diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-05 20:13:21 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-05 20:13:21 -0700 |
| commit | 47ec5303d73ea344e84f46660fff693c57641386 (patch) | |
| tree | a2252debab749de29620c43285295d60c4741119 /net/ipv6 | |
| parent | 8186749621ed6b8fc42644c399e8c755a2b6f630 (diff) | |
| parent | c1055b76ad00aed0e8b79417080f212d736246b6 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.
2) Support UDP segmentation in code TSO code, from Eric Dumazet.
3) Allow flashing different flash images in cxgb4 driver, from Vishal
Kulkarni.
4) Add drop frames counter and flow status to tc flower offloading,
from Po Liu.
5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.
6) Various new indirect call avoidance, from Eric Dumazet and Brian
Vazquez.
7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
Yonghong Song.
8) Support querying and setting hardware address of a port function via
devlink, use this in mlx5, from Parav Pandit.
9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.
10) Switch qca8k driver over to phylink, from Jonathan McDowell.
11) In bpftool, show list of processes holding BPF FD references to
maps, programs, links, and btf objects. From Andrii Nakryiko.
12) Several conversions over to generic power management, from Vaibhav
Gupta.
13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
Yakunin.
14) Various https url conversions, from Alexander A. Klimov.
15) Timestamping and PHC support for mscc PHY driver, from Antoine
Tenart.
16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.
17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.
18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.
19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
drivers. From Luc Van Oostenryck.
20) XDP support for xen-netfront, from Denis Kirjanov.
21) Support receive buffer autotuning in MPTCP, from Florian Westphal.
22) Support EF100 chip in sfc driver, from Edward Cree.
23) Add XDP support to mvpp2 driver, from Matteo Croce.
24) Support MPTCP in sock_diag, from Paolo Abeni.
25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
infrastructure, from Jakub Kicinski.
26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.
27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.
28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.
29) Refactor a lot of networking socket option handling code in order to
avoid set_fs() calls, from Christoph Hellwig.
30) Add rfc4884 support to icmp code, from Willem de Bruijn.
31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.
32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.
33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.
34) Support TCP syncookies in MPTCP, from Flowian Westphal.
35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
Brivio.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
net: thunderx: initialize VF's mailbox mutex before first usage
usb: hso: remove bogus check for EINPROGRESS
usb: hso: no complaint about kmalloc failure
hso: fix bailout in error case of probe
ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
selftests/net: relax cpu affinity requirement in msg_zerocopy test
mptcp: be careful on subflow creation
selftests: rtnetlink: make kci_test_encap() return sub-test result
selftests: rtnetlink: correct the final return value for the test
net: dsa: sja1105: use detected device id instead of DT one on mismatch
tipc: set ub->ifindex for local ipv6 address
ipv6: add ipv6_dev_find()
net: openvswitch: silence suspicious RCU usage warning
Revert "vxlan: fix tos value before xmit"
ptp: only allow phase values lower than 1 period
farsync: switch from 'pci_' to 'dma_' API
wan: wanxl: switch from 'pci_' to 'dma_' API
hv_netvsc: do not use VF device if link is down
dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
net: macb: Properly handle phylink on at91sam9x
...
Diffstat (limited to 'net/ipv6')
35 files changed, 961 insertions, 830 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index f4f19e89af5e..76bff79d6fed 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -14,7 +14,7 @@ menuconfig IPV6 <https://en.wikipedia.org/wiki/IPv6>. For specific information about IPv6 under Linux, see Documentation/networking/ipv6.rst and read the HOWTO at - <http://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/> + <https://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/> To compile this protocol support as a module, choose M here: the module will be called ipv6. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 840bfdb3d7bd..8e761b8c47c6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -163,7 +163,7 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); static void addrconf_type_change(struct net_device *dev, unsigned long event); -static int addrconf_ifdown(struct net_device *dev, int how); +static int addrconf_ifdown(struct net_device *dev, bool unregister); static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, @@ -1983,6 +1983,45 @@ int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) } EXPORT_SYMBOL(ipv6_chk_prefix); +/** + * ipv6_dev_find - find the first device with a given source address. + * @net: the net namespace + * @addr: the source address + * + * The caller should be protected by RCU, or RTNL. + */ +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr) +{ + unsigned int hash = inet6_addr_hash(net, addr); + struct inet6_ifaddr *ifp, *result = NULL; + struct net_device *dev = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { + if (net_eq(dev_net(ifp->idev->dev), net) && + ipv6_addr_equal(&ifp->addr, addr)) { + result = ifp; + break; + } + } + + if (!result) { + struct rt6_info *rt; + + rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); + if (rt) { + dev = rt->dst.dev; + ip6_rt_put(rt); + } + } else { + dev = result->idev->dev; + } + rcu_read_unlock(); + + return dev; +} +EXPORT_SYMBOL(ipv6_dev_find); + struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { @@ -3630,7 +3669,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, * an L3 master device (e.g., VRF) */ if (info->upper_dev && netif_is_l3_master(info->upper_dev)) - addrconf_ifdown(dev, 0); + addrconf_ifdown(dev, false); } return NOTIFY_OK; @@ -3663,9 +3702,9 @@ static bool addr_is_local(const struct in6_addr *addr) (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } -static int addrconf_ifdown(struct net_device *dev, int how) +static int addrconf_ifdown(struct net_device *dev, bool unregister) { - unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN; + unsigned long event = unregister ? NETDEV_UNREGISTER : NETDEV_DOWN; struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; @@ -3684,7 +3723,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) * Step 1: remove reference to ipv6 device from parent device. * Do not dev_put! */ - if (how) { + if (unregister) { idev->dead = 1; /* protected by rtnl_lock */ @@ -3698,7 +3737,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - if (!how && !idev->cnf.disable_ipv6) { + if (!unregister && !idev->cnf.disable_ipv6) { /* aggregate the system setting and interface setting */ int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; @@ -3736,7 +3775,7 @@ restart: addrconf_del_rs_timer(idev); /* Step 2: clear flags for stateless addrconf */ - if (!how) + if (!unregister) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); /* Step 3: clear tempaddr list */ @@ -3806,7 +3845,7 @@ restart: write_unlock_bh(&idev->lock); /* Step 5: Discard anycast and multicast list */ - if (how) { + if (unregister) { ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); } else { @@ -3816,7 +3855,7 @@ restart: idev->tstamp = jiffies; /* Last: Shot the device (if unregistered) */ - if (how) { + if (unregister) { addrconf_sysctl_unregister(idev); neigh_parms_release(&nd_tbl, idev->nd_parms); neigh_ifdown(&nd_tbl, dev); @@ -4038,7 +4077,7 @@ static void addrconf_dad_work(struct work_struct *w) in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 1); if (disable_ipv6) - addrconf_ifdown(idev->dev, 0); + addrconf_ifdown(idev->dev, false); goto out; } @@ -7187,9 +7226,9 @@ void addrconf_cleanup(void) for_each_netdev(&init_net, dev) { if (__in6_dev_get(dev) == NULL) continue; - addrconf_ifdown(dev, 1); + addrconf_ifdown(dev, true); } - addrconf_ifdown(init_net.loopback_dev, 2); + addrconf_ifdown(init_net.loopback_dev, true); /* * Check hash table. diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b304b882e031..0306509ab063 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -688,8 +688,6 @@ const struct proto_ops inet6_stream_ops = { .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, #endif .set_rcvlowat = tcp_set_rcvlowat, }; @@ -717,8 +715,6 @@ const struct proto_ops inet6_dgram_ops = { .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, #endif }; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 390bedde21a5..cc8ad7ddecda 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -19,6 +19,7 @@ #include <linux/route.