summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-09-07 14:02:58 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-07 14:02:58 -0700
commit626bf91a292e2035af5b9d9cce35c5c138dfe06d (patch)
tree9f6e7e74511e3f27430f338bc454959fd487bcfd /net
parent4c00e1e2e58eefb288ba9ef585b6f19e1f33bf1e (diff)
parent0f77f2defaf682eb7e7ef623168e49c74ae529e3 (diff)
Merge tag 'net-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes and stragglers from Jakub Kicinski: "Networking stragglers and fixes, including changes from netfilter, wireless and can. Current release - regressions: - qrtr: revert check in qrtr_endpoint_post(), fixes audio and wifi - ip_gre: validate csum_start only on pull - bnxt_en: fix 64-bit doorbell operation on 32-bit kernels - ionic: fix double use of queue-lock, fix a sleeping in atomic - can: c_can: fix null-ptr-deref on ioctl() - cs89x0: disable compile testing on powerpc Current release - new code bugs: - bridge: mcast: fix vlan port router deadlock, consistently disable BH Previous releases - regressions: - dsa: tag_rtl4_a: fix egress tags, only port 0 was working - mptcp: fix possible divide by zero - netfilter: nft_ct: protect nft_ct_pcpu_template_refcnt with mutex - netfilter: socket: icmp6: fix use-after-scope - stmmac: fix MAC not working when system resume back with WoL active Previous releases - always broken: - ip/ip6_gre: use the same logic as SIT interfaces when computing v6LL address - seg6: set fc_nlinfo in nh_create_ipv4, nh_create_ipv6 - mptcp: only send extra TCP acks in eligible socket states - dsa: lantiq_gswip: fix maximum frame length - stmmac: fix overall budget calculation for rxtx_napi - bnxt_en: fix firmware version reporting via devlink - renesas: sh_eth: add missing barrier to fix freeing wrong tx descriptor Stragglers: - netfilter: conntrack: switch to siphash - netfilter: refuse insertion if chain has grown too large - ncsi: add get MAC address command to get Intel i210 MAC address" * tag 'net-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (76 commits) ieee802154: Remove redundant initialization of variable ret net: stmmac: fix MAC not working when system resume back with WoL active net: phylink: add suspend/resume support net: renesas: sh_eth: Fix freeing wrong tx descriptor bonding: 3ad: pass parameter bond_params by reference cxgb3: fix oops on module removal can: c_can: fix null-ptr-deref on ioctl() can: rcar_canfd: add __maybe_unused annotation to silence warning net: wwan: iosm: Unify IO accessors used in the driver net: wwan: iosm: Replace io.*64_lo_hi() with regular accessors net: qcom/emac: Replace strlcpy with strscpy ip6_gre: Revert "ip6_gre: add validation for csum_start" net: hns3: make hclgevf_cmd_caps_bit_map0 and hclge_cmd_caps_bit_map0 static selftests/bpf: Test XDP bonding nest and unwind bonding: Fix negative jump label count on nested bonding MAINTAINERS: add VM SOCKETS (AF_VSOCK) entry stmmac: dwmac-loongson:Fix missing return value iwlwifi: fix printk format warnings in uefi.c net: create netdev->dev_addr assignment helpers bnxt_en: Fix possible unintended driver initiated error recovery ...
Diffstat (limited to 'net')
-rw-r--r--net/bridge/br_multicast.c4
-rw-r--r--net/core/pktgen.c1
-rw-r--r--net/core/skbuff.c2
-rw-r--r--net/dsa/tag_rtl4_a.c7
-rw-r--r--net/ipv4/cipso_ipv4.c18
-rw-r--r--net/ipv4/ip_gre.c9
-rw-r--r--net/ipv4/nexthop.c2
-rw-r--r--net/ipv6/addrconf.c28
-rw-r--r--net/ipv6/ip6_gre.c2
-rw-r--r--net/ipv6/mcast.c10
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c4
-rw-r--r--net/ipv6/seg6_iptunnel.c2
-rw-r--r--net/mac802154/iface.c2
-rw-r--r--net/mptcp/pm_netlink.c10
-rw-r--r--net/mptcp/protocol.c97
-rw-r--r--net/mptcp/protocol.h3
-rw-r--r--net/ncsi/internal.h3
-rw-r--r--net/ncsi/ncsi-manage.c25
-rw-r--r--net/ncsi/ncsi-pkt.h6
-rw-r--r--net/ncsi/ncsi-rsp.c42
-rw-r--r--net/netfilter/nf_conntrack_core.c103
-rw-r--r--net/netfilter/nf_conntrack_expect.c25
