diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 11:56:19 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 11:56:19 -0800 |
commit | 5bbcc0f595fadb4cac0eddc4401035ec0bd95b09 (patch) | |
tree | 3b65e490cc36a6c6fecac1fa24d9e0ac9ced4455 /net/ipv6 | |
parent | 892204e06cb9e89fbc4b299a678f9ca358e97cac (diff) | |
parent | 50895b9de1d3e0258e015e8e55128d835d9a9f19 (diff) | |
download | linux-5bbcc0f595fadb4cac0eddc4401035ec0bd95b09.tar.gz linux-5bbcc0f595fadb4cac0eddc4401035ec0bd95b09.tar.bz2 linux-5bbcc0f595fadb4cac0eddc4401035ec0bd95b09.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Maintain the TCP retransmit queue using an rbtree, with 1GB
windows at 100Gb this really has become necessary. From Eric
Dumazet.
2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.
3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
Lunn.
4) Add meter action support to openvswitch, from Andy Zhou.
5) Add a data meta pointer for BPF accessible packets, from Daniel
Borkmann.
6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.
7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.
8) More work to move the RTNL mutex down, from Florian Westphal.
9) Add 'bpftool' utility, to help with bpf program introspection.
From Jakub Kicinski.
10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
Dangaard Brouer.
11) Support 'blocks' of transformations in the packet scheduler which
can span multiple network devices, from Jiri Pirko.
12) TC flower offload support in cxgb4, from Kumar Sanghvi.
13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
Leitner.
14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.
15) Add RED qdisc offloadability, and use it in mlxsw driver. From
Nogah Frankel.
16) eBPF based device controller for cgroup v2, from Roman Gushchin.
17) Add some fundamental tracepoints for TCP, from Song Liu.
18) Remove garbage collection from ipv6 route layer, this is a
significant accomplishment. From Wei Wang.
19) Add multicast route offload support to mlxsw, from Yotam Gigi"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
tcp: highest_sack fix
geneve: fix fill_info when link down
bpf: fix lockdep splat
net: cdc_ncm: GetNtbFormat endian fix
openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
netem: remove unnecessary 64 bit modulus
netem: use 64 bit divide by rate
tcp: Namespace-ify sysctl_tcp_default_congestion_control
net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
ipv6: set all.accept_dad to 0 by default
uapi: fix linux/tls.h userspace compilation error
usbnet: ipheth: prevent TX queue timeouts when device not ready
vhost_net: conditionally enable tx polling
uapi: fix linux/rxrpc.h userspace compilation errors
net: stmmac: fix LPI transitioning for dwmac4
atm: horizon: Fix irq release error
net-sysfs: trigger netlink notification on ifalias change via sysfs
openvswitch: Using kfree_rcu() to simplify the code
openvswitch: Make local function ovs_nsh_key_attr_size() static
openvswitch: Fix return value check in ovs_meter_cmd_features()
...
Diffstat (limited to 'net/ipv6')
36 files changed, 1869 insertions, 1044 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8a1c846d3df9..a0ae1c9d37df 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -152,11 +152,13 @@ static void ipv6_regen_rndid(struct inet6_dev *idev); static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); -static int ipv6_count_addresses(struct inet6_dev *idev); +static int ipv6_count_addresses(const struct inet6_dev *idev); static int ipv6_generate_stable_address(struct in6_addr *addr, u8 dad_count, const struct inet6_dev *idev); +#define IN6_ADDR_HSIZE_SHIFT 8 +#define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) /* * Configured unicast address hash table */ @@ -192,8 +194,6 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo); -static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev); static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, @@ -231,7 +231,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, - .accept_dad = 1, + .accept_dad = 0, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, .stable_secret = { @@ -303,10 +303,10 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .disable_policy = 0, }; -/* Check if a valid qdisc is available */ -static inline bool addrconf_qdisc_ok(const struct net_device *dev) +/* Check if link is ready: is it up and is a valid qdisc available */ +static inline bool addrconf_link_ready(const struct net_device *dev) { - return !qdisc_tx_is_noop(dev); + return netif_oper_up(dev) && !qdisc_tx_is_noop(dev); } static void addrconf_del_rs_timer(struct inet6_dev *idev) @@ -451,7 +451,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ndev->token = in6addr_any; - if (netif_running(dev) && addrconf_qdisc_ok(dev)) + if (netif_running(dev) && addrconf_link_ready(dev)) ndev->if_flags |= IF_READY; ipv6_mc_init_dev(ndev); @@ -616,23 +616,23 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; + struct inet6_dev *in6_dev = NULL; + struct net_device *dev = NULL; struct netconfmsg *ncm; struct sk_buff *skb; struct ipv6_devconf *devconf; - struct inet6_dev *in6_dev; - struct net_device *dev; int ifindex; int err; err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, devconf_ipv6_policy, extack); if (err < 0) - goto errout; + return err; - err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) - goto errout; + return -EINVAL; + err = -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: @@ -642,10 +642,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, devconf = net->ipv6.devconf_dflt; break; default: - dev = __dev_get_by_index(net, ifindex); + dev = dev_get_by_index(net, ifindex); if (!dev) - goto errout; - in6_dev = __in6_dev_get(dev); + return -EINVAL; + in6_dev = in6_dev_get(dev); if (!in6_dev) goto errout; devconf = &in6_dev->cnf; @@ -653,7 +653,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = -ENOBUFS; - skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC); + skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; @@ -669,6 +669,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: + if (in6_dev) + in6_dev_put(in6_dev); + if (dev) + dev_put(dev); return err; } @@ -945,12 +949,50 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) break; } - list_add_tail(&ifp->if_list, p); + list_add_tail_rcu(&ifp->if_list, p); } -static u32 inet6_addr_hash(const struct in6_addr *addr) +static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr) { - return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT); + u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); + + return hash_32(val, IN6_ADDR_HSIZE_SHIFT); +} + +static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, + struct net_device *dev, unsigned int hash) +{ + struct inet6_ifaddr *ifp; + + hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { + if (!net_eq(dev_net(ifp->idev->dev), net)) + continue; + if (ipv6_addr_equal(&ifp->addr, addr)) { + if (!dev || ifp->idev->dev == dev) + return true; + } + } + return false; +} + +static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) +{ + unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr); + int err = 0; + + spin_lock(&addrconf_hash_lock); + + /* Ignore adding duplicate addresses on an interface */ + if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) { + ADBG("ipv6_add_addr: already assigned\n"); + err = -EEXIST; + } else { + hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); + } + + spin_unlock(&addrconf_hash_lock); + + return err; } /* On success it returns ifp with increased reference count */ @@ -958,13 +1000,13 @@ static u32 inet6_addr_hash(const struct in6_addr *addr) static struct inet6_ifaddr * ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, const struct in6_addr *peer_addr, int pfxlen, - int scope, u32 flags, u32 valid_lft, u32 prefered_lft) + int scope, u32 flags, u32 valid_lft, u32 prefered_lft, + bool can_block, struct netlink_ext_ack *extack) { + gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC; struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; - struct rt6_info *rt; - struct in6_validator_info i6vi; - unsigned int hash; + struct rt6_info *rt = NULL; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -974,42 +1016,33 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, addr_type & IPV6_ADDR_LOOPBACK)) return ERR_PTR(-EADDRNOTAVAIL); - rcu_read_lock_bh(); - - in6_dev_hold(idev); - if (idev->dead) { err = -ENODEV; /*XXX*/ - goto out2; + goto out; } if (idev->cnf.disable_ipv6) { err = -EACCES; - goto out2; - } - - i6vi.i6vi_addr = *addr; - i6vi.i6vi_dev = idev; - rcu_read_unlock_bh(); - - err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); - - rcu_read_lock_bh(); - err = notifier_to_errno(err); - if (err) - goto out2; - - spin_lock(&addrconf_hash_lock); - - /* Ignore adding duplicate addresses on an interface */ - if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { - ADBG("ipv6_add_addr: already assigned\n"); - err = -EEXIST; goto out; } - ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); + /* validator notifier needs to be blocking; + * do not call in atomic context + */ + if (can_block) { + struct in6_validator_info i6vi = { + .i6vi_addr = *addr, + .i6vi_dev = idev, + .extack = extack, + }; + + err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); + err = notifier_to_errno(err); + if (err < 0) + goto out; + } + ifa = kzalloc(sizeof(*ifa), gfp_flags); if (!ifa) { ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; @@ -1019,6 +1052,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, rt = addrconf_dst_alloc(idev, addr, false); if (IS_ERR(rt)) { err = PTR_ERR(rt); + rt = NULL; goto out; } @@ -1049,16 +1083,21 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->rt = rt; ifa->idev = idev; + in6_dev_hold(idev); + /* For caller */ refcount_set(&ifa->refcnt, 1); - /* Add to big hash table */ - hash = inet6_addr_hash(addr); + rcu_read_lock_bh(); - hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); - spin_unlock(&addrconf_hash_lock); + err = ipv6_add_addr_hash(idev->dev, ifa); + if (err < 0) { + rcu_read_unlock_bh(); + goto out; + } write_lock(&idev->lock); + /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); @@ -1069,21 +1108,23 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, in6_ifa_hold(ifa); write_unlock(&idev->lock); -out2: + rcu_read_unlock_bh(); - if (likely(err == 0)) - inet6addr_notifier_call_chain(NETDEV_UP, ifa); - else { - kfree(ifa); - in6_dev_put(idev); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); +out: + if (unlikely(err < 0)) { + if (rt) + ip6_rt_put(rt); + if (ifa) { + if (ifa->idev) + in6_dev_put(ifa->idev); + kfree(ifa); + } ifa = ERR_PTR(err); } return ifa; -out: - spin_unlock(&addrconf_hash_lock); - goto out2; } enum cleanup_prefix_rt_t { @@ -1204,7 +1245,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); - list_del_init(&ifp->if_list); + list_del_rcu(&ifp->if_list); __in6_ifa_put(ifp); write_unlock_bh(&ifp->idev->lock); @@ -1226,7 +1267,9 @@ out: in6_ifa_put(ifp); } -static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift) +static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, + struct inet6_ifaddr *ift, + bool block) { struct inet6_dev *idev = ifp->idev; struct in6_addr addr, *tmpaddr; @@ -1330,7 +1373,7 @@ retry: ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen, ipv6_addr_scope(&addr), addr_flags, - tmp_valid_lft, tmp_prefered_lft); + tmp_valid_lft, tmp_prefered_lft, block, NULL); if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); @@ -1558,8 +1601,7 @@ static int __ipv6_dev_get_saddr(struct net *net, { struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; - read_lock_bh(&idev->lock); - list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) { int i; /* @@ -1609,11 +1651,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } break; } else if (minihiscore < miniscore) { - if (hiscore->ifa) - in6_ifa_put(hiscore->ifa); - - in6_ifa_hold(score->ifa); - swap(hiscore, score); hiscore_idx = 1 - hiscore_idx; @@ -1625,7 +1662,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } } out: - read_unlock_bh(&idev->lock); return hiscore_idx; } @@ -1662,6 +1698,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, int dst_type; bool use_oif_addr = false; int hiscore_idx = 0; + int ret = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; @@ -1737,15 +1774,14 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, } out: - rcu_read_unlock(); - hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) - return -EADDRNOTAVAIL; + ret = -EADDRNOTAVAIL; + else + *saddr = hiscore->ifa->addr; - *saddr = hiscore->ifa->addr; - in6_ifa_put(hiscore->ifa); - return 0; + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(ipv6_dev_get_saddr); @@ -1785,15 +1821,15 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, return err; } -static int ipv6_count_addresses(struct inet6_dev *idev) +static int ipv6_count_addresses(const struct inet6_dev *idev) { + const struct inet6_ifaddr *ifp; int cnt = 0; - struct inet6_ifaddr *ifp; - read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) + rcu_read_lock(); + list_for_each_entry_rcu(ifp, &idev->addr_list, if_list) cnt++; - read_unlock_bh(&idev->lock); + rcu_read_unlock(); return cnt; } @@ -1808,11 +1844,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict, u32 banned_flags) { + unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp; - unsigned int hash = inet6_addr_hash(addr); u32 ifp_flags; - rcu_read_lock_bh(); + rcu_read_lock(); hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; @@ -1826,32 +1862,16 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, !(ifp_flags&banned_flags) && (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { - rcu_read_unlock_bh(); + rcu_read_unlock(); return 1; } } - rcu_read_unlock_bh(); + rcu_read_unlock(); return 0; } EXPORT_SYMBOL(ipv6_chk_addr_and_flags); -static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev) -{ - unsigned int hash = inet6_addr_hash(addr); - struct inet6_ifaddr *ifp; - - hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; - if (ipv6_addr_equal(&ifp->addr, addr)) { - if (!dev || ifp->idev->dev == dev) - return true; - } - } - return false; -} /* Compares an address/prefix_len with addresses on device @dev. * If one is found it returns true. @@ -1859,20 +1879,18 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; bool ret = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); if (ret) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); @@ -1882,22 +1900,20 @@ EXPORT_SYMBOL(ipv6_chk_custom_prefix); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; int onlink; onlink = 0; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); return onlink; @@ -1907,11 +1923,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { + unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp, *result = NULL; - unsigned int hash = inet6_addr_hash(addr); - rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { + rcu_read_lock(); + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -1923,7 +1939,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add } } } - rcu_read_unlock_bh(); + rcu_read_unlock(); return result; } @@ -1942,7 +1958,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) if (ifpub) { in6_ifa_hold(ifpub); spin_unlock_bh(&ifp->lock); - ipv6_create_tempaddr(ifpub, ifp); + ipv6_create_tempaddr(ifpub, ifp, true); in6_ifa_put(ifpub); } else { spin_unlock_bh(&ifp->lock); @@ -1975,7 +1991,7 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) return err; } -void addrconf_dad_failure(struct inet6_ifaddr *ifp) +void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(ifp->idev->dev); @@ -1985,8 +2001,8 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) return; } - net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n", - ifp->idev->dev->name, &ifp->addr); + net_info_ratelimited("%s: IPv6 duplicate address %pI6c used by %pM detected!\n", + ifp->idev->dev->name, &ifp->addr, eth_hdr(skb)->h_source); spin_lock_bh(&ifp->lock); @@ -2025,7 +2041,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen, scope, flags, valid_lft, - preferred_lft); + preferred_lft, false, NULL); if (IS_ERR(ifp2)) goto lock_errdad; @@ -2321,24 +2337,24 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); + rcu_read_lock(); + fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true); if (!fn) goto out; - noflags |= RTF_CACHE; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != dev->ifindex) continue; if ((rt->rt6i_flags & flags) != flags) continue; if ((rt->rt6i_flags & noflags) != 0) continue; - dst_hold(&rt->dst); + if (!dst_hold_safe(&rt->dst)) + rt = NULL; break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -2442,7 +2458,7 @@ static void manage_tempaddrs(struct inet6_dev *idev, * no temporary address currently exists. */ read_unlock_bh(&idev->lock); - ipv6_create_tempaddr(ifp, NULL); + ipv6_create_tempaddr(ifp, NULL, false); } else { read_unlock_bh(&idev->lock); } @@ -2483,7 +2499,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, pinfo->prefix_len, addr_type&IPV6_ADDR_SCOPE_MASK, addr_flags, valid_lft, - prefered_lft); + prefered_lft, false, NULL); if (IS_ERR_OR_NULL(ifp)) return -1; @@ -2793,7 +2809,8 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx, const struct in6_addr *peer_pfx, unsigned int plen, __u32 ifa_flags, - __u32 prefered_lft, __u32 valid_lft) + __u32 prefered_lft, __u32 valid_lft, + struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; @@ -2852,7 +2869,7 @@ static int inet6_addr_add(struct net *net, int ifindex, } ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags, - valid_lft, prefered_lft); + valid_lft, prefered_lft, true, extack); if (!IS_ERR(ifp)) { if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { @@ -2937,7 +2954,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) rtnl_lock(); err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL, ireq.ifr6_prefixlen, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, NULL); rtnl_unlock(); return err; } @@ -2967,7 +2984,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifp = ipv6_add_addr(idev, addr, NULL, plen, scope, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, + true, NULL); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; @@ -3067,7 +3085,7 @@ void addrconf_add_linklocal(struct inet6_dev *idev, #endif ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); addrconf_dad_start(ifp); @@ -3297,7 +3315,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev, struct rt6_info *rt, *prev; rt = addrconf_dst_alloc(idev, &ifp->addr, false); - if (unlikely(IS_ERR(rt))) + if (IS_ERR(rt)) return PTR_ERR(rt); /* ifp->rt can be accessed outside of rtnl */ @@ -3404,7 +3422,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, /* restore routes for permanent addresses */ addrconf_permanent_addr(dev); - if (!addrconf_qdisc_ok(dev)) { + if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", dev->name); @@ -3419,7 +3437,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } } else if (event == NETDEV_CHANGE) { - if (!addrconf_qdisc_ok(dev)) { + if (!addrconf_link_ready(dev)) { /* device is still not ready. */ break; } @@ -3563,7 +3581,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; - struct list_head del_list; int _keep_addr; bool keep_addr; int state, i; @@ -3655,7 +3672,6 @@ restart: */ keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); - INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { struct rt6_info *rt = NULL; bool keep; @@ -3664,8 +3680,6 @@ restart: keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && !addr_is_local(&ifa->addr); - if (!keep) - list_move(&ifa->if_list, &del_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); @@ -3699,19 +3713,14 @@ restart: } write_lock_bh(&idev->lock); + if (!keep) { + list_del_rcu(&ifa->if_list); + in6_ifa_put(ifa); + } } write_unlock_bh(&idev->lock); - /* now clean up addresses to be removed */ - while (!list_empty(&del_list)) { - ifa = list_first_entry(&del_list, - struct inet6_ifaddr, if_list); - list_del(&ifa->if_list); - - in6_ifa_put(ifa); - } - /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4093,9 +4102,9 @@ struct if6_iter_state { static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) { - struct inet6_ifaddr *ifa = NULL; struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct inet6_ifaddr *ifa = NULL; int p = 0; /* initial bucket if pos is 0 */ @@ -4105,7 +4114,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) } for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket], + hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -4131,7 +4140,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) { + hlist_for_each_entry_continue_rcu(ifa, addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; state->offset++; @@ -4140,7 +4149,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, while (++state->bucket < IN6_ADDR_HSIZE) { state->offset = 0; - hlist_for_each_entry_rcu_bh(ifa, + hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -4153,9 +4162,9 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(rcu_bh) + __acquires(rcu) { - rcu_read_lock_bh(); + rcu_read_lock(); return if6_get_first(seq, *pos); } @@ -4169,9 +4178,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void if6_seq_stop(struct seq_file *seq, void *v) - __releases(rcu_bh) + __releases(rcu) { - rcu_read_unlock_bh(); + rcu_read_unlock(); } static int if6_seq_show(struct seq_file *seq, void *v) @@ -4240,12 +4249,12 @@ void if6_proc_exit(void) /* Check if address is a home address configured on any interface. */ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { - int ret = 0; + unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp = NULL; - unsigned int hash = inet6_addr_hash(addr); + int ret = 0; - rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { + rcu_read_lock(); + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -4254,7 +4263,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) break; } } - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } #endif @@ -4344,7 +4353,7 @@ restart: spin_lock(&ifpub->lock); ifpub->regen_count = 0; spin_unlock(&ifpub->lock); - ipv6_create_tempaddr(ifpub, ifp); + ipv6_create_tempaddr(ifpub, ifp, true); in6_ifa_put(ifpub); in6_ifa_put(ifp); goto restart; @@ -4580,7 +4589,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, */ return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, ifm->ifa_prefixlen, ifa_flags, - preferred_lft, valid_lft); + preferred_lft, valid_lft, extack); } if (nlh->nlmsg_flags & NLM_F_EXCL || @@ -4907,17 +4916,15 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) - goto errout; + return err; addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) { - err = -EINVAL; - goto errout; - } + if (!addr) + return -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = __dev_get_by_index(net, ifm->ifa_index); + dev = dev_get_by_index(net, ifm->ifa_index); ifa = ipv6_get_ifaddr(net, addr, dev, 1); if (!ifa) { @@ -4943,6 +4950,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, errout_ifa: in6_ifa_put(ifa); errout: + if (dev) + dev_put(dev); return err; } @@ -5050,6 +5059,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; + array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; } static inline size_t inet6_ifla6_size(void) @@ -5899,10 +5909,9 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) spin_lock(&ifa->lock); if (ifa->rt) { struct rt6_info *rt = ifa->rt; - struct fib6_table *table = rt->rt6i_table; int cpu; - read_lock(&table->tb6_lock); + rcu_read_lock(); addrconf_set_nopolicy(ifa->rt, val); if (rt->rt6i_pcpu) { for_each_possible_cpu(cpu) { @@ -5912,7 +5921,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) addrconf_set_nopolicy(*rtp, val); } } - read_unlock(&table->tb6_lock); + rcu_read_unlock(); } spin_unlock(&ifa->lock); } @@ -5978,6 +5987,7 @@ int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, } static int minus_one = -1; +static const int zero = 0; static const int one = 1; static const int two_five_five = 255; @@ -6349,6 +6359,15 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = addrconf_sysctl_disable_policy, }, { + .procname = "ndisc_tclass", + .data = &ipv6_devconf.ndisc_tclass, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&zero, + .extra2 = (void *)&two_five_five, + }, + { /* sentinel */ } }; @@ -6586,13 +6605,13 @@ int __init addrconf_init(void) __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0); __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0); __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, - inet6_dump_ifaddr, 0); + inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED); __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr, 0); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, 0); __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, - inet6_netconf_dump_devconf, 0); + inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED); ipv6_addr_label_rtnl_register(); @@ -6619,9 +6638,9 @@ void addrconf_cleanup(void) unregister_pernet_subsys(&addrconf_ops); ipv6_addr_label_cleanup(); - rtnl_lock(); + rtnl_af_unregister(&inet6_ops); - __rtnl_af_unregister(&inet6_ops); + rtnl_lock(); /* clean dev list */ for_each_netdev(&init_net, dev) { diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 9e3488d50b15..32b564dfd02a 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -88,7 +88,7 @@ int __ipv6_addr_type(const struct in6_addr *addr) EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); -static ATOMIC_NOTIFIER_HEAD(inet6addr_validator_chain); +static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { @@ -110,19 +110,20 @@ EXPORT_SYMBOL(inet6addr_notifier_call_chain); int register_inet6addr_validator_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_register(&inet6addr_validator_chain, nb); + return blocking_notifier_chain_register(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(register_inet6addr_validator_notifier); int unregister_inet6addr_validator_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&inet6addr_validator_chain, nb); + return blocking_notifier_chain_unregister(&inet6addr_validator_chain, + nb); } EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) { - return atomic_notifier_call_chain(&inet6addr_validator_chain, val, v); + return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v); } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f664871feca6..00e1f8ee08f8 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -19,7 +19,6 @@ #include <linux/if_addrlabel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> -#include <linux/refcount.h> #if 0 #define ADDRLABEL(x...) printk(x) @@ -31,30 +30,15 @@ * Policy Table */ struct ip6addrlbl_entry { - possible_net_t lbl_net; struct in6_addr prefix; int prefixlen; int ifindex; int addrtype; u32 label; struct hlist_node list; - refcount_t refcnt; struct rcu_head rcu; }; -static struct ip6addrlbl_table -{ - struct hlist_head head; - spinlock_t lock; - u32 seq; -} ip6addrlbl_table; - -static inline -struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl) -{ - return read_pnet(&lbl->lbl_net); -} - /* * Default policy table (RFC6724 + extensions) * @@ -126,36 +110,11 @@ static const __net_initconst struct ip6addrlbl_init_table } }; -/* Object management */ -static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) -{ - kfree(p); -} - -static void ip6addrlbl_free_rcu(struct rcu_head *h) -{ - ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu)); -} - -static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) -{ - return refcount_inc_not_zero(&p->refcnt); -} - -static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) -{ - if (refcount_dec_and_test(&p->refcnt)) - call_rcu(&p->rcu, ip6addrlbl_free_rcu); -} - /* Find label */ -static bool __ip6addrlbl_match(struct net *net, - const struct ip6addrlbl_entry *p, +static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p, const struct in6_addr *addr, int addrtype, int ifindex) { - if (!net_eq(ip6addrlbl_net(p), net)) - return false; if (p->ifindex && p->ifindex != ifindex) return false; if (p->addrtype && p->addrtype != addrtype) @@ -170,8 +129,9 @@ static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, int type, int ifindex) { struct ip6addrlbl_entry *p; - hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { - if (__ip6addrlbl_match(net, p, addr, type, ifindex)) + + hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { + if (__ip6addrlbl_match(p, addr, type, ifindex)) return p; } return NULL; @@ -197,8 +157,7 @@ u32 ipv6_addr_label(struct net *net, } /* allocate one entry */ -static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, - const struct in6_addr *prefix, +static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix, int prefixlen, int ifindex, u32 label) { @@ -237,24 +196,22 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); - write_pnet(&newp->lbl_net, net); - refcount_set(&newp->refcnt, 1); return newp; } /* add a label */ -static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) +static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, + int replace) { - struct hlist_node *n; struct ip6addrlbl_entry *last = NULL, *p = NULL; + struct hlist_node *n; int ret = 0; ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, replace); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == newp->prefixlen && - net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && p->ifindex == newp->ifindex && ipv6_addr_equal(&p->prefix, &newp->prefix)) { if (!replace) { @@ -262,7 +219,7 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) goto out; } hlist_replace_rcu(&p->list, &newp->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); goto out; } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || (p->prefixlen < newp->prefixlen)) { @@ -274,10 +231,10 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) if (last) hlist_add_behind_rcu(&newp->list, &last->list); else - hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); + hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head); out: if (!ret) - ip6addrlbl_table.seq++; + net->ipv6.ip6addrlbl_table.seq++; return ret; } @@ -293,14 +250,14 @@ static int ip6addrlbl_add(struct net *net, __func__, prefix, prefixlen, ifindex, (unsigned int)label, replace); - newp = ip6addrlbl_alloc(net, prefix, prefixlen, ifindex, label); + newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label); if (IS_ERR(newp)) return PTR_ERR(newp); - spin_lock(&ip6addrlbl_table.lock); - ret = __ip6addrlbl_add(newp, replace); - spin_unlock(&ip6addrlbl_table.lock); + spin_lock(&net->ipv6.ip6addrlbl_table.lock); + ret = __ip6addrlbl_add(net, newp, replace); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); if (ret) - ip6addrlbl_free(newp); + kfree(newp); return ret; } @@ -316,13 +273,12 @@ static int __ip6addrlbl_del(struct net *net, ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && - net_eq(ip6addrlbl_net(p), net) && p->ifindex == ifindex && ipv6_addr_equal(&p->prefix, prefix)) { hlist_del_rcu(&p->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); ret = 0; break; } @@ -341,9 +297,9 @@ static int ip6addrlbl_del(struct net *net, __func__, prefix, prefixlen, ifindex); ipv6_addr_prefix(&prefix_buf, prefix, prefixlen); - spin_lock(&ip6addrlbl_table.lock); + spin_lock(&net->ipv6.ip6addrlbl_table.lock); ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex); - spin_unlock(&ip6addrlbl_table.lock); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); return ret; } @@ -355,6 +311,9 @@ static int __net_init ip6addrlbl_net_init(struct net *net) ADDRLABEL(KERN_DEBUG "%s\n", __func__); + spin_lock_init(&net->ipv6.ip6addrlbl_table.lock); + INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); + for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { int ret = ip6addrlbl_add(net, ip6addrlbl_init_table[i].prefix, @@ -374,14 +333,12 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) struct hlist_node *n; /* Remove all labels belonging to the exiting net */ - spin_lock(&ip6addrlbl_table.lock); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { - if (net_eq(ip6addrlbl_net(p), net)) { - hlist_del_rcu(&p->list); - ip6addrlbl_put(p); - } + spin_lock(&net->ipv6.ip6addrlbl_table.lock); + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { + hlist_del_rcu(&p->list); + kfree_rcu(p, rcu); } - spin_unlock(&ip6addrlbl_table.lock); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); } static struct pernet_operations ipv6_addr_label_ops = { @@ -391,8 +348,6 @@ static struct pernet_operations ipv6_addr_label_ops = { int __init ipv6_addr_label_init(void) { - spin_lock_init(&ip6addrlbl_table.lock); - return register_pernet_subsys(&ipv6_addr_label_ops); } @@ -511,11 +466,10 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) int err; rcu_read_lock(); - hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { - if (idx >= s_idx && - net_eq(ip6addrlbl_net(p), net)) { + hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { + if (idx >= s_idx) { err = ip6addrlbl_fill(skb, p, - ip6addrlbl_table.seq, + net->ipv6.ip6addrlbl_table.seq, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDRLABEL, @@ -568,38 +522,28 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, return -EINVAL; addr = nla_data(tb[IFAL_ADDRESS]); - rcu_read_lock(); - p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - if (p && !ip6addrlbl_hold(p)) - p = NULL; - lseq = ip6addrlbl_table.seq; - rcu_read_unlock(); - - if (!p) { - err = -ESRCH; - goto out; - } - skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); - if (!skb) { - ip6addrlbl_put(p); + if (!skb) return -ENOBUFS; - } - err = ip6addrlbl_fill(skb, p, lseq, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - RTM_NEWADDRLABEL, 0); + err = -ESRCH; - ip6addrlbl_put(p); + rcu_read_lock(); + p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); + lseq = net->ipv6.ip6addrlbl_table.seq; + if (p) + err = ip6addrlbl_fill(skb, p, lseq, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, + RTM_NEWADDRLABEL, 