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/icmp.h> #include <net/ipv6.h> #include <net/ndisc.h> @@ -284,6 +285,17 @@ int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr, } EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only); +static void ipv6_icmp_error_rfc4884(const struct sk_buff *skb, + struct sock_ee_data_rfc4884 *out) +{ + switch (icmp6_hdr(skb)->icmp6_type) { + case ICMPV6_TIME_EXCEED: + case ICMPV6_DEST_UNREACH: + ip_icmp_error_rfc4884(skb, out, sizeof(struct icmp6hdr), + icmp6_hdr(skb)->icmp6_datagram_len * 8); + } +} + void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { @@ -313,6 +325,10 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, serr->port = port; __skb_pull(skb, payload - skb->data); + + if (inet6_sk(sk)->recverr_rfc4884) + ipv6_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); + skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 5a8bbcdcaf2b..374105e4394f 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -580,7 +580,7 @@ looped_back: hdr->segments_left--; i = n - hdr->segments_left; - buf = kzalloc(ipv6_rpl_srh_alloc_size(n + 1) * 2, GFP_ATOMIC); + buf = kcalloc(struct_size(hdr, segments.addr, n + 2), 2, GFP_ATOMIC); if (unlikely(!buf)) { kfree_skb(skb); return -1; @@ -1232,7 +1232,6 @@ static void ipv6_renew_option(int renewtype, * @opt: original options * @newtype: option type to replace in @opt * @newopt: new option of type @newtype to replace (user-mem) - * @newoptlen: length of @newopt * * Returns a new set of options which is a copy of @opt with the * option type @newtype replaced with @newopt. diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index fafe556d21e0..8f9a83314de7 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -13,6 +13,7 @@ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/export.h> +#include <linux/indirect_call_wrapper.h> #include <net/fib_rules.h> #include <net/ipv6.h> @@ -111,11 +112,13 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, } else { struct rt6_info *rt; - rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, skb, flags); + rt = pol_lookup_func(lookup, + net, net->ipv6.fib6_local_tbl, fl6, skb, flags); if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put_flags(rt, flags); - rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags); + rt = pol_lookup_func(lookup, + net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put_flags(rt, flags); @@ -226,7 +229,8 @@ static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto out; } - rt = lookup(net, table, flp6, arg->lookup_data, flags); + rt = pol_lookup_func(lookup, + net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { err = fib6_rule_saddr(net, rule, flags, flp6, ip6_dst_idev(&rt->dst)->dev); @@ -252,8 +256,9 @@ out: return err; } -static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, - int flags, struct fib_lookup_arg *arg) +INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule, + struct flowi *flp, int flags, + struct fib_lookup_arg *arg) { if (arg->lookup_ptr == fib6_table_lookup) return fib6_rule_action_alt(rule, flp, flags, arg); @@ -261,7 +266,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, return __fib6_rule_action(rule, flp, flags, arg); } -static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, + struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct rt6_info *rt = res->rt6; @@ -293,7 +299,8 @@ suppress_route: return true; } -static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, + struct flowi *fl, int flags) { struct fib6_rule *r = (struct fib6_rule *) rule; struct flowi6 *fl6 = &fl->u.ip6; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 9df8737ae0d3..a4e4912ad607 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -439,8 +439,8 @@ static int icmp6_iif(const struct sk_buff *skb) /* * Send an ICMP message in response to a packet in error */ -static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) +void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct in6_addr *force_saddr) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -625,6 +625,7 @@ out: out_bh_enable: local_bh_enable(); } +EXPORT_SYMBOL(icmp6_send); /* Slightly more convenient version of icmp6_send. */ diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index fbe9d4295eac..2d3add9e6116 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -21,6 +21,8 @@ #include <net/ip.h> #include <net/sock_reuseport.h> +extern struct inet_hashinfo tcp_hashinfo; + u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) @@ -111,6 +113,23 @@ 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) +{ + struct sock *reuse_sk = NULL; + u32 phash; + + if (sk->sk_reuseport) { + phash = inet6_ehashfn(net, daddr, hnum, saddr, sport); + reuse_sk = reuseport_select_sock(sk, phash, skb, doff); + } + return reuse_sk; +} + /* called with rcu_read_lock() */ static struct sock *inet6_lhash2_lookup(struct net *net, struct inet_listen_hashbucket *ilb2, @@ -123,21 +142,17 @@ static struct sock *inet6_lhash2_lookup(struct net *net, struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; - u32 phash = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; score = compute_score(sk, net, hnum, daddr, dif, sdif, exact_dif); if (score > hiscore) { - if (sk->sk_reuseport) { - phash = inet6_ehashfn(net, daddr, hnum, - saddr, sport); - result = reuseport_select_sock(sk, phash, - skb, doff); - if (result) - return result; - } + result = lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, hnum); + if (result) + return result; + result = sk; hiscore = score; } @@ -146,6 +161,31 @@ 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) +{ + struct sock *sk, *reuse_sk; + bool no_reuseport; + + if (hashinfo != &tcp_hashinfo) + return NULL; /* only TCP is supported */ + + no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, + saddr, sport, daddr, hnum, &sk); + if (no_reuseport || IS_ERR_OR_NULL(sk)) + return sk; + + reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + if (reuse_sk) + sk = reuse_sk; + return sk; +} + struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, @@ -157,6 +197,14 @@ struct sock *inet6_lookup_listener(struct net *net, struct sock *result = NULL; 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); + if (result) + goto done; + } + hash2 = ipv6_portaddr_hash(net, daddr, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 49ee89bbcba0..25a90f3f705c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -314,7 +314,8 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, { struct rt6_info *rt; - rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags); + rt = pol_lookup_func(lookup, + net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put_flags(rt, flags); rt = net->ipv6.ip6_null_entry; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 73bb047e6037..aa673a6a7e43 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -371,7 +371,7 @@ static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned lo static struct ip6_flowlabel * fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, - char __user *optval, int optlen, int *err_p) + sockptr_t optval, int optlen, int *err_p) { struct ip6_flowlabel *fl = NULL; int olen; @@ -401,7 +401,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, memset(fl->opt, 0, sizeof(*fl->opt)); fl->opt->tot_len = sizeof(*fl->opt) + olen; err = -EFAULT; - if (copy_from_user(fl->opt+1, optval+CMSG_ALIGN(sizeof(*freq)), olen)) + if (copy_from_sockptr_offset(fl->opt + 1, optval, + CMSG_ALIGN(sizeof(*freq)), olen)) goto done; msg.msg_controllen = olen; @@ -533,187 +534,212 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, return -ENOENT; } -int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) +#define socklist_dereference(__sflp) \ + rcu_dereference_protected(__sflp, lockdep_is_held(&ip6_sk_fl_lock)) + +static int ipv6_flowlabel_put(struct sock *sk, struct in6_flowlabel_req *freq) { - int err; - struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_flowlabel_req freq; - struct ipv6_fl_socklist *sfl1 = NULL; - struct ipv6_fl_socklist *sfl; struct ipv6_fl_socklist __rcu **sflp; - struct ip6_flowlabel *fl, *fl1 = NULL; + struct ipv6_fl_socklist *sfl; + if (freq->flr_flags & IPV6_FL_F_REFLECT) { + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + if (!np->repflow) + return -ESRCH; + np->flow_label = 0; + np->repflow = 0; + return 0; + } - if (optlen < sizeof(freq)) - return -EINVAL; + spin_lock_bh(&ip6_sk_fl_lock); + for (sflp = &np->ipv6_fl_list; + (sfl = socklist_dereference(*sflp)) != NULL; + sflp = &sfl->next) { + if (sfl->fl->label == freq->flr_label) + goto found; + } + spin_unlock_bh(&ip6_sk_fl_lock); + return -ESRCH; +found: + if (freq->flr_label == (np->flow_label & IPV6_FLOWLABEL_MASK)) + np->flow_label &= ~IPV6_FLOWLABEL_MASK; + *sflp = sfl->next; + spin_unlock_bh(&ip6_sk_fl_lock); + fl_release(sfl->fl); + kfree_rcu(sfl, rcu); + return 0; +} - if (copy_from_user(&freq, optval, sizeof(freq))) - return -EFAULT; +static int ipv6_flowlabel_renew(struct sock *sk, struct in6_flowlabel_req *freq) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct net *net = sock_net(sk); + struct ipv6_fl_socklist *sfl; + int err; - switch (freq.flr_action) { - case IPV6_FL_A_PUT: - if (freq.flr_flags & IPV6_FL_F_REFLECT) { - if (sk->sk_protocol != IPPROTO_TCP) - return -ENOPROTOOPT; - if (!np->repflow) - return -ESRCH; - np->flow_label = 0; - np->repflow = 0; - return 0; - } - spin_lock_bh(&ip6_sk_fl_lock); - for (sflp = &np->ipv6_fl_list; - (sfl = rcu_dereference_protected(*sflp, - lockdep_is_held(&ip6_sk_fl_lock))) != NULL; - sflp = &sfl->next) { - if (sfl->fl->label == freq.flr_label) { - if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) - np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = sfl->next; - spin_unlock_bh(&ip6_sk_fl_lock); - fl_release(sfl->fl); - kfree_rcu(sfl, rcu); - return 0; - } + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { + if (sfl->fl->label == freq->flr_label) { + err = fl6_renew(sfl->fl, freq->flr_linger, + freq->flr_expires); + rcu_read_unlock_bh(); + return err; } - spin_unlock_bh(&ip6_sk_fl_lock); - return -ESRCH; + } + rcu_read_unlock_bh(); - case IPV6_FL_A_RENEW: - rcu_read_lock_bh(); - for_each_sk_fl_rcu(np, sfl) { - if (sfl->fl->label == freq.flr_label) { - err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires); - rcu_read_unlock_bh(); - return err; - } - } - rcu_read_unlock_bh(); + if (freq->flr_share == IPV6_FL_S_NONE && + ns_capable(net->user_ns, CAP_NET_ADMIN)) { + struct