From 8fc0e3b6a8666d656923d214e4dc791e9a17164a Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sat, 20 Feb 2021 15:01:15 +0200 Subject: xfrm: interface: fix ipv4 pmtu check to honor ip header df Frag needed should only be sent if the header enables DF. This fix allows packets larger than MTU to pass the xfrm interface and be fragmented after encapsulation, aligning behavior with non-interface xfrm. Fixes: f203b76d7809 ("xfrm: Add virtual xfrm interfaces") Signed-off-by: Eyal Birger Reviewed-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_interface.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 495b1f5c979b..8831f5a9e992 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -306,6 +306,8 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { + if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } @@ -314,6 +316,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) return -EMSGSIZE; } +xmit: xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = tdev; -- cgit v1.2.3-58-ga151 From 9ab1265d52314fce1b51e8665ea6dbc9ac1a027c Mon Sep 17 00:00:00 2001 From: Evan Nimmo Date: Tue, 2 Mar 2021 08:00:04 +1300 Subject: xfrm: Use actual socket sk instead of skb socket for xfrm_output_resume A situation can occur where the interface bound to the sk is different to the interface bound to the sk attached to the skb. The interface bound to the sk is the correct one however this information is lost inside xfrm_output2 and instead the sk on the skb is used in xfrm_output_resume instead. This assumes that the sk bound interface and the bound interface attached to the sk within the skb are the same which can lead to lookup failures inside ip_route_me_harder resulting in the packet being dropped. We have an l2tp v3 tunnel with ipsec protection. The tunnel is in the global VRF however we have an encapsulated dot1q tunnel interface that is within a different VRF. We also have a mangle rule that marks the packets causing them to be processed inside ip_route_me_harder. Prior to commit 31c70d5956fc ("l2tp: keep original skb ownership") this worked fine as the sk attached to the skb was changed from the dot1q encapsulated interface to the sk for the tunnel which meant the interface bound to the sk and the interface bound to the skb were identical. Commit 46d6c5ae953c ("netfilter: use actual socket sk rather than skb sk when routing harder") fixed some of these issues however a similar problem existed in the xfrm code. Fixes: 31c70d5956fc ("l2tp: keep original skb ownership") Signed-off-by: Evan Nimmo Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 2 +- net/ipv4/ah4.c | 2 +- net/ipv4/esp4.c | 2 +- net/ipv6/ah6.c | 2 +- net/ipv6/esp6.c | 2 +- net/xfrm/xfrm_output.c | 10 +++++----- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'net/xfrm') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b2a06f10b62c..bfbc7810df94 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1557,7 +1557,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, int xfrm_trans_queue(struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); -int xfrm_output_resume(struct sk_buff *skb, int err); +int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); #if IS_ENABLED(CONFIG_NET_PKTGEN) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index d99e1be94019..36ed85bf2ad5 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -141,7 +141,7 @@ static void ah_output_done(struct crypto_async_request *base, int err) } kfree(AH_SKB_CB(skb)->tmp); - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } static int ah_output(struct xfrm_state *x, struct sk_buff *skb) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index a3271ec3e162..4b834bbf95e0 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -279,7 +279,7 @@ static void esp_output_done(struct crypto_async_request *base, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 440080da805b..080ee7f44c64 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -316,7 +316,7 @@ static void ah6_output_done(struct crypto_async_request *base, int err) } kfree(AH_SKB_CB(skb)->tmp); - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 153ad103ba74..727d791ed5e6 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -314,7 +314,7 @@ static void esp_output_done(struct crypto_async_request *base, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } } diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index a7ab19353313..b81ca117dac7 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -503,22 +503,22 @@ out: return err; } -int xfrm_output_resume(struct sk_buff *skb, int err) +int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err) { struct net *net = xs_net(skb_dst(skb)->xfrm); while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset_ct(skb); - err = skb_dst(skb)->ops->local_out(net, skb->sk, skb); + err = skb_dst(skb)->ops->local_out(net, sk, skb); if (unlikely(err != 1)) goto out; if (!skb_dst(skb)->xfrm) - return dst_output(net, skb->sk, skb); + return dst_output(net, sk, skb); err = nf_hook(skb_dst(skb)->ops->family, - NF_INET_POST_ROUTING, net, skb->sk, skb, + NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; @@ -534,7 +534,7 @@ EXPORT_SYMBOL_GPL(xfrm_output_resume); static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { - return xfrm_output_resume(skb, 1); + return xfrm_output_resume(sk, skb, 1); } static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) -- cgit v1.2.3-58-ga151 From e88add19f68191448427a6e4eb059664650a837f Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Tue, 