From: Greg Kroah-Hartman Date: Fri, 2 Jun 2017 02:39:07 +0000 (+0900) Subject: 4.4-stable patches X-Git-Tag: v3.18.56~29 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=f2467b7ee0b7d59e4e7a966f65db33181011f561;p=thirdparty%2Fkernel%2Fstable-queue.git 4.4-stable patches added patches: be2net-fix-offload-features-for-q-in-q-packets.patch bridge-netlink-check-vlan_default_pvid-range.patch bridge-start-hello_timer-when-enabling-kernel_stp-in-br_stp_start.patch dccp-tcp-do-not-inherit-mc_list-from-parent.patch ipv4-add-reference-counting-to-metrics.patch ipv6-check-ip6_find_1stfragopt-return-value-properly.patch ipv6-dccp-do-not-inherit-ipv6_mc_list-from-parent.patch ipv6-fix-out-of-bound-writes-in-__ip6_append_data.patch ipv6-prevent-overrun-when-parsing-v6-header-options.patch net-improve-handling-of-failures-on-link-and-route-dumps.patch net-phy-marvell-limit-errata-to-88m1101.patch netem-fix-skb_orphan_partial.patch qmi_wwan-add-another-lenovo-em74xx-device-id.patch s390-qeth-add-missing-hash-table-initializations.patch s390-qeth-avoid-null-pointer-dereference-on-osn.patch s390-qeth-handle-sysfs-error-during-initialization.patch s390-qeth-unbreak-osm-and-osn-support.patch sctp-do-not-inherit-ipv6_-mc-ac-fl-_list-from-parent.patch sctp-fix-icmp-processing-if-skb-is-non-linear.patch sctp-fix-src-address-selection-if-using-secondary-addresses-for-ipv6.patch tcp-avoid-fastopen-api-to-be-used-on-af_unspec.patch tcp-avoid-fragmenting-peculiar-skbs-in-sack.patch tcp-eliminate-negative-reordering-in-tcp_clean_rtx_queue.patch virtio-net-enable-tso-checksum-offloads-for-q-in-q-vlans.patch vlan-fix-tcp-checksum-offloads-in-q-in-q-vlans.patch --- diff --git a/queue-4.4/be2net-fix-offload-features-for-q-in-q-packets.patch b/queue-4.4/be2net-fix-offload-features-for-q-in-q-packets.patch new file mode 100644 index 00000000000..54b3bd2f8f6 --- /dev/null +++ b/queue-4.4/be2net-fix-offload-features-for-q-in-q-packets.patch @@ -0,0 +1,44 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Vlad Yasevich +Date: Tue, 23 May 2017 13:38:42 -0400 +Subject: be2net: Fix offload features for Q-in-Q packets + +From: Vlad Yasevich + + +[ Upstream commit cc6e9de62a7f84c9293a2ea41bc412b55bb46e85 ] + +At least some of the be2net cards do not seem to be capabled +of performing checksum offload computions on Q-in-Q packets. +In these case, the recevied checksum on the remote is invalid +and TCP syn packets are dropped. + +This patch adds a call to check disbled acceleration features +on Q-in-Q tagged traffic. + +CC: Sathya Perla +CC: Ajit Khaparde +CC: Sriharsha Basavapatna +CC: Somnath Kotur +Signed-off-by: Vladislav Yasevich +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/emulex/benet/be_main.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/drivers/net/ethernet/emulex/benet/be_main.c ++++ b/drivers/net/ethernet/emulex/benet/be_main.c +@@ -5260,9 +5260,11 @@ static netdev_features_t be_features_che + struct be_adapter *adapter = netdev_priv(dev); + u8 l4_hdr = 0; + +- /* The code below restricts offload features for some tunneled packets. ++ /* The code below restricts offload features for some tunneled and ++ * Q-in-Q packets. + * Offload features for normal (non tunnel) packets are unchanged. + */ ++ features = vlan_features_check(skb, features); + if (!skb->encapsulation || + !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS)) + return features; diff --git a/queue-4.4/bridge-netlink-check-vlan_default_pvid-range.patch b/queue-4.4/bridge-netlink-check-vlan_default_pvid-range.patch new file mode 100644 index 00000000000..60d80339a0c --- /dev/null +++ b/queue-4.4/bridge-netlink-check-vlan_default_pvid-range.patch @@ -0,0 +1,53 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Tobias Jungel +Date: Wed, 17 May 2017 09:29:12 +0200 +Subject: bridge: netlink: check vlan_default_pvid range + +From: Tobias Jungel + + +[ Upstream commit a285860211bf257b0e6d522dac6006794be348af ] + +Currently it is allowed to set the default pvid of a bridge to a value +above VLAN_VID_MASK (0xfff). This patch adds a check to br_validate and +returns -EINVAL in case the pvid is out of bounds. + +Reproduce by calling: + +[root@test ~]# ip l a type bridge +[root@test ~]# ip l a type dummy +[root@test ~]# ip l s bridge0 type bridge vlan_filtering 1 +[root@test ~]# ip l s bridge0 type bridge vlan_default_pvid 9999 +[root@test ~]# ip l s dummy0 master bridge0 +[root@test ~]# bridge vlan +port vlan ids +bridge0 9999 PVID Egress Untagged + +dummy0 9999 PVID Egress Untagged + +Fixes: 0f963b7592ef ("bridge: netlink: add support for default_pvid") +Acked-by: Nikolay Aleksandrov +Signed-off-by: Tobias Jungel +Acked-by: Sabrina Dubroca +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/bridge/br_netlink.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/net/bridge/br_netlink.c ++++ b/net/bridge/br_netlink.c +@@ -768,6 +768,13 @@ static int br_validate(struct nlattr *tb + return -EPROTONOSUPPORT; + } + } ++ ++ if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { ++ __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); ++ ++ if (defpvid >= VLAN_VID_MASK) ++ return -EINVAL; ++ } + #endif + + return 0; diff --git a/queue-4.4/bridge-start-hello_timer-when-enabling-kernel_stp-in-br_stp_start.patch b/queue-4.4/bridge-start-hello_timer-when-enabling-kernel_stp-in-br_stp_start.patch new file mode 100644 index 00000000000..63c7d050199 --- /dev/null +++ b/queue-4.4/bridge-start-hello_timer-when-enabling-kernel_stp-in-br_stp_start.patch @@ -0,0 +1,58 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Xin Long +Date: Fri, 19 May 2017 22:20:29 +0800 +Subject: bridge: start hello_timer when enabling KERNEL_STP in br_stp_start + +From: Xin Long + + +[ Upstream commit 6d18c732b95c0a9d35e9f978b4438bba15412284 ] + +Since commit 76b91c32dd86 ("bridge: stp: when using userspace stp stop +kernel hello and hold timers"), bridge would not start hello_timer if +stp_enabled is not KERNEL_STP when br_dev_open. + +The problem is even if users set stp_enabled with KERNEL_STP later, +the timer will still not be started. It causes that KERNEL_STP can +not really work. Users have to re-ifup the bridge to avoid this. + +This patch is to fix it by starting br->hello_timer when enabling +KERNEL_STP in br_stp_start. + +As an improvement, it's also to start hello_timer again only when +br->stp_enabled is KERNEL_STP in br_hello_timer_expired, there is +no reason to start the timer again when it's NO_STP. + +Fixes: 76b91c32dd86 ("bridge: stp: when using userspace stp stop kernel hello and hold timers") +Reported-by: Haidong Li +Signed-off-by: Xin Long +Acked-by: Nikolay Aleksandrov +Reviewed-by: Ivan Vecera +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/bridge/br_stp_if.c | 1 + + net/bridge/br_stp_timer.c | 2 +- + 2 files changed, 2 insertions(+), 1 deletion(-) + +--- a/net/bridge/br_stp_if.c ++++ b/net/bridge/br_stp_if.c +@@ -166,6 +166,7 @@ static void br_stp_start(struct net_brid + br_debug(br, "using kernel STP\n"); + + /* To start timers on any ports left in blocking */ ++ mod_timer(&br->hello_timer, jiffies + br->hello_time); + br_port_state_selection(br); + } + +--- a/net/bridge/br_stp_timer.c ++++ b/net/bridge/br_stp_timer.c +@@ -40,7 +40,7 @@ static void br_hello_timer_expired(unsig + if (br->dev->flags & IFF_UP) { + br_config_bpdu_generation(br); + +- if (br->stp_enabled != BR_USER_STP) ++ if (br->stp_enabled == BR_KERNEL_STP) + mod_timer(&br->hello_timer, + round_jiffies(jiffies + br->hello_time)); + } diff --git a/queue-4.4/dccp-tcp-do-not-inherit-mc_list-from-parent.patch b/queue-4.4/dccp-tcp-do-not-inherit-mc_list-from-parent.patch new file mode 100644 index 00000000000..0f86dcbc049 --- /dev/null +++ b/queue-4.4/dccp-tcp-do-not-inherit-mc_list-from-parent.patch @@ -0,0 +1,42 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Eric Dumazet +Date: Tue, 9 May 2017 06:29:19 -0700 +Subject: dccp/tcp: do not inherit mc_list from parent + +From: Eric Dumazet + + +[ Upstream commit 657831ffc38e30092a2d5f03d385d710eb88b09a ] + +syzkaller found a way to trigger double frees from ip_mc_drop_socket() + +It turns out that leave a copy of parent mc_list at accept() time, +which is very bad. + +Very similar to commit 8b485ce69876 ("tcp: do not inherit +fastopen_req from parent") + +Initial report from Pray3r, completed by Andrey one. +Thanks a lot to them ! + +Signed-off-by: Eric Dumazet +Reported-by: Pray3r +Reported-by: Andrey Konovalov +Tested-by: Andrey Konovalov +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/inet_connection_sock.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/net/ipv4/inet_connection_sock.c ++++ b/net/ipv4/inet_connection_sock.c +@@ -669,6 +669,8 @@ struct sock *inet_csk_clone_lock(const s + inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); + newsk->sk_write_space = sk_stream_write_space; + ++ inet_sk(newsk)->mc_list = NULL; ++ + newsk->sk_mark = inet_rsk(req)->ir_mark; + atomic64_set(&newsk->sk_cookie, + atomic64_read(&inet_rsk(req)->ir_cookie)); diff --git a/queue-4.4/ipv4-add-reference-counting-to-metrics.patch b/queue-4.4/ipv4-add-reference-counting-to-metrics.patch new file mode 100644 index 00000000000..d4b5f448fbc --- /dev/null +++ b/queue-4.4/ipv4-add-reference-counting-to-metrics.patch @@ -0,0 +1,254 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Eric Dumazet +Date: Thu, 25 May 2017 14:27:35 -0700 +Subject: ipv4: add reference counting to metrics + +From: Eric Dumazet + + +[ Upstream commit 3fb07daff8e99243366a081e5129560734de4ada ] + +Andrey Konovalov reported crashes in ipv4_mtu() + +I could reproduce the issue with KASAN kernels, between +10.246.7.151 and 10.246.7.152 : + +1) 20 concurrent netperf -t TCP_RR -H 10.246.7.152 -l 1000 & + +2) At the same time run following loop : +while : +do + ip ro add 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500 + ip ro del 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500 +done + +Cong Wang attempted to add back rt->fi in commit +82486aa6f1b9 ("ipv4: restore rt->fi for reference counting") +but this proved to add some issues that were complex to solve. + +Instead, I