summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Kconfig2
-rw-r--r--net/ipv6/addrconf.c107
-rw-r--r--net/ipv6/af_inet6.c22
-rw-r--r--net/ipv6/anycast.c2
-rw-r--r--net/ipv6/datagram.c9
-rw-r--r--net/ipv6/exthdrs.c7
-rw-r--r--net/ipv6/icmp.c11
-rw-r--r--net/ipv6/ila/ila_main.c1
-rw-r--r--net/ipv6/ila/ila_xlat.c1
-rw-r--r--net/ipv6/inet6_hashtables.c69
-rw-r--r--net/ipv6/ip6_fib.c55
-rw-r--r--net/ipv6/ip6_gre.c3
-rw-r--r--net/ipv6/ip6_output.c18
-rw-r--r--net/ipv6/ip6_vti.c4
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/ipv6_sockglue.c22
-rw-r--r--net/ipv6/mcast.c8
-rw-r--r--net/ipv6/ndisc.c20
-rw-r--r--net/ipv6/netfilter/nf_defrag_ipv6_hooks.c11
-rw-r--r--net/ipv6/ping.c3
-rw-r--r--net/ipv6/raw.c23
-rw-r--r--net/ipv6/route.c30
-rw-r--r--net/ipv6/rpl_iptunnel.c3
-rw-r--r--net/ipv6/seg6_local.c108
-rw-r--r--net/ipv6/tcp_ipv6.c14
-rw-r--r--net/ipv6/udp.c115
-rw-r--r--net/ipv6/udp_offload.c10
-rw-r--r--net/ipv6/udplite.c1
-rw-r--r--net/ipv6/xfrm6_policy.c6
29 files changed, 437 insertions, 250 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 658bfed1df8b..08d4b7132d4c 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -152,7 +152,7 @@ config INET6_TUNNEL
default n
config IPV6_VTI
-tristate "Virtual (secure) IPv6: tunneling"
+ tristate "Virtual (secure) IPv6: tunneling"
select IPV6_TUNNEL
select NET_IP_TUNNEL
select XFRM
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 61291bd247b9..967913ad65e5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -202,6 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.ra_defrtr_metric = IP6_RT_PRIO_USER,
.accept_ra_from_local = 0,
.accept_ra_min_hop_limit= 1,
+ .accept_ra_min_lft = 0,
.accept_ra_pinfo = 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
.accept_ra_rtr_pref = 1,
@@ -262,6 +263,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.ra_defrtr_metric = IP6_RT_PRIO_USER,
.accept_ra_from_local = 0,
.accept_ra_min_hop_limit= 1,
+ .accept_ra_min_lft = 0,
.accept_ra_pinfo = 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
.accept_ra_rtr_pref = 1,
@@ -318,9 +320,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
static void addrconf_mod_rs_timer(struct inet6_dev *idev,
unsigned long when)
{
- if (!timer_pending(&idev->rs_timer))
+ if (!mod_timer(&idev->rs_timer, jiffies + when))
in6_dev_hold(idev);
- mod_timer(&idev->rs_timer, jiffies + when);
}
static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
@@ -1062,20 +1063,28 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
struct fib6_info *f6i = NULL;
int err = 0;
- if (addr_type == IPV6_ADDR_ANY ||
- (addr_type & IPV6_ADDR_MULTICAST &&
- !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) ||
- (!(idev->dev->flags & IFF_LOOPBACK) &&
- !netif_is_l3_master(idev->dev) &&
- addr_type & IPV6_ADDR_LOOPBACK))
+ if (addr_type == IPV6_ADDR_ANY) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid address");
return ERR_PTR(-EADDRNOTAVAIL);
+ } else if (addr_type & IPV6_ADDR_MULTICAST &&
+ !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) {
+ NL_SET_ERR_MSG_MOD(extack, "Cannot assign multicast address without \"IFA_F_MCAUTOJOIN\" flag");
+ return ERR_PTR(-EADDRNOTAVAIL);
+ } else if (!(idev->dev->flags & IFF_LOOPBACK) &&
+ !netif_is_l3_master(idev->dev) &&
+ addr_type & IPV6_ADDR_LOOPBACK) {
+ NL_SET_ERR_MSG_MOD(extack, "Cannot assign loopback address on this device");
+ return ERR_PTR(-EADDRNOTAVAIL);
+ }
if (idev->dead) {
- err = -ENODEV; /*XXX*/
+ NL_SET_ERR_MSG_MOD(extack, "device is going away");
+ err = -ENODEV;
goto out;
}
if (idev->cnf.disable_ipv6) {
+ NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device");
err = -EACCES;
goto out;
}
@@ -1102,7 +1111,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
goto out;
}
- f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags);
+ f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags, extack);
if (IS_ERR(f6i)) {
err = PTR_ERR(f6i);
f6i = NULL;
@@ -2562,12 +2571,18 @@ static void manage_tempaddrs(struct inet6_dev *idev,
ipv6_ifa_notify(0, ift);
}
- if ((create || list_empty(&idev->tempaddr_list)) &&
- idev->cnf.use_tempaddr > 0) {
+ /* Also create a temporary address if it's enabled but no temporary
+ * address currently exists.
+ * However, we get called with valid_lft == 0, prefered_lft == 0, create == false
+ * as part of cleanup (ie. deleting the mngtmpaddr).
+ * We don't want that to result in creating a new temporary ip address.
+ */
+ if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft))
+ create = true;
+
+ if (create && idev->cnf.use_tempaddr > 0) {
/* When a new public address is created as described
* in [ADDRCONF], also create a new temporary address.
- * Also create a temporary address if it's enabled but
- * no temporary address currently exists.