16 Mar 2021 11:56:29 +0100 Subject: net: xfrm: Localize sequence counter per network namespace A sequence counter write section must be serialized or its internal state can get corrupted. The "xfrm_state_hash_generation" seqcount is global, but its write serialization lock (net->xfrm.xfrm_state_lock) is instantiated per network namespace. The write protection is thus insufficient. To provide full protection, localize the sequence counter per network namespace instead. This should be safe as both the seqcount read and write sections access data exclusively within the network namespace. It also lays the foundation for transforming "xfrm_state_hash_generation" data type from seqcount_t to seqcount_LOCKNAME_t in further commits. Fixes: b65e3d7be06f ("xfrm: state: add sequence count to detect hash resizes") Signed-off-by: Ahmed S. Darwish Signed-off-by: Steffen Klassert --- include/net/netns/xfrm.h | 4 +++- net/xfrm/xfrm_state.c | 10 +++++----- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'net/xfrm') diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 59f45b1e9dac..b59d73d529ba 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -72,7 +72,9 @@ struct netns_xfrm { #if IS_ENABLED(CONFIG_IPV6) struct dst_ops xfrm6_dst_ops; #endif - spinlock_t xfrm_state_lock; + spinlock_t xfrm_state_lock; + seqcount_t xfrm_state_hash_generation; + spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; }; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d01ca1a18418..ffd315cff984 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -44,7 +44,6 @@ static void xfrm_state_gc_task(struct work_struct *work); */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; -static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation); static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); @@ -140,7 +139,7 @@ static void xfrm_hash_resize(struct work_struct *work) } spin_lock_bh(&net->xfrm.xfrm_state_lock); - write_seqcount_begin(&xfrm_state_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); @@ -156,7 +155,7 @@ static void xfrm_hash_resize(struct work_struct *work) rcu_assign_pointer(net->xfrm.state_byspi, nspi); net->xfrm.state_hmask = nhashmask; - write_seqcount_end(&xfrm_state_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); @@ -1063,7 +1062,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, to_put = NULL; - sequence = read_seqcount_begin(&xfrm_state_hash_generation); + sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); @@ -1176,7 +1175,7 @@ out: if (to_put) xfrm_state_put(to_put); - if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) { + if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) { *err = -EAGAIN; if (x) { xfrm_state_put(x); @@ -2666,6 +2665,7 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); + seqcount_init(&net->xfrm.xfrm_state_hash_generation); return 0; out_byspi: -- cgit v1.2.3-58-ga151 From bc8e0adff343d992ca76d871e8b5e6cb86e1fad9 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Tue, 16 Mar 2021 11:56:30 +0100 Subject: net: xfrm: Use sequence counter with associated spinlock A sequence counter write section must be serialized or its internal state can get corrupted. A plain seqcount_t does not contain the information of which lock must be held to guaranteee write side serialization. For xfrm_state_hash_generation, use seqcount_spinlock_t instead of plain seqcount_t. This allows to associate the spinlock used for write serialization with the sequence counter. It thus enables lockdep to verify that the write serialization lock is indeed held before entering the sequence counter write section. If lockdep is disabled, this lock association is compiled out and has neither storage size nor runtime overhead. Signed-off-by: Ahmed S. Darwish Signed-off-by: Steffen Klassert --- include/net/netns/xfrm.h | 2 +- net/xfrm/xfrm_state.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'net/xfrm') diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index b59d73d529ba..e816b6a3ef2b 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -73,7 +73,7 @@ struct netns_xfrm { struct dst_ops xfrm6_dst_ops; #endif spinlock_t xfrm_state_lock; - seqcount_t xfrm_state_hash_generation; + seqcount_spinlock_t xfrm_state_hash_generation; spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index ffd315cff984..4496f7efa220 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2665,7 +2665,8 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); - seqcount_init(&net->xfrm.xfrm_state_hash_generation); + seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation, + &net->xfrm.xfrm_state_lock); return 0; out_byspi: -- cgit v1.2.3-58-ga151 From 68dc022d04eb0fd60a540e242dcb11ec1bee07e2 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 19 Mar 2021 18:27:58 +0800 Subject: xfrm: BEET mode doesn't support fragments for inner packets BEET mode replaces the IP(6) Headers with new IP(6) Headers when sending packets. However, when it's a fragment before the replacement, currently kernel keeps the fragment flag and replace the address field then encaps it with ESP. It would cause in RX side the fragments to get reassembled before decapping with ESP, which is incorrect. In Xiumei's testing, these fragments went over an xfrm interface and got encapped with ESP in the device driver, and the traffic was broken. I don't have a good way to fix it, but only to warn this out in dmesg. Reported-by: Xiumei Mu Signed-off-by: Xin Long Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_output.