suggested to add a refcount to the metrics themselves, +being a standalone object (in particular, no reference to other objects) + +I tried to make this patch as small as possible to ease its backport, +instead of being super clean. Note that we believe that only ipv4 dst +need to take care of the metric refcount. But if this is wrong, +this patch adds the basic infrastructure to extend this to other +families. + +Many thanks to Julian Anastasov for reviewing this patch, and Cong Wang +for his efforts on this problem. + +Fixes: 2860583fe840 ("ipv4: Kill rt->fi") +Signed-off-by: Eric Dumazet +Reported-by: Andrey Konovalov +Reviewed-by: Julian Anastasov +Acked-by: Cong Wang +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + include/net/dst.h | 8 +++++++- + include/net/ip_fib.h | 10 +++++----- + net/core/dst.c | 23 ++++++++++++++--------- + net/ipv4/fib_semantics.c | 17 ++++++++++------- + net/ipv4/route.c | 10 +++++++++- + 5 files changed, 45 insertions(+), 23 deletions(-) + +--- a/include/net/dst.h ++++ b/include/net/dst.h +@@ -110,10 +110,16 @@ struct dst_entry { + }; + }; + ++struct dst_metrics { ++ u32 metrics[RTAX_MAX]; ++ atomic_t refcnt; ++}; ++extern const struct dst_metrics dst_default_metrics; ++ + u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); +-extern const u32 dst_default_metrics[]; + + #define DST_METRICS_READ_ONLY 0x1UL ++#define DST_METRICS_REFCOUNTED 0x2UL + #define DST_METRICS_FLAGS 0x3UL + #define __DST_METRICS_PTR(Y) \ + ((u32 *)((Y) & ~DST_METRICS_FLAGS)) +--- a/include/net/ip_fib.h ++++ b/include/net/ip_fib.h +@@ -112,11 +112,11 @@ struct fib_info { + unsigned char fib_type; + __be32 fib_prefsrc; + u32 fib_priority; +- u32 *fib_metrics; +-#define fib_mtu fib_metrics[RTAX_MTU-1] +-#define fib_window fib_metrics[RTAX_WINDOW-1] +-#define fib_rtt fib_metrics[RTAX_RTT-1] +-#define fib_advmss fib_metrics[RTAX_ADVMSS-1] ++ struct dst_metrics *fib_metrics; ++#define fib_mtu fib_metrics->metrics[RTAX_MTU-1] ++#define fib_window fib_metrics->metrics[RTAX_WINDOW-1] ++#define fib_rtt fib_metrics->metrics[RTAX_RTT-1] ++#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] + int fib_nhs; + #ifdef CONFIG_IP_ROUTE_MULTIPATH + int fib_weight; +--- a/net/core/dst.c ++++ b/net/core/dst.c +@@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, str + } + EXPORT_SYMBOL(dst_discard_out); + +-const u32 dst_default_metrics[RTAX_MAX + 1] = { ++const struct dst_metrics dst_default_metrics = { + /* This initializer is needed to force linker to place this variable + * into const section. Otherwise it might end into bss section. + * We really want to avoid false sharing on this variable, and catch + * any writes on it. + */ +- [RTAX_MAX] = 0xdeadbeef, ++ .refcnt = ATOMIC_INIT(1), + }; + + void dst_init(struct dst_entry *dst, struct dst_ops *ops, +@@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, str + if (dev) + dev_hold(dev); + dst->ops = ops; +- dst_init_metrics(dst, dst_default_metrics, true); ++ dst_init_metrics(dst, dst_default_metrics.metrics, true); + dst->expires = 0UL; + dst->path = dst; + dst->from = NULL; +@@ -315,25 +315,30 @@ EXPORT_SYMBOL(dst_release); + + u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) + { +- u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); ++ struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC); + + if (p) { +- u32 *old_p = __DST_METRICS_PTR(old); ++ struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); + unsigned long prev, new; + +- memcpy(p, old_p, sizeof(u32) * RTAX_MAX); ++ atomic_set(&p->refcnt, 1); ++ memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + kfree(p); +- p = __DST_METRICS_PTR(prev); ++ p = (struct dst_metrics *)__DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; ++ } else if (prev & DST_METRICS_REFCOUNTED) { ++ if (atomic_dec_and_test(&old_p->refcnt)) ++ kfree(old_p); + } + } +- return p; ++ BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0); ++ return (u32 *)p; + } + EXPORT_SYMBOL(dst_cow_metrics_generic); + +@@ -342,7 +347,7 @@ void __dst_destroy_metrics_generic(struc + { + unsigned long prev, new; + +- new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY; ++ new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY; + prev = cmpxchg(&dst->_metrics, old, new); + if (prev == old) + kfree(__DST_METRICS_PTR(old)); +--- a/net/ipv4/fib_semantics.c ++++ b/net/ipv4/fib_semantics.c +@@ -204,6 +204,7 @@ static void rt_fibinfo_free_cpus(struct + static void free_fib_info_rcu(struct rcu_head *head) + { + struct fib_info *fi = container_of(head, struct fib_info, rcu); ++ struct dst_metrics *m; + + change_nexthops(fi) { + if (nexthop_nh->nh_dev) +@@ -214,8 +215,9 @@ static void free_fib_info_rcu(struct rcu + rt_fibinfo_free(&nexthop_nh->nh_rth_input); + } endfor_nexthops(fi); + +- if (fi->fib_metrics != (u32 *) dst_default_metrics) +- kfree(fi->fib_metrics); ++ m = fi->fib_metrics; ++ if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt)) ++ kfree(m); + kfree(fi); + } + +@@ -982,11 +984,11 @@ fib_convert_metrics(struct fib_info *fi, + val = 255; + if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) + return -EINVAL; +- fi->fib_metrics[type - 1] = val; ++ fi->fib_metrics->metrics[type - 1] = val; + } + + if (ecn_ca) +- fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; ++ fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; + + return 0; + } +@@ -1044,11 +1046,12 @@ struct fib_info *fib_create_info(struct + goto failure; + fib_info_cnt++; + if (cfg->fc_mx) { +- fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); ++ fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL); + if (!fi->fib_metrics) + goto failure; ++ atomic_set(&fi->fib_metrics->refcnt, 1); + } else +- fi->fib_metrics = (u32 *) dst_default_metrics; ++ fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; + + fi->fib_net = net; + fi->fib_protocol = cfg->fc_protocol; +@@ -1251,7 +1254,7 @@ int fib_dump_info(struct sk_buff *skb, u + if (fi->fib_priority && + nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) + goto nla_put_failure; +- if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) ++ if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0) + goto nla_put_failure; + + if (fi->fib_prefsrc && +--- a/net/ipv4/route.c ++++ b/net/ipv4/route.c +@@ -1356,8 +1356,12 @@ static void rt_add_uncached_list(struct + + static void ipv4_dst_destroy(struct dst_entry *dst) + { ++ struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + struct rtable *rt = (struct rtable *) dst; + ++ if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt)) ++ kfree(p); ++ + if (!list_empty(&rt->rt_uncached)) { + struct uncached_list *ul = rt->rt_uncached_list; + +@@ -1409,7 +1413,11 @@ static void rt_set_nexthop(struct rtable + rt->rt_gateway = nh->nh_gw; + rt->rt_uses_gateway = 1; + } +- dst_init_metrics(&rt->dst, fi->fib_metrics, true); ++ dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true); ++ if (fi->fib_metrics != &dst_default_metrics) { ++ rt->dst._metrics |= DST_METRICS_REFCOUNTED; ++ atomic_inc(&fi->fib_metrics->refcnt); ++ } + #ifdef CONFIG_IP_ROUTE_CLASSID + rt->dst.tclassid = nh->nh_tclassid; + #endif diff --git a/queue-4.4/ipv6-check-ip6_find_1stfragopt-return-value-properly.patch b/queue-4.4/ipv6-check-ip6_find_1stfragopt-return-value-properly.patch new file mode 100644 index 00000000000..d4e3627e6ad --- /dev/null +++ b/queue-4.4/ipv6-check-ip6_find_1stfragopt-return-value-properly.patch @@ -0,0 +1,89 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: "David S. Miller" +Date: Wed, 17 May 2017 22:54:11 -0400 +Subject: ipv6: Check ip6_find_1stfragopt() return value properly. + +From: "David S. Miller" + + +[ Upstream commit 7dd7eb9513bd02184d45f000ab69d78cb1fa1531 ] + +Do not use unsigned variables to see if it returns a negative +error or not. + +Fixes: 2423496af35d ("ipv6: Prevent overrun when parsing v6 header options") +Reported-by: Julia Lawall +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv6/ip6_offload.c | 9 ++++----- + net/ipv6/ip6_output.c | 7 +++---- + net/ipv6/udp_offload.c | 8 +++++--- + 3 files changed, 12 insertions(+), 12 deletions(-) + +--- a/net/ipv6/ip6_offload.c ++++ b/net/ipv6/ip6_offload.c +@@ -62,7 +62,6 @@ static struct sk_buff *ipv6_gso_segment( + const struct net_offload *ops; + int proto; + struct frag_hdr *fptr; +- unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; + bool encap, udpfrag; +@@ -121,10 +120,10 @@ static struct sk_buff *ipv6_gso_segment( + skb->network_header = (u8 *)ipv6h - skb->head; + + if (udpfrag) { +- unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); +- if (unfrag_ip6hlen < 0) +- return ERR_PTR(unfrag_ip6hlen); +- fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); ++ int err = ip6_find_1stfragopt(skb, &prevhdr); ++ if (err < 0) ++ return ERR_PTR(err); ++ fptr = (struct frag_hdr *)((u8 *)ipv6h + err); + fptr->frag_off = htons(offset); + if (skb->next) + fptr->frag_off |= htons(IP6_MF); +--- a/net/ipv6/ip6_output.c ++++ b/net/ipv6/ip6_output.c +@@ -571,11 +571,10 @@ int ip6_fragment(struct net *net, struct + int ptr, offset = 0, err = 0; + u8 *prevhdr, nexthdr = 0; + +- hlen = ip6_find_1stfragopt(skb, &prevhdr); +- if (hlen < 0) { +- err = hlen; ++ err = ip6_find_1stfragopt(skb, &prevhdr); ++ if (err < 0) + goto fail; +- } ++ hlen = err; + nexthdr = *prevhdr; + + mtu = ip6_skb_dst_mtu(skb); +--- a/net/ipv6/udp_offload.c ++++ b/net/ipv6/udp_offload.c +@@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment + u8 frag_hdr_sz = sizeof(struct frag_hdr); + __wsum csum; + int tnl_hlen; ++ int err; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) +@@ -97,9 +98,10 @@ static struct sk_buff *udp6_ufo_fragment + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ +- unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); +- if (unfrag_ip6hlen < 0) +- return ERR_PTR(unfrag_ip6hlen); ++ err = ip6_find_1stfragopt(skb, &prevhdr); ++ if (err < 0) ++ return ERR_PTR(err); ++ unfrag_ip6hlen = err; + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + diff --git a/queue-4.4/ipv6-dccp-do-not-inherit-ipv6_mc_list-from-parent.patch