diff options
author | Ingo Molnar <mingo@kernel.org> | 2013-10-09 12:36:13 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2013-10-09 12:36:13 +0200 |
commit | 37bf06375c90a42fe07b9bebdb07bc316ae5a0ce (patch) | |
tree | de572dd6d3955b0725001776a7b03796f99e1e8e /net | |
parent | 6bfa687c19b7ab8adee03f0d43c197c2945dd869 (diff) | |
parent | d0e639c9e06d44e713170031fe05fb60ebe680af (diff) | |
download | op-kernel-dev-37bf06375c90a42fe07b9bebdb07bc316ae5a0ce.zip op-kernel-dev-37bf06375c90a42fe07b9bebdb07bc316ae5a0ce.tar.gz |
Merge tag 'v3.12-rc4' into sched/core
Merge Linux v3.12-rc4 to fix a conflict and also to refresh the tree
before applying more scheduler patches.
Conflicts:
arch/avr32/include/asm/Kbuild
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'net')
63 files changed, 640 insertions, 453 deletions
diff --git a/net/802/mrp.c b/net/802/mrp.c index 1eb05d8..3ed6162 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -24,6 +24,11 @@ static unsigned int mrp_join_time __read_mostly = 200; module_param(mrp_join_time, uint, 0644); MODULE_PARM_DESC(mrp_join_time, "Join time in ms (default 200ms)"); + +static unsigned int mrp_periodic_time __read_mostly = 1000; +module_param(mrp_periodic_time, uint, 0644); +MODULE_PARM_DESC(mrp_periodic_time, "Periodic time in ms (default 1s)"); + MODULE_LICENSE("GPL"); static const u8 @@ -595,6 +600,24 @@ static void mrp_join_timer(unsigned long data) mrp_join_timer_arm(app); } +static void mrp_periodic_timer_arm(struct mrp_applicant *app) +{ + mod_timer(&app->periodic_timer, + jiffies + msecs_to_jiffies(mrp_periodic_time)); +} + +static void mrp_periodic_timer(unsigned long data) +{ + struct mrp_applicant *app = (struct mrp_applicant *)data; + + spin_lock(&app->lock); + mrp_mad_event(app, MRP_EVENT_PERIODIC); + mrp_pdu_queue(app); + spin_unlock(&app->lock); + + mrp_periodic_timer_arm(app); +} + static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) { __be16 endmark; @@ -845,6 +868,9 @@ int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); setup_timer(&app->join_timer, mrp_join_timer, (unsigned long)app); mrp_join_timer_arm(app); + setup_timer(&app->periodic_timer, mrp_periodic_timer, + (unsigned long)app); + mrp_periodic_timer_arm(app); return 0; err3: @@ -870,6 +896,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) * all pending messages before the applicant is gone. */ del_timer_sync(&app->join_timer); + del_timer_sync(&app->periodic_timer); spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 4493913..813db4e 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -168,6 +168,7 @@ static int batadv_interface_tx(struct sk_buff *skb, case ETH_P_8021Q: vhdr = (struct vlan_ethhdr *)skb->data; vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + vid |= BATADV_VLAN_HAS_TAG; if (vhdr->h_vlan_encapsulated_proto != ethertype) break; @@ -331,6 +332,7 @@ void batadv_interface_rx(struct net_device *soft_iface, case ETH_P_8021Q: vhdr = (struct vlan_ethhdr *)skb->data; vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + vid |= BATADV_VLAN_HAS_TAG; if (vhdr->h_vlan_encapsulated_proto != ethertype) break; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 634deba..fb7356f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1146,7 +1146,11 @@ int hci_dev_open(__u16 dev) goto done; } - if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) { + /* Check for rfkill but allow the HCI setup stage to proceed + * (which in itself doesn't cause any RF activity). + */ + if (test_bit(HCI_RFKILLED, &hdev->dev_flags) && + !test_bit(HCI_SETUP, &hdev->dev_flags)) { ret = -ERFKILL; goto done; } @@ -1566,10 +1570,13 @@ static int hci_rfkill_set_block(void *data, bool blocked) BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); - if (!blocked) - return 0; - - hci_dev_do_close(hdev); + if (blocked) { + set_bit(HCI_RFKILLED, &hdev->dev_flags); + if (!test_bit(HCI_SETUP, &hdev->dev_flags)) + hci_dev_do_close(hdev); + } else { + clear_bit(HCI_RFKILLED, &hdev->dev_flags); + } return 0; } @@ -1591,9 +1598,13 @@ static void hci_power_on(struct work_struct *work) return; } - if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) { + clear_bit(HCI_AUTO_OFF, &hdev->dev_flags); + hci_dev_do_close(hdev); + } else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); + } if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) mgmt_index_added(hdev); @@ -2209,6 +2220,9 @@ int hci_register_dev(struct hci_dev *hdev) } } + if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) + set_bit(HCI_RFKILLED, &hdev->dev_flags); + set_bit(HCI_SETUP, &hdev->dev_flags); if (hdev->dev_type != HCI_AMP) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 94aab73..8db3e89 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3557,7 +3557,11 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) cp.handle = cpu_to_le16(conn->handle); if (ltk->authenticated) - conn->sec_level = BT_SECURITY_HIGH; + conn->pending_sec_level = BT_SECURITY_HIGH; + else + conn->pending_sec_level = BT_SECURITY_MEDIUM; + + conn->enc_key_size = ltk->enc_size; hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b3bb7bc..63fa111 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3755,6 +3755,13 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, sk = chan->sk; + /* For certain devices (ex: HID mouse), support for authentication, + * pairing and bonding is optional. For such devices, inorder to avoid + * the ACL alive for too long after L2CAP disconnection, reset the ACL + * disc_timeout back to HCI_DISCONN_TIMEOUT during L2CAP connect. + */ + conn->hcon->disc_timeout = HCI_DISCONN_TIMEOUT; + bacpy(&bt_sk(sk)->src, conn->src); bacpy(&bt_sk(sk)->dst, conn->dst); chan->psm = psm; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 6d126fa..84fcf9f 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -569,7 +569,6 @@ static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb) static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) { struct rfcomm_dev *dev = dlc->owner; - struct tty_struct *tty; if (!dev) return; @@ -581,38 +580,8 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) DPM_ORDER_DEV_AFTER_PARENT); wake_up_interruptible(&dev->port.open_wait); - } else if (dlc->state == BT_CLOSED) { - tty = tty_port_tty_get(&dev->port); - if (!tty) { - if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { - /* Drop DLC lock here to avoid deadlock - * 1. rfcomm_dev_get will take rfcomm_dev_lock - * but in rfcomm_dev_add there's lock order: - * rfcomm_dev_lock -> dlc lock - * 2. tty_port_put will deadlock if it's - * the last reference - * - * FIXME: when we release the lock anything - * could happen to dev, even its destruction - */ - rfcomm_dlc_unlock(dlc); - if (rfcomm_dev_get(dev->id) == NULL) { - rfcomm_dlc_lock(dlc); - return; - } - - if (!test_and_set_bit(RFCOMM_TTY_RELEASED, - &dev->flags)) - tty_port_put(&dev->port); - - tty_port_put(&dev->port); - rfcomm_dlc_lock(dlc); - } - } else { - tty_hangup(tty); - tty_kref_put(tty); - } - } + } else if (dlc->state == BT_CLOSED) + tty_port_tty_hangup(&dev->port, false); } static void rfcomm_dev_modem_status(struct rfcomm_dlc *dlc, u8 v24_sig) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index b9259ef..e74ddc1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -207,7 +207,7 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask) { int err = 0; - struct net_bridge_port *port = br_port_get_rcu(dev); + struct net_bridge_port *port = br_port_get_rtnl(dev); /* not a bridge port and */ if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) @@ -451,7 +451,7 @@ static size_t br_get_link_af_size(const struct net_device *dev) struct net_port_vlans *pv; if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rcu(dev)); + pv = nbp_get_vlan_info(br_port_get_rtnl(dev)); else if (dev->priv_flags & IFF_EBRIDGE) pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); else diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 598cb0b..efb57d9 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -202,13 +202,10 @@ struct net_bridge_port static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) { - struct net_bridge_port *port = - rcu_dereference_rtnl(dev->rx_handler_data); - - return br_port_exists(dev) ? port : NULL; + return rcu_dereference(dev->rx_handler_data); } -static inline struct net_bridge_port *br_port_get_rtnl(struct net_device *dev) +static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *dev) { return br_port_exists(dev) ? rtnl_dereference(dev->rx_handler_data) : NULL; @@ -746,6 +743,7 @@ extern struct net_bridge_port *br_get_port(struct net_bridge *br, extern void br_init_port(struct net_bridge_port *p); extern void br_become_designated_port(struct net_bridge_port *p); +extern void __br_set_forward_delay(struct net_bridge *br, unsigned long t); extern int br_set_forward_delay(struct net_bridge *br, unsigned long x); extern int br_set_hello_time(struct net_bridge *br, unsigned long x); extern int br_set_max_age(struct net_bridge *br, unsigned long x); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 1c0a50f..3c86f05 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -209,7 +209,7 @@ static void br_record_config_information(struct net_bridge_port *p, p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies - + (p->br->max_age - bpdu->message_age)); + + (bpdu->max_age - bpdu->message_age)); } /* called under bridge lock */ @@ -544,18 +544,27 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) } +void __br_set_forward_delay(struct net_bridge *br, unsigned long t) +{ + br->bridge_forward_delay = t; + if (br_is_root_bridge(br)) + br->forward_delay = br->bridge_forward_delay; +} + int br_set_forward_delay(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); + int err = -ERANGE; + spin_lock_bh(&br->lock); if (br->stp_enabled != BR_NO_STP && (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) - return -ERANGE; + goto unlock; - spin_lock_bh(&br->lock); - br->bridge_forward_delay = t; - if (br_is_root_bridge(br)) - br->forward_delay = br->bridge_forward_delay; + __br_set_forward_delay(br, t); + err = 0; + +unlock: spin_unlock_bh(&br->lock); - return 0; + return err; } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index d45e760..108084a 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -129,6 +129,14 @@ static void br_stp_start(struct net_bridge *br) char *envp[] = { NULL }; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + + spin_lock_bh(&br->lock); + + if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); + else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); + if (r == 0) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); @@ -137,10 +145,10 @@ static void br_stp_start(struct net_bridge *br) br_debug(br, "using kernel STP\n"); /* To start timers on any ports left in blocking */ - spin_lock_bh(&br->lock); br_port_state_selection(br); - spin_unlock_bh(&br->lock); } + + spin_unlock_bh(&br->lock); } static void br_stp_stop(struct net_bridge *br) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 1606f74..2b4b32a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2216,6 +2216,17 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc) EXPORT_SYMBOL(ceph_osdc_sync); /* + * Call all pending notify callbacks - for use after a watch is + * unregistered, to make sure no more callbacks for it will be invoked + */ +extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc) +{ + flush_workqueue(osdc->notify_wq); +} +EXPORT_SYMBOL(ceph_osdc_flush_notifies); + + +/* * init, shutdown */ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) diff --git a/net/core/dev.c b/net/core/dev.c index 5c713f2..65f829c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5247,10 +5247,12 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); +static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); + dev_net(dev)->dev_unreg_count++; } static void rollback_registered_many(struct list_head *head) @@ -5918,6 +5920,12 @@ void netdev_run_todo(void) if (dev->destructor) dev->destructor(dev); + /* Report a network device has been unregistered */ + rtnl_lock(); + dev_net(dev)->dev_unreg_count--; + __rtnl_unlock(); + wake_up(&netdev_unregistering_wq); + /* Free network device */ kobject_put(&dev->dev.kobj); } @@ -6603,6 +6611,34 @@ static void __net_exit default_device_exit(struct net *net) rtnl_unlock(); } +static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) +{ + /* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace in net_list. + */ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network @@ -6614,7 +6650,18 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); - rtnl_lock(); + /* To prevent network device cleanup code from dereferencing + * loopback devices or network devices that have been freed + * wait here for all pending unregistrations to complete, + * before unregistring the loopback device and allowing the + * network namespace be freed. + * + * The netdev todo list containing all network devices + * unregistrations that happen in default_device_exit_batch + * will run in the rtnl_unlock() at the end of + * default_device_exit_batch. + */ + rtnl_lock_unregistering(net_list); list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 1929af8..8d7d0dd 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -154,8 +154,8 @@ ipv6: if (poff >= 0) { __be32 *ports, _ports; - nhoff += poff; - ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports); + ports = skb_header_pointer(skb, nhoff + poff, + sizeof(_ports), &_ports); if (ports) flow->ports = *ports; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2c637e9..fc75c9e 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -550,7 +550,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo return; proto = ntohs(eth_hdr(skb)->h_proto); - if (proto == ETH_P_IP) { + if (proto == ETH_P_ARP) { struct arphdr *arp; unsigned char *arp_ptr; /* No arp on this interface */ @@ -1284,15 +1284,14 @@ EXPORT_SYMBOL_GPL(__netpoll_free_async); void netpoll_cleanup(struct netpoll *np) { - if (!np->dev) - return; - rtnl_lock(); + if (!np->dev) + goto out; __netpoll_cleanup(np); - rtnl_unlock(); - dev_put(np->dev); np->dev = NULL; +out: + rtnl_unlock(); } EXPORT_SYMBOL(netpoll_cleanup); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 6a2f13c..3f1ec15 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -10,11 +10,24 @@ #include <net/secure_seq.h> -static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; +#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) -void net_secret_init(void) +static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; + +static void net_secret_init(void) { - get_random_bytes(net_secret, sizeof(net_secret)); + u32 tmp; + int i; + + if (likely(net_secret[0])) + return; + + for (i = NET_SECRET_SIZE; i > 0;) { + do { + get_random_bytes(&tmp, sizeof(tmp)); + } while (!tmp); + cmpxchg(&net_secret[--i], 0, tmp); + } } #ifdef CONFIG_INET @@ -42,6 +55,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32)daddr[i]; @@ -63,6 +77,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32) daddr[i]; @@ -82,6 +97,7 @@ __u32 secure_ip_id(__be32 daddr) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force __u32) daddr; hash[1] = net_secret[13]; hash[2] = net_secret[14]; @@ -96,6 +112,7 @@ __u32 secure_ipv6_id(const __be32 daddr[4]) { __u32 hash[4]; + net_secret_init(); memcpy(hash, daddr, 16); md5_transform(hash, net_secret); @@ -107,6 +124,7 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -121,6 +139,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = (__force u32)dport ^ net_secret[14]; @@ -140,6 +159,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, u32 hash[MD5_DIGEST_WORDS]; u64 seq; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -164,6 +184,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, u64 seq; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + daddr[i]; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c61f9c..6cf9f77 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -135,6 +135,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (dst) dst->ops->redirect(dst, sk, skb); + goto out; } if (type == ICMPV6_PKT_TOOBIG) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7a1874b..cfeb85c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -263,10 +263,8 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) { + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); - net_secret_init(); - } } EXPORT_SYMBOL(build_ehash_secret); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d6c0e64..7defdc9 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(pip, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -736,7 +736,7 @@ static void igmp_gq_timer_expire(unsigned long data) in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_timer_expire(unsigned long data) @@ -749,7 +749,7 @@ static void igmp_ifc_timer_expire(unsigned long data) igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 000e3d2..33d5537 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -32,8 +32,8 @@ * At the moment of writing this notes identifier of IP packets is generated * to be unpredictable using this code only for packets subjected * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size uses a constant ID and do not use this code (see - * ip_select_ident() in include/net/ip.h). + * PMTU in size when local fragmentation is disabled use a constant ID and do + * not use this code (see ip_select_ident() in include/net/ip.h). * * Route cache entries hold references to our nodes. * New cache entries get references via lookup by destination IP address in diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9ee17e3..a04d872 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, &rt->dst, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -386,7 +386,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(iph, &rt->dst, sk, + ip_select_ident_more(skb, &rt->dst, sk, (skb_shinfo(skb)->gso_segs ?: 1) - 1); skb->priority = sk->sk_priority; @@ -1316,7 +1316,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, else ttl = ip_select_ttl(inet, &rt->dst); - iph = (struct iphdr *)skb->data; + iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = inet->tos; @@ -1324,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, &rt->dst, sk); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index ac9fabe0..63a6d6d 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -623,6 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_count = 0; } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) @@ -641,18 +642,17 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len; - if (max_headroom > dev->needed_headroom) { + if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; - if (skb_cow_head(skb, dev->needed_headroom)) { - dev->stats.tx_dropped++; - dev_kfree_skb(skb); - return; - } + + if (skb_cow_head(skb, dev->needed_headroom)) { + dev->stats.tx_dropped++; + dev_kfree_skb(skb); + return; } err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol, - ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df, - !net_eq(tunnel->net, dev_net(dev))); + tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return; @@ -853,8 +853,10 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - if (!IS_ERR(itn->fb_tunnel_dev)) + if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); + } rtnl_unlock(); return PTR_RET(itn->fb_tunnel_dev); @@ -884,8 +886,6 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head, if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); } - if (itn->fb_tunnel_dev) - unregister_netdevice_queue(itn->fb_tunnel_dev, head); } void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d6c856b..c31e3ad 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -61,7 +61,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, memset(IPCB(skb), 0, sizeof(*IPCB(skb))); /* Push down and install the IP header. */ - __skb_push(skb, sizeof(struct iphdr)); + skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9ae54b0..62212c7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1658,7 +1658,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(iph, skb_dst(skb), NULL); + ip_select_ident(skb, skb_dst(skb), NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 67e17dc..b6346bf 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -267,7 +267,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -350,7 +351,8 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -373,7 +375,9 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a86c7ae..193db03 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -218,8 +218,10 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_sk_update_pmtu(skb, sk, info); - else if (type == ICMP_REDIRECT) + else if (type == ICMP_REDIRECT) { ipv4_sk_redirect(skb, sk); + return; + } /* Report error on raw socket, if: 1. User requested ip_recverr. @@ -387,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4a22f3e..52f3c6b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -502,7 +502,9 @@ reset: * ACKs, wait for troubles. */ if (crtt > tp->srtt) { - inet_csk(sk)->icsk_rto = crtt + max(crtt >> 2, tcp_rto_min(sk)); + /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ + crtt >>= 3; + inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7c83cb8..e6bb825 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -895,8 +895,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_orphan(skb); skb->sk = sk; - skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? - tcp_wfree : sock_wfree; + skb->destructor = tcp_wfree; atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ @@ -1840,7 +1839,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; - tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1869,13 +1867,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } - /* TSQ : sk_wmem_alloc accounts skb truesize, - * including skb overhead. But thats OK. + /* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates */ - if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + limit = max(skb->truesize, sk->sk_pacing_rate >> 10); + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); break; } + limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 74d2c95..0ca44df 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -658,7 +658,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) break; case ICMP_REDIRECT: ipv4_sk_redirect(skb, sk); - break; + goto out; } /* diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index eb1dd4d..b5663c3 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -117,7 +117,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(top_iph, dst->child, NULL); + ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d6ff126..cd3fb30 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1499,6 +1499,33 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, return false; } +/* Compares an address/prefix_len with addresses on device @dev. + * If one is found it returns true. + */ +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; + 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) { + ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); + if (ret) + break; + } + read_unlock_bh(&idev->lock); + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(ipv6_chk_custom_prefix); + int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { struct inet6_dev *idev; @@ -2193,43 +2220,21 @@ ok: else stored_lft = 0; if (!update_lft && !create && stored_lft) { - if (valid_lft > MIN_VALID_LIFETIME || - valid_lft > stored_lft) - update_lft = 1; - else if (stored_lft <= MIN_VALID_LIFETIME) { - /* valid_lft <= stored_lft is always true */ - /* - * RFC 4862 Section 5.5.3e: - * "Note that the preferred lifetime of - * the corresponding address is always - * reset to the Preferred Lifetime in - * the received Prefix Information - * option, regardless of whether the - * valid lifetime is also reset or - * ignored." - * - * So if the preferred lifetime in - * this advertisement is different - * than what we have stored, but the - * valid lifetime is invalid, just - * reset prefered_lft. - * - * We must set the valid lifetime - * to the stored lifetime since we'll - * be updating the timestamp below, - * else we'll set it back to the - * minimum. - */ - if (prefered_lft != ifp->prefered_lft) { - valid_lft = stored_lft; - update_lft = 1; - } - } else { - valid_lft = MIN_VALID_LIFETIME; - if (valid_lft < prefered_lft) - prefered_lft = valid_lft; - update_lft = 1; - } + const u32 minimum_lft = min( + stored_lft, (u32)MIN_VALID_LIFETIME); + valid_lft = max(valid_lft, minimum_lft); + + /* RFC4862 Section 5.5.3e: + * "Note that the preferred lifetime of the + * corresponding address is always reset to + * the Preferred Lifetime in the received + * Prefix Information option, regardless of + * whether the valid lifetime is also reset or + * ignored." + * + * So we should always update prefered_lft here. + */ + update_lft = 1; } if (update_lft) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 6b26e9f..7bb5446 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -618,7 +618,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, struct ip6_tnl *tunnel = netdev_priv(dev); struct net_device *tdev; /* Device to other host */ struct ipv6hdr *ipv6h; /* Our new IP header */ - unsigned int max_headroom; /* The extra header space needed */ + unsigned int max_headroom = 0; /* The extra header space needed */ int gre_hlen; struct ipv6_tel_txoption opt; int mtu; @@ -693,7 +693,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); - max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; + max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3a692d5..a54c45c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1015,6 +1015,8 @@ static inline int ip6_ufo_append_data(struct sock *sk, * udp datagram */ if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) { + struct frag_hdr fhdr; + skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); @@ -1036,12 +1038,6 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - } - - err = skb_append_datato_frags(sk,skb, getfrag, from, - (length - transhdrlen)); - if (!err) { - struct frag_hdr fhdr; /* Specify the length of each IPv6 datagram fragment. * It has to be a multiple of 8. @@ -1052,15 +1048,10 @@ static inline int ip6_ufo_append_data(struct sock *sk, ipv6_select_ident(&fhdr, rt); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); - - return 0; } - /* There is not enough support do UPD LSO, - * so follow normal path - */ - kfree_skb(skb); - return err; + return skb_append_datato_frags(sk, skb, getfrag, from, + (length - transhdrlen)); } static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, @@ -1227,27 +1218,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * --yoshfuji */ - cork->length += length; - if (length > mtu) { - int proto = sk->sk_protocol; - if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ - ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); - return -EMSGSIZE; - } - - if (proto == IPPROTO_UDP && - (rt->dst.dev->features & NETIF_F_UFO)) { + if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_RAW)) { + ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); + return -EMSGSIZE; + } - err = ip6_ufo_append_data(sk, getfrag, from, length, - hh_len, fragheaderlen, - transhdrlen, mtu, flags, rt); - if (err) - goto error; - return 0; - } + skb = skb_peek_tail(&sk->sk_write_queue); + cork->length += length; + if (((length > mtu) || + (skb && skb_is_gso(skb))) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->dst.dev->features & NETIF_F_UFO)) { + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags, rt); + if (err) + goto error; + return 0; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + if (!skb) goto alloc_new_skb; while (length > 0) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 61355f7..a791552 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1656,9 +1656,9 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), - &parm->raddr) || - nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), &parm->laddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || @@ -1731,8 +1731,6 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) } } - t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); unregister_netdevice_many(&list); } @@ -1752,6 +1750,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 096cd67..d18f9f9 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2034,7 +2034,7 @@ static void mld_dad_timer_expire(unsigned long data) if (idev->mc_dad_count) mld_dad_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, @@ -2379,7 +2379,7 @@ static void mld_gq_timer_expire(unsigned long data) idev->mc_gq_running = 0; mld_send_report(idev, NULL); - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_timer_expire(unsigned long data) @@ -2392,7 +2392,7 @@ static void mld_ifc_timer_expire(unsigned long data) if (idev->mc_ifc_count) mld_ifc_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 19cfea8..2748b04 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -282,7 +282,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -372,7 +373,8 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -395,7 +397,9 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 61aaf70..2205e8e 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -69,8 +69,8 @@ icmpv6_manip_pkt(struct sk_buff *skb, hdr = (struct icmp6hdr *)(skb->data + hdroff); l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); - if (hdr->icmp6_code == ICMPV6_ECHO_REQUEST || - hdr->icmp6_code == ICMPV6_ECHO_REPLY) { + if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || + hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, 0); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 58916bb..a4ed241 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -335,8 +335,10 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + return; + } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 7ee5cb9..1926945 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -566,6 +566,70 @@ static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, return false; } +/* Checks if an address matches an address on the tunnel interface. + * Used to detect the NAT of proto 41 packets and let them pass spoofing test. + * Long story: + * This function is called after we considered the packet as spoofed + * in is_spoofed_6rd. + * We may have a router that is doing NAT for proto 41 packets + * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb + * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd + * function will return true, dropping the packet. + * But, we can still check if is spoofed against the IP + * addresses associated with the interface. + */ +static bool only_dnatted(const struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + int prefix_len; + +#ifdef CONFIG_IPV6_SIT_6RD + prefix_len = tunnel->ip6rd.prefixlen + 32 + - tunnel->ip6rd.relay_prefixlen; +#else + prefix_len = 48; +#endif + return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); +} + +/* Returns true if a packet is spoofed */ +static bool packet_is_spoofed(struct sk_buff *skb, + const struct iphdr *iph, + struct ip_tunnel *tunnel) +{ + const struct ipv6hdr *ipv6h; + + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) + return true; + + return false; + } + + if (tunnel->dev->flags & IFF_POINTOPOINT) + return false; + + ipv6h = ipv6_hdr(skb); + + if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { + net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; + } + + if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) + return false; + + if (only_dnatted(tunnel, &ipv6h->daddr)) + return false; + + net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; +} + static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); @@ -586,19 +650,9 @@ static int ipip6_rcv(struct sk_buff *skb) IPCB(skb)->flags = 0; skb->protocol = htons(ETH_P_IPV6); - if (tunnel->dev->priv_flags & IFF_ISATAP) { - if (!isatap_chksrc(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; - goto out; - } - } else if (!(tunnel->dev->flags&IFF_POINTOPOINT)) { - if (is_spoofed_6rd(tunnel, iph->saddr, - &ipv6_hdr(skb)->saddr) || - is_spoofed_6rd(tunnel, iph->daddr, - &ipv6_hdr(skb)->daddr)) { - tunnel->dev->stats.rx_errors++; - goto out; - } + if (packet_is_spoofed(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; } __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); @@ -748,7 +802,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -777,7 +831,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -1612,6 +1666,7 @@ static int __net_init sit_init_net(struct net *net) goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); + sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ @@ -1646,7 +1701,6 @@ static void __net_exit sit_exit_net(struct net *net) rtnl_lock(); sit_destroy_tunnels(sitn, &list); - unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f405815..72b7eaa 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -525,8 +525,10 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == ICMPV6_PKT_TOOBIG) ip6_sk_update_pmtu(skb, sk, info); - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + goto out; + } np = inet6_sk(sk); diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index 54563ad..355cc3b 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -154,6 +154,7 @@ static void lapb_t1timer_expiry(unsigned long param) } else { lapb->n2count++; lapb_requeue_frames(lapb); + lapb_kick(lapb); } break; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index f771390..f2e30fb 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1052,7 +1052,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, * Not an artificial restriction anymore, as we must prevent * possible loops created by swapping in setlist type of sets. */ if (!(from->type->features == to->type->features && - from->type->family == to->type->family)) + from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; strncpy(from_name, from->name, IPSET_MAXNAMELEN); @@ -1489,8 +1489,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, if (ret == -EAGAIN) ret = 1; - return (ret < 0 && ret != -ENOTEMPTY) ? ret : - ret > 0 ? 0 : -IPSET_ERR_EXIST; + return ret > 0 ? 0 : -IPSET_ERR_EXIST; } /* Get headed data of a set */ diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 6fdf88a..dac156f 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -116,12 +116,12 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src, { int protoff; u8 nexthdr; - __be16 frag_off; + __be16 frag_off = 0; nexthdr = ipv6_hdr(skb)->nexthdr; protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); - if (protoff < 0) + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) return false; return get_port(skb, nexthdr, protoff, src, port, proto); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 57beb17..707bc52 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -325,18 +325,22 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length) static void mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length) { - u8 i, j; - - for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++) - ; - h->nets[i].nets--; - - if (h->nets[i].nets != 0) - return; - - for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) { - h->nets[j].cidr = h->nets[j + 1].cidr; - h->nets[j].nets = h->nets[j + 1].nets; + u8 i, j, net_end = nets_length - 1; + + for (i = 0; i < nets_length; i++) { + if (h->nets[i].cidr != cidr) + continue; + if (h->nets[i].nets > 1 || i == net_end || + h->nets[i + 1].nets == 0) { + h->nets[i].nets--; + return; + } + for (j = i; j < net_end && h->nets[j].nets; j++) { + h->nets[j].cidr = h->nets[j + 1].cidr; + h->nets[j].nets = h->nets[j + 1].nets; + } + h->nets[j].nets = 0; + return; } } #endif diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index c6a5253..f15f3e2 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -260,7 +260,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip = htonl(ip); e.ip2 = htonl(ip2_from & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -544,7 +544,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index da740ce..223e9f5 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -199,7 +199,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret: ip_set_eexist(ret, flags) ? 0 : ret; } @@ -396,7 +396,7 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 84ae6f6..7d798d5 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -368,7 +368,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -634,7 +634,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 9a08698..09d6690 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -244,7 +244,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -489,7 +489,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f69e83..74fd00c 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -116,6 +116,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.inpkts++; @@ -123,11 +124,14 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.inpkts++; @@ -146,6 +150,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.outpkts++; @@ -153,11 +158,14 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.outpkts++; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c8148e4..a3df9bd 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -460,7 +460,7 @@ static inline void __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc) { atomic_inc(&svc->refcnt); - dest->svc = svc; + rcu_assign_pointer(dest->svc, svc); } static void ip_vs_service_free(struct ip_vs_service *svc) @@ -470,18 +470,25 @@ static void ip_vs_service_free(struct ip_vs_service *svc) kfree(svc); } -static void -__ip_vs_unbind_svc(struct ip_vs_dest *dest) +static void ip_vs_service_rcu_free(struct rcu_head *head) { - struct ip_vs_service *svc = dest->svc; + struct ip_vs_service *svc; + + svc = container_of(head, struct ip_vs_service, rcu_head); + ip_vs_service_free(svc); +} - dest->svc = NULL; +static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay) +{ if (atomic_dec_and_test(&svc->refcnt)) { IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port)); - ip_vs_service_free(svc); + if (do_delay) + call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); + else + ip_vs_service_free(svc); } } @@ -667,11 +674,6 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); - /* We can not reuse dest while in grace period - * because conns still can use dest->svc - */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (dest->af == svc->af && ip_vs_addr_equal(svc->af, &dest->addr, daddr) && dest->port == dport && @@ -697,8 +699,10 @@ out: static void ip_vs_dest_free(struct ip_vs_dest *dest) { + struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1); + __ip_vs_dst_cache_reset(dest); - __ip_vs_unbind_svc(dest); + __ip_vs_svc_put(svc, false); free_percpu(dest->stats.cpustats); kfree(dest); } @@ -771,6 +775,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct ip_vs_service *old_svc; struct ip_vs_scheduler *sched; int conn_flags; @@ -792,13 +797,14 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, atomic_set(&dest->conn_flags, conn_flags); /* bind the service */ - if (!dest->svc) { + old_svc = rcu_dereference_protected(dest->svc, 1); + if (!old_svc) { __ip_vs_bind_svc(dest, svc); } else { - if (dest->svc != svc) { - __ip_vs_unbind_svc(dest); + if (old_svc != svc) { ip_vs_zero_stats(&dest->stats); __ip_vs_bind_svc(dest, svc); + __ip_vs_svc_put(old_svc, true); } } @@ -998,16 +1004,6 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return 0; } -static void ip_vs_dest_wait_readers(struct rcu_head *head) -{ - struct ip_vs_dest *dest = container_of(head, struct ip_vs_dest, - rcu_head); - - /* End of grace period after unlinking */ - clear_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); -} - - /* * Delete a destination (must be already unlinked from the service) */ @@ -1023,20 +1019,16 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest, */ ip_vs_rs_unhash(dest); - if (!cleanup) { - set_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); - call_rcu(&dest->rcu_head, ip_vs_dest_wait_readers); - } - spin_lock_bh(&ipvs->dest_trash_lock); IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); /* dest lives in trash without reference */ list_add(&dest->t_list, &ipvs->dest_trash); + dest->idle_start = 0; spin_unlock_bh(&ipvs->dest_trash_lock); ip_vs_dest_put(dest); } @@ -1108,24 +1100,30 @@ static void ip_vs_dest_trash_expire(unsigned long data) struct net *net = (struct net *) data; struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_dest *dest, *next; + unsigned long now = jiffies; spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { - /* Skip if dest is in grace period */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (atomic_read(&dest->refcnt) > 0) continue; + if (dest->idle_start) { + if (time_before(now, dest->idle_start + + IP_VS_DEST_TRASH_PERIOD)) + continue; + } else { + dest->idle_start = max(1UL, now); + continue; + } IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n", dest->vfwmark, - IP_VS_DBG_ADDR(dest->svc->af, &dest->addr), + IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); list_del(&dest->t_list); ip_vs_dest_free(dest); } if (!list_empty(&ipvs->dest_trash)) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); spin_unlock(&ipvs->dest_trash_lock); } @@ -1320,14 +1318,6 @@ out: return ret; } -static void ip_vs_service_rcu_free(struct rcu_head *head) -{ - struct ip_vs_service *svc; - - svc = container_of(head, struct ip_vs_service, rcu_head); - ip_vs_service_free(svc); -} - /* * Delete a service from the service list * - The service must be unlinked, unlocked and not referenced! @@ -1376,13 +1366,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) /* * Free the service if nobody refers to it */ - if (atomic_dec_and_test(&svc->refcnt)) { - IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", - svc->fwmark, - IP_VS_DBG_ADDR(svc->af, &svc->addr), - ntohs(svc->port)); - call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); - } + __ip_vs_svc_put(svc, true); /* decrease the module use count */ ip_vs_use_count_dec(); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 6bee6d0..1425e9a 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -59,12 +59,13 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, struct ip_vs_cpu_stats __percpu *stats) { int i; + bool add = false; for_each_possible_cpu(i) { struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); unsigned int start; __u64 inbytes, outbytes; - if (i) { + if (add) { sum->conns += s->ustats.conns; sum->inpkts += s->ustats.inpkts; sum->outpkts += s->ustats.outpkts; @@ -76,6 +77,7 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, sum->inbytes += inbytes; sum->outbytes += outbytes; } else { + add = true; sum->conns = s->ustats.conns; sum->inpkts = s->ustats.inpkts; sum->outpkts = s->ustats.outpkts; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 1383b0e..eff13c9 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -93,7 +93,7 @@ struct ip_vs_lblc_entry { struct hlist_node list; int af; /* address family */ union nf_inet_addr addr; /* destination IP address */ - struct ip_vs_dest __rcu *dest; /* real server (cache) */ + struct ip_vs_dest *dest; /* real server (cache) */ unsigned long lastuse; /* last used time */ struct rcu_head rcu_head; }; @@ -130,20 +130,21 @@ static struct ctl_table vs_vars_table[] = { }; #endif -static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) +static void ip_vs_lblc_rcu_free(struct rcu_head *head) { - struct ip_vs_dest *dest; + struct ip_vs_lblc_entry *en = container_of(head, + struct ip_vs_lblc_entry, + rcu_head); - hlist_del_rcu(&en->list); - /* - * We don't kfree dest because it is referred either by its service - * or the trash dest list. - */ - dest = rcu_dereference_protected(en->dest, 1); - ip_vs_dest_put(dest); - kfree_rcu(en, rcu_head); + ip_vs_dest_put(en->dest); + kfree(en); } +static inline void ip_vs_lblc_del(struct ip_vs_lblc_entry *en) +{ + hlist_del_rcu(&en->list); + call_rcu(&en->rcu_head, ip_vs_lblc_rcu_free); +} /* * Returns hash value for IPVS LBLC entry @@ -203,30 +204,23 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr, struct ip_vs_lblc_entry *en; en = ip_vs_lblc_get(dest->af, tbl, daddr); - if (!en) { - en = kmalloc(sizeof(*en), GFP_ATOMIC); - if (!en) - return NULL; - - en->af = dest->af; - ip_vs_addr_copy(dest->af, &en->addr, daddr); - en->lastuse = jiffies; + if (en) { + if (en->dest == dest) + return en; + ip_vs_lblc_del(en); + } + en = kmalloc(sizeof(*en), GFP_ATOMIC); + if (!en) + return NULL; - ip_vs_dest_hold(dest); - RCU_INIT_POINTER(en->dest, dest); + en->af = dest->af; + ip_vs_addr_copy(dest->af, &en->addr, daddr); + en->lastuse = jiffies; - ip_vs_lblc_hash(tbl, en); - } else { - struct ip_vs_dest *old_dest; + ip_vs_dest_hold(dest); + en->dest = dest; - old_dest = rcu_dereference_protected(en->dest, 1); - if (old_dest != dest) { - ip_vs_dest_put(old_dest); - ip_vs_dest_hold(dest); - /* No ordering constraints for refcnt */ - RCU_INIT_POINTER(en->dest, dest); - } - } + ip_vs_lblc_hash(tbl, en); return en; } @@ -246,7 +240,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) tbl->dead = 1; for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } } @@ -281,7 +275,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) sysctl_lblc_expiration(svc))) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } spin_unlock(&svc->sched_lock); @@ -335,7 +329,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) if (time_before(now, en->lastuse + ENTRY_TIMEOUT)) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); goal--; } @@ -443,8 +437,8 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } @@ -511,7 +505,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, * free up entries from the trash at any time. */ - dest = rcu_dereference(en->dest); + dest = en->dest; if ((dest->flags & IP_VS_DEST_F_AVAILABLE) && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) goto out; @@ -631,7 +625,7 @@ static void __exit ip_vs_lblc_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler); unregister_pernet_subsys(&ip_vs_lblc_ops); - synchronize_rcu(); + rcu_barrier(); } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 