diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 150 | ||||
-rw-r--r-- | net/core/dst.c | 34 | ||||
-rw-r--r-- | net/core/ethtool.c | 106 | ||||
-rw-r--r-- | net/core/fib_rules.c | 3 | ||||
-rw-r--r-- | net/core/filter.c | 67 | ||||
-rw-r--r-- | net/core/link_watch.c | 2 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 24 | ||||
-rw-r--r-- | net/core/net_namespace.c | 12 | ||||
-rw-r--r-- | net/core/netpoll.c | 2 | ||||
-rw-r--r-- | net/core/pktgen.c | 37 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 16 | ||||
-rw-r--r-- | net/core/skbuff.c | 2 | ||||
-rw-r--r-- | net/core/sock.c | 10 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 9 |
14 files changed, 269 insertions, 205 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 3da9fb0..e95dc30 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1315,7 +1315,8 @@ void dev_disable_lro(struct net_device *dev) return; __ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO); - WARN_ON(dev->features & NETIF_F_LRO); + if (unlikely(dev->features & NETIF_F_LRO)) + netdev_WARN(dev, "failed to disable LRO!\n"); } EXPORT_SYMBOL(dev_disable_lro); @@ -2091,7 +2092,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 features; /* - * If device doesnt need skb->dst, release it right now while + * If device doesn't need skb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) @@ -2151,7 +2152,7 @@ gso: nskb->next = NULL; /* - * If device doesnt need nskb->dst, release it right now while + * If device doesn't need nskb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) @@ -2502,8 +2503,8 @@ static inline void ____napi_schedule(struct softnet_data *sd, __u32 __skb_get_rxhash(struct sk_buff *skb) { int nhoff, hash = 0, poff; - struct ipv6hdr *ip6; - struct iphdr *ip; + const struct ipv6hdr *ip6; + const struct iphdr *ip; u8 ip_proto; u32 addr1, addr2, ihl; union { @@ -2518,7 +2519,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(*ip) + nhoff)) goto done; - ip = (struct iphdr *) (skb->data + nhoff); + ip = (const struct iphdr *) (skb->data + nhoff); if (ip->frag_off & htons(IP_MF | IP_OFFSET)) ip_proto = 0; else @@ -2531,7 +2532,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff)) goto done; - ip6 = (struct ipv6hdr *) (skb->data + nhoff); + ip6 = (const struct ipv6hdr *) (skb->data + nhoff); ip_proto = ip6->nexthdr; addr1 = (__force u32) ip6->saddr.s6_addr32[3]; addr2 = (__force u32) ip6->daddr.s6_addr32[3]; @@ -2970,8 +2971,8 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions * a compare and 2 stores extra right now if we dont have it on * but have CONFIG_NET_CLS_ACT - * NOTE: This doesnt stop any functionality; if you dont have - * the ingress scheduler, you just cant add policies on ingress. + * NOTE: This doesn't stop any functionality; if you dont have + * the ingress scheduler, you just can't add policies on ingress. * */ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) @@ -3076,25 +3077,6 @@ void netdev_rx_handler_unregister(struct net_device *dev) } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); -static void vlan_on_bond_hook(struct sk_buff *skb) -{ - /* - * Make sure ARP frames received on VLAN interfaces stacked on - * bonding interfaces still make their way to any base bonding - * device that may have registered for a specific ptype. - */ - if (skb->dev->priv_flags & IFF_802_1Q_VLAN && - vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING && - skb->protocol == htons(ETH_P_ARP)) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - - if (!skb2) - return; - skb2->dev = vlan_dev_real_dev(skb->dev); - netif_rx(skb2); - } -} - static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; @@ -3130,6 +3112,12 @@ another_round: __this_cpu_inc(softnet_data.processed); + if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + goto out; + } + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -3177,15 +3165,13 @@ ncls: ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } - if (vlan_hwaccel_do_receive(&skb)) { + if (vlan_do_receive(&skb)) { ret = __netif_receive_skb(skb); goto out; } else if (unlikely(!skb)) goto out; } - vlan_on_bond_hook(skb); - /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; @@ -3800,7 +3786,7 @@ static void net_rx_action(struct softirq_action *h) * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid - * accidently calling ->poll() when NAPI is not scheduled. + * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (test_bit(NAPI_STATE_SCHED, &n->state)) { @@ -4510,6 +4496,30 @@ void dev_set_rx_mode(struct net_device *dev) } /** + * dev_ethtool_get_settings - call device's ethtool_ops::get_settings() + * @dev: device + * @cmd: memory area for ethtool_ops::get_settings() result + * + * The cmd arg is initialized properly (cleared and + * ethtool_cmd::cmd field set to ETHTOOL_GSET). + * + * Return device's ethtool_ops::get_settings() result value or + * -EOPNOTSUPP when device doesn't expose + * ethtool_ops::get_settings() operation. + */ +int dev_ethtool_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + memset(cmd, 0, sizeof(struct ethtool_cmd)); + cmd->cmd = ETHTOOL_GSET; + return dev->ethtool_ops->get_settings(dev, cmd); +} +EXPORT_SYMBOL(dev_ethtool_get_settings); + +/** * dev_get_flags - get flags reported to userspace * @dev: device * @@ -5203,11 +5213,15 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) } /* TSO requires that SG is present as well. */ - if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) { - netdev_info(dev, "Dropping NETIF_F_TSO since no SG feature.\n"); - features &= ~NETIF_F_TSO; + if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { + netdev_info(dev, "Dropping TSO features since no SG feature.\n"); + features &= ~NETIF_F_ALL_TSO; } + /* TSO ECN requires that TSO is present as well. */ + if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) + features &= ~NETIF_F_TSO_ECN; + /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); @@ -5236,11 +5250,13 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) } EXPORT_SYMBOL(netdev_fix_features); -void netdev_update_features(struct net_device *dev) +int __netdev_update_features(struct net_device *dev) { u32 features; int err = 0; + ASSERT_RTNL(); + features = netdev_get_wanted_features(dev); if (dev->netdev_ops->ndo_fix_features) @@ -5250,7 +5266,7 @@ void netdev_update_features(struct net_device *dev) features = netdev_fix_features(dev, features); if (dev->features == features) - return; + return 0; netdev_info(dev, "Features changed: 0x%08x -> 0x%08x\n", dev->features, features); @@ -5258,12 +5274,23 @@ void netdev_update_features(struct net_device *dev) if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); - if (!err) - dev->features = features; - else if (err < 0) + if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n", err, features, dev->features); + return -1; + } + + if (!err) + dev->features = features; + + return 1; +} + +void netdev_update_features(struct net_device *dev) +{ + if (__netdev_update_features(dev)) + netdev_features_change(dev); } EXPORT_SYMBOL(netdev_update_features); @@ -5414,6 +5441,14 @@ int register_netdevice(struct net_device *dev) dev->features &= ~NETIF_F_GSO; } + /* Turn on no cache copy if HW is doing checksum */ + dev->hw_features |= NETIF_F_NOCACHE_COPY; + if ((dev->features & NETIF_F_ALL_CSUM) && + !(dev->features & NETIF_F_NO_CSUM)) { + dev->wanted_features |= NETIF_F_NOCACHE_COPY; + dev->features |= NETIF_F_NOCACHE_COPY; + } + /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, * vlan_dev_init() will do the dev->features check, so these features * are enabled only if supported by underlying device. @@ -5430,7 +5465,7 @@ int register_netdevice(struct net_device *dev) goto err_uninit; dev->reg_state = NETREG_REGISTERED; - netdev_update_features(dev); + __netdev_update_features(dev); /* * Default initial state at registry is that the @@ -6153,29 +6188,20 @@ static int dev_cpu_callback(struct notifier_block *nfb, */ u32 netdev_increment_features(u32 all, u32 one, u32 mask) { - /* If device needs checksumming, downgrade to it. */ - if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) - all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM); - else if (mask & NETIF_F_ALL_CSUM) { - /* If one device supports v4/v6 checksumming, set for all. */ - if (one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM) && - !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - } + if (mask & NETIF_F_GEN_CSUM) + mask |= NETIF_F_ALL_CSUM; + mask |= NETIF_F_VLAN_CHALLENGED; - /* If one device supports hw checksumming, set for all. */ - if (one & NETIF_F_GEN_CSUM && !