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index b81ca117dac7..e4cb0ff4dcf4 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -660,6 +660,12 @@ 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; @@ -705,8 +711,15 @@ out: static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) + unsigned int ptr = 0; int err; + if (x->outer_mode.encap == XFRM_MODE_BEET && + ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) { + net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n"); + return -EAFNOSUPPORT; + } + err = xfrm6_tunnel_check_size(skb); if (err) return err; -- cgit v1.2.3-58-ga151 From c7dbf4c08868d9db89b8bfe8f8245ca61b01ed2f Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Fri, 26 Mar 2021 09:44:48 +0100 Subject: xfrm: Provide private skb extensions for segmented and hw offloaded ESP packets Commit 94579ac3f6d0 ("xfrm: Fix double ESP trailer insertion in IPsec crypto offload.") added a XFRM_XMIT flag to avoid duplicate ESP trailer insertion on HW offload. This flag is set on the secpath that is shared amongst segments. This lead to a situation where some segments are not transformed correctly when segmentation happens at layer 3. Fix this by using private skb extensions for segmented and hw offloaded ESP packets. Fixes: 94579ac3f6d0 ("xfrm: Fix double ESP trailer insertion in IPsec crypto offload.") Signed-off-by: Steffen Klassert --- net/ipv4/esp4_offload.c | 11 ++++++++++- net/ipv6/esp6_offload.c | 11 ++++++++++- net/xfrm/xfrm_device.c | 2 -- 3 files changed, 20 insertions(+), 4 deletions(-) (limited to 'net/xfrm') diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index ed3de486ea34..33687cf58286 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -314,8 +314,17 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ ip_hdr(skb)->tot_len = htons(skb->len); ip_send_check(ip_hdr(skb)); - if (hw_offload) + if (hw_offload) { + if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) + return -ENOMEM; + + xo = xfrm_offload(skb); + if (!xo) + return -EINVAL; + + xo->flags |= XFRM_XMIT; return 0; + } err = esp_output_tail(x, skb, &esp); if (err) diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index f35203ab39f5..4af56affaafd 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -348,8 +348,17 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features ipv6_hdr(skb)->payload_len = htons(len); - if (hw_offload) + if (hw_offload) { + if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) + return -ENOMEM; + + xo = xfrm_offload(skb); + if (!xo) + return -EINVAL; + + xo->flags |= XFRM_XMIT; return 0; + } err = esp6_output_tail(x, skb, &esp); if (err) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index edf11893dbe8..6d6917b68856 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -134,8 +134,6 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - xo->flags |= XFRM_XMIT; - if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) { struct sk_buff *segs; -- cgit v1.2.3-58-ga151 From ef19e111337f6c3dca7019a8bad5fbc6fb18d635 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 30 Mar 2021 00:25:06 +0100 Subject: xfrm/compat: Cleanup WARN()s that can be user-triggered Replace WARN_ONCE() that can be triggered from userspace with pr_warn_once(). Those still give user a hint what's the issue. I've left WARN()s that are not possible to trigger with current code-base and that would mean that the code has issues: - relying on current compat_msg_min[type] <= xfrm_msg_min[type] - expected 4-byte padding size difference between compat_msg_min[type] and xfrm_msg_min[type] - compat_policy[type].len <= xfrma_policy[type].len (for every type) Reported-by: syzbot+834ffd1afc7212eb8147@syzkaller.appspotmail.com Fixes: 5f3eea6b7e8f ("xfrm/compat: Attach xfrm dumps to 64=>32 bit translator") Cc: "David S. Miller" Cc: Eric Dumazet Cc: Herbert Xu Cc: Jakub Kicinski Cc: Steffen Klassert Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_compat.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index d8e8a11ca845..a20aec9d7393 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -216,7 +216,7 @@ static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, case XFRM_MSG_GETSADINFO: case XFRM_MSG_GETSPDINFO: default: - WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type); + pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return ERR_PTR(-EOPNOTSUPP); } @@ -277,7 +277,7 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) return xfrm_nla_cpy(dst, src, nla_len(src)); default: BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); - WARN_ONCE(1, "unsupported nla_type %d", src->nla_type); + pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } } @@ -315,8 +315,10 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src struct sk_buff *new = NULL; int err; - if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min))) + if (type >= ARRAY_SIZE(xfrm_msg_min)) { + pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return -EOPNOTSUPP; + } if (skb_shinfo(skb)->frag_list == NULL) { new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC); @@ -378,6 +380,10 @@ static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, struct nlmsghdr *nlmsg = dst; struct nlattr *nla; + /* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages + * have the same len or shorted than 64-bit ones. + * 32-bit translation that is bigger than 64-bit original is unexpected. + */ if (WARN_ON_ONCE(copy_len > payload)) copy_len = payload; -- cgit v1.2.3-58-ga151