*/
read_unlock_bh(&idev->lock);
ipv6_create_tempaddr(ifp, false);
@@ -2726,6 +2741,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
return;
}
+ if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft)
+ goto put;
+
/*
* Two things going on here:
* 1) Add routes for on-link prefixes
@@ -2920,30 +2938,40 @@ static int inet6_addr_add(struct net *net, int ifindex,
ASSERT_RTNL();
- if (cfg->plen > 128)
+ if (cfg->plen > 128) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length");
return -EINVAL;
+ }
/* check the lifetime */
- if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft)
+ if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) {
+ NL_SET_ERR_MSG_MOD(extack, "address lifetime invalid");
return -EINVAL;
+ }
- if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64)
+ if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) {
+ NL_SET_ERR_MSG_MOD(extack, "address with \"mngtmpaddr\" flag must have a prefix length of 64");
return -EINVAL;
+ }
dev = __dev_get_by_index(net, ifindex);
if (!dev)
return -ENODEV;
idev = addrconf_add_dev(dev);
- if (IS_ERR(idev))
+ if (IS_ERR(idev)) {
+ NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device");
return PTR_ERR(idev);
+ }
if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk,
true, cfg->pfx, ifindex);
- if (ret < 0)
+ if (ret < 0) {
+ NL_SET_ERR_MSG_MOD(extack, "Multicast auto join failed");
return ret;
+ }
}
cfg->scope = ipv6_addr_scope(cfg->pfx);
@@ -3000,22 +3028,29 @@ static int inet6_addr_add(struct net *net, int ifindex,
}
static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
- const struct in6_addr *pfx, unsigned int plen)
+ const struct in6_addr *pfx, unsigned int plen,
+ struct netlink_ext_ack *extack)
{
struct inet6_ifaddr *ifp;
struct inet6_dev *idev;
struct net_device *dev;
- if (plen > 128)
+ if (plen > 128) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid prefix length");
return -EINVAL;
+ }
dev = __dev_get_by_index(net, ifindex);
- if (!dev)
+ if (!dev) {
+ NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface");
return -ENODEV;
+ }
idev = __in6_dev_get(dev);
- if (!idev)
+ if (!idev) {
+ NL_SET_ERR_MSG_MOD(extack, "IPv6 is disabled on this device");
return -ENXIO;
+ }
read_lock_bh(&idev->lock);
list_for_each_entry(ifp, &idev->addr_list, if_list) {
@@ -3038,6 +3073,8 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
}
}
read_unlock_bh(&idev->lock);
+
+ NL_SET_ERR_MSG_MOD(extack, "address not found");
return -EADDRNOTAVAIL;
}
@@ -3080,7 +3117,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg)
rtnl_lock();
err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr,
- ireq.ifr6_prefixlen);
+ ireq.ifr6_prefixlen, NULL);
rtnl_unlock();
return err;
}
@@ -3483,7 +3520,7 @@ static int fixup_permanent_addr(struct net *net,
struct fib6_info *f6i, *prev;
f6i = addrconf_f6i_alloc(net, idev, &ifp->addr, false,
- GFP_ATOMIC);
+ GFP_ATOMIC, NULL);
if (IS_ERR(f6i))
return PTR_ERR(f6i);
@@ -4693,7 +4730,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
ifa_flags &= IFA_F_MANAGETEMPADDR;
return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx,
- ifm->ifa_prefixlen);
+ ifm->ifa_prefixlen, extack);
}
static int modify_prefix_route(struct inet6_ifaddr *ifp,
@@ -4898,8 +4935,10 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
}
dev = __dev_get_by_index(net, ifm->ifa_index);
- if (!dev)
+ if (!dev) {
+ NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface");
return -ENODEV;
+ }
if (tb[IFA_FLAGS])
cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]);
@@ -4934,10 +4973,12 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
}
if (nlh->nlmsg_flags & NLM_F_EXCL ||
- !(nlh->nlmsg_flags & NLM_F_REPLACE))
+ !(nlh->nlmsg_flags & NLM_F_REPLACE)) {
+ NL_SET_ERR_MSG_MOD(extack, "address already assigned");
err = -EEXIST;
- else
+ } else {
err = inet6_addr_modify(net, ifa, &cfg);
+ }
in6_ifa_put(ifa);
@@ -5597,6 +5638,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier;
array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na;
+ array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft;
}
static inline size_t inet6_ifla6_size(void)
@@ -6791,6 +6833,13 @@ static const struct ctl_table addrconf_sysctl[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "accept_ra_min_lft",
+ .data = &ipv6_devconf.accept_ra_min_lft,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "accept_ra_pinfo",
.data = &ipv6_devconf.accept_ra_pinfo,
.maxlen = sizeof(int),
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 5d593ddc0347..368824fe9719 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -102,9 +102,9 @@ bool ipv6_mod_enabled(void)
}
EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
-static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
+static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
{
- const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
+ const int offset = sk->sk_prot->ipv6_pinfo_offset;
return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
@@ -200,12 +200,12 @@ lookup_protocol:
sk->sk_reuse = SK_CAN_REUSE;
inet = inet_sk(sk);
- inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
+ inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
if (SOCK_RAW == sock->type) {
inet->inet_num = protocol;
if (IPPROTO_RAW == protocol)
- inet->hdrincl = 1;
+ inet_set_bit(HDRINCL, sk);
}
sk->sk_destruct = inet6_sock_destruct;
@@ -229,7 +229,7 @@ lookup_protocol:
*/
inet->uc_ttl = -1;
- inet->mc_loop = 1;
+ inet_set_bit(MC_LOOP, sk);
inet->mc_ttl = 1;
inet->mc_index = 0;
RCU_INIT_POINTER(inet->mc_list, NULL);
@@ -399,7 +399,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
sk->sk_ipv6only = 1;
/* Make sure we are allowed to bind here. */
- if (snum || !(inet->bind_address_no_port ||
+ if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) ||
(flags & BIND_FORCE_ADDRESS_NO_PORT))) {
err = sk->sk_prot->get_port(sk, snum);
if (err) {
@@ -435,10 +435,8 @@ out_unlock:
goto out;
}
-/* bind for INET6 API */
-int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
- struct sock *sk = sock->sk;
u32 flags = BIND_WITH_LOCK;
const struct proto *prot;
int err = 0;
@@ -462,6 +460,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
return __inet6_bind(sk, uaddr, addr_len, flags);
}
+
+/* bind for INET6 API */
+int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+ return inet6_bind_sk(sock->sk, uaddr, addr_len);
+}
EXPORT_SYMBOL(inet6_bind);
int inet6_release(struct socket *sock)
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index dacdea7fcb62..bb17f484ee2c 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -305,7 +305,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
}
net = dev_net(idev->dev);
- f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC);
+ f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC, NULL);
if (IS_ERR(f6i)) {
err = PTR_ERR(f6i);
goto out;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9b6818453afe..41ebc4e57473 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -38,10 +38,11 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
}
-static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
+static void ip6_datagram_flow_key_init(struct flowi6 *fl6,
+ const struct sock *sk)
{
- struct inet_sock *inet = inet_sk(sk);
- struct ipv6_pinfo *np = inet6_sk(sk);
+ const struct inet_sock *inet = inet_sk(sk);
+ const struct ipv6_pinfo *np = inet6_sk(sk);
int oif = sk->sk_bound_dev_if;
memset(fl6, 0, sizeof(*fl6));
@@ -523,7 +524,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
} else {
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin->sin6_addr);
- if (inet_sk(sk)->cmsg_flags)
+ if (inet_cmsg_flags(inet_sk(sk)))
ip_cmsg_recv(msg, skb);
}
}
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 202fc3aaa83c..4952ae792450 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -612,8 +612,6 @@ looped_back:
kfree(buf);
- skb_dst_drop(skb);
-
ip6_route_input(skb);
if (skb_dst(skb)->error) {
@@ -650,7 +648,6 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb)
struct inet6_dev *idev = __in6_dev_get(skb->dev);
struct inet6_skb_parm *opt = IP6CB(skb);
struct in6_addr *addr = NULL;
- struct in6_addr daddr;
int n, i;
struct ipv6_rt_hdr *hdr;
struct rt0_hdr *rthdr;
@@ -798,9 +795,7 @@ looped_back:
return -1;
}
- daddr = *addr;
- *addr = ipv6_hdr(skb)->daddr;
- ipv6_hdr(skb)->daddr = daddr;
+ swap(*addr, ipv6_hdr(skb)->daddr);
ip6_route_input(skb);
if (skb_dst(skb)->error) {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4159662fa214..93a594a901d1 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -424,7 +424,10 @@ static struct net_device *icmp6_dev(const struct sk_buff *skb)
if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
const struct rt6_info *rt6 = skb_rt6_info(skb);
- if (rt6)
+ /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.),
+ * and ip6_null_entry could be set to skb if no route is found.
