From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/net/xfrm/xfrm_output.c | 524 +++++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 497 insertions(+), 27 deletions(-)
diff --git a/kernel/net/xfrm/xfrm_output.c b/kernel/net/xfrm/xfrm_output.c
index c461628..381a5c1 100644
--- a/kernel/net/xfrm/xfrm_output.c
+++ b/kernel/net/xfrm/xfrm_output.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* xfrm_output.c - Common IPsec encapsulation code.
*
* Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
- *
- * 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.
*/
#include <linux/errno.h>
@@ -17,9 +13,19 @@
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
+#include <net/icmp.h>
+#include <net/inet_ecn.h>
#include <net/xfrm.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_route.h>
+#include <net/ipv6_stubs.h>
+#endif
+
+#include "xfrm_inout.h"
+
static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);
+static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
static int xfrm_skb_check_space(struct sk_buff *skb)
{
@@ -50,6 +56,358 @@
return child;
}
+/* Add encapsulation header.
+ *
+ * The IP header will be moved forward to make space for the encapsulation
+ * header.
+ */
+static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct iphdr *iph = ip_hdr(skb);
+ int ihl = iph->ihl * 4;
+
+ skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+ skb_set_network_header(skb, -x->props.header_len);
+ skb->mac_header = skb->network_header +
+ offsetof(struct iphdr, protocol);
+ skb->transport_header = skb->network_header + ihl;
+ __skb_pull(skb, ihl);
+ memmove(skb_network_header(skb), iph, ihl);
+ return 0;
+}
+
+/* Add encapsulation header.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the encapsulation header.
+ */
+static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ struct ipv6hdr *iph;
+ u8 *prevhdr;
+ int hdr_len;
+
+ iph = ipv6_hdr(skb);
+ skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+ hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+ if (hdr_len < 0)
+ return hdr_len;
+ skb_set_mac_header(skb,
+ (prevhdr - x->props.header_len) - skb->data);
+ skb_set_network_header(skb, -x->props.header_len);
+ skb->transport_header = skb->network_header + hdr_len;
+ __skb_pull(skb, hdr_len);
+ memmove(ipv6_hdr(skb), iph, hdr_len);
+ return 0;
+#else
+ WARN_ON_ONCE(1);
+ return -EAFNOSUPPORT;
+#endif
+}
+
+/* Add route optimization header space.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the route optimization header.
+ */
+static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ struct ipv6hdr *iph;
+ u8 *prevhdr;
+ int hdr_len;
+
+ iph = ipv6_hdr(skb);
+
+ hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+ if (hdr_len < 0)
+ return hdr_len;
+ skb_set_mac_header(skb,
+ (prevhdr - x->props.header_len) - skb->data);
+ skb_set_network_header(skb, -x->props.header_len);
+ skb->transport_header = skb->network_header + hdr_len;
+ __skb_pull(skb, hdr_len);
+ memmove(ipv6_hdr(skb), iph, hdr_len);
+
+ x->lastused = ktime_get_real_seconds();
+
+ return 0;
+#else
+ WARN_ON_ONCE(1);
+ return -EAFNOSUPPORT;
+#endif
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
+ */
+static int xfrm4_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ip_beet_phdr *ph;
+ struct iphdr *top_iph;
+ int hdrlen, optlen;
+
+ hdrlen = 0;
+ optlen = XFRM_MODE_SKB_CB(skb)->optlen;
+ if (unlikely(optlen))
+ hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
+
+ skb_set_network_header(skb, -x->props.header_len - hdrlen +
+ (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
+ if (x->sel.family != AF_INET6)
+ skb->network_header += IPV4_BEET_PHMAXLEN;
+ skb->mac_header = skb->network_header +
+ offsetof(struct iphdr, protocol);
+ skb->transport_header = skb->network_header + sizeof(*top_iph);
+
+ xfrm4_beet_make_header(skb);
+
+ ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen);
+
+ top_iph = ip_hdr(skb);
+
+ if (unlikely(optlen)) {
+ if (WARN_ON(optlen < 0))
+ return -EINVAL;
+
+ ph->padlen = 4 - (optlen & 4);
+ ph->hdrlen = optlen / 8;
+ ph->nexthdr = top_iph->protocol;
+ if (ph->padlen)
+ memset(ph + 1, IPOPT_NOP, ph->padlen);
+
+ top_iph->protocol = IPPROTO_BEETPH;
+ top_iph->ihl = sizeof(struct iphdr) / 4;
+ }
+
+ top_iph->saddr = x->props.saddr.a4;
+ top_iph->daddr = x->id.daddr.a4;
+
+ return 0;
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per RFC 2401.