ip6_flowlabel *fl = fl_lookup(net, freq->flr_label); - if (freq.flr_share == IPV6_FL_S_NONE && - ns_capable(net->user_ns, CAP_NET_ADMIN)) { - fl = fl_lookup(net, freq.flr_label); - if (fl) { - err = fl6_renew(fl, freq.flr_linger, freq.flr_expires); - fl_release(fl); - return err; - } + if (fl) { + err = fl6_renew(fl, freq->flr_linger, + freq->flr_expires); + fl_release(fl); + return err; } - return -ESRCH; - - case IPV6_FL_A_GET: - if (freq.flr_flags & IPV6_FL_F_REFLECT) { - struct net *net = sock_net(sk); - if (net->ipv6.sysctl.flowlabel_consistency) { - net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n"); - return -EPERM; - } + } + return -ESRCH; +} - if (sk->sk_protocol != IPPROTO_TCP) - return -ENOPROTOOPT; +static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, + sockptr_t optval, int optlen) +{ + struct ipv6_fl_socklist *sfl, *sfl1 = NULL; + struct ip6_flowlabel *fl, *fl1 = NULL; + struct ipv6_pinfo *np = inet6_sk(sk); + struct net *net = sock_net(sk); + int err; - np->repflow = 1; - return 0; + if (freq->flr_flags & IPV6_FL_F_REFLECT) { + if (net->ipv6.sysctl.flowlabel_consistency) { + net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n"); + return -EPERM; } - if (freq.flr_label & ~IPV6_FLOWLABEL_MASK) - return -EINVAL; + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + np->repflow = 1; + return 0; + } - if (net->ipv6.sysctl.flowlabel_state_ranges && - (freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG)) - return -ERANGE; + if (freq->flr_label & ~IPV6_FLOWLABEL_MASK) + return -EINVAL; + if (net->ipv6.sysctl.flowlabel_state_ranges && + (freq->flr_label & IPV6_FLOWLABEL_STATELESS_FLAG)) + return -ERANGE; - fl = fl_create(net, sk, &freq, optval, optlen, &err); - if (!fl) - return err; - sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL); + fl = fl_create(net, sk, freq, optval, optlen, &err); + if (!fl) + return err; - if (freq.flr_label) { - err = -EEXIST; - rcu_read_lock_bh(); - for_each_sk_fl_rcu(np, sfl) { - if (sfl->fl->label == freq.flr_label) { - if (freq.flr_flags&IPV6_FL_F_EXCL) { - rcu_read_unlock_bh(); - goto done; - } - fl1 = sfl->fl; - if (!atomic_inc_not_zero(&fl1->users)) - fl1 = NULL; - break; + sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL); + + if (freq->flr_label) { + err = -EEXIST; + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { + if (sfl->fl->label == freq->flr_label) { + if (freq->flr_flags & IPV6_FL_F_EXCL) { + rcu_read_unlock_bh(); + goto done; } + fl1 = sfl->fl; + if (!atomic_inc_not_zero(&fl1->users)) + fl1 = NULL; + break; } - rcu_read_unlock_bh(); + } + rcu_read_unlock_bh(); - if (!fl1) - fl1 = fl_lookup(net, freq.flr_label); - if (fl1) { + if (!fl1) + fl1 = fl_lookup(net, freq->flr_label); + if (fl1) { recheck: - err = -EEXIST; - if (freq.flr_flags&IPV6_FL_F_EXCL) - goto release; - err = -EPERM; - if (fl1->share == IPV6_FL_S_EXCL || - fl1->share != fl->share || - ((fl1->share == IPV6_FL_S_PROCESS) && - (fl1->owner.pid != fl->owner.pid)) || - ((fl1->share == IPV6_FL_S_USER) && - !uid_eq(fl1->owner.uid, fl->owner.uid))) - goto release; - - err = -ENOMEM; - if (!sfl1) - goto release; - if (fl->linger > fl1->linger) - fl1->linger = fl->linger; - if ((long)(fl->expires - fl1->expires) > 0) - fl1->expires = fl->expires; - fl_link(np, sfl1, fl1); - fl_free(fl); - return 0; + err = -EEXIST; + if (freq->flr_flags&IPV6_FL_F_EXCL) + goto release; + err = -EPERM; + if (fl1->share == IPV6_FL_S_EXCL || + fl1->share != fl->share || + ((fl1->share == IPV6_FL_S_PROCESS) && + (fl1->owner.pid != fl->owner.pid)) || + ((fl1->share == IPV6_FL_S_USER) && + !uid_eq(fl1->owner.uid, fl->owner.uid))) + goto release; + + err = -ENOMEM; + if (!sfl1) + goto release; + if (fl->linger > fl1->linger) + fl1->linger = fl->linger; + if ((long)(fl->expires - fl1->expires) > 0) + fl1->expires = fl->expires; + fl_link(np, sfl1, fl1); + fl_free(fl); + return 0; release: - fl_release(fl1); - goto done; - } - } - err = -ENOENT; - if (!(freq.flr_flags&IPV6_FL_F_CREATE)) - goto done; - - err = -ENOMEM; - if (!sfl1) + fl_release(fl1); goto done; + } + } + err = -ENOENT; + if (!(freq->flr_flags & IPV6_FL_F_CREATE)) + goto done; - err = mem_check(sk); - if (err != 0) - goto done; + err = -ENOMEM; + if (!sfl1) + goto done; - fl1 = fl_intern(net, fl, freq.flr_label); - if (fl1) - goto recheck; + err = mem_check(sk); + if (err != 0) + goto done; - if (!freq.flr_label) { - if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label, - &fl->label, sizeof(fl->label))) { - /* Intentionally ignore fault. */ - } - } + fl1 = fl_intern(net, fl, freq->flr_label); + if (fl1) + goto recheck; - fl_link(np, sfl1, fl); - return 0; + if (!freq->flr_label) { + size_t offset = offsetof(struct in6_flowlabel_req, flr_label); - default: - return -EINVAL; + if (copy_to_sockptr_offset(optval, offset, &fl->label, + sizeof(fl->label))) { + /* Intentionally ignore fault. */ + } } + fl_link(np, sfl1, fl); + return 0; done: fl_free(fl); kfree(sfl1); return err; } +int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen) +{ + struct in6_flowlabel_req freq; + + if (optlen < sizeof(freq)) + return -EINVAL; + if (copy_from_sockptr(&freq, optval, sizeof(freq))) + return -EFAULT; + + switch (freq.flr_action) { + case IPV6_FL_A_PUT: + return ipv6_flowlabel_put(sk, &freq); + case IPV6_FL_A_RENEW: + return ipv6_flowlabel_renew(sk, &freq); + case IPV6_FL_A_GET: + return ipv6_flowlabel_get(sk, &freq, optval, optlen); + default: + return -EINVAL; + } +} + #ifdef CONFIG_PROC_FS struct ip6fl_iter_state { diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index e0086758b6ee..70c8c2f36c98 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -9,6 +9,8 @@ #if IS_ENABLED(CONFIG_IPV6) +#if !IS_BUILTIN(CONFIG_IPV6) + static ip6_icmp_send_t __rcu *ip6_icmp_send; int inet6_register_icmp_sender(ip6_icmp_send_t *fn) @@ -37,14 +39,12 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); - - if (!send) - goto out; - send(skb, type, code, info, NULL); -out: + if (send) + send(skb, type, code, info, NULL); rcu_read_unlock(); } EXPORT_SYMBOL(icmpv6_send); +#endif #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_conntrack.h> diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 7fbb44736a34..a80f90bf3ae7 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -13,6 +13,8 @@ #include <net/protocol.h> #include <net/ipv6.h> #include <net/inet_common.h> +#include <net/tcp.h> +#include <net/udp.h> #include "ip6_offload.h" @@ -177,10 +179,6 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph, return len; } -INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, - struct sk_buff *)); INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, struct sk_buff *skb) { @@ -319,8 +317,6 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head, return inet_gro_receive(head, skb); } -INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff) { const struct net_offload *ops; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8a8c2d0cfcc8..c78e67d7747f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1118,6 +1118,7 @@ out_err_release: /** * ip6_dst_lookup - perform route lookup on flow + * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @dst: pointer to dst_entry * for result * @fl6: flow to lookup @@ -1136,6 +1137,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); /** * ip6_dst_lookup_flow - perform route lookup on flow with ipsec + * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup @@ -1202,11 +1204,11 @@ EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); * @skb: Packet for which lookup is done * @dev: Tunnel device * @net: Network namespace of tunnel device - * @sk: Socket which provides route info + * @sock: Socket which provides route info * @saddr: Memory to store the src ip address * @info: Tunnel information * @protocol: IP protocol - * @use_cahce: Flag to enable cache usage + * @use_cache: Flag to enable cache usage * This function performs a route lookup on a tunnel * * It returns a valid dst pointer and stores src address to be used in diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a18c378ca5f4..f635914f42ec 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -124,8 +124,12 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) return &dev->stats; } +#define for_each_ip6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses + * @net: network namespace * @link: ifindex of underlying interface * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point @@ -136,9 +140,6 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * else %NULL **/ -#define for_each_ip6_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - static struct ip6_tnl * ip6_tnl_lookup(struct net *net, int link, const struct in6_addr *remote, const struct in6_addr *local) @@ -302,8 +303,8 @@ out: /** * ip6_tnl_create - create a new tunnel + * @net: network namespace * @p: tunnel parameters - * @pt: pointer to new tunnel * * Description: * Create tunnel matching given parameters. @@ -351,6 +352,7 @@ failed: /** * ip6_tnl_locate - find or create tunnel matching given parameters + * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 0d964160a9dd..fac01b80a104 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -491,13 +491,16 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } dst_hold(dst); - dst = xfrm_lookup(t->net, dst, fl, NULL, 0); + dst = xfrm_lookup_route(t->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } + if (dst->flags & DST_XFRM_QUEUE) + goto queued; + x = dst->xfrm; if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr)) goto tx_err_link_failure; @@ -533,6 +536,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) goto tx_err_dst_release; } +queued: skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; @@ -1219,6 +1223,33 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .priority = 100, }; +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) +static int vti6_rcv_tunnel(struct sk_buff *skb) +{ + const xfrm_address_t *saddr; + __be32 spi; + + saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr; + spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr); + + return vti6_input_proto(skb, IPPROTO_IPV6, spi, 0); +} + +static struct xfrm6_tunnel vti_ipv6_handler __read_mostly = { + .handler = vti6_rcv_tunnel, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 0, +}; + +static struct xfrm6_tunnel vti_ip6ip_handler __read_mostly = { + .handler = vti6_rcv_tunnel, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 0, +}; +#endif + /** * vti6_tunnel_init - register protocol and reserve needed resources * @@ -1244,6 +1275,15 @@ static int __init vti6_tunnel_init(void) err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + msg = "ipv6 tunnel"; + err = xfrm6_tunnel_register(&vti_ipv6_handler, AF_INET6); + if (err < 0) + goto vti_tunnel_ipv6_failed; + err = xfrm6_tunnel_register(&vti_ip6ip_handler, AF_INET); + if (err < 0) + goto vti_tunnel_ip6ip_failed; +#endif msg = "netlink interface"; err = rtnl_link_register(&vti6_link_ops); @@ -1253,6 +1293,12 @@ static int __init vti6_tunnel_init(void) return 0; rtnl_link_failed: +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + err = xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); +vti_tunnel_ip6ip_failed: + err = xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); +vti_tunnel_ipv6_failed: +#endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); @@ -1271,6 +1317,10 @@ pernet_dev_failed: static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); + xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); +#endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 1f4d20e97c07..06b0d2c329b9 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1629,7 +1629,8 @@ EXPORT_SYMBOL(mroute6_is_socket); * MOSPF/PIM router set up we can clean this up. */ -int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) +int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, + unsigned int optlen) { int ret, parent = 0; struct mif6ctl vif; @@ -1665,7 +1666,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ADD_MIF: if (optlen < sizeof(vif)) return -EINVAL; - if (copy_from_user(&vif, optval, sizeof(vif))) + if (copy_from_sockptr(&vif, optval, sizeof(vif))) return -EFAULT; if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; @@ -1678,7 +1679,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_DEL_MIF: if (optlen < sizeof(mifi_t)) return -EINVAL; - if (copy_from_user(&mifi, optval, sizeof(mifi_t))) + if (copy_from_sockptr(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); ret = mif6_delete(mrt, mifi, 0, NULL); @@ -1697,7 +1698,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) return -EINVAL; - if (copy_from_user(&mfc, optval, sizeof(mfc))) + if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) return -EFAULT; if (parent == 0) parent = mfc.mf6cc_parent; @@ -1718,7 +1719,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (optlen != sizeof(flags)) return -EINVAL; - if (get_user(flags, (int __user *)optval)) + if (copy_from_sockptr(&flags, optval, sizeof(flags))) return -EFAULT; rtnl_lock(); mroute_clean_tables(mrt, flags); @@ -1735,7 +1736,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (optlen != sizeof(v)) return -EINVAL; - if (get_user(v, (int __user *)optval)) + if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; mrt->mroute_do_assert = v; return 0; @@ -1748,7 +1749,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (optlen != sizeof(v)) return -EINVAL; - if (get_user(v, (int __user *)optval)) + if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; v = !!v; rtnl_lock(); @@ -1769,7 +1770,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (optlen != sizeof(u32)) return -EINVAL; - if (get_user(v, (u32 __user *)optval)) + if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (v != RT_TABLE_DEFAULT && v >= 100000000) diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 99668bfebd85..daef890460b7 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -91,6 +91,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) t->props.mode = x->props.mode; memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr)); memcpy(&t->mark, &x->mark, sizeof(t->mark)); + t->if_id = x->if_id; if (xfrm_init_state(t)) goto error; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 76f9e41859a2..43a894bf9a1b 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -136,13 +136,42 @@ static bool setsockopt_needs_rtnl(int optname) return false; } +static int copy_group_source_from_sockptr(struct group_source_req *greqs, + sockptr_t optval, int optlen) +{ + if (in_compat_syscall()) { + struct compat_group_source_req gr32; + + if (optlen < sizeof(gr32)) + return -EINVAL; + if (copy_from_sockptr(&gr32, optval, sizeof(gr32))) + return -EFAULT; + greqs->gsr_interface = gr32.gsr_interface; + greqs->gsr_group = gr32.gsr_group; + greqs->gsr_source = gr32.gsr_source; + } else { + if (optlen < sizeof(*greqs)) + return -EINVAL; + if (copy_from_sockptr(greqs, optval, sizeof(*greqs))) + return -EFAULT; + } + + return 0; +} + static int do_ipv6_mcast_group_source(struct sock *sk, int optname, - struct group_source_req *greqs) + sockptr_t optval, int optlen) { + struct group_source_req greqs; int omode, add; + int ret; + + ret = copy_group_source_from_sockptr(&greqs, optval, optlen); + if (ret) + return ret; - if (greqs->gsr_group.ss_family != AF_INET6 || - greqs->gsr_source.ss_family != AF_INET6) + if (greqs.gsr_group.ss_family != AF_INET6 || + greqs.gsr_source.ss_family != AF_INET6) return -EADDRNOTAVAIL; if (optname == MCAST_BLOCK_SOURCE) { @@ -155,8 +184,8 @@ static int do_ipv6_mcast_group_source(struct sock *sk, int optname, struct sockaddr_in6 *psin6; int retv; - psin6 = (struct sockaddr_in6 *)&greqs->gsr_group; - retv = ipv6_sock_mc_join_ssm(sk, greqs->gsr_interface, + psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; + retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface, &psin6->sin6_addr, MCAST_INCLUDE); /* prior join w/ different source is ok */ @@ -168,11 +197,200 @@ static int do_ipv6_mcast_group_source(struct sock *sk, int optname, omode = MCAST_INCLUDE; add = 0; } - return ip6_mc_source(add, omode, sk, greqs); + return ip6_mc_source(add, omode, sk, &greqs); +} + +static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, + int optlen) +{ + struct group_filter *gsf; + int ret; + + if (optlen < GROUP_FILTER_SIZE(0)) + return -EINVAL; + if (optlen > sysctl_optmem_max) + return -ENOBUFS; + + gsf = memdup_sockptr(optval, optlen); + if (IS_ERR(gsf)) + return PTR_ERR(gsf); + + /* numsrc >= (4G-140)/128 overflow in 32 bits */ + ret = -ENOBUFS; + if (gsf->gf_numsrc >= 0x1ffffffU || + gsf->gf_numsrc > sysctl_mld_max_msf) + goto out_free_gsf; + + ret = -EINVAL; + if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) + goto out_free_gsf; + + ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist); +out_free_gsf: + kfree(gsf); + return ret; +} + +static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, + int optlen) +{ + const int size0 = offsetof(struct compat_group_filter, gf_slist); + struct compat_group_filter *gf32; + void *p; + int ret; + int n; + + if (optlen < size0) + return -EINVAL; + if (optlen > sysctl_optmem_max - 4) + return -ENOBUFS; + + p = kmalloc(optlen + 4, GFP_KERNEL); + if (!p) + return -ENOMEM; + + gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + ret = -EFAULT; + if (copy_from_sockptr(gf32, optval, optlen)) + goto out_free_p; + + /* numsrc >= (4G-140)/128 overflow in 32 bits */ + ret = -ENOBUFS; + n = gf32->gf_numsrc; + if (n >= 0x1ffffffU || n > sysctl_mld_max_msf) + goto out_free_p; + + ret = -EINVAL; + if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) + goto out_free_p; + + ret = ip6_mc_msfilter(sk, &(struct group_filter){ + .gf_interface = gf32->gf_interface, + .gf_group = gf32->gf_group, + .gf_fmode = gf32->gf_fmode, + .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist); + +out_free_p: + kfree(p); + return ret; +} + +static int ipv6_mcast_join_leave(struct sock *sk, int optname, + sockptr_t optval, int optlen) +{ + struct sockaddr_in6 *psin6; + struct group_req greq; + + if (optlen < sizeof(greq)) + return -EINVAL; + if (copy_from_sockptr(&greq, optval, sizeof(greq))) + return -EFAULT; + + if (greq.gr_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; + psin6 = (struct sockaddr_in6 *)&greq.gr_group; + if (optname == MCAST_JOIN_GROUP) + return ipv6_sock_mc_join(sk, greq.gr_interface, + &psin6->sin6_addr); + return ipv6_sock_mc_drop(sk, greq.gr_interface, &psin6->sin6_addr); +} + +static int compat_ipv6_mcast_join_leave(struct sock *sk, int optname, + sockptr_t optval, int optlen) +{ + struct compat_group_req gr32; + struct sockaddr_in6 *psin6; + + if (optlen < sizeof(gr32)) + return -EINVAL; + if (copy_from_sockptr(&gr32, optval, sizeof(gr32))) + return -EFAULT; + + if (gr32.gr_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; + psin6 = (struct sockaddr_in6 *)&gr32.gr_group; + if (optname == MCAST_JOIN_GROUP) + return ipv6_sock_mc_join(sk, gr32.gr_interface, + &psin6->sin6_addr); + return ipv6_sock_mc_drop(sk, gr32.gr_interface, &psin6->sin6_addr); +} + +static int ipv6_set_opt_hdr(struct sock *sk, int optname, sockptr_t optval, + int optlen) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_opt_hdr *new = NULL; + struct net *net = sock_net(sk); + struct ipv6_txoptions *opt; + int err; + + /* hop-by-hop / destination options are privileged option */ + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) + return -EPERM; + + /* remove any sticky options header with a zero option + * length, per RFC3542. + */ + if (optlen > 0) { + if (sockptr_is_null(optval)) + return -EINVAL; + if (optlen < sizeof(struct ipv6_opt_hdr) || + optlen & 0x7 || + optlen > 8 * 255) + return -EINVAL; + + new = memdup_sockptr(optval, optlen); + if (IS_ERR(new)) + return PTR_ERR(new); + if (unlikely(ipv6_optlen(new) > optlen)) { + kfree(new); + return -EINVAL; + } + } + + opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); + opt = ipv6_renew_options(sk, opt, optname, new); + kfree(new); + if (IS_ERR(opt)) + return PTR_ERR(opt); + + /* routing header option needs extra check */ + err = -EINVAL; + if (optname == IPV6_RTHDR && opt && opt->srcrt) { + struct ipv6_rt_hdr *rthdr = opt->srcrt; + switch (rthdr->type) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPV6_SRCRT_TYPE_2: + if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) + goto sticky_done; + break; +#endif + case IPV6_SRCRT_TYPE_4: + { + struct ipv6_sr_hdr *srh = + (struct ipv6_sr_hdr *)opt->srcrt; + + if (!seg6_validate_srh(srh, optlen, false)) + goto sticky_done; + break; + } + default: + goto sticky_done; + } + } + + err = 0; + opt = ipv6_update_options(sk, opt); +sticky_done: + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } + return err; } static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); @@ -180,11 +398,11 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, int retv = -ENOPROTOOPT; bool needs_rtnl = setsockopt_needs_rtnl(optname); - if (!optval) + if (sockptr_is_null(optval)) val = 0; else { if (optlen >= sizeof(int)) { - if (get_user(val, (int __user *) optval)) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; } else val = 0; @@ -436,82 +654,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_RTHDRDSTOPTS: case IPV6_RTHDR: case IPV6_DSTOPTS: - { - struct ipv6_txoptions *opt; - struct ipv6_opt_hdr *new = NULL; - - /* hop-by-hop / destination options are privileged option */ - retv = -EPERM; - if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) - break; - - /* remove any sticky options header with a zero option - * length, per RFC3542. - */ - if (optlen == 0) - optval = NULL; - else if (!optval) - goto e_inval; - else if (optlen < sizeof(struct ipv6_opt_hdr) || - optlen & 0x7 || optlen > 8 * 255) - goto e_inval; - else { - new = memdup_user(optval, optlen); - if (IS_ERR(new)) { - retv = PTR_ERR(new); - break; - } - if (unlikely(ipv6_optlen(new) > optlen)) { - kfree(new); - goto e_inval; - } - } - - opt = rcu_dereference_protected(np->opt, - lockdep_sock_is_held(sk)); - opt = ipv6_renew_options(sk, opt, optname, new); - kfree(new); - if (IS_ERR(opt)) { - retv = PTR_ERR(opt); - break; - } - - /* routing header option needs extra check */ - retv = -EINVAL; - if (optname == IPV6_RTHDR && opt && opt->srcrt) { - struct ipv6_rt_hdr *rthdr = opt->srcrt; - switch (rthdr->type) { -#if IS_ENABLED(CONFIG_IPV6_MIP6) - case IPV6_SRCRT_TYPE_2: - if (rthdr->hdrlen != 2 || - rthdr->segments_left != 1) - goto sticky_done; - - break; -#endif - case IPV6_SRCRT_TYPE_4: - { - struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *) - opt->srcrt; - - if (!seg6_validate_srh(srh, optlen, false)) - goto sticky_done; - break; - } - default: - goto sticky_done; - } - } - - retv = 0; - opt = ipv6_update_options(sk, opt); -sticky_done: - if (opt) { - atomic_sub(opt->tot_len, &sk->sk_omem_alloc); - txopt_put(opt); - } + retv = ipv6_set_opt_hdr(sk, optname, optval, optlen); break; - } case IPV6_PKTINFO: { @@ -519,12 +663,13 @@ sticky_done: if (optlen == 0) goto e_inval; - else if (optlen < sizeof(struct in6_pktinfo) || !optval) + else if (optlen < sizeof(struct in6_pktinfo) || + sockptr_is_null(optval)) goto e_inval; - if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) { - retv = -EFAULT; - break; + if (copy_from_sockptr(&pkt, optval, sizeof(pkt))) { + retv = -EFAULT; + break; } if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex)) goto e_inval; @@ -565,7 +710,7 @@ sticky_done: refcount_set(&opt->refcnt, 1); opt->tot_len = sizeof(*opt) + optlen; retv = -EFAULT; - if (copy_from_user(opt+1, optval, optlen)) + if (copy_from_sockptr(opt + 1, optval, optlen)) goto done; msg.msg_controllen = optlen; @@ -687,7 +832,7 @@ done: break; retv = -EFAULT; - if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq))) + if (copy_from_sockptr(&mreq, optval, sizeof(struct ipv6_mreq))) break; if (optname == IPV6_ADD_MEMBERSHIP) @@ -705,7 +850,7 @@ done: goto e_inval; retv = -EFAULT; - if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq))) + if (copy_from_sockptr(&mreq, optval, sizeof(struct ipv6_mreq))) break; if (optname == IPV6_JOIN_ANYCAST) @@ -723,77 +868,26 @@ done: case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: - { - struct group_req greq; - struct sockaddr_in6 *psin6; - - if (optlen < sizeof(struct group_req)) - goto e_inval; - - retv = -EFAULT; - if (copy_from_user(&greq, optval, sizeof(struct group_req))) - break; - if (greq.gr_group.ss_family != AF_INET6) { - retv = -EADDRNOTAVAIL; - break; - } - psin6 = (struct sockaddr_in6 *)&greq.gr_group; - if (optname == MCAST_JOIN_GROUP) - retv = ipv6_sock_mc_join(sk, greq.gr_interface, - &psin6->sin6_addr); + if (in_compat_syscall()) + retv = compat_ipv6_mcast_join_leave(sk, optname, optval, + optlen); else - retv = ipv6_sock_mc_drop(sk, greq.gr_interface, - &psin6->sin6_addr); + retv = ipv6_mcast_join_leave(sk, optname, optval, + optlen); break; - } case MCAST_JOIN_SOURCE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_BLOCK_SOURCE: case MCAST_UNBLOCK_SOURCE: - { - struct group_source_req greqs; - - if (optlen < sizeof(struct group_source_req)) - goto e_inval; - if (copy_from_user(&greqs, optval, sizeof(greqs))) { - retv = -EFAULT; - break; - } - retv = do_ipv6_mcast_group_source(sk, optname, &greqs); + retv = do_ipv6_mcast_group_source(sk, optname, optval, optlen); break; - } case MCAST_MSFILTER: - { - struct group_filter *gsf; - - if (optlen < GROUP_FILTER_SIZE(0)) - goto e_inval; - if (optlen > sysctl_optmem_max) { - retv = -ENOBUFS; - break; - } - gsf = memdup_user(optval, optlen); - if (IS_ERR(gsf)) { - retv = PTR_ERR(gsf); - break; - } - /* numsrc >= (4G-140)/128 overflow in 32 bits */ - if (gsf->gf_numsrc >= 0x1ffffffU || - gsf->gf_numsrc > sysctl_mld_max_msf) { - kfree(gsf); - retv = -ENOBUFS; - break; - } - if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) { - kfree(gsf); - retv = -EINVAL; - break; - } - retv = ip6_mc_msfilter(sk, gsf, gsf->gf_slist); - kfree(gsf); - + if (in_compat_syscall()) + retv = compat_ipv6_set_mcast_msfilter(sk, optval, + optlen); + else + retv = ipv6_set_mcast_msfilter(sk, optval, optlen); break; - } case IPV6_ROUTER_ALERT: if (optlen < sizeof(int)) goto e_inval; @@ -872,6 +966,14 @@ done: np->rxopt.bits.recvfragsize = valbool; retv = 0; break; + case IPV6_RECVERR_RFC4884: + if (optlen < sizeof(int)) + goto e_inval; + if (val < 0 || val > 1) + goto e_inval; + np->recverr_rfc4884 = valbool; + retv = 0; + break; } release_sock(sk); @@ -887,8 +989,8 @@ e_inval: return -EINVAL; } -int ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) +int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen) { int err; @@ -909,140 +1011,6 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, } EXPORT_SYMBOL(ipv6_setsockopt); -#ifdef CONFIG_COMPAT -int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) -{ - int err; - - if (level == SOL_IP && sk->sk_type != SOCK_RAW) { - if (udp_prot.compat_setsockopt != NULL) - return udp_prot.compat_setsockopt(sk, level, optname, - optval, optlen); - return udp_prot.setsockopt(sk, level, optname, optval, optlen); - } - - if (level != SOL_IPV6) - return -ENOPROTOOPT; - - switch (optname) { - case MCAST_JOIN_GROUP: - case MCAST_LEAVE_GROUP: - { - struct compat_group_req __user *gr32 = (void __user *)optval; - struct group_req greq; - struct sockaddr_in6 *psin6 = (struct sockaddr_in6 *)&greq.gr_group; - - if (optlen < sizeof(struct compat_group_req)) - return -EINVAL; - - if (get_user(greq.gr_interface, &gr32->gr_interface) || - copy_from_user(&greq.gr_group, &gr32->gr_group, - sizeof(greq.gr_group))) - return -EFAULT; - - if (greq.gr_group.ss_family != AF_INET6) - return -EADDRNOTAVAIL; - - rtnl_lock(); - lock_sock(sk); - if (optname == MCAST_JOIN_GROUP) - err = ipv6_sock_mc_join(sk, greq.gr_interface, - &psin6->sin6_addr); - else - err = ipv6_sock_mc_drop(sk, greq.gr_interface, - &psin6->sin6_addr); - release_sock(sk); - rtnl_unlock(); - return err; - } - case MCAST_JOIN_SOURCE_GROUP: - case MCAST_LEAVE_SOURCE_GROUP: - case MCAST_BLOCK_SOURCE: - case MCAST_UNBLOCK_SOURCE: - { - struct compat_group_source_req __user *gsr32 = (void __user *)optval; - struct group_source_req greqs; - - if (optlen < sizeof(struct compat_group_source_req)) - return -EINVAL; - - if (get_user(greqs.gsr_interface, &gsr32->gsr_interface) || - copy_from_user(&greqs.gsr_group, &gsr32->gsr_group, - sizeof(greqs.gsr_group)) || - copy_from_user(&greqs.gsr_source, &gsr32->gsr_source, - sizeof(greqs.gsr_source))) - return -EFAULT; - - rtnl_lock(); - lock_sock(sk); - err = do_ipv6_mcast_group_source(sk, optname, &greqs); - release_sock(sk); - rtnl_unlock(); - return err; - } - case MCAST_MSFILTER: - { - const int size0 = offsetof(struct compat_group_filter, gf_slist); - struct compat_group_filter *gf32; - void *p; - int n; - - if (optlen < size0) - return -EINVAL; - if (optlen > sysctl_optmem_max - 4) - return -ENOBUFS; - - p = kmalloc(optlen + 4, GFP_KERNEL); - if (!p) - return -ENOMEM; - - gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ - if (copy_from_user(gf32, optval, optlen)) { - err = -EFAULT; - goto mc_msf_out; - } - - n = gf32->gf_numsrc; - /* numsrc >= (4G-140)/128 overflow in 32 bits */ - if (n >= 0x1ffffffU || - n > sysctl_mld_max_msf) { - err = -ENOBUFS; - goto mc_msf_out; - } - if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) { - err = -EINVAL; - goto mc_msf_out; - } - - rtnl_lock(); - lock_sock(sk); - err = ip6_mc_msfilter(sk, &(struct group_filter){ - .gf_interface = gf32->gf_interface, - .gf_group = gf32->gf_group, - .gf_fmode = gf32->gf_fmode, - .