookup_nexthop(skb, NULL, slwt->table);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
/* decapsulate and forward inner L2 frame on specified interface */
static int input_action_end_dx2(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct net *net = dev_net(skb->dev);
struct net_device *odev;
struct ethhdr *eth;
if (!decap_and_validate(skb, NEXTHDR_NONE))
goto drop;
if (!pskb_may_pull(skb, ETH_HLEN))
goto drop;
skb_reset_mac_header(skb);
eth = (struct ethhdr *)skb->data;
/* To determine the frame's protocol, we assume it is 802.3. This avoids
* a call to eth_type_trans(), which is not really relevant for our
* use case.
*/
if (!eth_proto_is_802_3(eth->h_proto))
goto drop;
odev = dev_get_by_index_rcu(net, slwt->oif);
if (!odev)
goto drop;
/* As we accept Ethernet frames, make sure the egress device is of
* the correct type.
*/
if (odev->type != ARPHRD_ETHER)
goto drop;
if (!(odev->flags & IFF_UP) || !netif_carrier_ok(odev))
goto drop;
skb_orphan(skb);
if (skb_warn_if_lro(skb))
goto drop;
skb_forward_csum(skb);
if (skb->len - ETH_HLEN > odev->mtu)
goto drop;
skb->dev = odev;
skb->protocol = eth->h_proto;
return dev_queue_xmit(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
/* decapsulate and forward to specified nexthop */
static int input_action_end_dx6(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct in6_addr *nhaddr = NULL;
/* this function accepts IPv6 encapsulated packets, with either
* an SRH with SL=0, or no SRH.
*/
if (!decap_and_validate(skb, IPPROTO_IPV6))
goto drop;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
/* The inner packet is not associated to any local interface,
* so we do not call netif_rx().
*
* If slwt->nh6 is set to ::, then lookup the nexthop for the
* inner packet's DA. Otherwise, use the specified nexthop.
*/
if (!ipv6_addr_any(&slwt->nh6))
nhaddr = &slwt->nh6;
seg6_lookup_nexthop(skb, nhaddr, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int input_action_end_dx4(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct iphdr *iph;
__be32 nhaddr;
int err;
if (!decap_and_validate(skb, IPPROTO_IPIP))
goto drop;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto drop;
skb->protocol = htons(ETH_P_IP);
iph = ip_hdr(skb);
nhaddr = slwt->nh4.s_addr ?: iph->daddr;
skb_dst_drop(skb);
err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev);
if (err)
goto drop;
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int input_action_end_dt6(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
if (!decap_and_validate(skb, IPPROTO_IPV6))
goto drop;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
seg6_lookup_nexthop(skb, NULL, slwt->table);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
/* push an SRH on top of the current one */
static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
int err = -EINVAL;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
err = seg6_do_srh_inline(skb, slwt->srh);
if (err)
goto drop;
ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return err;
}
/* encapsulate within an outer IPv6 header and a specified SRH */
static int input_action_end_b6_encap(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
int err = -EINVAL;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
err = seg6_do_srh_encap(skb, slwt->srh, IPPROTO_IPV6);
if (err)
goto drop;
ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return err;
}
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. These helpers require CONFIG_IPV6=y (and not =m). Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:14 +08:00
DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
bool seg6_bpf_has_valid_srh(struct sk_buff *skb)
{
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
struct ipv6_sr_hdr *srh = srh_state->srh;
if (unlikely(srh == NULL))
return false;
if (unlikely(!srh_state->valid)) {
if ((srh_state->hdrlen & 7) != 0)
