From cc01572e2fb080e279ca625f239aca61f435ebf3 Mon Sep 17 00:00:00 2001 From: Yossi Kuperman Date: Wed, 17 Jan 2018 15:52:41 +0200 Subject: xfrm: Add SA to hardware at the end of xfrm_state_construct() Current code configures the hardware with a new SA before the state has been fully initialized. During this time interval, an incoming ESP packet can cause a crash due to a NULL dereference. More specifically, xfrm_input() considers the packet as valid, and yet, anti-replay mechanism is not initialized. Move hardware configuration to the end of xfrm_state_construct(), and mark the state as valid once the SA is fully initialized. Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API") Signed-off-by: Aviad Yehezkel Signed-off-by: Aviv Heller Signed-off-by: Yossi Kuperman Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 10 +++++++--- net/xfrm/xfrm_user.c | 18 +++++++++++------- 2 files changed, 18 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 429957412633..2d486492acdb 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2272,8 +2272,6 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) goto error; } - x->km.state = XFRM_STATE_VALID; - error: return err; } @@ -2282,7 +2280,13 @@ EXPORT_SYMBOL(__xfrm_init_state); int xfrm_init_state(struct xfrm_state *x) { - return __xfrm_init_state(x, true, false); + int err; + + err = __xfrm_init_state(x, true, false); + if (!err) + x->km.state = XFRM_STATE_VALID; + + return err; } EXPORT_SYMBOL(xfrm_init_state); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index bdb48e5dba04..7f52b8eb177d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -598,13 +598,6 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, goto error; } - if (attrs[XFRMA_OFFLOAD_DEV]) { - err = xfrm_dev_state_add(net, x, - nla_data(attrs[XFRMA_OFFLOAD_DEV])); - if (err) - goto error; - } - if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn, attrs[XFRMA_REPLAY_ESN_VAL]))) goto error; @@ -620,6 +613,14 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, /* override default values from above */ xfrm_update_ae_params(x, attrs, 0); + /* configure the hardware if offload is requested */ + if (attrs[XFRMA_OFFLOAD_DEV]) { + err = xfrm_dev_state_add(net, x, + nla_data(attrs[XFRMA_OFFLOAD_DEV])); + if (err) + goto error; + } + return x; error: @@ -662,6 +663,9 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } + if (x->km.state == XFRM_STATE_VOID) + x->km.state = XFRM_STATE_VALID; + c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; c.event = nlh->nlmsg_type; -- cgit v1.2.3-58-ga151 From aa5dd6fa6f5d4bdc82a67e952bba8ad2e98d77e2 Mon Sep 17 00:00:00 2001 From: Aviad Yehezkel Date: Thu, 18 Jan 2018 15:41:51 +0200 Subject: xfrm: fix error flow in case of add state fails If add state fails in case of device offload, netdev refcount will be negative since gc task is attempting to dev_free this state. This is fixed by putting NULL in state dev field. Signed-off-by: Aviad Yehezkel Signed-off-by: Boris Pismeny Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_device.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 30e5746085b8..ac9477189d1c 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -102,6 +102,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, err = dev->xfrmdev_ops->xdo_dev_state_add(x); if (err) { + xso->dev = NULL; dev_put(dev); return err; } -- cgit v1.2.3-58-ga151 From 5efec5c655dd31944af440ff2b0a93facc4a7762 Mon Sep 17 00:00:00 2001 From: Yossi Kuperman Date: Tue, 23 Jan 2018 00:16:21 +0200 Subject: xfrm: Fix eth_hdr(skb)->h_proto to reflect inner IP version IPSec tunnel mode supports encapsulation of IPv4 over IPv6 and vice-versa. The outer IP header is stripped and the inner IP inherits the original Ethernet header. Tcpdump fails to properly decode the inner packet in case that h_proto is different than the inner IP version. Fix h_proto to reflect the inner IP version. Signed-off-by: Yossi Kuperman Signed-off-by: Steffen Klassert --- net/ipv4/xfrm4_mode_tunnel.c | 1 + net/ipv6/xfrm6_mode_tunnel.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net') diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index e6265e2c274e..20ca486b3cad 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -92,6 +92,7 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 02556e356f87..dc93002ff9d1 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -92,6 +92,7 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); + eth_hdr(skb)->h_proto = skb->protocol; err = 0; -- cgit v1.2.3-58-ga151 From 545d8ae7affff7fb4f8bfd327c7c7790056535c4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 22 Jan 2018 16:34:09 -0600 Subject: xfrm: fix boolean assignment in xfrm_get_type_offload Assign true or false to boolean variables instead of an integer value. This issue was detected with the help of Coccinelle. Fixes: ffdb5211da1c ("xfrm: Auto-load xfrm offload modules") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 2d486492acdb..a3785f538018 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -317,7 +317,7 @@ retry: if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); - try_load = 0; + try_load = false; goto retry; } -- cgit v1.2.3-58-ga151 From e9191ffb65d8e159680ce0ad2224e1acbde6985c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 22 Jan 2018 20:06:42 +0000 Subject: ipv6: Fix getsockopt() for sockets with default IPV6_AUTOFLOWLABEL Commit 513674b5a2c9 ("net: reevalulate autoflowlabel setting after sysctl setting") removed the initialisation of ipv6_pinfo::autoflowlabel and added a second flag to indicate whether this field or the net namespace default should be used. The getsockopt() handling for this case was not updated, so it currently returns 0 for all sockets for which IPV6_AUTOFLOWLABEL is not explicitly enabled. Fix it to return the effective value, whether that has been set at the socket or net namespace level. Fixes: 513674b5a2c9 ("net: reevalulate autoflowlabel setting after sysctl ...") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/net/ipv6.h | 1 + net/ipv6/ip6_output.c | 2 +- net/ipv6/ipv6_sockglue.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index f73797e2fa60..221238254eb7 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -331,6 +331,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); +bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4f7d8de56611..3763dc01e374 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -166,7 +166,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } -static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) +bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) { if (!np->autoflowlabel_set) return ip6_default_np_autolabel(net); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 2d4680e0376f..e8ffb5b5d84e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1336,7 +1336,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break; case IPV6_AUTOFLOWLABEL: - val = np->autoflowlabel; + val = ip6_autoflowlabel(sock_net(sk), np); break; case IPV6_RECVFRAGSIZE: -- cgit v1.2.3-58-ga151 From 560a66075d694e6ec24c60967b4d93d97cbb33d1 Mon Sep 17 00:00:00 2001 From: Wolfgang Bumiller Date: Thu, 18 Jan 2018 11:32:35 +0100 Subject: net: sched: em_nbyte: don't add the data offset twice 'ptr' is shifted by the offset and then validated, the memcmp should not add it a second time. Signed-off-by: Wolfgang Bumiller Signed-off-by: David S. Miller --- net/sched/em_nbyte.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index df3110d69585..07c10bac06a0 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -51,7 +51,7 @@ static int em_nbyte_match(struct sk_buff *skb, struct tcf_ematch *em, if (!tcf_valid_offset(skb, ptr, nbyte->hdr.len)) return 0; - return !memcmp(ptr + nbyte->hdr.off, nbyte->pattern, nbyte->hdr.len); + return !memcmp(ptr, nbyte->pattern, nbyte->hdr.len); } static struct tcf_ematch_ops em_nbyte_ops = { -- cgit v1.2.3-58-ga151 From 581e7226a5d43f629eb6399a121f85f6a15f81be Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 24 Jan 2018 12:35:40 -0800 Subject: kcm: Only allow TCP sockets to be attached to a KCM mux TCP sockets for IPv4 and IPv6 that are not listeners or in closed stated are allowed to be attached to a KCM mux. Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+8865eaff7f9acd593945@syzkaller.appspotmail.com Signed-off-by: Tom Herbert Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/kcm/kcmsock.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index d4e98f20fc2a..7632797fb68e 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1387,8 +1387,13 @@ static int kcm_attach(struct socket *sock, struct socket *csock, if (!csk) return -EINVAL; - /* We must prevent loops or risk deadlock ! */ - if (csk->sk_family == PF_KCM) + /* Only allow TCP sockets to be attached for now */ + if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || + csk->sk_protocol != IPPROTO_TCP) + return -EOPNOTSUPP; + + /* Don't allow listeners or closed sockets */ + if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) return -EOPNOTSUPP; psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); -- cgit v1.2.3-58-ga151 From e5571240236c5652f3e079b1d5866716a7ad819c Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 24 Jan 2018 12:35:41 -0800 Subject: kcm: Check if sk_user_data already set in kcm_attach This is needed to prevent sk_user_data being overwritten. The check is done under the callback lock. This should prevent a socket from being attached twice to a KCM mux. It also prevents a socket from being attached for other use cases of sk_user_data as long as the other cases set sk_user_data under the lock. Followup work is needed to unify all the use cases of sk_user_data to use the same locking. Reported-by: syzbot+114b15f2be420a8886c3@syzkaller.appspotmail.com Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Signed-off-by: Tom Herbert Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/kcm/kcmsock.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 7632797fb68e..4a8d407f8902 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1410,9 +1410,18 @@ static int kcm_attach(struct socket *sock, struct socket *csock, return err; } - sock_hold(csk); - write_lock_bh(&csk->sk_callback_lock); + + /* Check if sk_user_data is aready by KCM or someone else. + * Must be done under lock to prevent race conditions. + */ + if (csk->sk_user_data) { + write_unlock_bh(&csk->sk_callback_lock); + strp_done(&psock->strp); + kmem_cache_free(kcm_psockp, psock); + return -EALREADY; + } + psock->save_data_ready = csk->sk_data_ready; psock->save_write_space = csk->sk_write_space; psock->save_state_change = csk->sk_state_change; @@ -1420,8 +1429,11 @@ static int kcm_attach(struct socket *sock, struct socket *csock, csk->sk_data_ready = psock_data_ready; csk->sk_write_space = psock_write_space; csk->sk_state_change = psock_state_change; + write_unlock_bh(&csk->sk_callback_lock); + sock_hold(csk); + /* Finished initialization, now add the psock to the MUX. */ spin_lock_bh(&mux->lock); head = &mux->psocks; -- cgit v1.2.3-58-ga151