diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-07-31 17:10:56 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-07-31 17:10:56 -0700 |
commit | 7c764cec3703583247c4ab837c652975a3d41f4b (patch) | |
tree | bd7149e43ee1d3465f7f3db5ed1df53c06eae62c /net | |
parent | acea568fa9eaeffbf949d15b2f7c9c346e16aae3 (diff) | |
parent | ea111545843e657504193e4f726e1116b96b8141 (diff) | |
download | linux-stable-7c764cec3703583247c4ab837c652975a3d41f4b.tar.gz linux-stable-7c764cec3703583247c4ab837c652975a3d41f4b.tar.bz2 linux-stable-7c764cec3703583247c4ab837c652975a3d41f4b.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Must teardown SR-IOV before unregistering netdev in igb driver, from
Alex Williamson.
2) Fix ipv6 route unreachable crash in IPVS, from Alex Gartrell.
3) Default route selection in ipv4 should take the prefix length, table
ID, and TOS into account, from Julian Anastasov.
4) sch_plug must have a reset method in order to purge all buffered
packets when the qdisc is reset, likewise for sch_choke, from WANG
Cong.
5) Fix deadlock and races in slave_changelink/br_setport in bridging.
From Nikolay Aleksandrov.
6) mlx4 bug fixes (wrong index in port even propagation to VFs,
overzealous BUG_ON assertion, etc.) from Ido Shamay, Jack
Morgenstein, and Or Gerlitz.
7) Turn off klog message about SCTP userspace interface compat that
makes no sense at all, from Daniel Borkmann.
8) Fix unbounded restarts of inet frag eviction process, causing NMI
watchdog soft lockup messages, from Florian Westphal.
9) Suspend/resume fixes for r8152 from Hayes Wang.
10) Fix busy loop when MSG_WAITALL|MSG_PEEK is used in TCP recv, from
Sabrina Dubroca.
11) Fix performance regression when removing a lot of routes from the
ipv4 routing tables, from Alexander Duyck.
12) Fix device leak in AF_PACKET, from Lars Westerhoff.
13) AF_PACKET also has a header length comparison bug due to signedness,
from Alexander Drozdov.
14) Fix bug in EBPF tail call generation on x86, from Daniel Borkmann.
15) Memory leaks, TSO stats, watchdog timeout and other fixes to
thunderx driver from Sunil Goutham and Thanneeru Srinivasulu.
16) act_bpf can leak memory when replacing programs, from Daniel
Borkmann.
17) WOL packet fixes in gianfar driver, from Claudiu Manoil.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
stmmac: fix missing MODULE_LICENSE in stmmac_platform
gianfar: Enable device wakeup when appropriate
gianfar: Fix suspend/resume for wol magic packet
gianfar: Fix warning when CONFIG_PM off
act_pedit: check binding before calling tcf_hash_release()
net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket
net: sched: fix refcount imbalance in actions
r8152: reset device when tx timeout
r8152: add pre_reset and post_reset
qlcnic: Fix corruption while copying
act_bpf: fix memory leaks when replacing bpf programs
net: thunderx: Fix for crash while BGX teardown
net: thunderx: Add PCI driver shutdown routine
net: thunderx: Fix crash when changing rss with mutliple traffic flows
net: thunderx: Set watchdog timeout value
net: thunderx: Wakeup TXQ only if CQE_TX are processed
net: thunderx: Suppress alloc_pages() failure warnings
net: thunderx: Fix TSO packet statistic
net: thunderx: Fix memory leak when changing queue count
net: thunderx: Fix RQ_DROP miscalculation
...