b/queue-4.4/ipv6-dccp-do-not-inherit-ipv6_mc_list-from-parent.patch new file mode 100644 index 00000000000..3ae850190ee --- /dev/null +++ b/queue-4.4/ipv6-dccp-do-not-inherit-ipv6_mc_list-from-parent.patch @@ -0,0 +1,63 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: WANG Cong +Date: Tue, 9 May 2017 16:59:54 -0700 +Subject: ipv6/dccp: do not inherit ipv6_mc_list from parent + +From: WANG Cong + + +[ Upstream commit 83eaddab4378db256d00d295bda6ca997cd13a52 ] + +Like commit 657831ffc38e ("dccp/tcp: do not inherit mc_list from parent") +we should clear ipv6_mc_list etc. for IPv6 sockets too. + +Cc: Eric Dumazet +Signed-off-by: Cong Wang +Acked-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/dccp/ipv6.c | 6 ++++++ + net/ipv6/tcp_ipv6.c | 2 ++ + 2 files changed, 8 insertions(+) + +--- a/net/dccp/ipv6.c ++++ b/net/dccp/ipv6.c +@@ -422,6 +422,9 @@ static struct sock *dccp_v6_request_recv + newsk->sk_backlog_rcv = dccp_v4_do_rcv; + newnp->pktoptions = NULL; + newnp->opt = NULL; ++ newnp->ipv6_mc_list = NULL; ++ newnp->ipv6_ac_list = NULL; ++ newnp->ipv6_fl_list = NULL; + newnp->mcast_oif = inet6_iif(skb); + newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + +@@ -486,6 +489,9 @@ static struct sock *dccp_v6_request_recv + /* Clone RX bits */ + newnp->rxopt.all = np->rxopt.all; + ++ newnp->ipv6_mc_list = NULL; ++ newnp->ipv6_ac_list = NULL; ++ newnp->ipv6_fl_list = NULL; + newnp->pktoptions = NULL; + newnp->opt = NULL; + newnp->mcast_oif = inet6_iif(skb); +--- a/net/ipv6/tcp_ipv6.c ++++ b/net/ipv6/tcp_ipv6.c +@@ -1033,6 +1033,7 @@ static struct sock *tcp_v6_syn_recv_sock + newtp->af_specific = &tcp_sock_ipv6_mapped_specific; + #endif + ++ newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; + newnp->pktoptions = NULL; +@@ -1102,6 +1103,7 @@ static struct sock *tcp_v6_syn_recv_sock + First: no IPv4 options. + */ + newinet->inet_opt = NULL; ++ newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; + diff --git a/queue-4.4/ipv6-fix-out-of-bound-writes-in-__ip6_append_data.patch b/queue-4.4/ipv6-fix-out-of-bound-writes-in-__ip6_append_data.patch new file mode 100644 index 00000000000..9365617d52a --- /dev/null +++ b/queue-4.4/ipv6-fix-out-of-bound-writes-in-__ip6_append_data.patch @@ -0,0 +1,67 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Eric Dumazet +Date: Fri, 19 May 2017 14:17:48 -0700 +Subject: ipv6: fix out of bound writes in __ip6_append_data() + +From: Eric Dumazet + + +[ Upstream commit 232cd35d0804cc241eb887bb8d4d9b3b9881c64a ] + +Andrey Konovalov and idaifish@gmail.com reported crashes caused by +one skb shared_info being overwritten from __ip6_append_data() + +Andrey program lead to following state : + +copy -4200 datalen 2000 fraglen 2040 +maxfraglen 2040 alloclen 2048 transhdrlen 0 offset 0 fraggap 6200 + +The skb_copy_and_csum_bits(skb_prev, maxfraglen, data + transhdrlen, +fraggap, 0); is overwriting skb->head and skb_shared_info + +Since we apparently detect this rare condition too late, move the +code earlier to even avoid allocating skb and risking crashes. + +Once again, many thanks to Andrey and syzkaller team. + +Signed-off-by: Eric Dumazet +Reported-by: Andrey Konovalov +Tested-by: Andrey Konovalov +Reported-by: +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv6/ip6_output.c | 15 ++++++++------- + 1 file changed, 8 insertions(+), 7 deletions(-) + +--- a/net/ipv6/ip6_output.c ++++ b/net/ipv6/ip6_output.c +@@ -1432,6 +1432,11 @@ alloc_new_skb: + */ + alloclen += sizeof(struct frag_hdr); + ++ copy = datalen - transhdrlen - fraggap; ++ if (copy < 0) { ++ err = -EINVAL; ++ goto error; ++ } + if (transhdrlen) { + skb = sock_alloc_send_skb(sk, + alloclen + hh_len, +@@ -1481,13 +1486,9 @@ alloc_new_skb: + data += fraggap; + pskb_trim_unique(skb_prev, maxfraglen); + } +- copy = datalen - transhdrlen - fraggap; +- +- if (copy < 0) { +- err = -EINVAL; +- kfree_skb(skb); +- goto error; +- } else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { ++ if (copy > 0 && ++ getfrag(from, data + transhdrlen, offset, ++ copy, fraggap, skb) < 0) { + err = -EFAULT; + kfree_skb(skb); + goto error; diff --git a/queue-4.4/ipv6-prevent-overrun-when-parsing-v6-header-options.patch b/queue-4.4/ipv6-prevent-overrun-when-parsing-v6-header-options.patch new file mode 100644 index 00000000000..3e9f650f602 --- /dev/null +++ b/queue-4.4/ipv6-prevent-overrun-when-parsing-v6-header-options.patch @@ -0,0 +1,226 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Craig Gallek +Date: Tue, 16 May 2017 14:36:23 -0400 +Subject: ipv6: Prevent overrun when parsing v6 header options + +From: Craig Gallek + + +[ Upstream commit 2423496af35d94a87156b063ea5cedffc10a70a1 ] + +The KASAN warning repoted below was discovered with a syzkaller +program. The reproducer is basically: + int s = socket(AF_INET6, SOCK_RAW, NEXTHDR_HOP); + send(s, &one_byte_of_data, 1, MSG_MORE); + send(s, &more_than_mtu_bytes_data, 2000, 0); + +The socket() call sets the nexthdr field of the v6 header to +NEXTHDR_HOP, the first send call primes the payload with a non zero +byte of data, and the second send call triggers the fragmentation path. + +The fragmentation code tries to parse the header options in order +to figure out where to insert the fragment option. Since nexthdr points +to an invalid option, the calculation of the size of the network header +can made to be much larger than the linear section of the skb and data +is read outside of it. + +This fix makes ip6_find_1stfrag return an error if it detects +running out-of-bounds. + +[ 42.361487] ================================================================== +[ 42.364412] BUG: KASAN: slab-out-of-bounds in ip6_fragment+0x11c8/0x3730 +[ 42.365471] Read of size 840 at addr ffff88000969e798 by task ip6_fragment-oo/3789 +[ 42.366469] +[ 42.366696] CPU: 1 PID: 3789 Comm: ip6_fragment-oo Not tainted 4.11.0+ #41 +[ 42.367628] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014 +[ 42.368824] Call Trace: +[ 42.369183] dump_stack+0xb3/0x10b +[ 42.369664] print_address_description+0x73/0x290 +[ 42.370325] kasan_report+0x252/0x370 +[ 42.370839] ? ip6_fragment+0x11c8/0x3730 +[ 42.371396] check_memory_region+0x13c/0x1a0 +[ 42.371978] memcpy+0x23/0x50 +[ 42.372395] ip6_fragment+0x11c8/0x3730 +[ 42.372920] ? nf_ct_expect_unregister_notifier+0x110/0x110 +[ 42.373681] ? ip6_copy_metadata+0x7f0/0x7f0 +[ 42.374263] ? ip6_forward+0x2e30/0x2e30 +[ 42.374803] ip6_finish_output+0x584/0x990 +[ 42.375350] ip6_output+0x1b7/0x690 +[ 42.375836] ? ip6_finish_output+0x990/0x990 +[ 42.376411] ? ip6_fragment+0x3730/0x3730 +[ 42.376968] ip6_local_out+0x95/0x160 +[ 42.377471] ip6_send_skb+0xa1/0x330 +[ 42.377969] ip6_push_pending_frames+0xb3/0xe0 +[ 42.378589] rawv6_sendmsg+0x2051/0x2db0 +[ 42.379129] ? rawv6_bind+0x8b0/0x8b0 +[ 42.379633] ? _copy_from_user+0x84/0xe0 +[ 42.380193] ? debug_check_no_locks_freed+0x290/0x290 +[ 42.380878] ? ___sys_sendmsg+0x162/0x930 +[ 42.381427] ? rcu_read_lock_sched_held+0xa3/0x120 +[ 42.382074] ? sock_has_perm+0x1f6/0x290 +[ 42.382614] ? ___sys_sendmsg+0x167/0x930 +[ 42.383173] ? lock_downgrade+0x660/0x660 +[ 42.383727] inet_sendmsg+0x123/0x500 +[ 42.384226] ? inet_sendmsg+0x123/0x500 +[ 42.384748] ? inet_recvmsg+0x540/0x540 +[ 42.385263] sock_sendmsg+0xca/0x110 +[ 42.385758] SYSC_sendto+0x217/0x380 +[ 42.386249] ? SYSC_connect+0x310/0x310 +[ 42.386783] ? __might_fault+0x110/0x1d0 +[ 42.387324] ? lock_downgrade+0x660/0x660 +[ 42.387880] ? __fget_light+0xa1/0x1f0 +[ 42.388403] ? __fdget+0x18/0x20 +[ 42.388851] ? sock_common_setsockopt+0x95/0xd0 +[ 42.389472] ? SyS_setsockopt+0x17f/0x260 +[ 42.390021] ? entry_SYSCALL_64_fastpath+0x5/0xbe +[ 42.390650] SyS_sendto+0x40/0x50 +[ 42.391103] entry_SYSCALL_64_fastpath+0x1f/0xbe +[ 42.391731] RIP: 0033:0x7fbbb711e383 +[ 42.392217] RSP: 002b:00007ffff4d34f28 EFLAGS: 00000246 ORIG_RAX: 000000000000002c +[ 42.393235] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fbbb711e383 +[ 42.394195] RDX: 0000000000001000 RSI: 00007ffff4d34f60 RDI: 0000000000000003 +[ 42.395145] RBP: 0000000000000046 R08: 00007ffff4d34f40 R09: 0000000000000018 +[ 42.396056] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000400aad +[ 42.396598] R13: 0000000000000066 R14: 00007ffff4d34ee0 R15: 00007fbbb717af00 +[ 42.397257] +[ 42.397411] Allocated by task 3789: +[ 42.397702] save_stack_trace+0x16/0x20 +[ 42.398005] save_stack+0x46/0xd0 +[ 42.398267] kasan_kmalloc+0xad/0xe0 +[ 42.398548] kasan_slab_alloc+0x12/0x20 +[ 42.398848] __kmalloc_node_track_caller+0xcb/0x380 +[ 42.399224] __kmalloc_reserve.isra.32+0x41/0xe0 +[ 42.399654] __alloc_skb+0xf8/0x580 +[ 42.400003] sock_wmalloc+0xab/0xf0 +[ 42.400346] __ip6_append_data.isra.41+0x2472/0x33d0 +[ 42.400813] ip6_append_data+0x1a8/0x2f0 +[ 42.401122] rawv6_sendmsg+0x11ee/0x2db0 +[ 42.401505] inet_sendmsg+0x123/0x500 +[ 42.401860] sock_sendmsg+0xca/0x110 +[ 42.402209] ___sys_sendmsg+0x7cb/0x930 +[ 42.402582] __sys_sendmsg+0xd9/0x190 +[ 42.402941] SyS_sendmsg+0x2d/0x50 +[ 42.403273] entry_SYSCALL_64_fastpath+0x1f/0xbe +[ 42.403718] +[ 42.403871] Freed by task 1794: +[ 42.404146] save_stack_trace+0x16/0x20 +[ 42.404515] save_stack+0x46/0xd0 +[ 42.404827] kasan_slab_free+0x72/0xc0 +[ 42.405167] kfree+0xe8/0x2b0 +[ 42.405462] skb_free_head+0x74/0xb0 +[ 42.405806] skb_release_data+0x30e/0x3a0 +[ 42.406198] skb_release_all+0x4a/0x60 +[ 42.406563] consume_skb+0x113/0x2e0 +[ 42.406910] skb_free_datagram+0x1a/0xe0 +[ 42.407288] netlink_recvmsg+0x60d/0xe40 +[ 42.407667] sock_recvmsg+0xd7/0x110 +[ 42.408022] ___sys_recvmsg+0x25c/0x580 +[ 42.408395] __sys_recvmsg+0xd6/0x190 +[ 42.408753] SyS_recvmsg+0x2d/0x50 +[ 42.409086] entry_SYSCALL_64_fastpath+0x1f/0xbe +[ 42.409513] +[ 42.409665] The buggy address belongs to the object at ffff88000969e780 +[ 42.409665] which belongs to the cache kmalloc-512 of size 512 +[ 42.410846] The buggy address is located 24 bytes inside of +[ 42.410846] 512-byte region [ffff88000969e780, ffff88000969e980) +[ 42.411941] The buggy address belongs to the page: +[ 42.412405] page:ffffea000025a780 count:1 mapcount:0 mapping: (null) index:0x0 compound_mapcount: 0 +[ 42.413298] flags: 0x100000000008100(slab|head) +[ 42.413729] raw: 