-rw-r--r--net/netfilter/nf_conntrack_netlink.c4
-rw-r--r--net/netfilter/nf_conntrack_standalone.c4
-rw-r--r--net/netfilter/nf_nat_core.c18
-rw-r--r--net/netfilter/nft_ct.c9
-rw-r--r--net/qrtr/qrtr.c2
-rw-r--r--net/sched/sch_fq_codel.c12
-rw-r--r--net/tipc/socket.c2
29 files changed, 298 insertions, 158 deletions
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 9231617a16e4..3523c8c7068f 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -4255,7 +4255,7 @@ int br_multicast_set_port_router(struct net_bridge_mcast_port *pmctx,
bool del = false;
brmctx = br_multicast_port_ctx_get_global(pmctx);
- spin_lock(&brmctx->br->multicast_lock);
+ spin_lock_bh(&brmctx->br->multicast_lock);
if (pmctx->multicast_router == val) {
/* Refresh the temp router port timer */
if (pmctx->multicast_router == MDB_RTR_TYPE_TEMP) {
@@ -4305,7 +4305,7 @@ int br_multicast_set_port_router(struct net_bridge_mcast_port *pmctx,
}
err = 0;
unlock:
- spin_unlock(&brmctx->br->multicast_lock);
+ spin_unlock_bh(&brmctx->br->multicast_lock);
return err;
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 9e5a3249373c..a3d74e2704c4 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3602,7 +3602,6 @@ out:
static int pktgen_thread_worker(void *arg)
{
- DEFINE_WAIT(wait);
struct pktgen_thread *t = arg;
struct pktgen_dev *pkt_dev = NULL;
int cpu = t->cpu;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f9311762cc47..2170bea2c7de 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3884,7 +3884,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
skb_push(nskb, -skb_network_offset(nskb) + offset);
skb_release_head_state(nskb);
- __copy_skb_header(nskb, skb);
+ __copy_skb_header(nskb, skb);
skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb));
skb_copy_from_linear_data_offset(skb, -tnl_hlen,
diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c
index 40811bab4d09..f920487ae145 100644
--- a/net/dsa/tag_rtl4_a.c
+++ b/net/dsa/tag_rtl4_a.c
@@ -54,9 +54,10 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb,
p = (__be16 *)tag;
*p = htons(RTL4_A_ETHERTYPE);
- out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8);
- /* The lower bits is the port number */
- out |= (u8)dp->index;
+ out = (RTL4_A_PROTOCOL_RTL8366RB << RTL4_A_PROTOCOL_SHIFT) | (2 << 8);
+ /* The lower bits indicate the port number */
+ out |= BIT(dp->index);
+
p = (__be16 *)(tag + 2);
*p = htons(out);
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 7fbd0b532f52..099259fc826a 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -465,16 +465,14 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def)
if (!doi_def)
return;
- if (doi_def->map.std) {
- switch (doi_def->type) {
- case CIPSO_V4_MAP_TRANS:
- kfree(doi_def->map.std->lvl.cipso);
- kfree(doi_def->map.std->lvl.local);
- kfree(doi_def->map.std->cat.cipso);
- kfree(doi_def->map.std->cat.local);
- kfree(doi_def->map.std);
- break;
- }
+ switch (doi_def->type) {
+ case CIPSO_V4_MAP_TRANS:
+ kfree(doi_def->map.std->lvl.cipso);
+ kfree(doi_def->map.std->lvl.local);
+ kfree(doi_def->map.std->cat.cipso);
+ kfree(doi_def->map.std->cat.local);
+ kfree(doi_def->map.std);
+ break;
}
kfree(doi_def);
}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 177d26d8fb9c..0fe6c936dc54 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -473,8 +473,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
static int gre_handle_offloads(struct sk_buff *skb, bool csum)
{
- if (csum && skb_checksum_start(skb) < skb->data)
- return -EINVAL;
return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
}
@@ -632,15 +630,20 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
}
if (dev->header_ops) {
+ const int pull_len = tunnel->hlen + sizeof(struct iphdr);
+
if (skb_cow_head(skb, 0))
goto free_skb;
tnl_params = (const struct iphdr *)skb->data;
+ if (pull_len > skb_transport_offset(skb))
+ goto free_skb;
+
/* Pull skb since ip_tunnel_xmit() needs skb->data pointing
* to gre header.