+ */
+ if (rt6 && rt6->rt6i_idev)
dev = rt6->rt6i_idev->dev;
}
@@ -1031,11 +1034,9 @@ drop_no_count:
return 0;
}
-void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
- u8 type,
+void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type,
const struct in6_addr *saddr,
- const struct in6_addr *daddr,
- int oif)
+ const struct in6_addr *daddr, int oif)
{
memset(fl6, 0, sizeof(*fl6));
fl6->saddr = *saddr;
diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c
index 3faf62530d6a..69caed07315f 100644
--- a/net/ipv6/ila/ila_main.c
+++ b/net/ipv6/ila/ila_main.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
#include <net/genetlink.h>
-#include <net/ila.h>
#include <net/netns/generic.h>
#include <uapi/linux/genetlink.h>
#include "ila.h"
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index bee45dfeb187..67e8c9440977 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -5,7 +5,6 @@
#include <linux/rhashtable.h>
#include <linux/vmalloc.h>
#include <net/genetlink.h>
-#include <net/ila.h>
#include <net/netns/generic.h>
#include <uapi/linux/genetlink.h>
#include "ila.h"
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b64b49012655..b0e8d278e8a9 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -39,6 +39,7 @@ u32 inet6_ehashfn(const struct net *net,
return __inet6_ehashfn(lhash, lport, fhash, fport,
inet6_ehash_secret + net_hash_mix(net));
}
+EXPORT_SYMBOL_GPL(inet6_ehashfn);
/*
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
@@ -111,22 +112,40 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
-static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb, int doff,
- const struct in6_addr *saddr,
- __be16 sport,
- const struct in6_addr *daddr,
- unsigned short hnum)
+/**
+ * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ * the selected sock or an error.
+ */
+struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr,
+ __be16 sport,
+ const struct in6_addr *daddr,
+ unsigned short hnum,
+ inet6_ehashfn_t *ehashfn)
{
struct sock *reuse_sk = NULL;
u32 phash;
if (sk->sk_reuseport) {
- phash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+ phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn,
+ net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
}
return reuse_sk;
}
+EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
/* called with rcu_read_lock() */
static struct sock *inet6_lhash2_lookup(struct net *net,
@@ -143,8 +162,8 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
- result = lookup_reuseport(net, sk, skb, doff,
- saddr, sport, daddr, hnum);
+ result = inet6_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum, inet6_ehashfn);
if (result)
return result;
@@ -156,30 +175,30 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
return result;
}
-static inline struct sock *inet6_lookup_run_bpf(struct net *net,
- struct inet_hashinfo *hashinfo,
- struct sk_buff *skb, int doff,
- const struct in6_addr *saddr,
- const __be16 sport,
- const struct in6_addr *daddr,
- const u16 hnum, const int dif)
+struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+ int protocol,
+ struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr,
+ const __be16 sport,
+ const struct in6_addr *daddr,
+ const u16 hnum, const int dif,
+ inet6_ehashfn_t *ehashfn)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
- if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
- return NULL; /* only TCP is supported */
-
- no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport,
+ no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
- reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+ reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum, ehashfn);
if (reuse_sk)
sk = reuse_sk;
return sk;
}
+EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
@@ -193,9 +212,11 @@ struct sock *inet6_lookup_listener(struct net *net,
unsigned int hash2;
/* Lookup redirect from BPF */
- if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
- result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
- saddr, sport, daddr, hnum, dif);
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+ hashinfo == net->ipv4.tcp_death_row.hashinfo) {
+ result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+ saddr, sport, daddr, hnum, dif,
+ inet6_ehashfn);
if (result)
goto done;
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bac768d36cc1..28b01a068412 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
INIT_LIST_HEAD(&f6i->fib6_siblings);
refcount_set(&f6i->fib6_ref, 1);
+ INIT_HLIST_NODE(&f6i->gc_link);
+
return f6i;
}
@@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
net->ipv6.fib6_null_entry);
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&table->tb6_peers);
+ INIT_HLIST_HEAD(&table->tb6_gc_hlist);
}
return table;
@@ -1057,6 +1060,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
lockdep_is_held(&table->tb6_lock));
}
}
+
+ fib6_clean_expires_locked(rt);
}
/*
@@ -1118,9 +1123,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
if (!(iter->fib6_flags & RTF_EXPIRES))
return -EEXIST;
if (!(rt->fib6_flags & RTF_EXPIRES))
- fib6_clean_expires(iter);
+ fib6_clean_expires_locked(iter);
else
- fib6_set_expires(iter, rt->expires);
+ fib6_set_expires_locked(iter,
+ rt->expires);
if (rt->fib6_pmtu)
fib6_metric_set(iter, RTAX_MTU,
@@ -1479,6 +1485,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
if (rt->nh)
list_add(&rt->nh_list, &rt->nh->f6i_list);
__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
+
+ if (fib6_has_expires(rt))
+ hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist);
+
fib6_start_gc(info->nl_net, rt);
}
@@ -2285,9 +2295,8 @@ static void fib6_flush_trees(struct net *net)
* Garbage collection
*/
-static int fib6_age(struct fib6_info *rt, void *arg)
+static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
{
- struct fib6_gc_args *gc_args = arg;
unsigned long now = jiffies;
/*
@@ -2295,7 +2304,7 @@ static int fib6_age(struct fib6_info *rt, void *arg)
* Routes are expired even if they are in use.