Diffstat (limited to 'net')
43 files changed, 402 insertions, 228 deletions
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 3d0f7d2a0616..ad82324f710f 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2312,6 +2312,10 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) return 1; chan = conn->smp; + if (!chan) { + BT_ERR("SMP security requested but not available"); + return 1; + } if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) return 1; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 0ff6e1bbca91..fa7bfced888e 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -37,15 +37,30 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) { - if (!is_skb_forwardable(skb->dev, skb)) { - kfree_skb(skb); - } else { - skb_push(skb, ETH_HLEN); - br_drop_fake_rtable(skb); - skb_sender_cpu_clear(skb); - dev_queue_xmit(skb); + if (!is_skb_forwardable(skb->dev, skb)) + goto drop; + + skb_push(skb, ETH_HLEN); + br_drop_fake_rtable(skb); + skb_sender_cpu_clear(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD))) { + int depth; + + if (!__vlan_get_protocol(skb, skb->protocol, &depth)) + goto drop; + + skb_set_network_header(skb, depth); } + dev_queue_xmit(skb); + + return 0; + +drop: + kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 1198a3dbad95..c94321955db7 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -445,6 +445,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (p->port->state == BR_STATE_DISABLED) goto unlock; + entry->state = p->state; rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 79db489cdade..0b39dcc65b94 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1416,8 +1416,7 @@ br_multicast_leave_group(struct net_bridge *br, spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || - (port && port->state == BR_STATE_DISABLED) || - timer_pending(&other_query->timer)) + (port && port->state == BR_STATE_DISABLED)) goto out; mdb = mlock_dereference(br->mdb, br); @@ -1425,6 +1424,31 @@ br_multicast_leave_group(struct net_bridge *br, if (!mp) goto out; + if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { + struct net_bridge_port_group __rcu **pp; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + br_mdb_notify(br->dev, port, group, RTM_DELMDB); + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + } + goto out; + } + + if (timer_pending(&other_query->timer)) + goto out; + if (br->multicast_querier) { __br_multicast_send_query(br, port, &mp->addr); @@ -1450,28 +1474,6 @@ br_multicast_leave_group(struct net_bridge *br, } } - if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { - struct net_bridge_port_group __rcu **pp; - - for (pp = &mp->ports; - (p = mlock_dereference(*pp, br)) != NULL; - pp = &p->next) { - if (p->port != port) - continue; - - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, port, group, RTM_DELMDB); - - if (!mp->ports && !mp->mglist && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); - } - goto out; - } - now = jiffies; time = now + br->multicast_last_member_count * br->multicast_last_member_interval; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 364bdc98bd9b..3da5525eb8a2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -693,9 +693,17 @@ static int br_port_slave_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[]) { + struct net_bridge *br = netdev_priv(brdev); + int ret; + if (!data) return 0; - return br_setport(br_port_get_rtnl(dev), data); + + spin_lock_bh(&br->lock); + ret = br_setport(br_port_get_rtnl(dev), data); + spin_unlock_bh(&br->lock); + + return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index b4b6dab9c285..ed74ffaa851f 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -209,8 +209,9 @@ void br_transmit_config(struct net_bridge_port *p) br_send_config_bpdu(p, &bpdu); p->topology_change_ack = 0; p->config_pending = 0; - mod_timer(&p->hold_timer, - round_jiffies(jiffies + BR_HOLD_TIME)); + if (p->br->stp_enabled == BR_KERNEL_STP) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); } } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index a2730e7196cd..4ca449a16132 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -48,7 +48,8 @@ void br_stp_enable_bridge(struct net_bridge *br) struct net_bridge_port *p; spin_lock_bh(&br->lock); - mod_timer(&br->hello_timer, jiffies + br->hello_time); + if (br->stp_enabled == BR_KERNEL_STP) + mod_timer(&br->hello_timer, jiffies + br->hello_time); mod_timer(&br->gc_timer, jiffies + HZ/10); br_config_bpdu_generation(br); @@ -127,6 +128,7 @@ static void br_stp_start(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); @@ -140,6 +142,10 @@ static void br_stp_start(struct net_bridge *br) if (r == 0) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); + /* Stop hello and hold timers */ + del_timer(&br->hello_timer); + list_for_each_entry(p, &br->port_list, list) + del_timer(&p->hold_timer); } else { br->stp_enabled = BR_KERNEL_STP; br_debug(br, "using kernel STP\n"); @@ -156,12 +162,17 @@ static void br_stp_stop(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; if (br->stp_enabled == BR_USER_STP) { r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); br_info(br, "userspace STP stopped, return code %d\n", r); /* To start timers on any ports left in blocking */ + mod_timer(&br->hello_timer, jiffies + br->hello_time); + list_for_each_entry(p, &br->port_list, list) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); spin_lock_bh(&br->lock); br_port_state_selection(br); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 7caf7fae2d5b..5f0f5af0ec35 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -40,7 +40,9 @@ static void br_hello_timer_expired(unsigned long arg) if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); - mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time)); + if (br->stp_enabled != BR_USER_STP) + mod_timer(&br->hello_timer, + round_jiffies(jiffies + br->hello_time)); } spin_unlock(&br->lock); } diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 1f2a126f4ffa..6441f47b1a8f 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -23,7 +23,8 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state struct cgroup_cls_state *task_cls_state(struct task_struct *p) { - return css_cls_state(task_css(p, net_cls_cgrp_id)); + return css_cls_state(task_css_check(p, net_cls_cgrp_id, + rcu_read_lock_bh_held())); } EXPORT_SYMBOL_GPL(task_cls_state); diff --git a/net/core/sock.c b/net/core/sock.c index 08f16db46070..193901d09757 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1497,7 +1497,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); /* SANITY */ - get_net(sock_net(newsk)); + if (likely(newsk->sk_net_refcnt)) + get_net(sock_net(newsk)); sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); @@ -1967,20 +1968,21 @@ static void __release_sock(struct sock *sk) * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long + * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ -int sk_wait_data(struct sock *sk, long *timeo) +int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { int rc; DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue)); + rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); finish_wait(sk_sleep(sk), &wait); return rc; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 52a94016526d..b5cf13a28009 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -886,7 +886,7 @@ verify_sock_status: break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); continue; found_ok_skb: if (len > skb->len) diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index f46e4d1306f2..214d44aef35b 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -207,7 +207,7 @@ found: } else { fq->q.meat += skb->len; } - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { @@ -287,7 +287,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, clone->data_len = clone->len; head->data_len -= clone->len; head->len -= clone->len; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } WARN_ON(head == NULL); @@ -310,7 +310,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&fq->q, sum_truesize); + sub_frag_mem_limit(fq->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 933a92820d26..6c8b1fbafce8 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1017,14 +1017,16 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) neigh = neigh_lookup(&arp_tbl, &ip, dev); if (neigh) { - read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); - r->arp_flags = arp_state_to_flags(neigh); - read_unlock_bh(&neigh->lock); - r->arp_ha.sa_family = dev->type; - strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); + if (!(neigh->nud_state & NUD_NOARP)) { + read_lock_bh(&neigh->lock); + memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + r->arp_flags = arp_state_to_flags(neigh); + read_unlock_bh(&neigh->lock); + r->arp_ha.sa_family = dev->type; + strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); + err = 0; + } neigh_release(neigh); - err = 0; } return err; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e813196c91c7..2d9cb1748f81 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -882,7 +882,6 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); - blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } return 0; } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index c6211ed60b03..9c02920725db 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -13,6 +13,7 @@ struct fib_alias { u8 fa_state; u8 fa_slen; u32 tb_id; + s16 fa_default; struct rcu_head rcu; }; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c7358ea4ae93..3a06586b170c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1202,23 +1202,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) } /* Must be invoked inside of an RCU protected region. */ -void fib_select_default(struct fib_result *res) +void fib_select_default(const struct flowi4 *flp, struct fib_result *res) { struct fib_info *fi = NULL, *last_resort = NULL; struct hlist_head *fa_head = res->fa_head; struct fib_table *tb = res->table; + u8 slen = 32 - res->prefixlen; int order = -1, last_idx = -1; - struct fib_alias *fa; + struct fib_alias *fa, *fa1 = NULL; + u32 last_prio = res->fi->fib_priority; + u8 last_tos = 0; hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; + if (fa->fa_slen != slen) + continue; + if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + continue; + if (fa->tb_id != tb->tb_id) + continue; + if (next_fi->fib_priority > last_prio && + fa->fa_tos == last_tos) { + if (last_tos) + continue; + break; + } + if (next_fi->fib_flags & RTNH_F_DEAD) + continue; + last_tos = fa->fa_tos; + last_prio = next_fi->fib_priority; + if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; - - if (next_fi->fib_priority > res->fi->fib_priority) - break; if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) continue; @@ -1228,10 +1245,11 @@ void fib_select_default(struct fib_result *res) if (!fi) { if (next_fi != res->fi) break; + fa1 = fa; } else if (!fib_detect_death(fi, order, &last_resort, - &last_idx, tb->tb_default)) { + &last_idx, fa1->fa_default)) { fib_result_assign(res, fi); - tb->tb_default = order; + fa1->fa_default = order; goto out; } fi = next_fi; @@ -1239,20 +1257,21 @@ void fib_select_default(struct fib_result *res) } if (order <= 0 || !fi) { - tb->tb_default = -1; + if (fa1) + fa1->fa_default = -1; goto out; } if (!fib_detect_death(fi, order, &last_resort, &last_idx, - tb->tb_default)) { + fa1->fa_default)) { fib_result_assign(res, fi); - tb->tb_default = order; + fa1->fa_default = order; goto out; } if (last_idx >= 0) fib_result_assign(res, last_resort); - tb->tb_default = last_idx; + fa1->fa_default = last_idx; out: return; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 15d32612e3c6..37c4bb89a708 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; + new_fa->fa_default = -1; err = switchdev_fib_ipv4_add(key, plen, fi, new_fa->fa_tos, @@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; + new_fa->fa_default = -1; /* (Optionally) offload fib entry to switch hardware. */ err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type, @@ -1791,8 +1793,6 @@ void fib_table_flush_external(struct fib_table *tb) if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); - } else { - leaf_pull_suffix(pn, n); } } } @@ -1862,8 +1862,6 @@ int fib_table_flush(struct fib_table *tb) if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); - } else { - leaf_pull_suffix(pn, n); } } @@ -1990,7 +1988,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) return NULL; tb->tb_id = id; - tb->tb_default = -1; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 5e346a082e5f..d0a7c0319e3d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -131,34 +131,22 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) unsigned int evicted = 0; HLIST_HEAD(expired); -evict_again: spin_lock(&hb->chain_lock); hlist_for_each_entry_safe(fq, n, &hb->chain, list) { if (!inet_fragq_should_evict(fq)) continue; - if (!del_timer(&fq->timer)) { - /* q expiring right now thus increment its refcount so - * it won't be freed under us and wait until the timer - * has finished executing then destroy it - */ - atomic_inc(&fq->refcnt); - spin_unlock(&hb->chain_lock); - del_timer_sync(&fq->timer); - inet_frag_put(fq, f); - goto evict_again; - } + if (!del_timer(&fq->timer)) + continue; - fq->flags |= INET_FRAG_EVICTED; - hlist_del(&fq->list); - hlist_add_head(&fq->list, &expired); + hlist_add_head(&fq->list_evictor, &expired); ++evicted; } spin_unlock(&hb->chain_lock); - hlist_for_each_entry_safe(fq, n, &expired, list) + hlist_for_each_entry_safe(fq, n, &expired, list_evictor) f->frag_expire((unsigned long) fq); return evicted; @@ -240,18 +228,20 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) int i; nf->low_thresh = 0; - local_bh_disable(); evict_again: + local_bh_disable(); seq = read_seqbegin(&f->rnd_seqlock); for (i = 0; i < INETFRAGS_HASHSZ ; i++) inet_evict_bucket(f, &f->hash[i]); - if (read_seqretry(&f->rnd_seqlock, seq)) - goto evict_again; - local_bh_enable(); + cond_resched(); + + if (read_seqretry(&f->rnd_seqlock, seq) || + percpu_counter_sum(&nf->mem)) + goto evict_again; percpu_counter_destroy(&nf->mem); } @@ -284,8 +274,8 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) struct inet_frag_bucket *hb; hb = get_frag_bucket_locked(fq, f); - if (!(fq->flags & INET_FRAG_EVICTED)) - hlist_del(&fq->list); + hlist_del(&fq->list); + fq->flags |= INET_FRAG_COMPLETE; spin_unlock(&hb->chain_lock); } @@ -297,7 +287,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); atomic_dec(&fq->refcnt); - fq->flags |= INET_FRAG_COMPLETE; } } EXPORT_SYMBOL(inet_frag_kill); @@ -330,11 +319,12 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) fp = xp; } sum = sum_truesize + f->qsize; - sub_frag_mem_limit(q, sum); if (f->destructor) f->destructor(q); kmem_cache_free(f->frags_cachep, q); + + sub_frag_mem_limit(nf, sum); } EXPORT_SYMBOL(inet_frag_destroy); @@ -390,7 +380,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, q->net = nf; f->constructor(q, arg); - add_frag_mem_limit(q, f->qsize); + add_frag_mem_limit(nf, f->qsize); setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 31f71b15cfba..921138f6c97c 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -202,7 +202,7 @@ static void ip_expire(unsigned long arg) ipq_kill(qp); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); - if (!(qp->q.flags & INET_FRAG_EVICTED)) { + if (!inet_frag_evicting(&qp->q)) { struct sk_buff *head = qp->q.fragments; const struct iphdr *iph; int err; @@ -309,7 +309,7 @@ static int ip_frag_reinit(struct ipq *qp) kfree_skb(fp); fp = xp; } while (fp); - sub_frag_mem_limit(&qp->q, sum_truesize); + sub_frag_mem_limit(qp->q.net, sum_truesize); qp->q.flags = 0; qp->q.len = 0; @@ -455,7 +455,7 @@ found: qp->q.fragments = next; qp->q.meat -= free_it->len; - sub_frag_mem_limit(&qp->q, free_it->truesize); + sub_frag_mem_limit(qp->q.net, free_it->truesize); kfree_skb(free_it); } } @@ -479,7 +479,7 @@ found: qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; - add_frag_mem_limit(&qp->q, skb->truesize); + add_frag_mem_limit(qp->q.net, skb->truesize); if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; @@ -587,7 +587,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - add_frag_mem_limit(&qp->q, clone->truesize); + add_frag_mem_limit(qp->q.net, clone->truesize); } skb_push(head, head->data - skb_network_header(head)); @@ -615,7 +615,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&qp->q, sum_truesize); + sub_frag_mem_limit(qp->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d0362a2de3d3..e681b852ced1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2176,7 +2176,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (!res.prefixlen && res.table->tb_num_default > 1 && res.type == RTN_UNICAST && !fl4->flowi4_oif) - fib_select_default(&res); + fib_select_default(fl4, &res); if (!fl4->saddr) fl4->saddr = FIB_RES_PREFSRC(net, res); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7f4056785acc..45534a5ab430 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -780,7 +780,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -1575,7 +1575,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - struct sk_buff *skb; + struct sk_buff *skb, *last; u32 urg_hole = 0; if (unlikely(flags & MSG_ERRQUEUE)) @@ -1635,7 +1635,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Next get a buffer. */ + last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { + last = skb; /* Now that we have two receive queues this * shouldn't happen. */ @@ -1754,8 +1756,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); - } else - sk_wait_data(sk, &timeo); + } else { + sk_wait_data(sk, &timeo, last); + } if (user_recv) { int chunk; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0a05b35a90fc..c53331cfed95 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1650,6 +1650,7 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; @@ -1664,6 +1665,11 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, ndisc_send_unsol_na(dev); in6_dev_put(idev); break; + case NETDEV_CHANGE: + change_info = ptr; + if (change_info->flags_changed & IFF_NOARP) + neigh_changeaddr(&nd_tbl, dev); + break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f187c8d8a1b..6d02498172c1 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -348,7 +348,7 @@ found: fq->ecn |= ecn; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -430,7 +430,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone->ip_summed = head->ip_summed; NFCT_FRAG6_CB(clone)->orig = NULL; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -454,7 +454,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; } - sub_frag_mem_limit(&fq->q, head->truesize); + sub_frag_mem_limit(fq->q.net, head->truesize); head->ignore_df = 1; head->next = NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 8ffa2c8cce77..f1159bb76e0a 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -144,7 +144,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - if (fq->q.flags & INET_FRAG_EVICTED) + if (inet_frag_evicting(&fq->q)) goto out_rcu_unlock; IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); @@ -330,7 +330,7 @@ found: fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -443,7 +443,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -481,7 +481,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&fq->q, sum_truesize); + sub_frag_mem_limit(fq->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8fd9febaa5ba..8dab4e569571 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -613,7 +613,7 @@ static int llc_wait_data(struct sock *sk, long timeo) if (signal_pending(current)) break; rc = 0; - if (sk_wait_data(sk, &timeo)) + if (sk_wait_data(sk, &timeo, NULL)) break; } return rc; @@ -802,7 +802,7 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, release_sock(sk); lock_sock(sk); } else - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) { net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n", diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5d2b806a862e..38fbc194b9cb 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -319,7 +319,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); @@ -467,7 +473,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 285eae3a1454..24c554201a76 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -842,15 +842,16 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, __ip_vs_dst_cache_reset(dest); spin_unlock_bh(&dest->dst_lock); - sched = rcu_dereference_protected(svc->scheduler, 1); if (add) { ip_vs_start_estimator(svc->net, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; - if (sched->add_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->add_dest) sched->add_dest(svc, dest); } else { - if (sched->upd_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->upd_dest) sched->upd_dest(svc, dest); } } @@ -1084,7 +1085,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_scheduler *sched; sched = rcu_dereference_protected(svc->scheduler, 1); - if (sched->del_dest) + if (sched && sched->del_dest) sched->del_dest(svc, dest); } } @@ -1175,11 +1176,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, ip_vs_use_count_inc(); /* Lookup the scheduler by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - ret = -ENOENT; - goto out_err; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + ret = -ENOENT; + goto out_err; + } } if (u->pe_name && *u->pe_name) { @@ -1240,10 +1244,12 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, spin_lock_init(&svc->stats.lock); /* Bind the scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) - goto out_err; - sched = NULL; + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) + goto out_err; + sched = NULL; + } /* Bind the ct retriever */ RCU_INIT_POINTER(svc->pe, pe); @@ -1291,17 +1297,20 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, static int ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) { - struct ip_vs_scheduler *sched, *old_sched; + struct ip_vs_scheduler *sched = NULL, *old_sched; struct ip_vs_pe *pe = NULL, *old_pe = NULL; int ret = 0; /* * Lookup the scheduler, by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - return -ENOENT; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + return -ENOENT; + } } old_sched = sched; @@ -1329,14 +1338,20 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) old_sched = rcu_dereference_protected(svc->scheduler, 1); if (sched != old_sched) { + if (old_sched) { + ip_vs_unbind_scheduler(svc, old_sched); + RCU_INIT_POINTER(svc->scheduler, NULL); + /* Wait all svc->sched_data users */ + synchronize_rcu(); + } /* Bind the new scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) { - old_sched = sched; - goto out; + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) { + ip_vs_scheduler_put(sched); + goto out; + } } - /* Unbind the old scheduler on success */ - ip_vs_unbind_scheduler(svc, old_sched); } /* @@ -1982,6 +1997,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; if (iter->table == ip_vs_svc_table) { #ifdef