0); + rcu_read_unlock(); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - goto out; + } else { + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } - - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); -out: return err; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fe5262fd6aa5..c26f71234b9c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -810,6 +810,10 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.idgen_retries = 3; net->ipv6.sysctl.idgen_delay = 1 * HZ; net->ipv6.sysctl.flowlabel_state_ranges = 0; + net->ipv6.sysctl.max_dst_opts_cnt = IP6_DEFAULT_MAX_DST_OPTS_CNT; + net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT; + net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN; + net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 3bd9d806b506..78c974391567 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -271,6 +271,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) case NEXTHDR_DEST: if (dir == XFRM_POLICY_OUT) ipv6_rearrange_destopt(iph, exthdr.opth); + /* fall through */ case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { net_dbg_ratelimited("overrun %sopts\n", diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c04d995df37c..a902ff8f59be 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -483,8 +483,8 @@ static inline int esp_remove_trailer(struct sk_buff *skb) goto out; } - if (skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2)) - BUG(); + ret = skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2); + BUG_ON(ret); ret = -EINVAL; padlen = nexthdr[0]; @@ -559,14 +559,14 @@ static void esp_input_restore_header(struct sk_buff *skb) static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) { struct xfrm_state *x = xfrm_input_state(skb); - struct ip_esp_hdr *esph = (struct ip_esp_hdr *)skb->data; /* For ESN we move the header forward by 4 bytes to * accomodate the high bits. We will move it back after * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = skb_push(skb, 4); + struct ip_esp_hdr *esph = skb_push(skb, 4); + *seqhi = esph->spi; esph->spi = esph->seq_no; esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 95516138e861..83bd75713535 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -74,8 +74,20 @@ struct tlvtype_proc { /* An unknown option is detected, decide what to do */ -static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) +static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff, + bool disallow_unknowns) { + if (disallow_unknowns) { + /* If unknown TLVs are disallowed by configuration + * then always silently drop packet. Note this also + * means no ICMP parameter problem is sent which + * could be a good property to mitigate a reflection DOS + * attack. + */ + + goto drop; + } + switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) { case 0: /* ignore */ return true; @@ -89,25 +101,36 @@ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; + /* fall through */ case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff); return false; } +drop: kfree_skb(skb); return false; } /* Parse tlv encoded option header (hop-by-hop or destination) */ -static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) +static bool ip6_parse_tlv(const struct tlvtype_proc *procs, + struct sk_buff *skb, + int max_count) { - const struct tlvtype_proc *curr; + int len = (skb_transport_header(skb)[1] + 1) << 3; const unsigned char *nh = skb_network_header(skb); int off = skb_network_header_len(skb); - int len = (skb_transport_header(skb)[1] + 1) << 3; + const struct tlvtype_proc *curr; + bool disallow_unknowns = false; + int tlv_count = 0; int padlen = 0; + if (unlikely(max_count < 0)) { + disallow_unknowns = true; + max_count = -max_count; + } + if (skb_transport_offset(skb) + len > skb_headlen(skb)) goto bad; @@ -148,6 +171,11 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) default: /* Other TLV code so scan list */ if (optlen > len) goto bad; + + tlv_count++; + if (tlv_count > max_count) + goto bad; + for (curr = procs; curr->type >= 0; curr++) { if (curr->type == nh[off]) { /* type specific length/alignment @@ -158,10 +186,10 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) break; } } - if (curr->type < 0) { - if (ip6_tlvopt_unknown(skb, off) == 0) - return false; - } + if (curr->type < 0 && + !ip6_tlvopt_unknown(skb, off, disallow_unknowns)) + return false; + padlen = 0; break; } @@ -186,7 +214,6 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) struct ipv6_destopt_hao *hao; struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); - struct in6_addr tmp_addr; int ret; if (opt->dsthao) { @@ -228,9 +255,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; - tmp_addr = ipv6h->saddr; - ipv6h->saddr = hao->addr; - hao->addr = tmp_addr; + swap(ipv6h->saddr, hao->addr); if (skb->tstamp == 0) __net_timestamp(skb); @@ -260,23 +285,31 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) __u16 dstbuf; #endif struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(skb->dev); + int extlen; if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); +fail_and_free: kfree_skb(skb); return -1; } + extlen = (skb_transport_header(skb)[1] + 1) << 3; + if (extlen > net->ipv6.sysctl.max_dst_opts_len) + goto fail_and_free; + opt->lastopt = opt->dst1 = skb_network_header_len(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) dstbuf = opt->dst1; #endif - if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { - skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; + if (ip6_parse_tlv(tlvprocdestopt_lst, skb, + init_net.ipv6.sysctl.max_dst_opts_cnt)) { + skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) opt->nhoff = dstbuf; @@ -805,6 +838,8 @@ static const struct tlvtype_proc tlvprochopopt_lst[] = { int ipv6_parse_hopopts(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); + struct net *net = dev_net(skb->dev); + int extlen; /* * skb_network_header(skb) is equal to skb->data, and @@ -815,13 +850,19 @@ int ipv6_parse_hopopts(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) || !pskb_may_pull(skb, (sizeof(struct ipv6hdr) + ((skb_transport_header(skb)[1] + 1) << 3)))) { +fail_and_free: kfree_skb(skb); return -1; } + extlen = (skb_transport_header(skb)[1] + 1) << 3; + if (extlen > net->ipv6.sysctl.max_hbh_opts_len) + goto fail_and_free; + opt->flags |= IP6SKB_HOPBYHOP; - if (ip6_parse_tlv(tlvprochopopt_lst, skb)) { - skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; + if (ip6_parse_tlv(tlvprochopopt_lst, skb, + init_net.ipv6.sysctl.max_hbh_opts_cnt)) { + skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); return 1; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 305e2ed730bf..11025f8d124b 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -99,7 +99,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, break; hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) - hdrlen = (hp->hdrlen+2)<<2; + hdrlen = ipv6_authlen(hp); else hdrlen = ipv6_optlen(hp); @@ -187,7 +187,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, { unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; - unsigned int len; bool found; if (fragoff) @@ -204,7 +203,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, start = *offset + sizeof(struct ipv6hdr); nexthdr = ip6->nexthdr; } - len = skb->len - start; do { struct ipv6_opt_hdr _hdr, *hp; @@ -273,7 +271,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, if (!found) { nexthdr = hp->nexthdr; - len -= hdrlen; start += hdrlen; } } while (!found); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 5acb54405b10..6ae5dd3f4d0d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -250,16 +250,15 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset) return (*op & 0xC0) == 0x80; } -int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, - struct icmp6hdr *thdr, int len) +void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, + struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; - int err = 0; skb = skb_peek(&sk->sk_write_queue); if (!skb) - goto out; + return; icmp6h = icmp6_hdr(skb); memcpy(icmp6h, thdr, sizeof(struct icmp6hdr)); @@ -287,8 +286,6 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, tmp_csum); } ip6_push_pending_frames(sk); -out: - return err; } struct icmpv6_msg { @@ -438,7 +435,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - int err = 0; u32 mark = IP6_REPLY_MARK(net, skb->mark); if ((u8 *)hdr < skb->head || @@ -575,17 +571,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, rcu_read_lock(); idev = __in6_dev_get(skb->dev); - err = ip6_append_data(sk, icmpv6_getfrag, &msg, - len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), - &ipc6, &fl6, (struct rt6_info *)dst, - MSG_DONTWAIT, &sockc_unused); - if (err) { + if (ip6_append_data(sk, icmpv6_getfrag, &msg, + len + sizeof(struct icmp6hdr), + sizeof(struct icmp6hdr), + &ipc6, &fl6, (struct rt6_info *)dst, + MSG_DONTWAIT, &sockc_unused)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, - len + sizeof(struct icmp6hdr)); + icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + len + sizeof(struct icmp6hdr)); } rcu_read_unlock(); out_dst_release: @@ -682,7 +677,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct icmpv6_msg msg; struct dst_entry *dst; struct ipcm6_cookie ipc6; - int err = 0; u32 mark = IP6_REPLY_MARK(net, skb->mark); struct sockcm_cookie sockc_unused = {0}; @@ -719,8 +713,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(net, sk, &dst, &fl6); - if (err) + if (ip6_dst_lookup(net, sk, &dst, &fl6)) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) @@ -737,17 +730,16 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipc6.dontfrag = np->dontfrag; ipc6.opt = NULL; - err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), &ipc6, &fl6, - (struct rt6_info *)dst, MSG_DONTWAIT, - &sockc_unused); - - if (err) { + if (ip6_append_data(sk, icmpv6_getfrag, &msg, + skb->len + sizeof(struct icmp6hdr), + sizeof(struct icmp6hdr), &ipc6, &fl6, + (struct rt6_info *)dst, MSG_DONTWAIT, + &sockc_unused)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, - skb->len + sizeof(struct icmp6hdr)); + icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + skb->len + sizeof(struct icmp6hdr)); } dst_release(dst); out: @@ -872,10 +864,8 @@ static int icmpv6_rcv(struct sk_buff *skb) goto discard_it; hdr = icmp6_hdr(skb); - /* - * Drop through to notify - */ - + /* to notify */ + /* fall through */ case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index e0170f62bc39..3c7a11b62334 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -55,17 +55,6 @@ struct ila_identifier { }; }; -enum { - ILA_ATYPE_IID = 0, - ILA_ATYPE_LUID, - ILA_ATYPE_VIRT_V4, - ILA_ATYPE_VIRT_UNI_V6, - ILA_ATYPE_VIRT_MULTI_V6, - ILA_ATYPE_RSVD_1, - ILA_ATYPE_RSVD_2, - ILA_ATYPE_RSVD_3, -}; - #define CSUM_NEUTRAL_FLAG htonl(0x10000000) struct ila_addr { @@ -93,6 +82,7 @@ struct ila_params { struct ila_locator locator_match; __wsum csum_diff; u8 csum_mode; + u8 ident_type; }; static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index aba0998ddbfb..8c88ecf29b93 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -13,30 +13,37 @@ #include <uapi/linux/ila.h> #include "ila.h" -static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) +void ila_init_saved_csum(struct ila_params *p) { - struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); + if (!p->locator_match.v64) + return; + p->csum_diff = compute_csum_diff8( + (__be32 *)&p->locator, + (__be32 *)&p->locator_match); +} + +static __wsum get_csum_diff_iaddr(struct ila_addr *iaddr, struct ila_params *p) +{ if (p->locator_match.v64) return p->csum_diff; else - return compute_csum_diff8((__be32 *)&iaddr->loc, - (__be32 *)&p->locator); + return compute_csum_diff8((__be32 *)&p->locator, + (__be32 *)&iaddr->loc); } -static void ila_csum_do_neutral(struct ila_addr *iaddr, - struct ila_params *p) +static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) +{ + return get_csum_diff_iaddr(ila_a2i(&ip6h->daddr), p); +} + +static void ila_csum_do_neutral_fmt(struct ila_addr *iaddr, + struct ila_params *p) { __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff, fval; - /* Check if checksum adjust value has been cached */ - if (p->locator_match.v64) { - diff = p->csum_diff; - } else { - diff = compute_csum_diff8((__be32 *)&p->locator, - (__be32 *)iaddr); - } + diff = get_csum_diff_iaddr(iaddr, p); fval = (__force __wsum)(ila_csum_neutral_set(iaddr->ident) ? CSUM_NEUTRAL_FLAG : ~CSUM_NEUTRAL_FLAG); @@ -53,13 +60,23 @@ static void ila_csum_do_neutral(struct ila_addr *iaddr, iaddr->ident.csum_neutral ^= 1; } -static void ila_csum_adjust_transport(struct sk_buff *skb, +static void ila_csum_do_neutral_nofmt(struct ila_addr *iaddr, struct ila_params *p) { + __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); + + diff = get_csum_diff_iaddr(iaddr, p); + + *adjust = ~csum_fold(csum_add(diff, csum_unfold(*adjust))); +} + +static void ila_csum_adjust_transport(struct sk_buff *skb, + struct ila_params *p) +{ size_t nhoff = sizeof(struct ipv6hdr); + struct ipv6hdr *ip6h = ipv6_hdr(skb); + __wsum diff; switch (ip6h->nexthdr) { case NEXTHDR_TCP: @@ -98,52 +115,45 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, } break; } - - /* Now change destination address */ - iaddr->loc = p->locator; } void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, - bool set_csum_neutral) + bool sir2ila) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); - /* First deal with the transport checksum */ - if (ila_csum_neutral_set(iaddr->ident)) { - /* C-bit is set in the locator indicating that this - * is a locator being translated to a SIR address. - * Perform (receiver) checksum-neutral translation. - */ - if (!set_csum_neutral) - ila_csum_do_neutral(iaddr, p); - } else { - switch (p->csum_mode) { - case ILA_CSUM_ADJUST_TRANSPORT: - ila_csum_adjust_transport(skb, p); - break; - case ILA_CSUM_NEUTRAL_MAP: - ila_csum_do_neutral(iaddr, p); - break; - case ILA_CSUM_NO_ACTION: + switch (p->csum_mode) { + case ILA_CSUM_ADJUST_TRANSPORT: + ila_csum_adjust_transport(skb, p); + break; + case ILA_CSUM_NEUTRAL_MAP: + if (sir2ila) { + if (WARN_ON(ila_csum_neutral_set(iaddr->ident))) { + /* Checksum flag should never be + * set in a formatted SIR address. + */ + break; + } + } else if (!ila_csum_neutral_set(iaddr->ident)) { + /* ILA to SIR translation and C-bit isn't + * set so we're good. + */ break; } + ila_csum_do_neutral_fmt(iaddr, p); + break; + case ILA_CSUM_NEUTRAL_MAP_AUTO: + ila_csum_do_neutral_nofmt(iaddr, p); + break; + case ILA_CSUM_NO_ACTION: + break; } /* Now change destination address */ iaddr->loc = p->locator; } -void ila_init_saved_csum(struct ila_params *p) -{ - if (!p->locator_match.v64) - return; - - p->csum_diff = compute_csum_diff8( - (__be32 *)&p->locator, - (__be32 *)&p->locator_match); -} - static int __init ila_init(void) { int ret; diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 696281b4bca2..3d56a2fb6f86 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -20,6 +20,7 @@ struct ila_lwt { struct ila_params p; struct dst_cache dst_cache; u32 connected : 1; + u32 lwt_output : 1; }; static inline struct ila_lwt *ila_lwt_lwtunnel( @@ -45,8 +46,10 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(orig_dst->lwtstate), - true); + if (ilwt->lwt_output) + ila_update_ipv6_locator(skb, + ila_params_lwtunnel(orig_dst->lwtstate), + true); if (rt->rt6i_flags & (RTF_GATEWAY | RTF_CACHE)) { /* Already have a next hop address in route, no need for @@ -98,11 +101,15 @@ drop: static int ila_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); + struct ila_lwt *ilwt = ila_lwt_lwtunnel(dst->lwtstate); if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false); + if (!ilwt->lwt_output) + ila_update_ipv6_locator(skb, + ila_params_lwtunnel(dst->lwtstate), + false); return dst->lwtstate->orig_input(skb); @@ -114,6 +121,8 @@ drop: static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, + [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, + [ILA_ATTR_HOOK_TYPE] = { .type = NLA_U8, }, }; static int ila_build_state(struct nlattr *nla, @@ -127,33 +136,84 @@ static int ila_build_state(struct nlattr *nla, struct lwtunnel_state *newts; const struct fib6_config *cfg6 = cfg; struct ila_addr *iaddr; + u8 ident_type = ILA_ATYPE_USE_FORMAT; + u8 hook_type = ILA_HOOK_ROUTE_OUTPUT; + u8 csum_mode = ILA_CSUM_NO_ACTION; + bool lwt_output = true; + u8 eff_ident_type; int ret; if (family != AF_INET6) return -EINVAL; - if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) { - /* Need to have full locator and at least type field - * included in destination - */ + ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); + if (ret < 0) + return ret; + + if (!tb[ILA_ATTR_LOCATOR]) return -EINVAL; - } iaddr = (struct ila_addr *)&cfg6->fc_dst; - if (!ila_addr_is_ila(iaddr) || ila_csum_neutral_set(iaddr->ident)) { - /* Don't allow translation for a non-ILA address or checksum - * neutral flag to be set. + if (tb[ILA_ATTR_IDENT_TYPE]) + ident_type = nla_get_u8(tb[ILA_ATTR_IDENT_TYPE]); + + if (ident_type == ILA_ATYPE_USE_FORMAT) { + /* Infer identifier type from type field in formatted + * identifier. */ + + if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) { + /* Need to have full locator and at least type field + * included in destination + */ + return -EINVAL; + } + + eff_ident_type = iaddr->ident.type; + } else { + eff_ident_type = ident_type; + } + + switch (eff_ident_type) { + case ILA_ATYPE_IID: + /* Don't allow ILA for IID type */ + return -EINVAL; + case ILA_ATYPE_LUID: + break; + case ILA_ATYPE_VIRT_V4: + case ILA_ATYPE_VIRT_UNI_V6: + case ILA_ATYPE_VIRT_MULTI_V6: + case ILA_ATYPE_NONLOCAL_ADDR: + /* These ILA formats are not supported yet. */ + default: return -EINVAL; } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); - if (ret < 0) - return ret; + if (tb[ILA_ATTR_HOOK_TYPE]) + hook_type = nla_get_u8(tb[ILA_ATTR_HOOK_TYPE]); + + switch (hook_type) { + case ILA_HOOK_ROUTE_OUTPUT: + lwt_output = true; + break; + case ILA_HOOK_ROUTE_INPUT: + lwt_output = false; + break; + default: + return -EINVAL; + } - if (!tb[ILA_ATTR_LOCATOR]) + if (tb[ILA_ATTR_CSUM_MODE]) + csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); + + if (csum_mode == ILA_CSUM_NEUTRAL_MAP && + ila_csum_neutral_set(iaddr->ident)) { + /* Don't allow translation if checksum neutral bit is + * configured and it's set in the SIR address. + */ return -EINVAL; + } newts = lwtunnel_state_alloc(sizeof(*ilwt)); if (!newts) @@ -166,19 +226,18 @@ static int ila_build_state(struct nlattr *nla, return ret; } + ilwt->lwt_output = !!lwt_output; + p = ila_params_lwtunnel(newts); + p->csum_mode = csum_mode; + p->ident_type = ident_type; p->locator.v64 = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]); /* Precompute checksum difference for translation since we * know both the old locator and the new one. */ p->locator_match = iaddr->loc; - p->csum_diff = compute_csum_diff8( - (__be32 *)&p->locator_match, (__be32 *)&p->locator); - - if (tb[ILA_ATTR_CSUM_MODE]) - p->csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); ila_init_saved_csum(p); @@ -203,13 +262,23 @@ static int ila_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct ila_params *p = ila_params_lwtunnel(lwtstate); + struct ila_lwt *ilwt = ila_lwt_lwtunnel(lwtstate); if (nla_put_u64_64bit(skb, ILA_ATTR_LOCATOR, (__force u64)p->locator.v64, ILA_ATTR_PAD)) goto nla_put_failure; + if (nla_put_u8(skb, ILA_ATTR_CSUM_MODE, (__force u8)p->csum_mode)) goto nla_put_failure; + if (nla_put_u8(skb, ILA_ATTR_IDENT_TYPE, (__force u8)p->ident_type)) + goto nla_put_failure; + + if (nla_put_u8(skb, ILA_ATTR_HOOK_TYPE, + ilwt->lwt_output ? ILA_HOOK_ROUTE_OUTPUT : + ILA_HOOK_ROUTE_INPUT)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -220,6 +289,8 @@ static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size_64bit(sizeof(u64)) + /* ILA_ATTR_LOCATOR */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_CSUM_MODE */ + nla_total_size(sizeof(u8)) + /* ILA_ATTR_IDENT_TYPE */ + nla_total_size(sizeof(u8)) + /* ILA_ATTR_HOOK_TYPE */ 0; } diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 3123b9de91b5..6eb5e68f112a 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -121,6 +121,7 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, + [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, }; static int parse_nl_config(struct genl_info *info, @@ -138,6 +139,14 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[ILA_ATTR_CSUM_MODE]) xp->ip.csum_mode = nla_get_u8(info->attrs[ILA_ATTR_CSUM_MODE]); + else + xp->ip.csum_mode = ILA_CSUM_NO_ACTION; + + if (info->attrs[ILA_ATTR_IDENT_TYPE]) + xp->ip.ident_type = nla_get_u8( + info->attrs[ILA_ATTR_IDENT_TYPE]); + else + xp->ip.ident_type = ILA_ATYPE_USE_FORMAT; if (info->attrs[ILA_ATTR_IFINDEX]) xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); @@ -198,7 +207,7 @@ static void ila_free_cb(void *ptr, void *arg) } } -static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral); +static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila); static unsigned int ila_nf_input(void *priv, @@ -396,7 +405,8 @@ static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) (__force u64)ila->xp.ip.locator_match.v64, ILA_ATTR_PAD) || nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->xp.ifindex) || - nla_put_u32(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode)) + nla_put_u8(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode) || + nla_put_u8(msg, ILA_ATTR_IDENT_TYPE, ila->xp.ip.ident_type)) return -1; return 0; @@ -607,7 +617,7 @@ static struct pernet_operations ila_net_ops = { .size = sizeof(struct ila_net), }; -static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral) +static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) { struct ila_map *ila; struct ipv6hdr *ip6h = ipv6_hdr(skb); @@ -617,16 +627,16 @@ static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral) /* Assumes skb contains a valid IPv6 header that is pulled */ - if (!ila_addr_is_ila(iaddr)) { - /* Type indicates this is not an ILA address */ - return 0; - } + /* No check here that ILA type in the mapping matches what is in the + * address. We assume that whatever sender gaves us can be translated. + * The checksum mode however is relevant. + */ rcu_read_lock(); ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan); if (ila) - ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral); + ila_update_ipv6_locator(skb, &ila->xp.ip, sir2ila); rcu_read_unlock(); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e5308d7cbd75..2e2804f5823e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -38,14 +38,6 @@ #include <net/ip6_fib.h> #include <net/ip6_route.h> -#define RT6_DEBUG 2 - -#if RT6_DEBUG >= 3 -#define RT6_TRACE(x...) pr_debug(x) -#else -#define RT6_TRACE(x...) do { ; } while (0) -#endif - static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { @@ -62,9 +54,12 @@ struct fib6_cleaner { #define FWS_INIT FWS_L #endif -static void fib6_prune_clones(struct net *net, struct fib6_node *fn); -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); -static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); +static struct fib6_node *fib6_repair_tree(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); @@ -110,6 +105,20 @@ enum { FIB6_NO_SERNUM_CHANGE = 0, }; +void fib6_update_sernum(struct rt6_info *rt) +{ + struct fib6_table *table = rt->rt6i_table; + struct net *net = dev_net(rt->dst.dev); + struct fib6_node *fn; + + spin_lock_bh(&table->tb6_lock); + fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&table->tb6_lock)); + if (fn) + fn->fn_sernum = fib6_new_sernum(net); + spin_unlock_bh(&table->tb6_lock); +} + /* * Auxiliary address test functions for the radix tree. * @@ -140,18 +149,21 @@ static __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } -static struct fib6_node *node_alloc(void) +static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); + if (fn) + net->ipv6.rt6_stats->fib_nodes++; return fn; } -static void node_free_immediate(struct fib6_node *fn) +static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); + net->ipv6.rt6_stats->fib_nodes--; } static void node_free_rcu(struct rcu_head *head) @@ -161,9 +173,10 @@ static void node_free_rcu(struct rcu_head *head) kmem_cache_free(fib6_node_kmem, fn); } -static void node_free(struct fib6_node *fn) +static void node_free(struct net *net, struct fib6_node *fn) { call_rcu(&fn->rcu, node_free_rcu); + net->ipv6.rt6_stats->fib_nodes--; } void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) @@ -185,9 +198,6 @@ void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) *ppcpu_rt = NULL; } } - - free_percpu(non_pcpu_rt->rt6i_pcpu); - non_pcpu_rt->rt6i_pcpu = NULL; } EXPORT_SYMBOL_GPL(rt6_free_pcpu); @@ -205,8 +215,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb) * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ - rwlock_init(&tb->tb6_lock); - + spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* @@ -225,7 +234,8 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; - table->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(table->tb6_root.leaf, + net->ipv6.ip6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); } @@ -322,11 +332,8 @@ unsigned int fib6_tables_seq_read(struct net *net) struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; - hlist_for_each_entry_rcu(tb, head, tb6_hlist) { - read_lock_bh(&tb->tb6_lock); + hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += tb->fib_seq; - read_unlock_bh(&tb->tb6_lock); - } } rcu_read_unlock(); @@ -346,9 +353,11 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, static int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, - struct rt6_info *rt) + struct rt6_info *rt, + struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { + .info.extack = extack, .rt = rt, }; @@ -372,7 +381,7 @@ static int fib6_node_dump(struct fib6_walker *w) { struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) + for_each_fib6_walker_rt(w) fib6_rt_dump(rt, w->args); w->leaf = NULL; return 0; @@ -382,9 +391,9 @@ static void fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { w->root = &tb->tb6_root; - read_lock_bh(&tb->tb6_lock); + spin_lock_bh(&tb->tb6_lock); fib6_walk(net, w); - read_unlock_bh(&tb->tb6_lock); + spin_unlock_bh(&tb->tb6_lock); } /* Called with rcu_read_lock() */ @@ -421,7 +430,7 @@ static int fib6_dump_node(struct fib6_walker *w) int res; struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args); if (res < 0) { /* Frame is full, suspend walking */ @@ -480,9 +489,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, w->count = 0; w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = w->root->fn_sernum; @@ -497,9 +506,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, } else w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; @@ -580,11 +589,13 @@ out: * node. */ -static struct fib6_node *fib6_add_1(struct fib6_node *root, - struct in6_addr *addr, int plen, - int offset, int allow_create, - int replace_required, int sernum, - struct netlink_ext_ack *extack) +static struct fib6_node *fib6_add_1(struct net *net, + struct fib6_table *table, + struct fib6_node *root, + struct in6_addr *addr, int plen, + int offset, int allow_create, + int replace_required, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -599,7 +610,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, fn = root; do { - key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match @@ -625,12 +638,10 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { - rt6_release(fn->leaf); - fn->leaf = NULL; + RCU_INIT_POINTER(fn->leaf, NULL); + rt6_release(leaf); } - fn->fn_sernum = sernum; - return fn; } @@ -639,10 +650,13 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, */ /* Try to walk down on tree. */ - fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right : fn->left; + fn = dir ? + rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)) : + rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { @@ -668,19 +682,17 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, * Create new leaf node without children. */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - - ln->parent = pn; - ln->fn_sernum = sernum; + RCU_INIT_POINTER(ln->parent, pn); if (dir) - pn->right = ln; + rcu_assign_pointer(pn->right, ln); else - pn->left = ln; + rcu_assign_pointer(pn->left, ln); return ln; @@ -694,7 +706,8 @@ insert_above: * and the current */ - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. @@ -710,14 +723,14 @@ insert_above: * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { - in = node_alloc(); - ln = node_alloc(); + in = node_alloc(net); + ln = node_alloc(net); if (!in || !ln) { if (in) - node_free_immediate(in); + node_free_immediate(net, in); if (ln) - node_free_immediate(ln); + node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } @@ -731,31 +744,28 @@ insert_above: in->fn_bit = bit; - in->parent = pn; + RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; - atomic_inc(&in->leaf->rt6i_ref); - - in->fn_sernum = sernum; + atomic_inc(&rcu_dereference_protected(in->leaf, + lockdep_is_held(&table->tb6_lock))->rt6i_ref); /* update parent pointer */ if (dir) - pn->right = in; + rcu_assign_pointer(pn->right, in); else - pn->left = in; + rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; - ln->parent = in; - fn->parent = in; - - ln->fn_sernum = sernum; + RCU_INIT_POINTER(ln->parent, in); + rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { - in->right = ln; - in->left = fn; + rcu_assign_pointer(in->right, ln); + rcu_assign_pointer(in->left, fn); } else { - in->left = ln; - in->right = fn; + rcu_assign_pointer(in->left, ln); + rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ @@ -765,28 +775,26 @@ insert_above: * (old node)[fn] NULL */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - ln->parent = pn; - - ln->fn_sernum = sernum; - - if (dir) - pn->right = ln; - else - pn->left = ln; + RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) - ln->right = fn; + RCU_INIT_POINTER(ln->right, fn); else - ln->left = fn; + RCU_INIT_POINTER(ln->left, fn); + + rcu_assign_pointer(fn->parent, ln); - fn->parent = ln; + if (dir) + rcu_assign_pointer(pn->right, ln); + else + rcu_assign_pointer(pn->left, ln); } return ln; } @@ -832,6 +840,8 @@ static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, struct net *net) { + struct fib6_table *table = rt->rt6i_table; + if (atomic_read(&rt->rt6i_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, @@ -840,12 +850,17 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * to still alive ones. */ while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_leaf; + if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { + new_leaf = fib6_find_prefix(net, table, fn); + atomic_inc(&new_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_leaf); rt6_release(rt); } - fn = fn->parent; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); } } } @@ -855,11 +870,14 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc) + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack) { + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); struct rt6_info *iter = NULL; - struct rt6_info **ins; - struct rt6_info **fallback_ins = NULL; + struct rt6_info __rcu **ins; + struct rt6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -874,7 +892,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, ins = &fn->leaf; - for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) { + for (iter = leaf; iter; + iter = rcu_dereference_protected(iter->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock))) { /* * Search for duplicates */ @@ -936,7 +956,8 @@ next_iter: if (fallback_ins && !found) { /* No ECMP-able route found, replace first non-ECMP one */ ins = fallback_ins; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); found++; } @@ -950,7 +971,7 @@ next_iter: struct rt6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ - sibling = fn->leaf; + sibling = leaf; while (sibling) { if (sibling->rt6i_metric == rt->rt6i_metric && rt6_qualify_for_ecmp(sibling)) { @@ -958,7 +979,8 @@ next_iter: &sibling->rt6i_siblings); break; } - sibling = sibling->dst.rt6_next; + sibling = rcu_dereference_protected(sibling->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings @@ -987,12 +1009,12 @@ add: if (err) return err; - rt->dst.rt6_next = iter; - *ins = rt; - rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(rt->dst.rt6_next, iter); atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, - rt); + rt, extack); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; @@ -1016,12 +1038,12 @@ add: if (err) return err; - *ins = rt; + atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); rt->dst.rt6_next = iter->dst.rt6_next; - atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, - rt); + rt, extack); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { @@ -1031,14 +1053,15 @@ add: nsiblings = iter->rt6i_nsiblings; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->dst.rt6_next; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); while (iter) { if (iter->rt6i_metric > rt->rt6i_metric) break; @@ -1046,14 +1069,16 @@ add: *ins = iter->dst.rt6_next; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->dst.rt6_next; } - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } WARN_ON(nsiblings != 0); } @@ -1077,16 +1102,33 @@ void fib6_force_start_gc(struct net *net) jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } +static void fib6_update_sernum_upto_root(struct rt6_info *rt, + int sernum) +{ + struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); + + /* paired with smp_rmb() in rt6_get_cookie_safe() */ + smp_wmb(); + while (fn) { + fn->fn_sernum = sernum; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); + } +} + /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees + * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc, struct netlink_ext_ack *extack) { + struct fib6_table *table = rt->rt6i_table; struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; int allow_create = 1; @@ -1095,6 +1137,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) return -EINVAL; + if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE)) + return -EINVAL; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) @@ -1105,9 +1149,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + fn = fib6_add_1(info->nl_net, table, root, + &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum, extack); + replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1120,7 +1165,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (rt->rt6i_src.plen) { struct fib6_node *sn; - if (!fn->subtree) { + if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* @@ -1134,42 +1179,40 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, */ /* Create subtree root node */ - sfn = node_alloc(); + sfn = node_alloc(info->nl_net); if (!sfn) goto failure; - sfn->leaf = info->nl_net->ipv6.ip6_null_entry; atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); + rcu_assign_pointer(sfn->leaf, + info->nl_net->ipv6.ip6_null_entry); sfn->fn_flags = RTN_ROOT; - sfn->fn_sernum = sernum; /* Now add the first leaf node to new subtree */ - sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, sfn, + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ - node_free_immediate(sfn); + node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ - sfn->parent = fn; - fn->subtree = sfn; + rcu_assign_pointer(sfn->parent, fn); + rcu_assign_pointer(fn->subtree, sfn); } else { - sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); @@ -1177,19 +1220,18 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } } - if (!fn->leaf) { - fn->leaf = rt; + if (!rcu_access_pointer(fn->leaf)) { atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(fn->leaf, rt); } fn = sn; } #endif - err = fib6_add_rt2node(fn, rt, info, mxc); + err = fib6_add_rt2node(fn, rt, info, mxc, extack); if (!err) { + fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); - if (!