0100000000008100 0000000000000000 0000000000000000 00000001800c000c +[ 42.414387] raw: ffffea00002a9500 0000000900000007 ffff88000c401280 0000000000000000 +[ 42.415074] page dumped because: kasan: bad access detected +[ 42.415604] +[ 42.415757] Memory state around the buggy address: +[ 42.416222] ffff88000969e880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 +[ 42.416904] ffff88000969e900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 +[ 42.417591] >ffff88000969e980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc +[ 42.418273] ^ +[ 42.418588] ffff88000969ea00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb +[ 42.419273] ffff88000969ea80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb +[ 42.419882] ================================================================== + +Reported-by: Andrey Konovalov +Signed-off-by: Craig Gallek +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv6/ip6_offload.c | 2 ++ + net/ipv6/ip6_output.c | 4 ++++ + net/ipv6/output_core.c | 14 ++++++++------ + net/ipv6/udp_offload.c | 2 ++ + 4 files changed, 16 insertions(+), 6 deletions(-) + +--- a/net/ipv6/ip6_offload.c ++++ b/net/ipv6/ip6_offload.c +@@ -122,6 +122,8 @@ static struct sk_buff *ipv6_gso_segment( + + if (udpfrag) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); ++ if (unfrag_ip6hlen < 0) ++ return ERR_PTR(unfrag_ip6hlen); + fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next) +--- a/net/ipv6/ip6_output.c ++++ b/net/ipv6/ip6_output.c +@@ -572,6 +572,10 @@ int ip6_fragment(struct net *net, struct + u8 *prevhdr, nexthdr = 0; + + hlen = ip6_find_1stfragopt(skb, &prevhdr); ++ if (hlen < 0) { ++ err = hlen; ++ goto fail; ++ } + nexthdr = *prevhdr; + + mtu = ip6_skb_dst_mtu(skb); +--- a/net/ipv6/output_core.c ++++ b/net/ipv6/output_core.c +@@ -79,14 +79,13 @@ EXPORT_SYMBOL(ipv6_select_ident); + int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) + { + u16 offset = sizeof(struct ipv6hdr); +- struct ipv6_opt_hdr *exthdr = +- (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); + int found_rhdr = 0; + *nexthdr = &ipv6_hdr(skb)->nexthdr; + +- while (offset + 1 <= packet_len) { ++ while (offset <= packet_len) { ++ struct ipv6_opt_hdr *exthdr; + + switch (**nexthdr) { + +@@ -107,13 +106,16 @@ int ip6_find_1stfragopt(struct sk_buff * + return offset; + } + +- offset += ipv6_optlen(exthdr); +- *nexthdr = &exthdr->nexthdr; ++ if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) ++ return -EINVAL; ++ + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); ++ offset += ipv6_optlen(exthdr); ++ *nexthdr = &exthdr->nexthdr; + } + +- return offset; ++ return -EINVAL; + } + EXPORT_SYMBOL(ip6_find_1stfragopt); + +--- a/net/ipv6/udp_offload.c ++++ b/net/ipv6/udp_offload.c +@@ -98,6 +98,8 @@ static struct sk_buff *udp6_ufo_fragment + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); ++ if (unfrag_ip6hlen < 0) ++ return ERR_PTR(unfrag_ip6hlen); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + diff --git a/queue-4.4/net-improve-handling-of-failures-on-link-and-route-dumps.patch b/queue-4.4/net-improve-handling-of-failures-on-link-and-route-dumps.patch new file mode 100644 index 00000000000..ee9e5bb0ced --- /dev/null +++ b/queue-4.4/net-improve-handling-of-failures-on-link-and-route-dumps.patch @@ -0,0 +1,205 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: David Ahern +Date: Mon, 15 May 2017 23:19:17 -0700 +Subject: net: Improve handling of failures on link and route dumps + +From: David Ahern + + +[ Upstream commit f6c5775ff0bfa62b072face6bf1d40f659f194b2 ] + +In general, rtnetlink dumps do not anticipate failure to dump a single +object (e.g., link or route) on a single pass. As both route and link +objects have grown via more attributes, that is no longer a given. + +netlink dumps can handle a failure if the dump function returns an +error; specifically, netlink_dump adds the return code to the response +if it is <= 0 so userspace is notified of the failure. The missing +piece is the rtnetlink dump functions returning the error. + +Fix route and link dump functions to return the errors if no object is +added to an skb (detected by skb->len != 0). IPv6 route dumps +(rt6_dump_route) already return the error; this patch updates IPv4 and +link dumps. Other dump functions may need to be ajusted as well. + +Reported-by: Jan Moskyto Matejka +Signed-off-by: David Ahern +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/core/rtnetlink.c | 36 ++++++++++++++++++++++++------------ + net/ipv4/fib_frontend.c | 15 +++++++++++---- + net/ipv4/fib_trie.c | 26 ++++++++++++++------------ + 3 files changed, 49 insertions(+), 28 deletions(-) + +--- a/net/core/rtnetlink.c ++++ b/net/core/rtnetlink.c +@@ -1458,13 +1458,13 @@ static int rtnl_dump_ifinfo(struct sk_bu + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); +- /* If we ran out of room on the first message, +- * we're in trouble +- */ +- WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + +- if (err < 0) +- goto out; ++ if (err < 0) { ++ if (likely(skb->len)) ++ goto out; ++ ++ goto out_err; ++ } + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + cont: +@@ -1472,10 +1472,12 @@ cont: + } + } + out: ++ err = skb->len; ++out_err: + cb->args[1] = idx; + cb->args[0] = h; + +- return skb->len; ++ return err; + } + + int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len) +@@ -3127,8 +3129,12 @@ static int rtnl_bridge_getlink(struct sk + err = br_dev->netdev_ops->ndo_bridge_getlink( + skb, portid, seq, dev, + filter_mask, NLM_F_MULTI); +- if (err < 0 && err != -EOPNOTSUPP) +- break; ++ if (err < 0 && err != -EOPNOTSUPP) { ++ if (likely(skb->len)) ++ break; ++ ++ goto out_err; ++ } + } + idx++; + } +@@ -3139,16 +3145,22 @@ static int rtnl_bridge_getlink(struct sk + seq, dev, + filter_mask, + NLM_F_MULTI); +- if (err < 0 && err != -EOPNOTSUPP) +- break; ++ if (err < 0 && err != -EOPNOTSUPP) { ++ if (likely(skb->len)) ++ break; ++ ++ goto out_err; ++ } + } + idx++; + } + } ++ err = skb->len; ++out_err: + rcu_read_unlock(); + cb->args[0] = idx; + +- return skb->len; ++ return err; + } + + static inline size_t bridge_nlmsg_size(void) +--- a/net/ipv4/fib_frontend.c ++++ b/net/ipv4/fib_frontend.c +@@ -757,7 +757,7 @@ static int inet_dump_fib(struct sk_buff + unsigned int e = 0, s_e; + struct fib_table *tb; + struct hlist_head *head; +- int dumped = 0; ++ int dumped = 0, err; + + if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && + ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) +@@ -777,20 +777,27 @@ static int inet_dump_fib(struct sk_buff + if (dumped) + memset(&cb->args[2], 0, sizeof(cb->args) - + 2 * sizeof(cb->args[0])); +- if (fib_table_dump(tb, skb, cb) < 0) +- goto out; ++ err = fib_table_dump(tb, skb, cb); ++ if (err < 0) { ++ if (likely(skb->len)) ++ goto out; ++ ++ goto out_err; ++ } + dumped = 1; + next: + e++; + } + } + out: ++ err = skb->len; ++out_err: + rcu_read_unlock(); + + cb->args[1] = e; + cb->args[0] = h; + +- return skb->len; ++ return err; + } + + /* Prepare and feed intra-kernel routing request. +--- a/net/ipv4/fib_trie.c ++++ b/net/ipv4/fib_trie.c +@@ -1906,6 +1906,8 @@ static int fn_trie_dump_leaf(struct key_ + + /* rcu_read_lock is hold by caller */ + hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { ++ int err; ++ + if (i < s_i) { + i++; + continue; +@@ -1916,17 +1918,14 @@ static int fn_trie_dump_leaf(struct key_ + continue; + } + +- if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid, +- cb->nlh->nlmsg_seq, +- RTM_NEWROUTE, +- tb->tb_id, +- fa->fa_type, +- xkey, +- KEYLENGTH - fa->fa_slen, +- fa->fa_tos, +- fa->fa_info, NLM_F_MULTI) < 0) { ++ err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, ++ cb->nlh->nlmsg_seq, RTM_NEWROUTE, ++ tb->tb_id, fa->fa_type, ++ xkey, KEYLENGTH - fa->fa_slen, ++ fa->fa_tos, fa->fa_info, NLM_F_MULTI); ++ if (err < 0) { + cb->args[4] = i; +- return -1; ++ return err; + } + i++; + } +@@ -1948,10 +1947,13 @@ int fib_table_dump(struct fib_table *tb, + t_key key = cb->args[3]; + + while ((l = leaf_walk_rcu(&tp, key)) != NULL) { +- if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) { ++ int err; ++ ++ err = fn_trie_dump_leaf(l, tb, skb, cb); ++ if (err < 0) { + cb->args[3] = key; + cb->args[2] = count; +- return -1; ++ return err; + } + + ++count; diff --git a/queue-4.4/net-phy-marvell-limit-errata-to-88m1101.patch b/queue-4.4/net-phy-marvell-limit-errata-to-88m1101.patch new file mode 100644 index 00000000000..48160c698ae --- /dev/null +++ b/queue-4.4/net-phy-marvell-limit-errata-to-88m1101.patch @@ -0,0 +1,114 @@ +From f2899788353c13891412b273fdff5f02d49aa40f Mon Sep 17 00:00:00 2001 +From: Andrew Lunn +Date: Tue, 23 May 2017 17:49:13 +0200 +Subject: net: phy: marvell: Limit errata to 88m1101 + +From: Andrew Lunn + +commit f2899788353c13891412b273fdff5f02d49aa40f upstream. + +The 88m1101 has an errata when configuring autoneg. However, it was +being applied to many other Marvell PHYs as well. Limit its scope to +just the 88m1101. + +Fixes: 76884679c644 ("phylib: Add support for Marvell 88e1111S and 88e1145") +Reported-by: Daniel Walker +Signed-off-by: Andrew Lunn +Acked-by: Harini Katakam +Reviewed-by: Florian Fainelli +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman + +--- + drivers/net/phy/marvell.c | 66 +++++++++++++++++++++++++--------------------- + 1 file changed, 37 insertions(+), 29 deletions(-) + +--- a/drivers/net/phy/marvell.c ++++ b/drivers/net/phy/marvell.c +@@ -203,34 +203,6 @@ static int marvell_config_aneg(struct ph + { + int err; + +- /* The Marvell PHY has an errata which requires +- * that certain registers get written in order +- * to restart autonegotiation */ +- err = phy_write(phydev, MII_BMCR, BMCR_RESET); +- +- if (err < 0) +- return err; +- +- err = phy_write(phydev, 0x1d, 0x1f); +- if (err < 0) +- return err; +- +- err = phy_write(phydev, 0x1e, 0x200c); +- if (err < 0) +- return err; +- +- err = phy_write(phydev, 0x1d, 0x5); +- if (err < 0) +- return err; +- +- err = phy_write(phydev, 0x1e, 0); +- if (err < 0) +- return err; +- +- err = phy_write(phydev, 0x1e, 0x100); +- if (err < 0) +- return err; +- + err = marvell_set_polarity(phydev, phydev->mdix); + if (err < 0) + return err; +@@ -264,6 +236,42 @@ static int marvell_config_aneg(struct ph + return 0; + } + ++static int m88e1101_config_aneg(struct phy_device *phydev) ++{ ++ int err; ++ ++ /* This Marvell PHY has an errata which requires ++ * that certain registers get written in order ++ * to restart autonegotiation ++ */ ++ err = phy_write(phydev, MII_BMCR, BMCR_RESET); ++ ++ if (err < 0) ++ return err; ++ ++ err = phy_write(phydev, 0x1d, 0x1f); ++ if (err < 0) ++ return err; ++ ++ err = phy_write(phydev, 0x1e, 0x200c); ++ if (err < 0) ++ return err; ++ ++ err = phy_write(phydev, 0x1d, 0x5); ++ if (err < 0) ++ return err; ++ ++ err = phy_write(phydev, 0x1e, 0); ++ if (err < 0) ++ return err; ++ ++ err = phy_write(phydev, 0x1e, 0x100); ++ if (err < 0) ++ return err; ++ ++ return marvell_config_aneg(phydev); ++} ++ + #ifdef CONFIG_OF_MDIO + /* + * Set and/or override some configuration registers based on the +@@ -993,7 +1001,7 @@ static struct phy_driver marvell_drivers + .name = "Marvell 88E1101", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, +- .config_aneg = &marvell_config_aneg, ++ .config_aneg = &m88e1101_config_aneg, + .read_status = &genphy_read_status, + .ack_interrupt = &marvell_ack_interrupt, + .config_intr = &marvell_config_intr, diff --git a/queue-4.4/netem-fix-skb_orphan_partial.patch b/queue-4.4/netem-fix-skb_orphan_partial.patch new file mode 100644 index 00000000000..3deb1ad818e --- /dev/null +++ b/queue-4.4/netem-fix-skb_orphan_partial.patch @@ -0,0 +1,54 @@ +From f6ba8d33cfbb46df569972e64dbb5bb7e929bfd9 Mon Sep 17 00:00:00 2001 +From: Eric Dumazet +Date: Thu, 11 May 2017 15:24:41 -0700 +Subject: netem: fix skb_orphan_partial() + +From: Eric Dumazet + +commit f6ba8d33cfbb46df569972e64dbb5bb7e929bfd9 upstream. + +I should have known that lowering skb->truesize was dangerous :/ + +In case packets are not leaving the host via a standard Ethernet device, +but looped back to local sockets, bad things can happen, as reported +by Michael Madsen ( https://bugzilla.kernel.org/show_bug.cgi?id=195713 ) + +So instead of tweaking skb->truesize, lets change skb->destructor +and keep a reference on the owner socket via its sk_refcnt. + +Fixes: f2f872f9272a ("netem: Introduce skb_orphan_partial() helper") +Signed-off-by: Eric Dumazet +Reported-by: Michael Madsen +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman + +--- + net/core/sock.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +--- a/net/core/sock.c ++++ b/net/core/sock.c +@@ -1690,17 +1690,17 @@ EXPORT_SYMBOL(skb_set_owner_w); + + void skb_orphan_partial(struct sk_buff *skb) + { +- /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, +- * so we do not completely orphan skb, but transfert all +- * accounted bytes but one, to avoid unexpected reorders. +- */ + if (skb->destructor == sock_wfree + #ifdef CONFIG_INET + || skb->destructor == tcp_wfree + #endif + ) { +- atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); +- skb->truesize = 1; ++ struct sock *sk = skb->sk; ++ ++ if (atomic_inc_not_zero(&sk->sk_refcnt)) { ++ atomic_sub(skb->truesize, &sk->sk_wmem_alloc); ++ skb->destructor = sock_efree; ++ } + } else { + skb_orphan(skb); + } diff --git a/queue-4.4/qmi_wwan-add-another-lenovo-em74xx-device-id.patch b/queue-4.4/qmi_wwan-add-another-lenovo-em74xx-device-id.patch new file mode 100644 index 00000000000..61a4ea6c8b0 --- /dev/null +++ b/queue-4.4/qmi_wwan-add-another-lenovo-em74xx-device-id.patch @@ -0,0 +1,33 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Bjørn Mork +Date: Wed, 17 May 2017 16:31:41 +0200 +Subject: qmi_wwan: add another Lenovo EM74xx device ID + +From: Bjørn Mork + + +[ Upstream commit 486181bcb3248e2f1977f4e69387a898234a4e1e ] + +In their infinite wisdom, and never ending quest for end user frustration, +Lenovo has decided to use a new USB device ID for the wwan modules in +their 2017 laptops. The actual hardware is still the Sierra Wireless +EM7455 or EM7430, depending on region. + +Signed-off-by: Bjørn Mork +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/usb/qmi_wwan.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/drivers/net/usb/qmi_wwan.c ++++ b/drivers/net/usb/qmi_wwan.c +@@ -730,6 +730,8 @@ static const struct usb_device_id produc + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ ++ {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ ++ {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ + {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ + {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/queue-4.4/s390-qeth-add-missing-hash-table-initializations.patch b/queue-4.4/s390-qeth-add-missing-hash-table-initializations.patch new file mode 100644 index 00000000000..95604a229fd --- /dev/null +++ b/queue-4.4/s390-qeth-add-missing-hash-table-initializations.patch @@ -0,0 +1,34 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Ursula Braun +Date: Wed, 10 May 2017 19:07:54 +0200 +Subject: s390/qeth: add missing hash table initializations + +From: Ursula Braun + + +[ Upstream commit ebccc7397e4a49ff64c8f44a54895de9d32fe742 ] + +commit 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") +added new hash tables, but missed to initialize them. + +Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") +Signed-off-by: Ursula Braun +Reviewed-by: Julian Wiedmann +Signed-off-by: Julian Wiedmann +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/s390/net/qeth_l3_main.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/drivers/s390/net/qeth_l3_main.c ++++ b/drivers/s390/net/qeth_l3_main.c +@@ -3232,6 +3232,8 @@ static int qeth_l3_probe_device(struct c + rc = qeth_l3_create_device_attributes(&gdev->dev); + if (rc) + return rc; ++ hash_init(card->ip_htable); ++ hash_init(card->ip_mc_htable); + card->options.layer2 = 0; + card->info.hwtrap = 0; + return 0; diff --git a/queue-4.4/s390-qeth-avoid-null-pointer-dereference-on-osn.patch b/queue-4.4/s390-qeth-avoid-null-pointer-dereference-on-osn.patch new file mode 100644 index 00000000000..8499532dab3 --- /dev/null +++ b/queue-4.4/s390-qeth-avoid-null-pointer-dereference-on-osn.patch @@ -0,0 +1,46 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Julian Wiedmann +Date: Wed, 10 May 2017 19:07:53 +0200 +Subject: s390/qeth: avoid null pointer dereference on OSN + +From: Julian Wiedmann + + +[ Upstream commit 25e2c341e7818a394da9abc403716278ee646014 ] + +Access card->dev only after checking whether's its valid. + +Signed-off-by: Julian Wiedmann +Reviewed-by: Ursula Braun +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/s390/net/qeth_l2_main.c | 10 ++++++---- + 1 file changed, 6 insertions(+), 4 deletions(-) + +--- a/drivers/s390/net/qeth_l2_main.c ++++ b/drivers/s390/net/qeth_l2_main.c +@@ -1112,7 +1112,6 @@ static int qeth_l2_setup_netdev(struct q + case QETH_CARD_TYPE_OSN: + card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, + ether_setup); +- card->dev->flags |= IFF_NOARP; + break; + default: + card->dev = alloc_etherdev(0); +@@ -1125,9 +1124,12 @@ static int qeth_l2_setup_netdev(struct q + card->dev->watchdog_timeo = QETH_TX_TIMEOUT; + card->dev->mtu = card->info.initial_mtu; + card->dev->netdev_ops = &qeth_l2_netdev_ops; +- card->dev->ethtool_ops = +- (card->info.type != QETH_CARD_TYPE_OSN) ? +- &qeth_l2_ethtool_ops : &qeth_l2_osn_ops; ++ if (card->info.type == QETH_CARD_TYPE_OSN) { ++ card->dev->ethtool_ops = &qeth_l2_osn_ops; ++ card->dev->flags |= IFF_NOARP; ++ } else { ++ card->dev->ethtool_ops = &qeth_l2_ethtool_ops; ++ } + card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { + card->dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM; diff --git a/queue-4.4/s390-qeth-handle-sysfs-error-during-initialization.patch b/queue-4.4/s390-qeth-handle-sysfs-error-during-initialization.patch new file mode 100644 index 00000000000..6aa2e49443c --- /dev/null +++ b/queue-4.4/s390-qeth-handle-sysfs-error-during-initialization.patch @@ -0,0 +1,82 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Ursula Braun +Date: Wed, 10 May 2017 19:07:51 +0200 +Subject: s390/qeth: handle sysfs error during initialization + +From: Ursula Braun + + +[ Upstream commit 9111e7880ccf419548c7b0887df020b08eadb075 ] + +When setting up the device from within the layer discipline's +probe routine, creating the layer-specific sysfs attributes can fail. +Report this error back to the caller, and handle it by +releasing the layer discipline. + +Signed-off-by: Ursula Braun +[jwi: updated commit msg, moved an OSN change to a subsequent patch] +Signed-off-by: Julian Wiedmann +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/s390/net/qeth_core_main.c | 4 +++- + drivers/s390/net/qeth_core_sys.c | 2 ++ + drivers/s390/net/qeth_l2_main.c | 5 ++++- + drivers/s390/net/qeth_l3_main.c | 5 ++++- + 4 files changed, 13 insertions(+), 3 deletions(-) + +--- a/drivers/s390/net/qeth_core_main.c ++++ b/drivers/s390/net/qeth_core_main.c +@@ -5650,8 +5650,10 @@ static int qeth_core_set_online(struct c + if (rc) + goto err; + rc = card->discipline->setup(card->gdev); +- if (rc) ++ if (rc) { ++ qeth_core_free_discipline(card); + goto err; ++ } + } + rc = card->discipline->set_online(gdev); + err: +--- a/drivers/s390/net/qeth_core_sys.c ++++ b/drivers/s390/net/qeth_core_sys.c +@@ -422,6 +422,8 @@ static ssize_t qeth_dev_layer2_store(str + goto out; + + rc = card->discipline->setup(card->gdev); ++ if (rc) ++ qeth_core_free_discipline(card); + out: + mutex_unlock(&card->discipline_mutex); + return rc ? rc : count; +--- a/drivers/s390/net/qeth_l2_main.c ++++ b/drivers/s390/net/qeth_l2_main.c +@@ -1030,8 +1030,11 @@ static int qeth_l2_stop(struct net_devic + static int qeth_l2_probe_device(struct ccwgroup_device *gdev) + { + struct qeth_card *card = dev_get_drvdata(&gdev->dev); ++ int rc; + +- qeth_l2_create_device_attributes(&gdev->dev); ++ rc = qeth_l2_create_device_attributes(&gdev->dev); ++ if (rc) ++ return rc; + INIT_LIST_HEAD(&card->vid_list); + hash_init(card->mac_htable); + card->options.layer2 = 1; +--- a/drivers/s390/net/qeth_l3_main.c ++++ b/drivers/s390/net/qeth_l3_main.c +@@ -3227,8 +3227,11 @@ static int