+ */
+static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ struct iphdr *top_iph;
+ int flags;
+
+ skb_set_inner_network_header(skb, skb_network_offset(skb));
+ skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+ skb_set_network_header(skb, -x->props.header_len);
+ skb->mac_header = skb->network_header +
+ offsetof(struct iphdr, protocol);
+ skb->transport_header = skb->network_header + sizeof(*top_iph);
+ top_iph = ip_hdr(skb);
+
+ top_iph->ihl = 5;
+ top_iph->version = 4;
+
+ top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
+
+ /* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
+ if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+ top_iph->tos = 0;
+ else
+ top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
+ top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
+ XFRM_MODE_SKB_CB(skb)->tos);
+
+ flags = x->props.flags;
+ if (flags & XFRM_STATE_NOECN)
+ IP_ECN_clear(top_iph);
+
+ top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
+ 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
+
+ top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst));
+
+ top_iph->saddr = x->props.saddr.a4;
+ top_iph->daddr = x->id.daddr.a4;
+ ip_select_ident(dev_net(dst->dev), skb, NULL);
+
+ return 0;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int xfrm6_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ struct ipv6hdr *top_iph;
+ int dsfield;
+
+ skb_set_inner_network_header(skb, skb_network_offset(skb));
+ skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+ skb_set_network_header(skb, -x->props.header_len);
+ skb->mac_header = skb->network_header +
+ offsetof(struct ipv6hdr, nexthdr);
+ skb->transport_header = skb->network_header + sizeof(*top_iph);
+ top_iph = ipv6_hdr(skb);
+
+ top_iph->version = 6;
+
+ memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
+ sizeof(top_iph->flow_lbl));
+ top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
+
+ if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+ dsfield = 0;
+ else
+ dsfield = XFRM_MODE_SKB_CB(skb)->tos;
+ dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos);
+ if (x->props.flags & XFRM_STATE_NOECN)
+ dsfield &= ~INET_ECN_MASK;
+ ipv6_change_dsfield(top_iph, 0, dsfield);
+ top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst));
+ top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+ top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
+ return 0;
+}
+
+static int xfrm6_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *top_iph;
+ struct ip_beet_phdr *ph;
+ int optlen, hdr_len;
+
+ hdr_len = 0;
+ optlen = XFRM_MODE_SKB_CB(skb)->optlen;
+ if (unlikely(optlen))
+ hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4);
+
+ skb_set_network_header(skb, -x->props.header_len - hdr_len);
+ if (x->sel.family != AF_INET6)
+ skb->network_header += IPV4_BEET_PHMAXLEN;
+ skb->mac_header = skb->network_header +
+ offsetof(struct ipv6hdr, nexthdr);
+ skb->transport_header = skb->network_header + sizeof(*top_iph);
+ ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len);
+
+ xfrm6_beet_make_header(skb);
+
+ top_iph = ipv6_hdr(skb);
+ if (unlikely(optlen)) {
+ if (WARN_ON(optlen < 0))
+ return -EINVAL;
+
+ ph->padlen = 4 - (optlen & 4);
+ ph->hdrlen = optlen / 8;
+ ph->nexthdr = top_iph->nexthdr;
+ if (ph->padlen)
+ memset(ph + 1, IPOPT_NOP, ph->padlen);
+
+ top_iph->nexthdr = IPPROTO_BEETPH;
+ }
+
+ top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+ top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
+ return 0;
+}
+#endif
+
+/* Add encapsulation header.
+ *
+ * On exit, the transport header will be set to the start of the
+ * encapsulation header to be filled in by x->type->output and the mac
+ * header will be set to the nextheader (protocol for IPv4) field of the
+ * extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header.
+ * The value of the network header will always point to the top IP header
+ * while skb->data will point to the payload.