return false;
srh->hdrlen = (u8)(srh_state->hdrlen >> 3);
if (!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3))
return false;
srh_state->valid = true;
}
return true;
}
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
static int input_action_end_bpf(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
struct ipv6_sr_hdr *srh;
int ret;
srh = get_and_validate_srh(skb);
if (!srh) {
kfree_skb(skb);
return -EINVAL;
}
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
/* preempt_disable is needed to protect the per-CPU buffer srh_state,
* which is also accessed by the bpf_lwt_seg6_* helpers
*/
preempt_disable();
srh_state->srh = srh;
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
srh_state->hdrlen = srh->hdrlen << 3;
srh_state->valid = true;
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
rcu_read_lock();
bpf_compute_data_pointers(skb);
ret = bpf_prog_run_save_cb(slwt->bpf.prog, skb);
rcu_read_unlock();
switch (ret) {
case BPF_OK:
case BPF_REDIRECT:
break;
case BPF_DROP:
goto drop;
default:
pr_warn_once("bpf-seg6local: Illegal return value %u\n", ret);
goto drop;
}
if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
goto drop;
preempt_enable();
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
if (ret != BPF_REDIRECT)
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
preempt_enable();
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
kfree_skb(skb);
return -EINVAL;
}
static struct seg6_action_desc seg6_action_table[] = {
{
.action = SEG6_LOCAL_ACTION_END,
.attrs = 0,
.input = input_action_end,
},
{
.action = SEG6_LOCAL_ACTION_END_X,
.attrs = (1 << SEG6_LOCAL_NH6),
.input = input_action_end_x,
},
{
.action = SEG6_LOCAL_ACTION_END_T,
.attrs = (1 << SEG6_LOCAL_TABLE),
.input = input_action_end_t,
},
{
.action = SEG6_LOCAL_ACTION_END_DX2,
.attrs = (1 << SEG6_LOCAL_OIF),
.input = input_action_end_dx2,
},
{
.action = SEG6_LOCAL_ACTION_END_DX6,
.attrs = (1 << SEG6_LOCAL_NH6),
.input = input_action_end_dx6,
},
{
.action = SEG6_LOCAL_ACTION_END_DX4,
.attrs = (1 << SEG6_LOCAL_NH4),
.input = input_action_end_dx4,
},
{
.action = SEG6_LOCAL_ACTION_END_DT6,
.attrs = (1 << SEG6_LOCAL_TABLE),
.input = input_action_end_dt6,
},
{
.action = SEG6_LOCAL_ACTION_END_B6,
.attrs = (1 << SEG6_LOCAL_SRH),
.input = input_action_end_b6,
},
{
.action = SEG6_LOCAL_ACTION_END_B6_ENCAP,
.attrs = (1 << SEG6_LOCAL_SRH),
.input = input_action_end_b6_encap,
.static_headroom = sizeof(struct ipv6hdr),
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
},
{
.action = SEG6_LOCAL_ACTION_END_BPF,
.attrs = (1 << SEG6_LOCAL_BPF),
.input = input_action_end_bpf,
},
};
static struct seg6_action_desc *__get_action_desc(int action)
{
struct seg6_action_desc *desc;
int i, count;
count = ARRAY_SIZE(seg6_action_table);
for (i = 0; i < count; i++) {
desc = &seg6_action_table[i];
if (desc->action == action)
return desc;
}
return NULL;
}
static int seg6_local_input(struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
struct seg6_action_desc *desc;
struct seg6_local_lwt *slwt;
if (skb->protocol != htons(ETH_P_IPV6)) {
kfree_skb(skb);
return -EINVAL;
}
slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
desc = slwt->desc;
return desc->input(skb, slwt);
}
static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
[SEG6_LOCAL_ACTION] = { .type = NLA_U32 },
[SEG6_LOCAL_SRH] = { .type = NLA_BINARY },
[SEG6_LOCAL_TABLE] = { .type = NLA_U32 },
[SEG6_LOCAL_NH4] = { .type = NLA_BINARY,
.len = sizeof(struct in_addr) },
[SEG6_LOCAL_NH6] = { .type = NLA_BINARY,
.len = sizeof(struct in6_addr) },
[SEG6_LOCAL_IIF] = { .type = NLA_U32 },
[SEG6_LOCAL_OIF] = { .type = NLA_U32 },
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
[SEG6_LOCAL_BPF] = { .type = NLA_NESTED },
};
static int parse_nla_srh(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
int len;
srh = nla_data(attrs[SEG6_LOCAL_SRH]);