*/
- skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+ skb_pull(skb, pull_len);
skb_reset_mac_header(skb);
} else {
if (skb_cow_head(skb, dev->needed_headroom))
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 4075230b14c6..75ca4b6e484f 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2490,6 +2490,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh,
.fc_gw4 = cfg->gw.ipv4,
.fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0,
.fc_flags = cfg->nh_flags,
+ .fc_nlinfo = cfg->nlinfo,
.fc_encap = cfg->nh_encap,
.fc_encap_type = cfg->nh_encap_type,
};
@@ -2528,6 +2529,7 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh,
.fc_ifindex = cfg->nh_ifindex,
.fc_gateway = cfg->gw.ipv6,
.fc_flags = cfg->nh_flags,
+ .fc_nlinfo = cfg->nlinfo,
.fc_encap = cfg->nh_encap,
.fc_encap_type = cfg->nh_encap_type,
.fc_is_fdb = cfg->nh_fdb,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 17756f3ed33b..c6a90b7bbb70 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3092,19 +3092,22 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
}
}
-#if IS_ENABLED(CONFIG_IPV6_SIT)
-static void sit_add_v4_addrs(struct inet6_dev *idev)
+#if IS_ENABLED(CONFIG_IPV6_SIT) || IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE)
+static void add_v4_addrs(struct inet6_dev *idev)
{
struct in6_addr addr;
struct net_device *dev;
struct net *net = dev_net(idev->dev);
- int scope, plen;
+ int scope, plen, offset = 0;
u32 pflags = 0;
ASSERT_RTNL();
memset(&addr, 0, sizeof(struct in6_addr));
- memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
+ /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
+ if (idev->dev->addr_len == sizeof(struct in6_addr))
+ offset = sizeof(struct in6_addr) - 4;
+ memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
if (idev->dev->flags&IFF_POINTOPOINT) {
addr.s6_addr32[0] = htonl(0xfe800000);
@@ -3342,8 +3345,6 @@ static void addrconf_dev_config(struct net_device *dev)
(dev->type != ARPHRD_IEEE1394) &&
(dev->type != ARPHRD_TUNNEL6) &&
(dev->type != ARPHRD_6LOWPAN) &&
- (dev->type != ARPHRD_IP6GRE) &&
- (dev->type != ARPHRD_IPGRE) &&
(dev->type != ARPHRD_TUNNEL) &&
(dev->type != ARPHRD_NONE) &&
(dev->type != ARPHRD_RAWIP)) {
@@ -3391,14 +3392,14 @@ static void addrconf_sit_config(struct net_device *dev)
return;
}
- sit_add_v4_addrs(idev);
+ add_v4_addrs(idev);
if (dev->flags&IFF_POINTOPOINT)
addrconf_add_mroute(dev);
}
#endif
-#if IS_ENABLED(CONFIG_NET_IPGRE)
+#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE)
static void addrconf_gre_config(struct net_device *dev)
{
struct inet6_dev *idev;
@@ -3411,7 +3412,13 @@ static void addrconf_gre_config(struct net_device *dev)
return;
}
- addrconf_addr_gen(idev, true);
+ if (dev->type == ARPHRD_ETHER) {
+ addrconf_addr_gen(idev, true);
+ return;
+ }
+
+ add_v4_addrs(idev);
+
if (dev->flags & IFF_POINTOPOINT)
addrconf_add_mroute(dev);
}
@@ -3587,7 +3594,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
addrconf_sit_config(dev);
break;
#endif
-#if IS_ENABLED(CONFIG_NET_IPGRE)
+#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE)
+ case ARPHRD_IP6GRE:
case ARPHRD_IPGRE:
addrconf_gre_config(dev);
break;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 7baf41d160f5..3ad201d372d8 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -629,8 +629,6 @@ drop:
static int gre_handle_offloads(struct sk_buff *skb, bool csum)
{
- if (csum && skb_checksum_start(skb) < skb->data)
- return -EINVAL;
return iptunnel_handle_offloads(skb,
csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index cd951faa2fac..bed8155508c8 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1356,8 +1356,8 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld,
return 0;
}
-static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld,
- unsigned long *max_delay)
+static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld,
+ unsigned long *max_delay)
{
*max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL);
@@ -1367,7 +1367,7 @@ static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld,
idev->mc_maxdelay = *max_delay;
- return 0;
+ return;
}
/* called with rcu_read_lock() */
@@ -1454,9 +1454,7 @@ static void __mld_query_work(struct sk_buff *skb)
mlh2 = (struct mld2_query *)skb_transport_header(skb);
- err = mld_process_v2(idev, mlh2, &max_delay);
- if (err < 0)
- goto out;
+ mld_process_v2(idev, mlh2, &max_delay);
if (group_type == IPV6_ADDR_ANY) { /* general query */
if (mlh2->mld2q_nsrcs)
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index 6fd54744cbc3..aa5bb8789ba0 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -99,7 +99,7 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
{
__be16 dport, sport;
const struct in6_addr *daddr = NULL, *saddr = NULL;
- struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct ipv6hdr *iph = ipv6_hdr(skb), ipv6_var;
struct sk_buff *data_skb = NULL;
int doff = 0;
int thoff = 0, tproto;
@@ -129,8 +129,6 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
thoff + sizeof(*hp);
} else if (tproto == IPPROTO_ICMPV6) {
- struct ipv6hdr ipv6_var;
-