*/
- if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
+ if (fib6_has_expires(rt) && rt->expires) {
if (time_after(now, rt->expires)) {
RT6_TRACE("expiring %p\n", rt);
return -1;
@@ -2312,6 +2321,40 @@ static int fib6_age(struct fib6_info *rt, void *arg)
return 0;
}
+static void fib6_gc_table(struct net *net,
+ struct fib6_table *tb6,
+ struct fib6_gc_args *gc_args)
+{
+ struct fib6_info *rt;
+ struct hlist_node *n;
+ struct nl_info info = {
+ .nl_net = net,
+ .skip_notify = false,
+ };
+
+ hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
+ if (fib6_age(rt, gc_args) == -1)
+ fib6_del(rt, &info);
+}
+
+static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
+{
+ struct fib6_table *table;
+ struct hlist_head *head;
+ unsigned int h;
+
+ rcu_read_lock();
+ for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+ spin_lock_bh(&table->tb6_lock);
+ fib6_gc_table(net, table, gc_args);
+ spin_unlock_bh(&table->tb6_lock);
+ }
+ }
+ rcu_read_unlock();
+}
+
void fib6_run_gc(unsigned long expires, struct net *net, bool force)
{
struct fib6_gc_args gc_args;
@@ -2327,7 +2370,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
net->ipv6.sysctl.ip6_rt_gc_interval;
gc_args.more = 0;
- fib6_clean_all(net, fib6_age, &gc_args);
+ fib6_gc_all(net, &gc_args);
now = jiffies;
net->ipv6.ip6_rt_last_gc = now;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index da80974ad23a..070d87abf7c0 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -955,7 +955,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
goto tx_err;
if (skb->len > dev->mtu + dev->hard_header_len) {
- pskb_trim(skb, dev->mtu + dev->hard_header_len);
+ if (pskb_trim(skb, dev->mtu + dev->hard_header_len))
+ goto tx_err;
truncate = true;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1e8c90e97608..0665e8b09968 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -113,7 +113,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
if (lwtunnel_xmit_redirect(dst->lwtstate)) {
int res = lwtunnel_xmit(skb);
- if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+ if (res != LWTUNNEL_XMIT_CONTINUE)
return res;
}
@@ -1591,7 +1591,7 @@ emsgsize:
}
}
} else if ((flags & MSG_SPLICE_PAGES) && length) {
- if (inet_sk(sk)->hdrincl)
+ if (inet_test_bit(HDRINCL, sk))
return -EPERM;
if (rt->dst.dev->features & NETIF_F_SG &&
getfrag == ip_generic_getfrag)
@@ -1693,7 +1693,10 @@ alloc_new_skb:
fraglen = datalen + fragheaderlen;
copy = datalen - transhdrlen - fraggap - pagedlen;
- if (copy < 0) {
+ /* [!] NOTE: copy may be negative if pagedlen>0
+ * because then the equation may reduces to -fraggap.
+ */
+ if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) {
err = -EINVAL;
goto error;
}
@@ -1744,6 +1747,8 @@ alloc_new_skb:
err = -EFAULT;
kfree_skb(skb);
goto error;
+ } else if (flags & MSG_SPLICE_PAGES) {
+ copy = 0;
}
offset += copy;
@@ -1791,6 +1796,10 @@ alloc_new_skb:
} else if (flags & MSG_SPLICE_PAGES) {
struct msghdr *msg = from;
+ err = -EIO;
+ if (WARN_ON_ONCE(copy > msg->msg_iter.count))
+ goto error;
+
err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
sk->sk_allocation);
if (err < 0)
@@ -1986,7 +1995,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
u8 icmp6_type;
- if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl)
+ if (sk->sk_socket->type == SOCK_RAW &&
+ !inet_test_bit(HDRINCL, sk))
icmp6_type = fl6->fl6_icmp_type;
else
icmp6_type = icmp6_hdr(skb)->icmp6_type;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 10b222865d46..73c85d4e0e9c 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -568,12 +568,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
vti6_addr_conflict(t, ipv6_hdr(skb)))
goto tx_err;
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
break;
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
break;
default:
goto tx_err;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index cc3d5ad17257..67a3b8f6e72b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1073,7 +1073,7 @@ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt,
And all this only to mangle msg->im6_msgtype and
to set msg->im6_mbz to "mbz" :-)
*/
- skb_push(skb, -skb_network_offset(pkt));
+ __skb_pull(skb, skb_network_offset(pkt));
skb_push(skb, sizeof(*msg));
skb_reset_transport_header(skb);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index ae818ff46224..0e2a0847b387 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -102,7 +102,7 @@ int ip6_ra_control(struct sock *sk, int sel)
struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
struct ipv6_txoptions *opt)
{
- if (inet_sk(sk)->is_icsk) {
+ if (inet_test_bit(IS_ICSK, sk)) {
if (opt &&
!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) {
@@ -474,8 +474,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
WRITE_ONCE(sk->sk_prot, &tcp_prot);
/* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific);
- sk->sk_socket->ops = &inet_stream_ops;
- sk->sk_family = PF_INET;
+ WRITE_ONCE(sk->sk_socket->ops, &inet_stream_ops);
+ WRITE_ONCE(sk->sk_family, PF_INET);
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
} else {
struct proto *prot = &udp_prot;
@@ -488,8 +488,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
/* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */
WRITE_ONCE(sk->sk_prot, prot);
- sk->sk_socket->ops = &inet_dgram_ops;
- sk->sk_family = PF_INET;
+ WRITE_ONCE(sk->sk_socket->ops, &inet_dgram_ops);
+ WRITE_ONCE(sk->sk_family, PF_INET);
}
/* Disable all options not to allocate memory anymore,
@@ -633,7 +633,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
if (optlen < sizeof(int))
goto e_inval;
/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
- inet_sk(sk)->transparent = valbool;
+ inet_assign_bit(TRANSPARENT, sk, valbool);
retv = 0;
break;
@@ -641,7 +641,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
if (optlen < sizeof(int))
goto e_inval;
/* we also don't have a separate freebind bit for IPV6 */
- inet_sk(sk)->freebind = valbool;
+ inet_assign_bit(FREEBIND, sk, valbool);