len = nla_len(attrs[SEG6_LOCAL_SRH]);
/* SRH must contain at least one segment */
if (len < sizeof(*srh) + sizeof(struct in6_addr))
return -EINVAL;
if (!seg6_validate_srh(srh, len))
return -EINVAL;
slwt->srh = kmemdup(srh, len, GFP_KERNEL);
if (!slwt->srh)
return -ENOMEM;
slwt->headroom += len;
return 0;
}
static int put_nla_srh(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
struct nlattr *nla;
int len;
srh = slwt->srh;
len = (srh->hdrlen + 1) << 3;
nla = nla_reserve(skb, SEG6_LOCAL_SRH, len);
if (!nla)
return -EMSGSIZE;
memcpy(nla_data(nla), srh, len);
return 0;
}
static int cmp_nla_srh(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
int len = (a->srh->hdrlen + 1) << 3;
if (len != ((b->srh->hdrlen + 1) << 3))
return 1;
return memcmp(a->srh, b->srh, len);
}
static int parse_nla_table(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
slwt->table = nla_get_u32(attrs[SEG6_LOCAL_TABLE]);
return 0;
}
static int put_nla_table(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
if (nla_put_u32(skb, SEG6_LOCAL_TABLE, slwt->table))
return -EMSGSIZE;
return 0;
}
static int cmp_nla_table(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
if (a->table != b->table)
return 1;
return 0;
}
static int parse_nla_nh4(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
memcpy(&slwt->nh4, nla_data(attrs[SEG6_LOCAL_NH4]),
sizeof(struct in_addr));
return 0;
}
static int put_nla_nh4(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct nlattr *nla;
nla = nla_reserve(skb, SEG6_LOCAL_NH4, sizeof(struct in_addr));
if (!nla)
return -EMSGSIZE;
memcpy(nla_data(nla), &slwt->nh4, sizeof(struct in_addr));
return 0;
}
static int cmp_nla_nh4(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
return memcmp(&a->nh4, &b->nh4, sizeof(struct in_addr));
}
static int parse_nla_nh6(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
memcpy(&slwt->nh6, nla_data(attrs[SEG6_LOCAL_NH6]),
sizeof(struct in6_addr));
return 0;
}
static int put_nla_nh6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct nlattr *nla;
nla = nla_reserve(skb, SEG6_LOCAL_NH6, sizeof(struct in6_addr));
if (!nla)
return -EMSGSIZE;
memcpy(nla_data(nla), &slwt->nh6, sizeof(struct in6_addr));
return 0;
}
static int cmp_nla_nh6(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
return memcmp(&a->nh6, &b->nh6, sizeof(struct in6_addr));
}
static int parse_nla_iif(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
slwt->iif = nla_get_u32(attrs[SEG6_LOCAL_IIF]);
return 0;
}
static int put_nla_iif(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
if (nla_put_u32(skb, SEG6_LOCAL_IIF, slwt->iif))
return -EMSGSIZE;
return 0;
}
static int cmp_nla_iif(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
if (a->iif != b->iif)
return 1;
return 0;
}
static int parse_nla_oif(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
slwt->oif = nla_get_u32(attrs[SEG6_LOCAL_OIF]);
return 0;
}
static int put_nla_oif(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
if (nla_put_u32(skb, SEG6_LOCAL_OIF, slwt->oif))
return -EMSGSIZE;
return 0;
}
static int cmp_nla_oif(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
if (a->oif != b->oif)
return 1;
return 0;
}
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
#define MAX_PROG_NAME 256
static const struct nla_policy bpf_prog_policy[SEG6_LOCAL_BPF_PROG_MAX + 1] = {
[SEG6_LOCAL_BPF_PROG] = { .type = NLA_U32, },
[SEG6_LOCAL_BPF_PROG_NAME] = { .type = NLA_NUL_STRING,
.len = MAX_PROG_NAME },
};
static int parse_nla_bpf(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
struct nlattr *tb[SEG6_LOCAL_BPF_PROG_MAX + 1];
struct bpf_prog *p;
int ret;
u32 fd;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
ret = nla_parse_nested_deprecated(tb, SEG6_LOCAL_BPF_PROG_MAX,
attrs[SEG6_LOCAL_BPF],
bpf_prog_policy, NULL);
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
if (ret < 0)
return ret;