if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
&sport, &dport, &ipv6_var))
return NULL;
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 1bf5f5ae75ac..3adc5d9211ad 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -385,7 +385,7 @@ static int seg6_output_core(struct net *net, struct sock *sk,
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
struct seg6_lwt *slwt;
- int err = -EINVAL;
+ int err;
err = seg6_do_srh(skb);
if (unlikely(err))
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 1cf5ac09edcb..323d3d2d986f 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -617,7 +617,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name,
{
struct net_device *ndev = NULL;
struct ieee802154_sub_if_data *sdata = NULL;
- int ret = -ENOMEM;
+ int ret;
ASSERT_RTNL();
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1e4289c507ff..c4f9a5ce3815 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -644,15 +644,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
if (subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- bool slow;
spin_unlock_bh(&msk->pm.lock);
pr_debug("send ack for %s",
mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr");
- slow = lock_sock_fast(ssk);
- tcp_send_ack(ssk);
- unlock_sock_fast(ssk, slow);
+ mptcp_subflow_send_ack(ssk);
spin_lock_bh(&msk->pm.lock);
}
}
@@ -669,7 +666,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
struct sock *sk = (struct sock *)msk;
struct mptcp_addr_info local;
- bool slow;
local_address((struct sock_common *)ssk, &local);
if (!addresses_equal(&local, addr, addr->port))
@@ -682,9 +678,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
spin_unlock_bh(&msk->pm.lock);
pr_debug("send ack for mp_prio");
- slow = lock_sock_fast(ssk);
- tcp_send_ack(ssk);
- unlock_sock_fast(ssk, slow);
+ mptcp_subflow_send_ack(ssk);
spin_lock_bh(&msk->pm.lock);
return 0;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ade648c3512b..2602f1386160 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -440,19 +440,22 @@ static bool tcp_can_send_ack(const struct sock *ssk)
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
}
+void mptcp_subflow_send_ack(struct sock *ssk)
+{
+ bool slow;
+
+ slow = lock_sock_fast(ssk);
+ if (tcp_can_send_ack(ssk))
+ tcp_send_ack(ssk);
+ unlock_sock_fast(ssk, slow);
+}
+
static void mptcp_send_ack(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- bool slow;
-
- slow = lock_sock_fast(ssk);
- if (tcp_can_send_ack(ssk))
- tcp_send_ack(ssk);
- unlock_sock_fast(ssk, slow);
- }
+ mptcp_for_each_subflow(msk, subflow)
+ mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow));
}
static void mptcp_subflow_cleanup_rbuf(struct sock *ssk)
@@ -1003,6 +1006,13 @@ static void mptcp_wmem_uncharge(struct sock *sk, int size)
msk->wmem_reserved += size;
}
+static void __mptcp_mem_reclaim_partial(struct sock *sk)
+{
+ lockdep_assert_held_once(&sk->sk_lock.slock);
+ __mptcp_update_wmem(sk);
+ sk_mem_reclaim_partial(sk);
+}
+
static void mptcp_mem_reclaim_partial(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1094,12 +1104,8 @@ static void __mptcp_clean_una(struct sock *sk)
msk->recovery = false;
out:
- if (cleaned) {
- if (tcp_under_memory_pressure(sk)) {
- __mptcp_update_wmem(sk);
- sk_mem_reclaim_partial(sk);
- }
- }
+ if (cleaned && tcp_under_memory_pressure(sk))
+ __mptcp_mem_reclaim_partial(sk);
if (snd_una == READ_ONCE(msk->snd_nxt) && !msk->recovery) {
if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
@@ -1179,6 +1185,7 @@ struct mptcp_sendmsg_info {
u16 limit;
u16 sent;
unsigned int flags;
+ bool data_lock_held;
};
static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq,
@@ -1250,17 +1257,17 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
return false;
}
-static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk)
+static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held)
{
- return !ssk->sk_tx_skb_cache &&
- tcp_under_memory_pressure(sk);
-}
+ gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation;
-static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk)
-{
- if (unlikely(mptcp_must_reclaim_memory(sk, ssk)))
- mptcp_mem_reclaim_partial(sk);
- return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation);
+ if (unlikely(tcp_under_memory_pressure(sk))) {
+ if (data_lock_held)
+ __mptcp_mem_reclaim_partial(sk);
+ else
+ mptcp_mem_reclaim_partial(sk);
+ }
+ return __mptcp_alloc_tx_skb(sk, ssk, gfp);
}
/* note: this always recompute the csum on the whole skb, even
@@ -1284,7 +1291,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
bool zero_window_probe = false;
struct mptcp_ext *mpext = NULL;
struct sk_buff *skb, *tail;
- bool can_collapse = false;
+ bool must_collapse = false;
int size_bias = 0;
int avail_size;
size_t ret = 0;
@@ -1304,16 +1311,24 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
* SSN association set here
*/
mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
- can_collapse = (info->size_goal - skb->len > 0) &&
- mptcp_skb_can_collapse_to(data_seq, skb, mpext);
- if (!can_collapse) {
+ if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) {