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist); - release_sock(sk); - rtnl_unlock(); -mc_msf_out: - kfree(p); - return err; - } - } - - err = do_ipv6_setsockopt(sk, level, optname, optval, optlen); -#ifdef CONFIG_NETFILTER - /* we need to exclude all possible ENOPROTOOPTs except default case */ - if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY && - optname != IPV6_XFRM_POLICY) - err = compat_nf_setsockopt(sk, PF_INET6, optname, optval, - optlen); -#endif - return err; -} -EXPORT_SYMBOL(compat_ipv6_setsockopt); -#endif - static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, int optname, char __user *optval, int len) { @@ -1077,6 +1045,75 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, return len; } +static int ipv6_get_msfilter(struct sock *sk, void __user *optval, + int __user *optlen, int len) +{ + const int size0 = offsetof(struct group_filter, gf_slist); + struct group_filter __user *p = optval; + struct group_filter gsf; + int num; + int err; + + if (len < size0) + return -EINVAL; + if (copy_from_user(&gsf, p, size0)) + return -EFAULT; + if (gsf.gf_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; + num = gsf.gf_numsrc; + lock_sock(sk); + err = ip6_mc_msfget(sk, &gsf, p->gf_slist); + if (!err) { + if (num > gsf.gf_numsrc) + num = gsf.gf_numsrc; + if (put_user(GROUP_FILTER_SIZE(num), optlen) || + copy_to_user(p, &gsf, size0)) + err = -EFAULT; + } + release_sock(sk); + return err; +} + +static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval, + int __user *optlen) +{ + const int size0 = offsetof(struct compat_group_filter, gf_slist); + struct compat_group_filter __user *p = optval; + struct compat_group_filter gf32; + struct group_filter gf; + int len, err; + int num; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < size0) + return -EINVAL; + + if (copy_from_user(&gf32, p, size0)) + return -EFAULT; + gf.gf_interface = gf32.gf_interface; + gf.gf_fmode = gf32.gf_fmode; + num = gf.gf_numsrc = gf32.gf_numsrc; + gf.gf_group = gf32.gf_group; + + if (gf.gf_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; + + lock_sock(sk); + err = ip6_mc_msfget(sk, &gf, p->gf_slist); + release_sock(sk); + if (err) + return err; + if (num > gf.gf_numsrc) + num = gf.gf_numsrc; + len = GROUP_FILTER_SIZE(num) - (sizeof(gf)-sizeof(gf32)); + if (put_user(len, optlen) || + put_user(gf.gf_fmode, &p->gf_fmode) || + put_user(gf.gf_numsrc, &p->gf_numsrc)) + return -EFAULT; + return 0; +} + static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen, unsigned int flags) { @@ -1100,33 +1137,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = sk->sk_family; break; case MCAST_MSFILTER: - { - struct group_filter __user *p = (void __user *)optval; - struct group_filter gsf; - const int size0 = offsetof(struct group_filter, gf_slist); - int num; - int err; - - if (len < size0) - return -EINVAL; - if (copy_from_user(&gsf, p, size0)) - return -EFAULT; - if (gsf.gf_group.ss_family != AF_INET6) - return -EADDRNOTAVAIL; - num = gsf.gf_numsrc; - lock_sock(sk); - err = ip6_mc_msfget(sk, &gsf, p->gf_slist); - if (!err) { - if (num > gsf.gf_numsrc) - num = gsf.gf_numsrc; - if (put_user(GROUP_FILTER_SIZE(num), optlen) || - copy_to_user(p, &gsf, size0)) - err = -EFAULT; - } - release_sock(sk); - return err; - } - + if (in_compat_syscall()) + return compat_ipv6_get_msfilter(sk, optval, optlen); + return ipv6_get_msfilter(sk, optval, optlen, len); case IPV6_2292PKTOPTIONS: { struct msghdr msg; @@ -1435,6 +1448,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->rtalert_isolate; break; + case IPV6_RECVERR_RFC4884: + val = np->recverr_rfc4884; + break; + default: return -ENOPROTOOPT; } @@ -1474,78 +1491,3 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, return err; } EXPORT_SYMBOL(ipv6_getsockopt); - -#ifdef CONFIG_COMPAT -int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - int err; - - if (level == SOL_IP && sk->sk_type != SOCK_RAW) { - if (udp_prot.compat_getsockopt != NULL) - return udp_prot.compat_getsockopt(sk, level, optname, - optval, optlen); - return udp_prot.getsockopt(sk, level, optname, optval, optlen); - } - - if (level != SOL_IPV6) - return -ENOPROTOOPT; - - if (optname == MCAST_MSFILTER) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); - struct compat_group_filter __user *p = (void __user *)optval; - struct compat_group_filter gf32; - struct group_filter gf; - int ulen, err; - int num; - - if (get_user(ulen, optlen)) - return -EFAULT; - - if (ulen < size0) - return -EINVAL; - - if (copy_from_user(&gf32, p, size0)) - return -EFAULT; - - gf.gf_interface = gf32.gf_interface; - gf.gf_fmode = gf32.gf_fmode; - num = gf.gf_numsrc = gf32.gf_numsrc; - gf.gf_group = gf32.gf_group; - - if (gf.gf_group.ss_family != AF_INET6) - return -EADDRNOTAVAIL; - lock_sock(sk); - err = ip6_mc_msfget(sk, &gf, p->gf_slist); - release_sock(sk); - if (err) - return err; - if (num > gf.gf_numsrc) - num = gf.gf_numsrc; - ulen = GROUP_FILTER_SIZE(num) - (sizeof(gf)-sizeof(gf32)); - if (put_user(ulen, optlen) || - put_user(gf.gf_fmode, &p->gf_fmode) || - put_user(gf.gf_numsrc, &p->gf_numsrc)) - return -EFAULT; - return 0; - } - - err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, - MSG_CMSG_COMPAT); -#ifdef CONFIG_NETFILTER - /* we need to exclude all possible ENOPROTOOPTs except default case */ - if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { - int len; - - if (get_user(len, optlen)) - return -EFAULT; - - err = compat_nf_getsockopt(sk, PF_INET6, optname, optval, &len); - if (err >= 0) - err = put_user(len, optlen); - } -#endif - return err; -} -EXPORT_SYMBOL(compat_ipv6_getsockopt); -#endif diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e96a431549bc..2e2119bfcf13 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -960,8 +960,7 @@ static int compat_table_info(const struct xt_table_info *info, } #endif -static int get_info(struct net *net, void __user *user, - const int *len, int compat) +static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -975,7 +974,7 @@ static int get_info(struct net *net, void __user *user, name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_COMPAT - if (compat) + if (in_compat_syscall()) xt_compat_lock(AF_INET6); #endif t = xt_request_find_table_lock(net, AF_INET6, name); @@ -985,7 +984,7 @@ static int get_info(struct net *net, void __user *user, #ifdef CONFIG_COMPAT struct xt_table_info tmp; - if (compat) { + if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; @@ -1011,7 +1010,7 @@ static int get_info(struct net *net, void __user *user, } else ret = PTR_ERR(t); #ifdef CONFIG_COMPAT - if (compat) + if (in_compat_syscall()) xt_compat_unlock(AF_INET6); #endif return ret; @@ -1120,7 +1119,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, } static int -do_replace(struct net *net, const void __user *user, unsigned int len) +do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ip6t_replace tmp; @@ -1128,7 +1127,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; - if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) + if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ @@ -1144,8 +1143,8 @@ do_replace(struct net *net, const void __user *user, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - if (copy_from_user(loc_cpu_entry, user + sizeof(tmp), - tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } @@ -1169,8 +1168,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len) } static int -do_add_counters(struct net *net, const void __user *user, unsigned int len, - int compat) +do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; @@ -1181,7 +1179,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, struct ip6t_entry *iter; unsigned int addend; - paddc = xt_copy_counters_from_user(user, len, &tmp, compat); + paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET6, tmp.name); @@ -1495,7 +1493,7 @@ out_unlock: } static int -compat_do_replace(struct net *net, void __user *user, unsigned int len) +compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ip6t_replace tmp; @@ -1503,7 +1501,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; - if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) + if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ @@ -1519,8 +1517,8 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - if (copy_from_user(loc_cpu_entry, user + sizeof(tmp), - tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } @@ -1543,31 +1541,6 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return ret; } -static int -compat_do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, - unsigned int len) -{ - int ret; - - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - return -EPERM; - - switch (cmd) { - case IP6T_SO_SET_REPLACE: - ret = compat_do_replace(sock_net(sk), user, len); - break; - - case IP6T_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sock_net(sk), user, len, 1); - break; - - default: - ret = -EINVAL; - } - - return ret; -} - struct compat_ip6t_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; @@ -1643,33 +1616,10 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, xt_compat_unlock(AF_INET6); return ret; } - -static int do_ip6t_get_ctl(struct sock *, int, void __user *, int *); - -static int -compat_do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) -{ - int ret; - - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - return -EPERM; - - switch (cmd) { - case IP6T_SO_GET_INFO: - ret = get_info(sock_net(sk), user, len, 1); - break; - case IP6T_SO_GET_ENTRIES: - ret = compat_get_entries(sock_net(sk), user, len); - break; - default: - ret = do_ip6t_get_ctl(sk, cmd, user, len); - } - return ret; -} #endif static int -do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) +do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; @@ -1678,11 +1628,16 @@ do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) switch (cmd) { case IP6T_SO_SET_REPLACE: - ret = do_replace(sock_net(sk), user, len); +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = compat_do_replace(sock_net(sk), arg, len); + else +#endif + ret = do_replace(sock_net(sk), arg, len); break; case IP6T_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sock_net(sk), user, len, 0); + ret = do_add_counters(sock_net(sk), arg, len); break; default: @@ -1702,11 +1657,16 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) switch (cmd) { case IP6T_SO_GET_INFO: - ret = get_info(sock_net(sk), user, len, 0); + ret = get_info(sock_net(sk), user, len); break; case IP6T_SO_GET_ENTRIES: - ret = get_entries(sock_net(sk), user, len); +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = compat_get_entries(sock_net(sk), user, len); + else +#endif + ret = get_entries(sock_net(sk), user, len); break; case IP6T_SO_GET_REVISION_MATCH: @@ -1897,15 +1857,9 @@ static struct nf_sockopt_ops ip6t_sockopts = { .set_optmin = IP6T_BASE_CTL, .set_optmax = IP6T_SO_SET_MAX+1, .set = do_ip6t_set_ctl, -#ifdef CONFIG_COMPAT - .compat_set = compat_do_ip6t_set_ctl, -#endif .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, -#ifdef CONFIG_COMPAT - .compat_get = compat_do_ip6t_get_ctl, -#endif .owner = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 4e15a14435e4..70da2f2ce064 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -74,8 +74,7 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) ahinfo->hdrres, ah->reserved, !(ahinfo->hdrres && ah->reserved)); - return (ah != NULL) && - spi_match(ahinfo->spis[0], ahinfo->spis[1], + return spi_match(ahinfo->spis[0], ahinfo->spis[1], ntohl(ah->spi), !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && (!ahinfo->hdrlen || diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index fb91eeee4a1e..3aad6439386b 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -85,8 +85,7 @@ frag_mt6(const struct sk_buff *skb, struct xt_action_param *par) !((fraginfo->flags & IP6T_FRAG_NMF) && (ntohs(fh->frag_off) & IP6_MF))); - return (fh != NULL) && - id_match(fraginfo->ids[0], fraginfo->ids[1], + return id_match(fraginfo->ids[0], fraginfo->ids[1], ntohl(fh->identification), !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) && !((fraginfo->flags & IP6T_FRAG_RES) && diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 467b2a86031b..e7a3fb9355ee 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -86,8 +86,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) ((optinfo->hdrlen == hdrlen) ^ !!(optinfo->invflags & IP6T_OPTS_INV_LEN)))); - ret = (oh != NULL) && - (!(optinfo->flags & IP6T_OPTS_LEN) || + ret = (!(optinfo->flags & IP6T_OPTS_LEN) || ((optinfo->hdrlen == hdrlen) ^ !!(optinfo->invflags & IP6T_OPTS_INV_LEN))); diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index f633dc84ca3f..733c83d38b30 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -89,8 +89,7 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) !((rtinfo->flags & IP6T_RT_RES) && (((const struct rt0_hdr *)rh)->reserved))); - ret = (rh != NULL) && - (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], + ret = (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], rh->segments_left, !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && (!(rtinfo->flags & IP6T_RT_LEN) || diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 5fae66f66671..4aef6baaa55e 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -126,6 +126,21 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, } EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_put); +static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) +{ + struct dst_entry *dst = NULL; + struct flowi fl; + + memset(&fl, 0, sizeof(struct flowi)); + fl.u.ip6.daddr = ipv6_hdr(skb_in)->saddr; + nf_ip6_route(dev_net(skb_in->dev), &dst, &fl, false); + if (!dst) + return -1; + + skb_dst_set(skb_in, dst); + return 0; +} + void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) { struct net_device *br_indev __maybe_unused; @@ -154,6 +169,14 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; + + if (hook == NF_INET_PRE_ROUTING) { + nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); + if (!dst) + return; + skb_dst_set(oldskb, dst); + } + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); @@ -245,6 +268,9 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) skb_in->dev = net->loopback_dev; + if (hooknum == NF_INET_PRE_ROUTING && nf_reject6_fill_skb_dst(skb_in)) + return; + icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); } EXPORT_SYMBOL_GPL(nf_send_unreach6); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 98ac32b49d8c..6caa062f68e7 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -114,6 +114,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); ipcm6_init_sk(&ipc6, np); + ipc6.sockc.mark = sk->sk_mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8ef5a7b30524..874f01cd7aec 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -972,13 +972,13 @@ do_confirm: } static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + sockptr_t optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); - if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen)) + if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: @@ -1015,12 +1015,12 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; - if (get_user(val, (int __user *)optval)) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { @@ -1062,7 +1062,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, } static int rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { switch (level) { case SOL_RAW: @@ -1084,30 +1084,6 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) -{ - switch (level) { - case SOL_RAW: - break; - case SOL_ICMPV6: - if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; - return rawv6_seticmpfilter(sk, level, optname, optval, optlen); - case SOL_IPV6: - if (optname == IPV6_CHECKSUM || - optname == IPV6_HDRINCL) - break; - fallthrough; - default: - return compat_ipv6_setsockopt(sk, level, optname, - optval, optlen); - } - return do_rawv6_setsockopt(sk, level, optname, optval, optlen); -} -#endif - static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -1169,30 +1145,6 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - switch (level) { - case SOL_RAW: - break; - case SOL_ICMPV6: - if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; - return rawv6_geticmpfilter(sk, level, optname, optval, optlen); - case SOL_IPV6: - if (optname == IPV6_CHECKSUM || - optname == IPV6_HDRINCL) - break; - fallthrough; - default: - return compat_ipv6_getsockopt(sk, level, optname, - optval, optlen); - } - return do_rawv6_getsockopt(sk, level, optname, optval, optlen); -} -#endif - static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { @@ -1297,8 +1249,6 @@ struct proto rawv6_prot = { .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, #ifdef CONFIG_COMPAT - .compat_setsockopt = compat_rawv6_setsockopt, - .compat_getsockopt = compat_rawv6_getsockopt, .compat_ioctl = compat_rawv6_ioctl, #endif .diag_destroy = raw_abort, @@ -1378,8 +1328,6 @@ const struct proto_ops inet6_sockraw_ops = { .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, #endif }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4c36bd0c7930..5e7e25e2523a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -61,6 +61,7 @@ #include <net/l3mdev.h> #include <net/ip.h> #include <linux/uaccess.h> +#include <linux/btf_ids.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> @@ -1210,7 +1211,7 @@ fallback: return nrt; } -static struct rt6_info *ip6_pol_route_lookup(struct net *net, +INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, @@ -2277,7 +2278,7 @@ out: } EXPORT_SYMBOL_GPL(ip6_pol_route); -static struct rt6_info *ip6_pol_route_input(struct net *net, +INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, @@ -2468,7 +2469,7 @@ void ip6_route_input(struct sk_buff *skb) &fl6, skb, flags)); } -static struct rt6_info *ip6_pol_route_output(struct net *net, +INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, @@ -2915,7 +2916,7 @@ struct ip6rd_flowi { struct in6_addr gateway; }; -static struct rt6_info *__ip6_route_redirect(struct net *net, +INDIRECT_CALLABLE_SCOPE struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, @@ -6423,21 +6424,29 @@ void __init ip6_route_init_special_entries(void) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt) -static const struct bpf_iter_reg ipv6_route_reg_info = { - .target = "ipv6_route", +BTF_ID_LIST(btf_fib6_info_id) +BTF_ID(struct, fib6_info) + +static const struct bpf_iter_seq_info ipv6_route_seq_info = { .seq_ops = &ipv6_route_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct ipv6_route_iter), +}; + +static struct bpf_iter_reg ipv6_route_reg_info = { + .target = "ipv6_route", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ipv6_route, rt), PTR_TO_BTF_ID_OR_NULL }, }, + .seq_info = &ipv6_route_seq_info, }; static int __init bpf_iter_register(void) { + ipv6_route_reg_info.ctx_arg_info[0].btf_id = *btf_fib6_info_id; return bpf_iter_reg_target(&ipv6_route_reg_info); } diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index c3ececd7cfc1..5fdf3ebb953f 