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= NETIF_F_HW_CSUM; - } - } + all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; + all &= one | ~NETIF_F_ALL_FOR_ALL; - one |= NETIF_F_ALL_CSUM; + /* If device needs checksumming, downgrade to it. */ + if (all & (NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM)) + all &= ~NETIF_F_NO_CSUM; - one |= all & NETIF_F_ONE_FOR_ALL; - all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO; - all |= one & mask & NETIF_F_ONE_FOR_ALL; + /* If one device supports hw checksumming, set for all. */ + if (all & NETIF_F_GEN_CSUM) + all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); return all; } @@ -6336,7 +6362,7 @@ static void __net_exit default_device_exit(struct net *net) if (dev->rtnl_link_ops) continue; - /* Push remaing network devices to init_net */ + /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { diff --git a/net/core/dst.c b/net/core/dst.c index 91104d3..30f0093 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -166,7 +166,8 @@ EXPORT_SYMBOL(dst_discard); const u32 dst_default_metrics[RTAX_MAX]; -void *dst_alloc(struct dst_ops *ops, int initial_ref) +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, int flags) { struct dst_entry *dst; @@ -174,15 +175,36 @@ void *dst_alloc(struct dst_ops *ops, int initial_ref) if (ops->gc(ops)) return NULL; } - dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC); + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) return NULL; - atomic_set(&dst->__refcnt, initial_ref); + dst->child = NULL; + dst->dev = dev; + if (dev) + dev_hold(dev); dst->ops = ops; - dst->lastuse = jiffies; - dst->path = dst; - dst->input = dst->output = dst_discard; dst_init_metrics(dst, dst_default_metrics, true); + dst->expires = 0UL; + dst->path = dst; + dst->neighbour = NULL; + dst->hh = NULL; +#ifdef CONFIG_XFRM + dst->xfrm = NULL; +#endif + dst->input = dst_discard; + dst->output = dst_discard; + dst->error = 0; + dst->obsolete = initial_obsolete; + dst->header_len = 0; + dst->trailer_len = 0; +#ifdef CONFIG_IP_ROUTE_CLASSID + dst->tclassid = 0; +#endif + atomic_set(&dst->__refcnt, initial_ref); + dst->__use = 0; + dst->lastuse = jiffies; + dst->flags = flags; + dst->next = NULL; #if RT_CACHE_DEBUG >= 2 atomic_inc(&dst_total); #endif diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 74ead9e..d8b1a8d 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -21,6 +21,8 @@ #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/slab.h> +#include <linux/rtnetlink.h> +#include <linux/sched.h> /* * Some useful ethtool_ops methods that're device independent. @@ -317,7 +319,7 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) dev->wanted_features &= ~features[0].valid; dev->wanted_features |= features[0].valid & features[0].requested; - netdev_update_features(dev); + __netdev_update_features(dev); if ((dev->wanted_features ^ dev->features) & features[0].valid) ret |= ETHTOOL_F_WISH; @@ -359,7 +361,7 @@ static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GS /* NETIF_F_NTUPLE */ "rx-ntuple-filter", /* NETIF_F_RXHASH */ "rx-hashing", /* NETIF_F_RXCSUM */ "rx-checksum", - "", + /* NETIF_F_NOCACHE_COPY */ "tx-nocache-copy" "", }; @@ -499,7 +501,7 @@ static int ethtool_set_one_feature(struct net_device *dev, else dev->wanted_features &= ~mask; - netdev_update_features(dev); + __netdev_update_features(dev); return 0; } @@ -544,14 +546,14 @@ int __ethtool_set_flags(struct net_device *dev, u32 data) } /* allow changing only bits set in hw_features */ - changed = (data ^ dev->wanted_features) & flags_dup_features; + changed = (data ^ dev->features) & flags_dup_features; if (changed & ~dev->hw_features) return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; dev->wanted_features = - (dev->wanted_features & ~changed) | data; + (dev->wanted_features & ~changed) | (data & dev->hw_features); - netdev_update_features(dev); + __netdev_update_features(dev); return 0; } @@ -908,6 +910,9 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL; int ret; + if (!ops->set_rx_ntuple) + return -EOPNOTSUPP; + if (!(dev->features & NETIF_F_NTUPLE)) return -EINVAL; @@ -1441,6 +1446,35 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_ringparam(dev, &ringparam); } +static noinline_for_stack int ethtool_get_channels(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + + if (!dev->ethtool_ops->get_channels) + return -EOPNOTSUPP; + + dev->ethtool_ops->get_channels(dev, &channels); + + if (copy_to_user(useraddr, &channels, sizeof(channels))) + return -EFAULT; + return 0; +} + +static noinline_for_stack int ethtool_set_channels(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_channels channels; + + if (!dev->ethtool_ops->set_channels) + return -EOPNOTSUPP; + + if (copy_from_user(&channels, useraddr, sizeof(channels))) + return -EFAULT; + + return dev->ethtool_ops->set_channels(dev, &channels); +} + static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam = { ETHTOOL_GPAUSEPARAM }; @@ -1618,14 +1652,64 @@ out: static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; + static bool busy; + int rc; - if (!dev->ethtool_ops->phys_id) + if (!dev->ethtool_ops->set_phys_id && !dev->ethtool_ops->phys_id) return -EOPNOTSUPP; + if (busy) + return -EBUSY; + if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; - return dev->ethtool_ops->phys_id(dev, id.data); + if (!dev->ethtool_ops->set_phys_id) + /* Do it the old way */ + return dev->ethtool_ops->phys_id(dev, id.data); + + rc = dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); + if (rc < 0) + return rc; + + /* Drop the RTNL lock while waiting, but prevent reentry or + * removal of the device. + */ + busy = true; + dev_hold(dev); + rtnl_unlock(); + + if (rc == 0) { + /* Driver will handle this itself */ + schedule_timeout_interruptible( + id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT); + } else { + /* Driver expects to be called at twice the frequency in rc */ + int n = rc * 2, i, interval = HZ / n; + + /* Count down seconds */ + do { + /* Count down iterations per second */ + i = n; + do { + rtnl_lock(); + rc = dev->ethtool_ops->set_phys_id(dev, + (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); + rtnl_unlock(); + if (rc) + break; + schedule_timeout_interruptible(interval); + } while (!signal_pending(current) && --i != 0); + } while (!signal_pending(current) && + (id.data == 0 || --id.data != 0)); + } + + rtnl_lock(); + dev_put(dev); + busy = false; + + (void)dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); + return rc; } static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) @@ -1953,6 +2037,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SGRO: rc = ethtool_set_one_feature(dev, useraddr, ethcmd); break; + case ETHTOOL_GCHANNELS: + rc = ethtool_get_channels(dev, useraddr); + break; + case ETHTOOL_SCHANNELS: + rc = ethtool_set_channels(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 8248ebb..3911586 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -590,7 +590,8 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, int idx = 0; struct fib_rule *rule; - list_for_each_entry(rule, &ops->rules_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; diff --git a/net/core/filter.c b/net/core/filter.c index 232b187..0eb8c44 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -39,65 +39,6 @@ #include <linux/filter.h> #include <linux/reciprocal_div.h> -enum { - BPF_S_RET_K = 1, - BPF_S_RET_A, - BPF_S_ALU_ADD_K, - BPF_S_ALU_ADD_X, - BPF_S_ALU_SUB_K, - BPF_S_ALU_SUB_X, - BPF_S_ALU_MUL_K, - BPF_S_ALU_MUL_X, - BPF_S_ALU_DIV_X, - BPF_S_ALU_AND_K, - BPF_S_ALU_AND_X, - BPF_S_ALU_OR_K, - BPF_S_ALU_OR_X, - BPF_S_ALU_LSH_K, - BPF_S_ALU_LSH_X, - BPF_S_ALU_RSH_K, - BPF_S_ALU_RSH_X, - BPF_S_ALU_NEG, - BPF_S_LD_W_ABS, - BPF_S_LD_H_ABS, - BPF_S_LD_B_ABS, - BPF_S_LD_W_LEN, - BPF_S_LD_W_IND, - BPF_S_LD_H_IND, - BPF_S_LD_B_IND, - BPF_S_LD_IMM, - BPF_S_LDX_W_LEN, - BPF_S_LDX_B_MSH, - BPF_S_LDX_IMM, - BPF_S_MISC_TAX, - BPF_S_MISC_TXA, - BPF_S_ALU_DIV_K, - BPF_S_LD_MEM, - BPF_S_LDX_MEM, - BPF_S_ST, - BPF_S_STX, - BPF_S_JMP_JA, - BPF_S_JMP_JEQ_K, - BPF_S_JMP_JEQ_X, - BPF_S_JMP_JGE_K, - BPF_S_JMP_JGE_X, - BPF_S_JMP_JGT_K, - BPF_S_JMP_JGT_X, - BPF_S_JMP_JSET_K, - BPF_S_JMP_JSET_X, - /* Ancillary data */ - BPF_S_ANC_PROTOCOL, - BPF_S_ANC_PKTTYPE, - BPF_S_ANC_IFINDEX, - BPF_S_ANC_NLATTR, - BPF_S_ANC_NLATTR_NEST, - BPF_S_ANC_MARK, - BPF_S_ANC_QUEUE, - BPF_S_ANC_HATYPE, - BPF_S_ANC_RXHASH, - BPF_S_ANC_CPU, -}; - /* No hurry in this branch */ static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size) { @@ -145,7 +86,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns); + unsigned int pkt_len = SK_RUN_FILTER(filter, skb); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } @@ -425,7 +366,7 @@ EXPORT_SYMBOL(sk_run_filter); * As we dont want to clear mem[] array for each packet going through * sk_run_filter(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure - * a malicious user doesnt try to abuse us. + * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(struct sock_filter *filter, int flen) { @@ -638,6 +579,7 @@ void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); + bpf_jit_free(fp); kfree(fp); } EXPORT_SYMBOL(sk_filter_release_rcu); @@ -672,6 +614,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) atomic_set(&fp->refcnt, 1); fp->len = fprog->len; + fp->bpf_func = sk_run_filter; err = sk_chk_filter(fp->insns, fp->len); if (err) { @@ -679,6 +622,8 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return err; } + bpf_jit_compile(fp); + old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); rcu_assign_pointer(sk->sk_filter, fp); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 01a1101..a7b3421 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -129,7 +129,7 @@ static void linkwatch_schedule_work(int urgent) if (!cancel_delayed_work(&linkwatch_work)) return; - /* Otherwise we reschedule it again for immediate exection. */ + /* Otherwise we reschedule it again for immediate execution. */ schedule_delayed_work(&linkwatch_work, 0); } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5ceb257..381813e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -28,6 +28,7 @@ static const char fmt_hex[] = "%#x\n"; static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; +static const char fmt_udec[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; @@ -145,13 +146,10 @@ static ssize_t show_speed(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && - netdev->ethtool_ops && - netdev->ethtool_ops->get_settings) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; - - if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) - ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd)); + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!dev_ethtool_get_settings(netdev, &cmd)) + ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd)); } rtnl_unlock(); return ret; @@ -166,13 +164,11 @@ static ssize_t show_duplex(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && - netdev->ethtool_ops && - netdev->ethtool_ops->get_settings) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; - - if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) - ret = sprintf(buf, "%s\n", cmd.duplex ? "full" : "half"); + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!dev_ethtool_get_settings(netdev, &cmd)) + ret = sprintf(buf, "%s\n", + cmd.duplex ? "full" : "half"); } rtnl_unlock(); return ret; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3f86026..1abb5084 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -216,11 +216,14 @@ static void net_free(struct net *net) kmem_cache_free(net_cachep, net); } -static struct net *net_create(void) +struct net *copy_net_ns(unsigned long flags, struct net *old_net) { struct net *net; int rv; + if (!(flags & CLONE_NEWNET)) + return get_net(old_net); + net = net_alloc(); if (!net) return ERR_PTR(-ENOMEM); @@ -239,13 +242,6 @@ static struct net *net_create(void) return net; } -struct net *copy_net_ns(unsigned long flags, struct net *old_net) -{ - if (!(flags & CLONE_NEWNET)) - return get_net(old_net); - return net_create(); -} - static DEFINE_SPINLOCK(cleanup_list_lock); static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 06be243..46d9c3a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -539,7 +539,7 @@ int __netpoll_rx(struct sk_buff *skb) { int proto, len, ulen; int hits = 0; - struct iphdr *iph; + const struct iphdr *iph; struct udphdr *uh; struct netpoll_info *npinfo = skb->dev->npinfo; struct netpoll *np, *tmp; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index aeeece7..ff79d94 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2514,7 +2514,6 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) { struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int err = 0; - struct iphdr *iph; if (!x) return 0; @@ -2524,7 +2523,6 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) return 0; spin_lock(&x->lock); - iph = ip_hdr(skb); err = x->outer_mode->output(x, skb); if (err) @@ -2624,6 +2622,7 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } else { int frags = pkt_dev->nfrags; int i, len; + int frag_len; if (frags > MAX_SKB_FRAGS) @@ -2635,6 +2634,8 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } i = 0; + frag_len = (datalen/frags) < PAGE_SIZE ? + (datalen/frags) : PAGE_SIZE; while (datalen > 0) { if (unlikely(!pkt_dev->page)) { int node = numa_node_id(); @@ -2648,38 +2649,18 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, skb_shinfo(skb)->frags[i].page = pkt_dev->page; get_page(pkt_dev->page); skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + /*last fragment, fill rest of data*/ + if (i == (frags - 1)) + skb_shinfo(skb)->frags[i].size = + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + else + skb_shinfo(skb)->frags[i].size = frag_len; datalen -= skb_shinfo(skb)->frags[i].size; skb->len += skb_shinfo(skb)->frags[i].size; skb->data_len += skb_shinfo(skb)->frags[i].size; i++; skb_shinfo(skb)->nr_frags = i; } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; - - skb_shinfo(skb)->frags[i - 1].size -= rem; - - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } } /* Stamp the time, and sequence number, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 49f7ea5..29633125 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -196,7 +196,7 @@ EXPORT_SYMBOL_GPL(__rtnl_register); * as failure of this function is very unlikely, it can only happen due * to lack of memory when allocating the chain to store all message * handlers for a protocol. Meant for use in init functions where lack - * of memory implies no sense in continueing. + * of memory implies no sense in continuing. */ void rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit) @@ -1007,10 +1007,11 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[0]; s_idx = cb->args[1]; + rcu_read_lock(); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { if (idx < s_idx) goto cont; if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, @@ -1023,6 +1024,7 @@ cont: } } out: + rcu_read_unlock(); cb->args[1] = idx; cb->args[0] = h; @@ -1440,7 +1442,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, errout: if (err < 0 && modified && net_ratelimit()) printk(KERN_WARNING "A link change request failed with " - "some changes comitted already. Interface %s may " + "some changes committed already. Interface %s may " "have been left with an inconsistent configuration, " "please check.\n", dev->name); @@ -1879,7 +1881,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) int min_len; int family; int type; - int err; type = nlh->nlmsg_type; if (type > RTM_MAX) @@ -1906,11 +1907,8 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (dumpit == NULL) return -EOPNOTSUPP; - __rtnl_unlock(); rtnl = net->rtnl; - err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); - rtnl_lock(); - return err; + return netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); } memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *))); @@ -1980,7 +1978,7 @@ static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, - rtnetlink_rcv, &rtnl_mutex, THIS_MODULE); + rtnetlink_rcv, NULL, THIS_MODULE); if (!sk) return -ENOMEM; net->rtnl = sk; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 801dd08..7ebeed0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2267,7 +2267,7 @@ EXPORT_SYMBOL(skb_prepare_seq_read); * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * - * Note 1: The size of each block of data returned can be arbitary, + * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy seqeuental * reads of potentially non linear data. * diff --git a/net/core/sock.c b/net/core/sock.c index 7dfed79..6e81978 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -215,7 +215,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; -/* Maximal space eaten by iovec or ancilliary data plus some space */ +/* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); @@ -1175,7 +1175,7 @@ static void __sk_free(struct sock *sk) void sk_free(struct sock *sk) { /* - * We substract one from sk_wmem_alloc and can know if + * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ @@ -1185,10 +1185,10 @@ void sk_free(struct sock *sk) EXPORT_SYMBOL(sk_free); /* - * Last sock_put should drop referrence to sk->sk_net. It has already - * been dropped in sk_change_net. Taking referrence to stopping namespace + * Last sock_put should drop reference to sk->sk_net. It has already + * been dropped in sk_change_net. Taking reference to stopping namespace * is not an option. - * Take referrence to a socket to remove it from hash _alive_ and after that + * Take reference to a socket to remove it from hash _alive_ and after that * destroy it in the context of init_net. */ void sk_release_kernel(struct sock *sk) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 385b609..a829e3f 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -122,6 +122,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_BPF_JIT + { + .procname = "bpf_jit_enable", + .data = &bpf_jit_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif { .procname = "netdev_tstamp_prequeue", .data = &netdev_tstamp_prequeue, |