TCP_SKB_CB(skb)->eor = 1;
- } else {
+ goto alloc_skb;
+ }
+
+ must_collapse = (info->size_goal - skb->len > 0) &&
+ (skb_shinfo(skb)->nr_frags < sysctl_max_skb_frags);
+ if (must_collapse) {
size_bias = skb->len;
avail_size = info->size_goal - skb->len;
}
}
+alloc_skb:
+ if (!must_collapse && !ssk->sk_tx_skb_cache &&
+ !mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held))
+ return 0;
+
/* Zero window and all data acked? Probe. */
avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size);
if (avail_size == 0) {
@@ -1343,7 +1358,6 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
if (skb == tail) {
TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH;
mpext->data_len += ret;
- WARN_ON_ONCE(!can_collapse);
WARN_ON_ONCE(zero_window_probe);
goto out;
}
@@ -1530,15 +1544,6 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
if (ssk != prev_ssk)
lock_sock(ssk);
- /* keep it simple and always provide a new skb for the
- * subflow, even if we will not use it when collapsing
- * on the pending one
- */
- if (!mptcp_alloc_tx_skb(sk, ssk)) {
- mptcp_push_release(sk, ssk, &info);
- goto out;
- }
-
ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
if (ret <= 0) {
mptcp_push_release(sk, ssk, &info);
@@ -1571,7 +1576,9 @@ out:
static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- struct mptcp_sendmsg_info info;
+ struct mptcp_sendmsg_info info = {
+ .data_lock_held = true,
+ };
struct mptcp_data_frag *dfrag;
struct sock *xmit_ssk;
int len, copied = 0;
@@ -1597,13 +1604,6 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
goto out;
}
- if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) {
- __mptcp_update_wmem(sk);
- sk_mem_reclaim_partial(sk);
- }
- if (!__mptcp_alloc_tx_skb(sk, ssk, GFP_ATOMIC))
- goto out;
-
ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
if (ret <= 0)
goto out;
@@ -2409,9 +2409,6 @@ static void __mptcp_retrans(struct sock *sk)
info.sent = 0;
info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
while (info.sent < info.limit) {
- if (!mptcp_alloc_tx_skb(sk, ssk))
- break;
-
ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
if (ret <= 0)
break;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d7aba1c4dc48..d3e6fd1615f1 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -34,7 +34,7 @@
#define OPTIONS_MPTCP_MPC (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | \
OPTION_MPTCP_MPC_ACK)
#define OPTIONS_MPTCP_MPJ (OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \
- OPTION_MPTCP_MPJ_SYNACK)
+ OPTION_MPTCP_MPJ_ACK)
/* MPTCP option subtypes */
#define MPTCPOPT_MP_CAPABLE 0
@@ -573,6 +573,7 @@ void __init mptcp_subflow_init(void);
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow);
+void mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_reset(struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 0b6cfd3b31e0..03757e76bb6b 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -80,6 +80,7 @@ enum {
#define NCSI_OEM_MFR_BCM_ID 0x113d
#define NCSI_OEM_MFR_INTEL_ID 0x157
/* Intel specific OEM command */
+#define NCSI_OEM_INTEL_CMD_GMA 0x06 /* CMD ID for Get MAC */
#define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */
/* Broadcom specific OEM Command */
#define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */
@@ -89,6 +90,7 @@ enum {
#define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */
#define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */
/* OEM Command payload lengths*/
+#define NCSI_OEM_INTEL_CMD_GMA_LEN 5
#define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7
#define NCSI_OEM_BCM_CMD_GMA_LEN 12
#define NCSI_OEM_MLX_CMD_GMA_LEN 8
@@ -99,6 +101,7 @@ enum {
/* Mac address offset in OEM response */
#define BCM_MAC_ADDR_OFFSET 28
#define MLX_MAC_ADDR_OFFSET 8
+#define INTEL_MAC_ADDR_OFFSET 1
struct ncsi_channel_version {
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 89c7742cd72e..7121ce2a47c0 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -795,13 +795,36 @@ static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca)
return ret;
}
+static int ncsi_oem_gma_handler_intel(struct ncsi_cmd_arg *nca)
+{
+ unsigned char data[NCSI_OEM_INTEL_CMD_GMA_LEN];
+ int ret = 0;
+
+ nca->payload = NCSI_OEM_INTEL_CMD_GMA_LEN;
+
+ memset(data, 0, NCSI_OEM_INTEL_CMD_GMA_LEN);
+ *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID);
+ data[4] = NCSI_OEM_INTEL_CMD_GMA;
+
+ nca->data = data;
+
+ ret = ncsi_xmit_cmd(nca);
+ if (ret)
+ netdev_err(nca->ndp->ndev.dev,
+ "NCSI: Failed to transmit cmd 0x%x during configure\n",
+ nca->type);
+
+ return ret;
+}
+
/* OEM Command handlers initialization */
static struct ncsi_oem_gma_handler {
unsigned int mfr_id;
int (*handler)(struct ncsi_cmd_arg *nca);
} ncsi_oem_gma_handlers[] = {
{ NCSI_OEM_MFR_BCM_ID, ncsi_oem_gma_handler_bcm },
- { NCSI_OEM_MFR_MLX_ID, ncsi_oem_gma_handler_mlx }
+ { NCSI_OEM_MFR_MLX_ID, ncsi_oem_gma_handler_mlx },
+ { NCSI_OEM_MFR_INTEL_ID, ncsi_oem_gma_handler_intel }
};
static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id)
diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h