retv = 0;
break;
@@ -831,7 +831,7 @@ done:
goto e_inval;
retv = -EPROTO;
- if (inet_sk(sk)->is_icsk)
+ if (inet_test_bit(IS_ICSK, sk))
break;
retv = -EFAULT;
@@ -923,7 +923,7 @@ done:
goto e_inval;
np->recverr = valbool;
if (!val)
- skb_queue_purge(&sk->sk_error_queue);
+ skb_errqueue_purge(&sk->sk_error_queue);
retv = 0;
break;
case IPV6_FLOWINFO_SEND:
@@ -1330,11 +1330,11 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
}
case IPV6_TRANSPARENT:
- val = inet_sk(sk)->transparent;
+ val = inet_test_bit(TRANSPARENT, sk);
break;
case IPV6_FREEBIND:
- val = inet_sk(sk)->freebind;
+ val = inet_test_bit(FREEBIND, sk);
break;
case IPV6_RECVORIGDSTADDR:
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 714cdc9e2b8e..5ce25bcb9974 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1699,11 +1699,9 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted)
return scount;
}
-static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb,
- struct net_device *dev,
- const struct in6_addr *saddr,
- const struct in6_addr *daddr,
- int proto, int len)
+static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb,
+ struct net_device *dev, const struct in6_addr *saddr,
+ const struct in6_addr *daddr, int proto, int len)
{
struct ipv6hdr *hdr;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 18634ebd20a4..553c8664e0a7 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
static inline int ndisc_is_useropt(const struct net_device *dev,
struct nd_opt_hdr *opt)
{
- return opt->nd_opt_type == ND_OPT_RDNSS ||
+ return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
+ opt->nd_opt_type == ND_OPT_RDNSS ||
opt->nd_opt_type == ND_OPT_DNSSL ||
opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
opt->nd_opt_type == ND_OPT_PREF64 ||
@@ -1266,10 +1267,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
}
#endif
- /*
- * set the RA_RECV flag in the interface
- */
-
in6_dev = __in6_dev_get(skb->dev);
if (!in6_dev) {
ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n",
@@ -1327,6 +1324,14 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
goto skip_defrtr;
}
+ lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
+ if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_lft) {
+ ND_PRINTK(2, info,
+ "RA: router lifetime (%ds) is too short: %s\n",
+ lifetime, skb->dev->name);
+ goto skip_defrtr;
+ }
+
/* Do not accept RA with source-addr found on local machine unless
* accept_ra_from_local is set to true.
*/
@@ -1339,8 +1344,6 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
goto skip_defrtr;
}
- lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
-
#ifdef CONFIG_IPV6_ROUTER_PREF
pref = ra_msg->icmph.icmp6_router_pref;
/* 10b is handled as if it were 00b (medium) */
@@ -1516,6 +1519,9 @@ skip_linkparms:
if (ri->prefix_len == 0 &&
!in6_dev->cnf.accept_ra_defrtr)
continue;
+ if (ri->lifetime != 0 &&
+ ntohl(ri->lifetime) < in6_dev->cnf.accept_ra_min_lft)
+ continue;
if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
continue;
if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index cb4eb1d2c620..d59b296b4f51 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/icmp.h>
+#include <linux/rcupdate.h>
#include <linux/sysctl.h>
#include <net/ipv6_frag.h>
@@ -96,6 +97,12 @@ static void __net_exit defrag6_net_exit(struct net *net)
}
}
+static const struct nf_defrag_hook defrag_hook = {
+ .owner = THIS_MODULE,
+ .enable = nf_defrag_ipv6_enable,
+ .disable = nf_defrag_ipv6_disable,
+};
+
static struct pernet_operations defrag6_net_ops = {
.exit = defrag6_net_exit,
};
@@ -114,6 +121,9 @@ static int __init nf_defrag_init(void)
pr_err("nf_defrag_ipv6: can't register pernet ops\n");
goto cleanup_frag6;
}
+
+ rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook);
+
return ret;
cleanup_frag6:
@@ -124,6 +134,7 @@ cleanup_frag6:
static void __exit nf_defrag_fini(void)
{
+ rcu_assign_pointer(nf_defrag_v6_hook, NULL);
unregister_pernet_subsys(&defrag6_net_ops);
nf_ct_frag6_cleanup();
}
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index f804c11e2146..1b2772834972 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipcm6_init_sk(&ipc6, np);
ipc6.sockc.tsflags = sk->sk_tsflags;
- ipc6.sockc.mark = sk->sk_mark;
+ ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
fl6.flowi6_oif = oif;
@@ -215,6 +215,7 @@ struct proto pingv6_prot = {
.get_port = ping_get_port,
.put_port = ping_unhash,
.obj_size = sizeof(struct raw6_sock),
+ .ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6),
};
EXPORT_SYMBOL_GPL(pingv6_prot);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ac1cef094c5f..0eae7661a85c 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -291,7 +291,6 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
- struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
int err;
int harderr;
@@ -315,7 +314,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
}
if (np->recverr) {
u8 *payload = skb->data;
- if (!inet->hdrincl)
+ if (!inet_test_bit(HDRINCL, sk))
payload += offset;
ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload);
}
@@ -406,7 +405,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
skb->len,
inet->inet_num, 0));
- if (inet->hdrincl) {
+ if (inet_test_bit(HDRINCL, sk)) {
if (skb_checksum_complete(skb)) {
atomic_inc(&sk->sk_drops);
kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM);
@@ -614,7 +613,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
skb_reserve(skb, hlen);
skb->protocol = htons(ETH_P_IPV6);
- skb->priority = sk->sk_priority;
+ skb->priority = READ_ONCE(sk->sk_priority);
skb->mark = sockc->mark;
skb->tstamp = sockc->transmit_time;
@@ -762,24 +761,19 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
- /* hdrincl should be READ_ONCE(inet->hdrincl)
- * but READ_ONCE() doesn't work with bit fields.
- * Doing this indirectly yields the same result.
- */
- hdrincl = inet->hdrincl;
- hdrincl = READ_ONCE(hdrincl);
+ hdrincl = inet_test_bit(HDRINCL, sk);
/*
* Get and verify the address.