CONFIG_IP_VS_IPV6 @@ -1990,18 +2006,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), - sched->name); + sched_name); else #endif seq_printf(seq, "%s %08X:%04X %s %s ", ip_vs_proto_name(svc->protocol), ntohl(svc->addr.ip), ntohs(svc->port), - sched->name, + sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } else { seq_printf(seq, "FWM %08X %s %s", - svc->fwmark, sched->name, + svc->fwmark, sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } @@ -2427,13 +2443,15 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { struct ip_vs_scheduler *sched; struct ip_vs_kstats kstats; + char *sched_name; sched = rcu_dereference_protected(src->scheduler, 1); + sched_name = sched ? sched->name : "none"; dst->protocol = src->protocol; dst->addr = src->addr.ip; dst->port = src->port; dst->fwmark = src->fwmark; - strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name)); + strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name)); dst->flags = src->flags; dst->timeout = src->timeout / HZ; dst->netmask = src->netmask; @@ -2892,6 +2910,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, struct ip_vs_flags flags = { .flags = svc->flags, .mask = ~0 }; struct ip_vs_kstats kstats; + char *sched_name; nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE); if (!nl_service) @@ -2910,8 +2929,9 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, } sched = rcu_dereference_protected(svc->scheduler, 1); + sched_name = sched ? sched->name : "none"; pe = rcu_dereference_protected(svc->pe, 1); - if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) || + if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) || (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) || nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) || nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) || diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 199760c71f39..7e8141647943 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -74,7 +74,7 @@ void ip_vs_unbind_scheduler(struct ip_vs_service *svc, if (sched->done_service) sched->done_service(svc); - /* svc->scheduler can not be set to NULL */ + /* svc->scheduler can be set to NULL only by caller */ } @@ -147,21 +147,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler) void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg) { - struct ip_vs_scheduler *sched; + struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; - sched = rcu_dereference(svc->scheduler); if (svc->fwmark) { IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n", - sched->name, svc->fwmark, svc->fwmark, msg); + sched_name, svc->fwmark, svc->fwmark, msg); #ifdef CONFIG_IP_VS_IPV6 } else if (svc->af == AF_INET6) { IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), msg); #endif } else { IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.ip, ntohs(svc->port), msg); } } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index b08ba9538d12..d99ad93eb855 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -612,7 +612,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, pkts = atomic_add_return(1, &cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); - ip_vs_sync_conn(net, cp->control, pkts); + ip_vs_sync_conn(net, cp, pkts); } } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index bf66a8657a5f..258a0b0e82a2 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -130,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; - fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0; fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ? FLOWI_FLAG_KNOWN_NH : 0; @@ -505,6 +504,13 @@ err_put: return -1; err_unreach: + /* The ip6_link_failure function requires the dev field to be set + * in order to get the net (further for the sake of fwmark + * reflection). + */ + if (!skb->dev) + skb->dev = skb_dst(skb)->dev; + dst_link_failure(skb); return -1; } @@ -523,10 +529,27 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); } return ret; } +/* In the event of a remote destination, it's possible that we would have + * matches against an old socket (particularly a TIME-WAIT socket). This + * causes havoc down the line (ip_local_out et. al. expect regular sockets + * and invalid memory accesses will happen) so simply drop the association + * in this case. +*/ +static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb) +{ + /* If dev is set, the packet came from the LOCAL_IN callback and + * not from a local TCP socket. + */ + if (skb->dev) + skb_orphan(skb); +} + /* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, struct ip_vs_conn *cp, int local) @@ -538,12 +561,23 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 1); + + /* Remove the early_demux association unless it's bound for the + * exact same port and address on this host after translation. + */ + if (!local || cp->vport != cp->dport || + !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr)) + ip_vs_drop_early_demux_sk(skb); + if (!local) { skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else ret = NF_ACCEPT; + return ret; } @@ -557,7 +591,10 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (likely(!