index 80938b338fee..ba66c7dc3a21 100644
--- a/net/ncsi/ncsi-pkt.h
+++ b/net/ncsi/ncsi-pkt.h
@@ -178,6 +178,12 @@ struct ncsi_rsp_oem_bcm_pkt {
unsigned char data[]; /* Cmd specific Data */
};
+/* Intel Response Data */
+struct ncsi_rsp_oem_intel_pkt {
+ unsigned char cmd; /* OEM Command ID */
+ unsigned char data[]; /* Cmd specific Data */
+};
+
/* Get Link Status */
struct ncsi_rsp_gls_pkt {
struct ncsi_rsp_pkt_hdr rsp; /* Response header */
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index d48374894817..6447a09932f5 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -699,9 +699,51 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr)
return 0;
}
+/* Response handler for Intel command Get Mac Address */
+static int ncsi_rsp_handler_oem_intel_gma(struct ncsi_request *nr)
+{
+ struct ncsi_dev_priv *ndp = nr->ndp;
+ struct net_device *ndev = ndp->ndev.dev;
+ const struct net_device_ops *ops = ndev->netdev_ops;
+ struct ncsi_rsp_oem_pkt *rsp;
+ struct sockaddr saddr;
+ int ret = 0;
+
+ /* Get the response header */
+ rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp);
+
+ saddr.sa_family = ndev->type;
+ ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+ memcpy(saddr.sa_data, &rsp->data[INTEL_MAC_ADDR_OFFSET], ETH_ALEN);
+ /* Increase mac address by 1 for BMC's address */
+ eth_addr_inc((u8 *)saddr.sa_data);
+ if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
+ return -ENXIO;
+
+ /* Set the flag for GMA command which should only be called once */
+ ndp->gma_flag = 1;
+
+ ret = ops->ndo_set_mac_address(ndev, &saddr);
+ if (ret < 0)
+ netdev_warn(ndev,
+ "NCSI: 'Writing mac address to device failed\n");
+
+ return ret;
+}
+
/* Response handler for Intel card */
static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr)
{
+ struct ncsi_rsp_oem_intel_pkt *intel;
+ struct ncsi_rsp_oem_pkt *rsp;
+
+ /* Get the response header */
+ rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp);
+ intel = (struct ncsi_rsp_oem_intel_pkt *)(rsp->data);
+
+ if (intel->cmd == NCSI_OEM_INTEL_CMD_GMA)
+ return ncsi_rsp_handler_oem_intel_gma(nr);
+
return 0;
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index d31dbccbe7bd..94e18fb9690d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -21,7 +21,6 @@
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/random.h>
-#include <linux/jhash.h>
#include <linux/siphash.h>
#include <linux/err.h>
#include <linux/percpu.h>
@@ -78,6 +77,8 @@ static __read_mostly bool nf_conntrack_locks_all;
#define GC_SCAN_INTERVAL (120u * HZ)
#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
+#define MAX_CHAINLEN 64u
+
static struct conntrack_gc_work conntrack_gc_work;
void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
@@ -184,25 +185,31 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
unsigned int nf_conntrack_max __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_max);
seqcount_spinlock_t nf_conntrack_generation __read_mostly;
-static unsigned int nf_conntrack_hash_rnd __read_mostly;
+static siphash_key_t nf_conntrack_hash_rnd __read_mostly;
static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
const struct net *net)
{
- unsigned int n;
- u32 seed;
+ struct {
+ struct nf_conntrack_man src;
+ union nf_inet_addr dst_addr;
+ u32 net_mix;
+ u16 dport;
+ u16 proto;
+ } __aligned(SIPHASH_ALIGNMENT) combined;
get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd));
- /* The direction must be ignored, so we hash everything up to the
- * destination ports (which is a multiple of 4) and treat the last
- * three bytes manually.
- */
- seed = nf_conntrack_hash_rnd ^ net_hash_mix(net);
- n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);
- return jhash2((u32 *)tuple, n, seed ^
- (((__force __u16)tuple->dst.u.all << 16) |
- tuple->dst.protonum));
+ memset(&combined, 0, sizeof(combined));
+
+ /* The direction must be ignored, so handle usable members manually. */
+ combined.src = tuple->src;
+ combined.dst_addr = tuple->dst.u3;
+ combined.net_mix = net_hash_mix(net);
+ combined.dport = (__force __u16)tuple->dst.u.all;
+ combined.proto = tuple->dst.protonum;
+
+ return (u32)siphash(&combined, sizeof(combined), &nf_conntrack_hash_rnd);
}
static u32 scale_hash(u32 hash)
@@ -835,7 +842,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
+ unsigned int chainlen = 0;
unsigned int sequence;
+ int err = -EEXIST;
zone = nf_ct_zone(ct);
@@ -849,15 +858,24 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* See if there's one in the list already, including reverse */
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) {
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
+ if (chainlen++ > MAX_CHAINLEN)
+ goto chaintoolong;
+ }
+
+ chainlen = 0;
+
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) {
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
+ if (chainlen++ > MAX_CHAINLEN)
+ goto chaintoolong;
+ }
smp_wmb();
/* The caller holds a reference to this object */
@@ -867,11 +885,13 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
NF_CT_STAT_INC(net, insert);