*/
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
fl6.flowi6_uid = sk->sk_uid;
ipcm6_init(&ipc6);
ipc6.sockc.tsflags = sk->sk_tsflags;
- ipc6.sockc.mark = sk->sk_mark;
+ ipc6.sockc.mark = fl6.flowi6_mark;
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
@@ -1000,7 +994,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
case IPV6_HDRINCL:
if (sk->sk_type != SOCK_RAW)
return -EINVAL;
- inet_sk(sk)->hdrincl = !!val;
+ inet_assign_bit(HDRINCL, sk, val);
return 0;
case IPV6_CHECKSUM:
if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 &&
@@ -1068,7 +1062,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
switch (optname) {
case IPV6_HDRINCL:
- val = inet_sk(sk)->hdrincl;
+ val = inet_test_bit(HDRINCL, sk);
break;
case IPV6_CHECKSUM:
/*
@@ -1216,6 +1210,7 @@ struct proto rawv6_prot = {
.hash = raw_hash_sk,
.unhash = raw_unhash_sk,
.obj_size = sizeof(struct raw6_sock),
+ .ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6),
.useroffset = offsetof(struct raw6_sock, filter),
.usersize = sizeof_field(struct raw6_sock, filter),
.h.raw_hash = &raw_v6_hashinfo,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 15cade57f7c6..d15a9e3aa24a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -90,7 +90,7 @@ unsigned int ip6_mtu(const struct dst_entry *dst);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
- struct net_device *dev, int how);
+ struct net_device *dev);
static void ip6_dst_gc(struct dst_ops *ops);
static int ip6_pkt_discard(struct sk_buff *skb);
@@ -371,8 +371,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
fib6_info_release(from);
}
-static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
- int how)
+static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
@@ -2951,7 +2950,8 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
if (!oif && skb->dev)
oif = l3mdev_master_ifindex(skb->dev);
- ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
+ ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark),
+ sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -3172,8 +3172,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif)
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
{
- ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark,
- sk->sk_uid);
+ ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if,
+ READ_ONCE(sk->sk_mark), sk->sk_uid);
}
EXPORT_SYMBOL_GPL(ip6_sk_redirect);
@@ -3760,10 +3760,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
rt->dst_nocount = true;
if (cfg->fc_flags & RTF_EXPIRES)
- fib6_set_expires(rt, jiffies +
- clock_t_to_jiffies(cfg->fc_expires));
+ fib6_set_expires_locked(rt, jiffies +
+ clock_t_to_jiffies(cfg->fc_expires));
else
- fib6_clean_expires(rt);
+ fib6_clean_expires_locked(rt);
if (cfg->fc_protocol == RTPROT_UNSPEC)
cfg->fc_protocol = RTPROT_BOOT;
@@ -4543,7 +4543,8 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff
struct fib6_info *addrconf_f6i_alloc(struct net *net,
struct inet6_dev *idev,
const struct in6_addr *addr,
- bool anycast, gfp_t gfp_flags)
+ bool anycast, gfp_t gfp_flags,
+ struct netlink_ext_ack *extack)
{
struct fib6_config cfg = {
.fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL,
@@ -4565,7 +4566,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
cfg.fc_flags |= RTF_LOCAL;
}
- f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
+ f6i = ip6_route_info_create(&cfg, gfp_flags, extack);
if (!IS_ERR(f6i)) {
f6i->dst_nocount = true;
@@ -4580,21 +4581,19 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
/* remove deleted ip from prefsrc entries */
struct arg_dev_net_ip {
- struct net_device *dev;
struct net *net;
struct in6_addr *addr;
};
static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
{
- struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
struct net *net = ((struct arg_dev_net_ip *)arg)->net;
struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
if (!rt->nh &&
- ((void *)rt->fib6_nh->fib_nh_dev == dev || !dev) &&
rt != net->ipv6.fib6_null_entry &&
- ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) {
+ ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr) &&
+ !ipv6_chk_addr(net, addr, rt->fib6_nh->fib_nh_dev, 0)) {
spin_lock_bh(&rt6_exception_lock);
/* remove prefsrc entry */
rt->fib6_prefsrc.plen = 0;
@@ -4607,7 +4606,6 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
{
struct net *net = dev_net(ifp->idev->dev);
struct arg_dev_net_ip adni = {
- .dev = ifp->idev->dev,
.net = net,
.addr = &ifp->addr,
};
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index b1c028df686e..a013b92cbb86 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -272,8 +272,6 @@ static int rpl_input(struct sk_buff *skb)
dst = dst_cache_get(&rlwt->cache);
preempt_enable();
- skb_dst_drop(skb);
-
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
@@ -284,6 +282,7 @@ static int rpl_input(struct sk_buff *skb)
preempt_enable();
}
} else {
+ skb_dst_drop(skb);
skb_dst_set(skb, dst);
}
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index dd433cc265c8..24e2b4b494cb 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -109,15 +109,19 @@ struct bpf_lwt_prog {
#define next_csid_chk_lcnode_fn_bits(flen) \
next_csid_chk_lcblock_bits(flen)
+/* flag indicating that flavors are set up for a given End* behavior */
+#define SEG6_F_LOCAL_FLAVORS SEG6_F_ATTR(SEG6_LOCAL_FLAVORS)
+
#define SEG6_F_LOCAL_FLV_OP(flvname) BIT(SEG6_LOCAL_FLV_OP_##flvname)
+#define SEG6_F_LOCAL_FLV_NEXT_CSID SEG6_F_LOCAL_FLV_OP(NEXT_CSID)
#define SEG6_F_LOCAL_FLV_PSP SEG6_F_LOCAL_FLV_OP(PSP)
/* Supported RFC8986 Flavor operations are reported in this bitmask */
#define SEG6_LOCAL_FLV8986_SUPP_OPS SEG6_F_LOCAL_FLV_PSP
-/* Supported Flavor operations are reported in this bitmask */
-#define SEG6_LOCAL_FLV_SUPP_OPS (SEG6_F_LOCAL_FLV_OP(NEXT_CSID) | \
+#define SEG6_LOCAL_END_FLV_SUPP_OPS (SEG6_F_LOCAL_FLV_NEXT_CSID | \
SEG6_LOCAL_FLV8986_SUPP_OPS)
+#define SEG6_LOCAL_END_X_FLV_SUPP_OPS SEG6_F_LOCAL_FLV_NEXT_CSID
struct seg6_flavors_info {
/* Flavor operations */
@@ -411,9 +415,72 @@ static int end_next_csid_core(struct sk_buff *skb, struct seg6_local_lwt *slwt)
return input_action_end_finish(skb, slwt);
}
+static int input_action_end_x_finish(struct sk_buff *skb,
+ struct seg6_local_lwt *slwt)
+{
+ seg6_lookup_nexthop(skb, &slwt->nh6, 0);
+
+ return dst_input(skb);
+}
+
+static int input_action_end_x_core(struct sk_buff *skb,
+ struct seg6_local_lwt *slwt)
+{
+ struct ipv6_sr_hdr *srh;
+
+ srh = get_and_validate_srh(skb);
+ if (!srh)
+ goto drop;
+
+ advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
+
+ return input_action_end_x_finish(skb, slwt);
+
+drop:
+ kfree_skb(skb);
+ return -EINVAL;
+}
+
+static int end_x_next_csid_core(struct sk_buff *skb,
+ struct seg6_local_lwt *slwt)
+{
+ const struct seg6_flavors_info *finfo = &slwt->flv_info;
+ struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
+
+ if (seg6_next_csid_is_arg_zero(daddr, finfo))
+ return input_action_end_x_core(skb, slwt);
+
+ /* update DA */
+ seg6_next_csid_advance_arg(daddr, finfo);
+
+ return input_action_end_x_finish(skb, slwt);
+}
+
static bool seg6_next_csid_enabled(__u32 fops)
{
- return fops & BIT(SEG6_LOCAL_FLV_OP_NEXT_CSID);
+ return fops & SEG6_F_LOCAL_FLV_NEXT_CSID;
+}
+
+/* Processing of SRv6 End, End.X, and End.T behaviors can be extended through
+ * the flavors framework. These behaviors must report the subset of (flavor)
+ * operations they currently implement. In this way, if a user specifies a
+ * flavor combination that is not supported by a given End* behavior, the
+ * kernel refuses to instantiate the tunnel reporting the error.