(rt->rt6i_flags & RTF_CACHE)) - fib6_prune_clones(info->nl_net, pn); } out: @@ -1199,19 +1241,23 @@ out: * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ - if (pn != fn && pn->leaf == rt) { - pn->leaf = NULL; + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + if (pn != fn && pn_leaf == rt) { + pn_leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); atomic_dec(&rt->rt6i_ref); } - if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) { - pn->leaf = fib6_find_prefix(info->nl_net, pn); + if (pn != fn && !pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { + pn_leaf = fib6_find_prefix(info->nl_net, table, pn); #if RT6_DEBUG >= 2 - if (!pn->leaf) { - WARN_ON(pn->leaf == NULL); - pn->leaf = info->nl_net->ipv6.ip6_null_entry; + if (!pn_leaf) { + WARN_ON(!pn_leaf); + pn_leaf = info->nl_net->ipv6.ip6_null_entry; } #endif - atomic_inc(&pn->leaf->rt6i_ref); + atomic_inc(&pn_leaf->rt6i_ref); + rcu_assign_pointer(pn->leaf, pn_leaf); } #endif goto failure; @@ -1226,7 +1272,7 @@ failure: * fn->leaf. */ if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) - fib6_repair_tree(info->nl_net, fn); + fib6_repair_tree(info->nl_net, table, fn); /* Always release dst as dst->__refcnt is guaranteed * to be taken before entering this function */ @@ -1264,7 +1310,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, dir = addr_bit_set(args->addr, fn->fn_bit); - next = dir ? fn->right : fn->left; + next = dir ? rcu_dereference(fn->right) : + rcu_dereference(fn->left); if (next) { fn = next; @@ -1274,18 +1321,22 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, } while (fn) { - if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree || fn->fn_flags & RTN_RTINFO) { + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; - key = (struct rt6key *) ((u8 *) fn->leaf + - args->offset); + if (!leaf) + goto backtrack; + + key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) { + if (subtree) { struct fib6_node *sfn; - sfn = fib6_lookup_1(fn->subtree, - args + 1); + sfn = fib6_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; @@ -1295,18 +1346,18 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, return fn; } } -#ifdef CONFIG_IPV6_SUBTREES backtrack: -#endif if (fn->fn_flags & RTN_ROOT) break; - fn = fn->parent; + fn = rcu_dereference(fn->parent); } return NULL; } +/* called with rcu_read_lock() held + */ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -1337,54 +1388,87 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) + * exact_match == true means we try to find fn with exact match of + * the passed in prefix addr + * exact_match == false means we try to find fn with longest prefix + * match of the passed in prefix addr. This is useful for finding fn + * for cached route as it will be stored in the exception table under + * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, - int plen, int offset) + int plen, int offset, + bool exact_match) { - struct fib6_node *fn; + struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { - struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = rcu_dereference(fn->leaf); + struct rt6key *key; + + /* This node is being deleted */ + if (!leaf) { + if (plen <= fn->fn_bit) + goto out; + else + goto next; + } + + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) - return NULL; + goto out; if (plen == fn->fn_bit) return fn; + prev = fn; + +next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) - fn = fn->right; + fn = rcu_dereference(fn->right); else - fn = fn->left; + fn = rcu_dereference(fn->left); } - return NULL; +out: + if (exact_match) + return NULL; + else + return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len) + const struct in6_addr *saddr, int src_len, + bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, - offsetof(struct rt6_info, rt6i_dst)); + offsetof(struct rt6_info, rt6i_dst), + exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); - if (fn && fn->subtree) - fn = fib6_locate_1(fn->subtree, saddr, src_len, - offsetof(struct rt6_info, rt6i_src)); + if (fn) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree) { + fn = fib6_locate_1(subtree, saddr, src_len, + offsetof(struct rt6_info, rt6i_src), + exact_match); + } + } } #endif @@ -1400,16 +1484,26 @@ struct fib6_node *fib6_locate(struct fib6_node *root, * */ -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn) { + struct fib6_node *child_left, *child_right; + if (fn->fn_flags & RTN_ROOT) return net->ipv6.ip6_null_entry; while (fn) { - if (fn->left) - return fn->left->leaf; - if (fn->right) - return fn->right->leaf; + child_left = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + child_right = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + if (child_left) + return rcu_dereference_protected(child_left->leaf, + lockdep_is_held(&table->tb6_lock)); + if (child_right) + return rcu_dereference_protected(child_right->leaf, + lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } @@ -1419,31 +1513,49 @@ static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. + * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, - struct fib6_node *fn) + struct fib6_table *table, + struct fib6_node *fn) { int children; int nstate; - struct fib6_node *child, *pn; + struct fib6_node *child; struct fib6_walker *w; int iter = 0; for (;;) { + struct fib6_node *fn_r = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *fn_l = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_r = rcu_dereference_protected(pn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_l = rcu_dereference_protected(pn->left, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_fn_leaf; + RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); - WARN_ON(fn->leaf); + WARN_ON(fn_leaf); children = 0; child = NULL; - if (fn->right) - child = fn->right, children |= 1; - if (fn->left) - child = fn->left, children |= 2; + if (fn_r) + child = fn_r, children |= 1; + if (fn_l) + child = fn_l, children |= 2; if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -1451,36 +1563,36 @@ static struct fib6_node *fib6_repair_tree(struct net *net, || (children && fn->fn_flags & RTN_ROOT) #endif ) { - fn->leaf = fib6_find_prefix(net, fn); + new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 - if (!fn->leaf) { - WARN_ON(!fn->leaf); - fn->leaf = net->ipv6.ip6_null_entry; + if (!new_fn_leaf) { + WARN_ON(!new_fn_leaf); + new_fn_leaf = net->ipv6.ip6_null_entry; } #endif - atomic_inc(&fn->leaf->rt6i_ref); - return fn->parent; + atomic_inc(&new_fn_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_fn_leaf); + return pn; } - pn = fn->parent; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); - FIB6_SUBTREE(pn) = NULL; + RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) - pn->right = child; - else if (pn->left == fn) - pn->left = child; + if (pn_r == fn) + rcu_assign_pointer(pn->right, child); + else if (pn_l == fn) + rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) - child->parent = pn; + rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } @@ -1489,19 +1601,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net, read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { - if (w->root == fn) { - w->root = w->node = NULL; - RT6_TRACE("W %p adjusted by delroot 1\n", w); - } else if (w->node == fn) { + if (w->node == fn) { RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { - if (w->root == fn) { - w->root = child; - RT6_TRACE("W %p adjusted by delroot 2\n", w); - } if (w->node == fn) { w->node = child; if (children&2) { @@ -1516,33 +1621,39 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } read_unlock(&net->ipv6.fib6_walker_lock); - node_free(fn); + node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; - rt6_release(pn->leaf); - pn->leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); + rt6_release(pn_leaf); fn = pn; } } -static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, - struct nl_info *info) +static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, + struct rt6_info __rcu **rtp, struct nl_info *info) { struct fib6_walker *w; - struct rt6_info *rt = *rtp; + struct rt6_info *rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; RT6_TRACE("fib6_del_route\n"); + WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE); + /* Unlink it */ *rtp = rt->dst.rt6_next; rt->rt6i_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; + /* Flush all cached dst in exception table */ + rt6_flush_exceptions(rt); + /* Reset round-robin state, if necessary */ - if (fn->rr_ptr == rt) + if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ @@ -1561,36 +1672,38 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rt->dst.rt6_next; + w->leaf = rcu_dereference_protected(rt->dst.rt6_next, + lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); - rt->dst.rt6_next = NULL; - /* If it was last route, expunge its radix tree node */ - if (!fn->leaf) { + if (!rcu_access_pointer(fn->leaf)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; - fn = fib6_repair_tree(net, fn); + fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); - call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt); + call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); rt6_release(rt); } +/* Need to own table->tb6_lock */ int fib6_del(struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, lockdep_is_held(&rt->rt6i_table->tb6_lock)); + struct fib6_table *table = rt->rt6i_table; struct net *net = info->nl_net; - struct rt6_info **rtp; + struct rt6_info __rcu **rtp; + struct rt6_info __rcu **rtp_next; #if RT6_DEBUG >= 2 if (rt->dst.obsolete > 0) { @@ -1603,28 +1716,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - if (!(rt->rt6i_flags & RTF_CACHE)) { - struct fib6_node *pn = fn; -#ifdef CONFIG_IPV6_SUBTREES - /* clones of this route might be in another subtree */ - if (rt->rt6i_src.plen) { - while (!(pn->fn_flags & RTN_ROOT)) - pn = pn->parent; - pn = pn->parent; - } -#endif - fib6_prune_clones(info->nl_net, pn); - } + /* remove cached dst from exception table */ + if (rt->rt6i_flags & RTF_CACHE) + return rt6_remove_exception_rt(rt); /* * Walk the leaf entries looking for ourself */ - for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) { - if (*rtp == rt) { - fib6_del_route(fn, rtp, info); + for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { + struct rt6_info *cur = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); + if (rt == cur) { + fib6_del_route(table, fn, rtp, info); return 0; } + rtp_next = &cur->dst.rt6_next; } return -ENOENT; } @@ -1651,22 +1758,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. + * + * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { - struct fib6_node *fn, *pn; + struct fib6_node *fn, *pn, *left, *right; + + /* w->root should always be table->tb6_root */ + WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; - if (w->prune && fn != w->root && - fn->fn_flags & RTN_RTINFO && w->state < FWS_C) { - w->state = FWS_C; - w->leaf = fn->leaf; - } switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: @@ -1676,21 +1783,26 @@ static int fib6_walk_continue(struct fib6_walker *w) } w->state = FWS_L; #endif + /* fall through */ case FWS_L: - if (fn->left) { - w->node = fn->left; + left = rcu_dereference_protected(fn->left, 1); + if (left) { + w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; + /* fall through */ case FWS_R: - if (fn->right) { - w->node = fn->right; + right = rcu_dereference_protected(fn->right, 1); + if (right) { + w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; - w->leaf = fn->leaf; + w->leaf = rcu_dereference_protected(fn->leaf, 1); + /* fall through */ case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; @@ -1709,10 +1821,13 @@ static int fib6_walk_continue(struct fib6_walker *w) } skip: w->state = FWS_U; + /* fall through */ case FWS_U: if (fn == w->root) return 0; - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, 1); + left = rcu_dereference_protected(pn->left, 1); + right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { @@ -1721,13 +1836,13 @@ skip: continue; } #endif - if (pn->left == fn) { + if (left == fn) { w->state = FWS_R; continue; } - if (pn->right == fn) { + if (right == fn) { w->state = FWS_C; - w->leaf = w->node->leaf; + w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 @@ -1770,7 +1885,7 @@ static int fib6_clean_node(struct fib6_walker *w) return 0; } - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; @@ -1798,20 +1913,16 @@ static int fib6_clean_node(struct fib6_walker *w) * func is called on each route. * It may return -1 -> delete this route. * 0 -> continue walking - * - * prune==1 -> only immediate children of node (certainly, - * ignoring pure split nodes) will be scanned. */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct rt6_info *, void *arg), - bool prune, int sernum, void *arg) + int sernum, void *arg) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; - c.w.prune = prune; c.w.count = 0; c.w.skip = 0; c.func = func; @@ -1834,10 +1945,10 @@ static void __fib6_clean_all(struct net *net, for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, - func, false, sernum, arg); - write_unlock_bh(&table->tb6_lock); + func, sernum, arg); + spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); @@ -1849,22 +1960,6 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *), __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg); } -static int fib6_prune_clone(struct rt6_info *rt, void *arg) -{ - if (rt->rt6i_flags & RTF_CACHE) { - RT6_TRACE("pruning clone %p\n", rt); - return -1; - } - - return 0; -} - -static void fib6_prune_clones(struct net *net, struct fib6_node *fn) -{ - fib6_clean_tree(net, fn, fib6_prune_clone, true, - FIB6_NO_SERNUM_CHANGE, NULL); -} - static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); @@ -1876,12 +1971,6 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -struct fib6_gc_args -{ - int timeout; - int more; -}; - static int fib6_age(struct rt6_info *rt, void *arg) { struct fib6_gc_args *gc_args = arg; @@ -1890,9 +1979,6 @@ static int fib6_age(struct rt6_info *rt, void *arg) /* * check addrconf expiration here. * Routes are expired even if they are in use. - * - * Also age clones. Note, that clones are aged out - * only if they are not in use now. */ if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) { @@ -1901,31 +1987,14 @@ static int fib6_age(struct rt6_info *rt, void *arg) return -1; } gc_args->more++; - } else if (rt->rt6i_flags & RTF_CACHE) { - if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) - rt->dst.obsolete = DST_OBSOLETE_KILL; - if (atomic_read(&rt->dst.__refcnt) == 1 && - rt->dst.obsolete == DST_OBSOLETE_KILL) { - RT6_TRACE("aging clone %p\n", rt); - return -1; - } else if (rt->rt6i_flags & RTF_GATEWAY) { - struct neighbour *neigh; - __u8 neigh_flags = 0; - - neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); - if (neigh) { - neigh_flags = neigh->flags; - neigh_release(neigh); - } - if (!