local_bh_enable();
return 0;
-
+chaintoolong:
+ NF_CT_STAT_INC(net, chaintoolong);
+ err = -ENOSPC;
out:
nf_conntrack_double_unlock(hash, reply_hash);
local_bh_enable();
- return -EEXIST;
+ return err;
}
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
@@ -1084,6 +1104,7 @@ int
__nf_conntrack_confirm(struct sk_buff *skb)
{
const struct nf_conntrack_zone *zone;
+ unsigned int chainlen = 0, sequence;
unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
@@ -1091,7 +1112,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
struct hlist_nulls_node *n;
enum ip_conntrack_info ctinfo;
struct net *net;
- unsigned int sequence;
int ret = NF_DROP;
ct = nf_ct_get(skb, &ctinfo);
@@ -1151,15 +1171,28 @@ __nf_conntrack_confirm(struct sk_buff *skb)
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) {
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
+ if (chainlen++ > MAX_CHAINLEN)
+ goto chaintoolong;
+ }
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
+ chainlen = 0;
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) {
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
+ if (chainlen++ > MAX_CHAINLEN) {
+chaintoolong:
+ nf_ct_add_to_dying_list(ct);
+ NF_CT_STAT_INC(net, chaintoolong);
+ NF_CT_STAT_INC(net, insert_failed);
+ ret = NF_DROP;
+ goto dying;
+ }
+ }
/* Timer relative to confirmation time, not original
setting time, otherwise we'd get timer wrap in
@@ -2594,26 +2627,24 @@ int nf_conntrack_init_start(void)
spin_lock_init(&nf_conntrack_locks[i]);
if (!nf_conntrack_htable_size) {
- /* Idea from tcp.c: use 1/16384 of memory.
- * On i386: 32MB machine has 512 buckets.
- * >= 1GB machines have 16384 buckets.
- * >= 4GB machines have 65536 buckets.
- */
nf_conntrack_htable_size
= (((nr_pages << PAGE_SHIFT) / 16384)
/ sizeof(struct hlist_head));
- if (nr_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE)))
- nf_conntrack_htable_size = 65536;
+ if (BITS_PER_LONG >= 64 &&
+ nr_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE)))
+ nf_conntrack_htable_size = 262144;
else if (nr_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
- nf_conntrack_htable_size = 16384;
- if (nf_conntrack_htable_size < 32)
- nf_conntrack_htable_size = 32;
-
- /* Use a max. factor of four by default to get the same max as
- * with the old struct list_heads. When a table size is given
- * we use the old value of 8 to avoid reducing the max.
- * entries. */
- max_factor = 4;
+ nf_conntrack_htable_size = 65536;
+
+ if (nf_conntrack_htable_size < 1024)
+ nf_conntrack_htable_size = 1024;
+ /* Use a max. factor of one by default to keep the average
+ * hash chain length at 2 entries. Each entry has to be added
+ * twice (once for original direction, once for reply).
+ * When a table size is given we use the old value of 8 to
+ * avoid implicit reduction of the max entries setting.
+ */
+ max_factor = 1;
}
nf_conntrack_hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, 1);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 1e851bc2e61a..f562eeef4234 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -17,7 +17,7 @@
#include <linux/err.h>
#include <linux/percpu.h>
#include <linux/kernel.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
#include <linux/moduleparam.h>
#include <linux/export.h>
#include <net/net_namespace.h>
@@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_hash);
unsigned int nf_ct_expect_max __read_mostly;
static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
-static unsigned int nf_ct_expect_hashrnd __read_mostly;
+static siphash_key_t nf_ct_expect_hashrnd __read_mostly;
/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
@@ -81,15 +81,26 @@ static void nf_ct_expectation_timed_out(struct timer_list *t)
static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple)
{
- unsigned int hash, seed;
+ struct {
+ union nf_inet_addr dst_addr;
+ u32 net_mix;
+ u16 dport;
+ u8 l3num;
+ u8 protonum;
+ } __aligned(SIPHASH_ALIGNMENT) combined;
+ u32 hash;
get_random_once(&nf_ct_expect_hashrnd, sizeof(nf_ct_expect_hashrnd));
- seed = nf_ct_expect_hashrnd ^ net_hash_mix(n);
+ memset(&combined, 0, sizeof(combined));
- hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
- (((tuple->dst.protonum ^ tuple->src.l3num) << 16) |
- (__force __u16)tuple->dst.u.all) ^ seed);
+ combined.dst_addr = tuple->dst.u3;
+ combined.net_mix = net_hash_mix(n);
+ combined.dport = (__force __u16)tuple->dst.u.all;
+ combined.l3num = tuple->src.l3num;
+ combined.protonum = tuple->dst.protonum;
+
+ hash = siphash(&combined, sizeof(combined), &nf_ct_expect_hashrnd);
return reciprocal_scale(hash, nf_ct_expect_hsize);
}
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 5f9fc6b94855..f1e5443fe7c7 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2528,7 +2528,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
nla_put_be32(skb, CTA_STATS_SEARCH_RESTART,
htonl(st->search_restart)) ||
nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE,
- htonl(st->clash_resolve)))
+ htonl(st->clash_resolve)) ||
+ nla_put_be32(skb, CTA_STATS_CHAIN_TOOLONG,
+ htonl(st->chaintoolong)))
