diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 238 | ||||
-rw-r--r-- | net/core/dev_addr_lists.c | 40 | ||||
-rw-r--r-- | net/core/dst.c | 16 | ||||
-rw-r--r-- | net/core/ethtool.c | 12 | ||||
-rw-r--r-- | net/core/fib_rules.c | 6 | ||||
-rw-r--r-- | net/core/filter.c | 35 | ||||
-rw-r--r-- | net/core/link_watch.c | 29 | ||||
-rw-r--r-- | net/core/neighbour.c | 10 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 18 | ||||
-rw-r--r-- | net/core/netpoll.c | 104 | ||||
-rw-r--r-- | net/core/netprio_cgroup.c | 96 | ||||
-rw-r--r-- | net/core/pktgen.c | 2 | ||||
-rw-r--r-- | net/core/request_sock.c | 95 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 55 | ||||
-rw-r--r-- | net/core/scm.c | 48 | ||||
-rw-r--r-- | net/core/secure_seq.c | 1 | ||||
-rw-r--r-- | net/core/skbuff.c | 212 | ||||
-rw-r--r-- | net/core/sock.c | 159 | ||||
-rw-r--r-- | net/core/sock_diag.c | 3 | ||||
-rw-r--r-- | net/core/utils.c | 20 |
20 files changed, 826 insertions, 373 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 0ebaea16632f..1e0a1847c3bb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -959,18 +959,30 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -static int dev_get_valid_name(struct net_device *dev, const char *name) +static int dev_alloc_name_ns(struct net *net, + struct net_device *dev, + const char *name) { - struct net *net; + char buf[IFNAMSIZ]; + int ret; - BUG_ON(!dev_net(dev)); - net = dev_net(dev); + ret = __dev_alloc_name(net, name, buf); + if (ret >= 0) + strlcpy(dev->name, buf, IFNAMSIZ); + return ret; +} + +static int dev_get_valid_name(struct net *net, + struct net_device *dev, + const char *name) +{ + BUG_ON(!net); if (!dev_valid_name(name)) return -EINVAL; if (strchr(name, '%')) - return dev_alloc_name(dev, name); + return dev_alloc_name_ns(net, dev, name); else if (__dev_get_by_name(net, name)) return -EEXIST; else if (dev->name != name) @@ -1006,7 +1018,7 @@ int dev_change_name(struct net_device *dev, const char *newname) memcpy(oldname, dev->name, IFNAMSIZ); - err = dev_get_valid_name(dev, newname); + err = dev_get_valid_name(net, dev, newname); if (err < 0) return err; @@ -1055,6 +1067,8 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { + char *new_ifalias; + ASSERT_RTNL(); if (len >= IFALIASZ) @@ -1068,9 +1082,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return 0; } - dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!dev->ifalias) + new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); + if (!new_ifalias) return -ENOMEM; + dev->ifalias = new_ifalias; strlcpy(dev->ifalias, alias, len+1); return len; @@ -1106,11 +1121,23 @@ void netdev_state_change(struct net_device *dev) } EXPORT_SYMBOL(netdev_state_change); -int netdev_bonding_change(struct net_device *dev, unsigned long event) +/** + * netdev_notify_peers - notify network peers about existence of @dev + * @dev: network device + * + * Generate traffic such that interested network peers are aware of + * @dev, such as by generating a gratuitous ARP. This may be used when + * a device wants to inform the rest of the network about some sort of + * reconfiguration such as a failover event or virtual machine + * migration. + */ +void netdev_notify_peers(struct net_device *dev) { - return call_netdevice_notifiers(event, dev); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + rtnl_unlock(); } -EXPORT_SYMBOL(netdev_bonding_change); +EXPORT_SYMBOL(netdev_notify_peers); /** * dev_load - load a network module @@ -1172,6 +1199,7 @@ static int __dev_open(struct net_device *dev) net_dmaengine_get(); dev_set_rx_mode(dev); dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; @@ -1390,7 +1418,6 @@ rollback: nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } @@ -1432,7 +1459,6 @@ int unregister_netdevice_notifier(struct notifier_block *nb) nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } unlock: @@ -1638,6 +1664,19 @@ static inline int deliver_skb(struct sk_buff *skb, return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } +static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) +{ + if (ptype->af_packet_priv == NULL) + return false; + + if (ptype->id_match) + return ptype->id_match(ptype, skb->sk); + else if ((struct sock *)ptype->af_packet_priv == skb->sk) + return true; + + return false; +} + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1655,8 +1694,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * they originated from - MvS (miquels@drinkel.ow.org) */ if ((ptype->dev == dev || !ptype->dev) && - (ptype->af_packet_priv == NULL || - (struct sock *)ptype->af_packet_priv != skb->sk)) { + (!skb_loop_sk(ptype, skb))) { if (pt_prev) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; @@ -2118,7 +2156,8 @@ static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) static netdev_features_t harmonize_features(struct sk_buff *skb, __be16 protocol, netdev_features_t features) { - if (!can_checksum_protocol(features, protocol)) { + if (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; features &= ~NETIF_F_SG; } else if (illegal_highdma(skb->dev, skb)) { @@ -2133,6 +2172,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) __be16 protocol = skb->protocol; netdev_features_t features = skb->dev->features; + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + features &= ~NETIF_F_GSO_MASK; + if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; @@ -2155,9 +2197,7 @@ EXPORT_SYMBOL(netif_skb_features); /* * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or - * 2. skb is fragmented and the device does not support SG, or if - * at least one of fragments is in highmem and device does not - * support DMA from it. + * 2. skb is fragmented and the device does not support SG. */ static inline int skb_needs_linearize(struct sk_buff *skb, int features) @@ -2186,9 +2226,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); - if (!list_empty(&ptype_all)) - dev_queue_xmit_nit(skb, dev); - features = netif_skb_features(skb); if (vlan_tx_tag_present(skb) && @@ -2223,6 +2260,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, } } + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + skb_len = skb->len; rc = ops->ndo_start_xmit(skb, dev); trace_net_dev_xmit(skb, rc, dev, skb_len); @@ -2245,6 +2285,9 @@ gso: if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(nskb); + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(nskb, dev); + skb_len = nskb->len; rc = ops->ndo_start_xmit(nskb, dev); trace_net_dev_xmit(nskb, rc, dev, skb_len); @@ -2354,8 +2397,8 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -static struct netdev_queue *dev_pick_tx(struct net_device *dev, - struct sk_buff *skb) +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb) { int queue_index; const struct net_device_ops *ops = dev->netdev_ops; @@ -2529,7 +2572,7 @@ int dev_queue_xmit(struct sk_buff *skb) skb_update_prio(skb); - txq = dev_pick_tx(dev, skb); + txq = netdev_pick_tx(dev, skb); q = rcu_dereference_bh(txq->qdisc); #ifdef CONFIG_NET_CLS_ACT @@ -2602,6 +2645,8 @@ EXPORT_SYMBOL(dev_queue_xmit); =======================================================================*/ int netdev_max_backlog __read_mostly = 1000; +EXPORT_SYMBOL(netdev_max_backlog); + int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; int weight_p __read_mostly = 64; /* old backlog weight */ @@ -2628,15 +2673,16 @@ void __skb_get_rxhash(struct sk_buff *skb) if (!skb_flow_dissect(skb, &keys)) return; - if (keys.ports) { - if ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]) - swap(keys.port16[0], keys.port16[1]); + if (keys.ports) skb->l4_rxhash = 1; - } /* get a consistent hash (same value on both flow directions) */ - if ((__force u32)keys.dst < (__force u32)keys.src) + if (((__force u32)keys.dst < (__force u32)keys.src) || + (((__force u32)keys.dst == (__force u32)keys.src) && + ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { swap(keys.dst, keys.src); + swap(keys.port16[0], keys.port16[1]); + } hash = jhash_3words((__force u32)keys.dst, (__force u32)keys.src, @@ -3155,6 +3201,23 @@ void netdev_rx_handler_unregister(struct net_device *dev) } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); +/* + * Limit the use of PFMEMALLOC reserves to those protocols that implement + * the special handling of PFMEMALLOC skbs. + */ +static bool skb_pfmemalloc_protocol(struct sk_buff *skb) +{ + switch (skb->protocol) { + case __constant_htons(ETH_P_ARP): + case __constant_htons(ETH_P_IP): + case __constant_htons(ETH_P_IPV6): + case __constant_htons(ETH_P_8021Q): + return true; + default: + return false; + } +} + static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; @@ -3164,14 +3227,27 @@ static int __netif_receive_skb(struct sk_buff *skb) bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; + unsigned long pflags = current->flags; net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + current->flags |= PF_MEMALLOC; + /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) - return NET_RX_DROP; + goto out; orig_dev = skb->dev; @@ -3191,7 +3267,7 @@ another_round: if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { skb = vlan_untag(skb); if (unlikely(!skb)) - goto out; + goto unlock; } #ifdef CONFIG_NET_CLS_ACT @@ -3201,6 +3277,9 @@ another_round: } #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + goto skip_taps; + list_for_each_entry_rcu(ptype, &ptype_all, list) { if (!ptype->dev || ptype->dev == skb->dev) { if (pt_prev) @@ -3209,13 +3288,18 @@ another_round: } } +skip_taps: #ifdef CONFIG_NET_CLS_ACT skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto out; + goto unlock; ncls: #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb) + && !skb_pfmemalloc_protocol(skb)) + goto drop; + rx_handler = rcu_dereference(skb->dev->rx_handler); if (vlan_tx_tag_present(skb)) { if (pt_prev) { @@ -3225,7 +3309,7 @@ ncls: if (vlan_do_receive(&skb, !rx_handler)) goto another_round; else if (unlikely(!skb)) - goto out; + goto unlock; } if (rx_handler) { @@ -3235,7 +3319,7 @@ ncls: } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: - goto out; + goto unlock; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: @@ -3264,10 +3348,11 @@ ncls: if (pt_prev) { if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) - ret = -ENOMEM; + goto drop; else ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { +drop: atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining @@ -3276,8 +3361,10 @@ ncls: ret = NET_RX_DROP; } -out: +unlock: rcu_read_unlock(); +out: + tsk_restore_flags(current, pflags, PF_MEMALLOC); return ret; } @@ -4450,8 +4537,8 @@ static void dev_change_rx_flags(struct net_device *dev, int flags) static int __dev_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; ASSERT_RTNL(); @@ -4482,8 +4569,9 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), - audit_get_loginuid(current), - uid, gid, + from_kuid(&init_user_ns, audit_get_loginuid(current)), + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } @@ -4801,6 +4889,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) err = ops->ndo_set_mac_address(dev, sa); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); return err; } EXPORT_SYMBOL(dev_set_mac_address); @@ -5175,12 +5264,12 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) */ static int dev_new_index(struct net *net) { - static int ifindex; + int ifindex = net->ifindex; for (;;) { if (++ifindex <= 0) ifindex = 1; if (!__dev_get_by_index(net, ifindex)) - return ifindex; + return net->ifindex = ifindex; } } @@ -5258,10 +5347,6 @@ static void rollback_registered_many(struct list_head *head) netdev_unregister_kobject(dev); } - /* Process any work delayed until the end of the batch */ - dev = list_first_entry(head, struct net_device, unreg_list); - call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - synchronize_net(); list_for_each_entry(dev, head, unreg_list) @@ -5519,7 +5604,7 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; - ret = dev_get_valid_name(dev, dev->name); + ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; @@ -5533,7 +5618,12 @@ int register_netdevice(struct net_device *dev) } } - dev->ifindex = dev_new_index(net); + ret = -EBUSY; + if (!dev->ifindex) + dev->ifindex = dev_new_index(net); + else if (__dev_get_by_index(net, dev->ifindex)) + goto err_uninit; + if (dev->iflink == -1) dev->iflink = dev->ifindex; @@ -5576,9 +5666,12 @@ int register_netdevice(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); + linkwatch_init_dev(dev); + dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); @@ -5682,6 +5775,7 @@ EXPORT_SYMBOL(netdev_refcnt_read); /** * netdev_wait_allrefs - wait until all references are gone. + * @dev: target net_device * * This is called when unregistering network devices. * @@ -5707,9 +5801,12 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users - * should have already handle it the first time */ + __rtnl_unlock(); + rcu_barrier(); + rtnl_lock(); + + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events @@ -5771,9 +5868,8 @@ void netdev_run_todo(void) __rtnl_unlock(); - /* Wait for rcu callbacks to finish before attempting to drain - * the device list. This usually avoids a 250ms wait. - */ + + /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); @@ -5782,6 +5878,10 @@ void netdev_run_todo(void) = list_first_entry(&list, struct net_device, todo_list); list_del(&dev->todo_list); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + __rtnl_unlock(); + if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { pr_err("network todo '%s' but state %d\n", dev->name, dev->reg_state); @@ -5877,6 +5977,8 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) return queue; } +static const struct ethtool_ops default_ethtool_ops; + /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for @@ -5942,6 +6044,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_segs = GSO_MAX_SEGS; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); @@ -5963,6 +6066,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, strcpy(dev->name, name); dev->group = INIT_NETDEV_GROUP; + if (!dev->ethtool_ops) + dev->ethtool_ops = &default_ethtool_ops; return dev; free_all: @@ -6147,7 +6252,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* We get here if we can't use the current device name */ if (!pat) goto out; - if (dev_get_valid_name(dev, pat) < 0) + if (dev_get_valid_name(net, dev, pat) < 0) goto out; } @@ -6175,7 +6280,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); + rcu_barrier(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); /* @@ -6358,22 +6464,26 @@ const char *netdev_drivername(const struct net_device *dev) return empty; } -int __netdev_printk(const char *level, const struct net_device *dev, +static int __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf) { int r; - if (dev && dev->dev.parent) - r = dev_printk(level, dev->dev.parent, "%s: %pV", - netdev_name(dev), vaf); - else if (dev) + if (dev && dev->dev.parent) { + r = dev_printk_emit(level[1] - '0', + dev->dev.parent, + "%s %s %s: %pV", + dev_driver_string(dev->dev.parent), + dev_name(dev->dev.parent), + netdev_name(dev), vaf); + } else if (dev) { r = printk("%s%s: %pV", level, netdev_name(dev), vaf); - else + } else { r = printk("%s(NULL net_device): %pV", level, vaf); + } return r; } -EXPORT_SYMBOL(__netdev_printk); int netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) @@ -6388,6 +6498,7 @@ int netdev_printk(const char *level, const struct net_device *dev, vaf.va = &args; r = __netdev_printk(level, dev, &vaf); + va_end(args); return r; @@ -6407,6 +6518,7 @@ int func(const struct net_device *dev, const char *fmt, ...) \ vaf.va = &args; \ \ r = __netdev_printk(level, dev, &vaf); \ + \ va_end(args); \ \ return r; \ diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index c4cc2bc49f06..87cc17db2d56 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -22,7 +22,7 @@ */ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, + const unsigned char *addr, int addr_len, unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; @@ -46,7 +46,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, + const unsigned char *addr, int addr_len, unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; @@ -72,14 +72,15 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, return __hw_addr_create_ex(list, addr, addr_len, addr_type, global); } -static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_add(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false); } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, + const unsigned char *addr, int addr_len, unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; @@ -104,8 +105,9 @@ static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, return -ENOENT; } -static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_del(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) { return __hw_addr_del_ex(list, addr, addr_len, addr_type, false); } @@ -278,7 +280,7 @@ EXPORT_SYMBOL(dev_addr_init); * * The caller must hold the rtnl_mutex. */ -int dev_addr_add(struct net_device *dev, unsigned char *addr, +int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; @@ -303,7 +305,7 @@ EXPORT_SYMBOL(dev_addr_add); * * The caller must hold the rtnl_mutex. */ -int dev_addr_del(struct net_device *dev, unsigned char *addr, +int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; @@ -390,7 +392,7 @@ EXPORT_SYMBOL(dev_addr_del_multiple); * @dev: device * @addr: address to add */ -int dev_uc_add_excl(struct net_device *dev, unsigned char *addr) +int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { struct netdev_hw_addr *ha; int err; @@ -421,7 +423,7 @@ EXPORT_SYMBOL(dev_uc_add_excl); * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ -int dev_uc_add(struct net_device *dev, unsigned char *addr) +int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; @@ -443,7 +445,7 @@ EXPORT_SYMBOL(dev_uc_add); * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ -int dev_uc_del(struct net_device *dev, unsigned char *addr) +int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; @@ -543,7 +545,7 @@ EXPORT_SYMBOL(dev_uc_init); * @dev: device * @addr: address to add */ -int dev_mc_add_excl(struct net_device *dev, unsigned char *addr) +int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { struct netdev_hw_addr *ha; int err; @@ -566,7 +568,7 @@ out: } EXPORT_SYMBOL(dev_mc_add_excl); -static int __dev_mc_add(struct net_device *dev, unsigned char *addr, +static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; @@ -587,7 +589,7 @@ static int __dev_mc_add(struct net_device *dev, unsigned char *addr, * Add a multicast address to the device or increase * the reference count if it already exists. */ -int dev_mc_add(struct net_device *dev, unsigned char *addr) +int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } @@ -600,13 +602,13 @@ EXPORT_SYMBOL(dev_mc_add); * * Add a global multicast address to the device. */ -int dev_mc_add_global(struct net_device *dev, unsigned char *addr) +int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); -static int __dev_mc_del(struct net_device *dev, unsigned char *addr, +static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; @@ -628,7 +630,7 @@ static int __dev_mc_del(struct net_device *dev, unsigned char *addr, * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ -int dev_mc_del(struct net_device *dev, unsigned char *addr) +int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } @@ -642,7 +644,7 @@ EXPORT_SYMBOL(dev_mc_del); * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ -int dev_mc_del_global(struct net_device *dev, unsigned char *addr) +int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } diff --git a/net/core/dst.c b/net/core/dst.c index 069d51d29414..ee6153e2cf43 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -149,7 +149,15 @@ int dst_discard(struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard); -const u32 dst_default_metrics[RTAX_MAX]; +const u32 dst_default_metrics[RTAX_MAX + 1] = { + /* This initializer is needed to force linker to place this variable + * into const section. Otherwise it might end into bss section. + * We really want to avoid false sharing on this variable, and catch + * any writes on it. + */ + [RTAX_MAX] = 0xdeadbeef, +}; + void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags) @@ -214,8 +222,8 @@ void __dst_free(struct dst_entry *dst) if (dst_garbage.timer_inc > DST_GC_INC) { dst_garbage.timer_inc = DST_GC_INC; dst_garbage.timer_expires = DST_GC_MIN; - cancel_delayed_work(&dst_gc_work); - schedule_delayed_work(&dst_gc_work, dst_garbage.timer_expires); + mod_delayed_work(system_wq, &dst_gc_work, + dst_garbage.timer_expires); } spin_unlock_bh(&dst_garbage.lock); } @@ -366,7 +374,7 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, struct dst_entry *dst, *last = NULL; switch (event) { - case NETDEV_UNREGISTER: + case NETDEV_UNREGISTER_FINAL: case NETDEV_DOWN: mutex_lock(&dst_gc_mutex); for (dst = dst_busy_list; dst; dst = dst->next) { diff --git a/net/core/ethtool.c b/net/core/ethtool.c index cbf033dcaf1f..4d64cc2e3fa9 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1426,18 +1426,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; - if (!dev->ethtool_ops) { - /* A few commands do not require any driver support, - * are unprivileged, and do not change anything, so we - * can take a shortcut to them. */ - if (ethcmd == ETHTOOL_GDRVINFO) - return ethtool_get_drvinfo(dev, useraddr); - else if (ethcmd == ETHTOOL_GET_TS_INFO) - return ethtool_get_ts_info(dev, useraddr); - else - return -EOPNOTSUPP; - } - /* Allow some commands to be done by anyone */ switch (ethcmd) { case ETHTOOL_GSET: diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index ab7db83236c9..58a4ba27dfe3 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -402,7 +402,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (unresolved) ops->unresolved_rules++; - notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); return 0; @@ -500,7 +500,7 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) } notify_rule_change(RTM_DELRULE, rule, ops, nlh, - NETLINK_CB(skb).pid); + NETLINK_CB(skb).portid); if (ops->delete) ops->delete(rule); fib_rule_put(rule); @@ -601,7 +601,7 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, if (idx < cb->args[1]) goto skip; - if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid, + if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops) < 0) break; diff --git a/net/core/filter.c b/net/core/filter.c index d4ce2dc712e3..3d92ebb7fbcf 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -83,6 +83,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) int err; struct sk_filter *filter; + /* + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory + */ + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + err = security_sock_rcv_skb(sk, skb); if (err) return err; @@ -159,6 +167,14 @@ unsigned int sk_run_filter(const struct sk_buff *skb, case BPF_S_ALU_DIV_K: A = reciprocal_divide(A, K); continue; + case BPF_S_ALU_MOD_X: + if (X == 0) + return 0; + A %= X; + continue; + case BPF_S_ALU_MOD_K: + A %= K; + continue; case BPF_S_ALU_AND_X: A &= X; continue; @@ -171,6 +187,13 @@ unsigned int sk_run_filter(const struct sk_buff *skb, case BPF_S_ALU_OR_K: A |= K; continue; + case BPF_S_ANC_ALU_XOR_X: + case BPF_S_ALU_XOR_X: + A ^= X; + continue; + case BPF_S_ALU_XOR_K: + A ^= K; + continue; case BPF_S_ALU_LSH_X: A <<= X; continue; @@ -318,9 +341,6 @@ load_b: case BPF_S_ANC_CPU: A = raw_smp_processor_id(); continue; - case BPF_S_ANC_ALU_XOR_X: - A ^= X; - continue; case BPF_S_ANC_NLATTR: { struct nlattr *nla; @@ -461,10 +481,14 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) [BPF_ALU|BPF_MUL|BPF_K] = BPF_S_ALU_MUL_K, [BPF_ALU|BPF_MUL|BPF_X] = BPF_S_ALU_MUL_X, [BPF_ALU|BPF_DIV|BPF_X] = BPF_S_ALU_DIV_X, + [BPF_ALU|BPF_MOD|BPF_K] = BPF_S_ALU_MOD_K, + [BPF_ALU|BPF_MOD|BPF_X] = BPF_S_ALU_MOD_X, [BPF_ALU|BPF_AND|BPF_K] = BPF_S_ALU_AND_K, [BPF_ALU|BPF_AND|BPF_X] = BPF_S_ALU_AND_X, [BPF_ALU|BPF_OR|BPF_K] = BPF_S_ALU_OR_K, [BPF_ALU|BPF_OR|BPF_X] = BPF_S_ALU_OR_X, + [BPF_ALU|BPF_XOR|BPF_K] = BPF_S_ALU_XOR_K, + [BPF_ALU|BPF_XOR|BPF_X] = BPF_S_ALU_XOR_X, [BPF_ALU|BPF_LSH|BPF_K] = BPF_S_ALU_LSH_K, [BPF_ALU|BPF_LSH|BPF_X] = BPF_S_ALU_LSH_X, [BPF_ALU|BPF_RSH|BPF_K] = BPF_S_ALU_RSH_K, @@ -523,6 +547,11 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) return -EINVAL; ftest->k = reciprocal_value(ftest->k); break; + case BPF_S_ALU_MOD_K: + /* check for division by zero */ + if (ftest->k == 0) + return -EINVAL; + break; case BPF_S_LD_MEM: case BPF_S_LDX_MEM: case BPF_S_ST: diff --git a/net/core/link_watch.c b/net/core/link_watch.c index c3519c6d1b16..8f82a5cc3851 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -76,6 +76,14 @@ static void rfc2863_policy(struct net_device *dev) } +void linkwatch_init_dev(struct net_device *dev) +{ + /* Handle pre-registration link state changes */ + if (!netif_carrier_ok(dev) || netif_dormant(dev)) + rfc2863_policy(dev); +} + + static bool linkwatch_urgent_event(struct net_device *dev) { if (!netif_running(dev)) @@ -120,22 +128,13 @@ static void linkwatch_schedule_work(int urgent) delay = 0; /* - * This is true if we've scheduled it immeditately or if we don't - * need an immediate execution and it's already pending. + * If urgent, schedule immediate execution; otherwise, don't + * override the existing timer. */ - if (schedule_delayed_work(&linkwatch_work, delay) == !delay) - return; - - /* Don't bother if there is nothing urgent. */ - if (!test_bit(LW_URGENT, &linkwatch_flags)) - return; - - /* It's already running which is good enough. */ - if (!