From 6a53b7593233ab9e4f96873ebacc0f653a55c3e1 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 27 Nov 2017 11:15:16 -0800 Subject: [PATCH 1/8] xfrm: check id proto in validate_tmpl() syzbot reported a kernel warning in xfrm_state_fini(), which indicates that we have entries left in the list net->xfrm.state_all whose proto is zero. And xfrm_id_proto_match() doesn't consider them as a match with IPSEC_PROTO_ANY in this case. Proto with value 0 is probably not a valid value, at least verify_newsa_info() doesn't consider it valid either. This patch fixes it by checking the proto value in validate_tmpl() and rejecting invalid ones, like what iproute2 does in xfrm_xfrmproto_getbyname(). Reported-by: syzbot Cc: Steffen Klassert Cc: Herbert Xu Signed-off-by: Cong Wang Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 983b0233767b..c2cfcc6fdb34 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1445,6 +1445,21 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) default: return -EINVAL; } + + switch (ut[i].id.proto) { + case IPPROTO_AH: + case IPPROTO_ESP: + case IPPROTO_COMP: +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: +#endif + case IPSEC_PROTO_ANY: + break; + default: + return -EINVAL; + } + } return 0; From e719135881f00c01ca400abb8a5dadaf297a24f9 Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Wed, 29 Nov 2017 18:23:56 +0100 Subject: [PATCH 2/8] xfrm: fix XFRMA_OUTPUT_MARK policy entry This seems to be an obvious typo, NLA_U32 is type of the attribute, not its (minimal) length. Fixes: 077fbac405bf ("net: xfrm: support setting an output mark.") Signed-off-by: Michal Kubecek Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c2cfcc6fdb34..ff58c37469d6 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2485,7 +2485,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, - [XFRMA_OUTPUT_MARK] = { .len = NLA_U32 }, + [XFRMA_OUTPUT_MARK] = { .type = NLA_U32 }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { From 4ce3dbe397d7b6b15f272ae757c78c35e9e4b61d Mon Sep 17 00:00:00 2001 From: Aviv Heller Date: Tue, 28 Nov 2017 19:55:40 +0200 Subject: [PATCH 3/8] xfrm: Fix xfrm_input() to verify state is valid when (encap_type < 0) Code path when (encap_type < 0) does not verify the state is valid before progressing. This will result in a crash if, for instance, x->km.state == XFRM_STATE_ACQ. Fixes: 7785bba299a8 ("esp: Add a software GRO codepath") Signed-off-by: Aviv Heller Signed-off-by: Yevgeny Kliteynik Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 347ab31574d5..da6447389ffb 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -207,7 +207,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) xfrm_address_t *daddr; struct xfrm_mode *inner_mode; u32 mark = skb->mark; - unsigned int family; + unsigned int family = AF_UNSPEC; int decaps = 0; int async = 0; bool xfrm_gro = false; @@ -216,6 +216,16 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) if (encap_type < 0) { x = xfrm_input_state(skb); + + if (unlikely(x->km.state != XFRM_STATE_VALID)) { + if (x->km.state == XFRM_STATE_ACQ) + XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); + else + XFRM_INC_STATS(net, + LINUX_MIB_XFRMINSTATEINVALID); + goto drop; + } + family = x->outer_mode->afinfo->family; /* An encap_type of -1 indicates async resumption. */ From ddc47e4404b58f03e98345398fb12d38fe291512 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 29 Nov 2017 06:53:55 +0100 Subject: [PATCH 4/8] xfrm: Fix stack-out-of-bounds read on socket policy lookup. When we do tunnel or beet mode, we pass saddr and daddr from the template to xfrm_state_find(), this is ok. On transport mode, we pass the addresses from the flowi, assuming that the IP addresses (and address family) don't change during transformation. This assumption is wrong in the IPv4 mapped IPv6 case, packet is IPv4 and template is IPv6. Fix this by catching address family missmatches of the policy and the flow already before we do the lookup. Reported-by: syzbot Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9542975eb2f9..038ec68f6901 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1168,9 +1168,15 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { - bool match = xfrm_selector_match(&pol->selector, fl, family); + bool match; int err = 0; + if (pol->family != family) { + pol = NULL; + goto out; + } + + match = xfrm_selector_match(&pol->selector, fl, family); if (match) { if ((sk->sk_mark & pol->mark.m) != pol->mark.v) { pol = NULL; From 75bf50f4aaa1c78d769d854ab3d975884909e4fb Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Thu, 7 Dec 2017 21:54:27 +0100 Subject: [PATCH 5/8] xfrm: fix xfrm_do_migrate() with AEAD e.g(AES-GCM) copy geniv when cloning the xfrm state. x->geniv was not copied to the new state and migration would fail. xfrm_do_migrate .. xfrm_state_clone() .. .. esp_init_aead() crypto_alloc_aead() crypto_alloc_tfm() crypto_find_alg() return EAGAIN and failed Signed-off-by: Antony Antony Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 1f5cee2269af..88d0a563e141 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1344,6 +1344,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); + x->geniv = orig->geniv; if (!x->aead) goto error; } From 732706afe1cc46ef48493b3d2b69c98f36314ae4 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Fri, 8 Dec 2017 08:07:25 +0100 Subject: [PATCH 6/8] xfrm: Fix stack-out-of-bounds with misconfigured transport mode policies. On policies with a transport mode template, we pass the addresses from the flowi to xfrm_state_find(), assuming that the IP addresses (and address family) don't change during transformation. Unfortunately our policy template validation is not strict enough. It is possible to configure policies with transport mode template where the address family of the template does not match the selectors address family. This lead to stack-out-of-bound reads because we compare arddesses of the wrong family. Fix this by refusing such a configuration, address family can not change on transport mode. We use the assumption that, on transport mode, the first templates address family must match the address family of the policy selector. Subsequent transport mode templates must mach the address family of the previous template. Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ff58c37469d6..bdb48e5dba04 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1419,11 +1419,14 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) { + u16 prev_family; int i; if (nr > XFRM_MAX_DEPTH) return -EINVAL; + prev_family = family; + for (i = 0; i < nr; i++) { /* We never validated the ut->family value, so many * applications simply leave it at zero. The check was @@ -1435,6 +1438,12 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) if (!ut[i].family) ut[i].family = family; + if ((ut[i].mode == XFRM_MODE_TRANSPORT) && + (ut[i].family != prev_family)) + return -EINVAL; + + prev_family = ut[i].family; + switch (ut[i].family) { case AF_INET: break; From d2950278d2d04ff5314abeb38d9c59c4e7c0ee53 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Dec 2017 18:23:09 +0100 Subject: [PATCH 7/8] xfrm: put policies when reusing pcpu xdst entry We need to put the policies when re-using the pcpu xdst entry, else this leaks the reference. Fixes: ec30d78c14a813db39a647b6a348b428 ("xfrm: add xdst pcpu cache") Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 038ec68f6901..70aa5cb0c659 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1839,6 +1839,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, sizeof(struct xfrm_policy *) * num_pols) == 0 && xfrm_xdst_can_reuse(xdst, xfrm, err)) { dst_hold(&xdst->u.dst); + xfrm_pols_put(pols, num_pols); while (err > 0) xfrm_state_put(xfrm[--err]); return xdst; From acf568ee859f098279eadf551612f103afdacb4e Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 15 Dec 2017 16:40:44 +1100 Subject: [PATCH 8/8] xfrm: Reinject transport-mode packets through tasklet This is an old bugbear of mine: https://www.mail-archive.com/netdev@vger.kernel.org/msg03894.html By crafting special packets, it is possible to cause recursion in our kernel when processing transport-mode packets at levels that are only limited by packet size. The easiest one is with DNAT, but an even worse one is where UDP encapsulation is used in which case you just have to insert an UDP encapsulation header in between each level of recursion. This patch avoids this problem by reinjecting tranport-mode packets through a tasklet. Fixes: b05e106698d9 ("[IPV4/6]: Netfilter IPsec input