goto nla_put_failure;
nlmsg_end(skb, nlh);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 7e0d956da51d..80f675d884b2 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -432,7 +432,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v)
unsigned int nr_conntracks;
if (v == SEQ_START_TOKEN) {
- seq_puts(seq, "entries clashres found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n");
+ seq_puts(seq, "entries clashres found new invalid ignore delete chainlength insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n");
return 0;
}
@@ -447,7 +447,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v)
st->invalid,
0,
0,
- 0,
+ st->chaintoolong,
st->insert,
st->insert_failed,
st->drop,
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 7de595ead06a..7008961f5cb0 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -13,7 +13,7 @@
#include <linux/skbuff.h>
#include <linux/gfp.h>
#include <net/xfrm.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
#include <linux/rtnetlink.h>
#include <net/netfilter/nf_conntrack.h>
@@ -34,7 +34,7 @@ static unsigned int nat_net_id __read_mostly;
static struct hlist_head *nf_nat_bysource __read_mostly;
static unsigned int nf_nat_htable_size __read_mostly;
-static unsigned int nf_nat_hash_rnd __read_mostly;
+static siphash_key_t nf_nat_hash_rnd __read_mostly;
struct nf_nat_lookup_hook_priv {
struct nf_hook_entries __rcu *entries;
@@ -153,12 +153,22 @@ static unsigned int
hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple)
{
unsigned int hash;
+ struct {
+ struct nf_conntrack_man src;
+ u32 net_mix;
+ u32 protonum;
+ } __aligned(SIPHASH_ALIGNMENT) combined;
get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd));
+ memset(&combined, 0, sizeof(combined));
+
/* Original src, to ensure we map it consistently if poss. */
- hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
- tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n));
+ combined.src = tuple->src;
+ combined.net_mix = net_hash_mix(n);
+ combined.protonum = tuple->dst.protonum;
+
+ hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd);
return reciprocal_scale(hash, nf_nat_htable_size);
}
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 337e22d8b40b..99b1de14ff7e 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -41,6 +41,7 @@ struct nft_ct_helper_obj {
#ifdef CONFIG_NF_CONNTRACK_ZONES
static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template);
static unsigned int nft_ct_pcpu_template_refcnt __read_mostly;
+static DEFINE_MUTEX(nft_ct_pcpu_mutex);
#endif
static u64 nft_ct_get_eval_counter(const struct nf_conn_counter *c,
@@ -525,8 +526,10 @@ static void __nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv)
#endif
#ifdef CONFIG_NF_CONNTRACK_ZONES
case NFT_CT_ZONE:
+ mutex_lock(&nft_ct_pcpu_mutex);
if (--nft_ct_pcpu_template_refcnt == 0)
nft_ct_tmpl_put_pcpu();
+ mutex_unlock(&nft_ct_pcpu_mutex);
break;
#endif
default:
@@ -564,9 +567,13 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
#endif
#ifdef CONFIG_NF_CONNTRACK_ZONES
case NFT_CT_ZONE:
- if (!nft_ct_tmpl_alloc_pcpu())
+ mutex_lock(&nft_ct_pcpu_mutex);
+ if (!nft_ct_tmpl_alloc_pcpu()) {
+ mutex_unlock(&nft_ct_pcpu_mutex);
return -ENOMEM;
+ }
nft_ct_pcpu_template_refcnt++;
+ mutex_unlock(&nft_ct_pcpu_mutex);
len = sizeof(u16);
break;
#endif
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 525e3ea063b1..ec2322529727 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -493,7 +493,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
goto err;
}
- if (!size || size & 3 || len != size + hdrlen)
+ if (!size || len != ALIGN(size, 4) + hdrlen)
goto err;
if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA &&
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index c4afdd026f51..bb0cd6d3d2c2 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -369,6 +369,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
{
struct fq_codel_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_FQ_CODEL_MAX + 1];
+ u32 quantum = 0;
int err;
if (!opt)
@@ -386,6 +387,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
q->flows_cnt > 65536)
return -EINVAL;
}
+ if (tb[TCA_FQ_CODEL_QUANTUM]) {
+ quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
+ if (quantum > FQ_CODEL_QUANTUM_MAX) {
+ NL_SET_ERR_MSG(extack, "Invalid quantum");
+ return -EINVAL;
+ }
+ }
sch_tree_lock(sch);
if (tb[TCA_FQ_CODEL_TARGET]) {
@@ -412,8 +420,8 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
if (tb[TCA_FQ_CODEL_ECN])
q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]);
- if (tb[TCA_FQ_CODEL_QUANTUM])
- q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
+ if (quantum)
+ q->quantum = quantum;
if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index e3105ba407c7..a0a27d87f631 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1426,7 +1426,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
if (ua) {
if (!tipc_uaddr_valid(ua, m->msg_namelen))
return -EINVAL;
- atype = ua->addrtype;
+ atype = ua->addrtype;
}
/* If socket belongs to a communication group follow other paths */