__cancel_delayed_work(&linkwatch_work)) - return; - - /* Otherwise we reschedule it again for immediate execution. */ - schedule_delayed_work(&linkwatch_work, 0); + if (test_bit(LW_URGENT, &linkwatch_flags)) + mod_delayed_work(system_wq, &linkwatch_work, 0); + else + schedule_delayed_work(&linkwatch_work, delay); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 117afaf51268..baca771caae2 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1545,7 +1545,7 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot allocate neighbour cache hashes"); rwlock_init(&tbl->lock); - INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); skb_queue_head_init_class(&tbl->proxy_queue, @@ -2102,7 +2102,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid, + if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) break; @@ -2115,7 +2115,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (neightbl_fill_param_info(skb, tbl, p, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) @@ -2244,7 +2244,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, continue; if (idx < s_idx) goto next; - if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, + if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI) <= 0) { @@ -2281,7 +2281,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, continue; if (idx < s_idx) goto next; - if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, + if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, tbl) <= 0) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 72607174ea5a..bcf02f608cbf 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -166,9 +166,21 @@ static ssize_t show_duplex(struct device *dev, if (netif_running(netdev)) { struct ethtool_cmd cmd; - if (!__ethtool_get_settings(netdev, &cmd)) - ret = sprintf(buf, "%s\n", - cmd.duplex ? "full" : "half"); + if (!__ethtool_get_settings(netdev, &cmd)) { + const char *duplex; + switch (cmd.duplex) { + case DUPLEX_HALF: + duplex = "half"; + break; + case DUPLEX_FULL: + duplex = "full"; + break; + default: + duplex = "unknown"; + break; + } + ret = sprintf(buf, "%s\n", duplex); + } } rtnl_unlock(); return ret; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index b4c90e42b443..77a0388fc3be 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -26,6 +26,7 @@ #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> #include <asm/unaligned.h> @@ -54,7 +55,7 @@ static atomic_t trapped; MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void arp_reply(struct sk_buff *skb); +static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); @@ -170,7 +171,8 @@ static void poll_napi(struct net_device *dev) list_for_each_entry(napi, &dev->napi_list, dev_list) { if (napi->poll_owner != smp_processor_id() && spin_trylock(&napi->poll_lock)) { - budget = poll_one_napi(dev->npinfo, napi, budget); + budget = poll_one_napi(rcu_dereference_bh(dev->npinfo), + napi, budget); spin_unlock(&napi->poll_lock); if (!budget) @@ -185,13 +187,14 @@ static void service_arp_queue(struct netpoll_info *npi) struct sk_buff *skb; while ((skb = skb_dequeue(&npi->arp_tx))) - arp_reply(skb); + netpoll_arp_reply(skb, npi); } } static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; + struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); if (!dev || !netif_running(dev)) return; @@ -206,17 +209,18 @@ static void netpoll_poll_dev(struct net_device *dev) poll_napi(dev); if (dev->flags & IFF_SLAVE) { - if (dev->npinfo) { + if (ni) { struct net_device *bond_dev = dev->master; struct sk_buff *skb; - while ((skb = skb_dequeue(&dev->npinfo->arp_tx))) { + struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo); + while ((skb = skb_dequeue(&ni->arp_tx))) { skb->dev = bond_dev; - skb_queue_tail(&bond_dev->npinfo->arp_tx, skb); + skb_queue_tail(&bond_ni->arp_tx, skb); } } } - service_arp_queue(dev->npinfo); + service_arp_queue(ni); zap_completion_queue(); } @@ -302,6 +306,7 @@ static int netpoll_owner_active(struct net_device *dev) return 0; } +/* call with IRQ disabled */ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, struct net_device *dev) { @@ -309,8 +314,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, unsigned long tries; const struct net_device_ops *ops = dev->netdev_ops; /* It is up to the caller to keep npinfo alive. */ - struct netpoll_info *npinfo = np->dev->npinfo; + struct netpoll_info *npinfo; + + WARN_ON_ONCE(!irqs_disabled()); + npinfo = rcu_dereference_bh(np->dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { __kfree_skb(skb); return; @@ -319,16 +327,22 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, /* don't get messages out of order, and no recursion */ if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { struct netdev_queue *txq; - unsigned long flags; - txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); + txq = netdev_pick_tx(dev, skb); - local_irq_save(flags); /* try until next clock tick */ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; tries > 0; --tries) { if (__netif_tx_trylock(txq)) { if (!netif_xmit_stopped(txq)) { + if (vlan_tx_tag_present(skb) && + !(netif_skb_features(skb) & NETIF_F_HW_VLAN_TX)) { + skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + if (unlikely(!skb)) + break; + skb->vlan_tci = 0; + } + status = ops->ndo_start_xmit(skb, dev); if (status == NETDEV_TX_OK) txq_trans_update(txq); @@ -347,10 +361,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, } WARN_ONCE(!irqs_disabled(), - "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n", + "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n", dev->name, ops->ndo_start_xmit); - local_irq_restore(flags); } if (status != NETDEV_TX_OK) { @@ -367,6 +380,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; + static atomic_t ip_ident; udp_len = len + sizeof(*udph); ip_len = udp_len + sizeof(*iph); @@ -402,7 +416,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) put_unaligned(0x45, (unsigned char *)iph); iph->tos = 0; put_unaligned(htons(ip_len), &(iph->tot_len)); - iph->id = 0; + iph->id = htons(atomic_inc_return(&ip_ident)); iph->frag_off = 0; iph->ttl = 64; iph->protocol = IPPROTO_UDP; @@ -423,9 +437,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void arp_reply(struct sk_buff *skb) +static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) { - struct netpoll_info *npinfo = skb->dev->npinfo; struct arphdr *arp; unsigned char *arp_ptr; int size, type = ARPOP_REPLY, ptype = ETH_P_ARP; @@ -543,13 +556,12 @@ static void arp_reply(struct sk_buff *skb) spin_unlock_irqrestore(&npinfo->rx_lock, flags); } -int __netpoll_rx(struct sk_buff *skb) +int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) { int proto, len, ulen; int hits = 0; const struct iphdr *iph; struct udphdr *uh; - struct netpoll_info *npinfo = skb->dev->npinfo; struct netpoll *np, *tmp; if (list_empty(&npinfo->rx_np)) @@ -565,6 +577,12 @@ int __netpoll_rx(struct sk_buff *skb) return 1; } + if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + goto out; + } + proto = ntohs(eth_hdr(skb)->h_proto); if (proto != ETH_P_IP) goto out; @@ -715,7 +733,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) } EXPORT_SYMBOL(netpoll_parse_options); -int __netpoll_setup(struct netpoll *np, struct net_device *ndev) +int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) { struct netpoll_info *npinfo; const struct net_device_ops *ops; @@ -734,7 +752,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) } if (!ndev->npinfo) { - npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); + npinfo = kmalloc(sizeof(*npinfo), gfp); if (!npinfo) { err = -ENOMEM; goto out; @@ -752,7 +770,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) ops = np->dev->netdev_ops; if (ops->ndo_netpoll_setup) { - err = ops->ndo_netpoll_setup(ndev, npinfo); + err = ops->ndo_netpoll_setup(ndev, npinfo, gfp); if (err) goto free_npinfo; } @@ -857,7 +875,7 @@ int netpoll_setup(struct netpoll *np) refill_skbs(); rtnl_lock(); - err = __netpoll_setup(np, ndev); + err = __netpoll_setup(np, ndev, GFP_KERNEL); rtnl_unlock(); if (err) @@ -878,6 +896,24 @@ static int __init netpoll_init(void) } core_initcall(netpoll_init); +static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) +{ + struct netpoll_info *npinfo = + container_of(rcu_head, struct netpoll_info, rcu); + + skb_queue_purge(&npinfo->arp_tx); + skb_queue_purge(&npinfo->txq); + + /* we can't call cancel_delayed_work_sync here, as we are in softirq */ + cancel_delayed_work(&npinfo->tx_work); + + /* clean after last, unfinished work */ + __skb_queue_purge(&npinfo->txq); + /* now cancel it again */ + cancel_delayed_work(&npinfo->tx_work); + kfree(npinfo); +} + void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; @@ -903,20 +939,24 @@ void __netpoll_cleanup(struct netpoll *np) ops->ndo_netpoll_cleanup(np->dev); RCU_INIT_POINTER(np->dev->npinfo, NULL); + call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); + } +} +EXPORT_SYMBOL_GPL(__netpoll_cleanup); - /* avoid racing with NAPI reading npinfo */ - synchronize_rcu_bh(); +static void rcu_cleanup_netpoll(struct rcu_head *rcu_head) +{ + struct netpoll *np = container_of(rcu_head, struct netpoll, rcu); - skb_queue_purge(&npinfo->arp_tx); - skb_queue_purge(&npinfo->txq); - cancel_delayed_work_sync(&npinfo->tx_work); + __netpoll_cleanup(np); + kfree(np); +} - /* clean after last, unfinished work */ - __skb_queue_purge(&npinfo->txq); - kfree(npinfo); - } +void __netpoll_free_rcu(struct netpoll *np) +{ + call_rcu_bh(&np->rcu, rcu_cleanup_netpoll); } -EXPORT_SYMBOL_GPL(__netpoll_cleanup); +EXPORT_SYMBOL_GPL(__netpoll_free_rcu); void netpoll_cleanup(struct netpoll *np) { diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 63d15e8f80e9..4a83fb3c8e87 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -73,7 +73,6 @@ static int extend_netdev_table(struct net_device *dev, u32 new_len) ((sizeof(u32) * new_len)); struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL); struct netprio_map *old_priomap; - int i; old_priomap = rtnl_dereference(dev->priomap); @@ -82,10 +81,10 @@ static int extend_netdev_table(struct net_device *dev, u32 new_len) return -ENOMEM; } - for (i = 0; - old_priomap && (i < old_priomap->priomap_len); - i++) - new_priomap->priomap[i] = old_priomap->priomap[i]; + if (old_priomap) + memcpy(new_priomap->priomap, old_priomap->priomap, + old_priomap->priomap_len * + sizeof(old_priomap->priomap[0])); new_priomap->priomap_len = new_len; @@ -101,39 +100,11 @@ static int write_update_netdev_table(struct net_device *dev) u32 max_len; struct netprio_map *map; - rtnl_lock(); max_len = atomic_read(&max_prioidx) + 1; map = rtnl_dereference(dev->priomap); if (!map || map->priomap_len < max_len) ret = extend_netdev_table(dev, max_len); - rtnl_unlock(); - - return ret; -} - -static int update_netdev_tables(void) -{ - int ret = 0; - struct net_device *dev; - u32 max_len; - struct netprio_map *map; - rtnl_lock(); - max_len = atomic_read(&max_prioidx) + 1; - for_each_netdev(&init_net, dev) { - map = rtnl_dereference(dev->priomap); - /* - * don't allocate priomap if we didn't - * change net_prio.ifpriomap (map == NULL), - * this will speed up skb_update_prio. - */ - if (map && map->priomap_len < max_len) { - ret = extend_netdev_table(dev, max_len); - if (ret < 0) - break; - } - } - rtnl_unlock(); return ret; } @@ -155,12 +126,6 @@ static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) goto out; } - ret = update_netdev_tables(); - if (ret < 0) { - put_prioidx(cs->prioidx); - goto out; - } - return &cs->css; out: kfree(cs); @@ -234,7 +199,7 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft, /* *Separate the devname from the associated priority - *and advance the priostr poitner to the priority value + *and advance the priostr pointer to the priority value */ *priostr = '\0'; priostr++; @@ -256,17 +221,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft, if (!dev) goto out_free_devname; + rtnl_lock(); ret = write_update_netdev_table(dev); if (ret < 0) goto out_put_dev; - rcu_read_lock(); - map = rcu_dereference(dev->priomap); + map = rtnl_dereference(dev->priomap); if (map) map->priomap[prioidx] = priority; - rcu_read_unlock(); out_put_dev: + rtnl_unlock(); dev_put(dev); out_free_devname: @@ -277,12 +242,6 @@ out_free_devname: void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct task_struct *p; - char *tmp = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL); - - if (!tmp) { - pr_warn("Unable to attach cgrp due to alloc failure!\n"); - return; - } cgroup_taskset_for_each(p, cgrp, tset) { unsigned int fd; @@ -296,32 +255,24 @@ void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) continue; } - rcu_read_lock(); + spin_lock(&files->file_lock); fdt = files_fdtable(files); for (fd = 0; fd < fdt->max_fds; fd++) { - char *path; struct file *file; struct socket *sock; - unsigned long s; - int rv, err = 0; + int err; file = fcheck_files(files, fd); if (!file) continue; - path = d_path(&file->f_path, tmp, PAGE_SIZE); - rv = sscanf(path, "socket:[%lu]", &s); - if (rv <= 0) - continue; - sock = sock_from_file(file, &err); - if (!err) + if (sock) sock_update_netprioidx(sock->sk, p); } - rcu_read_unlock(); + spin_unlock(&files->file_lock); task_unlock(p); } - kfree(tmp); } static struct cftype ss_files[] = { @@ -342,11 +293,19 @@ struct cgroup_subsys net_prio_subsys = { .create = cgrp_create, .destroy = cgrp_destroy, .attach = net_prio_attach, -#ifdef CONFIG_NETPRIO_CGROUP .subsys_id = net_prio_subsys_id, -#endif .base_cftypes = ss_files, - .module = THIS_MODULE + .module = THIS_MODULE, + + /* + * net_prio has artificial limit on the number of cgroups and + * disallows nesting making it impossible to co-mount it with other + * hierarchical subsystems. Remove the artificially low PRIOIDX_SZ + * limit and properly nest configuration such that children follow + * their parents' configurations by default and are allowed to + * override and remove the following. + */ + .broken_hierarchy = true, }; static int netprio_device_event(struct notifier_block *unused, @@ -382,10 +341,6 @@ static int __init init_cgroup_netprio(void) ret = cgroup_load_subsys(&net_prio_subsys); if (ret) goto out; -#ifndef CONFIG_NETPRIO_CGROUP - smp_wmb(); - net_prio_subsys_id = net_prio_subsys.subsys_id; -#endif register_netdevice_notifier(&netprio_device_notifier); @@ -402,11 +357,6 @@ static void __exit exit_cgroup_netprio(void) cgroup_unload_subsys(&net_prio_subsys); -#ifndef CONFIG_NETPRIO_CGROUP - net_prio_subsys_id = -1; - synchronize_rcu(); -#endif - rtnl_lock(); for_each_netdev(&init_net, dev) { old = rtnl_dereference(dev->priomap); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index cce9e53528b1..148e73d2c451 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2721,7 +2721,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 - pkt_dev->pkt_overhead; - if (datalen < sizeof(struct pktgen_hdr)) + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) datalen = sizeof(struct pktgen_hdr); udph->source = htons(pkt_dev->cur_udp_src); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 9b570a6a33c5..c31d9e8668c3 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -15,6 +15,7 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/tcp.h> #include <linux/vmalloc.h> #include <net/request_sock.h> @@ -130,3 +131,97 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) kfree(lopt); } +/* + * This function is called to set a Fast Open socket's "fastopen_rsk" field + * to NULL when a TFO socket no longer needs to access the request_sock. + * This happens only after 3WHS has been either completed or aborted (e.g., + * RST is received). + * + * Before TFO, a child socket is created only after 3WHS is completed, + * hence it never needs to access the request_sock. things get a lot more + * complex with TFO. A child socket, accepted or not, has to access its + * request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts, + * until 3WHS is either completed or aborted. Afterwards the req will stay + * until either the child socket is accepted, or in the rare case when the + * listener is closed before the child is accepted. + * + * In short, a request socket is only freed after BOTH 3WHS has completed + * (or aborted) and the child socket has been accepted (or listener closed). + * When a child socket is accepted, its corresponding req->sk is set to + * NULL since it's no longer needed. More importantly, "req->sk == NULL" + * will be used by the code below to determine if a child socket has been + * accepted or not, and the check is protected by the fastopenq->lock + * described below. + * + * Note that fastopen_rsk is only accessed from the child socket's context + * with its socket lock held. But a request_sock (req) can be accessed by + * both its child socket through fastopen_rsk, and a listener socket through + * icsk_accept_queue.rskq_accept_head. To protect the access a simple spin + * lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created. + * only in the rare case when both the listener and the child locks are held, + * e.g., in inet_csk_listen_stop() do we not need to acquire the lock. + * The lock also protects other fields such as fastopenq->qlen, which is + * decremented by this function when fastopen_rsk is no longer needed. + * + * Note that another solution was to simply use the existing socket lock + * from the listener. But first socket lock is difficult to use. It is not + * a simple spin lock - one must consider sock_owned_by_user() and arrange + * to use sk_add_backlog() stuff. But what really makes it infeasible is the + * locking hierarchy violation. E.g., inet_csk_listen_stop() may try to + * acquire a child's lock while holding listener's socket lock. A corner + * case might also exist in tcp_v4_hnd_req() that will trigger this locking + * order. + * + * When a TFO req is created, it needs to sock_hold its listener to prevent + * the latter data structure from going away. + * + * This function also sets "treq->listener" to NULL and unreference listener + * socket. treq->listener is used by the listener so it is protected by the + * fastopenq->lock in this function. + */ +void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, + bool reset) +{ + struct sock *lsk = tcp_rsk(req)->listener; + struct fastopen_queue *fastopenq = + inet_csk(lsk)->icsk_accept_queue.fastopenq; + + BUG_ON(!spin_is_locked(&sk->sk_lock.slock) && !sock_owned_by_user(sk)); + + tcp_sk(sk)->fastopen_rsk = NULL; + spin_lock_bh(&fastopenq->lock); + fastopenq->qlen--; + tcp_rsk(req)->listener = NULL; + if (req->sk) /* the child socket hasn't been accepted yet */ + goto out; + + if (!reset || lsk->sk_state != TCP_LISTEN) { + /* If the listener has been closed don't bother with the + * special RST handling below. + */ + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); + reqsk_free(req); + return; + } + /* Wait for 60secs before removing a req that has triggered RST. + * This is a simple defense against TFO spoofing attack - by + * counting the req against fastopen.max_qlen, and disabling + * TFO when the qlen exceeds max_qlen. + * + * For more details see CoNext'11 "TCP Fast Open" paper. + */ + req->expires = jiffies + 60*HZ; + if (fastopenq->rskq_rst_head == NULL) + fastopenq->rskq_rst_head = req; + else + fastopenq->rskq_rst_tail->dl_next = req; + + req->dl_next = NULL; + fastopenq->rskq_rst_tail = req; + fastopenq->qlen++; +out: + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); + return; +} diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 334b930e0de3..76d4c2c3c89b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -618,16 +618,20 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error) { struct rta_cacheinfo ci = { - .rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse), + .rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse), .rta_used = dst->__use, .rta_clntref = atomic_read(&(dst->__refcnt)), .rta_error = error, .rta_id = id, }; - if (expires) - ci.rta_expires = jiffies_to_clock_t(expires); + if (expires) { + unsigned long clock; + clock = jiffies_to_clock_t(abs(expires)); + clock = min_t(unsigned long, clock, INT_MAX); + ci.rta_expires = (expires > 0) ? clock : -clock; + } return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); } EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); @@ -659,6 +663,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } +static unsigned int rtnl_dev_get_flags(const struct net_device *dev) +{ + return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | + (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); +} + static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, const struct ifinfomsg *ifm) { @@ -667,7 +677,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ if (ifm->ifi_change) flags = (flags & ifm->ifi_change) | - (dev->flags & ~ifm->ifi_change); + (rtnl_dev_get_flags(dev) & ~ifm->ifi_change); return flags; } @@ -1071,7 +1081,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) goto cont; if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, NLM_F_MULTI, ext_filter_mask) <= 0) @@ -1371,6 +1381,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; send_addr_notify = 1; modified = 1; + add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { @@ -1801,8 +1812,6 @@ replay: return -ENODEV; } - if (ifm->ifi_index) - return -EOPNOTSUPP; if (tb[IFLA_MAP] || tb[IFLA_MASTER] || tb[IFLA_PROTINFO]) return -EOPNOTSUPP; @@ -1828,10 +1837,14 @@ replay: return PTR_ERR(dest_net); dev = rtnl_create_link(net, dest_net, ifname, ops, tb); - - if (IS_ERR(dev)) + if (IS_ERR(dev)) { err = PTR_ERR(dev); - else if (ops->newlink) + goto out; + } + + dev->ifindex = ifm->ifi_index; + + if (ops->newlink) err = ops->newlink(net, dev, tb, data); else err = register_netdevice(dev); @@ -1886,14 +1899,14 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (nskb == NULL) return -ENOBUFS; - err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, + err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, ext_filter_mask); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(nskb); } else - err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid); + err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); return err; } @@ -2077,7 +2090,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { master = dev->master; - err = master->netdev_ops->ndo_fdb_add(ndm, dev, addr, + err = master->netdev_ops->ndo_fdb_add(ndm, tb, + dev, addr, nlh->nlmsg_flags); if (err) goto out; @@ -2087,7 +2101,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Embedded bridge, macvlan, and any other device support */ if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) { - err = dev->netdev_ops->ndo_fdb_add(ndm, dev, addr, + err = dev->netdev_ops->ndo_fdb_add(ndm, tb, + dev, addr, nlh->nlmsg_flags); if (!err) { @@ -2167,9 +2182,9 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, { struct netdev_hw_addr *ha; int err; - u32 pid, seq; + u32 portid, seq; - pid = NETLINK_CB(cb->skb).pid; + portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; list_for_each_entry(ha, &list->list, list) { @@ -2177,7 +2192,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, - pid, seq, 0, NTF_SELF); + portid, seq, 0, NTF_SELF); if (err < 0) return err; skip: @@ -2345,7 +2360,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_PRE_TYPE_CHANGE: case NETDEV_GOING_DOWN: case NETDEV_UNREGISTER: - case NETDEV_UNREGISTER_BATCH: + case NETDEV_UNREGISTER_FINAL: case NETDEV_RELEASE: case NETDEV_JOIN: break; @@ -2368,9 +2383,10 @@ static int __net_init rtnetlink_net_init(struct net *net) .groups = RTNLGRP_MAX, .input = rtnetlink_rcv, .cb_mutex = &rtnl_mutex, + .flags = NL_CFG_F_NONROOT_RECV, }; - sk = netlink_kernel_create(net, NETLINK_ROUTE, THIS_MODULE, &cfg); + sk = netlink_kernel_create(net, NETLINK_ROUTE, &cfg); if (!sk) return -ENOMEM; net->rtnl = sk; @@ -2403,7 +2419,6 @@ void __init rtnetlink_init(void) if (register_pernet_subsys(&rtnetlink_net_ops)) panic("rtnetlink_init: cannot initialize rtnetlink\n"); - netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV); register_netdevice_notifier(&rtnetlink_dev_notifier); rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, diff --git a/net/core/scm.c b/net/core/scm.c index 8f6ccfd68ef4..9c1c63da3ca8 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -45,12 +45,17 @@ static __inline__ int scm_check_creds(struct ucred *creds) { const struct cred *cred = current_cred(); + kuid_t uid = make_kuid(cred->user_ns, creds->uid); + kgid_t gid = make_kgid(cred->user_ns, creds->gid); + + if (!uid_valid(uid) || !gid_valid(gid)) + return -EINVAL; if ((creds->pid == task_tgid_vnr(current) || capable(CAP_SYS_ADMIN)) && - ((creds->uid == cred->uid || creds->uid == cred->euid || - creds->uid == cred->suid) || capable(CAP_SETUID)) && - ((creds->gid == cred->gid || creds->gid == cred->egid || - creds->gid == cred->sgid) || capable(CAP_SETGID))) { + ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || + uid_eq(uid, cred->suid)) || capable(CAP_SETUID)) && + ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || + gid_eq(gid, cred->sgid)) || capable(CAP_SETGID))) { return 0; } return -EPERM; @@ -149,39 +154,54 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) goto error; break; case SCM_CREDENTIALS: + { + struct ucred creds; + kuid_t uid; + kgid_t gid; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct ucred))) goto error; - memcpy(&p->creds, CMSG_DATA(cmsg), sizeof(struct ucred)); - err = scm_check_creds(&p->creds); + memcpy(&creds, CMSG_DATA(cmsg), sizeof(struct ucred)); + err = scm_check_creds(&creds); if (err) goto error; - if (!p->pid || pid_vnr(p->pid) != p->creds.pid) { + p->creds.pid = creds.pid; + if (!p->pid || pid_vnr(p->pid) != creds.pid) { struct pid *pid; err = -ESRCH; - pid = find_get_pid(p->creds.pid); + pid = find_get_pid(creds.pid); if (!pid) goto error; put_pid(p->pid); p->pid = pid; } + err = -EINVAL; + uid = make_kuid(current_user_ns(), creds.uid); + gid = make_kgid(current_user_ns(), creds.gid); + if (!uid_valid(uid) || !gid_valid(gid)) + goto error; + + p->creds.uid = uid; + p->creds.gid = gid; + if (!p->cred || - (p->cred->euid != p->creds.uid) || - (p->cred->egid != p->creds.gid)) { + !uid_eq(p->cred->euid, uid) || + !gid_eq(p->cred->egid, gid)) { struct cred *cred; err = -ENOMEM; cred = prepare_creds(); if (!cred) goto error; - cred->uid = cred->euid = p->creds.uid; - cred->gid = cred->egid = p->creds.gid; + cred->uid = cred->euid = uid; + cred->gid = cred->egid = gid; if (p->cred) put_cred(p->cred); p->cred = cred; } break; + } default: goto error; } @@ -265,6 +285,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax; i++, cmfptr++) { + struct socket *sock; int new_fd; err = security_file_receive(fp[i]); if (err) @@ -281,6 +302,9 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } /* Bump the usage count and install the file. */ get_file(fp[i]); + sock = sock_from_file(fp[i], &err); + if (sock) + sock_update_netprioidx(sock->sk, current); fd_install(new_fd, fp[i]); } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 99b2596531bb..e61a8bb7fce7 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -76,6 +76,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, return hash[0]; } +EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 368f65c15e4f..cdc28598f4ef 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -145,6 +145,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) BUG(); } + +/* + * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells + * the caller if emergency pfmemalloc reserves are being used. If it is and + * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves + * may be used. Otherwise, the packet data may be discarded until enough + * memory is free + */ +#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ + __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) +void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, + bool *pfmemalloc) +{ + void *obj; + bool ret_pfmemalloc = false; + + /* + * Try a regular allocation, when that fails and we're not entitled + * to the reserves, fail. + */ + obj = kmalloc_node_track_caller(size, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj || !(gfp_pfmemalloc_allowed(flags))) + goto out; + + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmalloc_node_track_caller(size, flags, node); + +out: + if (pfmemalloc) + *pfmemalloc = ret_pfmemalloc; + + return obj; +} + /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. @@ -155,8 +192,10 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask - * @fclone: allocate from fclone cache instead of head cache - * and allocate a cloned (child) skb + * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache + * instead of head cache and allocate a cloned (child) skb. + * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for + * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a @@ -167,14 +206,19 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, - int fclone, int node) + int flags, int node) { struct kmem_cache *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + bool pfmemalloc; + + cache = (flags & SKB_ALLOC_FCLONE) + ? skbuff_fclone_cache : skbuff_head_cache; - cache = fclone ? skbuff_fclone_cache : skbuff_head_cache; + if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) + gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); @@ -189,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - data = kmalloc_node_track_caller(size, gfp_mask, node); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; /* kmalloc(size) might give us more room than requested. @@ -207,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, memset(skb, 0, offsetof(struct sk_buff, tail)); /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); + skb->pfmemalloc = pfmemalloc; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -222,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(&shinfo->dataref, 1); kmemcheck_annotate_variable(shinfo->destructor_arg); - if (fclone) { + if (flags & SKB_ALLOC_FCLONE) { struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); @@ -232,6 +277,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(fclone_ref, 1); child->fclone = SKB_FCLONE_UNAVAILABLE; + child->pfmemalloc = pfmemalloc; } out: return skb; @@ -294,55 +340,74 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { - struct page *page; - unsigned int offset; - unsigned int pagecnt_bias; + struct page_frag frag; + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_count every time we allocate a fragment. + */ + unsigned int pagecnt_bias; }; static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); -#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES) +#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768) +#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER) +#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE -/** - * netdev_alloc_frag - allocate a page fragment - * @fragsz: fragment size - * - * Allocates a frag from a page for receive buffer. - * Uses GFP_ATOMIC allocations. - */ -void *netdev_alloc_frag(unsigned int fragsz) +static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct netdev_alloc_cache *nc; void *data = NULL; + int order; unsigned long flags; local_irq_save(flags); nc = &__get_cpu_var(netdev_alloc_cache); - if (unlikely(!nc->page)) { + if (unlikely(!nc->frag.page)) { refill: - nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD); - if (unlikely(!nc->page)) - goto end; + for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) { + gfp_t gfp = gfp_mask; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN; + nc->frag.page = alloc_pages(gfp, order); + if (likely(nc->frag.page)) + break; + if (--order < 0) + goto end; + } + nc->frag.size = PAGE_SIZE << order; recycle: - atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS); - nc->pagecnt_bias = NETDEV_PAGECNT_BIAS; - nc->offset = 0; + atomic_set(&nc->frag.page->_count, NETDEV_PAGECNT_MAX_BIAS); + nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS; + nc->frag.offset = 0; } - if (nc->offset + fragsz > PAGE_SIZE) { + if (nc->frag.offset + fragsz > nc->frag.size) { /* avoid unnecessary locked operations if possible */ - if ((atomic_read(&nc->page->_count) == nc->pagecnt_bias) || - atomic_sub_and_test(nc->pagecnt_bias, &nc->page->_count)) + if ((atomic_read(&nc->frag.page->_count) == nc->pagecnt_bias) || + atomic_sub_and_test(nc->pagecnt_bias, &nc->frag.page->_count)) goto recycle; goto refill; } - data = page_address(nc->page) + nc->offset; - nc->offset += fragsz; + data = page_address(nc->frag.page) + nc->frag.offset; + nc->frag.offset += fragsz; nc->pagecnt_bias--; end: local_irq_restore(flags); return data; } + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +void *netdev_alloc_frag(unsigned int fragsz) +{ + return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); +} EXPORT_SYMBOL(netdev_alloc_frag); /** @@ -366,7 +431,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { - void *data = netdev_alloc_frag(fragsz); + void *data; + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __netdev_alloc_frag(fragsz, gfp_mask); if (likely(data)) { skb = build_skb(data, fragsz); @@ -374,7 +444,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, put_page(virt_to_head_page(data)); } } else { - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, + SKB_ALLOC_RX, NUMA_NO_NODE); } if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); @@ -656,6 +727,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #if IS_ENABLED(CONFIG_IP_VS) new->ipvs_property = old->ipvs_property; #endif + new->pfmemalloc = old->pfmemalloc; new->protocol = old->protocol; new->mark = old->mark; new->skb_iif = old->skb_iif; @@ -814,6 +886,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n->fclone = SKB_FCLONE_CLONE; atomic_inc(fclone_ref); } else { + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; @@ -850,6 +925,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } +static inline int skb_alloc_rx_flag(const struct sk_buff *skb) +{ + if (skb_pfmemalloc(skb)) + return SKB_ALLOC_RX; + return 0; +} + /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy @@ -871,7 +953,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { int headerlen = skb_headroom(skb); unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = alloc_skb(size, gfp_mask); + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -906,7 +989,8 @@ EXPORT_SYMBOL(skb_copy); struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { unsigned int size = skb_headlen(skb) + headroom; - struct sk_buff *n = alloc_skb(size, gfp_mask); + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) goto out; @@ -979,8 +1063,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, size = SKB_DATA_ALIGN(size); - data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), - gfp_mask); + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(ksize(data)); @@ -1092,8 +1178,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask); + struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; int off; @@ -1582,38 +1669,19 @@ static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sk_buff *skb, struct sock *sk) { - struct page *p = sk->sk_sndmsg_page; - unsigned int off; + struct page_frag *pfrag = sk_page_frag(sk); - if (!p) { -new_page: - p = sk->sk_sndmsg_page = alloc_pages(sk->sk_allocation, 0); - if (!p) - return NULL; - - off = sk->sk_sndmsg_off = 0; - /* hold one ref to this page until it's full */ - } else { - unsigned int mlen; - - /* If we are the only user of the page, we can reset offset */ - if (page_count(p) == 1) - sk->sk_sndmsg_off = 0; - off = sk->sk_sndmsg_off; - mlen = PAGE_SIZE - off; - if (mlen < 64 && mlen < *len) { - put_page(p); - goto new_page; - } + if (!sk_page_frag_refill(sk, pfrag)) + return NULL; - *len = min_t(unsigned int, *len, mlen); - } + *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); - memcpy(page_address(p) + off, page_address(page) + *offset, *len); - sk->sk_sndmsg_off += *len; - *offset = off; + memcpy(page_address(pfrag->page) + pfrag->offset, + page_address(page) + *offset, *len); + *offset = pfrag->offset; + pfrag->offset += *len; - return p; + return pfrag->page; } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, @@ -2775,8 +2843,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { - nskb = alloc_skb(hsize + doffset + headroom, - GFP_ATOMIC); + nskb = __alloc_skb(hsize + doffset + headroom, + GFP_ATOMIC, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (unlikely(!nskb)) goto err; @@ -3414,8 +3483,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS) return false; - delta = from->truesize - - SKB_TRUESIZE(skb_end_pointer(from) - from->head); + delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); } WARN_ON_ONCE(delta < len); @@ -3428,7 +3496,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (!skb_cloned(from)) skb_shinfo(from)->nr_frags = 0; - /* if the skb is cloned this does nothing since we set nr_frags to 0 */ + /* if the skb is not cloned this does nothing + * since we set nr_frags to 0. + */ for (i = 0; i < skb_shinfo(from)->nr_frags; i++) skb_frag_ref(from, i); diff --git a/net/core/sock.c b/net/core/sock.c index 2676a88f533e..8a146cfcc366 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,7 +142,7 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { struct proto *proto; @@ -271,16 +271,60 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); -#if defined(CONFIG_CGROUPS) -#if !defined(CONFIG_NET_CLS_CGROUP) -int net_cls_subsys_id = -1; -EXPORT_SYMBOL_GPL(net_cls_subsys_id); -#endif -#if !defined(CONFIG_NETPRIO_CGROUP) -int net_prio_subsys_id = -1; -EXPORT_SYMBOL_GPL(net_prio_subsys_id); -#endif -#endif +struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(memalloc_socks); + +/** + * sk_set_memalloc - sets %SOCK_MEMALLOC + * @sk: socket to set it on + * + * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. + * It's the responsibility of the admin to adjust min_free_kbytes + * to meet the requirements + */ +void sk_set_memalloc(struct sock *sk) +{ + sock_set_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation |= __GFP_MEMALLOC; + static_key_slow_inc(&memalloc_socks); +} +EXPORT_SYMBOL_GPL(sk_set_memalloc); + +void sk_clear_memalloc(struct sock *sk) +{ + sock_reset_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation &= ~__GFP_MEMALLOC; + static_key_slow_dec(&memalloc_socks); + + /* + * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward + * progress of swapping. However, if SOCK_MEMALLOC is cleared while + * it has rmem allocations there is a risk that the user of the + * socket cannot make forward progress due to exceeding the rmem + * limits. By rights, sk_clear_memalloc() should only be called + * on sockets being torn down but warn and reset the accounting if + * that assumption breaks. + */ + if (WARN_ON(sk->sk_forward_alloc)) + sk_mem_reclaim(sk); +} +EXPORT_SYMBOL_GPL(sk_clear_memalloc); + +int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + int ret; + unsigned long pflags = current->flags; + + /* these should have been dropped before queueing */ + BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); + + current->flags |= PF_MEMALLOC; + ret = sk->sk_backlog_rcv(sk, skb); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + + return ret; +} +EXPORT_SYMBOL(__sk_backlog_rcv); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -353,7 +397,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (err) return err; - if (!sk_rmem_schedule(sk, skb->truesize)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } @@ -636,7 +680,8 @@ set_rcvbuf: case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) tcp_set_keepalive(sk, valbool); #endif sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); @@ -813,8 +858,8 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred, if (cred) { struct user_namespace *current_ns = current_user_ns(); - ucred->uid = from_kuid(current_ns, cred->euid); - ucred->gid = from_kgid(current_ns, cred->egid); + ucred->uid = from_kuid_munged(current_ns, cred->euid); + ucred->gid = from_kgid_munged(current_ns, cred->egid); } } EXPORT_SYMBOL_GPL(cred_to_ucred); @@ -1168,6 +1213,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) } #ifdef CONFIG_CGROUPS +#if IS_ENABLED(CONFIG_NET_CLS_CGROUP) void sock_update_classid(struct sock *sk) { u32 classid; @@ -1175,11 +1221,13 @@ void sock_update_classid(struct sock *sk) rcu_read_lock(); /* doing current task, which cannot vanish. */ classid = task_cls_classid(current); rcu_read_unlock(); - if (classid && classid != sk->sk_classid) + if (classid != sk->sk_classid) sk->sk_classid = classid; } EXPORT_SYMBOL(sock_update_classid); +#endif +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) void sock_update_netprioidx(struct sock *sk, struct task_struct *task) { if (in_interrupt()) @@ -1189,6 +1237,7 @@ void sock_update_netprioidx(struct sock *sk, struct task_struct *task) } EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif +#endif /** * sk_alloc - All socket objects are allocated here @@ -1403,24 +1452,12 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; + sk->sk_gso_max_segs = dst->dev->gso_max_segs; } } } EXPORT_SYMBOL_GPL(sk_setup_caps); -void __init sk_init(void) -{ - if (totalram_pages <= 4096) { - sysctl_wmem_max = 32767; - sysctl_rmem_max = 32767; - sysctl_wmem_default = 32767; - sysctl_rmem_default = 32767; - } else if (totalram_pages >= 131072) { - sysctl_wmem_max = 131071; - sysctl_rmem_max = 131071; - } -} - /* * Simple resource managers for sockets. */ @@ -1467,16 +1504,23 @@ EXPORT_SYMBOL(sock_rfree); void sock_edemux(struct sk_buff *skb) { - sock_put(skb->sk); + struct sock *sk = skb->sk; + +#ifdef CONFIG_INET + if (sk->sk_state == TCP_TIME_WAIT) + inet_twsk_put(inet_twsk(sk)); + else +#endif + sock_put(sk); } EXPORT_SYMBOL(sock_edemux); -int sock_i_uid(struct sock *sk) +kuid_t sock_i_uid(struct sock *sk) { - int uid; + kuid_t uid; read_lock_bh(&sk->sk_callback_lock); - uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; + uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; read_unlock_bh(&sk->sk_callback_lock); return uid; } @@ -1681,6 +1725,45 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, } EXPORT_SYMBOL(sock_alloc_send_skb); +/* On 32bit arches, an skb frag is limited to 2^15 */ +#define SKB_FRAG_PAGE_ORDER get_order(32768) + +bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) +{ + int order; + + if (pfrag->page) { + if (atomic_read(&pfrag->page->_count) == 1) { + pfrag->offset = 0; + return true; + } + if (pfrag->offset < pfrag->size) + return true; + put_page(pfrag->page); + } + + /* We restrict high order allocations to users that can afford to wait */ + order = (sk->sk_allocation & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0; + + do { + gfp_t gfp = sk->sk_allocation; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN; + pfrag->page = alloc_pages(gfp, order); + if (likely(pfrag->page)) { + pfrag->offset = 0; + pfrag->size = PAGE_SIZE << order; + return true; + } + } while (--order >= 0); + + sk_enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return false; +} +EXPORT_SYMBOL(sk_page_frag_refill); + static void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) @@ -2110,8 +2193,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; @@ -2354,6 +2437,12 @@ void sk_common_release(struct sock *sk) xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); + + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + } + sock_put(sk); } EXPORT_SYMBOL(sk_common_release); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 9d8755e4a7a5..602cd637182e 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -172,8 +172,7 @@ static int __net_init diag_net_init(struct net *net) .input = sock_diag_rcv, }; - net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, - THIS_MODULE, &cfg); + net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); return net->diag_nlsk == NULL ? -ENOMEM : 0; } diff --git a/net/core/utils.c b/net/core/utils.c index 39895a65e54a..f5613d569c23 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -294,6 +294,26 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, } EXPORT_SYMBOL(inet_proto_csum_replace4); +void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, + const __be32 *from, const __be32 *to, + int pseudohdr) +{ + __be32 diff[] = { + ~from[0], ~from[1], ~from[2], ~from[3], + to[0], to[1], to[2], to[3], + }; + if (skb->ip_summed != CHECKSUM_PARTIAL) { + *sum = csum_fold(csum_partial(diff, sizeof(diff), + ~csum_unfold(*sum))); + if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) + skb->csum = ~csum_partial(diff, sizeof(diff), + ~skb->csum); + } else if (pseudohdr) + *sum = ~csum_fold(csum_partial(diff, sizeof(diff), + csum_unfold(*sum))); +} +EXPORT_SYMBOL(inet_proto_csum_replace16); + int mac_pton(const char *s, u8 *mac) { int i; |