(cp->flags & IP_VS_CONN_F_NFCT))) ip_vs_notrack(skb); if (!local) { + ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else @@ -845,6 +882,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, struct ipv6hdr *old_ipv6h = NULL; #endif + ip_vs_drop_early_demux_sk(skb); + if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) { new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 13fad8668f83..651039ad1681 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -287,6 +287,46 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) spin_unlock(&pcpu->lock); } +/* Released via destroy_conntrack() */ +struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) +{ + struct nf_conn *tmpl; + + tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL); + if (tmpl == NULL) + return NULL; + + tmpl->status = IPS_TEMPLATE; + write_pnet(&tmpl->ct_net, net); + +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (zone) { + struct nf_conntrack_zone *nf_ct_zone; + + nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC); + if (!nf_ct_zone) + goto out_free; + nf_ct_zone->id = zone; + } +#endif + atomic_set(&tmpl->ct_general.use, 0); + + return tmpl; +#ifdef CONFIG_NF_CONNTRACK_ZONES +out_free: + kfree(tmpl); + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); + +static void nf_ct_tmpl_free(struct nf_conn *tmpl) +{ + nf_ct_ext_destroy(tmpl); + nf_ct_ext_free(tmpl); + kfree(tmpl); +} + static void destroy_conntrack(struct nf_conntrack *nfct) { @@ -298,6 +338,10 @@ destroy_conntrack(struct nf_conntrack *nfct) NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); + if (unlikely(nf_ct_is_template(ct))) { + nf_ct_tmpl_free(ct); + return; + } rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto && l4proto->destroy) @@ -540,28 +584,6 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); -/* deletion from this larval template list happens via nf_ct_put() */ -void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) -{ - struct ct_pcpu *pcpu; - - __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); - nf_conntrack_get(&tmpl->ct_general); - - /* add this conntrack to the (per cpu) tmpl list */ - local_bh_disable(); - tmpl->cpu = smp_processor_id(); - pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu); - - spin_lock(&pcpu->lock); - /* Overload tuple linked list to put us in template list. */ - hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &pcpu->tmpl); - spin_unlock_bh(&pcpu->lock); -} -EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); - /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) @@ -1751,7 +1773,6 @@ int nf_conntrack_init_net(struct net *net) spin_lock_init(&pcpu->lock); INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL); } net->ct.stat = alloc_percpu(struct ip_conntrack_stat); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 7a17070c5dab..b45a4223cb05 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -219,7 +219,8 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, a->mask.src.u3.all[count] & b->mask.src.u3.all[count]; } - return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask); + return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) && + nf_ct_zone(a->master) == nf_ct_zone(b->master); } static inline int expect_matches(const struct nf_conntrack_expect *a, diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d1c23940a86a..6b8b0abbfab4 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2995,11 +2995,6 @@ ctnetlink_create_expect(struct net *net, u16 zone, } err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) - goto err_exp; - - return 0; -err_exp: nf_ct_expect_put(exp); err_ct: nf_ct_put(ct); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 789feeae6c44..71f1e9fdfa18 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -349,12 +349,10 @@ static void __net_exit synproxy_proc_exit(struct net *net) static int __net_init synproxy_net_init(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); - struct nf_conntrack_tuple t; struct nf_conn *ct; int err = -ENOMEM; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL); + ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL); if (IS_ERR(ct)) { err = PTR_ERR(ct); goto err1; @@ -365,7 +363,8 @@ static int __net_init synproxy_net_init(struct net *net) if (!nfct_synproxy_ext_add(ct)) goto err2; - nf_conntrack_tmpl_insert(net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 75747aecdebe..c6630030c912 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -184,7 +184,6 @@ out: static int xt_ct_tg_check(const struct xt_tgchk_param *par, struct xt_ct_target_info_v1 *info) { - struct nf_conntrack_tuple t; struct nf_conn *ct; int ret = -EOPNOTSUPP; @@ -202,8 +201,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err1; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL); + ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL); ret = PTR_ERR(ct); if (IS_ERR(ct)) goto err2; @@ -227,8 +225,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err3; } - - nf_conntrack_tmpl_insert(par->net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); out: info->ct = ct; return 0; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f407ebc13481..29d2c31f406c 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -126,6 +126,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { ret = -ENOMEM; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c9e8741226c6..ed458b315ef4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2403,7 +2403,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, addr, hlen); - if (tp_len > dev->mtu + dev->hard_header_len) { + if (likely(tp_len >= 0) && + tp_len > dev->mtu + dev->hard_header_len) { struct ethhdr *ehdr; /* Earlier code assumed this would be a VLAN pkt, * double-check this now that we have the actual @@ -2784,7 +2785,7 @@ static int packet_release(struct socket *sock) static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) { struct packet_sock *po = pkt_sk(sk); - const struct net_device *dev_curr; + struct net_device *dev_curr; __be16 proto_curr; bool need_rehook; @@ -2808,15 +2809,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) po->num = proto; po->prot_hook.type = proto; - - if (po->prot_hook.dev) - dev_put(po->prot_hook.dev); - po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; packet_cached_dev_assign(po, dev); } + if (dev_curr) + dev_put(dev_curr); if (proto == 0 || !need_rehook) goto