5199448..0b85500 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -89,7 +89,7 @@ */ struct ip_vs_dest_set_elem { struct list_head list; /* list link */ - struct ip_vs_dest __rcu *dest; /* destination server */ + struct ip_vs_dest *dest; /* destination server */ struct rcu_head rcu_head; }; @@ -107,11 +107,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, if (check) { list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) - /* already existed */ + if (e->dest == dest) return; } } @@ -121,7 +117,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, return; ip_vs_dest_hold(dest); - RCU_INIT_POINTER(e->dest, dest); + e->dest = dest; list_add_rcu(&e->list, &set->list); atomic_inc(&set->size); @@ -129,22 +125,27 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, set->lastmod = jiffies; } +static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head) +{ + struct ip_vs_dest_set_elem *e; + + e = container_of(head, struct ip_vs_dest_set_elem, rcu_head); + ip_vs_dest_put(e->dest); + kfree(e); +} + static void ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) { struct ip_vs_dest_set_elem *e; list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) { + if (e->dest == dest) { /* HIT */ atomic_dec(&set->size); set->lastmod = jiffies; - ip_vs_dest_put(dest); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); break; } } @@ -155,16 +156,8 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) struct ip_vs_dest_set_elem *e, *ep; list_for_each_entry_safe(e, ep, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - /* - * We don't kfree dest because it is referred either - * by its service or by the trash dest list. - */ - ip_vs_dest_put(d); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); } } @@ -175,12 +168,9 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) struct ip_vs_dest *dest, *least; int loh, doh; - if (set == NULL) - return NULL; - /* select the first destination server, whose weight > 0 */ list_for_each_entry_rcu(e, &set->list, list) { - least = rcu_dereference(e->dest); + least = e->dest; if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; @@ -195,13 +185,13 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) /* find the destination with the weighted least load */ nextstage: list_for_each_entry_continue_rcu(e, &set->list, list) { - dest = rcu_dereference(e->dest); + dest = e->dest; if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); - if ((loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) + if (((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { least = dest; loh = doh; @@ -232,7 +222,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* select the first destination server, whose weight > 0 */ list_for_each_entry(e, &set->list, list) { - most = rcu_dereference_protected(e->dest, 1); + most = e->dest; if (atomic_read(&most->weight) > 0) { moh = ip_vs_dest_conn_overhead(most); goto nextstage; @@ -243,11 +233,11 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* find the destination with the weighted most load */ nextstage: list_for_each_entry_continue(e, &set->list, list) { - dest = rcu_dereference_protected(e->dest, 1); + dest = e->dest; doh = ip_vs_dest_conn_overhead(dest); /* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */ - if ((moh * atomic_read(&dest->weight) < - doh * atomic_read(&most->weight)) + if (((__s64)moh * atomic_read(&dest->weight) < + (__s64)doh * atomic_read(&most->weight)) && (atomic_read(&dest->weight) > 0)) { most = dest; moh = doh; @@ -611,8 +601,8 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } @@ -819,7 +809,7 @@ static void __exit ip_vs_lblcr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); unregister_pernet_subsys(&ip_vs_lblcr_ops); - synchronize_rcu(); + rcu_barrier(); } diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index d8d9860..961a6de 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -40,7 +40,7 @@ #include <net/ip_vs.h> -static inline unsigned int +static inline int ip_vs_nq_dest_overhead(struct ip_vs_dest *dest) { /* @@ -59,7 +59,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least = NULL; - unsigned int loh = 0, doh; + int loh = 0, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -92,8 +92,8 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, } if (!least || - (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight))) { + ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight))) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index a5284cc..e446b9f 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -44,7 +44,7 @@ #include <net/ip_vs.h> -static inline unsigned int +static inline int ip_vs_sed_dest_overhead(struct ip_vs_dest *dest) { /* @@ -63,7 +63,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -99,8 +99,8 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_sed_dest_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 6dc1fa1..b5b4650 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -35,7 +35,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "ip_vs_wlc_schedule(): Scheduling...\n"); @@ -71,8 +71,8 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b75ff64..c47444e 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 6fd967c..cdf4567 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -24,7 +24,7 @@ int synproxy_net_id; EXPORT_SYMBOL_GPL(synproxy_net_id); -void +bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts) { @@ -32,7 +32,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, u8 buf[40], *ptr; ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); - BUG_ON(ptr == NULL); + if (ptr == NULL) + return false; opts->options = 0; while (length > 0) { @@ -41,16 +42,16 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, switch (opcode) { case TCPOPT_EOL: - return; + return true; case TCPOPT_NOP: length--; continue; default: opsize = *ptr++; if (opsize < 2) - return; + return true; if (opsize > length) - return; + return true; switch (opcode) { case TCPOPT_MSS: @@ -84,6 +85,7 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length -= opsize; } } + return true; } EXPORT_SYMBOL_GPL(synproxy_parse_options); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 95a98c8..ae2e5c1 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1009,7 +1009,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, verdict = NF_DROP; if (ct) - nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff); + nfqnl_ct_seq_adjust(entry->skb, ct, ctinfo, diff); } if (nfqa[NFQA_MARK]) diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 32ad015..a2fef8b 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -285,7 +285,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) /* remove one skb from head of flow queue */ -static struct sk_buff *fq_dequeue_head(struct fq_flow *flow) +static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) { struct sk_buff *skb = flow->head; @@ -293,6 +293,8 @@ static struct sk_buff *fq_dequeue_head(struct fq_flow *flow) flow->head = skb->next; skb->next = NULL; flow->qlen--; + sch->qstats.backlog -= qdisc_pkt_len(skb); + sch->q.qlen--; } return skb; } @@ -418,8 +420,9 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; + u32 rate; - skb = fq_dequeue_head(&q->internal); + skb = fq_dequeue_head(sch, &q->internal); if (skb) goto out; fq_check_throttled(q, now); @@ -449,7 +452,7 @@ begin: goto begin; } - skb = fq_dequeue_head(f); + skb = fq_dequeue_head(sch, f); if (!skb) { head->first = f->next; /* force a pass through old_flows to prevent starvation */ @@ -466,43 +469,74 @@ begin: f->time_next_packet = now; f->credit -= qdisc_pkt_len(skb); - if (f->credit <= 0 && - q->rate_enable && - skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) { - u32 rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate; + if (f->credit > 0 || !q->rate_enable) + goto out; - rate = min(rate, q->flow_max_rate); - if (rate) { - u64 len = (u64)qdisc_pkt_len(skb) * NSEC_PER_SEC; - - do_div(len, rate); - /* Since socket rate can change later, - * clamp the delay to 125 ms. - * TODO: maybe segment the too big skb, as in commit - * e43ac79a4bc ("sch_tbf: segment too big GSO packets") - */ - if (unlikely(len > 125 * NSEC_PER_MSEC)) { - len = 125 * NSEC_PER_MSEC; - q->stat_pkts_too_long++; - } + if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) { + rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate; - f->time_next_packet = now + len; + rate = min(rate, q->flow_max_rate); + } else { + rate = q->flow_max_rate; + if (rate == ~0U) + goto out; + } + if (rate) { + u32 plen = max(qdisc_pkt_len(skb), q->quantum); + u64 len = (u64)plen * NSEC_PER_SEC; + + do_div(len, rate); + /* Since socket rate can change later, + * clamp the delay to 125 ms. + * TODO: maybe segment the too big skb, as in commit + * e43ac79a4bc ("sch_tbf: segment too big GSO packets") + */ + if (unlikely(len > 125 * NSEC_PER_MSEC)) { + len = 125 * NSEC_PER_MSEC; + q->stat_pkts_too_long++; } + + f->time_next_packet = now + len; } out: - sch->qstats.backlog -= qdisc_pkt_len(skb); qdisc_bstats_update(sch, skb); - sch->q.qlen--; qdisc_unthrottled(sch); return skb; } static void fq_reset(struct Qdisc *sch) { + struct fq_sched_data *q = qdisc_priv(sch); + struct rb_root *root; struct sk_buff *skb; + struct rb_node *p; + struct fq_flow *f; + unsigned int idx; - while ((skb = fq_dequeue(sch)) != NULL) + while ((skb = fq_dequeue_head(sch, &q->internal)) != NULL) kfree_skb(skb); + + if (!q->fq_root) + return; + + for (idx = 0; idx < (1U << q->fq_trees_log); idx++) { + root = &q->fq_root[idx]; + while ((p = rb_first(root)) != NULL) { + f = container_of(p, struct fq_flow, fq_node); + rb_erase(p, root); + + while ((skb = fq_dequeue_head(sch, f)) != NULL) + kfree_skb(skb); + + kmem_cache_free(fq_flow_cachep, f); + } + } + q->new_flows.first = NULL; + q->old_flows.first = NULL; + q->delayed = RB_ROOT; + q->flows = 0; + q->inactive_flows = 0; + q->throttled_flows = 0; } static void fq_rehash(struct fq_sched_data *q, @@ -645,6 +679,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); + if (!skb) + break; kfree_skb(skb); drop_count++; } @@ -657,21 +693,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) static void fq_destroy(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); - struct rb_root *root; - struct rb_node *p; - unsigned int idx; - if (q->fq_root) { - for (idx = 0; idx < (1U << q->fq_trees_log); idx++) { - root = &q->fq_root[idx]; - while ((p = rb_first(root)) != NULL) { - rb_erase(p, root); - kmem_cache_free(fq_flow_cachep, - container_of(p, struct fq_flow, fq_node)); - } - } - kfree(q->fq_root); - } + fq_reset(sch); + kfree(q->fq_root); qdisc_watchdog_cancel(&q->watchdog); } diff --git a/net/sctp/input.c b/net/sctp/input.c index 5f20686..98b69bb 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -634,8 +634,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) break; case ICMP_REDIRECT: sctp_icmp_redirect(sk, transport, skb); - err = 0; - break; + /* Fall through to out_unlock. */ default: goto out_unlock; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index da613ce..e7b2d4f 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -183,7 +183,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; case NDISC_REDIRECT: sctp_icmp_redirect(sk, transport, skb); - break; + goto out_unlock; default: break; } @@ -204,44 +204,23 @@ out: in6_dev_put(idev); } -/* Based on tcp_v6_xmit() in tcp_ipv6.c. */ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) { struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi6 fl6; - - memset(&fl6, 0, sizeof(fl6)); - - fl6.flowi6_proto = sk->sk_protocol; - - /* Fill in the dest address from the route entry passed with the skb - * and the source address from the transport. - */ - fl6.daddr = transport->ipaddr.v6.sin6_addr; - fl6.saddr = transport->saddr.v6.sin6_addr; - - fl6.flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl6.flowlabel); - if (ipv6_addr_type(&fl6.saddr) & IPV6_ADDR_LINKLOCAL) - fl6.flowi6_oif = transport->saddr.v6.sin6_scope_id; - else - fl6.flowi6_oif = sk->sk_bound_dev_if; - - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - fl6.daddr = *rt0->addr; - } + struct flowi6 *fl6 = &transport->fl.u.ip6; pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb, - skb->len, &fl6.saddr, &fl6.daddr); + skb->len, &fl6->saddr, &fl6->daddr); - SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); + IP6_ECN_flow_xmit(sk, fl6->flowlabel); if (!(transport->param_flags & SPP_PMTUD_ENABLE)) skb->local_df = 1; - return ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); + + return ip6_xmit(sk, skb, fl6, np->opt, np->tclass); } /* Returns the dst cache entry for the given source and destination ip @@ -254,10 +233,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct dst_entry *dst = NULL; struct flowi6 *fl6 = &fl->u.ip6; struct sctp_bind_addr *bp; + struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; union sctp_addr *baddr = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; + struct in6_addr *final_p, final; __u8 matchlen = 0; __u8 bmatchlen; sctp_scope_t scope; @@ -281,7 +262,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, pr_debug("src=%pI6 - ", &fl6->saddr); } - dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + final_p = fl6_update_dst(fl6, np->opt, &final); + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); if (!asoc || saddr) goto out; @@ -333,10 +315,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } } rcu_read_unlock(); + if (baddr) { fl6->saddr = baddr->v6.sin6_addr; fl6->fl6_sport = baddr->v6.sin6_port; - dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + final_p = fl6_update_dst(fl6, np->opt, &final); + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); } out: diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index fcac5d1..0846566 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1075,6 +1075,15 @@ gss_destroy(struct rpc_auth *auth) kref_put(&gss_auth->kref, gss_free_callback); } +/* + * Auths may be shared between rpc clients that were cloned from a + * common client with the same xprt, if they also share the flavor and + * target_name. + * + * The auth is looked up from the oldest parent sharing the same + * cl_xprt, and the auth itself references only that common parent + * (which is guaranteed to last as long as any of its descendants). + */ static struct gss_auth * gss_auth_find_or_add_hashed(struct rpc_auth_create_args *args, struct rpc_clnt *clnt, @@ -1088,6 +1097,8 @@ gss_auth_find_or_add_hashed(struct rpc_auth_create_args *args, gss_auth, hash, hashval) { + if (gss_auth->client != clnt) + continue; if (gss_auth->rpc_auth.au_flavor != args->pseudoflavor) continue; if (gss_auth->target_name != args->target_name) { diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 9bc6db04..e7000be 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -47,12 +47,12 @@ static int net_ctl_permissions(struct ctl_table_header *head, /* Allow network administrator to have same access as root. */ if (ns_capable(net->user_ns, CAP_NET_ADMIN) || - uid_eq(root_uid, current_uid())) { + uid_eq(root_uid, current_euid())) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } /* Allow netns root group to have the same access as the root group */ - if (gid_eq(root_gid, current_gid())) { + if (in_egroup_p(root_gid)) { int mode = (table->mode >> 3) & 7; return (mode << 3) | mode; } |