(neigh_flags & NTF_ROUTER)) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); - return -1; - } - } - gc_args->more++; } + /* Also age clones in the exception table. + * Note, that clones are aged out + * only if they are not in use now. + */ + rt6_age_exceptions(rt, gc_args, now); + return 0; } @@ -1993,7 +2062,8 @@ static int __net_init fib6_net_init(struct net *net) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; - net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); @@ -2004,7 +2074,8 @@ static int __net_init fib6_net_init(struct net *net) if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; - net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); @@ -2134,7 +2205,9 @@ static int ipv6_route_yield(struct fib6_walker *w) return 1; do { - iter->w.leaf = iter->w.leaf->dst.rt6_next; + iter->w.leaf = rcu_dereference_protected( + iter->w.leaf->dst.rt6_next, + lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; @@ -2199,7 +2272,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = ((struct rt6_info *)v)->dst.rt6_next; + n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next); if (n) { ++*pos; return n; @@ -2207,9 +2280,9 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) iter_table: ipv6_route_check_sernum(iter); - read_lock(&iter->tbl->tb6_lock); + spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); - read_unlock(&iter->tbl->tb6_lock); + spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { if (v) ++*pos; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 59c121b932ac..b90bad7a4e56 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -369,6 +369,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { + struct net *net = dev_net(skb->dev); const struct gre_base_hdr *greh; const struct ipv6hdr *ipv6h; int grehlen = sizeof(*greh); @@ -402,9 +403,8 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; switch (type) { - __u32 teli; struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu; + __u32 teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -435,12 +435,11 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } return; case ICMPV6_PKT_TOOBIG: - mtu = be32_to_cpu(info) - offset - t->tun_hlen; - if (t->dev->type == ARPHRD_ETHER) - mtu -= ETH_HLEN; - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; - t->dev->mtu = mtu; + ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); + return; + case NDISC_REDIRECT: + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); return; } @@ -503,7 +502,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, __u32 *pmtu, __be16 proto) { struct ip6_tnl *tunnel = netdev_priv(dev); - struct dst_entry *dst = skb_dst(skb); __be16 protocol; if (dev->type == ARPHRD_ETHER) @@ -522,10 +520,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - /* TooBig packet may have updated dst->dev's mtu */ - if (dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); - return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } @@ -1164,19 +1158,21 @@ err_alloc_dev: return err; } -static void __net_exit ip6gre_exit_net(struct net *net) +static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list) { + struct net *net; LIST_HEAD(list); rtnl_lock(); - ip6gre_destroy_tunnels(net, &list); + list_for_each_entry(net, net_list, exit_list) + ip6gre_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations ip6gre_net_ops = { .init = ip6gre_init_net, - .exit = ip6gre_exit_net, + .exit_batch = ip6gre_exit_batch_net, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), }; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index dab946554157..3d3092adf1d2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -471,15 +471,16 @@ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { - const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data; - struct ip6_tnl *t; - int rel_msg = 0; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; + struct net *net = dev_net(skb->dev); u8 rel_type = ICMPV6_DEST_UNREACH; u8 rel_code = ICMPV6_ADDR_UNREACH; - u8 tproto; __u32 rel_info = 0; - __u16 len; + struct ip6_tnl *t; int err = -ENOENT; + int rel_msg = 0; + u8 tproto; + __u16 len; /* If the packet doesn't contain the original IPv6 header we are in trouble since we might need the source address for further @@ -497,9 +498,8 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, err = 0; switch (*type) { - __u32 teli; struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu; + __u32 mtu, teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -530,11 +530,11 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, } break; case ICMPV6_PKT_TOOBIG: + ip6_update_pmtu(skb, net, htonl(*info), 0, 0, + sock_net_uid(net, NULL)); mtu = *info - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - t->dev->mtu = mtu; - len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len); if (len > mtu) { rel_type = ICMPV6_PKT_TOOBIG; @@ -543,6 +543,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; + case NDISC_REDIRECT: + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + break; } *type = rel_type; @@ -559,13 +563,12 @@ static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - int rel_msg = 0; - u8 rel_type = type; - u8 rel_code = code; __u32 rel_info = ntohl(info); - int err; - struct sk_buff *skb2; const struct iphdr *eiph; + struct sk_buff *skb2; + int err, rel_msg = 0; + u8 rel_type = type; + u8 rel_code = code; struct rtable *rt; struct flowi4 fl4; @@ -590,9 +593,6 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; - case NDISC_REDIRECT: - rel_type = ICMP_REDIRECT; - rel_code = ICMP_REDIR_HOST; default: return 0; } @@ -611,33 +611,26 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, eiph = ip_hdr(skb2); /* Try to guess incoming interface */ - rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, - eiph->saddr, 0, - 0, 0, - IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, + 0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; + ip_rt_put(rt); /* route "incoming" packet */ if (rt->rt_flags & RTCF_LOCAL) { - ip_rt_put(rt); - rt = NULL; rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, - eiph->daddr, eiph->saddr, - 0, 0, - IPPROTO_IPIP, - RT_TOS(eiph->tos), 0); - if (IS_ERR(rt) || - rt->dst.dev->type != ARPHRD_TUNNEL) { + eiph->daddr, eiph->saddr, 0, 0, + IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; } skb_dst_set(skb2, &rt->dst); } else { - ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) @@ -649,10 +642,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, + rel_info); } - if (rel_type == ICMP_REDIRECT) - skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -665,11 +657,10 @@ static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - int rel_msg = 0; + __u32 rel_info = ntohl(info); + int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; - __u32 rel_info = ntohl(info); - int err; err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); @@ -769,7 +760,8 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, if ((ipv6_addr_is_multicast(laddr) || likely(ipv6_chk_addr(net, laddr, ldev, 0))) && - likely(!ipv6_chk_addr(net, raddr, NULL, 0))) + ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) || + likely(!ipv6_chk_addr(net, raddr, NULL, 0)))) ret = 1; } return ret; @@ -999,7 +991,8 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0))) pr_warn("%s xmit: Local address not yet configured!\n", p->name); - else if (!ipv6_addr_is_multicast(raddr) && + else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && + !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr(net, raddr, NULL, 0))) pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", p->name); @@ -2168,17 +2161,16 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .priority = 1, }; -static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; - LIST_HEAD(list); for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6_link_ops) - unregister_netdevice_queue(dev, &list); + unregister_netdevice_queue(dev, list); for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); @@ -2187,12 +2179,10 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) - unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } - - unregister_netdevice_many(&list); } static int __net_init ip6_tnl_init_net(struct net *net) @@ -2236,16 +2226,21 @@ err_alloc_dev: return err; } -static void __net_exit ip6_tnl_exit_net(struct net *net) +static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list) { + struct net *net; + LIST_HEAD(list); + rtnl_lock(); - ip6_tnl_destroy_tunnels(net); + list_for_each_entry(net, net_list, exit_list) + ip6_tnl_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, - .exit = ip6_tnl_exit_net, + .exit_batch = ip6_tnl_exit_batch_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index bcdc2d557de1..dbb74f3c57a7 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1053,23 +1053,22 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .get_link_net = ip6_tnl_get_link_net, }; -static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) +static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, + struct list_head *list) { int h; struct ip6_tnl *t; - LIST_HEAD(list); for (h = 0; h < IP6_VTI_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t) { - unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); - unregister_netdevice_many(&list); + unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) @@ -1109,18 +1108,24 @@ err_alloc_dev: return err; } -static void __net_exit vti6_exit_net(struct net *net) +static void __net_exit vti6_exit_batch_net(struct list_head *net_list) { - struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct vti6_net *ip6n; + struct net *net; + LIST_HEAD(list); rtnl_lock(); - vti6_destroy_tunnels(ip6n); + list_for_each_entry(net, net_list, exit_list) { + ip6n = net_generic(net, vti6_net_id); + vti6_destroy_tunnels(ip6n, &list); + } + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, - .exit = vti6_exit_net, + .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f5500f5444e9..9c24b85949c1 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1617,6 +1617,10 @@ int ip6mr_sk_done(struct sock *sk) struct net *net = sock_net(sk); struct mr6_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return err; + rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == mrt->mroute6_sk) { @@ -1722,6 +1726,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; + /* fall through */ case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a5e466d4e093..b9404feabd78 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -377,6 +377,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; break; + case IPV6_FREEBIND: + if (optlen < sizeof(int)) + goto e_inval; + /* we also don't have a separate freebind bit for IPV6 */ + inet_sk(sk)->freebind = valbool; + retv = 0; + break; + case IPV6_RECVORIGDSTADDR: if (optlen < sizeof(int)) goto e_inval; @@ -1214,6 +1222,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = inet_sk(sk)->transparent; break; + case IPV6_FREEBIND: + val = inet_sk(sk)->freebind; + break; + case IPV6_RECVORIGDSTADDR: val = np->rxopt.bits.rxorigdstaddr; break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 266a530414d7..b3cea200c85e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -46,6 +46,7 @@ #endif #include <linux/if_addr.h> +#include <linux/if_ether.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> @@ -426,12 +427,19 @@ static void ip6_nd_hdr(struct sk_buff *skb, int hop_limit, int len) { struct ipv6hdr *hdr; + struct inet6_dev *idev; + unsigned tclass; + + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); + tclass = idev ? idev->cnf.ndisc_tclass : 0; + rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - ip6_flow_hdr(hdr, 0, 0); + ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; @@ -822,7 +830,7 @@ have_ifp: * who is doing DAD * so fail our DAD process */ - addrconf_dad_failure(ifp); + addrconf_dad_failure(skb, ifp); return; } else { /* @@ -975,7 +983,7 @@ static void ndisc_recv_na(struct sk_buff *skb) if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { - addrconf_dad_failure(ifp); + addrconf_dad_failure(skb, ifp); return; } /* What should we make now? The advertisement @@ -989,8 +997,8 @@ static void ndisc_recv_na(struct sk_buff *skb) */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK(1, warn, - "NA: someone advertises our address %pI6 on %s!\n", - &ifp->addr, ifp->idev->dev->name); + "NA: %pM advertised our address %pI6c on %s!\n", + eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 01bd3ee5ebc6..f06e25065a34 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -800,6 +800,25 @@ get_counters(const struct xt_table_info *t, } } +static void get_old_counters(const struct xt_table_info *t, + struct xt_counters counters[]) +{ + struct ip6t_entry *iter; + unsigned int cpu, i; + + for_each_possible_cpu(cpu) { + i = 0; + xt_entry_foreach(iter, t->entries, t->size) { + const struct xt_counters *tmp; + + tmp = xt_get_per_cpu_counter(&iter->counters, cpu); + ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); + ++i; + } + cond_resched(); + } +} + static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; @@ -1090,8 +1109,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters, and synchronize with replace */ - get_counters(oldinfo, counters); + get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index fe01dc953c56..3b80a38f62b8 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -339,7 +339,7 @@ static void ipv6_hooks_unregister(struct net *net) mutex_unlock(®ister_ipv6_hooks); } -struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { +const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .l3proto = PF_INET6, .pkt_to_tuple = ipv6_pkt_to_tuple, .invert_tuple = ipv6_invert_tuple, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index a9e1fd1a8536..3ac0d826afc4 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -94,7 +94,6 @@ static int icmpv6_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeout) { /* Do not immediately delete the connection after the first @@ -176,6 +175,12 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } +static void icmpv6_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMPV6, "%s", msg); +} + static int icmpv6_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, @@ -187,17 +192,13 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmp6h == NULL) { - if (LOG_INVALID(net, IPPROTO_ICMPV6)) - nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL, - "nf_ct_icmpv6: short packet "); + icmpv6_error_log(skb, net, pf, "short packet"); return -NF_ACCEPT; } if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { - if (LOG_INVALID(net, IPPROTO_ICMPV6)) - nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL, - "nf_ct_icmpv6: ICMPv6 checksum failed "); + icmpv6_error_log(skb, net, pf, "ICMPv6 checksum failed"); return -NF_ACCEPT; } @@ -258,9 +259,14 @@ static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], return 0; } -static int icmpv6_nlattr_tuple_size(void) +static unsigned int icmpv6_nlattr_tuple_size(void) { - return nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); + + return size; } #endif diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b263bf3a19f7..977d8900cfd1 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -169,12 +169,13 @@ static unsigned int nf_hashfn(const struct inet_frag_queue *q) return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } -static void nf_ct_frag6_expire(unsigned long data) +static void nf_ct_frag6_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, nf_frag.frags); ip6_expire_frag_queue(net, fq, &nf_frags); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 46d6dba50698..1d2fb9267d6f 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -290,7 +290,8 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index a338bbc33cf3..4a7e5ffa5108 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -31,37 +31,6 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, return id; } -/* This function exists only for tap drivers that must support broken - * clients requesting UFO without specifying an IPv6 fragment ID. - * - * This is similar to ipv6_select_ident() but we use an independent hash - * seed to limit information leakage. - * - * The network header must be set before calling this. - */ -void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) -{ - static u32 ip6_proxy_idents_hashrnd __read_mostly; - struct in6_addr buf[2]; - struct in6_addr *addrs; - u32 id; - - addrs = skb_header_pointer(skb, - skb_network_offset(skb) + - offsetof(struct ipv6hdr, saddr), - sizeof(buf), buf); - if (!addrs) - return; - - net_get_random_once(&ip6_proxy_idents_hashrnd, - sizeof(ip6_proxy_idents_hashrnd)); - - id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd, - &addrs[1], &addrs[0]); - skb_shinfo(skb)->ip6_frag_id = htonl(id); -} -EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); - __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index ac826dd338ff..d12c55dad7d1 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -154,9 +154,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, - (struct icmp6hdr *) &pfh.icmph, - len); + icmpv6_push_pending_frames(sk, &fl6, + (struct