out_unlock; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index af427a3dbcba..43ec92680ae8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -45,7 +45,7 @@ void tcf_hash_destroy(struct tc_action *a) } EXPORT_SYMBOL(tcf_hash_destroy); -int tcf_hash_release(struct tc_action *a, int bind) +int __tcf_hash_release(struct tc_action *a, bool bind, bool strict) { struct tcf_common *p = a->priv; int ret = 0; @@ -53,7 +53,7 @@ int tcf_hash_release(struct tc_action *a, int bind) if (p) { if (bind) p->tcfc_bindcnt--; - else if (p->tcfc_bindcnt > 0) + else if (strict && p->tcfc_bindcnt > 0) return -EPERM; p->tcfc_refcnt--; @@ -64,9 +64,10 @@ int tcf_hash_release(struct tc_action *a, int bind) ret = 1; } } + return ret; } -EXPORT_SYMBOL(tcf_hash_release); +EXPORT_SYMBOL(__tcf_hash_release); static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, struct tc_action *a) @@ -136,7 +137,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; hlist_for_each_entry_safe(p, n, head, tcfc_head) { a->priv = p; - ret = tcf_hash_release(a, 0); + ret = __tcf_hash_release(a, false, true); if (ret == ACT_P_DELETED) { module_put(a->ops->owner); n_i++; @@ -408,7 +409,7 @@ int tcf_action_destroy(struct list_head *actions, int bind) int ret = 0; list_for_each_entry_safe(a, tmp, actions, list) { - ret = tcf_hash_release(a, bind); + ret = __tcf_hash_release(a, bind, true); if (ret == ACT_P_DELETED) module_put(a->ops->owner); else if (ret < 0) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 1df78289e248..d0edeb7a1950 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -27,9 +27,10 @@ struct tcf_bpf_cfg { struct bpf_prog *filter; struct sock_filter *bpf_ops; - char *bpf_name; + const char *bpf_name; u32 bpf_fd; u16 bpf_num_ops; + bool is_ebpf; }; static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, @@ -207,6 +208,7 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) cfg->bpf_ops = bpf_ops; cfg->bpf_num_ops = bpf_num_ops; cfg->filter = fp; + cfg->is_ebpf = false; return 0; } @@ -241,18 +243,40 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) cfg->bpf_fd = bpf_fd; cfg->bpf_name = name; cfg->filter = fp; + cfg->is_ebpf = true; return 0; } +static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) +{ + if (cfg->is_ebpf) + bpf_prog_put(cfg->filter); + else + bpf_prog_destroy(cfg->filter); + + kfree(cfg->bpf_ops); + kfree(cfg->bpf_name); +} + +static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, + struct tcf_bpf_cfg *cfg) +{ + cfg->is_ebpf = tcf_bpf_is_ebpf(prog); + cfg->filter = prog->filter; + + cfg->bpf_ops = prog->bpf_ops; + cfg->bpf_name = prog->bpf_name; +} + static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *act, int replace, int bind) { struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; - struct tcf_bpf_cfg cfg; bool is_bpf, is_ebpf; int ret; @@ -301,6 +325,9 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, prog = to_bpf(act); spin_lock_bh(&prog->tcf_lock); + if (ret != ACT_P_CREATED) + tcf_bpf_prog_fill_cfg(prog, &old); + prog->bpf_ops = cfg.bpf_ops; prog->bpf_name = cfg.bpf_name; @@ -316,32 +343,22 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (ret == ACT_P_CREATED) tcf_hash_insert(act); + else + tcf_bpf_cfg_cleanup(&old); return ret; destroy_fp: - if (is_ebpf) - bpf_prog_put(cfg.filter); - else - bpf_prog_destroy(cfg.filter); - - kfree(cfg.bpf_ops); - kfree(cfg.bpf_name); - + tcf_bpf_cfg_cleanup(&cfg); return ret; } static void tcf_bpf_cleanup(struct tc_action *act, int bind) { - const struct tcf_bpf *prog = act->priv; - - if (tcf_bpf_is_ebpf(prog)) - bpf_prog_put(prog->filter); - else - bpf_prog_destroy(prog->filter); + struct tcf_bpf_cfg tmp; - kfree(prog->bpf_ops); - kfree(prog->bpf_name); + tcf_bpf_prog_fill_cfg(act->priv, &tmp); + tcf_bpf_cfg_cleanup(&tmp); } static struct tc_action_ops act_bpf_ops __read_mostly = { diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 17e6d6669c7f..ff8b466a73f6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -68,13 +68,12 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; } else { - p = to_pedit(a); - tcf_hash_release(a, bind); if (bind) return 0; + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; - + p = to_pedit(a); if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) { keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 93d5742dc7e0..6a783afe4960 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -385,6 +385,19 @@ static void choke_reset(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); + while (q->head != q->tail) { + struct sk_buff *skb = q->tab[q->head]; + + q->head = (q->head + 1) & q->tab_mask; + if (!skb) + continue; + qdisc_qstats_backlog_dec(sch, skb); + --sch->q.qlen; + qdisc_drop(skb, sch); + } + + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + q->head = q->tail = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 89f8fcf73f18..ade9445a55ab 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -216,6 +216,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .peek = qdisc_peek_head, .init = plug_init, .change = plug_change, + .reset = qdisc_reset_queue, .owner = THIS_MODULE, }; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1425ec2bbd5a..17bef01b9aa3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2200,12 +2200,6 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) return -EFAULT; - if (sctp_sk(sk)->subscribe.sctp_data_io_event) - pr_warn_ratelimited(DEPRECATED "%s (pid %d) " - "Requested SCTP_SNDRCVINFO event.\n" - "Use SCTP_RCVINFO through SCTP_RECVRCVINFO option instead.\n", - current->comm, task_pid_nr(current)); - /* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, * if there is no data to be sent or retransmit, the stack will * immediately send up this notification. |