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -136,8 +136,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, oldhdr = ipv6_hdr(skb); - buf = kzalloc(ipv6_rpl_srh_alloc_size(srh->segments_left - 1) * 2, - GFP_ATOMIC); + buf = kcalloc(struct_size(srh, segments.addr, srh->segments_left), 2, GFP_ATOMIC); if (!buf) return -ENOMEM; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index e0e9f48ab14f..897fa59c47de 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -27,6 +27,23 @@ #include <net/seg6_hmac.h> #endif +static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) +{ + int head = 0; + + switch (tuninfo->mode) { + case SEG6_IPTUN_MODE_INLINE: + break; + case SEG6_IPTUN_MODE_ENCAP: + head = sizeof(struct ipv6hdr); + break; + case SEG6_IPTUN_MODE_L2ENCAP: + return 0; + } + + return ((tuninfo->srh->hdrlen + 1) << 3) + head; +} + struct seg6_lwt { struct dst_cache cache; struct seg6_iptunnel_encap tuninfo[]; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 13235a012388..e796a64be308 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk, false); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); if (!req) goto out; @@ -178,9 +178,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) treq = tcp_rsk(req); treq->tfo_listener = false; - if (IS_ENABLED(CONFIG_MPTCP)) - treq->is_mptcp = 0; - if (security_inet_conn_request(sk, skb, req)) goto out_free; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f67d45ff00b4..305870a72352 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -567,7 +567,7 @@ static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, } static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, - char __user *optval, int optlen) + sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; @@ -577,7 +577,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, if (optlen < sizeof(cmd)) return -EINVAL; - if (copy_from_user(&cmd, optval, sizeof(cmd))) + if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin6->sin6_family != AF_INET6) @@ -1811,6 +1811,13 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_destructor = tcp_twsk_destructor, }; +INDIRECT_CALLABLE_SCOPE void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + __tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr); +} + const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, @@ -1824,10 +1831,6 @@ const struct inet_connection_sock_af_ops ipv6_specific = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_ipv6_setsockopt, - .compat_getsockopt = compat_ipv6_getsockopt, -#endif .mtu_reduced = tcp_v6_mtu_reduced, }; @@ -1854,10 +1857,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_ipv6_setsockopt, - .compat_getsockopt = compat_ipv6_getsockopt, -#endif .mtu_reduced = tcp_v4_mtu_reduced, }; @@ -2115,10 +2114,6 @@ struct proto tcpv6_prot = { .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = &tcp_hashinfo, .no_autobind = true, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_tcp_setsockopt, - .compat_getsockopt = compat_tcp_getsockopt, -#endif .diag_destroy = tcp_abort, }; EXPORT_SYMBOL_GPL(tcpv6_prot); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 06c02ebe6b9b..00e8d8b1c9a7 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -155,6 +155,33 @@ drop: return 0; } +#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) +static int tunnel6_rcv_cb(struct sk_buff *skb, u8 proto, int err) +{ + struct xfrm6_tunnel __rcu *head; + struct xfrm6_tunnel *handler; + int ret; + + head = (proto == IPPROTO_IPV6) ? tunnel6_handlers : tunnel46_handlers; + + for_each_tunnel_rcu(head, handler) { + if (handler->cb_handler) { + ret = handler->cb_handler(skb, err); + if (ret <= 0) + return ret; + } + } + + return 0; +} + +static const struct xfrm_input_afinfo tunnel6_input_afinfo = { + .family = AF_INET6, + .is_ipip = true, + .callback = tunnel6_rcv_cb, +}; +#endif + static int tunnel46_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; @@ -245,11 +272,25 @@ static int __init tunnel6_init(void) inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); return -EAGAIN; } +#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) + if (xfrm_input_register_afinfo(&tunnel6_input_afinfo)) { + pr_err("%s: can't add input afinfo\n", __func__); + inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); + inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); + if (xfrm6_tunnel_mpls_supported()) + inet6_del_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS); + return -EAGAIN; + } +#endif return 0; } static void __exit tunnel6_fini(void) { +#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) + if (xfrm_input_unregister_afinfo(&tunnel6_input_afinfo)) + pr_err("%s: can't remove input afinfo\n", __func__); +#endif if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP)) pr_err("%s: can't remove protocol\n", __func__); if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6)) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index a8d74f44056a..29d9691359b9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -141,6 +141,24 @@ 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, @@ -148,9 +166,8 @@ static struct sock *udp6_lib_lookup2(struct net *net, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result, *reuseport_result; + struct sock *sk, *result; int score, badness; - u32 hash = 0; result = NULL; badness = -1; @@ -158,26 +175,44 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - reuseport_result = NULL; + result = lookup_reuseport(net, sk, skb, + saddr, sport, daddr, hnum); + /* Fall back to scoring if group has connections */ + if (result && !reuseport_has_conns(sk, false)) + return result; - if (sk->sk_reuseport && - sk->sk_state != TCP_ESTABLISHED) { - hash = udp6_ehashfn(net, daddr, hnum, - saddr, sport); - - reuseport_result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (reuseport_result && !reuseport_has_conns(sk, false)) - return reuseport_result; - } - - result = reuseport_result ? : sk; + result = result ? : sk; badness = score; } } 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) +{ + struct sock *sk, *reuse_sk; + bool no_reuseport; + + if (udptable != &udp_table) + return NULL; /* only UDP is supported */ + + no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, + saddr, sport, daddr, hnum, &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, @@ -188,25 +223,42 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned short hnum = ntohs(dport); unsigned int hash2, slot2; struct udp_hslot *hslot2; - struct sock *result; + struct sock *result, *sk; hash2 = ipv6_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; + /* Lookup connected or non-wildcard sockets */ result = udp6_lib_lookup2(net, saddr, sport, daddr, hnum, dif, sdif, hslot2, skb); - if (!result) { - hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); - slot2 = hash2 & udptable->mask; + if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) + 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); + if (sk) { + result = sk; + goto done; + } + } - hslot2 = &udptable->hash2[slot2]; + /* Got non-wildcard socket or error on first lookup */ + if (result) + goto done; - result = udp6_lib_lookup2(net, saddr, sport, - &in6addr_any, hnum, dif, sdif, - hslot2, skb); - } + /* Lookup wildcard sockets */ + hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + + result = udp6_lib_lookup2(net, saddr, sport, + &in6addr_any, hnum, dif, sdif, + hslot2, skb); +done: if (IS_ERR(result)) return NULL; return result; @@ -1062,6 +1114,9 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, * @sk: socket we are sending on * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) + * @saddr: source address + * @daddr: destination address + * @len: length of packet */ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, const struct in6_addr *saddr, @@ -1561,26 +1616,16 @@ void udpv6_destroy_sock(struct sock *sk) /* * Socket option code for UDP */ -int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) +int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, + return udp_lib_setsockopt(sk, level, optname, + optval, optlen, udp_v6_push_pending_frames); return ipv6_setsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_v6_push_pending_frames); - return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); -} -#endif - int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -1589,16 +1634,6 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); -} -#endif - /* thinking of making this const? Don't. * early_demux can change based on sysctl. */ @@ -1681,10 +1716,6 @@ struct proto udpv6_prot = { .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udp_table, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udpv6_setsockopt, - .compat_getsockopt = compat_udpv6_getsockopt, -#endif .diag_destroy = udp_abort, }; diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 20e324b6f358..b2fcc46c1630 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -17,14 +17,8 @@ void udp_v6_rehash(struct sock *sk); int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); -int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen); -#ifdef CONFIG_COMPAT -int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen); -int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); -#endif +int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen); int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index bf7a7acd39b1..fbb700d3f437 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -52,10 +52,6 @@ struct proto udplitev6_prot = { .sysctl_mem = sysctl_udp_mem, .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udpv6_setsockopt, - .compat_getsockopt = compat_udpv6_getsockopt, -#endif }; static struct inet_protosw udplite6_protosw = { |