qeth_l3_setup_netdev(struct q + static int qeth_l3_probe_device(struct ccwgroup_device *gdev) + { + struct qeth_card *card = dev_get_drvdata(&gdev->dev); ++ int rc; + +- qeth_l3_create_device_attributes(&gdev->dev); ++ rc = qeth_l3_create_device_attributes(&gdev->dev); ++ if (rc) ++ return rc; + card->options.layer2 = 0; + card->info.hwtrap = 0; + return 0; diff --git a/queue-4.4/s390-qeth-unbreak-osm-and-osn-support.patch b/queue-4.4/s390-qeth-unbreak-osm-and-osn-support.patch new file mode 100644 index 00000000000..2d08eeafeab --- /dev/null +++ b/queue-4.4/s390-qeth-unbreak-osm-and-osn-support.patch @@ -0,0 +1,263 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Julian Wiedmann +Date: Wed, 10 May 2017 19:07:52 +0200 +Subject: s390/qeth: unbreak OSM and OSN support + +From: Julian Wiedmann + + +[ Upstream commit 2d2ebb3ed0c6acfb014f98e427298673a5d07b82 ] + +commit b4d72c08b358 ("qeth: bridgeport support - basic control") +broke the support for OSM and OSN devices as follows: + +As OSM and OSN are L2 only, qeth_core_probe_device() does an early +setup by loading the l2 discipline and calling qeth_l2_probe_device(). +In this context, adding the l2-specific bridgeport sysfs attributes +via qeth_l2_create_device_attributes() hits a BUG_ON in fs/sysfs/group.c, +since the basic sysfs infrastructure for the device hasn't been +established yet. + +Note that OSN actually has its own unique sysfs attributes +(qeth_osn_devtype), so the additional attributes shouldn't be created +at all. +For OSM, add a new qeth_l2_devtype that contains all the common +and l2-specific sysfs attributes. +When qeth_core_probe_device() does early setup for OSM or OSN, assign +the corresponding devtype so that the ccwgroup probe code creates the +full set of sysfs attributes. +This allows us to skip qeth_l2_create_device_attributes() in case +of an early setup. + +Any device that can't do early setup will initially have only the +generic sysfs attributes, and when it's probed later +qeth_l2_probe_device() adds the l2-specific attributes. + +If an early-setup device is removed (by calling ccwgroup_ungroup()), +device_unregister() will - using the devtype - delete the +l2-specific attributes before qeth_l2_remove_device() is called. +So make sure to not remove them twice. + +What complicates the issue is that qeth_l2_probe_device() and +qeth_l2_remove_device() is also called on a device when its +layer2 attribute changes (ie. its layer mode is switched). +For early-setup devices this wouldn't work properly - we wouldn't +remove the l2-specific attributes when switching to L3. +But switching the layer mode doesn't actually make any sense; +we already decided that the device can only operate in L2! +So just refuse to switch the layer mode on such devices. Note that +OSN doesn't have a layer2 attribute, so we only need to special-case +OSM. + +Based on an initial patch by Ursula Braun. + +Fixes: b4d72c08b358 ("qeth: bridgeport support - basic control") +Signed-off-by: Julian Wiedmann +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/s390/net/qeth_core.h | 4 ++++ + drivers/s390/net/qeth_core_main.c | 17 +++++++++-------- + drivers/s390/net/qeth_core_sys.c | 22 ++++++++++++++-------- + drivers/s390/net/qeth_l2.h | 2 ++ + drivers/s390/net/qeth_l2_main.c | 17 +++++++++++++---- + drivers/s390/net/qeth_l2_sys.c | 8 ++++++++ + drivers/s390/net/qeth_l3_main.c | 1 + + 7 files changed, 51 insertions(+), 20 deletions(-) + +--- a/drivers/s390/net/qeth_core.h ++++ b/drivers/s390/net/qeth_core.h +@@ -717,6 +717,7 @@ enum qeth_discipline_id { + }; + + struct qeth_discipline { ++ const struct device_type *devtype; + void (*start_poll)(struct ccw_device *, int, unsigned long); + qdio_handler_t *input_handler; + qdio_handler_t *output_handler; +@@ -881,6 +882,9 @@ extern struct qeth_discipline qeth_l2_di + extern struct qeth_discipline qeth_l3_discipline; + extern const struct attribute_group *qeth_generic_attr_groups[]; + extern const struct attribute_group *qeth_osn_attr_groups[]; ++extern const struct attribute_group qeth_device_attr_group; ++extern const struct attribute_group qeth_device_blkt_group; ++extern const struct device_type qeth_generic_devtype; + extern struct workqueue_struct *qeth_wq; + + int qeth_card_hw_is_reachable(struct qeth_card *); +--- a/drivers/s390/net/qeth_core_main.c ++++ b/drivers/s390/net/qeth_core_main.c +@@ -5449,10 +5449,12 @@ void qeth_core_free_discipline(struct qe + card->discipline = NULL; + } + +-static const struct device_type qeth_generic_devtype = { ++const struct device_type qeth_generic_devtype = { + .name = "qeth_generic", + .groups = qeth_generic_attr_groups, + }; ++EXPORT_SYMBOL_GPL(qeth_generic_devtype); ++ + static const struct device_type qeth_osn_devtype = { + .name = "qeth_osn", + .groups = qeth_osn_attr_groups, +@@ -5578,23 +5580,22 @@ static int qeth_core_probe_device(struct + goto err_card; + } + +- if (card->info.type == QETH_CARD_TYPE_OSN) +- gdev->dev.type = &qeth_osn_devtype; +- else +- gdev->dev.type = &qeth_generic_devtype; +- + switch (card->info.type) { + case QETH_CARD_TYPE_OSN: + case QETH_CARD_TYPE_OSM: + rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2); + if (rc) + goto err_card; ++ ++ gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN) ++ ? card->discipline->devtype ++ : &qeth_osn_devtype; + rc = card->discipline->setup(card->gdev); + if (rc) + goto err_disc; +- case QETH_CARD_TYPE_OSD: +- case QETH_CARD_TYPE_OSX: ++ break; + default: ++ gdev->dev.type = &qeth_generic_devtype; + break; + } + +--- a/drivers/s390/net/qeth_core_sys.c ++++ b/drivers/s390/net/qeth_core_sys.c +@@ -409,12 +409,16 @@ static ssize_t qeth_dev_layer2_store(str + + if (card->options.layer2 == newdis) + goto out; +- else { +- card->info.mac_bits = 0; +- if (card->discipline) { +- card->discipline->remove(card->gdev); +- qeth_core_free_discipline(card); +- } ++ if (card->info.type == QETH_CARD_TYPE_OSM) { ++ /* fixed layer, can't switch */ ++ rc = -EOPNOTSUPP; ++ goto out; ++ } ++ ++ card->info.mac_bits = 0; ++ if (card->discipline) { ++ card->discipline->remove(card->gdev); ++ qeth_core_free_discipline(card); + } + + rc = qeth_core_load_discipline(card, newdis); +@@ -701,10 +705,11 @@ static struct attribute *qeth_blkt_devic + &dev_attr_inter_jumbo.attr, + NULL, + }; +-static struct attribute_group qeth_device_blkt_group = { ++const struct attribute_group qeth_device_blkt_group = { + .name = "blkt", + .attrs = qeth_blkt_device_attrs, + }; ++EXPORT_SYMBOL_GPL(qeth_device_blkt_group); + + static struct attribute *qeth_device_attrs[] = { + &dev_attr_state.attr, +@@ -724,9 +729,10 @@ static struct attribute *qeth_device_att + &dev_attr_switch_attrs.attr, + NULL, + }; +-static struct attribute_group qeth_device_attr_group = { ++const struct attribute_group qeth_device_attr_group = { + .attrs = qeth_device_attrs, + }; ++EXPORT_SYMBOL_GPL(qeth_device_attr_group); + + const struct attribute_group *qeth_generic_attr_groups[] = { + &qeth_device_attr_group, +--- a/drivers/s390/net/qeth_l2.h ++++ b/drivers/s390/net/qeth_l2.h +@@ -8,6 +8,8 @@ + + #include "qeth_core.h" + ++extern const struct attribute_group *qeth_l2_attr_groups[]; ++ + int qeth_l2_create_device_attributes(struct device *); + void qeth_l2_remove_device_attributes(struct device *); + void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card); +--- a/drivers/s390/net/qeth_l2_main.c ++++ b/drivers/s390/net/qeth_l2_main.c +@@ -1027,14 +1027,21 @@ static int qeth_l2_stop(struct net_devic + return 0; + } + ++static const struct device_type qeth_l2_devtype = { ++ .name = "qeth_layer2", ++ .groups = qeth_l2_attr_groups, ++}; ++ + static int qeth_l2_probe_device(struct ccwgroup_device *gdev) + { + struct qeth_card *card = dev_get_drvdata(&gdev->dev); + int rc; + +- rc = qeth_l2_create_device_attributes(&gdev->dev); +- if (rc) +- return rc; ++ if (gdev->dev.type == &qeth_generic_devtype) { ++ rc = qeth_l2_create_device_attributes(&gdev->dev); ++ if (rc) ++ return rc; ++ } + INIT_LIST_HEAD(&card->vid_list); + hash_init(card->mac_htable); + card->options.layer2 = 1; +@@ -1046,7 +1053,8 @@ static void qeth_l2_remove_device(struct + { + struct qeth_card *card = dev_get_drvdata(&cgdev->dev); + +- qeth_l2_remove_device_attributes(&cgdev->dev); ++ if (cgdev->dev.type == &qeth_generic_devtype) ++ qeth_l2_remove_device_attributes(&cgdev->dev); + qeth_set_allowed_threads(card, 0, 1); + wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0); + +@@ -1432,6 +1440,7 @@ static int qeth_l2_control_event(struct + } + + struct qeth_discipline qeth_l2_discipline = { ++ .devtype = &qeth_l2_devtype, + .start_poll = qeth_qdio_start_poll, + .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, + .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, +--- a/drivers/s390/net/qeth_l2_sys.c ++++ b/drivers/s390/net/qeth_l2_sys.c +@@ -272,3 +272,11 @@ void qeth_l2_setup_bridgeport_attrs(stru + } else + qeth_bridgeport_an_set(card, 0); + } ++ ++const struct attribute_group *qeth_l2_attr_groups[] = { ++ &qeth_device_attr_group, ++ &qeth_device_blkt_group, ++ /* l2 specific, see l2_{create,remove}_device_attributes(): */ ++ &qeth_l2_bridgeport_attr_group, ++ NULL, ++}; +--- a/drivers/s390/net/qeth_l3_main.c ++++ b/drivers/s390/net/qeth_l3_main.c +@@ -3522,6 +3522,7 @@ static int qeth_l3_control_event(struct + } + + struct qeth_discipline qeth_l3_discipline = { ++ .devtype = &qeth_generic_devtype, + .start_poll = qeth_qdio_start_poll, + .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, + .