if (!tb[SEG6_LOCAL_BPF_PROG] || !tb[SEG6_LOCAL_BPF_PROG_NAME])
return -EINVAL;
slwt->bpf.name = nla_memdup(tb[SEG6_LOCAL_BPF_PROG_NAME], GFP_KERNEL);
if (!slwt->bpf.name)
return -ENOMEM;
fd = nla_get_u32(tb[SEG6_LOCAL_BPF_PROG]);
p = bpf_prog_get_type(fd, BPF_PROG_TYPE_LWT_SEG6LOCAL);
if (IS_ERR(p)) {
kfree(slwt->bpf.name);
return PTR_ERR(p);
}
slwt->bpf.prog = p;
return 0;
}
static int put_nla_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct nlattr *nest;
if (!slwt->bpf.prog)
return 0;
nest = nla_nest_start_noflag(skb, SEG6_LOCAL_BPF);
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
if (!nest)
return -EMSGSIZE;
if (nla_put_u32(skb, SEG6_LOCAL_BPF_PROG, slwt->bpf.prog->aux->id))
return -EMSGSIZE;
if (slwt->bpf.name &&
nla_put_string(skb, SEG6_LOCAL_BPF_PROG_NAME, slwt->bpf.name))
return -EMSGSIZE;
return nla_nest_end(skb, nest);
}
static int cmp_nla_bpf(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
if (!a->bpf.name && !b->bpf.name)
return 0;
if (!a->bpf.name || !b->bpf.name)
return 1;
return strcmp(a->bpf.name, b->bpf.name);
}
struct seg6_action_param {
int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt);
int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
int (*cmp)(struct seg6_local_lwt *a, struct seg6_local_lwt *b);
};
static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {
[SEG6_LOCAL_SRH] = { .parse = parse_nla_srh,
.put = put_nla_srh,
.cmp = cmp_nla_srh },
[SEG6_LOCAL_TABLE] = { .parse = parse_nla_table,
.put = put_nla_table,
.cmp = cmp_nla_table },
[SEG6_LOCAL_NH4] = { .parse = parse_nla_nh4,
.put = put_nla_nh4,
.cmp = cmp_nla_nh4 },
[SEG6_LOCAL_NH6] = { .parse = parse_nla_nh6,
.put = put_nla_nh6,
.cmp = cmp_nla_nh6 },
[SEG6_LOCAL_IIF] = { .parse = parse_nla_iif,
.put = put_nla_iif,
.cmp = cmp_nla_iif },
[SEG6_LOCAL_OIF] = { .parse = parse_nla_oif,
.put = put_nla_oif,
.cmp = cmp_nla_oif },
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
[SEG6_LOCAL_BPF] = { .parse = parse_nla_bpf,
.put = put_nla_bpf,
.cmp = cmp_nla_bpf },
};
static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
struct seg6_action_param *param;
struct seg6_action_desc *desc;
int i, err;
desc = __get_action_desc(slwt->action);
if (!desc)
return -EINVAL;
if (!desc->input)
return -EOPNOTSUPP;
slwt->desc = desc;
slwt->headroom += desc->static_headroom;
for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
if (desc->attrs & (1 << i)) {
if (!attrs[i])
return -EINVAL;
param = &seg6_action_params[i];
err = param->parse(attrs, slwt);
if (err < 0)
return err;
}
}
return 0;
}
static int seg6_local_build_state(struct nlattr *nla, unsigned int family,
const void *cfg, struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[SEG6_LOCAL_MAX + 1];
struct lwtunnel_state *newts;
struct seg6_local_lwt *slwt;
int err;
if (family != AF_INET6)
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, SEG6_LOCAL_MAX, nla,
seg6_local_policy, extack);
if (err < 0)
return err;
if (!tb[SEG6_LOCAL_ACTION])
return -EINVAL;
newts = lwtunnel_state_alloc(sizeof(*slwt));
if (!newts)
return -ENOMEM;
slwt = seg6_local_lwtunnel(newts);
slwt->action = nla_get_u32(tb[SEG6_LOCAL_ACTION]);
err = parse_nla_action(tb, slwt);
if (err < 0)
goto out_free;
newts->type = LWTUNNEL_ENCAP_SEG6_LOCAL;
newts->flags = LWTUNNEL_STATE_INPUT_REDIRECT;
newts->headroom = slwt->headroom;
*ts = newts;
return 0;
out_free:
kfree(slwt->srh);
kfree(newts);
return err;
}
static void seg6_local_destroy_state(struct lwtunnel_state *lwt)
{
struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
kfree(slwt->srh);
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
if (slwt->desc->attrs & (1 << SEG6_LOCAL_BPF)) {
kfree(slwt->bpf.name);
bpf_prog_put(slwt->bpf.prog);
}
return;
}
static int seg6_local_fill_encap(struct sk_buff *skb,
struct lwtunnel_state *lwt)
{
struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