hooks") Signed-off-by: Herbert Xu Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 3 +++ net/ipv4/xfrm4_input.c | 12 ++++++++- net/ipv6/xfrm6_input.c | 10 +++++++- net/xfrm/xfrm_input.c | 57 ++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 80 insertions(+), 2 deletions(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index dc28a98ce97c..ae35991b5877 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1570,6 +1570,9 @@ int xfrm_init_state(struct xfrm_state *x); int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); +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(struct sock *sk, struct sk_buff *skb); int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index e50b7fea57ee..bcfc00e88756 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -23,6 +23,12 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) return xfrm4_extract_header(skb); } +static int xfrm4_rcv_encap_finish2(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + return dst_input(skb); +} + static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -33,7 +39,11 @@ static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, iph->tos, skb->dev)) goto drop; } - return dst_input(skb); + + if (xfrm_trans_queue(skb, xfrm4_rcv_encap_finish2)) + goto drop; + + return 0; drop: kfree_skb(skb); return NET_RX_DROP; diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index fe04e23af986..841f4a07438e 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -32,6 +32,14 @@ int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, } EXPORT_SYMBOL(xfrm6_rcv_spi); +static int xfrm6_transport_finish2(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + if (xfrm_trans_queue(skb, ip6_rcv_finish)) + __kfree_skb(skb); + return -1; +} + int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); @@ -56,7 +64,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, dev_net(skb->dev), NULL, skb, skb->dev, NULL, - ip6_rcv_finish); + xfrm6_transport_finish2); return -1; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index da6447389ffb..3f6f6f8c9fa5 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -8,15 +8,29 @@ * */ +#include +#include #include #include #include +#include #include #include #include #include #include +struct xfrm_trans_tasklet { + struct tasklet_struct tasklet; + struct sk_buff_head queue; +}; + +struct xfrm_trans_cb { + int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); +}; + +#define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) + static struct kmem_cache *secpath_cachep __read_mostly; static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); @@ -25,6 +39,8 @@ static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[AF_INET6 + 1]; static struct gro_cells gro_cells; static struct net_device xfrm_napi_dev; +static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet); + int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; @@ -477,9 +493,41 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr) } EXPORT_SYMBOL(xfrm_input_resume); +static void xfrm_trans_reinject(unsigned long data) +{ + struct xfrm_trans_tasklet *trans = (void *)data; + struct sk_buff_head queue; + struct sk_buff *skb; + + __skb_queue_head_init(&queue); + skb_queue_splice_init(&trans->queue, &queue); + + while ((skb = __skb_dequeue(&queue))) + XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb); +} + +int xfrm_trans_queue(struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)) +{ + struct xfrm_trans_tasklet *trans; + + trans = this_cpu_ptr(&xfrm_trans_tasklet); + + if (skb_queue_len(&trans->queue) >= netdev_max_backlog) + return -ENOBUFS; + + XFRM_TRANS_SKB_CB(skb)->finish = finish; + skb_queue_tail(&trans->queue, skb); + tasklet_schedule(&trans->tasklet); + return 0; +} +EXPORT_SYMBOL(xfrm_trans_queue); + void __init xfrm_input_init(void) { int err; + int i; init_dummy_netdev(&xfrm_napi_dev); err = gro_cells_init(&gro_cells, &xfrm_napi_dev); @@ -490,4 +538,13 @@ void __init xfrm_input_init(void) sizeof(struct sec_path), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + + for_each_possible_cpu(i) { + struct xfrm_trans_tasklet *trans; + + trans = &per_cpu(xfrm_trans_tasklet, i); + __skb_queue_head_init(&trans->queue); + tasklet_init(&trans->tasklet, xfrm_trans_reinject, + (unsigned long)trans); + } }