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, diff --git a/queue-4.4/sctp-do-not-inherit-ipv6_-mc-ac-fl-_list-from-parent.patch b/queue-4.4/sctp-do-not-inherit-ipv6_-mc-ac-fl-_list-from-parent.patch new file mode 100644 index 00000000000..138de50e0bf --- /dev/null +++ b/queue-4.4/sctp-do-not-inherit-ipv6_-mc-ac-fl-_list-from-parent.patch @@ -0,0 +1,34 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Eric Dumazet +Date: Wed, 17 May 2017 07:16:40 -0700 +Subject: sctp: do not inherit ipv6_{mc|ac|fl}_list from parent + +From: Eric Dumazet + + +[ Upstream commit fdcee2cbb8438702ea1b328fb6e0ac5e9a40c7f8 ] + +SCTP needs fixes similar to 83eaddab4378 ("ipv6/dccp: do not inherit +ipv6_mc_list from parent"), otherwise bad things can happen. + +Signed-off-by: Eric Dumazet +Reported-by: Andrey Konovalov +Tested-by: Andrey Konovalov +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/sctp/ipv6.c | 3 +++ + 1 file changed, 3 insertions(+) + +--- a/net/sctp/ipv6.c ++++ b/net/sctp/ipv6.c +@@ -674,6 +674,9 @@ static struct sock *sctp_v6_create_accep + newnp = inet6_sk(newsk); + + memcpy(newnp, np, sizeof(struct ipv6_pinfo)); ++ newnp->ipv6_mc_list = NULL; ++ newnp->ipv6_ac_list = NULL; ++ newnp->ipv6_fl_list = NULL; + + rcu_read_lock(); + opt = rcu_dereference(np->opt); diff --git a/queue-4.4/sctp-fix-icmp-processing-if-skb-is-non-linear.patch b/queue-4.4/sctp-fix-icmp-processing-if-skb-is-non-linear.patch new file mode 100644 index 00000000000..ca955fb2d95 --- /dev/null +++ b/queue-4.4/sctp-fix-icmp-processing-if-skb-is-non-linear.patch @@ -0,0 +1,72 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Davide Caratti +Date: Thu, 25 May 2017 19:14:56 +0200 +Subject: sctp: fix ICMP processing if skb is non-linear + +From: Davide Caratti + + +[ Upstream commit 804ec7ebe8ea003999ca8d1bfc499edc6a9e07df ] + +sometimes ICMP replies to INIT chunks are ignored by the client, even if +the encapsulated SCTP headers match an open socket. This happens when the +ICMP packet is carried by a paged skb: use skb_header_pointer() to read +packet contents beyond the SCTP header, so that chunk header and initiate +tag are validated correctly. + +v2: +- don't use skb_header_pointer() to read the transport header, since + icmp_socket_deliver() already puts these 8 bytes in the linear area. +- change commit message to make specific reference to INIT chunks. + +Signed-off-by: Davide Caratti +Acked-by: Marcelo Ricardo Leitner +Acked-by: Vlad Yasevich +Reviewed-by: Xin Long +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/sctp/input.c | 16 +++++++++------- + 1 file changed, 9 insertions(+), 7 deletions(-) + +--- a/net/sctp/input.c ++++ b/net/sctp/input.c +@@ -472,15 +472,14 @@ struct sock *sctp_err_lookup(struct net + struct sctp_association **app, + struct sctp_transport **tpp) + { ++ struct sctp_init_chunk *chunkhdr, _chunkhdr; + union sctp_addr saddr; + union sctp_addr daddr; + struct sctp_af *af; + struct sock *sk = NULL; + struct sctp_association *asoc; + struct sctp_transport *transport = NULL; +- struct sctp_init_chunk *chunkhdr; + __u32 vtag = ntohl(sctphdr->vtag); +- int len = skb->len - ((void *)sctphdr - (void *)skb->data); + + *app = NULL; *tpp = NULL; + +@@ -515,13 +514,16 @@ struct sock *sctp_err_lookup(struct net + * discard the packet. + */ + if (vtag == 0) { +- chunkhdr = (void *)sctphdr + sizeof(struct sctphdr); +- if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t) +- + sizeof(__be32) || ++ /* chunk header + first 4 octects of init header */ ++ chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) + ++ sizeof(struct sctphdr), ++ sizeof(struct sctp_chunkhdr) + ++ sizeof(__be32), &_chunkhdr); ++ if (!chunkhdr || + chunkhdr->chunk_hdr.type != SCTP_CID_INIT || +- ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) { ++ ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) + goto out; +- } ++ + } else if (vtag != asoc->c.peer_vtag) { + goto out; + } diff --git a/queue-4.4/sctp-fix-src-address-selection-if-using-secondary-addresses-for-ipv6.patch b/queue-4.4/sctp-fix-src-address-selection-if-using-secondary-addresses-for-ipv6.patch new file mode 100644 index 00000000000..8ad123ce4bb --- /dev/null +++ b/queue-4.4/sctp-fix-src-address-selection-if-using-secondary-addresses-for-ipv6.patch @@ -0,0 +1,119 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Xin Long +Date: Fri, 12 May 2017 14:39:52 +0800 +Subject: sctp: fix src address selection if using secondary addresses for ipv6 + +From: Xin Long + + +[ Upstream commit dbc2b5e9a09e9a6664679a667ff81cff6e5f2641 ] + +Commit 0ca50d12fe46 ("sctp: fix src address selection if using secondary +addresses") has fixed a src address selection issue when using secondary +addresses for ipv4. + +Now sctp ipv6 also has the similar issue. When using a secondary address, +sctp_v6_get_dst tries to choose the saddr which has the most same bits +with the daddr by sctp_v6_addr_match_len. It may make some cases not work +as expected. + +hostA: + [1] fd21:356b:459a:cf10::11 (eth1) + [2] fd21:356b:459a:cf20::11 (eth2) + +hostB: + [a] fd21:356b:459a:cf30::2 (eth1) + [b] fd21:356b:459a:cf40::2 (eth2) + +route from hostA to hostB: + fd21:356b:459a:cf30::/64 dev eth1 metric 1024 mtu 1500 + +The expected path should be: + fd21:356b:459a:cf10::11 <-> fd21:356b:459a:cf30::2 +But addr[2] matches addr[a] more bits than addr[1] does, according to +sctp_v6_addr_match_len. It causes the path to be: + fd21:356b:459a:cf20::11 <-> fd21:356b:459a:cf30::2 + +This patch is to fix it with the same way as Marcelo's fix for sctp ipv4. +As no ip_dev_find for ipv6, this patch is to use ipv6_chk_addr to check +if the saddr is in a dev instead. + +Note that for backwards compatibility, it will still do the addr_match_len +check here when no optimal is found. + +Reported-by: Patrick Talbert +Signed-off-by: Xin Long +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/sctp/ipv6.c | 46 +++++++++++++++++++++++++++++----------------- + 1 file changed, 29 insertions(+), 17 deletions(-) + +--- a/net/sctp/ipv6.c ++++ b/net/sctp/ipv6.c +@@ -239,12 +239,10 @@ static void sctp_v6_get_dst(struct sctp_ + struct sctp_bind_addr *bp; + struct ipv6_pinfo *np = inet6_sk(sk); + struct sctp_sockaddr_entry *laddr; +- union sctp_addr *baddr = NULL; + union sctp_addr *daddr = &t->ipaddr; + union sctp_addr dst_saddr; + struct in6_addr *final_p, final; + __u8 matchlen = 0; +- __u8 bmatchlen; + sctp_scope_t scope; + + memset(fl6, 0, sizeof(struct flowi6)); +@@ -311,23 +309,37 @@ static void sctp_v6_get_dst(struct sctp_ + */ + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { +- if (!laddr->valid) ++ struct dst_entry *bdst; ++ __u8 bmatchlen; ++ ++ if (!laddr->valid || ++ laddr->state != SCTP_ADDR_SRC || ++ laddr->a.sa.sa_family != AF_INET6 || ++ scope > sctp_scope(&laddr->a)) + continue; +- if ((laddr->state == SCTP_ADDR_SRC) && +- (laddr->a.sa.sa_family == AF_INET6) && +- (scope <= sctp_scope(&laddr->a))) { +- bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); +- if (!baddr || (matchlen < bmatchlen)) { +- baddr = &laddr->a; +- matchlen = bmatchlen; +- } +- } +- } +- if (baddr) { +- fl6->saddr = baddr->v6.sin6_addr; +- fl6->fl6_sport = baddr->v6.sin6_port; ++ ++ fl6->saddr = laddr->a.v6.sin6_addr; ++ fl6->fl6_sport = laddr->a.v6.sin6_port; + final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); +- dst = ip6_dst_lookup_flow(sk, fl6, final_p); ++ bdst = ip6_dst_lookup_flow(sk, fl6, final_p); ++ ++ if (!IS_ERR(bdst) && ++ ipv6_chk_addr(dev_net(bdst->dev), ++ &laddr->a.v6.sin6_addr, bdst->dev, 1)) { ++ if (!IS_ERR_OR_NULL(dst)) ++ dst_release(dst); ++ dst = bdst; ++ break; ++ } ++ ++ bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); ++ if (matchlen > bmatchlen) ++ continue; ++ ++ if (!IS_ERR_OR_NULL(dst)) ++ dst_release(dst); ++ dst = bdst; ++ matchlen = bmatchlen; + } + rcu_read_unlock(); + diff --git a/queue-4.4/series b/queue-4.4/series index 7c9df61070c..e48d988960e 100644 --- a/queue-4.4/series +++ b/queue-4.4/series @@ -1 +1,26 @@ sparc-fix-wstringop-overflow-warning.patch +dccp-tcp-do-not-inherit-mc_list-from-parent.patch +ipv6-dccp-do-not-inherit-ipv6_mc_list-from-parent.patch +s390-qeth-handle-sysfs-error-during-initialization.patch +s390-qeth-unbreak-osm-and-osn-support.patch +s390-qeth-avoid-null-pointer-dereference-on-osn.patch +s390-qeth-add-missing-hash-table-initializations.patch +tcp-avoid-fragmenting-peculiar-skbs-in-sack.patch +sctp-fix-src-address-selection-if-using-secondary-addresses-for-ipv6.patch +sctp-do-not-inherit-ipv6_-mc-ac-fl-_list-from-parent.patch +tcp-eliminate-negative-reordering-in-tcp_clean_rtx_queue.patch +net-improve-handling-of-failures-on-link-and-route-dumps.patch +ipv6-prevent-overrun-when-parsing-v6-header-options.patch +ipv6-check-ip6_find_1stfragopt-return-value-properly.patch +bridge-netlink-check-vlan_default_pvid-range.patch +qmi_wwan-add-another-lenovo-em74xx-device-id.patch +bridge-start-hello_timer-when-enabling-kernel_stp-in-br_stp_start.patch +ipv6-fix-out-of-bound-writes-in-__ip6_append_data.patch +be2net-fix-offload-features-for-q-in-q-packets.patch +virtio-net-enable-tso-checksum-offloads-for-q-in-q-vlans.patch +tcp-avoid-fastopen-api-to-be-used-on-af_unspec.patch +sctp-fix-icmp-processing-if-skb-is-non-linear.patch +ipv4-add-reference-counting-to-metrics.patch +netem-fix-skb_orphan_partial.patch +net-phy-marvell-limit-errata-to-88m1101.patch +vlan-fix-tcp-checksum-offloads-in-q-in-q-vlans.patch diff --git a/queue-4.4/tcp-avoid-fastopen-api-to-be-used-on-af_unspec.patch b/queue-4.4/tcp-avoid-fastopen-api-to-be-used-on-af_unspec.patch new file mode 100644 index 00000000000..5483e0b039d --- /dev/null +++ b/queue-4.4/tcp-avoid-fastopen-api-to-be-used-on-af_unspec.patch @@ -0,0 +1,88 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Wei Wang +Date: Wed, 24 May 2017 09:59:31 -0700 +Subject: tcp: avoid fastopen API to be used on AF_UNSPEC + +From: Wei Wang + + +[ Upstream commit ba615f675281d76fd19aa03558777f81fb6b6084 ] + +Fastopen API should be used to perform fastopen operations on the TCP +socket. It does not make sense to use fastopen API to perform disconnect +by calling it with AF_UNSPEC. The fastopen data path is also prone to +race conditions and bugs when using with AF_UNSPEC. + +One issue reported and analyzed by Vegard Nossum is as follows: ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ +Thread A: Thread B: +------------------------------------------------------------------------ +sendto() + - tcp_sendmsg() + - sk_stream_memory_free() = 0 + - goto wait_for_sndbuf + - sk_stream_wait_memory() + - sk_wait_event() // sleep + | sendto(flags=MSG_FASTOPEN, dest_addr=AF_UNSPEC) + | - tcp_sendmsg() + | - tcp_sendmsg_fastopen() + | - __inet_stream_connect() + | - tcp_disconnect() //because of AF_UNSPEC + | - tcp_transmit_skb()// send RST + | - return 0; // no reconnect! + | - sk_stream_wait_connect() + | - sock_error() + | - xchg(&sk->sk_err, 0) + | - return -ECONNRESET + - ... // wake up, see sk->sk_err == 0 + - skb_entail() on TCP_CLOSE socket + +If the connection is reopened then we will send a brand new SYN packet +after thread A has already queued a buffer. At this point I think the +socket internal state (sequence numbers etc.) becomes messed up. + +When the new connection is closed, the FIN-ACK is rejected because the +sequence number is outside the window. The other side tries to +retransmit, +but __tcp_retransmit_skb() calls tcp_trim_head() on an empty skb which +corrupts the skb data length and hits a BUG() in copy_and_csum_bits(). ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ + +Hence, this patch adds a check for AF_UNSPEC in the fastopen data path +and return EOPNOTSUPP to user if such case happens. + +Fixes: cf60af03ca4e7 ("tcp: Fast Open client - sendmsg(MSG_FASTOPEN)") +Reported-by: Vegard Nossum +Signed-off-by: Wei Wang +Signed-off-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp.c | 7 +++++-- + 1 file changed, 5 insertions(+), 2 deletions(-) + +--- a/net/ipv4/tcp.c ++++ b/net/ipv4/tcp.c +@@ -1071,9 +1071,12 @@ static int tcp_sendmsg_fastopen(struct s + int *copied, size_t size) + { + struct tcp_sock *tp = tcp_sk(sk); ++ struct sockaddr *uaddr = msg->msg_name; + int err, flags; + +- if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) ++ if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || ++ (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && ++ uaddr->sa_family == AF_UNSPEC)) + return -EOPNOTSUPP; + if (tp->fastopen_req) + return -EALREADY; /* Another Fast Open is in progress */ +@@ -1086,7 +1089,7 @@ static int tcp_sendmsg_fastopen(struct s + tp->fastopen_req->size = size; + + flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; +- err = __inet_stream_connect(sk->sk_socket, msg->msg_name, ++ err = __inet_stream_connect(sk->sk_socket, uaddr, + msg->msg_namelen, flags); + *copied = tp->fastopen_req->copied; + tcp_free_fastopen_req(tp); diff --git a/queue-4.4/tcp-avoid-fragmenting-peculiar-skbs-in-sack.patch b/queue-4.4/tcp-avoid-fragmenting-peculiar-skbs-in-sack.patch new file mode 100644 index 00000000000..3221d8a2c3d --- /dev/null +++ b/queue-4.4/tcp-avoid-fragmenting-peculiar-skbs-in-sack.patch @@ -0,0 +1,55 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Yuchung Cheng +Date: Wed, 10 May 2017 17:01:27 -0700 +Subject: tcp: avoid fragmenting peculiar skbs in SACK + +From: Yuchung Cheng + + +[ Upstream commit b451e5d24ba6687c6f0e7319c727a709a1846c06 ] + +This patch fixes a bug in splitting an SKB during SACK +processing. Specifically if an skb contains multiple +packets and is only partially sacked in the higher sequences, +tcp_match_sack_to_skb() splits the skb and marks the second fragment +as SACKed. + +The current code further attempts rounding up the first fragment +to MSS boundaries. But it misses a boundary condition when the +rounded-up fragment size (pkt_len) is exactly skb size. Spliting +such an skb is pointless and causses a kernel warning and aborts +the SACK processing. This patch universally checks such over-split +before calling tcp_fragment to prevent these unnecessary warnings. + +Fixes: adb92db857ee ("tcp: Make SACK code to split only at mss boundaries") +Signed-off-by: Yuchung Cheng +Signed-off-by: Eric Dumazet +Signed-off-by: Soheil Hassas Yeganeh +Acked-by: Neal Cardwell +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_input.c | 9 +++++---- + 1 file changed, 5 insertions(+), 4 deletions(-) + +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -1134,13 +1134,14 @@ static int tcp_match_skb_to_sack(struct + */ + if (pkt_len > mss) { + unsigned int new_len = (pkt_len / mss) * mss; +- if (!in_sack && new_len < pkt_len) { ++ if (!in_sack && new_len < pkt_len) + new_len += mss; +- if (new_len >= skb->len) +- return 0; +- } + pkt_len = new_len; + } ++ ++ if (pkt_len >= skb->len && !in_sack) ++ return 0; ++ + err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); + if (err < 0) + return err; diff --git a/queue-4.4/tcp-eliminate-negative-reordering-in-tcp_clean_rtx_queue.patch b/queue-4.4/tcp-eliminate-negative-reordering-in-tcp_clean_rtx_queue.patch new file mode 100644 index 00000000000..82474bdf417 --- /dev/null +++ b/queue-4.4/tcp-eliminate-negative-reordering-in-tcp_clean_rtx_queue.patch @@ -0,0 +1,44 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Soheil Hassas Yeganeh +Date: Mon, 15 May 2017 17:05:47 -0400 +Subject: tcp: eliminate negative reordering in tcp_clean_rtx_queue + +From: Soheil Hassas Yeganeh + + +[ Upstream commit bafbb9c73241760023d8981191ddd30bb1c6dbac ] + +tcp_ack() can call tcp_fragment() which may dededuct the +value tp->fackets_out when MSS changes. When prior_fackets +is larger than tp->fackets_out, tcp_clean_rtx_queue() can +invoke tcp_update_reordering() with negative values. This +results in absurd tp->reodering values higher than +sysctl_tcp_max_reordering. + +Note that tcp_update_reordering indeeds sets tp->reordering +to min(sysctl_tcp_max_reordering, metric), but because +the comparison is signed, a negative metric always wins. + +Fixes: c7caf8d3ed7a ("[TCP]: Fix reord detection due to snd_una covered holes") +Reported-by: Rebecca Isaacs +Signed-off-by: Soheil Hassas Yeganeh +Signed-off-by: Neal Cardwell +Signed-off-by: Yuchung Cheng +Signed-off-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_input.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -3220,7 +3220,7 @@ static int tcp_clean_rtx_queue(struct so + int delta; + + /* Non-retransmitted hole got filled? That's reordering */ +- if (reord < prior_fackets) ++ if (reord < prior_fackets && reord <= tp->fackets_out) + tcp_update_reordering(sk, tp->fackets_out - reord, 0); + + delta = tcp_is_fack(tp) ? pkts_acked : diff --git a/queue-4.4/virtio-net-enable-tso-checksum-offloads-for-q-in-q-vlans.patch b/queue-4.4/virtio-net-enable-tso-checksum-offloads-for-q-in-q-vlans.patch new file mode 100644 index 00000000000..a933290916c --- /dev/null +++ b/queue-4.4/virtio-net-enable-tso-checksum-offloads-for-q-in-q-vlans.patch @@ -0,0 +1,34 @@ +From foo@baz Fri Jun 2 09:29:55 JST 2017 +From: Vlad Yasevich +Date: Tue, 23 May 2017 13:38:43 -0400 +Subject: virtio-net: enable TSO/checksum offloads for Q-in-Q vlans + +From: Vlad Yasevich + + +[ Upstream commit 2836b4f224d4fd7d1a2b23c3eecaf0f0ae199a74 ] + +Since virtio does not provide it's own ndo_features_check handler, +TSO, and now checksum offload, are disabled for stacked vlans. +Re-enable the support and let the host take care of it. This +restores/improves Guest-to-Guest performance over Q-in-Q vlans. + +Acked-by: Jason Wang +Acked-by: Michael S. Tsirkin +Signed-off-by: Vladislav Yasevich +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/virtio_net.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/net/virtio_net.c ++++ b/drivers/net/virtio_net.c +@@ -1415,6 +1415,7 @@ static const struct net_device_ops virtn + #ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = virtnet_busy_poll, + #endif ++ .ndo_features_check = passthru_features_check, + }; + + static void virtnet_config_changed_work(struct work_struct *work) diff --git a/queue-4.4/vlan-fix-tcp-checksum-offloads-in-q-in-q-vlans.patch b/queue-4.4/vlan-fix-tcp-checksum-offloads-in-q-in-q-vlans.patch new file mode 100644 index 00000000000..f0bc602a0a9 --- /dev/null +++ b/queue-4.4/vlan-fix-tcp-checksum-offloads-in-q-in-q-vlans.patch @@ -0,0 +1,72 @@ +From 35d2f80b07bbe03fb358afb0bdeff7437a7d67ff Mon Sep 17 00:00:00 2001 +From: Vlad Yasevich +Date: Tue, 23 May 2017 13:38:41 -0400 +Subject: vlan: Fix tcp checksum offloads in Q-in-Q vlans + +From: Vlad Yasevich + +commit 35d2f80b07bbe03fb358afb0bdeff7437a7d67ff upstream. + +It appears that TCP checksum offloading has been broken for +Q-in-Q vlans. The behavior was execerbated by the +series + commit afb0bc972b52 ("Merge branch 'stacked_vlan_tso'") +that that enabled accleleration features on stacked vlans. + +However, event without that series, it is possible to trigger +this issue. It just requires a lot more specialized configuration. + +The root cause is the interaction between how +netdev_intersect_features() works, the features actually set on +the vlan devices and HW having the ability to run checksum with +longer headers. + +The issue starts when netdev_interesect_features() replaces +NETIF_F_HW_CSUM with a combination of NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM, +if the HW advertises IP|IPV6 specific checksums. This happens +for tagged and multi-tagged packets. However, HW that enables +IP|IPV6 checksum offloading doesn't gurantee that packets with +arbitrarily long headers can be checksummed. + +This patch disables IP|IPV6 checksums on the packet for multi-tagged +packets. + +CC: Toshiaki Makita +CC: Michal Kubecek +Signed-off-by: Vladislav Yasevich +Acked-by: Toshiaki Makita +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman + +--- + include/linux/if_vlan.h | 19 ++++++++++--------- + 1 file changed, 10 insertions(+), 9 deletions(-) + +--- a/include/linux/if_vlan.h ++++ b/include/linux/if_vlan.h +@@ -616,15 +616,16 @@ static inline bool skb_vlan_tagged_multi + static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, + netdev_features_t features) + { +- if (skb_vlan_tagged_multi(skb)) +- features = netdev_intersect_features(features, +- NETIF_F_SG | +- NETIF_F_HIGHDMA | +- NETIF_F_FRAGLIST | +- NETIF_F_GEN_CSUM | +- NETIF_F_HW_VLAN_CTAG_TX | +- NETIF_F_HW_VLAN_STAG_TX); +- ++ if (skb_vlan_tagged_multi(skb)) { ++ /* In the case of multi-tagged packets, use a direct mask ++ * instead of using netdev_interesect_features(), to make ++ * sure that only devices supporting NETIF_F_HW_CSUM will ++ * have checksum offloading support. ++ */ ++ features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | ++ NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | ++ NETIF_F_HW_VLAN_STAG_TX; ++ } + return features; + } +