+ */
+static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ int err;
+
+ err = xfrm_inner_extract_output(x, skb);
+ if (err)
+ return err;
+
+ IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+ skb->protocol = htons(ETH_P_IP);
+
+ switch (x->outer_mode.encap) {
+ case XFRM_MODE_BEET:
+ return xfrm4_beet_encap_add(x, skb);
+ case XFRM_MODE_TUNNEL:
+ return xfrm4_tunnel_encap_add(x, skb);
+ }
+
+ WARN_ON_ONCE(1);
+ return -EOPNOTSUPP;
+}
+
+static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ int err;
+
+ err = xfrm_inner_extract_output(x, skb);
+ if (err)
+ return err;
+
+ skb->ignore_df = 1;
+ skb->protocol = htons(ETH_P_IPV6);
+
+ switch (x->outer_mode.encap) {
+ case XFRM_MODE_BEET:
+ return xfrm6_beet_encap_add(x, skb);
+ case XFRM_MODE_TUNNEL:
+ return xfrm6_tunnel_encap_add(x, skb);
+ default:
+ WARN_ON_ONCE(1);
+ return -EOPNOTSUPP;
+ }
+#endif
+ WARN_ON_ONCE(1);
+ return -EAFNOSUPPORT;
+}
+
+static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ switch (x->outer_mode.encap) {
+ case XFRM_MODE_BEET:
+ case XFRM_MODE_TUNNEL:
+ if (x->outer_mode.family == AF_INET)
+ return xfrm4_prepare_output(x, skb);
+ if (x->outer_mode.family == AF_INET6)
+ return xfrm6_prepare_output(x, skb);
+ break;
+ case XFRM_MODE_TRANSPORT:
+ if (x->outer_mode.family == AF_INET)
+ return xfrm4_transport_output(x, skb);
+ if (x->outer_mode.family == AF_INET6)
+ return xfrm6_transport_output(x, skb);
+ break;
+ case XFRM_MODE_ROUTEOPTIMIZATION:
+ if (x->outer_mode.family == AF_INET6)
+ return xfrm6_ro_output(x, skb);
+ WARN_ON_ONCE(1);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ return xfrm_outer_mode_output(x, skb);
+}
+EXPORT_SYMBOL_GPL(pktgen_xfrm_outer_mode_output);
+
static int xfrm_output_one(struct sk_buff *skb, int err)
{
struct dst_entry *dst = skb_dst(skb);
@@ -68,7 +426,7 @@
skb->mark = xfrm_smark_get(skb->mark, x);
- err = x->outer_mode->output(x, skb);
+ err = xfrm_outer_mode_output(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
goto error_nolock;
@@ -131,7 +489,7 @@
}
skb_dst_set(skb, dst);
x = dst->xfrm;
- } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));
+ } while (x && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL));
return 0;
@@ -148,7 +506,7 @@
struct net *net = xs_net(skb_dst(skb)->xfrm);
while (likely((err = xfrm_output_one(skb, err)) == 0)) {
- nf_reset(skb);
+ nf_reset_ct(skb);
err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
if (unlikely(err != 1))
@@ -179,10 +537,10 @@
static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct sk_buff *segs;
+ struct sk_buff *segs, *nskb;
- BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
- BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
+ BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET);
+ BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_GSO_CB_OFFSET);
segs = skb_gso_segment(skb, 0);
kfree_skb(skb);
if (IS_ERR(segs))
@@ -190,20 +548,17 @@
if (segs == NULL)
return -EINVAL;
- do {
- struct sk_buff *nskb = segs->next;
+ skb_list_walk_safe(segs, segs, nskb) {
int err;
- segs->next = NULL;
+ skb_mark_not_on_list(segs);
err = xfrm_output2(net, sk, segs);
if (unlikely(err)) {
kfree_skb_list(nskb);
return err;
}
-
- segs = nskb;
- } while (segs);
+ }
return 0;
}
@@ -214,24 +569,33 @@
struct xfrm_state *x = skb_dst(skb)->xfrm;
int err;
+ switch (x->outer_mode.family) {
+ case AF_INET:
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