struct seg6_action_param *param;
int i, err;
if (nla_put_u32(skb, SEG6_LOCAL_ACTION, slwt->action))
return -EMSGSIZE;
for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
if (slwt->desc->attrs & (1 << i)) {
param = &seg6_action_params[i];
err = param->put(skb, slwt);
if (err < 0)
return err;
}
}
return 0;
}
static int seg6_local_get_encap_size(struct lwtunnel_state *lwt)
{
struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
unsigned long attrs;
int nlsize;
nlsize = nla_total_size(4); /* action */
attrs = slwt->desc->attrs;
if (attrs & (1 << SEG6_LOCAL_SRH))
nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3);
if (attrs & (1 << SEG6_LOCAL_TABLE))
nlsize += nla_total_size(4);
if (attrs & (1 << SEG6_LOCAL_NH4))
nlsize += nla_total_size(4);
if (attrs & (1 << SEG6_LOCAL_NH6))
nlsize += nla_total_size(16);
if (attrs & (1 << SEG6_LOCAL_IIF))
nlsize += nla_total_size(4);
if (attrs & (1 << SEG6_LOCAL_OIF))
nlsize += nla_total_size(4);
ipv6: sr: Add seg6local action End.BPF This patch adds the End.BPF action to the LWT seg6local infrastructure. This action works like any other seg6local End action, meaning that an IPv6 header with SRH is needed, whose DA has to be equal to the SID of the action. It will also advance the SRH to the next segment, the BPF program does not have to take care of this. Since the BPF program may not be a source of instability in the kernel, it is important to ensure that the integrity of the packet is maintained before yielding it back to the IPv6 layer. The hook hence keeps track if the SRH has been altered through the helpers, and re-validates its content if needed with seg6_validate_srh. The state kept for validation is stored in a per-CPU buffer. The BPF program is not allowed to directly write into the packet, and only some fields of the SRH can be altered through the helper bpf_lwt_seg6_store_bytes. Performances profiling has shown that the SRH re-validation does not induce a significant overhead. If the altered SRH is deemed as invalid, the packet is dropped. This validation is also done before executing any action through bpf_lwt_seg6_action, and will not be performed again if the SRH is not modified after calling the action. The BPF program may return 3 types of return codes: - BPF_OK: the End.BPF action will look up the next destination through seg6_lookup_nexthop. - BPF_REDIRECT: if an action has been executed through the bpf_lwt_seg6_action helper, the BPF program should return this value, as the skb's destination is already set and the default lookup should not be performed. - BPF_DROP : the packet will be dropped. Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-20 21:58:16 +08:00
if (attrs & (1 << SEG6_LOCAL_BPF))
nlsize += nla_total_size(sizeof(struct nlattr)) +
nla_total_size(MAX_PROG_NAME) +
nla_total_size(4);
return nlsize;
}
static int seg6_local_cmp_encap(struct lwtunnel_state *a,
struct lwtunnel_state *b)
{
struct seg6_local_lwt *slwt_a, *slwt_b;
struct seg6_action_param *param;
int i;
slwt_a = seg6_local_lwtunnel(a);
slwt_b = seg6_local_lwtunnel(b);
if (slwt_a->action != slwt_b->action)
return 1;
if (slwt_a->desc->attrs != slwt_b->desc->attrs)
return 1;
for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
if (slwt_a->desc->attrs & (1 << i)) {
param = &seg6_action_params[i];
if (param->cmp(slwt_a, slwt_b))
return 1;
}
}
return 0;
}
static const struct lwtunnel_encap_ops seg6_local_ops = {
.build_state = seg6_local_build_state,
.destroy_state = seg6_local_destroy_state,
.input = seg6_local_input,
.fill_encap = seg6_local_fill_encap,
.get_encap_size = seg6_local_get_encap_size,
.cmp_encap = seg6_local_cmp_encap,
.owner = THIS_MODULE,
};
int __init seg6_local_init(void)
{
return lwtunnel_encap_add_ops(&seg6_local_ops,
LWTUNNEL_ENCAP_SEG6_LOCAL);
}
void seg6_local_exit(void)
{
lwtunnel_encap_del_ops(&seg6_local_ops, LWTUNNEL_ENCAP_SEG6_LOCAL);
}