+ */
+static int seg6_flv_supp_ops_by_action(int action, __u32 *fops)
+{
+ switch (action) {
+ case SEG6_LOCAL_ACTION_END:
+ *fops = SEG6_LOCAL_END_FLV_SUPP_OPS;
+ break;
+ case SEG6_LOCAL_ACTION_END_X:
+ *fops = SEG6_LOCAL_END_X_FLV_SUPP_OPS;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
}
/* We describe the packet state in relation to the absence/presence of the SRH
@@ -746,21 +813,14 @@ static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt)
/* regular endpoint, and forward to specified nexthop */
static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
- struct ipv6_sr_hdr *srh;
-
- srh = get_and_validate_srh(skb);
- if (!srh)
- goto drop;
-
- advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
-
- seg6_lookup_nexthop(skb, &slwt->nh6, 0);
+ const struct seg6_flavors_info *finfo = &slwt->flv_info;
+ __u32 fops = finfo->flv_ops;
- return dst_input(skb);
+ /* check for the presence of NEXT-C-SID since it applies first */
+ if (seg6_next_csid_enabled(fops))
+ return end_x_next_csid_core(skb, slwt);
-drop:
- kfree_skb(skb);
- return -EINVAL;
+ return input_action_end_x_core(skb, slwt);
}
static int input_action_end_t(struct sk_buff *skb, struct seg6_local_lwt *slwt)
@@ -1404,13 +1464,14 @@ static struct seg6_action_desc seg6_action_table[] = {
.action = SEG6_LOCAL_ACTION_END,
.attrs = 0,
.optattrs = SEG6_F_LOCAL_COUNTERS |
- SEG6_F_ATTR(SEG6_LOCAL_FLAVORS),
+ SEG6_F_LOCAL_FLAVORS,
.input = input_action_end,
},
{
.action = SEG6_LOCAL_ACTION_END_X,
.attrs = SEG6_F_ATTR(SEG6_LOCAL_NH6),
- .optattrs = SEG6_F_LOCAL_COUNTERS,
+ .optattrs = SEG6_F_LOCAL_COUNTERS |
+ SEG6_F_LOCAL_FLAVORS,
.input = input_action_end_x,
},
{
@@ -2070,7 +2131,8 @@ static int parse_nla_flavors(struct nlattr **attrs, struct seg6_local_lwt *slwt,
{
struct seg6_flavors_info *finfo = &slwt->flv_info;
struct nlattr *tb[SEG6_LOCAL_FLV_MAX + 1];
- unsigned long fops;
+ int action = slwt->action;
+ __u32 fops, supp_fops;
int rc;
rc = nla_parse_nested_deprecated(tb, SEG6_LOCAL_FLV_MAX,
@@ -2086,7 +2148,8 @@ static int parse_nla_flavors(struct nlattr **attrs, struct seg6_local_lwt *slwt,
return -EINVAL;
fops = nla_get_u32(tb[SEG6_LOCAL_FLV_OPERATION]);
- if (fops & ~SEG6_LOCAL_FLV_SUPP_OPS) {
+ rc = seg6_flv_supp_ops_by_action(action, &supp_fops);
+ if (rc < 0 || (fops & ~supp_fops)) {
NL_SET_ERR_MSG(extack, "Unsupported Flavor operation(s)");
return -EOPNOTSUPP;
}
@@ -2618,6 +2681,11 @@ int __init seg6_local_init(void)
*/
BUILD_BUG_ON(SEG6_LOCAL_MAX + 1 > BITS_PER_TYPE(unsigned long));
+ /* Check whether the number of defined flavors exceeds the maximum
+ * allowed value.
+ */
+ BUILD_BUG_ON(SEG6_LOCAL_FLV_OP_MAX + 1 > BITS_PER_TYPE(__u32));
+
/* If the default NEXT-C-SID Locator-Block/Node Function lengths (in
* bits) have been changed with invalid values, kernel build stops
* here.