+ break;
+ case AF_INET6:
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
+ IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
+ break;
+ }
+
secpath_reset(skb);
if (xfrm_dev_offload_ok(skb, x)) {
struct sec_path *sp;
- sp = secpath_dup(skb->sp);
+ sp = secpath_set(skb);
if (!sp) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
kfree_skb(skb);
return -ENOMEM;
}
- if (skb->sp)
- secpath_put(skb->sp);
- skb->sp = sp;
skb->encapsulation = 1;
sp->olen++;
- sp->xvec[skb->sp->len++] = x;
+ sp->xvec[sp->len++] = x;
xfrm_state_hold(x);
if (skb_is_gso(skb)) {
@@ -263,20 +627,126 @@
}
EXPORT_SYMBOL_GPL(xfrm_output);
-int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+static int xfrm4_tunnel_check_size(struct sk_buff *skb)
{
- struct xfrm_mode *inner_mode;
+ int mtu, ret = 0;
+
+ if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE)
+ goto out;
+
+ if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df)
+ goto out;
+
+ mtu = dst_mtu(skb_dst(skb));
+ if ((!skb_is_gso(skb) && skb->len > mtu) ||
+ (skb_is_gso(skb) &&
+ !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) {
+ skb->protocol = htons(ETH_P_IP);
+
+ if (skb->sk)
+ xfrm_local_error(skb, mtu);
+ else
+ icmp_send(skb, ICMP_DEST_UNREACH,
+ ICMP_FRAG_NEEDED, htonl(mtu));
+ ret = -EMSGSIZE;
+ }
+out:
+ return ret;
+}
+
+static int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ int err;
+
+ if (x->outer_mode.encap == XFRM_MODE_BEET &&
+ ip_is_fragment(ip_hdr(skb))) {
+ net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n");
+ return -EAFNOSUPPORT;
+ }
+
+ err = xfrm4_tunnel_check_size(skb);
+ if (err)
+ return err;
+
+ XFRM_MODE_SKB_CB(skb)->protocol = ip_hdr(skb)->protocol;
+
+ xfrm4_extract_header(skb);
+ return 0;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int xfrm6_tunnel_check_size(struct sk_buff *skb)
+{
+ int mtu, ret = 0;
+ struct dst_entry *dst = skb_dst(skb);
+
+ if (skb->ignore_df)
+ goto out;
+
+ mtu = dst_mtu(dst);
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+
+ if ((!skb_is_gso(skb) && skb->len > mtu) ||
+ (skb_is_gso(skb) &&
+ !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) {
+ skb->dev = dst->dev;
+ skb->protocol = htons(ETH_P_IPV6);
+
+ if (xfrm6_local_dontfrag(skb->sk))
+ ipv6_stub->xfrm6_local_rxpmtu(skb, mtu);
+ else if (skb->sk)
+ xfrm_local_error(skb, mtu);
+ else
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ ret = -EMSGSIZE;
+ }
+out:
+ return ret;
+}
+#endif
+
+static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ int err;
+
+ err = xfrm6_tunnel_check_size(skb);
+ if (err)
+ return err;
+
+ XFRM_MODE_SKB_CB(skb)->protocol = ipv6_hdr(skb)->nexthdr;
+
+ xfrm6_extract_header(skb);
+ return 0;
+#else
+ WARN_ON_ONCE(1);
+ return -EAFNOSUPPORT;
+#endif
+}
+
+static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ const struct xfrm_mode *inner_mode;
+
if (x->sel.family == AF_UNSPEC)
inner_mode = xfrm_ip2inner_mode(x,
xfrm_af2proto(skb_dst(skb)->ops->family));
else
- inner_mode = x->inner_mode;
+ inner_mode = &x->inner_mode;
if (inner_mode == NULL)
return -EAFNOSUPPORT;
- return inner_mode->afinfo->extract_output(x, skb);
+
+ switch (inner_mode->family) {
+ case AF_INET:
+ return xfrm4_extract_output(x, skb);
+ case AF_INET6:
+ return xfrm6_extract_output(x, skb);
+ }
+
+ return -EAFNOSUPPORT;
}
-EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);
void xfrm_local_error(struct sk_buff *skb, int mtu)
{
--
Gitblit v1.6.2