icmp6hdr *)&pfh.icmph, len); } release_sock(sk); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e4462b0ff801..761a473a07c5 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1055,6 +1055,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } @@ -1077,6 +1078,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); @@ -1138,6 +1140,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } @@ -1160,6 +1163,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 846012eae526..afbc000ad4f2 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -170,12 +170,13 @@ out: } EXPORT_SYMBOL(ip6_expire_frag_queue); -static void ip6_frag_expire(unsigned long data) +static void ip6_frag_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ipv6.frags); ip6_expire_frag_queue(net, fq, &ip6_frags); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a96d5b385d8f..05eb7bc36156 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -44,6 +44,7 @@ #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> @@ -104,6 +105,9 @@ static int rt6_fill_node(struct net *net, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -139,9 +143,11 @@ static void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; + struct net *net = dev_net(rt->dst.dev); spin_lock_bh(&ul->lock); list_del(&rt->rt6i_uncached); + atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache); spin_unlock_bh(&ul->lock); } } @@ -355,8 +361,10 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, flags); - if (rt) + if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); + } return rt; } @@ -369,17 +377,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, if (rt) { rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); - if (rt->rt6i_pcpu) { - int cpu; - - for_each_possible_cpu(cpu) { - struct rt6_info **p; - - p = per_cpu_ptr(rt->rt6i_pcpu, cpu); - /* no one shares rt */ - *p = NULL; - } - } else { + if (!rt->rt6i_pcpu) { dst_release_immediate(&rt->dst); return NULL; } @@ -392,6 +390,7 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_exception_bucket *bucket; struct dst_entry *from = dst->from; struct inet6_dev *idev; @@ -404,6 +403,11 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1); + if (bucket) { + rt->rt6i_exception_bucket = NULL; + kfree(bucket); + } dst->from = NULL; dst_release(from); @@ -478,7 +482,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match, } /* - * Route lookup. Any table->tb6_lock is implied. + * Route lookup. rcu_read_lock() should be held. */ static inline struct rt6_info *rt6_device_match(struct net *net, @@ -493,7 +497,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (!oif && ipv6_addr_any(saddr)) goto out; - for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) { + for (sprt = rt; sprt; sprt = rcu_dereference(sprt->dst.rt6_next)) { struct net_device *dev = sprt->dst.dev; if (oif) { @@ -702,6 +706,7 @@ out: } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, + struct rt6_info *leaf, struct rt6_info *rr_head, u32 metric, int oif, int strict, bool *do_rr) @@ -711,7 +716,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; cont = NULL; - for (rt = rr_head; rt; rt = rt->dst.rt6_next) { + for (rt = rr_head; rt; rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -720,7 +725,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = find_match(rt, oif, strict, &mpri, match, do_rr); } - for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { + for (rt = leaf; rt && rt != rr_head; + rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -732,37 +738,59 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, if (match || !cont) return match; - for (rt = cont; rt; rt = rt->dst.rt6_next) + for (rt = cont; rt; rt = rcu_dereference(rt->dst.rt6_next)) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } -static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) +static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, + int oif, int strict) { + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6_info *match, *rt0; - struct net *net; bool do_rr = false; + int key_plen; - rt0 = fn->rr_ptr; + if (!leaf || leaf == net->ipv6.ip6_null_entry) + return net->ipv6.ip6_null_entry; + + rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) - fn->rr_ptr = rt0 = fn->leaf; + rt0 = leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + /* Double check to make sure fn is not an intermediate node + * and fn->leaf does not points to its child's leaf + * (This might happen if all routes under fn are deleted from + * the tree and fib6_repair_tree() is called on the node.) + */ + key_plen = rt0->rt6i_dst.plen; +#ifdef CONFIG_IPV6_SUBTREES + if (rt0->rt6i_src.plen) + key_plen = rt0->rt6i_src.plen; +#endif + if (fn->fn_bit != key_plen) + return net->ipv6.ip6_null_entry; + + match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict, &do_rr); if (do_rr) { - struct rt6_info *next = rt0->dst.rt6_next; + struct rt6_info *next = rcu_dereference(rt0->dst.rt6_next); /* no entries matched; do round-robin */ if (!next || next->rt6i_metric != rt0->rt6i_metric) - next = fn->leaf; - - if (next != rt0) - fn->rr_ptr = next; + next = leaf; + + if (next != rt0) { + spin_lock_bh(&leaf->rt6i_table->tb6_lock); + /* make sure next is not being deleted from the tree */ + if (next->rt6i_node) + rcu_assign_pointer(fn->rr_ptr, next); + spin_unlock_bh(&leaf->rt6i_table->tb6_lock); + } } - net = dev_net(rt0->dst.dev); return match ? match : net->ipv6.ip6_null_entry; } @@ -850,13 +878,14 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { - struct fib6_node *pn; + struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; - pn = fn->parent; - if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) - fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); + pn = rcu_dereference(fn->parent); + sn = FIB6_SUBTREE(pn); + if (sn && sn != fn) + fn = fib6_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) @@ -864,29 +893,59 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn, } } +static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, + bool null_fallback) +{ + struct rt6_info *rt = *prt; + + if (dst_hold_safe(&rt->dst)) + return true; + if (null_fallback) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } else { + rt = NULL; + } + *prt = rt; + return false; +} + static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, int flags) { + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; - struct rt6_info *rt; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - rt = fn->leaf; - rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); - if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags); + rt = rcu_dereference(fn->leaf); + if (!rt) { + rt = net->ipv6.ip6_null_entry; + } else { + rt = rt6_device_match(net, rt, &fl6->saddr, + fl6->flowi6_oif, flags); + if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) + rt = rt6_multipath_select(rt, fl6, + fl6->flowi6_oif, flags); + } if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); + /* Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; + + if (ip6_hold_safe(net, &rt, true)) + dst_use_noref(&rt->dst, jiffies); + + rcu_read_unlock(); - trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + trace_fib6_table_lookup(net, rt, table, fl6); return rt; @@ -938,9 +997,9 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, struct fib6_table *table; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, mxc, extack); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); return err; } @@ -1038,7 +1097,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) return pcpu_rt; } -/* It should be called with read_lock_bh(&tb6_lock) acquired */ +/* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) { struct rt6_info *pcpu_rt, **p; @@ -1046,16 +1105,14 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) p = this_cpu_ptr(rt->rt6i_pcpu); pcpu_rt = *p; - if (pcpu_rt) { - dst_hold(&pcpu_rt->dst); + if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false)) rt6_dst_from_metrics_check(pcpu_rt); - } + return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) { - struct fib6_table *table = rt->rt6i_table; struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(rt); @@ -1066,36 +1123,526 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) return net->ipv6.ip6_null_entry; } - read_lock_bh(&table->tb6_lock); - if (rt->rt6i_pcpu) { - p = this_cpu_ptr(rt->rt6i_pcpu); - prev = cmpxchg(p, NULL, pcpu_rt); - if (prev) { - /* If someone did it before us, return prev instead */ - dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = prev; - } - } else { - /* rt has been removed from the fib6 tree - * before we have a chance to acquire the read_lock. - * In this case, don't brother to create a pcpu rt - * since rt is going away anyway. The next - * dst_check() will trigger a re-lookup. - */ - dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = rt; - } dst_hold(&pcpu_rt->dst); + p = this_cpu_ptr(rt->rt6i_pcpu); + prev = cmpxchg(p, NULL, pcpu_rt); + BUG_ON(prev); + rt6_dst_from_metrics_check(pcpu_rt); - read_unlock_bh(&table->tb6_lock); return pcpu_rt; } +/* exception hash table implementation + */ +static DEFINE_SPINLOCK(rt6_exception_lock); + +/* Remove rt6_ex from hash table and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_remove_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex) +{ + struct net *net; + + if (!bucket || !rt6_ex) + return; + + net = dev_net(rt6_ex->rt6i->dst.dev); + rt6_ex->rt6i->rt6i_node = NULL; + hlist_del_rcu(&rt6_ex->hlist); + rt6_release(rt6_ex->rt6i); + kfree_rcu(rt6_ex, rcu); + WARN_ON_ONCE(!bucket->depth); + bucket->depth--; + net->ipv6.rt6_stats->fib_rt_cache--; +} + +/* Remove oldest rt6_ex in bucket and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) +{ + struct rt6_exception *rt6_ex, *oldest = NULL; + + if (!bucket) + return; + + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) + oldest = rt6_ex; + } + rt6_remove_exception(bucket, oldest); +} + +static u32 rt6_exception_hash(const struct in6_addr *dst, + const struct in6_addr *src) +{ + static u32 seed __read_mostly; + u32 val; + + net_get_random_once(&seed, sizeof(seed)); + val = jhash(dst, sizeof(*dst), seed); + +#ifdef CONFIG_IPV6_SUBTREES + if (src) + val = jhash(src, sizeof(*src), val); +#endif + return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rt6_exception_lock + */ +static struct rt6_exception * +__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rcu_read_lock() + */ +static struct rt6_exception * +__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +static int rt6_insert_exception(struct rt6_info *nrt, + struct rt6_info *ort) +{ + struct net *net = dev_net(ort->dst.dev); + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err = 0; + + /* ort can't be a cache or pcpu route */ + if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) + ort = (struct rt6_info *)ort->dst.from; + WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)); + + spin_lock_bh(&rt6_exception_lock); + + if (ort->exception_bucket_flushed) { + err = -EINVAL; + goto out; + } + + bucket = rcu_dereference_protected(ort->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) { + bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), + GFP_ATOMIC); + if (!bucket) { + err = -ENOMEM; + goto out; + } + rcu_assign_pointer(ort->rt6i_exception_bucket, bucket); + } + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates ort is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (ort->rt6i_src.plen) + src_key = &nrt->rt6i_src.addr; +#endif + + /* Update rt6i_prefsrc as it could be changed + * in rt6_remove_prefsrc() + */ + nrt->rt6i_prefsrc = ort->rt6i_prefsrc; + /* rt6_mtu_change() might lower mtu on ort. + * Only insert this exception route if its mtu + * is less than ort's mtu value. + */ + if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) { + err = -EINVAL; + goto out; + } + + rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_remove_exception(bucket, rt6_ex); + + rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); + if (!rt6_ex) { + err = -ENOMEM; + goto out; + } + rt6_ex->rt6i = nrt; + rt6_ex->stamp = jiffies; + atomic_inc(&nrt->rt6i_ref); + nrt->rt6i_node = ort->rt6i_node; + hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); + bucket->depth++; + net->ipv6.rt6_stats->fib_rt_cache++; + + if (bucket->depth > FIB6_MAX_DEPTH) + rt6_exception_remove_oldest(bucket); + +out: + spin_unlock_bh(&rt6_exception_lock); + + /* Update fn->fn_sernum to invalidate all cached dst */ + if (!err) { + fib6_update_sernum(ort); + fib6_force_start_gc(net); + } + + return err; +} + +void rt6_flush_exceptions(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + spin_lock_bh(&rt6_exception_lock); + /* Prevent rt6_insert_exception() to recreate the bucket list */ + rt->exception_bucket_flushed = 1; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) + goto out; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) + rt6_remove_exception(bucket, rt6_ex); + WARN_ON_ONCE(bucket->depth); + bucket++; + } + +out: + spin_unlock_bh(&rt6_exception_lock); +} + +/* Find cached rt in the hash table inside passed in rt + * Caller has to hold rcu_read_lock() + */ +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + struct rt6_info *res = NULL; + + bucket = rcu_dereference(rt->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates rt is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (rt->rt6i_src.plen) + src_key = saddr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); + + if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) + res = rt6_ex->rt6i; + + return res; +} + +/* Remove the passed in cached rt from the hash table that contains it */ +int rt6_remove_exception_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err; + + if (!from || + !(rt->rt6i_flags & RTF_CACHE)) + return -EINVAL; + + if (!rcu_access_pointer(from->rt6i_exception_bucket)) + return -ENOENT; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(from->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_spinlock(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) { + rt6_remove_exception(bucket, rt6_ex); + err = 0; + } else { + err = -ENOENT; + } + + spin_unlock_bh(&rt6_exception_lock); + return err; +} + +/* Find rt6_ex which contains the passed in rt cache and + * refresh its stamp + */ +static void rt6_update_exception_stamp_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + + if (!from || + !(rt->rt6i_flags & RTF_CACHE)) + return; + + rcu_read_lock(); + bucket = rcu_dereference(from->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_ex->stamp = jiffies; + + rcu_read_unlock(); +} + +static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + rt6_ex->rt6i->rt6i_prefsrc.plen = 0; + } + bucket++; + } + } +} + +static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + /* For RTF_CACHE with rt6i_pmtu == 0 + * (i.e. a redirected route), + * the metrics of its rt->dst.from has already + * been updated. + */ + if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) + entry->rt6i_pmtu = mtu; + } + bucket++; + } + } +} + +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +static void rt6_exceptions_clean_tohost(struct rt6_info *rt, + struct in6_addr *gateway) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == + RTF_CACHE_GATEWAY && + ipv6_addr_equal(gateway, + &entry->rt6i_gateway)) { + rt6_remove_exception(bucket, rt6_ex); + } + } + bucket++; + } + } + + spin_unlock_bh(&rt6_exception_lock); +} + +static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_info *rt = rt6_ex->rt6i; + + /* we are pruning and obsoleting aged-out and non gateway exceptions + * even if others have still references to them, so that on next + * dst_check() such references can be dropped. + * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when + * expired, independently from their aging, as per RFC 8201 section 4 + */ + if (!(rt->rt6i_flags & RTF_EXPIRES) && + time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { + RT6_TRACE("aging clone %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } else if (rt->rt6i_flags & RTF_GATEWAY) { + struct neighbour *neigh; + __u8 neigh_flags = 0; + + neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); + if (neigh) { + neigh_flags = neigh->flags; + neigh_release(neigh); + } + if (!