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 40dd92a2f480..3a88545a265d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -564,8 +564,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
- tclass, sk->sk_priority);
+ err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark),
+ opt, tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -939,7 +939,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
if (sk->sk_state == TCP_TIME_WAIT)
mark = inet_twsk(sk)->tw_mark;
else
- mark = sk->sk_mark;
+ mark = READ_ONCE(sk->sk_mark);
skb_set_delivery_time(buff, tcp_transmit_time(sk), true);
}
if (txhash) {
@@ -1126,10 +1126,11 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
- req->ts_recent, sk->sk_bound_dev_if,
+ READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
- ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority,
- tcp_rsk(req)->txhash);
+ ipv6_get_dsfield(ipv6_hdr(skb)), 0,
+ READ_ONCE(sk->sk_priority),
+ READ_ONCE(tcp_rsk(req)->txhash));
}
@@ -2175,6 +2176,7 @@ struct proto tcpv6_prot = {
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp6_sock),
+ .ipv6_pinfo_offset = offsetof(struct tcp6_sock, inet6),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.twsk_prot = &tcp6_timewait_sock_ops,
.rsk_prot = &tcp6_request_sock_ops,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 317b01c9bc39..ebc6ae47cfea 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -45,11 +45,13 @@
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/ip6_tunnel.h>
+#include <trace/events/udp.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
#include <net/busy_poll.h>
#include <net/sock_reuseport.h>
+#include <net/gro.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
@@ -70,11 +72,12 @@ int udpv6_init_sock(struct sock *sk)
return 0;
}
-static u32 udp6_ehashfn(const struct net *net,
- const struct in6_addr *laddr,
- const u16 lport,
- const struct in6_addr *faddr,
- const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp6_ehashfn(const struct net *net,
+ const struct in6_addr *laddr,
+ const u16 lport,
+ const struct in6_addr *faddr,
+ const __be16 fport)
{
static u32 udp6_ehash_secret __read_mostly;
static u32 udp_ipv6_hash_secret __read_mostly;
@@ -90,7 +93,7 @@ static u32 udp6_ehashfn(const struct net *net,
fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);
return __inet6_ehashfn(lhash, lport, fhash, fport,
- udp_ipv6_hash_secret + net_hash_mix(net));
+ udp6_ehash_secret + net_hash_mix(net));
}
int udp_v6_get_port(struct sock *sk, unsigned short snum)
@@ -159,24 +162,6 @@ static int compute_score(struct sock *sk, struct net *net,
return score;
}
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb,
- const struct in6_addr *saddr,
- __be16 sport,
- const struct in6_addr *daddr,
- unsigned int hnum)
-{
- struct sock *reuse_sk = NULL;
- u32 hash;
-
- if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
- hash = udp6_ehashfn(net, daddr, hnum, saddr, sport);
- reuse_sk = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- }
- return reuse_sk;
-}
-
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -193,44 +178,35 @@ static struct sock *udp6_lib_lookup2(struct net *net,
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
- result = lookup_reuseport(net, sk, skb,
- saddr, sport, daddr, hnum);
+ badness = score;
+
+ if (sk->sk_state == TCP_ESTABLISHED) {
+ result = sk;
+ continue;
+ }
+
+ result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, udp6_ehashfn);
+ if (!result) {
+ result = sk;
+ continue;
+ }
+
/* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk))
+ if (!reuseport_has_conns(sk))
return result;
- result = result ? : sk;
- badness = score;
+ /* Reuseport logic returned an error, keep original score. */
+ if (IS_ERR(result))
+ continue;
+
+ badness = compute_score(sk, net, saddr, sport,
+ daddr, hnum, dif, sdif);
}
}
return result;
}
-static inline struct sock *udp6_lookup_run_bpf(struct net *net,
- struct udp_table *udptable,
- struct sk_buff *skb,
- const struct in6_addr *saddr,
- __be16 sport,
- const struct in6_addr *daddr,
- u16 hnum, const int dif)
-{
- struct sock *sk, *reuse_sk;
- bool no_reuseport;
-
- if (udptable != net->ipv4.udp_table)
- return NULL; /* only UDP is supported */
-
- no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport,
- daddr, hnum, dif, &sk);
- if (no_reuseport || IS_ERR_OR_NULL(sk))
- return sk;
-
- reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
- if (reuse_sk)
- sk = reuse_sk;
- return sk;
-}
-
/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -255,9 +231,11 @@ struct sock *__udp6_lib_lookup(struct net *net,
goto done;
/* Lookup redirect from BPF */
- if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
- sk = udp6_lookup_run_bpf(net, udptable, skb,
- saddr, sport, daddr, hnum, dif);
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
+ udptable == net->ipv4.udp_table) {
+ sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, dif,
+ udp6_ehashfn);
if (sk) {
result = sk;
goto done;
@@ -299,10 +277,13 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
+ int iif, sdif;
+
+ inet6_get_iif_sdif(skb, &iif, &sdif);
return __udp6_lib_lookup(net, &iph->saddr, sport,
- &iph->daddr, dport, inet6_iif(skb),
- inet6_sdif(skb), net->ipv4.udp_table, NULL);
+ &iph->daddr, dport, iif,
+ sdif, net->ipv4.udp_table, NULL);
}
/* Must be called under rcu_read_lock().
@@ -439,7 +420,7 @@ try_again:
ip6_datagram_recv_common_ctl(sk, msg, skb);
if (is_udp4) {
- if (inet->cmsg_flags)
+ if (inet_cmsg_flags(inet))
ip_cmsg_recv_offset(msg, sk, skb,
sizeof(struct udphdr), off);
} else {
@@ -623,7 +604,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (type == NDISC_REDIRECT) {
if (tunnel) {
ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
- sk->sk_mark, sk->sk_uid);
+ READ_ONCE(sk->sk_mark), sk->sk_uid);
} else {
ip6_sk_redirect(skb, sk);
}
@@ -680,6 +661,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb_reason(skb, drop_reason);
+ trace_udp_fail_queue_rcv_skb(rc, sk);
return -1;
}
@@ -986,7 +968,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
goto csum_error;
/* Check if the socket is already available, e.g. due to early demux */
- sk = skb_steal_sock(skb, &refcounted);
+ sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+ &refcounted, udp6_ehashfn);
+ if (IS_ERR(sk))
+ goto no_sk;
+
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
@@ -1020,7 +1006,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
goto report_csum_error;
return udp6_unicast_rcv_skb(sk, skb, uh);
}
-
+no_sk:
reason = SKB_DROP_REASON_NO_SOCKET;
if (!uh->check)
@@ -1354,7 +1340,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipcm6_init(&ipc6);
ipc6.gso_size = READ_ONCE(up->gso_size);
ipc6.sockc.tsflags = sk->sk_tsflags;
- ipc6.sockc.mark = sk->sk_mark;
+ ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
/* destination address check */
if (sin6) {
@@ -1796,6 +1782,7 @@ struct proto udpv6_prot = {
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
.obj_size = sizeof(struct udp6_sock),
+ .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6),
.h.udp_table = NULL,
.diag_destroy = udp_abort,
};
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index ad3b8726873e..6b95ba241ebe 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -43,8 +43,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
- if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
- !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST))
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
return __udp_gso_segment(skb, features, true);
mss = skb_shinfo(skb)->gso_size;
@@ -119,10 +118,13 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
{
const struct ipv6hdr *iph = skb_gro_network_header(skb);
struct net *net = dev_net(skb->dev);
+ int iif, sdif;
+
+ inet6_get_iif_sdif(skb, &iif, &sdif);
return __udp6_lib_lookup(net, &iph->saddr, sport,
- &iph->daddr, dport, inet6_iif(skb),
- inet6_sdif(skb), net->ipv4.udp_table, NULL);
+ &iph->daddr, dport, iif,
+ sdif, net->ipv4.udp_table, NULL);
}
INDIRECT_CALLABLE_SCOPE
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 8e010d07917a..267d491e9707 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -67,6 +67,7 @@ struct proto udplitev6_prot = {
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
.obj_size = sizeof(struct udp6_sock),
+ .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6),
.h.udp_table = &udplite_table,
};
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 8f931e46b460..41a680c76d2e 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -124,14 +124,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
xfrm_dst_destroy(xdst);
}
-static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
- int unregister)
+static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
{
struct xfrm_dst *xdst;
- if (!unregister)
- return;
-
xdst = (struct xfrm_dst *)dst;
if (xdst->u.rt6.rt6i_idev->dev == dev) {
struct inet6_dev *loopback_idev =
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-02-20 18:39:02 +0000