(neigh_flags & NTF_ROUTER)) { + RT6_TRACE("purging route %p via non-router but gateway\n", + rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + } else if (__rt6_check_expired(rt)) { + RT6_TRACE("purging expired route %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + gc_args->more++; +} + +void rt6_age_exceptions(struct rt6_info *rt, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + rt6_age_examine_exception(bucket, rt6_ex, + gc_args, now); + } + bucket++; + } + } + spin_unlock_bh(&rt6_exception_lock); +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; int strict = 0; strict |= flags & RT6_LOOKUP_F_IFACE; @@ -1103,7 +1650,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (net->ipv6.devconf_all->forwarding == 0) strict |= RT6_LOOKUP_F_REACHABLE; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; @@ -1112,7 +1659,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, oif = 0; redo_rt6_select: - rt = rt6_select(fn, oif, strict); + rt = rt6_select(net, fn, oif, strict); if (rt->rt6i_nsiblings) rt = rt6_multipath_select(rt, fl6, oif, strict); if (rt == net->ipv6.ip6_null_entry) { @@ -1127,14 +1674,23 @@ redo_rt6_select: } } + /*Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; - if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) { - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); - - rt6_dst_from_metrics_check(rt); - - trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + if (rt == net->ipv6.ip6_null_entry) { + rcu_read_unlock(); + dst_hold(&rt->dst); + trace_fib6_table_lookup(net, rt, table, fl6); + return rt; + } else if (rt->rt6i_flags & RTF_CACHE) { + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + rt6_dst_from_metrics_check(rt); + } + rcu_read_unlock(); + trace_fib6_table_lookup(net, rt, table, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !(rt->rt6i_flags & RTF_GATEWAY))) { @@ -1146,8 +1702,14 @@ redo_rt6_select: struct rt6_info *uncached_rt; - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + } else { + rcu_read_unlock(); + uncached_rt = rt; + goto uncached_rt_out; + } + rcu_read_unlock(); uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); dst_release(&rt->dst); @@ -1157,12 +1719,14 @@ redo_rt6_select: * No need for another dst_hold() */ rt6_uncached_list_add(uncached_rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); } else { uncached_rt = net->ipv6.ip6_null_entry; dst_hold(&uncached_rt->dst); } - trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6); +uncached_rt_out: + trace_fib6_table_lookup(net, uncached_rt, table, fl6); return uncached_rt; } else { @@ -1170,26 +1734,28 @@ redo_rt6_select: struct rt6_info *pcpu_rt; - rt->dst.lastuse = jiffies; - rt->dst.__use++; + dst_use_noref(&rt->dst, jiffies); + local_bh_disable(); pcpu_rt = rt6_get_pcpu_route(rt); - if (pcpu_rt) { - read_unlock_bh(&table->tb6_lock); - } else { - /* We have to do the read_unlock first - * because rt6_make_pcpu_route() may trigger - * ip6_dst_gc() which will take the write_lock. - */ - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - pcpu_rt = rt6_make_pcpu_route(rt); - dst_release(&rt->dst); + if (!pcpu_rt) { + /* atomic_inc_not_zero() is needed when using rcu */ + if (atomic_inc_not_zero(&rt->rt6i_ref)) { + /* No dst_hold() on rt is needed because grabbing + * rt->rt6i_ref makes sure rt can't be released. + */ + pcpu_rt = rt6_make_pcpu_route(rt); + rt6_release(rt); + } else { + /* rt is already removed from tree */ + pcpu_rt = net->ipv6.ip6_null_entry; + dst_hold(&pcpu_rt->dst); + } } - - trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6); + local_bh_enable(); + rcu_read_unlock(); + trace_fib6_table_lookup(net, pcpu_rt, table, fl6); return pcpu_rt; - } } EXPORT_SYMBOL_GPL(ip6_pol_route); @@ -1328,6 +1894,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; @@ -1491,23 +2058,17 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); + /* update rt6_ex->stamp for cache */ + if (rt6->rt6i_flags & RTF_CACHE) + rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct rt6_info *nrt6; nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); - - /* ip6_ins_rt(nrt6) will bump the - * rt6->rt6i_node->fn_sernum - * which will fail the next rt6_check() and - * invalidate the sk->sk_dst_cache. - */ - ip6_ins_rt(nrt6); - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt6->dst); + if (rt6_insert_exception(nrt6, rt6)) + dst_release_immediate(&nrt6->dst); } } } @@ -1571,7 +2132,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; /* Get the "current" route for this destination and @@ -1584,10 +2145,10 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, * routes. */ - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt6_check_expired(rt)) continue; if (rt->dst.error) @@ -1596,8 +2157,23 @@ restart: continue; if (fl6->flowi6_oif != rt->dst.dev->ifindex) continue; - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + /* rt_cache's gateway might be different from its 'parent' + * in the case of an ip redirect. + * So we keep searching in the exception table if the gateway + * is different. + */ + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) { + rt_cache = rt6_find_cached_rt(rt, + &fl6->daddr, + &fl6->saddr); + if (rt_cache && + ipv6_addr_equal(&rdfl->gateway, + &rt_cache->rt6i_gateway)) { + rt = rt_cache; + break; + } continue; + } break; } @@ -1615,11 +2191,11 @@ restart: } out: - dst_hold(&rt->dst); + ip6_hold_safe(net, &rt, true); - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); - trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + trace_fib6_table_lookup(net, rt, table, fl6); return rt; }; @@ -1766,6 +2342,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, * do proper release of the net_device */ rt6_uncached_list_add(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); @@ -1801,6 +2378,7 @@ out: static int ip6_convert_metrics(struct mx6_config *mxc, const struct fib6_config *cfg) { + struct net *net = cfg->fc_nlinfo.nl_net; bool ecn_ca = false; struct nlattr *nla; int remaining; @@ -1826,7 +2404,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc, char tmp[TCP_CA_NAME_MAX]; nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); if (val == TCP_CA_UNSPEC) goto err; } else { @@ -1901,6 +2479,12 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } + /* RTF_CACHE is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_CACHE) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); + goto out; + } + if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; @@ -2216,9 +2800,9 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) } table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out: ip6_rt_put(rt); @@ -2244,7 +2828,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) if (rt == net->ipv6.ip6_null_entry) goto out_put; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) { struct rt6_info *sibling, *next_sibling; @@ -2274,7 +2858,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) err = fib6_del(rt, info); out_unlock: - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out_put: ip6_rt_put(rt); @@ -2288,9 +2872,9 @@ out_put: static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { + struct rt6_info *rt, *rt_cache; struct fib6_table *table; struct fib6_node *fn; - struct rt6_info *rt; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); @@ -2299,17 +2883,22 @@ static int ip6_route_del(struct fib6_config *cfg, return err; } - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, - &cfg->fc_src, cfg->fc_src_len); + &cfg->fc_src, cfg->fc_src_len, + !(cfg->fc_flags & RTF_CACHE)); if (fn) { - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - if ((rt->rt6i_flags & RTF_CACHE) && - !(cfg->fc_flags & RTF_CACHE)) - continue; + for_each_fib6_node_rt_rcu(fn) { + if (cfg->fc_flags & RTF_CACHE) { + rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst, + &cfg->fc_src); + if (!rt_cache) + continue; + rt = rt_cache; + } if (cfg->fc_ifindex && (!rt->dst.dev || rt->dst.dev->ifindex != cfg->fc_ifindex)) @@ -2321,8 +2910,9 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) continue; - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); + if (!dst_hold_safe(&rt->dst)) + break; + rcu_read_unlock(); /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) @@ -2331,7 +2921,7 @@ static int ip6_route_del(struct fib6_config *cfg, return __ip6_del_rt_siblings(rt, cfg); } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return err; } @@ -2435,8 +3025,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - if (ip6_ins_rt(nrt)) - goto out_release; + /* No need to remove rt from the exception table if rt is + * a cached route because rt6_insert_exception() will + * takes care of it + */ + if (rt6_insert_exception(nrt, rt)) { + dst_release_immediate(&nrt->dst); + goto out; + } netevent.old = &rt->dst; netevent.new = &nrt->dst; @@ -2444,17 +3040,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); - if (rt->rt6i_flags & RTF_CACHE) { - rt = (struct rt6_info *) dst_clone(&rt->dst); - ip6_del_rt(rt); - } - -out_release: - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt->dst); - out: neigh_release(neigh); } @@ -2511,23 +3096,23 @@ static struct rt6_info *rt6_get_route_info(struct net *net, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0); + rcu_read_lock(); + fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != ifindex) continue; if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) continue; - dst_hold(&rt->dst); + ip6_hold_safe(NULL, &rt, false); break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -2573,16 +3158,16 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (dev == rt->dst.dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) break; } if (rt) - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); + ip6_hold_safe(NULL, &rt, false); + rcu_read_unlock(); return rt; } @@ -2620,17 +3205,20 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table) struct rt6_info *rt; restart: - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - ip6_del_rt(rt); + if (dst_hold_safe(&rt->dst)) { + rcu_read_unlock(); + ip6_del_rt(rt); + } else { + rcu_read_unlock(); + } goto restart; } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } @@ -2818,8 +3406,12 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) if (((void *)rt->dst.dev == dev || !dev) && rt != net->ipv6.ip6_null_entry && ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->rt6i_prefsrc.plen = 0; + /* need to update cache as well */ + rt6_exceptions_remove_prefsrc(rt); + spin_unlock_bh(&rt6_exception_lock); } return 0; } @@ -2836,18 +3428,23 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) -#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct rt6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; - if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || - ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && - ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { return -1; } + + /* Further clean up cached routes in exception table. + * This is needed because cached route may have a different + * gateway than its 'parent' in the case of an ip redirect. + */ + rt6_exceptions_clean_tohost(rt, gateway); + return 0; } @@ -2926,19 +3523,14 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) if (rt->dst.dev == arg->dev && dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { - if (rt->rt6i_flags & RTF_CACHE) { - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu) - rt->rt6i_pmtu = arg->mtu; - } else if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + spin_lock_bh(&rt6_exception_lock); + if (dst_mtu(&rt->dst) >= arg->mtu || + (dst_mtu(&rt->dst) < arg->mtu && + dst_mtu(&rt->dst) == idev->cnf.mtu6)) { dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); } + rt6_exceptions_update_pmtu(rt, arg->mtu); + spin_unlock_bh(&rt6_exception_lock); } return 0; } @@ -3839,7 +4431,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, - net->ipv6.rt6_stats->fib_rt_alloc, + atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index ac912bb21747..d60ddcb0bfe2 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -91,29 +91,35 @@ struct sit_net { * Must be invoked with rcu_read_lock */ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, - struct net_device *dev, __be32 remote, __be32 local) + struct net_device *dev, + __be32 remote, __be32 local, + int sifindex) { unsigned int h0 = HASH(remote); unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); + int ifindex = dev ? dev->ifindex : 0; for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->ifindex == t->parms.link) && + (!dev || !t->parms.link || ifindex == t->parms.link || + sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->ifindex == t->parms.link) && + (!dev || !t->parms.link || ifindex == t->parms.link || + sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && - (!dev || !t->parms.link || dev->ifindex == t->parms.link) && + (!dev || !t->parms.link || ifindex == t->parms.link || + sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } @@ -486,6 +492,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; + int sifindex; int err; switch (type) { @@ -517,10 +524,9 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; - t = ipip6_tunnel_lookup(dev_net(skb->dev), - skb->dev, - iph->daddr, - iph->saddr); + sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; + t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, + iph->daddr, iph->saddr, sifindex); if (!t) goto out; @@ -633,10 +639,12 @@ static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; + int sifindex; int err; + sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, - iph->saddr, iph->daddr); + iph->saddr, iph->daddr, sifindex); if (tunnel) { struct pcpu_sw_netstats *tstats; @@ -704,10 +712,13 @@ static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { const struct iphdr *iph; struct ip_tunnel *tunnel; + int sifindex; + + sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; iph = ip_hdr(skb); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, - iph->saddr, iph->daddr); + iph->saddr, iph->daddr, sifindex); if (tunnel) { const struct tnl_ptk_info *tpi; @@ -1848,19 +1859,22 @@ err_alloc_dev: return err; } -static void __net_exit sit_exit_net(struct net *net) +static void __net_exit sit_exit_batch_net(struct list_head *net_list) { LIST_HEAD(list); + struct net *net; rtnl_lock(); - sit_destroy_tunnels(net, &list); + list_for_each_entry(net, net_list, exit_list) + sit_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, - .exit = sit_exit_net, + .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), }; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 4e7817abc0b9..e7a3a6b6cf56 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -244,7 +244,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); - tcp_select_initial_window(tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index f7051ba5b8af..a789a8ac6a64 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -98,6 +98,34 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "max_dst_opts_number", + .data = &init_net.ipv6.sysctl.max_dst_opts_cnt, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "max_hbh_opts_number", + .data = &init_net.ipv6.sysctl.max_hbh_opts_cnt, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "max_dst_opts_length", + .data = &init_net.ipv6.sysctl.max_dst_opts_len, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "max_hbh_length", + .data = &init_net.ipv6.sysctl.max_hbh_opts_len, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -158,6 +186,10 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind; ipv6_table[9].data = &net->ipv6.sysctl.flowlabel_reflect; + ipv6_table[10].data = &net->ipv6.sysctl.max_dst_opts_cnt; + ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt; + ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; + ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 64d94afa427f..6bb98c93edfe 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -69,6 +69,8 @@ #include <crypto/hash.h> #include <linux/scatterlist.h> +#include <trace/events/tcp.h> + static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); @@ -890,7 +892,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) int genhash; struct sock *sk1 = NULL; #endif - int oif; + int oif = 0; if (th->rst) return; @@ -939,7 +941,11 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - oif = sk ? sk->sk_bound_dev_if : 0; + if (sk) { + oif = sk->sk_bound_dev_if; + trace_tcp_send_reset(sk, skb); + } + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG @@ -1577,8 +1583,9 @@ do_time_wait: refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v6_timewait_ack(sk, skb); break; @@ -1933,8 +1940,8 @@ struct proto tcpv6_prot = { .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, .sysctl_mem = sysctl_tcp_mem, - .sysctl_wmem = sysctl_tcp_wmem, - .sysctl_rmem = sysctl_tcp_rmem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 17e95a0386b3..885ade234a49 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -153,6 +153,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) switch (nexthdr) { case NEXTHDR_FRAGMENT: onlyproto = 1; + /* fall through */ case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 4e438bc7ee87..f85f0d7480ac 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -338,6 +338,14 @@ static int __net_init xfrm6_tunnel_net_init(struct net *net) static void __net_exit xfrm6_tunnel_net_exit(struct net *net) { + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); + unsigned int i; + + for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) + WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); + + for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) + WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byspi[i])); } static struct pernet_operations xfrm6_tunnel_net_ops = { |